1 files changed, 265 insertions, 490 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);