Commit d29e89e3 authored by Roland Kammerer's avatar Roland Kammerer Committed by Jens Axboe

drbd: narrow rcu_read_lock in drbd_sync_handshake

So far there was the possibility that we called
genlmsg_new(GFP_NOIO)/mutex_lock() while holding an rcu_read_lock().

This included cases like:

drbd_sync_handshake (acquire the RCU lock)
  drbd_asb_recover_1p
    drbd_khelper
      drbd_bcast_event
        genlmsg_new(GFP_NOIO) --> may sleep

drbd_sync_handshake (acquire the RCU lock)
  drbd_asb_recover_1p
    drbd_khelper
      notify_helper
        genlmsg_new(GFP_NOIO) --> may sleep

drbd_sync_handshake (acquire the RCU lock)
  drbd_asb_recover_1p
    drbd_khelper
      notify_helper
        mutex_lock --> may sleep

While using GFP_ATOMIC whould have been possible in the first two cases,
the real fix is to narrow the rcu_read_lock.
Reported-by: default avatarJia-Ju Bai <baijiaju1990@163.com>
Reviewed-by: default avatarLars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: default avatarRoland Kammerer <roland.kammerer@linbit.com>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 3a762de5
......@@ -3364,7 +3364,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
enum drbd_conns rv = C_MASK;
enum drbd_disk_state mydisk;
struct net_conf *nc;
int hg, rule_nr, rr_conflict, tentative;
int hg, rule_nr, rr_conflict, tentative, always_asbp;
mydisk = device->state.disk;
if (mydisk == D_NEGOTIATING)
......@@ -3415,8 +3415,12 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
rcu_read_lock();
nc = rcu_dereference(peer_device->connection->net_conf);
always_asbp = nc->always_asbp;
rr_conflict = nc->rr_conflict;
tentative = nc->tentative;
rcu_read_unlock();
if (hg == 100 || (hg == -100 && nc->always_asbp)) {
if (hg == 100 || (hg == -100 && always_asbp)) {
int pcount = (device->state.role == R_PRIMARY)
+ (peer_role == R_PRIMARY);
int forced = (hg == -100);
......@@ -3455,9 +3459,6 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
"Sync from %s node\n",
(hg < 0) ? "peer" : "this");
}
rr_conflict = nc->rr_conflict;
tentative = nc->tentative;
rcu_read_unlock();
if (hg == -100) {
/* FIXME this log message is not correct if we end up here
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment