[PATCH 09/13] nohz: Allow timekeeper's tick to stop when all full dynticks CPUs are idle

[Frederic Weisbecker]

When all full dynticks CPUs are idle, as detected by RCU's sysidle
detection, there is no need to keep the timekeeping CPU's tick alive
anymore. So lets shut it down when we meet this favourable state. The
timekeeper will be notified with an IPI if any full dynticks CPU
wakes up.

Also, since we plan to allow every CPUs outside the full dynticks range
to handle the timekeeping duty, lets also allow the timekeeping duty
to be balanced. The only requirement is that the last timekeeper can't
shut down its idle tick further than 1 jiffie until some other CPU
takes its duty or until all full dynticks CPUs go to sleep.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: John Stultz <john.stultz@xxxxxxxxxx>
Cc: Alex Shi <alex.shi@xxxxxxxxxx>
Cc: Kevin Hilman <khilman@xxxxxxxxxx>
---
 kernel/time/tick-sched.c | 67 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 50 insertions(+), 17 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0d2d774..527b501 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -192,6 +192,49 @@ static bool can_stop_full_tick(void)
 	return true;
 }
 
+/*
+ * Fetch max deferment for the current clockevent source until it overflows.
+ * Also in full dynticks environment, make sure the current timekeeper
+ * stays periodic until some other CPU can take its timekeeping duty
+ * or until all full dynticks go to sleep.
+ */
+static u64 tick_timekeeping_max_deferment(struct tick_sched *ts)
+{
+	int cpu;
+	u64 ret = KTIME_MAX;
+
+	/*
+	 * Fast path for full dynticks off-case: skip to
+	 * clockevent max deferment
+	 */
+	if (!tick_nohz_full_enabled())
+		return timekeeping_max_deferment();
+
+	cpu = smp_processor_id();
+
+	/* Full dynticks CPU don't take timekeeping duty */
+	if (!tick_timekeeping_cpu(cpu))
+		return timekeeping_max_deferment();
+
+	/*
+	 * If we are the timekeeper and all full dynticks CPUs are idle,
+	 * then we can finally sleep.
+	 */
+	if (tick_do_timer_cpu == cpu ||
+	    (tick_do_timer_cpu == TICK_DO_TIMER_NONE &&	ts->do_timer_last == 1)) {
+		if (!rcu_sys_is_idle()) {
+			/*
+			 * Stop tick for 1 jiffy. In practice we stay periodic
+			 * but that let us possibly delegate our timekeeping duty
+			 * to stop the tick for real in the future.
+			 */
+			ret = tick_period.tv64;
+		}
+	}
+
+	return min_t(u64, ret, timekeeping_max_deferment());
+}
+
 static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
 
 /*
@@ -352,7 +395,12 @@ void __init tick_nohz_init(void)
 	cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask);
 	pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
 }
-#endif
+# else /* CONFIG_NO_HZ_FULL */
+static u64 tick_timekeeping_max_deferment(struct tick_sched *ts)
+{
+	return timekeeping_max_deferment();
+}
+#endif /* CONFIG_NO_HZ_FULL */
 
 /*
  * NOHZ - aka dynamic tick functionality
@@ -532,7 +580,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
 
-	time_delta = timekeeping_max_deferment();
+	time_delta = tick_timekeeping_max_deferment(ts);
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
@@ -726,21 +774,6 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 	}
 
-	if (tick_nohz_full_enabled()) {
-		/*
-		 * Keep the tick alive to guarantee timekeeping progression
-		 * if there are full dynticks CPUs around
-		 */
-		if (tick_do_timer_cpu == cpu)
-			return false;
-		/*
-		 * Boot safety: make sure the timekeeping duty has been
-		 * assigned before entering dyntick-idle mode,
-		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
-			return false;
-	}
-
 	return true;
 }
 
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/