namespace.c

/*
 *  linux/fs/namespace.c
 *
 * (C) Copyright Al Viro 2000, 2001
 *	Released under GPL v2.
 *
 * Based on code from fs/super.c, copyright Linus Torvalds and others.
 * Heavily rewritten.
 */

#include <linux/config.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/acct.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"

extern int __init init_rootfs(void);

#ifdef CONFIG_SYSFS
extern int __init sysfs_init(void);
#else
static inline int sysfs_init(void)
{
	return 0;
}
#endif

/* spinlock for vfsmount related operations, inplace of dcache_lock */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);

static int event;

static struct list_head *mount_hashtable;
static int hash_mask __read_mostly, hash_bits __read_mostly;
static kmem_cache_t *mnt_cache;
static struct rw_semaphore namespace_sem;

static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
{
	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
	tmp = tmp + (tmp >> hash_bits);
	return tmp & hash_mask;
}

struct vfsmount *alloc_vfsmnt(const char *name)
{
	struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL);
	if (mnt) {
		memset(mnt, 0, sizeof(struct vfsmount));
		atomic_set(&mnt->mnt_count, 1);
		INIT_LIST_HEAD(&mnt->mnt_hash);
		INIT_LIST_HEAD(&mnt->mnt_child);
		INIT_LIST_HEAD(&mnt->mnt_mounts);
		INIT_LIST_HEAD(&mnt->mnt_list);
		INIT_LIST_HEAD(&mnt->mnt_expire);
		INIT_LIST_HEAD(&mnt->mnt_share);
		if (name) {
			int size = strlen(name) + 1;
			char *newname = kmalloc(size, GFP_KERNEL);
			if (newname) {
				memcpy(newname, name, size);
				mnt->mnt_devname = newname;
			}
		}
	}
	return mnt;
}

void free_vfsmnt(struct vfsmount *mnt)
{
	kfree(mnt->mnt_devname);
	kmem_cache_free(mnt_cache, mnt);
}

/*
 * Now, lookup_mnt increments the ref count before returning
 * the vfsmount struct.
 */
struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
	struct list_head *head = mount_hashtable + hash(mnt, dentry);
	struct list_head *tmp = head;
	struct vfsmount *p, *found = NULL;

	spin_lock(&vfsmount_lock);
	for (;;) {
		tmp = tmp->next;
		p = NULL;
		if (tmp == head)
			break;
		p = list_entry(tmp, struct vfsmount, mnt_hash);
		if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) {
			found = mntget(p);
			break;
		}
	}
	spin_unlock(&vfsmount_lock);
	return found;
}

static inline int check_mnt(struct vfsmount *mnt)
{
	return mnt->mnt_namespace == current->namespace;
}

static void touch_namespace(struct namespace *ns)
{
	if (ns) {
		ns->event = ++event;
		wake_up_interruptible(&ns->poll);
	}
}

static void __touch_namespace(struct namespace *ns)
{
	if (ns && ns->event != event) {
		ns->event = event;
		wake_up_interruptible(&ns->poll);
	}
}

static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
{
	old_nd->dentry = mnt->mnt_mountpoint;
	old_nd->mnt = mnt->mnt_parent;
	mnt->mnt_parent = mnt;
	mnt->mnt_mountpoint = mnt->mnt_root;
	list_del_init(&mnt->mnt_child);
	list_del_init(&mnt->mnt_hash);
	old_nd->dentry->d_mounted--;
}

void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
			struct vfsmount *child_mnt)
{
	child_mnt->mnt_parent = mntget(mnt);
	child_mnt->mnt_mountpoint = dget(dentry);
	dentry->d_mounted++;
}

static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd)
{
	mnt_set_mountpoint(nd->mnt, nd->dentry, mnt);
	list_add_tail(&mnt->mnt_hash, mount_hashtable +
			hash(nd->mnt, nd->dentry));
	list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts);
}

/*
 * the caller must hold vfsmount_lock
 */
static void commit_tree(struct vfsmount *mnt)
{
	struct vfsmount *parent = mnt->mnt_parent;
	struct vfsmount *m;
	LIST_HEAD(head);
	struct namespace *n = parent->mnt_namespace;

