drbd: Finish requests that completed while IO was frozen

Requests of an acked epoch are stored on the barrier_acked_requests list. In
case the private bio of such a request completes while IO on the drbd device
is suspended [req_mod(completed_ok)] then the request stays there.

When thawing IO because the fence_peer handler returned, then we use
tl_clear() to apply the connection_lost_while_pending event to all requests
on the transfer-log and the barrier_acked_requests list.

Up to now the connection_lost_while_pending event was not applied
on requests on the barrier_acked_requests list. Fixed that.

I.e. now the connection_lost_while_pending and resend events are
applied to requests on the barrier_acked_requests list. For that
it is necessary that the resend event finishes (local only)
READS correctly.

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_req.c b/drivers/block/drbd/drbd_req.c
index a9111b6..6e8d097 100644 (file)
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -683,6 +683,12 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
                break;
 
        case RESEND:
+               /* Simply complete (local only) READs. */
+               if (!(req->rq_state & RQ_WRITE) && !req->w.cb) {
+                       mod_rq_state(req, m, RQ_COMPLETION_SUSP, 0);
+                       break;
+               }
+
                /* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK
                   before the connection loss (B&C only); only P_BARRIER_ACK
                   (or the local completion?) was missing when we suspended.

diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 12f2b4f..c16349a 100644 (file)
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1503,7 +1503,6 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
        if (ns_max.susp_fen) {
                /* case1: The outdate peer handler is successful: */
                if (ns_max.pdsk <= D_OUTDATED) {
-                       tl_clear(tconn);
                        rcu_read_lock();
                        idr_for_each_entry(&tconn->volumes, mdev, vnr) {
                                if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
@@ -1512,10 +1511,13 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
                                }
                        }
                        rcu_read_unlock();
-                       conn_request_state(tconn,
-                                          (union drbd_state) { { .susp_fen = 1 } },
-                                          (union drbd_state) { { .susp_fen = 0 } },
-                                          CS_VERBOSE);
+                       spin_lock_irq(&tconn->req_lock);
+                       _tl_restart(tconn, CONNECTION_LOST_WHILE_PENDING);
+                       _conn_request_state(tconn,
+                                           (union drbd_state) { { .susp_fen = 1 } },
+                                           (union drbd_state) { { .susp_fen = 0 } },
+                                           CS_VERBOSE);
+                       spin_unlock_irq(&tconn->req_lock);
                }
                /* case2: The connection was established again: */
                if (ns_min.conn >= C_CONNECTED) {