From: Ming Lei <ming.lei@xxxxxxxxxx>
commit 29b434d1e49252b3ad56ad3197e47fafff5356a1 upstream.
Move start_freeze into nvme_rdma_configure_io_queues(), and there is
at least two benefits:
1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal
2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.
One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:
1) same problem exists with current code base
2) compared with !mpath, mpath use case is dominant
Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
Tested-by: Yi Zhang <yi.zhang@xxxxxxxxxx>
Reviewed-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/nvme/host/rdma.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -918,6 +918,7 @@ static int nvme_rdma_configure_io_queues
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -926,6 +927,7 @@ static int nvme_rdma_configure_io_queues
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -975,7 +977,6 @@ static void nvme_rdma_teardown_io_queues
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
