Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b6a370ba authored by Philipp Reisner's avatar Philipp Reisner
Browse files

drbd: Fix a potential write ordering issue on SyncTarget nodes 



If a SyncTarget node gets a P_RS_DATA_REPLY before a P_DATA packet
for the same sector, it simply submits these two IO requests.

  This is be possible because on the SyncSource node, the data of the
  P_RS_DATA_REPLY packet was read from disk.  Immediately after that a
  write request from upper layers came in.

The disk scheduler or even the "hardware" queues on the disk drive might
reorder these writes.

Signed-off-by: default avatarPhilipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: default avatarLars Ellenberg <lars.ellenberg@linbit.com>
parent fc28845b

drivers/block/drbd/drbd_receiver.c

+21 −0
Original line number Diff line number Diff line
@@ -1585,6 +1585,24 @@ static int e_send_discard_ack(struct drbd_conf *mdev, struct drbd_work *w, int u 
	return ok;

}



static bool overlapping_resync_write(struct drbd_conf *mdev, struct drbd_epoch_entry *data_e)

{



	struct drbd_epoch_entry *rs_e;

	bool rv = 0;



	spin_lock_irq(&mdev->req_lock);

	list_for_each_entry(rs_e, &mdev->sync_ee, w.list) {

		if (overlaps(data_e->sector, data_e->size, rs_e->sector, rs_e->size)) {

			rv = 1;

			break;

		}

	}

	spin_unlock_irq(&mdev->req_lock);



	return rv;

}



/* Called from receive_Data.

 * Synchronize packets on sock with packets on msock.

 *
@@ -1828,6 +1846,9 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned 
	list_add(&e->w.list, &mdev->active_ee);

	spin_unlock_irq(&mdev->req_lock);



	if (mdev->state.conn == C_SYNC_TARGET)

		wait_event(mdev->ee_wait, !overlapping_resync_write(mdev, e));



	switch (mdev->net_conf->wire_protocol) {

	case DRBD_PROT_C:

		inc_unacked(mdev);