[Intel-xe] [PATCH v4 1/8] fixup! drm/sched: Convert drm scheduler to use a work queue rather than kthread
Thomas Hellström
thomas.hellstrom at linux.intel.com
Fri Jun 16 15:10:01 UTC 2023
On 6/15/23 19:30, Matthew Brost wrote:
> Add run WQ argument to drm_sched_init so user can control run WQ.
>
> Acked-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
> drivers/gpu/drm/etnaviv/etnaviv_sched.c | 2 +-
> drivers/gpu/drm/lima/lima_sched.c | 2 +-
> drivers/gpu/drm/msm/msm_ringbuffer.c | 7 ++++---
> drivers/gpu/drm/panfrost/panfrost_job.c | 2 +-
> drivers/gpu/drm/scheduler/sched_main.c | 4 +++-
> drivers/gpu/drm/v3d/v3d_sched.c | 10 +++++-----
> drivers/gpu/drm/xe/xe_devcoredump_types.h | 1 +
> drivers/gpu/drm/xe/xe_execlist.c | 2 +-
> drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
> include/drm/gpu_scheduler.h | 1 +
> 11 files changed, 20 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 64e7584c5dd2..2e776ece4251 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -2364,7 +2364,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
> break;
> }
>
> - r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
> + r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL,
> ring->num_hw_submission, 0,
> timeout, adev->reset_domain->wq,
> ring->sched_score, ring->name,
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index 1ae87dfd19c4..8486a2923f1b 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -133,7 +133,7 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
> {
> int ret;
>
> - ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops,
> + 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);
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index ff003403fbbc..54f53bece27c 100644
> --- a/drivers/gpu/drm/lima/lima_sched.c
> +++ b/drivers/gpu/drm/lima/lima_sched.c
> @@ -488,7 +488,7 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
>
> INIT_WORK(&pipe->recover_work, lima_sched_recover_work);
>
> - return drm_sched_init(&pipe->base, &lima_sched_ops, 1,
> + 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);
> diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
> index b60199184409..e1cff31f147a 100644
> --- a/drivers/gpu/drm/msm/msm_ringbuffer.c
> +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
> @@ -93,9 +93,10 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
> /* currently managing hangcheck ourselves: */
> sched_timeout = MAX_SCHEDULE_TIMEOUT;
>
> - ret = drm_sched_init(&ring->sched, &msm_sched_ops,
> - num_hw_submissions, 0, sched_timeout,
> - NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);
> + 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);
> if (ret) {
> goto fail;
> }
> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> index dbc597ab46fb..f48b07056a16 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> @@ -815,7 +815,7 @@ int panfrost_job_init(struct panfrost_device *pfdev)
> js->queue[j].fence_context = dma_fence_context_alloc(1);
>
> ret = drm_sched_init(&js->queue[j].sched,
> - &panfrost_sched_ops,
> + &panfrost_sched_ops, NULL,
> nentries, 0,
> msecs_to_jiffies(JOB_TIMEOUT_MS),
> pfdev->reset.wq,
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index db70a57a3a1a..6bc29d509161 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -1178,6 +1178,7 @@ static void drm_sched_main(struct work_struct *w)
> *
> * @sched: scheduler instance
> * @ops: backend operations for this scheduler
> + * @run_wq: workqueue to use for run work. If NULL, the system_wq is used
> * @hw_submission: number of hw submissions that can be in flight
> * @hang_limit: number of times to allow a job to hang before dropping it
> * @timeout: timeout value in jiffies for the scheduler
> @@ -1191,6 +1192,7 @@ static void drm_sched_main(struct work_struct *w)
> */
> int drm_sched_init(struct drm_gpu_scheduler *sched,
> const struct drm_sched_backend_ops *ops,
> + struct workqueue_struct *run_wq,
> unsigned hw_submission, unsigned hang_limit,
> long timeout, struct workqueue_struct *timeout_wq,
> atomic_t *score, const char *name, struct device *dev)
