drm/amdgpu: Move CG/PG setting out of delay worker thread

Partially revert commit 2dc80b00
("drm/amdgpu: optimize amdgpu driver load & resume time")'

1. CG/PG enablement are part of gpu hw ip initialize, we should
wait for them complete. otherwise, there are some potential conflicts,
for example, Suspend and CG enablement concurrently.
2. better run ib test after hw initialize completely. That is to say,
   ib test should be after CG/PG enablement. otherwise, the test will
   not cover the cg/pg/poweroff enable case.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1707,10 +1707,6 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 	if (amdgpu_emu_mode == 1)
 		return 0;
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -1791,6 +1787,9 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		}
 	}
 
+	amdgpu_device_ip_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_pg_state(adev);
+
 	queue_delayed_work(system_wq, &adev->late_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
@@ -1919,8 +1918,11 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
-	amdgpu_device_ip_late_set_cg_state(adev);
-	amdgpu_device_ip_late_set_pg_state(adev);
+	int r;
+
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
 }
 
 /**