10 files changed, 283 insertions, 40 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index a55e68f2cfc8..09d05ab262be 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -140,12 +140,14 @@ int cpuidle_idle_call(void)
                 return 0;
         }
 
-        trace_cpu_idle_rcuidle(next_state, dev->cpu);
-
         broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
 
-        if (broadcast)
-                clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+        if (broadcast &&
+            clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+                return -EBUSY;
+
+
+        trace_cpu_idle_rcuidle(next_state, dev->cpu);
 
         if (cpuidle_state_is_coupled(dev, drv, next_state))
                 entered_state = cpuidle_enter_state_coupled(dev, drv,
@@ -153,11 +155,11 @@ int cpuidle_idle_call(void)
         else
                 entered_state = cpuidle_enter_state(dev, drv, next_state);
 
+        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+
         if (broadcast)
                 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
 
-        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
-
         /* give the governor an opportunity to reflect on the outcome */
         if (cpuidle_curr_governor->reflect)
                 cpuidle_curr_governor->reflect(dev, entered_state);
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 493aa021c7a9..2e4cb67f6e56 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -62,6 +62,11 @@ enum clock_event_mode {
 #define CLOCK_EVT_FEAT_DYNIRQ           0x000020
 #define CLOCK_EVT_FEAT_PERCPU           0x000040
 
+/*
+ * Clockevent device is based on a hrtimer for broadcast
+ */
+#define CLOCK_EVT_FEAT_HRTIMER          0x000080
+
 /**
  * struct clock_event_device - clock event device descriptor
  * @event_handler:      Assigned by the framework to be called by the low
@@ -83,6 +88,7 @@ enum clock_event_mode {
  * @name:               ptr to clock event name
  * @rating:             variable to rate clock event devices
  * @irq:                IRQ number (only for non CPU local devices)
+ * @bound_on:           Bound on CPU
  * @cpumask:            cpumask to indicate for which CPUs this device works
  * @list:               list head for the management code
  * @owner:              module reference
@@ -113,6 +119,7 @@ struct clock_event_device {
         const char              *name;
         int                     rating;
         int                     irq;
+        int                     bound_on;
         const struct cpumask    *cpumask;
         struct list_head        list;
         struct module           *owner;
@@ -180,15 +187,17 @@ extern int tick_receive_broadcast(void);
 #endif
 
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void tick_setup_hrtimer_broadcast(void);
 extern int tick_check_broadcast_expired(void);
 #else
 static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
-extern void clockevents_notify(unsigned long reason, void *arg);
+extern int clockevents_notify(unsigned long reason, void *arg);
 #else
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
 #endif
 
 #else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
@@ -196,8 +205,9 @@ static inline void clockevents_notify(unsigned long reason, void *arg) {}
 static inline void clockevents_suspend(void) {}
 static inline void clockevents_resume(void) {}
 
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
 static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
 
 #endif
 
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 3ce6e8c5f3fc..f448513a45ed 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -124,7 +124,7 @@ config NO_HZ_FULL
 endchoice
 
 config NO_HZ_FULL_ALL
-       bool "Full dynticks system on all CPUs by default"
+       bool "Full dynticks system on all CPUs by default (except CPU 0)"
        depends on NO_HZ_FULL
        help
          If the user doesn't pass the nohz_full boot option to
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 9250130646f5..57a413fd0ebf 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)         += clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)     += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y                                          += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT)                     += tick-broadcast-hrtimer.o
+endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)               += sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)                      += tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)                      += tick-sched.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad6043bcb..ad362c260ef4 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -439,6 +439,19 @@ void clockevents_config_and_register(struct clock_event_device *dev,
 }
 EXPORT_SYMBOL_GPL(clockevents_config_and_register);
 
