On Thu, Jun 24, 2021 at 1:45 PM Daniel Vetter <daniel.vetter@xxxxxxxx> wrote:
>
> This is a very confusingly named function, because not just does it
> init an object, it arms it and provides a point of no return for
> pushing a job into the scheduler. It would be nice if that's a bit
> clearer in the interface.
>
> But the real reason is that I want to push the dependency tracking
> helpers into the scheduler code, and that means drm_sched_job_init
> must be called a lot earlier, without arming the job.
>
> v2:
> - don't change .gitignore (Steven)
> - don't forget v3d (Emma)
>
> Acked-by: Steven Price <steven.price@xxxxxxx>
> Signed-off-by: Daniel Vetter <daniel.vetter@xxxxxxxxx>
> Cc: Lucas Stach <l.stach@xxxxxxxxxxxxxx>
> Cc: Russell King <linux+etnaviv@xxxxxxxxxxxxxxx>
> Cc: Christian Gmeiner <christian.gmeiner@xxxxxxxxx>
> Cc: Qiang Yu <yuq825@xxxxxxxxx>
> Cc: Rob Herring <robh@xxxxxxxxxx>
> Cc: Tomeu Vizoso <tomeu.vizoso@xxxxxxxxxxxxx>
> Cc: Steven Price <steven.price@xxxxxxx>
> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@xxxxxxxxxxxxx>
> Cc: David Airlie <airlied@xxxxxxxx>
> Cc: Daniel Vetter <daniel@xxxxxxxx>
> Cc: Sumit Semwal <sumit.semwal@xxxxxxxxxx>
> Cc: "Christian König" <christian.koenig@xxxxxxx>
> Cc: Masahiro Yamada <masahiroy@xxxxxxxxxx>
> Cc: Kees Cook <keescook@xxxxxxxxxxxx>
> Cc: Adam Borowski <kilobyte@xxxxxxxxxx>
> Cc: Nick Terrell <terrelln@xxxxxx>
> Cc: Mauro Carvalho Chehab <mchehab+huawei@xxxxxxxxxx>
> Cc: Paul Menzel <pmenzel@xxxxxxxxxxxxx>
> Cc: Sami Tolvanen <samitolvanen@xxxxxxxxxx>
> Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
> Cc: Alex Deucher <alexander.deucher@xxxxxxx>
> Cc: Dave Airlie <airlied@xxxxxxxxxx>
> Cc: Nirmoy Das <nirmoy.das@xxxxxxx>
> Cc: Deepak R Varma <mh12gx2825@xxxxxxxxx>
> Cc: Lee Jones <lee.jones@xxxxxxxxxx>
> Cc: Kevin Wang <kevin1.wang@xxxxxxx>
> Cc: Chen Li <chenli@xxxxxxxxxxxxx>
> Cc: Luben Tuikov <luben.tuikov@xxxxxxx>
> Cc: "Marek Olšák" <marek.olsak@xxxxxxx>
> Cc: Dennis Li <Dennis.Li@xxxxxxx>
> Cc: Maarten Lankhorst <maarten.lankhorst@xxxxxxxxxxxxxxx>
> Cc: Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx>
> Cc: Sonny Jiang <sonny.jiang@xxxxxxx>
> Cc: Boris Brezillon <boris.brezillon@xxxxxxxxxxxxx>
> Cc: Tian Tao <tiantao6@xxxxxxxxxxxxx>
> Cc: Jack Zhang <Jack.Zhang1@xxxxxxx>
> Cc: etnaviv@xxxxxxxxxxxxxxxxxxxxx
> Cc: lima@xxxxxxxxxxxxxxxxxxxxx
> Cc: linux-media@xxxxxxxxxxxxxxx
> Cc: linaro-mm-sig@xxxxxxxxxxxxxxxx
> Cc: Emma Anholt <emma@xxxxxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 ++
> drivers/gpu/drm/amd/amdgpu/amdgpu_job.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_entity.c | 6 +++---
> drivers/gpu/drm/scheduler/sched_fence.c | 15 ++++++++++-----
> drivers/gpu/drm/scheduler/sched_main.c | 23 ++++++++++++++++++++++-
> drivers/gpu/drm/v3d/v3d_gem.c | 2 ++
> include/drm/gpu_scheduler.h | 6 +++++-
> 10 files changed, 52 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index c5386d13eb4a..a4ec092af9a7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -1226,6 +1226,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
> if (r)
> goto error_unlock;
>
> + drm_sched_job_arm(&job->base);
> +
> /* No memory allocation is allowed while holding the notifier lock.
> * The lock is held until amdgpu_cs_submit is finished and fence is
> * added to BOs.
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index d33e6d97cc89..5ddb955d2315 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -170,6 +170,8 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
> if (r)
> return r;
>
> + drm_sched_job_arm(&job->base);
> +
> *f = dma_fence_get(&job->base.s_fence->finished);
> amdgpu_job_free_resources(job);
> drm_sched_entity_push_job(&job->base, entity);
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index 19826e504efc..af1671f01c7f 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -163,6 +163,8 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
> if (ret)
> goto out_unlock;
>
> + drm_sched_job_arm(&submit->sched_job);
> +
> submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished);
> submit->out_fence_id = idr_alloc_cyclic(&submit->gpu->fence_idr,
> submit->out_fence, 0,
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index ecf3267334ff..bd1af1fd8c0f 100644
> --- a/drivers/gpu/drm/lima/lima_sched.c
> +++ b/drivers/gpu/drm/lima/lima_sched.c
> @@ -129,6 +129,8 @@ int lima_sched_task_init(struct lima_sched_task *task,
> return err;
> }
>
> + drm_sched_job_arm(&task->base);
> +
> task->num_bos = num_bos;
> task->vm = lima_vm_get(vm);
>
> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> index beb62c8fc851..1e950534b9b0 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> @@ -244,6 +244,8 @@ int panfrost_job_push(struct panfrost_job *job)
> goto unlock;
> }
>
> + drm_sched_job_arm(&job->base);
> +
> job->render_done_fence = dma_fence_get(&job->base.s_fence->finished);
>
> ret = panfrost_acquire_object_fences(job->bos, job->bo_count,
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 79554aa4dbb1..f7347c284886 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -485,9 +485,9 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
> * @sched_job: job to submit
> * @entity: scheduler entity
> *
> - * Note: To guarantee that the order of insertion to queue matches
> - * the job's fence sequence number this function should be
> - * called with drm_sched_job_init under common lock.
> + * Note: To guarantee that the order of insertion to queue matches the job's
> + * fence sequence number this function should be called with drm_sched_job_arm()
> + * under common lock.
> *
> * Returns 0 for success, negative error code otherwise.
> */
> diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
> index 69de2c76731f..0ba810c198bd 100644
> --- a/drivers/gpu/drm/scheduler/sched_fence.c
> +++ b/drivers/gpu/drm/scheduler/sched_fence.c
> @@ -152,11 +152,10 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
> }
> EXPORT_SYMBOL(to_drm_sched_fence);
>
> -struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
> - void *owner)
> +struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
> + void *owner)
> {
> struct drm_sched_fence *fence = NULL;
> - unsigned seq;
>
> fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
> if (fence == NULL)
> @@ -166,13 +165,19 @@ struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
> fence->sched = entity->rq->sched;
> spin_lock_init(&fence->lock);
>
> + return fence;
> +}
If there's an error path between fence_alloc (job_init()) and
fence_create() (job_arm()) time, how does the s_fence get freed?
Before, I was committed to calling drm_sched_entity_push_job() which
lead to the job being processed and freed, but now I think we need
some other non-pushed-job free path.
> +EXPORT_SYMBOL(drm_sched_job_arm);
> +
> /**
> * drm_sched_job_cleanup - clean up scheduler job resources
> *
> diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
> index 4eb354226972..5c3a99027ecd 100644
> --- a/drivers/gpu/drm/v3d/v3d_gem.c
> +++ b/drivers/gpu/drm/v3d/v3d_gem.c
> @@ -475,6 +475,8 @@ v3d_push_job(struct v3d_file_priv *v3d_priv,
> if (ret)
> return ret;
>
> + drm_sched_job_arm(&job->base);
> +
> job->done_fence = dma_fence_get(&job->base.s_fence->finished);
>
> /* put by scheduler job completion */
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index d18af49fd009..80438d126c9d 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -313,6 +313,7 @@ void drm_sched_fini(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_arm(struct drm_sched_job *job);
> void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
> struct drm_gpu_scheduler **sched_list,
> unsigned int num_sched_list);
> @@ -352,8 +353,11 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
> enum drm_sched_priority priority);
> bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);
>
> -struct drm_sched_fence *drm_sched_fence_create(
> +struct drm_sched_fence *drm_sched_fence_alloc(
> struct drm_sched_entity *s_entity, void *owner);
> +void drm_sched_fence_init(struct drm_sched_fence *fence,
> + struct drm_sched_entity *entity);
> +
> void drm_sched_fence_scheduled(struct drm_sched_fence *fence);
> void drm_sched_fence_finished(struct drm_sched_fence *fence);
>
> --
> 2.32.0.rc2
>
