[PATCH] drm/scheduler re-insert Bailing job to avoid memleak

[Alex Deucher]

+dri-devel

Please be sure to cc dri-devel when you send out gpu scheduler patches.

On Thu, Mar 11, 2021 at 10:57 PM Jack Zhang <Jack.Zhang1 at amd.com> wrote:
>
> re-insert Bailing jobs to avoid memory leak.
>
> Signed-off-by: Jack Zhang <Jack.Zhang1 at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    | 8 ++++++--
>  drivers/gpu/drm/scheduler/sched_main.c     | 8 +++++++-
>  include/drm/gpu_scheduler.h                | 1 +
>  4 files changed, 17 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 79b9cc73763f..86463b0f936e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -4815,8 +4815,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>                                         job ? job->base.id : -1);
>
>                 /* even we skipped this reset, still need to set the job to guilty */
> -               if (job)
> +               if (job) {
>                         drm_sched_increase_karma(&job->base);
> +                       r = DRM_GPU_SCHED_STAT_BAILING;
> +               }
>                 goto skip_recovery;
>         }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 759b34799221..41390bdacd9e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -34,6 +34,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>         struct amdgpu_job *job = to_amdgpu_job(s_job);
>         struct amdgpu_task_info ti;
>         struct amdgpu_device *adev = ring->adev;
> +       int ret;
>
>         memset(&ti, 0, sizeof(struct amdgpu_task_info));
>
> @@ -52,8 +53,11 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>                   ti.process_name, ti.tgid, ti.task_name, ti.pid);
>
>         if (amdgpu_device_should_recover_gpu(ring->adev)) {
> -               amdgpu_device_gpu_recover(ring->adev, job);
> -               return DRM_GPU_SCHED_STAT_NOMINAL;
> +               ret = amdgpu_device_gpu_recover(ring->adev, job);
> +               if (ret == DRM_GPU_SCHED_STAT_BAILING)
> +                       return DRM_GPU_SCHED_STAT_BAILING;
> +               else
> +                       return DRM_GPU_SCHED_STAT_NOMINAL;
>         } else {
>                 drm_sched_suspend_timeout(&ring->sched);
>                 if (amdgpu_sriov_vf(adev))
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 92d8de24d0a1..a44f621fb5c4 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -314,6 +314,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
>  {
>         struct drm_gpu_scheduler *sched;
>         struct drm_sched_job *job;
> +       int ret;
>
>         sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
>
> @@ -331,8 +332,13 @@ static void drm_sched_job_timedout(struct work_struct *work)
>                 list_del_init(&job->list);
>                 spin_unlock(&sched->job_list_lock);
>
> -               job->sched->ops->timedout_job(job);
> +               ret = job->sched->ops->timedout_job(job);
>
> +               if (ret == DRM_GPU_SCHED_STAT_BAILING) {
> +                       spin_lock(&sched->job_list_lock);
> +                       list_add(&job->node, &sched->ring_mirror_list);
> +                       spin_unlock(&sched->job_list_lock);
> +               }
>                 /*
>                  * Guilty job did complete and hence needs to be manually removed
>                  * See drm_sched_stop doc.
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index 4ea8606d91fe..8093ac2427ef 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -210,6 +210,7 @@ enum drm_gpu_sched_stat {
>         DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */
>         DRM_GPU_SCHED_STAT_NOMINAL,
>         DRM_GPU_SCHED_STAT_ENODEV,
> +       DRM_GPU_SCHED_STAT_BAILING,
>  };
>
>  /**
> --
> 2.25.1
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx