drm/amdgpu: put the SMC into the proper state on reset/unload

When doing a GPU reset or unloading the driver, we need to
put the SMU into the apprpriate state for the re-init after
the reset or unload to reliably work.

I don't think this is necessary for BACO because the SMU actually
controls the BACO state to it needs to be active.

For suspend (S3), the asic is put into D3 so the SMU would be
powered down so I don't think we need to put the SMU into
any special state.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 5cbed256f006486206b5716a148cf8343ea3fac1..c87dfdb8aedb7d889c7948f52a27a6dcfbb53b31 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -990,6 +990,7 @@ struct amdgpu_device {
        /* record last mm index being written through WREG32*/
        unsigned long last_mm_index;
        bool                            in_gpu_reset;
+       enum pp_mp1_state               mp1_state;
        struct mutex  lock_reset;
        struct amdgpu_doorbell_index doorbell_index;
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 14a9169446f57307c593419d425b717e879bed0a..2081649f49ca8829d2df2bb6643a649951bcc6d0 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2175,6 +2175,21 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
                        DRM_ERROR("suspend of IP block <%s> failed %d\n",
                                  adev->ip_blocks[i].version->funcs->name, r);
                }
+               /* handle putting the SMC in the appropriate state */
+               if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
+                       if (is_support_sw_smu(adev)) {
+                               /* todo */
+                       } else if (adev->powerplay.pp_funcs &&
+                                  adev->powerplay.pp_funcs->set_mp1_state) {
+                               r = adev->powerplay.pp_funcs->set_mp1_state(
+                                       adev->powerplay.pp_handle,
+                                       adev->mp1_state);
+                               if (r) {
+                                       DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
+                                                 adev->mp1_state, r);
+                               }
+                       }
+               }
        }
 
        return 0;
@@ -3640,6 +3655,17 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
 
        atomic_inc(&adev->gpu_reset_counter);
        adev->in_gpu_reset = 1;
+       switch (amdgpu_asic_reset_method(adev)) {
+       case AMD_RESET_METHOD_MODE1:
+               adev->mp1_state = PP_MP1_STATE_SHUTDOWN;
+               break;
+       case AMD_RESET_METHOD_MODE2:
+               adev->mp1_state = PP_MP1_STATE_RESET;
+               break;
+       default:
+               adev->mp1_state = PP_MP1_STATE_NONE;
+               break;
+       }
        /* Block kfd: SRIOV would do it separately */
        if (!amdgpu_sriov_vf(adev))
                 amdgpu_amdkfd_pre_reset(adev);
@@ -3653,6 +3679,7 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
        if (!amdgpu_sriov_vf(adev))
                 amdgpu_amdkfd_post_reset(adev);
        amdgpu_vf_error_trans_all(adev);
+       adev->mp1_state = PP_MP1_STATE_NONE;
        adev->in_gpu_reset = 0;
        mutex_unlock(&adev->lock_reset);
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 56f807757d2c288b9934c463ebcc03ca97441681..e3e09e6d7f4223ad6990690989415b2b8633ee6e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1096,7 +1096,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
         * unfortunately we can't detect certain
         * hypervisors so just do this all the time.
         */
+       adev->mp1_state = PP_MP1_STATE_UNLOAD;
        amdgpu_device_ip_suspend(adev);
+       adev->mp1_state = PP_MP1_STATE_NONE;
 }
 
 static int amdgpu_pmops_suspend(struct device *dev)