[PATCH v3 11/21] nvme-rdma: Use CCR to recover controller that hits an error

[Mohamed Khalfella]

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 at purestorage.com>
---
 drivers/nvme/host/rdma.c | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 35c0822edb2d..2fb47f41215f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -106,6 +106,7 @@ struct nvme_rdma_ctrl {
 
 	/* other member variables */
 	struct blk_mq_tag_set	tag_set;
+	struct work_struct	fencing_work;
 	struct work_struct	err_work;
 
 	struct nvme_rdma_qe	async_event_sqe;
@@ -1120,11 +1121,30 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	nvme_rdma_reconnect_or_remove(ctrl, ret);
 }
 
+static void nvme_rdma_fencing_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *rdma_ctrl = container_of(work,
+			struct nvme_rdma_ctrl, fencing_work);
+	struct nvme_ctrl *ctrl = &rdma_ctrl->ctrl;
+	unsigned long rem;
+
+	rem = nvme_fence_ctrl(ctrl);
+	if (rem) {
+		dev_info(ctrl->device,
+			 "CCR failed, skipping time-based recovery\n");
+	}
+
+	nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCED);
+	if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+		queue_work(nvme_reset_wq, &rdma_ctrl->err_work);
+}
+
 static void nvme_rdma_error_recovery_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl = container_of(work,
 			struct nvme_rdma_ctrl, err_work);
 
+	flush_work(&ctrl->fencing_work);
 	nvme_stop_keep_alive(&ctrl->ctrl);
 	flush_work(&ctrl->ctrl.async_event_work);
 	nvme_rdma_teardown_io_queues(ctrl, false);
@@ -1147,6 +1167,12 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 
 static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 {
+	if (nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_FENCING)) {
+		dev_warn(ctrl->ctrl.device, "starting controller fencing\n");
+		queue_work(nvme_wq, &ctrl->fencing_work);
+		return;
+	}
+
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
@@ -1957,13 +1983,15 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 	struct nvme_command *cmd = req->req.cmd;
 	int qid = nvme_rdma_queue_idx(queue);
+	enum nvme_ctrl_state state;
 
 	dev_warn(ctrl->ctrl.device,
 		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
 		 rq->tag, nvme_cid(rq), cmd->common.opcode,
 		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
-	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
+	state = nvme_ctrl_state(&ctrl->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
@@ -2169,6 +2197,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
 	int ret;
 
+	flush_work(&ctrl->fencing_work);
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
 
@@ -2281,6 +2310,7 @@ static struct nvme_rdma_ctrl *nvme_rdma_alloc_ctrl(struct device *dev,
 
 	INIT_DELAYED_WORK(&ctrl->reconnect_work,
 			nvme_rdma_reconnect_ctrl_work);
+	INIT_WORK(&ctrl->fencing_work, nvme_rdma_fencing_work);
 	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work);
 
-- 
2.52.0