[PATCH v3 01/36] timers: Use static keys for migrate_enable/nohz_active

[Anna-Maria Gleixner]

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

The members migrate_enable and nohz_active in the timer/hrtimer per CPU
bases have been introduced to avoid accessing global variables for these
decisions.

Still that results in a (cache hot) load and conditional branch, which can
be avoided by using static keys.

Implement it with static keys and optimize for the most critical case of
high performance networking which tends to disable the timer migration
functionality.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
---
 include/linux/hrtimer.h     |  4 --
 kernel/time/hrtimer.c       | 17 +++------
 kernel/time/tick-internal.h | 19 ++++++----
 kernel/time/tick-sched.c    |  2 +-
 kernel/time/timer.c         | 91 +++++++++++++++++++++++----------------------
 5 files changed, 65 insertions(+), 68 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 012c37fdb688..79b2a8d29d8c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -153,8 +153,6 @@ enum  hrtimer_base_type {
  * @cpu:		cpu number
  * @active_bases:	Bitfield to mark bases with active timers
  * @clock_was_set_seq:	Sequence counter of clock was set events
- * @migration_enabled:	The migration of hrtimers to other cpus is enabled
- * @nohz_active:	The nohz functionality is enabled
  * @expires_next:	absolute time of the next event which was scheduled
  *			via clock_set_next_event()
  * @next_timer:		Pointer to the first expiring timer
@@ -178,8 +176,6 @@ struct hrtimer_cpu_base {
 	unsigned int			cpu;
 	unsigned int			active_bases;
 	unsigned int			clock_was_set_seq;
-	bool				migration_enabled;
-	bool				nohz_active;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	unsigned int			in_hrtirq	: 1,
 					hres_active	: 1,
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index d32520840fde..69d203d8b12d 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -178,23 +178,16 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 #endif
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
-					 int pinned)
-{
-	if (pinned || !base->migration_enabled)
-		return base;
-	return &per_cpu(hrtimer_bases, get_nohz_timer_target());
-}
-#else
 static inline
 struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
 					 int pinned)
 {
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+	if (static_branch_unlikely(&timers_migration_enabled) && !pinned)
+		return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+#endif
 	return base;
 }
-#endif
 
 /*
  * We switch the timer base to a power-optimized selected CPU target,
@@ -969,7 +962,7 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * Kick to reschedule the next tick to handle the new timer
 		 * on dynticks target.
 		 */
-		if (new_base->cpu_base->nohz_active)
+		if (is_timers_nohz_active())
 			wake_up_nohz_cpu(new_base->cpu_base->cpu);
 	} else {
 		hrtimer_reprogram(timer, new_base);
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f8e1845aa464..4ac74dff59f0 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -150,14 +150,19 @@ static inline void tick_nohz_init(void) { }
 
 #ifdef CONFIG_NO_HZ_COMMON
 extern unsigned long tick_nohz_active;
-#else
+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
+#else /* CONFIG_NO_HZ_COMMON */
+static inline void timers_update_nohz(void) { }
 #define tick_nohz_active (0)
-#endif
-
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void timers_update_migration(bool update_nohz);
-#else
-static inline void timers_update_migration(bool update_nohz) { }
+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/tick-sched.c b/kernel/time/tick-sched.c
index 99578f06c8d4..f371f25f3510 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1079,7 +1079,7 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
 	ts->nohz_mode = mode;
 	/* One update is enough */
 	if (!test_and_set_bit(0, &tick_nohz_active))
-		timers_update_migration(true);
+		timers_update_nohz();
 }
 
 /**
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ffebcf878fba..1e2140a23044 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -200,8 +200,6 @@ struct timer_base {
 	unsigned long		clk;
 	unsigned long		next_expiry;
 	unsigned int		cpu;
-	bool			migration_enabled;
-	bool			nohz_active;
 	bool			is_idle;
 	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
@@ -210,45 +208,59 @@ struct timer_base {
 
 static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
+
+DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
+static DEFINE_MUTEX(timer_keys_mutex);
+
+static void timer_update_keys(struct work_struct *work);
+static DECLARE_WORK(timer_update_work, timer_update_keys);
+
+#ifdef CONFIG_SMP
 unsigned int sysctl_timer_migration = 1;
 
