diff options
authorBart Van Assche <>2016-10-28 17:20:32 -0700
committerJens Axboe <>2016-11-02 11:17:24 -0600
commited87d81f2676a54c2bb2a0391671180d1b94bc77 (patch)
parentc73b8adcc83cc5328c10e947dbcf5c7d861d155b (diff)
blk-mq: Avoid that requeueing starts stopped queues
Since blk_mq_requeue_work() starts stopped queues and since execution of this function can be scheduled after a queue has been stopped it is not possible to stop queues without using an additional state variable to track whether or not the queue has been stopped. Hence modify blk_mq_requeue_work() such that it does not start stopped queues. My conclusion after a review of the blk_mq_stop_hw_queues() and blk_mq_{delay_,}kick_requeue_list() callers is as follows: * In the dm driver starting and stopping queues should only happen if __dm_suspend() or __dm_resume() is called and not if the requeue list is processed. * In the SCSI core queue stopping and starting should only be performed by the scsi_internal_device_block() and scsi_internal_device_unblock() functions but not by any other function. Although the blk_mq_stop_hw_queue() call in scsi_queue_rq() may help to reduce CPU load if a LLD queue is full, figuring out whether or not a queue should be restarted when requeueing a command would require to introduce additional locking in scsi_mq_requeue_cmd() to avoid a race with scsi_internal_device_block(). Avoid this complexity by removing the blk_mq_stop_hw_queue() call from scsi_queue_rq(). * In the NVMe core only the functions that call blk_mq_start_stopped_hw_queues() explicitly should start stopped queues. * A blk_mq_start_stopped_hwqueues() call must be added in the xen-blkfront driver in its blkif_recover() function. Signed-off-by: Bart Van Assche <> Cc: Konrad Rzeszutek Wilk <> Cc: Roger Pau Monné <> Cc: Mike Snitzer <> Cc: James Bottomley <> Cc: Martin K. Petersen <> Reviewed-by: Sagi Grimberg <> Reviewed-by: Christoph Hellwig <> Signed-off-by: Jens Axboe <>
4 files changed, 3 insertions, 12 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 447c37f39e32..d95034ae64f6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -501,11 +501,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
blk_mq_insert_request(rq, false, false, false);
- /*
- * Use the start variant of queue running here, so that running
- * the requeue work will kick stopped queues.
- */
- blk_mq_start_hw_queues(q);
+ blk_mq_run_hw_queues(q, false);
void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 9908597c5209..71ca36eab558 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2045,6 +2045,7 @@ static int blkif_recover(struct blkfront_info *info)
BUG_ON(req->nr_phys_segments > segs);
+ blk_mq_start_stopped_hw_queues(info->rq, true);
while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index f76cc36b8546..a9e9e781bb77 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -338,12 +338,7 @@ static void dm_old_requeue_request(struct request *rq)
static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
- unsigned long flags;
- spin_lock_irqsave(q->queue_lock, flags);
- if (!blk_queue_stopped(q))
- blk_mq_delay_kick_requeue_list(q, msecs);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ blk_mq_delay_kick_requeue_list(q, msecs);
void dm_mq_kick_requeue_list(struct mapped_device *md)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 8c52622ac257..2b78ff12bf3c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1952,7 +1952,6 @@ out_put_device:
switch (ret) {
- blk_mq_stop_hw_queue(hctx);
if (atomic_read(&sdev->device_busy) == 0 &&
blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);