diff mbox series

[5.4,043/270] nvme-rdma: fix controller reset hang during traffic

Message ID 20200817143757.947858638@linuxfoundation.org
State New
Headers show
Series None | expand

Commit Message

Greg KH Aug. 17, 2020, 3:14 p.m. UTC 
From: Sagi Grimberg <sagi@grimberg.me>

[ Upstream commit 9f98772ba307dd89a3d17dc2589f213d3972fc64 ]

commit fe35ec58f0d3 ("block: update hctx map when use multiple maps")
exposed an issue where we may hang trying to wait for queue freeze
during I/O. We call blk_mq_update_nr_hw_queues which in case of multiple
queue maps (which we have now for default/read/poll) is attempting to
freeze the queue. However we never started queue freeze when starting the
reset, which means that we have inflight pending requests that entered the
queue that we will not complete once the queue is quiesced.

So start a freeze before we quiesce the queue, and unfreeze the queue
after we successfully connected the I/O queues (and make sure to call
blk_mq_update_nr_hw_queues only after we are sure that the queue was
already frozen).

This follows to how the pci driver handles resets.

Fixes: fe35ec58f0d3 ("block: update hctx map when use multiple maps")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/host/rdma.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index cd0d499781908..d0336545e1fe0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -890,15 +890,20 @@  static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->ctrl.connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(&ctrl->tag_set,
-			ctrl->ctrl.queue_count - 1);
 	}
 
 	ret = nvme_rdma_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_wait_freeze(&ctrl->ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
+			ctrl->ctrl.queue_count - 1);
+		nvme_unfreeze(&ctrl->ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -931,6 +936,7 @@  static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {