Commit cb0de06d authored by Christian König's avatar Christian König Committed by Alex Deucher
Browse files

drm/amdgpu: remove all KFD fences from the BO on release 



Remove all KFD BOs from the private dma_resv object.

This prevents the KFD from being evict unecessarily when an exported BO
is released.

Signed-off-by: default avatarChristian König <christian.koenig@amd.com>
Signed-off-by: default avatarJames Zhu <James.Zhu@amd.com>
Reviewed-by: default avatarFelix Kuehling <felix.kuehling@amd.com>
Reviewed-and-tested-by: default avatarJames Zhu <James.Zhu@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 3521276a

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

+2 −3
Original line number Diff line number Diff line
@@ -193,7 +193,7 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data); 
#if IS_ENABLED(CONFIG_HSA_AMD)

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);

void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo);

int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni,

				unsigned long cur_seq, struct kgd_mem *mem);

int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
@@ -213,9 +213,8 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) 
}



static inline

int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)

void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo)

{

	return 0;

}



static inline

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

+22 −30
Original line number Diff line number Diff line
@@ -370,40 +370,32 @@ 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)

/**

 * amdgpu_amdkfd_remove_all_eviction_fences - Remove all eviction fences

 * @bo: the BO where to remove the evictions fences from.

 *

 * This functions should only be used on release when all references to the BO

 * are already dropped. We remove the eviction fence from the private copy of

 * the dma_resv object here since that is what is used during release to

 * determine of the BO is idle or not.

 */

void amdgpu_amdkfd_remove_all_eviction_fences(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;



	/* we can always get vm_bo from root PD bo.*/

	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;

	struct dma_resv *resv = &bo->tbo.base._resv;

	struct dma_fence *fence, *stub;

	struct dma_resv_iter cursor;



	ef = container_of(dma_fence_get(&info->eviction_fence->base),

			struct amdgpu_amdkfd_fence, base);

	dma_resv_assert_held(resv);



	BUG_ON(!dma_resv_trylock(bo->tbo.base.resv));

	ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef);

	dma_resv_unlock(bo->tbo.base.resv);

	stub = dma_fence_get_stub();

	dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) {

		if (!to_amdgpu_amdkfd_fence(fence))

			continue;



	dma_fence_put(&ef->base);

	return ret;

		dma_resv_replace_fences(resv, fence->context, stub,

					DMA_RESV_USAGE_BOOKKEEP);

	}

	dma_fence_put(stub);

}



static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

+23 −15
Original line number Diff line number Diff line
@@ -1295,28 +1295,36 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) 
	if (abo->kfd_bo)

		amdgpu_amdkfd_release_notify(abo);



	/* We only remove the fence if the resv has individualized. */

	WARN_ON_ONCE(bo->type == ttm_bo_type_kernel

			&& bo->base.resv != &bo->base._resv);

	if (bo->base.resv == &bo->base._resv)

		amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo);

	/*

	 * We lock the private dma_resv object here and since the BO is about to

	 * be released nobody else should have a pointer to it.

	 * So when this locking here fails something is wrong with the reference

	 * counting.

	 */

	if (WARN_ON_ONCE(!dma_resv_trylock(&bo->base._resv)))

		return;



	amdgpu_amdkfd_remove_all_eviction_fences(abo);



	if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM ||

	    !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) ||

	    adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev)))

		return;

		goto out;



	if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))

		return;

	r = dma_resv_reserve_fences(&bo->base._resv, 1);

	if (r)

		goto out;



	r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true);

	if (WARN_ON(r))

		goto out;



	r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true);

	if (!WARN_ON(r)) {

	amdgpu_vram_mgr_set_cleared(bo->resource);

		amdgpu_bo_fence(abo, fence, false);

	dma_resv_add_fence(&bo->base._resv, fence, DMA_RESV_USAGE_KERNEL);

	dma_fence_put(fence);

	}



	dma_resv_unlock(bo->base.resv);

out:

	dma_resv_unlock(&bo->base._resv);

}



/**