[PATCH] drm/amdkfd: fix ttm size refactor fallout

Christian König christian.koenig at amd.com
Mon Dec 14 20:27:09 UTC 2020


Am 14.12.20 um 20:17 schrieb Daniel Vetter:
> I guess Christian didn't compile test amdkfd.

Scratching my head what has happened here. When I tested everything was 
at least building fine.

>
> Fixes: e11bfb99d6ec ("drm/ttm: cleanup BO size handling v3")
> Cc: Christian König <christian.koenig at amd.com>
> Cc: Huang Rui <ray.huang at amd.com> (v1)
> Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
> Cc: Felix Kuehling <Felix.Kuehling at amd.com>
> Cc: amd-gfx at lists.freedesktop.org
> Signed-off-by: Daniel Vetter <daniel.vetter at intel.com>

Reviewed-by: Christian König <christian.koenig at amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index 7791d074bd32..a9647e7f98a8 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -453,7 +453,7 @@ static int add_bo_to_vm(struct amdgpu_device *adev, struct kgd_mem *mem,
>   	struct amdgpu_bo *bo = mem->bo;
>   	uint64_t va = mem->va;
>   	struct list_head *list_bo_va = &mem->bo_va_list;
> -	unsigned long bo_size = bo->tbo.mem.size;
> +	unsigned long bo_size = bo->tbo.base.size;
>   
>   	if (!va) {
>   		pr_err("Invalid VA when adding BO to VM\n");
> @@ -1281,7 +1281,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
>   		struct kgd_dev *kgd, struct kgd_mem *mem, uint64_t *size)
>   {
>   	struct amdkfd_process_info *process_info = mem->process_info;
> -	unsigned long bo_size = mem->bo->tbo.mem.size;
> +	unsigned long bo_size = mem->bo->tbo.base.size;
>   	struct kfd_bo_va_list *entry, *tmp;
>   	struct bo_vm_reservation_context ctx;
>   	struct ttm_validate_buffer *bo_list_entry;
> @@ -1402,7 +1402,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
>   	mutex_lock(&mem->lock);
>   
>   	domain = mem->domain;
> -	bo_size = bo->tbo.mem.size;
> +	bo_size = bo->tbo.base.size;
>   
>   	pr_debug("Map VA 0x%llx - 0x%llx to vm %p domain %s\n",
>   			mem->va,
> @@ -1506,7 +1506,7 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
>   	struct amdgpu_device *adev = get_amdgpu_device(kgd);
>   	struct amdkfd_process_info *process_info =
>   		((struct amdgpu_vm *)vm)->process_info;
> -	unsigned long bo_size = mem->bo->tbo.mem.size;
> +	unsigned long bo_size = mem->bo->tbo.base.size;
>   	struct kfd_bo_va_list *entry;
>   	struct bo_vm_reservation_context ctx;
>   	int ret;



More information about the amd-gfx mailing list