drbd: serialize sending of resync uuid with pending w_send_oos

To improve the latency of IO requests during bitmap exchange,
we recently allowed writes while waiting for the bitmap, sending "set
out-of-sync" information packets for any newly dirtied bits.

We have to make sure that the new resync-uuid does not overtake
these "set oos" packets. Once the resync-uuid is received, the
sync target starts the resync process, and expects the bitmap to
only be cleared, not re-set.

If we use this protocol extension, we queue the generation and sending
of the resync-uuid on the worker, which naturally serializes with all
previously queued packets.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

drivers/block/drbd/drbd_int.h

@@ -1204,7 +1204,7 @@ extern int drbd_send(struct drbd_conf *mdev, struct socket *sock,
 extern int drbd_send_protocol(struct drbd_conf *mdev);
 extern int drbd_send_uuids(struct drbd_conf *mdev);
 extern int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev);
-extern int drbd_send_sync_uuid(struct drbd_conf *mdev, u64 val);
+extern int drbd_gen_and_send_sync_uuid(struct drbd_conf *mdev);
 extern int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags flags);
 extern int _drbd_send_state(struct drbd_conf *mdev);
 extern int drbd_send_state(struct drbd_conf *mdev);

drivers/block/drbd/drbd_main.c

@@ -1387,6 +1387,17 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 		spin_unlock_irq(&mdev->req_lock);
 	}
 
+	/* Became sync source.  With protocol >= 96, we still need to send out
+	 * the sync uuid now. Need to do that before any drbd_send_state, or
+	 * the other side may go "paused sync" before receiving the sync uuids,
+	 * which is unexpected. */
+	if ((os.conn != C_SYNC_SOURCE && os.conn != C_PAUSED_SYNC_S) &&
+	    (ns.conn == C_SYNC_SOURCE || ns.conn == C_PAUSED_SYNC_S) &&
+	    mdev->agreed_pro_version >= 96 && get_ldev(mdev)) {
+		drbd_gen_and_send_sync_uuid(mdev);
+		put_ldev(mdev);
+	}
+
 	/* Do not change the order of the if above and the two below... */
 	if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) {      /* attach on the peer */
 		drbd_send_uuids(mdev);
@@ -1980,12 +1991,17 @@ int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev)
 	return _drbd_send_uuids(mdev, 8);
 }
 
-
-int drbd_send_sync_uuid(struct drbd_conf *mdev, u64 val)
+int drbd_gen_and_send_sync_uuid(struct drbd_conf *mdev)
 {
 	struct p_rs_uuid p;
+	u64 uuid;
+
+	D_ASSERT(mdev->state.disk == D_UP_TO_DATE);
 
-	p.uuid = cpu_to_be64(val);
+	get_random_bytes(&uuid, sizeof(u64));
+	drbd_uuid_set(mdev, UI_BITMAP, uuid);
+	drbd_md_sync(mdev);
+	p.uuid = cpu_to_be64(uuid);
 
 	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SYNC_UUID,
 			     (struct p_header80 *)&p, sizeof(p));

drivers/block/drbd/drbd_worker.c

@@ -1516,18 +1516,6 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 		return;
 	}
 
-	if (side == C_SYNC_TARGET) {
-		mdev->bm_resync_fo = 0;
-	} else /* side == C_SYNC_SOURCE */ {
-		u64 uuid;
-
-		get_random_bytes(&uuid, sizeof(u64));
-		drbd_uuid_set(mdev, UI_BITMAP, uuid);
-		drbd_send_sync_uuid(mdev, uuid);
-
-		D_ASSERT(mdev->state.disk == D_UP_TO_DATE);
-	}
-
 	write_lock_irq(&global_state_lock);
 	ns = mdev->state;
 
@@ -1565,7 +1553,19 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 		_drbd_pause_after(mdev);
 	}
 	write_unlock_irq(&global_state_lock);
-	put_ldev(mdev);
+
+	if (side == C_SYNC_TARGET)
+		mdev->bm_resync_fo = 0;
+
+	/* Since protocol 96, we must serialize drbd_gen_and_send_sync_uuid
+	 * with w_send_oos, or the sync target will get confused as to
+	 * how much bits to resync.  We cannot do that always, because for an
+	 * empty resync and protocol < 95, we need to do it here, as we call
+	 * drbd_resync_finished from here in that case.
+	 * We drbd_gen_and_send_sync_uuid here for protocol < 96,
+	 * and from after_state_ch otherwise. */
+	if (side == C_SYNC_SOURCE && mdev->agreed_pro_version < 96)
+		drbd_gen_and_send_sync_uuid(mdev);
 
 	if (r == SS_SUCCESS) {
 		dev_info(DEV, "Began resync as %s (will sync %lu KB [%lu bits set]).\n",
@@ -1601,6 +1601,7 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 
 		drbd_md_sync(mdev);
 	}
+	put_ldev(mdev);
 	drbd_state_unlock(mdev);
 }