diff options
| author | David Francis <David.Francis@amd.com> | 2023-10-12 10:35:20 -0400 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-10-27 14:15:16 -0400 |
| commit | 142262a1c02ad4d334ca1152dc4a0f6db3ef3bfc (patch) | |
| tree | c999569dfc17380436eab0628c41b8aa4590281e /drivers/gpu/drm/amd/amdkfd | |
| parent | a395f7ffcebe59477d80f049889cb652d80db040 (diff) | |
drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
On gfx943 APU, EXT_COHERENT should give MTYPE_CC for local and
MTYPE_UC for nonlocal memory.
On NUMA systems, local memory gets the local mtype, set by an
override callback. If EXT_COHERENT is set, memory will be set as
MTYPE_UC by default, with local memory MTYPE_CC.
Add an option in the override function for this case, and
add a check to ensure it is not used on UNCACHED memory.
V2: Combined APU and NUMA code into one patch
V3: Fixed a potential nullptr in amdgpu_vm_bo_update
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 3560a5a58090..e67d06a42809 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1282,7 +1282,7 @@ svm_range_get_pte_flags(struct kfd_node *node, if (num_possible_nodes() <= 1) mapping_flags |= mtype_local; else - mapping_flags |= AMDGPU_VM_MTYPE_NC; + mapping_flags |= ext_coherent ? AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; /* system memory accessed by the dGPU */ } else { mapping_flags |= AMDGPU_VM_MTYPE_UC; @@ -1317,7 +1317,7 @@ svm_range_unmap_from_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, pr_debug("[0x%llx 0x%llx]\n", start, last); - return amdgpu_vm_update_range(adev, vm, false, true, true, NULL, start, + return amdgpu_vm_update_range(adev, vm, false, true, true, false, NULL, start, last, init_pte_value, 0, 0, NULL, NULL, fence); } @@ -1424,8 +1424,8 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange, * different memory partition based on fpfn/lpfn, we should use * same vm_manager.vram_base_offset regardless memory partition. */ - r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb, NULL, - last_start, prange->start + i, + r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb, true, + NULL, last_start, prange->start + i, pte_flags, (last_start - prange->start) << PAGE_SHIFT, bo_adev ? bo_adev->vm_manager.vram_base_offset : 0, |