proc/mounts: add cursor

If mounts are deleted after a read(2) call on /proc/self/mounts (or its
kin), the subsequent read(2) could miss a mount that comes after the
deleted one in the list.  This is because the file position is interpreted
as the number mount entries from the start of the list.

E.g. first read gets entries #0 to #9; the seq file index will be 10.  Then
entry #5 is deleted, resulting in #10 becoming #9 and #11 becoming #10,
etc...  The next read will continue from entry #10, and #9 is missed.

Solve this by adding a cursor entry for each open instance.  Taking the
global namespace_sem for write seems excessive, since we are only dealing
with a per-namespace list.  Instead add a per-namespace spinlock and use
that together with namespace_sem taken for read to protect against
concurrent modification of the mount list.  This may reduce parallelism of
is_local_mountpoint(), but it's hardly a big contention point.  We could
also use RCU freeing of cursors to make traversal not need additional
locks, if that turns out to be neceesary.

Only move the cursor once for each read (cursor is not added on open) to
minimize cacheline invalidation.  When EOF is reached, the cursor is taken
off the list, in order to prevent an excessive number of cursors due to
inactive open file descriptors.

Reported-by: Karel Zak <kzak@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

1 files changed, 75 insertions, 16 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index a28e4db075ed..3ee236f228a2 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -648,6 +648,21 @@ struct vfsmount *lookup_mnt(const struct path *path)
 	return m;
 }
 
+static inline void lock_ns_list(struct mnt_namespace *ns)
+{
+	spin_lock(&ns->ns_lock);
+}
+
+static inline void unlock_ns_list(struct mnt_namespace *ns)
+{
+	spin_unlock(&ns->ns_lock);
+}
+
+static inline bool mnt_is_cursor(struct mount *mnt)
+{
+	return mnt->mnt.mnt_flags & MNT_CURSOR;
+}
+
 /*
  * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
  *                         current mount namespace.
@@ -673,11 +688,15 @@ bool __is_local_mountpoint(struct dentry *dentry)
 		goto out;
 
 	down_read(&namespace_sem);
+	lock_ns_list(ns);
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		if (mnt_is_cursor(mnt))
+			continue;
 		is_covered = (mnt->mnt_mountpoint == dentry);
 		if (is_covered)
 			break;
 	}
+	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 out:
 	return is_covered;
@@ -1245,46 +1264,71 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 }
 
 #ifdef CONFIG_PROC_FS
+static struct mount *mnt_list_next(struct mnt_namespace *ns,
+				   struct list_head *p)
+{
+	struct mount *mnt, *ret = NULL;
+
+	lock_ns_list(ns);
+	list_for_each_continue(p, &ns->list) {
+		mnt = list_entry(p, typeof(*mnt), mnt_list);
+		if (!mnt_is_cursor(mnt)) {
+			ret = mnt;
+			break;
+		}
+	}
+	unlock_ns_list(ns);
+
+	return ret;
+}
+
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct list_head *prev;
 
 	down_read(&namespace_sem);
-	if (p->cached_event == p->ns->event) {
-		void *v = p->cached_mount;
-		if (*pos == p->cached_index)
-			return v;
-		if (*pos == p->cached_index + 1) {
-			v = seq_list_next(v, &p->ns->list, &p->cached_index);
-			return p->cached_mount = v;
-		}
+	if (!*pos) {
+		prev = &p->ns->list;
+	} else {
+		prev = &p->cursor.mnt_list;
+
+		/* Read after we'd reached the end? */
+		if (list_empty(prev))
+			return NULL;
 	}
 
-	p->cached_event = p->ns->event;
-	p->cached_mount = seq_list_start(&p->ns->list, *pos);
-	p->cached_index = *pos;
-	return p->cached_mount;
+	return mnt_list_next(p->ns, prev);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct mount *mnt = v;
 
-	p->cached_mount = seq_list_next(v, &p->ns->list, pos);
-	p->cached_index = *pos;
-	return p->cached_mount;
+	++*pos;
+	return mnt_list_next(p->ns, &mnt->mnt_list);
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
+	struct proc_mounts *p = m->private;
+	struct mount *mnt = v;
+
+	lock_ns_list(p->ns);
+	if (mnt)
+		list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list);
+	else
+		list_del_init(&p->cursor.mnt_list);
+	unlock_ns_list(p->ns);
 	up_read(&namespace_sem);
 }
 
 static int m_show(struct seq_file *m, void *v)
 {
 	struct proc_mounts *p = m->private;
-	struct mount *r = list_entry(v, struct mount, mnt_list);
+	struct mount *r = v;
 	return p->show(m, &r->mnt);
 }
 
@@ -1294,6 +1338,15 @@ const struct seq_operations mounts_op = {
 	.stop	= m_stop,
 	.show	= m_show,
 };
+
+void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
+{
+	down_read(&namespace_sem);
+	lock_ns_list(ns);
+	list_del(&cursor->mnt_list);
+	unlock_ns_list(ns);
+	up_read(&namespace_sem);
+}
 #endif  /* CONFIG_PROC_FS */
 
 /**
@@ -3202,6 +3255,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	atomic_set(&new_ns->count, 1);
 	INIT_LIST_HEAD(&new_ns->list);
 	init_waitqueue_head(&new_ns->poll);
+	spin_lock_init(&new_ns->ns_lock);
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
 	return new_ns;
@@ -3842,10 +3896,14 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	bool visible = false;
 
 	down_read(&namespace_sem);
+	lock_ns_list(ns);
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
 		struct mount *child;
 		int mnt_flags;
 
+		if (mnt_is_cursor(mnt))
+			continue;
+
 		if (mnt->mnt.mnt_sb->s_type != sb->s_type)
 			continue;
 
@@ -3893,6 +3951,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	next:	;
 	}
 found:
+	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 	return visible;
 }