drm/amdgpu: init iommu after amdkfd device init

This patch is to fix clinfo failure in Raven/Picasso:

Number of platforms: 1
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 2.2 AMD-APP (3364.0)
Platform Name: AMD Accelerated Parallel Processing
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callback

Platform Name: AMD Accelerated Parallel Processing Number of devices: 0

Signed-off-by: Yifan Zhang <[e-mail]>
Reviewed-by: James Zhu <[e-mail]>
Tested-by: James Zhu <[e-mail]>
Acked-by: Felix Kuehling <[e-mail]>
Signed-off-by: Alex Deucher <[e-mail]>

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

···
 	if (r)
 		goto init_failed;
 
-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		goto init_failed;
-
 	r = amdgpu_device_ip_hw_init_phase1(adev);
 	if (r)
 		goto init_failed;
···
 	/* Don't init kfd if whole hive need to be reset during init */
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
+
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
 
 	amdgpu_fru_get_product_info(adev);