sched: Use rt.nr_cpus_allowed to recover select_task_rq() cycles

rt.nr_cpus_allowed is always available, use it to bail from select_task_rq()
when only one cpu can be used, and saves some cycles for pinned tasks.

See the line marked with '*' below:

  # taskset -c 3 pipe-test

   PerfTop:     997 irqs/sec  kernel:89.5%  exact:  0.0% [1000Hz cycles],  (all, CPU: 3)
------------------------------------------------------------------------------------------------

             Virgin                                    Patched
             samples  pcnt function                    samples  pcnt function
             _______ _____ ___________________________ _______ _____ ___________________________

             2880.00 10.2% __schedule                  3136.00 11.3% __schedule
             1634.00  5.8% pipe_read                   1615.00  5.8% pipe_read
             1458.00  5.2% system_call                 1534.00  5.5% system_call
             1382.00  4.9% _raw_spin_lock_irqsave      1412.00  5.1% _raw_spin_lock_irqsave
             1202.00  4.3% pipe_write                  1255.00  4.5% copy_user_generic_string
             1164.00  4.1% copy_user_generic_string    1241.00  4.5% __switch_to
             1097.00  3.9% __switch_to                  929.00  3.3% mutex_lock
              872.00  3.1% mutex_lock                   846.00  3.0% mutex_unlock
              687.00  2.4% mutex_unlock                 804.00  2.9% pipe_write
              682.00  2.4% native_sched_clock           713.00  2.6% native_sched_clock
              643.00  2.3% system_call_after_swapgs     653.00  2.3% _raw_spin_unlock_irqrestore
              617.00  2.2% sched_clock_local            633.00  2.3% fsnotify
              612.00  2.2% fsnotify                     605.00  2.2% sched_clock_local
              596.00  2.1% _raw_spin_unlock_irqrestore  593.00  2.1% system_call_after_swapgs
              542.00  1.9% sysret_check                 559.00  2.0% sysret_check
              467.00  1.7% fget_light                   472.00  1.7% fget_light
              462.00  1.6% finish_task_switch           461.00  1.7% finish_task_switch
              437.00  1.5% vfs_write                    442.00  1.6% vfs_write
              431.00  1.5% do_sync_write                428.00  1.5% do_sync_write
*             413.00  1.5% select_task_rq_fair          404.00  1.5% _raw_spin_lock_irq
              386.00  1.4% update_curr                  402.00  1.4% update_curr
              385.00  1.4% rw_verify_area               389.00  1.4% do_sync_read
              377.00  1.3% _raw_spin_lock_irq           378.00  1.4% vfs_read
              369.00  1.3% do_sync_read                 340.00  1.2% pipe_iov_copy_from_user
              360.00  1.3% vfs_read                     316.00  1.1% __wake_up_sync_key
              342.00  1.2% hrtick_start_fair            313.00  1.1% __wake_up_common
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1321971504.6855.15.camel@marge.simson.netSigned-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched/fair.c

@@ -2744,6 +2744,9 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 	int want_sd = 1;
 	int sync = wake_flags & WF_SYNC;
 
+	if (p->rt.nr_cpus_allowed == 1)
+		return prev_cpu;
+
 	if (sd_flag & SD_BALANCE_WAKE) {
 		if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
 			want_affine = 1;

kernel/sched/rt.c

@@ -1200,6 +1200,9 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 
 	cpu = task_cpu(p);
 
+	if (p->rt.nr_cpus_allowed == 1)
+		goto out;
+
 	/* For anything but wake ups, just return the task_cpu */
 	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
 		goto out;