[PATCH 3.16 310/346] fanotify: fix list corruption in fanotify_get_response()

From: Ben Hutchings
Date: Sun Nov 13 2016 - 22:24:19 EST


3.16.39-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jan Kara <jack@xxxxxxx>

commit 96d41019e3ac55f6f0115b0ce97e4f24a3d636d2 upstream.

fanotify_get_response() calls fsnotify_remove_event() when it finds that
group is being released from fanotify_release() (bypass_perm is set).

However the event it removes need not be only in the group's notification
queue but it can have already moved to access_list (userspace read the
event before closing the fanotify instance fd) which is protected by a
different lock. Thus when fsnotify_remove_event() races with
fanotify_release() operating on access_list, the list can get corrupted.

Fix the problem by moving all the logic removing permission events from
the lists to one place - fanotify_release().

Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events")
Link: http://lkml.kernel.org/r/1473797711-14111-3-git-send-email-jack@xxxxxxx
Signed-off-by: Jan Kara <jack@xxxxxxx>
Reported-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
Tested-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
Reviewed-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 3.16:
- s/fsnotify_remove_first_event/fsnotify_remove_notify_event/
- Adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
fs/notify/fanotify/fanotify.c | 13 +------------
fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++------------
fs/notify/notification.c | 15 ---------------
include/linux/fsnotify_backend.h | 3 ---
4 files changed, 25 insertions(+), 42 deletions(-)

--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ static int fanotify_get_response(struct

pr_debug("%s: group=%p event=%p\n", __func__, group, event);

- wait_event(group->fanotify_data.access_waitq, event->response ||
- atomic_read(&group->fanotify_data.bypass_perm));
-
- if (!event->response) { /* bypass_perm set */
- /*
- * Event was canceled because group is being destroyed. Remove
- * it from group's event list because we are responsible for
- * freeing the permission event.
- */
- fsnotify_remove_event(group, &event->fae.fse);
- return 0;
- }
+ wait_event(group->fanotify_data.access_waitq, event->response);

/* userspace responded, convert to something usable */
switch (event->response) {
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode

#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_perm_event_info *event, *next;
+ struct fsnotify_event *fsn_event;

/*
- * There may be still new events arriving in the notification queue
- * but since userspace cannot use fanotify fd anymore, no event can
- * enter or leave access_list by now.
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
*/
- spin_lock(&group->fanotify_data.access_lock);
-
- atomic_inc(&group->fanotify_data.bypass_perm);
+ fsnotify_group_stop_queueing(group);

+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->fanotify_data.access_lock);
list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
fae.fse.list) {
pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode
spin_unlock(&group->fanotify_data.access_lock);

/*
- * Since bypass_perm is set, newly queued events will not wait for
- * access response. Wake up the already sleeping ones now.
- * synchronize_srcu() in fsnotify_destroy_group() will wait for all
- * processes sleeping in fanotify_handle_event() waiting for access
- * response and thus also for all permission events to be freed.
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
*/
+ mutex_lock(&group->notification_mutex);
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ fsn_event = fsnotify_remove_notify_event(group);
+ if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+ fsnotify_destroy_event(group, fsn_event);
+ else
+ FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ }
+ mutex_unlock(&group->notification_mutex);
+
+ /* Response for all permission events it set, wakeup waiters */
wake_up(&group->fanotify_data.access_waitq);
#endif

@@ -742,7 +755,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned
spin_lock_init(&group->fanotify_data.access_lock);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
- atomic_set(&group->fanotify_data.bypass_perm, 0);
#endif
switch (flags & FAN_ALL_CLASS_BITS) {
case FAN_CLASS_NOTIF:
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -132,21 +132,6 @@ queue:
}

/*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
- struct fsnotify_event *event)
-{
- mutex_lock(&group->notification_mutex);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- group->q_len--;
- }
- mutex_unlock(&group->notification_mutex);
-}
-
-/*
* Remove and return the first event from the notification list. It is the
* responsibility of the caller to destroy the obtained event
*/
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -182,7 +182,6 @@ struct fsnotify_group {
spinlock_t access_lock;
struct list_head access_list;
wait_queue_head_t access_waitq;
- atomic_t bypass_perm;
#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
int f_flags;
unsigned int max_marks;
@@ -329,8 +328,6 @@ extern int fsnotify_add_notify_event(str
struct fsnotify_event *event,
int (*merge)(struct list_head *,
struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
/* true if the group notification queue is empty */
extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
/* return, but do not dequeue the first event on the notification queue */