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+        clockevents_config(dev, freq);
+
+        if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+                return clockevents_program_event(dev, dev->next_event, false);
+
+        if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+                dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+
+        return 0;
+}
+
 /**
  * clockevents_update_freq - Update frequency and reprogram a clock event device.
  * @dev:        device to modify
@@ -446,17 +459,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register);
  *
  * Reconfigure and reprogram a clock event device in oneshot
  * mode. Must be called on the cpu for which the device delivers per
- * cpu timer events with interrupts disabled!  Returns 0 on success,
- * -ETIME when the event is in the past.
+ * cpu timer events. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
  */
 int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
-        clockevents_config(dev, freq);
-
-        if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
-                return 0;
+        unsigned long flags;
+        int ret;
 
-        return clockevents_program_event(dev, dev->next_event, false);
+        local_irq_save(flags);
+        ret = tick_broadcast_update_freq(dev, freq);
+        if (ret == -ENODEV)
+                ret = __clockevents_update_freq(dev, freq);
+        local_irq_restore(flags);
+        return ret;
 }
 
 /*
@@ -524,12 +542,13 @@ void clockevents_resume(void)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 /**
  * clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
  */
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
 {
         struct clock_event_device *dev, *tmp;
         unsigned long flags;
-        int cpu;
+        int cpu, ret = 0;
 
         raw_spin_lock_irqsave(&clockevents_lock, flags);
 
@@ -542,7 +561,7 @@ void clockevents_notify(unsigned long reason, void *arg)
 
         case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
         case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
-                tick_broadcast_oneshot_control(reason);
+                ret = tick_broadcast_oneshot_control(reason);
                 break;
 
         case CLOCK_EVT_NOTIFY_CPU_DYING:
@@ -585,6 +604,7 @@ void clockevents_notify(unsigned long reason, void *arg)
                 break;
         }
         raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+        return ret;
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index af8d1d4f3d55..419a52cecd20 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -514,12 +514,13 @@ static void sync_cmos_clock(struct work_struct *work)
                 next.tv_sec++;
                 next.tv_nsec -= NSEC_PER_SEC;
         }
-        schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+        queue_delayed_work(system_power_efficient_wq,
+                           &sync_cmos_work, timespec_to_jiffies(&next));
 }
 
 void ntp_notify_cmos_timer(void)
 {
-        schedule_delayed_work(&sync_cmos_work, 0);
+        queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
 }
 
 #else
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 000000000000..eb682d5c697c
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+                        struct clock_event_device *bc)
+{
+        switch (mode) {
+        case CLOCK_EVT_MODE_SHUTDOWN:
+                /*
+                 * Note, we cannot cancel the timer here as we might
+                 * run into the following live lock scenario:
+                 *
+                 * cpu 0                cpu1
+                 * lock(broadcast_lock);
+                 *                      hrtimer_interrupt()
+                 *                      bc_handler()
+                 *                         tick_handle_oneshot_broadcast();
+                 *                          lock(broadcast_lock);
+                 * hrtimer_cancel()
+                 *  wait_for_callback()
+                 */
+                hrtimer_try_to_cancel(&bctimer);
+                break;
+        default:
+                break;
+        }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+        /*
+         * We try to cancel the timer first. If the callback is on
+         * flight on some other cpu then we let it handle it. If we
+         * were able to cancel the timer nothing can rearm it as we
+         * own broadcast_lock.
+         *
+         * However we can also be called from the event handler of
+         * ce_broadcast_hrtimer itself when it expires. We cannot
+         * restart the timer because we are in the callback, but we
+         * can set the expiry time and let the callback return
+         * HRTIMER_RESTART.
+         */
+        if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+                hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+                /* Bind the "device" to the cpu */
+                bc->bound_on = smp_processor_id();
+        } else if (bc->bound_on == smp_processor_id()) {
+                hrtimer_set_expires(&bctimer, expires);
+        }
+        return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+        .set_mode               = bc_set_mode,
+        .set_next_ktime         = bc_set_next,
+        .features               = CLOCK_EVT_FEAT_ONESHOT |
+                                  CLOCK_EVT_FEAT_KTIME |
+                                  CLOCK_EVT_FEAT_HRTIMER,
+        .rating                 = 0,
+        .bound_on               = -1,
+        .min_delta_ns           = 1,
+        .max_delta_ns           = KTIME_MAX,
+        .min_delta_ticks        = 1,
+        .max_delta_ticks        = ULONG_MAX,
+        .mult                   = 1,
+        .shift                  = 0,
+        .cpumask                = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+        ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+        if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+                return HRTIMER_NORESTART;
+
+        return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+        hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+        bctimer.function = bc_handler;
+        clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 98977a57ac72..64c5990fd500 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -120,6 +120,19 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
         return (dev && tick_broadcast_device.evtdev == dev);
 }
 
