1 files changed, 136 insertions, 18 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 2ffc5a2905d4..c6533ce9cdee 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -777,6 +777,20 @@ static void attach_mnt(struct mount *mnt,
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 }
 
+static void attach_shadowed(struct mount *mnt,
+			struct mount *parent,
+			struct mount *shadows)
+{
+	if (shadows) {
+		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+		list_add(&mnt->mnt_child, &shadows->mnt_child);
+	} else {
+		hlist_add_head_rcu(&mnt->mnt_hash,
+				m_hash(&parent->mnt, mnt->mnt_mountpoint));
+		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	}
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -795,12 +809,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 
 	list_splice(&head, n->list.prev);
 
-	if (shadows)
-		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
-	else
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	attach_shadowed(mnt, parent, shadows);
 	touch_mnt_namespace(n);
 }
 
@@ -885,10 +894,23 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
 	/* Don't allow unprivileged users to change mount flags */
-	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
-		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+	if (flag & CL_UNPRIVILEGED) {
+		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+		if (mnt->mnt.mnt_flags & MNT_READONLY)
+			mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+		if (mnt->mnt.mnt_flags & MNT_NODEV)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+		if (mnt->mnt.mnt_flags & MNT_NOSUID)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+		if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+	}
 
 	/* Don't allow unprivileged users to reveal what is under a mount */
 	if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire))
@@ -1204,6 +1226,11 @@ static void namespace_unlock(void)
 	head.first->pprev = &head.first;
 	INIT_HLIST_HEAD(&unmounted);
 
+	/* undo decrements we'd done in umount_tree() */
+	hlist_for_each_entry(mnt, &head, mnt_hash)
+		if (mnt->mnt_ex_mountpoint.mnt)
+			mntget(mnt->mnt_ex_mountpoint.mnt);
+
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
@@ -1240,6 +1267,9 @@ void umount_tree(struct mount *mnt, int how)
 		hlist_add_head(&p->mnt_hash, &tmp_list);
 	}
 
+	hlist_for_each_entry(p, &tmp_list, mnt_hash)
+		list_del_init(&p->mnt_child);
+
 	if (how)
 		propagate_umount(&tmp_list);
 
@@ -1250,9 +1280,9 @@ void umount_tree(struct mount *mnt, int how)
 		p->mnt_ns = NULL;
 		if (how < 2)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
-		list_del_init(&p->mnt_child);
 		if (mnt_has_parent(p)) {
 			put_mountpoint(p->mnt_mp);
+			mnt_add_count(p->mnt_parent, -1);
 			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
 			p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint;
 			p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt;
@@ -1265,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how)
 	}
 	if (last) {
 		last->mnt_hash.next = unmounted.first;
+		if (unmounted.first)
+			unmounted.first->pprev = &last->mnt_hash.next;
 		unmounted.first = tmp_list.first;
 		unmounted.first->pprev = &unmounted.first;
 	}
@@ -1335,6 +1367,8 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
@@ -1407,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 	if (mnt->mnt.mnt_flags & MNT_LOCKED)
 		goto dput_and_out;
+	retval = -EPERM;
+	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+		goto dput_and_out;
 
 	retval = do_umount(mnt, flags);
 dput_and_out:
@@ -1483,6 +1520,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
+			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1504,7 +1542,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			attach_mnt(q, parent, p->mnt_mp);
+			mnt_set_mountpoint(parent, p->mnt_mp, q);
+			if (!list_empty(&parent->mnt_mounts)) {
+				t = list_last_entry(&parent->mnt_mounts,
+					struct mount, mnt_child);
+				if (t->mnt_mp != p->mnt_mp)
+					t = NULL;
+			}
+			attach_shadowed(q, parent, t);
 			unlock_mount_hash();
 		}
 	}
@@ -1541,6 +1586,33 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	namespace_unlock();
 }
 
+/**
+ * clone_private_mount - create a private clone of a path
+ *
+ * This creates a new vfsmount, which will be the clone of @path.  The new will
+ * not be attached anywhere in the namespace and will be private (i.e. changes
+ * to the originating mount won't be propagated into this).
+ *
+ * Release with mntput().
+ */
+struct vfsmount *clone_private_mount(struct path *path)
+{
+	struct mount *old_mnt = real_mount(path->mnt);
+	struct mount *new_mnt;
+
+	if (IS_MNT_UNBINDABLE(old_mnt))
+		return ERR_PTR(-EINVAL);
+
+	down_read(&namespace_sem);
+	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
+	up_read(&namespace_sem);
+	if (IS_ERR(new_mnt))
+		return ERR_CAST(new_mnt);
+
+	return &new_mnt->mnt;
+}
+EXPORT_SYMBOL_GPL(clone_private_mount);
+
 int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
 		   struct vfsmount *root)
 {
@@ -1661,9 +1733,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		if (err)
 			goto out;
 		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		lock_mount_hash();
 		if (err)
 			goto out_cleanup_ids;
-		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	} else {
@@ -1690,6 +1762,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	return 0;
 
  out_cleanup_ids:
+	while (!hlist_empty(&tree_list)) {
+		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		umount_tree(child, 0);
+	}
+	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
@@ -1882,9 +1959,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
-	if (mnt->mnt_flags & MNT_LOCK_READONLY)
-		return -EPERM;
-
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
@@ -1910,6 +1984,39 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
+	/* Don't allow changing of locked mnt flags.
+	 *
+	 * No locks need to be held here while testing the various
+	 * MNT_LOCK flags because those flags can never be cleared
+	 * once they are set.
+	 */
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+	    !(mnt_flags & MNT_READONLY)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+	    !(mnt_flags & MNT_NODEV)) {
+		/* Was the nodev implicitly added in mount? */
+		if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+		    !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+			mnt_flags |= MNT_NODEV;
+		} else {
+			return -EPERM;
+		}
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+	    !(mnt_flags & MNT_NOSUID)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+	    !(mnt_flags & MNT_NOEXEC)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+	    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+		return -EPERM;
+	}
+
 	err = security_sb_remount(sb, data);
 	if (err)
 		return err;
@@ -1923,7 +2030,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 		err = do_remount_sb(sb, flags, data, 0);
 	if (!err) {
 		lock_mount_hash();
-		mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
 		mnt->mnt.mnt_flags = mnt_flags;
 		touch_mnt_namespace(mnt->mnt_ns);
 		unlock_mount_hash();
@@ -2044,7 +2151,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+	mnt_flags &= ~MNT_INTERNAL_FLAGS;
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
@@ -2108,7 +2215,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 		 */
 		if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
 			flags |= MS_NODEV;
-			mnt_flags |= MNT_NODEV;
+			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 	}
 
@@ -2422,6 +2529,14 @@ long do_mount(const char *dev_name, const char *dir_name,
 	if (flags & MS_RDONLY)
 		mnt_flags |= MNT_READONLY;
 
+	/* The default atime for remount is preservation */
+	if ((flags & MS_REMOUNT) &&
+	    ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+		       MS_STRICTATIME)) == 0)) {
+		mnt_flags &= ~MNT_ATIME_MASK;
+		mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+	}
+
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
 		   MS_STRICTATIME);
@@ -2754,6 +2869,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make sure we can reach put_old from new_root */
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
+	/* make certain new is below the root */
+	if (!is_path_reachable(new_mnt, new.dentry, &root))
+		goto out4;
 	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
 	detach_mnt(new_mnt, &parent_path);