[RFC PATCH v5] drm/amdgpu: Remove kfd eviction fence before release bo

[Felix Kuehling]

Hi Xinhui,

Two suggestions inline. Looks good to me otherwise.

On 2020-02-17 10:36 p.m., xinhui pan wrote:
> 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 amd.com>
> CC: Christian König <christian.koenig at amd.com>
> CC: Felix Kuehling <felix.kuehling at amd.com>
> CC: Alex Deucher <alexander.deucher at amd.com>
> ---
> change from v4:
> based on new ttm code.
>
> 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  | 37 +++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_object.c    |  4 ++
>   3 files changed, 42 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> index 9e8db702d878..0ee8aae6c519 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..6aa20aa82bd3 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;

This should not be necessary. Every page table BO has a pointer to a 
vm_bo that has a pointer to the vm. So you don't need to find the root.

This should do the trick:

	if (!bo->vm_bo || !bo->vm_bo->vm)
		return 0;
	vm = bo->vm_bo->vm;


> +
> +	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);
> +
> +	dma_resv_lock(bo->tbo.base.resv, NULL);
> +	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)
>   {
> @@ -1045,6 +1080,8 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
>   	list_del(&vm->vm_list_node);
>   	mutex_unlock(&process_info->lock);
>   
> +	vm->process_info = NULL;
> +
>   	/* Release per-process resources when last compute VM is destroyed */
>   	if (!process_info->n_vms) {
>   		WARN_ON(!list_empty(&process_info->kfd_bo_list));
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 6f60a581e3ba..16586651020f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -1307,6 +1307,10 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
>   	if (abo->kfd_bo)
>   		amdgpu_amdkfd_unreserve_memory_limit(abo);
>   
> +	/* We only remove the fence if the resv has individualized. */
> +	if (bo->base.resv == &bo->base._resv)

Should this be a WARN_ON? We expect this condition to be always true. If 
it's not, there should be a noisy warning that something is wrong.

Regards,
   Felix


> +		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;