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq)
+{
+        int ret = -ENODEV;
+
+        if (tick_is_broadcast_device(dev)) {
+                raw_spin_lock(&tick_broadcast_lock);
+                ret = __clockevents_update_freq(dev, freq);
+                raw_spin_unlock(&tick_broadcast_lock);
+        }
+        return ret;
+}
+
+
 static void err_broadcast(const struct cpumask *mask)
 {
         pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
@@ -272,12 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask)
  */
 static void tick_do_periodic_broadcast(void)
 {
-        raw_spin_lock(&tick_broadcast_lock);
-
         cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
         tick_do_broadcast(tmpmask);
-
-        raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -287,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
         ktime_t next;
 
+        raw_spin_lock(&tick_broadcast_lock);
+
         tick_do_periodic_broadcast();
 
         /*
          * The device is in periodic mode. No reprogramming necessary:
          */
         if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
-                return;
+                goto unlock;
 
         /*
          * Setup the next period for devices, which do not have
@@ -306,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
                 next = ktime_add(next, tick_period);
 
                 if (!clockevents_program_event(dev, next, false))
-                        return;
+                        goto unlock;
                 tick_do_periodic_broadcast();
         }
+unlock:
+        raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -630,24 +643,61 @@ again:
         raw_spin_unlock(&tick_broadcast_lock);
 }
 
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+        if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+                return 0;
+        if (bc->next_event.tv64 == KTIME_MAX)
+                return 0;
+        return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+                                     struct clock_event_device *dev)
+{
+        /*
+         * For hrtimer based broadcasting we cannot shutdown the cpu
+         * local device if our own event is the first one to expire or
+         * if we own the broadcast timer.
+         */
+        if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+                if (broadcast_needs_cpu(bc, smp_processor_id()))
+                        return;
+                if (dev->next_event.tv64 < bc->next_event.tv64)
+                        return;
+        }
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+        struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+        if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+                return;
+        /* This moves the broadcast assignment to this cpu */
+        clockevents_program_event(bc, bc->next_event, 1);
+}
+
 /*
  * Powerstate information: The system enters/leaves a state, where
  * affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
  */
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
 {
         struct clock_event_device *bc, *dev;
         struct tick_device *td;
         unsigned long flags;
         ktime_t now;
-        int cpu;
+        int cpu, ret = 0;
 
         /*
          * Periodic mode does not care about the enter/exit of power
          * states
          */
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-                return;
+                return 0;
 
         /*
          * We are called with preemtion disabled from the depth of the
@@ -658,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         dev = td->evtdev;
 
         if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-                return;
+                return 0;
 
         bc = tick_broadcast_device.evtdev;
 
@@ -666,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
                 if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
                         WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
-                        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+                        broadcast_shutdown_local(bc, dev);
                         /*
                          * We only reprogram the broadcast timer if we
                          * did not mark ourself in the force mask and
@@ -679,6 +729,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
                             dev->next_event.tv64 < bc->next_event.tv64)
                                 tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
                 }
+                /*
+                 * If the current CPU owns the hrtimer broadcast
+                 * mechanism, it cannot go deep idle and we remove the
+                 * CPU from the broadcast mask. We don't have to go
+                 * through the EXIT path as the local timer is not
+                 * shutdown.
+                 */
+                ret = broadcast_needs_cpu(bc, cpu);
+                if (ret)
+                        cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
         } else {
                 if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -746,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         }
 out:
         raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+        return ret;
 }
 
