Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Good amount of cleanups and tech debt removals in here, and as a
  result, the diffstat shows a nice net reduction in code.

   - Softirq completion cleanups (Christoph)

   - Stop using ->queuedata (Christoph)

   - Cleanup bd claiming (Christoph)

   - Use check_events, moving away from the legacy media change
     (Christoph)

   - Use inode i_blkbits consistently (Christoph)

   - Remove old unused writeback congestion bits (Christoph)

   - Cleanup/unify submission path (Christoph)

   - Use bio_uninit consistently, instead of bio_disassociate_blkg
     (Christoph)

   - sbitmap cleared bits handling (John)

   - Request merging blktrace event addition (Jan)

   - sysfs add/remove race fixes (Luis)

   - blk-mq tag fixes/optimizations (Ming)

   - Duplicate words in comments (Randy)

   - Flush deferral cleanup (Yufen)

   - IO context locking/retry fixes (John)

   - struct_size() usage (Gustavo)

   - blk-iocost fixes (Chengming)

   - blk-cgroup IO stats fixes (Boris)

   - Various little fixes"

* tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits)
  block: blk-timeout: delete duplicated word
  block: blk-mq-sched: delete duplicated word
  block: blk-mq: delete duplicated word
  block: genhd: delete duplicated words
  block: elevator: delete duplicated word and fix typos
  block: bio: delete duplicated words
  block: bfq-iosched: fix duplicated word
  iocost_monitor: start from the oldest usage index
  iocost: Fix check condition of iocg abs_vdebt
  block: Remove callback typedefs for blk_mq_ops
  block: Use non _rcu version of list functions for tag_set_list
  blk-cgroup: show global disk stats in root cgroup io.stat
  blk-cgroup: make iostat functions visible to stat printing
  block: improve discard bio alignment in __blkdev_issue_discard()
  block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers
  block: defer flush request no matter whether we have elevator
  block: make blk_timeout_init() static
  block: remove retry loop in ioc_release_fn()
  block: remove unnecessary ioc nested locking
  block: integrate bd_start_claiming into __blkdev_get
  ...

18 files changed, 128 insertions, 251 deletions

diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index a3cc8ecb50da..d553bb5bc17a 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/user_namespace.h>
+#include <linux/blkdev.h>
 #include "adfs.h"
 #include "dir_f.h"
 #include "dir_fplus.h"
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a85817f54483..a26a0f96c119 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/uio.h>
+#include <linux/blkdev.h>
 #include "affs.h"
 
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 64cdf4d8e424..2482032021ca 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -22,6 +22,7 @@
 #include <linux/cred.h>
 #include <linux/exportfs.h>
 #include <linux/seq_file.h>
+#include <linux/blkdev.h>
 
 #include "befs.h"
 #include "btree.h"
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0ae656e022fd..3f94a06a0946 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -105,16 +105,7 @@ EXPORT_SYMBOL(invalidate_bdev);
 
 static void set_init_blocksize(struct block_device *bdev)
 {
-	unsigned bsize = bdev_logical_block_size(bdev);
-	loff_t size = i_size_read(bdev->bd_inode);
-
-	while (bsize < PAGE_SIZE) {
-		if (size & bsize)
-			break;
-		bsize <<= 1;
-	}
-	bdev->bd_block_size = bsize;
-	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
 }
 
 int set_blocksize(struct block_device *bdev, int size)
@@ -128,9 +119,8 @@ int set_blocksize(struct block_device *bdev, int size)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
-	if (bdev->bd_block_size != size) {
+	if (bdev->bd_inode->i_blkbits != blksize_bits(size)) {
 		sync_blockdev(bdev);
-		bdev->bd_block_size = size;
 		bdev->bd_inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
 	}
@@ -703,12 +693,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return result;
 
-	result = blk_queue_enter(bdev->bd_queue, 0);
+	result = blk_queue_enter(bdev->bd_disk->queue, 0);
 	if (result)
 		return result;
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
 			      REQ_OP_READ);
-	blk_queue_exit(bdev->bd_queue);
+	blk_queue_exit(bdev->bd_disk->queue);
 	return result;
 }
 
@@ -739,7 +729,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
-	result = blk_queue_enter(bdev->bd_queue, 0);
+	result = blk_queue_enter(bdev->bd_disk->queue, 0);
 	if (result)
 		return result;
 
@@ -752,7 +742,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		clean_page_buffers(page);
 		unlock_page(page);
 	}
-	blk_queue_exit(bdev->bd_queue);
+	blk_queue_exit(bdev->bd_disk->queue);
 	return result;
 }
 
@@ -783,7 +773,6 @@ static void init_once(void *foo)
 
 	memset(bdev, 0, sizeof(*bdev));
 	mutex_init(&bdev->bd_mutex);
-	INIT_LIST_HEAD(&bdev->bd_list);
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
@@ -799,9 +788,6 @@ static void bdev_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
 	clear_inode(inode);
-	spin_lock(&bdev_lock);
-	list_del_init(&bdev->bd_list);
-	spin_unlock(&bdev_lock);
 	/* Detach inode from wb early as bdi_put() may free bdi->wb */
 	inode_detach_wb(inode);
 	if (bdev->bd_bdi != &noop_backing_dev_info) {
@@ -876,8 +862,6 @@ static int bdev_set(struct inode *inode, void *data)
 	return 0;
 }
 
-static LIST_HEAD(all_bdevs);
-
 struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
@@ -895,7 +879,6 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;
@@ -903,9 +886,6 @@ struct block_device *bdget(dev_t dev)
 		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		spin_lock(&bdev_lock);
-		list_add(&bdev->bd_list, &all_bdevs);
-		spin_unlock(&bdev_lock);
 		unlock_new_inode(inode);
 	}
 	return bdev;
@@ -926,13 +906,14 @@ EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
-	struct block_device *bdev;
+	struct inode *inode;
 	long ret = 0;
-	spin_lock(&bdev_lock);
-	list_for_each_entry(bdev, &all_bdevs, bd_list) {
-		ret += bdev->bd_inode->i_mapping->nrpages;
-	}
-	spin_unlock(&bdev_lock);
+
+	spin_lock(&blockdev_superblock->s_inode_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list)
+		ret += inode->i_mapping->nrpages;
+	spin_unlock(&blockdev_superblock->s_inode_list_lock);
+
 	return ret;
 }
 
@@ -1034,30 +1015,28 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 }
 
 /**
- * bd_prepare_to_claim - prepare to claim a block device
+ * 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
  *
- * Prepare to claim @bdev.  This function fails if @bdev is already
- * claimed by another holder and waits if another claiming is in
- * progress.  This function doesn't actually claim.  On successful
- * return, the caller has ownership of bd_claiming and bd_holder[s].
- *
- * CONTEXT:
- * spin_lock(&bdev_lock).  Might release bdev_lock, sleep and regrab
- * it multiple times.
+ * Claim @bdev.  This function fails if @bdev is already claimed by another
+ * holder and waits if another claiming is in progress. return, the caller
+ * has ownership of bd_claiming and bd_holder[s].
  *
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-static int bd_prepare_to_claim(struct block_device *bdev,
-			       struct block_device *whole, void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
+		void *holder)
 {
 retry:
+	spin_lock(&bdev_lock);
 	/* if someone else claimed, fail */
-	if (!bd_may_claim(bdev, whole, holder))
+	if (!bd_may_claim(bdev, whole, holder)) {
+		spin_unlock(&bdev_lock);
 		return -EBUSY;
+	}
 
 	/* if claiming is already in progress, wait for it to finish */
 	if (whole->bd_claiming) {
@@ -1068,13 +1047,15 @@ retry:
 		spin_unlock(&bdev_lock);
 		schedule();
 		finish_wait(wq, &wait);
-		spin_lock(&bdev_lock);
 		goto retry;
 	}
 
 	/* yay, all mine */
+	whole->bd_claiming = holder;
+	spin_unlock(&bdev_lock);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
 
 static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
 {
@@ -1097,78 +1078,6 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
 	return disk;
 }
 
-/**
- * bd_start_claiming - start claiming a block device
- * @bdev: block device of interest
- * @holder: holder trying to claim @bdev
- *
- * @bdev is about to be opened exclusively.  Check @bdev can be opened
- * exclusively and mark that an exclusive open is in progress.  Each
- * successful call to this function must be matched with a call to
- * either bd_finish_claiming() or bd_abort_claiming() (which do not
- * fail).
- *
- * This function is used to gain exclusive access to the block device
- * without actually causing other exclusive open attempts to fail. It
- * should be used when the open sequence itself requires exclusive
- * access but may subsequently fail.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * Pointer to the block device containing @bdev on success, ERR_PTR()
- * value on failure.
- */
-struct block_device *bd_start_claiming(struct block_device *bdev, void *holder)
-{
-	struct gendisk *disk;
-	struct block_device *whole;
-	int partno, err;
-
-	might_sleep();
-
-	/*
-	 * @bdev might not have been initialized properly yet, look up
-	 * and grab the outer block device the hard way.
-	 */
-	disk = bdev_get_gendisk(bdev, &partno);
-	if (!disk)
-		return ERR_PTR(-ENXIO);
-
-	/*
-	 * Normally, @bdev should equal what's returned from bdget_disk()
-	 * if partno is 0; however, some drivers (floppy) use multiple
-	 * bdev's for the same physical device and @bdev may be one of the
-	 * aliases.  Keep @bdev if partno is 0.  This means claimer
-	 * tracking is broken for those devices but it has always been that
-	 * way.
-	 */
-	if (partno)
-		whole = bdget_disk(disk, 0);
-	else
-		whole = bdgrab(bdev);
-
-	put_disk_and_module(disk);
-	if (!whole)
-		return ERR_PTR(-ENOMEM);
-
-	/* prepare to claim, if successful, mark claiming in progress */
-	spin_lock(&bdev_lock);
-
-	err = bd_prepare_to_claim(bdev, whole, holder);
-	if (err == 0) {
-		whole->bd_claiming = holder;
-		spin_unlock(&bdev_lock);
-		return whole;
-	} else {
-		spin_unlock(&bdev_lock);
-		bdput(whole);
-		return ERR_PTR(err);
-	}
-}
-EXPORT_SYMBOL(bd_start_claiming);
-
 static void bd_clear_claiming(struct block_device *whole, void *holder)
 {
 	lockdep_assert_held(&bdev_lock);
@@ -1181,14 +1090,14 @@ 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 (returned from bd_start_claiming())
+ * @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.
  */
-void bd_finish_claiming(struct block_device *bdev, struct block_device *whole,
-			void *holder)
+static void bd_finish_claiming(struct block_device *bdev,
+		struct block_device *whole, void *holder)
 {
 	spin_lock(&bdev_lock);
 	BUG_ON(!bd_may_claim(bdev, whole, holder));
@@ -1203,12 +1112,11 @@ void bd_finish_claiming(struct block_device *bdev, struct block_device *whole,
 	bd_clear_claiming(whole, holder);
 	spin_unlock(&bdev_lock);
 }
-EXPORT_SYMBOL(bd_finish_claiming);
 
 /**
  * bd_abort_claiming - abort claiming of a block device
  * @bdev: block device of interest
- * @whole: whole block device (returned from bd_start_claiming())
+ * @whole: whole block device
  * @holder: holder that has claimed @bdev
  *
  * Abort claiming of a block device when the exclusive open failed. This can be
@@ -1368,26 +1276,6 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 #endif
 
 /**
- * flush_disk - invalidates all buffer-cache entries on a disk
- *
- * @bdev:      struct block device to be flushed
- * @kill_dirty: flag to guide handling of dirty inodes
- *
- * Invalidates all buffer-cache entries on a disk. It should be called
- * when a disk has been changed -- either by a media change or online
- * resize.
- */
-static void flush_disk(struct block_device *bdev, bool kill_dirty)
-{
-	if (__invalidate_device(bdev, kill_dirty)) {
-		printk(KERN_WARNING "VFS: busy inodes on changed media or "
-		       "resized disk %s\n",
-		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
-	}
-	bdev->bd_invalidated = 1;
-}
-
-/**
  * check_disk_size_change - checks for disk size change and adjusts bdev size.
  * @disk: struct gendisk to check
  * @bdev: struct bdev to adjust.
@@ -1411,8 +1299,9 @@ static void check_disk_size_change(struct gendisk *disk,
 			       disk->disk_name, bdev_size, disk_size);
 		}
 		i_size_write(bdev->bd_inode, disk_size);
-		if (bdev_size > disk_size)
-			flush_disk(bdev, false);
+		if (bdev_size > disk_size && __invalidate_device(bdev, false))
+			pr_warn("VFS: busy inodes on resized disk %s\n",
+				disk->disk_name);
 	}
 	bdev->bd_invalidated = 0;
 }
@@ -1471,7 +1360,10 @@ int check_disk_change(struct block_device *bdev)
 	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return 0;
 
-	flush_disk(bdev, true);
+	if (__invalidate_device(bdev, true))
+		pr_warn("VFS: busy inodes on changed media %s\n",
+			disk->disk_name);
+	bdev->bd_invalidated = 1;
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
 	return 1;
@@ -1547,13 +1439,15 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
 
-static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
+		int for_part)
 {
+	struct block_device *whole = NULL, *claiming = NULL;
 	struct gendisk *disk;
 	int ret;
 	int partno;
 	int perm = 0;
-	bool first_open = false;
+	bool first_open = false, unblock_events = true, need_restart;
 
 	if (mode & FMODE_READ)
 		perm |= MAY_READ;
@@ -1569,18 +1463,36 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	}
 
  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;
+	}
+
 	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_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		bdev->bd_partno = partno;
 
@@ -1593,20 +1505,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			ret = 0;
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev, mode);
-				if (ret == -ERESTARTSYS) {
-					/* Lost a race with 'disk' being
-					 * deleted, try again.
-					 * See md.c
-					 */
-					disk_put_part(bdev->bd_part);
-					bdev->bd_part = NULL;
-					bdev->bd_disk = NULL;
-					bdev->bd_queue = NULL;
-					mutex_unlock(&bdev->bd_mutex);
-					disk_unblock_events(disk);
-					put_disk_and_module(disk);
-					goto restart;
-				}
+				/*
+				 * If we lost a race with 'disk' being deleted,
+				 * try again.  See md.c
+				 */
+				if (ret == -ERESTARTSYS)
+					need_restart = true;
 			}
 
 			if (!ret) {
@@ -1627,18 +1531,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_clear;
 		} else {
-			struct block_device *whole;
-			whole = bdget_disk(disk, 0);
-			ret = -ENOMEM;
-			if (!whole)
-				goto out_clear;
 			BUG_ON(for_part);
-			ret = __blkdev_get(whole, mode, 1);
-			if (ret) {
-				bdput(whole);
+			ret = __blkdev_get(whole, mode, NULL, 1);
+			if (ret)
 				goto out_clear;
-			}
-			bdev->bd_contains = whole;
+			bdev->bd_contains = bdgrab(whole);
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1667,27 +1564,52 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_openers++;
 	if (for_part)
 		bdev->bd_part_count++;
+	if (claiming)
+		bd_finish_claiming(bdev, claiming, holder);
+
+	/*
+	 * 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);
-	disk_unblock_events(disk);
+
+	if (unblock_events)
+		disk_unblock_events(disk);
+
 	/* only one opener holds refs to the module and disk */
 	if (!first_open)
 		put_disk_and_module(disk);
+	if (whole)
+		bdput(whole);
 	return 0;
 
  out_clear:
 	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
-	bdev->bd_queue = 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;
 }
 
@@ -1712,50 +1634,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  */
 int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
-	struct block_device *whole = NULL;
 	int res;
 
-	WARN_ON_ONCE((mode & FMODE_EXCL) && !holder);
-
-	if ((mode & FMODE_EXCL) && holder) {
-		whole = bd_start_claiming(bdev, holder);
-		if (IS_ERR(whole)) {
-			bdput(bdev);
-			return PTR_ERR(whole);
-		}
-	}
-
-	res = __blkdev_get(bdev, mode, 0);
-
-	if (whole) {
-		struct gendisk *disk = whole->bd_disk;
-
-		/* finish claiming */
-		mutex_lock(&bdev->bd_mutex);
-		if (!res)
-			bd_finish_claiming(bdev, whole, holder);
-		else
-			bd_abort_claiming(bdev, whole, holder);
-		/*
-		 * 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 (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
-		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
-			bdev->bd_write_holder = true;
-			disk_block_events(disk);
-		}
-
-		mutex_unlock(&bdev->bd_mutex);
-		bdput(whole);
-	}
-
+	res =__blkdev_get(bdev, mode, holder, 0);
 	if (res)
 		bdput(bdev);
-
 	return res;
 }
 EXPORT_SYMBOL(blkdev_get);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c850d7f44fbe..9ae25f632157 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1677,27 +1677,6 @@ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
 	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
 }
 
