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
  ...

22 files changed, 357 insertions, 671 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9e84b1928b94..9e56ee1f2652 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -32,6 +32,7 @@
 #include <linux/cleancache.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/falloc.h>
+#include <linux/part_stat.h>
 #include <linux/uaccess.h>
 #include <linux/suspend.h>
 #include "internal.h"
@@ -110,24 +111,20 @@ EXPORT_SYMBOL(invalidate_bdev);
 int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 			loff_t lstart, loff_t lend)
 {
-	struct block_device *claimed_bdev = NULL;
-	int err;
-
 	/*
 	 * If we don't hold exclusive handle for the device, upgrade to it
 	 * while we discard the buffer cache to avoid discarding buffers
 	 * under live filesystem.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bdev->bd_contains;
-		err = bd_prepare_to_claim(bdev, claimed_bdev,
-					  truncate_bdev_range);
+		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
 		if (err)
 			return err;
 	}
+
 	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
-	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
 }
 EXPORT_SYMBOL(truncate_bdev_range);
@@ -548,55 +545,47 @@ EXPORT_SYMBOL(fsync_bdev);
  * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
  * actually.
  */
-struct super_block *freeze_bdev(struct block_device *bdev)
+int freeze_bdev(struct block_device *bdev)
 {
 	struct super_block *sb;
 	int error = 0;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (++bdev->bd_fsfreeze_count > 1) {
-		/*
-		 * We don't even need to grab a reference - the first call
-		 * to freeze_bdev grab an active reference and only the last
-		 * thaw_bdev drops it.
-		 */
-		sb = get_super(bdev);
-		if (sb)
-			drop_super(sb);
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return sb;
-	}
+	if (++bdev->bd_fsfreeze_count > 1)
+		goto done;
 
 	sb = get_active_super(bdev);
 	if (!sb)
-		goto out;
+		goto sync;
 	if (sb->s_op->freeze_super)
 		error = sb->s_op->freeze_super(sb);
 	else
 		error = freeze_super(sb);
+	deactivate_super(sb);
+
 	if (error) {
-		deactivate_super(sb);
 		bdev->bd_fsfreeze_count--;
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return ERR_PTR(error);
+		goto done;
 	}
-	deactivate_super(sb);
- out:
+	bdev->bd_fsfreeze_sb = sb;
+
+sync:
 	sync_blockdev(bdev);
+done:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-	return sb;	/* thaw_bdev releases s->s_umount */
+	return error;
 }
 EXPORT_SYMBOL(freeze_bdev);
 
 /**
  * thaw_bdev  -- unlock filesystem
  * @bdev:	blockdevice to unlock
- * @sb:		associated superblock
  *
  * Unlocks the filesystem and marks it writeable again after freeze_bdev().
  */
-int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+int thaw_bdev(struct block_device *bdev)
 {
+	struct super_block *sb;
 	int error = -EINVAL;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
@@ -607,6 +596,7 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 	if (--bdev->bd_fsfreeze_count > 0)
 		goto out;
 
+	sb = bdev->bd_fsfreeze_sb;
 	if (!sb)
 		goto out;
 
@@ -792,23 +782,19 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 
 static void bdev_free_inode(struct inode *inode)
 {
+	struct block_device *bdev = I_BDEV(inode);
+
+	free_percpu(bdev->bd_stats);
+	kfree(bdev->bd_meta_info);
+
 	kmem_cache_free(bdev_cachep, BDEV_I(inode));
 }
 
-static void init_once(void *foo)
+static void init_once(void *data)
 {
-	struct bdev_inode *ei = (struct bdev_inode *) foo;
-	struct block_device *bdev = &ei->bdev;
+	struct bdev_inode *ei = data;
 
-	memset(bdev, 0, sizeof(*bdev));
-	mutex_init(&bdev->bd_mutex);
-#ifdef CONFIG_SYSFS
-	INIT_LIST_HEAD(&bdev->bd_holder_disks);
-#endif
-	bdev->bd_bdi = &noop_backing_dev_info;
 	inode_init_once(&ei->vfs_inode);
-	/* Initialize mutex for freeze. */
-	mutex_init(&bdev->bd_fsfreeze_mutex);
 }
 
 static void bdev_evict_inode(struct inode *inode)
@@ -870,72 +856,72 @@ void __init bdev_cache_init(void)
 	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
 }
 
-/*
- * Most likely _very_ bad one - but then it's hardly critical for small
- * /dev and can be fixed when somebody will need really large one.
- * Keep in mind that it will be fed through icache hash function too.
- */
-static inline unsigned long hash(dev_t dev)
+struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 {
-	return MAJOR(dev)+MINOR(dev);
-}
+	struct block_device *bdev;
+	struct inode *inode;
 
-static int bdev_test(struct inode *inode, void *data)
-{
-	return BDEV_I(inode)->bdev.bd_dev == *(dev_t *)data;
+	inode = new_inode(blockdev_superblock);
+	if (!inode)
+		return NULL;
+	inode->i_mode = S_IFBLK;
+	inode->i_rdev = 0;
+	inode->i_data.a_ops = &def_blk_aops;
+	mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+
+	bdev = I_BDEV(inode);
+	memset(bdev, 0, sizeof(*bdev));
+	mutex_init(&bdev->bd_mutex);
+	mutex_init(&bdev->bd_fsfreeze_mutex);
+	spin_lock_init(&bdev->bd_size_lock);
+	bdev->bd_disk = disk;
+	bdev->bd_partno = partno;
+	bdev->bd_inode = inode;
+	bdev->bd_bdi = &noop_backing_dev_info;
+#ifdef CONFIG_SYSFS
+	INIT_LIST_HEAD(&bdev->bd_holder_disks);
+#endif
+	bdev->bd_stats = alloc_percpu(struct disk_stats);
+	if (!bdev->bd_stats) {
+		iput(inode);
+		return NULL;
+	}
+	return bdev;
 }
 
-static int bdev_set(struct inode *inode, void *data)
+void bdev_add(struct block_device *bdev, dev_t dev)
 {
-	BDEV_I(inode)->bdev.bd_dev = *(dev_t *)data;
-	return 0;
+	bdev->bd_dev = dev;
+	bdev->bd_inode->i_rdev = dev;
+	bdev->bd_inode->i_ino = dev;
+	insert_inode_hash(bdev->bd_inode);
 }
 
 static struct block_device *bdget(dev_t dev)
 {
-	struct block_device *bdev;
 	struct inode *inode;
 
-	inode = iget5_locked(blockdev_superblock, hash(dev),
-			bdev_test, bdev_set, &dev);
-
+	inode = ilookup(blockdev_superblock, dev);
 	if (!inode)
 		return NULL;
-
-	bdev = &BDEV_I(inode)->bdev;
-
-	if (inode->i_state & I_NEW) {
-		spin_lock_init(&bdev->bd_size_lock);
-		bdev->bd_contains = NULL;
-		bdev->bd_super = NULL;
-		bdev->bd_inode = inode;
-		bdev->bd_part_count = 0;
-		inode->i_mode = S_IFBLK;
-		inode->i_rdev = dev;
-		inode->i_bdev = bdev;
-		inode->i_data.a_ops = &def_blk_aops;
-		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		unlock_new_inode(inode);
-	}
-	return bdev;
+	return &BDEV_I(inode)->bdev;
 }
 
 /**
  * bdgrab -- Grab a reference to an already referenced block device
  * @bdev:	Block device to grab a reference to.
+ *
+ * Returns the block_device with an additional reference when successful,
+ * or NULL if the inode is already beeing freed.
  */
 struct block_device *bdgrab(struct block_device *bdev)
 {
-	ihold(bdev->bd_inode);
+	if (!igrab(bdev->bd_inode))
+		return NULL;
 	return bdev;
 }
 EXPORT_SYMBOL(bdgrab);
 
-struct block_device *bdget_part(struct hd_struct *part)
-{
-	return bdget(part_devt(part));
-}
-
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
@@ -953,67 +939,8 @@ void bdput(struct block_device *bdev)
 {
 	iput(bdev->bd_inode);
 }
-
 EXPORT_SYMBOL(bdput);
  
-static struct block_device *bd_acquire(struct inode *inode)
-{
-	struct block_device *bdev;
-
-	spin_lock(&bdev_lock);
-	bdev = inode->i_bdev;
-	if (bdev && !inode_unhashed(bdev->bd_inode)) {
-		bdgrab(bdev);
-		spin_unlock(&bdev_lock);
-		return bdev;
-	}
-	spin_unlock(&bdev_lock);
-
-	/*
-	 * i_bdev references block device inode that was already shut down
-	 * (corresponding device got removed).  Remove the reference and look
-	 * up block device inode again just in case new device got
-	 * reestablished under the same device number.
-	 */
-	if (bdev)
-		bd_forget(inode);
-
-	bdev = bdget(inode->i_rdev);
-	if (bdev) {
-		spin_lock(&bdev_lock);
-		if (!inode->i_bdev) {
-			/*
-			 * We take an additional reference to bd_inode,
-			 * and it's released in clear_inode() of inode.
-			 * So, we can access it via ->i_mapping always
-			 * without igrab().
-			 */
-			bdgrab(bdev);
-			inode->i_bdev = bdev;
-			inode->i_mapping = bdev->bd_inode->i_mapping;
-		}
-		spin_unlock(&bdev_lock);
-	}
-	return bdev;
-}
-
-/* Call when you free inode */
-
-void bd_forget(struct inode *inode)
-{
-	struct block_device *bdev = NULL;
-
-	spin_lock(&bdev_lock);
-	if (!sb_is_blkdev_sb(inode->i_sb))
-		bdev = inode->i_bdev;
-	inode->i_bdev = NULL;
-	inode->i_mapping = &inode->i_data;
-	spin_unlock(&bdev_lock);
-
-	if (bdev)
-		bdput(bdev);
-}
-
 /**
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
@@ -1049,7 +976,6 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 /**
  * bd_prepare_to_claim - claim a block device
  * @bdev: block device of interest
- * @whole: the whole device containing @bdev, may equal @bdev
  * @holder: holder trying to claim @bdev
  *
  * Claim @bdev.  This function fails if @bdev is already claimed by another
@@ -1059,9 +985,12 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
-		void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, void *holder)
 {
+	struct block_device *whole = bdev_whole(bdev);
+
+	if (WARN_ON_ONCE(!holder))
+		return -EINVAL;
 retry:
 	spin_lock(&bdev_lock);
 	/* if someone else claimed, fail */
@@ -1089,27 +1018,6 @@ retry:
 }
 EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
 
-static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
-{
-	struct gendisk *disk = get_gendisk(bdev->bd_dev, partno);
-
-	if (!disk)
-		return NULL;
-	/*
-	 * Now that we hold gendisk reference we make sure bdev we looked up is
-	 * not stale. If it is, it means device got removed and created before
-	 * we looked up gendisk and we fail open in such case. Associating
-	 * unhashed bdev with newly created gendisk could lead to two bdevs
-	 * (and thus two independent caches) being associated with one device
-	 * which is bad.
-	 */
-	if (inode_unhashed(bdev->bd_inode)) {
-		put_disk_and_module(disk);
-		return NULL;
-	}
-	return disk;
-}
-
 static void bd_clear_claiming(struct block_device *whole, void *holder)
 {
 	lockdep_assert_held(&bdev_lock);
@@ -1122,15 +1030,15 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
 /**
  * bd_finish_claiming - finish claiming of a block device
  * @bdev: block device of interest
- * @whole: whole block device
  * @holder: holder that has claimed @bdev
  *
  * Finish exclusive open of a block device. Mark the device as exlusively
  * open by the holder and wake up all waiters for exclusive open to finish.
  */
-static void bd_finish_claiming(struct block_device *bdev,
-		struct block_device *whole, void *holder)
+static void bd_finish_claiming(struct block_device *bdev, void *holder)
 {
+	struct block_device *whole = bdev_whole(bdev);
+
 	spin_lock(&bdev_lock);
 	BUG_ON(!bd_may_claim(bdev, whole, holder));
 	/*
@@ -1155,11 +1063,10 @@ static void bd_finish_claiming(struct block_device *bdev,
  * also used when exclusive open is not actually desired and we just needed
  * to block other exclusive openers for a while.
  */
-void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
-		       void *holder)
+void bd_abort_claiming(struct block_device *bdev, void *holder)
 {
 	spin_lock(&bdev_lock);
-	bd_clear_claiming(whole, holder);
+	bd_clear_claiming(bdev_whole(bdev), holder);
 	spin_unlock(&bdev_lock);
 }
 EXPORT_SYMBOL(bd_abort_claiming);
@@ -1230,7 +1137,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	WARN_ON_ONCE(!bdev->bd_holder);
 
