user cases: 1. KFD wraps amdgpu_bo_create, they have no fallback case which is different with amdgpu_gem_object_create. since upstream branch has no amdgpu_amdkfd_gpuvm.c, which need KFD guys add this flag to __alloc_memory_of_gpu: + flags |= AMDGPU_GEM_CREATE_NO_FALLBACK; 2. UMD can specify this flag for their allocation as well if they like. v2: squash in merge conflict fix (Chunming)
Showing the changes to include/uapi (1 of 3 files). Show all
Unified · Split
| @@ -95,6 +95,8 @@ extern "C" { · 94 unmodified lines | ||
| 95 | 95 | #define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID (1 << 6) |
| 96 | 96 | /* Flag that BO sharing will be explicitly synchronized */ |
| 97 | 97 | #define AMDGPU_GEM_CREATE_EXPLICIT_SYNC (1 << 7) |
| 98 | +/* Flag that BO doesn't need fallback */ | |
| 99 | +#define AMDGPU_GEM_CREATE_NO_FALLBACK (1 << 8) | |
| 98 | 100 | |
| 99 | 101 | struct drm_amdgpu_gem_create_in { |
| 100 | 102 | /** the requested memory size */ |