Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (23 commits)
  sanitize vfsmount refcounting changes
  fix old umount_tree() breakage
  autofs4: Merge the remaining dentry ops tables
  Unexport do_add_mount() and add in follow_automount(), not ->d_automount()
  Allow d_manage() to be used in RCU-walk mode
  Remove a further kludge from __do_follow_link()
  autofs4: Bump version
  autofs4: Add v4 pseudo direct mount support
  autofs4: Fix wait validation
  autofs4: Clean up autofs4_free_ino()
  autofs4: Clean up dentry operations
  autofs4: Clean up inode operations
  autofs4: Remove unused code
  autofs4: Add d_manage() dentry operation
  autofs4: Add d_automount() dentry operation
  Remove the automount through follow_link() kludge code from pathwalk
  CIFS: Use d_automount() rather than abusing follow_link()
  NFS: Use d_automount() rather than abusing follow_link()
  AFS: Use d_automount() rather than abusing follow_link()
  Add an AT_NO_AUTOMOUNT flag to suppress terminal automount
  ...

Documentation/filesystems/Locking

@@ -19,6 +19,8 @@ prototypes:
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
+	struct vfsmount *(*d_automount)(struct path *path);
+	int (*d_manage)(struct dentry *, bool);
 
 locking rules:
 		rename_lock	->d_lock	may block	rcu-walk
@@ -29,6 +31,8 @@ d_delete:	no		yes		no		no
 d_release:	no		no		yes		no
 d_iput:		no		no		yes		no
 d_dname:	no		no		no		no
+d_automount:	no		no		yes		no
+d_manage:	no		no		yes (ref-walk)	maybe
 
 --------------------------- inode_operations --------------------------- 
 prototypes:

Documentation/filesystems/vfs.txt

@@ -864,6 +864,8 @@ struct dentry_operations {
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)(struct dentry *, char *, int);
+	struct vfsmount *(*d_automount)(struct path *);
+	int (*d_manage)(struct dentry *, bool, bool);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -930,6 +932,47 @@ struct dentry_operations {
 	at the end of the buffer, and returns a pointer to the first char.
 	dynamic_dname() helper function is provided to take care of this.
 
+  d_automount: called when an automount dentry is to be traversed (optional).
+	This should create a new VFS mount record and return the record to the
+	caller.  The caller is supplied with a path parameter giving the
+	automount directory to describe the automount target and the parent
+	VFS mount record to provide inheritable mount parameters.  NULL should
+	be returned if someone else managed to make the automount first.  If
+	the vfsmount creation failed, then an error code should be returned.
+	If -EISDIR is returned, then the directory will be treated as an
+	ordinary directory and returned to pathwalk to continue walking.
+
+	If a vfsmount is returned, the caller will attempt to mount it on the
+	mountpoint and will remove the vfsmount from its expiration list in
+	the case of failure.  The vfsmount should be returned with 2 refs on
+	it to prevent automatic expiration - the caller will clean up the
+	additional ref.
+
+	This function is only used if DCACHE_NEED_AUTOMOUNT is set on the
+	dentry.  This is set by __d_instantiate() if S_AUTOMOUNT is set on the
+	inode being added.
+
+  d_manage: called to allow the filesystem to manage the transition from a
+	dentry (optional).  This allows autofs, for example, to hold up clients
+	waiting to explore behind a 'mountpoint' whilst letting the daemon go
+	past and construct the subtree there.  0 should be returned to let the
+	calling process continue.  -EISDIR can be returned to tell pathwalk to
+	use this directory as an ordinary directory and to ignore anything
+	mounted on it and not to check the automount flag.  Any other error
+	code will abort pathwalk completely.
+
+	If the 'mounting_here' parameter is true, then namespace_sem is being
+	held by the caller and the function should not initiate any mounts or
+	unmounts that it will then wait for.
+
+	If the 'rcu_walk' parameter is true, then the caller is doing a
+	pathwalk in RCU-walk mode.  Sleeping is not permitted in this mode,
+	and the caller can be asked to leave it and call again by returing
+	-ECHILD.
+
+	This function is only used if DCACHE_MANAGE_TRANSIT is set on the
+	dentry being transited from.
+
 Example :
 
 static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)

drivers/mtd/mtdchar.c

@@ -1201,7 +1201,7 @@ err_unregister_chdev:
 static void __exit cleanup_mtdchar(void)
 {
 	unregister_mtd_user(&mtdchar_notifier);
-	mntput_long(mtd_inode_mnt);
+	mntput(mtd_inode_mnt);
 	unregister_filesystem(&mtd_inodefs_type);
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 }

drivers/staging/autofs/dirhash.c

@@ -88,14 +88,13 @@ struct autofs_dir_ent *autofs_expire(struct super_block *sb,
 		}
 		path.mnt = mnt;
 		path_get(&path);
-		if (!follow_down(&path)) {
+		if (!follow_down_one(&path)) {
 			path_put(&path);
 			DPRINTK(("autofs: not expirable\
 			(not a mounted directory): %s\n", ent->name));
 			continue;
 		}
-		while (d_mountpoint(path.dentry) && follow_down(&path))
-			;
+		follow_down(&path, false);  // TODO: need to check error
 		umount_ok = may_umount(path.mnt);
 		path_put(&path);
 

fs/afs/dir.c

@@ -66,6 +66,7 @@ const struct dentry_operations afs_fs_dentry_operations = {
 	.d_revalidate	= afs_d_revalidate,
 	.d_delete	= afs_d_delete,
 	.d_release	= afs_d_release,
+	.d_automount	= afs_d_automount,
 };
 
 #define AFS_DIR_HASHTBL_SIZE	128

fs/afs/inode.c

@@ -184,7 +184,8 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 	inode->i_generation	= 0;
 
 	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
-	inode->i_flags |= S_NOATIME;
+	set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+	inode->i_flags |= S_AUTOMOUNT | S_NOATIME;
 	unlock_new_inode(inode);
 	_leave(" = %p", inode);
 	return inode;

fs/afs/internal.h

@@ -592,6 +592,7 @@ extern const struct inode_operations afs_mntpt_inode_operations;
 extern const struct inode_operations afs_autocell_inode_operations;
 extern const struct file_operations afs_mntpt_file_operations;
 
+extern struct vfsmount *afs_d_automount(struct path *);
 extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
 extern void afs_mntpt_kill_timer(void);
 

fs/afs/mntpt.c

@@ -24,7 +24,6 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir,
 				       struct dentry *dentry,
 				       struct nameidata *nd);
 static int afs_mntpt_open(struct inode *inode, struct file *file);
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd);
 static void afs_mntpt_expiry_timed_out(struct work_struct *work);
 
 const struct file_operations afs_mntpt_file_operations = {
@@ -34,13 +33,11 @@ const struct file_operations afs_mntpt_file_operations = {
 
 const struct inode_operations afs_mntpt_inode_operations = {
 	.lookup		= afs_mntpt_lookup,
-	.follow_link	= afs_mntpt_follow_link,
 	.readlink	= page_readlink,
 	.getattr	= afs_getattr,
 };
 
 const struct inode_operations afs_autocell_inode_operations = {
-	.follow_link	= afs_mntpt_follow_link,
 	.getattr	= afs_getattr,
 };
 
@@ -88,6 +85,7 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
 		_debug("symlink is a mountpoint");
 		spin_lock(&vnode->lock);
 		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+		vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
 		spin_unlock(&vnode->lock);
 	}
 
@@ -238,52 +236,24 @@ error_no_devname:
 }
 
 /*
- * follow a link from a mountpoint directory, thus causing it to be mounted
+ * handle an automount point
  */
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *afs_d_automount(struct path *path)
 {
 	struct vfsmount *newmnt;
-	int err;
 
-	_enter("%p{%s},{%s:%p{%s},}",
-	       dentry,
-	       dentry->d_name.name,
-	       nd->path.mnt->mnt_devname,
-	       dentry,
-	       nd->path.dentry->d_name.name);
-
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
-
-	newmnt = afs_mntpt_do_automount(nd->path.dentry);
-	if (IS_ERR(newmnt)) {
-		path_put(&nd->path);
-		return (void *)newmnt;
-	}
+	_enter("{%s,%s}", path->mnt->mnt_devname, path->dentry->d_name.name);
 
-	mntget(newmnt);
-	err = do_add_mount(newmnt, &nd->path, MNT_SHRINKABLE, &afs_vfsmounts);
-	switch (err) {
-	case 0:
-		path_put(&nd->path);
-		nd->path.mnt = newmnt;
-		nd->path.dentry = dget(newmnt->mnt_root);
-		queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
-				   afs_mntpt_expiry_timeout * HZ);
-		break;
-	case -EBUSY:
-		/* someone else made a mount here whilst we were busy */
-		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path))
-			;
-		err = 0;
-	default:
-		mntput(newmnt);
-		break;
-	}
+	newmnt = afs_mntpt_do_automount(path->dentry);
+	if (IS_ERR(newmnt))
+		return newmnt;
 
-	_leave(" = %d", err);
-	return ERR_PTR(err);
+	mntget(newmnt); /* prevent immediate expiration */
+	mnt_set_expiry(newmnt, &afs_vfsmounts);
+	queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
+			   afs_mntpt_expiry_timeout * HZ);
+	_leave(" = %p {%s}", newmnt, newmnt->mnt_devname);
+	return newmnt;
 }
 
 /*

fs/anon_inodes.c

@@ -233,7 +233,7 @@ static int __init anon_inode_init(void)
 	return 0;
 
 err_mntput:
-	mntput_long(anon_inode_mnt);
+	mntput(anon_inode_mnt);
 err_unregister_filesystem:
 	unregister_filesystem(&anon_inode_fs_type);
 err_exit:

fs/autofs4/autofs_i.h

@@ -99,7 +99,6 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
-#define AUTOFS_INF_MOUNTPOINT	(1<<1) /* mountpoint status for direct expire */
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
 struct autofs_wait_queue {
@@ -176,13 +175,6 @@ static inline int autofs4_ispending(struct dentry *dentry)
 	return 0;
 }
 
-static inline void autofs4_copy_atime(struct file *src, struct file *dst)
-{
-	dst->f_path.dentry->d_inode->i_atime =
-		src->f_path.dentry->d_inode->i_atime;
-	return;
-}
-
 struct inode *autofs4_get_inode(struct super_block *, struct autofs_info *);
 void autofs4_free_ino(struct autofs_info *);
 
@@ -212,11 +204,83 @@ void autofs_dev_ioctl_exit(void);
 
 extern const struct inode_operations autofs4_symlink_inode_operations;
 extern const struct inode_operations autofs4_dir_inode_operations;
-extern const struct inode_operations autofs4_root_inode_operations;
-extern const struct inode_operations autofs4_indirect_root_inode_operations;
-extern const struct inode_operations autofs4_direct_root_inode_operations;
 extern const struct file_operations autofs4_dir_operations;
 extern const struct file_operations autofs4_root_operations;
+extern const struct dentry_operations autofs4_dentry_operations;
+
+/* VFS automount flags management functions */
+
+static inline void __managed_dentry_set_automount(struct dentry *dentry)
+{
+	dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
+}
+
+static inline void managed_dentry_set_automount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_automount(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_automount(struct dentry *dentry)
+{
+	dentry->d_flags &= ~DCACHE_NEED_AUTOMOUNT;
+}
+
+static inline void managed_dentry_clear_automount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_automount(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_set_transit(struct dentry *dentry)
+{
+	dentry->d_flags |= DCACHE_MANAGE_TRANSIT;
+}
+
+static inline void managed_dentry_set_transit(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_transit(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_transit(struct dentry *dentry)
+{
+	dentry->d_flags &= ~DCACHE_MANAGE_TRANSIT;
+}
+
+static inline void managed_dentry_clear_transit(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_transit(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_set_managed(struct dentry *dentry)
+{
+	dentry->d_flags |= (DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT);
+}
+
+static inline void managed_dentry_set_managed(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_managed(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_managed(struct dentry *dentry)
+{
+	dentry->d_flags &= ~(DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT);
+}
+
+static inline void managed_dentry_clear_managed(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_managed(dentry);
+	spin_unlock(&dentry->d_lock);
+}
 
