From 45f1ff59e27ca59d33cc1a317e669d90022ccf7d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 22 Mar 2018 17:50:49 +0100 Subject: cpuidle: Return nohz hint from cpuidle_select() Add a new pointer argument to cpuidle_select() and to the ->select cpuidle governor callback to allow a boolean value indicating whether or not the tick should be stopped before entering the selected state to be returned from there. Make the ladder governor ignore that pointer (to preserve its current behavior) and make the menu governor return 'false" through it if: (1) the idle exit latency is constrained at 0, or (2) the selected state is a polling one, or (3) the expected idle period duration is within the tick period range. In addition to that, the correction factor computations in the menu governor need to take the possibility that the tick may not be stopped into account to avoid artificially small correction factor values. To that end, add a mechanism to record tick wakeups, as suggested by Peter Zijlstra, and use it to modify the menu_update() behavior when tick wakeup occurs. Namely, if the CPU is woken up by the tick and the return value of tick_nohz_get_sleep_length() is not within the tick boundary, the predicted idle duration is likely too short, so make menu_update() try to compensate for that by updating the governor statistics as though the CPU was idle for a long time. Since the value returned through the new argument pointer of cpuidle_select() is not used by its caller yet, this change by itself is not expected to alter the functionality of the code. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- kernel/sched/idle.c | 4 +++- kernel/time/tick-sched.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 4f64835d38a8..a966bd2a6fa0 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -183,13 +183,15 @@ static void cpuidle_idle_call(void) next_state = cpuidle_find_deepest_state(drv, dev); call_cpuidle(drv, dev, next_state); } else { + bool stop_tick = true; + tick_nohz_idle_stop_tick(); rcu_idle_enter(); /* * Ask the cpuidle framework to choose a convenient idle state. */ - next_state = cpuidle_select(drv, dev); + next_state = cpuidle_select(drv, dev, &stop_tick); entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f5d37788ea85..69fe113cfc7f 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -966,6 +966,20 @@ void tick_nohz_irq_exit(void) tick_nohz_full_update_tick(ts); } +/** + * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + */ +bool tick_nohz_idle_got_tick(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->inidle > 1) { + ts->inidle = 1; + return true; + } + return false; +} + /** * tick_nohz_get_sleep_length - return the length of the current sleep * @@ -1077,6 +1091,9 @@ static void tick_nohz_handler(struct clock_event_device *dev) struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); + if (ts->inidle) + ts->inidle = 2; + dev->next_event = KTIME_MAX; tick_sched_do_timer(now); @@ -1174,6 +1191,9 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); + if (ts->inidle) + ts->inidle = 2; + tick_sched_do_timer(now); /* -- cgit v1.2.3