Re: [PATCH] drm/scheduler: Add drm_sched_job_cleanup

[Christian König <ckoenig.leichtzumerken@xxxxxxxxx>]

Am 26.10.18 um 13:06 schrieb Sharat Masetty:
> This patch adds a new API to clean up the scheduler job resources. This
> is primarliy needed in cases the job was created but was not queued to
> the scheduler queue. Additionally with this change, the layer which
> creates the scheduler job also gets to free up the job's resources and
> this entails moving the dma_fence_put(finished_fence) to the drivers
> ops free handler routines.
>
> Signed-off-by: Sharat Masetty <smasetty@xxxxxxxxxxxxxx>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c   |  3 +--
>   drivers/gpu/drm/amd/amdgpu/amdgpu_job.c  |  2 ++
>   drivers/gpu/drm/etnaviv/etnaviv_sched.c  |  3 +++
>   drivers/gpu/drm/scheduler/sched_entity.c |  1 -
>   drivers/gpu/drm/scheduler/sched_main.c   | 12 +++++++++++-
>   drivers/gpu/drm/v3d/v3d_sched.c          |  2 ++
>   include/drm/gpu_scheduler.h              |  1 +
>   7 files changed, 20 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index 663043c..5d768f9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -1260,8 +1260,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
>   	return 0;
>   
>   error_abort:
> -	dma_fence_put(&job->base.s_fence->finished);
> -	job->base.s_fence = NULL;
> +	drm_sched_job_cleanup(&job->base);
>   	amdgpu_mn_unlock(p->mn);
>   
>   error_unlock:
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 755f733..e0af44f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -112,6 +112,8 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
>   	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
>   	struct amdgpu_job *job = to_amdgpu_job(s_job);
>   
> +	drm_sched_job_cleanup(s_job);
> +
>   	amdgpu_ring_priority_put(ring, s_job->s_priority);
>   	dma_fence_put(job->fence);
>   	amdgpu_sync_free(&job->sync);
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index e7c3ed6..6f3c9bf 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -127,6 +127,8 @@ static void etnaviv_sched_free_job(struct drm_sched_job *sched_job)
>   {
>   	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
>   
> +	drm_sched_job_cleanup(sched_job);
> +
>   	etnaviv_submit_put(submit);
>   }
>   
> @@ -159,6 +161,7 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
>   						submit->out_fence, 0,
>   						INT_MAX, GFP_KERNEL);
>   	if (submit->out_fence_id < 0) {
> +		drm_sched_job_cleanup(&submit->sched_job);
>   		ret = -ENOMEM;
>   		goto out_unlock;
>   	}
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 3e22a54..8ff9d21f 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -204,7 +204,6 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
>   
>   	drm_sched_fence_finished(job->s_fence);
>   	WARN_ON(job->s_fence->parent);
> -	dma_fence_put(&job->s_fence->finished);
>   	job->sched->ops->free_job(job);
>   }
>   
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 44fe587..147af89 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -220,7 +220,6 @@ static void drm_sched_job_finish(struct work_struct *work)
>   	drm_sched_start_timeout(sched);
>   	spin_unlock(&sched->job_list_lock);
>   
> -	dma_fence_put(&s_job->s_fence->finished);
>   	sched->ops->free_job(s_job);
>   }
>   
> @@ -424,6 +423,17 @@ int drm_sched_job_init(struct drm_sched_job *job,
>   EXPORT_SYMBOL(drm_sched_job_init);
>   
>   /**
> + * drm_sched_job_cleanup - clean up scheduler job resources
> + *
> + * @job: scheduler job to clean up
> + */
> +void drm_sched_job_cleanup(struct drm_sched_job *job)
> +{
> +	dma_fence_put(&job->s_fence->finished);

Please set job->s_fence to NULL here or otherwise we could try to free 
it again in some code paths.

Apart from that looks good to me,
Christian.

> +}
> +EXPORT_SYMBOL(drm_sched_job_cleanup);
> +
> +/**
>    * drm_sched_ready - is the scheduler ready
>    *
>    * @sched: scheduler instance
> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
> index 9243dea..4ecd45e 100644
> --- a/drivers/gpu/drm/v3d/v3d_sched.c
> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
> @@ -35,6 +35,8 @@
>   {
>   	struct v3d_job *job = to_v3d_job(sched_job);
>   
> +	drm_sched_job_cleanup(sched_job);
> +
>   	v3d_exec_put(job->exec);
>   }
>   
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index d87b268..41136c4a 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -293,6 +293,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>   int drm_sched_job_init(struct drm_sched_job *job,
>   		       struct drm_sched_entity *entity,
>   		       void *owner);
> +void drm_sched_job_cleanup(struct drm_sched_job *job);
>   void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
>   void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
>   			    struct drm_sched_job *job);