On 2023-02-18 16:15, Rob Clark wrote:
> As the finished fence is the one that is exposed to userspace, and
> therefore the one that other operations, like atomic update, would
> block on, we need to propagate the deadline from from the finished
> fence to the actual hw fence.
>
> v2: Split into drm_sched_fence_set_parent() (ckoenig)
> v3: Ensure a thread calling drm_sched_fence_set_deadline_finished() sees
> fence->parent set before drm_sched_fence_set_parent() does this
> test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT).
>
> Signed-off-by: Rob Clark <robdcl...@chromium.org>
Looks good.
This patch is Acked-by: Luben Tuikov <luben.tui...@amd.com>
--
Regards,
Luben
> ---
> drivers/gpu/drm/scheduler/sched_fence.c | 46 +++++++++++++++++++++++++
> drivers/gpu/drm/scheduler/sched_main.c | 2 +-
> include/drm/gpu_scheduler.h | 8 +++++
> 3 files changed, 55 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_fence.c
> b/drivers/gpu/drm/scheduler/sched_fence.c
> index 7fd869520ef2..43e2d4f5fe3b 100644
> --- a/drivers/gpu/drm/scheduler/sched_fence.c
> +++ b/drivers/gpu/drm/scheduler/sched_fence.c
> @@ -123,6 +123,37 @@ static void drm_sched_fence_release_finished(struct
> dma_fence *f)
> dma_fence_put(&fence->scheduled);
> }
>
> +static void drm_sched_fence_set_deadline_finished(struct dma_fence *f,
> + ktime_t deadline)
> +{
> + struct drm_sched_fence *fence = to_drm_sched_fence(f);
> + struct dma_fence *parent;
> + unsigned long flags;
> +
> + spin_lock_irqsave(&fence->lock, flags);
> +
> + /* If we already have an earlier deadline, keep it: */
> + if (test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags) &&
> + ktime_before(fence->deadline, deadline)) {
> + spin_unlock_irqrestore(&fence->lock, flags);
> + return;
> + }
> +
> + fence->deadline = deadline;
> + set_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags);
> +
> + spin_unlock_irqrestore(&fence->lock, flags);
> +
> + /*
> + * smp_load_aquire() to ensure that if we are racing another
> + * thread calling drm_sched_fence_set_parent(), that we see
> + * the parent set before it calls test_bit(HAS_DEADLINE_BIT)
> + */
> + parent = smp_load_acquire(&fence->parent);
> + if (parent)
> + dma_fence_set_deadline(parent, deadline);
> +}
> +
> static const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
> .get_driver_name = drm_sched_fence_get_driver_name,
> .get_timeline_name = drm_sched_fence_get_timeline_name,
> @@ -133,6 +164,7 @@ static const struct dma_fence_ops
> drm_sched_fence_ops_finished = {
> .get_driver_name = drm_sched_fence_get_driver_name,
> .get_timeline_name = drm_sched_fence_get_timeline_name,
> .release = drm_sched_fence_release_finished,
> + .set_deadline = drm_sched_fence_set_deadline_finished,
> };
>
> struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
> @@ -147,6 +179,20 @@ struct drm_sched_fence *to_drm_sched_fence(struct
> dma_fence *f)
> }
> EXPORT_SYMBOL(to_drm_sched_fence);
>
> +void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
> + struct dma_fence *fence)
> +{
> + /*
> + * smp_store_release() to ensure another thread racing us
> + * in drm_sched_fence_set_deadline_finished() sees the
> + * fence's parent set before test_bit()
> + */
> + smp_store_release(&s_fence->parent, dma_fence_get(fence));
> + if (test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT,
> + &s_fence->finished.flags))
> + dma_fence_set_deadline(fence, s_fence->deadline);
> +}
> +
> struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity
> *entity,
> void *owner)
> {
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c
> b/drivers/gpu/drm/scheduler/sched_main.c
> index 4e6ad6e122bc..007f98c48f8d 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -1019,7 +1019,7 @@ static int drm_sched_main(void *param)
> drm_sched_fence_scheduled(s_fence);
>
> if (!IS_ERR_OR_NULL(fence)) {
> - s_fence->parent = dma_fence_get(fence);
> + drm_sched_fence_set_parent(s_fence, fence);
> /* Drop for original kref_init of the fence */
> dma_fence_put(fence);
>
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index 9db9e5e504ee..8b31a954a44d 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -280,6 +280,12 @@ struct drm_sched_fence {
> */
> struct dma_fence finished;
>
> + /**
> + * @deadline: deadline set on &drm_sched_fence.finished which
> + * potentially needs to be propagated to &drm_sched_fence.parent
> + */
> + ktime_t deadline;
> +
> /**
> * @parent: the fence returned by &drm_sched_backend_ops.run_job
> * when scheduling the job on hardware. We signal the
> @@ -568,6 +574,8 @@ 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);
>
> +void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
> + struct dma_fence *fence);
> 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,
