[tip:timers/core] hrtimer: Unify remote enqueue handling

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  14c803419de6acba08e143d51813ac5e0f3443b8
Gitweb:     https://git.kernel.org/tip/14c803419de6acba08e143d51813ac5e0f3443b8
Author:     Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
AuthorDate: Thu, 21 Dec 2017 11:41:49 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 16 Jan 2018 02:53:58 +0100

hrtimer: Unify remote enqueue handling

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
case:

  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
not:

  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
    hrtimer_start_range_ns()

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

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

Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: John Stultz <john.stultz@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: keescook@xxxxxxxxxxxx
Link: http://lkml.kernel.org/r/20171221104205.7269-21-anna-maria@xxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 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 e6a78ae..1c68bf2 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -685,21 +685,24 @@ 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)
 		return;
 
 	/*
 	 * 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);
 }
 
@@ -936,16 +939,7 @@ 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:
 	unlock_hrtimer_base(timer, &flags);
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f690628..e277284 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -151,18 +151,12 @@ static inline void tick_nohz_init(void) { }
 #ifdef CONFIG_NO_HZ_COMMON
 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_likely(&timers_nohz_active);
-}
 # ifdef CONFIG_SMP
 extern struct static_key_false timers_migration_enabled;
 # endif
 #else /* CONFIG_NO_HZ_COMMON */
 static inline void timers_update_nohz(void) { }
 #define tick_nohz_active (0)
-static inline bool is_timers_nohz_active(void) { return false; }
 #endif
 
 DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index d530f72..48150ab 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]);
 
 #ifdef CONFIG_NO_HZ_COMMON
 
-DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
+static DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
 static DEFINE_MUTEX(timer_keys_mutex);
 
 static void timer_update_keys(struct work_struct *work);
@@ -258,6 +258,13 @@ int timer_migration_handler(struct ctl_table *table, int write,
 	mutex_unlock(&timer_keys_mutex);
 	return ret;
 }
+
+static inline bool is_timers_nohz_active(void)
+{
+	return static_branch_unlikely(&timers_nohz_active);
+}
+#else
+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,