[Intel-xe] [PATCH 3/8] drm/sched: Add DRM_SCHED_POLICY_SINGLE_ENTITY scheduling policy
Christopher Snowhill
kode54 at gmail.com
Mon May 22 05:48:50 UTC 2023
On Sun, May 21, 2023 at 6:50 PM Matthew Brost <matthew.brost at intel.com> wrote:
>
> DRM_SCHED_POLICY_SINGLE_ENTITY creates a 1 to 1 relationship between
> scheduler and entity. No priorities or run queue used in this mode.
> Intended for devices with firmware schedulers.
>
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
> drivers/gpu/drm/scheduler/sched_entity.c | 40 ++++++++++++---
> drivers/gpu/drm/scheduler/sched_fence.c | 2 +-
> drivers/gpu/drm/scheduler/sched_main.c | 63 +++++++++++++++++++++---
> include/drm/gpu_scheduler.h | 8 +++
> 4 files changed, 96 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index e1838e328de8..90e925804a20 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -83,6 +83,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
> memset(entity, 0, sizeof(struct drm_sched_entity));
> INIT_LIST_HEAD(&entity->list);
> entity->rq = NULL;
> + entity->single_sched = NULL;
> entity->guilty = guilty;
> entity->num_sched_list = num_sched_list;
> entity->priority = priority;
This very important patch segment was omitted here:
@@ -91,7 +92,15 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
RB_CLEAR_NODE(&entity->rb_tree_node);
if(num_sched_list) {
- entity->rq = &sched_list[0]->sched_rq[entity->priority];
+ if (sched_list[0]->sched_policy !=
+ DRM_SCHED_POLICY_SINGLE_ENTITY) {
+ entity->rq = &sched_list[0]->sched_rq[entity->priority];
+ } else {
+ if (num_sched_list != 1 || sched_list[0]->single_entity)
+ return -EINVAL;
+ sched_list[0]->single_entity = entity;
+ entity->single_sched = sched_list[0];
+ }
}
init_completion(&entity->entity_idle);
> @@ -124,7 +125,8 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
> struct drm_gpu_scheduler **sched_list,
> unsigned int num_sched_list)
> {
> - WARN_ON(!num_sched_list || !sched_list);
> + WARN_ON(!num_sched_list || !sched_list ||
> + !!entity->single_sched);
>
> entity->sched_list = sched_list;
> entity->num_sched_list = num_sched_list;
> @@ -215,13 +217,15 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
> {
> struct drm_sched_job *job;
> struct dma_fence *prev;
> + bool single_entity = !!entity->single_sched;
>
> - if (!entity->rq)
> + if (!entity->rq && !single_entity)
> return;
>
> spin_lock(&entity->rq_lock);
> entity->stopped = true;
> - drm_sched_rq_remove_entity(entity->rq, entity);
> + if (!single_entity)
> + drm_sched_rq_remove_entity(entity->rq, entity);
> spin_unlock(&entity->rq_lock);
>
> /* Make sure this entity is not used by the scheduler at the moment */
> @@ -243,6 +247,20 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
> dma_fence_put(prev);
> }
>
> +/**
> + * drm_sched_entity_to_scheduler - Schedule entity to GPU scheduler
> + * @entity: scheduler entity
> + *
> + * Returns GPU scheduler for the entity
> + */
> +struct drm_gpu_scheduler *
> +drm_sched_entity_to_scheduler(struct drm_sched_entity *entity)
> +{
> + bool single_entity = !!entity->single_sched;
> +
> + return single_entity ? entity->single_sched : entity->rq->sched;
> +}
> +
> /**
> * drm_sched_entity_flush - Flush a context entity
> *
> @@ -260,11 +278,12 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
> struct drm_gpu_scheduler *sched;
> struct task_struct *last_user;
> long ret = timeout;
> + bool single_entity = !!entity->single_sched;
>
> - if (!entity->rq)
> + if (!entity->rq && !single_entity)
> return 0;
>
> - sched = entity->rq->sched;
> + sched = drm_sched_entity_to_scheduler(entity);
> /**
> * The client will not queue more IBs during this fini, consume existing
> * queued IBs or discard them on SIGKILL
> @@ -357,7 +376,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
> container_of(cb, struct drm_sched_entity, cb);
>
> drm_sched_entity_clear_dep(f, cb);
> - drm_sched_wakeup(entity->rq->sched);
> + drm_sched_wakeup(drm_sched_entity_to_scheduler(entity));
> }
>
> /**
> @@ -371,6 +390,8 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
> void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
> enum drm_sched_priority priority)
> {
> + WARN_ON(!!entity->single_sched);
> +
> spin_lock(&entity->rq_lock);
> entity->priority = priority;
> spin_unlock(&entity->rq_lock);
> @@ -383,7 +404,7 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority);
> */
> static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
> {
> - struct drm_gpu_scheduler *sched = entity->rq->sched;
> + struct drm_gpu_scheduler *sched = drm_sched_entity_to_scheduler(entity);
> struct dma_fence *fence = entity->dependency;
> struct drm_sched_fence *s_fence;
>
> @@ -476,7 +497,8 @@ 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 (entity->rq->sched->sched_policy == DRM_SCHED_POLICY_FIFO) {
> + if (drm_sched_entity_to_scheduler(entity)->sched_policy ==
> + DRM_SCHED_POLICY_FIFO) {
> struct drm_sched_job *next;
>
> next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
> @@ -499,6 +521,8 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
> struct drm_gpu_scheduler *sched;
> struct drm_sched_rq *rq;
>
> + WARN_ON(!!entity->single_sched);
> +
> /* single possible engine and already selected */
> if (!entity->sched_list)
> return;
> diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
> index ef120475e7c6..b3b0472dc202 100644
> --- a/drivers/gpu/drm/scheduler/sched_fence.c
> +++ b/drivers/gpu/drm/scheduler/sched_fence.c
> @@ -215,7 +215,7 @@ void drm_sched_fence_init(struct drm_sched_fence *fence,
> {
> unsigned seq;
>
> - fence->sched = entity->rq->sched;
> + fence->sched = drm_sched_entity_to_scheduler(entity);
> seq = atomic_inc_return(&entity->fence_seq);
> dma_fence_init(&fence->scheduled, &drm_sched_fence_ops_scheduled,
> &fence->lock, entity->fence_context, seq);
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index ead122e99d00..d9efa0bd69c8 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -32,7 +32,8 @@
> * backend operations to the scheduler like submitting a job to hardware run queue,
> * returning the dependencies of a job etc.
> *
> - * The organisation of the scheduler is the following:
> + * The organisation of the scheduler is the following for scheduling policies
> + * DRM_SCHED_POLICY_RR and DRM_SCHED_POLICY_FIFO:
> *
> * 1. Each hw run queue has one scheduler
> * 2. Each scheduler has multiple run queues with different priorities
> @@ -41,7 +42,22 @@
> * 4. Entities themselves maintain a queue of jobs that will be scheduled on
> * the hardware.
> *
> - * The jobs in a entity are always scheduled in the order that they were pushed.
> + * The organisation of the scheduler is the following for scheduling policy
> + * DRM_SCHED_POLICY_SINGLE_ENTITY:
> + *
> + * 1. One to one relationship between scheduler and entity
> + * 2. No priorities implemented per scheduler (single job queue)
> + * 3. No run queues in scheduler rather jobs are directly dequeued from entity
> + * 4. The entity maintains a queue of jobs that will be scheduled on the
> + * hardware
> + *
> + * The jobs in a entity are always scheduled in the order that they were pushed
> + * regardless of scheduling policy.
> + *
> + * A policy of DRM_SCHED_POLICY_RR or DRM_SCHED_POLICY_FIFO is expected to used
> + * when the KMD is scheduling directly on the hardware while a scheduling policy
> + * of DRM_SCHED_POLICY_SINGLE_ENTITY is expected to be used when there is a
> + * firmare scheduler.
> *
> * Note that once a job was taken from the entities queue and pushed to the
> * hardware, i.e. the pending queue, the entity must not be referenced anymore
> @@ -96,6 +112,8 @@ static inline void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *enti
>
> void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
> {
> + WARN_ON(!!entity->single_sched);
> +
> /*
> * Both locks need to be grabbed, one to protect from entity->rq change
> * for entity from within concurrent drm_sched_entity_select_rq and the
> @@ -126,6 +144,8 @@ void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
> static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
> struct drm_sched_rq *rq)
> {
> + WARN_ON(sched->sched_policy == DRM_SCHED_POLICY_SINGLE_ENTITY);
> +
> spin_lock_init(&rq->lock);
> INIT_LIST_HEAD(&rq->entities);
> rq->rb_tree_root = RB_ROOT_CACHED;
> @@ -144,6 +164,8 @@ static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
> void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
> struct drm_sched_entity *entity)
> {
> + WARN_ON(!!entity->single_sched);
> +
> if (!list_empty(&entity->list))
> return;
>
> @@ -166,6 +188,8 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
> void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
> struct drm_sched_entity *entity)
> {
> + WARN_ON(!!entity->single_sched);
> +
> if (list_empty(&entity->list))
> return;
>
> @@ -696,7 +720,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
> struct drm_sched_entity *entity,
> void *owner)
> {
> - if (!entity->rq)
> + if (!entity->rq && !entity->single_sched)
> return -ENOENT;
>
> job->entity = entity;
> @@ -729,13 +753,16 @@ void drm_sched_job_arm(struct drm_sched_job *job)
> {
> struct drm_gpu_scheduler *sched;
> struct drm_sched_entity *entity = job->entity;
> + bool single_entity = !!entity->single_sched;
>
> BUG_ON(!entity);
> - drm_sched_entity_select_rq(entity);
> - sched = entity->rq->sched;
> + if (!single_entity)
> + drm_sched_entity_select_rq(entity);
> + sched = drm_sched_entity_to_scheduler(entity);
>
> job->sched = sched;
> - job->s_priority = entity->rq - sched->sched_rq;
> + if (!single_entity)
> + job->s_priority = entity->rq - sched->sched_rq;
> job->id = atomic64_inc_return(&sched->job_id_count);
>
> drm_sched_fence_init(job->s_fence, job->entity);
> @@ -959,6 +986,13 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
> if (!drm_sched_ready(sched))
> return NULL;
>
> + if (sched->single_entity) {
> + if (drm_sched_entity_is_ready(sched->single_entity))
> + return sched->single_entity;
> +
> + return NULL;
> + }
> +
> /* Kernel run queue has higher priority than normal run queue*/
> for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
> entity = sched->sched_policy == DRM_SCHED_POLICY_FIFO ?
