aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/time/tick-sched.c
diff options
context:
space:
mode:
authorAnna-Maria Behnsen <anna-maria@linutronix.de>2024-02-21 10:05:31 +0100
committerThomas Gleixner <tglx@linutronix.de>2024-02-22 17:52:30 +0100
commite2e1d724e948c87a31c18c34c6b6a193a9b2a0f0 (patch)
tree0d4a769e48155bdf6aaa71c8b420b1590896ff4e /kernel/time/tick-sched.c
parent39ed699fb660c65cef4759c041763c75e0948425 (diff)
downloadlinux-e2e1d724e948c87a31c18c34c6b6a193a9b2a0f0.tar.gz
timers: Move marking timer bases idle into tick_nohz_stop_tick()
The timer base is marked idle when get_next_timer_interrupt() is executed. But the decision whether the tick will be stopped and whether the system is able to go idle is done later. When the timer bases is marked idle and a new first timer is enqueued remote an IPI is raised. Even if it is not required because the tick is not stopped and the timer base is evaluated again at the next tick. To prevent this, the timer base is marked idle in tick_nohz_stop_tick() and get_next_timer_interrupt() is streamlined by only looking for the next timer interrupt. All other work is postponed to timer_base_try_to_set_idle() which is called by tick_nohz_stop_tick(). timer_base_try_to_set_idle() never resets timer_base::is_idle state. This is done when the tick is restarted via tick_nohz_restart_sched_tick(). With this, tick_sched::tick_stopped and timer_base::is_idle are always in sync. So there is no longer the need to execute timer_clear_idle() in tick_nohz_idle_retain_tick(). This was required before, as tick_nohz_next_event() set timer_base::is_idle even if the tick would not be stopped. So timer_clear_idle() is only executed, when timer base is idle. So the check whether timer base is idle, is now no longer required as well. While at it fix some nearby whitespace damage as well. Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Link: https://lore.kernel.org/r/20240221090548.36600-4-anna-maria@linutronix.de
Diffstat (limited to 'kernel/time/tick-sched.c')
-rw-r--r--kernel/time/tick-sched.c40
1 files changed, 28 insertions, 12 deletions
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7c9efe3d9d5620..344b904f520f57 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -860,11 +860,6 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
delta = next_tick - basemono;
if (delta <= (u64)TICK_NSEC) {
/*
- * Tell the timer code that the base is not idle, i.e. undo
- * the effect of get_next_timer_interrupt():
- */
- timer_clear_idle();
- /*
* We've not stopped the tick yet, and there's a timer in the
* next period, so no point in stopping it either, bail.
*/
@@ -899,13 +894,39 @@ out:
static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+ unsigned long basejiff = ts->last_jiffies;
u64 basemono = ts->timer_expires_base;
- u64 expires = ts->timer_expires;
+ bool timer_idle;
+ u64 expires;
/* Make sure we won't be trying to stop it twice in a row. */
ts->timer_expires_base = 0;
/*
+ * Now the tick should be stopped definitely - so the timer base needs
+ * to be marked idle as well to not miss a newly queued timer.
+ */
+ expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle);
+ if (expires > ts->timer_expires) {
+ /*
+ * This path could only happen when the first timer was removed
+ * between calculating the possible sleep length and now (when
+ * high resolution mode is not active, timer could also be a
+ * hrtimer).
+ *
+ * We have to stick to the original calculated expiry value to
+ * not stop the tick for too long with a shallow C-state (which
+ * was programmed by cpuidle because of an early next expiration
+ * value).
+ */
+ expires = ts->timer_expires;
+ }
+
+ /* If the timer base is not idle, retain the not yet stopped tick. */
+ if (!timer_idle)
+ return;
+
+ /*
* 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
@@ -1001,7 +1022,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
touch_softlockup_watchdog_sched();
/* Cancel the scheduled timer and restore the tick: */
- ts->tick_stopped = 0;
+ ts->tick_stopped = 0;
tick_nohz_restart(ts, now);
}
@@ -1157,11 +1178,6 @@ void tick_nohz_idle_stop_tick(void)
void tick_nohz_idle_retain_tick(void)
{
tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
- /*
- * Undo the effect of get_next_timer_interrupt() called from
- * tick_nohz_next_event().
- */
- timer_clear_idle();
}
/**