nvme: fix regression when disconnect a recovering ctrl
We encountered a problem that the disconnect command hangs.
After analyzing the log and stack, we found that the triggering
process is as follows:
CPU0 CPU1
nvme_rdma_error_recovery_work
nvme_rdma_teardown_io_queues
nvme_do_delete_ctrl nvme_stop_queues
nvme_remove_namespaces
--clear ctrl->namespaces
nvme_start_queues
--no ns in ctrl->namespaces
nvme_ns_remove return(because ctrl is deleting)
blk_freeze_queue
blk_mq_freeze_queue_wait
--wait for ns to unquiesce to clean infligt IO, hang forever
This problem was not found in older kernels because we will flush
err work in nvme_stop_ctrl before nvme_remove_namespaces.It does not
seem to be modified for functional reasons, the patch can be revert
to solve the problem.
Revert commit 794a4cb3d2f7 ("nvme: remove the .stop_ctrl callout")
Signed-off-by: Ruozhu Li <liruozhu@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 009c2cf3..7a9e6ff 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2193,9 +2193,6 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
{
- cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
- cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
-
nvme_tcp_teardown_io_queues(ctrl, shutdown);
nvme_stop_admin_queue(ctrl);
if (shutdown)
@@ -2235,6 +2232,12 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
nvme_tcp_reconnect_or_remove(ctrl);
}
+static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
+{
+ cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work);
+ cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
+}
+
static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
@@ -2556,6 +2559,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
.submit_async_event = nvme_tcp_submit_async_event,
.delete_ctrl = nvme_tcp_delete_ctrl,
.get_address = nvmf_get_address,
+ .stop_ctrl = nvme_tcp_stop_ctrl,
};
static bool
