blk-mq: introduce BLK_STS_DEV_RESOURCE

This status is returned from driver to block layer if device related
resource is unavailable, but driver can guarantee that IO dispatch
will be triggered in future when the resource is available.

Convert some drivers to return BLK_STS_DEV_RESOURCE.  Also, if driver
returns BLK_STS_RESOURCE and SCHED_RESTART is set, rerun queue after
a delay (BLK_MQ_DELAY_QUEUE) to avoid IO stalls.  BLK_MQ_DELAY_QUEUE is
3 ms because both scsi-mq and nvmefc are using that magic value.

If a driver can make sure there is in-flight IO, it is safe to return
BLK_STS_DEV_RESOURCE because:

1) If all in-flight IOs complete before examining SCHED_RESTART in
blk_mq_dispatch_rq_list(), SCHED_RESTART must be cleared, so queue
is run immediately in this case by blk_mq_dispatch_rq_list();

2) if there is any in-flight IO after/when examining SCHED_RESTART
in blk_mq_dispatch_rq_list():
- if SCHED_RESTART isn't set, queue is run immediately as handled in 1)
- otherwise, this request will be dispatched after any in-flight IO is
  completed via blk_mq_sched_restart()

3) if SCHED_RESTART is set concurently in context because of
BLK_STS_RESOURCE, blk_mq_delay_run_hw_queue() will cover the above two
cases and make sure IO hang can be avoided.

One invariant is that queue will be rerun if SCHED_RESTART is set.

Suggested-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

6 files changed, 10 insertions, 19 deletions

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6655893a3a7a..287a09611c0f 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -1230,7 +1230,7 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 				return BLK_STS_OK;
 			} else
 				/* requeue request */
-				return BLK_STS_RESOURCE;
+				return BLK_STS_DEV_RESOURCE;
 		}
 	}
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 68846897d213..79908e6ddbf2 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -276,7 +276,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		/* Out of mem doesn't actually happen, since we fall back
 		 * to direct descriptors */
 		if (err == -ENOMEM || err == -ENOSPC)
-			return BLK_STS_RESOURCE;
+			return BLK_STS_DEV_RESOURCE;
 		return BLK_STS_IOERR;
 	}
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 891265acb10e..e126e4cac2ca 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -911,7 +911,7 @@ out_err:
 out_busy:
 	blk_mq_stop_hw_queue(hctx);
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
-	return BLK_STS_RESOURCE;
+	return BLK_STS_DEV_RESOURCE;
 }
 
 static void blkif_complete_rq(struct request *rq)
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index b7d175e94a02..348a0cb6963a 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -404,7 +404,7 @@ static blk_status_t dm_dispatch_clone_request(struct request *clone, struct requ
 
 	clone->start_time = jiffies;
 	r = blk_insert_cloned_request(clone->q, clone);
-	if (r != BLK_STS_OK && r != BLK_STS_RESOURCE)
+	if (r != BLK_STS_OK && r != BLK_STS_RESOURCE && r != BLK_STS_DEV_RESOURCE)
 		/* must complete clone in terms of original request */
 		dm_complete_request(rq, r);
 	return r;
@@ -496,7 +496,7 @@ check_again:
 		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
 				     blk_rq_pos(rq));
 		ret = dm_dispatch_clone_request(clone, rq);
-		if (ret == BLK_STS_RESOURCE) {
+		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
 			blk_rq_unprep_clone(clone);
 			tio->ti->type->release_clone_rq(clone);
 			tio->clone = NULL;
@@ -769,7 +769,6 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 		/* Undo dm_start_request() before requeuing */
 		rq_end_stats(md, rq);
 		rq_completed(md, rq_data_dir(rq), false);
-		blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
 		return BLK_STS_RESOURCE;
 	}
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 99bf51c7e513..b856d7c919d2 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -35,8 +35,6 @@ enum nvme_fc_queue_flags {
 	NVME_FC_Q_LIVE,
 };
 
-#define NVMEFC_QUEUE_DELAY	3		/* ms units */
-
 #define NVME_FC_DEFAULT_DEV_LOSS_TMO	60	/* seconds */
 
 struct nvme_fc_queue {
@@ -2231,7 +2229,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	 * the target device is present
 	 */
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
-		goto busy;
+		return BLK_STS_RESOURCE;
 
 	if (!nvme_fc_ctrl_get(ctrl))
 		return BLK_STS_IOERR;
@@ -2311,16 +2309,10 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 				ret != -EBUSY)
 			return BLK_STS_IOERR;
 
-		goto busy;
+		return BLK_STS_RESOURCE;
 	}
 
 	return BLK_STS_OK;
-
-busy:
-	if (!(op->flags & FCOP_FLAGS_AEN) && queue->hctx)
-		blk_mq_delay_run_hw_queue(queue->hctx, NVMEFC_QUEUE_DELAY);
-
-	return BLK_STS_RESOURCE;
 }
 
 static inline blk_status_t nvme_fc_is_ready(struct nvme_fc_queue *queue,
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index d9ca1dfab154..55be2550c555 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2030,9 +2030,9 @@ out_put_budget:
 	case BLK_STS_OK:
 		break;
 	case BLK_STS_RESOURCE:
-		if (atomic_read(&sdev->device_busy) == 0 &&
-		    !scsi_device_blocked(sdev))
-			blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
+		if (atomic_read(&sdev->device_busy) ||
+		    scsi_device_blocked(sdev))
+			ret = BLK_STS_DEV_RESOURCE;
 		break;
 	default:
 		/*