From ff99849b00fef595ae46681ce0c2217a9f834332 Mon Sep 17 00:00:00 2001 From: Jingwen Chen Date: Tue, 20 Jul 2021 18:35:35 +0800 Subject: [PATCH] drm/amd/amdgpu: consider kernel job always not guilty MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit [Why] Currently all timedout job will be considered to be guilty. In SRIOV multi-vf use case, the vf flr happens first and then job time out is found. There can be several jobs timeout during a very small time slice. And if the innocent sdma job time out is found before the real bad job, then the innocent sdma job will be set to guilty. This will lead to a page fault after resubmitting job. [How] If the job is a kernel job, we will always consider it not guilty Reviewed-by: Christian König Signed-off-by: Jingwen Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f8bc670fe3f9..5d2453cc880c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4468,7 +4468,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, amdgpu_fence_driver_force_completion(ring); } - if(job) + if (job && job->vm) drm_sched_increase_karma(&job->base); r = amdgpu_reset_prepare_hwcontext(adev, reset_context); @@ -4932,7 +4932,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress", job ? job->base.id : -1, hive->hive_id); amdgpu_put_xgmi_hive(hive); - if (job) + if (job && job->vm) drm_sched_increase_karma(&job->base); return 0; } @@ -4956,7 +4956,7 @@ 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 && job->vm) drm_sched_increase_karma(&job->base); goto skip_recovery; } -- 2.11.0