[PATCH v2] timers: Recalculate next timer interrupt only when necessary

[Frederic Weisbecker <frederic@kernel.org>]

The nohz tick code recalculates the timer wheel's next expiry on each
idle loop iteration.

On the other hand, the base next expiry is now always cached and updated
upon timer enqueue and execution. Only timer dequeue may leave
base->next_expiry out of date (but then its stale value won't ever go
past the actual next expiry to be recalculated).

Since recalculating the next_expiry isn't a free operation, especially
when the last wheel level is reached to find out that no timer has
been enqueued at all, reuse the next expiry cache when it is known to be
reliable, which it is most of the time.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Anna-Maria Behnsen <anna-maria@linutronix.de>
---
Changes since v1:
_ Fix changelog's ramblings
_ Fix structure layout

 kernel/time/timer.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 77e21e98ec32..96d802e9769e 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -204,6 +204,7 @@ struct timer_base {
 	unsigned long		clk;
 	unsigned long		next_expiry;
 	unsigned int		cpu;
+	bool			next_expiry_recalc;
 	bool			is_idle;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
@@ -593,6 +594,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 		 * can reevaluate the wheel:
 		 */
 		base->next_expiry = bucket_expiry;
+		base->next_expiry_recalc = false;
 		trigger_dyntick_cpu(base, timer);
 	}
 }
@@ -836,8 +838,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
 	if (!timer_pending(timer))
 		return 0;
 
-	if (hlist_is_singular_node(&timer->entry, base->vectors + idx))
+	if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) {
 		__clear_bit(idx, base->pending_map);
+		base->next_expiry_recalc = true;
+	}
 
 	detach_timer(timer, clear_pending);
 	return 1;
@@ -1571,6 +1575,9 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 		clk >>= LVL_CLK_SHIFT;
 		clk += adj;
 	}
+
+	base->next_expiry_recalc = false;
+
 	return next;
 }
 
@@ -1631,9 +1638,11 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		return expires;
 
 	raw_spin_lock(&base->lock);
-	nextevt = __next_timer_interrupt(base);
+	if (base->next_expiry_recalc)
+		base->next_expiry = __next_timer_interrupt(base);
+	nextevt = base->next_expiry;
 	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
-	base->next_expiry = nextevt;
+
 	/*
 	 * We have a fresh next event. Check whether we can forward the
 	 * base. We can only do that when @basej is past base->clk
@@ -1725,6 +1734,12 @@ static inline void __run_timers(struct timer_base *base)
 	while (time_after_eq(jiffies, base->clk) &&
 	       time_after_eq(jiffies, base->next_expiry)) {
 		levels = collect_expired_timers(base, heads);
+		/*
+		 * The only possible reason for not finding any expired
+		 * timer at this clk is that all matching timers have been
+		 * dequeued.
+		 */
+		WARN_ON_ONCE(!levels && !base->next_expiry_recalc);
 		base->clk++;
 		base->next_expiry = __next_timer_interrupt(base);
 
-- 
2.26.2