 /* Initializing function */
 
@@ -229,19 +293,6 @@ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
 int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
-static inline int autofs4_follow_mount(struct path *path)
-{
-	int res = 0;
-
-	while (d_mountpoint(path->dentry)) {
-		int followed = follow_down(path);
-		if (!followed)
-			break;
-		res = 1;
-	}
-	return res;
-}
-
 static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
 {
 	return new_encode_dev(sbi->sb->s_dev);

fs/autofs4/dev-ioctl.c

@@ -551,7 +551,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 
 		err = have_submounts(path.dentry);
 
-		if (follow_down(&path))
+		if (follow_down_one(&path))
 			magic = path.mnt->mnt_sb->s_magic;
 	}
 

fs/autofs4/expire.c

@@ -26,10 +26,6 @@ static inline int autofs4_can_expire(struct dentry *dentry,
 	if (ino == NULL)
 		return 0;
 
-	/* No point expiring a pending mount */
-	if (ino->flags & AUTOFS_INF_PENDING)
-		return 0;
-
 	if (!do_now) {
 		/* Too young to die */
 		if (!timeout || time_after(ino->last_used + timeout, now))
@@ -56,7 +52,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 
 	path_get(&path);
 
-	if (!follow_down(&path))
+	if (!follow_down_one(&path))
 		goto done;
 
 	if (is_autofs4_dentry(path.dentry)) {
@@ -283,6 +279,7 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	unsigned long timeout;
 	struct dentry *root = dget(sb->s_root);
 	int do_now = how & AUTOFS_EXP_IMMEDIATE;
+	struct autofs_info *ino;
 
 	if (!root)
 		return NULL;
@@ -291,19 +288,21 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	timeout = sbi->exp_timeout;
 
 	spin_lock(&sbi->fs_lock);
+	ino = autofs4_dentry_ino(root);
+	/* No point expiring a pending mount */
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		spin_unlock(&sbi->fs_lock);
+		return NULL;
+	}
+	managed_dentry_set_transit(root);
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 		struct autofs_info *ino = autofs4_dentry_ino(root);
-		if (d_mountpoint(root)) {
-			ino->flags |= AUTOFS_INF_MOUNTPOINT;
-			spin_lock(&root->d_lock);
-			root->d_flags &= ~DCACHE_MOUNTED;
-			spin_unlock(&root->d_lock);
-		}
 		ino->flags |= AUTOFS_INF_EXPIRING;
 		init_completion(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		return root;
 	}
+	managed_dentry_clear_transit(root);
 	spin_unlock(&sbi->fs_lock);
 	dput(root);
 
@@ -340,6 +339,10 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	while ((dentry = get_next_positive_dentry(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
+		/* No point expiring a pending mount */
+		if (ino->flags & AUTOFS_INF_PENDING)
+			goto cont;
+		managed_dentry_set_transit(dentry);
 
 		/*
 		 * Case 1: (i) indirect mount or top level pseudo direct mount
@@ -399,6 +402,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 			}
 		}
 next:
+		managed_dentry_clear_transit(dentry);
+cont:
 		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
@@ -479,6 +484,8 @@ int autofs4_expire_run(struct super_block *sb,
 	spin_lock(&sbi->fs_lock);
 	ino = autofs4_dentry_ino(dentry);
 	ino->flags &= ~AUTOFS_INF_EXPIRING;
+	if (!d_unhashed(dentry))
+		managed_dentry_clear_transit(dentry);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -504,18 +511,18 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
-		if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
-			spin_lock(&sb->s_root->d_lock);
-			/*
-			 * If we haven't been expired away, then reset
-			 * mounted status.
-			 */
-			if (mnt->mnt_parent != mnt)
-				sb->s_root->d_flags |= DCACHE_MOUNTED;
-			spin_unlock(&sb->s_root->d_lock);
-			ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
-		}
 		ino->flags &= ~AUTOFS_INF_EXPIRING;
+		spin_lock(&dentry->d_lock);
+		if (ret)
+			__managed_dentry_clear_transit(dentry);
+		else {
+			if ((IS_ROOT(dentry) ||
+			    (autofs_type_indirect(sbi->type) &&
+			     IS_ROOT(dentry->d_parent))) &&
+			    !(dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+				__managed_dentry_set_automount(dentry);
+		}
+		spin_unlock(&dentry->d_lock);
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		dput(dentry);

fs/autofs4/inode.c

@@ -45,7 +45,6 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
 
 	if (!reinit) {
 		ino->flags = 0;
-		ino->inode = NULL;
 		ino->dentry = NULL;
 		ino->size = 0;
 		INIT_LIST_HEAD(&ino->active);
@@ -76,19 +75,8 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
 
 void autofs4_free_ino(struct autofs_info *ino)
 {
-	struct autofs_info *p_ino;
-
 	if (ino->dentry) {
 		ino->dentry->d_fsdata = NULL;
-		if (ino->dentry->d_inode) {
-			struct dentry *parent = ino->dentry->d_parent;
-			if (atomic_dec_and_test(&ino->count)) {
-				p_ino = autofs4_dentry_ino(parent);
-				if (p_ino && parent != ino->dentry)
-					atomic_dec(&p_ino->count);
-			}
-			dput(ino->dentry);
-		}
 		ino->dentry = NULL;
 	}
 	if (ino->free)
@@ -251,10 +239,6 @@ static struct autofs_info *autofs4_mkroot(struct autofs_sb_info *sbi)
 	return ino;
 }
 
-static const struct dentry_operations autofs4_sb_dentry_operations = {
-	.d_release      = autofs4_dentry_release,
-};
-
 int autofs4_fill_super(struct super_block *s, void *data, int silent)
 {
 	struct inode * root_inode;
@@ -292,6 +276,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	s->s_blocksize_bits = 10;
 	s->s_magic = AUTOFS_SUPER_MAGIC;
 	s->s_op = &autofs4_sops;
+	s->s_d_op = &autofs4_dentry_operations;
 	s->s_time_gran = 1;
 
 	/*
@@ -309,7 +294,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		goto fail_iput;
 	pipe = NULL;
 
-	d_set_d_op(root, &autofs4_sb_dentry_operations);
 	root->d_fsdata = ino;
 
 	/* Can this call block? */
@@ -320,10 +304,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		goto fail_dput;
 	}
 
+	if (autofs_type_trigger(sbi->type))
+		__managed_dentry_set_managed(root);
+
 	root_inode->i_fop = &autofs4_root_operations;
-	root_inode->i_op = autofs_type_trigger(sbi->type) ?
-			&autofs4_direct_root_inode_operations :
-			&autofs4_indirect_root_inode_operations;
+	root_inode->i_op = &autofs4_dir_inode_operations;
 
 	/* Couldn't this be tested earlier? */
 	if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
@@ -391,7 +376,6 @@ struct inode *autofs4_get_inode(struct super_block *sb,
 	if (inode == NULL)
 		return NULL;
 
-	inf->inode = inode;
 	inode->i_mode = inf->mode;
 	if (sb->s_root) {
 		inode->i_uid = sb->s_root->d_inode->i_uid;

fs/autofs4/root.c

@@ -35,10 +35,8 @@ static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
-static void *autofs4_follow_link(struct dentry *, struct nameidata *);
-
-#define TRIGGER_FLAGS   (LOOKUP_CONTINUE | LOOKUP_DIRECTORY)
-#define TRIGGER_INTENTS (LOOKUP_OPEN | LOOKUP_CREATE)
+static struct vfsmount *autofs4_d_automount(struct path *);
+static int autofs4_d_manage(struct dentry *, bool, bool);
 
 const struct file_operations autofs4_root_operations = {
 	.open		= dcache_dir_open,
@@ -60,7 +58,7 @@ const struct file_operations autofs4_dir_operations = {
 	.llseek		= dcache_dir_lseek,
 };
 
-const struct inode_operations autofs4_indirect_root_inode_operations = {
+const struct inode_operations autofs4_dir_inode_operations = {
 	.lookup		= autofs4_lookup,
 	.unlink		= autofs4_dir_unlink,
 	.symlink	= autofs4_dir_symlink,
@@ -68,20 +66,10 @@ const struct inode_operations autofs4_indirect_root_inode_operations = {
 	.rmdir		= autofs4_dir_rmdir,
 };
 
-const struct inode_operations autofs4_direct_root_inode_operations = {
-	.lookup		= autofs4_lookup,
-	.unlink		= autofs4_dir_unlink,
-	.mkdir		= autofs4_dir_mkdir,
-	.rmdir		= autofs4_dir_rmdir,
-	.follow_link	= autofs4_follow_link,
-};
-
-const struct inode_operations autofs4_dir_inode_operations = {
-	.lookup		= autofs4_lookup,
-	.unlink		= autofs4_dir_unlink,
-	.symlink	= autofs4_dir_symlink,
-	.mkdir		= autofs4_dir_mkdir,
-	.rmdir		= autofs4_dir_rmdir,
+const struct dentry_operations autofs4_dentry_operations = {
+	.d_automount	= autofs4_d_automount,
+	.d_manage	= autofs4_d_manage,
+	.d_release	= autofs4_dentry_release,
 };
 
 static void autofs4_add_active(struct dentry *dentry)
@@ -116,14 +104,6 @@ static void autofs4_del_active(struct dentry *dentry)
 	return;
 }
 
-static unsigned int autofs4_need_mount(unsigned int flags)
-{
-	unsigned int res = 0;
-	if (flags & (TRIGGER_FLAGS | TRIGGER_INTENTS))
-		res = 1;
-	return res;
-}
-
 static int autofs4_dir_open(struct inode *inode, struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -158,239 +138,6 @@ out:
 	return dcache_dir_open(inode, file);
 }
 
-static int try_to_fill_dentry(struct dentry *dentry, int flags)
-{
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	int status;
-
-	DPRINTK("dentry=%p %.*s ino=%p",
-		 dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
-
-	/*
-	 * Wait for a pending mount, triggering one if there
-	 * isn't one already
-	 */
-	if (dentry->d_inode == NULL) {
-		DPRINTK("waiting for mount name=%.*s",
-			 dentry->d_name.len, dentry->d_name.name);
-
-		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-
-		DPRINTK("mount done status=%d", status);
-
-		/* Turn this into a real negative dentry? */
-		if (status == -ENOENT) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-			return status;
-		} else if (status) {
-			/* Return a negative dentry, but leave it "pending" */
-			return status;
-		}
-	/* Trigger mount for path component or follow link */
-	} else if (ino->flags & AUTOFS_INF_PENDING ||
-			autofs4_need_mount(flags)) {
-		DPRINTK("waiting for mount name=%.*s",
-			dentry->d_name.len, dentry->d_name.name);
-
-		spin_lock(&sbi->fs_lock);
-		ino->flags |= AUTOFS_INF_PENDING;
-		spin_unlock(&sbi->fs_lock);
-		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-
-		DPRINTK("mount done status=%d", status);
-
-		if (status) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-			return status;
-		}
-	}
-
-	/* Initialize expiry counter after successful mount */
-	ino->last_used = jiffies;
-
-	spin_lock(&sbi->fs_lock);
-	ino->flags &= ~AUTOFS_INF_PENDING;
-	spin_unlock(&sbi->fs_lock);
-
-	return 0;
-}
-
-/* For autofs direct mounts the follow link triggers the mount */
-static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	int oz_mode = autofs4_oz_mode(sbi);
-	unsigned int lookup_type;
-	int status;
-
-	DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d",
-		dentry, dentry->d_name.len, dentry->d_name.name, oz_mode,
-		nd->flags);
-	/*
-	 * For an expire of a covered direct or offset mount we need
-	 * to break out of follow_down() at the autofs mount trigger
-	 * (d_mounted--), so we can see the expiring flag, and manage
-	 * the blocking and following here until the expire is completed.
-	 */
-	if (oz_mode) {
-		spin_lock(&sbi->fs_lock);
-		if (ino->flags & AUTOFS_INF_EXPIRING) {
-			spin_unlock(&sbi->fs_lock);
-			/* Follow down to our covering mount. */
-			if (!follow_down(&nd->path))
-				goto done;
-			goto follow;
-		}
-		spin_unlock(&sbi->fs_lock);
-		goto done;
-	}
-
-	/* If an expire request is pending everyone must wait. */
-	autofs4_expire_wait(dentry);
-
-	/* We trigger a mount for almost all flags */
-	lookup_type = autofs4_need_mount(nd->flags);
-	spin_lock(&sbi->fs_lock);
-	spin_lock(&autofs4_lock);
-	spin_lock(&dentry->d_lock);
-	if (!(lookup_type || ino->flags & AUTOFS_INF_PENDING)) {
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-		spin_unlock(&sbi->fs_lock);
-		goto follow;
-	}
-
-	/*
-	 * If the dentry contains directories then it is an autofs
-	 * multi-mount with no root mount offset. So don't try to
-	 * mount it again.
-	 */
-	if (ino->flags & AUTOFS_INF_PENDING ||
-	    (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs))) {
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-		spin_unlock(&sbi->fs_lock);
-
-		status = try_to_fill_dentry(dentry, nd->flags);
-		if (status)
-			goto out_error;
-
-		goto follow;
-	}
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
-	spin_unlock(&sbi->fs_lock);
-follow:
-	/*
-	 * If there is no root mount it must be an autofs
-	 * multi-mount with no root offset so we don't need
-	 * to follow it.
-	 */
-	if (d_mountpoint(dentry)) {
-		if (!autofs4_follow_mount(&nd->path)) {
-			status = -ENOENT;
-			goto out_error;
-		}
-	}
-
-done:
-	return NULL;
-
-out_error:
-	path_put(&nd->path);
-	return ERR_PTR(status);
-}
-
-/*
- * Revalidate is called on every cache lookup.  Some of those
- * cache lookups may actually happen while the dentry is not
- * yet completely filled in, and revalidate has to delay such
- * lookups..
- */
-static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
-	struct inode *dir;
-	struct autofs_sb_info *sbi;
-	int oz_mode;
-	int flags = nd ? nd->flags : 0;
-	int status = 1;
-
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	dir = dentry->d_parent->d_inode;
-	sbi = autofs4_sbi(dir->i_sb);
-	oz_mode = autofs4_oz_mode(sbi);
-
-	/* Pending dentry */
-	spin_lock(&sbi->fs_lock);
-	if (autofs4_ispending(dentry)) {
-		/* The daemon never causes a mount to trigger */
-		spin_unlock(&sbi->fs_lock);
-
-		if (oz_mode)
-			return 1;
-
-		/*
-		 * If the directory has gone away due to an expire
-		 * we have been called as ->d_revalidate() and so
-		 * we need to return false and proceed to ->lookup().
-		 */
-		if (autofs4_expire_wait(dentry) == -EAGAIN)
-			return 0;
-
-		/*
-		 * A zero status is success otherwise we have a
-		 * negative error code.
-		 */
-		status = try_to_fill_dentry(dentry, flags);
-		if (status == 0)
-			return 1;
-
-		return status;
-	}
-	spin_unlock(&sbi->fs_lock);
-
-	/* Negative dentry.. invalidate if "old" */
-	if (dentry->d_inode == NULL)
-		return 0;
-
-	/* Check for a non-mountpoint directory with no contents */
-	spin_lock(&autofs4_lock);
-	spin_lock(&dentry->d_lock);
-	if (S_ISDIR(dentry->d_inode->i_mode) &&
-	    !d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
-		DPRINTK("dentry=%p %.*s, emptydir",
-			 dentry, dentry->d_name.len, dentry->d_name.name);
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-
-		/* The daemon never causes a mount to trigger */
-		if (oz_mode)
-			return 1;
-
-		/*
-		 * A zero status is success otherwise we have a
-		 * negative error code.
-		 */
-		status = try_to_fill_dentry(dentry, flags);
-		if (status == 0)
-			return 1;
-
-		return status;
-	}
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
-
-	return 1;
-}
-
 void autofs4_dentry_release(struct dentry *de)
 {
 	struct autofs_info *inf;
@@ -398,11 +145,8 @@ void autofs4_dentry_release(struct dentry *de)
 	DPRINTK("releasing %p", de);
 
 	inf = autofs4_dentry_ino(de);
-	de->d_fsdata = NULL;
-
 	if (inf) {
 		struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
-
 		if (sbi) {
 			spin_lock(&sbi->lookup_lock);
 			if (!list_empty(&inf->active))
@@ -411,26 +155,10 @@ void autofs4_dentry_release(struct dentry *de)
 				list_del(&inf->expiring);
 			spin_unlock(&sbi->lookup_lock);
 		}
-
-		inf->dentry = NULL;
-		inf->inode = NULL;
-
 		autofs4_free_ino(inf);
 	}
 }
 
-/* For dentries of directories in the root dir */
-static const struct dentry_operations autofs4_root_dentry_operations = {
-	.d_revalidate	= autofs4_revalidate,
-	.d_release	= autofs4_dentry_release,
-};
-
-/* For other dentries */
-static const struct dentry_operations autofs4_dentry_operations = {
-	.d_revalidate	= autofs4_revalidate,
-	.d_release	= autofs4_dentry_release,
-};
-
 static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
@@ -541,50 +269,244 @@ next:
 	return NULL;
 }
 
+static int autofs4_mount_wait(struct dentry *dentry)
+{
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	int status;
+
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		DPRINTK("waiting for mount name=%.*s",
+			dentry->d_name.len, dentry->d_name.name);
+		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
+		DPRINTK("mount wait done status=%d", status);
+		ino->last_used = jiffies;
+		return status;
+	}
+	return 0;
+}
+
+static int do_expire_wait(struct dentry *dentry)
+{
+	struct dentry *expiring;
+
+	expiring = autofs4_lookup_expiring(dentry);
+	if (!expiring)
+		return autofs4_expire_wait(dentry);
+	else {
+		/*
+		 * If we are racing with expire the request might not
+		 * be quite complete, but the directory has been removed
+		 * so it must have been successful, just wait for it.
+		 */
+		autofs4_expire_wait(expiring);
+		autofs4_del_expiring(expiring);
+		dput(expiring);
+	}
+	return 0;
+}
+
+static struct dentry *autofs4_mountpoint_changed(struct path *path)
+{
+	struct dentry *dentry = path->dentry;
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+
+	/*
+	 * If this is an indirect mount the dentry could have gone away
+	 * as a result of an expire and a new one created.
+	 */
+	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
+		struct dentry *parent = dentry->d_parent;
+		struct dentry *new = d_lookup(parent, &dentry->d_name);
+		if (!new)
+			return NULL;
+		dput(path->dentry);
+		path->dentry = new;
+	}
+	return path->dentry;
+}
+
+static struct vfsmount *autofs4_d_automount(struct path *path)
+{
+	struct dentry *dentry = path->dentry;
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	int status;
+
+	DPRINTK("dentry=%p %.*s",
+		dentry, dentry->d_name.len, dentry->d_name.name);
+
+	/*
+	 * Someone may have manually umounted this or it was a submount
+	 * that has gone away.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
+		if (!(dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
+		     (dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+			__managed_dentry_set_transit(path->dentry);
+	}
+	spin_unlock(&dentry->d_lock);
+
+	/* The daemon never triggers a mount. */
+	if (autofs4_oz_mode(sbi))
+		return NULL;
+
+	/*
+	 * If an expire request is pending everyone must wait.
+	 * If the expire fails we're still mounted so continue
+	 * the follow and return. A return of -EAGAIN (which only
+	 * happens with indirect mounts) means the expire completed
+	 * and the directory was removed, so just go ahead and try
+	 * the mount.
+	 */
+	status = do_expire_wait(dentry);
+	if (status && status != -EAGAIN)
+		return NULL;
+
+	/* Callback to the daemon to perform the mount or wait */
+	spin_lock(&sbi->fs_lock);
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		spin_unlock(&sbi->fs_lock);
+		status = autofs4_mount_wait(dentry);
+		if (status)
+			return ERR_PTR(status);
+		spin_lock(&sbi->fs_lock);
+		goto done;
+	}
+
+	/*
+	 * If the dentry is a symlink it's equivalent to a directory
+	 * having d_mountpoint() true, so there's no need to call back
+	 * to the daemon.
+	 */
+	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode))
+		goto done;
+	if (!d_mountpoint(dentry)) {
+		/*
+		 * It's possible that user space hasn't removed directories
+		 * after umounting a rootless multi-mount, although it
+		 * should. For v5 have_submounts() is sufficient to handle
+		 * this because the leaves of the directory tree under the
+		 * mount never trigger mounts themselves (they have an autofs
+		 * trigger mount mounted on them). But v4 pseudo direct mounts
+		 * do need the leaves to to trigger mounts. In this case we
+		 * have no choice but to use the list_empty() check and
+		 * require user space behave.
+		 */
+		if (sbi->version > 4) {
+			if (have_submounts(dentry))
+				goto done;
+		} else {
+			spin_lock(&dentry->d_lock);
+			if (!list_empty(&dentry->d_subdirs)) {
+				spin_unlock(&dentry->d_lock);
+				goto done;
+			}
+			spin_unlock(&dentry->d_lock);
+		}
+		ino->flags |= AUTOFS_INF_PENDING;
+		spin_unlock(&sbi->fs_lock);
+		status = autofs4_mount_wait(dentry);
+		if (status)
+			return ERR_PTR(status);
+		spin_lock(&sbi->fs_lock);
+		ino->flags &= ~AUTOFS_INF_PENDING;
+	}
+done:
+	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
+		/*
+		 * Any needed mounting has been completed and the path updated
+		 * so turn this into a normal dentry so we don't continually
+		 * call ->d_automount() and ->d_manage().
+		 */
+		spin_lock(&dentry->d_lock);
+		__managed_dentry_clear_transit(dentry);
+		/*
+		 * Only clear DMANAGED_AUTOMOUNT for rootless multi-mounts and
+		 * symlinks as in all other cases the dentry will be covered by
+		 * an actual mount so ->d_automount() won't be called during
+		 * the follow.
+		 */
+		if ((!d_mountpoint(dentry) &&
+		    !list_empty(&dentry->d_subdirs)) ||
+		    (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)))
+			__managed_dentry_clear_automount(dentry);
+		spin_unlock(&dentry->d_lock);
+	}
+	spin_unlock(&sbi->fs_lock);
+
+	/* Mount succeeded, check if we ended up with a new dentry */
+	dentry = autofs4_mountpoint_changed(path);
+	if (!dentry)
+		return ERR_PTR(-ENOENT);
+
+	return NULL;
+}
+
+int autofs4_d_manage(struct dentry *dentry, bool mounting_here, bool rcu_walk)
+{
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+
+	DPRINTK("dentry=%p %.*s",
+		dentry, dentry->d_name.len, dentry->d_name.name);
+
+	/* The daemon never waits. */
+	if (autofs4_oz_mode(sbi) || mounting_here) {
+		if (!d_mountpoint(dentry))
+			return -EISDIR;
+		return 0;
+	}
+
+	/* We need to sleep, so we need pathwalk to be in ref-mode */
+	if (rcu_walk)
+		return -ECHILD;
+
+	/* Wait for pending expires */
+	do_expire_wait(dentry);
+
+	/*
+	 * This dentry may be under construction so wait on mount
+	 * completion.
+	 */
+	return autofs4_mount_wait(dentry);
+}
+
 /* Lookups in the root directory */
 static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
-	struct dentry *expiring, *active;
-	int oz_mode;
+	struct dentry *active;
 
