diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 2def3448ffd91b33c05225fd08eb90aecf847b10..22e2ed21d45953271d903f9e987380e390766b40 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1191,7 +1191,7 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM; bool coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT; bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED; - /* TODO: memory partitions struct amdgpu_vm *vm = mapping->bo_va->base.vm;*/ + struct amdgpu_vm *vm = mapping->bo_va->base.vm; unsigned int mtype_local, mtype; bool snoop = false; bool is_local; @@ -1252,8 +1252,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, } is_local = (!is_vram && (adev->flags & AMD_IS_APU) && num_possible_nodes() <= 1) || - (is_vram && adev == bo_adev /* TODO: memory partitions && - bo->mem_id == vm->mem_id*/); + (is_vram && adev == bo_adev && + bo->mem_id == vm->mem_id); snoop = true; if (uncached) { mtype = MTYPE_UC; @@ -1340,13 +1340,12 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev, return; } - /* TODO: memory partitions. mem_id is hard-coded to 0 for now. - * FIXME: Only supported on native mode for now. For carve-out, the + /* FIXME: Only supported on native mode for now. For carve-out, the * NUMA affinity of the GPU/VM needs to come from the PCI info because * memory partitions are not associated with different NUMA nodes. */ - if (adev->gmc.is_app_apu) { - local_node = adev->gmc.mem_partitions[/*vm->mem_id*/0].numa.node; + if (adev->gmc.is_app_apu && vm->mem_id >= 0) { + local_node = adev->gmc.mem_partitions[vm->mem_id].numa.node; } else { dev_dbg(adev->dev, "Only native mode APU is supported.\n"); return; @@ -1361,7 +1360,7 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev, } nid = pfn_to_nid(addr >> PAGE_SHIFT); dev_dbg(adev->dev, "vm->mem_id=%d, local_node=%d, nid=%d\n", - /*vm->mem_id*/0, local_node, nid); + vm->mem_id, local_node, nid); if (nid == local_node) { uint64_t old_flags = *flags; unsigned int mtype_local = MTYPE_RW; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f6a886d9e9027861accc3abc9259b85bee3ad169..8b5453fd304a81bb300eb15940286cbe2082ee41 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1202,8 +1202,8 @@ svm_range_get_pte_flags(struct kfd_node *node, mapping_flags |= AMDGPU_VM_MTYPE_UC; } else if (domain == SVM_RANGE_VRAM_DOMAIN) { /* local HBM region close to partition */ - if (bo_node->adev == node->adev /* TODO: memory partitions && - bo_node->mem_id == node->mem_id*/) + if (bo_node->adev == node->adev && + (!bo_node->xcp || !node->xcp || bo_node->xcp->mem_id == node->xcp->mem_id)) mapping_flags |= mtype_local; /* local HBM region far from partition or remote XGMI GPU */ else if (svm_nodes_in_same_hive(bo_node, node)) @@ -1357,8 +1357,9 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange, (last_domain == SVM_RANGE_VRAM_DOMAIN) ? 1 : 0, pte_flags); - /* TODO: we still need to determine the vm_manager.vram_base_offset based on - * the memory partition. + /* For dGPU mode, we use same vm_manager to allocate VRAM for + * 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,