namespace.c

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

#endif

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

static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry)
{
	while (1) {
		if (d == dentry)
			return 1;
		if (d == NULL || d == d->d_parent)
			return 0;
		d = d->d_parent;
	}
}

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 (!lives_below_in_same_fs(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;
			spin_lock(&vfsmount_lock);
			list_add_tail(&q->mnt_list, &res->mnt_list);
			attach_mnt(q, &path);
			spin_unlock(&vfsmount_lock);
		}
	}
	return res;
Enomem:
	if (res) {
		LIST_HEAD(umount_list);
		spin_lock(&vfsmount_lock);
		umount_tree(res, 0, &umount_list);
		spin_unlock(&vfsmount_lock);
		release_mounts(&umount_list);
	}
	return NULL;
}

struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry)
{
	struct vfsmount *tree;
	down_write(&namespace_sem);
	tree = copy_tree(mnt, 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);
	spin_lock(&vfsmount_lock);
	umount_tree(mnt, 0, &umount_list);
	spin_unlock(&vfsmount_lock);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
}

/*
 *  @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;

	if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list))
		return -EINVAL;

	if (IS_MNT_SHARED(dest_mnt)) {
		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
			set_mnt_shared(p);
	}

	spin_lock(&vfsmount_lock);
	if (parent_path) {
		detach_mnt(source_mnt, parent_path);
		attach_mnt(source_mnt, path);
		touch_mnt_namespace(current->nsproxy->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);
	}
	spin_unlock(&vfsmount_lock);
	return 0;
}

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

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

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

	err = security_sb_check_sb(mnt, &nd->path);
	if (err)
		goto out_unlock;

	err = -ENOENT;
	if (IS_ROOT(nd->path.dentry) || !d_unhashed(nd->path.dentry))
		err = attach_recursive_mnt(mnt, &nd->path, NULL);
out_unlock:
	mutex_unlock(&nd->path.dentry->d_inode->i_mutex);
	if (!err)
		security_sb_post_addmount(mnt, &nd->path);
	return err;
}

/*
 * recursively change the type of the mountpoint.
 * noinline this do_mount helper to save do_mount stack space.
 */
static noinline int do_change_type(struct nameidata *nd, int flag)
{
	struct vfsmount *m, *mnt = nd->path.mnt;
	int recurse = flag & MS_REC;
	int type = flag & ~MS_REC;

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

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

	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
		change_mnt_propagation(m, type);
	spin_unlock(&vfsmount_lock);
	up_write(&namespace_sem);
	return 0;
}

/*
 * do loopback mount.
 * noinline this do_mount helper to save do_mount stack space.
 */
static noinline int do_loopback(struct nameidata *nd, char *old_name,
				int recurse)
{
	struct nameidata old_nd;
	struct vfsmount *mnt = NULL;
	int err = mount_is_safe(nd);
	if (err)
		return err;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
	if (err)
		return err;

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

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

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

	if (!mnt)
		goto out;

	err = graft_tree(mnt, nd);
	if (err) {
		LIST_HEAD(umount_list);
		spin_lock(&vfsmount_lock);
		umount_tree(mnt, 0, &umount_list);
		spin_unlock(&vfsmount_lock);
		release_mounts(&umount_list);
	}

out:
	up_write(&namespace_sem);
	path_put(&old_nd.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.
 * noinline this do_mount helper to save do_mount stack space.
 */
static noinline int do_remount(struct nameidata *nd, int flags, int mnt_flags,
		      void *data)
{
	int err;
	struct super_block *sb = nd->path.mnt->mnt_sb;

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

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

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

	down_write(&sb->s_umount);
	if (flags & MS_BIND)
		err = change_mount_flags(nd->path.mnt, flags);
	else
		err = do_remount_sb(sb, flags, data, 0);
	if (!err)
		nd->path.mnt->mnt_flags = mnt_flags;
	up_write(&sb->s_umount);
	if (!err)
		security_sb_post_remount(nd->path.mnt, flags, data);
	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;
}

/*
 * noinline this do_mount helper to save do_mount stack space.
 */
static noinline int do_move_mount(struct nameidata *nd, char *old_name)
{
	struct nameidata old_nd;
	struct path parent_path;
	struct vfsmount *p;
	int err = 0;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
	if (err)
		return err;

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

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

	if (!IS_ROOT(nd->path.dentry) && d_unhashed(nd->path.dentry))
		goto out1;

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

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

	if (S_ISDIR(nd->path.dentry->d_inode->i_mode) !=
	      S_ISDIR(old_nd.path.dentry->d_inode->i_mode))
		goto out1;
	/*
	 * Don't move a mount residing in a shared parent.
	 */
	if (old_nd.path.mnt->mnt_parent &&
	    IS_MNT_SHARED(old_nd.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(nd->path.mnt) &&
	    tree_contains_unbindable(old_nd.path.mnt))
		goto out1;
	err = -ELOOP;
	for (p = nd->path.mnt; p->mnt_parent != p; p = p->mnt_parent)
		if (p == old_nd.path.mnt)
			goto out1;

	err = attach_recursive_mnt(old_nd.path.mnt, &nd->path, &parent_path);
	if (err)
		goto out1;

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

/*
 * create a new mount for userspace and request it to be added into the
 * namespace's tree
 * noinline this do_mount helper to save do_mount stack space.
 */
static noinline int do_new_mount(struct nameidata *nd, char *type, int flags,
			int mnt_flags, char *name, void *data)
{
	struct vfsmount *mnt;

	if (!type || !memchr(type, 0, PAGE_SIZE))
		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, nd, 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 nameidata *nd,
		 int mnt_flags, struct list_head *fslist)
{
	int err;

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

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (nd->path.mnt->mnt_sb == newmnt->mnt_sb &&
	    nd->path.mnt->mnt_root == nd->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, nd)))
		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);
	spin_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);
	}
	spin_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
 */
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(mnt->mnt_ns);
			umount_tree(mnt, 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;
}

/*
 * 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.
 * Therefore, if this magic number is present, it carries no information
 * and must be discarded.
 */
long do_mount(char *dev_name, char *dir_name, char *type_page,
		  unsigned long flags, void *data_page)
{
	struct nameidata nd;
	int retval = 0;
	int mnt_flags = 0;

	/* Discard magic */
	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
		flags &= ~MS_MGC_MSK;

	/* Basic sanity checks */

	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
		return -EINVAL;
	if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))
		return -EINVAL;

	if (data_page)
		((char *)data_page)[PAGE_SIZE - 1] = 0;

	/* Separate the per-mountpoint flags */
	if (flags & MS_NOSUID)
		mnt_flags |= MNT_NOSUID;
	if (flags & MS_NODEV)
		mnt_flags |= MNT_NODEV;
	if (flags & MS_NOEXEC)
		mnt_flags |= MNT_NOEXEC;
	if (flags & MS_NOATIME)
		mnt_flags |= MNT_NOATIME;
	if (flags & MS_NODIRATIME)
		mnt_flags |= MNT_NODIRATIME;
	if (flags & MS_RELATIME)
		mnt_flags |= MNT_RELATIME;
	if (flags & MS_RDONLY)
		mnt_flags |= MNT_READONLY;

	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);

	/* ... and get the mountpoint */
	retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd);
	if (retval)
		return retval;

	retval = security_sb_mount(dev_name, &nd.path,
				   type_page, flags, data_page);
	if (retval)
		goto dput_out;

	if (flags & MS_REMOUNT)
		retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
				    data_page);
	else if (flags & MS_BIND)
		retval = do_loopback(&nd, dev_name, flags & MS_REC);
	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
		retval = do_change_type(&nd, flags);
	else if (flags & MS_MOVE)
		retval = do_move_mount(&nd, dev_name);
	else
		retval = do_new_mount(&nd, type_page, flags, mnt_flags,
				      dev_name, data_page);
dput_out:
	path_put(&nd.path);
	return retval;
}

/*
 * Allocate a new namespace structure and populate it with contents
 * copied from the namespace of the passed in task structure.
 */
static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
		struct fs_struct *fs)
{
	struct mnt_namespace *new_ns;
	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
	struct vfsmount *p, *q;

	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
	if (!new_ns)
		return ERR_PTR(-ENOMEM);

	atomic_set(&new_ns->count, 1);
	INIT_LIST_HEAD(&new_ns->list);
	init_waitqueue_head(&new_ns->poll);
	new_ns->event = 0;

	down_write(&namespace_sem);
	/* First pass: copy the tree topology */
	new_ns->root = copy_tree(mnt_ns->root, mnt_ns->root->mnt_root,
					CL_COPY_ALL | CL_EXPIRE);
	if (!new_ns->root) {
		up_write(&namespace_sem);
		kfree(new_ns);
		return ERR_PTR(-ENOMEM);;
	}
	spin_lock(&vfsmount_lock);
	list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
	spin_unlock(&vfsmount_lock);

	/*
	 * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
	 * as belonging to new namespace.  We have already acquired a private
	 * fs_struct, so tsk->fs->lock is not needed.
	 */
	p = mnt_ns->root;
	q = new_ns->root;
	while (p) {
		q->mnt_ns = new_ns;
		if (fs) {
			if (p == fs->root.mnt) {
				rootmnt = p;
				fs->root.mnt = mntget(q);
			}
			if (p == fs->pwd.mnt) {
				pwdmnt = p;
				fs->pwd.mnt = mntget(q);
			}
			if (p == fs->altroot.mnt) {
				altrootmnt = p;
				fs->altroot.mnt = mntget(q);
			}
		}
		p = next_mnt(p, mnt_ns->root);
		q = next_mnt(q, new_ns->root);
	}
	up_write(&namespace_sem);

	if (rootmnt)
		mntput(rootmnt);
	if (pwdmnt)
		mntput(pwdmnt);
	if (altrootmnt)
		mntput(altrootmnt);

	return new_ns;
}

struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
		struct fs_struct *new_fs)
{
	struct mnt_namespace *new_ns;

	BUG_ON(!ns);
	get_mnt_ns(ns);

	if (!(flags & CLONE_NEWNS))
		return ns;

	new_ns = dup_mnt_ns(ns, new_fs);

	put_mnt_ns(ns);
	return new_ns;
}

asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
			  char __user * type, unsigned long flags,
			  void __user * data)
{
	int retval;
	unsigned long data_page;
	unsigned long type_page;
	unsigned long dev_page;
	char *dir_page;

	retval = copy_mount_options(type, &type_page);
	if (retval < 0)
		return retval;

	dir_page = getname(dir_name);
	retval = PTR_ERR(dir_page);
	if (IS_ERR(dir_page))
		goto out1;

	retval = copy_mount_options(dev_name, &dev_page);
	if (retval < 0)
		goto out2;

	retval = copy_mount_options(data, &data_page);
	if (retval < 0)
		goto out3;

	lock_kernel();
	retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
			  flags, (void *)data_page);
	unlock_kernel();
	free_page(data_page);

out3:
	free_page(dev_page);
out2:
	putname(dir_page);
out1:
	free_page(type_page);
	return retval;
}

/*
 * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
 * It can block. Requires the big lock held.
 */
void set_fs_root(struct fs_struct *fs, struct path *path)
{
	struct path old_root;

	write_lock(&fs->lock);
	old_root = fs->root;
	fs->root = *path;
	path_get(path);
	write_unlock(&fs->lock);
	if (old_root.dentry)
		path_put(&old_root);
}

/*
 * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
 * It can block. Requires the big lock held.
 */
void set_fs_pwd(struct fs_struct *fs, struct path *path)
{
	struct path old_pwd;

	write_lock(&fs->lock);
	old_pwd = fs->pwd;
	fs->pwd = *path;
	path_get(path);
	write_unlock(&fs->lock);

	if (old_pwd.dentry)
		path_put(&old_pwd);
}

static void chroot_fs_refs(struct path *old_root, struct path *new_root)
{
	struct task_struct *g, *p;
	struct fs_struct *fs;

	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		task_lock(p);
		fs = p->fs;
		if (fs) {
			atomic_inc(&fs->count);
			task_unlock(p);
			if (fs->root.dentry == old_root->dentry
			    && fs->root.mnt == old_root->mnt)
				set_fs_root(fs, new_root);
			if (fs->pwd.dentry == old_root->dentry
			    && fs->pwd.mnt == old_root->mnt)
				set_fs_pwd(fs, new_root);
			put_fs_struct(fs);
		} else
			task_unlock(p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);
}

/*
 * pivot_root Semantics:
 * Moves the root file system of the current process to the directory put_old,
 * makes new_root as the new root file system of the current process, and sets
 * root/cwd of all processes which had them on the current root to new_root.
 *
 * Restrictions:
 * The new_root and put_old must be directories, and  must not be on the
 * same file  system as the current process root. The put_old  must  be
 * underneath new_root,  i.e. adding a non-zero number of /.. to the string
 * pointed to by put_old must yield the same directory as new_root. No other
 * file system may be mounted on put_old. After all, new_root is a mountpoint.
 *
 * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem.
 * See Documentation/filesystems/ramfs-rootfs-initramfs.txt for alternatives
 * in this situation.
 *
 * Notes:
 *  - we don't move root/cwd if they are not at the root (reason: if something
 *    cared enough to change them, it's probably wrong to force them elsewhere)
 *  - it's okay to pick a root that isn't the root of a file system, e.g.
 *    /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
 *    though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
 *    first.
 */
asmlinkage long sys_pivot_root(const char __user * new_root,
			       const char __user * put_old)
{
	struct vfsmount *tmp;
	struct nameidata new_nd, old_nd, user_nd;
	struct path parent_path, root_parent;
	int error;

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

	lock_kernel();

	error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
			    &new_nd);