[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>

60 files changed, 391 insertions, 352 deletions

diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 61c599b4a1e..872943004e5 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -99,12 +99,13 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
  * @flags: mount flags
  * @dev_name: device name that was mounted
  * @data: mount options
+ * @mnt: mountpoint record to be instantiated
  *
  */
 
-static struct super_block *v9fs_get_sb(struct file_system_type
-				       *fs_type, int flags,
-				       const char *dev_name, void *data)
+static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data,
+		       struct vfsmount *mnt)
 {
 	struct super_block *sb = NULL;
 	struct v9fs_fcall *fcall = NULL;
@@ -123,17 +124,19 @@ static struct super_block *v9fs_get_sb(struct file_system_type
 
 	v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
 	if (!v9ses)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	if ((newfid = v9fs_session_init(v9ses, dev_name, data)) < 0) {
 		dprintk(DEBUG_ERROR, "problem initiating session\n");
-		sb = ERR_PTR(newfid);
+		retval = newfid;
 		goto out_free_session;
 	}
 
 	sb = sget(fs_type, NULL, v9fs_set_super, v9ses);
-	if (IS_ERR(sb))
+	if (IS_ERR(sb)) {
+		retval = PTR_ERR(sb);
 		goto out_close_session;
+	}
 	v9fs_fill_super(sb, v9ses, flags);
 
 	inode = v9fs_get_inode(sb, S_IFDIR | mode);
@@ -184,19 +187,19 @@ static struct super_block *v9fs_get_sb(struct file_system_type
 		goto put_back_sb;
 	}
 
-	return sb;
+	return simple_set_mnt(mnt, sb);
 
 out_close_session:
 	v9fs_session_close(v9ses);
 out_free_session:
 	kfree(v9ses);
-	return sb;
+	return retval;
 
 put_back_sb:
 	/* deactivate_super calls v9fs_kill_super which will frees the rest */
 	up_write(&sb->s_umount);
 	deactivate_super(sb);
-	return ERR_PTR(retval);
+	return retval;
 }
 
 /**
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 252abda0d20..1b58a9b7f6a 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -470,10 +470,11 @@ error:
 	return -EINVAL;
 }
 
-static struct super_block *adfs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int adfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, adfs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, adfs_fill_super,
+			   mnt);
 }
 
 static struct file_system_type adfs_fs_type = {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 4d7e5b19e5c..6a52e787540 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -524,10 +524,11 @@ affs_statfs(struct super_block *sb, struct kstatfs *buf)
 	return 0;
 }
 
-static struct super_block *affs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int affs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, affs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, affs_fill_super,
+			   mnt);
 }
 
 static struct file_system_type affs_fs_type = {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 53c56e7231a..82468df0ba5 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -38,9 +38,9 @@ struct afs_mount_params {
 static void afs_i_init_once(void *foo, kmem_cache_t *cachep,
 			    unsigned long flags);
 
-static struct super_block *afs_get_sb(struct file_system_type *fs_type,
-				      int flags, const char *dev_name,
-				      void *data);
+static int afs_get_sb(struct file_system_type *fs_type,
+		      int flags, const char *dev_name,
+		      void *data, struct vfsmount *mnt);
 
 static struct inode *afs_alloc_inode(struct super_block *sb);
 
@@ -294,10 +294,11 @@ static int afs_fill_super(struct super_block *sb, void *data, int silent)
  * get an AFS superblock
  * - TODO: don't use get_sb_nodev(), but rather call sget() directly
  */
-static struct super_block *afs_get_sb(struct file_system_type *fs_type,
-				      int flags,
-				      const char *dev_name,
-				      void *options)
+static int afs_get_sb(struct file_system_type *fs_type,
+		      int flags,
+		      const char *dev_name,
+		      void *options,
+		      struct vfsmount *mnt)
 {
 	struct afs_mount_params params;
 	struct super_block *sb;
@@ -311,7 +312,7 @@ static struct super_block *afs_get_sb(struct file_system_type *fs_type,
 	ret = afscm_start();
 	if (ret < 0) {
 		_leave(" = %d", ret);
-		return ERR_PTR(ret);
+		return ret;
 	}
 
 	/* parse the options */
@@ -348,18 +349,19 @@ static struct super_block *afs_get_sb(struct file_system_type *fs_type,
 		goto error;
 	}
 	sb->s_flags |= MS_ACTIVE;
+	simple_set_mnt(mnt, sb);
 
 	afs_put_volume(params.volume);
 	afs_put_cell(params.default_cell);
-	_leave(" = %p", sb);
-	return sb;
+	_leave(" = 0 [%p]", 0, sb);
+	return 0;
 
  error:
 	afs_put_volume(params.volume);
 	afs_put_cell(params.default_cell);
 	afscm_stop();
 	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	return ret;
 } /* end afs_get_sb() */
 
 /*****************************************************************************/
diff --git a/fs/autofs/init.c b/fs/autofs/init.c
index b977ece69f0..aca12375240 100644
--- a/fs/autofs/init.c
+++ b/fs/autofs/init.c
@@ -14,10 +14,10 @@
 #include <linux/init.h>
 #include "autofs_i.h"
 
-static struct super_block *autofs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int autofs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_nodev(fs_type, flags, data, autofs_fill_super);
+	return get_sb_nodev(fs_type, flags, data, autofs_fill_super, mnt);
 }
 
 static struct file_system_type autofs_fs_type = {
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index acecec8578c..5d9193332be 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -14,10 +14,10 @@
 #include <linux/init.h>
 #include "autofs_i.h"
 
-static struct super_block *autofs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int autofs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_nodev(fs_type, flags, data, autofs4_fill_super);
+	return get_sb_nodev(fs_type, flags, data, autofs4_fill_super, mnt);
 }
 
 static struct file_system_type autofs_fs_type = {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 68ebd10f345..6ed07a5f10c 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -899,11 +899,12 @@ befs_statfs(struct super_block *sb, struct kstatfs *buf)
 	return 0;
 }
 
-static struct super_block *
+static int
 befs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name,
-	    void *data)
+	    void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, befs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, befs_fill_super,
+			   mnt);
 }
 
 static struct file_system_type befs_fs_type = {
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 55a7a78332f..e7da03f63a5 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -410,10 +410,10 @@ out:
 	return -EINVAL;
 }
 
-static struct super_block *bfs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int bfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, bfs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, bfs_fill_super, mnt);
 }
 
 static struct file_system_type bfs_fs_type = {
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 599f36fd0f6..07a4996cca3 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -739,10 +739,10 @@ static int bm_fill_super(struct super_block * sb, void * data, int silent)
 	return err;
 }
 
-static struct super_block *bm_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int bm_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, bm_fill_super);
+	return get_sb_single(fs_type, flags, data, bm_fill_super, mnt);
 }
 
 static struct linux_binfmt misc_format = {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 44aaba202f7..028d9fb9c2d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -300,10 +300,10 @@ static struct super_operations bdev_sops = {
 	.clear_inode = bdev_clear_inode,
 };
 
-static struct super_block *bd_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int bd_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576);
+	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
 }
 
 static struct file_system_type bd_type = {
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c262d8874ce..08b35801dfe 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -460,9 +460,9 @@ struct super_operations cifs_super_ops = {
 	.remount_fs = cifs_remount,
 };
 
-static struct super_block *
+static int
 cifs_get_sb(struct file_system_type *fs_type,
-	    int flags, const char *dev_name, void *data)
+	    int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
 	int rc;
 	struct super_block *sb = sget(fs_type, NULL, set_anon_super, NULL);
@@ -470,7 +470,7 @@ cifs_get_sb(struct file_system_type *fs_type,
 	cFYI(1, ("Devname: %s flags: %d ", dev_name, flags));
 
 	if (IS_ERR(sb))
-		return sb;
+		return PTR_ERR(sb);
 
 	sb->s_flags = flags;
 
@@ -478,10 +478,10 @@ cifs_get_sb(struct file_system_type *fs_type,
 	if (rc) {
 		up_write(&sb->s_umount);
 		deactivate_super(sb);
-		return ERR_PTR(rc);
+		return rc;
 	}
 	sb->s_flags |= MS_ACTIVE;
-	return sb;
+	return simple_set_mnt(mnt, sb);
 }
 
 static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov,
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index ada1a81df6b..cba70201567 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -307,10 +307,10 @@ static int coda_statfs(struct super_block *sb, struct kstatfs *buf)
 
 /* init_coda: used by filesystems.c to register coda */
 
-static struct super_block *coda_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int coda_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_nodev(fs_type, flags, data, coda_fill_super);
+	return get_sb_nodev(fs_type, flags, data, coda_fill_super, mnt);
 }
 
 struct file_system_type coda_fs_type = {
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index f920d30478e..94dab7bdd85 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -103,10 +103,10 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 }
 
-static struct super_block *configfs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int configfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, configfs_fill_super);
+	return get_sb_single(fs_type, flags, data, configfs_fill_super, mnt);
 }
 
 static struct file_system_type configfs_fs_type = {
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 9efcc3a164e..37a91a153aa 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -528,10 +528,11 @@ static struct super_operations cramfs_ops = {
 	.statfs		= cramfs_statfs,
 };
 
-static struct super_block *cramfs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int cramfs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, cramfs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, cramfs_fill_super,
+			   mnt);
 }
 
 static struct file_system_type cramfs_fs_type = {
diff --git a/fs/dcache.c b/fs/dcache.c
index 59dbc92c207..313b54b2b8f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -687,46 +687,6 @@ void shrink_dcache_parent(struct dentry * parent)
 		prune_dcache(found, parent->d_sb);
 }
 
-/**
- * shrink_dcache_anon - further prune the cache
- * @head: head of d_hash list of dentries to prune
- *
- * Prune the dentries that are anonymous
- *
- * parsing d_hash list does not hlist_for_each_entry_rcu() as it
- * done under dcache_lock.
- *
- */
-void shrink_dcache_anon(struct super_block *sb)
-{
-	struct hlist_node *lp;
-	struct hlist_head *head = &sb->s_anon;
-	int found;
-	do {
-		found = 0;
-		spin_lock(&dcache_lock);
-		hlist_for_each(lp, head) {
-			struct dentry *this = hlist_entry(lp, struct dentry, d_hash);
-			if (!list_empty(&this->d_lru)) {
-				dentry_stat.nr_unused--;
-				list_del_init(&this->d_lru);
-			}
-
-			/* 
-			 * move only zero ref count dentries to the end 
-			 * of the unused list for prune_dcache
-			 */
-			if (!atomic_read(&this->d_count)) {
-				list_add_tail(&this->d_lru, &dentry_unused);
-				dentry_stat.nr_unused++;
-				found++;
-			}
-		}
-		spin_unlock(&dcache_lock);
-		prune_dcache(found, sb);
-	} while(found);
-}
-
 /*
  * Scan `nr' dentries and return the number which remain.
  *
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index b55b4ea9a67..440128ebef3 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -111,11 +111,11 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent)
 	return simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
 }
 
-static struct super_block *debug_get_sb(struct file_system_type *fs_type,
-				        int flags, const char *dev_name,
-					void *data)
+static int debug_get_sb(struct file_system_type *fs_type,
+			int flags, const char *dev_name,
+			void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, debug_fill_super);
+	return get_sb_single(fs_type, flags, data, debug_fill_super, mnt);
 }
 
 static struct file_system_type debug_fs_type = {
diff --git a/fs/devfs/base.c b/fs/devfs/base.c
index 52f5059c4f3..51a97f13274 100644
--- a/fs/devfs/base.c
+++ b/fs/devfs/base.c
@@ -2549,11 +2549,11 @@ static int devfs_fill_super(struct super_block *sb, void *data, int silent)
 	return -EINVAL;
 }				/*  End Function devfs_fill_super  */
 
-static struct super_block *devfs_get_sb(struct file_system_type *fs_type,
-					int flags, const char *dev_name,
-					void *data)
+static int devfs_get_sb(struct file_system_type *fs_type,
+			int flags, const char *dev_name,
+			void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, devfs_fill_super);
+	return get_sb_single(fs_type, flags, data, devfs_fill_super, mnt);
 }
 
 static struct file_system_type devfs_fs_type = {
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 14c5620b5ca..f7aef5bb584 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -130,10 +130,10 @@ fail:
 	return -ENOMEM;
 }
 
-static struct super_block *devpts_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int devpts_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, devpts_fill_super);
+	return get_sb_single(fs_type, flags, data, devpts_fill_super, mnt);
 }
 
 static struct file_system_type devpts_fs_type = {
diff --git a/fs/efs/super.c b/fs/efs/super.c
index dff623e3ddb..1ba5e14f879 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -18,10 +18,10 @@
 static int efs_statfs(struct super_block *s, struct kstatfs *buf);
 static int efs_fill_super(struct super_block *s, void *d, int silent);
 
-static struct super_block *efs_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int efs_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, efs_fill_super);
+	return get_sb_bdev(fs_type, flags, dev_name, data, efs_fill_super, mnt);
 }
 
 static struct file_system_type efs_fs_type = {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 2695337d4d6..08e7e6a555c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -268,9 +268,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		   int maxevents, long timeout);
 static int eventpollfs_delete_dentry(struct dentry *dentry);
 static struct inode *ep_eventpoll_inode(void);
-static struct super_block *eventpollfs_get_sb(struct file_system_type *fs_type,
-					      int flags, const char *dev_name,
-					      void *data);
+static int eventpollfs_get_sb(struct file_system_type *fs_type,
+			      int flags, const char *dev_name,
+			      void *data, struct vfsmount *mnt);
 
 /*
  * This semaphore is used to serialize ep_free() and eventpoll_release_file().
@@ -1595,11 +1595,12 @@ eexit_1:
 }
 
 
-static struct super_block *
+static int
 eventpollfs_get_sb(struct file_system_type *fs_type, int flags,
-		   const char *dev_name, void *data)
+		   const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_pseudo(fs_type, "eventpoll:", NULL, EVENTPOLLFS_MAGIC);
+	return get_sb_pseudo(fs_type, "eventpoll:", NULL, EVENTPOLLFS_MAGIC,
+			     mnt);
 }
 
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7e30bae174e..a4dfffac596 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1087,10 +1087,10 @@ static int ext2_statfs (struct super_block * sb, struct kstatfs * buf)
 	return 0;
 }