This patch is in preparation for a better load balancing in scheduler. It allows us to associate entities with the run queues instead of binding them to a scheduler.
Signed-off-by: Nayan Deshmukh nayan26deshmukh@gmail.com --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 ++++-- include/drm/gpu_scheduler.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 7d2560699b84..429b1328653a 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb); * * Initializes a scheduler runqueue. */ -static void drm_sched_rq_init(struct drm_sched_rq *rq) +static void drm_sched_rq_init(struct drm_gpu_scheduler *sched, + struct drm_sched_rq *rq) { spin_lock_init(&rq->lock); INIT_LIST_HEAD(&rq->entities); rq->current_entity = NULL; + rq->sched = sched; }
/** @@ -926,7 +928,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->timeout = timeout; sched->hang_limit = hang_limit; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++) - drm_sched_rq_init(&sched->sched_rq[i]); + drm_sched_rq_init(sched, &sched->sched_rq[i]);
init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 4214ceb71c05..43e93d6077cf 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -93,6 +93,7 @@ struct drm_sched_entity { * struct drm_sched_rq - queue of entities to be scheduled. * * @lock: to modify the entities list. + * @sched: the scheduler to which this rq belongs to. * @entities: list of the entities to be scheduled. * @current_entity: the entity which is to be scheduled. * @@ -102,6 +103,7 @@ struct drm_sched_entity { */ struct drm_sched_rq { spinlock_t lock; + struct drm_gpu_scheduler *sched; struct list_head entities; struct drm_sched_entity *current_entity; };
replace run queue by a list of run queues and remove the sched arg as that is part of run queue itself
Signed-off-by: Nayan Deshmukh nayan26deshmukh@gmail.com Reviewed-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 +-- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 4 ++-- drivers/gpu/drm/etnaviv/etnaviv_drv.c | 8 ++++---- drivers/gpu/drm/scheduler/gpu_scheduler.c | 20 ++++++++++++-------- drivers/gpu/drm/v3d/v3d_drv.c | 7 +++---- include/drm/gpu_scheduler.h | 6 +++--- 11 files changed, 33 insertions(+), 33 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 0120b24fae1b..83e3b320a793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -90,8 +90,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, if (ring == &adev->gfx.kiq.ring) continue;
- r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity, - rq, &ctx->guilty); + r = drm_sched_entity_init(&ctx->rings[i].entity, + &rq, 1, &ctx->guilty); if (r) goto failed; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 0246cb87d9e4..360d6b82c3c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -140,8 +140,7 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
ring = adev->mman.buffer_funcs_ring; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL]; - r = drm_sched_entity_init(&ring->sched, &adev->mman.entity, - rq, NULL); + r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL); if (r) { DRM_ERROR("Failed setting up TTM BO move run queue.\n"); goto error_entity; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 0b46ea1c6290..0d8c57fc3d09 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -266,8 +266,8 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
ring = &adev->uvd.inst[j].ring; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst[j].entity, &rq, + 1, NULL); if (r != 0) { DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index b0dcdfd85f5b..c0790e4c5454 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -190,8 +190,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
ring = &adev->vce.ring[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->vce.entity, - rq, NULL); + r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL); if (r != 0) { DRM_ERROR("Failed setting up VCE run queue.\n"); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 712af5c1a5d6..fb7da0740ad8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2562,8 +2562,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, ring_instance %= adev->vm_manager.vm_pte_num_rings; ring = adev->vm_manager.vm_pte_rings[ring_instance]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL]; - r = drm_sched_entity_init(&ring->sched, &vm->entity, - rq, NULL); + r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL); if (r) return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 8ee1c2eaaa14..da38aa2f3d13 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -429,8 +429,8 @@ static int uvd_v6_0_sw_init(void *handle) struct drm_sched_rq *rq; ring = &adev->uvd.inst->ring_enc[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst->entity_enc, + &rq, 1, NULL); if (r) { DRM_ERROR("Failed setting up UVD ENC run queue.\n"); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index ba244d3b74db..69221430aa38 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -431,8 +431,8 @@ static int uvd_v7_0_sw_init(void *handle) for (j = 0; j < adev->uvd.num_uvd_inst; j++) { ring = &adev->uvd.inst[j].ring_enc[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst[j].entity_enc, + &rq, 1, NULL); if (r) { DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j); return r; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 45bfdf4cc107..36414ba56b22 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -49,12 +49,12 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
for (i = 0; i < ETNA_MAX_PIPES; i++) { struct etnaviv_gpu *gpu = priv->gpu[i]; + struct drm_sched_rq *rq;
if (gpu) { - drm_sched_entity_init(&gpu->sched, - &ctx->sched_entity[i], - &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL], - NULL); + rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + drm_sched_entity_init(&ctx->sched_entity[i], + &rq, 1, NULL); } }
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 429b1328653a..16bf446aa6b3 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -162,26 +162,30 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq) * drm_sched_entity_init - Init a context entity used by scheduler when * submit to HW ring. * - * @sched: scheduler instance * @entity: scheduler entity to init - * @rq: the run queue this entity belongs + * @rq_list: the list of run queue on which jobs from this + * entity can be submitted + * @num_rq_list: number of run queue in rq_list * @guilty: atomic_t set to 1 when a job on this queue * is found to be guilty causing a timeout * + * Note: the rq_list should have atleast one element to schedule + * the entity + * * Returns 0 on success or a negative error code on failure. */ -int drm_sched_entity_init(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, - struct drm_sched_rq *rq, +int drm_sched_entity_init(struct drm_sched_entity *entity, + struct drm_sched_rq **rq_list, + unsigned int num_rq_list, atomic_t *guilty) { - if (!(sched && entity && rq)) + if (!(entity && rq_list && num_rq_list > 0 && rq_list[0])) return -EINVAL;
memset(entity, 0, sizeof(struct drm_sched_entity)); INIT_LIST_HEAD(&entity->list); - entity->rq = rq; - entity->sched = sched; + entity->rq = rq_list[0]; + entity->sched = rq_list[0]->sched; entity->guilty = guilty; entity->last_scheduled = NULL;
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 567f7d46d912..1dceba2b42fd 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -123,6 +123,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file) { struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv; + struct drm_sched_rq *rq; int i;
v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL); @@ -132,10 +133,8 @@ v3d_open(struct drm_device *dev, struct drm_file *file) v3d_priv->v3d = v3d;
for (i = 0; i < V3D_MAX_QUEUES; i++) { - drm_sched_entity_init(&v3d->queue[i].sched, - &v3d_priv->sched_entity[i], - &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL], - NULL); + rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL); }
file->driver_priv = v3d_priv; diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 43e93d6077cf..2205e89722f6 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -282,9 +282,9 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const char *name); void drm_sched_fini(struct drm_gpu_scheduler *sched);
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, - struct drm_sched_rq *rq, +int drm_sched_entity_init(struct drm_sched_entity *entity, + struct drm_sched_rq **rq_list, + unsigned int num_rq_list, atomic_t *guilty); long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, long timeout);
I forgot to add these: On Fri, Jul 13, 2018 at 3:21 PM Nayan Deshmukh nayan26deshmukh@gmail.com wrote:
This patch is in preparation for a better load balancing in scheduler. It allows us to associate entities with the run queues instead of binding them to a scheduler.
Signed-off-by: Nayan Deshmukh nayan26deshmukh@gmail.com
Reviewed-by: Christian König christian.koenig@amd.com Acked-by: Eric Anholt eric@anholt.net
drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 ++++-- include/drm/gpu_scheduler.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 7d2560699b84..429b1328653a 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
- Initializes a scheduler runqueue.
*/ -static void drm_sched_rq_init(struct drm_sched_rq *rq) +static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
struct drm_sched_rq *rq){ spin_lock_init(&rq->lock); INIT_LIST_HEAD(&rq->entities); rq->current_entity = NULL;
rq->sched = sched;}
/** @@ -926,7 +928,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->timeout = timeout; sched->hang_limit = hang_limit; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
drm_sched_rq_init(&sched->sched_rq[i]);
drm_sched_rq_init(sched, &sched->sched_rq[i]); init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled);diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 4214ceb71c05..43e93d6077cf 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -93,6 +93,7 @@ struct drm_sched_entity {
- struct drm_sched_rq - queue of entities to be scheduled.
- @lock: to modify the entities list.
- @sched: the scheduler to which this rq belongs to.
- @entities: list of the entities to be scheduled.
- @current_entity: the entity which is to be scheduled.
@@ -102,6 +103,7 @@ struct drm_sched_entity { */ struct drm_sched_rq { spinlock_t lock;
struct drm_gpu_scheduler *sched; struct list_head entities; struct drm_sched_entity *current_entity;};
2.14.3
Am 13.07.2018 um 15:40 schrieb Nayan Deshmukh:
I forgot to add these:
Not a problem at all. It is actually my job to do this while committing the patches.
BTW: I've pushed you patches to amd-staging-drm-next just a few minutes ago. Thanks for the help.
I'm preparing quite a cleanup for amdgpu which should make your live easier, but still no idea why the scheduler hangs when we try to load balance jobs.
Regards, Christian.
On Fri, Jul 13, 2018 at 3:21 PM Nayan Deshmukh nayan26deshmukh@gmail.com wrote:
This patch is in preparation for a better load balancing in scheduler. It allows us to associate entities with the run queues instead of binding them to a scheduler.
Signed-off-by: Nayan Deshmukh nayan26deshmukh@gmail.com
Reviewed-by: Christian König christian.koenig@amd.com Acked-by: Eric Anholt eric@anholt.net
drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 ++++-- include/drm/gpu_scheduler.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 7d2560699b84..429b1328653a 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
- Initializes a scheduler runqueue.
*/ -static void drm_sched_rq_init(struct drm_sched_rq *rq) +static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
struct drm_sched_rq *rq){ spin_lock_init(&rq->lock); INIT_LIST_HEAD(&rq->entities); rq->current_entity = NULL;
rq->sched = sched;}
/**
@@ -926,7 +928,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->timeout = timeout; sched->hang_limit = hang_limit; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
drm_sched_rq_init(&sched->sched_rq[i]);
drm_sched_rq_init(sched, &sched->sched_rq[i]); init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled);diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 4214ceb71c05..43e93d6077cf 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -93,6 +93,7 @@ struct drm_sched_entity {
- struct drm_sched_rq - queue of entities to be scheduled.
- @lock: to modify the entities list.
- @sched: the scheduler to which this rq belongs to.
- @entities: list of the entities to be scheduled.
- @current_entity: the entity which is to be scheduled.
@@ -102,6 +103,7 @@ struct drm_sched_entity { */ struct drm_sched_rq { spinlock_t lock;
struct drm_gpu_scheduler *sched; struct list_head entities; struct drm_sched_entity *current_entity;-- 2.14.3
dri-devel@lists.freedesktop.org
-
Christian König -
Nayan Deshmukh