1 files changed, 38 insertions, 44 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 1b466c54a357..2f2e93927f46 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -355,12 +355,13 @@ static struct mount *alloc_vfsmnt(const char *name)
 		if (err)
 			goto out_free_cache;
 
-		if (name) {
+		if (name)
 			mnt->mnt_devname = kstrdup_const(name,
 							 GFP_KERNEL_ACCOUNT);
-			if (!mnt->mnt_devname)
-				goto out_free_id;
-		}
+		else
+			mnt->mnt_devname = "none";
+		if (!mnt->mnt_devname)
+			goto out_free_id;
 
 #ifdef CONFIG_SMP
 		mnt->mnt_pcp = alloc_percpu(struct mnt_pcp);
@@ -1264,7 +1265,7 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc)
 	if (!fc->root)
 		return ERR_PTR(-EINVAL);
 
-	mnt = alloc_vfsmnt(fc->source ?: "none");
+	mnt = alloc_vfsmnt(fc->source);
 	if (!mnt)
 		return ERR_PTR(-ENOMEM);
 
@@ -1325,21 +1326,6 @@ struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
-struct vfsmount *
-vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
-	     const char *name, void *data)
-{
-	/* Until it is worked out how to pass the user namespace
-	 * through from the parent mount to the submount don't support
-	 * unprivileged mounts with submounts.
-	 */
-	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
-		return ERR_PTR(-EPERM);
-
-	return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
-}
-EXPORT_SYMBOL_GPL(vfs_submount);
-
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -3648,7 +3634,7 @@ static int do_move_mount(struct path *old_path,
 	if (!(attached ? check_mnt(old) : is_anon_ns(ns)))
 		goto out;
 
-	if (is_anon_ns(ns)) {
+	if (is_anon_ns(ns) && ns == p->mnt_ns) {
 		/*
 		 * Ending up with two files referring to the root of the
 		 * same anonymous mount namespace would cause an error
@@ -3656,16 +3642,7 @@ static int do_move_mount(struct path *old_path,
 		 * twice into the mount tree which would be rejected
 		 * later. But be explicit about it right here.
 		 */
-		if ((is_anon_ns(p->mnt_ns) && ns == p->mnt_ns))
-			goto out;
-
-		/*
-		 * If this is an anonymous mount tree ensure that mount
-		 * propagation can detect mounts that were just
-		 * propagated to the target mount tree so we don't
-		 * propagate onto them.
-		 */
-		ns->mntns_flags |= MNTNS_PROPAGATING;
+		goto out;
 	} else if (is_anon_ns(p->mnt_ns)) {
 		/*
 		 * Don't allow moving an attached mount tree to an
@@ -3722,8 +3699,6 @@ static int do_move_mount(struct path *old_path,
 	if (attached)
 		put_mountpoint(old_mp);
 out:
-	if (is_anon_ns(ns))
-		ns->mntns_flags &= ~MNTNS_PROPAGATING;
 	unlock_mount(mp);
 	if (!err) {
 		if (attached) {
@@ -3899,10 +3874,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 		return PTR_ERR(m);
 
 	mnt = real_mount(m);
-	/* The new mount record should have at least 2 refs to prevent it being
-	 * expired before we get a chance to add it
-	 */
-	BUG_ON(mnt_get_count(mnt) < 2);
 
 	if (m->mnt_sb == path->mnt->mnt_sb &&
 	    m->mnt_root == dentry) {
@@ -3935,7 +3906,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 	unlock_mount(mp);
 	if (unlikely(err))
 		goto discard;
-	mntput(m);
 	return 0;
 
 discard_locked:
@@ -3949,7 +3919,6 @@ discard:
 		namespace_unlock();
 	}
 	mntput(m);
-	mntput(m);
 	return err;
 }
 
@@ -3986,11 +3955,14 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 
 	/* extract from the expiration list every vfsmount that matches the
 	 * following criteria:
+	 * - already mounted
 	 * - 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 (!is_mounted(&mnt->mnt))
+			continue;
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
 			propagate_mount_busy(mnt, 1))
 			continue;
@@ -5491,7 +5463,7 @@ static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq)
 		seq->buf[seq->count] = '\0';
 		seq->count = start;
 		seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
-	} else if (r->mnt_devname) {
+	} else {
 		seq_puts(seq, r->mnt_devname);
 	}
 	return 0;
@@ -5804,7 +5776,9 @@ static int grab_requested_root(struct mnt_namespace *ns, struct path *root)
 			     STATMOUNT_SB_SOURCE | \
 			     STATMOUNT_OPT_ARRAY | \
 			     STATMOUNT_OPT_SEC_ARRAY | \
-			     STATMOUNT_SUPPORTED_MASK)
+			     STATMOUNT_SUPPORTED_MASK | \
+			     STATMOUNT_MNT_UIDMAP | \
+			     STATMOUNT_MNT_GIDMAP)
 
 static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 			struct mnt_namespace *ns)
@@ -5839,13 +5813,29 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 		return err;
 
 	s->root = root;
-	s->idmap = mnt_idmap(s->mnt);
-	if (s->mask & STATMOUNT_SB_BASIC)
-		statmount_sb_basic(s);
 
+	/*
+	 * Note that mount properties in mnt->mnt_flags, mnt->mnt_idmap
+	 * can change concurrently as we only hold the read-side of the
+	 * namespace semaphore and mount properties may change with only
+	 * the mount lock held.
+	 *
+	 * We could sample the mount lock sequence counter to detect
+	 * those changes and retry. But it's not worth it. Worst that
+	 * happens is that the mnt->mnt_idmap pointer is already changed
+	 * while mnt->mnt_flags isn't or vica versa. So what.
+	 *
+	 * Both mnt->mnt_flags and mnt->mnt_idmap are set and retrieved
+	 * via READ_ONCE()/WRITE_ONCE() and guard against theoretical
+	 * torn read/write. That's all we care about right now.
+	 */
+	s->idmap = mnt_idmap(s->mnt);
 	if (s->mask & STATMOUNT_MNT_BASIC)
 		statmount_mnt_basic(s);
 
+	if (s->mask & STATMOUNT_SB_BASIC)
+		statmount_sb_basic(s);
+
 	if (s->mask & STATMOUNT_PROPAGATE_FROM)
 		statmount_propagate_from(s);
 
@@ -6157,6 +6147,10 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	    !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
 		return -ENOENT;
 
+	/*
+	 * We only need to guard against mount topology changes as
+	 * listmount() doesn't care about any mount properties.
+	 */
 	scoped_guard(rwsem_read, &namespace_sem)
 		ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids,
 				   nr_mnt_ids, (flags & LISTMOUNT_REVERSE));