[PATCH 2/3] drm/amdgpu/mes: fix bo va unmap issue in mes

[Jack Xiao]

Need reserve buffers before unmap mes ctx bo va.

Signed-off-by: Jack Xiao <jack.x...@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 59 +++++++++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h |  2 +
 2 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index db2138b7a858..de80161fb27b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1174,6 +1174,61 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device 
*adev,
        return r;
 }
 
+int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev,
+                                  struct amdgpu_mes_ctx_data *ctx_data)
+{
+       struct amdgpu_bo_va *bo_va = ctx_data->meta_data_va;
+       struct amdgpu_bo *bo = ctx_data->meta_data_obj;
+       struct amdgpu_vm *vm = bo_va->base.vm;
+       struct amdgpu_bo_list_entry vm_pd;
+       struct list_head list, duplicates;
+       struct dma_fence *fence = NULL;
+       struct ttm_validate_buffer tv;
+       struct ww_acquire_ctx ticket;
+       long r = 0;
+
+       INIT_LIST_HEAD(&list);
+       INIT_LIST_HEAD(&duplicates);
+
+       tv.bo = &bo->tbo;
+       tv.num_shared = 2;
+       list_add(&tv.head, &list);
+
+       amdgpu_vm_get_pd_bo(vm, &list, &vm_pd);
+
+       r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates);
+       if (r) {
+               dev_err(adev->dev, "leaking bo va because "
+                       "we fail to reserve bo (%ld)\n", r);
+               return r;
+       }
+
+       amdgpu_vm_bo_del(adev, bo_va);
+       if (!amdgpu_vm_ready(vm))
+               goto out_unlock;
+
+       fence = dma_resv_excl_fence(bo->tbo.base.resv);
+       if (fence) {
+               amdgpu_bo_fence(bo, fence, true);
+               fence = NULL;
+       }
+
+       r = amdgpu_vm_clear_freed(adev, vm, &fence);
+       if (r || !fence)
+               goto out_unlock;
+
+       dma_fence_wait(fence, false);
+       amdgpu_bo_fence(bo, fence, true);
+       dma_fence_put(fence);
+
+out_unlock:
+       if (unlikely(r < 0))
+               dev_err(adev->dev, "failed to clear page tables (%ld)\n", r);
+       ttm_eu_backoff_reservation(&ticket, &list);
+
+       return r;
+}
+
 static int amdgpu_mes_test_create_gang_and_queues(struct amdgpu_device *adev,
                                          int pasid, int *gang_id,
                                          int queue_type, int num_queue,
@@ -1335,9 +1390,7 @@ int amdgpu_mes_self_test(struct amdgpu_device *adev)
        amdgpu_mes_destroy_process(adev, pasid);
 
 error_vm:
-       BUG_ON(amdgpu_bo_reserve(ctx_data.meta_data_obj, true));
-       amdgpu_vm_bo_del(adev, ctx_data.meta_data_va);
-       amdgpu_bo_unreserve(ctx_data.meta_data_obj);
+       amdgpu_mes_ctx_unmap_meta_data(adev, &ctx_data);
 
 error_fini:
        amdgpu_vm_fini(adev, vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 02daffbda02d..3730df05f6b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -352,6 +352,8 @@ void amdgpu_mes_ctx_free_meta_data(struct 
amdgpu_mes_ctx_data *ctx_data);
 int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
                                 struct amdgpu_vm *vm,
                                 struct amdgpu_mes_ctx_data *ctx_data);
+int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev,
+                                  struct amdgpu_mes_ctx_data *ctx_data);
 
 int amdgpu_mes_self_test(struct amdgpu_device *adev);
 
-- 
2.35.1