blk-mq: insert passthrough request into hctx->dispatch directly

For some reason, device may be in one situation which can't handle
FS request, so STS_RESOURCE is always returned and the FS request
will be added to hctx->dispatch. However passthrough request may
be required at that time for fixing the problem. If passthrough
request is added to scheduler queue, there isn't any chance for
blk-mq to dispatch it given we prioritize requests in hctx->dispatch.
Then the FS IO request may never be completed, and IO hang is caused.

So passthrough request has to be added to hctx->dispatch directly
for fixing the IO hang.

Fix this issue by inserting passthrough request into hctx->dispatch
directly together withing adding FS request to the tail of
hctx->dispatch in blk_mq_dispatch_rq_list(). Actually we add FS request
to tail of hctx->dispatch at default, see blk_mq_request_bypass_insert().

Then it becomes consistent with original legacy IO request
path, in which passthrough request is always added to q->queue_head.

Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 11 insertions, 7 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a12b1763508d..5e1e4151cb51 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -735,7 +735,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * merge.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false);
+			blk_mq_request_bypass_insert(rq, false, false);
 		else
 			blk_mq_sched_insert_request(rq, true, false, false);
 	}
@@ -1286,7 +1286,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			q->mq_ops->commit_rqs(hctx);
 
 		spin_lock(&hctx->lock);
-		list_splice_init(list, &hctx->dispatch);
+		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -1677,12 +1677,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	if (at_head)
+		list_add(&rq->queuelist, &hctx->dispatch);
+	else
+		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
 	if (run_queue)
@@ -1849,7 +1853,7 @@ insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, run_queue);
+	blk_mq_request_bypass_insert(rq, false, run_queue);
 	return BLK_STS_OK;
 }
 
@@ -1876,7 +1880,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, true);
+		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
 		blk_mq_end_request(rq, ret);
 
@@ -1910,7 +1914,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		if (ret != BLK_STS_OK) {
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
-				blk_mq_request_bypass_insert(rq,
+				blk_mq_request_bypass_insert(rq, false,
 							list_empty(list));
 				break;
 			}