block: make blkdev_get/put() handle exclusive access

Over time, block layer has accumulated a set of APIs dealing with bdev
open, close, claim and release.

* blkdev_get/put() are the primary open and close functions.

* bd_claim/release() deal with exclusive open.

* open/close_bdev_exclusive() are combination of open and claim and
  the other way around, respectively.

* bd_link/unlink_disk_holder() to create and remove holder/slave
  symlinks.

* open_by_devnum() wraps bdget() + blkdev_get().

The interface is a bit confusing and the decoupling of open and claim
makes it impossible to properly guarantee exclusive access as
in-kernel open + claim sequence can disturb the existing exclusive
open even before the block layer knows the current open if for another
exclusive access.  Reorganize the interface such that,

* blkdev_get() is extended to include exclusive access management.
  @holder argument is added and, if is @FMODE_EXCL specified, it will
  gain exclusive access atomically w.r.t. other exclusive accesses.

* blkdev_put() is similarly extended.  It now takes @mode argument and
  if @FMODE_EXCL is set, it releases an exclusive access.  Also, when
  the last exclusive claim is released, the holder/slave symlinks are
  removed automatically.

* bd_claim/release() and close_bdev_exclusive() are no longer
  necessary and either made static or removed.

* bd_link_disk_holder() remains the same but bd_unlink_disk_holder()
  is no longer necessary and removed.

* open_bdev_exclusive() becomes a simple wrapper around lookup_bdev()
  and blkdev_get().  It also has an unexpected extra bdev_read_only()
  test which probably should be moved into blkdev_get().

* open_by_devnum() is modified to take @holder argument and pass it to
  blkdev_get().

Most of bdev open/close operations are unified into blkdev_get/put()
and most exclusive accesses are tested atomically at the open time (as
it should).  This cleans up code and removes some, both valid and
invalid, but unnecessary all the same, corner cases.

open_bdev_exclusive() and open_by_devnum() can use further cleanup -
rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop
special features.  Well, let's leave them for another day.

Most conversions are straight-forward.  drbd conversion is a bit more
involved as there was some reordering, but the logic should stay the
same.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Neil Brown <neilb@suse.de>
Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <joel.becker@oracle.com>
Cc: Alex Elder <aelder@sgi.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: dm-devel@redhat.com
Cc: drbd-dev@lists.linbit.com
Cc: Leo Chen <leochen@broadcom.com>
Cc: Scott Branden <sbranden@broadcom.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Joern Engel <joern@logfs.org>
Cc: reiserfs-devel@vger.kernel.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>

13 files changed, 87 insertions, 166 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9329068684d2..fc48912354d1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -660,7 +660,7 @@ 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 */
@@ -807,10 +807,10 @@ static void __bd_claim(struct block_device *bdev, struct block_device *whole,
 {
         /* 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
+         * be set to bd_may_claim before being set to holder
          */
         whole->bd_holders++;
-        whole->bd_holder = bd_claim;
+        whole->bd_holder = bd_may_claim;
         bdev->bd_holders++;
         bdev->bd_holder = holder;
 }
@@ -835,37 +835,7 @@ static void bd_finish_claiming(struct block_device *bdev,
         __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)
+static void bd_release(struct block_device *bdev)
 {
         spin_lock(&bdev_lock);
         if (!--bdev->bd_contains->bd_holders)
@@ -875,8 +845,6 @@ void bd_release(struct block_device *bdev)
         spin_unlock(&bdev_lock);
 }
 
-EXPORT_SYMBOL(bd_release);
-
 #ifdef CONFIG_SYSFS
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
@@ -943,7 +911,7 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(bd_link_disk_holder);
 
-void bd_unlink_disk_holder(struct block_device *bdev)
+static void bd_unlink_disk_holder(struct block_device *bdev)
 {
         struct gendisk *disk = bdev->bd_holder_disk;
 
@@ -954,7 +922,9 @@ void bd_unlink_disk_holder(struct block_device *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_GPL(bd_unlink_disk_holder);
+#else
+static inline void bd_unlink_disk_holder(struct block_device *bdev)
+{ }
 #endif
 
 /*
@@ -964,12 +934,12 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
  * 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 *open_by_devnum(dev_t dev, fmode_t mode, void *holder)
 {
         struct block_device *bdev = bdget(dev);
         int err = -ENOMEM;
         if (bdev)
-                err = blkdev_get(bdev, mode);
+                err = blkdev_get(bdev, mode, holder);
         return err ? ERR_PTR(err) : bdev;
 }
 
@@ -1235,17 +1205,37 @@ 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)
+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);
+
+        if (whole) {
+                if (res == 0)
+                        bd_finish_claiming(bdev, whole, holder);
+                else
+                        bd_abort_claiming(whole, holder);
+        }
+
+        return res;
 }
 EXPORT_SYMBOL(blkdev_get);
 
 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
@@ -1266,26 +1256,9 @@ 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)
@@ -1329,6 +1302,13 @@ 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) {
+                mutex_lock(&bdev->bd_mutex);
+                bd_release(bdev);
+                if (!bdev->bd_holders)
+                        bd_unlink_disk_holder(bdev);
+                mutex_unlock(&bdev->bd_mutex);
+        }
         return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
@@ -1336,8 +1316,7 @@ 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);
 }
 
