X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fblock_dev.c;h=f45dbc18dd175891950ddb84fffa2bc6ce0df117;hb=6b65c5c61bf86086817a5ed786c8f45755ac83b3;hp=b721955d382ebbd3e8b1467bf02f53ad0ae7b8fa;hpb=c3279d1454cdfed02a557d789d8a6d08ab4cbe70;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/block_dev.c b/fs/block_dev.c
index b721955..f45dbc1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/buffer_head.h>
+#include <linux/pagevec.h>
 #include <linux/writeback.h>
 #include <linux/mpage.h>
 #include <linux/mount.h>
@@ -174,6 +175,152 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 				iov, offset, nr_segs, blkdev_get_blocks, NULL);
 }
 
+/*
+ * Write out and wait upon all the dirty data associated with a block
+ * device via its mapping.  Does not take the superblock lock.
+ */
+int sync_blockdev(struct block_device *bdev)
+{
+	int ret = 0;
+
+	if (bdev)
+		ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
+	return ret;
+}
+EXPORT_SYMBOL(sync_blockdev);
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * device.   Filesystem data as well as the underlying block
+ * device.  Takes the superblock lock.
+ */
+int fsync_bdev(struct block_device *bdev)
+{
+	struct super_block *sb = get_super(bdev);
+	if (sb) {
+		int res = fsync_super(sb);
+		drop_super(sb);
+		return res;
+	}
+	return sync_blockdev(bdev);
+}
+EXPORT_SYMBOL(fsync_bdev);
+
+/**
+ * freeze_bdev  --  lock a filesystem and force it into a consistent state
+ * @bdev:	blockdevice to lock
+ *
+ * This takes the block device bd_mount_sem to make sure no new mounts
+ * happen on bdev until thaw_bdev() is called.
+ * If a superblock is found on this device, we take the s_umount semaphore
+ * on it to make sure nobody unmounts until the snapshot creation is done.
+ * The reference counter (bd_fsfreeze_count) guarantees that only the last
+ * unfreeze process can unfreeze the frozen filesystem actually when multiple
+ * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
+ * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
+ * actually.
+ */
+struct super_block *freeze_bdev(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error = 0;
+
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (bdev->bd_fsfreeze_count > 0) {
+		bdev->bd_fsfreeze_count++;
+		sb = get_super(bdev);
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return sb;
+	}
+	bdev->bd_fsfreeze_count++;
+
+	down(&bdev->bd_mount_sem);
+	sb = get_super(bdev);
+	if (sb && !(sb->s_flags & MS_RDONLY)) {
+		sb->s_frozen = SB_FREEZE_WRITE;
+		smp_wmb();
+
+		__fsync_super(sb);
+
+		sb->s_frozen = SB_FREEZE_TRANS;
+		smp_wmb();
+
+		sync_blockdev(sb->s_bdev);
+
+		if (sb->s_op->freeze_fs) {
+			error = sb->s_op->freeze_fs(sb);
+			if (error) {
+				printk(KERN_ERR
+					"VFS:Filesystem freeze failed\n");
+				sb->s_frozen = SB_UNFROZEN;
+				drop_super(sb);
+				up(&bdev->bd_mount_sem);
+				bdev->bd_fsfreeze_count--;
+				mutex_unlock(&bdev->bd_fsfreeze_mutex);
+				return ERR_PTR(error);
+			}
+		}
+	}
+
+	sync_blockdev(bdev);
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+
+	return sb;	/* thaw_bdev releases s->s_umount and bd_mount_sem */
+}
+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 error = 0;
+
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (!bdev->bd_fsfreeze_count) {
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return -EINVAL;
+	}
+
+	bdev->bd_fsfreeze_count--;
+	if (bdev->bd_fsfreeze_count > 0) {
+		if (sb)
+			drop_super(sb);
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return 0;
+	}
+
+	if (sb) {
+		BUG_ON(sb->s_bdev != bdev);
+		if (!(sb->s_flags & MS_RDONLY)) {
+			if (sb->s_op->unfreeze_fs) {
+				error = sb->s_op->unfreeze_fs(sb);
+				if (error) {
+					printk(KERN_ERR
+						"VFS:Filesystem thaw failed\n");
+					sb->s_frozen = SB_FREEZE_TRANS;
+					bdev->bd_fsfreeze_count++;
+					mutex_unlock(&bdev->bd_fsfreeze_mutex);
+					return error;
+				}
+			}
+			sb->s_frozen = SB_UNFROZEN;
+			smp_wmb();
+			wake_up(&sb->s_wait_unfrozen);
+		}
+		drop_super(sb);
+	}
+
+	up(&bdev->bd_mount_sem);
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	return 0;
+}
+EXPORT_SYMBOL(thaw_bdev);
+
 static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, blkdev_get_block, wbc);
@@ -285,6 +432,8 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&bdev->bd_holder_list);
 #endif
 	inode_init_once(&ei->vfs_inode);
+	/* Initialize mutex for freeze. */
+	mutex_init(&bdev->bd_fsfreeze_mutex);
 }
 
 static inline void __bd_forget(struct inode *inode)
@@ -326,12 +475,13 @@ static struct file_system_type bd_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-static struct vfsmount *bd_mnt __read_mostly;
-struct super_block *blockdev_superblock;
+struct super_block *blockdev_superblock __read_mostly;
 
 void __init bdev_cache_init(void)
 {
 	int err;
+	struct vfsmount *bd_mnt;
+
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
 				SLAB_MEM_SPREAD|SLAB_PANIC),
@@ -373,7 +523,7 @@ struct block_device *bdget(dev_t dev)
 	struct block_device *bdev;
 	struct inode *inode;
 
-	inode = iget5_locked(bd_mnt->mnt_sb, hash(dev),
+	inode = iget5_locked(blockdev_superblock, hash(dev),
 			bdev_test, bdev_set, &dev);
 
 	if (!inode)
@@ -463,7 +613,7 @@ void bd_forget(struct inode *inode)
 
 	spin_lock(&bdev_lock);
 	if (inode->i_bdev) {
-		if (inode->i_sb != blockdev_superblock)
+		if (!sb_is_blkdev_sb(inode->i_sb))
 			bdev = inode->i_bdev;
 		__bd_forget(inode);
 	}
@@ -840,22 +990,45 @@ EXPORT_SYMBOL_GPL(bd_release_from_disk);
  * to be used for internal purposes.  If you ever need it - reconsider
  * your API.
  */
-struct block_device *open_by_devnum(dev_t dev, unsigned mode)
+struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
 {
 	struct block_device *bdev = bdget(dev);
 	int err = -ENOMEM;
-	int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
 	if (bdev)
-		err = blkdev_get(bdev, mode, flags);
+		err = blkdev_get(bdev, mode);
 	return err ? ERR_PTR(err) : bdev;
 }
 
 EXPORT_SYMBOL(open_by_devnum);
 
 /**
- * check_disk_size_change - checks for disk size change and adjusts
- *                          bdev size.
+ * flush_disk - invalidates all buffer-cache entries on a disk
+ *
+ * @bdev:      struct block device to be flushed
  *
+ * Invalidates all buffer-cache entries on a disk. It should be called
+ * when a disk has been changed -- either by a media change or online
+ * resize.
+ */
+static void flush_disk(struct block_device *bdev)
+{
+	if (__invalidate_device(bdev)) {
+		char name[BDEVNAME_SIZE] = "";
+
+		if (bdev->bd_disk)
+			disk_name(bdev->bd_disk, 0, name);
+		printk(KERN_WARNING "VFS: busy inodes on changed media or "
+		       "resized disk %s\n", name);
+	}
+
+	if (!bdev->bd_disk)
+		return;
+	if (disk_partitionable(bdev->bd_disk))
+		bdev->bd_invalidated = 1;
+}
+
+/**
+ * check_disk_size_change - checks for disk size change and adjusts bdev size.
  * @disk: struct gendisk to check
  * @bdev: struct bdev to adjust.
  *
@@ -876,14 +1049,13 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 		       "%s: detected capacity change from %lld to %lld\n",
 		       name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
+		flush_disk(bdev);
 	}
 }
 EXPORT_SYMBOL(check_disk_size_change);
 
