@@ -72,6 +72,23 @@ void nvme_tcp_ofld_unregister_dev(struct nvme_tcp_ofld_dev *dev)
}
EXPORT_SYMBOL_GPL(nvme_tcp_ofld_unregister_dev);
+/**
+ * nvme_tcp_ofld_error_recovery() - NVMeTCP Offload library error recovery.
+ * function.
+ * @nctrl: NVMe controller instance to change to resetting.
+ *
+ * API function that change the controller state to resseting.
+ * Part of the overall controller reset sequence.
+ */
+void nvme_tcp_ofld_error_recovery(struct nvme_ctrl *nctrl)
+{
+ if (!nvme_change_ctrl_state(nctrl, NVME_CTRL_RESETTING))
+ return;
+
+ queue_work(nvme_reset_wq, &to_tcp_ofld_ctrl(nctrl)->err_work);
+}
+EXPORT_SYMBOL_GPL(nvme_tcp_ofld_error_recovery);
+
/**
* nvme_tcp_ofld_report_queue_err() - NVMeTCP Offload report error event
* callback function. Pointed to by nvme_tcp_ofld_queue->report_err.
@@ -82,7 +99,8 @@ EXPORT_SYMBOL_GPL(nvme_tcp_ofld_unregister_dev);
*/
int nvme_tcp_ofld_report_queue_err(struct nvme_tcp_ofld_queue *queue)
{
- /* Placeholder - invoke error recovery flow */
+ pr_err("nvme-tcp-offload queue error\n");
+ nvme_tcp_ofld_error_recovery(&queue->ctrl->nctrl);
return 0;
}
@@ -287,6 +305,28 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new)
return rc;
}
+static void nvme_tcp_ofld_reconnect_or_remove(struct nvme_ctrl *nctrl)
+{
+ /* If we are resetting/deleting then do nothing */
+ if (nctrl->state != NVME_CTRL_CONNECTING) {
+ WARN_ON_ONCE(nctrl->state == NVME_CTRL_NEW ||
+ nctrl->state == NVME_CTRL_LIVE);
+
+ return;
+ }
+
+ if (nvmf_should_reconnect(nctrl)) {
+ dev_info(nctrl->device, "Reconnecting in %d seconds...\n",
+ nctrl->opts->reconnect_delay);
+ queue_delayed_work(nvme_wq,
+ &to_tcp_ofld_ctrl(nctrl)->connect_work,
+ nctrl->opts->reconnect_delay * HZ);
+ } else {
+ dev_info(nctrl->device, "Removing controller...\n");
+ nvme_delete_ctrl(nctrl);
+ }
+}
+
static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new)
{
struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
@@ -410,10 +450,63 @@ nvme_tcp_ofld_teardown_io_queues(struct nvme_ctrl *nctrl, bool remove)
/* Placeholder - teardown_io_queues */
}
+static void nvme_tcp_ofld_reconnect_ctrl_work(struct work_struct *work)
+{
+ struct nvme_tcp_ofld_ctrl *ctrl =
+ container_of(to_delayed_work(work),
+ struct nvme_tcp_ofld_ctrl,
+ connect_work);
+ struct nvme_ctrl *nctrl = &ctrl->nctrl;
+
+ ++nctrl->nr_reconnects;
+
+ if (nvme_tcp_ofld_setup_ctrl(nctrl, false))
+ goto requeue;
+
+ dev_info(nctrl->device, "Successfully reconnected (%d attempt)\n",
+ nctrl->nr_reconnects);
+
+ nctrl->nr_reconnects = 0;
+
+ return;
+
+requeue:
+ dev_info(nctrl->device, "Failed reconnect attempt %d\n",
+ nctrl->nr_reconnects);
+ nvme_tcp_ofld_reconnect_or_remove(nctrl);
+}
+
+static void nvme_tcp_ofld_error_recovery_work(struct work_struct *work)
+{
+ struct nvme_tcp_ofld_ctrl *ctrl =
+ container_of(work, struct nvme_tcp_ofld_ctrl, err_work);
+ struct nvme_ctrl *nctrl = &ctrl->nctrl;
+
+ nvme_stop_keep_alive(nctrl);
+ nvme_tcp_ofld_teardown_io_queues(nctrl, false);
+ /* unquiesce to fail fast pending requests */
+ nvme_start_queues(nctrl);
+ nvme_tcp_ofld_teardown_admin_queue(nctrl, false);
+ blk_mq_unquiesce_queue(nctrl->admin_q);
+
+ if (!nvme_change_ctrl_state(nctrl, NVME_CTRL_CONNECTING)) {
+ /* state change failure is ok if we started nctrl delete */
+ WARN_ON_ONCE(nctrl->state != NVME_CTRL_DELETING &&
+ nctrl->state != NVME_CTRL_DELETING_NOIO);
+
+ return;
+ }
+
+ nvme_tcp_ofld_reconnect_or_remove(nctrl);
+}
+
static void
nvme_tcp_ofld_teardown_ctrl(struct nvme_ctrl *nctrl, bool shutdown)
{
- /* Placeholder - err_work and connect_work */
+ struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+
+ cancel_work_sync(&ctrl->err_work);
+ cancel_delayed_work_sync(&ctrl->connect_work);
nvme_tcp_ofld_teardown_io_queues(nctrl, shutdown);
blk_mq_quiesce_queue(nctrl->admin_q);
if (shutdown)
@@ -428,6 +521,32 @@ static void nvme_tcp_ofld_delete_ctrl(struct nvme_ctrl *nctrl)
nvme_tcp_ofld_teardown_ctrl(nctrl, true);
}
+static void nvme_tcp_ofld_reset_ctrl_work(struct work_struct *work)
+{
+ struct nvme_ctrl *nctrl =
+ container_of(work, struct nvme_ctrl, reset_work);
+
+ nvme_stop_ctrl(nctrl);
+ nvme_tcp_ofld_teardown_ctrl(nctrl, false);
+
+ if (!nvme_change_ctrl_state(nctrl, NVME_CTRL_CONNECTING)) {
+ /* state change failure is ok if we started ctrl delete */
+ WARN_ON_ONCE(nctrl->state != NVME_CTRL_DELETING &&
+ nctrl->state != NVME_CTRL_DELETING_NOIO);
+
+ return;
+ }
+
+ if (nvme_tcp_ofld_setup_ctrl(nctrl, false))
+ goto out_fail;
+
+ return;
+
+out_fail:
+ ++nctrl->nr_reconnects;
+ nvme_tcp_ofld_reconnect_or_remove(nctrl);
+}
+
static int
nvme_tcp_ofld_init_request(struct blk_mq_tag_set *set,
struct request *rq,
@@ -521,6 +640,10 @@ nvme_tcp_ofld_create_ctrl(struct device *ndev, struct nvmf_ctrl_options *opts)
opts->nr_poll_queues + 1;
nctrl->sqsize = opts->queue_size - 1;
nctrl->kato = opts->kato;
+ INIT_DELAYED_WORK(&ctrl->connect_work,
+ nvme_tcp_ofld_reconnect_ctrl_work);
+ INIT_WORK(&ctrl->err_work, nvme_tcp_ofld_error_recovery_work);
+ INIT_WORK(&nctrl->reset_work, nvme_tcp_ofld_reset_ctrl_work);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
opts->trsvcid =
kstrdup(__stringify(NVME_TCP_DISC_PORT), GFP_KERNEL);
@@ -197,3 +197,4 @@ struct nvme_tcp_ofld_ops {
/* Exported functions for lower vendor specific offload drivers */
int nvme_tcp_ofld_register_dev(struct nvme_tcp_ofld_dev *dev);
void nvme_tcp_ofld_unregister_dev(struct nvme_tcp_ofld_dev *dev);
+void nvme_tcp_ofld_error_recovery(struct nvme_ctrl *nctrl);