No need to do a check for 'affine wakeup and passive balancing possibilities'
in select_task_rq_fair() when task_cpu(p) == this_cpu.
I guess, this part got missed upon introduction of per-sched_class
select_task_rq() in try_to_wake_up().
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
        this_cpu = smp_processor_id();
        new_cpu  = cpu;
 
+       if (cpu == this_cpu)
+               goto out_set_cpu;
+
        for_each_domain(this_cpu, sd) {
                if (cpu_isset(cpu, sd->span)) {
                        this_sd = sd;