On 02.09.25 06:06, Dave Airlie wrote:
> From: Dave Airlie <airl...@redhat.com>
>
> This adds support for adding a obj cgroup to a buffer object,
> and passing in the placement flags to make sure it's accounted
> properly.
>
> Signed-off-by: Dave Airlie <airl...@redhat.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 ++
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 13 +++++++++----
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 ++
> mm/memcontrol.c | 1 +
> 5 files changed, 15 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index d1ccbfcf21fa..a01fe7594e3a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -198,6 +198,7 @@ static void amdgpu_gem_object_free(struct drm_gem_object
> *gobj)
> struct amdgpu_bo *aobj = gem_to_amdgpu_bo(gobj);
>
> amdgpu_hmm_unregister(aobj);
> + obj_cgroup_put(aobj->tbo.objcg);
This should probably be in ttm_bo_release() instead and passed in as parameter
to ttm_bo_init_reserved().
Apart from tha looks good to me.
Regards,
Christian.
> ttm_bo_put(&aobj->tbo);
> }
>
> @@ -225,6 +226,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev,
> unsigned long size,
> bp.domain = initial_domain;
> bp.bo_ptr_size = sizeof(struct amdgpu_bo);
> bp.xcp_id_plus1 = xcp_id_plus1;
> + bp.objcg = get_obj_cgroup_from_current();
>
> r = amdgpu_bo_create_user(adev, &bp, &ubo);
> if (r)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 122a88294883..cbd09c680d33 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -159,7 +159,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo
> *abo, u32 domain)
> places[c].mem_type =
> abo->flags & AMDGPU_GEM_CREATE_PREEMPTIBLE ?
> AMDGPU_PL_PREEMPT : TTM_PL_TT;
> - places[c].flags = 0;
> + places[c].flags = TTM_PL_FLAG_MEMCG;
> /*
> * When GTT is just an alternative to VRAM make sure that we
> * only use it as fallback and still try to fill up VRAM first.
> @@ -174,7 +174,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo
> *abo, u32 domain)
> places[c].fpfn = 0;
> places[c].lpfn = 0;
> places[c].mem_type = TTM_PL_SYSTEM;
> - places[c].flags = 0;
> + places[c].flags = TTM_PL_FLAG_MEMCG;
> c++;
> }
>
> @@ -654,16 +654,21 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
> size = ALIGN(size, PAGE_SIZE);
> }
>
> - if (!amdgpu_bo_validate_size(adev, size, bp->domain))
> + if (!amdgpu_bo_validate_size(adev, size, bp->domain)) {
> + obj_cgroup_put(bp->objcg);
> return -ENOMEM;
> + }
>
> BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo));
>
> *bo_ptr = NULL;
> bo = kvzalloc(bp->bo_ptr_size, GFP_KERNEL);
> - if (bo == NULL)
> + if (bo == NULL) {
> + obj_cgroup_put(bp->objcg);
> return -ENOMEM;
> + }
> drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size);
> + bo->tbo.objcg = bp->objcg;
> bo->tbo.base.funcs = &amdgpu_gem_object_funcs;
> bo->vm_bo = NULL;
> bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain :
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> index c316920f3450..8cccbe62e328 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
> @@ -55,6 +55,7 @@ struct amdgpu_bo_param {
> enum ttm_bo_type type;
> bool no_wait_gpu;
> struct dma_resv *resv;
> + struct obj_cgroup *objcg;
> void (*destroy)(struct ttm_buffer_object
> *bo);
> /* xcp partition number plus 1, 0 means any partition */
> int8_t xcp_id_plus1;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index f71431e8e6b9..a3fa28e5a43e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -151,11 +151,13 @@ static void amdgpu_evict_flags(struct ttm_buffer_object
> *bo,
> amdgpu_bo_placement_from_domain(abo,
> AMDGPU_GEM_DOMAIN_GTT |
> AMDGPU_GEM_DOMAIN_CPU);
> }
> + abo->placements[0].flags &= ~TTM_PL_FLAG_MEMCG;
> break;
> case TTM_PL_TT:
> case AMDGPU_PL_PREEMPT:
> default:
> amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
> + abo->placements[0].flags &= ~TTM_PL_FLAG_MEMCG;
> break;
> }
> *placement = abo->placement;
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 3d637c7e10cf..e4dc0cc43bc9 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2722,6 +2722,7 @@ __always_inline struct obj_cgroup
> *current_obj_cgroup(void)
>
> return objcg;
> }
> +EXPORT_SYMBOL_GPL(current_obj_cgroup);
>
> struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
> {
