Merge tag 'for-5.16/block-2021-11-09' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Set of fixes for the batched tag allocation (Ming, me)

 - add_disk() error handling fix (Luis)

 - Nested queue quiesce fixes (Ming)

 - Shared tags init error handling fix (Ye)

 - Misc cleanups (Jean, Ming, me)

* tag 'for-5.16/block-2021-11-09' of git://git.kernel.dk/linux-block:
  nvme: wait until quiesce is done
  scsi: make sure that request queue queiesce and unquiesce balanced
  scsi: avoid to quiesce sdev->request_queue two times
  blk-mq: add one API for waiting until quiesce is done
  blk-mq: don't free tags if the tag_set is used by other device in queue initialztion
  block: fix device_add_disk() kobject_create_and_add() error handling
  block: ensure cached plug request matches the current queue
  block: move queue enter logic into blk_mq_submit_bio()
  block: make bio_queue_enter() fast-path available inline
  block: split request allocation components into helpers
  block: have plug stored requests hold references to the queue
  blk-mq: update hctx->nr_active in blk_mq_end_request_batch()
  blk-mq: add RQF_ELV debug entry
  blk-mq: only try to run plug merge if request has same queue with incoming bio
  block: move RQF_ELV setting into allocators
  dm: don't stop request queue after the dm device is suspended
  block: replace always false argument with 'false'
  block: assign correct tag before doing prefetch of request
  blk-mq: fix redundant check of !e expression

3 files changed, 44 insertions, 32 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8d3157241262..662742a310cb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1927,16 +1927,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 
 	dm_table_event_callback(t, event_callback, md);
 
-	/*
-	 * The queue hasn't been stopped yet, if the old table type wasn't
-	 * for request-based during suspension.  So stop it to prevent
-	 * I/O mapping before resume.
-	 * This must be done before setting the queue restrictions,
-	 * because request-based dm may be run just after the setting.
-	 */
-	if (request_based)
-		dm_stop_queue(q);
-
 	if (request_based) {
 		/*
 		 * Leverage the fact that request-based DM targets are
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 838b5e2058be..4b5de8f5435a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4518,6 +4518,8 @@ static void nvme_stop_ns_queue(struct nvme_ns *ns)
 {
 	if (!test_and_set_bit(NVME_NS_STOPPED, &ns->flags))
 		blk_mq_quiesce_queue(ns->queue);
+	else
+		blk_mq_wait_quiesce_done(ns->queue);
 }
 
 /*
@@ -4637,6 +4639,8 @@ void nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (!test_and_set_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
 		blk_mq_quiesce_queue(ctrl->admin_q);
+	else
+		blk_mq_wait_quiesce_done(ctrl->admin_q);
 }
 EXPORT_SYMBOL_GPL(nvme_stop_admin_queue);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1344553afe70..b731c2983515 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2665,6 +2665,40 @@ scsi_target_resume(struct scsi_target *starget)
 }
 EXPORT_SYMBOL(scsi_target_resume);
 
+static int __scsi_internal_device_block_nowait(struct scsi_device *sdev)
+{
+	if (scsi_device_set_state(sdev, SDEV_BLOCK))
+		return scsi_device_set_state(sdev, SDEV_CREATED_BLOCK);
+
+	return 0;
+}
+
+void scsi_start_queue(struct scsi_device *sdev)
+{
+	if (cmpxchg(&sdev->queue_stopped, 1, 0))
+		blk_mq_unquiesce_queue(sdev->request_queue);
+}
+
+static void scsi_stop_queue(struct scsi_device *sdev, bool nowait)
+{
+	/*
+	 * The atomic variable of ->queue_stopped covers that
+	 * blk_mq_quiesce_queue* is balanced with blk_mq_unquiesce_queue.
+	 *
+	 * However, we still need to wait until quiesce is done
+	 * in case that queue has been stopped.
+	 */
+	if (!cmpxchg(&sdev->queue_stopped, 0, 1)) {
+		if (nowait)
+			blk_mq_quiesce_queue_nowait(sdev->request_queue);
+		else
+			blk_mq_quiesce_queue(sdev->request_queue);
+	} else {
+		if (!nowait)
+			blk_mq_wait_quiesce_done(sdev->request_queue);
+	}
+}
+
 /**
  * scsi_internal_device_block_nowait - try to transition to the SDEV_BLOCK state
  * @sdev: device to block
@@ -2681,24 +2715,16 @@ EXPORT_SYMBOL(scsi_target_resume);
  */
 int scsi_internal_device_block_nowait(struct scsi_device *sdev)
 {
-	struct request_queue *q = sdev->request_queue;
-	int err = 0;
-
-	err = scsi_device_set_state(sdev, SDEV_BLOCK);
-	if (err) {
-		err = scsi_device_set_state(sdev, SDEV_CREATED_BLOCK);
-
-		if (err)
-			return err;
-	}
+	int ret = __scsi_internal_device_block_nowait(sdev);
 
 	/*
 	 * The device has transitioned to SDEV_BLOCK.  Stop the
 	 * block layer from calling the midlayer with this device's
 	 * request queue.
 	 */
-	blk_mq_quiesce_queue_nowait(q);
-	return 0;
+	if (!ret)
+		scsi_stop_queue(sdev, true);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
 
@@ -2719,25 +2745,17 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
  */
 static int scsi_internal_device_block(struct scsi_device *sdev)
 {
-	struct request_queue *q = sdev->request_queue;
 	int err;
 
 	mutex_lock(&sdev->state_mutex);
-	err = scsi_internal_device_block_nowait(sdev);
+	err = __scsi_internal_device_block_nowait(sdev);
 	if (err == 0)
-		blk_mq_quiesce_queue(q);
+		scsi_stop_queue(sdev, false);
 	mutex_unlock(&sdev->state_mutex);
 
 	return err;
 }
 
-void scsi_start_queue(struct scsi_device *sdev)
-{
-	struct request_queue *q = sdev->request_queue;
-
-	blk_mq_unquiesce_queue(q);
-}
-
 /**
  * scsi_internal_device_unblock_nowait - resume a device after a block request
  * @sdev:	device to resume