-void timers_update_migration(bool update_nohz)
+DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
+
+static void timers_update_migration(void)
 {
 	bool on = sysctl_timer_migration && tick_nohz_active;
-	unsigned int cpu;
 
-	/* Avoid the loop, if nothing to update */
-	if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
-		return;
+	if (on)
+		static_branch_enable(&timers_migration_enabled);
+	else
+		static_branch_disable(&timers_migration_enabled);
+}
+#else
+static inline void timers_update_migration(void) { }
+#endif /* !CONFIG_SMP */
 
-	for_each_possible_cpu(cpu) {
-		per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
-		per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
-		per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
-		if (!update_nohz)
-			continue;
-		per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
-		per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
-		per_cpu(hrtimer_bases.nohz_active, cpu) = true;
-	}
+static void timer_update_keys(struct work_struct *work)
+{
+	mutex_lock(&timer_keys_mutex);
+	timers_update_migration();
+	static_branch_enable(&timers_nohz_active);
+	mutex_unlock(&timer_keys_mutex);
+}
+
+void timers_update_nohz(void)
+{
+	schedule_work(&timer_update_work);
 }
 
 int timer_migration_handler(struct ctl_table *table, int write,
 			    void __user *buffer, size_t *lenp,
 			    loff_t *ppos)
 {
-	static DEFINE_MUTEX(mutex);
 	int ret;
 
-	mutex_lock(&mutex);
+	mutex_lock(&timer_keys_mutex);
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write)
-		timers_update_migration(false);
-	mutex_unlock(&mutex);
+		timers_update_migration();
+	mutex_unlock(&timer_keys_mutex);
 	return ret;
 }
-#endif
+#endif /* NO_HZ_COMMON */
 
 static unsigned long round_jiffies_common(unsigned long j, int cpu,
 		bool force_up)
@@ -534,7 +546,7 @@ __internal_add_timer(struct timer_base *base, struct timer_list *timer)
 static void
 trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 {
-	if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+	if (!is_timers_nohz_active())
 		return;
 
 	/*
@@ -826,7 +838,7 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 	 * If the timer is deferrable and nohz is active then we need to use
 	 * the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
+	if (is_timers_nohz_active() &&
 	    (tflags & TIMER_DEFERRABLE))
 		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
 	return base;
@@ -840,7 +852,7 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
 	 * If the timer is deferrable and nohz is active then we need to use
 	 * the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
+	if (is_timers_nohz_active() &&
 	    (tflags & TIMER_DEFERRABLE))
 		base = this_cpu_ptr(&timer_bases[BASE_DEF]);
 	return base;
@@ -851,21 +863,20 @@ static inline struct timer_base *get_timer_base(u32 tflags)
 	return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
 static inline struct timer_base *
 get_target_base(struct timer_base *base, unsigned tflags)
 {
-#ifdef CONFIG_SMP
-	if ((tflags & TIMER_PINNED) || !base->migration_enabled)
-		return get_timer_this_cpu_base(tflags);
-	return get_timer_cpu_base(tflags, get_nohz_timer_target());
-#else
-	return get_timer_this_cpu_base(tflags);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+	if (static_branch_unlikely(&timers_migration_enabled) &&
+	    !(tflags & TIMER_PINNED))
+		return get_timer_cpu_base(tflags, get_nohz_timer_target());
 #endif
+	return get_timer_this_cpu_base(tflags);
 }
 
 static inline void forward_timer_base(struct timer_base *base)
 {
+#ifdef CONFIG_NO_HZ_COMMON
 	unsigned long jnow;
 
 	/*
@@ -889,16 +900,8 @@ static inline void forward_timer_base(struct timer_base *base)
 		base->clk = jnow;
 	else
 		base->clk = base->next_expiry;
-}
-#else
-static inline struct timer_base *
-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) { }
 #endif
+}
 
 
 /*
@@ -1684,7 +1687,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 	base->must_forward_clk = false;
 
 	__run_timers(base);
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+	if (is_timers_nohz_active())
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
 }
 
@@ -1698,7 +1701,7 @@ void run_local_timers(void)
 	hrtimer_run_queues();
 	/* Raise the softirq only if required. */
 	if (time_before(jiffies, base->clk)) {
-		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+		if (!is_timers_nohz_active())
 			return;
 		/* CPU is awake, so check the deferrable base. */
 		base++;
-- 
2.11.0