nvme-fc: release io queues to allow fast fail

Rather than leaving io queues quiesced after tearing down an association,
restart them. This allows ios to be replayed, with fastfail ios terminating
and non-fastfail getting into loops of retry.

This follows rdma's lead.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimber.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index b528a2f5826cbfe19b22aadd7e09e1ceff512cb6..41d45a1b5c628c143caac1886bd52f08a360f15e 100644 (file)
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2790,6 +2790,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
        /* re-enable the admin_q so anything new can fast fail */
        blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
+       /* resume the io queues so that things will fast fail */
+       nvme_start_queues(&ctrl->ctrl);
+
        nvme_fc_ctlr_inactive_on_rport(ctrl);
 }
 
@@ -2804,9 +2807,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl)
         * waiting for io to terminate
         */
        nvme_fc_delete_association(ctrl);
-
-       /* resume the io queues so that things will fast fail */
-       nvme_start_queues(nctrl);
 }
 
 static void