 /**
- * revalidate_disk - wrapper for lower-level driver's revalidate_disk
- *                   call-back
- *
+ * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
  * @disk: struct gendisk to be revalidated
  *
  * This routine is a wrapper for lower-level driver's revalidate_disk
@@ -929,13 +1101,9 @@ int check_disk_change(struct block_device *bdev)
 	if (!bdops->media_changed(bdev->bd_disk))
 		return 0;
 
-	if (__invalidate_device(bdev))
-		printk("VFS: busy inodes on changed media.\n");
-
+	flush_disk(bdev);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
-	if (disk_partitionable(bdev->bd_disk))
-		bdev->bd_invalidated = 1;
 	return 1;
 }
 
@@ -956,9 +1124,7 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
-			int for_part);
-static int __blkdev_put(struct block_device *bdev, int for_part);
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
  * bd_mutex locking:
@@ -967,17 +1133,16 @@ static int __blkdev_put(struct block_device *bdev, int for_part);
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
 
-static int do_open(struct block_device *bdev, struct file *file, int for_part)
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
-	struct hd_struct *part = NULL;
 	int ret;
 	int partno;
 	int perm = 0;
 
-	if (file->f_mode & FMODE_READ)
+	if (mode & FMODE_READ)
 		perm |= MAY_READ;
-	if (file->f_mode & FMODE_WRITE)
+	if (mode & FMODE_WRITE)
 		perm |= MAY_WRITE;
 	/*
 	 * hooks: /n/, see "layering violations".
@@ -988,27 +1153,41 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		return ret;
 	}
 
-	ret = -ENXIO;
-	file->f_mapping = bdev->bd_inode->i_mapping;
-
 	lock_kernel();
+ restart:
 
+	ret = -ENXIO;
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out_unlock_kernel;
-	part = disk_get_part(disk, partno);
-	if (!part)
-		goto out_unlock_kernel;
 
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
-		bdev->bd_part = part;
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
+
+			ret = -ENXIO;
+			bdev->bd_part = disk_get_part(disk, partno);
+			if (!bdev->bd_part)
+				goto out_clear;
+
 			if (disk->fops->open) {
-				ret = disk->fops->open(bdev->bd_inode, file);
+				ret = disk->fops->open(bdev, mode);
+				if (ret == -ERESTARTSYS) {
+					/* Lost a race with 'disk' being
+					 * deleted, try again.
+					 * See md.c
+					 */
+					disk_put_part(bdev->bd_part);
+					bdev->bd_part = NULL;
+					module_put(disk->fops->owner);
+					put_disk(disk);
+					bdev->bd_disk = NULL;
+					mutex_unlock(&bdev->bd_mutex);
+					goto restart;
+				}
 				if (ret)
 					goto out_clear;
 			}
@@ -1028,28 +1207,27 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 			if (!whole)
 				goto out_clear;
 			BUG_ON(for_part);
-			ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
+			ret = __blkdev_get(whole, mode, 1);
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
 			bdev->bd_inode->i_data.backing_dev_info =
 			   whole->bd_inode->i_data.backing_dev_info;
+			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
-			    !part || !part->nr_sects) {
+			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_size(bdev, (loff_t)part->nr_sects << 9);
+			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
-		disk_put_part(part);
 		put_disk(disk);
 		module_put(disk->fops->owner);
-		part = NULL;
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
-				ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
+				ret = bdev->bd_disk->fops->open(bdev, mode);
 				if (ret)
 					goto out_unlock_bdev;
 			}
@@ -1065,18 +1243,18 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	return 0;
 
  out_clear:
+	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		__blkdev_put(bdev->bd_contains, 1);
+		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
  out_unlock_kernel:
 	unlock_kernel();
 
