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

block/blk-core.c

@@ -386,30 +386,6 @@ void blk_cleanup_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
 
-static bool blk_try_enter_queue(struct request_queue *q, bool pm)
-{
-	rcu_read_lock();
-	if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))
-		goto fail;
-
-	/*
-	 * The code that increments the pm_only counter must ensure that the
-	 * counter is globally visible before the queue is unfrozen.
-	 */
-	if (blk_queue_pm_only(q) &&
-	    (!pm || queue_rpm_status(q) == RPM_SUSPENDED))
-		goto fail_put;
-
-	rcu_read_unlock();
-	return true;
-
-fail_put:
-	blk_queue_exit(q);
-fail:
-	rcu_read_unlock();
-	return false;
-}
-
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
@@ -442,10 +418,8 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 	return 0;
 }
 
-static inline int bio_queue_enter(struct bio *bio)
+int __bio_queue_enter(struct request_queue *q, struct bio *bio)
 {
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-
 	while (!blk_try_enter_queue(q, false)) {
 		struct gendisk *disk = bio->bi_bdev->bd_disk;
 
@@ -742,7 +716,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 	return BLK_STS_OK;
 }
 
-static noinline_for_stack bool submit_bio_checks(struct bio *bio)
+noinline_for_stack bool submit_bio_checks(struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -860,24 +834,25 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	return false;
 }
 
-static void __submit_bio(struct bio *bio)
+static void __submit_bio_fops(struct gendisk *disk, struct bio *bio)
 {
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-
 	if (unlikely(bio_queue_enter(bio) != 0))
 		return;
-
-	if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio))
-		goto queue_exit;
-	if (!disk->fops->submit_bio) {
-		blk_mq_submit_bio(bio);
-		return;
-	}
+	if (submit_bio_checks(bio) && blk_crypto_bio_prep(&bio))
 		disk->fops->submit_bio(bio);
-queue_exit:
 	blk_queue_exit(disk->queue);
 }
 
+static void __submit_bio(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+
+	if (!disk->fops->submit_bio)
+		blk_mq_submit_bio(bio);
+	else
+		__submit_bio_fops(disk, bio);
+}
+
 /*
  * The loop in this function may be a bit non-obvious, and so deserves some
  * explanation:
@@ -1615,7 +1590,13 @@ void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 		flush_plug_callbacks(plug, from_schedule);
 	if (!rq_list_empty(plug->mq_list))
 		blk_mq_flush_plug_list(plug, from_schedule);
-	if (unlikely(!from_schedule && plug->cached_rq))
+	/*
+	 * Unconditionally flush out cached requests, even if the unplug
+	 * event came from schedule. Since we know hold references to the
+	 * queue for cached requests, we don't want a blocked task holding
+	 * up a queue freeze/quiesce event.
+	 */
+	if (unlikely(!rq_list_empty(plug->cached_rq)))
 		blk_mq_free_plug_rqs(plug);
 }
 

block/blk-merge.c

@@ -1101,9 +1101,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		 * the same queue, there should be only one such rq in a queue
 		 */
 		*same_queue_rq = true;
-	}
-	if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK)
+
+		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+				BIO_MERGE_OK)
 			return true;
+	}
 	return false;
 }
 

block/blk-mq-debugfs.c

@@ -308,6 +308,7 @@ static const char *const rqf_name[] = {
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(MQ_POLL_SLEPT),
+	RQF_NAME(ELV),
 };
 #undef RQF_NAME
 

block/blk-mq-sched.c

@@ -370,15 +370,20 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 	bool ret = false;
 	enum hctx_type type;
 
-	if (e && e->type->ops.bio_merge)
-		return e->type->ops.bio_merge(q, bio, nr_segs);
+	if (bio_queue_enter(bio))
+		return false;
+
+	if (e && e->type->ops.bio_merge) {
+		ret = e->type->ops.bio_merge(q, bio, nr_segs);
+		goto out_put;
+	}
 
 	ctx = blk_mq_get_ctx(q);
 	hctx = blk_mq_map_queue(q, bio->bi_opf, ctx);
 	type = hctx->type;
 	if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) ||
 	    list_empty_careful(&ctx->rq_lists[type]))
-		return false;
+		goto out_put;
 
 	/* default per sw-queue merge */
 	spin_lock(&ctx->lock);
@@ -391,6 +396,8 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 		ret = true;
 
 	spin_unlock(&ctx->lock);
+out_put:
+	blk_queue_exit(q);
 	return ret;
 }
 
@@ -497,7 +504,7 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 		 * busy in case of 'none' scheduler, and this way may save
 		 * us one extra enqueue & dequeue to sw queue.
 		 */
-		if (!hctx->dispatch_busy && !e && !run_queue_async) {
+		if (!hctx->dispatch_busy && !run_queue_async) {
 			blk_mq_try_issue_list_directly(hctx, list);
 			if (list_empty(list))
 				goto out;

block/blk-mq.c

@@ -251,22 +251,18 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q)
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
 
 /**
- * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
+ * blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done
  * @q: request queue.
  *
- * Note: this function does not prevent that the struct request end_io()
- * callback function is invoked. Once this function is returned, we make
- * sure no dispatch can happen until the queue is unquiesced via
- * blk_mq_unquiesce_queue().
+ * Note: it is driver's responsibility for making sure that quiesce has
+ * been started.
  */
-void blk_mq_quiesce_queue(struct request_queue *q)
+void blk_mq_wait_quiesce_done(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 	bool rcu = false;
 
-	blk_mq_quiesce_queue_nowait(q);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->flags & BLK_MQ_F_BLOCKING)
 			synchronize_srcu(hctx->srcu);
@@ -276,6 +272,22 @@ void blk_mq_quiesce_queue(struct request_queue *q)
 	if (rcu)
 		synchronize_rcu();
 }
+EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done);
+
+/**
+ * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
+ * @q: request queue.
+ *
+ * Note: this function does not prevent that the struct request end_io()
+ * callback function is invoked. Once this function is returned, we make
+ * sure no dispatch can happen until the queue is unquiesced via
+ * blk_mq_unquiesce_queue().
+ */
+void blk_mq_quiesce_queue(struct request_queue *q)
+{
+	blk_mq_quiesce_queue_nowait(q);
+	blk_mq_wait_quiesce_done(q);
+}
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
 
 /*
@@ -405,12 +417,15 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 	for (i = 0; tag_mask; i++) {
 		if (!(tag_mask & (1UL << i)))
 			continue;
-		prefetch(tags->static_rqs[tag]);
 		tag = tag_offset + i;
+		prefetch(tags->static_rqs[tag]);
 		tag_mask &= ~(1UL << i);
 		rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
 		rq_list_add(data->cached_rq, rq);
+		nr++;
 	}
+	/* caller already holds a reference, add for remainder */
+	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
 	data->nr_tags -= nr;
 
 	return rq_list_pop(data->cached_rq);
@@ -419,7 +434,6 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 {
 	struct request_queue *q = data->q;
-	struct elevator_queue *e = q->elevator;
 	u64 alloc_time_ns = 0;
 	struct request *rq;
 	unsigned int tag;
@@ -431,7 +445,11 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
-	if (e) {
+	if (q->elevator) {
+		struct elevator_queue *e = q->elevator;
+
+		data->rq_flags |= RQF_ELV;
+
 		/*
 		 * Flush/passthrough requests are special and go directly to the
 		 * dispatch list. Don't include reserved tags in the
@@ -447,7 +465,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 retry:
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!e)
+	if (!(data->rq_flags & RQF_ELV))
 		blk_mq_tag_busy(data->hctx);
 
 	/*
@@ -490,7 +508,6 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		.q		= q,
 		.flags		= flags,
 		.cmd_flags	= op,
-		.rq_flags	= q->elevator ? RQF_ELV : 0,
 		.nr_tags	= 1,
 	};
 	struct request *rq;
@@ -520,7 +537,6 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		.q		= q,
 		.flags		= flags,
 		.cmd_flags	= op,
-		.rq_flags	= q->elevator ? RQF_ELV : 0,
 		.nr_tags	= 1,
 	};
 	u64 alloc_time_ns = 0;
@@ -561,6 +577,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 
 	if (!q->elevator)
 		blk_mq_tag_busy(data.hctx);
+	else
+		data.rq_flags |= RQF_ELV;
 
 	ret = -EWOULDBLOCK;
 	tag = blk_mq_get_tag(&data);
@@ -627,10 +645,8 @@ void blk_mq_free_plug_rqs(struct blk_plug *plug)
 {
 	struct request *rq;
 
-	while ((rq = rq_list_pop(&plug->cached_rq)) != NULL) {
-		percpu_ref_get(&rq->q->q_usage_counter);
+	while ((rq = rq_list_pop(&plug->cached_rq)) != NULL)
 		blk_mq_free_request(rq);
-	}
 }
 
 static void req_bio_endio(struct request *rq, struct bio *bio,
@@ -815,6 +831,13 @@ static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
 {
 	struct request_queue *q = hctx->queue;
 
+	/*
+	 * All requests should have been marked as RQF_MQ_INFLIGHT, so
+	 * update hctx->nr_active in batch
+	 */
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_sub_active_requests(hctx, nr_tags);
+
 	blk_mq_put_tags(hctx->tags, tag_array, nr_tags);
 	percpu_ref_put_many(&q->q_usage_counter, nr_tags);
 }
@@ -2232,7 +2255,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	plug->rq_count = 0;
 
 	if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
-		blk_mq_plug_issue_direct(plug, from_schedule);
+		blk_mq_plug_issue_direct(plug, false);
 		if (rq_list_empty(plug->mq_list))
 			return;
 	}
@@ -2472,6 +2495,83 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
 	return BLK_MAX_REQUEST_COUNT;
 }
 
+static bool blk_attempt_bio_merge(struct request_queue *q, struct bio *bio,
+				  unsigned int nr_segs, bool *same_queue_rq)
+{
+	if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
+		if (blk_attempt_plug_merge(q, bio, nr_segs, same_queue_rq))
+			return true;
+		if (blk_mq_sched_bio_merge(q, bio, nr_segs))
+			return true;
+	}
+	return false;
+}
+
+static struct request *blk_mq_get_new_requests(struct request_queue *q,
+					       struct blk_plug *plug,
+					       struct bio *bio,
+					       unsigned int nsegs,
+					       bool *same_queue_rq)
+{
+	struct blk_mq_alloc_data data = {
+		.q		= q,
+		.nr_tags	= 1,
+		.cmd_flags	= bio->bi_opf,
+	};
+	struct request *rq;
+
+	if (unlikely(bio_queue_enter(bio)))
+		return NULL;
+	if (unlikely(!submit_bio_checks(bio)))
+		goto put_exit;
+	if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq))
+		goto put_exit;
+
+	rq_qos_throttle(q, bio);
+
+	if (plug) {
+		data.nr_tags = plug->nr_ios;
+		plug->nr_ios = 1;
+		data.cached_rq = &plug->cached_rq;
+	}
+
+	rq = __blk_mq_alloc_requests(&data);
+	if (rq)
+		return rq;
+
+	rq_qos_cleanup(q, bio);
+	if (bio->bi_opf & REQ_NOWAIT)
+		bio_wouldblock_error(bio);
+put_exit:
+	blk_queue_exit(q);
+	return NULL;
+}
+
+static inline struct request *blk_mq_get_request(struct request_queue *q,
+						 struct blk_plug *plug,
+						 struct bio *bio,
+						 unsigned int nsegs,
+						 bool *same_queue_rq)
+{
+	if (plug) {
+		struct request *rq;
+
+		rq = rq_list_peek(&plug->cached_rq);
+		if (rq && rq->q == q) {
+			if (unlikely(!submit_bio_checks(bio)))
+				return NULL;
+			if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq))
+				return NULL;
+			plug->cached_rq = rq_list_next(rq);
+			INIT_LIST_HEAD(&rq->queuelist);
+			rq_qos_throttle(q, bio);
+			return rq;
+		}
+	}
+
+	return blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq);
+}
+
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2495,47 +2595,20 @@ void blk_mq_submit_bio(struct bio *bio)
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
+	if (unlikely(!blk_crypto_bio_prep(&bio)))
+		return;
+
 	blk_queue_bounce(q, &bio);
 	if (blk_may_split(q, bio))
 		__blk_queue_split(q, &bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
-		goto queue_exit;
-
-	if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
-		if (blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
-			goto queue_exit;
-		if (blk_mq_sched_bio_merge(q, bio, nr_segs))
-			goto queue_exit;
-	}
-
-	rq_qos_throttle(q, bio);
+		return;
 
 	plug = blk_mq_plug(q, bio);
-	if (plug && plug->cached_rq) {
-		rq = rq_list_pop(&plug->cached_rq);
-		INIT_LIST_HEAD(&rq->queuelist);
-	} else {
-		struct blk_mq_alloc_data data = {
-			.q		= q,
-			.nr_tags	= 1,
-			.cmd_flags	= bio->bi_opf,
-			.rq_flags	= q->elevator ? RQF_ELV : 0,
-		};
-
-		if (plug) {
-			data.nr_tags = plug->nr_ios;
-			plug->nr_ios = 1;
-			data.cached_rq = &plug->cached_rq;
-		}
-		rq = __blk_mq_alloc_requests(&data);
-		if (unlikely(!rq)) {
-			rq_qos_cleanup(q, bio);
-			if (bio->bi_opf & REQ_NOWAIT)
-				bio_wouldblock_error(bio);
-			goto queue_exit;
-		}
-	}
+	rq = blk_mq_get_request(q, plug, bio, nr_segs, &same_queue_rq);
+	if (unlikely(!rq))
+		return;
 
 	trace_block_getrq(bio);
 
