From 068f73f767a1ed7f27f1eb48343a7bf2d88c1a58 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 30 Jul 2020 13:42:42 -0700 Subject: nvme-rdma: fix reset hang if controller died in the middle of a reset [ Upstream commit 2362acb6785611eda795bfc12e1ea6b202ecf62c ] 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 Signed-off-by: Sagi Grimberg Signed-off-by: Sasha Levin --- drivers/nvme/host/rdma.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'drivers/nvme/host/rdma.c') diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4e73da2c45bb..f0847f2bb117 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -899,7 +899,15 @@ 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); @@ -907,6 +915,9 @@ 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); -- cgit v1.2.3