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: Christian König <christian.koenig@amd.com>
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-and-tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 22 insertions, 30 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ea3f7ee189235..62ca12e945810 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -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;
+	struct dma_resv *resv = &bo->tbo.base._resv;
+	struct dma_fence *fence, *stub;
+	struct dma_resv_iter cursor;
 
-	vm_bo = root->vm_bo;
-	if (!vm_bo)
-		return 0;
+	dma_resv_assert_held(resv);
 
-	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);
+	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,