[PATCH] VFS: Permit filesystem to override root dentry on mount

Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.

The filesystem is then required to manually set the superblock and root dentry
pointers.  For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).

The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.

This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing.  In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.

The patch also makes the following changes:

 (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
     pointer argument and return an integer, so most filesystems have to change
     very little.

 (*) If one of the convenience function is not used, then get_sb() should
     normally call simple_set_mnt() to instantiate the vfsmount. This will
     always return 0, and so can be tail-called from get_sb().

 (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
     dcache upon superblock destruction rather than shrink_dcache_anon().

     This is required because the superblock may now have multiple trees that
     aren't actually bound to s_root, but that still need to be cleaned up. The
     currently called functions assume that the whole tree is rooted at s_root,
     and that anonymous dentries are not the roots of trees which results in
     dentries being left unculled.

     However, with the way NFS superblock sharing are currently set to be
     implemented, these assumptions are violated: the root of the filesystem is
     simply a dummy dentry and inode (the real inode for '/' may well be
     inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
     with child trees.

     [*] Anonymous until discovered from another tree.

 (*) The documentation has been adjusted, including the additional bit of
     changing ext2_* into foo_* in the documentation.

[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 62 insertions, 47 deletions

diff --git a/fs/super.c b/fs/super.c
index 9d5c2add7228..324c2d232f54 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -231,7 +231,7 @@ void generic_shutdown_super(struct super_block *sb)
 	if (root) {
 		sb->s_root = NULL;
 		shrink_dcache_parent(root);
-		shrink_dcache_anon(sb);
+		shrink_dcache_sb(sb);
 		dput(root);
 		fsync_super(sb);
 		lock_super(sb);
@@ -676,9 +676,10 @@ static void bdev_uevent(struct block_device *bdev, enum kobject_action action)
 	}
 }
 
-struct super_block *get_sb_bdev(struct file_system_type *fs_type,
+int get_sb_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
+	int (*fill_super)(struct super_block *, void *, int),
+	struct vfsmount *mnt)
 {
 	struct block_device *bdev;
 	struct super_block *s;
@@ -686,7 +687,7 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 
 	bdev = open_bdev_excl(dev_name, flags, fs_type);
 	if (IS_ERR(bdev))
-		return (struct super_block *)bdev;
+		return PTR_ERR(bdev);
 
 	/*
 	 * once the super is inserted into the list by sget, s_umount
@@ -697,15 +698,17 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 	s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
 	mutex_unlock(&bdev->bd_mount_mutex);
 	if (IS_ERR(s))
-		goto out;
+		goto error_s;
 
 	if (s->s_root) {
 		if ((flags ^ s->s_flags) & MS_RDONLY) {
 			up_write(&s->s_umount);
 			deactivate_super(s);
-			s = ERR_PTR(-EBUSY);
+			error = -EBUSY;
+			goto error_bdev;
 		}
-		goto out;
+
+		close_bdev_excl(bdev);
 	} else {
 		char b[BDEVNAME_SIZE];
 
@@ -716,18 +719,21 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 		if (error) {
 			up_write(&s->s_umount);
 			deactivate_super(s);
-			s = ERR_PTR(error);
-		} else {
-			s->s_flags |= MS_ACTIVE;
-			bdev_uevent(bdev, KOBJ_MOUNT);
+			goto error;
 		}
+
+		s->s_flags |= MS_ACTIVE;
+		bdev_uevent(bdev, KOBJ_MOUNT);
 	}
 
-	return s;
+	return simple_set_mnt(mnt, s);
 
-out:
+error_s:
+	error = PTR_ERR(s);
+error_bdev:
 	close_bdev_excl(bdev);
-	return s;
+error:
+	return error;
 }
 
 EXPORT_SYMBOL(get_sb_bdev);
@@ -744,15 +750,16 @@ void kill_block_super(struct super_block *sb)
 
 EXPORT_SYMBOL(kill_block_super);
 
-struct super_block *get_sb_nodev(struct file_system_type *fs_type,
+int get_sb_nodev(struct file_system_type *fs_type,
 	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
+	int (*fill_super)(struct super_block *, void *, int),
+	struct vfsmount *mnt)
 {
 	int error;
 	struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
 
 	if (IS_ERR(s))
-		return s;
+		return PTR_ERR(s);
 
 	s->s_flags = flags;
 
