void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
{
- struct drm_sched_rq *rq = sched->rq;
- struct drm_sched_entity *s_entity;
struct drm_sched_job *s_job;
+ struct drm_sched_entity *s_entity = NULL;
+ int i;
/* Signal all jobs not yet scheduled */
- spin_lock(&rq->lock);
- list_for_each_entry(s_entity, &rq->entities, list) {
- while ((s_job = drm_sched_entity_queue_pop(s_entity))) {
- struct drm_sched_fence *s_fence = s_job->s_fence;
-
- dma_fence_signal(&s_fence->scheduled);
- dma_fence_set_error(&s_fence->finished, -EHWPOISON);
- dma_fence_signal(&s_fence->finished);
+ for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
+ struct drm_sched_rq *rq = sched->sched_rq[i];
+ spin_lock(&rq->lock);
+ list_for_each_entry(s_entity, &rq->entities, list) {
+ while ((s_job = drm_sched_entity_queue_pop(s_entity))) {
+ struct drm_sched_fence *s_fence = s_job->s_fence;
+
+ dma_fence_signal(&s_fence->scheduled);
+ dma_fence_set_error(&s_fence->finished, -EHWPOISON);
+ dma_fence_signal(&s_fence->finished);
+ }
}
+ spin_unlock(&rq->lock);
}
- spin_unlock(&rq->lock);
/* Signal all jobs already scheduled to HW */
list_for_each_entry(s_job, &sched->pending_list, list) {
entity->guilty = guilty;
entity->priority = priority;
entity->last_user = current->group_leader;
+ entity->rq_priority = drm_sched_policy == DRM_SCHED_POLICY_FAIR ?
+ DRM_SCHED_PRIORITY_KERNEL : priority;
entity->num_sched_list = num_sched_list;
entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
RCU_INIT_POINTER(entity->last_scheduled, NULL);
RB_CLEAR_NODE(&entity->rb_tree_node);
- if (!sched_list[0]->rq) {
+ if (!sched_list[0]->sched_rq) {
/* Since every entry covered by num_sched_list
* should be non-NULL and therefore we warn drivers
* not to do this and to fix their DRM calling order.
*/
pr_warn("%s: called with uninitialized scheduler\n", __func__);
} else {
- entity->rq = sched_list[0]->rq;
+ enum drm_sched_priority p = entity->priority;
+
+ /*
+ * The "priority" of an entity cannot exceed the number of
+ * run-queues of a scheduler. Protect against num_rqs being 0,
+ * by converting to signed. Choose the lowest priority
+ * available.
+ */
+ if (p >= sched_list[0]->num_user_rqs) {
+ dev_err(sched_list[0]->dev, "entity with out-of-bounds priority:%u num_user_rqs:%u\n",
+ p, sched_list[0]->num_user_rqs);
+ p = max_t(s32,
+ (s32)sched_list[0]->num_user_rqs - 1,
+ (s32)DRM_SCHED_PRIORITY_KERNEL);
+ entity->priority = p;
+ }
+ entity->rq = sched_list[0]->sched_rq[entity->rq_priority];
}
init_completion(&entity->entity_idle);
spin_lock(&entity->lock);
sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list);
- rq = sched ? sched->rq : NULL;
+ rq = sched ? sched->sched_rq[entity->rq_priority] : NULL;
if (rq != entity->rq) {
drm_sched_rq_remove_entity(entity->rq, entity);
entity->rq = rq;
{
struct drm_sched_entity *entity = sched_job->entity;
bool first;
+ ktime_t submit_ts;
trace_drm_sched_job_queue(sched_job, entity);
/*
* After the sched_job is pushed into the entity queue, it may be
* completed and freed up at any time. We can no longer access it.
+ * Make sure to set the submit_ts first, to avoid a race.
*/
+ sched_job->submit_ts = submit_ts = ktime_get();
first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
/* first job wakes up scheduler */
if (first) {
struct drm_gpu_scheduler *sched;
- sched = drm_sched_rq_add_entity(entity);
+ sched = drm_sched_rq_add_entity(entity, submit_ts);
if (sched)
drm_sched_wakeup(sched);
}
struct ewma_drm_sched_avgtime avg_job_us;
};
+/* Used to choose between FIFO and RR job-scheduling */
+extern int drm_sched_policy;
+
+#define DRM_SCHED_POLICY_RR 0
+#define DRM_SCHED_POLICY_FIFO 1
+#define DRM_SCHED_POLICY_FAIR 2
+
bool drm_sched_can_queue(struct drm_gpu_scheduler *sched,
struct drm_sched_entity *entity);
void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
struct drm_sched_rq *rq);
struct drm_gpu_scheduler *
-drm_sched_rq_add_entity(struct drm_sched_entity *entity);
+drm_sched_rq_add_entity(struct drm_sched_entity *entity, ktime_t ts);
void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
struct drm_sched_entity *entity);
void drm_sched_rq_pop_entity(struct drm_sched_entity *entity);
struct drm_sched_entity *
-drm_sched_select_entity(struct drm_gpu_scheduler *sched);
+drm_sched_rq_select_entity(struct drm_gpu_scheduler *sched,
+ struct drm_sched_rq *rq);
void drm_sched_entity_select_rq(struct drm_sched_entity *entity);
struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity);
#define CREATE_TRACE_POINTS
#include "gpu_scheduler_trace.h"
+int drm_sched_policy = DRM_SCHED_POLICY_FAIR;
+
+/**
+ * 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, " __stringify(DRM_SCHED_POLICY_FAIR) " = Fair (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_sched_run_job_queue(sched);
}
+/**
+ * drm_sched_select_entity - Select next entity to process
+ *
+ * @sched: scheduler instance
+ *
+ * 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 = NULL;
+ int i;
+
+ /* Start with the highest priority.
+ */
+ for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
+ entity = drm_sched_rq_select_entity(sched, sched->sched_rq[i]);
+ if (entity)
+ break;
+ }
+
+ return IS_ERR(entity) ? NULL : entity;
+}
+
/**
* drm_sched_get_finished_job - fetch the next finished job to be destroyed
*
/* Find entity with a ready job */
entity = drm_sched_select_entity(sched);
- if (IS_ERR_OR_NULL(entity)) {
+ if (!entity) {
/*
* Either no more work to do, or the next ready job needs more
* credits than the scheduler has currently available.
*/
int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_args *args)
{
+ int i;
+
sched->ops = args->ops;
sched->credit_limit = args->credit_limit;
sched->name = args->name;
sched->score = args->score ? args->score : &sched->_score;
sched->dev = args->dev;
- if (sched->rq) {
+ if (args->num_rqs > DRM_SCHED_PRIORITY_COUNT) {
+ /* This is a gross violation--tell drivers what the problem is.
+ */
+ dev_err(sched->dev, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
+ __func__);
+ return -EINVAL;
+ } else if (sched->sched_rq) {
/* Not an error, but warn anyway so drivers can
* fine-tune their DRM calling order, and return all
* is good.
sched->own_submit_wq = true;
}
- sched->rq = kzalloc_obj(*sched->rq);
- if (!sched->rq)
+ sched->num_user_rqs = args->num_rqs;
+ sched->num_rqs = drm_sched_policy != DRM_SCHED_POLICY_FAIR ?
+ args->num_rqs : 1;
+ sched->sched_rq = kzalloc_objs(*sched->sched_rq, args->num_rqs);
+ if (!sched->sched_rq)
goto Out_check_own;
- drm_sched_rq_init(sched, sched->rq);
+ for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
+ sched->sched_rq[i] = kzalloc_obj(*sched->sched_rq[i]);
+ if (!sched->sched_rq[i])
+ goto Out_unroll;
+ drm_sched_rq_init(sched, sched->sched_rq[i]);
+ }
init_waitqueue_head(&sched->job_scheduled);
INIT_LIST_HEAD(&sched->pending_list);
sched->ready = true;
return 0;
+Out_unroll:
+ for (--i ; i >= DRM_SCHED_PRIORITY_KERNEL; i--)
+ kfree(sched->sched_rq[i]);
+ kfree(sched->sched_rq);
+ sched->sched_rq = NULL;
Out_check_own:
if (sched->own_submit_wq)
destroy_workqueue(sched->submit_wq);
*/
void drm_sched_fini(struct drm_gpu_scheduler *sched)
{
+ int i;
+
drm_sched_wqueue_stop(sched);
+ for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++)
+ kfree(sched->sched_rq[i]);
+
/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */
wake_up_all(&sched->job_scheduled);
if (sched->own_submit_wq)
destroy_workqueue(sched->submit_wq);
sched->ready = false;
- kfree(sched->rq);
- sched->rq = NULL;
+ kfree(sched->sched_rq);
+ sched->sched_rq = NULL;
if (!list_empty(&sched->pending_list))
dev_warn(sched->dev, "Tearing down scheduler while jobs are pending!\n");
*/
void drm_sched_increase_karma(struct drm_sched_job *bad)
{
+ int i;
+ struct drm_sched_entity *tmp;
+ struct drm_sched_entity *entity;
struct drm_gpu_scheduler *sched = bad->sched;
- struct drm_sched_entity *entity, *tmp;
- struct drm_sched_rq *rq = sched->rq;
/* 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.
*/
- if (bad->s_priority == DRM_SCHED_PRIORITY_KERNEL)
- return;
-
- atomic_inc(&bad->karma);
-
- spin_lock(&rq->lock);
- list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
- if (bad->s_fence->scheduled.context == entity->fence_context) {
- if (entity->guilty)
- atomic_set(entity->guilty, 1);
- break;
+ if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
+ atomic_inc(&bad->karma);
+
+ for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
+ struct drm_sched_rq *rq = sched->sched_rq[i];
+
+ spin_lock(&rq->lock);
+ list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
+ if (bad->s_fence->scheduled.context ==
+ entity->fence_context) {
+ if (entity->guilty)
+ atomic_set(entity->guilty, 1);
+ break;
+ }
+ }
+ spin_unlock(&rq->lock);
+ if (&entity->list != &rq->entities)
+ break;
}
}
- spin_unlock(&rq->lock);
}
EXPORT_SYMBOL(drm_sched_increase_karma);
rq->head_prio = prio;
}
-static void drm_sched_rq_remove_tree_locked(struct drm_sched_entity *entity,
+static void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *entity,
struct drm_sched_rq *rq)
{
lockdep_assert_held(&entity->lock);
}
}
-static void drm_sched_rq_update_tree_locked(struct drm_sched_entity *entity,
+static void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity,
struct drm_sched_rq *rq,
ktime_t ts)
{
lockdep_assert_held(&entity->lock);
lockdep_assert_held(&rq->lock);
- drm_sched_rq_remove_tree_locked(entity, rq);
+ drm_sched_rq_remove_fifo_locked(entity, rq);
entity->oldest_job_waiting = ts;
return runtime;
}
+static ktime_t drm_sched_entity_get_job_ts(struct drm_sched_entity *entity)
+{
+ return drm_sched_entity_update_vruntime(entity);
+}
+
/**
* drm_sched_rq_add_entity - add an entity
* @entity: scheduler entity
+ * @ts: submission timestamp
*
* Adds a scheduler entity to the run queue.
*
* been stopped and cannot be submitted to.
*/
struct drm_gpu_scheduler *
-drm_sched_rq_add_entity(struct drm_sched_entity *entity)
+drm_sched_rq_add_entity(struct drm_sched_entity *entity, ktime_t ts)
{
struct drm_gpu_scheduler *sched;
struct drm_sched_rq *rq;
- ktime_t ts;
/* Add the entity to the run queue */
spin_lock(&entity->lock);
list_add_tail(&entity->list, &rq->entities);
}
- ts = drm_sched_rq_get_min_vruntime(rq);
- ts = drm_sched_entity_restore_vruntime(entity, ts, rq->head_prio);
- drm_sched_rq_update_tree_locked(entity, rq, ts);
+ if (drm_sched_policy == DRM_SCHED_POLICY_FAIR) {
+ ts = drm_sched_rq_get_min_vruntime(rq);
+ ts = drm_sched_entity_restore_vruntime(entity, ts,
+ rq->head_prio);
+ } else if (drm_sched_policy == DRM_SCHED_POLICY_RR) {
+ ts = entity->rr_ts;
+ }
+
+ drm_sched_rq_update_fifo_locked(entity, rq, ts);
spin_unlock(&rq->lock);
spin_unlock(&entity->lock);
atomic_dec(rq->sched->score);
list_del_init(&entity->list);
- drm_sched_rq_remove_tree_locked(entity, rq);
+ drm_sched_rq_remove_fifo_locked(entity, rq);
spin_unlock(&rq->lock);
}
+static ktime_t
+drm_sched_rq_next_rr_ts(struct drm_sched_rq *rq,
+ struct drm_sched_entity *entity)
+{
+ ktime_t ts;
+
+ lockdep_assert_held(&entity->lock);
+ lockdep_assert_held(&rq->lock);
+
+ ts = ktime_add_ns(rq->rr_ts, 1);
+ entity->rr_ts = ts;
+ rq->rr_ts = ts;
+
+ return ts;
+}
+
/**
* drm_sched_rq_pop_entity - pops an entity
* @entity: scheduler entity
if (next_job) {
ktime_t ts;
- ts = drm_sched_entity_update_vruntime(entity);
- drm_sched_rq_update_tree_locked(entity, rq, ts);
+ if (drm_sched_policy == DRM_SCHED_POLICY_FAIR)
+ ts = drm_sched_entity_get_job_ts(entity);
+ else if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
+ ts = next_job->submit_ts;
+ else
+ ts = drm_sched_rq_next_rr_ts(rq, entity);
+
+ drm_sched_rq_update_fifo_locked(entity, rq, ts);
} else {
- ktime_t min_vruntime;
+ drm_sched_rq_remove_fifo_locked(entity, rq);
- drm_sched_rq_remove_tree_locked(entity, rq);
- min_vruntime = drm_sched_rq_get_min_vruntime(rq);
- drm_sched_entity_save_vruntime(entity, min_vruntime);
+ if (drm_sched_policy == DRM_SCHED_POLICY_FAIR) {
+ ktime_t min_vruntime;
+
+ min_vruntime = drm_sched_rq_get_min_vruntime(rq);
+ drm_sched_entity_save_vruntime(entity, min_vruntime);
+ }
}
spin_unlock(&rq->lock);
spin_unlock(&entity->lock);
}
/**
- * drm_sched_select_entity - Select an entity which provides a job to run
+ * drm_sched_rq_select_entity - Select an entity which provides a job to run
* @sched: the gpu scheduler
+ * @rq: scheduler run queue to check.
*
* Find oldest waiting ready entity.
*
* its job; return NULL, if no ready entity was found.
*/
struct drm_sched_entity *
-drm_sched_select_entity(struct drm_gpu_scheduler *sched)
+drm_sched_rq_select_entity(struct drm_gpu_scheduler *sched,
+ struct drm_sched_rq *rq)
{
- struct drm_sched_rq *rq = sched->rq;
struct rb_node *rb;
spin_lock(&rq->lock);
* @lock:
*
* Lock protecting the run-queue (@rq) to which this entity belongs,
- * @priority and the list of schedulers (@sched_list, @num_sched_list).
+ * @priority, the list of schedulers (@sched_list, @num_sched_list) and
+ * the @rr_ts field.
*/
spinlock_t lock;
*/
enum drm_sched_priority priority;
+ /**
+ * @rq_priority: Run-queue priority
+ */
+ enum drm_sched_priority rq_priority;
+
+ /**
+ * @rr_ts:
+ *
+ * Fake timestamp of the last popped job from the entity.
+ */
+ ktime_t rr_ts;
+
/**
* @job_queue: the list of jobs of this entity.
*/
* struct drm_sched_rq - queue of entities to be scheduled.
*
* @sched: the scheduler to which this rq belongs to.
- * @lock: protects @entities, @rb_tree_root and @head_prio.
+ * @lock: protects @entities, @rb_tree_root, @rr_ts and @head_prio.
+ * @rr_ts: monotonically incrementing fake timestamp for RR mode.
* @entities: list of the entities to be scheduled.
* @rb_tree_root: root of time based priority queue of entities for FIFO scheduling
* @head_prio: priority of the top tree element.
spinlock_t lock;
/* Following members are protected by the @lock: */
+ ktime_t rr_ts;
struct list_head entities;
struct rb_root_cached rb_tree_root;
enum drm_sched_priority head_prio;
* to schedule the job.
*/
struct drm_sched_job {
+ /**
+ * @submit_ts:
+ *
+ * When the job was pushed into the entity queue.
+ */
+ ktime_t submit_ts;
+
/**
* @sched:
*
* @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.
- * @rq: Scheduler run queue.
+ * @num_user_rqs: Number of run-queues. This is at most
+ * DRM_SCHED_PRIORITY_COUNT, as there's usually one run-queue per
+ * priority, but could be less.
+ * @num_rqs: Equal to @num_user_rqs for FIFO and RR and 1 for the FAIR policy.
+ * @sched_rq: An allocated array of run-queues of size @num_rqs;
* @job_scheduled: once drm_sched_entity_flush() is called the scheduler
* waits on this wait queue until all the scheduled jobs are
* finished.
atomic_t credit_count;
long timeout;
const char *name;
- struct drm_sched_rq *rq;
+ u32 num_rqs;
+ u32 num_user_rqs;
+ struct drm_sched_rq **sched_rq;
wait_queue_head_t job_scheduled;
atomic64_t job_id_count;
struct workqueue_struct *submit_wq;
projects / thirdparty / kernel / linux.git / commitdiff
