From: Ilya Dryomov <idryomov@xxxxxxxxx>
commit 69c7b2fe4c9cc1d3b1186d1c5606627ecf0de883 upstream.
The way the delayed work is handled in ceph_monc_stop() is prone to
races with mon_fault() and possibly also finish_hunting(). Both of
these can requeue the delayed work which wouldn't be canceled by any of
the following code in case that happens after cancel_delayed_work_sync()
runs -- __close_session() doesn't mess with the delayed work in order
to avoid interfering with the hunting interval logic. This part was
missed in commit b5d91704f53e ("libceph: behave in mon_fault() if
cur_mon < 0") and use-after-free can still ensue on monc and objects
that hang off of it, with monc->auth and monc->monmap being
particularly susceptible to quickly being reused.
To fix this:
- clear monc->cur_mon and monc->hunting as part of closing the session
in ceph_monc_stop()
- bail from delayed_work() if monc->cur_mon is cleared, similar to how
it's done in mon_fault() and finish_hunting() (based on monc->hunting)
- call cancel_delayed_work_sync() after the session is closed
Cc: stable@xxxxxxxxxxxxxxx
Link: https://tracker.ceph.com/issues/66857
Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxx>
Reviewed-by: Xiubo Li <xiubli@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/ceph/mon_client.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -963,13 +963,19 @@ static void delayed_work(struct work_str
struct ceph_mon_client *monc =
container_of(work, struct ceph_mon_client, delayed_work.work);
- dout("monc delayed_work\n");
mutex_lock(&monc->mutex);
+ dout("%s mon%d\n", __func__, monc->cur_mon);
+ if (monc->cur_mon < 0) {
+ goto out;
+ }
+
if (monc->hunting) {
dout("%s continuing hunt\n", __func__);
reopen_session(monc);
} else {
int is_auth = ceph_auth_is_authenticated(monc->auth);
+
+ dout("%s is_authed %d\n", __func__, is_auth);
if (ceph_con_keepalive_expired(&monc->con,
CEPH_MONC_PING_TIMEOUT)) {
dout("monc keepalive timeout\n");
@@ -994,6 +1000,8 @@ static void delayed_work(struct work_str
}
}
__schedule_delayed(monc);
+
+out:
mutex_unlock(&monc->mutex);
}
@@ -1106,13 +1114,15 @@ EXPORT_SYMBOL(ceph_monc_init);
void ceph_monc_stop(struct ceph_mon_client *monc)
{
dout("stop\n");
- cancel_delayed_work_sync(&monc->delayed_work);
mutex_lock(&monc->mutex);
__close_session(monc);
+ monc->hunting = false;
monc->cur_mon = -1;
mutex_unlock(&monc->mutex);
+ cancel_delayed_work_sync(&monc->delayed_work);
+
/*
* flush msgr queue before we destroy ourselves to ensure that:
* - any work that references our embedded con is finished.
Patches currently in stable-queue which might be from idryomov@xxxxxxxxx are
queue-4.19/libceph-fix-race-between-delayed_work-and-ceph_monc_stop.patch
