dlan17/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drm/amdgpu: Add support to change mtype for 2nd part of gart BOs on GFX9

Browse Source 
This change prepares for a workaround in amdkfd for a GFX9 HW bug. It
requires the control stack memory of compute queues, which is allocated
from the second page of MQD gart BOs, to have mtype NC, rather than
the default UC.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Yong Zhao
2018-05-15 13:44:26 -05:00
committed by Alex Deucher
parent 8eb7719813
commit 959a2091fa
3 changed files with 51 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/uapi/drm/amdgpu_drm.h
+4
View File
@@ -101,6 +101,10 @@ extern "C" {
#define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID (1 << 6)
/* Flag that BO sharing will be explicitly synchronized */
#define AMDGPU_GEM_CREATE_EXPLICIT_SYNC (1 << 7)
/* Flag that indicates allocating MQD gart on GFX9, where the mtype
* for the second page onward should be set to NC.
*/
#define AMDGPU_GEM_CREATE_MQD_GFX9 (1 << 8)
struct drm_amdgpu_gem_create_in {
/** the requested memory size */