From d5ea093eebf022ec69970107db45dc06318d7e5a Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Thu, 22 Aug 2019 15:01:37 -0400 Subject: dmr/amdgpu: Add system auto reboot to RAS. In case of RAS error allow user configure auto system reboot through ras_ctrl. This is also part of the temproray work around for the RAS hang problem. v4: Use latest kernel API for disk sync. Signed-off-by: Andrey Grodzovsky Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 98ff987ae940..e89aa2dc5c11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -65,6 +65,8 @@ #include "amdgpu_ras.h" #include "amdgpu_pmu.h" +#include + MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin"); @@ -3769,6 +3771,18 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, int i, r = 0; bool in_ras_intr = amdgpu_ras_intr_triggered(); + /* + * Flush RAM to disk so that after reboot + * the user can read log and see why the system rebooted. + */ + if (in_ras_intr && amdgpu_ras_get_context(adev)->reboot) { + + DRM_WARN("Emergency reboot."); + + ksys_sync_helper(); + emergency_restart(); + } + need_full_reset = job_signaled = false; INIT_LIST_HEAD(&device_list); -- cgit v1.2.3