Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "A rather largish update for everything time and timer related:

   - Cache footprint optimizations for both hrtimers and timer wheel

   - Lower the NOHZ impact on systems which have NOHZ or timer migration
     disabled at runtime.

   - Optimize run time overhead of hrtimer interrupt by making the clock
     offset updates smarter

   - hrtimer cleanups and removal of restrictions to tackle some
     problems in sched/perf

   - Some more leap second tweaks

   - Another round of changes addressing the 2038 problem

   - First step to change the internals of clock event devices by
     introducing the necessary infrastructure

   - Allow constant folding for usecs/msecs_to_jiffies()

   - The usual pile of clockevent/clocksource driver updates

  The hrtimer changes contain updates to sched, perf and x86 as they
  depend on them plus changes all over the tree to cleanup API changes
  and redundant code, which got copied all over the place.  The y2038
  changes touch s390 to remove the last non 2038 safe code related to
  boot/persistant clock"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  clocksource: Increase dependencies of timer-stm32 to limit build wreckage
  timer: Minimize nohz off overhead
  timer: Reduce timer migration overhead if disabled
  timer: Stats: Simplify the flags handling
  timer: Replace timer base by a cpu index
  timer: Use hlist for the timer wheel hash buckets
  timer: Remove FIFO "guarantee"
  timers: Sanitize catchup_timer_jiffies() usage
  hrtimer: Allow hrtimer::function() to free the timer
  seqcount: Introduce raw_write_seqcount_barrier()
  seqcount: Rename write_seqcount_barrier()
  hrtimer: Fix hrtimer_is_queued() hole
  hrtimer: Remove HRTIMER_STATE_MIGRATE
  selftest: Timers: Avoid signal deadlock in leap-a-day
  timekeeping: Copy the shadow-timekeeper over the real timekeeper last
  clockevents: Check state instead of mode in suspend/resume path
  selftests: timers: Add leap-second timer edge testing to leap-a-day.c
  ntp: Do leapsecond adjustment in adjtimex read path
  time: Prevent early expiry of hrtimers[CLOCK_REALTIME] at the leap second edge
  ntp: Introduce and use SECS_PER_DAY macro instead of 86400
  ...

1 files changed, 132 insertions, 188 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 914259128145..c792429e98c6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -399,7 +399,7 @@ void __init tick_nohz_init(void)
  * NO HZ enabled ?
  */
 static int tick_nohz_enabled __read_mostly  = 1;
-int tick_nohz_active  __read_mostly;
+unsigned long tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
@@ -565,156 +565,144 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+	hrtimer_cancel(&ts->sched_timer);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
+
+	/* Forward the time to expire in the future */
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 					 ktime_t now, int cpu)
 {
-	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
-	ktime_t last_update, expires, ret = { .tv64 = 0 };
-	unsigned long rcu_delta_jiffies;
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
-	u64 time_delta;
-
-	time_delta = timekeeping_max_deferment();
+	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+	unsigned long seq, basejiff;
+	ktime_t	tick;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&jiffies_lock);
-		last_update = last_jiffies_update;
-		last_jiffies = jiffies;
+		basemono = last_jiffies_update.tv64;
+		basejiff = jiffies;
 	} while (read_seqretry(&jiffies_lock, seq));
+	ts->last_jiffies = basejiff;
 
-	if (rcu_needs_cpu(&rcu_delta_jiffies) ||
+	if (rcu_needs_cpu(basemono, &next_rcu) ||
 	    arch_needs_cpu() || irq_work_needs_cpu()) {
-		next_jiffies = last_jiffies + 1;
-		delta_jiffies = 1;
+		next_tick = basemono + TICK_NSEC;
 	} else {
-		/* Get the next timer wheel timer */
-		next_jiffies = get_next_timer_interrupt(last_jiffies);
-		delta_jiffies = next_jiffies - last_jiffies;
-		if (rcu_delta_jiffies < delta_jiffies) {
-			next_jiffies = last_jiffies + rcu_delta_jiffies;
-			delta_jiffies = rcu_delta_jiffies;
-		}
+		/*
+		 * Get the next pending timer. If high resolution
+		 * timers are enabled this only takes the timer wheel
+		 * timers into account. If high resolution timers are
+		 * disabled this also looks at the next expiring
+		 * hrtimer.
+		 */
+		next_tmr = get_next_timer_interrupt(basejiff, basemono);
+		ts->next_timer = next_tmr;
+		/* Take the next rcu event into account */
+		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
 	}
 
 	/*
-	 * Do not stop the tick, if we are only one off (or less)
-	 * or if the cpu is required for RCU:
+	 * If the tick is due in the next period, keep it ticking or
+	 * restart it proper.
 	 */
-	if (!ts->tick_stopped && delta_jiffies <= 1)
-		goto out;
-
-	/* Schedule the tick, if we are at least one jiffie off */
-	if ((long)delta_jiffies >= 1) {
-
-		/*
-		 * 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. Keep track of the fact that it was the one
-		 * which had the do_timer() duty last. If this cpu is
-		 * the one which had the do_timer() duty last, we
-		 * limit the sleep time to the timekeeping
-		 * max_deferement value which we retrieved
-		 * above. Otherwise we can sleep as long as we want.
-		 */
-		if (cpu == tick_do_timer_cpu) {
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-			ts->do_timer_last = 1;
-		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
-			time_delta = KTIME_MAX;
-			ts->do_timer_last = 0;
-		} else if (!ts->do_timer_last) {
-			time_delta = KTIME_MAX;
+	delta = next_tick - basemono;
+	if (delta <= (u64)TICK_NSEC) {
+		tick.tv64 = 0;
+		if (!ts->tick_stopped)
+			goto out;
+		if (delta == 0) {
+			/* Tick is stopped, but required now. Enforce it */
+			tick_nohz_restart(ts, now);
+			goto out;
 		}
+	}
+
+	/*
+	 * 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. Keep track of the fact that it
+	 * was the one which had the do_timer() duty last. If this cpu
+	 * is the one which had the do_timer() duty last, we limit the
+	 * sleep time to the timekeeping max_deferement value.
+	 * Otherwise we can sleep as long as we want.
+	 */
+	delta = timekeeping_max_deferment();
+	if (cpu == tick_do_timer_cpu) {
+		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		ts->do_timer_last = 1;
+	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+		delta = KTIME_MAX;
+		ts->do_timer_last = 0;
+	} else if (!ts->do_timer_last) {
+		delta = KTIME_MAX;
+	}
 
 #ifdef CONFIG_NO_HZ_FULL
-		if (!ts->inidle) {
-			time_delta = min(time_delta,
-					 scheduler_tick_max_deferment());
-		}
+	/* Limit the tick delta to the maximum scheduler deferment */
+	if (!ts->inidle)
+		delta = min(delta, scheduler_tick_max_deferment());
 #endif
 
-		/*
-		 * calculate the expiry time for the next timer wheel
-		 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
-		 * that there is no timer pending or at least extremely
-		 * far into the future (12 days for HZ=1000). In this
-		 * case we set the expiry to the end of time.
-		 */
-		if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
-			/*
-			 * Calculate the time delta for the next timer event.
-			 * If the time delta exceeds the maximum time delta
-			 * permitted by the current clocksource then adjust
-			 * the time delta accordingly to ensure the
-			 * clocksource does not wrap.
-			 */
-			time_delta = min_t(u64, time_delta,
-					   tick_period.tv64 * delta_jiffies);
-		}
-
-		if (time_delta < KTIME_MAX)
-			expires = ktime_add_ns(last_update, time_delta);
-		else
-			expires.tv64 = KTIME_MAX;
-
-		/* Skip reprogram of event if its not changed */
-		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
-			goto out;
+	/* Calculate the next expiry time */
+	if (delta < (KTIME_MAX - basemono))
+		expires = basemono + delta;
+	else
+		expires = KTIME_MAX;
 
-		ret = expires;
+	expires = min_t(u64, expires, next_tick);
+	tick.tv64 = expires;
 
-		/*
-		 * nohz_stop_sched_tick can be called several times before
-		 * the nohz_restart_sched_tick is called. This happens when
-		 * interrupts arrive which do not cause a reschedule. In the
-		 * first call we save the current tick time, so we can restart
-		 * the scheduler tick in nohz_restart_sched_tick.
-		 */
-		if (!ts->tick_stopped) {
-			nohz_balance_enter_idle(cpu);
-			calc_load_enter_idle();
+	/* Skip reprogram of event if its not changed */
+	if (ts->tick_stopped && (expires == dev->next_event.tv64))
+		goto out;
 
-			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
-			ts->tick_stopped = 1;
-			trace_tick_stop(1, " ");
-		}
+	/*
+	 * nohz_stop_sched_tick can be called several times before
+	 * the nohz_restart_sched_tick is called. This happens when
+	 * interrupts arrive which do not cause a reschedule. In the
+	 * first call we save the current tick time, so we can restart
+	 * the scheduler tick in nohz_restart_sched_tick.
+	 */
+	if (!ts->tick_stopped) {
+		nohz_balance_enter_idle(cpu);
+		calc_load_enter_idle();
 
-		/*
-		 * If the expiration time == KTIME_MAX, then
-		 * in this case we simply stop the tick timer.
-		 */
-		 if (unlikely(expires.tv64 == KTIME_MAX)) {
-			if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-				hrtimer_cancel(&ts->sched_timer);
-			goto out;
-		}
+		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
+		ts->tick_stopped = 1;
+		trace_tick_stop(1, " ");
+	}
 
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start(&ts->sched_timer, expires,
-				      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				goto out;
-		} else if (!tick_program_event(expires, 0))
-				goto out;
-		/*
-		 * We are past the event already. So we crossed a
-		 * jiffie boundary. Update jiffies and raise the
-		 * softirq.
-		 */
-		tick_do_update_jiffies64(ktime_get());
+	/*
+	 * If the expiration time == KTIME_MAX, then we simply stop
+	 * the tick timer.
+	 */
+	if (unlikely(expires == KTIME_MAX)) {
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+			hrtimer_cancel(&ts->sched_timer);
+		goto out;
 	}
-	raise_softirq_irqoff(TIMER_SOFTIRQ);
+
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+	else
+		tick_program_event(tick, 1);
 out:
-	ts->next_jiffies = next_jiffies;
-	ts->last_jiffies = last_jiffies;
+	/* Update the estimated sleep length */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
-
-	return ret;
+	return tick;
 }
 
 static void tick_nohz_full_stop_tick(struct tick_sched *ts)
@@ -876,32 +864,6 @@ ktime_t tick_nohz_get_sleep_length(void)
 	return ts->sleep_length;
 }
 
-static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
-
-	while (1) {
-		/* Forward the time to expire in the future */
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start_expires(&ts->sched_timer,
-					      HRTIMER_MODE_ABS_PINNED);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				break;
-		} else {
-			if (!tick_program_event(
-				hrtimer_get_expires(&ts->sched_timer), 0))
-				break;
-		}
-		/* Reread time and update jiffies */
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
-}
-
 static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 {
 	/* Update jiffies first */
@@ -972,12 +934,6 @@ void tick_nohz_idle_exit(void)
 	local_irq_enable();
 }
 
-static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
-{
-	hrtimer_forward(&ts->sched_timer, now, tick_period);
-	return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
-}
-
 /*
  * The nohz low res interrupt handler
  */
@@ -996,10 +952,18 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	if (unlikely(ts->tick_stopped))
 		return;
 
-	while (tick_nohz_reprogram(ts, now)) {
-		now = ktime_get();
-		tick_do_update_jiffies64(now);
-	}
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
+{
+	if (!tick_nohz_enabled)
+		return;
+	ts->nohz_mode = mode;
+	/* One update is enough */
+	if (!test_and_set_bit(0, &tick_nohz_active))
+		timers_update_migration(true);
 }
 
 /**
@@ -1013,13 +977,8 @@ static void tick_nohz_switch_to_nohz(void)
 	if (!tick_nohz_enabled)
 		return;
 
-	local_irq_disable();
-	if (tick_switch_to_oneshot(tick_nohz_handler)) {
-		local_irq_enable();
+	if (tick_switch_to_oneshot(tick_nohz_handler))
 		return;
-	}
-	tick_nohz_active = 1;
-	ts->nohz_mode = NOHZ_MODE_LOWRES;
 
 	/*
 	 * Recycle the hrtimer in ts, so we can share the
@@ -1029,13 +988,10 @@ static void tick_nohz_switch_to_nohz(void)
 	/* Get the next period */
 	next = tick_init_jiffy_update();
 
-	for (;;) {
-		hrtimer_set_expires(&ts->sched_timer, next);
-		if (!tick_program_event(next, 0))
-			break;
-		next = ktime_add(next, tick_period);
-	}
-	local_irq_enable();
+	hrtimer_forward_now(&ts->sched_timer, tick_period);
+	hrtimer_set_expires(&ts->sched_timer, next);
+	tick_program_event(next, 1);
+	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
 }
 
 /*
@@ -1087,6 +1043,7 @@ static inline void tick_nohz_irq_enter(void)
 
 static inline void tick_nohz_switch_to_nohz(void) { }
 static inline void tick_nohz_irq_enter(void) { }
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
@@ -1167,22 +1124,9 @@ void tick_setup_sched_timer(void)
 		hrtimer_add_expires_ns(&ts->sched_timer, offset);
 	}
 
-	for (;;) {
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-		hrtimer_start_expires(&ts->sched_timer,
-				      HRTIMER_MODE_ABS_PINNED);
-		/* Check, if the timer was already in the past */
-		if (hrtimer_active(&ts->sched_timer))
-			break;
-		now = ktime_get();
-	}
-
-#ifdef CONFIG_NO_HZ_COMMON
-	if (tick_nohz_enabled) {
-		ts->nohz_mode = NOHZ_MODE_HIGHRES;
-		tick_nohz_active = 1;
-	}
-#endif
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+	tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
 }
 #endif /* HIGH_RES_TIMERS */
 
@@ -1227,7 +1171,7 @@ void tick_oneshot_notify(void)
  * Called cyclic from the hrtimer softirq (driven by the timer
  * softirq) allow_nohz signals, that we can switch into low-res nohz
  * mode, because high resolution timers are disabled (either compile
- * or runtime).
+ * or runtime). Called with interrupts disabled.
  */
 int tick_check_oneshot_change(int allow_nohz)
 {