drm/amdgpu: fix MGPU fan boost enablement for XGMI reset

MGPU fan boost feature should not be enabled until all the
devices from the same hive are all back from reset.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Evan Quan
2019-06-26 10:53:39 +08:00
committed by Alex Deucher
parent 4b22e7e33f
commit fdafb3597a
3 changed files with 19 additions and 2 deletions

View File

@@ -3559,6 +3559,12 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
if (vram_lost)
amdgpu_device_fill_reset_magic(tmp_adev);
/*
* Add this ASIC as tracked as reset was already
* complete successfully.
*/
amdgpu_register_gpu_instance(tmp_adev);
r = amdgpu_device_ip_late_init(tmp_adev);
if (r)
goto out;
@@ -3693,6 +3699,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
device_list_handle = &device_list;
}
/*
* Mark these ASICs to be reseted as untracked first
* And add them back after reset completed
*/
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head)
amdgpu_unregister_gpu_instance(tmp_adev);
/* block all schedulers and reset given job's ring */
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {