Merge branch 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block: (43 commits)
  block: ensure that completion error gets properly traced
  blktrace: add missing probe argument to block_bio_complete
  block cfq: don't use atomic_t for cfq_group
  block cfq: don't use atomic_t for cfq_queue
  block: trace event block fix unassigned field
  block: add internal hd part table references
  block: fix accounting bug on cross partition merges
  kref: add kref_test_and_get
  bio-integrity: mark kintegrityd_wq highpri and CPU intensive
  block: make kblockd_workqueue smarter
  Revert "sd: implement sd_check_events()"
  block: Clean up exit_io_context() source code.
  Fix compile warnings due to missing removal of a 'ret' variable
  fs/block: type signature of major_to_index(int) to major_to_index(unsigned)
  block: convert !IS_ERR(p) && p to !IS_ERR_NOR_NULL(p)
  cfq-iosched: don't check cfqg in choose_service_tree()
  fs/splice: Pull buf->ops->confirm() from splice_from_pipe actors
  cdrom: export cdrom_check_events()
  sd: implement sd_check_events()
  sr: implement sr_check_events()
  ...

18 files changed, 347 insertions, 698 deletions

diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 4d0ff5ee27b8..e49cce234c65 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -782,7 +782,12 @@ void __init bio_integrity_init(void)
 {
 	unsigned int i;
 
-	kintegrityd_wq = create_workqueue("kintegrityd");
+	/*
+	 * kintegrityd won't block much but may burn a lot of CPU cycles.
+	 * Make it highpri CPU intensive wq with max concurrency of 1.
+	 */
+	kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
+					 WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
 	if (!kintegrityd_wq)
 		panic("Failed to create kintegrityd\n");
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 88da70355aa3..fe3f59c14a02 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -432,9 +432,6 @@ static void init_once(void *foo)
 	mutex_init(&bdev->bd_mutex);
 	INIT_LIST_HEAD(&bdev->bd_inodes);
 	INIT_LIST_HEAD(&bdev->bd_list);
-#ifdef CONFIG_SYSFS
-	INIT_LIST_HEAD(&bdev->bd_holder_list);
-#endif
 	inode_init_once(&ei->vfs_inode);
 	/* Initialize mutex for freeze. */
 	mutex_init(&bdev->bd_fsfreeze_mutex);
@@ -669,7 +666,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 	else if (bdev->bd_contains == bdev)
 		return true;  	 /* is a whole device which isn't held */
 
-	else if (whole->bd_holder == bd_claim)
+	else if (whole->bd_holder == bd_may_claim)
 		return true; 	 /* is a partition of a device that is being partitioned */
 	else if (whole->bd_holder != NULL)
 		return false;	 /* is a partition of a held device */
@@ -781,439 +778,87 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 	}
 }
 
-/* releases bdev_lock */
-static void __bd_abort_claiming(struct block_device *whole, void *holder)
-{
-	BUG_ON(whole->bd_claiming != holder);
-	whole->bd_claiming = NULL;
-	wake_up_bit(&whole->bd_claiming, 0);
-
-	spin_unlock(&bdev_lock);
-	bdput(whole);
-}
-
-/**
- * bd_abort_claiming - abort claiming a block device
- * @whole: whole block device returned by bd_start_claiming()
- * @holder: holder trying to claim @bdev
- *
- * Abort a claiming block started by bd_start_claiming().  Note that
- * @whole is not the block device to be claimed but the whole device
- * returned by bd_start_claiming().
- *
- * CONTEXT:
- * Grabs and releases bdev_lock.
- */
-static void bd_abort_claiming(struct block_device *whole, void *holder)
-{
-	spin_lock(&bdev_lock);
-	__bd_abort_claiming(whole, holder);		/* releases bdev_lock */
-}
-
-/* increment holders when we have a legitimate claim. requires bdev_lock */
-static void __bd_claim(struct block_device *bdev, struct block_device *whole,
-					void *holder)
-{
-	/* note that for a whole device bd_holders
-	 * will be incremented twice, and bd_holder will
-	 * be set to bd_claim before being set to holder
-	 */
-	whole->bd_holders++;
-	whole->bd_holder = bd_claim;
-	bdev->bd_holders++;
-	bdev->bd_holder = holder;
-}
-
-/**
- * bd_finish_claiming - finish claiming a block device
- * @bdev: block device of interest (passed to bd_start_claiming())
- * @whole: whole block device returned by bd_start_claiming()
- * @holder: holder trying to claim @bdev
- *
- * Finish a claiming block started by bd_start_claiming().
- *
- * CONTEXT:
- * Grabs and releases bdev_lock.
- */
-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));
-	__bd_claim(bdev, whole, holder);
-	__bd_abort_claiming(whole, holder); /* not actually an abort */
-}
-
-/**
- * bd_claim - claim a block device
- * @bdev: block device to claim
- * @holder: holder trying to claim @bdev
- *
- * Try to claim @bdev which must have been opened successfully.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * 0 if successful, -EBUSY if @bdev is already claimed.
- */
-int bd_claim(struct block_device *bdev, void *holder)
-{
-	struct block_device *whole = bdev->bd_contains;
-	int res;
-
-	might_sleep();
-
-	spin_lock(&bdev_lock);
-	res = bd_prepare_to_claim(bdev, whole, holder);
-	if (res == 0)
-		__bd_claim(bdev, whole, holder);
-	spin_unlock(&bdev_lock);
-
-	return res;
-}
-EXPORT_SYMBOL(bd_claim);
-
-void bd_release(struct block_device *bdev)
-{
-	spin_lock(&bdev_lock);
-	if (!--bdev->bd_contains->bd_holders)
-		bdev->bd_contains->bd_holder = NULL;
-	if (!--bdev->bd_holders)
-		bdev->bd_holder = NULL;
-	spin_unlock(&bdev_lock);
-}
-
-EXPORT_SYMBOL(bd_release);
-
 #ifdef CONFIG_SYSFS
-/*
- * Functions for bd_claim_by_kobject / bd_release_from_kobject
- *
- *     If a kobject is passed to bd_claim_by_kobject()
- *     and the kobject has a parent directory,
- *     following symlinks are created:
- *        o from the kobject to the claimed bdev
- *        o from "holders" directory of the bdev to the parent of the kobject
- *     bd_release_from_kobject() removes these symlinks.
- *
- *     Example:
- *        If /dev/dm-0 maps to /dev/sda, kobject corresponding to
- *        /sys/block/dm-0/slaves is passed to bd_claim_by_kobject(), then:
- *           /sys/block/dm-0/slaves/sda --> /sys/block/sda
- *           /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
- */
-
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
-	if (!from || !to)
-		return 0;
 	return sysfs_create_link(from, to, kobject_name(to));
 }
 
 static void del_symlink(struct kobject *from, struct kobject *to)
 {
-	if (!from || !to)
-		return;
 	sysfs_remove_link(from, kobject_name(to));
 }
 
-/*
- * 'struct bd_holder' contains pointers to kobjects symlinked by
- * bd_claim_by_kobject.
- * It's connected to bd_holder_list which is protected by bdev->bd_sem.
- */
-struct bd_holder {
-	struct list_head list;	/* chain of holders of the bdev */
-	int count;		/* references from the holder */
-	struct kobject *sdir;	/* holder object, e.g. "/block/dm-0/slaves" */
-	struct kobject *hdev;	/* e.g. "/block/dm-0" */
-	struct kobject *hdir;	/* e.g. "/block/sda/holders" */
-	struct kobject *sdev;	/* e.g. "/block/sda" */
-};
-
-/*
- * Get references of related kobjects at once.
- * Returns 1 on success. 0 on failure.
- *
- * Should call bd_holder_release_dirs() after successful use.
- */
-static int bd_holder_grab_dirs(struct block_device *bdev,
-			struct bd_holder *bo)
-{
-	if (!bdev || !bo)
-		return 0;
-
-	bo->sdir = kobject_get(bo->sdir);
-	if (!bo->sdir)
-		return 0;
-
-	bo->hdev = kobject_get(bo->sdir->parent);
-	if (!bo->hdev)
-		goto fail_put_sdir;
-
-	bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
-	if (!bo->sdev)
-		goto fail_put_hdev;
-
-	bo->hdir = kobject_get(bdev->bd_part->holder_dir);
-	if (!bo->hdir)
-		goto fail_put_sdev;
-
-	return 1;
-
-fail_put_sdev:
-	kobject_put(bo->sdev);
-fail_put_hdev:
-	kobject_put(bo->hdev);
-fail_put_sdir:
-	kobject_put(bo->sdir);
-
-	return 0;
-}
-
-/* Put references of related kobjects at once. */
-static void bd_holder_release_dirs(struct bd_holder *bo)
-{
-	kobject_put(bo->hdir);
-	kobject_put(bo->sdev);
-	kobject_put(bo->hdev);
-	kobject_put(bo->sdir);
-}
-
-static struct bd_holder *alloc_bd_holder(struct kobject *kobj)
-{
-	struct bd_holder *bo;
-
-	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-	if (!bo)
-		return NULL;
-
-	bo->count = 1;
-	bo->sdir = kobj;
-
-	return bo;
-}
-
-static void free_bd_holder(struct bd_holder *bo)
-{
-	kfree(bo);
-}
-
 /**
- * find_bd_holder - find matching struct bd_holder from the block device
+ * bd_link_disk_holder - create symlinks between holding disk and slave bdev
+ * @bdev: the claimed slave bdev
+ * @disk: the holding disk
  *
- * @bdev:	struct block device to be searched
- * @bo:		target struct bd_holder
- *
- * Returns matching entry with @bo in @bdev->bd_holder_list.
- * If found, increment the reference count and return the pointer.
- * If not found, returns NULL.
- */
-static struct bd_holder *find_bd_holder(struct block_device *bdev,
-					struct bd_holder *bo)
-{
-	struct bd_holder *tmp;
-
-	list_for_each_entry(tmp, &bdev->bd_holder_list, list)
-		if (tmp->sdir == bo->sdir) {
-			tmp->count++;
-			return tmp;
-		}
-
-	return NULL;
-}
-
-/**
- * add_bd_holder - create sysfs symlinks for bd_claim() relationship
- *
- * @bdev:	block device to be bd_claimed
- * @bo:		preallocated and initialized by alloc_bd_holder()
- *
- * Add @bo to @bdev->bd_holder_list, create symlinks.
- *
- * Returns 0 if symlinks are created.
- * Returns -ve if something fails.
- */
-static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
-{
-	int err;
-
-	if (!bo)
-		return -EINVAL;
-
-	if (!bd_holder_grab_dirs(bdev, bo))
-		return -EBUSY;
-
-	err = add_symlink(bo->sdir, bo->sdev);
-	if (err)
-		return err;
-
-	err = add_symlink(bo->hdir, bo->hdev);
-	if (err) {
-		del_symlink(bo->sdir, bo->sdev);
-		return err;
-	}
-
-	list_add_tail(&bo->list, &bdev->bd_holder_list);
-	return 0;
-}
-
-/**
- * del_bd_holder - delete sysfs symlinks for bd_claim() relationship
+ * This functions creates the following sysfs symlinks.
  *
- * @bdev:	block device to be bd_claimed
- * @kobj:	holder's kobject
+ * - from "slaves" directory of the holder @disk to the claimed @bdev
+ * - from "holders" directory of the @bdev to the holder @disk
  *
- * If there is matching entry with @kobj in @bdev->bd_holder_list
- * and no other bd_claim() from the same kobject,
- * remove the struct bd_holder from the list, delete symlinks for it.
+ * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
+ * passed to bd_link_disk_holder(), then:
  *
- * Returns a pointer to the struct bd_holder when it's removed from the list
- * and ready to be freed.
- * Returns NULL if matching claim isn't found or there is other bd_claim()
- * by the same kobject.
- */
-static struct bd_holder *del_bd_holder(struct block_device *bdev,
-					struct kobject *kobj)
-{
-	struct bd_holder *bo;
-
-	list_for_each_entry(bo, &bdev->bd_holder_list, list) {
-		if (bo->sdir == kobj) {
-			bo->count--;
-			BUG_ON(bo->count < 0);
-			if (!bo->count) {
-				list_del(&bo->list);
-				del_symlink(bo->sdir, bo->sdev);
-				del_symlink(bo->hdir, bo->hdev);
-				bd_holder_release_dirs(bo);
-				return bo;
-			}
-			break;
-		}
-	}
-
-	return NULL;
-}
-
-/**
- * bd_claim_by_kobject - bd_claim() with additional kobject signature
+ *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
+ *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
  *
- * @bdev:	block device to be claimed
- * @holder:	holder's signature
- * @kobj:	holder's kobject
+ * The caller must have claimed @bdev before calling this function and
+ * ensure that both @bdev and @disk are valid during the creation and
+ * lifetime of these symlinks.
  *
- * Do bd_claim() and if it succeeds, create sysfs symlinks between
- * the bdev and the holder's kobject.
- * Use bd_release_from_kobject() when relesing the claimed bdev.
+ * CONTEXT:
+ * Might sleep.
  *
- * Returns 0 on success. (same as bd_claim())
- * Returns errno on failure.
+ * RETURNS:
+ * 0 on success, -errno on failure.
  */
-static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
-				struct kobject *kobj)
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 {
-	int err;
-	struct bd_holder *bo, *found;
-
-	if (!kobj)
-		return -EINVAL;
-
-	bo = alloc_bd_holder(kobj);
-	if (!bo)
-		return -ENOMEM;
+	int ret = 0;
 
 	mutex_lock(&bdev->bd_mutex);
 
-	err = bd_claim(bdev, holder);
-	if (err)
-		goto fail;
+	WARN_ON_ONCE(!bdev->bd_holder || bdev->bd_holder_disk);
 
-	found = find_bd_holder(bdev, bo);
-	if (found)
-		goto fail;
+	/* FIXME: remove the following once add_disk() handles errors */
+	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
+		goto out_unlock;
 
-	err = add_bd_holder(bdev, bo);
-	if (err)
-		bd_release(bdev);
-	else
-		bo = NULL;
-fail:
-	mutex_unlock(&bdev->bd_mutex);
-	free_bd_holder(bo);
-	return err;
-}
+	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	if (ret)
+		goto out_unlock;
 
-/**
- * bd_release_from_kobject - bd_release() with additional kobject signature
- *
- * @bdev:	block device to be released
- * @kobj:	holder's kobject
- *
- * Do bd_release() and remove sysfs symlinks created by bd_claim_by_kobject().
- */
-static void bd_release_from_kobject(struct block_device *bdev,
-					struct kobject *kobj)
-{
-	if (!kobj)
-		return;
+	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	if (ret) {
+		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+		goto out_unlock;
+	}
 
-	mutex_lock(&bdev->bd_mutex);
-	bd_release(bdev);
-	free_bd_holder(del_bd_holder(bdev, kobj));
+	bdev->bd_holder_disk = disk;
+out_unlock:
 	mutex_unlock(&bdev->bd_mutex);
+	return ret;
 }
+EXPORT_SYMBOL_GPL(bd_link_disk_holder);
 
-/**
- * bd_claim_by_disk - wrapper function for bd_claim_by_kobject()
- *
- * @bdev:	block device to be claimed
- * @holder:	holder's signature
- * @disk:	holder's gendisk
- *
- * Call bd_claim_by_kobject() with getting @disk->slave_dir.
- */
-int bd_claim_by_disk(struct block_device *bdev, void *holder,
-			struct gendisk *disk)
+static void bd_unlink_disk_holder(struct block_device *bdev)
 {
-	return bd_claim_by_kobject(bdev, holder, kobject_get(disk->slave_dir));
-}
-EXPORT_SYMBOL_GPL(bd_claim_by_disk);
+	struct gendisk *disk = bdev->bd_holder_disk;
 
-/**
- * bd_release_from_disk - wrapper function for bd_release_from_kobject()
- *
- * @bdev:	block device to be claimed
- * @disk:	holder's gendisk
- *
- * Call bd_release_from_kobject() and put @disk->slave_dir.
- */
-void bd_release_from_disk(struct block_device *bdev, struct gendisk *disk)
-{
-	bd_release_from_kobject(bdev, disk->slave_dir);
-	kobject_put(disk->slave_dir);
-}
-EXPORT_SYMBOL_GPL(bd_release_from_disk);
-#endif
+	bdev->bd_holder_disk = NULL;
+	if (!disk)
+		return;
 
-/*
- * Tries to open block device by device number.  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.
- */
-struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
-{
-	struct block_device *bdev = bdget(dev);
-	int err = -ENOMEM;
-	if (bdev)
-		err = blkdev_get(bdev, mode);
-	return err ? ERR_PTR(err) : bdev;
+	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
 }
-
-EXPORT_SYMBOL(open_by_devnum);
+#else
+static inline void bd_unlink_disk_holder(struct block_device *bdev)
+{ }
+#endif
 
 /**
  * flush_disk - invalidates all buffer-cache entries on a disk
@@ -1309,10 +954,11 @@ int check_disk_change(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	const struct block_device_operations *bdops = disk->fops;
+	unsigned int events;
 
-	if (!bdops->media_changed)
-		return 0;
-	if (!bdops->media_changed(bdev->bd_disk))
+	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
+				   DISK_EVENT_EJECT_REQUEST);
+	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return 0;
 
 	flush_disk(bdev);
@@ -1475,17 +1121,171 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	return ret;
 }
 
-int blkdev_get(struct block_device *bdev, fmode_t mode)
+/**
+ * blkdev_get - open a block device
+ * @bdev: 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.
+ *
+ * On success, the reference count of @bdev is unchanged.  On failure,
+ * @bdev is put.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
-	return __blkdev_get(bdev, mode, 0);
+	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);
+
+	/* __blkdev_get() may alter read only status, check it afterwards */
+	if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+		__blkdev_put(bdev, mode, 0);
+		res = -EACCES;
+	}
+
+	if (whole) {
+		/* finish claiming */
+		mutex_lock(&bdev->bd_mutex);
+		spin_lock(&bdev_lock);
+
+		if (!res) {
+			BUG_ON(!bd_may_claim(bdev, whole, holder));
+			/*
+			 * Note that for a whole device bd_holders
+			 * will be incremented twice, and bd_holder
+			 * will be set to bd_may_claim before being
+			 * set to holder
+			 */
+			whole->bd_holders++;
+			whole->bd_holder = bd_may_claim;
+			bdev->bd_holders++;
+			bdev->bd_holder = holder;
+		}
+
+		/* tell others that we're done */
+		BUG_ON(whole->bd_claiming != holder);
+		whole->bd_claiming = NULL;
+		wake_up_bit(&whole->bd_claiming, 0);
+
+		spin_unlock(&bdev_lock);
+
+		/*
+		 * Block event polling for write claims.  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) {
+			bdev->bd_write_holder = true;
+			disk_block_events(bdev->bd_disk);
+		}
+
+		mutex_unlock(&bdev->bd_mutex);
+		bdput(whole);
+	}
+
+	return res;
 }
 EXPORT_SYMBOL(blkdev_get);
 
+/**
+ * blkdev_get_by_path - open a block device by name
+ * @path: path to the block device to open
+ * @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.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to 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;
+
+	err = blkdev_get(bdev, mode, holder);
+	if (err)
+		return ERR_PTR(err);
+
+	return bdev;
+}
+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 *whole = NULL;
 	struct block_device *bdev;
-	int res;
 
 	/*
 	 * Preserve backwards compatibility and allow large file access
@@ -1506,26 +1306,9 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if (bdev == NULL)
 		return -ENOMEM;
 
-	if (filp->f_mode & FMODE_EXCL) {
-		whole = bd_start_claiming(bdev, filp);
-		if (IS_ERR(whole)) {
-			bdput(bdev);
-			return PTR_ERR(whole);
-		}
-	}
-
 	filp->f_mapping = bdev->bd_inode->i_mapping;
 
-	res = blkdev_get(bdev, filp->f_mode);
-
-	if (whole) {
-		if (res == 0)
-			bd_finish_claiming(bdev, whole, filp);
-		else
-			bd_abort_claiming(whole, filp);
-	}
-
-	return res;
+	return blkdev_get(bdev, filp->f_mode, filp);
 }
 
 static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
@@ -1539,6 +1322,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_part_count--;
 
 	if (!--bdev->bd_openers) {
+		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
 	}
@@ -1569,6 +1353,45 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 
 int blkdev_put(struct block_device *bdev, fmode_t mode)
 {
+	if (mode & FMODE_EXCL) {
+		bool bdev_free;
+
+		/*
+		 * Release a claim on the device.  The holder fields
+		 * are protected with bdev_lock.  bd_mutex is to
+		 * synchronize disk_holder unlinking.
+		 */
+		mutex_lock(&bdev->bd_mutex);
+		spin_lock(&bdev_lock);
+
+		WARN_ON_ONCE(--bdev->bd_holders < 0);
+		WARN_ON_ONCE(--bdev->bd_contains->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;
+
+		spin_unlock(&bdev_lock);
+
+		/*
+		 * If this was the last claim, remove holder link and
+		 * unblock evpoll if it was a write holder.
+		 */
+		if (bdev_free) {
+			bd_unlink_disk_holder(bdev);
+			if (bdev->bd_write_holder) {
+				disk_unblock_events(bdev->bd_disk);
+				bdev->bd_write_holder = false;
+			} else
+				disk_check_events(bdev->bd_disk);
+		}
+
+		mutex_unlock(&bdev->bd_mutex);
+	} else
+		disk_check_events(bdev->bd_disk);
+
 	return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
@@ -1576,8 +1399,7 @@ EXPORT_SYMBOL(blkdev_put);
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
-	if (bdev->bd_holder == filp)
-		bd_release(bdev);
+
 	return blkdev_put(bdev, filp->f_mode);
 }
 
@@ -1722,67 +1544,6 @@ fail:
 }
 EXPORT_SYMBOL(lookup_bdev);
 
-/**
- * open_bdev_exclusive  -  open a block device by name and set it up for use
- *
- * @path:	special file representing the block device
- * @mode:	FMODE_... combination to pass be used
- * @holder:	owner for exclusion
- *
- * Open the blockdevice described by the special file at @path, claim it
- * for the @holder.
- */
-struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
-{
-	struct block_device *bdev, *whole;
-	int error;
-
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev))
-		return bdev;
-
-	whole = bd_start_claiming(bdev, holder);
-	if (IS_ERR(whole)) {
-		bdput(bdev);
-		return whole;
-	}
-
-	error = blkdev_get(bdev, mode);
-	if (error)
-		goto out_abort_claiming;
-
-	error = -EACCES;
-	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
-		goto out_blkdev_put;
-
-	bd_finish_claiming(bdev, whole, holder);
-	return bdev;
-
-out_blkdev_put:
-	blkdev_put(bdev, mode);
-out_abort_claiming:
-	bd_abort_claiming(whole, holder);
-	return ERR_PTR(error);
-}
-
-EXPORT_SYMBOL(open_bdev_exclusive);
-
-/**
- * close_bdev_exclusive  -  close a blockdevice opened by open_bdev_exclusive()
- *
- * @bdev:	blockdevice to close
- * @mode:	mode, must match that used to open.
- *
- * This is the counterpart to open_bdev_exclusive().
- */
-void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
-{
-	bd_release(bdev);
-	blkdev_put(bdev, mode);
-}
-
-EXPORT_SYMBOL(close_bdev_exclusive);
-
 int __invalidate_device(struct block_device *bdev)
 {
 	struct super_block *sb = get_super(bdev);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6b9884507837..1718e1a5c320 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -493,7 +493,7 @@ again:
 			continue;
 
 		if (device->bdev) {
-			close_bdev_exclusive(device->bdev, device->mode);
+			blkdev_put(device->bdev, device->mode);
 			device->bdev = NULL;
 			fs_devices->open_devices--;
 		}
@@ -527,7 +527,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		if (device->bdev) {
-			close_bdev_exclusive(device->bdev, device->mode);
+			blkdev_put(device->bdev, device->mode);
 			fs_devices->open_devices--;
 		}
 		if (device->writeable) {
@@ -584,13 +584,15 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	int seeding = 1;
 	int ret = 0;
 
+	flags |= FMODE_EXCL;
+
 	list_for_each_entry(device, head, dev_list) {
 		if (device->bdev)
 			continue;
 		if (!device->name)
 			continue;
 
-		bdev = open_bdev_exclusive(device->name, flags, holder);
+		bdev = blkdev_get_by_path(device->name, flags, holder);
 		if (IS_ERR(bdev)) {
 			printk(KERN_INFO "open %s failed\n", device->name);
 			goto error;
@@ -642,7 +644,7 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 error_brelse:
 		brelse(bh);
 error_close:
-		close_bdev_exclusive(bdev, FMODE_READ);
+		blkdev_put(bdev, flags);
 error:
 		continue;
 	}
@@ -688,7 +690,8 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 	mutex_lock(&uuid_mutex);
 
-	bdev = open_bdev_exclusive(path, flags, holder);
+	flags |= FMODE_EXCL;
+	bdev = blkdev_get_by_path(path, flags, holder);
 
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
@@ -720,7 +723,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 	brelse(bh);
 error_close:
-	close_bdev_exclusive(bdev, flags);
+	blkdev_put(bdev, flags);
 error:
 	mutex_unlock(&uuid_mutex);
 	return ret;
@@ -1183,8 +1186,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 			goto out;
 		}
 	} else {
-		bdev = open_bdev_exclusive(device_path, FMODE_READ,
-				      root->fs_info->bdev_holder);
+		bdev = blkdev_get_by_path(device_path, FMODE_READ | FMODE_EXCL,
+					  root->fs_info->bdev_holder);
 		if (IS_ERR(bdev)) {
 			ret = PTR_ERR(bdev);
 			goto out;
@@ -1251,7 +1254,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
 	if (device->bdev) {
-		close_bdev_exclusive(device->bdev, device->mode);
+		blkdev_put(device->bdev, device->mode);
 		device->bdev = NULL;
 		device->fs_devices->open_devices--;
 	}
@@ -1294,7 +1297,7 @@ error_brelse:
 	brelse(bh);
 error_close:
 	if (bdev)
-		close_bdev_exclusive(bdev, FMODE_READ);
+		blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
 	mutex_unlock(&uuid_mutex);
@@ -1446,7 +1449,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
 		return -EINVAL;
 
-	bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder);
+	bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+				  root->fs_info->bdev_holder);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
@@ -1572,7 +1576,7 @@ out:
 	mutex_unlock(&root->fs_info->volume_mutex);
 	return ret;
 error:
-	close_bdev_exclusive(bdev, 0);
+	blkdev_put(bdev, FMODE_EXCL);
 	if (seeding_dev) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2740db49eb04..1be781079450 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -50,7 +50,7 @@ struct btrfs_device {
 
 	struct block_device *bdev;
 
-	/* the mode sent to open_bdev_exclusive */
+	/* the mode sent to blkdev_get */
 	fmode_t mode;
 
 	char *name;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 6e99b9ddd4e9..dca9e5e0f73b 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -59,7 +59,7 @@ static struct char_device_struct {
 } *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
 
 /* index in the above */
-static inline int major_to_index(int major)
+static inline int major_to_index(unsigned major)
 {
 	return major % CHRDEV_MAJOR_HASH_SIZE;
 }
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index b7d0554631e4..7aa767d4f06f 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -364,7 +364,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
 	struct block_device *bdev;
 	char b[BDEVNAME_SIZE];
 
-	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
 	if (IS_ERR(bdev))
 		goto fail;
 	return bdev;
@@ -381,8 +381,7 @@ fail:
  */
 static int ext3_blkdev_put(struct block_device *bdev)
 {
-	bd_release(bdev);
-	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
@@ -2162,13 +2161,6 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 	if (bdev == NULL)
 		return NULL;
 
-	if (bd_claim(bdev, sb)) {
-		ext3_msg(sb, KERN_ERR,
-			"error: failed to claim external journal device");
-		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
-		return NULL;
-	}
-
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 29c80f6d8b27..cb10a06775e4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -657,7 +657,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
 	struct block_device *bdev;
 	char b[BDEVNAME_SIZE];
 
-	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
 	if (IS_ERR(bdev))
 		goto fail;
 	return bdev;
@@ -673,8 +673,7 @@ fail:
  */
 static int ext4_blkdev_put(struct block_device *bdev)
 {
-	bd_release(bdev);
-	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -3778,13 +3777,6 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	if (bdev == NULL)
 		return NULL;
 
-	if (bd_claim(bdev, sb)) {
-		ext4_msg(sb, KERN_ERR,
-			"failed to claim external journal device");
-		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
-		return NULL;
-	}
-
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 693f4470a2df..777927ce6f79 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1268,7 +1268,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 {
 	struct block_device *bdev;
 	struct super_block *s;
-	fmode_t mode = FMODE_READ;
+	fmode_t mode = FMODE_READ | FMODE_EXCL;
 	int error;
 	struct gfs2_args args;
 	struct gfs2_sbd *sdp;
@@ -1276,7 +1276,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	if (!(flags & MS_RDONLY))
 		mode |= FMODE_WRITE;
 
-	bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+	bdev = blkdev_get_by_path(dev_name, mode, fs_type);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
@@ -1298,7 +1298,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 		goto error_bdev;
 
 	if (s->s_root)
-		close_bdev_exclusive(bdev, mode);
+		blkdev_put(bdev, mode);
 
 	memset(&args, 0, sizeof(args));
 	args.ar_quota = GFS2_QUOTA_DEFAULT;
@@ -1342,7 +1342,7 @@ error_super:
 	deactivate_locked_super(s);
 	return ERR_PTR(error);
 error_bdev:
-	close_bdev_exclusive(bdev, mode);
+	blkdev_put(bdev, mode);
 	return ERR_PTR(error);
 }
 
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index e1b8493b9aaa..278e3fb40b71 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1120,16 +1120,13 @@ int lmLogOpen(struct super_block *sb)
 	 * file systems to log may have n-to-1 relationship;
 	 */
 
-	bdev = open_by_devnum(sbi->logdev, FMODE_READ|FMODE_WRITE);
+	bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+				 log);
 	if (IS_ERR(bdev)) {
 		rc = -PTR_ERR(bdev);
 		goto free;
 	}
 
-	if ((rc = bd_claim(bdev, log))) {
-		goto close;
-	}
-
 	log->bdev = bdev;
 	memcpy(log->uuid, sbi->loguuid, sizeof(log->uuid));
 
@@ -1137,7 +1134,7 @@ int lmLogOpen(struct super_block *sb)
 	 * initialize log:
 	 */
 	if ((rc = lmLogInit(log)))
-		goto unclaim;
+		goto close;
 
 	list_add(&log->journal_list, &jfs_external_logs);
 
@@ -1163,11 +1160,8 @@ journal_found:
 	list_del(&log->journal_list);
 	lbmLogShutdown(log);
 
-      unclaim:
-	bd_release(bdev);
-
       close:		/* close external log device */
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
       free:		/* free log descriptor */
 	mutex_unlock(&jfs_log_mutex);
@@ -1512,8 +1506,7 @@ int lmLogClose(struct super_block *sb)
 	bdev = log->bdev;
 	rc = lmLogShutdown(log);
 
-	bd_release(bdev);
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
 	kfree(log);
 
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 92ca6fbe09bd..723bc5bca09a 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -300,7 +300,7 @@ static int bdev_write_sb(struct super_block *sb, struct page *page)
 
 static void bdev_put_device(struct logfs_super *s)
 {
-	close_bdev_exclusive(s->s_bdev, FMODE_READ|FMODE_WRITE);
+	blkdev_put(s->s_bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
@@ -325,13 +325,14 @@ int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type,
 {
 	struct block_device *bdev;
 
-	bdev = open_bdev_exclusive(devname, FMODE_READ|FMODE_WRITE, type);
+	bdev = blkdev_get_by_path(devname, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+				  type);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
 	if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
 		int mtdnr = MINOR(bdev->bd_dev);
-		close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 		return logfs_get_sb_mtd(p, mtdnr);
 	}
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 3a359023c9f7..230b79fbf005 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -845,11 +845,6 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
 	struct page *page = buf->page;
 	size_t size;
-	int ret;
-
-	ret = buf->ops->confirm(pipe, buf);
-	if (unlikely(ret))
-		return ret;
 
 	size = sd->len;
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 70dfdd532b83..0994f6a76c07 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1163,14 +1163,14 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 {
 	struct nilfs_super_data sd;
 	struct super_block *s;
-	fmode_t mode = FMODE_READ;
+	fmode_t mode = FMODE_READ | FMODE_EXCL;
 	struct dentry *root_dentry;
 	int err, s_new = false;
 
 	if (!(flags & MS_RDONLY))
 		mode |= FMODE_WRITE;
 
-	sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+	sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type);
 	if (IS_ERR(sd.bdev))
 		return ERR_CAST(sd.bdev);
 
@@ -1249,7 +1249,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 	}
 
 	if (!s_new)
-		close_bdev_exclusive(sd.bdev, mode);
+		blkdev_put(sd.bdev, mode);
 
 	return root_dentry;
 
@@ -1258,7 +1258,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 
  failed:
 	if (!s_new)
-		close_bdev_exclusive(sd.bdev, mode);
+		blkdev_put(sd.bdev, mode);
 	return ERR_PTR(err);
 }
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a6cc05302e9f..b108e863d8f6 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1729,7 +1729,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		goto out;
 
 	reg->hr_bdev = I_BDEV(filp->f_mapping->host);
-	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ);
+	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, NULL);
 	if (ret) {
 		reg->hr_bdev = NULL;
 		goto out;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 0a8b0ad0c7e2..9c21119512b9 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -237,6 +237,13 @@ ssize_t part_size_show(struct device *dev,
 	return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
+ssize_t part_ro_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	return sprintf(buf, "%d\n", p->policy ? 1 : 0);
+}
+
 ssize_t part_alignment_offset_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
@@ -312,6 +319,7 @@ ssize_t part_fail_store(struct device *dev,
 static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
 		   NULL);
@@ -326,6 +334,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_partition.attr,
 	&dev_attr_start.attr,
 	&dev_attr_size.attr,
+	&dev_attr_ro.attr,
 	&dev_attr_alignment_offset.attr,
 	&dev_attr_discard_alignment.attr,
 	&dev_attr_stat.attr,
@@ -372,6 +381,11 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
 	put_device(part_to_dev(part));
 }
 
+void __delete_partition(struct hd_struct *part)
+{
+	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
+}
+
 void delete_partition(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = disk->part_tbl;
@@ -390,7 +404,7 @@ void delete_partition(struct gendisk *disk, int partno)
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
-	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
+	hd_struct_put(part);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -489,6 +503,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
+	hd_ref_init(p);
 	return p;
 
 out_free_info:
@@ -507,65 +522,6 @@ out_put:
 	return ERR_PTR(err);
 }
 
-/* Not exported, helper to add_disk(). */
-void register_disk(struct gendisk *disk)
-{
-	struct device *ddev = disk_to_dev(disk);
-	struct block_device *bdev;
-	struct disk_part_iter piter;
-	struct hd_struct *part;
-	int err;
-
-	ddev->parent = disk->driverfs_dev;
-
-	dev_set_name(ddev, disk->disk_name);
-
-	/* delay uevents, until we scanned partition table */
-	dev_set_uevent_suppress(ddev, 1);
-
-	if (device_add(ddev))
-		return;
-	if (!sysfs_deprecated) {
-		err = sysfs_create_link(block_depr, &ddev->kobj,
-					kobject_name(&ddev->kobj));
-		if (err) {
-			device_del(ddev);
-			return;
-		}
-	}
-	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
-	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
-
-	/* No minors to use for partitions */
-	if (!disk_partitionable(disk))
-		goto exit;
-
-	/* No such device (e.g., media were just removed) */
-	if (!get_capacity(disk))
-		goto exit;
-
-	bdev = bdget_disk(disk, 0);
-	if (!bdev)
-		goto exit;
-
-	bdev->bd_invalidated = 1;
-	err = blkdev_get(bdev, FMODE_READ);
-	if (err < 0)
-		goto exit;
-	blkdev_put(bdev, FMODE_READ);
-
-exit:
-	/* announce disk after possible partitions are created */
-	dev_set_uevent_suppress(ddev, 0);
-	kobject_uevent(&ddev->kobj, KOBJ_ADD);
-
-	/* announce possible partitions */
-	disk_part_iter_init(&piter, disk, 0);
-	while ((part = disk_part_iter_next(&piter)))
-		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
-	disk_part_iter_exit(&piter);
-}
-
 static bool disk_unlock_native_capacity(struct gendisk *disk)
 {
 	const struct block_device_operations *bdops = disk->fops;
@@ -728,33 +684,3 @@ fail:
 }
 
 EXPORT_SYMBOL(read_dev_sector);
-
-void del_gendisk(struct gendisk *disk)
-{
-	struct disk_part_iter piter;
-	struct hd_struct *part;
-
-	/* invalidate stuff */
-	disk_part_iter_init(&piter, disk,
-			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
-	while ((part = disk_part_iter_next(&piter))) {
-		invalidate_partition(disk, part->partno);
-		delete_partition(disk, part->partno);
-	}
-	disk_part_iter_exit(&piter);
-
-	invalidate_partition(disk, 0);
-	blk_free_devt(disk_to_dev(disk)->devt);
-	set_capacity(disk, 0);
-	disk->flags &= ~GENHD_FL_UP;
-	unlink_gendisk(disk);
-	part_stat_set_all(&disk->part0, 0);
-	disk->part0.stamp = 0;
-
-	kobject_put(disk->part0.holder_dir);
-	kobject_put(disk->slave_dir);
-	disk->driverfs_dev = NULL;
-	if (!sysfs_deprecated)
-		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
-	device_del(disk_to_dev(disk));
-}
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index d31bce1a9f90..3eea859e6990 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2551,8 +2551,6 @@ static int release_journal_dev(struct super_block *super,
 	result = 0;
 
 	if (journal->j_dev_bd != NULL) {
-		if (journal->j_dev_bd->bd_dev != super->s_dev)
-			bd_release(journal->j_dev_bd);
 		result = blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
 		journal->j_dev_bd = NULL;
 	}
@@ -2570,7 +2568,7 @@ static int journal_init_dev(struct super_block *super,
 {
 	int result;
 	dev_t jdev;
-	fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE;
+	fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
 	char b[BDEVNAME_SIZE];
 
 	result = 0;
@@ -2584,7 +2582,10 @@ static int journal_init_dev(struct super_block *super,
 
 	/* there is no "jdev" option and journal is on separate device */
 	if ((!jdev_name || !jdev_name[0])) {
-		journal->j_dev_bd = open_by_devnum(jdev, blkdev_mode);
+		if (jdev == super->s_dev)
+			blkdev_mode &= ~FMODE_EXCL;
+		journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode,
+						      journal);
 		journal->j_dev_mode = blkdev_mode;
 		if (IS_ERR(journal->j_dev_bd)) {
 			result = PTR_ERR(journal->j_dev_bd);
@@ -2593,22 +2594,14 @@ static int journal_init_dev(struct super_block *super,
 					 "cannot init journal device '%s': %i",
 					 __bdevname(jdev, b), result);
 			return result;
-		} else if (jdev != super->s_dev) {
-			result = bd_claim(journal->j_dev_bd, journal);
-			if (result) {
-				blkdev_put(journal->j_dev_bd, blkdev_mode);
-				return result;
-			}
-
+		} else if (jdev != super->s_dev)
 			set_blocksize(journal->j_dev_bd, super->s_blocksize);
-		}
 
 		return 0;
 	}
 
 	journal->j_dev_mode = blkdev_mode;
-	journal->j_dev_bd = open_bdev_exclusive(jdev_name,
-						blkdev_mode, journal);
+	journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, journal);
 	if (IS_ERR(journal->j_dev_bd)) {
 		result = PTR_ERR(journal->j_dev_bd);
 		journal->j_dev_bd = NULL;
diff --git a/fs/splice.c b/fs/splice.c
index ce2f02579e35..50a5d978da16 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -682,19 +682,14 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 {
 	struct file *file = sd->u.file;
 	loff_t pos = sd->pos;
-	int ret, more;
-
-	ret = buf->ops->confirm(pipe, buf);
-	if (!ret) {
-		more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
-		if (file->f_op && file->f_op->sendpage)
-			ret = file->f_op->sendpage(file, buf->page, buf->offset,
-						   sd->len, &pos, more);
-		else
-			ret = -EINVAL;
-	}
+	int more;
 
-	return ret;
+	if (!likely(file->f_op && file->f_op->sendpage))
+		return -EINVAL;
+
+	more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
+	return file->f_op->sendpage(file, buf->page, buf->offset,
+				    sd->len, &pos, more);
 }
 
 /*
@@ -727,13 +722,6 @@ int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	void *fsdata;
 	int ret;
 
-	/*
-	 * make sure the data in this buffer is uptodate
-	 */
-	ret = buf->ops->confirm(pipe, buf);
-	if (unlikely(ret))
-		return ret;
-
 	offset = sd->pos & ~PAGE_CACHE_MASK;
 
 	this_len = sd->len;
@@ -805,12 +793,17 @@ int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
 		if (sd->len > sd->total_len)
 			sd->len = sd->total_len;
 
-		ret = actor(pipe, buf, sd);
-		if (ret <= 0) {
+		ret = buf->ops->confirm(pipe, buf);
+		if (unlikely(ret)) {
 			if (ret == -ENODATA)
 				ret = 0;
 			return ret;
 		}
+
+		ret = actor(pipe, buf, sd);
+		if (ret <= 0)
+			return ret;
+
 		buf->offset += ret;
 		buf->len -= ret;
 
@@ -1044,10 +1037,6 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	int ret;
 	void *data;
 
-	ret = buf->ops->confirm(pipe, buf);
-	if (ret)
-		return ret;
-
 	data = buf->ops->map(pipe, buf, 0);
 	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
 	buf->ops->unmap(pipe, buf, data);
@@ -1495,10 +1484,6 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	char *src;
 	int ret;
 
-	ret = buf->ops->confirm(pipe, buf);
-	if (unlikely(ret))
-		return ret;
-
 	/*
 	 * See if we can use the atomic maps, by prefaulting in the
 	 * pages and doing an atomic copy
diff --git a/fs/super.c b/fs/super.c
index 823e061faa87..4f6a3571a634 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -767,13 +767,13 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 {
 	struct block_device *bdev;
 	struct super_block *s;
-	fmode_t mode = FMODE_READ;
+	fmode_t mode = FMODE_READ | FMODE_EXCL;
 	int error = 0;
 
 	if (!(flags & MS_RDONLY))
 		mode |= FMODE_WRITE;
 
-	bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+	bdev = blkdev_get_by_path(dev_name, mode, fs_type);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
@@ -802,13 +802,13 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 
 		/*
 		 * s_umount nests inside bd_mutex during
-		 * __invalidate_device().  close_bdev_exclusive()
-		 * acquires bd_mutex and can't be called under
-		 * s_umount.  Drop s_umount temporarily.  This is safe
-		 * as we're holding an active reference.
+		 * __invalidate_device().  blkdev_put() acquires
+		 * bd_mutex and can't be called under s_umount.  Drop
+		 * s_umount temporarily.  This is safe as we're
+		 * holding an active reference.
 		 */
 		up_write(&s->s_umount);
-		close_bdev_exclusive(bdev, mode);
+		blkdev_put(bdev, mode);
 		down_write(&s->s_umount);
 	} else {
 		char b[BDEVNAME_SIZE];
@@ -832,7 +832,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 error_s:
 	error = PTR_ERR(s);
 error_bdev:
-	close_bdev_exclusive(bdev, mode);
+	blkdev_put(bdev, mode);
 error:
 	return ERR_PTR(error);
 }
@@ -863,7 +863,8 @@ void kill_block_super(struct super_block *sb)
 	bdev->bd_super = NULL;
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
-	close_bdev_exclusive(bdev, mode);
+	WARN_ON_ONCE(!(mode & FMODE_EXCL));
+	blkdev_put(bdev, mode | FMODE_EXCL);
 }
 
 EXPORT_SYMBOL(kill_block_super);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index a10f6416e563..bd07f7339366 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -606,7 +606,8 @@ xfs_blkdev_get(
 {
 	int			error = 0;
 
-	*bdevp = open_bdev_exclusive(name, FMODE_READ|FMODE_WRITE, mp);
+	*bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+				    mp);
 	if (IS_ERR(*bdevp)) {
 		error = PTR_ERR(*bdevp);
 		printk("XFS: Invalid device [%s], error=%d\n", name, error);
@@ -620,7 +621,7 @@ xfs_blkdev_put(
 	struct block_device	*bdev)
 {
 	if (bdev)
-		close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 /*