drm/amdgpu: adjust HDP write queue flushing for tlb invalidation

Separate tlb invalidation and hdp flushing and move the HDP
flush to the caller.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 0a4f34a..d0617f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -247,6 +247,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 		}
 	}
 	mb();
+	amdgpu_asic_flush_hdp(adev);
 	amdgpu_gart_flush_gpu_tlb(adev, 0);
 	return 0;
 }
@@ -329,6 +330,7 @@ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		return r;
 
 	mb();
+	amdgpu_asic_flush_hdp(adev);
 	amdgpu_gart_flush_gpu_tlb(adev, 0);
 	return 0;
 }