3 files changed, 171 insertions, 135 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4a08472c3ca7..41be02250e08 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -271,50 +271,15 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
-static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
+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;
-	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
-	int cpu;
-
-	cpu = smp_processor_id();
-	ts = &per_cpu(tick_cpu_sched, cpu);
-
-	now = tick_nohz_start_idle(cpu, ts);
-
-	/*
-	 * If this cpu is offline and it 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. If we don't drop
-	 * this here the jiffies might be stale and do_timer() never
-	 * invoked.
-	 */
-	if (unlikely(!cpu_online(cpu))) {
-		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-	}
-
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
-		return;
 
-	if (need_resched())
-		return;
-
-	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
-		static int ratelimit;
-
-		if (ratelimit < 10) {
-			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       (unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
-		return;
-	}
-
-	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&xtime_lock);
@@ -397,6 +362,8 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
 			goto out;
 
+		ret = expires;
+
 		/*
 		 * nohz_stop_sched_tick can be called several times before
 		 * the nohz_restart_sched_tick is called. This happens when
@@ -408,16 +375,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 			select_nohz_load_balancer(1);
 			calc_load_enter_idle();
 
-			ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
+			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 			ts->tick_stopped = 1;
-			ts->idle_jiffies = last_jiffies;
 		}
 
-		ts->idle_sleeps++;
-
-		/* Mark expires */
-		ts->idle_expires = expires;
-
 		/*
 		 * If the expiration time == KTIME_MAX, then
 		 * in this case we simply stop the tick timer.
@@ -448,6 +409,65 @@ out:
 	ts->next_jiffies = next_jiffies;
 	ts->last_jiffies = last_jiffies;
 	ts->sleep_length = ktime_sub(dev->next_event, now);
+
+	return ret;
+}
+
+static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
+{
+	/*
+	 * If this cpu is offline and it 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. If we don't drop
+	 * this here the jiffies might be stale and do_timer() never
+	 * invoked.
+	 */
+	if (unlikely(!cpu_online(cpu))) {
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+	}
+
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+		return false;
+
+	if (need_resched())
+		return false;
+
+	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
+		static int ratelimit;
+
+		if (ratelimit < 10) {
+			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+			       (unsigned int) local_softirq_pending());
+			ratelimit++;
+		}
+		return false;
+	}
+
+	return true;
+}
+
+static void __tick_nohz_idle_enter(struct tick_sched *ts)
+{
+	ktime_t now, expires;
+	int cpu = smp_processor_id();
+
+	now = tick_nohz_start_idle(cpu, ts);
+
+	if (can_stop_idle_tick(cpu, ts)) {
+		int was_stopped = ts->tick_stopped;
+
+		ts->idle_calls++;
+
+		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
+		if (expires.tv64 > 0LL) {
+			ts->idle_sleeps++;
+			ts->idle_expires = expires;
+		}
+
+		if (!was_stopped && ts->tick_stopped)
+			ts->idle_jiffies = ts->last_jiffies;
+	}
 }
 
 /**
@@ -485,7 +505,7 @@ void tick_nohz_idle_enter(void)
 	 * update of the idle time accounting in tick_nohz_start_idle().
 	 */
 	ts->inidle = 1;
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 
 	local_irq_enable();
 }
@@ -505,7 +525,7 @@ void tick_nohz_irq_exit(void)
 	if (!ts->inidle)
 		return;
 
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 }
 
 /**
@@ -523,7 +543,7 @@ ktime_t tick_nohz_get_sleep_length(void)
 static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 {
 	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
 
 	while (1) {
 		/* Forward the time to expire in the future */
@@ -546,6 +566,41 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	}
 }
 
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
+{
+	/* Update jiffies first */
+	select_nohz_load_balancer(0);
+	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
+
+	touch_softlockup_watchdog();
+	/*
+	 * Cancel the scheduled timer and restore the tick
+	 */
+	ts->tick_stopped  = 0;
+	ts->idle_exittime = now;
+
+	tick_nohz_restart(ts, now);
+}
+
+static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	unsigned long ticks;
+	/*
+	 * We stopped the tick in idle. Update process times would miss the
+	 * time we slept as update_process_times does only a 1 tick
+	 * accounting. Enforce that this is accounted to idle !
+	 */
+	ticks = jiffies - ts->idle_jiffies;
+	/*
+	 * We might be one off. Do not randomly account a huge number of ticks!
+	 */
+	if (ticks && ticks < LONG_MAX)
+		account_idle_ticks(ticks);
+#endif
+}
+
 /**
  * tick_nohz_idle_exit - restart the idle tick from the idle task
  *
@@ -557,9 +612,6 @@ void tick_nohz_idle_exit(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	unsigned long ticks;
-#endif
 	ktime_t now;
 
 	local_irq_disable();
@@ -574,40 +626,11 @@ void tick_nohz_idle_exit(void)
 	if (ts->idle_active)
 		tick_nohz_stop_idle(cpu, now);
 
-	if (!ts->tick_stopped) {
-		local_irq_enable();
-		return;
+	if (ts->tick_stopped) {
+		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_account_idle_ticks(ts);
 	}
 
-	/* Update jiffies first */
-	select_nohz_load_balancer(0);
-	tick_do_update_jiffies64(now);
-	update_cpu_load_nohz();
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	/*
-	 * We stopped the tick in idle. Update process times would miss the
-	 * time we slept as update_process_times does only a 1 tick
-	 * accounting. Enforce that this is accounted to idle !
-	 */
-	ticks = jiffies - ts->idle_jiffies;
-	/*
-	 * We might be one off. Do not randomly account a huge number of ticks!
-	 */
-	if (ticks && ticks < LONG_MAX)
-		account_idle_ticks(ticks);
-#endif
-
-	calc_load_exit_idle();
-	touch_softlockup_watchdog();
-	/*
-	 * Cancel the scheduled timer and restore the tick
-	 */
-	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;
-
-	tick_nohz_restart(ts, now);
-
 	local_irq_enable();
 }
 
@@ -811,7 +834,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 		 */
 		if (ts->tick_stopped) {
 			touch_softlockup_watchdog();
-			ts->idle_jiffies++;
+			if (idle_cpu(cpu))
+				ts->idle_jiffies++;
 		}
 		update_process_times(user_mode(regs));
 		profile_tick(CPU_PROFILING);
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 3258455549f4..af5a7e9f164b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -167,7 +167,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	{
 		struct tick_sched *ts = tick_get_tick_sched(cpu);
 		P(nohz_mode);
-		P_ns(idle_tick);
+		P_ns(last_tick);
 		P(tick_stopped);
 		P(idle_jiffies);
 		P(idle_calls);
@@ -259,7 +259,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.6\n");
+	SEQ_printf(m, "Timer List Version: v0.7\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 6ec7e7e0db43..a61c09374eba 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -77,6 +77,7 @@ struct tvec_base {
 	struct timer_list *running_timer;
 	unsigned long timer_jiffies;
 	unsigned long next_timer;
+	unsigned long active_timers;
 	struct tvec_root tv1;
 	struct tvec tv2;
 	struct tvec tv3;
@@ -330,7 +331,8 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+static void
+__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
 	unsigned long expires = timer->expires;
 	unsigned long idx = expires - base->timer_jiffies;
@@ -372,6 +374,19 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 	list_add_tail(&timer->entry, vec);
 }
 
+static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+{
+	__internal_add_timer(base, timer);
+	/*
+	 * Update base->active_timers and base->next_timer
+	 */
+	if (!tbase_get_deferrable(timer->base)) {
+		if (time_before(timer->expires, base->next_timer))
+			base->next_timer = timer->expires;
+		base->active_timers++;
+	}
+}
+
 #ifdef CONFIG_TIMER_STATS
 void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
 {
@@ -654,8 +669,7 @@ void init_timer_deferrable_key(struct timer_list *timer,
 }
 EXPORT_SYMBOL(init_timer_deferrable_key);
 
-static inline void detach_timer(struct timer_list *timer,
-				int clear_pending)
+static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 {
 	struct list_head *entry = &timer->entry;
 
@@ -667,6 +681,29 @@ static inline void detach_timer(struct timer_list *timer,
 	entry->prev = LIST_POISON2;
 }
 
+static inline void
+detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
+{
+	detach_timer(timer, true);
+	if (!tbase_get_deferrable(timer->base))
+		timer->base->active_timers--;
+}
+
+static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
+			     bool clear_pending)
+{
+	if (!timer_pending(timer))
+		return 0;
+
+	detach_timer(timer, clear_pending);
+	if (!tbase_get_deferrable(timer->base)) {
+		timer->base->active_timers--;
+		if (timer->expires == base->next_timer)
+			base->next_timer = base->timer_jiffies;
+	}
+	return 1;
+}
+
 /*
  * We are using hashed locking: holding per_cpu(tvec_bases).lock
  * means that all timers which are tied to this base via timer->base are
@@ -712,16 +749,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
 	base = lock_timer_base(timer, &flags);
 
