[PATCH v3 10/21] nvme-tcp: Use CCR to recover controller that hits an error

[Hannes Reinecke]

On 2/14/26 05:25, 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 at purestorage.com>
> ---
>   drivers/nvme/host/tcp.c | 32 +++++++++++++++++++++++++++++++-
>   1 file changed, 31 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index 69cb04406b47..229cfdffd848 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -193,6 +193,7 @@ 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;
> @@ -611,6 +612,12 @@ 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;
>   
> @@ -2470,12 +2477,31 @@ 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, 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, &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);
> @@ -2518,6 +2544,7 @@ 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);
> @@ -2643,13 +2670,15 @@ 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
> @@ -2904,6 +2933,7 @@ 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);
>   

I still would love to have the 'FENCING/FENCED' state handled in the
generic code, but that would require quite some twiddling with the
transport-specific error handlings. So probably not for this round.

Other than that:

Reviewed-by: Hannes Reinecke <hare at suse.de>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare at 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