[PATCH 3/5] drm/sched: stop passing non struct drm_device to drm_err() and friends

[Jani Nikula]

On Thu, 23 Jan 2025, Simona Vetter <simona.vetter at ffwll.ch> wrote:
> On Thu, Jan 23, 2025 at 05:09:10PM +0200, Jani Nikula wrote:
>> The expectation is that the struct drm_device based logging helpers get
>> passed an actual struct drm_device pointer rather than some random
>> struct pointer where you can dereference the ->dev member.
>> 
>> Convert drm_err(sched, ...) to dev_err(sched->dev, ...) and
>> similar. This matches current usage, as struct drm_device is not
>> available, but drops "[drm]" or "[drm] *ERROR*" prefix from logging.
>> 
>> Unfortunately, there's no dev_WARN_ON(), so the conversion is not
>> exactly the same.
>> 
>> Signed-off-by: Jani Nikula <jani.nikula at intel.com>
>
> For the two previous patches just dev_ makes sense since they're just
> platform drivers, but for drm/sched I wonder whether it wouldn't be better
> to switch from struct device * to struct drm_device * instead. I guess
> might be best to leave that decision to scheduler folks.

I had a very brief look, and it seemed like struct drm_device isn't
passed around in sched. If use of struct drm_device is preferred, I'm
not the best person to figure out how to do that. But the abuse of the
drm_err() and friends macros needs to stop.

> Anyway on the series and with that caveat:
>
> Reviewed-by: Simona Vetter <simona.vetter at ffwll.ch>

Thanks,
Jani.

>
>
>> 
>> ---
>> 
>> Cc: Matthew Brost <matthew.brost at intel.com>
>> Cc: Danilo Krummrich <dakr at kernel.org>
>> Cc: Philipp Stanner <phasta at kernel.org>
>> Cc: "Christian König" <ckoenig.leichtzumerken at gmail.com>
>> Cc: dri-devel at lists.freedesktop.org
>> ---
>>  drivers/gpu/drm/scheduler/sched_entity.c |  2 +-
>>  drivers/gpu/drm/scheduler/sched_main.c   | 20 +++++++++++---------
>>  2 files changed, 12 insertions(+), 10 deletions(-)
>> 
>> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
>> index 69bcf0e99d57..e29af71d4b5c 100644
>> --- a/drivers/gpu/drm/scheduler/sched_entity.c
>> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
>> @@ -92,7 +92,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
>>  		 * the lowest priority available.
>>  		 */
>>  		if (entity->priority >= sched_list[0]->num_rqs) {
>> -			drm_err(sched_list[0], "entity with out-of-bounds priority:%u num_rqs:%u\n",
>> +			dev_err(sched_list[0]->dev, "entity with out-of-bounds priority:%u num_rqs:%u\n",
>>  				entity->priority, sched_list[0]->num_rqs);
>>  			entity->priority = max_t(s32, (s32) sched_list[0]->num_rqs - 1,
>>  						 (s32) DRM_SCHED_PRIORITY_KERNEL);
>> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
>> index a48be16ab84f..d1c1f22fd1db 100644
>> --- a/drivers/gpu/drm/scheduler/sched_main.c
>> +++ b/drivers/gpu/drm/scheduler/sched_main.c
>> @@ -103,9 +103,9 @@ static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched)
>>  {
>>  	u32 credits;
>>  
>> -	drm_WARN_ON(sched, check_sub_overflow(sched->credit_limit,
>> -					      atomic_read(&sched->credit_count),
>> -					      &credits));
>> +	WARN_ON(check_sub_overflow(sched->credit_limit,
>> +				   atomic_read(&sched->credit_count),
>> +				   &credits));
>>  
>>  	return credits;
>>  }
>> @@ -130,9 +130,11 @@ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched,
>>  	/* If a job exceeds the credit limit, truncate it to the credit limit
>>  	 * itself to guarantee forward progress.
>>  	 */
>> -	if (drm_WARN(sched, s_job->credits > sched->credit_limit,
>> -		     "Jobs may not exceed the credit limit, truncate.\n"))
>> +	if (s_job->credits > sched->credit_limit) {
>> +		dev_WARN(sched->dev,
>> +			 "Jobs may not exceed the credit limit, truncate.\n");
>>  		s_job->credits = sched->credit_limit;
>> +	}
>>  
>>  	return drm_sched_available_credits(sched) >= s_job->credits;
>>  }
>> @@ -790,7 +792,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
>>  		 * or worse--a blank screen--leave a trail in the
>>  		 * logs, so this can be debugged easier.
>>  		 */
>> -		drm_err(job->sched, "%s: entity has no rq!\n", __func__);
>> +		dev_err(job->sched->dev, "%s: entity has no rq!\n", __func__);
>>  		return -ENOENT;
>>  	}
>>  
>> @@ -1280,7 +1282,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>>  	if (num_rqs > DRM_SCHED_PRIORITY_COUNT) {
>>  		/* This is a gross violation--tell drivers what the  problem is.
>>  		 */
>> -		drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
>> +		dev_err(sched->dev, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
>>  			__func__);
>>  		return -EINVAL;
>>  	} else if (sched->sched_rq) {
>> @@ -1288,7 +1290,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>>  		 * fine-tune their DRM calling order, and return all
>>  		 * is good.
>>  		 */
>> -		drm_warn(sched, "%s: scheduler already initialized!\n", __func__);
>> +		dev_warn(sched->dev, "%s: scheduler already initialized!\n", __func__);
>>  		return 0;
>>  	}
>>  
>> @@ -1343,7 +1345,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>>  Out_check_own:
>>  	if (sched->own_submit_wq)
>>  		destroy_workqueue(sched->submit_wq);
>> -	drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
>> +	dev_err(sched->dev, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
>>  	return -ENOMEM;
>>  }
>>  EXPORT_SYMBOL(drm_sched_init);
>> -- 
>> 2.39.5
>> 

-- 
Jani Nikula, Intel