Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Ingo Molnar:
 "This cycle had the following changes:

   - Timer tracing improvements (Anna-Maria Gleixner)

   - Continued tasklet reduction work: remove the hrtimer_tasklet
     (Thomas Gleixner)

   - Fix CPU hotplug remove race in the tick-broadcast mask handling
     code (Thomas Gleixner)

   - Force upper bound for setting CLOCK_REALTIME, to fix ABI
     inconsistencies with handling values that are close to the maximum
     supported and the vagueness of when uptime related wraparound might
     occur. Make the consistent maximum the year 2232 across all
     relevant ABIs and APIs. (Thomas Gleixner)

   - various cleanups and smaller fixes"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tick: Fix typos in comments
  tick/broadcast: Fix warning about undefined tick_broadcast_oneshot_offline()
  timekeeping: Force upper bound for setting CLOCK_REALTIME
  timer/trace: Improve timer tracing
  timer/trace: Replace deprecated vsprintf pointer extension %pf by %ps
  timer: Move trace point to get proper index
  tick/sched: Update tick_sched struct documentation
  tick: Remove outgoing CPU from broadcast masks
  timekeeping: Consistently use unsigned int for seqcount snapshot
  softirq: Remove tasklet_hrtimer
  xfrm: Replace hrtimer tasklet with softirq hrtimer
  mac80211_hwsim: Replace hrtimer tasklet with softirq hrtimer

drivers/net/wireless/mac80211_hwsim.c

@@ -521,7 +521,7 @@ struct mac80211_hwsim_data {
 	unsigned int rx_filter;
 	bool started, idle, scanning;
 	struct mutex mutex;
-	struct tasklet_hrtimer beacon_timer;
+	struct hrtimer beacon_timer;
 	enum ps_mode {
 		PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
 	} ps;
@@ -1460,7 +1460,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 {
 	struct mac80211_hwsim_data *data = hw->priv;
 	data->started = false;
-	tasklet_hrtimer_cancel(&data->beacon_timer);
+	hrtimer_cancel(&data->beacon_timer);
 	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 }
 
@@ -1583,14 +1583,12 @@ static enum hrtimer_restart
 mac80211_hwsim_beacon(struct hrtimer *timer)
 {
 	struct mac80211_hwsim_data *data =
-		container_of(timer, struct mac80211_hwsim_data,
-			     beacon_timer.timer);
+		container_of(timer, struct mac80211_hwsim_data, beacon_timer);
 	struct ieee80211_hw *hw = data->hw;
 	u64 bcn_int = data->beacon_int;
-	ktime_t next_bcn;
 
 	if (!data->started)
-		goto out;
+		return HRTIMER_NORESTART;
 
 	ieee80211_iterate_active_interfaces_atomic(
 		hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -1601,12 +1599,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer)
 		bcn_int -= data->bcn_delta;
 		data->bcn_delta = 0;
 	}
-
-	next_bcn = ktime_add(hrtimer_get_expires(timer),
-			     ns_to_ktime(bcn_int * 1000));
-	tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
-	return HRTIMER_NORESTART;
+	hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+			ns_to_ktime(bcn_int * NSEC_PER_USEC));
+	return HRTIMER_RESTART;
 }
 
 static const char * const hwsim_chanwidths[] = {
@@ -1680,15 +1675,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 	mutex_unlock(&data->mutex);
 
 	if (!data->started || !data->beacon_int)
-		tasklet_hrtimer_cancel(&data->beacon_timer);
-	else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+		hrtimer_cancel(&data->beacon_timer);
+	else if (!hrtimer_is_queued(&data->beacon_timer)) {
 		u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
 		u32 bcn_int = data->beacon_int;
 		u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
 
-		tasklet_hrtimer_start(&data->beacon_timer,
-				      ns_to_ktime(until_tbtt * 1000),
-				      HRTIMER_MODE_REL);
+		hrtimer_start(&data->beacon_timer,
+			      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+			      HRTIMER_MODE_REL_SOFT);
 	}
 
 	return 0;
@@ -1751,7 +1746,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			  info->enable_beacon, info->beacon_int);
 		vp->bcn_en = info->enable_beacon;
 		if (data->started &&
-		    !hrtimer_is_queued(&data->beacon_timer.timer) &&
+		    !hrtimer_is_queued(&data->beacon_timer) &&
 		    info->enable_beacon) {
 			u64 tsf, until_tbtt;
 			u32 bcn_int;
@@ -1759,9 +1754,10 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			tsf = mac80211_hwsim_get_tsf(hw, vif);
 			bcn_int = data->beacon_int;
 			until_tbtt = bcn_int - do_div(tsf, bcn_int);
-			tasklet_hrtimer_start(&data->beacon_timer,
-					      ns_to_ktime(until_tbtt * 1000),
-					      HRTIMER_MODE_REL);
+
+			hrtimer_start(&data->beacon_timer,
+				      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL_SOFT);
 		} else if (!info->enable_beacon) {
 			unsigned int count = 0;
 			ieee80211_iterate_active_interfaces_atomic(
@@ -1770,7 +1766,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			wiphy_dbg(hw->wiphy, "  beaconing vifs remaining: %u",
 				  count);
 			if (count == 0) {
-				tasklet_hrtimer_cancel(&data->beacon_timer);
+				hrtimer_cancel(&data->beacon_timer);
 				data->beacon_int = 0;
 			}
 		}
@@ -2933,9 +2929,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
-	tasklet_hrtimer_init(&data->beacon_timer,
-			     mac80211_hwsim_beacon,
-			     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_ABS_SOFT);
+	data->beacon_timer.function = mac80211_hwsim_beacon;
 
 	err = ieee80211_register_hw(hw);
 	if (err < 0) {

include/linux/interrupt.h

@@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
 			 void (*func)(unsigned long), unsigned long data);
 
-struct tasklet_hrtimer {
-	struct hrtimer		timer;
-	struct tasklet_struct	tasklet;
-	enum hrtimer_restart	(*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-		     enum hrtimer_restart (*function)(struct hrtimer *),
-		     clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-			   const enum hrtimer_mode mode)
-{
-	hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
-	hrtimer_cancel(&ttimer->timer);
-	tasklet_kill(&ttimer->tasklet);
-}
-
 /*
  * Autoprobing for irqs:
  *

include/linux/tick.h

@@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode);
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_offline_cpu(unsigned int cpu);
+#else
+static inline void tick_offline_cpu(unsigned int cpu) { }
+#endif
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else

include/linux/time64.h

@@ -33,6 +33,17 @@ struct itimerspec64 {
 #define KTIME_MAX			((s64)~((u64)1 << 63))
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 
+/*
+ * Limits for settimeofday():
+ *
+ * To prevent setting the time close to the wraparound point time setting
+ * is limited so a reasonable uptime can be accomodated. Uptime of 30 years
+ * should be really sufficient, which means the cutoff is 2232. At that
+ * point the cutoff is just a small part of the larger problem.
+ */
+#define TIME_UPTIME_SEC_MAX		(30LL * 365 * 24 *3600)
+#define TIME_SETTOD_SEC_MAX		(KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX)
+
 static inline int timespec64_equal(const struct timespec64 *a,
 				   const struct timespec64 *b)
 {
@@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts)
 	return true;
 }
 
+static inline bool timespec64_valid_settod(const struct timespec64 *ts)
+{
+	if (!timespec64_valid(ts))
+		return false;
+	/* Disallow values which cause overflow issues vs. CLOCK_REALTIME */
+	if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX)
+		return false;
+	return true;
+}
+
 /**
  * timespec64_to_ns - Convert timespec64 to nanoseconds
  * @ts:		pointer to the timespec64 variable to be converted

include/net/xfrm.h

@@ -219,7 +219,7 @@ struct xfrm_state {
 	struct xfrm_stats	stats;
 
 	struct xfrm_lifetime_cur curlft;
-	struct tasklet_hrtimer	mtimer;
+	struct hrtimer		mtimer;
 
 	struct xfrm_state_offload xso;
 

include/trace/events/timer.h

@@ -73,7 +73,7 @@ TRACE_EVENT(timer_start,
 		__entry->flags		= flags;
 	),
 
-	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now,
 		  __entry->flags & TIMER_CPUMASK,
@@ -89,23 +89,27 @@ TRACE_EVENT(timer_start,
  */
 TRACE_EVENT(timer_expire_entry,
 
