timer: Minimize nohz off overhead

If nohz is disabled on the kernel command line the [hr]timer code
still calls wake_up_nohz_cpu() and tick_nohz_full_cpu(), a pretty
pointless exercise. Cache nohz_active in [hr]timer per cpu bases and
avoid the overhead.

Before:
  48.10%  hog       [.] main
  15.25%  [kernel]  [k] _raw_spin_lock_irqsave
   9.76%  [kernel]  [k] _raw_spin_unlock_irqrestore
   6.50%  [kernel]  [k] mod_timer
   6.44%  [kernel]  [k] lock_timer_base.isra.38
   3.87%  [kernel]  [k] detach_if_pending
   3.80%  [kernel]  [k] del_timer
   2.67%  [kernel]  [k] internal_add_timer
   1.33%  [kernel]  [k] __internal_add_timer
   0.73%  [kernel]  [k] timerfn
   0.54%  [kernel]  [k] wake_up_nohz_cpu

After:
  48.73%  hog       [.] main
  15.36%  [kernel]  [k] _raw_spin_lock_irqsave
   9.77%  [kernel]  [k] _raw_spin_unlock_irqrestore
   6.61%  [kernel]  [k] lock_timer_base.isra.38
   6.42%  [kernel]  [k] mod_timer
   3.90%  [kernel]  [k] detach_if_pending
   3.76%  [kernel]  [k] del_timer
   2.41%  [kernel]  [k] internal_add_timer
   1.39%  [kernel]  [k] __internal_add_timer
   0.76%  [kernel]  [k] timerfn

We probably should have a cached value for nohz full in the per cpu
bases as well to avoid the cpumask check. The base cache line is hot
already, the cpumask not necessarily.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Joonwoo Park <joonwoop@codeaurora.org>
Cc: Wenbo Wang <wenbo.wang@memblaze.com>
Link: http://lkml.kernel.org/r/20150526224512.207378134@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 12 insertions, 4 deletions

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 343142ed996a..520499dd85af 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -86,6 +86,7 @@ struct tvec_base {
         unsigned long all_timers;
         int cpu;
         bool migration_enabled;
+        bool nohz_active;
         struct tvec_root tv1;
         struct tvec tv2;
         struct tvec tv3;
@@ -99,7 +100,7 @@ static DEFINE_PER_CPU(struct tvec_base, tvec_bases);
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 unsigned int sysctl_timer_migration = 1;
 
-void timers_update_migration(void)
+void timers_update_migration(bool update_nohz)
 {
         bool on = sysctl_timer_migration && tick_nohz_active;
         unsigned int cpu;
@@ -111,6 +112,10 @@ void timers_update_migration(void)
         for_each_possible_cpu(cpu) {
                 per_cpu(tvec_bases.migration_enabled, cpu) = on;
                 per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
+                if (!update_nohz)
+                        continue;
+                per_cpu(tvec_bases.nohz_active, cpu) = true;
+                per_cpu(hrtimer_bases.nohz_active, cpu) = true;
         }
 }
 
@@ -124,7 +129,7 @@ int timer_migration_handler(struct ctl_table *table, int write,
         mutex_lock(&mutex);
         ret = proc_dointvec(table, write, buffer, lenp, ppos);
         if (!ret && write)
-                timers_update_migration();
+                timers_update_migration(false);
         mutex_unlock(&mutex);
         return ret;
 }
@@ -436,8 +441,11 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
          * require special care against races with idle_cpu(), lets deal
          * with that later.
          */
-        if (!(timer->flags & TIMER_DEFERRABLE) || tick_nohz_full_cpu(base->cpu))
-                wake_up_nohz_cpu(base->cpu);
+        if (base->nohz_active) {
+                if (!(timer->flags & TIMER_DEFERRABLE) ||
+                    tick_nohz_full_cpu(base->cpu))
+                        wake_up_nohz_cpu(base->cpu);
+        }
 }
 
 #ifdef CONFIG_TIMER_STATS