Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Another series of killing more code than what is being added, again
  thanks to Christoph's relentless cleanups and tech debt tackling.

  This contains:

   - blk-iocost improvements (Baolin Wang)

   - part0 iostat fix (Jeffle Xu)

   - Disable iopoll for split bios (Jeffle Xu)

   - block tracepoint cleanups (Christoph Hellwig)

   - Merging of struct block_device and hd_struct (Christoph Hellwig)

   - Rework/cleanup of how block device sizes are updated (Christoph
     Hellwig)

   - Simplification of gendisk lookup and removal of block device
     aliasing (Christoph Hellwig)

   - Block device ioctl cleanups (Christoph Hellwig)

   - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig)

   - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig)

   - sbitmap improvements (Pavel Begunkov)

   - Hybrid polling fix (Pavel Begunkov)

   - bvec iteration improvements (Pavel Begunkov)

   - Zone revalidation fixes (Damien Le Moal)

   - blk-throttle limit fix (Yu Kuai)

   - Various little fixes"

* tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits)
  blk-mq: fix msec comment from micro to milli seconds
  blk-mq: update arg in comment of blk_mq_map_queue
  blk-mq: add helper allocating tagset->tags
  Revert "block: Fix a lockdep complaint triggered by request queue flushing"
  nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class
  blk-mq: add new API of blk_mq_hctx_set_fq_lock_class
  block: disable iopoll for split bio
  block: Improve blk_revalidate_disk_zones() checks
  sbitmap: simplify wrap check
  sbitmap: replace CAS with atomic and
  sbitmap: remove swap_lock
  sbitmap: optimise sbitmap_deferred_clear()
  blk-mq: skip hybrid polling if iopoll doesn't spin
  blk-iocost: Factor out the base vrate change into a separate function
  blk-iocost: Factor out the active iocgs' state check into a separate function
  blk-iocost: Move the usage ratio calculation to the correct place
  blk-iocost: Remove unnecessary advance declaration
  blk-iocost: Fix some typos in comments
  blktrace: fix up a kerneldoc comment
  block: remove the request_queue to argument request based tracepoints
  ...

14 files changed, 112 insertions, 170 deletions

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 214326383145..85b1f2a9b72d 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -475,7 +475,7 @@ struct search {
 	unsigned int		read_dirty_data:1;
 	unsigned int		cache_missed:1;
 
-	struct hd_struct	*part;
+	struct block_device	*part;
 	unsigned long		start_time;
 
 	struct btree_op		op;
@@ -1073,7 +1073,7 @@ struct detached_dev_io_private {
 	unsigned long		start_time;
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
-	struct hd_struct	*part;
+	struct block_device	*part;
 };
 
 static void detached_dev_end_io(struct bio *bio)
@@ -1230,8 +1230,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 
 	if (dc->io_disable)
 		return -EIO;
-
-	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
+	if (!dc->bdev->bd_disk->fops->ioctl)
+		return -ENOTTY;
+	return dc->bdev->bd_disk->fops->ioctl(dc->bdev, mode, cmd, arg);
 }
 
 void bch_cached_dev_request_init(struct cached_dev *dc)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 46a00134a36a..04fa40868fbe 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1408,7 +1408,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 			q->limits.raid_partial_stripes_expensive;
 
 	ret = bcache_device_init(&dc->disk, block_size,
-			 dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
+			 bdev_nr_sectors(dc->bdev) - dc->sb.data_offset,
 			 dc->bdev, &bcache_cached_ops);
 	if (ret)
 		return ret;
@@ -1447,8 +1447,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto err;
 
 	err = "error creating kobject";
-	if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj,
-			"bcache"))
+	if (kobject_add(&dc->disk.kobj, bdev_kobj(bdev), "bcache"))
 		goto err;
 	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
 		goto err;
@@ -2342,9 +2341,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto err;
 	}
 
-	if (kobject_add(&ca->kobj,
-			&part_to_dev(bdev->bd_part)->kobj,
-			"bcache")) {
+	if (kobject_add(&ca->kobj, bdev_kobj(bdev), "bcache")) {
 		err = "error calling kobject_add";
 		ret = -ENOMEM;
 		goto out;
@@ -2383,38 +2380,38 @@ kobj_attribute_write(register,		register_bcache);
 kobj_attribute_write(register_quiet,	register_bcache);
 kobj_attribute_write(pendings_cleanup,	bch_pending_bdevs_cleanup);
 
-static bool bch_is_open_backing(struct block_device *bdev)
+static bool bch_is_open_backing(dev_t dev)
 {
 	struct cache_set *c, *tc;
 	struct cached_dev *dc, *t;
 
 	list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
 		list_for_each_entry_safe(dc, t, &c->cached_devs, list)
-			if (dc->bdev == bdev)
+			if (dc->bdev->bd_dev == dev)
 				return true;
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
-		if (dc->bdev == bdev)
+		if (dc->bdev->bd_dev == dev)
 			return true;
 	return false;
 }
 
-static bool bch_is_open_cache(struct block_device *bdev)
+static bool bch_is_open_cache(dev_t dev)
 {
 	struct cache_set *c, *tc;
 
 	list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
 		struct cache *ca = c->cache;
 
-		if (ca->bdev == bdev)
+		if (ca->bdev->bd_dev == dev)
 			return true;
 	}
 
 	return false;
 }
 
-static bool bch_is_open(struct block_device *bdev)
+static bool bch_is_open(dev_t dev)
 {
-	return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
+	return bch_is_open_cache(dev) || bch_is_open_backing(dev);
 }
 
 struct async_reg_args {
@@ -2538,9 +2535,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 				  sb);
 	if (IS_ERR(bdev)) {
 		if (bdev == ERR_PTR(-EBUSY)) {
-			bdev = lookup_bdev(strim(path));
+			dev_t dev;
+
 			mutex_lock(&bch_register_lock);
-			if (!IS_ERR(bdev) && bch_is_open(bdev))
+			if (lookup_bdev(strim(path), &dev) == 0 &&
+			    bch_is_open(dev))
 				err = "device already registered";
 			else
 				err = "device busy";
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index d522093cb39d..086d293c2b03 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -96,19 +96,12 @@ struct mapped_device {
 	 */
 	struct workqueue_struct *wq;
 
-	/*
-	 * freeze/thaw support require holding onto a super block
-	 */
-	struct super_block *frozen_sb;
-
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
 	/* kobject and completion */
 	struct dm_kobject_holder kobj_holder;
 
-	struct block_device *bdev;
-
 	struct dm_stats stats;
 
 	/* for blk-mq request-based DM support */
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 56b723d012ac..23c38777e8f6 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -700,8 +700,7 @@ static void rs_set_capacity(struct raid_set *rs)
 {
 	struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
 
-	set_capacity(gendisk, rs->md.array_sectors);
-	revalidate_disk_size(gendisk, true);
+	set_capacity_and_notify(gendisk, rs->md.array_sectors);
 }
 
 /*
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 729a72ec30cc..13b4385f4d5a 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -397,7 +397,7 @@ static int map_request(struct dm_rq_target_io *tio)
 		}
 
 		/* The target has remapped the I/O so dispatch it */
-		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
+		trace_block_rq_remap(clone, disk_devt(dm_disk(md)),
 				     blk_rq_pos(rq));
 		ret = dm_dispatch_clone_request(clone, rq);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 7eeb7c4169c9..188f41287f18 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -347,16 +347,9 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 dev_t dm_get_dev_t(const char *path)
 {
 	dev_t dev;
-	struct block_device *bdev;
 
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev))
+	if (lookup_bdev(path, &dev))
 		dev = name_to_dev_t(path);
-	else {
-		dev = bdev->bd_dev;
-		bdput(bdev);
-	}
-
 	return dev;
 }
 EXPORT_SYMBOL_GPL(dm_get_dev_t);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4e0cbfe3f14d..5b2f371ec4bb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -570,7 +570,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 		}
 	}
 