 /*
@@ -852,6 +913,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
         cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
         cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
+        broadcast_move_bc(cpu);
+
         raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 8329669b51ec..7ab92b19965a 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -46,7 +46,7 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
 extern void tick_resume_oneshot(void);
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -58,7 +58,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
         BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
@@ -87,7 +87,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
         BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
@@ -111,6 +111,7 @@ extern int tick_resume_broadcast(void);
 extern void tick_broadcast_init(void);
 extern void
 tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
 
 #else /* !BROADCAST */
 
@@ -133,6 +134,8 @@ static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline int tick_resume_broadcast(void) { return 0; }
 static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
+                                             u32 freq) { return -ENODEV; }
 
 /*
  * Set the periodic handler in non broadcast mode
@@ -152,6 +155,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
         return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
 
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
 #endif
 
 extern void do_timer(unsigned long ticks);
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd241b9e5..a71bdfdb51e7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -81,6 +81,7 @@ struct tvec_base {
         unsigned long timer_jiffies;
         unsigned long next_timer;
         unsigned long active_timers;
+        unsigned long all_timers;
         struct tvec_root tv1;
         struct tvec tv2;
         struct tvec tv3;
@@ -337,6 +338,20 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
+/*
+ * If the list is empty, catch up ->timer_jiffies to the current time.
+ * The caller must hold the tvec_base lock.  Returns true if the list
+ * was empty and therefore ->timer_jiffies was updated.
+ */
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+        if (!base->all_timers) {
+                base->timer_jiffies = jiffies;
+                return true;
+        }
+        return false;
+}
+
 static void
 __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
@@ -383,15 +398,17 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
+        (void)catchup_timer_jiffies(base);
         __internal_add_timer(base, timer);
         /*
          * Update base->active_timers and base->next_timer
          */
         if (!tbase_get_deferrable(timer->base)) {
-                if (time_before(timer->expires, base->next_timer))
+                if (!base->active_timers++ ||
+                    time_before(timer->expires, base->next_timer))
                         base->next_timer = timer->expires;
-                base->active_timers++;
         }
+        base->all_timers++;
 }
 
 #ifdef CONFIG_TIMER_STATS
@@ -671,6 +688,8 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
         detach_timer(timer, true);
         if (!tbase_get_deferrable(timer->base))
                 base->active_timers--;
+        base->all_timers--;
+        (void)catchup_timer_jiffies(base);
 }
 
 static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
@@ -685,6 +704,8 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
                 if (timer->expires == base->next_timer)
                         base->next_timer = base->timer_jiffies;
         }
+        base->all_timers--;
+        (void)catchup_timer_jiffies(base);
         return 1;
 }
 
@@ -939,8 +960,15 @@ void add_timer_on(struct timer_list *timer, int cpu)
          * with the timer by holding the timer base lock. This also
          * makes sure that a CPU on the way to stop its tick can not
          * evaluate the timer wheel.
+         *
+         * Spare the IPI for deferrable timers on idle targets though.
+         * The next busy ticks will take care of it. Except full dynticks
+         * require special care against races with idle_cpu(), lets deal
+         * with that later.
          */
-        wake_up_nohz_cpu(cpu);
+        if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu))
+                wake_up_nohz_cpu(cpu);
+
         spin_unlock_irqrestore(&base->lock, flags);
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
@@ -1146,6 +1174,10 @@ static inline void __run_timers(struct tvec_base *base)
         struct timer_list *timer;
 
         spin_lock_irq(&base->lock);
+        if (catchup_timer_jiffies(base)) {
+                spin_unlock_irq(&base->lock);
+                return;
+        }
         while (time_after_eq(jiffies, base->timer_jiffies)) {
                 struct list_head work_list;
                 struct list_head *head = &work_list;
@@ -1559,6 +1591,7 @@ static int init_timers_cpu(int cpu)
         base->timer_jiffies = jiffies;
         base->next_timer = base->timer_jiffies;
         base->active_timers = 0;
+        base->all_timers = 0;
         return 0;
 }