+static int cpu_to_queue_index(unsigned int nr_queues, const int cpu,
+			      const struct cpumask *online_mask)
  {
-	return cpu * nr_queues / nr_cpus;
+	/*
+	 * Non online CPU will be mapped to queue index 0.
+	 */
+	if (!cpumask_test_cpu(cpu, online_mask))
+		return 0;

Why not map offline cpus to what they would've map to if they were
online?

+		if (cpu < nr_queues) {
+			map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);
+		} else {
+			first_sibling = get_first_sibling(cpu);
+			if (first_sibling == cpu)
+				map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);

This seems to be the only reference to online_mask left (on each side of
the if statement. I think you can just not pass it and use
cpu_online_mask in cpu_to_queue_index.