-	DPRINTK("name = %.*s",
-		dentry->d_name.len, dentry->d_name.name);
+	DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name);
 
 	/* File name too long to exist */
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	sbi = autofs4_sbi(dir->i_sb);
-	oz_mode = autofs4_oz_mode(sbi);
 
 	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
-		 current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
+		current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
 
 	active = autofs4_lookup_active(dentry);
 	if (active) {
-		dentry = active;
-		ino = autofs4_dentry_ino(dentry);
+		return active;
 	} else {
 		/*
-		 * Mark the dentry incomplete but don't hash it. We do this
-		 * to serialize our inode creation operations (symlink and
-		 * mkdir) which prevents deadlock during the callback to
-		 * the daemon. Subsequent user space lookups for the same
-		 * dentry are placed on the wait queue while the daemon
-		 * itself is allowed passage unresticted so the create
-		 * operation itself can then hash the dentry. Finally,
-		 * we check for the hashed dentry and return the newly
-		 * hashed dentry.
+		 * A dentry that is not within the root can never trigger a
+		 * mount operation, unless the directory already exists, so we
+		 * can return fail immediately.  The daemon however does need
+		 * to create directories within the file system.
 		 */
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
+		if (!autofs4_oz_mode(sbi) && !IS_ROOT(dentry->d_parent))
+			return ERR_PTR(-ENOENT);
+
+		/* Mark entries in the root as mount triggers */
+		if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
+			__managed_dentry_set_managed(dentry);
 
-		/*
-		 * And we need to ensure that the same dentry is used for
-		 * all following lookup calls until it is hashed so that
-		 * the dentry flags are persistent throughout the request.
-		 */
 		ino = autofs4_init_ino(NULL, sbi, 0555);
 		if (!ino)
 			return ERR_PTR(-ENOMEM);
@@ -596,82 +518,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
 
 		d_instantiate(dentry, NULL);
 	}
-
-	if (!oz_mode) {
-		mutex_unlock(&dir->i_mutex);
-		expiring = autofs4_lookup_expiring(dentry);
-		if (expiring) {
-			/*
-			 * If we are racing with expire the request might not
-			 * be quite complete but the directory has been removed
-			 * so it must have been successful, so just wait for it.
-			 */
-			autofs4_expire_wait(expiring);
-			autofs4_del_expiring(expiring);
-			dput(expiring);
-		}
-
-		spin_lock(&sbi->fs_lock);
-		ino->flags |= AUTOFS_INF_PENDING;
-		spin_unlock(&sbi->fs_lock);
-		if (dentry->d_op && dentry->d_op->d_revalidate)
-			(dentry->d_op->d_revalidate)(dentry, nd);
-		mutex_lock(&dir->i_mutex);
-	}
-
-	/*
-	 * If we are still pending, check if we had to handle
-	 * a signal. If so we can force a restart..
-	 */
-	if (ino->flags & AUTOFS_INF_PENDING) {
-		/* See if we were interrupted */
-		if (signal_pending(current)) {
-			sigset_t *sigset = &current->pending.signal;
-			if (sigismember (sigset, SIGKILL) ||
-			    sigismember (sigset, SIGQUIT) ||
-			    sigismember (sigset, SIGINT)) {
-			    if (active)
-				dput(active);
-			    return ERR_PTR(-ERESTARTNOINTR);
-			}
-		}
-		if (!oz_mode) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-		}
-	}
-
-	/*
-	 * If this dentry is unhashed, then we shouldn't honour this
-	 * lookup.  Returning ENOENT here doesn't do the right thing
-	 * for all system calls, but it should be OK for the operations
-	 * we permit from an autofs.
-	 */
-	if (!oz_mode && d_unhashed(dentry)) {
-		/*
-		 * A user space application can (and has done in the past)
-		 * remove and re-create this directory during the callback.
-		 * This can leave us with an unhashed dentry, but a
-		 * successful mount!  So we need to perform another
-		 * cached lookup in case the dentry now exists.
-		 */
-		struct dentry *parent = dentry->d_parent;
-		struct dentry *new = d_lookup(parent, &dentry->d_name);
-		if (new != NULL)
-			dentry = new;
-		else
-			dentry = ERR_PTR(-ENOENT);
-
-		if (active)
-			dput(active);
-
-		return dentry;
-	}
-
-	if (active)
-		return active;
-
 	return NULL;
 }
 
@@ -716,18 +562,12 @@ static int autofs4_dir_symlink(struct inode *dir,
 	}
 	d_add(dentry, inode);
 
-	if (dir == dir->i_sb->s_root->d_inode)
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
-	else
-		d_set_d_op(dentry, &autofs4_dentry_operations);
-
 	dentry->d_fsdata = ino;
 	ino->dentry = dget(dentry);
 	atomic_inc(&ino->count);
 	p_ino = autofs4_dentry_ino(dentry->d_parent);
 	if (p_ino && dentry->d_parent != dentry)
 		atomic_inc(&p_ino->count);
-	ino->inode = inode;
 
 	ino->u.symlink = cp;
 	dir->i_mtime = CURRENT_TIME;
@@ -782,6 +622,58 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	return 0;
 }
 
+/*
+ * Version 4 of autofs provides a pseudo direct mount implementation
+ * that relies on directories at the leaves of a directory tree under
+ * an indirect mount to trigger mounts. To allow for this we need to
+ * set the DMANAGED_AUTOMOUNT and DMANAGED_TRANSIT flags on the leaves
+ * of the directory tree. There is no need to clear the automount flag
+ * following a mount or restore it after an expire because these mounts
+ * are always covered. However, it is neccessary to ensure that these
+ * flags are clear on non-empty directories to avoid unnecessary calls
+ * during path walks.
+ */
+static void autofs_set_leaf_automount_flags(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	/* root and dentrys in the root are already handled */
+	if (IS_ROOT(dentry->d_parent))
+		return;
+
+	managed_dentry_set_managed(dentry);
+
+	parent = dentry->d_parent;
+	/* only consider parents below dentrys in the root */
+	if (IS_ROOT(parent->d_parent))
+		return;
+	managed_dentry_clear_managed(parent);
+	return;
+}
+
+static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
+{
+	struct list_head *d_child;
+	struct dentry *parent;
+
+	/* flags for dentrys in the root are handled elsewhere */
+	if (IS_ROOT(dentry->d_parent))
+		return;
+
+	managed_dentry_clear_managed(dentry);
+
+	parent = dentry->d_parent;
+	/* only consider parents below dentrys in the root */
+	if (IS_ROOT(parent->d_parent))
+		return;
+	d_child = &dentry->d_u.d_child;
+	/* Set parent managed if it's becoming empty */
+	if (d_child->next == &parent->d_subdirs &&
+	    d_child->prev == &parent->d_subdirs)
+		managed_dentry_set_managed(parent);
+	return;
+}
+
 static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
@@ -809,6 +701,9 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&autofs4_lock);
 
+	if (sbi->version < 5)
+		autofs_clear_leaf_automount_flags(dentry);
+
 	if (atomic_dec_and_test(&ino->count)) {
 		p_ino = autofs4_dentry_ino(dentry->d_parent);
 		if (p_ino && dentry->d_parent != dentry)
@@ -851,10 +746,8 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	}
 	d_add(dentry, inode);
 
-	if (dir == dir->i_sb->s_root->d_inode)
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
-	else
-		d_set_d_op(dentry, &autofs4_dentry_operations);
+	if (sbi->version < 5)
+		autofs_set_leaf_automount_flags(dentry);
 
 	dentry->d_fsdata = ino;
 	ino->dentry = dget(dentry);
@@ -862,7 +755,6 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	p_ino = autofs4_dentry_ino(dentry->d_parent);
 	if (p_ino && dentry->d_parent != dentry)
 		atomic_inc(&p_ino->count);
-	ino->inode = inode;
 	inc_nlink(dir);
 	dir->i_mtime = CURRENT_TIME;
 
@@ -944,8 +836,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 int is_autofs4_dentry(struct dentry *dentry)
 {
 	return dentry && dentry->d_inode &&
-		(dentry->d_op == &autofs4_root_dentry_operations ||
-		 dentry->d_op == &autofs4_dentry_operations) &&
+		dentry->d_op == &autofs4_dentry_operations &&
 		dentry->d_fsdata != NULL;
 }
 

fs/autofs4/waitq.c

@@ -309,6 +309,9 @@ static int validate_request(struct autofs_wait_queue **wait,
 	 * completed while we waited on the mutex ...
 	 */
 	if (notify == NFY_MOUNT) {
+		struct dentry *new = NULL;
+		int valid = 1;
+
 		/*
 		 * If the dentry was successfully mounted while we slept
 		 * on the wait queue mutex we can return success. If it
@@ -316,8 +319,20 @@ static int validate_request(struct autofs_wait_queue **wait,
 		 * a multi-mount with no mount at it's base) we can
 		 * continue on and create a new request.
 		 */
+		if (!IS_ROOT(dentry)) {
+			if (dentry->d_inode && d_unhashed(dentry)) {
+				struct dentry *parent = dentry->d_parent;
+				new = d_lookup(parent, &dentry->d_name);
+				if (new)
+					dentry = new;
+			}
+		}
 		if (have_submounts(dentry))
-			return 0;
+			valid = 0;
+
+		if (new)
+			dput(new);
+		return valid;
 	}
 
 	return 1;

fs/cifs/cifs_dfs_ref.c

@@ -255,35 +255,6 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb,
 
 }
 
-static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
-				struct list_head *mntlist)
-{
-	/* stolen from afs code */
-	int err;
-
-	mntget(newmnt);
-	err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags | MNT_SHRINKABLE, mntlist);
-	switch (err) {
-	case 0:
-		path_put(&nd->path);
-		nd->path.mnt = newmnt;
-		nd->path.dentry = dget(newmnt->mnt_root);
-		schedule_delayed_work(&cifs_dfs_automount_task,
-				      cifs_dfs_mountpoint_expiry_timeout);
-		break;
-	case -EBUSY:
-		/* someone else made a mount here whilst we were busy */
-		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path))
-			;
-		err = 0;
-	default:
-		mntput(newmnt);
-		break;
-	}
-	return err;
-}
-
 static void dump_referral(const struct dfs_info3_param *ref)
 {
 	cFYI(1, "DFS: ref path: %s", ref->path_name);
@@ -293,45 +264,43 @@ static void dump_referral(const struct dfs_info3_param *ref)
 				ref->path_consumed);
 }
 
-
-static void*
-cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+/*
+ * Create a vfsmount that we can automount
+ */
+static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 {
 	struct dfs_info3_param *referrals = NULL;
 	unsigned int num_referrals = 0;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsSesInfo *ses;
-	char *full_path = NULL;
+	char *full_path;
 	int xid, i;
-	int rc = 0;
-	struct vfsmount *mnt = ERR_PTR(-ENOENT);
+	int rc;
+	struct vfsmount *mnt;
 	struct tcon_link *tlink;
 
 	cFYI(1, "in %s", __func__);
-	BUG_ON(IS_ROOT(dentry));
+	BUG_ON(IS_ROOT(mntpt));
 
 	xid = GetXid();
 
