drm/amdgpu: pre-map device buffer as cached for A+A config

For A+A configuration, device memory is supposed to be mapped as
cachable from CPU side. For kernel pre-map gpu device memory using
ioremap_cache
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Christian Koenig <Christian.Koenig@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1811,8 +1811,13 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	/* Change the size here instead of the init above so only lpfn is affected */
 	amdgpu_ttm_set_buffer_funcs_status(adev, false);
 #ifdef CONFIG_64BIT
-	adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base,
-						adev->gmc.visible_vram_size);
+	if (adev->gmc.xgmi.connected_to_cpu)
+		adev->mman.aper_base_kaddr = ioremap_cache(adev->gmc.aper_base,
+				adev->gmc.visible_vram_size);
+
+	else
+		adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base,
+				adev->gmc.visible_vram_size);
 #endif
 
 	/*