highres/dyntick: prevent xtime lock contention

While the !highres/!dyntick code assigns the duty of the do_timer() call to
one specific CPU, this was dropped in the highres/dyntick part during
development.

Steven Rostedt discovered the xtime lock contention on highres/dyntick due
to several CPUs trying to update jiffies.

Add the single CPU assignement back.  In the dyntick case this needs to be
handled carefully, as the CPU which has the do_timer() duty must drop the
assignement and let it be grabbed by another CPU, which is active.
Otherwise the do_timer() calls would not happen during the long sleep.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Mark Lord <mlord@pobox.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 40 insertions, 2 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 51556b95f60f..f4fc867f467d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -221,6 +221,18 @@ void tick_nohz_stop_sched_tick(void)
                         ts->tick_stopped = 1;
                         ts->idle_jiffies = last_jiffies;
                 }
+
+                /*
+                 * If this cpu is the one which updates jiffies, then
+                 * give up the assignment and let it be taken by the
+                 * cpu which runs the tick timer next, which might be
+                 * this cpu as well. If we don't drop this here the
+                 * jiffies might be stale and do_timer() never
+                 * invoked.
+                 */
+                if (cpu == tick_do_timer_cpu)
+                        tick_do_timer_cpu = -1;
+
                 /*
                  * calculate the expiry time for the next timer wheel
                  * timer
@@ -338,12 +350,24 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 {
         struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
         struct pt_regs *regs = get_irq_regs();
+        int cpu = smp_processor_id();
         ktime_t now = ktime_get();
 
         dev->next_event.tv64 = KTIME_MAX;
 
+        /*
+         * Check if the do_timer duty was dropped. We don't care about
+         * concurrency: This happens only when the cpu in charge went
+         * into a long sleep. If two cpus happen to assign themself to
+         * this duty, then the jiffies update is still serialized by
+         * xtime_lock.
+         */
+        if (unlikely(tick_do_timer_cpu == -1))
+                tick_do_timer_cpu = cpu;
+
         /* Check, if the jiffies need an update */
-        tick_do_update_jiffies64(now);
+        if (tick_do_timer_cpu == cpu)
+                tick_do_update_jiffies64(now);
 
         /*
          * When we are idle and the tick is stopped, we have to touch
@@ -431,9 +455,23 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
         struct hrtimer_cpu_base *base = timer->base->cpu_base;
         struct pt_regs *regs = get_irq_regs();
         ktime_t now = ktime_get();
+        int cpu = smp_processor_id();
+
+#ifdef CONFIG_NO_HZ
+        /*
+         * Check if the do_timer duty was dropped. We don't care about
+         * concurrency: This happens only when the cpu in charge went
+         * into a long sleep. If two cpus happen to assign themself to
+         * this duty, then the jiffies update is still serialized by
+         * xtime_lock.
+         */
+        if (unlikely(tick_do_timer_cpu == -1))
+                tick_do_timer_cpu = cpu;
+#endif
 
         /* Check, if the jiffies need an update */
-        tick_do_update_jiffies64(now);
+        if (tick_do_timer_cpu == cpu)
+                tick_do_update_jiffies64(now);
 
         /*
          * Do not call, when we are not in irq context and have