nvme-tcp: 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).

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index dbb661b899ef635ed689f2faa59ad19d769d3c4c..873d6afcbc9ee97b7a874d268a7c9707c783f514 100644 (file)
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1783,7 +1783,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
        if (!new) {
                nvme_start_queues(ctrl);
-               nvme_wait_freeze(ctrl);
+               if (!nvme_wait_freeze_timeout(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->tagset,
                        ctrl->queue_count - 1);
                nvme_unfreeze(ctrl);
@@ -1791,6 +1799,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
        return 0;
 
+out_wait_freeze_timed_out:
+       nvme_stop_queues(ctrl);
+       nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
        if (new)
                blk_cleanup_queue(ctrl->connect_q);