diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 27 |
1 files changed, 11 insertions, 16 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 64f37713b270..c4a6fe3070b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4668,7 +4668,6 @@ static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev) int i; lockdep_assert_held(&adev->reset_domain->sem); - dump_stack(); for (i = 0; i < adev->num_regs; i++) { adev->reset_dump_reg_value[i] = RREG32(adev->reset_dump_reg_list[i]); @@ -5109,7 +5108,8 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev) */ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, - struct amdgpu_job *job) + struct amdgpu_job *job, + struct amdgpu_reset_context *reset_context) { struct list_head device_list, *device_list_handle = NULL; bool job_signaled = false; @@ -5119,9 +5119,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, bool need_emergency_restart = false; bool audio_suspended = false; int tmp_vram_lost_counter; - struct amdgpu_reset_context reset_context; - - memset(&reset_context, 0, sizeof(reset_context)); /* * Special case: RAS triggered and full reset isn't supported @@ -5147,12 +5144,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, if (hive) mutex_lock(&hive->hive_lock); - reset_context.method = AMD_RESET_METHOD_NONE; - reset_context.reset_req_dev = adev; - reset_context.job = job; - reset_context.hive = hive; - clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); - + reset_context->job = job; + reset_context->hive = hive; /* * Build list of devices to reset. * In case we are in XGMI hive mode, resort the device list @@ -5236,8 +5229,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * * job->base holds a reference to parent fence */ - if (job && (job->hw_fence.ops != NULL) && - dma_fence_is_signaled(&job->hw_fence)) { + if (job && dma_fence_is_signaled(&job->hw_fence)) { job_signaled = true; dev_info(adev->dev, "Guilty job already signaled, skipping HW reset"); goto skip_hw_reset; @@ -5245,7 +5237,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - r = amdgpu_device_pre_asic_reset(tmp_adev, &reset_context); + r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context); /*TODO Should we stop ?*/ if (r) { dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ", @@ -5272,7 +5264,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2)) amdgpu_ras_resume(adev); } else { - r = amdgpu_do_asic_reset(device_list_handle, &reset_context); + r = amdgpu_do_asic_reset(device_list_handle, reset_context); if (r && r == -EAGAIN) goto retry; } @@ -5292,7 +5284,7 @@ skip_hw_reset: if (amdgpu_gpu_recovery == 2 && !(tmp_vram_lost_counter < atomic_read(&adev->vram_lost_counter))) amdgpu_device_recheck_guilty_jobs( - tmp_adev, device_list_handle, &reset_context); + tmp_adev, device_list_handle, reset_context); for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = tmp_adev->rings[i]; @@ -5307,6 +5299,9 @@ skip_hw_reset: drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res); } + if (adev->enable_mes) + amdgpu_mes_self_test(tmp_adev); + if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) { drm_helper_resume_force_mode(adev_to_drm(tmp_adev)); } |