* through the jobs entity pointer.
*/
+/**
+ * DOC: Flow Control
+ *
+ * The DRM GPU scheduler provides a flow control mechanism to regulate the rate
+ * in which the jobs fetched from scheduler entities are executed.
+ *
+ * In this context the &drm_gpu_scheduler keeps track of a driver specified
+ * credit limit representing the capacity of this scheduler and a credit count;
+ * every &drm_sched_job carries a driver specified number of credits.
+ *
+ * Once a job is executed (but not yet finished), the job's credits contribute
+ * to the scheduler's credit count until the job is finished. If by executing
+ * one more job the scheduler's credit count would exceed the scheduler's
+ * credit limit, the job won't be executed. Instead, the scheduler will wait
+ * until the credit count has decreased enough to not overflow its credit limit.
+ * This implies waiting for previously executed jobs.
+ *
+ * Optionally, drivers may register a callback (update_job_credits) provided by
+ * struct drm_sched_backend_ops to update the job's credits dynamically. The
+ * scheduler executes this callback every time the scheduler considers a job for
+ * execution and subsequently checks whether the job fits the scheduler's credit
+ * limit.
+ */
+
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/completion.h>
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);
+static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched)
+{
+ u32 credits;
+
+ drm_WARN_ON(sched, check_sub_overflow(sched->credit_limit,
+ atomic_read(&sched->credit_count),
+ &credits));
+
+ return credits;
+}
+
+/**
+ * drm_sched_can_queue -- Can we queue more to the hardware?
+ * @sched: scheduler instance
+ * @entity: the scheduler entity
+ *
+ * Return true if we can push at least one more job from @entity, false
+ * otherwise.
+ */
+static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched,
+ struct drm_sched_entity *entity)
+{
+ struct drm_sched_job *s_job;
+
+ s_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
+ if (!s_job)
+ return false;
+
+ if (sched->ops->update_job_credits) {
+ s_job->credits = sched->ops->update_job_credits(s_job);
+
+ drm_WARN(sched, !s_job->credits,
+ "Jobs with zero credits bypass job-flow control.\n");
+ }
+
+ /* If a job exceeds the credit limit, truncate it to the credit limit
+ * itself to guarantee forward progress.
+ */
+ if (drm_WARN(sched, s_job->credits > sched->credit_limit,
+ "Jobs may not exceed the credit limit, truncate.\n"))
+ s_job->credits = sched->credit_limit;
+
+ return drm_sched_available_credits(sched) >= s_job->credits;
+}
+
static __always_inline bool drm_sched_entity_compare_before(struct rb_node *a,
const struct rb_node *b)
{
/**
* drm_sched_rq_select_entity_rr - Select an entity which could provide a job to run
*
+ * @sched: the gpu scheduler
* @rq: scheduler run queue to check.
*
- * Try to find a ready entity, returns NULL if none found.
+ * Try to find the next ready entity.
+ *
+ * Return an entity if one is found; return an error-pointer (!NULL) if an
+ * entity was ready, but the scheduler had insufficient credits to accommodate
+ * its job; return NULL, if no ready entity was found.
*/
static struct drm_sched_entity *
-drm_sched_rq_select_entity_rr(struct drm_sched_rq *rq)
+drm_sched_rq_select_entity_rr(struct drm_gpu_scheduler *sched,
+ struct drm_sched_rq *rq)
{
struct drm_sched_entity *entity;
if (entity) {
list_for_each_entry_continue(entity, &rq->entities, list) {
if (drm_sched_entity_is_ready(entity)) {
+ /* If we can't queue yet, preserve the current
+ * entity in terms of fairness.
+ */
+ if (!drm_sched_can_queue(sched, entity)) {
+ spin_unlock(&rq->lock);
+ return ERR_PTR(-ENOSPC);
+ }
+
rq->current_entity = entity;
reinit_completion(&entity->entity_idle);
spin_unlock(&rq->lock);
}
list_for_each_entry(entity, &rq->entities, list) {
-
if (drm_sched_entity_is_ready(entity)) {
+ /* If we can't queue yet, preserve the current entity in
+ * terms of fairness.
+ */
+ if (!drm_sched_can_queue(sched, entity)) {
+ spin_unlock(&rq->lock);
+ return ERR_PTR(-ENOSPC);
+ }
+
rq->current_entity = entity;
reinit_completion(&entity->entity_idle);
spin_unlock(&rq->lock);
/**
* drm_sched_rq_select_entity_fifo - Select an entity which provides a job to run
*
+ * @sched: the gpu scheduler
* @rq: scheduler run queue to check.
*
- * Find oldest waiting ready entity, returns NULL if none found.
+ * Find oldest waiting ready entity.
+ *
+ * Return an entity if one is found; return an error-pointer (!NULL) if an
+ * entity was ready, but the scheduler had insufficient credits to accommodate
+ * its job; return NULL, if no ready entity was found.
*/
static struct drm_sched_entity *
-drm_sched_rq_select_entity_fifo(struct drm_sched_rq *rq)
+drm_sched_rq_select_entity_fifo(struct drm_gpu_scheduler *sched,
+ struct drm_sched_rq *rq)
{
struct rb_node *rb;
entity = rb_entry(rb, struct drm_sched_entity, rb_tree_node);
if (drm_sched_entity_is_ready(entity)) {
+ /* If we can't queue yet, preserve the current entity in
+ * terms of fairness.
+ */
+ if (!drm_sched_can_queue(sched, entity)) {
+ spin_unlock(&rq->lock);
+ return ERR_PTR(-ENOSPC);
+ }
+
rq->current_entity = entity;
reinit_completion(&entity->entity_idle);
break;
struct drm_sched_fence *s_fence = s_job->s_fence;
struct drm_gpu_scheduler *sched = s_fence->sched;
- atomic_dec(&sched->hw_rq_count);
+ atomic_sub(s_job->credits, &sched->credit_count);
atomic_dec(sched->score);
trace_drm_sched_process_job(s_fence);
&s_job->cb)) {
dma_fence_put(s_job->s_fence->parent);
s_job->s_fence->parent = NULL;
- atomic_dec(&sched->hw_rq_count);
+ atomic_sub(s_job->credits, &sched->credit_count);
} else {
/*
* remove job from pending_list.
list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
struct dma_fence *fence = s_job->s_fence->parent;
- atomic_inc(&sched->hw_rq_count);
+ atomic_add(s_job->credits, &sched->credit_count);
if (!full_recovery)
continue;
* drm_sched_job_init - init a scheduler job
* @job: scheduler job to init
* @entity: scheduler entity to use
+ * @credits: the number of credits this job contributes to the schedulers
+ * credit limit
* @owner: job owner for debugging
*
* Refer to drm_sched_entity_push_job() documentation
*/
int drm_sched_job_init(struct drm_sched_job *job,
struct drm_sched_entity *entity,
- void *owner)
+ u32 credits, void *owner)
{
if (!entity->rq) {
/* This will most likely be followed by missing frames
return -ENOENT;
}
+ if (unlikely(!credits)) {
+ pr_err("*ERROR* %s: credits cannot be 0!\n", __func__);
+ return -EINVAL;
+ }
+
job->entity = entity;
+ job->credits = credits;
job->s_fence = drm_sched_fence_alloc(entity, owner);
if (!job->s_fence)
return -ENOMEM;
}
EXPORT_SYMBOL(drm_sched_job_cleanup);
-/**
- * drm_sched_can_queue -- Can we queue more to the hardware?
- * @sched: scheduler instance
- *
- * Return true if we can push more jobs to the hw, otherwise false.
- */
-static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched)
-{
- return atomic_read(&sched->hw_rq_count) <
- sched->hw_submission_limit;
-}
-
/**
* drm_sched_wakeup - Wake up the scheduler if it is ready to queue
* @sched: scheduler instance
+ * @entity: the scheduler entity
*
* Wake up the scheduler if we can queue jobs.
*/
struct drm_sched_entity *entity)
{
if (drm_sched_entity_is_ready(entity))
- if (drm_sched_can_queue(sched))
+ if (drm_sched_can_queue(sched, entity))
drm_sched_run_job_queue(sched);
}
*
* @sched: scheduler instance
*
- * Returns the entity to process or NULL if none are found.
+ * Return an entity to process or NULL if none are found.
+ *
+ * Note, that we break out of the for-loop when "entity" is non-null, which can
+ * also be an error-pointer--this assures we don't process lower priority
+ * run-queues. See comments in the respectively called functions.
*/
static struct drm_sched_entity *
drm_sched_select_entity(struct drm_gpu_scheduler *sched)
struct drm_sched_entity *entity;
int i;
- if (!drm_sched_can_queue(sched))
- return NULL;
-
/* Kernel run queue has higher priority than normal run queue*/
for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
entity = drm_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]);
+ drm_sched_rq_select_entity_fifo(sched, sched->sched_rq[i]) :
+ drm_sched_rq_select_entity_rr(sched, sched->sched_rq[i]);
if (entity)
break;
}
- return entity;
+ return IS_ERR(entity) ? NULL : entity;
}
/**
s_fence = sched_job->s_fence;
- atomic_inc(&sched->hw_rq_count);
+ atomic_add(sched_job->credits, &sched->credit_count);
drm_sched_job_begin(sched_job);
trace_drm_run_job(sched_job, entity);
* @submit_wq: workqueue to use for submission. If NULL, an ordered wq is
* allocated and used
* @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT
- * @hw_submission: number of hw submissions that can be in flight
+ * @credit_limit: the number of credits this scheduler can hold from all jobs
* @hang_limit: number of times to allow a job to hang before dropping it
* @timeout: timeout value in jiffies for the scheduler
* @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is
int drm_sched_init(struct drm_gpu_scheduler *sched,
const struct drm_sched_backend_ops *ops,
struct workqueue_struct *submit_wq,
- u32 num_rqs, uint32_t hw_submission, unsigned int hang_limit,
+ u32 num_rqs, u32 credit_limit, unsigned int hang_limit,
long timeout, struct workqueue_struct *timeout_wq,
atomic_t *score, const char *name, struct device *dev)
{
int i, ret;
sched->ops = ops;
- sched->hw_submission_limit = hw_submission;
+ sched->credit_limit = credit_limit;
sched->name = name;
sched->timeout = timeout;
sched->timeout_wq = timeout_wq ? : system_wq;
init_waitqueue_head(&sched->job_scheduled);
INIT_LIST_HEAD(&sched->pending_list);
spin_lock_init(&sched->job_list_lock);
- atomic_set(&sched->hw_rq_count, 0);
+ atomic_set(&sched->credit_count, 0);
INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
INIT_WORK(&sched->work_run_job, drm_sched_run_job_work);
INIT_WORK(&sched->work_free_job, drm_sched_free_job_work);
* @sched: the scheduler instance on which this job is scheduled.
* @s_fence: contains the fences for the scheduling of job.
* @finish_cb: the callback for the finished fence.
+ * @credits: the number of credits this job contributes to the scheduler
* @work: Helper to reschdeule job kill to different context.
* @id: a unique id assigned to each job scheduled on the scheduler.
* @karma: increment on every hang caused by this job. If this exceeds the hang
struct drm_gpu_scheduler *sched;
struct drm_sched_fence *s_fence;
+ u32 credits;
+
/*
* work is used only after finish_cb has been used and will not be
* accessed anymore.
* and it's time to clean it up.
*/
void (*free_job)(struct drm_sched_job *sched_job);
+
+ /**
+ * @update_job_credits: Called when the scheduler is considering this
+ * job for execution.
+ *
+ * This callback returns the number of credits the job would take if
+ * pushed to the hardware. Drivers may use this to dynamically update
+ * the job's credit count. For instance, deduct the number of credits
+ * for already signalled native fences.
+ *
+ * This callback is optional.
+ */
+ u32 (*update_job_credits)(struct drm_sched_job *sched_job);
};
/**
* struct drm_gpu_scheduler - scheduler instance-specific data
*
* @ops: backend operations provided by the driver.
- * @hw_submission_limit: the max size of the hardware queue.
+ * @credit_limit: the credit limit of this scheduler
+ * @credit_count: the current credit count of this scheduler
* @timeout: the time after which a job is removed from the scheduler.
* @name: name of the ring for which this scheduler is being used.
* @num_rqs: Number of run-queues. This is at most DRM_SCHED_PRIORITY_COUNT,
* @job_scheduled: once @drm_sched_entity_do_release is called the scheduler
* waits on this wait queue until all the scheduled jobs are
* finished.
- * @hw_rq_count: the number of jobs currently in the hardware queue.
* @job_id_count: used to assign unique id to the each job.
* @submit_wq: workqueue used to queue @work_run_job and @work_free_job
* @timeout_wq: workqueue used to queue @work_tdr
*/
struct drm_gpu_scheduler {
const struct drm_sched_backend_ops *ops;
- uint32_t hw_submission_limit;
+ u32 credit_limit;
+ atomic_t credit_count;
long timeout;
const char *name;
u32 num_rqs;
struct drm_sched_rq **sched_rq;
wait_queue_head_t job_scheduled;
- atomic_t hw_rq_count;
atomic64_t job_id_count;
struct workqueue_struct *submit_wq;
struct workqueue_struct *timeout_wq;
int drm_sched_init(struct drm_gpu_scheduler *sched,
const struct drm_sched_backend_ops *ops,
struct workqueue_struct *submit_wq,
- u32 num_rqs, uint32_t hw_submission, unsigned int hang_limit,
+ u32 num_rqs, u32 credit_limit, unsigned int hang_limit,
long timeout, struct workqueue_struct *timeout_wq,
atomic_t *score, const char *name, struct device *dev);
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);
+ u32 credits, void *owner);
void drm_sched_job_arm(struct drm_sched_job *job);
int drm_sched_job_add_dependency(struct drm_sched_job *job,
struct dma_fence *fence);
projects / linux.git / commitdiff