Merge branch 'mnt_devname' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/viro/vfs-2.6

* 'mnt_devname' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  vfs: bury ->get_sb()
  nfs: switch NFS from ->get_sb() to ->mount()
  nfs: stop mangling ->mnt_devname on NFS
  vfs: new superblock methods to override /proc/*/mount{s,info}
  nfs: nfs_do_{ref,sub}mount() superblock argument is redundant
  nfs: make nfs_path() work without vfsmount
  nfs: store devname at disconnected NFS roots
  nfs: propagate devname to nfs{,4}_get_root()

Documentation/filesystems/Locking

@@ -166,13 +166,11 @@ prototypes:
 	void (*kill_sb) (struct super_block *);
 locking rules:
 		may block
-get_sb		yes
 mount		yes
 kill_sb		yes
 
-->get_sb() returns error or 0 with locked superblock attached to the vfsmount
-(exclusive on ->s_umount).
-->mount() returns ERR_PTR or the root dentry.
+->mount() returns ERR_PTR or the root dentry; its superblock should be locked
+on return.
 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 unlocks and drops the reference.
 

Documentation/filesystems/porting

@@ -394,3 +394,10 @@ file) you must return -EOPNOTSUPP if FALLOC_FL_PUNCH_HOLE is set in mode.
 Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set,
 so the i_size should not change when hole punching, even when puching the end of
 a file off.
+
+--
+[mandatory]
+	->get_sb() is gone.  Switch to use of ->mount().  Typically it's just
+a matter of switching from calling get_sb_... to mount_... and changing the
+function type.  If you were doing it manually, just switch from setting ->mnt_root
+to some pointer to returning that pointer.  On errors return ERR_PTR(...).

Documentation/filesystems/vfs.txt

@@ -95,10 +95,11 @@ functions:
    extern int unregister_filesystem(struct file_system_type *);
 
 The passed struct file_system_type describes your filesystem. When a
-request is made to mount a device onto a directory in your filespace,
-the VFS will call the appropriate get_sb() method for the specific
-filesystem. The dentry for the mount point will then be updated to
-point to the root inode for the new filesystem.
+request is made to mount a filesystem onto a directory in your namespace,
+the VFS will call the appropriate mount() method for the specific
+filesystem.  New vfsmount refering to the tree returned by ->mount()
+will be attached to the mountpoint, so that when pathname resolution
+reaches the mountpoint it will jump into the root of that vfsmount.
 
 You can see all filesystems that are registered to the kernel in the
 file /proc/filesystems.
@@ -107,14 +108,14 @@ file /proc/filesystems.
 struct file_system_type
 -----------------------
 
-This describes the filesystem. As of kernel 2.6.22, the following
+This describes the filesystem. As of kernel 2.6.39, the following
 members are defined:
 
 struct file_system_type {
 	const char *name;
 	int fs_flags;
-        int (*get_sb) (struct file_system_type *, int,
-                       const char *, void *, struct vfsmount *);
+        struct dentry (*mount) (struct file_system_type *, int,
+                       const char *, void *);
         void (*kill_sb) (struct super_block *);
         struct module *owner;
         struct file_system_type * next;
@@ -128,11 +129,11 @@ struct file_system_type {
 
   fs_flags: various flags (i.e. FS_REQUIRES_DEV, FS_NO_DCACHE, etc.)
 
-  get_sb: the method to call when a new instance of this
+  mount: the method to call when a new instance of this
 	filesystem should be mounted
 
   kill_sb: the method to call when an instance of this filesystem
-	should be unmounted
+	should be shut down
 
   owner: for internal VFS use: you should initialize this to THIS_MODULE in
   	most cases.
@@ -141,7 +142,7 @@ struct file_system_type {
 
   s_lock_key, s_umount_key: lockdep-specific
 
-The get_sb() method has the following arguments:
+The mount() method has the following arguments:
 
   struct file_system_type *fs_type: describes the filesystem, partly initialized
   	by the specific filesystem code
@@ -153,32 +154,39 @@ The get_sb() method has the following arguments:
   void *data: arbitrary mount options, usually comes as an ASCII
 	string (see "Mount Options" section)
 
-  struct vfsmount *mnt: a vfs-internal representation of a mount point
+The mount() method must return the root dentry of the tree requested by
+caller.  An active reference to its superblock must be grabbed and the
+superblock must be locked.  On failure it should return ERR_PTR(error).
 
