From the design it looks good to me, but I really don't know much about
XGMI.
When you want to simplify it a bit, I'm pretty sure the calls to
ttm_bo_lock_delayed_workqueue()/ttm_bo_unlock_delayed_workqueue() can
just be dropped.
They are copy & pasted over from radeon and on amdgpu there isn't any
reason for that any more.
Christian.
Am 28.11.18 um 16:07 schrieb Grodzovsky, Andrey:
Ping...
Andrey
On 11/27/2018 01:37 PM, Andrey Grodzovsky wrote:
This set of patches adds support to reset entire XGMI hive
when reset is required.
Patches 1-2 refactoring a bit the XGMI infrastructure as
preparaton for the actual hive reset change.
Patch 5 is GPU reset/recovery refactored to support XGMI
hive reset.
Andrey Grodzovsky (3):
drm/amdgpu: Refactor amdgpu_xgmi_add_device v3
drm/amdgpu: Expose hive adev list and xgmi_mutex v3
drm/amdgpu: Refactor GPU reset for XGMI hive case v3
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 9 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 376 ++++++++++++++++++++---------
drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 68 +++---
drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h | 39 +++
4 files changed, 343 insertions(+), 149 deletions(-)
create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx