From: Sagi Grimberg <sagi@xxxxxxxxxxx>
[ 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 <hch@xxxxxx>
Signed-off-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/nvme/host/rdma.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 99bf88eb812c5..6c07bb55b0f83 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -950,7 +950,15 @@ 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);
@@ -958,6 +966,9 @@ 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);
--
2.25.1
