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: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 6b0505a..d601501 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1585,6 +1585,24 @@
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 @@
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);