Re: [PATCH] drm/sched: Add device pointer to drm_gpu_scheduler

["Christian König" <christian.koenig@amd.com>]

Am 21.02.22 um 10:57 schrieb Jiawei Gu:
> Add device pointer so scheduler's printing can use
> DRM_DEV_ERROR() instead, which makes life easier under multiple GPU
> scenario.
>
> v2: amend all calls of drm_sched_init()
> v3: fill dev pointer for all drm_sched_init() calls
>
> Signed-off-by: Jiawei Gu <Jiawei.Gu@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com>

When Andrey is fine with that as well I think the best approach is to 
push this upstream through drm-misc-next since it touches multiple drivers.

We can merge it into the DKMS branch as well if necessary.

Regards,
Christian

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c |  2 +-
>   drivers/gpu/drm/etnaviv/etnaviv_sched.c   |  2 +-
>   drivers/gpu/drm/lima/lima_sched.c         |  2 +-
>   drivers/gpu/drm/panfrost/panfrost_job.c   |  2 +-
>   drivers/gpu/drm/scheduler/sched_main.c    |  9 +++++----
>   drivers/gpu/drm/v3d/v3d_sched.c           | 10 +++++-----
>   include/drm/gpu_scheduler.h               |  3 ++-
>   7 files changed, 16 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 45977a72b5dd..cd2d594d4ffc 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -502,7 +502,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>   
>   	r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
>   			   num_hw_submission, amdgpu_job_hang_limit,
> -			   timeout, NULL, sched_score, ring->name);
> +			   timeout, NULL, sched_score, ring->name, adev->dev);
>   	if (r) {
>   		DRM_ERROR("Failed to create scheduler on ring %s.\n",
>   			  ring->name);
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index 58f593b278c1..35e5ef7dbdcc 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -195,7 +195,7 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
>   	ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops,
>   			     etnaviv_hw_jobs_limit, etnaviv_job_hang_limit,
>   			     msecs_to_jiffies(500), NULL, NULL,
> -			     dev_name(gpu->dev));
> +			     dev_name(gpu->dev), gpu->dev);
>   	if (ret)
>   		return ret;
>   
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index 5612d73f238f..8d517c8880e3 100644
> --- a/drivers/gpu/drm/lima/lima_sched.c
> +++ b/drivers/gpu/drm/lima/lima_sched.c
> @@ -490,7 +490,7 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
>   	return drm_sched_init(&pipe->base, &lima_sched_ops, 1,
>   			      lima_job_hang_limit,
>   			      msecs_to_jiffies(timeout), NULL,
> -			      NULL, name);
> +			      NULL, name, pipe->ldev->dev);
>   }
>   
>   void lima_sched_pipe_fini(struct lima_sched_pipe *pipe)
> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> index 908d79520853..a6925dbb6224 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> @@ -812,7 +812,7 @@ int panfrost_job_init(struct panfrost_device *pfdev)
>   				     nentries, 0,
>   				     msecs_to_jiffies(JOB_TIMEOUT_MS),
>   				     pfdev->reset.wq,
> -				     NULL, "pan_js");
> +				     NULL, "pan_js", pfdev->dev);
>   		if (ret) {
>   			dev_err(pfdev->dev, "Failed to create scheduler: %d.", ret);
>   			goto err_sched;
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index f91fb31ab7a7..b81fceb0b8a2 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -491,7 +491,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
>   			if (r == -ENOENT)
>   				drm_sched_job_done(s_job);
>   			else if (r)
> -				DRM_ERROR("fence add callback failed (%d)\n",
> +				DRM_DEV_ERROR(sched->dev, "fence add callback failed (%d)\n",
>   					  r);
>   		} else
>   			drm_sched_job_done(s_job);
> @@ -957,7 +957,7 @@ static int drm_sched_main(void *param)
>   			if (r == -ENOENT)
>   				drm_sched_job_done(sched_job);
>   			else if (r)
> -				DRM_ERROR("fence add callback failed (%d)\n",
> +				DRM_DEV_ERROR(sched->dev, "fence add callback failed (%d)\n",
>   					  r);
>   			dma_fence_put(fence);
>   		} else {
> @@ -991,7 +991,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>   		   const struct drm_sched_backend_ops *ops,
>   		   unsigned hw_submission, unsigned hang_limit,
>   		   long timeout, struct workqueue_struct *timeout_wq,
> -		   atomic_t *score, const char *name)
> +		   atomic_t *score, const char *name, struct device *dev)
>   {
>   	int i, ret;
>   	sched->ops = ops;
> @@ -1001,6 +1001,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>   	sched->timeout_wq = timeout_wq ? : system_wq;
>   	sched->hang_limit = hang_limit;
>   	sched->score = score ? score : &sched->_score;
> +	sched->dev = dev;
>   	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
>   		drm_sched_rq_init(sched, &sched->sched_rq[i]);
>   
> @@ -1018,7 +1019,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
>   	if (IS_ERR(sched->thread)) {
>   		ret = PTR_ERR(sched->thread);
>   		sched->thread = NULL;
> -		DRM_ERROR("Failed to create scheduler for %s.\n", name);
> +		DRM_DEV_ERROR(sched->dev, "Failed to create scheduler for %s.\n", name);
>   		return ret;
>   	}
>   
> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
> index e0cb7d0697a7..080710fd8eb7 100644
> --- a/drivers/gpu/drm/v3d/v3d_sched.c
> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
> @@ -391,7 +391,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>   			     &v3d_bin_sched_ops,
>   			     hw_jobs_limit, job_hang_limit,
>   			     msecs_to_jiffies(hang_limit_ms), NULL,
> -			     NULL, "v3d_bin");
> +			     NULL, "v3d_bin", &(v3d_to_pdev(v3d)->dev));
>   	if (ret) {
>   		dev_err(v3d->drm.dev, "Failed to create bin scheduler: %d.", ret);
>   		return ret;
> @@ -401,7 +401,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>   			     &v3d_render_sched_ops,
>   			     hw_jobs_limit, job_hang_limit,
>   			     msecs_to_jiffies(hang_limit_ms), NULL,
> -			     NULL, "v3d_render");
> +			     NULL, "v3d_render", &(v3d_to_pdev(v3d)->dev));
>   	if (ret) {
>   		dev_err(v3d->drm.dev, "Failed to create render scheduler: %d.",
>   			ret);
> @@ -413,7 +413,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>   			     &v3d_tfu_sched_ops,
>   			     hw_jobs_limit, job_hang_limit,
>   			     msecs_to_jiffies(hang_limit_ms), NULL,
> -			     NULL, "v3d_tfu");
> +			     NULL, "v3d_tfu", &(v3d_to_pdev(v3d)->dev));
>   	if (ret) {
>   		dev_err(v3d->drm.dev, "Failed to create TFU scheduler: %d.",
>   			ret);
> @@ -426,7 +426,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>   				     &v3d_csd_sched_ops,
>   				     hw_jobs_limit, job_hang_limit,
>   				     msecs_to_jiffies(hang_limit_ms), NULL,
> -				     NULL, "v3d_csd");
> +				     NULL, "v3d_csd", &(v3d_to_pdev(v3d)->dev));
>   		if (ret) {
>   			dev_err(v3d->drm.dev, "Failed to create CSD scheduler: %d.",
>   				ret);
> @@ -438,7 +438,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>   				     &v3d_cache_clean_sched_ops,
>   				     hw_jobs_limit, job_hang_limit,
>   				     msecs_to_jiffies(hang_limit_ms), NULL,
> -				     NULL, "v3d_cache_clean");
> +				     NULL, "v3d_cache_clean", &(v3d_to_pdev(v3d)->dev));
>   		if (ret) {
>   			dev_err(v3d->drm.dev, "Failed to create CACHE_CLEAN scheduler: %d.",
>   				ret);
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index bbc22fad8d80..944f83ef9f2e 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -457,13 +457,14 @@ struct drm_gpu_scheduler {
>   	atomic_t                        _score;
>   	bool				ready;
>   	bool				free_guilty;
> +	struct device			*dev;
>   };
>   
>   int drm_sched_init(struct drm_gpu_scheduler *sched,
>   		   const struct drm_sched_backend_ops *ops,
>   		   uint32_t hw_submission, unsigned hang_limit,
>   		   long timeout, struct workqueue_struct *timeout_wq,
> -		   atomic_t *score, const char *name);
> +		   atomic_t *score, const char *name, struct device *dev);
>   
>   void drm_sched_fini(struct drm_gpu_scheduler *sched);
>   int drm_sched_job_init(struct drm_sched_job *job,