[PATCH v2 2/2] drm/xe/guc: Only add GuC crash dump if available

[John Harrison]

On 3/27/2025 4:40 PM, Zhanjun Dong wrote:
> Add flag of GuC crash dump received. LFD only include crash dump
> section when crash dump is available.
>
> Signed-off-by: Zhanjun Dong <zhanjun.dong at intel.com>
> ---
>   drivers/gpu/drm/xe/xe_guc_ct.c        | 13 +++++++-----
>   drivers/gpu/drm/xe/xe_guc_log.c       | 30 +++++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_guc_log_types.h |  2 ++
>   3 files changed, 40 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index 72ad576fc18e..44c11ec662e5 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -1127,12 +1127,15 @@ static int guc_crash_process_msg(struct xe_guc_ct *ct, u32 action)
>   {
>   	struct xe_gt *gt = ct_to_gt(ct);
>   
> -	if (action == XE_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED)
> +	if (action == XE_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED) {
>   		xe_gt_err(gt, "GuC Crash dump notification\n");
> -	else if (action == XE_GUC_ACTION_NOTIFY_EXCEPTION)
> -		xe_gt_err(gt, "GuC Exception notification\n");
> -	else
> -		xe_gt_err(gt, "Unknown GuC crash notification: 0x%04X\n", action);
> +		ct_to_guc(ct)->log.crash_dumped = true;
This will also need to be cleared in the GuC reset path. There is no 
guarantee that the log will be saved via the LFD system before a reset 
wipes it out. And then a subsequent save will see a stale crash dump.

> +	} else {
> +		if (action == XE_GUC_ACTION_NOTIFY_EXCEPTION)
You can use "} else if( ..." to avoid the unnecessary extra level of 
indentation.

> +			xe_gt_err(gt, "GuC Exception notification\n");
> +		else
> +			xe_gt_err(gt, "Unknown GuC crash notification: 0x%04X\n", action);
> +	}
>   
>   	CT_DEAD(ct, NULL, CRASH);
>   
> diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
> index 5659d60e41ab..29684393a62d 100644
> --- a/drivers/gpu/drm/xe/xe_guc_log.c
> +++ b/drivers/gpu/drm/xe/xe_guc_log.c
> @@ -536,6 +536,36 @@ static uint xe_guc_log_save_to_lfd_buf(char *buf, int size, u32 *guc_log_bin,
>   		return len;
>   	index += len;
>   
> +	/* For Crash dump, rd/wr ptr has no effect, only add if crash_dumped is true */
> +	if (log->crash_dumped) {
> +		struct guc_log_buffer_entry_list *entry;
> +
> +		entry = &entry_list[GUC_LOG_BUFFER_STATE_HEADER_ENTRY_CRASH];
> +		if (entry->buf_size) {
> +			int i;
> +			u32 *buf32 = (u32 *)&bin[entry->offset];
> +
> +			/* Check if crash dump section are all zero */
> +			for (i = 0; i < entry->buf_size / 4; i++)
> +				if (buf32[i])
> +					break;
> +
> +			/* Buffer has non-zero data */
> +			if (i < entry->buf_size / 4) {
> +				len = xe_guc_log_add_typed_payload(&buf[index], size - index,
> +								   GUC_LFD_TYPE_FW_CRASH_DUMP,
> +								   entry->buf_size,
> +								   &bin[entry->offset]);
> +				if (len < 0)
> +					return len;
> +				index += len;
> +
> +				/* Clear flag */
> +				log->crash_dumped = false;
> +			}
> +		}
> +	}
> +
>   	return index;
>   }
>   
> diff --git a/drivers/gpu/drm/xe/xe_guc_log_types.h b/drivers/gpu/drm/xe/xe_guc_log_types.h
> index b3d5c72ac752..d351f639727b 100644
> --- a/drivers/gpu/drm/xe/xe_guc_log_types.h
> +++ b/drivers/gpu/drm/xe/xe_guc_log_types.h
> @@ -46,6 +46,8 @@ struct xe_guc_log {
>   	u32 level;
>   	/** @bo: XE BO for GuC log */
>   	struct xe_bo *bo;
> +	/** @crash_dumped: Indicate if crash dumped */
> +	bool crash_dumped;
>   	/** @stats: logging related stats */
>   	struct {
>   		u32 sampled_overflow;