[PATCH v8 17/25] timer: Retrieve next expiry of pinned/non-pinned timers separately

[Anna-Maria Behnsen]

For the conversion of the NOHZ timer placement to a pull at expiry time
model it's required to have separate expiry times for the pinned and the
non-pinned (movable) timers. Therefore struct timer_events is introduced.

No functional change

Originally-by: Richard Cochran (linutronix GmbH) <richardcochran@xxxxxxxxx>
Signed-off-by: Anna-Maria Behnsen <anna-maria@xxxxxxxxxxxxx>
Reviewed-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
---
 kernel/time/timer.c | 48 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 37 insertions(+), 11 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 1cd214c2f3f1..4230fc6fa1ed 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -221,6 +221,11 @@ struct timer_base {
 
 static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
 
+struct timer_events {
+	u64	local;
+	u64	global;
+};
+
 #ifdef CONFIG_NO_HZ_COMMON
 
 static DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
@@ -1971,9 +1976,10 @@ static unsigned long next_timer_interrupt(struct timer_base *base)
 	return base->next_expiry;
 }
 
-static inline unsigned long __get_next_timer_interrupt(unsigned long basej,
+static inline unsigned long __get_next_timer_interrupt(unsigned long basej, u64 basem,
 						       struct timer_base *base_local,
-						       struct timer_base *base_global)
+						       struct timer_base *base_global,
+						       struct timer_events *tevt)
 {
 	unsigned long nextevt, nextevt_local, nextevt_global;
 	bool local_first;
@@ -1996,12 +2002,32 @@ static inline unsigned long __get_next_timer_interrupt(unsigned long basej,
 
 	nextevt = local_first ? nextevt_local : nextevt_global;
 
-	if (base_local->timers_pending || base_global->timers_pending) {
+	/*
+	 * If the @nextevt is at max. one tick away, use @nextevt and store
+	 * it in the local expiry value. The next global event is irrelevant in
+	 * this case and can be left as KTIME_MAX.
+	 */
+	if (time_before_eq(nextevt, basej + 1)) {
 		/* If we missed a tick already, force 0 delta */
 		if (time_before(nextevt, basej))
 			nextevt = basej;
+		tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC;
+		return tevt->local;
 	}
 
+	/*
+	 * Update tevt->* values:
+	 *
+	 * If the local queue expires first, then the global event can
+	 * be ignored. If the global queue is empty, nothing to do
+	 * either.
+	 */
+	if (!local_first && base_global->timers_pending)
+		tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC;
+
+	if (base_local->timers_pending)
+		tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC;
+
 	return nextevt;
 }
 
@@ -2015,16 +2041,15 @@ static inline unsigned long __get_next_timer_interrupt(unsigned long basej,
  */
 u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
+	struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX };
 	struct timer_base *base_local, *base_global;
-	u64 expires = KTIME_MAX;
-	unsigned long nextevt;
 
 	/*
 	 * 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 expires;
+		return KTIME_MAX;
 
 	base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
 	base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]);
@@ -2032,14 +2057,14 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 	raw_spin_lock(&base_local->lock);
 	raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
 
-	nextevt = __get_next_timer_interrupt(basej, base_local, base_global);
+	__get_next_timer_interrupt(basej, basem, base_local, base_global, &tevt);
 
 	raw_spin_unlock(&base_global->lock);
 	raw_spin_unlock(&base_local->lock);
 
-	expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
+	tevt.local = min_t(u64, tevt.local, tevt.global);
 
-	return cmp_next_hrtimer_event(basem, expires);
+	return cmp_next_hrtimer_event(basem, tevt.local);
 }
 
 /**
@@ -2055,6 +2080,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
  */
 u64 timer_set_idle(unsigned long basej, u64 basem, bool *idle)
 {
+	struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX };
 	struct timer_base *base_local, *base_global;
 	unsigned long nextevt;
 
@@ -2073,7 +2099,7 @@ u64 timer_set_idle(unsigned long basej, u64 basem, bool *idle)
 	raw_spin_lock(&base_local->lock);
 	raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
 
-	nextevt = __get_next_timer_interrupt(basej, base_local, base_global);
+	nextevt = __get_next_timer_interrupt(basej, basem, base_local, base_global, &tevt);
 
 	/*
 	 * We have a fresh next event. Check whether we can forward the
@@ -2097,7 +2123,7 @@ u64 timer_set_idle(unsigned long basej, u64 basem, bool *idle)
 	raw_spin_unlock(&base_global->lock);
 	raw_spin_unlock(&base_local->lock);
 
-	return basem + (u64)(nextevt - basej) * TICK_NSEC;
+	return min_t(u64, tevt.local, tevt.global);
 }
 
 /**
-- 
2.39.2