@@ -2616,10 +2689,6 @@ void blk_mq_submit_bio(struct bio *bio)
 		/* Default case. */
 		blk_mq_sched_insert_request(rq, false, true, true);
 	}
-
-	return;
-queue_exit:
-	blk_queue_exit(q);
 }
 
 static size_t order_to_size(unsigned int order)
@@ -3605,7 +3674,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx = hctxs[j];
 
 		if (hctx) {
-			__blk_mq_free_map_and_rqs(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
 			hctxs[j] = NULL;
 		}
@@ -4113,8 +4181,13 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 		if (q->nr_hw_queues != set->nr_hw_queues) {
+			int i = prev_nr_hw_queues;
+
 			pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n",
 					nr_hw_queues, prev_nr_hw_queues);
+			for (; i < set->nr_hw_queues; i++)
+				__blk_mq_free_map_and_rqs(set, i);
+
 			set->nr_hw_queues = prev_nr_hw_queues;
 			blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
 			goto fallback;

block/blk-mq.h

@@ -225,12 +225,18 @@ static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
 		atomic_inc(&hctx->nr_active);
 }
 
-static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
+		int val)
 {
 	if (blk_mq_is_shared_tags(hctx->flags))
-		atomic_dec(&hctx->queue->nr_active_requests_shared_tags);
+		atomic_sub(val, &hctx->queue->nr_active_requests_shared_tags);
 	else
-		atomic_dec(&hctx->nr_active);
+		atomic_sub(val, &hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	__blk_mq_sub_active_requests(hctx, 1);
 }
 
 static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)

block/blk.h

@@ -55,6 +55,41 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 void blk_freeze_queue(struct request_queue *q);
 void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic);
 void blk_queue_start_drain(struct request_queue *q);
+int __bio_queue_enter(struct request_queue *q, struct bio *bio);
+bool submit_bio_checks(struct bio *bio);
+
+static inline bool blk_try_enter_queue(struct request_queue *q, bool pm)
+{
+	rcu_read_lock();
+	if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))
+		goto fail;
+
+	/*
+	 * The code that increments the pm_only counter must ensure that the
+	 * counter is globally visible before the queue is unfrozen.
+	 */
+	if (blk_queue_pm_only(q) &&
+	    (!pm || queue_rpm_status(q) == RPM_SUSPENDED))
+		goto fail_put;
+
+	rcu_read_unlock();
+	return true;
+
+fail_put:
+	blk_queue_exit(q);
+fail:
+	rcu_read_unlock();
+	return false;
+}
+
+static inline int bio_queue_enter(struct bio *bio)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+
+	if (blk_try_enter_queue(q, false))
+		return 0;
+	return __bio_queue_enter(q, bio);
+}
 
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,

block/genhd.c

@@ -469,11 +469,15 @@ int device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk->part0->bd_holder_dir =
 		kobject_create_and_add("holders", &ddev->kobj);
-	if (!disk->part0->bd_holder_dir)
+	if (!disk->part0->bd_holder_dir) {
+		ret = -ENOMEM;
 		goto out_del_integrity;
+	}
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
-	if (!disk->slave_dir)
+	if (!disk->slave_dir) {
+		ret = -ENOMEM;
 		goto out_put_holder_dir;
+	}
 
 	ret = bd_register_pending_holders(disk);
 	if (ret < 0)

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

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);
 

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

include/linux/blk-mq.h

@@ -798,6 +798,7 @@ void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_quiesce_queue(struct request_queue *q);
+void blk_mq_wait_quiesce_done(struct request_queue *q);
 void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);

include/scsi/scsi_device.h

@@ -207,6 +207,7 @@ struct scsi_device {
 					 * creation time */
 	unsigned ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */
 
+	unsigned int queue_stopped;	/* request queue is quiesced */
 	bool offline_already;		/* Device offline message logged */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */