[PATCH 2/2 v2] nvme-rdma: fix controller reset hang during traffic

[Sagi Grimberg]

commit fe35ec58f0d3 ("block: update hctx map when use multiple maps")
exposed an issue where we may hang trying to wait for queue freeze
during I/O. We call blk_mq_update_nr_hw_queues which in case of multiple
queue maps (which we have now for default/read/poll) is attempting to
freeze the queue. However we never started queue freeze when starting the
reset, which means that we have inflight pending requests that entered the
queue that we will not complete once the queue is quiesced.

So start a freeze before we quiesce the queue, and unfreeze the queue
after we successfully connected the I/O queues (and make sure to call
blk_mq_update_nr_hw_queues only after we are sure that the queue was
already frozen).

This follows to how the pci driver handles resets.

Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
---
Changes from v1:
- fix silly compilation errors

 drivers/nvme/host/rdma.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 5c3848974ccb..44c76ffbb264 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -967,15 +967,20 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->ctrl.connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(&ctrl->tag_set,
-			ctrl->ctrl.queue_count - 1);
 	}
 
 	ret = nvme_rdma_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_wait_freeze(&ctrl->ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
+			ctrl->ctrl.queue_count - 1);
+		nvme_unfreeze(&ctrl->ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -1008,6 +1013,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {
-- 
2.25.1