nvme-rdma: fix reset hang if controller died in the middle of a reset

If the controller becomes unresponsive in the middle of a reset, we
will hang because we are waiting for the freeze to complete, but that
cannot happen since we have commands that are inflight holding the
q_usage_counter, and we can't blindly fail requests that times out.

So give a timeout and if we cannot wait for queue freeze before
unfreezing, fail and have the error handling take care how to
proceed (either schedule a reconnect of remove the controller).

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index cb8731f4b3166fe35e812ff35c8871d80d45f9a6..1d8ea5305d60f009e0fd0cbe7af3acec7b249a52 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -976,7 +976,15 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
        if (!new) {
                nvme_start_queues(&ctrl->ctrl);
-               nvme_wait_freeze(&ctrl->ctrl);
+               if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
+                       /*
+                        * If we timed out waiting for freeze we are likely to
+                        * be stuck.  Fail the controller initialization just
+                        * to be safe.
+                        */
+                       ret = -ENODEV;
+                       goto out_wait_freeze_timed_out;
+               }
                blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
                        ctrl->ctrl.queue_count - 1);
                nvme_unfreeze(&ctrl->ctrl);
@@ -984,6 +992,9 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
        return 0;
 
+out_wait_freeze_timed_out:
+       nvme_stop_queues(&ctrl->ctrl);
+       nvme_rdma_stop_io_queues(ctrl);
 out_cleanup_connect_q:
        if (new)
                blk_cleanup_queue(ctrl->ctrl.connect_q);