-	if (timer_pending(timer)) {
-		detach_timer(timer, 0);
-		if (timer->expires == base->next_timer &&
-		    !tbase_get_deferrable(timer->base))
-			base->next_timer = base->timer_jiffies;
-		ret = 1;
-	} else {
-		if (pending_only)
-			goto out_unlock;
-	}
+	ret = detach_if_pending(timer, base, false);
+	if (!ret && pending_only)
+		goto out_unlock;
 
 	debug_activate(timer, expires);
 
@@ -752,9 +782,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 	}
 
 	timer->expires = expires;
-	if (time_before(timer->expires, base->next_timer) &&
-	    !tbase_get_deferrable(timer->base))
-		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 
 out_unlock:
@@ -920,9 +947,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	spin_lock_irqsave(&base->lock, flags);
 	timer_set_base(timer, base);
 	debug_activate(timer, timer->expires);
-	if (time_before(timer->expires, base->next_timer) &&
-	    !tbase_get_deferrable(timer->base))
-		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 	/*
 	 * Check whether the other CPU is idle and needs to be
@@ -959,13 +983,7 @@ int del_timer(struct timer_list *timer)
 	timer_stats_timer_clear_start_info(timer);
 	if (timer_pending(timer)) {
 		base = lock_timer_base(timer, &flags);
-		if (timer_pending(timer)) {
-			detach_timer(timer, 1);
-			if (timer->expires == base->next_timer &&
-			    !tbase_get_deferrable(timer->base))
-				base->next_timer = base->timer_jiffies;
-			ret = 1;
-		}
+		ret = detach_if_pending(timer, base, true);
 		spin_unlock_irqrestore(&base->lock, flags);
 	}
 
@@ -990,19 +1008,10 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	base = lock_timer_base(timer, &flags);
 
-	if (base->running_timer == timer)
-		goto out;
-
-	timer_stats_timer_clear_start_info(timer);
-	ret = 0;
-	if (timer_pending(timer)) {
-		detach_timer(timer, 1);
-		if (timer->expires == base->next_timer &&
-		    !tbase_get_deferrable(timer->base))
-			base->next_timer = base->timer_jiffies;
-		ret = 1;
+	if (base->running_timer != timer) {
+		timer_stats_timer_clear_start_info(timer);
+		ret = detach_if_pending(timer, base, true);
 	}
-out:
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
@@ -1089,7 +1098,8 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 	 */
 	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
 		BUG_ON(tbase_get_base(timer->base) != base);
-		internal_add_timer(base, timer);
+		/* No accounting, while moving them */
+		__internal_add_timer(base, timer);
 	}
 
 	return index;
@@ -1178,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base)
 			timer_stats_account_timer(timer);
 
 			base->running_timer = timer;
-			detach_timer(timer, 1);
+			detach_expired_timer(timer, base);
 
 			spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn, data);
@@ -1316,18 +1326,21 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
 unsigned long get_next_timer_interrupt(unsigned long now)
 {
 	struct tvec_base *base = __this_cpu_read(tvec_bases);
-	unsigned long expires;
+	unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
 	 * Possible pending timers will be migrated later to an active cpu.
 	 */
 	if (cpu_is_offline(smp_processor_id()))
-		return now + NEXT_TIMER_MAX_DELTA;
+		return expires;
+
 	spin_lock(&base->lock);
-	if (time_before_eq(base->next_timer, base->timer_jiffies))
-		base->next_timer = __next_timer_interrupt(base);
-	expires = base->next_timer;
+	if (base->active_timers) {
+		if (time_before_eq(base->next_timer, base->timer_jiffies))
+			base->next_timer = __next_timer_interrupt(base);
+		expires = base->next_timer;
+	}
 	spin_unlock(&base->lock);
 
 	if (time_before_eq(expires, now))
@@ -1704,6 +1717,7 @@ static int __cpuinit init_timers_cpu(int cpu)
 
 	base->timer_jiffies = jiffies;
 	base->next_timer = base->timer_jiffies;
+	base->active_timers = 0;
 	return 0;
 }
 
@@ -1714,11 +1728,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea
 
 	while (!list_empty(head)) {
 		timer = list_first_entry(head, struct timer_list, entry);
-		detach_timer(timer, 0);
+		/* We ignore the accounting on the dying cpu */
+		detach_timer(timer, false);
 		timer_set_base(timer, new_base);
-		if (time_before(timer->expires, new_base->next_timer) &&
-		    !tbase_get_deferrable(timer->base))
-			new_base->next_timer = timer->expires;
 		internal_add_timer(new_base, timer);
 	}
 }