Re: [PATCH 1/1] drm/amdgpu: Fix compute VM BO params after rebase v2
Am 06.09.2018 um 16:32 schrieb Felix Kuehling: The intent of two commits was lost in the last rebase: 810955b drm/amdgpu: Fix acquiring VM on large-BAR systems b5d21aa drm/amdgpu: Don't use shadow BO for compute context This commit restores the original behaviour: * Don't set AMDGPU_GEM_CREATE_NO_CPU_ACCESS for page directories to allow them to be reused for compute VMs * Don't create shadow BOs for page tables in compute VMs v2: move more logic into amdgpu_vm_bo_param Signed-off-by: Felix Kuehling Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ea5e277..1d7e3c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -595,9 +595,8 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm, AMDGPU_GEM_CREATE_CPU_GTT_USWC; if (vm->use_cpu_for_update) bp->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - else - bp->flags |= AMDGPU_GEM_CREATE_SHADOW | - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; + else if (!vm->root.base.bo || vm->root.base.bo->shadow) + bp->flags |= AMDGPU_GEM_CREATE_SHADOW; bp->type = ttm_bo_type_kernel; if (vm->root.base.bo) bp->resv = vm->root.base.bo->tbo.resv; @@ -2749,6 +2748,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, vm->last_update = NULL; amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, ); + if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) + bp.flags &= ~AMDGPU_GEM_CREATE_SHADOW; r = amdgpu_bo_create(adev, , ); if (r) goto error_free_sched_entity; ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[PATCH 1/1] drm/amdgpu: Fix compute VM BO params after rebase v2
The intent of two commits was lost in the last rebase: 810955b drm/amdgpu: Fix acquiring VM on large-BAR systems b5d21aa drm/amdgpu: Don't use shadow BO for compute context This commit restores the original behaviour: * Don't set AMDGPU_GEM_CREATE_NO_CPU_ACCESS for page directories to allow them to be reused for compute VMs * Don't create shadow BOs for page tables in compute VMs v2: move more logic into amdgpu_vm_bo_param Signed-off-by: Felix Kuehling --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ea5e277..1d7e3c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -595,9 +595,8 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm, AMDGPU_GEM_CREATE_CPU_GTT_USWC; if (vm->use_cpu_for_update) bp->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - else - bp->flags |= AMDGPU_GEM_CREATE_SHADOW | - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; + else if (!vm->root.base.bo || vm->root.base.bo->shadow) + bp->flags |= AMDGPU_GEM_CREATE_SHADOW; bp->type = ttm_bo_type_kernel; if (vm->root.base.bo) bp->resv = vm->root.base.bo->tbo.resv; @@ -2749,6 +2748,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, vm->last_update = NULL; amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, ); + if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) + bp.flags &= ~AMDGPU_GEM_CREATE_SHADOW; r = amdgpu_bo_create(adev, , ); if (r) goto error_free_sched_entity; -- 2.7.4 ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
