drbd: allow read requests to be retried after force-detach

Sometimes, a lower level block device turns into a tar-pit,
not completing requests at all, not even doing error completion.

We can force-detach from such a tar-pit block device,
either by disk-timeout, or by drbdadm detach --force.

Queueing for retry only from the request destruction path (kref hit 0)
makes it impossible to retry affected read requests from the peer,
until the local IO completion happened, as the locally submitted
bio holds a reference on the drbd request object.

If we can only complete READs when the local completion finally
happens, we would not need to force-detach in the first place.

Instead, queue for retry where we otherwise had done the error completion.

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

1 files changed, 18 insertions, 5 deletions

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index d07cb31a36e..c0acd86c841 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2216,12 +2216,25 @@ static void do_retry(struct work_struct *ws)
 		struct drbd_conf *mdev = req->w.mdev;
 		struct bio *bio = req->master_bio;
 		unsigned long start_time = req->start_time;
-
-		/* We have exclusive access to this request object.
-		 * If it had not been RQ_POSTPONED, the code path which queued
-		 * it here would have completed and freed it already.
+		bool expected;
+
+		expected = 
+			expect(atomic_read(&req->completion_ref) == 0) &&
+			expect(req->rq_state & RQ_POSTPONED) &&
+			expect((req->rq_state & RQ_LOCAL_PENDING) == 0 ||
+				(req->rq_state & RQ_LOCAL_ABORTED) != 0);
+
+		if (!expected)
+			dev_err(DEV, "req=%p completion_ref=%d rq_state=%x\n",
+				req, atomic_read(&req->completion_ref),
+				req->rq_state);
+
+		/* We still need to put one kref associated with the
+		 * "completion_ref" going zero in the code path that queued it
+		 * here.  The request object may still be referenced by a
+		 * frozen local req->private_bio, in case we force-detached.
 		 */
-		mempool_free(req, drbd_request_mempool);
+		kref_put(&req->kref, drbd_req_destroy);
 
 		/* A single suspended or otherwise blocking device may stall
 		 * all others as well.  Fortunately, this code path is to