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
-
 	/*
 	 * The MSDFS spec states that paths in DFS referral requests and
 	 * responses must be prefixed by a single '\' character instead of
 	 * the double backslashes usually used in the UNC. This function
 	 * gives us the latter, so we must adjust the result.
 	 */
-	full_path = build_path_from_dentry(dentry);
-	if (full_path == NULL) {
-		rc = -ENOMEM;
-		goto out_err;
-	}
+	mnt = ERR_PTR(-ENOMEM);
+	full_path = build_path_from_dentry(mntpt);
+	if (full_path == NULL)
+		goto free_xid;
 
-	cifs_sb = CIFS_SB(dentry->d_inode->i_sb);
+	cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
 	tlink = cifs_sb_tlink(cifs_sb);
+	mnt = ERR_PTR(-EINVAL);
 	if (IS_ERR(tlink)) {
-		rc = PTR_ERR(tlink);
-		goto out_err;
+		mnt = ERR_CAST(tlink);
+		goto free_full_path;
 	}
 	ses = tlink_tcon(tlink)->ses;
 
@@ -341,46 +310,63 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 
 	cifs_put_tlink(tlink);
 
+	mnt = ERR_PTR(-ENOENT);
 	for (i = 0; i < num_referrals; i++) {
 		int len;
-		dump_referral(referrals+i);
+		dump_referral(referrals + i);
 		/* connect to a node */
 		len = strlen(referrals[i].node_name);
 		if (len < 2) {
 			cERROR(1, "%s: Net Address path too short: %s",
 					__func__, referrals[i].node_name);
-			rc = -EINVAL;
-			goto out_err;
+			mnt = ERR_PTR(-EINVAL);
+			break;
 		}
 		mnt = cifs_dfs_do_refmount(cifs_sb,
 				full_path, referrals + i);
 		cFYI(1, "%s: cifs_dfs_do_refmount:%s , mnt:%p", __func__,
 					referrals[i].node_name, mnt);
-
-		/* complete mount procedure if we accured submount */
 		if (!IS_ERR(mnt))
-			break;
+			goto success;
 	}
 
-	/* we need it cause for() above could exit without valid submount */
-	rc = PTR_ERR(mnt);
-	if (IS_ERR(mnt))
-		goto out_err;
-
-	rc = add_mount_helper(mnt, nd, &cifs_dfs_automount_list);
+	/* no valid submounts were found; return error from get_dfs_path() by
+	 * preference */
+	if (rc != 0)
+		mnt = ERR_PTR(rc);
 
-out:
-	FreeXid(xid);
+success:
 	free_dfs_info_array(referrals, num_referrals);
+free_full_path:
 	kfree(full_path);
+free_xid:
+	FreeXid(xid);
 	cFYI(1, "leaving %s" , __func__);
-	return ERR_PTR(rc);
-out_err:
-	path_put(&nd->path);
-	goto out;
+	return mnt;
+}
+
+/*
+ * Attempt to automount the referral
+ */
+struct vfsmount *cifs_dfs_d_automount(struct path *path)
+{
+	struct vfsmount *newmnt;
+
+	cFYI(1, "in %s", __func__);
+
+	newmnt = cifs_dfs_do_automount(path->dentry);
+	if (IS_ERR(newmnt)) {
+		cFYI(1, "leaving %s [automount failed]" , __func__);
+		return newmnt;
+	}
+
+	mntget(newmnt); /* prevent immediate expiration */
+	mnt_set_expiry(newmnt, &cifs_dfs_automount_list);
+	schedule_delayed_work(&cifs_dfs_automount_task,
+			      cifs_dfs_mountpoint_expiry_timeout);
+	cFYI(1, "leaving %s [ok]" , __func__);
+	return newmnt;
 }
 
 const struct inode_operations cifs_dfs_referral_inode_operations = {
-	.follow_link = cifs_dfs_follow_mountpoint,
 };
-

fs/cifs/cifsfs.h

@@ -93,6 +93,12 @@ extern int cifs_readdir(struct file *file, void *direntry, filldir_t filldir);
 extern const struct dentry_operations cifs_dentry_ops;
 extern const struct dentry_operations cifs_ci_dentry_ops;
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
+extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
+#else
+#define cifs_dfs_d_automount NULL
+#endif
+
 /* Functions related to symlinks */
 extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
 extern void cifs_put_link(struct dentry *direntry,

fs/cifs/dir.c

@@ -675,6 +675,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
 
 const struct dentry_operations cifs_dentry_ops = {
 	.d_revalidate = cifs_d_revalidate,
+	.d_automount = cifs_dfs_d_automount,
 /* d_delete:       cifs_d_delete,      */ /* not needed except for debugging */
 };
 
@@ -711,4 +712,5 @@ const struct dentry_operations cifs_ci_dentry_ops = {
 	.d_revalidate = cifs_d_revalidate,
 	.d_hash = cifs_ci_hash,
 	.d_compare = cifs_ci_compare,
+	.d_automount = cifs_dfs_d_automount,
 };

fs/cifs/inode.c

@@ -32,7 +32,7 @@
 #include "fscache.h"
 
 
-static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
+static void cifs_set_ops(struct inode *inode)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 
@@ -60,7 +60,7 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
 		break;
 	case S_IFDIR:
 #ifdef CONFIG_CIFS_DFS_UPCALL
-		if (is_dfs_referral) {
+		if (IS_AUTOMOUNT(inode)) {
 			inode->i_op = &cifs_dfs_referral_inode_operations;
 		} else {
 #else /* NO DFS support, treat as a directory */
@@ -167,7 +167,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	}
 	spin_unlock(&inode->i_lock);
 
-	cifs_set_ops(inode, fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL);
+	if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
+		inode->i_flags |= S_AUTOMOUNT;
+	cifs_set_ops(inode);
 }
 
 void

fs/dcache.c

@@ -1380,8 +1380,11 @@ EXPORT_SYMBOL(d_set_d_op);
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
 	spin_lock(&dentry->d_lock);
-	if (inode)
+	if (inode) {
+		if (unlikely(IS_AUTOMOUNT(inode)))
+			dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
 		list_add(&dentry->d_alias, &inode->i_dentry);
+	}
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);

fs/fs_struct.c

@@ -4,6 +4,19 @@
 #include <linux/path.h>
 #include <linux/slab.h>
 #include <linux/fs_struct.h>
+#include "internal.h"
+
+static inline void path_get_longterm(struct path *path)
+{
+	path_get(path);
+	mnt_make_longterm(path->mnt);
+}
+
+static inline void path_put_longterm(struct path *path)
+{
+	mnt_make_shortterm(path->mnt);
+	path_put(path);
+}
 
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
@@ -17,11 +30,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 	write_seqcount_begin(&fs->seq);
 	old_root = fs->root;
 	fs->root = *path;
-	path_get_long(path);
+	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 	if (old_root.dentry)
-		path_put_long(&old_root);
+		path_put_longterm(&old_root);
 }
 
 /*
@@ -36,12 +49,12 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 	write_seqcount_begin(&fs->seq);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
-	path_get_long(path);
+	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 
 	if (old_pwd.dentry)
-		path_put_long(&old_pwd);
+		path_put_longterm(&old_pwd);
 }
 
 void chroot_fs_refs(struct path *old_root, struct path *new_root)
@@ -59,13 +72,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 			write_seqcount_begin(&fs->seq);
 			if (fs->root.dentry == old_root->dentry
 			    && fs->root.mnt == old_root->mnt) {
-				path_get_long(new_root);
+				path_get_longterm(new_root);
 				fs->root = *new_root;
 				count++;
 			}
 			if (fs->pwd.dentry == old_root->dentry
 			    && fs->pwd.mnt == old_root->mnt) {
-				path_get_long(new_root);
+				path_get_longterm(new_root);
 				fs->pwd = *new_root;
 				count++;
 			}
@@ -76,13 +89,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 	while (count--)
-		path_put_long(old_root);
+		path_put_longterm(old_root);
 }
 
 void free_fs_struct(struct fs_struct *fs)
 {
-	path_put_long(&fs->root);
-	path_put_long(&fs->pwd);
+	path_put_longterm(&fs->root);
+	path_put_longterm(&fs->pwd);
 	kmem_cache_free(fs_cachep, fs);
 }
 
@@ -118,9 +131,9 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 
 		spin_lock(&old->lock);
 		fs->root = old->root;
-		path_get_long(&fs->root);
+		path_get_longterm(&fs->root);
 		fs->pwd = old->pwd;
-		path_get_long(&fs->pwd);
+		path_get_longterm(&fs->pwd);
 		spin_unlock(&old->lock);
 	}
 	return fs;

fs/internal.h

@@ -70,6 +70,11 @@ extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
 extern void release_mounts(struct list_head *);
 extern void umount_tree(struct vfsmount *, int, struct list_head *);
 extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
+extern int do_add_mount(struct vfsmount *, struct path *, int);
+extern void mnt_clear_expiry(struct vfsmount *);
+
+extern void mnt_make_longterm(struct vfsmount *);
+extern void mnt_make_shortterm(struct vfsmount *);
 
 extern void __init mnt_init(void);
 

fs/namei.c

@@ -367,18 +367,6 @@ void path_get(struct path *path)
 }
 EXPORT_SYMBOL(path_get);
 
-/**
- * path_get_long - get a long reference to a path
- * @path: path to get the reference to
- *
- * Given a path increment the reference count to the dentry and the vfsmount.
- */
-void path_get_long(struct path *path)
-{
-	mntget_long(path->mnt);
-	dget(path->dentry);
-}
-
 /**
  * path_put - put a reference to a path
  * @path: path to put the reference to
@@ -392,18 +380,6 @@ void path_put(struct path *path)
 }
 EXPORT_SYMBOL(path_put);
 
-/**
- * path_put_long - put a long reference to a path
- * @path: path to put the reference to
- *
- * Given a path decrement the reference count to the dentry and the vfsmount.
- */
-void path_put_long(struct path *path)
-{
-	dput(path->dentry);
-	mntput_long(path->mnt);
-}
-
 /**
  * nameidata_drop_rcu - drop this nameidata out of rcu-walk
  * @nd: nameidata pathwalk data to drop
@@ -800,12 +776,8 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p)
 	touch_atime(link->mnt, dentry);
 	nd_set_link(nd, NULL);
 
-	if (link->mnt != nd->path.mnt) {
-		path_to_nameidata(link, nd);
-		nd->inode = nd->path.dentry->d_inode;
-		dget(dentry);
-	}
-	mntget(link->mnt);
+	if (link->mnt == nd->path.mnt)
+		mntget(link->mnt);
 
 	nd->last_type = LAST_BIND;
 	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
@@ -896,54 +868,169 @@ int follow_up(struct path *path)
 }
 
 /*
- * serialization is taken care of in namespace.c
+ * Perform an automount
+ * - return -EISDIR to tell follow_managed() to stop and return the path we
+ *   were called with.
  */
-static void __follow_mount_rcu(struct nameidata *nd, struct path *path,
-				struct inode **inode)
+static int follow_automount(struct path *path, unsigned flags,
+			    bool *need_mntput)
 {
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted;
-		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
-		if (!mounted)
-			return;
-		path->mnt = mounted;
-		path->dentry = mounted->mnt_root;
-		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
-		*inode = path->dentry->d_inode;
+	struct vfsmount *mnt;
+	int err;
+
+	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
+		return -EREMOTE;
+
+	/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
+	 * and this is the terminal part of the path.
+	 */
+	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_CONTINUE))
+		return -EISDIR; /* we actually want to stop here */
+
+	/* We want to mount if someone is trying to open/create a file of any
+	 * type under the mountpoint, wants to traverse through the mountpoint
+	 * or wants to open the mounted directory.
+	 *
+	 * We don't want to mount if someone's just doing a stat and they've
+	 * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
+	 * appended a '/' to the name.
+	 */
+	if (!(flags & LOOKUP_FOLLOW) &&
+	    !(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
+		       LOOKUP_OPEN | LOOKUP_CREATE)))
+		return -EISDIR;
+
+	current->total_link_count++;
+	if (current->total_link_count >= 40)
+		return -ELOOP;
+
+	mnt = path->dentry->d_op->d_automount(path);
+	if (IS_ERR(mnt)) {
+		/*
+		 * The filesystem is allowed to return -EISDIR here to indicate
+		 * it doesn't want to automount.  For instance, autofs would do
+		 * this so that its userspace daemon can mount on this dentry.
+		 *
+		 * However, we can only permit this if it's a terminal point in
+		 * the path being looked up; if it wasn't then the remainder of
+		 * the path is inaccessible and we should say so.
+		 */
+		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_CONTINUE))
+			return -EREMOTE;
+		return PTR_ERR(mnt);
 	}
-}
 
-static int __follow_mount(struct path *path)
-{
-	int res = 0;
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path);
-		if (!mounted)
-			break;
+	if (!mnt) /* mount collision */
+		return 0;
+
+	/* The new mount record should have at least 2 refs to prevent it being
+	 * expired before we get a chance to add it
+	 */
+	BUG_ON(mnt_get_count(mnt) < 2);
+
+	if (mnt->mnt_sb == path->mnt->mnt_sb &&
+	    mnt->mnt_root == path->dentry) {
+		mnt_clear_expiry(mnt);
+		mntput(mnt);
+		mntput(mnt);
+		return -ELOOP;
+	}
+
+	/* We need to add the mountpoint to the parent.  The filesystem may
+	 * have placed it on an expiry list, and so we need to make sure it
+	 * won't be expired under us if do_add_mount() fails (do_add_mount()
+	 * will eat a reference unconditionally).
+	 */
+	mntget(mnt);
+	err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
+	switch (err) {
+	case -EBUSY:
+		/* Someone else made a mount here whilst we were busy */
+		err = 0;
+	default:
+		mnt_clear_expiry(mnt);
+		mntput(mnt);
+		mntput(mnt);
+		return err;
+	case 0:
+		mntput(mnt);
 		dput(path->dentry);
-		if (res)
+		if (*need_mntput)
 			mntput(path->mnt);
-		path->mnt = mounted;
-		path->dentry = dget(mounted->mnt_root);
-		res = 1;
+		path->mnt = mnt;
+		path->dentry = dget(mnt->mnt_root);
+		*need_mntput = true;
+		return 0;
 	}
-	return res;
 }
 
-static void follow_mount(struct path *path)
+/*
+ * Handle a dentry that is managed in some way.
+ * - Flagged for transit management (autofs)
+ * - Flagged as mountpoint
+ * - Flagged as automount point
+ *
+ * This may only be called in refwalk mode.
+ *
+ * Serialization is taken care of in namespace.c
+ */
+static int follow_managed(struct path *path, unsigned flags)
 {
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path);
-		if (!mounted)
-			break;
-		dput(path->dentry);
-		mntput(path->mnt);
-		path->mnt = mounted;
-		path->dentry = dget(mounted->mnt_root);
+	unsigned managed;
+	bool need_mntput = false;
+	int ret;
+
+	/* Given that we're not holding a lock here, we retain the value in a
+	 * local variable for each dentry as we look at it so that we don't see
+	 * the components of that value change under us */
+	while (managed = ACCESS_ONCE(path->dentry->d_flags),
+	       managed &= DCACHE_MANAGED_DENTRY,
+	       unlikely(managed != 0)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held. */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(path->dentry,
+							   false, false);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (mounted) {
+				dput(path->dentry);
+				if (need_mntput)
+					mntput(path->mnt);
+				path->mnt = mounted;
+				path->dentry = dget(mounted->mnt_root);
+				need_mntput = true;
+				continue;
+			}
+
+			/* Something is mounted on this dentry in another
+			 * namespace and/or whatever was mounted there in this
+			 * namespace got unmounted before we managed to get the
+			 * vfsmount_lock */
+		}
+
+		/* Handle an automount point */
+		if (managed & DCACHE_NEED_AUTOMOUNT) {
+			ret = follow_automount(path, flags, &need_mntput);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+			continue;
+		}
+
+		/* We didn't change the current path point */
+		break;
 	}
+	return 0;
 }
 
-int follow_down(struct path *path)
+int follow_down_one(struct path *path)
 {
 	struct vfsmount *mounted;
 
@@ -958,13 +1045,41 @@ int follow_down(struct path *path)
 	return 0;
 }
 
+/*
+ * Skip to top of mountpoint pile in rcuwalk mode.  We abort the rcu-walk if we
+ * meet a managed dentry and we're not walking to "..".  True is returned to
+ * continue, false to abort.
+ */
+static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
+			       struct inode **inode, bool reverse_transit)
+{
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted;
+		if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
+		    !reverse_transit &&
+		    path->dentry->d_op->d_manage(path->dentry, false, true) < 0)
+			return false;
+		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
+		if (!mounted)
+			break;
+		path->mnt = mounted;
+		path->dentry = mounted->mnt_root;
+		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+		*inode = path->dentry->d_inode;
+	}
+
+	if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+		return reverse_transit;
+	return true;
+}
+
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct inode *inode = nd->inode;
 
 	set_root_rcu(nd);
 
-	while(1) {
+	while (1) {
 		if (nd->path.dentry == nd->root.dentry &&
 		    nd->path.mnt == nd->root.mnt) {
 			break;
@@ -987,12 +1102,80 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		inode = nd->path.dentry->d_inode;
 	}
-	__follow_mount_rcu(nd, &nd->path, &inode);
+	__follow_mount_rcu(nd, &nd->path, &inode, true);
 	nd->inode = inode;
 
 	return 0;
 }
 
+/*
+ * Follow down to the covering mount currently visible to userspace.  At each
+ * point, the filesystem owning that dentry may be queried as to whether the
+ * caller is permitted to proceed or not.
+ *
+ * Care must be taken as namespace_sem may be held (indicated by mounting_here
+ * being true).
+ */
+int follow_down(struct path *path, bool mounting_here)
+{
+	unsigned managed;
+	int ret;
+
+	while (managed = ACCESS_ONCE(path->dentry->d_flags),
+	       unlikely(managed & DCACHE_MANAGED_DENTRY)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held.
+		 *
+		 * We indicate to the filesystem if someone is trying to mount
+		 * something here.  This gives autofs the chance to deny anyone
+		 * other than its daemon the right to mount on its
+		 * superstructure.
+		 *
+		 * The filesystem may sleep at this point.
+		 */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(
+				path->dentry, mounting_here, false);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (!mounted)
+				break;
+			dput(path->dentry);
+			mntput(path->mnt);
+			path->mnt = mounted;
+			path->dentry = dget(mounted->mnt_root);
+			continue;
+		}
+
+		/* Don't handle automount points here */
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
+ */
+static void follow_mount(struct path *path)
+{
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted = lookup_mnt(path);
+		if (!mounted)
+			break;
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
+	}
+}
+
 static void follow_dotdot(struct nameidata *nd)
 {
 	set_root(nd);
@@ -1057,12 +1240,14 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
 	struct inode *dir;
+	int err;
+
 	/*
 	 * See if the low-level filesystem might want
 	 * to use its own hash..
 	 */
 	if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
-		int err = parent->d_op->d_hash(parent, nd->inode, name);
+		err = parent->d_op->d_hash(parent, nd->inode, name);
 		if (err < 0)
 			return err;
 	}
@@ -1089,22 +1274,28 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		nd->seq = seq;
 		if (dentry->d_flags & DCACHE_OP_REVALIDATE)
 			goto need_revalidate;
+done2:
 		path->mnt = mnt;
 		path->dentry = dentry;
-		__follow_mount_rcu(nd, path, inode);
-	} else {
-		dentry = __d_lookup(parent, name);
-		if (!dentry)
-			goto need_lookup;
+		if (likely(__follow_mount_rcu(nd, path, inode, false)))
+			return 0;
+		if (nameidata_drop_rcu(nd))
+			return -ECHILD;
+		/* fallthru */
+	}
+	dentry = __d_lookup(parent, name);
+	if (!dentry)
+		goto need_lookup;
 found:
-		if (dentry->d_flags & DCACHE_OP_REVALIDATE)
-			goto need_revalidate;
+	if (dentry->d_flags & DCACHE_OP_REVALIDATE)
+		goto need_revalidate;
 done:
-		path->mnt = mnt;
-		path->dentry = dentry;
-		__follow_mount(path);
-		*inode = path->dentry->d_inode;
-	}
+	path->mnt = mnt;
+	path->dentry = dentry;
+	err = follow_managed(path, nd->flags);
+	if (unlikely(err < 0))
+		return err;
+	*inode = path->dentry->d_inode;
 	return 0;
 
 need_lookup:
@@ -1143,23 +1334,14 @@ need_revalidate:
 		goto need_lookup;
 	if (IS_ERR(dentry))
 		goto fail;
+	if (nd->flags & LOOKUP_RCU)
+		goto done2;
 	goto done;
 
 fail:
 	return PTR_ERR(dentry);
 }
 
-/*
- * This is a temporary kludge to deal with "automount" symlinks; proper
- * solution is to trigger them on follow_mount(), so that do_lookup()
- * would DTRT.  To be killed before 2.6.34-final.
- */
-static inline int follow_on_final(struct inode *inode, unsigned lookup_flags)
-{
-	return inode && unlikely(inode->i_op->follow_link) &&
-		((lookup_flags & LOOKUP_FOLLOW) || S_ISDIR(inode->i_mode));
-}
-
 /*
  * Name resolution.
  * This is the basic name resolution function, turning a pathname into
@@ -1298,7 +1480,8 @@ last_component:
 		err = do_lookup(nd, &this, &next, &inode);
 		if (err)
 			break;
-		if (follow_on_final(inode, lookup_flags)) {
+		if (inode && unlikely(inode->i_op->follow_link) &&
+		    (lookup_flags & LOOKUP_FOLLOW)) {
 			if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
 				return -ECHILD;
 			BUG_ON(inode != next.dentry->d_inode);
@@ -2200,11 +2383,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (open_flag & O_EXCL)
 		goto exit_dput;
 
-	if (__follow_mount(path)) {
-		error = -ELOOP;
-		if (open_flag & O_NOFOLLOW)
-			goto exit_dput;
-	}
+	error = follow_managed(path, nd->flags);
+	if (error < 0)
+		goto exit_dput;
 
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
@@ -2353,8 +2534,7 @@ reval:
 		struct inode *linki = link.dentry->d_inode;
 		void *cookie;
 		error = -ELOOP;
-		/* S_ISDIR part is a temporary automount kludge */
-		if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(linki->i_mode))
+		if (!(nd.flags & LOOKUP_FOLLOW))
 			goto exit_dput;
 		if (count++ == 32)
 			goto exit_dput;
@@ -3413,6 +3593,7 @@ const struct inode_operations page_symlink_inode_operations = {
 };
 
 EXPORT_SYMBOL(user_path_at);
+EXPORT_SYMBOL(follow_down_one);
 EXPORT_SYMBOL(follow_down);
 EXPORT_SYMBOL(follow_up);
 EXPORT_SYMBOL(get_write_access); /* binfmt_aout */

fs/namespace.c

@@ -183,7 +183,7 @@ static inline void mnt_dec_count(struct vfsmount *mnt)
 unsigned int mnt_get_count(struct vfsmount *mnt)
 {
 #ifdef CONFIG_SMP
-	unsigned int count = atomic_read(&mnt->mnt_longrefs);
+	unsigned int count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -217,7 +217,7 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		if (!mnt->mnt_pcp)
 			goto out_free_devname;
 
-		atomic_set(&mnt->mnt_longrefs, 1);
+		this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
 #else
 		mnt->mnt_count = 1;
 		mnt->mnt_writers = 0;
@@ -624,8 +624,11 @@ static void commit_tree(struct vfsmount *mnt)
 	BUG_ON(parent == mnt);
 
 	list_add_tail(&head, &mnt->mnt_list);
-	list_for_each_entry(m, &head, mnt_list)
+	list_for_each_entry(m, &head, mnt_list) {
 		m->mnt_ns = n;
+		atomic_inc(&m->mnt_longterm);
+	}
+
 	list_splice(&head, n->list.prev);
 
 	list_add_tail(&mnt->mnt_hash, mount_hashtable +
@@ -734,51 +737,30 @@ static inline void mntfree(struct vfsmount *mnt)
 	deactivate_super(sb);
 }
 
-#ifdef CONFIG_SMP
-static inline void __mntput(struct vfsmount *mnt, int longrefs)
+static void mntput_no_expire(struct vfsmount *mnt)
 {
-	if (!longrefs) {
 put_again:
-		br_read_lock(vfsmount_lock);
-		if (likely(atomic_read(&mnt->mnt_longrefs))) {
-			mnt_dec_count(mnt);
-			br_read_unlock(vfsmount_lock);
-			return;
-		}
+#ifdef CONFIG_SMP
+	br_read_lock(vfsmount_lock);
+	if (likely(atomic_read(&mnt->mnt_longterm))) {
+		mnt_dec_count(mnt);
 		br_read_unlock(vfsmount_lock);
-	} else {
-		BUG_ON(!atomic_read(&mnt->mnt_longrefs));
-		if (atomic_add_unless(&mnt->mnt_longrefs, -1, 1))
-			return;
+		return;
 	}
+	br_read_unlock(vfsmount_lock);
 
 	br_write_lock(vfsmount_lock);
-	if (!longrefs)
-		mnt_dec_count(mnt);
-	else
-		atomic_dec(&mnt->mnt_longrefs);
+	mnt_dec_count(mnt);
 	if (mnt_get_count(mnt)) {
 		br_write_unlock(vfsmount_lock);
 		return;
 	}
-	if (unlikely(mnt->mnt_pinned)) {
-		mnt_add_count(mnt, mnt->mnt_pinned + 1);
-		mnt->mnt_pinned = 0;
-		br_write_unlock(vfsmount_lock);
-		acct_auto_close_mnt(mnt);
-		goto put_again;
-	}
-	br_write_unlock(vfsmount_lock);
-	mntfree(mnt);
-}
 #else
-static inline void __mntput(struct vfsmount *mnt, int longrefs)
-{
-put_again:
 	mnt_dec_count(mnt);
 	if (likely(mnt_get_count(mnt)))
 		return;
 	br_write_lock(vfsmount_lock);
+#endif
 	if (unlikely(mnt->mnt_pinned)) {
 		mnt_add_count(mnt, mnt->mnt_pinned + 1);
 		mnt->mnt_pinned = 0;
@@ -789,12 +771,6 @@ put_again:
 	br_write_unlock(vfsmount_lock);
 	mntfree(mnt);
 }
-#endif
-
-static void mntput_no_expire(struct vfsmount *mnt)
-{
-	__mntput(mnt, 0);
-}
 
 void mntput(struct vfsmount *mnt)
 {
@@ -802,7 +778,7 @@ void mntput(struct vfsmount *mnt)
 		/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
 		if (unlikely(mnt->mnt_expiry_mark))
 			mnt->mnt_expiry_mark = 0;
-		__mntput(mnt, 0);
+		mntput_no_expire(mnt);
 	}
 }
 EXPORT_SYMBOL(mntput);
@@ -815,33 +791,6 @@ struct vfsmount *mntget(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL(mntget);
 
-void mntput_long(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	if (mnt) {
-		/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
-		if (unlikely(mnt->mnt_expiry_mark))
-			mnt->mnt_expiry_mark = 0;
-		__mntput(mnt, 1);
-	}
-#else
-	mntput(mnt);
-#endif
-}
-EXPORT_SYMBOL(mntput_long);
-
-struct vfsmount *mntget_long(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	if (mnt)
-		atomic_inc(&mnt->mnt_longrefs);
-	return mnt;
-#else
-	return mntget(mnt);
-#endif
-}
-EXPORT_SYMBOL(mntget_long);
-
 void mnt_pin(struct vfsmount *mnt)
 {
 	br_write_lock(vfsmount_lock);
@@ -1216,7 +1165,7 @@ void release_mounts(struct list_head *head)
 			dput(dentry);
 			mntput(m);
 		}
-		mntput_long(mnt);
+		mntput(mnt);
 	}
 }
 
@@ -1226,19 +1175,21 @@ void release_mounts(struct list_head *head)
  */
 void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 {
+	LIST_HEAD(tmp_list);
 	struct vfsmount *p;
 
 	for (p = mnt; p; p = next_mnt(p, mnt))
-		list_move(&p->mnt_hash, kill);
+		list_move(&p->mnt_hash, &tmp_list);
 
 	if (propagate)
-		propagate_umount(kill);
+		propagate_umount(&tmp_list);
 
-	list_for_each_entry(p, kill, mnt_hash) {
+	list_for_each_entry(p, &tmp_list, mnt_hash) {
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
+		atomic_dec(&p->mnt_longterm);
 		list_del_init(&p->mnt_child);
 		if (p->mnt_parent != p) {
 			p->mnt_parent->mnt_ghosts++;
@@ -1246,6 +1197,7 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
 	}
+	list_splice(&tmp_list, kill);
 }
 
 static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);
@@ -1844,9 +1796,10 @@ static int do_move_mount(struct path *path, char *old_name)
 		return err;
 
 	down_write(&namespace_sem);
-	while (d_mountpoint(path->dentry) &&
-	       follow_down(path))
-		;
+	err = follow_down(path, true);
+	if (err < 0)
+		goto out;
+
 	err = -EINVAL;
 	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
 		goto out;
@@ -1924,15 +1877,14 @@ static int do_new_mount(struct path *path, char *type, int flags,
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
-	return do_add_mount(mnt, path, mnt_flags, NULL);
+	return do_add_mount(mnt, path, mnt_flags);
 }
 
 /*
  * add a mount into a namespace's mount tree
- * - provide the option of adding the new mount to an expiration list
+ * - this unconditionally eats one of the caller's references to newmnt.
  */
-int do_add_mount(struct vfsmount *newmnt, struct path *path,
-		 int mnt_flags, struct list_head *fslist)
+int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
 {
 	int err;
 
@@ -1940,9 +1892,10 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 
 	down_write(&namespace_sem);
 	/* Something was mounted here while we slept */
-	while (d_mountpoint(path->dentry) &&
-	       follow_down(path))
-		;
+	err = follow_down(path, true);
+	if (err < 0)
+		goto unlock;
+
 	err = -EINVAL;
 	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
 		goto unlock;
@@ -1961,19 +1914,45 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 	if ((err = graft_tree(newmnt, path)))
 		goto unlock;
 
-	if (fslist) /* add to the specified expiration list */
-		list_add_tail(&newmnt->mnt_expire, fslist);
-
 	up_write(&namespace_sem);
 	return 0;
 
 unlock:
 	up_write(&namespace_sem);
-	mntput_long(newmnt);
+	mntput(newmnt);
 	return err;
 }
 
-EXPORT_SYMBOL_GPL(do_add_mount);
+/**
+ * mnt_set_expiry - Put a mount on an expiration list
+ * @mnt: The mount to list.
+ * @expiry_list: The list to add the mount to.
+ */
+void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
+{
+	down_write(&namespace_sem);
+	br_write_lock(vfsmount_lock);
+
+	list_add_tail(&mnt->mnt_expire, expiry_list);
+
+	br_write_unlock(vfsmount_lock);
+	up_write(&namespace_sem);
+}
+EXPORT_SYMBOL(mnt_set_expiry);
+
+/*
+ * Remove a vfsmount from any expiration list it may be on
+ */
+void mnt_clear_expiry(struct vfsmount *mnt)
+{
+	if (!list_empty(&mnt->mnt_expire)) {
+		down_write(&namespace_sem);
+		br_write_lock(vfsmount_lock);
+		list_del_init(&mnt->mnt_expire);
+		br_write_unlock(vfsmount_lock);
+		up_write(&namespace_sem);
+	}
+}
 
 /*
  * process a list of expirable mountpoints with the intent of discarding any
@@ -2262,6 +2241,20 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	return new_ns;
 }
 
+void mnt_make_longterm(struct vfsmount *mnt)
+{
+	atomic_inc(&mnt->mnt_longterm);
+}
+
+void mnt_make_shortterm(struct vfsmount *mnt)
+{
+	if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
+		return;
+	br_write_lock(vfsmount_lock);
+	atomic_dec(&mnt->mnt_longterm);
+	br_write_unlock(vfsmount_lock);
+}
+
 /*
  * Allocate a new namespace structure and populate it with contents
  * copied from the namespace of the passed in task structure.
@@ -2299,14 +2292,19 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	q = new_ns->root;
 	while (p) {
 		q->mnt_ns = new_ns;
+		atomic_inc(&q->mnt_longterm);
 		if (fs) {
 			if (p == fs->root.mnt) {
+				fs->root.mnt = mntget(q);
+				atomic_inc(&q->mnt_longterm);
+				mnt_make_shortterm(p);
 				rootmnt = p;
-				fs->root.mnt = mntget_long(q);
 			}
 			if (p == fs->pwd.mnt) {
+				fs->pwd.mnt = mntget(q);
+				atomic_inc(&q->mnt_longterm);
+				mnt_make_shortterm(p);
 				pwdmnt = p;
-				fs->pwd.mnt = mntget_long(q);
 			}
 		}
 		p = next_mnt(p, mnt_ns->root);
@@ -2315,9 +2313,9 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	up_write(&namespace_sem);
 
 	if (rootmnt)
-		mntput_long(rootmnt);
+		mntput(rootmnt);
 	if (pwdmnt)
-		mntput_long(pwdmnt);
+		mntput(pwdmnt);
 
 	return new_ns;
 }
@@ -2350,6 +2348,7 @@ struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
 	new_ns = alloc_mnt_ns();
 	if (!IS_ERR(new_ns)) {
 		mnt->mnt_ns = new_ns;
+		atomic_inc(&mnt->mnt_longterm);
 		new_ns->root = mnt;
 		list_add(&new_ns->list, &new_ns->root->mnt_list);
 	}

fs/nfs/dir.c

@@ -970,7 +970,7 @@ int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 
-	if (test_bit(NFS_INO_MOUNTPOINT, &NFS_I(inode)->flags))
+	if (IS_AUTOMOUNT(inode))
 		return 0;
 	if (nd != NULL) {
 		/* VFS wants an on-the-wire revalidation */
@@ -1173,6 +1173,7 @@ 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,
 };
 
 static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
@@ -1246,6 +1247,7 @@ const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs_open_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
+	.d_automount	= nfs_d_automount,
 };
 
 /*

fs/nfs/inode.c

@@ -300,7 +300,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 				else
 					inode->i_op = &nfs_mountpoint_inode_operations;
 				inode->i_fop = NULL;
-				set_bit(NFS_INO_MOUNTPOINT, &nfsi->flags);
+				inode->i_flags |= S_AUTOMOUNT;
 			}
 		} else if (S_ISLNK(inode->i_mode))
 			inode->i_op = &nfs_symlink_inode_operations;
@@ -1208,7 +1208,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	/* Update the fsid? */
 	if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
 			!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
-			!test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags))
+			!IS_AUTOMOUNT(inode))
 		server->fsid = fattr->fsid;
 
 	/*

fs/nfs/internal.h

@@ -252,6 +252,7 @@ extern char *nfs_path(const char *base,
 		      const struct dentry *droot,
 		      const 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 *);

fs/nfs/namespace.c

@@ -97,9 +97,8 @@ Elong:
 }
 
 /*
- * nfs_follow_mountpoint - handle crossing a mountpoint on the server
- * @dentry - dentry of mountpoint
- * @nd - nameidata info
+ * nfs_d_automount - Handle crossing a mountpoint on the server
+ * @path - The mountpoint
  *
  * When we encounter a mountpoint on the server, we want to set up
  * a mountpoint on the client too, to prevent inode numbers from
@@ -109,87 +108,65 @@ Elong:
  * situation, and that different filesystems may want to use
  * different security flavours.
  */
-static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *nfs_d_automount(struct path *path)
 {
 	struct vfsmount *mnt;
-	struct nfs_server *server = NFS_SERVER(dentry->d_inode);
+	struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
 	struct dentry *parent;
 	struct nfs_fh *fh = NULL;
 	struct nfs_fattr *fattr = NULL;
 	int err;
 
-	dprintk("--> nfs_follow_mountpoint()\n");
+	dprintk("--> nfs_d_automount()\n");
 
-	err = -ESTALE;
-	if (IS_ROOT(dentry))
-		goto out_err;
+	mnt = ERR_PTR(-ESTALE);
+	if (IS_ROOT(path->dentry))
+		goto out_nofree;
 
-	err = -ENOMEM;
+	mnt = ERR_PTR(-ENOMEM);
 	fh = nfs_alloc_fhandle();
 	fattr = nfs_alloc_fattr();
 	if (fh == NULL || fattr == NULL)
-		goto out_err;
+		goto out;
 
 	dprintk("%s: enter\n", __func__);
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
 
-	/* Look it up again */
-	parent = dget_parent(nd->path.dentry);
+	/* Look it up again to get its attributes */
+	parent = dget_parent(path->dentry);
 	err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
-						  &nd->path.dentry->d_name,
+						  &path->dentry->d_name,
 						  fh, fattr);
 	dput(parent);
-	if (err != 0)
-		goto out_err;
+	if (err != 0) {
+		mnt = ERR_PTR(err);
+		goto out;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
-		mnt = nfs_do_refmount(nd->path.mnt, nd->path.dentry);
+		mnt = nfs_do_refmount(path->mnt, path->dentry);
 	else
-		mnt = nfs_do_submount(nd->path.mnt, nd->path.dentry, fh,
-				      fattr);
-	err = PTR_ERR(mnt);
+		mnt = nfs_do_submount(path->mnt, path->dentry, fh, fattr);
 	if (IS_ERR(mnt))
-		goto out_err;
+		goto out;
 
-	mntget(mnt);
-	err = do_add_mount(mnt, &nd->path, nd->path.mnt->mnt_flags|MNT_SHRINKABLE,
-			   &nfs_automount_list);
-	if (err < 0) {
-		mntput(mnt);
-		if (err == -EBUSY)
-			goto out_follow;
-		goto out_err;
-	}
-	path_put(&nd->path);
-	nd->path.mnt = mnt;
-	nd->path.dentry = dget(mnt->mnt_root);
+	dprintk("%s: done, success\n", __func__);
+	mntget(mnt); /* prevent immediate expiration */
+	mnt_set_expiry(mnt, &nfs_automount_list);
 	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+
 out:
 	nfs_free_fattr(fattr);
 	nfs_free_fhandle(fh);
-	dprintk("%s: done, returned %d\n", __func__, err);
-
-	dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
-	return ERR_PTR(err);
-out_err:
-	path_put(&nd->path);
-	goto out;
-out_follow:
-	while (d_mountpoint(nd->path.dentry) &&
-	       follow_down(&nd->path))
-		;
-	err = 0;
-	goto out;
+out_nofree:
+	dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+	return mnt;
 }
 
 const struct inode_operations nfs_mountpoint_inode_operations = {
-	.follow_link	= nfs_follow_mountpoint,
 	.getattr	= nfs_getattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
-	.follow_link	= nfs_follow_mountpoint,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)

fs/nfsd/vfs.c

@@ -87,8 +87,9 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 			    .dentry = dget(dentry)};
 	int err = 0;
 
-	while (d_mountpoint(path.dentry) && follow_down(&path))
-		;
+	err = follow_down(&path, false);
+	if (err < 0)
+		goto out;
 
 	exp2 = rqst_exp_get_by_name(rqstp, &path);
 	if (IS_ERR(exp2)) {

fs/pipe.c

@@ -1292,7 +1292,7 @@ static int __init init_pipe_fs(void)
 static void __exit exit_pipe_fs(void)
 {
 	unregister_filesystem(&pipe_fs_type);
-	mntput_long(pipe_mnt);
+	mntput(pipe_mnt);
 }
 
 fs_initcall(init_pipe_fs);

fs/stat.c

@@ -75,11 +75,13 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 	int error = -EINVAL;
 	int lookup_flags = 0;
 
-	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0)
 		goto out;
 
 	if (!(flag & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
+	if (flag & AT_NO_AUTOMOUNT)
+		lookup_flags |= LOOKUP_NO_AUTOMOUNT;
 
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)

fs/super.c

@@ -1141,7 +1141,7 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
 	return mnt;
 
  err:
-	mntput_long(mnt);
+	mntput(mnt);
 	return ERR_PTR(err);
 }
 

include/linux/auto_fs4.h

@@ -24,7 +24,7 @@
 #define AUTOFS_MIN_PROTO_VERSION	3
 #define AUTOFS_MAX_PROTO_VERSION	5
 
-#define AUTOFS_PROTO_SUBVERSION		1
+#define AUTOFS_PROTO_SUBVERSION		2
 
 /* Mask for expire behaviour */
 #define AUTOFS_EXP_IMMEDIATE		1

include/linux/dcache.h

@@ -167,6 +167,8 @@ struct dentry_operations {
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)(struct dentry *, char *, int);
+	struct vfsmount *(*d_automount)(struct path *);
+	int (*d_manage)(struct dentry *, bool, bool);
 } ____cacheline_aligned;
 
 /*
@@ -205,13 +207,18 @@ struct dentry_operations {
 
 #define DCACHE_CANT_MOUNT	0x0100
 #define DCACHE_GENOCIDE		0x0200
-#define DCACHE_MOUNTED		0x0400	/* is a mountpoint */
 
 #define DCACHE_OP_HASH		0x1000
 #define DCACHE_OP_COMPARE	0x2000
 #define DCACHE_OP_REVALIDATE	0x4000
 #define DCACHE_OP_DELETE	0x8000
 
+#define DCACHE_MOUNTED		0x10000	/* is a mountpoint */
+#define DCACHE_NEED_AUTOMOUNT	0x20000	/* handle automount on this dir */
+#define DCACHE_MANAGE_TRANSIT	0x40000	/* manage transit from this dirent */
+#define DCACHE_MANAGED_DENTRY \
+	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
+
 extern seqlock_t rename_lock;
 
 static inline int dname_external(struct dentry *dentry)
@@ -399,7 +406,12 @@ static inline void dont_mount(struct dentry *dentry)
 
 extern void dput(struct dentry *);
 
-static inline int d_mountpoint(struct dentry *dentry)
+static inline bool d_managed(struct dentry *dentry)
+{
+	return dentry->d_flags & DCACHE_MANAGED_DENTRY;
+}
+
+static inline bool d_mountpoint(struct dentry *dentry)
 {
 	return dentry->d_flags & DCACHE_MOUNTED;
 }

include/linux/fcntl.h

@@ -45,6 +45,7 @@
 #define AT_REMOVEDIR		0x200   /* Remove directory instead of
                                            unlinking file.  */
 #define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
 
 #ifdef __KERNEL__
 

include/linux/fs.h

@@ -242,6 +242,7 @@ struct inodes_stat_t {
 #define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
 #define S_PRIVATE	512	/* Inode is fs-internal */
 #define S_IMA		1024	/* Inode has an associated IMA struct */
+#define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -277,6 +278,7 @@ struct inodes_stat_t {
 #define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
 #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
+#define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
 
 /* the read-only stuff doesn't really belong here, but any other place is
    probably as bad and I don't want to create yet another include file. */

include/linux/mount.h

@@ -60,7 +60,7 @@ struct vfsmount {
 	struct super_block *mnt_sb;	/* pointer to superblock */
 #ifdef CONFIG_SMP
 	struct mnt_pcp __percpu *mnt_pcp;
-	atomic_t mnt_longrefs;
+	atomic_t mnt_longterm;		/* how many of the refs are longterm */
 #else
 	int mnt_count;
 	int mnt_writers;
@@ -96,8 +96,6 @@ extern int mnt_clone_write(struct vfsmount *mnt);
 extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mntput(struct vfsmount *mnt);
 extern struct vfsmount *mntget(struct vfsmount *mnt);
-extern void mntput_long(struct vfsmount *mnt);
-extern struct vfsmount *mntget_long(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
 extern void mnt_unpin(struct vfsmount *mnt);
 extern int __mnt_is_readonly(struct vfsmount *mnt);
@@ -110,12 +108,7 @@ extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
 				      void *data);
 
-struct nameidata;
-
-struct path;
-extern int do_add_mount(struct vfsmount *newmnt, struct path *path,
-			int mnt_flags, struct list_head *fslist);
-
+extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);
 
 extern dev_t name_to_dev_t(char *name);

include/linux/namei.h

@@ -45,6 +45,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
  *  - ending slashes ok even for nonexistent files
  *  - internal "there are more path components" flag
  *  - dentry cache is untrusted; force a real lookup
+ *  - suppress terminal automount
  */
 #define LOOKUP_FOLLOW		0x0001
 #define LOOKUP_DIRECTORY	0x0002
@@ -53,6 +54,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_PARENT		0x0010
 #define LOOKUP_REVAL		0x0020
 #define LOOKUP_RCU		0x0040
+#define LOOKUP_NO_AUTOMOUNT	0x0080
 /*
  * Intent data
  */
@@ -79,7 +81,8 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry
 
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 
-extern int follow_down(struct path *);
+extern int follow_down_one(struct path *);
+extern int follow_down(struct path *, bool);
 extern int follow_up(struct path *);
 
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);

include/linux/nfs_fs.h

@@ -215,7 +215,6 @@ struct nfs_inode {
 #define NFS_INO_ADVISE_RDPLUS	(0)		/* advise readdirplus */
 #define NFS_INO_STALE		(1)		/* possible stale inode */
 #define NFS_INO_ACL_LRU_SET	(2)		/* Inode is on the LRU list */
-#define NFS_INO_MOUNTPOINT	(3)		/* inode is remote mountpoint */
 #define NFS_INO_FLUSHING	(4)		/* inode is flushing out data */
 #define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
 #define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */

include/linux/path.h

@@ -10,9 +10,7 @@ struct path {
 };
 
 extern void path_get(struct path *);
-extern void path_get_long(struct path *);
 extern void path_put(struct path *);
-extern void path_put_long(struct path *);
 
 static inline int path_equal(const struct path *path1, const struct path *path2)
 {