[PATCH v6 10/18] nvme-tcp: Use CCR to recover controller that hits an error

[Mohamed Khalfella <mkhalfella@purestorage.com>]

An alive nvme controller that hits an error now will move to FENCING
state instead of RESETTING state. ctrl->fencing_work attempts CCR to
terminate inflight IOs. Regardless of the success or failure of CCR
operation the controller is transitioned to RESETTING state to continue
error recovery process.

Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
---
 drivers/nvme/host/tcp.c | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 921934028e0b..febbe8954473 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -167,6 +167,7 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
+	struct work_struct	fencing_work;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -616,6 +617,12 @@ static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue)
 
 static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 {
+	if (nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCING)) {
+		dev_warn(ctrl->device, "starting controller fencing\n");
+		queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->fencing_work);
+		return;
+	}
+
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
@@ -2558,6 +2565,22 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
 	nvme_tcp_reconnect_or_remove(ctrl, ret);
 }
 
+static void nvme_tcp_fencing_work(struct work_struct *work)
+{
+	struct nvme_tcp_ctrl *tcp_ctrl = container_of(work,
+			struct nvme_tcp_ctrl, fencing_work);
+	struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
+	unsigned long rem;
+
+	rem = nvme_fence_ctrl(ctrl);
+	if (rem)
+		dev_info(ctrl->device, "CCR failed, starting error recovery\n");
+
+	nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCED);
+	if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+		queue_work(nvme_reset_wq, &tcp_ctrl->err_work);
+}
+
 static void nvme_tcp_error_recovery_work(struct work_struct *work)
 {
 	struct nvme_tcp_ctrl *tcp_ctrl = container_of(work,
@@ -2633,6 +2656,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 
 static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
 {
+	flush_work(&to_tcp_ctrl(ctrl)->fencing_work);
 	flush_work(&to_tcp_ctrl(ctrl)->err_work);
 	cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
 }
@@ -2731,13 +2755,15 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
 	struct nvme_command *cmd = &pdu->cmd;
 	int qid = nvme_tcp_queue_id(req->queue);
+	enum nvme_ctrl_state state;
 
 	dev_warn(ctrl->device,
 		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
 		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
 		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
-	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
+	state = nvme_ctrl_state(ctrl);
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_FENCING) {
 		/*
 		 * If we are resetting, connecting or deleting we should
 		 * complete immediately because we may block controller
@@ -2996,6 +3022,7 @@ static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
 
 	INIT_DELAYED_WORK(&ctrl->connect_work,
 			nvme_tcp_reconnect_ctrl_work);
+	INIT_WORK(&ctrl->fencing_work, nvme_tcp_fencing_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
 
-- 
2.55.0