From b29cd4677d7b29381b851a24cedb6d7cd15f747b Mon Sep 17 00:00:00 2001 From: Bojan Radovic Date: Thu, 20 Aug 2020 16:34:05 +0200 Subject: drm/amdgpu: Fix for timeout after TDR Adding update of guilty flag for job that caused hang in amdgpu_device_gpu_recover Change-Id: Ia6db7231d1aa47b4ad6223e66161bc7e35207511 Signed-off-by: Bojan Radovic --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d04526f2a0ff..c34b1a6751b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4542,6 +4542,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, goto skip_hw_reset; } + if(job) + drm_sched_increase_karma(&job->base); + retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { r = amdgpu_device_pre_asic_reset(tmp_adev, -- cgit v1.2.3