-The get_sb() method must determine if the block device specified
-in the dev_name and fs_type contains a filesystem of the type the method
-supports. If it succeeds in opening the named block device, it initializes a
-struct super_block descriptor for the filesystem contained by the block device.
-On failure it returns an error.
+The arguments match those of mount(2) and their interpretation
+depends on filesystem type.  E.g. for block filesystems, dev_name is
+interpreted as block device name, that device is opened and if it
+contains a suitable filesystem image the method creates and initializes
+struct super_block accordingly, returning its root dentry to caller.
+
+->mount() may choose to return a subtree of existing filesystem - it
+doesn't have to create a new one.  The main result from the caller's
+point of view is a reference to dentry at the root of (sub)tree to
+be attached; creation of new superblock is a common side effect.
 
 The most interesting member of the superblock structure that the
-get_sb() method fills in is the "s_op" field. This is a pointer to
+mount() method fills in is the "s_op" field. This is a pointer to
 a "struct super_operations" which describes the next level of the
 filesystem implementation.
 
-Usually, a filesystem uses one of the generic get_sb() implementations
-and provides a fill_super() method instead. The generic methods are:
+Usually, a filesystem uses one of the generic mount() implementations
+and provides a fill_super() callback instead. The generic variants are:
 
-  get_sb_bdev: mount a filesystem residing on a block device
+  mount_bdev: mount a filesystem residing on a block device
 
-  get_sb_nodev: mount a filesystem that is not backed by a device
+  mount_nodev: mount a filesystem that is not backed by a device
 
-  get_sb_single: mount a filesystem which shares the instance between
+  mount_single: mount a filesystem which shares the instance between
   	all mounts
 
-A fill_super() method implementation has the following arguments:
+A fill_super() callback implementation has the following arguments:
 
-  struct super_block *sb: the superblock structure. The method fill_super()
+  struct super_block *sb: the superblock structure. The callback
   	must initialize this properly.
 
   void *data: arbitrary mount options, usually comes as an ASCII

fs/namespace.c

@@ -978,7 +978,13 @@ static int show_vfsmnt(struct seq_file *m, void *v)
 	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 
-	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (mnt->mnt_sb->s_op->show_devname) {
+		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+		if (err)
+			goto out;
+	} else {
+		mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	}
 	seq_putc(m, ' ');
 	seq_path(m, &mnt_path, " \t\n\\");
 	seq_putc(m, ' ');
@@ -1025,7 +1031,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
 
 	seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	seq_dentry(m, mnt->mnt_root, " \t\n\\");
+	if (sb->s_op->show_path)
+		err = sb->s_op->show_path(m, mnt);
+	else
+		seq_dentry(m, mnt->mnt_root, " \t\n\\");
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 	seq_path_root(m, &mnt_path, &root, " \t\n\\");
 	if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
@@ -1060,7 +1071,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
 	seq_puts(m, " - ");
 	show_type(m, sb);
 	seq_putc(m, ' ');
-	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (sb->s_op->show_devname)
+		err = sb->s_op->show_devname(m, mnt);
+	else
+		mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (err)
+		goto out;
 	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
 	err = show_sb_opts(m, sb);
 	if (err)
@@ -1086,11 +1102,15 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	int err = 0;
 
 	/* device */
-	if (mnt->mnt_devname) {
-		seq_puts(m, "device ");
-		mangle(m, mnt->mnt_devname);
-	} else
-		seq_puts(m, "no device");
+	if (mnt->mnt_sb->s_op->show_devname) {
+		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+	} else {
+		if (mnt->mnt_devname) {
+			seq_puts(m, "device ");
+			mangle(m, mnt->mnt_devname);
+		} else
+			seq_puts(m, "no device");
+	}
 
 	/* mount point */
 	seq_puts(m, " mounted on ");
@@ -1104,7 +1124,8 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	/* optional statistics */
 	if (mnt->mnt_sb->s_op->show_stats) {
 		seq_putc(m, ' ');
-		err = mnt->mnt_sb->s_op->show_stats(m, mnt);
+		if (!err)
+			err = mnt->mnt_sb->s_op->show_stats(m, mnt);
 	}
 
 	seq_putc(m, '\n');

fs/nfs/dir.c

@@ -1169,11 +1169,23 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 	iput(inode);
 }
 
+static void nfs_d_release(struct dentry *dentry)
+{
+	/* free cached devname value, if it survived that far */
+	if (unlikely(dentry->d_fsdata)) {
+		if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+			WARN_ON(1);
+		else
+			kfree(dentry->d_fsdata);
+	}
+}
+
 const struct dentry_operations nfs_dentry_operations = {
 	.d_revalidate	= nfs_lookup_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
 	.d_automount	= nfs_d_automount,
+	.d_release	= nfs_d_release,
 };
 
 static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
@@ -1248,6 +1260,7 @@ const struct dentry_operations nfs4_dentry_operations = {
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
 	.d_automount	= nfs_d_automount,
+	.d_release	= nfs_d_release,
 };
 
 /*

fs/nfs/getroot.c

@@ -75,18 +75,25 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 /*
  * get an NFS2/NFS3 root dentry from the root filehandle
  */
-struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh,
+			    const char *devname)
 {
 	struct nfs_server *server = NFS_SB(sb);
 	struct nfs_fsinfo fsinfo;
 	struct dentry *ret;
 	struct inode *inode;
+	void *name = kstrdup(devname, GFP_KERNEL);
 	int error;
 
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
 	/* get the actual root for this mount */
 	fsinfo.fattr = nfs_alloc_fattr();
-	if (fsinfo.fattr == NULL)
+	if (fsinfo.fattr == NULL) {
+		kfree(name);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
 	if (error < 0) {
@@ -119,7 +126,15 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 	}
 
 	security_d_instantiate(ret, inode);
+	spin_lock(&ret->d_lock);
+	if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
+		ret->d_fsdata = name;
+		name = NULL;
+	}
+	spin_unlock(&ret->d_lock);
 out:
+	if (name)
+		kfree(name);
 	nfs_free_fattr(fsinfo.fattr);
 	return ret;
 }
@@ -169,27 +184,35 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
 /*
  * get an NFS4 root dentry from the root filehandle
  */
-struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh,
+			     const char *devname)
 {
 	struct nfs_server *server = NFS_SB(sb);
 	struct nfs_fattr *fattr = NULL;
 	struct dentry *ret;
 	struct inode *inode;
+	void *name = kstrdup(devname, GFP_KERNEL);
 	int error;
 
 	dprintk("--> nfs4_get_root()\n");
 
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
 	/* get the info about the server and filesystem */
 	error = nfs4_server_capabilities(server, mntfh);
 	if (error < 0) {
 		dprintk("nfs_get_root: getcaps error = %d\n",
 			-error);
+		kfree(name);
 		return ERR_PTR(error);
 	}
 
 	fattr = nfs_alloc_fattr();
-	if (fattr == NULL)
-		return ERR_PTR(-ENOMEM);;
+	if (fattr == NULL) {
+		kfree(name);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	/* get the actual root for this mount */
 	error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
@@ -223,8 +246,15 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 	}
 
 	security_d_instantiate(ret, inode);
-
+	spin_lock(&ret->d_lock);
+	if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
+		ret->d_fsdata = name;
+		name = NULL;
+	}
+	spin_unlock(&ret->d_lock);
 out:
+	if (name)
+		kfree(name);
 	nfs_free_fattr(fattr);
 	dprintk("<-- nfs4_get_root()\n");
 	return ret;

fs/nfs/internal.h

@@ -163,10 +163,10 @@ static inline void nfs_fs_proc_exit(void)
 
 /* nfs4namespace.c */
 #ifdef CONFIG_NFS_V4
-extern struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry);
+extern struct vfsmount *nfs_do_refmount(struct dentry *dentry);
 #else
 static inline
-struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry)
+struct vfsmount *nfs_do_refmount(struct dentry *dentry)
 {
 	return ERR_PTR(-ENOENT);
 }
@@ -247,16 +247,16 @@ extern void nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
 
 /* namespace.c */
-extern char *nfs_path(const char *base,
-		      const struct dentry *droot,
-		      const struct dentry *dentry,
+extern char *nfs_path(char **p, struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 extern struct vfsmount *nfs_d_automount(struct path *path);
 
 /* getroot.c */
-extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
+extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
+				   const char *);
 #ifdef CONFIG_NFS_V4
-extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *);
+extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
+				    const char *);
 
 extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
@@ -288,12 +288,11 @@ extern int _nfs4_call_sync_session(struct nfs_server *server,
 /*
  * Determine the device name as a string
  */
-static inline char *nfs_devname(const struct vfsmount *mnt_parent,
-				const struct dentry *dentry,
+static inline char *nfs_devname(struct dentry *dentry,
 				char *buffer, ssize_t buflen)
 {
-	return nfs_path(mnt_parent->mnt_devname, mnt_parent->mnt_root,
-			dentry, buffer, buflen);
+	char *dummy;
+	return nfs_path(&dummy, dentry, buffer, buflen);
 }
 
 /*