On Thu, Sep 14, 2023 at 12:23:35AM -0400, Luben Tuikov wrote:
> On 2023-09-14 00:18, Luben Tuikov wrote:
> > On 2023-09-11 22:16, Matthew Brost wrote:
> >> Rather than a global modparam for scheduling policy, move the scheduling
> >> policy to scheduler / entity so user can control each scheduler / entity
> >> policy.
> >>
> >> v2:
> >> - s/DRM_SCHED_POLICY_MAX/DRM_SCHED_POLICY_COUNT (Luben)
> >> - Only include policy in scheduler (Luben)
> >>
> >> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> >> ---
> >> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
> >> drivers/gpu/drm/etnaviv/etnaviv_sched.c | 3 ++-
> >> drivers/gpu/drm/lima/lima_sched.c | 3 ++-
> >> drivers/gpu/drm/msm/msm_ringbuffer.c | 3 ++-
> >> drivers/gpu/drm/nouveau/nouveau_sched.c | 3 ++-
> >> drivers/gpu/drm/panfrost/panfrost_job.c | 3 ++-
> >> drivers/gpu/drm/scheduler/sched_entity.c | 24 ++++++++++++++++++----
> >> drivers/gpu/drm/scheduler/sched_main.c | 23 +++++++++++++++------
> >> drivers/gpu/drm/v3d/v3d_sched.c | 15 +++++++++-----
> >> include/drm/gpu_scheduler.h | 20 ++++++++++++------
> >> 10 files changed, 72 insertions(+), 26 deletions(-)
> >>
> >> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> >> index c83a76bccc1d..ecb00991dd51 100644
> >> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> >> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> >> @@ -2309,6 +2309,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
> >> ring->num_hw_submission, 0,
> >> timeout, adev->reset_domain->wq,
> >> ring->sched_score, ring->name,
> >> + DRM_SCHED_POLICY_DEFAULT,
> >> adev->dev);
> >> if (r) {
> >> DRM_ERROR("Failed to create scheduler on ring %s.\n",
> >> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> >> index 618a804ddc34..3646f995ca94 100644
> >> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> >> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> >> @@ -137,7 +137,8 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
> >> ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, NULL,
> >> etnaviv_hw_jobs_limit, etnaviv_job_hang_limit,
> >> msecs_to_jiffies(500), NULL, NULL,
> >> - dev_name(gpu->dev), gpu->dev);
> >> + dev_name(gpu->dev), DRM_SCHED_POLICY_DEFAULT,
> >> + 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 8d858aed0e56..465d4bf3882b 100644
> >> --- a/drivers/gpu/drm/lima/lima_sched.c
> >> +++ b/drivers/gpu/drm/lima/lima_sched.c
> >> @@ -491,7 +491,8 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
> >> return drm_sched_init(&pipe->base, &lima_sched_ops, NULL, 1,
> >> lima_job_hang_limit,
> >> msecs_to_jiffies(timeout), NULL,
> >> - NULL, name, pipe->ldev->dev);
> >> + NULL, name, DRM_SCHED_POLICY_DEFAULT,
> >> + pipe->ldev->dev);
> >> }
> >>
> >> void lima_sched_pipe_fini(struct lima_sched_pipe *pipe)
> >> diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
> >> index b8865e61b40f..f45e674a0aaf 100644
> >> --- a/drivers/gpu/drm/msm/msm_ringbuffer.c
> >> +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
> >> @@ -96,7 +96,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
> >>
> >> ret = drm_sched_init(&ring->sched, &msm_sched_ops, NULL,
> >> num_hw_submissions, 0, sched_timeout,
> >> - NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);
> >> + NULL, NULL, to_msm_bo(ring->bo)->name,
> >> + DRM_SCHED_POLICY_DEFAULT, gpu->dev->dev);
> >> if (ret) {
> >> goto fail;
> >> }
> >> diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
> >> index d458c2227d4f..70e497e40c70 100644
> >> --- a/drivers/gpu/drm/nouveau/nouveau_sched.c
> >> +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
> >> @@ -431,7 +431,8 @@ int nouveau_sched_init(struct nouveau_drm *drm)
> >>
> >> return drm_sched_init(sched, &nouveau_sched_ops, NULL,
> >> NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit,
> >> - NULL, NULL, "nouveau_sched", drm->dev->dev);
> >> + NULL, NULL, "nouveau_sched",
> >> + DRM_SCHED_POLICY_DEFAULT, drm->dev->dev);
> >> }
> >>
> >> void nouveau_sched_fini(struct nouveau_drm *drm)
> >> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> >> index 326ca1ddf1d7..ad36bf3a4699 100644
> >> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> >> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> >> @@ -835,7 +835,8 @@ int panfrost_job_init(struct panfrost_device *pfdev)
> >> nentries, 0,
> >> msecs_to_jiffies(JOB_TIMEOUT_MS),
> >> pfdev->reset.wq,
> >> - NULL, "pan_js", pfdev->dev);
> >> + NULL, "pan_js", DRM_SCHED_POLICY_DEFAULT,
> >> + 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_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> >> index a42763e1429d..65a972b52eda 100644
> >> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> >> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> >> @@ -33,6 +33,20 @@
> >> #define to_drm_sched_job(sched_job) \
> >> container_of((sched_job), struct drm_sched_job, queue_node)
> >>
> >> +static bool bad_policies(struct drm_gpu_scheduler **sched_list,
> >> + unsigned int num_sched_list)
> >
> > Rename the function to the status quo,
> > drm_sched_policy_mismatch(...
> >
Will do.
> >> +{
> >> + enum drm_sched_policy sched_policy = sched_list[0]->sched_policy;
> >> + unsigned int i;
> >> +
> >> + /* All schedule policies must match */
> >> + for (i = 1; i < num_sched_list; ++i)
> >> + if (sched_policy != sched_list[i]->sched_policy)
> >> + return true;
> >> +
> >> + return false;
> >> +}
> >> +
> >> /**
> >> * drm_sched_entity_init - Init a context entity used by scheduler when
> >> * submit to HW ring.
> >> @@ -62,7 +76,8 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
> >> unsigned int num_sched_list,
> >> atomic_t *guilty)
> >> {
> >> - if (!(entity && sched_list && (num_sched_list == 0 || sched_list[0])))
> >> + if (!(entity && sched_list && (num_sched_list == 0 || sched_list[0])) ||
> >> + bad_policies(sched_list, num_sched_list))
> >> return -EINVAL;
> >>
> >> memset(entity, 0, sizeof(struct drm_sched_entity));
> >> @@ -486,7 +501,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
> >> * Update the entity's location in the min heap according to
> >> * the timestamp of the next job, if any.
> >> */
> >> - if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) {
> >> + if (entity->rq->sched->sched_policy == DRM_SCHED_POLICY_FIFO) {
> >> struct drm_sched_job *next;
> >>
> >> next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
> >> @@ -558,7 +573,8 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
> >> void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
> >> {
> >> struct drm_sched_entity *entity = sched_job->entity;
> >> - bool first;
> >> + bool first, fifo = entity->rq->sched->sched_policy ==
> >> + DRM_SCHED_POLICY_FIFO;
> >> ktime_t submit_ts;
> >>
> >> trace_drm_sched_job(sched_job, entity);
> >> @@ -587,7 +603,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
> >> drm_sched_rq_add_entity(entity->rq, entity);
> >> spin_unlock(&entity->rq_lock);
> >>
> >> - if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
> >> + if (fifo)
> >> drm_sched_rq_update_fifo(entity, submit_ts);
> >>
> >> drm_sched_wakeup_if_can_queue(entity->rq->sched);
> >> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> >> index 614e8c97a622..545d5298c086 100644
> >> --- a/drivers/gpu/drm/scheduler/sched_main.c
> >> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> >> @@ -66,14 +66,14 @@
> >> #define to_drm_sched_job(sched_job) \
> >> container_of((sched_job), struct drm_sched_job, queue_node)
> >>
> >> -int drm_sched_policy = DRM_SCHED_POLICY_FIFO;
> >> +int default_drm_sched_policy = DRM_SCHED_POLICY_FIFO;
> >>
> >> /**
> >> * DOC: sched_policy (int)
> >> * Used to override default entities scheduling policy in a run queue.
> >> */
> >> -MODULE_PARM_DESC(sched_policy, "Specify the scheduling policy for entities on a run-queue, " __stringify(DRM_SCHED_POLICY_RR) " = Round Robin, " __stringify(DRM_SCHED_POLICY_FIFO) " = FIFO (default).");
> >> -module_param_named(sched_policy, drm_sched_policy, int, 0444);
> >> +MODULE_PARM_DESC(sched_policy, "Specify the default scheduling policy for entities on a run-queue, " __stringify(DRM_SCHED_POLICY_RR) " = Round Robin, " __stringify(DRM_SCHED_POLICY_FIFO) " = FIFO (default).");
> >
> > Note, that you don't need to add "default" in the text as it is already there at the very end "FIFO (default)."
> > Else, it gets confusing what is meant by "default". Like this:
> >
> > Specify the default scheduling policy for entities on a run-queue, 1 = Round Robin, 2 = FIFO (default).
> >
> > See "default" appear twice and it creates confusion? We don't need our internal "default" play to get
> > exported all the way to the casual user reading this. It is much clear, however,
> >
> > Specify the scheduling policy for entities on a run-queue, 1 = Round Robin, 2 = FIFO (default).
> >
> > To mean, if unset, the default one would be used. But this is all internal code stuff.
> >
> > So I'd say leave this one alone.
> >
Ok.
> >> +module_param_named(sched_policy, default_drm_sched_policy, int, 0444);
> >
> > Put "default" as a postfix:
> > default_drm_sched_policy --> drm_sched_policy_default
> >
Sure.
> >>
> >> static __always_inline bool drm_sched_entity_compare_before(struct rb_node *a,
> >> const struct rb_node *b)
> >> @@ -177,7 +177,7 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
> >> if (rq->current_entity == entity)
> >> rq->current_entity = NULL;
> >>
> >> - if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
> >> + if (rq->sched->sched_policy == DRM_SCHED_POLICY_FIFO)
> >> drm_sched_rq_remove_fifo_locked(entity);
> >>
> >> spin_unlock(&rq->lock);
> >> @@ -898,7 +898,7 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
> >>
> >> /* Kernel run queue has higher priority than normal run queue*/
> >> for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
> >> - entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ?
> >> + entity = sched->sched_policy == DRM_SCHED_POLICY_FIFO ?
> >> drm_sched_rq_select_entity_fifo(&sched->sched_rq[i]) :
> >> drm_sched_rq_select_entity_rr(&sched->sched_rq[i]);
> >> if (entity)
> >> @@ -1071,6 +1071,7 @@ static void drm_sched_main(struct work_struct *w)
> >> * used
> >> * @score: optional score atomic shared with other schedulers
> >> * @name: name used for debugging
> >> + * @sched_policy: schedule policy
> >> * @dev: target &struct device
> >> *
> >> * Return 0 on success, otherwise error code.
> >> @@ -1080,9 +1081,15 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
> >> struct workqueue_struct *submit_wq,
> >> unsigned hw_submission, unsigned hang_limit,
> >> long timeout, struct workqueue_struct *timeout_wq,
> >> - atomic_t *score, const char *name, struct device *dev)
> >> + atomic_t *score, const char *name,
> >> + enum drm_sched_policy sched_policy,
> >> + struct device *dev)
> >> {
> >> int i;
> >> +
> >> + if (sched_policy >= DRM_SCHED_POLICY_COUNT)
> >> + return -EINVAL;
> >> +
> >> sched->ops = ops;
> >> sched->hw_submission_limit = hw_submission;
> >> sched->name = name;
> >> @@ -1092,6 +1099,10 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
> >> sched->hang_limit = hang_limit;
> >> sched->score = score ? score : &sched->_score;
> >> sched->dev = dev;
> >> + if (sched_policy == DRM_SCHED_POLICY_DEFAULT)
> >> + sched->sched_policy = default_drm_sched_policy;
> >> + else
> >> + sched->sched_policy = sched_policy;
>
> Note also that here you can use a ternary operator as opposed to an if-control.
>
> sched->sched_policy = sched_policy == DRM_SCHED_POLICY_UNSET ?
> drm_sched_policy_default : sched_policy;
Sure, will fix in next rev.
Matt
>
> --
> Regards,
> Luben
>
