[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, 27 insertions, 22 deletions

diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 9d0521451f59..2378a662c256 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -111,9 +111,10 @@ static int jffs2_sb_set(struct super_block *sb, void *data)
 	return 0;
 }
 
-static struct super_block *jffs2_get_sb_mtd(struct file_system_type *fs_type,
-					      int flags, const char *dev_name,
-					      void *data, struct mtd_info *mtd)
+static int jffs2_get_sb_mtd(struct file_system_type *fs_type,
+			    int flags, const char *dev_name,
+			    void *data, struct mtd_info *mtd,
+			    struct vfsmount *mnt)
 {
 	struct super_block *sb;
 	struct jffs2_sb_info *c;
@@ -121,19 +122,20 @@ static struct super_block *jffs2_get_sb_mtd(struct file_system_type *fs_type,
 
 	c = kmalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	memset(c, 0, sizeof(*c));
 	c->mtd = mtd;
 
 	sb = sget(fs_type, jffs2_sb_compare, jffs2_sb_set, c);
 
 	if (IS_ERR(sb))
-		goto out_put;
+		goto out_error;
 
 	if (sb->s_root) {
 		/* New mountpoint for JFFS2 which is already mounted */
 		D1(printk(KERN_DEBUG "jffs2_get_sb_mtd(): Device %d (\"%s\") is already mounted\n",
 			  mtd->index, mtd->name));
+		ret = simple_set_mnt(mnt, sb);
 		goto out_put;
 	}
 
@@ -161,44 +163,47 @@ static struct super_block *jffs2_get_sb_mtd(struct file_system_type *fs_type,
 		/* Failure case... */
 		up_write(&sb->s_umount);
 		deactivate_super(sb);
-		return ERR_PTR(ret);
+		return ret;
 	}
 
 	sb->s_flags |= MS_ACTIVE;
-	return sb;
+	return simple_set_mnt(mnt, sb);
 
+out_error:
+	ret = PTR_ERR(sb);
  out_put:
 	kfree(c);
 	put_mtd_device(mtd);
 
-	return sb;
+	return ret;
 }
 
-static struct super_block *jffs2_get_sb_mtdnr(struct file_system_type *fs_type,
-					      int flags, const char *dev_name,
-					      void *data, int mtdnr)
+static int jffs2_get_sb_mtdnr(struct file_system_type *fs_type,
+			      int flags, const char *dev_name,
+			      void *data, int mtdnr,
+			      struct vfsmount *mnt)
 {
 	struct mtd_info *mtd;
 
 	mtd = get_mtd_device(NULL, mtdnr);
 	if (!mtd) {
 		D1(printk(KERN_DEBUG "jffs2: MTD device #%u doesn't appear to exist\n", mtdnr));
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
-	return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd);
+	return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt);
 }
 
-static struct super_block *jffs2_get_sb(struct file_system_type *fs_type,
-					int flags, const char *dev_name,
-					void *data)
+static int jffs2_get_sb(struct file_system_type *fs_type,
+			int flags, const char *dev_name,
+			void *data, struct vfsmount *mnt)
 {
 	int err;
 	struct nameidata nd;
 	int mtdnr;
 
 	if (!dev_name)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	D1(printk(KERN_DEBUG "jffs2_get_sb(): dev_name \"%s\"\n", dev_name));
 
@@ -220,7 +225,7 @@ static struct super_block *jffs2_get_sb(struct file_system_type *fs_type,
 				mtd = get_mtd_device(NULL, mtdnr);
 				if (mtd) {
 					if (!strcmp(mtd->name, dev_name+4))
-						return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd);
+						return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt);
 					put_mtd_device(mtd);
 				}
 			}
@@ -233,7 +238,7 @@ static struct super_block *jffs2_get_sb(struct file_system_type *fs_type,
 			if (!*endptr) {
 				/* It was a valid number */
 				D1(printk(KERN_DEBUG "jffs2_get_sb(): mtd%%d, mtdnr %d\n", mtdnr));
-				return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr);
+				return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt);
 			}
 		}
 	}
@@ -247,7 +252,7 @@ static struct super_block *jffs2_get_sb(struct file_system_type *fs_type,
 		  err, nd.dentry->d_inode));
 
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	err = -EINVAL;
 
@@ -269,11 +274,11 @@ static struct super_block *jffs2_get_sb(struct file_system_type *fs_type,
 	mtdnr = iminor(nd.dentry->d_inode);
 	path_release(&nd);
 
-	return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr);
+	return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt);
 
 out:
 	path_release(&nd);
-	return ERR_PTR(err);
+	return err;
 }
 
 static void jffs2_put_super (struct super_block *sb)