[PATCH v4 10/15] nvme-tcp: Use CCR to recover controller that hits an error

Mohamed Khalfella posted 15 patches 5 days, 13 hours ago
[PATCH v4 10/15] nvme-tcp: Use CCR to recover controller that hits an error
Posted by Mohamed Khalfella 5 days, 13 hours ago
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 | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 243dab830dc8..6393ec2b3b55 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -194,6 +194,7 @@ 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;
@@ -612,6 +613,12 @@ 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;
 
@@ -2471,12 +2478,29 @@ 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;
+	int ret;
+
+	ret = nvme_fence_ctrl(ctrl);
+	if (ret)
+		dev_info(ctrl->device, "CCR failed with error %d\n", ret);
+
+	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,
 				struct nvme_tcp_ctrl, err_work);
 	struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
 
+	flush_work(&to_tcp_ctrl(ctrl)->fencing_work);
 	if (nvme_tcp_key_revoke_needed(ctrl))
 		nvme_auth_revoke_tls_key(ctrl);
 	nvme_stop_keep_alive(ctrl);
@@ -2519,6 +2543,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 		container_of(work, struct nvme_ctrl, reset_work);
 	int ret;
 
+	flush_work(&to_tcp_ctrl(ctrl)->fencing_work);
 	if (nvme_tcp_key_revoke_needed(ctrl))
 		nvme_auth_revoke_tls_key(ctrl);
 	nvme_stop_ctrl(ctrl);
@@ -2644,13 +2669,15 @@ 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
@@ -2905,6 +2932,7 @@ 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);
 
-- 
2.52.0
Re: [PATCH v4 10/15] nvme-tcp: Use CCR to recover controller that hits an error
Posted by Hannes Reinecke 3 days, 3 hours ago
On 3/28/26 01:43, Mohamed Khalfella wrote:
> 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 | 30 +++++++++++++++++++++++++++++-
>   1 file changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index 243dab830dc8..6393ec2b3b55 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -194,6 +194,7 @@ 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;
> @@ -612,6 +613,12 @@ 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;
>   
> @@ -2471,12 +2478,29 @@ 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;
> +	int ret;
> +
> +	ret = nvme_fence_ctrl(ctrl);
> +	if (ret)
> +		dev_info(ctrl->device, "CCR failed with error %d\n", ret);
> +
> +	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);
> +}
> +

To follow up to my comments on the previous patches:
As we're already using a work queue, wouldn't it be better / easier
to make 'nvme_fence_ctrl()' asynchronous and explicitely call 
'nvme_fence_wait()' or something here?

>   static void nvme_tcp_error_recovery_work(struct work_struct *work)
>   {
>   	struct nvme_tcp_ctrl *tcp_ctrl = container_of(work,
>   				struct nvme_tcp_ctrl, err_work);
>   	struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
>   
> +	flush_work(&to_tcp_ctrl(ctrl)->fencing_work);
>   	if (nvme_tcp_key_revoke_needed(ctrl))
>   		nvme_auth_revoke_tls_key(ctrl);
>   	nvme_stop_keep_alive(ctrl);
> @@ -2519,6 +2543,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
>   		container_of(work, struct nvme_ctrl, reset_work);
>   	int ret;
>   
> +	flush_work(&to_tcp_ctrl(ctrl)->fencing_work);
>   	if (nvme_tcp_key_revoke_needed(ctrl))
>   		nvme_auth_revoke_tls_key(ctrl);
>   	nvme_stop_ctrl(ctrl);
> @@ -2644,13 +2669,15 @@ 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

Do we need to call nvme_tcp_error_recovery() even if the controller is
in 'FENCING'?
Don't we just need to return BLK_EH_RESET_TIMER when in 'FENCING' ?

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare@suse.de                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich