[PATCH v9 03/11] drm/xe/devcoredump: Improve section headings and add tile info

[John Harrison]

On 12/12/2024 10:17, Souza, Jose wrote:
> On Wed, 2024-10-02 at 17:46 -0700, John.C.Harrison at Intel.com wrote:
>> From: John Harrison <John.C.Harrison at Intel.com>
>>
>> The xe_guc_exec_queue_snapshot is not really a GuC internal thing and
>> is definitely not a GuC CT thing. So give it its own section heading.
>> The snapshot itself is really a capture of the submission backend's
>> internal state. Although all it currently prints out is the submission
>> contexts. So label it as 'Contexts'. If more general state is added
>> later then it could be change to 'Submission backend' or some such.
>>
>> Further, everything from the GuC CT section onwards is GT specific but
>> there was no indication of which GT it was related to (and that is
>> impossible to work out from the other fields that are given). So add a
>> GT section heading. Also include the tile id of the GT, because again
>> significant information.
>>
>> Lastly, drop a couple of unnecessary line feeds within sections.
>>
>> v2: Add GT section heading, add tile id to device section.
>>
>> Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
>> Reviewed-by: Julia Filipchuk <julia.filipchuk at intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_devcoredump.c       | 5 +++++
>>   drivers/gpu/drm/xe/xe_devcoredump_types.h | 3 ++-
>>   drivers/gpu/drm/xe/xe_device.c            | 1 +
>>   drivers/gpu/drm/xe/xe_guc_submit.c        | 2 +-
>>   drivers/gpu/drm/xe/xe_hw_engine.c         | 1 -
>>   5 files changed, 9 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
>> index d23719d5c2a3..2690f1d1cde4 100644
>> --- a/drivers/gpu/drm/xe/xe_devcoredump.c
>> +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
>> @@ -96,8 +96,13 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count,
>>   	drm_printf(&p, "Process: %s\n", ss->process_name);
>>   	xe_device_snapshot_print(xe, &p);
>>   
>> +	drm_printf(&p, "\n**** GT #%d ****\n", ss->gt->info.id);
>> +	drm_printf(&p, "\tTile: %d\n", ss->gt->tile->id);
>> +
>>   	drm_puts(&p, "\n**** GuC CT ****\n");
>>   	xe_guc_ct_snapshot_print(ss->ct, &p);
>> +
>> +	drm_puts(&p, "\n**** Contexts ****\n");
>>   	xe_guc_exec_queue_snapshot_print(ss->ge, &p);
> This broke Mesa parser!
> It can't now parse the exec_queue context because it was expected to be on the '**** GuC CT ****' section.
Then the mesa parse needs to be updated. That was clearly a bug - exec 
queue contexts are absolutely not GuC CT data and should not be in the 
GuC CT section.

John.

>
>>   
>>   	drm_puts(&p, "\n**** Job ****\n");
>> diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
>> index 440d05d77a5a..3cc2f095fdfb 100644
>> --- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
>> +++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
>> @@ -37,7 +37,8 @@ struct xe_devcoredump_snapshot {
>>   	/* GuC snapshots */
>>   	/** @ct: GuC CT snapshot */
>>   	struct xe_guc_ct_snapshot *ct;
>> -	/** @ge: Guc Engine snapshot */
>> +
>> +	/** @ge: GuC Submission Engine snapshot */
>>   	struct xe_guc_submit_exec_queue_snapshot *ge;
>>   
>>   	/** @hwe: HW Engine snapshot array */
>> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
>> index 09a7ad830e69..030cf703e970 100644
>> --- a/drivers/gpu/drm/xe/xe_device.c
>> +++ b/drivers/gpu/drm/xe/xe_device.c
>> @@ -961,6 +961,7 @@ void xe_device_snapshot_print(struct xe_device *xe, struct drm_printer *p)
>>   
>>   	for_each_gt(gt, xe, id) {
>>   		drm_printf(p, "GT id: %u\n", id);
>> +		drm_printf(p, "\tTile: %u\n", gt->tile->id);
>>   		drm_printf(p, "\tType: %s\n",
>>   			   gt->info.type == XE_GT_TYPE_MAIN ? "main" : "media");
>>   		drm_printf(p, "\tIP ver: %u.%u.%u\n",
>> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
>> index 0ac4a19ec9cc..8690df699170 100644
>> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
>> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
>> @@ -2240,7 +2240,7 @@ xe_guc_exec_queue_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps
>>   	if (!snapshot)
>>   		return;
>>   
>> -	drm_printf(p, "\nGuC ID: %d\n", snapshot->guc.id);
>> +	drm_printf(p, "GuC ID: %d\n", snapshot->guc.id);
>>   	drm_printf(p, "\tName: %s\n", snapshot->name);
>>   	drm_printf(p, "\tClass: %d\n", snapshot->class);
>>   	drm_printf(p, "\tLogical mask: 0x%x\n", snapshot->logical_mask);
>> diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
>> index ea6d9ef7fab6..6c9c27304cdc 100644
>> --- a/drivers/gpu/drm/xe/xe_hw_engine.c
>> +++ b/drivers/gpu/drm/xe/xe_hw_engine.c
>> @@ -1084,7 +1084,6 @@ void xe_hw_engine_snapshot_print(struct xe_hw_engine_snapshot *snapshot,
>>   	if (snapshot->hwe->class == XE_ENGINE_CLASS_COMPUTE)
>>   		drm_printf(p, "\tRCU_MODE: 0x%08x\n",
>>   			   snapshot->reg.rcu_mode);
>> -	drm_puts(p, "\n");
>>   }
>>   
>>   /**