@@ -1494,55 +1473,27 @@ EXPORT_SYMBOL(lookup_bdev);
  */
 struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
 {
-        struct block_device *bdev, *whole;
+        struct block_device *bdev;
         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);
+        error = blkdev_get(bdev, mode | FMODE_EXCL, holder);
         if (error)
-                goto out_abort_claiming;
+                return ERR_PTR(error);
 
-        error = -EACCES;
-        if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
-                goto out_blkdev_put;
+        if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+                blkdev_put(bdev, mode);
+                return ERR_PTR(-EACCES);
+        }
 
-        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 d39596224d21..f1b729d3b883 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -489,7 +489,7 @@ again:
                         continue;
 
                 if (device->bdev) {
-                        close_bdev_exclusive(device->bdev, device->mode);
+                        blkdev_put(device->bdev, device->mode | FMODE_EXCL);
                         device->bdev = NULL;
                         fs_devices->open_devices--;
                 }
@@ -523,7 +523,7 @@ 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 | FMODE_EXCL);
                         fs_devices->open_devices--;
                 }
                 if (device->writeable) {
@@ -638,7 +638,7 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 error_brelse:
                 brelse(bh);
 error_close:
-                close_bdev_exclusive(bdev, flags);
+                blkdev_put(bdev, flags | FMODE_EXCL);
 error:
                 continue;
         }
@@ -716,7 +716,7 @@ 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 | FMODE_EXCL);
 error:
         mutex_unlock(&uuid_mutex);
         return ret;
@@ -1244,7 +1244,7 @@ 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 | FMODE_EXCL);
                 device->bdev = NULL;
                 device->fs_devices->open_devices--;
         }
@@ -1287,7 +1287,7 @@ 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);
@@ -1565,7 +1565,7 @@ 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/ext3/super.c b/fs/ext3/super.c
index 2fedaf8b5012..23e7513dba9c 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -347,7 +347,7 @@ 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 = open_by_devnum(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
         if (IS_ERR(bdev))
                 goto fail;
         return bdev;
@@ -364,8 +364,7 @@ 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)
@@ -2136,13 +2135,6 @@ 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 61182fe6254e..5dd0b3e76fa8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -647,7 +647,7 @@ 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 = open_by_devnum(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
         if (IS_ERR(bdev))
                 goto fail;
         return bdev;
@@ -663,8 +663,7 @@ 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)
@@ -3758,13 +3757,6 @@ 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 3eb1393f7b81..c1f0763a022b 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -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 | FMODE_EXCL);
 
         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 | FMODE_EXCL);
         return ERR_PTR(error);
 }
 
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index e1b8493b9aaa..5a290f22dcc3 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 = open_by_devnum(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..734b9025858e 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)
@@ -331,7 +331,7 @@ int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type,
 
         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/nilfs2/super.c b/fs/nilfs2/super.c
index f804d41ec9d3..756a6798d7c8 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1233,7 +1233,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
         }
 
         if (!s_new)
-                close_bdev_exclusive(sd.bdev, mode);
+                blkdev_put(sd.bdev, mode | FMODE_EXCL);
 
         return root_dentry;
 
@@ -1242,7 +1242,7 @@ 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 | FMODE_EXCL);
         return ERR_PTR(err);
 }
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 52c7557f3e25..d0a2721eaceb 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1674,7 +1674,7 @@ 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..2e6501d034ab 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -549,7 +549,7 @@ void register_disk(struct gendisk *disk)
                 goto exit;
 
         bdev->bd_invalidated = 1;
-        err = blkdev_get(bdev, FMODE_READ);
+        err = blkdev_get(bdev, FMODE_READ, NULL);
         if (err < 0)
                 goto exit;
         blkdev_put(bdev, FMODE_READ);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 076c8b194682..b488136f5ace 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2552,8 +2552,6 @@ 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;
         }
@@ -2571,7 +2569,7 @@ 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;
@@ -2585,7 +2583,9 @@ 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 = open_by_devnum(jdev, blkdev_mode, journal);
                 journal->j_dev_mode = blkdev_mode;
                 if (IS_ERR(journal->j_dev_bd)) {
                         result = PTR_ERR(journal->j_dev_bd);
@@ -2594,15 +2594,8 @@ 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;
         }
diff --git a/fs/super.c b/fs/super.c
index ca696155cd9a..22374bf0ba87 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -801,13 +801,13 @@ 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 | FMODE_EXCL);
                 down_write(&s->s_umount);
         } else {
                 char b[BDEVNAME_SIZE];
@@ -831,7 +831,7 @@ 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 | FMODE_EXCL);
 error:
         return ERR_PTR(error);
 }
@@ -862,7 +862,7 @@ void kill_block_super(struct super_block *sb)
         bdev->bd_super = NULL;
         generic_shutdown_super(sb);
         sync_blockdev(bdev);
-        close_bdev_exclusive(bdev, mode);
+        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 9f3a78fe6ae4..a1a6e5ceea67 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -623,7 +623,7 @@ 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);
 }
 
 /*