diff options
| author | YiPeng Chai <YiPeng.Chai@amd.com> | 2022-11-08 12:11:18 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2022-11-18 02:07:52 +0300 |
| commit | 1a11a65d5395ccdcd07f19a75da82a3d74c368dd (patch) | |
| tree | 75f8c3b4b464fbc2fd8f59764860cb6855a38a76 /drivers/gpu/drm | |
| parent | 64a3dbb06ad88d89a0958ccafc4f01611657f641 (diff) | |
| download | linux-1a11a65d5395ccdcd07f19a75da82a3d74c368dd.tar.xz | |
drm/amdgpu: Enable mode-1 reset for RAS recovery in fatal error mode
The patch is enabling mode-1 reset for RAS recovery in fatal error mode.
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 |
2 files changed, 10 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 0f5cbc70682a..3d5d5d49cfab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4593,6 +4593,10 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) if (amdgpu_gpu_recovery == 0) goto disabled; + /* Skip soft reset check in fatal error mode */ + if (!amdgpu_ras_is_poison_mode_supported(adev)) + return true; + if (!amdgpu_device_ip_check_soft_reset(adev)) { dev_info(adev->dev,"Timeout, but no hardware hang detected.\n"); return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 693bce07eb46..8fca3cc273e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1948,7 +1948,12 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) reset_context.method = AMD_RESET_METHOD_NONE; reset_context.reset_req_dev = adev; - clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + + /* Perform full reset in fatal error mode */ + if (!amdgpu_ras_is_poison_mode_supported(ras->adev)) + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + else + clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context); } |