[PATCH v4 20/36] hrtimer: Unify handling of remote enqueue

From: Anna-Maria Gleixner
Date: Thu Dec 21 2017 - 05:46:52 EST

hrtimer_reprogram() is conditionally invoked from hrtimer_start_range_ns()
when hrtimer_cpu_base.hres_active is true.

In the !hres_active case there is a special condition for the nohz_active

If the newly enqueued timer expires before the first expiring timer on a
remote CPU then the remote CPU needs to be notified and woken up from a
NOHZ idle sleep to take the new first expiring timer into account.

Previous changes have already established the prerequisites to make the
remote enqueue behaviour the same whether high resolution mode is active or

If the to be enqueued timer expires before the first expiring timer on a
remote CPU, then it cannot be enqueued there.

This was done for the high resolution mode because there is no way to
access the remote CPU timer hardware. The same is true for NOHZ, but was
handled differently by unconditionally enqueuing the timer and waking up
the remote CPU so it can reprogram its timer. Again there is no compelling
reason for this difference.

hrtimer_check_target(), which makes the 'can remote enqueue' decision is
already unconditional, but not yet functional because nothing updates
hrtimer_cpu_base.expires_next in the !hres_active case.

To unify this the following changes are required:

1) Make the store of the new first expiry time unconditonal in
hrtimer_reprogram() and check __hrtimer_hres_active() before proceeding
to the actual hardware access. This check also lets the compiler
eliminate the rest of the function in case of CONFIG_HIGH_RES_TIMERS=n.

2) Invoke hrtimer_reprogram() unconditionally from

3) Remove the remote wakeup special case for the !high_res && nohz_active

Confine the timers_nohz_active static key to timer.c which is the only user

Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
kernel/time/hrtimer.c | 18 ++++++------------
kernel/time/tick-internal.h | 6 ------
kernel/time/timer.c | 9 ++++++++-
3 files changed, 14 insertions(+), 19 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index dd202c796662..c8528b932247 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -687,21 +687,24 @@ static void hrtimer_reprogram(struct hrtimer *timer,

/* Update the pointer to the next expiring timer */
cpu_base->next_timer = timer;
+ cpu_base->expires_next = expires;

+ * If hres is not active, hardware does not have to be
+ * programmed yet.
+ *
* If a hang was detected in the last timer interrupt then we
* do not schedule a timer which is earlier than the expiry
* which we enforced in the hang detection. We want the system
* to make progress.
- if (cpu_base->hang_detected)
+ if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)

* Program the timer hardware. We enforce the expiry for
* events which are already in the past.
- cpu_base->expires_next = expires;
tick_program_event(expires, 1);

@@ -938,16 +941,7 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
if (!leftmost)
goto unlock;

- if (!hrtimer_is_hres_active(timer)) {
- /*
- * Kick to reschedule the next tick to handle the new timer
- * on dynticks target.
- */
- if (is_timers_nohz_active())
- wake_up_nohz_cpu(new_base->cpu_base->cpu);
- } else {
- hrtimer_reprogram(timer, new_base);
- }
+ hrtimer_reprogram(timer, new_base);
unlock_hrtimer_base(timer, &flags);
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 4ac74dff59f0..e277284c2831 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -151,18 +151,12 @@ static inline void tick_nohz_init(void) { }
extern unsigned long tick_nohz_active;
extern void timers_update_nohz(void);
-extern struct static_key_false timers_nohz_active;
-static inline bool is_timers_nohz_active(void)
- return static_branch_unlikely(&timers_nohz_active);
# ifdef CONFIG_SMP
extern struct static_key_false timers_migration_enabled;
# endif
static inline void timers_update_nohz(void) { }
#define tick_nohz_active (0)
-static inline bool is_timers_nohz_active(void) { return false; }

DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 1e2140a23044..4b39029fbe99 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -210,7 +210,7 @@ static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);


+static DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
static DEFINE_MUTEX(timer_keys_mutex);

static void timer_update_keys(struct work_struct *work);
@@ -260,6 +260,13 @@ int timer_migration_handler(struct ctl_table *table, int write,
return ret;
+static inline bool is_timers_nohz_active(void)
+ return static_branch_unlikely(&timers_nohz_active);
+static inline bool is_timers_nohz_active(void) { return false; }
#endif /* NO_HZ_COMMON */

static unsigned long round_jiffies_common(unsigned long j, int cpu,