-static int btrfs_congested_fn(void *congested_data, int bdi_bits)
-{
-	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
-	int ret = 0;
-	struct btrfs_device *device;
-	struct backing_dev_info *bdi;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
-		if (!device->bdev)
-			continue;
-		bdi = device->bdev->bd_bdi;
-		if (bdi_congested(bdi, bdi_bits)) {
-			ret = 1;
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 /*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
@@ -3112,8 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->congested_fn = btrfs_congested_fn;
-	sb->s_bdi->congested_data = fs_info;
 	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
 	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
diff --git a/fs/buffer.c b/fs/buffer.c
index dc5e05b47646..061dd202979d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3039,10 +3039,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 	if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
 		clear_buffer_write_io_error(bh);
 
-	/*
-	 * from here on down, it's all bio -- do the initial mapping,
-	 * submit_bio -> generic_make_request may further map this bio around
-	 */
 	bio = bio_alloc(GFP_NOIO, 1);
 
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 6d5370eac2a8..183299892465 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1387,8 +1387,8 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 * Attempt to prefetch the pieces we likely need later.
 	 */
 	prefetch(&bdev->bd_disk->part_tbl);
-	prefetch(bdev->bd_queue);
-	prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
+	prefetch(bdev->bd_disk->queue);
+	prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES);
 
 	return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block,
 				     end_io, submit_io, flags);
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 4a6ebff2af76..a4a945d0ac6a 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
+#include <linux/blkdev.h>
 
 #include "efs.h"
 #include <linux/efs_vh.h>
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2f224b98ee94..f35a37c65e5f 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -17,6 +17,7 @@
 #include <linux/cred.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
+#include <linux/blkdev.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/internal.h b/fs/internal.h
index 9b863a7bd708..969988d3d397 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -23,7 +23,9 @@ struct user_namespace;
 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)
 {
@@ -33,7 +35,18 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 {
 	return 0;
 }
-#endif
+static inline void iterate_bdevs(void (*f)(struct block_device *, void *),
+		void *arg)
+{
+}
+static inline int emergency_thaw_bdev(struct super_block *sb)
+{
+	return 0;
+}
+static inline void bd_forget(struct inode *inode)
+{
+}
+#endif /* CONFIG_BLOCK */
 
 /*
  * buffer.c
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d634561f871a..78f5c96c76f3 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -612,9 +612,6 @@ static bool rootdir_empty(struct super_block *sb, unsigned long block)
 
 /*
  * Initialize the superblock and read the root inode.
- *
- * Note: a check_disk_change() has been done immediately prior
- * to this call, so we don't need to check again.
  */
 static int isofs_fill_super(struct super_block *s, void *data, int silent)
 {
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index eb8b9e233d73..2935d4c776ec 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -36,6 +36,7 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 66acea9d878b..bde787c354fc 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -6,6 +6,7 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
 #include "jfs_metapage.h"
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 3c4811469ae8..a87d4391e6b5 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -8,6 +8,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 
 #include "dir.h"
 #include "aops.h"
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
index 37d38697eaf8..837971e74109 100644
--- a/fs/proc/devices.c
+++ b/fs/proc/devices.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/blkdev.h>
 
 static int devinfo_show(struct seq_file *f, void *v)
 {
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 7b4bac91146b..bb02989d92b6 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -78,6 +78,7 @@
 #include <linux/namei.h>
 #include <linux/capability.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 #include "../internal.h" /* ugh */
 
 #include <linux/uaccess.h>
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index ff336513c254..155b82870333 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -15,6 +15,7 @@
 #include "reiserfs.h"
 #include <linux/init.h>
 #include <linux/proc_fs.h>
+#include <linux/blkdev.h>
 
 /*
  * LOCKING:
diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c
index 4bcc3e61056c..b03333f1c84a 100644
--- a/fs/xfs/xfs_pwork.c
+++ b/fs/xfs/xfs_pwork.c
@@ -132,5 +132,5 @@ xfs_pwork_guess_datadev_parallelism(
 	 * For now we'll go with the most conservative setting possible,
 	 * which is two threads for an SSD and 1 thread everywhere else.
 	 */
-	return blk_queue_nonrot(btp->bt_bdev->bd_queue) ? 2 : 1;
+	return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1;
 }