-	TP_PROTO(struct timer_list *timer),
+	TP_PROTO(struct timer_list *timer, unsigned long baseclk),
 
-	TP_ARGS(timer),
+	TP_ARGS(timer, baseclk),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer	)
 		__field( unsigned long,	now	)
 		__field( void *,	function)
+		__field( unsigned long,	baseclk	)
 	),
 
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->now		= jiffies;
 		__entry->function	= timer->function;
+		__entry->baseclk	= baseclk;
 	),
 
-	TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
+	TP_printk("timer=%p function=%ps now=%lu baseclk=%lu",
+		  __entry->timer, __entry->function, __entry->now,
+		  __entry->baseclk)
 );
 
 /**
@@ -210,7 +214,7 @@ TRACE_EVENT(hrtimer_start,
 		__entry->mode		= mode;
 	),
 
-	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+	TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu "
 		  "mode=%s", __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->expires,
 		  (unsigned long long) __entry->softexpires,
@@ -243,7 +247,8 @@ TRACE_EVENT(hrtimer_expire_entry,
 		__entry->function	= hrtimer->function;
 	),
 
-	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
+	TP_printk("hrtimer=%p function=%ps now=%llu",
+		  __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->now)
 );
 

kernel/cpu.c

@@ -861,6 +861,8 @@ static int take_cpu_down(void *_param)
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(cpu);
 	/* Park the stopper thread */
 	stop_machine_park(cpu);
 	return 0;

kernel/softirq.c

@@ -573,57 +573,6 @@ void tasklet_kill(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(tasklet_kill);
 
-/*
- * tasklet_hrtimer
- */
-
-/*
- * The trampoline is called when the hrtimer expires. It schedules a tasklet
- * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
- * hrtimer callback, but from softirq context.
- */
-static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
-{
-	struct tasklet_hrtimer *ttimer =
-		container_of(timer, struct tasklet_hrtimer, timer);
-
-	tasklet_hi_schedule(&ttimer->tasklet);
-	return HRTIMER_NORESTART;
-}
-
-/*
- * Helper function which calls the hrtimer callback from
- * tasklet/softirq context
- */
-static void __tasklet_hrtimer_trampoline(unsigned long data)
-{
-	struct tasklet_hrtimer *ttimer = (void *)data;
-	enum hrtimer_restart restart;
-
-	restart = ttimer->function(&ttimer->timer);
-	if (restart != HRTIMER_NORESTART)
-		hrtimer_restart(&ttimer->timer);
-}
-
-/**
- * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
- * @ttimer:	 tasklet_hrtimer which is initialized
- * @function:	 hrtimer callback function which gets called from softirq context
- * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
- * @mode:	 hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
- */
-void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-			  enum hrtimer_restart (*function)(struct hrtimer *),
-			  clockid_t which_clock, enum hrtimer_mode mode)
-{
-	hrtimer_init(&ttimer->timer, which_clock, mode);
-	ttimer->timer.function = __hrtimer_tasklet_trampoline;
-	tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
-		     (unsigned long)ttimer);
-	ttimer->function = function;
-}
-EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-
 void __init softirq_init(void)
 {
 	int cpu;

kernel/time/clockevents.c

@@ -611,6 +611,22 @@ void clockevents_resume(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+/**
+ * tick_offline_cpu - Take CPU out of the broadcast mechanism
+ * @cpu:	The outgoing CPU
+ *
+ * Called on the outgoing CPU after it took itself offline.
+ */
+void tick_offline_cpu(unsigned int cpu)
+{
+	raw_spin_lock(&clockevents_lock);
+	tick_broadcast_offline(cpu);
+	raw_spin_unlock(&clockevents_lock);
+}
+# endif
+
 /**
  * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
  */
@@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu)
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	tick_shutdown_broadcast_oneshot(cpu);
-	tick_shutdown_broadcast(cpu);
 	tick_shutdown(cpu);
 	/*
 	 * Unregister the clock event devices which were

kernel/time/jiffies.c

@@ -63,7 +63,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {

kernel/time/sched_clock.c

@@ -94,7 +94,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
-	unsigned long seq;
+	unsigned int seq;
 	struct clock_read_data *rd;
 
 	do {
@@ -267,7 +267,7 @@ void __init generic_sched_clock_init(void)
  */
 static u64 notrace suspended_sched_clock_read(void)
 {
-	unsigned long seq = raw_read_seqcount(&cd.seq);
+	unsigned int seq = raw_read_seqcount(&cd.seq);
 
 	return cd.read_data[seq & 1].epoch_cyc;
 }

kernel/time/tick-broadcast.c

@@ -36,10 +36,16 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+# ifdef CONFIG_HOTPLUG_CPU
+static void tick_broadcast_oneshot_offline(unsigned int cpu);
+# endif
 #else
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
 static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
+# ifdef CONFIG_HOTPLUG_CPU
+static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { }
+# endif
 #endif
 
 /*
@@ -433,27 +439,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * Remove a CPU from broadcasting
- */
-void tick_shutdown_broadcast(unsigned int cpu)
+static void tick_shutdown_broadcast(void)
 {
-	struct clock_event_device *bc;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
-	bc = tick_broadcast_device.evtdev;
-	cpumask_clear_cpu(cpu, tick_broadcast_mask);
-	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
 		if (bc && cpumask_empty(tick_broadcast_mask))
 			clockevents_shutdown(bc);
 	}
+}
 
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_broadcast_offline(unsigned int cpu)
+{
+	raw_spin_lock(&tick_broadcast_lock);
+	cpumask_clear_cpu(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	tick_broadcast_oneshot_offline(cpu);
+	tick_shutdown_broadcast();
+	raw_spin_unlock(&tick_broadcast_lock);
 }
+
 #endif
 
 void tick_suspend_broadcast(void)
@@ -801,13 +809,13 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 * either the CPU handling the broadcast
 			 * interrupt or we got woken by something else.
 			 *
-			 * We are not longer in the broadcast mask, so
+			 * We are no longer in the broadcast mask, so
 			 * if the cpu local expiry time is already
 			 * reached, we would reprogram the cpu local
 			 * timer with an already expired event.
 			 *
 			 * This can lead to a ping-pong when we return
-			 * to idle and therefor rearm the broadcast
+			 * to idle and therefore rearm the broadcast
 			 * timer before the cpu local timer was able
 			 * to fire. This happens because the forced
 			 * reprogramming makes sure that the event
@@ -950,14 +958,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 }
 
 /*
- * Remove a dead CPU from broadcasting
+ * Remove a dying CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int cpu)
+static void tick_broadcast_oneshot_offline(unsigned int cpu)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
 	/*
 	 * Clear the broadcast masks for the dead cpu, but do not stop
 	 * the broadcast device!
@@ -965,8 +969,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
-
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 #endif
 

kernel/time/tick-common.c

@@ -157,7 +157,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	    !tick_broadcast_oneshot_active()) {
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
-		unsigned long seq;
+		unsigned int seq;
 		ktime_t next;
 
 		do {

kernel/time/tick-internal.h

@@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
 extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_shutdown_broadcast(unsigned int cpu);
 extern void tick_suspend_broadcast(void);
 extern void tick_resume_broadcast(void);
 extern bool tick_resume_check_broadcast(void);
@@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
 static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
 static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_shutdown_broadcast(unsigned int cpu) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline void tick_resume_broadcast(void) { }
 static inline bool tick_resume_check_broadcast(void) { return false; }
@@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 /* Functions related to oneshot broadcasting */
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #else /* !(BROADCAST && ONESHOT): */
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
 #endif /* !(BROADCAST && ONESHOT) */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_broadcast_offline(unsigned int cpu);
+#else
+static inline void tick_broadcast_offline(unsigned int cpu) { }
+#endif
+
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
 extern void tick_nohz_init(void);

kernel/time/tick-sched.c

@@ -654,7 +654,8 @@ static inline bool local_timer_softirq_pending(void)
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
 	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
-	unsigned long seq, basejiff;
+	unsigned long basejiff;
+	unsigned int seq;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {

kernel/time/tick-sched.h

@@ -24,12 +24,19 @@ enum tick_nohz_mode {
  * struct tick_sched - sched tick emulation and no idle tick control/stats
  * @sched_timer:	hrtimer to schedule the periodic tick in high
  *			resolution mode
+ * @check_clocks:	Notification mechanism about clocksource changes
+ * @nohz_mode:		Mode - one state of tick_nohz_mode
+ * @inidle:		Indicator that the CPU is in the tick idle mode
+ * @tick_stopped:	Indicator that the idle tick has been stopped
+ * @idle_active:	Indicator that the CPU is actively in the tick idle mode;
+ *			it is resetted during irq handling phases.
+ * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ * @got_idle_tick:	Tick timer function has run with @inidle set
  * @last_tick:		Store the last tick expiry time when the tick
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
  * @next_tick:		Next tick to be fired when in dynticks mode.
- * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
  * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
@@ -40,8 +47,8 @@ enum tick_nohz_mode {
  * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
  * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
- * @do_timer_lst:	CPU was the last one doing do_timer before going idle
- * @got_idle_tick:	Tick timer function has run with @inidle set
+ * @next_timer:		Expiry time of next expiring timer for debugging purpose only
+ * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;

kernel/time/time.c

@@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 	static int firsttime = 1;
 	int error = 0;
 
-	if (tv && !timespec64_valid(tv))
+	if (tv && !timespec64_valid_settod(tv))
 		return -EINVAL;
 
 	error = security_settime64(tv, tz);

kernel/time/timekeeping.c

@@ -720,7 +720,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 void ktime_get_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
@@ -829,7 +829,7 @@ EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
 ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
 {
 	ktime_t *offset = offsets[offs];
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t tconv;
 
 	do {
@@ -960,7 +960,7 @@ time64_t __ktime_get_real_seconds(void)
 void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t base_raw;
 	ktime_t base_real;
 	u64 nsec_raw;
@@ -1122,7 +1122,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 	ktime_t base_real, base_raw;
 	u64 nsec_real, nsec_raw;
 	u8 cs_was_changed_seq;
-	unsigned long seq;
+	unsigned int seq;
 	bool do_interp;
 	int ret;
 
@@ -1221,7 +1221,7 @@ int do_settimeofday64(const struct timespec64 *ts)
 	unsigned long flags;
 	int ret = 0;
 
-	if (!timespec64_valid_strict(ts))
+	if (!timespec64_valid_settod(ts))
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1278,7 +1278,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts)
 	/* Make sure the proposed value is valid */
 	tmp = timespec64_add(tk_xtime(tk), *ts);
 	if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 ||
-	    !timespec64_valid_strict(&tmp)) {
+	    !timespec64_valid_settod(&tmp)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -1409,7 +1409,7 @@ int timekeeping_notify(struct clocksource *clock)
 void ktime_get_raw_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	do {
@@ -1431,7 +1431,7 @@ EXPORT_SYMBOL(ktime_get_raw_ts64);
 int timekeeping_valid_for_hres(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	int ret;
 
 	do {
@@ -1450,7 +1450,7 @@ int timekeeping_valid_for_hres(void)
 u64 timekeeping_max_deferment(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {
@@ -1527,7 +1527,7 @@ void __init timekeeping_init(void)
 	unsigned long flags;
 
 	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
-	if (timespec64_valid_strict(&wall_time) &&
+	if (timespec64_valid_settod(&wall_time) &&
 	    timespec64_to_ns(&wall_time) > 0) {
 		persistent_clock_exists = true;
 	} else if (timespec64_to_ns(&wall_time) != 0) {
@@ -2150,7 +2150,7 @@ EXPORT_SYMBOL_GPL(getboottime64);
 void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
@@ -2164,7 +2164,7 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 now, mono;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);

kernel/time/timer.c

@@ -536,6 +536,8 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	hlist_add_head(&timer->entry, base->vectors + idx);
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
+
+	trace_timer_start(timer, timer->expires, timer->flags);
 }
 
 static void
@@ -757,13 +759,6 @@ static inline void debug_init(struct timer_list *timer)
 	trace_timer_init(timer);
 }
 
