1 files changed, 63 insertions, 47 deletions

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 63a8ce7177dd..352b161113cd 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -571,18 +571,15 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk,
 static void
 trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 {
-	if (!is_timers_nohz_active())
-		return;
-
 	/*
-	 * TODO: This wants some optimizing similar to the code below, but we
-	 * will do that when we switch from push to pull for deferrable timers.
+	 * Deferrable timers do not prevent the CPU from entering dynticks and
+	 * are not taken into account on the idle/nohz_full path. An IPI when a
+	 * new deferrable timer is enqueued will wake up the remote CPU but
+	 * nothing will be done with the deferrable timer base. Therefore skip
+	 * the remote IPI for deferrable timers completely.
 	 */
-	if (timer->flags & TIMER_DEFERRABLE) {
-		if (tick_nohz_full_cpu(base->cpu))
-			wake_up_nohz_cpu(base->cpu);
+	if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE)
 		return;
-	}
 
 	/*
 	 * We might have to IPI the remote CPU if the base is idle and the
@@ -606,7 +603,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
 
-	trace_timer_start(timer, timer->expires, timer->flags);
+	trace_timer_start(timer, bucket_expiry);
 
 	/*
 	 * Check whether this is the new first expiring timer. The
@@ -942,31 +939,34 @@ get_target_base(struct timer_base *base, unsigned tflags)
 	return get_timer_this_cpu_base(tflags);
 }
 
-static inline void forward_timer_base(struct timer_base *base)
+static inline void __forward_timer_base(struct timer_base *base,
+					unsigned long basej)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
-
 	/*
-	 * No need to forward if we are close enough below jiffies.
-	 * Also while executing timers, base->clk is 1 offset ahead
-	 * of jiffies to avoid endless requeuing to current jiffies.
+	 * Check whether we can forward the base. We can only do that when
+	 * @basej is past base->clk otherwise we might rewind base->clk.
 	 */
-	if ((long)(jnow - base->clk) < 1)
+	if (time_before_eq(basej, base->clk))
 		return;
 
 	/*
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jnow)) {
-		base->clk = jnow;
+	if (time_after(base->next_expiry, basej)) {
+		base->clk = basej;
 	} else {
 		if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
 			return;
 		base->clk = base->next_expiry;
 	}
+
 }
 
+static inline void forward_timer_base(struct timer_base *base)
+{
+	__forward_timer_base(base, READ_ONCE(jiffies));
+}
 
 /*
  * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -1803,8 +1803,10 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset,
 /*
  * Search the first expiring timer in the various clock levels. Caller must
  * hold base->lock.
+ *
+ * Store next expiry time in base->next_expiry.
  */
-static unsigned long __next_timer_interrupt(struct timer_base *base)
+static void next_expiry_recalc(struct timer_base *base)
 {
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
@@ -1870,10 +1872,9 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 		clk += adj;
 	}
 
+	base->next_expiry = next;
 	base->next_expiry_recalc = false;
 	base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
-
-	return next;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -1921,8 +1922,9 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA;
 	u64 expires = KTIME_MAX;
-	unsigned long nextevt;
+	bool was_idle;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1933,37 +1935,44 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 
 	raw_spin_lock(&base->lock);
 	if (base->next_expiry_recalc)
-		base->next_expiry = __next_timer_interrupt(base);
-	nextevt = base->next_expiry;
+		next_expiry_recalc(base);
 
 	/*
 	 * We have a fresh next event. Check whether we can forward the
-	 * base. We can only do that when @basej is past base->clk
-	 * otherwise we might rewind base->clk.
+	 * base.
 	 */
-	if (time_after(basej, base->clk)) {
-		if (time_after(nextevt, basej))
-			base->clk = basej;
-		else if (time_after(nextevt, base->clk))
-			base->clk = nextevt;
-	}
+	__forward_timer_base(base, basej);
 
-	if (time_before_eq(nextevt, basej)) {
-		expires = basem;
-		base->is_idle = false;
+	if (base->timers_pending) {
+		nextevt = base->next_expiry;
+
+		/* If we missed a tick already, force 0 delta */
+		if (time_before(nextevt, basej))
+			nextevt = basej;
+		expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 	} else {
-		if (base->timers_pending)
-			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle.
-		 * Also the tick is stopped so any added timer must forward
-		 * the base clk itself to keep granularity small. This idle
-		 * logic is only maintained for the BASE_STD base, deferrable
-		 * timers may still see large granularity skew (by design).
+		 * Move next_expiry for the empty base into the future to
+		 * prevent a unnecessary raise of the timer softirq when the
+		 * next_expiry value will be reached even if there is no timer
+		 * pending.
 		 */
-		if ((expires - basem) > TICK_NSEC)
-			base->is_idle = true;
+		base->next_expiry = nextevt;
 	}
+
+	/*
+	 * Base is idle if the next event is more than a tick away.
+	 *
+	 * If the base is marked idle then any timer add operation must forward
+	 * the base clk itself to keep granularity small. This idle logic is
+	 * only maintained for the BASE_STD base, deferrable timers may still
+	 * see large granularity skew (by design).
+	 */
+	was_idle = base->is_idle;
+	base->is_idle = time_after(nextevt, basej + 1);
+	if (was_idle != base->is_idle)
+		trace_timer_base_idle(base->is_idle, base->cpu);
+
 	raw_spin_unlock(&base->lock);
 
 	return cmp_next_hrtimer_event(basem, expires);
@@ -1984,7 +1993,10 @@ void timer_clear_idle(void)
 	 * sending the IPI a few instructions smaller for the cost of taking
 	 * the lock in the exit from idle path.
 	 */
-	base->is_idle = false;
+	if (base->is_idle) {
+		base->is_idle = false;
+		trace_timer_base_idle(false, smp_processor_id());
+	}
 }
 #endif
 
@@ -2015,8 +2027,12 @@ static inline void __run_timers(struct timer_base *base)
 		 */
 		WARN_ON_ONCE(!levels && !base->next_expiry_recalc
 			     && base->timers_pending);
+		/*
+		 * While executing timers, base->clk is set 1 offset ahead of
+		 * jiffies to avoid endless requeuing to current jiffies.
+		 */
 		base->clk++;
-		base->next_expiry = __next_timer_interrupt(base);
+		next_expiry_recalc(base);
 
 		while (levels--)
 			expire_timers(base, heads + levels);