	BUG_ON(parent == mnt);

	list_add_tail(&head, &mnt->mnt_list);
	list_for_each_entry(m, &head, mnt_list)
		m->mnt_namespace = n;
	list_splice(&head, n->list.prev);

	list_add_tail(&mnt->mnt_hash, mount_hashtable +
				hash(parent, mnt->mnt_mountpoint));
	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
	touch_namespace(n);
}

static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root)
{
	struct list_head *next = p->mnt_mounts.next;
	if (next == &p->mnt_mounts) {
		while (1) {
			if (p == root)
				return NULL;
			next = p->mnt_child.next;
			if (next != &p->mnt_parent->mnt_mounts)
				break;
			p = p->mnt_parent;
		}
	}
	return list_entry(next, struct vfsmount, mnt_child);
}

static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
					int flag)
{
	struct super_block *sb = old->mnt_sb;
	struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);

	if (mnt) {
		mnt->mnt_flags = old->mnt_flags;
		atomic_inc(&sb->s_active);
		mnt->mnt_sb = sb;
		mnt->mnt_root = dget(root);
		mnt->mnt_mountpoint = mnt->mnt_root;
		mnt->mnt_parent = mnt;

		if ((flag & CL_PROPAGATION) || IS_MNT_SHARED(old))
			list_add(&mnt->mnt_share, &old->mnt_share);
		if (flag & CL_MAKE_SHARED)
			set_mnt_shared(mnt);

		/* stick the duplicate mount on the same expiry list
		 * as the original if that was on one */
		if (flag & CL_EXPIRE) {
			spin_lock(&vfsmount_lock);
			if (!list_empty(&old->mnt_expire))
				list_add(&mnt->mnt_expire, &old->mnt_expire);
			spin_unlock(&vfsmount_lock);
		}
	}
	return mnt;
}

static inline void __mntput(struct vfsmount *mnt)
{
	struct super_block *sb = mnt->mnt_sb;
	dput(mnt->mnt_root);
	free_vfsmnt(mnt);
	deactivate_super(sb);
}

void mntput_no_expire(struct vfsmount *mnt)
{
repeat:
	if (atomic_dec_and_lock(&mnt->mnt_count, &vfsmount_lock)) {
		if (likely(!mnt->mnt_pinned)) {
			spin_unlock(&vfsmount_lock);
			__mntput(mnt);
			return;
		}
		atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count);
		mnt->mnt_pinned = 0;
		spin_unlock(&vfsmount_lock);
		acct_auto_close_mnt(mnt);
		security_sb_umount_close(mnt);
		goto repeat;
	}
}

EXPORT_SYMBOL(mntput_no_expire);

void mnt_pin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	mnt->mnt_pinned++;
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_pin);

void mnt_unpin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	if (mnt->mnt_pinned) {
		atomic_inc(&mnt->mnt_count);
		mnt->mnt_pinned--;
	}
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_unpin);

/* iterator */
static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p;
	loff_t l = *pos;

	down_read(&namespace_sem);
	list_for_each(p, &n->list)
		if (!l--)
			return list_entry(p, struct vfsmount, mnt_list);
	return NULL;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p = ((struct vfsmount *)v)->mnt_list.next;
	(*pos)++;
	return p == &n->list ? NULL : list_entry(p, struct vfsmount, mnt_list);
}

static void m_stop(struct seq_file *m, void *v)
{
	up_read(&namespace_sem);
}

static inline void mangle(struct seq_file *m, const char *s)
{
	seq_escape(m, s, " \t\n\\");
}

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = v;
	int err = 0;
	static struct proc_fs_info {
		int flag;
		char *str;
	} fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_DIRSYNC, ",dirsync" },
		{ MS_MANDLOCK, ",mand" },
		{ MS_NOATIME, ",noatime" },
		{ MS_NODIRATIME, ",nodiratime" },
		{ 0, NULL }
	};
	static struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ 0, NULL }
	};
	struct proc_fs_info *fs_infop;

	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_putc(m, ' ');
	seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
	seq_putc(m, ' ');
	mangle(m, mnt->mnt_sb->s_type->name);
	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_sb->s_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	if (mnt->mnt_sb->s_op->show_options)
		err = mnt->mnt_sb->s_op->show_options(m, mnt);
	seq_puts(m, " 0 0\n");
	return err;
}

struct seq_operations mounts_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_vfsmnt
};

/**
 * may_umount_tree - check if a mount tree is busy
 * @mnt: root of mount tree
 *
 * This is called to check if a tree of mounts has any
 * open files, pwds, chroots or sub mounts that are
 * busy.
 */
int may_umount_tree(struct vfsmount *mnt)
{
	int actual_refs = 0;
	int minimum_refs = 0;
	struct vfsmount *p;

	spin_lock(&vfsmount_lock);
	for (p = mnt; p; p = next_mnt(p, mnt)) {
		actual_refs += atomic_read(&p->mnt_count);
		minimum_refs += 2;
	}
	spin_unlock(&vfsmount_lock);

	if (actual_refs > minimum_refs)
		return -EBUSY;

	return 0;
}

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)
{
	if (atomic_read(&mnt->mnt_count) > 2)
		return -EBUSY;
	return 0;
}

EXPORT_SYMBOL(may_umount);

void release_mounts(struct list_head *head)
{
	struct vfsmount *mnt;
	while(!list_empty(head)) {
		mnt = list_entry(head->next, struct vfsmount, mnt_hash);
		list_del_init(&mnt->mnt_hash);
		if (mnt->mnt_parent != mnt) {
			struct dentry *dentry;
			struct vfsmount *m;
			spin_lock(&vfsmount_lock);
			dentry = mnt->mnt_mountpoint;
			m = mnt->mnt_parent;
			mnt->mnt_mountpoint = mnt->mnt_root;
			mnt->mnt_parent = mnt;
			spin_unlock(&vfsmount_lock);
			dput(dentry);
			mntput(m);
		}
		mntput(mnt);
	}
}

void umount_tree(struct vfsmount *mnt, struct list_head *kill)
{
	struct vfsmount *p;

	for (p = mnt; p; p = next_mnt(p, mnt)) {
		list_del(&p->mnt_hash);
		list_add(&p->mnt_hash, kill);
	}

	list_for_each_entry(p, kill, mnt_hash) {
		list_del_init(&p->mnt_expire);
		list_del_init(&p->mnt_list);
		__touch_namespace(p->mnt_namespace);
		p->mnt_namespace = NULL;
		list_del_init(&p->mnt_child);
		if (p->mnt_parent != p)
			mnt->mnt_mountpoint->d_mounted--;
	}
}

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->rootmnt ||
		    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.
	 */

	lock_kernel();
	if ((flags & MNT_FORCE) && sb->s_op->umount_begin)
		sb->s_op->umount_begin(sb);
	unlock_kernel();

	/*
	 * 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->rootmnt && !(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)) {
			lock_kernel();
			DQUOT_OFF(sb);
			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
			unlock_kernel();
		}
		up_write(&sb->s_umount);
		return retval;
	}

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

	retval = -EBUSY;
	if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) {
		if (!list_empty(&mnt->mnt_list))
			umount_tree(mnt, &umount_list);
		retval = 0;
	}
	spin_unlock(&vfsmount_lock);
	if (retval)
		security_sb_umount_busy(mnt);
	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
 */

asmlinkage long sys_umount(char __user * name, int flags)
{
	struct nameidata nd;
	int retval;

	retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
	if (retval)
		goto out;
	retval = -EINVAL;
	if (nd.dentry != nd.mnt->mnt_root)
		goto dput_and_out;
	if (!check_mnt(nd.mnt))
		goto dput_and_out;

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

	retval = do_umount(nd.mnt, flags);
dput_and_out:
	path_release_on_umount(&nd);
out:
	return retval;
}

#ifdef __ARCH_WANT_SYS_OLDUMOUNT

/*
 *	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->dentry->d_inode->i_mode))
		return -EPERM;
	if (nd->dentry->d_inode->i_mode & S_ISVTX) {
		if (current->uid != nd->dentry->d_inode->i_uid)
			return -EPERM;
	}
	if (permission(nd->dentry->d_inode, MAY_WRITE, nd))
		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 nameidata nd;

	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)) {
			while (p != s->mnt_parent) {
				p = p->mnt_parent;
				q = q->mnt_parent;
			}
			p = s;
			nd.mnt = q;
			nd.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, &nd);
			spin_unlock(&vfsmount_lock);
		}
	}
	return res;
Enomem:
	if (res) {
		LIST_HEAD(umount_list);
		spin_lock(&vfsmount_lock);
		umount_tree(res, &umount_list);
		spin_unlock(&vfsmount_lock);
		release_mounts(&umount_list);
	}
	return NULL;
}

/*
 *  @source_mnt : mount tree to be attached
 *  @nd        : place the mount tree @source_mnt is attached
 *
 *  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  |
 * 	| dest     |               |                |
 * 	|   |      |               |                |
 * 	|   v      |               |                |
 * 	|********************************************
 * 	|  shared  | shared (++)   |     shared (+) |
 * 	|          |               |                |
 * 	|non-shared| shared (+)    |      private   |
 * 	*********************************************
 * 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.
 *
 * 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 nameidata *nd)
{
	LIST_HEAD(tree_list);
	struct vfsmount *dest_mnt = nd->mnt;
	struct dentry *dest_dentry = nd->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);
	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->dentry->d_inode->i_mode) !=
	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
		return -ENOTDIR;

	err = -ENOENT;
	down(&nd->dentry->d_inode->i_sem);
	if (IS_DEADDIR(nd->dentry->d_inode))
		goto out_unlock;

	err = security_sb_check_sb(mnt, nd);
	if (err)
		goto out_unlock;

	err = -ENOENT;
	if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry))
		err = attach_recursive_mnt(mnt, nd);
out_unlock:
	up(&nd->dentry->d_inode->i_sem);
	if (!err)
		security_sb_post_addmount(mnt, nd);
	return err;
}

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

	if (nd->dentry != nd->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.
 */
static 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 (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
		goto out;

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

	if (!mnt)
		goto out;

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

out:
	up_write(&namespace_sem);
	path_release(&old_nd);
	return err;
}

/*
 * 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 nameidata *nd, int flags, int mnt_flags,
		      void *data)
{
	int err;
	struct super_block *sb = nd->mnt->mnt_sb;

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

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

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

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

static int do_move_mount(struct nameidata *nd, char *old_name)
{
	struct nameidata old_nd, parent_nd;
	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->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
		goto out;

	err = -ENOENT;
	down(&nd->dentry->d_inode->i_sem);
	if (IS_DEADDIR(nd->dentry->d_inode))
		goto out1;

	spin_lock(&vfsmount_lock);
	if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))
		goto out2;

	err = -EINVAL;
	if (old_nd.dentry != old_nd.mnt->mnt_root)
		goto out2;

	if (old_nd.mnt == old_nd.mnt->mnt_parent)
		goto out2;

	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
	      S_ISDIR(old_nd.dentry->d_inode->i_mode))
		goto out2;

	err = -ELOOP;
	for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent)
		if (p == old_nd.mnt)
			goto out2;
	err = 0;

	detach_mnt(old_nd.mnt, &parent_nd);
	attach_mnt(old_nd.mnt, nd);
	touch_namespace(current->namespace);

	/* if the mount is moved, it should no longer be expire
	 * automatically */
	list_del_init(&old_nd.mnt->mnt_expire);
out2:
	spin_unlock(&vfsmount_lock);
out1:
	up(&nd->dentry->d_inode->i_sem);
out:
	up_write(&namespace_sem);
	if (!err)
		path_release(&parent_nd);
	path_release(&old_nd);
	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 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->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt))
		goto unlock;

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (nd->mnt->mnt_sb == newmnt->mnt_sb &&
	    nd->mnt->mnt_root == nd->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 */
		spin_lock(&vfsmount_lock);
		list_add_tail(&newmnt->mnt_expire, fslist);
		spin_unlock(&vfsmount_lock);
	}
	up_write(&namespace_sem);
	return 0;

unlock:
	up_write(&namespace_sem);
	mntput(newmnt);
	return err;
}

EXPORT_SYMBOL_GPL(do_add_mount);

static void expire_mount(struct vfsmount *mnt, struct list_head *mounts,
				struct list_head *umounts)
{
	spin_lock(&vfsmount_lock);

	/*
	 * Check if mount is still attached, if not, let whoever holds it deal
	 * with the sucker
	 */
	if (mnt->mnt_parent == mnt) {
		spin_unlock(&vfsmount_lock);
		return;
	}

	/*
	 * Check that it is still dead: the count should now be 2 - as
	 * contributed by the vfsmount parent and the mntget above
	 */