-	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	if (!bdev->bd_disk->fops->ioctl)
+		r = -ENOTTY;
+	else
+		r = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
 out:
 	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
@@ -1274,8 +1277,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		break;
 	case DM_MAPIO_REMAPPED:
 		/* the bio has been remapped so dispatch it */
-		trace_block_bio_remap(clone->bi_disk->queue, clone,
-				      bio_dev(io->orig_bio), sector);
+		trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector);
 		ret = submit_bio_noacct(clone);
 		break;
 	case DM_MAPIO_KILL:
@@ -1420,18 +1422,12 @@ static int __send_empty_flush(struct clone_info *ci)
 	 */
 	bio_init(&flush_bio, NULL, 0);
 	flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+	flush_bio.bi_disk = ci->io->md->disk;
+	bio_associate_blkg(&flush_bio);
+
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
 
-	/*
-	 * Empty flush uses a statically initialized bio, as the base for
-	 * cloning.  However, blkg association requires that a bdev is
-	 * associated with a gendisk, which doesn't happen until the bdev is
-	 * opened.  So, blkg association is done at issue time of the flush
-	 * rather than when the device is created in alloc_dev().
-	 */
-	bio_set_dev(ci->bio, ci->io->md->bdev);
-
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
@@ -1611,12 +1607,12 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * (by eliminating DM's splitting and just using bio_split)
 				 */
 				part_stat_lock();
-				__dm_part_stat_sub(&dm_disk(md)->part0,
+				__dm_part_stat_sub(dm_disk(md)->part0,
 						   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
 				part_stat_unlock();
 
 				bio_chain(b, bio);
-				trace_block_split(md->queue, b, bio->bi_iter.bi_sector);
+				trace_block_split(b, bio->bi_iter.bi_sector);
 				ret = submit_bio_noacct(bio);
 				break;
 			}
@@ -1748,11 +1744,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 
 	cleanup_srcu_struct(&md->io_barrier);
 
-	if (md->bdev) {
-		bdput(md->bdev);
-		md->bdev = NULL;
-	}
-
 	mutex_destroy(&md->suspend_lock);
 	mutex_destroy(&md->type_lock);
 	mutex_destroy(&md->table_devices_lock);
@@ -1844,10 +1835,6 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->wq)
 		goto bad;
 
-	md->bdev = bdget_disk(md->disk, 0);
-	if (!md->bdev)
-		goto bad;
-
 	dm_stats_init(&md->stats);
 
 	/* Populate the mapping, nobody knows we exist yet */
@@ -1972,8 +1959,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity(md->disk, size);
-	bd_set_nr_sectors(md->bdev, size);
+	set_capacity_and_notify(md->disk, size);
 
 	dm_table_event_callback(t, event_callback, md);
 
@@ -2256,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put);
 static bool md_in_flight_bios(struct mapped_device *md)
 {
 	int cpu;
-	struct hd_struct *part = &dm_disk(md)->part0;
+	struct block_device *part = dm_disk(md)->part0;
 	long sum = 0;
 
 	for_each_possible_cpu(cpu) {
@@ -2391,27 +2377,19 @@ static int lock_fs(struct mapped_device *md)
 {
 	int r;
 
-	WARN_ON(md->frozen_sb);
+	WARN_ON(test_bit(DMF_FROZEN, &md->flags));
 
-	md->frozen_sb = freeze_bdev(md->bdev);
-	if (IS_ERR(md->frozen_sb)) {
-		r = PTR_ERR(md->frozen_sb);
-		md->frozen_sb = NULL;
-		return r;
-	}
-
-	set_bit(DMF_FROZEN, &md->flags);
-
-	return 0;
+	r = freeze_bdev(md->disk->part0);
+	if (!r)
+		set_bit(DMF_FROZEN, &md->flags);
+	return r;
 }
 
 static void unlock_fs(struct mapped_device *md)
 {
 	if (!test_bit(DMF_FROZEN, &md->flags))
 		return;
-
-	thaw_bdev(md->bdev, md->frozen_sb);
-	md->frozen_sb = NULL;
+	thaw_bdev(md->disk->part0);
 	clear_bit(DMF_FROZEN, &md->flags);
 }
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 4aaf4820b6f6..35e2690c1803 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -581,8 +581,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		process_metadata_update(mddev, msg);
 		break;
 	case CHANGE_CAPACITY:
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk_size(mddev->gendisk, true);
+		set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
 		break;
 	case RESYNCING:
 		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
@@ -1296,13 +1295,10 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
 		if (ret)
 			pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n",
 			       __func__, __LINE__);
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk_size(mddev->gendisk, true);
+		set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
 	} else {
 		/* revert to previous sectors */
 		ret = mddev->pers->resize(mddev, old_dev_sectors);
-		if (!ret)
-			revalidate_disk_size(mddev->gendisk, true);
 		ret = __sendmsg(cinfo, &cmsg);
 		if (ret)
 			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 5ab22069b5be..68cac7d19278 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -200,9 +200,8 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 		"copied raid_disks doesn't match mddev->raid_disks");
 	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
-	set_capacity(mddev->gendisk, mddev->array_sectors);
+	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
-	revalidate_disk_size(mddev->gendisk, true);
 	kfree_rcu(oldconf, rcu);
 	return 0;
 }
@@ -258,8 +257,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		bio_endio(bio);
 	} else {
 		if (mddev->gendisk)
-			trace_block_bio_remap(bio->bi_disk->queue,
-					      bio, disk_devt(mddev->gendisk),
+			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
 					      bio_sector);
 		mddev_check_writesame(mddev, bio);
 		mddev_check_write_zeroes(mddev, bio);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0037c6ecab65..0445f44ae635 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -464,7 +464,7 @@ struct md_io {
 	bio_end_io_t *orig_bi_end_io;
 	void *orig_bi_private;
 	unsigned long start_time;
-	struct hd_struct *part;
+	struct block_device *part;
 };
 
 static void md_end_io(struct bio *bio)
@@ -2414,7 +2414,6 @@ EXPORT_SYMBOL(md_integrity_add_rdev);
 static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 {
 	char b[BDEVNAME_SIZE];
-	struct kobject *ko;
 	int err;
 
 	/* prevent duplicates */
@@ -2477,9 +2476,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
 
-	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
 	/* failure here is OK */
-	err = sysfs_create_link(&rdev->kobj, ko, "block");
+	err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block");
 	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 	rdev->sysfs_unack_badblocks =
 		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
@@ -5355,10 +5353,9 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 
 	if (!err) {
 		mddev->array_sectors = sectors;
-		if (mddev->pers) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
-		}
+		if (mddev->pers)
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 	}
 	mddev_unlock(mddev);
 	return err ?: len;
@@ -5765,11 +5762,12 @@ static int md_alloc(dev_t dev, char *name)
 	return error;
 }
 
-static struct kobject *md_probe(dev_t dev, int *part, void *data)
+static void md_probe(dev_t dev)
 {
+	if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512)
+		return;
 	if (create_on_open)
 		md_alloc(dev, NULL);
-	return NULL;
 }
 
 static int add_named_array(const char *val, const struct kernel_param *kp)
@@ -6107,8 +6105,7 @@ int do_md_run(struct mddev *mddev)
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk_size(mddev->gendisk, true);
+	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
 	clear_bit(MD_NOT_READY, &mddev->flags);
 	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@@ -6423,10 +6420,9 @@ static int do_md_stop(struct mddev *mddev, int mode,
 			if (rdev->raid_disk >= 0)
 				sysfs_unlink_rdev(mddev, rdev);
 
-		set_capacity(disk, 0);
+		set_capacity_and_notify(disk, 0);
 		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
-		revalidate_disk_size(disk, true);
 
 		if (mddev->ro)
 			mddev->ro = 0;
@@ -6535,7 +6531,7 @@ static void autorun_devices(int part)
 			break;
 		}
 
-		md_probe(dev, NULL, NULL);
+		md_probe(dev);
 		mddev = mddev_find(dev);
 		if (!mddev || !mddev->gendisk) {
 			if (mddev)
@@ -7257,8 +7253,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
 		else if (mddev->queue) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 		}
 	}
 	return rv;
@@ -7480,7 +7476,6 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
 	case ADD_NEW_DISK:
-	case BLKROSET:
 	case GET_ARRAY_INFO:
 	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
@@ -7507,7 +7502,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	int ro;
 	bool did_set_md_closing = false;
 
 	if (!md_ioctl_valid(cmd))
@@ -7687,35 +7681,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			goto unlock;
 		}
 		break;
-
-	case BLKROSET:
-		if (get_user(ro, (int __user *)(arg))) {
-			err = -EFAULT;
-			goto unlock;
-		}
-		err = -EINVAL;
-
-		/* if the bdev is going readonly the value of mddev->ro
-		 * does not matter, no writes are coming
-		 */
-		if (ro)
-			goto unlock;
-
-		/* are we are already prepared for writes? */
-		if (mddev->ro != 1)
-			goto unlock;
-
-		/* transitioning to readauto need only happen for
-		 * arrays that call md_write_start
-		 */
-		if (mddev->pers) {
-			err = restart_array(mddev);
-			if (err == 0) {
-				mddev->ro = 2;
-				set_disk_ro(mddev->gendisk, 0);
-			}
-		}
-		goto unlock;
 	}
 
 	/*
@@ -7809,6 +7774,36 @@ static int md_compat_ioctl(struct block_device *bdev, fmode_t mode,
 }
 #endif /* CONFIG_COMPAT */
 
+static int md_set_read_only(struct block_device *bdev, bool ro)
+{
+	struct mddev *mddev = bdev->bd_disk->private_data;
+	int err;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+
+	if (!mddev->raid_disks && !mddev->external) {
+		err = -ENODEV;
+		goto out_unlock;
+	}
+
+	/*
+	 * Transitioning to read-auto need only happen for arrays that call
+	 * md_write_start and which are not ready for writes yet.
+	 */
+	if (!ro && mddev->ro == 1 && mddev->pers) {
+		err = restart_array(mddev);
+		if (err)
+			goto out_unlock;
+		mddev->ro = 2;
+	}
+
+out_unlock:
+	mddev_unlock(mddev);
+	return err;
+}
+
 static int md_open(struct block_device *bdev, fmode_t mode)
 {
 	/*
@@ -7886,6 +7881,7 @@ const struct block_device_operations md_fops =
 #endif
 	.getgeo		= md_getgeo,
 	.check_events	= md_check_events,
+	.set_read_only	= md_set_read_only,
 };
 
 static int md_thread(void *arg)
@@ -8445,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
-		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
+		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
@@ -9015,10 +9011,9 @@ void md_do_sync(struct md_thread *thread)
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
-		if (!mddev_is_clustered(mddev)) {
-			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk_size(mddev->gendisk, true);
-		}
+		if (!mddev_is_clustered(mddev))
+			set_capacity_and_notify(mddev->gendisk,
+						mddev->array_sectors);
 	}
 
 	spin_lock(&mddev->lock);
@@ -9547,18 +9542,15 @@ static int __init md_init(void)
 	if (!md_rdev_misc_wq)
 		goto err_rdev_misc_wq;
 
-	if ((ret = register_blkdev(MD_MAJOR, "md")) < 0)
+	ret = __register_blkdev(MD_MAJOR, "md", md_probe);
+	if (ret < 0)
 		goto err_md;
 
-	if ((ret = register_blkdev(0, "mdp")) < 0)
+	ret = __register_blkdev(0, "mdp", md_probe);
+	if (ret < 0)
 		goto err_mdp;
 	mdp_major = ret;
 
-	blk_register_region(MKDEV(MD_MAJOR, 0), 512, THIS_MODULE,
-			    md_probe, NULL, NULL);
-	blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE,
-			    md_probe, NULL, NULL);
-
 	register_reboot_notifier(&md_notifier);
 	raid_table_header = register_sysctl_table(raid_root_table);
 
@@ -9825,9 +9817,6 @@ static __exit void md_exit(void)
 	struct list_head *tmp;
 	int delay = 1;
 
-	blk_unregister_region(MKDEV(MD_MAJOR,0), 512);
-	blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
-
 	unregister_blkdev(MD_MAJOR,"md");
 	unregister_blkdev(mdp_major, "mdp");
 	unregister_reboot_notifier(&md_notifier);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 35843df15b5e..67f157f2525d 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -508,8 +508,8 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 		bio_chain(discard_bio, bio);
 		bio_clone_blkg_association(discard_bio, bio);
 		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
-				discard_bio, disk_devt(mddev->gendisk),
+			trace_block_bio_remap(discard_bio,
+				disk_devt(mddev->gendisk),
 				bio->bi_iter.bi_sector);
 		submit_bio_noacct(discard_bio);
 	}
@@ -581,8 +581,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		tmp_dev->data_offset;
 
 	if (mddev->gendisk)
-		trace_block_bio_remap(bio->bi_disk->queue, bio,
-				disk_devt(mddev->gendisk), bio_sector);
+		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
+				      bio_sector);
 	mddev_check_writesame(mddev, bio);
 	mddev_check_write_zeroes(mddev, bio);
 	submit_bio_noacct(bio);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 960d854c07f8..c0347997f6ff 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1305,8 +1305,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r1_bio;
 
 	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
-				disk_devt(mddev->gendisk), r1_bio->sector);
+	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
+				      r1_bio->sector);
 
 	submit_bio_noacct(read_bio);
 }
@@ -1517,8 +1517,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		atomic_inc(&r1_bio->remaining);
 
 		if (mddev->gendisk)
-			trace_block_bio_remap(mbio->bi_disk->queue,
-					      mbio, disk_devt(mddev->gendisk),
+			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
 					      r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_disk = (void *)conf->mirrors[i].rdev;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3b598a3cb462..800fe0628d25 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1201,8 +1201,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r10_bio;
 
 	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio->bi_disk->queue,
-	                              read_bio, disk_devt(mddev->gendisk),
+	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
 	                              r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
@@ -1251,8 +1250,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	mbio->bi_private = r10_bio;
 
 	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio->bi_disk->queue,
-				      mbio, disk_devt(conf->mddev->gendisk),
+		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
 				      r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_disk = (void *)rdev;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 39343479ac2a..3a90cc0e43ca 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1222,9 +1222,9 @@ again:
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
 			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bi->bi_disk->queue,
-						      bi, disk_devt(conf->mddev->gendisk),
-						      sh->dev[i].sector);
+				trace_block_bio_remap(bi,
+						disk_devt(conf->mddev->gendisk),
+						sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
@@ -1272,9 +1272,9 @@ again:
 			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
 			if (conf->mddev->gendisk)
-				trace_block_bio_remap(rbi->bi_disk->queue,
-						      rbi, disk_devt(conf->mddev->gendisk),
-						      sh->dev[i].sector);
+				trace_block_bio_remap(rbi,
+						disk_devt(conf->mddev->gendisk),
+						sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
@@ -5468,8 +5468,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		spin_unlock_irq(&conf->device_lock);
 
 		if (mddev->gendisk)
-			trace_block_bio_remap(align_bi->bi_disk->queue,
-					      align_bi, disk_devt(mddev->gendisk),
+			trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk),
 					      raid_bio->bi_iter.bi_sector);
 		submit_bio_noacct(align_bi);
 		return 1;