> @@ -1199,9 +1201,9 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
> sched->ops = ops;
> sched->hw_submission_limit = hw_submission;
> sched->name = name;
> + sched->run_wq = run_wq ? : system_wq;
> sched->timeout = timeout;
> sched->timeout_wq = timeout_wq ? : system_wq;
> - sched->run_wq = system_wq; /* FIXME: Let user pass this in */
> sched->hang_limit = hang_limit;
> sched->score = score ? score : &sched->_score;
> sched->dev = dev;
> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
> index 06238e6d7f5c..38e092ea41e6 100644
> --- a/drivers/gpu/drm/v3d/v3d_sched.c
> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
> @@ -388,7 +388,7 @@ v3d_sched_init(struct v3d_dev *v3d)
> int ret;
>
> ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
> - &v3d_bin_sched_ops,
> + &v3d_bin_sched_ops, NULL,
> hw_jobs_limit, job_hang_limit,
> msecs_to_jiffies(hang_limit_ms), NULL,
> NULL, "v3d_bin", v3d->drm.dev);
> @@ -396,7 +396,7 @@ v3d_sched_init(struct v3d_dev *v3d)
> return ret;
>
> ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
> - &v3d_render_sched_ops,
> + &v3d_render_sched_ops, NULL,
> hw_jobs_limit, job_hang_limit,
> msecs_to_jiffies(hang_limit_ms), NULL,
> NULL, "v3d_render", v3d->drm.dev);
> @@ -404,7 +404,7 @@ v3d_sched_init(struct v3d_dev *v3d)
> goto fail;
>
> ret = drm_sched_init(&v3d->queue[V3D_TFU].sched,
> - &v3d_tfu_sched_ops,
> + &v3d_tfu_sched_ops, NULL,
> hw_jobs_limit, job_hang_limit,
> msecs_to_jiffies(hang_limit_ms), NULL,
> NULL, "v3d_tfu", v3d->drm.dev);
> @@ -413,7 +413,7 @@ v3d_sched_init(struct v3d_dev *v3d)
>
> if (v3d_has_csd(v3d)) {
> ret = drm_sched_init(&v3d->queue[V3D_CSD].sched,
> - &v3d_csd_sched_ops,
> + &v3d_csd_sched_ops, NULL,
> hw_jobs_limit, job_hang_limit,
> msecs_to_jiffies(hang_limit_ms), NULL,
> NULL, "v3d_csd", v3d->drm.dev);
> @@ -421,7 +421,7 @@ v3d_sched_init(struct v3d_dev *v3d)
> goto fail;
>
> ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
> - &v3d_cache_clean_sched_ops,
> + &v3d_cache_clean_sched_ops, NULL,
> hw_jobs_limit, job_hang_limit,
> msecs_to_jiffies(hang_limit_ms), NULL,
> NULL, "v3d_cache_clean", v3d->drm.dev);
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
> index c0d711eb6ab3..cc3ff3ac47ff 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
> +++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
> @@ -11,6 +11,7 @@
>
> #include "xe_hw_engine_types.h"
>
> +struct xe_ct;
> struct xe_device;
>
> /**
> diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
> index 5d2d26e361b9..f0eb8bb277ce 100644
> --- a/drivers/gpu/drm/xe/xe_execlist.c
> +++ b/drivers/gpu/drm/xe/xe_execlist.c
> @@ -336,7 +336,7 @@ static int execlist_engine_init(struct xe_engine *e)
>
> exl->engine = e;
>
> - err = drm_sched_init(&exl->sched, &drm_sched_ops,
> + err = drm_sched_init(&exl->sched, &drm_sched_ops, NULL,
> e->lrc[0].ring.size / MAX_JOB_SIZE_BYTES,
> XE_SCHED_HANG_LIMIT, XE_SCHED_JOB_TIMEOUT,
> NULL, NULL, e->hwe->name,
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index b209e4c2a3a9..5c9a6866bd3d 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1064,7 +1064,7 @@ static int guc_engine_init(struct xe_engine *e)
> init_waitqueue_head(&ge->suspend_wait);
>
> timeout = xe_vm_no_dma_fences(e->vm) ? MAX_SCHEDULE_TIMEOUT : HZ * 5;
> - err = drm_sched_init(&ge->sched, &drm_sched_ops,
> + err = drm_sched_init(&ge->sched, &drm_sched_ops, NULL,
> e->lrc[0].ring.size / MAX_JOB_SIZE_BYTES,
> 64, timeout, guc_to_gt(guc)->ordered_wq, NULL,
> e->name, gt_to_xe(e->gt)->drm.dev);
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index 79311df9dd09..419c0446edd7 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -547,6 +547,7 @@ struct drm_gpu_scheduler {
>
> int drm_sched_init(struct drm_gpu_scheduler *sched,
> const struct drm_sched_backend_ops *ops,
> + struct workqueue_struct *run_wq,
> uint32_t hw_submission, unsigned hang_limit,
> long timeout, struct workqueue_struct *timeout_wq,
> atomic_t *score, const char *name, struct device *dev);
More information about the Intel-xe
mailing list