drbd: only fail empty flushes if no good data is reachable

We completed empty flushes (blkdev_issue_flush()) with IO error
if we lost the local disk, even if we still have an established
replication link to a healthy remote disk.

Fix this to only report errors to upper layers,
if neither local nor remote data is reachable.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 16 insertions, 4 deletions

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 9f7ff1cb46ff..beefe65764ff 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -263,8 +263,7 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
                 else
                         root = &mdev->read_requests;
                 drbd_remove_request_interval(root, req);
-        } else if (!(s & RQ_POSTPONED))
-                D_ASSERT((s & (RQ_NET_MASK & ~RQ_NET_DONE)) == 0);
+        }
 
         /* Before we can signal completion to the upper layers,
          * we may need to close the current transfer log epoch.
@@ -755,6 +754,11 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
                 D_ASSERT(req->rq_state & RQ_NET_PENDING);
                 mod_rq_state(req, m, RQ_NET_PENDING, RQ_NET_OK|RQ_NET_DONE);
                 break;
+
+        case QUEUE_AS_DRBD_BARRIER:
+                start_new_tl_epoch(mdev->tconn);
+                mod_rq_state(req, m, 0, RQ_NET_OK|RQ_NET_DONE);
+                break;
         };
 
         return rv;
@@ -975,8 +979,8 @@ static int drbd_process_write_request(struct drbd_request *req)
                 /* The only size==0 bios we expect are empty flushes. */
                 D_ASSERT(req->master_bio->bi_rw & REQ_FLUSH);
                 if (remote)
-                        start_new_tl_epoch(mdev->tconn);
-                return 0;
+                        _req_mod(req, QUEUE_AS_DRBD_BARRIER);
+                return remote;
         }
 
         if (!remote && !send_oos)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index c08d22964d06..978cb1addc98 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -88,6 +88,14 @@ enum drbd_req_event {
         QUEUE_FOR_NET_READ,
         QUEUE_FOR_SEND_OOS,
 
+        /* An empty flush is queued as P_BARRIER,
+         * which will cause it to complete "successfully",
+         * even if the local disk flush failed.
+         *
+         * Just like "real" requests, empty flushes (blkdev_issue_flush()) will
+         * only see an error if neither local nor remote data is reachable. */
+        QUEUE_AS_DRBD_BARRIER,
+
         SEND_CANCELED,
         SEND_FAILED,
         HANDED_OVER_TO_NETWORK,