namespace.c

EXPORT_SYMBOL(may_umount_tree);

/**
 * may_umount - check if a mount point is busy
 * @mnt: root of mount
 *
 * This is called to check if a mount point has any
 * open files, pwds, chroots or sub mounts. If the
 * mount has sub mounts this will return busy
 * regardless of whether the sub mounts are busy.
 *
 * Doesn't take quota and stuff into account. IOW, in some cases it will
 * give false negatives. The main reason why it's here is that we need
 * a non-destructive way to look for easily umountable filesystems.
 */
int may_umount(struct vfsmount *mnt)
{
	int ret = 1;
	down_read(&namespace_sem);
	br_read_lock(vfsmount_lock);
	if (propagate_mount_busy(mnt, 2))
		ret = 0;
	br_read_unlock(vfsmount_lock);
	up_read(&namespace_sem);
	return ret;
}

EXPORT_SYMBOL(may_umount);

void release_mounts(struct list_head *head)
{
	struct vfsmount *mnt;
	while (!list_empty(head)) {
		mnt = list_first_entry(head, struct vfsmount, mnt_hash);
		list_del_init(&mnt->mnt_hash);
		if (mnt->mnt_parent != mnt) {
			struct dentry *dentry;
			struct vfsmount *m;

			br_write_lock(vfsmount_lock);
			dentry = mnt->mnt_mountpoint;
			m = mnt->mnt_parent;
			mnt->mnt_mountpoint = mnt->mnt_root;
			mnt->mnt_parent = mnt;
			m->mnt_ghosts--;
			br_write_unlock(vfsmount_lock);
			dput(dentry);
			mntput(m);
		}
		mntput(mnt);
	}
}

/*
 * vfsmount lock must be held for write
 * namespace_sem must be held for write
 */
void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
{
	struct vfsmount *p;

	for (p = mnt; p; p = next_mnt(p, mnt))
		list_move(&p->mnt_hash, kill);

	if (propagate)
		propagate_umount(kill);

	list_for_each_entry(p, kill, mnt_hash) {
		list_del_init(&p->mnt_expire);
		list_del_init(&p->mnt_list);
		__touch_mnt_namespace(p->mnt_ns);
		p->mnt_ns = NULL;
		list_del_init(&p->mnt_child);
		if (p->mnt_parent != p) {
			p->mnt_parent->mnt_ghosts++;
			p->mnt_mountpoint->d_mounted--;
		}
		change_mnt_propagation(p, MS_PRIVATE);
	}
}

static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);

static int do_umount(struct vfsmount *mnt, int flags)
{
	struct super_block *sb = mnt->mnt_sb;
	int retval;
	LIST_HEAD(umount_list);

	retval = security_sb_umount(mnt, flags);
	if (retval)
		return retval;

	/*
	 * Allow userspace to request a mountpoint be expired rather than
	 * unmounting unconditionally. Unmount only happens if:
	 *  (1) the mark is already set (the mark is cleared by mntput())
	 *  (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
	 */
	if (flags & MNT_EXPIRE) {
		if (mnt == current->fs->root.mnt ||
		    flags & (MNT_FORCE | MNT_DETACH))
			return -EINVAL;

		if (atomic_read(&mnt->mnt_count) != 2)
			return -EBUSY;

		if (!xchg(&mnt->mnt_expiry_mark, 1))
			return -EAGAIN;
	}

	/*
	 * If we may have to abort operations to get out of this
	 * mount, and they will themselves hold resources we must
	 * allow the fs to do things. In the Unix tradition of
	 * 'Gee thats tricky lets do it in userspace' the umount_begin
	 * might fail to complete on the first run through as other tasks
	 * must return, and the like. Thats for the mount program to worry
	 * about for the moment.
	 */

	if (flags & MNT_FORCE && sb->s_op->umount_begin) {
		sb->s_op->umount_begin(sb);
	}

	/*
	 * No sense to grab the lock for this test, but test itself looks
	 * somewhat bogus. Suggestions for better replacement?
	 * Ho-hum... In principle, we might treat that as umount + switch
	 * to rootfs. GC would eventually take care of the old vfsmount.
	 * Actually it makes sense, especially if rootfs would contain a
	 * /reboot - static binary that would close all descriptors and
	 * call reboot(9). Then init(8) could umount root and exec /reboot.
	 */
	if (mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
		/*
		 * Special case for "unmounting" root ...
		 * we just try to remount it readonly.
		 */
		down_write(&sb->s_umount);
		if (!(sb->s_flags & MS_RDONLY))
			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
		up_write(&sb->s_umount);
		return retval;
	}

	down_write(&namespace_sem);
	br_write_lock(vfsmount_lock);
	event++;

	if (!(flags & MNT_DETACH))
		shrink_submounts(mnt, &umount_list);

	retval = -EBUSY;
	if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) {
		if (!list_empty(&mnt->mnt_list))
			umount_tree(mnt, 1, &umount_list);
		retval = 0;
	}
	br_write_unlock(vfsmount_lock);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
	return retval;
}

/*
 * Now umount can handle mount points as well as block devices.
 * This is important for filesystems which use unnamed block devices.
 *
 * We now support a flag for forced unmount like the other 'big iron'
 * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
 */

SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
{
	struct path path;
	int retval;
	int lookup_flags = 0;

	if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
		return -EINVAL;

	if (!(flags & UMOUNT_NOFOLLOW))
		lookup_flags |= LOOKUP_FOLLOW;

	retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
	if (retval)
		goto out;
	retval = -EINVAL;
	if (path.dentry != path.mnt->mnt_root)
		goto dput_and_out;
	if (!check_mnt(path.mnt))
		goto dput_and_out;

	retval = -EPERM;
	if (!capable(CAP_SYS_ADMIN))
		goto dput_and_out;

	retval = do_umount(path.mnt, flags);
dput_and_out:
	/* we mustn't call path_put() as that would clear mnt_expiry_mark */
	dput(path.dentry);
	mntput_no_expire(path.mnt);
out:
	return retval;
}

#ifdef __ARCH_WANT_SYS_OLDUMOUNT

/*
 *	The 2.0 compatible umount. No flags.
 */
SYSCALL_DEFINE1(oldumount, char __user *, name)
{
	return sys_umount(name, 0);
}

#endif

static int mount_is_safe(struct path *path)
{
	if (capable(CAP_SYS_ADMIN))
		return 0;
	return -EPERM;
#ifdef notyet
	if (S_ISLNK(path->dentry->d_inode->i_mode))
		return -EPERM;
	if (path->dentry->d_inode->i_mode & S_ISVTX) {
		if (current_uid() != path->dentry->d_inode->i_uid)
			return -EPERM;
	}
	if (inode_permission(path->dentry->d_inode, MAY_WRITE))
		return -EPERM;
	return 0;
#endif
}

struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
					int flag)
{
	struct vfsmount *res, *p, *q, *r, *s;
	struct path path;

	if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt))
		return NULL;

	res = q = clone_mnt(mnt, dentry, flag);
	if (!q)
		goto Enomem;
	q->mnt_mountpoint = mnt->mnt_mountpoint;

	p = mnt;
	list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
		if (!is_subdir(r->mnt_mountpoint, dentry))
			continue;

		for (s = r; s; s = next_mnt(s, r)) {
			if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(s)) {
				s = skip_mnt_tree(s);
				continue;
			}
			while (p != s->mnt_parent) {
				p = p->mnt_parent;
				q = q->mnt_parent;
			}
			p = s;
			path.mnt = q;
			path.dentry = p->mnt_mountpoint;
			q = clone_mnt(p, p->mnt_root, flag);
			if (!q)
				goto Enomem;
			br_write_lock(vfsmount_lock);
			list_add_tail(&q->mnt_list, &res->mnt_list);
			attach_mnt(q, &path);
			br_write_unlock(vfsmount_lock);
		}
	}
	return res;
Enomem:
	if (res) {
		LIST_HEAD(umount_list);
		br_write_lock(vfsmount_lock);
		umount_tree(res, 0, &umount_list);
		br_write_unlock(vfsmount_lock);
		release_mounts(&umount_list);
	}
	return NULL;
}

struct vfsmount *collect_mounts(struct path *path)
{
	struct vfsmount *tree;
	down_write(&namespace_sem);
	tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE);
	up_write(&namespace_sem);
	return tree;
}

void drop_collected_mounts(struct vfsmount *mnt)
{
	LIST_HEAD(umount_list);
	down_write(&namespace_sem);
	br_write_lock(vfsmount_lock);
	umount_tree(mnt, 0, &umount_list);
	br_write_unlock(vfsmount_lock);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
}

int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
		   struct vfsmount *root)
{
	struct vfsmount *mnt;
	int res = f(root, arg);
	if (res)
		return res;
	list_for_each_entry(mnt, &root->mnt_list, mnt_list) {
		res = f(mnt, arg);
		if (res)
			return res;
	}
	return 0;
}

static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
{
	struct vfsmount *p;

	for (p = mnt; p != end; p = next_mnt(p, mnt)) {
		if (p->mnt_group_id && !IS_MNT_SHARED(p))
			mnt_release_group_id(p);
	}
}

static int invent_group_ids(struct vfsmount *mnt, bool recurse)
{
	struct vfsmount *p;

	for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
		if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
			int err = mnt_alloc_group_id(p);
			if (err) {
				cleanup_group_ids(mnt, p);
				return err;
			}
		}
	}

	return 0;
}

/*
 *  @source_mnt : mount tree to be attached
 *  @nd         : place the mount tree @source_mnt is attached
 *  @parent_nd  : if non-null, detach the source_mnt from its parent and
 *  		   store the parent mount and mountpoint dentry.
 *  		   (done when source_mnt is moved)
 *
 *  NOTE: in the table below explains the semantics when a source mount
 *  of a given type is attached to a destination mount of a given type.
 * ---------------------------------------------------------------------------
 * |         BIND MOUNT OPERATION                                            |
 * |**************************************************************************
 * | source-->| shared        |       private  |       slave    | unbindable |
 * | dest     |               |                |                |            |
 * |   |      |               |                |                |            |
 * |   v      |               |                |                |            |
 * |**************************************************************************
 * |  shared  | shared (++)   |     shared (+) |     shared(+++)|  invalid   |
 * |          |               |                |                |            |
 * |non-shared| shared (+)    |      private   |      slave (*) |  invalid   |
 * ***************************************************************************
 * A bind operation clones the source mount and mounts the clone on the
 * destination mount.
 *
 * (++)  the cloned mount is propagated to all the mounts in the propagation
 * 	 tree of the destination mount and the cloned mount is added to
 * 	 the peer group of the source mount.
 * (+)   the cloned mount is created under the destination mount and is marked
 *       as shared. The cloned mount is added to the peer group of the source
 *       mount.
 * (+++) the mount is propagated to all the mounts in the propagation tree
 *       of the destination mount and the cloned mount is made slave
 *       of the same master as that of the source mount. The cloned mount
 *       is marked as 'shared and slave'.
 * (*)   the cloned mount is made a slave of the same master as that of the
 * 	 source mount.
 *
 * ---------------------------------------------------------------------------
 * |         		MOVE MOUNT OPERATION                                 |
 * |**************************************************************************
 * | source-->| shared        |       private  |       slave    | unbindable |
 * | dest     |               |                |                |            |
 * |   |      |               |                |                |            |
 * |   v      |               |                |                |            |
 * |**************************************************************************
 * |  shared  | shared (+)    |     shared (+) |    shared(+++) |  invalid   |
 * |          |               |                |                |            |
 * |non-shared| shared (+*)   |      private   |    slave (*)   | unbindable |
 * ***************************************************************************
 *
 * (+)  the mount is moved to the destination. And is then propagated to
 * 	all the mounts in the propagation tree of the destination mount.
 * (+*)  the mount is moved to the destination.
 * (+++)  the mount is moved to the destination and is then propagated to
 * 	all the mounts belonging to the destination mount's propagation tree.
 * 	the mount is marked as 'shared and slave'.
 * (*)	the mount continues to be a slave at the new location.
 *
 * if the source mount is a tree, the operations explained above is
 * applied to each mount in the tree.
 * Must be called without spinlocks held, since this function can sleep
 * in allocations.
 */
static int attach_recursive_mnt(struct vfsmount *source_mnt,
			struct path *path, struct path *parent_path)
{
	LIST_HEAD(tree_list);
	struct vfsmount *dest_mnt = path->mnt;
	struct dentry *dest_dentry = path->dentry;
	struct vfsmount *child, *p;
	int err;

	if (IS_MNT_SHARED(dest_mnt)) {
		err = invent_group_ids(source_mnt, true);
		if (err)
			goto out;
	}
	err = propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list);
	if (err)
		goto out_cleanup_ids;

	br_write_lock(vfsmount_lock);

	if (IS_MNT_SHARED(dest_mnt)) {
		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
			set_mnt_shared(p);
	}
	if (parent_path) {
		detach_mnt(source_mnt, parent_path);
		attach_mnt(source_mnt, path);
		touch_mnt_namespace(parent_path->mnt->mnt_ns);
	} else {
		mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt);
		commit_tree(source_mnt);
	}

	list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
		list_del_init(&child->mnt_hash);
		commit_tree(child);
	}
	br_write_unlock(vfsmount_lock);

	return 0;

 out_cleanup_ids:
	if (IS_MNT_SHARED(dest_mnt))
		cleanup_group_ids(source_mnt, NULL);
 out:
	return err;
}

static int graft_tree(struct vfsmount *mnt, struct path *path)
{
	int err;
	if (mnt->mnt_sb->s_flags & MS_NOUSER)
		return -EINVAL;

	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
		return -ENOTDIR;

	err = -ENOENT;
	mutex_lock(&path->dentry->d_inode->i_mutex);
	if (cant_mount(path->dentry))
		goto out_unlock;

	if (!d_unlinked(path->dentry))
		err = attach_recursive_mnt(mnt, path, NULL);
out_unlock:
	mutex_unlock(&path->dentry->d_inode->i_mutex);
	return err;
}

/*
 * Sanity check the flags to change_mnt_propagation.
 */

static int flags_to_propagation_type(int flags)
{
	int type = flags & ~MS_REC;

	/* Fail if any non-propagation flags are set */
	if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
		return 0;
	/* Only one propagation flag should be set */
	if (!is_power_of_2(type))
		return 0;
	return type;
}

/*
 * recursively change the type of the mountpoint.
 */
static int do_change_type(struct path *path, int flag)
{
	struct vfsmount *m, *mnt = path->mnt;
	int recurse = flag & MS_REC;
	int type;
	int err = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (path->dentry != path->mnt->mnt_root)
		return -EINVAL;

	type = flags_to_propagation_type(flag);
	if (!type)
		return -EINVAL;

	down_write(&namespace_sem);
	if (type == MS_SHARED) {
		err = invent_group_ids(mnt, recurse);
		if (err)
			goto out_unlock;
	}

	br_write_lock(vfsmount_lock);
	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
		change_mnt_propagation(m, type);
	br_write_unlock(vfsmount_lock);

 out_unlock:
	up_write(&namespace_sem);
	return err;
}

/*
 * do loopback mount.
 */
static int do_loopback(struct path *path, char *old_name,
				int recurse)
{
	struct path old_path;
	struct vfsmount *mnt = NULL;
	int err = mount_is_safe(path);
	if (err)
		return err;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
	if (err)
		return err;

	down_write(&namespace_sem);
	err = -EINVAL;
	if (IS_MNT_UNBINDABLE(old_path.mnt))
		goto out;

	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
		goto out;

	err = -ENOMEM;
	if (recurse)
		mnt = copy_tree(old_path.mnt, old_path.dentry, 0);
	else
		mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);

	if (!mnt)
		goto out;

	err = graft_tree(mnt, path);
	if (err) {
		LIST_HEAD(umount_list);

		br_write_lock(vfsmount_lock);
		umount_tree(mnt, 0, &umount_list);
		br_write_unlock(vfsmount_lock);
		release_mounts(&umount_list);
	}

out:
	up_write(&namespace_sem);
	path_put(&old_path);
	return err;
}

static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
{
	int error = 0;
	int readonly_request = 0;

	if (ms_flags & MS_RDONLY)
		readonly_request = 1;
	if (readonly_request == __mnt_is_readonly(mnt))
		return 0;

	if (readonly_request)
		error = mnt_make_readonly(mnt);
	else
		__mnt_unmake_readonly(mnt);
	return error;
}

/*
 * change filesystem flags. dir should be a physical root of filesystem.
 * If you've mounted a non-root directory somewhere and want to do remount
 * on it - tough luck.
 */
static int do_remount(struct path *path, int flags, int mnt_flags,
		      void *data)
{
	int err;
	struct super_block *sb = path->mnt->mnt_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!check_mnt(path->mnt))
		return -EINVAL;

	if (path->dentry != path->mnt->mnt_root)
		return -EINVAL;

	down_write(&sb->s_umount);
	if (flags & MS_BIND)
		err = change_mount_flags(path->mnt, flags);
	else
		err = do_remount_sb(sb, flags, data, 0);
	if (!err) {
		br_write_lock(vfsmount_lock);
		mnt_flags |= path->mnt->mnt_flags & MNT_PROPAGATION_MASK;
		path->mnt->mnt_flags = mnt_flags;
		br_write_unlock(vfsmount_lock);
	}
	up_write(&sb->s_umount);
	if (!err) {
		br_write_lock(vfsmount_lock);
		touch_mnt_namespace(path->mnt->mnt_ns);
		br_write_unlock(vfsmount_lock);
	}
	return err;
}

static inline int tree_contains_unbindable(struct vfsmount *mnt)
{
	struct vfsmount *p;
	for (p = mnt; p; p = next_mnt(p, mnt)) {
		if (IS_MNT_UNBINDABLE(p))
			return 1;
	}
	return 0;
}

static int do_move_mount(struct path *path, char *old_name)
{
	struct path old_path, parent_path;
	struct vfsmount *p;
	int err = 0;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
	if (err)
		return err;

	down_write(&namespace_sem);
	while (d_mountpoint(path->dentry) &&
	       follow_down(path))
		;
	err = -EINVAL;
	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
		goto out;

	err = -ENOENT;
	mutex_lock(&path->dentry->d_inode->i_mutex);
	if (cant_mount(path->dentry))
		goto out1;

	if (d_unlinked(path->dentry))
		goto out1;

	err = -EINVAL;
	if (old_path.dentry != old_path.mnt->mnt_root)
		goto out1;

	if (old_path.mnt == old_path.mnt->mnt_parent)
		goto out1;

	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
	      S_ISDIR(old_path.dentry->d_inode->i_mode))
		goto out1;
	/*
	 * Don't move a mount residing in a shared parent.
	 */
	if (old_path.mnt->mnt_parent &&
	    IS_MNT_SHARED(old_path.mnt->mnt_parent))
		goto out1;
	/*
	 * Don't move a mount tree containing unbindable mounts to a destination
	 * mount which is shared.
	 */
	if (IS_MNT_SHARED(path->mnt) &&
	    tree_contains_unbindable(old_path.mnt))
		goto out1;
	err = -ELOOP;
	for (p = path->mnt; p->mnt_parent != p; p = p->mnt_parent)
		if (p == old_path.mnt)
			goto out1;

	err = attach_recursive_mnt(old_path.mnt, path, &parent_path);
	if (err)
		goto out1;

	/* if the mount is moved, it should no longer be expire
	 * automatically */
	list_del_init(&old_path.mnt->mnt_expire);
out1:
	mutex_unlock(&path->dentry->d_inode->i_mutex);
out:
	up_write(&namespace_sem);
	if (!err)
		path_put(&parent_path);
	path_put(&old_path);
	return err;
}

/*
 * create a new mount for userspace and request it to be added into the
 * namespace's tree
 */
static int do_new_mount(struct path *path, char *type, int flags,
			int mnt_flags, char *name, void *data)
{
	struct vfsmount *mnt;

	if (!type)
		return -EINVAL;

	/* we need capabilities... */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	mnt = do_kern_mount(type, flags, name, data);
	if (IS_ERR(mnt))
		return PTR_ERR(mnt);

	return do_add_mount(mnt, path, mnt_flags, NULL);
}

/*
 * add a mount into a namespace's mount tree
 * - provide the option of adding the new mount to an expiration list
 */
int do_add_mount(struct vfsmount *newmnt, struct path *path,
		 int mnt_flags, struct list_head *fslist)
{
	int err;

	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);

	down_write(&namespace_sem);
	/* Something was mounted here while we slept */
	while (d_mountpoint(path->dentry) &&
	       follow_down(path))
		;
	err = -EINVAL;
	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
		goto unlock;

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (path->mnt->mnt_sb == newmnt->mnt_sb &&
	    path->mnt->mnt_root == path->dentry)
		goto unlock;

	err = -EINVAL;
	if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
		goto unlock;

	newmnt->mnt_flags = mnt_flags;
	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(newmnt);
	return err;
}

EXPORT_SYMBOL_GPL(do_add_mount);

/*
 * process a list of expirable mountpoints with the intent of discarding any
 * mountpoints that aren't in use and haven't been touched since last we came
 * here
 */
void mark_mounts_for_expiry(struct list_head *mounts)
{
	struct vfsmount *mnt, *next;
	LIST_HEAD(graveyard);
	LIST_HEAD(umounts);

	if (list_empty(mounts))
		return;

	down_write(&namespace_sem);
	br_write_lock(vfsmount_lock);

	/* extract from the expiration list every vfsmount that matches the
	 * following criteria:
	 * - only referenced by its parent vfsmount
	 * - still marked for expiry (marked on the last call here; marks are
	 *   cleared by mntput())
	 */
	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
			propagate_mount_busy(mnt, 1))
			continue;
		list_move(&mnt->mnt_expire, &graveyard);
	}
	while (!list_empty(&graveyard)) {
		mnt = list_first_entry(&graveyard, struct vfsmount, mnt_expire);
		touch_mnt_namespace(mnt->mnt_ns);
		umount_tree(mnt, 1, &umounts);
	}
	br_write_unlock(vfsmount_lock);
	up_write(&namespace_sem);

	release_mounts(&umounts);
}

EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);

/*
 * Ripoff of 'select_parent()'
 *
 * search the list of submounts for a given mountpoint, and move any
 * shrinkable submounts to the 'graveyard' list.
 */
static int select_submounts(struct vfsmount *parent, struct list_head *graveyard)
{
	struct vfsmount *this_parent = parent;
	struct list_head *next;
	int found = 0;

repeat:
	next = this_parent->mnt_mounts.next;
resume:
	while (next != &this_parent->mnt_mounts) {
		struct list_head *tmp = next;
		struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child);

		next = tmp->next;
		if (!(mnt->mnt_flags & MNT_SHRINKABLE))
			continue;
		/*
		 * Descend a level if the d_mounts list is non-empty.
		 */
		if (!list_empty(&mnt->mnt_mounts)) {
			this_parent = mnt;
			goto repeat;
		}

		if (!propagate_mount_busy(mnt, 1)) {
			list_move_tail(&mnt->mnt_expire, graveyard);
			found++;
		}
	}
	/*
	 * All done at this level ... ascend and resume the search
	 */
	if (this_parent != parent) {
		next = this_parent->mnt_child.next;
		this_parent = this_parent->mnt_parent;
		goto resume;
	}
	return found;
}

/*
 * process a list of expirable mountpoints with the intent of discarding any
 * submounts of a specific parent mountpoint
 *
 * vfsmount_lock must be held for write
 */
static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts)
{
	LIST_HEAD(graveyard);
	struct vfsmount *m;

	/* extract submounts of 'mountpoint' from the expiration list */
	while (select_submounts(mnt, &graveyard)) {
		while (!list_empty(&graveyard)) {
			m = list_first_entry(&graveyard, struct vfsmount,
						mnt_expire);
			touch_mnt_namespace(m->mnt_ns);
			umount_tree(m, 1, umounts);
		}
	}
}

/*
 * Some copy_from_user() implementations do not return the exact number of
 * bytes remaining to copy on a fault.  But copy_mount_options() requires that.
 * Note that this function differs from copy_from_user() in that it will oops
 * on bad values of `to', rather than returning a short copy.
 */
static long exact_copy_from_user(void *to, const void __user * from,
				 unsigned long n)
{
	char *t = to;
	const char __user *f = from;
	char c;

	if (!access_ok(VERIFY_READ, from, n))
		return n;

	while (n) {
		if (__get_user(c, f)) {
			memset(t, 0, n);
			break;
		}
		*t++ = c;
		f++;
		n--;
	}
	return n;
}

int copy_mount_options(const void __user * data, unsigned long *where)
{
	int i;
	unsigned long page;
	unsigned long size;

	*where = 0;
	if (!data)
		return 0;

	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	/* We only care that *some* data at the address the user
	 * gave us is valid.  Just in case, we'll zero
	 * the remainder of the page.
	 */
	/* copy_from_user cannot cross TASK_SIZE ! */
	size = TASK_SIZE - (unsigned long)data;
	if (size > PAGE_SIZE)
		size = PAGE_SIZE;

	i = size - exact_copy_from_user((void *)page, data, size);
	if (!i) {
		free_page(page);
		return -EFAULT;
	}
	if (i != PAGE_SIZE)
		memset((char *)page + i, 0, PAGE_SIZE - i);
	*where = page;
	return 0;
}

int copy_mount_string(const void __user *data, char **where)
{
	char *tmp;

	if (!data) {
		*where = NULL;
		return 0;
	}

	tmp = strndup_user(data, PAGE_SIZE);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	*where = tmp;
	return 0;
}

/*
 * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
 * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
 *
 * data is a (void *) that can point to any structure up to
 * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
 * information (or be NULL).
 *
 * Pre-0.97 versions of mount() didn't have a flags word.
 * When the flags word was introduced its top half was required
 * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.