hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

nvme-rdma: teardown admin/io queues once on error recovery 

Relying on the queue state while tearing down on every reconnect
attempt is not a good design. We should do it once in err_work
and simply try to establish the queues for each reconnect attempt.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
Sagi Grimberg 2017-10-11 15:29:11 +03:00 committed by Christoph Hellwig
parent 0fc176dfda
commit 5e1fe61d41
1 changed files with 12 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
drivers/nvme/host/rdma.c
View File

@ -925,10 +925,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
++ctrl->ctrl.nr_reconnects;
if (ctrl->ctrl.queue_count > 1)
nvme_rdma_destroy_io_queues(ctrl, false);
nvme_rdma_destroy_admin_queue(ctrl, false);
ret = nvme_rdma_configure_admin_queue(ctrl, false);
if (ret)
goto requeue;
@ -936,7 +932,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
if (ctrl->ctrl.queue_count > 1) {
ret = nvme_rdma_configure_io_queues(ctrl, false);
if (ret)
goto requeue;
goto destroy_admin;
}
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
@ -946,14 +942,17 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
return;
}
ctrl->ctrl.nr_reconnects = 0;
nvme_start_ctrl(&ctrl->ctrl);
dev_info(ctrl->ctrl.device, "Successfully reconnected\n");
dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
ctrl->ctrl.nr_reconnects);
ctrl->ctrl.nr_reconnects = 0;
return;
destroy_admin:
nvme_rdma_destroy_admin_queue(ctrl, false);
requeue:
dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
ctrl->ctrl.nr_reconnects);
@ -969,17 +968,15 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
}
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
/* We must take care of fastfail/requeue all our inflight requests */
if (ctrl->ctrl.queue_count > 1)
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, false);
}
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, false);
/*
* queues are not a live anymore, so restart the queues to fail fast