@@ -760,10 +767,10 @@ struct super_block *get_sb_nodev(struct file_system_type *fs_type,
 	if (error) {
 		up_write(&s->s_umount);
 		deactivate_super(s);
-		return ERR_PTR(error);
+		return error;
 	}
 	s->s_flags |= MS_ACTIVE;
-	return s;
+	return simple_set_mnt(mnt, s);
 }
 
 EXPORT_SYMBOL(get_sb_nodev);
@@ -773,94 +780,102 @@ static int compare_single(struct super_block *s, void *p)
 	return 1;
 }
 
-struct super_block *get_sb_single(struct file_system_type *fs_type,
+int get_sb_single(struct file_system_type *fs_type,
 	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
+	int (*fill_super)(struct super_block *, void *, int),
+	struct vfsmount *mnt)
 {
 	struct super_block *s;
 	int error;
 
 	s = sget(fs_type, compare_single, set_anon_super, NULL);
 	if (IS_ERR(s))
-		return s;
+		return PTR_ERR(s);
 	if (!s->s_root) {
 		s->s_flags = flags;
 		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
 		if (error) {
 			up_write(&s->s_umount);
 			deactivate_super(s);
-			return ERR_PTR(error);
+			return error;
 		}
 		s->s_flags |= MS_ACTIVE;
 	}
 	do_remount_sb(s, flags, data, 0);
-	return s;
+	return simple_set_mnt(mnt, s);
 }
 
 EXPORT_SYMBOL(get_sb_single);
 
 struct vfsmount *
-do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
 {
-	struct file_system_type *type = get_fs_type(fstype);
-	struct super_block *sb = ERR_PTR(-ENOMEM);
 	struct vfsmount *mnt;
-	int error;
 	char *secdata = NULL;
+	int error;
 
 	if (!type)
 		return ERR_PTR(-ENODEV);
 
+	error = -ENOMEM;
 	mnt = alloc_vfsmnt(name);
 	if (!mnt)
 		goto out;
 
 	if (data) {
 		secdata = alloc_secdata();
-		if (!secdata) {
-			sb = ERR_PTR(-ENOMEM);
+		if (!secdata)
 			goto out_mnt;
-		}
 
 		error = security_sb_copy_data(type, data, secdata);
-		if (error) {
-			sb = ERR_PTR(error);
+		if (error)
 			goto out_free_secdata;
-		}
 	}
 
-	sb = type->get_sb(type, flags, name, data);
-	if (IS_ERR(sb))
+	error = type->get_sb(type, flags, name, data, mnt);
+	if (error < 0)
 		goto out_free_secdata;
- 	error = security_sb_kern_mount(sb, secdata);
+
+ 	error = security_sb_kern_mount(mnt->mnt_sb, secdata);
  	if (error)
  		goto out_sb;
-	mnt->mnt_sb = sb;
-	mnt->mnt_root = dget(sb->s_root);
-	mnt->mnt_mountpoint = sb->s_root;
+
+	mnt->mnt_mountpoint = mnt->mnt_root;
 	mnt->mnt_parent = mnt;
-	up_write(&sb->s_umount);
+	up_write(&mnt->mnt_sb->s_umount);
 	free_secdata(secdata);
-	put_filesystem(type);
 	return mnt;
 out_sb:
-	up_write(&sb->s_umount);
-	deactivate_super(sb);
-	sb = ERR_PTR(error);
+	dput(mnt->mnt_root);
+	up_write(&mnt->mnt_sb->s_umount);
+	deactivate_super(mnt->mnt_sb);
 out_free_secdata:
 	free_secdata(secdata);
 out_mnt:
 	free_vfsmnt(mnt);
 out:
+	return ERR_PTR(error);
+}
+
+EXPORT_SYMBOL_GPL(vfs_kern_mount);
+
+struct vfsmount *
+do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+{
+	struct file_system_type *type = get_fs_type(fstype);
+	struct vfsmount *mnt;
+	if (!type)
+		return ERR_PTR(-ENODEV);
+	mnt = vfs_kern_mount(type, flags, name, data);
 	put_filesystem(type);
-	return (struct vfsmount *)sb;
+	return mnt;
 }
 
 EXPORT_SYMBOL_GPL(do_kern_mount);
 
 struct vfsmount *kern_mount(struct file_system_type *type)
 {
-	return do_kern_mount(type->name, 0, type->name, NULL);
+	return vfs_kern_mount(type, 0, type->name, NULL);
 }
 
 EXPORT_SYMBOL(kern_mount);