[PATCH 1/4] drm/amdgpu: add sched sync for amdgpu job

[Christian König]

Am 10.05.2017 um 09:31 schrieb Chunming Zhou:
> this is an improvement for previous patch, the sched_sync is to store fence
> that could be skipped as scheduled, when job is executed, we didn't need
> pipeline_sync if all fences in sched_sync are signalled, otherwise insert
> pipeline_sync still.
>
> Change-Id: I26d3a2794272ba94b25753d4bf367326d12f6939
> Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c  | 7 ++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 ++++-
>   3 files changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 787acd7..ef018bf 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1162,6 +1162,7 @@ struct amdgpu_job {
>   	struct amdgpu_vm	*vm;
>   	struct amdgpu_ring	*ring;
>   	struct amdgpu_sync	sync;
> +	struct amdgpu_sync	sched_sync;
>   	struct amdgpu_ib	*ibs;
>   	struct fence		*fence; /* the hw fence */
>   	uint32_t		preamble_status;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> index 2c6624d..86ad507 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
> @@ -121,6 +121,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
>   {
>   	struct amdgpu_device *adev = ring->adev;
>   	struct amdgpu_ib *ib = &ibs[0];
> +	struct fence *tmp;
>   	bool skip_preamble, need_ctx_switch;
>   	unsigned patch_offset = ~0;
>   	struct amdgpu_vm *vm;
> @@ -167,8 +168,12 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
>   		return r;
>   	}
>   
> -	if (ring->funcs->emit_pipeline_sync && job && job->need_pipeline_sync)
> +	if (ring->funcs->emit_pipeline_sync && job &&
> +	    (tmp = amdgpu_sync_get_fence(&job->sched_sync))) {
> +		job->need_pipeline_sync = true;
>   		amdgpu_ring_emit_pipeline_sync(ring);
> +		fence_put(tmp);
> +	}
>   	if (vm) {
>   		amdgpu_ring_insert_nop(ring, extra_nop); /* prevent CE go too fast than DE */
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index cfa97ab..fa0c8b1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -60,6 +60,7 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
>   	(*job)->need_pipeline_sync = false;
>   
>   	amdgpu_sync_create(&(*job)->sync);
> +	amdgpu_sync_create(&(*job)->sched_sync);
>   
>   	return 0;
>   }
> @@ -98,6 +99,7 @@ static void amdgpu_job_free_cb(struct amd_sched_job *s_job)
>   
>   	fence_put(job->fence);
>   	amdgpu_sync_free(&job->sync);
> +	amdgpu_sync_free(&job->sched_sync);
>   	kfree(job);
>   }
>   
> @@ -107,6 +109,7 @@ void amdgpu_job_free(struct amdgpu_job *job)
>   
>   	fence_put(job->fence);
>   	amdgpu_sync_free(&job->sync);
> +	amdgpu_sync_free(&job->sched_sync);
>   	kfree(job);
>   }
>   
> @@ -154,7 +157,7 @@ static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
>   	}
>   
>   	if (amd_sched_dependency_optimized(fence, sched_job->s_entity))
> -		job->need_pipeline_sync = true;
> +		amdgpu_sync_fence(job->adev, &job->sched_sync, fence);

This can result in an -ENOMEM and additional to that we only need to 
remember the last fence optimized like this, not all of them.

So just keep the last one found here in job->sched_fence instead.

Regards,
Christian.

>   
>   	return fence;
>   }