[PATCH] nvme/fc: Short-circuit reconnect retries

[Himanshu Madhani]

On 5/21/21 3:23 AM, Hannes Reinecke wrote:
> Returning an nvme status from nvme_fc_create_association() indicates
> that the association is established, and we should honour the DNR bit.
> If it's set a reconnect attempt will just return the same error, so
> we can short-circuit the reconnect attempts and fail the connection
> directly.
> 
> Signed-off-by: Hannes Reinecke <hare at suse.de>
> ---
>   drivers/nvme/host/fc.c | 25 +++++++++++++++++--------
>   1 file changed, 17 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
> index d9ab9e7871d0..b16acab5d8d8 100644
> --- a/drivers/nvme/host/fc.c
> +++ b/drivers/nvme/host/fc.c
> @@ -3095,6 +3095,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
>   	if (ctrl->ctrl.icdoff) {
>   		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
>   				ctrl->ctrl.icdoff);
> +		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
>   		goto out_disconnect_admin_queue;
>   	}
>   
> @@ -3102,6 +3103,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
>   	if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) {
>   		dev_err(ctrl->ctrl.device,
>   			"Mandatory sgls are not supported!\n");
> +		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
>   		goto out_disconnect_admin_queue;
>   	}
>   
> @@ -3268,11 +3270,13 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
>   	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
>   		return;
>   
> -	if (portptr->port_state == FC_OBJSTATE_ONLINE)
> +	if (portptr->port_state == FC_OBJSTATE_ONLINE) {
>   		dev_info(ctrl->ctrl.device,
>   			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
>   			ctrl->cnum, status);
> -	else if (time_after_eq(jiffies, rport->dev_loss_end))
> +		if (status > 0 && (status & NVME_SC_DNR))
> +			recon = false;
> +	} else if (time_after_eq(jiffies, rport->dev_loss_end))
>   		recon = false;
>   
>   	if (recon && nvmf_should_reconnect(&ctrl->ctrl)) {
> @@ -3286,12 +3290,17 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
>   
>   		queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay);
>   	} else {
> -		if (portptr->port_state == FC_OBJSTATE_ONLINE)
> -			dev_warn(ctrl->ctrl.device,
> -				"NVME-FC{%d}: Max reconnect attempts (%d) "
> -				"reached.\n",
> -				ctrl->cnum, ctrl->ctrl.nr_reconnects);
> -		else
> +		if (portptr->port_state == FC_OBJSTATE_ONLINE) {
> +			if (status > 0 && (status & NVME_SC_DNR))
> +				dev_warn(ctrl->ctrl.device,
> +					 "NVME-FC{%d}: reconnect failure\n",
> +					 ctrl->cnum);
> +			else
> +				dev_warn(ctrl->ctrl.device,
> +					 "NVME-FC{%d}: Max reconnect attempts "
> +					 "(%d) reached.\n",
> +					 ctrl->cnum, ctrl->ctrl.nr_reconnects);
> +		} else
>   			dev_warn(ctrl->ctrl.device,
>   				"NVME-FC{%d}: dev_loss_tmo (%d) expired "
>   				"while waiting for remoteport connectivity.\n",
> 

Looks Good to me.

Reviewed-by: Himanshu Madhani <himanshu.madhani at oracle.com>

-- 
Himanshu Madhani                                Oracle Linux Engineering