Register the VRAM manager with the dmem cgroup reclaim infrastructure so that lowering dmem.max below current VRAM usage triggers TTM eviction rather than failing with -EBUSY.
Guard place->flags in amdgpu_ttm_bo_eviction_valuable() against NULL, as the TTM reclaim path passes a NULL place in cgroup drain mode. v3: - Rebased on fix for uninitialized list and buddy allocator on the drmm_cgroup_register_region() error path. Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 9 ++++++--- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 2740de94e93c..8cbcd33f51a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1488,7 +1488,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, dma_resv_for_each_fence(&resv_cursor, bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, f) { if (amdkfd_fence_check_mm(f, current->mm) && - !(place->flags & TTM_PL_FLAG_CONTIGUOUS)) + !(place && (place->flags & TTM_PL_FLAG_CONTIGUOUS))) return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index ac3f71d77140..a1f1ae264a40 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -916,6 +916,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) { struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; struct ttm_resource_manager *man = &mgr->manager; + struct dmem_cgroup_region *cg; int err; ttm_resource_manager_init(man, &adev->mman.bdev, @@ -932,9 +933,11 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) if (err) return err; - man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size); - if (IS_ERR(man->cg)) - return PTR_ERR(man->cg); + cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", + adev->gmc.real_vram_size); + if (IS_ERR(cg)) + return PTR_ERR(cg); + ttm_resource_manager_set_dmem_region(man, cg); ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager); ttm_resource_manager_set_used(man, true); -- 2.54.0
