Re: [PATCH v4 05/10] lib/igt_drm_netlink: add get_error_threshold command support

["Purkait, Soham" <soham.purkait@intel.com>]

Hi Ravi,

On 03-09-2026 13:03, Ravi Kishore Koppuravuri wrote:
> Add support for GET_ERROR_THRESHOLD to fetch the current value of error
> threshold
>
> Cc: Purkait Soham <soham.purkait@intel.com>
> Cc: Riana Tauro <riana.tauro@intel.com>
> Cc: Gupta Anshuman <anshuman.gupta@intel.com>
> Cc: Jadav Raag <raag.jadav@intel.com>
> Cc: Nilawar Badal <badal.nilawar@intel.com>
> Cc: Koujalagi Mallesh <mallesh.koujalagi@intel.com>
> Cc: Harish Chegondi <harish.chegondi@intel.com>
> Signed-off-by: Ravi Kishore Koppuravuri <ravi.kishore.koppuravuri@intel.com>
> ---
> v2:Added a check whether error_threshold updated by valid callback or not
> v4:Renamed the library functions with prefix "igt_drm_netlink_*" (Nikula
>     Jani & Kamil)
> ---
>   lib/igt_drm_netlink.c | 58 ++++++++++++++++++++++++++++++++++++++++---
>   lib/igt_drm_netlink.h |  2 ++
>   2 files changed, 57 insertions(+), 3 deletions(-)
>
> diff --git a/lib/igt_drm_netlink.c b/lib/igt_drm_netlink.c
> index b18e3eeb6..1be7d4361 100644
> --- a/lib/igt_drm_netlink.c
> +++ b/lib/igt_drm_netlink.c
> @@ -40,6 +40,21 @@ static int ras_command_cb(struct nl_msg *msg, void *arg)
>   		ctx->error_value = nla_get_u32(attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE]);
>   		break;
>   	}
> +	case DRM_RAS_CMD_GET_ERROR_THRESHOLD: {
> + struct nlattr *attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX + 1];
Could this be moved at the start of the function ? e.g:
struct nlattr *attrs[(DRM_RAS_A_ERROR_EVENT_ATTRS_MAX >
                   DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX ?
                   DRM_RAS_A_ERROR_EVENT_ATTRS_MAX :
                   DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX) + 1];
> +
> +		ret = genlmsg_parse(nlh, 0, attrs,
> +				    DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX, NULL);
> +		if (ret < 0)
> +			return NL_SKIP;
> +
> +		if (!attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD])
> +			return NL_SKIP;
> +
> +		ctx->error_threshold =
> +			nla_get_u32(attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD]);
> +		break;
> +	}
>   	default:
>   		return NL_SKIP;
>   	}
> @@ -183,6 +198,7 @@ static int send_command(struct app_context *ctx, uint8_t cmd)
>   	}
>   
>   	switch (cmd) {
> +	case DRM_RAS_CMD_GET_ERROR_THRESHOLD:
>   	case DRM_RAS_CMD_GET_ERROR_COUNTER:
>   		ctx->response_required = true;
>   		ret = nla_put_u32(msg,
> @@ -233,6 +249,7 @@ static void reset_drm_ras_netlink_context(struct app_context *ctx)
>   	ctx->reply_received = false;
>   	ctx->ack_received = false;
>   	ctx->response_required = false;
> +	ctx->error_threshold = 0;
>   	ctx->family_id = -1;
>   }
>   
> @@ -283,10 +300,8 @@ int igt_drm_netlink_init(struct app_context *ctx)
>   	return 0;
>   }
>   
> -int igt_drm_netlink_get_error_counter(struct app_context *ctx)
> +static int validate_inputs(struct app_context *ctx, uint8_t cmd)
>   {
> -	int ret;
> -
>   	if (!ctx || !ctx->sock || ctx->family_id < 0)
>   		return -EINVAL;
>   
> @@ -299,6 +314,17 @@ int igt_drm_netlink_get_error_counter(struct app_context *ctx)
>   		return -EINVAL;
>   	}
>   
> +	return 0;
> +}
> +
> +int igt_drm_netlink_get_error_counter(struct app_context *ctx)
> +{
> +	int ret;
> +
> +	ret = validate_inputs(ctx, DRM_RAS_CMD_GET_ERROR_COUNTER);
> +	if (ret < 0)
> +		return ret;
> +
>   	ctx->error_value = UINT32_MAX;
>   
>   	ret = send_command(ctx, DRM_RAS_CMD_GET_ERROR_COUNTER);
> @@ -316,3 +342,29 @@ int igt_drm_netlink_get_error_counter(struct app_context *ctx)
>   
>   	return 0;
>   }
> +
> +int igt_drm_netlink_get_error_threshold(struct app_context *ctx)
> +{
> +	int ret;
> +
> +	ret = validate_inputs(ctx, DRM_RAS_CMD_GET_ERROR_THRESHOLD);
> +	if (ret < 0)
> +		return ret;
> +
> +	ctx->error_threshold = UINT32_MAX;

Could it be initialized with 0 ?

Thanks,
Soham
> +
> +	ret = send_command(ctx, DRM_RAS_CMD_GET_ERROR_THRESHOLD);
> +	if (ret < 0)
> +		return ret;
> +
> +	if (ctx->error_threshold == UINT32_MAX) {
> +		igt_warn("No valid error threshold reply: node_id=%u error_id=%u kernel_error=%d\n",
> +			 ctx->node_id, ctx->error_id, ctx->last_nl_error);
> +		return ctx->last_nl_error ? ctx->last_nl_error : -ENODATA;
> +	}
> +
> +	igt_debug("Retrieved error threshold: node_id=%u error_id=%u threshold=%u\n",
> +		  ctx->node_id, ctx->error_id, ctx->error_threshold);
> +
> +	return 0;
> +}
> diff --git a/lib/igt_drm_netlink.h b/lib/igt_drm_netlink.h
> index 5db7f4ab5..89ef58243 100644
> --- a/lib/igt_drm_netlink.h
> +++ b/lib/igt_drm_netlink.h
> @@ -18,12 +18,14 @@ struct app_context {
>   	bool reply_received;
>   	bool ack_received;
>   	bool response_required;
> +	uint32_t error_threshold;
>   	int family_id;
>   };
>   
>   void igt_drm_netlink_cleanup(struct app_context *ctx);
>   int igt_drm_netlink_init(struct app_context *ctx);
>   int igt_drm_netlink_get_error_counter(struct app_context *ctx);
> +int igt_drm_netlink_get_error_threshold(struct app_context *ctx);
>   
>   #endif /* IGT_DRM_NETLINK_H */
>