> @@ -1206,6 +1240,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
> return -EINVAL;
>
> sched->ops = ops;
> + sched->single_entity = NULL;
> sched->hw_submission_limit = hw_submission;
> sched->name = name;
> sched->run_wq = run_wq ? : system_wq;
> @@ -1218,7 +1253,9 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
> sched->sched_policy = default_drm_sched_policy;
> else
> sched->sched_policy = sched_policy;
> - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
> + for (i = DRM_SCHED_PRIORITY_MIN; sched_policy !=
> + DRM_SCHED_POLICY_SINGLE_ENTITY && i < DRM_SCHED_PRIORITY_COUNT;
> + i++)
> drm_sched_rq_init(sched, &sched->sched_rq[i]);
>
> init_waitqueue_head(&sched->job_scheduled);
> @@ -1251,7 +1288,15 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
>
> drm_sched_run_wq_stop(sched);
>
> - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
> + if (sched->single_entity) {
> + spin_lock(&sched->single_entity->rq_lock);
> + sched->single_entity->stopped = true;
> + spin_unlock(&sched->single_entity->rq_lock);
> + }
> +
> + for (i = DRM_SCHED_PRIORITY_COUNT - 1; sched->sched_policy !=
> + DRM_SCHED_POLICY_SINGLE_ENTITY && i >= DRM_SCHED_PRIORITY_MIN;
> + i--) {
> struct drm_sched_rq *rq = &sched->sched_rq[i];
>
> if (!rq)
> @@ -1295,6 +1340,8 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
> struct drm_sched_entity *entity;
> struct drm_gpu_scheduler *sched = bad->sched;
>
> + WARN_ON(sched->sched_policy == DRM_SCHED_POLICY_SINGLE_ENTITY);
> +
> /* don't change @bad's karma if it's from KERNEL RQ,
> * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
> * corrupt but keep in mind that kernel jobs always considered good.
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index 929d0d567a0b..1a26f501a400 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -79,6 +79,7 @@ enum drm_sched_policy {
> DRM_SCHED_POLICY_DEFAULT,
> DRM_SCHED_POLICY_RR,
> DRM_SCHED_POLICY_FIFO,
> + DRM_SCHED_POLICY_SINGLE_ENTITY,
> DRM_SCHED_POLICY_COUNT,
> };
>
> @@ -112,6 +113,9 @@ struct drm_sched_entity {
> */
> struct drm_sched_rq *rq;
>
> + /** @single_sched: Single scheduler */
> + struct drm_gpu_scheduler *single_sched;
> +
> /**
> * @sched_list:
> *
> @@ -496,6 +500,7 @@ struct drm_sched_backend_ops {
> * struct drm_gpu_scheduler - scheduler instance-specific data
> *
> * @ops: backend operations provided by the driver.
> + * @single_entity: Single entity for the scheduler
> * @hw_submission_limit: the max size of the hardware queue.
> * @timeout: the time after which a job is removed from the scheduler.
> * @name: name of the ring for which this scheduler is being used.
> @@ -527,6 +532,7 @@ struct drm_sched_backend_ops {
> */
> struct drm_gpu_scheduler {
> const struct drm_sched_backend_ops *ops;
> + struct drm_sched_entity *single_entity;
> uint32_t hw_submission_limit;
> long timeout;
> const char *name;
> @@ -612,6 +618,8 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
> struct drm_gpu_scheduler **sched_list,
> unsigned int num_sched_list,
> atomic_t *guilty);
> +struct drm_gpu_scheduler *
> +drm_sched_entity_to_scheduler(struct drm_sched_entity *entity);
> long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout);
> void drm_sched_entity_fini(struct drm_sched_entity *entity);
> void drm_sched_entity_destroy(struct drm_sched_entity *entity);
> --
> 2.34.1
>
More information about the Intel-xe
mailing list