Merge tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:

 - disk events cleanup (Christoph)

 - gendisk and request queue allocation simplifications (Christoph)

 - bdev_disk_changed cleanups (Christoph)

 - IO priority improvements (Bart)

 - Chained bio completion trace fix (Edward)

 - blk-wbt fixes (Jan)

 - blk-wbt enable/disable fix (Zhang)

 - Scheduler dispatch improvements (Jan, Ming)

 - Shared tagset scheduler improvements (John)

 - BFQ updates (Paolo, Luca, Pietro)

 - BFQ lock inversion fix (Jan)

 - Documentation improvements (Kir)

 - CLONE_IO block cgroup fix (Tejun)

 - Remove of ancient and deprecated block dump feature (zhangyi)

 - Discard merge fix (Ming)

 - Misc fixes or followup fixes (Colin, Damien, Dan, Long, Max, Thomas,
   Yang)

* tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block: (129 commits)
  block: fix discard request merge
  block/mq-deadline: Remove a WARN_ON_ONCE() call
  blk-mq: update hctx->dispatch_busy in case of real scheduler
  blk: Fix lock inversion between ioc lock and bfqd lock
  bfq: Remove merged request already in bfq_requests_merged()
  block: pass a gendisk to bdev_disk_changed
  block: move bdev_disk_changed
  block: add the events* attributes to disk_attrs
  block: move the disk events code to a separate file
  block: fix trace completion for chained bio
  block/partitions/msdos: Fix typo inidicator -> indicator
  block, bfq: reset waker pointer with shared queues
  block, bfq: check waker only for queues with no in-flight I/O
  block, bfq: avoid delayed merge of async queues
  block, bfq: boost throughput by extending queue-merging times
  block, bfq: consider also creation time in delayed stable merge
  block, bfq: fix delayed stable merge check
  block, bfq: let also stably merged queues enjoy weight raising
  blk-wbt: make sure throttle is enabled properly
  blk-wbt: introduce a new disable state to prevent false positive by rwb_enabled()
  ...

5 files changed, 26 insertions, 45 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index bea8c4429ae8..185246a0d855 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -890,13 +890,9 @@ static void bcache_device_free(struct bcache_device *d)
 		if (disk_added)
 			del_gendisk(disk);
 
-		if (disk->queue)
-			blk_cleanup_queue(disk->queue);
-
+		blk_cleanup_disk(disk);
 		ida_simple_remove(&bcache_device_idx,
 				  first_minor_to_idx(disk->first_minor));
-		if (disk_added)
-			put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -946,7 +942,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto err;
 
-	d->disk = alloc_disk(BCACHE_MINORS);
+	d->disk = blk_alloc_disk(NUMA_NO_NODE);
 	if (!d->disk)
 		goto err;
 
@@ -955,14 +951,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	d->disk->major		= bcache_major;
 	d->disk->first_minor	= idx_to_first_minor(idx);
+	d->disk->minors		= BCACHE_MINORS;
 	d->disk->fops		= ops;
 	d->disk->private_data	= d;
 
-	q = blk_alloc_queue(NUMA_NO_NODE);
-	if (!q)
-		return -ENOMEM;
-
-	d->disk->queue			= q;
+	q = d->disk->queue;
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 9c3bc3711b33..0dbd48cbdff9 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -530,7 +530,6 @@ static const struct blk_mq_ops dm_mq_ops = {
 
 int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 {
-	struct request_queue *q;
 	struct dm_target *immutable_tgt;
 	int err;
 
@@ -557,12 +556,10 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 	if (err)
 		goto out_kfree_tag_set;
 
-	q = blk_mq_init_allocated_queue(md->tag_set, md->queue, true);
-	if (IS_ERR(q)) {
-		err = PTR_ERR(q);
+	err = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+	if (err)
 		goto out_tag_set;
-	}
-
+	elevator_init_mq(md->queue);
 	return 0;
 
 out_tag_set:
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 190e714cb565..a57aba553ebb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1801,13 +1801,13 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		md->disk->private_data = NULL;
 		spin_unlock(&_minor_lock);
 		del_gendisk(md->disk);
-		put_disk(md->disk);
 	}
 
-	if (md->queue) {
+	if (md->queue)
 		dm_queue_destroy_keyslot_manager(md->queue);
-		blk_cleanup_queue(md->queue);
-	}
+
+	if (md->disk)
+		blk_cleanup_disk(md->disk);
 
 	cleanup_srcu_struct(&md->io_barrier);
 
@@ -1869,13 +1869,10 @@ static struct mapped_device *alloc_dev(int minor)
 	 * established. If request-based table is loaded: blk-mq will
 	 * override accordingly.
 	 */
-	md->queue = blk_alloc_queue(numa_node_id);
-	if (!md->queue)
-		goto bad;
-
-	md->disk = alloc_disk_node(1, md->numa_node_id);
+	md->disk = blk_alloc_disk(md->numa_node_id);
 	if (!md->disk)
 		goto bad;
+	md->queue = md->disk->queue;
 
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
@@ -1888,6 +1885,7 @@ static struct mapped_device *alloc_dev(int minor)
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
+	md->disk->minors = 1;
 	md->disk->fops = &dm_blk_dops;
 	md->disk->queue = md->queue;
 	md->disk->private_data = md;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 49f897fbb89b..d806be8cc210 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5598,12 +5598,10 @@ static void md_free(struct kobject *ko)
 	if (mddev->sysfs_level)
 		sysfs_put(mddev->sysfs_level);
 
-	if (mddev->gendisk)
+	if (mddev->gendisk) {
 		del_gendisk(mddev->gendisk);
-	if (mddev->queue)
-		blk_cleanup_queue(mddev->queue);
-	if (mddev->gendisk)
-		put_disk(mddev->gendisk);
+		blk_cleanup_disk(mddev->gendisk);
+	}
 	percpu_ref_exit(&mddev->writes_pending);
 
 	bioset_exit(&mddev->bio_set);
@@ -5711,20 +5709,13 @@ static int md_alloc(dev_t dev, char *name)
 		goto abort;
 
 	error = -ENOMEM;
-	mddev->queue = blk_alloc_queue(NUMA_NO_NODE);
-	if (!mddev->queue)
+	disk = blk_alloc_disk(NUMA_NO_NODE);
+	if (!disk)
 		goto abort;
 
-	blk_set_stacking_limits(&mddev->queue->limits);
-
-	disk = alloc_disk(1 << shift);
-	if (!disk) {
-		blk_cleanup_queue(mddev->queue);
-		mddev->queue = NULL;
-		goto abort;
-	}
 	disk->major = MAJOR(mddev->unit);
 	disk->first_minor = unit << shift;
+	disk->minors = 1 << shift;
 	if (name)
 		strcpy(disk->disk_name, name);
 	else if (partitioned)
@@ -5733,7 +5724,9 @@ static int md_alloc(dev_t dev, char *name)
 		sprintf(disk->disk_name, "md%d", unit);
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
-	disk->queue = mddev->queue;
+
+	mddev->queue = disk->queue;
+	blk_set_stacking_limits(&mddev->queue->limits);
 	blk_queue_write_cache(mddev->queue, true, true);
 	/* Allow extended partitions.  This makes the
 	 * 'mdp' device redundant, but we can't really
diff --git a/drivers/md/md.h b/drivers/md/md.h
index fb7eab58cfd5..a88086d4110c 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -395,10 +395,10 @@ struct mddev {
 	 * that we are never stopping an array while it is open.
 	 * 'reconfig_mutex' protects all other reconfiguration.
 	 * These locks are separate due to conflicting interactions
-	 * with bdev->bd_mutex.
+	 * with disk->open_mutex.
 	 * Lock ordering is:
-	 *  reconfig_mutex -> bd_mutex
-	 *  bd_mutex -> open_mutex:  e.g. __blkdev_get -> md_open
+	 *  reconfig_mutex -> disk->open_mutex
+	 *  disk->open_mutex -> open_mutex:  e.g. __blkdev_get -> md_open
 	 */
 	struct mutex			open_mutex;
 	struct mutex			reconfig_mutex;