-	disk_put_part(part);
 	if (disk)
 		module_put(disk->fops->owner);
 	put_disk(disk);
@@ -1085,28 +1263,9 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	return ret;
 }
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
-			int for_part)
+int blkdev_get(struct block_device *bdev, fmode_t mode)
 {
-	/*
-	 * This crockload is due to bad choice of ->open() type.
-	 * It will go away.
-	 * For now, block device ->open() routine must _not_
-	 * examine anything in 'inode' argument except ->i_rdev.
-	 */
-	struct file fake_file = {};
-	struct dentry fake_dentry = {};
-	fake_file.f_mode = mode;
-	fake_file.f_flags = flags;
-	fake_file.f_path.dentry = &fake_dentry;
-	fake_dentry.d_inode = bdev->bd_inode;
-
-	return do_open(bdev, &fake_file, for_part);
-}
-
-int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
-{
-	return __blkdev_get(bdev, mode, flags, 0);
+	return __blkdev_get(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_get);
 
@@ -1123,28 +1282,39 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	 */
 	filp->f_flags |= O_LARGEFILE;
 
+	if (filp->f_flags & O_NDELAY)
+		filp->f_mode |= FMODE_NDELAY;
+	if (filp->f_flags & O_EXCL)
+		filp->f_mode |= FMODE_EXCL;
+	if ((filp->f_flags & O_ACCMODE) == 3)
+		filp->f_mode |= FMODE_WRITE_IOCTL;
+
 	bdev = bd_acquire(inode);
 	if (bdev == NULL)
 		return -ENOMEM;
 
-	res = do_open(bdev, filp, 0);
+	filp->f_mapping = bdev->bd_inode->i_mapping;
+
+	res = blkdev_get(bdev, filp->f_mode);
 	if (res)
 		return res;
 
-	if (!(filp->f_flags & O_EXCL) )
-		return 0;
+	if (filp->f_mode & FMODE_EXCL) {
+		res = bd_claim(bdev, filp);
+		if (res)
+			goto out_blkdev_put;
+	}
 
-	if (!(res = bd_claim(bdev, filp)))
-		return 0;
+	return 0;
 
-	blkdev_put(bdev);
+ out_blkdev_put:
+	blkdev_put(bdev, filp->f_mode);
 	return res;
 }
 
-static int __blkdev_put(struct block_device *bdev, int for_part)
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	int ret = 0;
-	struct inode *bd_inode = bdev->bd_inode;
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
@@ -1159,7 +1329,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
+			ret = disk->fops->release(disk, mode);
 	}
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
@@ -1178,13 +1348,13 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	if (victim)
-		__blkdev_put(victim, 1);
+		__blkdev_put(victim, mode, 1);
 	return ret;
 }
 
-int blkdev_put(struct block_device *bdev)
+int blkdev_put(struct block_device *bdev, fmode_t mode)
 {
-	return __blkdev_put(bdev, 0);
+	return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
 
@@ -1193,12 +1363,38 @@ 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);
+	return blkdev_put(bdev, filp->f_mode);
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	fmode_t mode = file->f_mode;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
+	if (file->f_flags & O_NDELAY)
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
+	return blkdev_ioctl(bdev, mode, cmd, arg);
+}
+
+/*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+static int blkdev_releasepage(struct page *page, gfp_t wait)
+{
+	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+	if (super && super->s_op->bdev_try_to_free_page)
+		return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+	return try_to_free_buffers(page);
 }
 
 static const struct address_space_operations def_blk_aops = {
@@ -1208,6 +1404,7 @@ static const struct address_space_operations def_blk_aops = {
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.writepages	= generic_writepages,
+	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 };
 
@@ -1234,7 +1431,7 @@ int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
 	int res;
 	mm_segment_t old_fs = get_fs();
 	set_fs(KERNEL_DS);
-	res = blkdev_ioctl(bdev->bd_inode, NULL, cmd, arg);
+	res = blkdev_ioctl(bdev, 0, cmd, arg);
 	set_fs(old_fs);
 	return res;
 }
@@ -1243,40 +1440,39 @@ EXPORT_SYMBOL(ioctl_by_bdev);
 
 /**
  * lookup_bdev  - lookup a struct block_device by name
+ * @pathname:	special file representing the block device
  *
- * @path:	special file representing the block device
- *
- * Get a reference to the blockdevice at @path in the current
+ * Get a reference to the blockdevice at @pathname in the current
  * namespace if possible and return it.  Return ERR_PTR(error)
  * otherwise.
  */
-struct block_device *lookup_bdev(const char *path)
+struct block_device *lookup_bdev(const char *pathname)
 {
 	struct block_device *bdev;
 	struct inode *inode;
-	struct nameidata nd;
+	struct path path;
 	int error;
 
-	if (!path || !*path)
+	if (!pathname || !*pathname)
 		return ERR_PTR(-EINVAL);
 
-	error = path_lookup(path, LOOKUP_FOLLOW, &nd);
+	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
 	if (error)
 		return ERR_PTR(error);
 
-	inode = nd.path.dentry->d_inode;
+	inode = path.dentry->d_inode;
 	error = -ENOTBLK;
 	if (!S_ISBLK(inode->i_mode))
 		goto fail;
 	error = -EACCES;
-	if (nd.path.mnt->mnt_flags & MNT_NODEV)
+	if (path.mnt->mnt_flags & MNT_NODEV)
 		goto fail;
 	error = -ENOMEM;
 	bdev = bd_acquire(inode);
 	if (!bdev)
 		goto fail;
 out:
-	path_put(&nd.path);
+	path_put(&path);
 	return bdev;
 fail:
 	bdev = ERR_PTR(error);
@@ -1285,32 +1481,29 @@ fail:
 EXPORT_SYMBOL(lookup_bdev);
 
 /**
- * open_bdev_excl  -  open a block device by name and set it up for use
+ * open_bdev_exclusive  -  open a block device by name and set it up for use
  *
  * @path:	special file representing the block device
- * @flags:	%MS_RDONLY for opening read-only
+ * @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_excl(const char *path, int flags, void *holder)
+struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
 {
 	struct block_device *bdev;
-	mode_t mode = FMODE_READ;
 	int error = 0;
 
 	bdev = lookup_bdev(path);
 	if (IS_ERR(bdev))
 		return bdev;
 
-	if (!(flags & MS_RDONLY))
-		mode |= FMODE_WRITE;
-	error = blkdev_get(bdev, mode, 0);
+	error = blkdev_get(bdev, mode);
 	if (error)
 		return ERR_PTR(error);
 	error = -EACCES;
-	if (!(flags & MS_RDONLY) && bdev_read_only(bdev))
+	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
 		goto blkdev_put;
 	error = bd_claim(bdev, holder);
 	if (error)
@@ -1319,26 +1512,27 @@ struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
 	return bdev;
 	
 blkdev_put:
-	blkdev_put(bdev);
+	blkdev_put(bdev, mode);
 	return ERR_PTR(error);
 }
 
-EXPORT_SYMBOL(open_bdev_excl);
+EXPORT_SYMBOL(open_bdev_exclusive);
 
 /**
- * close_bdev_excl  -  release a blockdevice openen by open_bdev_excl()
+ * 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_excl().
+ * This is the counterpart to open_bdev_exclusive().
  */
-void close_bdev_excl(struct block_device *bdev)
+void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
 {
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put(bdev, mode);
 }
 
-EXPORT_SYMBOL(close_bdev_excl);
+EXPORT_SYMBOL(close_bdev_exclusive);
 
 int __invalidate_device(struct block_device *bdev)
 {