namespace.c

	spin_lock(&vfsmount_lock);
	/* if the mount is moved, it should no longer be expire
	 * automatically */
	list_del_init(&old_nd.mnt->mnt_expire);
	spin_unlock(&vfsmount_lock);
out1:
	mutex_unlock(&nd->dentry->d_inode->i_mutex);
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
	 */
	if (!propagate_mount_busy(mnt, 2)) {
		/* delete from the namespace */
		touch_namespace(mnt->mnt_namespace);
		list_del_init(&mnt->mnt_list);
		mnt->mnt_namespace = NULL;
		umount_tree(mnt, 1, umounts);
		spin_unlock(&vfsmount_lock);
	} else {
		/*
		 * Someone brought it back to life whilst we didn't have any
		 * locks held so return it to the expiration list
		 */
		list_add_tail(&mnt->mnt_expire, mounts);
		spin_unlock(&vfsmount_lock);
	}
}

/*
 * 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 namespace *namespace;
	struct vfsmount *mnt, *next;
	LIST_HEAD(graveyard);

	if (list_empty(mounts))
		return;

	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) ||
		    atomic_read(&mnt->mnt_count) != 1)
			continue;

		mntget(mnt);
		list_move(&mnt->mnt_expire, &graveyard);
	}

	/*
	 * go through the vfsmounts we've just consigned to the graveyard to
	 * - check that they're still dead
	 * - delete the vfsmount from the appropriate namespace under lock
	 * - dispose of the corpse
	 */
	while (!list_empty(&graveyard)) {
		LIST_HEAD(umounts);
		mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire);
		list_del_init(&mnt->mnt_expire);

		/* don't do anything if the namespace is dead - all the
		 * vfsmounts from it are going away anyway */
		namespace = mnt->mnt_namespace;
		if (!namespace || !namespace->root)
			continue;
		get_namespace(namespace);

		spin_unlock(&vfsmount_lock);
		down_write(&namespace_sem);
		expire_mount(mnt, mounts, &umounts);
		up_write(&namespace_sem);
		release_mounts(&umounts);
		mntput(mnt);
		put_namespace(namespace);
		spin_lock(&vfsmount_lock);
	}

	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);

/*
 * 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;

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

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

	retval = security_sb_mount(dev_name, &nd, 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_release(&nd);
	return retval;
}

int copy_namespace(int flags, struct task_struct *tsk)
{
	struct namespace *namespace = tsk->namespace;
	struct namespace *new_ns;
	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
	struct fs_struct *fs = tsk->fs;
	struct vfsmount *p, *q;

	if (!namespace)
		return 0;

	get_namespace(namespace);

	if (!(flags & CLONE_NEWNS))
		return 0;

	if (!capable(CAP_SYS_ADMIN)) {
		put_namespace(namespace);
		return -EPERM;
	}

	new_ns = kmalloc(sizeof(struct namespace), GFP_KERNEL);
	if (!new_ns)
		goto out;

	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(namespace->root, namespace->root->mnt_root,
					CL_COPY_ALL | CL_EXPIRE);
	if (!new_ns->root) {
		up_write(&namespace_sem);
		kfree(new_ns);
		goto out;
	}
	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 = namespace->root;
	q = new_ns->root;
	while (p) {
		q->mnt_namespace = new_ns;
		if (fs) {
			if (p == fs->rootmnt) {
				rootmnt = p;
				fs->rootmnt = mntget(q);
			}
			if (p == fs->pwdmnt) {
				pwdmnt = p;
				fs->pwdmnt = mntget(q);
			}
			if (p == fs->altrootmnt) {
				altrootmnt = p;
				fs->altrootmnt = mntget(q);
			}
		}
		p = next_mnt(p, namespace->root);
		q = next_mnt(q, new_ns->root);
	}
	up_write(&namespace_sem);

	tsk->namespace = new_ns;

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

	put_namespace(namespace);
	return 0;

out:
	put_namespace(namespace);
	return -ENOMEM;
}

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 vfsmount *mnt,
		 struct dentry *dentry)
{
	struct dentry *old_root;
	struct vfsmount *old_rootmnt;
	write_lock(&fs->lock);
	old_root = fs->root;
	old_rootmnt = fs->rootmnt;
	fs->rootmnt = mntget(mnt);
	fs->root = dget(dentry);
	write_unlock(&fs->lock);
	if (old_root) {
		dput(old_root);
		mntput(old_rootmnt);
	}
}

/*
 * 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 vfsmount *mnt,
		struct dentry *dentry)
{
	struct dentry *old_pwd;
	struct vfsmount *old_pwdmnt;

	write_lock(&fs->lock);
	old_pwd = fs->pwd;
	old_pwdmnt = fs->pwdmnt;
	fs->pwdmnt = mntget(mnt);
	fs->pwd = dget(dentry);
	write_unlock(&fs->lock);

	if (old_pwd) {
		dput(old_pwd);
		mntput(old_pwdmnt);
	}
}

static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
{
	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 == old_nd->dentry
			    && fs->rootmnt == old_nd->mnt)
				set_fs_root(fs, new_nd->mnt, new_nd->dentry);
			if (fs->pwd == old_nd->dentry
			    && fs->pwdmnt == old_nd->mnt)
				set_fs_pwd(fs, new_nd->mnt, new_nd->dentry);
			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, parent_nd, root_parent, user_nd;
	int error;

