[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>

3 files changed, 17 insertions, 13 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 46d0e079735d..0dd1610a94a9 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -217,7 +217,6 @@ extern struct dentry * d_alloc_anon(struct inode *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
-extern void shrink_dcache_anon(struct super_block *);
 extern int d_invalidate(struct dentry *);
 
 /* only used at mount-time */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 73c7d6f04b31..3e50dd24af87 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1269,23 +1269,26 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent,
 struct file_system_type {
         const char *name;
         int fs_flags;
-        struct super_block *(*get_sb) (struct file_system_type *, int,
-                                       const char *, void *);
+        int (*get_sb) (struct file_system_type *, int,
+                       const char *, void *, struct vfsmount *);
         void (*kill_sb) (struct super_block *);
         struct module *owner;
         struct file_system_type * next;
         struct list_head fs_supers;
 };
 
-struct super_block *get_sb_bdev(struct file_system_type *fs_type,
+extern 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));
-struct super_block *get_sb_single(struct file_system_type *fs_type,
+        int (*fill_super)(struct super_block *, void *, int),
+        struct vfsmount *mnt);
+extern int get_sb_single(struct file_system_type *fs_type,
         int flags, void *data,
-        int (*fill_super)(struct super_block *, void *, int));
-struct super_block *get_sb_nodev(struct file_system_type *fs_type,
+        int (*fill_super)(struct super_block *, void *, int),
+        struct vfsmount *mnt);
+extern 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);
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
@@ -1296,8 +1299,10 @@ struct super_block *sget(struct file_system_type *type,
                         int (*test)(struct super_block *,void *),
                         int (*set)(struct super_block *,void *),
                         void *data);
-struct super_block *get_sb_pseudo(struct file_system_type *, char *,
-                        struct super_operations *ops, unsigned long);
+extern int get_sb_pseudo(struct file_system_type *, char *,
+        struct super_operations *ops, unsigned long,
+        struct vfsmount *mnt);
+extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 int __put_super(struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
 void unnamed_dev_init(void);
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index 78ecfa28b1c2..00b340ba6612 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -2,8 +2,8 @@
 #define _LINUX_RAMFS_H
 
 struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev);
-struct super_block *ramfs_get_sb(struct file_system_type *fs_type,
-         int flags, const char *dev_name, void *data);
+extern int ramfs_get_sb(struct file_system_type *fs_type,
+         int flags, const char *dev_name, void *data, struct vfsmount *mnt);
 
 #ifndef CONFIG_MMU
 extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file,