[RFC PATCH v4] drm/amdgpu: Remove kfd eviction fence before release bo
Christian König
christian.koenig at amd.com
Sat Feb 8 15:57:25 UTC 2020
Am 08.02.20 um 16:09 schrieb Pan, Xinhui:
> No need to trigger eviction as the memory mapping will not be used anymore.
>
> All pt/pd bos share same resv, hence the same shared eviction fence. Everytime page table is freed, the fence will be signled and that cuases kfd unexcepted evictions.
>
> Signed-off-by: xinhui pan <xinhui.pan at example.com>
> ---
> change from v3:
> fix a coding error
>
> change from v2:
> based on Chris' drm/ttm: rework BO delayed delete patchset.
>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 +
> .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 36 +++++++++++++++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 ++
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 1 +
> drivers/gpu/drm/ttm/ttm_bo.c | 16 +++++----
> 5 files changed, 49 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> index 47b0f2957d1f..265b1ed7264c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> @@ -96,6 +96,7 @@ struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
> struct mm_struct *mm);
> bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
> struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
> +int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo);
>
> struct amdkfd_process_info {
> /* List head of all VMs that belong to a KFD process */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index ef721cb65868..d4b117065c1e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -276,6 +276,41 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
> return 0;
> }
>
> +int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
> +{
> + struct amdgpu_bo *root = bo;
> + struct amdgpu_vm_bo_base *vm_bo;
> + struct amdgpu_vm *vm;
> + struct amdkfd_process_info *info;
> + struct amdgpu_amdkfd_fence *ef;
> + int ret;
> +
> + while (root->parent)
> + root = root->parent;
> +
> + vm_bo = root->vm_bo;
> + if (!vm_bo)
> + return 0;
> +
> + vm = vm_bo->vm;
> + if (!vm)
> + return 0;
> +
> + info = vm->process_info;
> + if (!info || !info->eviction_fence)
> + return 0;
> +
> + ef = container_of(dma_fence_get(&info->eviction_fence->base),
> + struct amdgpu_amdkfd_fence, base);
> +
> + BUG_ON(!dma_resv_trylock(&bo->tbo.base._resv));
> + ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef);
> + dma_resv_unlock(&bo->tbo.base._resv);
> +
> + dma_fence_put(&ef->base);
> + return ret;
> +}
> +
> static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
> bool wait)
> {
> @@ -1051,6 +1086,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
> WARN_ON(!list_empty(&process_info->userptr_valid_list));
> WARN_ON(!list_empty(&process_info->userptr_inval_list));
>
> + vm->process_info = NULL;
> dma_fence_put(&process_info->eviction_fence->base);
> cancel_delayed_work_sync(&process_info->restore_userptr_work);
> put_pid(process_info->pid);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 6f60a581e3ba..3784d178c965 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -1307,6 +1307,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
> if (abo->kfd_bo)
> amdgpu_amdkfd_unreserve_memory_limit(abo);
>
> + amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo);
> +
> if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node ||
> !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE))
> return;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 247f328b7223..eca4ec66c1ee 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -3109,6 +3109,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
> }
>
> amdgpu_vm_free_pts(adev, vm, NULL);
> + root->vm_bo = NULL;
> amdgpu_bo_unreserve(root);
> amdgpu_bo_unref(&root);
> WARN_ON(vm->root.base.bo);
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 6c3cea509e25..855d3566381e 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -399,8 +399,7 @@ static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo)
> BUG_ON(!dma_resv_trylock(&bo->base._resv));
>
> r = dma_resv_copy_fences(&bo->base._resv, bo->base.resv);
> - if (r)
> - dma_resv_unlock(&bo->base._resv);
> + dma_resv_unlock(&bo->base._resv);
>
> return r;
> }
> @@ -565,9 +564,6 @@ static void ttm_bo_release(struct kref *kref)
> int ret;
>
> if (!bo->deleted) {
> - if (bo->bdev->driver->release_notify)
> - bo->bdev->driver->release_notify(bo);
> -
> drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node);
> ttm_mem_io_lock(man, false);
> ttm_mem_io_free_vm(bo);
> @@ -581,6 +577,14 @@ static void ttm_bo_release(struct kref *kref)
> dma_resv_wait_timeout_rcu(bo->base.resv, true, false,
> 30 * HZ);
> }
> +
> + spin_lock(&ttm_bo_glob.lru_lock);
> + if (bo->type != ttm_bo_type_sg)
> + bo->base.resv = &bo->base._resv;
This still doesn't works correctly and can cause very subtle crashes.
I will try to send out a patch set on Monday which should work.
Christian.
> + spin_unlock(&ttm_bo_glob.lru_lock);
> +
> + if (bo->bdev->driver->release_notify)
> + bo->bdev->driver->release_notify(bo);
> }
>
> if (!dma_resv_test_signaled_rcu(bo->base.resv, true)) {
> @@ -599,8 +603,6 @@ static void ttm_bo_release(struct kref *kref)
> }
>
> spin_lock(&ttm_bo_glob.lru_lock);
> - if (bo->type != ttm_bo_type_sg)
> - bo->base.resv = &bo->base._resv;
> kref_init(&bo->kref);
> list_add_tail(&bo->ddestroy, &bdev->ddestroy);
> spin_unlock(&ttm_bo_glob.lru_lock);
More information about the amd-gfx
mailing list