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

	lock_kernel();

	error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
			    &new_nd);
	if (error)
		goto out0;
	error = -EINVAL;
	if (!check_mnt(new_nd.mnt))
		goto out1;

	error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd);
	if (error)
		goto out1;

	error = security_sb_pivotroot(&old_nd, &new_nd);
	if (error) {
		path_release(&old_nd);
		goto out1;
	}

	read_lock(&current->fs->lock);
	user_nd.mnt = mntget(current->fs->rootmnt);
	user_nd.dentry = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	down_write(&namespace_sem);
	mutex_lock(&old_nd.dentry->d_inode->i_mutex);
	error = -EINVAL;
	if (IS_MNT_SHARED(old_nd.mnt) ||
		IS_MNT_SHARED(new_nd.mnt->mnt_parent) ||
		IS_MNT_SHARED(user_nd.mnt->mnt_parent))
		goto out2;
	if (!check_mnt(user_nd.mnt))
		goto out2;
	error = -ENOENT;
	if (IS_DEADDIR(new_nd.dentry->d_inode))
		goto out2;
	if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry))
		goto out2;
	if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry))
		goto out2;
	error = -EBUSY;
	if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt)
		goto out2; /* loop, on the same file system  */
	error = -EINVAL;
	if (user_nd.mnt->mnt_root != user_nd.dentry)
		goto out2; /* not a mountpoint */
	if (user_nd.mnt->mnt_parent == user_nd.mnt)
		goto out2; /* not attached */
	if (new_nd.mnt->mnt_root != new_nd.dentry)
		goto out2; /* not a mountpoint */
	if (new_nd.mnt->mnt_parent == new_nd.mnt)
		goto out2; /* not attached */
	tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
	spin_lock(&vfsmount_lock);
	if (tmp != new_nd.mnt) {
		for (;;) {
			if (tmp->mnt_parent == tmp)
				goto out3; /* already mounted on put_old */
			if (tmp->mnt_parent == new_nd.mnt)
				break;
			tmp = tmp->mnt_parent;
		}
		if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry))
			goto out3;
	} else if (!is_subdir(old_nd.dentry, new_nd.dentry))
		goto out3;
	detach_mnt(new_nd.mnt, &parent_nd);
	detach_mnt(user_nd.mnt, &root_parent);
	attach_mnt(user_nd.mnt, &old_nd);     /* mount old root on put_old */
	attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */
	touch_namespace(current->namespace);
	spin_unlock(&vfsmount_lock);
	chroot_fs_refs(&user_nd, &new_nd);
	security_sb_post_pivotroot(&user_nd, &new_nd);
	error = 0;
	path_release(&root_parent);
	path_release(&parent_nd);
out2:
	mutex_unlock(&old_nd.dentry->d_inode->i_mutex);
	up_write(&namespace_sem);
	path_release(&user_nd);
	path_release(&old_nd);
out1:
	path_release(&new_nd);
out0:
	unlock_kernel();
	return error;
out3:
	spin_unlock(&vfsmount_lock);
	goto out2;
}

static void __init init_mount_tree(void)
{
	struct vfsmount *mnt;
	struct namespace *namespace;
	struct task_struct *g, *p;

	mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
	if (IS_ERR(mnt))
		panic("Can't create rootfs");
	namespace = kmalloc(sizeof(*namespace), GFP_KERNEL);
	if (!namespace)
		panic("Can't allocate initial namespace");
	atomic_set(&namespace->count, 1);
	INIT_LIST_HEAD(&namespace->list);
	init_waitqueue_head(&namespace->poll);
	namespace->event = 0;
	list_add(&mnt->mnt_list, &namespace->list);
	namespace->root = mnt;
	mnt->mnt_namespace = namespace;

	init_task.namespace = namespace;
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		get_namespace(namespace);
		p->namespace = namespace;
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);

	set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root);
	set_fs_root(current->fs, namespace->root, namespace->root->mnt_root);
}

void __init mnt_init(unsigned long mempages)
{
	struct list_head *d;
	unsigned int nr_hash;
	int i;

	init_rwsem(&namespace_sem);

	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount),
			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL, NULL);

	mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);

	if (!mount_hashtable)
		panic("Failed to allocate mount hash table\n");

	/*
	 * Find the power-of-two list-heads that can fit into the allocation..
	 * We don't guarantee that "sizeof(struct list_head)" is necessarily
	 * a power-of-two.
	 */
	nr_hash = PAGE_SIZE / sizeof(struct list_head);
	hash_bits = 0;
	do {
		hash_bits++;
	} while ((nr_hash >> hash_bits) != 0);
	hash_bits--;

	/*
	 * Re-calculate the actual number of entries and the mask
	 * from the number of bits we can fit.
	 */
	nr_hash = 1UL << hash_bits;
	hash_mask = nr_hash - 1;

	printk("Mount-cache hash table entries: %d\n", nr_hash);

	/* And initialize the newly allocated array */
	d = mount_hashtable;
	i = nr_hash;
	do {
		INIT_LIST_HEAD(d);
		d++;
		i--;
	} while (i);
	sysfs_init();
	init_rootfs();
	init_mount_tree();
}

void __put_namespace(struct namespace *namespace)
{
	struct vfsmount *root = namespace->root;
	LIST_HEAD(umount_list);
	namespace->root = NULL;
	spin_unlock(&vfsmount_lock);
	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	umount_tree(root, 0, &umount_list);
	spin_unlock(&vfsmount_lock);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
	kfree(namespace);
}