 	/* FIXME: remove the following once add_disk() handles errors */
-	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
+	if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir))
 		goto out_unlock;
 
 	holder = bd_find_holder_disk(bdev, disk);
@@ -1249,24 +1156,24 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	holder->disk = disk;
 	holder->refcnt = 1;
 
-	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	ret = add_symlink(disk->slave_dir, bdev_kobj(bdev));
 	if (ret)
 		goto out_free;
 
-	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
 	if (ret)
 		goto out_del;
 	/*
 	 * bdev could be deleted beneath us which would implicitly destroy
 	 * the holder directory.  Hold on to it.
 	 */
-	kobject_get(bdev->bd_part->holder_dir);
+	kobject_get(bdev->bd_holder_dir);
 
 	list_add(&holder->list, &bdev->bd_holder_disks);
 	goto out_unlock;
 
 out_del:
-	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	del_symlink(disk->slave_dir, bdev_kobj(bdev));
 out_free:
 	kfree(holder);
 out_unlock:
@@ -1294,10 +1201,9 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	holder = bd_find_holder_disk(bdev, disk);
 
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
-		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
-		del_symlink(bdev->bd_part->holder_dir,
-			    &disk_to_dev(disk)->kobj);
-		kobject_put(bdev->bd_part->holder_dir);
+		del_symlink(disk->slave_dir, bdev_kobj(bdev));
+		del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
+		kobject_put(bdev->bd_holder_dir);
 		list_del_init(&holder->list);
 		kfree(holder);
 	}
@@ -1307,77 +1213,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 #endif
 
-/**
- * check_disk_size_change - checks for disk size change and adjusts bdev size.
- * @disk: struct gendisk to check
- * @bdev: struct bdev to adjust.
- * @verbose: if %true log a message about a size change if there is any
- *
- * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs. When shrinking the bdev size, its all caches
- * are freed.
- */
-static void check_disk_size_change(struct gendisk *disk,
-		struct block_device *bdev, bool verbose)
-{
-	loff_t disk_size, bdev_size;
-
-	spin_lock(&bdev->bd_size_lock);
-	disk_size = (loff_t)get_capacity(disk) << 9;
-	bdev_size = i_size_read(bdev->bd_inode);
-	if (disk_size != bdev_size) {
-		if (verbose) {
-			printk(KERN_INFO
-			       "%s: detected capacity change from %lld to %lld\n",
-			       disk->disk_name, bdev_size, disk_size);
-		}
-		i_size_write(bdev->bd_inode, disk_size);
-	}
-	spin_unlock(&bdev->bd_size_lock);
-
-	if (bdev_size > disk_size) {
-		if (__invalidate_device(bdev, false))
-			pr_warn("VFS: busy inodes on resized disk %s\n",
-				disk->disk_name);
-	}
-}
-
-/**
- * revalidate_disk_size - checks for disk size change and adjusts bdev size.
- * @disk: struct gendisk to check
- * @verbose: if %true log a message about a size change if there is any
- *
- * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs. When shrinking the bdev size, its all caches
- * are freed.
- */
-void revalidate_disk_size(struct gendisk *disk, bool verbose)
-{
-	struct block_device *bdev;
-
-	/*
-	 * Hidden disks don't have associated bdev so there's no point in
-	 * revalidating them.
-	 */
-	if (disk->flags & GENHD_FL_HIDDEN)
-		return;
-
-	bdev = bdget_disk(disk, 0);
-	if (bdev) {
-		check_disk_size_change(disk, bdev, verbose);
-		bdput(bdev);
-	}
-}
-EXPORT_SYMBOL(revalidate_disk_size);
-
-void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
-{
-	spin_lock(&bdev->bd_size_lock);
-	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	spin_unlock(&bdev->bd_size_lock);
-}
-EXPORT_SYMBOL(bd_set_nr_sectors);
-
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 int bdev_disk_changed(struct block_device *bdev, bool invalidate)
@@ -1411,8 +1246,6 @@ rescan:
 			disk->fops->revalidate_disk(disk);
 	}
 
-	check_disk_size_change(disk, bdev, !invalidate);
-
 	if (get_capacity(disk)) {
 		ret = blk_add_partitions(disk, bdev);
 		if (ret == -EAGAIN)
@@ -1439,71 +1272,19 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
  *  mutex_lock(part->bd_mutex)
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
-
-static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
-		int for_part)
+static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 {
-	struct block_device *whole = NULL, *claiming = NULL;
-	struct gendisk *disk;
-	int ret;
-	int partno;
-	bool first_open = false, unblock_events = true, need_restart;
-
- restart:
-	need_restart = false;
-	ret = -ENXIO;
-	disk = bdev_get_gendisk(bdev, &partno);
-	if (!disk)
-		goto out;
-
-	if (partno) {
-		whole = bdget_disk(disk, 0);
-		if (!whole) {
-			ret = -ENOMEM;
-			goto out_put_disk;
-		}
-	}
-
-	if (!for_part && (mode & FMODE_EXCL)) {
-		WARN_ON_ONCE(!holder);
-		if (whole)
-			claiming = whole;
-		else
-			claiming = bdev;
-		ret = bd_prepare_to_claim(bdev, claiming, holder);
-		if (ret)
-			goto out_put_whole;
-	}
+	struct gendisk *disk = bdev->bd_disk;
+	int ret = 0;
 
-	disk_block_events(disk);
-	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
-		first_open = true;
-		bdev->bd_disk = disk;
-		bdev->bd_contains = bdev;
-		bdev->bd_partno = partno;
-
-		if (!partno) {
-			ret = -ENXIO;
-			bdev->bd_part = disk_get_part(disk, partno);
-			if (!bdev->bd_part)
-				goto out_clear;
-
+		if (!bdev_is_partition(bdev)) {
 			ret = 0;
-			if (disk->fops->open) {
+			if (disk->fops->open)
 				ret = disk->fops->open(bdev, mode);
-				/*
-				 * If we lost a race with 'disk' being deleted,
-				 * try again.  See md.c
-				 */
-				if (ret == -ERESTARTSYS)
-					need_restart = true;
-			}
 
-			if (!ret) {
-				bd_set_nr_sectors(bdev, get_capacity(disk));
+			if (!ret)
 				set_init_blocksize(bdev);
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1516,28 +1297,33 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
 			if (ret)
-				goto out_clear;
+				return ret;
 		} else {
-			BUG_ON(for_part);
-			ret = __blkdev_get(whole, mode, NULL, 1);
-			if (ret)
-				goto out_clear;
-			bdev->bd_contains = bdgrab(whole);
-			bdev->bd_part = disk_get_part(disk, partno);
+			struct block_device *whole = bdgrab(disk->part0);
+
+			mutex_lock_nested(&whole->bd_mutex, 1);
+			ret = __blkdev_get(whole, mode);
+			if (ret) {
+				mutex_unlock(&whole->bd_mutex);
+				bdput(whole);
+				return ret;
+			}
+			whole->bd_part_count++;
+			mutex_unlock(&whole->bd_mutex);
+
 			if (!(disk->flags & GENHD_FL_UP) ||
-			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
-				ret = -ENXIO;
-				goto out_clear;
+			    !bdev_nr_sectors(bdev)) {
+				__blkdev_put(whole, mode, 1);
+				bdput(whole);
+				return -ENXIO;
 			}
-			bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects);
 			set_init_blocksize(bdev);
 		}
 
 		if (bdev->bd_bdi == &noop_backing_dev_info)
 			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	} else {
-		if (bdev->bd_contains == bdev) {
-			ret = 0;
+		if (!bdev_is_partition(bdev)) {
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
@@ -1545,101 +1331,145 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
-				goto out_unlock_bdev;
+				return ret;
 		}
 	}
 	bdev->bd_openers++;
-	if (for_part)
-		bdev->bd_part_count++;
-	if (claiming)
-		bd_finish_claiming(bdev, claiming, holder);
+	return 0;
+}
 
-	/*
-	 * Block event polling for write claims if requested.  Any write holder
-	 * makes the write_holder state stick until all are released.  This is
-	 * good enough and tracking individual writeable reference is too
-	 * fragile given the way @mode is used in blkdev_get/put().
-	 */
-	if (claiming && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
-	    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
-		bdev->bd_write_holder = true;
-		unblock_events = false;
-	}
-	mutex_unlock(&bdev->bd_mutex);
+struct block_device *blkdev_get_no_open(dev_t dev)
+{
+	struct block_device *bdev;
+	struct gendisk *disk;
 
-	if (unblock_events)
-		disk_unblock_events(disk);
+	down_read(&bdev_lookup_sem);
+	bdev = bdget(dev);
+	if (!bdev) {
+		up_read(&bdev_lookup_sem);
+		blk_request_module(dev);
+		down_read(&bdev_lookup_sem);
+
+		bdev = bdget(dev);
+		if (!bdev)
+			goto unlock;
+	}
 
-	/* only one opener holds refs to the module and disk */
-	if (!first_open)
-		put_disk_and_module(disk);
-	if (whole)
-		bdput(whole);
-	return 0;
+	disk = bdev->bd_disk;
+	if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj))
+		goto bdput;
+	if ((disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP)
+		goto put_disk;
+	if (!try_module_get(bdev->bd_disk->fops->owner))
+		goto put_disk;
+	up_read(&bdev_lookup_sem);
+	return bdev;
+put_disk:
+	put_disk(disk);
+bdput:
+	bdput(bdev);
+unlock:
+	up_read(&bdev_lookup_sem);
+	return NULL;
+}
 
- out_clear:
-	disk_put_part(bdev->bd_part);
-	bdev->bd_disk = NULL;
-	bdev->bd_part = NULL;
-	if (bdev != bdev->bd_contains)
-		__blkdev_put(bdev->bd_contains, mode, 1);
-	bdev->bd_contains = NULL;
- out_unlock_bdev:
-	if (claiming)
-		bd_abort_claiming(bdev, claiming, holder);
-	mutex_unlock(&bdev->bd_mutex);
-	disk_unblock_events(disk);
- out_put_whole:
- 	if (whole)
-		bdput(whole);
- out_put_disk:
-	put_disk_and_module(disk);
-	if (need_restart)
-		goto restart;
- out:
-	return ret;
+void blkdev_put_no_open(struct block_device *bdev)
+{
+	module_put(bdev->bd_disk->fops->owner);
+	put_disk(bdev->bd_disk);
+	bdput(bdev);
 }
 
 /**
- * blkdev_get - open a block device
- * @bdev: block_device to open
+ * blkdev_get_by_dev - open a block device by device number
+ * @dev: device number of block device to open
  * @mode: FMODE_* mask
  * @holder: exclusive holder identifier
  *
- * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
- * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
- * @holder is invalid.  Exclusive opens may nest for the same @holder.
+ * Open the block device described by device number @dev. If @mode includes
+ * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
+ * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
+ * the same @holder.
  *
- * On success, the reference count of @bdev is unchanged.  On failure,
- * @bdev is put.
+ * Use this interface ONLY if you really do not have anything better - i.e. when
+ * you are behind a truly sucky interface and all you are given is a device
+ * number.  Everything else should use blkdev_get_by_path().
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * 0 on success, -errno on failure.
+ * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 {
-	int ret, perm = 0;
+	bool unblock_events = true;
+	struct block_device *bdev;
+	struct gendisk *disk;
+	int ret;
 
-	if (mode & FMODE_READ)
-		perm |= MAY_READ;
-	if (mode & FMODE_WRITE)
-		perm |= MAY_WRITE;
-	ret = devcgroup_inode_permission(bdev->bd_inode, perm);
+	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
+			MAJOR(dev), MINOR(dev),
+			((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
+			((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
-		goto bdput;
+		return ERR_PTR(ret);
+
+	/*
+	 * If we lost a race with 'disk' being deleted, try again.  See md.c.
+	 */
+retry:
+	bdev = blkdev_get_no_open(dev);
+	if (!bdev)
+		return ERR_PTR(-ENXIO);
+	disk = bdev->bd_disk;
+
+	if (mode & FMODE_EXCL) {
+		ret = bd_prepare_to_claim(bdev, holder);
+		if (ret)
+			goto put_blkdev;
+	}
+
+	disk_block_events(disk);
 
-	ret =__blkdev_get(bdev, mode, holder, 0);
+	mutex_lock(&bdev->bd_mutex);
+	ret =__blkdev_get(bdev, mode);
 	if (ret)
-		goto bdput;
-	return 0;
+		goto abort_claiming;
+	if (mode & FMODE_EXCL) {
+		bd_finish_claiming(bdev, holder);
 
-bdput:
-	bdput(bdev);
-	return ret;
+		/*
+		 * Block event polling for write claims if requested.  Any write
+		 * holder makes the write_holder state stick until all are
+		 * released.  This is good enough and tracking individual
+		 * writeable reference is too fragile given the way @mode is
+		 * used in blkdev_get/put().
+		 */
+		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
+			bdev->bd_write_holder = true;
+			unblock_events = false;
+		}
+	}
+	mutex_unlock(&bdev->bd_mutex);
+
+	if (unblock_events)
+		disk_unblock_events(disk);
+	return bdev;
+
+abort_claiming:
+	if (mode & FMODE_EXCL)
+		bd_abort_claiming(bdev, holder);
+	mutex_unlock(&bdev->bd_mutex);
+	disk_unblock_events(disk);
+put_blkdev:
+	blkdev_put_no_open(bdev);
+	if (ret == -ERESTARTSYS)
+		goto retry;
+	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL(blkdev_get_by_dev);
 
 /**
  * blkdev_get_by_path - open a block device by name
@@ -1647,32 +1477,30 @@ bdput:
  * @mode: FMODE_* mask
  * @holder: exclusive holder identifier
  *
- * Open the blockdevice described by the device file at @path.  @mode
- * and @holder are identical to blkdev_get().
- *
- * On success, the returned block_device has reference count of one.
+ * Open the block device described by the device file at @path.  If @mode
+ * includes %FMODE_EXCL, the block device is opened with exclusive access.
+ * Specifying %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may
+ * nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 					void *holder)
 {
 	struct block_device *bdev;
-	int err;
-
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev))
-		return bdev;
+	dev_t dev;
+	int error;
 
-	err = blkdev_get(bdev, mode, holder);
-	if (err)
-		return ERR_PTR(err);
+	error = lookup_bdev(path, &dev);
+	if (error)
+		return ERR_PTR(error);
 
-	if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+	bdev = blkdev_get_by_dev(dev, mode, holder);
+	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
 		blkdev_put(bdev, mode);
 		return ERR_PTR(-EACCES);
 	}
@@ -1681,45 +1509,6 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(blkdev_get_by_path);
 
-/**
- * blkdev_get_by_dev - open a block device by device number
- * @dev: device number of block device to open
- * @mode: FMODE_* mask
- * @holder: exclusive holder identifier
- *
- * Open the blockdevice described by device number @dev.  @mode and
- * @holder are identical to blkdev_get().
- *
- * Use it ONLY if you really do not have anything better - i.e. when
- * you are behind a truly sucky interface and all you are given is a
- * device number.  _Never_ to be used for internal purposes.  If you
- * ever need it - reconsider your API.
- *
- * On success, the returned block_device has reference count of one.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * Pointer to block_device on success, ERR_PTR(-errno) on failure.
- */
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
-{
-	struct block_device *bdev;
-	int err;
-
-	bdev = bdget(dev);
-	if (!bdev)
-		return ERR_PTR(-ENOMEM);
-
-	err = blkdev_get(bdev, mode, holder);
-	if (err)
-		return ERR_PTR(err);
-
-	return bdev;
-}
-EXPORT_SYMBOL(blkdev_get_by_dev);
-
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev;
@@ -1741,14 +1530,12 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if ((filp->f_flags & O_ACCMODE) == 3)
 		filp->f_mode |= FMODE_WRITE_IOCTL;
 
-	bdev = bd_acquire(inode);
-	if (bdev == NULL)
-		return -ENOMEM;
-
+	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 	filp->f_mapping = bdev->bd_inode->i_mapping;
 	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
-
-	return blkdev_get(bdev, filp->f_mode, filp);
+	return 0;
 }
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
@@ -1774,34 +1561,28 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
-
 		bdev_write_inode(bdev);
+		if (bdev_is_partition(bdev))
+			victim = bdev_whole(bdev);
 	}
-	if (bdev->bd_contains == bdev) {
-		if (disk->fops->release)
-			disk->fops->release(disk, mode);
-	}
-	if (!bdev->bd_openers) {
-		disk_put_part(bdev->bd_part);
-		bdev->bd_part = NULL;
-		bdev->bd_disk = NULL;
-		if (bdev != bdev->bd_contains)
-			victim = bdev->bd_contains;
-		bdev->bd_contains = NULL;
-
-		put_disk_and_module(disk);
-	}
+
+	if (!bdev_is_partition(bdev) && disk->fops->release)
+		disk->fops->release(disk, mode);
 	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdev);
-	if (victim)
+	if (victim) {
 		__blkdev_put(victim, mode, 1);
+		bdput(victim);
+	}
 }
 
 void blkdev_put(struct block_device *bdev, fmode_t mode)
 {
+	struct gendisk *disk = bdev->bd_disk;
+
 	mutex_lock(&bdev->bd_mutex);
 
 	if (mode & FMODE_EXCL) {
+		struct block_device *whole = bdev_whole(bdev);
 		bool bdev_free;
 
 		/*
@@ -1812,13 +1593,12 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		spin_lock(&bdev_lock);
 
 		WARN_ON_ONCE(--bdev->bd_holders < 0);
-		WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);
+		WARN_ON_ONCE(--whole->bd_holders < 0);
 
-		/* bd_contains might point to self, check in a separate step */
 		if ((bdev_free = !bdev->bd_holders))
 			bdev->bd_holder = NULL;
-		if (!bdev->bd_contains->bd_holders)
-			bdev->bd_contains->bd_holder = NULL;
+		if (!whole->bd_holders)
+			whole->bd_holder = NULL;
 
 		spin_unlock(&bdev_lock);
 
@@ -1827,7 +1607,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		 * unblock evpoll if it was a write holder.
 		 */
 		if (bdev_free && bdev->bd_write_holder) {
-			disk_unblock_events(bdev->bd_disk);
+			disk_unblock_events(disk);
 			bdev->bd_write_holder = false;
 		}
 	}
@@ -1837,11 +1617,11 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	 * event.  This is to ensure detection of media removal commanded
 	 * from userland - e.g. eject(1).
 	 */
-	disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE);
-
+	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
 	mutex_unlock(&bdev->bd_mutex);
 
