From: xinhui pan Date: Thu, 4 Jul 2019 02:54:58 +0000 (+0800) Subject: drm/amdgpu: Disable ras features on all IPs before gpu reset X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=f1c1314be4297183937fc2eab994be688425e328;p=linux.git drm/amdgpu: Disable ras features on all IPs before gpu reset Perform a ras_suspend to disable ras on all IPs to workaround some ROCm stability issue. Signed-off-by: xinhui pan Acked-by: Andrey Grodzovsky Signed-off-by: Alex Deucher --- diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 802809aa801d2..b4616853f4610 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3719,6 +3719,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, /* block all schedulers and reset given job's ring */ list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { + /* disable ras on ALL IPs */ + if (amdgpu_device_ip_need_full_reset(tmp_adev)) + amdgpu_ras_suspend(tmp_adev); + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = tmp_adev->rings[i];