diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 47aac179951a..c268bd033064 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4749,6 +4749,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, struct amdgpu_device *tmp_adev = NULL; bool need_full_reset, skip_hw_reset, vram_lost = false; int r = 0; + bool gpu_reset_for_dev_remove = 0; /* Try reset handler method first */ tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, @@ -4768,6 +4769,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags); + gpu_reset_for_dev_remove = + test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + /* * ASIC reset has to be done on all XGMI hive nodes ASAP * to allow proper links negotiation in FW (within 1 sec) @@ -4812,6 +4817,18 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, amdgpu_ras_intr_cleared(); } + /* Since the mode1 reset affects base ip blocks, the + * phase1 ip blocks need to be resumed. Otherwise there + * will be a BIOS signature error and the psp bootloader + * can't load kdb on the next amdgpu install. + */ + if (gpu_reset_for_dev_remove) { + list_for_each_entry(tmp_adev, device_list_handle, reset_list) + amdgpu_device_ip_resume_phase1(tmp_adev); + + goto end; + } + list_for_each_entry(tmp_adev, device_list_handle, reset_list) { if (need_full_reset) { /* post card */ @@ -5134,6 +5151,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, bool need_emergency_restart = false; bool audio_suspended = false; int tmp_vram_lost_counter; + bool gpu_reset_for_dev_remove = false; + + gpu_reset_for_dev_remove = + test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); /* * Special case: RAS triggered and full reset isn't supported @@ -5253,6 +5275,10 @@ 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) { + if (gpu_reset_for_dev_remove) { + /* Workaroud for ASICs need to disable SMC first */ + amdgpu_device_smu_fini_early(tmp_adev); + } r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context); /*TODO Should we stop ?*/ if (r) { @@ -5286,6 +5312,9 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ adev->asic_reset_res = 0; goto retry; } + + if (!r && gpu_reset_for_dev_remove) + goto recover_end; } skip_hw_reset: @@ -5359,6 +5388,7 @@ skip_sched_resume: amdgpu_device_unset_mp1_state(tmp_adev); } +recover_end: tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, reset_list); amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); |