 	__blkdev_put(bdev, mode, 0);
+	blkdev_put_no_open(bdev);
 }
 EXPORT_SYMBOL(blkdev_put);
 
@@ -2054,37 +1834,32 @@ const struct file_operations def_blk_fops = {
  * namespace if possible and return it.  Return ERR_PTR(error)
  * otherwise.
  */
-struct block_device *lookup_bdev(const char *pathname)
+int lookup_bdev(const char *pathname, dev_t *dev)
 {
-	struct block_device *bdev;
 	struct inode *inode;
 	struct path path;
 	int error;
 
 	if (!pathname || !*pathname)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
 	if (error)
-		return ERR_PTR(error);
+		return error;
 
 	inode = d_backing_inode(path.dentry);
 	error = -ENOTBLK;
 	if (!S_ISBLK(inode->i_mode))
-		goto fail;
+		goto out_path_put;
 	error = -EACCES;
 	if (!may_open_dev(&path))
-		goto fail;
-	error = -ENOMEM;
-	bdev = bd_acquire(inode);
-	if (!bdev)
-		goto fail;
-out:
+		goto out_path_put;
+
+	*dev = inode->i_rdev;
+	error = 0;
+out_path_put:
 	path_put(&path);
-	return bdev;
-fail:
-	bdev = ERR_PTR(error);
-	goto out;
+	return error;
 }
 EXPORT_SYMBOL(lookup_bdev);
 
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4522a1c4cd08..19b9fffa2c9c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1343,8 +1343,6 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 
 void btrfs_sysfs_remove_device(struct btrfs_device *device)
 {
-	struct hd_struct *disk;
-	struct kobject *disk_kobj;
 	struct kobject *devices_kobj;
 
 	/*
@@ -1354,11 +1352,8 @@ void btrfs_sysfs_remove_device(struct btrfs_device *device)
 	devices_kobj = device->fs_info->fs_devices->devices_kobj;
 	ASSERT(devices_kobj);
 
-	if (device->bdev) {
-		disk = device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
-		sysfs_remove_link(devices_kobj, disk_kobj->name);
-	}
+	if (device->bdev)
+		sysfs_remove_link(devices_kobj, bdev_kobj(device->bdev)->name);
 
 	if (device->devid_kobj.state_initialized) {
 		kobject_del(&device->devid_kobj);
@@ -1464,11 +1459,7 @@ int btrfs_sysfs_add_device(struct btrfs_device *device)
 	nofs_flag = memalloc_nofs_save();
 
 	if (device->bdev) {
-		struct hd_struct *disk;
-		struct kobject *disk_kobj;
-
-		disk = device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
+		struct kobject *disk_kobj = bdev_kobj(device->bdev);
 
 		ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name);
 		if (ret) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 7930e1c78c45..ee086fc56c30 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -935,16 +935,16 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		 * make sure it's the same device if the device is mounted
 		 */
 		if (device->bdev) {
-			struct block_device *path_bdev;
+			int error;
+			dev_t path_dev;
 
-			path_bdev = lookup_bdev(path);
-			if (IS_ERR(path_bdev)) {
+			error = lookup_bdev(path, &path_dev);
+			if (error) {
 				mutex_unlock(&fs_devices->device_list_mutex);
-				return ERR_CAST(path_bdev);
+				return ERR_PTR(error);
 			}
 
-			if (device->bdev != path_bdev) {
-				bdput(path_bdev);
+			if (device->bdev->bd_dev != path_dev) {
 				mutex_unlock(&fs_devices->device_list_mutex);
 				/*
 				 * device->fs_info may not be reliable here, so
@@ -959,7 +959,6 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 						  task_pid_nr(current));
 				return ERR_PTR(-EEXIST);
 			}
-			bdput(path_bdev);
 			btrfs_info_in_rcu(device->fs_info,
 	"devid %llu device path %s changed to %s scanned by %s (%d)",
 					  devid, rcu_str_deref(device->name),
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 155545180046..c38846659019 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -165,7 +165,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 	if (!zone_info)
 		return -ENOMEM;
 
-	nr_sectors = bdev->bd_part->nr_sects;
+	nr_sectors = bdev_nr_sectors(bdev);
 	zone_sectors = bdev_zone_sectors(bdev);
 	/* Check if it's power of 2 (see is_power_of_2) */
 	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
@@ -505,7 +505,7 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
 		return -EINVAL;
 	zone_size = zone_sectors << SECTOR_SHIFT;
 	zone_sectors_shift = ilog2(zone_sectors);
-	nr_sectors = bdev->bd_part->nr_sects;
+	nr_sectors = bdev_nr_sectors(bdev);
 	nr_zones = nr_sectors >> zone_sectors_shift;
 
 	sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
@@ -603,7 +603,7 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 
 	zone_sectors = bdev_zone_sectors(bdev);
 	zone_sectors_shift = ilog2(zone_sectors);
-	nr_sectors = bdev->bd_part->nr_sects;
+	nr_sectors = bdev_nr_sectors(bdev);
 	nr_zones = nr_sectors >> zone_sectors_shift;
 
 	sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
diff --git a/fs/buffer.c b/fs/buffer.c
index b56f99f82b5b..32647d2011df 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -523,7 +523,7 @@ repeat:
 
 void emergency_thaw_bdev(struct super_block *sb)
 {
-	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+	while (sb->s_bdev && !thaw_bdev(sb->s_bdev))
 		printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
 }
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index f0381876a7e5..524e13432447 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -624,7 +624,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
 	case EXT4_GOING_FLAGS_DEFAULT:
 		freeze_bdev(sb->s_bdev);
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
-		thaw_bdev(sb->s_bdev, sb);
+		thaw_bdev(sb->s_bdev);
 		break;
 	case EXT4_GOING_FLAGS_LOGFLUSH:
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94472044f4c1..a2ec60fa8811 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4044,9 +4044,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sb_block = sb_block;
-	if (sb->s_bdev->bd_part)
-		sbi->s_sectors_written_start =
-			part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
+	sbi->s_sectors_written_start =
+		part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
 
 	/* Cleanup superblock name */
 	strreplace(sb->s_id, '/', '!');
@@ -5505,15 +5504,10 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	 */
 	if (!(sb->s_flags & SB_RDONLY))
 		ext4_update_tstamp(es, s_wtime);
-	if (sb->s_bdev->bd_part)
-		es->s_kbytes_written =
-			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
-			    ((part_stat_read(sb->s_bdev->bd_part,
-					     sectors[STAT_WRITE]) -
-			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
-	else
-		es->s_kbytes_written =
-			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
+	es->s_kbytes_written =
+		cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+		    ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
+		      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
 		ext4_free_blocks_count_set(es,
 			EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 4e27fe6ed3ae..075aa3a19ff5 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 {
 	struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%lu\n",
-			(part_stat_read(sb->s_bdev->bd_part,
-					sectors[STAT_WRITE]) -
+			(part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
 			 sbi->s_sectors_written_start) >> 1);
 }
 
@@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 {
 	struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)(sbi->s_kbytes_written +
-			((part_stat_read(sb->s_bdev->bd_part,
-					 sectors[STAT_WRITE]) -
+			((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 023462e80e58..54a1905af052 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1395,7 +1395,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u32 crc32 = 0;
 	int i;
 	int cp_payload_blks = __cp_payload(sbi);
-	struct super_block *sb = sbi->sb;
 	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
 	u64 kbytes_written;
 	int err;
@@ -1489,9 +1488,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	start_blk += data_sum_blocks;
 
 	/* Record write statistics in the hot node summary */
-	kbytes_written = sbi->kbytes_written;
-	if (sb->s_bdev->bd_part)
-		kbytes_written += BD_PART_WRITTEN(sbi);
+	kbytes_written = sbi->kbytes_written + BD_PART_WRITTEN(sbi);
 
 	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9a321c52face..9f793923dabe 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1675,7 +1675,7 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
+	(((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) -   \
 		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ee861c6d9ff0..a9fc482a0e60 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2230,16 +2230,12 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
-		sb = freeze_bdev(sb->s_bdev);
-		if (IS_ERR(sb)) {
-			ret = PTR_ERR(sb);
+		ret = freeze_bdev(sb->s_bdev);
+		if (ret)
 			goto out;
-		}
-		if (sb) {
-			f2fs_stop_checkpoint(sbi, false);
-			set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
-			thaw_bdev(sb->s_bdev, sb);
-		}
+		f2fs_stop_checkpoint(sbi, false);
+		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+		thaw_bdev(sb->s_bdev);
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 00eff2f51807..af9f449da64b 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3151,7 +3151,7 @@ static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx,
 static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 {
 	struct block_device *bdev = FDEV(devi).bdev;
-	sector_t nr_sectors = bdev->bd_part->nr_sects;
+	sector_t nr_sectors = bdev_nr_sectors(bdev);
 	struct f2fs_report_zones_args rep_zone_arg;
 	int ret;
 
@@ -3700,10 +3700,8 @@ try_onemore:
 	}
 
 	/* For write statistics */
-	if (sb->s_bdev->bd_part)
-		sbi->sectors_written_start =
-			(u64)part_stat_read(sb->s_bdev->bd_part,
-					    sectors[STAT_WRITE]);
+	sbi->sectors_written_start =
+		(u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index ec77ccfea923..24e876e849c5 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -90,11 +90,6 @@ static ssize_t free_segments_show(struct f2fs_attr *a,
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
-	struct super_block *sb = sbi->sb;
-
-	if (!sb->s_bdev->bd_part)
-		return sprintf(buf, "0\n");
-
 	return sprintf(buf, "%llu\n",
 			(unsigned long long)(sbi->kbytes_written +
 			BD_PART_WRITTEN(sbi)));
@@ -103,12 +98,8 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 static ssize_t features_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
-	struct super_block *sb = sbi->sb;
 	int len = 0;
 
-	if (!sb->s_bdev->bd_part)
-		return sprintf(buf, "0\n");
-
 	if (f2fs_sb_has_encrypt(sbi))
 		len += scnprintf(buf, PAGE_SIZE - len, "%s",
 						"encryption");
diff --git a/fs/inode.c b/fs/inode.c
index 9d78c37b00b8..cb008acf0efd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -155,7 +155,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_bytes = 0;
 	inode->i_generation = 0;
 	inode->i_pipe = NULL;
-	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
 	inode->i_link = NULL;
 	inode->i_dir_seq = 0;
@@ -580,8 +579,6 @@ static void evict(struct inode *inode)
 		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 	}
-	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
-		bd_forget(inode);
 	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
 		cd_forget(inode);
 
diff --git a/fs/internal.h b/fs/internal.h
index 6fd14ea213c3..77c50befbfbe 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -25,7 +25,6 @@ extern void __init bdev_cache_init(void);
 extern int __sync_blockdev(struct block_device *bdev, int wait);
 void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 void emergency_thaw_bdev(struct super_block *sb);
-void bd_forget(struct inode *inode);
 #else
 static inline void bdev_cache_init(void)
 {
@@ -43,9 +42,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb)
 {
 	return 0;
 }
-static inline void bd_forget(struct inode *inode)
-{
-}
 #endif /* CONFIG_BLOCK */
 
 /*
@@ -116,7 +112,8 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
  */
 extern int reconfigure_super(struct fs_context *);
 extern bool trylock_super(struct super_block *sb);
-extern struct super_block *user_get_super(dev_t);
+struct super_block *user_get_super(dev_t, bool excl);
+void put_super(struct super_block *sb);
 extern bool mount_capable(struct fs_context *);
 
 /*
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 22e31050f33e..6f9392c35eef 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2802,11 +2802,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
 
 static bool io_bdev_nowait(struct block_device *bdev)
 {
-#ifdef CONFIG_BLOCK
 	return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
-#else
-	return true;
-#endif
 }
 
 /*
@@ -2819,14 +2815,16 @@ static bool io_file_supports_async(struct file *file, int rw)
 	umode_t mode = file_inode(file)->i_mode;
 
 	if (S_ISBLK(mode)) {
-		if (io_bdev_nowait(file->f_inode->i_bdev))
+		if (IS_ENABLED(CONFIG_BLOCK) &&
+		    io_bdev_nowait(I_BDEV(file->f_mapping->host)))
 			return true;
 		return false;
 	}
 	if (S_ISCHR(mode) || S_ISSOCK(mode))
 		return true;
 	if (S_ISREG(mode)) {
-		if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
+		if (IS_ENABLED(CONFIG_BLOCK) &&
+		    io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
 		    file->f_op != &io_uring_fops)
 			return true;
 		return false;
diff --git a/fs/pipe.c b/fs/pipe.c
index 0ac197658a2d..c5989cfd564d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1342,9 +1342,8 @@ out_revert_acct:
 }
 
 /*
- * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
- * location, so checking ->i_pipe is not enough to verify that this is a
- * pipe.
+ * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is
+ * not enough to verify that this is a pipe.
  */
 struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice)
 {
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index 882d0bc0cfd7..4bb8a344957a 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -244,7 +244,7 @@ static struct block_device *psblk_get_bdev(void *holder,
 			return bdev;
 	}
 
-	nr_sects = part_nr_sects_read(bdev->bd_part);
+	nr_sects = bdev_nr_sectors(bdev);
 	if (!nr_sects) {
 		pr_err("not enough space for '%s'\n", blkdev);
 		blkdev_put(bdev, mode);
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 9af95c7a0bbe..6d16b2be5ac4 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -20,6 +20,7 @@
 #include <linux/writeback.h>
 #include <linux/nospec.h>
 #include "compat.h"
+#include "../internal.h"
 
 static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 				     qid_t id)
@@ -865,27 +866,42 @@ static bool quotactl_cmd_onoff(int cmd)
 static struct super_block *quotactl_block(const char __user *special, int cmd)
 {
 #ifdef CONFIG_BLOCK
-	struct block_device *bdev;
 	struct super_block *sb;
 	struct filename *tmp = getname(special);
+	bool excl = false, thawed = false;
+	int error;
+	dev_t dev;
 
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	bdev = lookup_bdev(tmp->name);
+	error = lookup_bdev(tmp->name, &dev);
 	putname(tmp);
-	if (IS_ERR(bdev))
-		return ERR_CAST(bdev);
-	if (quotactl_cmd_onoff(cmd))
-		sb = get_super_exclusive_thawed(bdev);
-	else if (quotactl_cmd_write(cmd))
-		sb = get_super_thawed(bdev);
-	else
-		sb = get_super(bdev);
-	bdput(bdev);
+	if (error)
+		return ERR_PTR(error);
+
+	if (quotactl_cmd_onoff(cmd)) {
+		excl = true;
+		thawed = true;
+	} else if (quotactl_cmd_write(cmd)) {
+		thawed = true;
+	}
+
+retry:
+	sb = user_get_super(dev, excl);
 	if (!sb)
 		return ERR_PTR(-ENODEV);
-
+	if (thawed && sb->s_writers.frozen != SB_UNFROZEN) {
+		if (excl)
+			up_write(&sb->s_umount);
+		else
+			up_read(&sb->s_umount);
+		wait_event(sb->s_writers.wait_unfrozen,
+			   sb->s_writers.frozen == SB_UNFROZEN);
+		put_super(sb);
+		goto retry;
+	}
 	return sb;
+
 #else
 	return ERR_PTR(-ENODEV);
 #endif
diff --git a/fs/statfs.c b/fs/statfs.c
index 59f33752c131..68cb07788750 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -235,7 +235,7 @@ SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user
 
 static int vfs_ustat(dev_t dev, struct kstatfs *sbuf)
 {
-	struct super_block *s = user_get_super(dev);
+	struct super_block *s = user_get_super(dev, false);
 	int err;
 	if (!s)
 		return -EINVAL;
diff --git a/fs/super.c b/fs/super.c
index 98bb0629ee10..2c6cdea2ab2d 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -307,7 +307,7 @@ static void __put_super(struct super_block *s)
  *	Drops a temporary reference, frees superblock if there's no
  *	references left.
  */
-static void put_super(struct super_block *sb)
+void put_super(struct super_block *sb)
 {
 	spin_lock(&sb_lock);
 	__put_super(sb);
@@ -740,7 +740,14 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-static struct super_block *__get_super(struct block_device *bdev, bool excl)
+/**
+ * get_super - get the superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device given. %NULL is returned if no match is found.
+ */
+struct super_block *get_super(struct block_device *bdev)
 {
 	struct super_block *sb;
 
@@ -755,17 +762,11 @@ rescan:
 		if (sb->s_bdev == bdev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			if (!excl)
-				down_read(&sb->s_umount);
-			else
-				down_write(&sb->s_umount);
+			down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			if (!excl)
-				up_read(&sb->s_umount);
-			else
-				up_write(&sb->s_umount);
+			up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -777,66 +778,6 @@ rescan:
 }
 
 /**
- *	get_super - get the superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device given. %NULL is returned if no match is found.
- */
-struct super_block *get_super(struct block_device *bdev)
-{
-	return __get_super(bdev, false);
-}
-EXPORT_SYMBOL(get_super);
-
-static struct super_block *__get_super_thawed(struct block_device *bdev,
-					      bool excl)
-{
-	while (1) {
-		struct super_block *s = __get_super(bdev, excl);
-		if (!s || s->s_writers.frozen == SB_UNFROZEN)
-			return s;
-		if (!excl)
-			up_read(&s->s_umount);
-		else
-			up_write(&s->s_umount);
-		wait_event(s->s_writers.wait_unfrozen,
-			   s->s_writers.frozen == SB_UNFROZEN);
-		put_super(s);
-	}
-}
-
-/**
- *	get_super_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen). %NULL is returned if no match
- *	is found.
- */
-struct super_block *get_super_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, false);
-}
-EXPORT_SYMBOL(get_super_thawed);
-
-/**
- *	get_super_exclusive_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen) and s_umount semaphore is held
- *	in exclusive mode. %NULL is returned if no match is found.
- */
-struct super_block *get_super_exclusive_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, true);
-}
-EXPORT_SYMBOL(get_super_exclusive_thawed);
-
-/**
  * get_active_super - get an active reference to the superblock of a device
  * @bdev: device to get the superblock for
  *
@@ -867,7 +808,7 @@ restart:
 	return NULL;
 }
 
-struct super_block *user_get_super(dev_t dev)
+struct super_block *user_get_super(dev_t dev, bool excl)
 {
 	struct super_block *sb;
 
@@ -879,11 +820,17 @@ rescan:
 		if (sb->s_dev ==  dev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			down_read(&sb->s_umount);
+			if (excl)
+				down_write(&sb->s_umount);
+			else
+				down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			up_read(&sb->s_umount);
+			if (excl)
+				up_write(&sb->s_umount);
+			else
+				up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ef1d5bb88b93..b7c5783a031c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -433,13 +433,10 @@ xfs_fs_goingdown(
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
-		struct super_block *sb = freeze_bdev(mp->m_super->s_bdev);
-
-		if (sb && !IS_ERR(sb)) {
+		if (!freeze_bdev(mp->m_super->s_bdev)) {
 			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
-			thaw_bdev(sb->s_bdev, sb);
+			thaw_bdev(mp->m_super->s_bdev);
 		}
-
 		break;
 	}
 	case XFS_FSOP_GOING_FLAGS_LOGFLUSH: