summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSagi Grimberg <sagi@grimberg.me>2020-07-30 13:42:42 -0700
committerSagi Grimberg <sagi@grimberg.me>2020-08-28 16:43:57 -0700
commit2362acb6785611eda795bfc12e1ea6b202ecf62c (patch)
tree91e74929817b26140bac7093ae5be70efb7b4bd0
parent0475a8dcbcee92a5d22e40c9c6353829fc6294b8 (diff)
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>
-rw-r--r--drivers/nvme/host/rdma.c13
1 files changed, 12 insertions, 1 deletions
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index cb8731f4b316..1d8ea5305d60 100644
--- 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);