-static inline void
-debug_activate(struct timer_list *timer, unsigned long expires)
-{
-	debug_timer_activate(timer);
-	trace_timer_start(timer, expires, timer->flags);
-}
-
 static inline void debug_deactivate(struct timer_list *timer)
 {
 	debug_timer_deactivate(timer);
@@ -1037,7 +1032,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 	}
 
-	debug_activate(timer, expires);
+	debug_timer_activate(timer);
 
 	timer->expires = expires;
 	/*
@@ -1171,7 +1166,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	}
 	forward_timer_base(base);
 
-	debug_activate(timer, timer->expires);
+	debug_timer_activate(timer);
 	internal_add_timer(base, timer);
 	raw_spin_unlock_irqrestore(&base->lock, flags);
 }
@@ -1298,7 +1293,9 @@ int del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
-static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *))
+static void call_timer_fn(struct timer_list *timer,
+			  void (*fn)(struct timer_list *),
+			  unsigned long baseclk)
 {
 	int count = preempt_count();
 
@@ -1321,7 +1318,7 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 	 */
 	lock_map_acquire(&lockdep_map);
 
-	trace_timer_expire_entry(timer);
+	trace_timer_expire_entry(timer, baseclk);
 	fn(timer);
 	trace_timer_expire_exit(timer);
 
@@ -1342,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 
 static void expire_timers(struct timer_base *base, struct hlist_head *head)
 {
+	/*
+	 * This value is required only for tracing. base->clk was
+	 * incremented directly before expire_timers was called. But expiry
+	 * is related to the old base->clk value.
+	 */
+	unsigned long baseclk = base->clk - 1;
+
 	while (!hlist_empty(head)) {
 		struct timer_list *timer;
 		void (*fn)(struct timer_list *);
@@ -1355,11 +1359,11 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 
 		if (timer->flags & TIMER_IRQSAFE) {
 			raw_spin_unlock(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock(&base->lock);
 		} else {
 			raw_spin_unlock_irq(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock_irq(&base->lock);
 		}
 	}

net/xfrm/xfrm_state.c

@@ -434,7 +434,7 @@ EXPORT_SYMBOL(xfrm_state_free);
 
 static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
-	tasklet_hrtimer_cancel(&x->mtimer);
+	hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
 	kfree(x->aead);
 	kfree(x->aalg);
@@ -479,8 +479,8 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
-	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
-	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
+	struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	time64_t now = ktime_get_real_seconds();
 	time64_t next = TIME64_MAX;
 	int warn = 0;
@@ -544,7 +544,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 		km_state_expired(x, 0, 0);
 resched:
 	if (next != TIME64_MAX) {
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
+		hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+		ret = HRTIMER_RESTART;
 	}
 
 	goto out;
@@ -561,7 +562,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 
 out:
 	spin_unlock(&x->lock);
-	return HRTIMER_NORESTART;
+	return ret;
 }
 
 static void xfrm_replay_timer_handler(struct timer_list *t);
@@ -580,8 +581,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		INIT_HLIST_NODE(&x->bydst);
 		INIT_HLIST_NODE(&x->bysrc);
 		INIT_HLIST_NODE(&x->byspi);
-		tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
-					CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
+		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+		x->mtimer.function = xfrm_timer_handler;
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
 		x->curlft.add_time = ktime_get_real_seconds();
 		x->lft.soft_byte_limit = XFRM_INF;
@@ -1047,7 +1048,9 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
-			tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+			hrtimer_start(&x->mtimer,
+				      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+				      HRTIMER_MODE_REL_SOFT);
 			net->xfrm.state_num++;
 			xfrm_hash_grow_check(net, x->bydst.next != NULL);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -1159,7 +1162,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 	}
 
-	tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
@@ -1266,7 +1269,9 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 		x->mark.m = m->m;
 		x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 		xfrm_state_hold(x);
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer,
+			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		list_add(&x->km.all, &net->xfrm.state_all);
 		hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 		h = xfrm_src_hash(net, daddr, saddr, family);
@@ -1571,7 +1576,8 @@ int xfrm_state_update(struct xfrm_state *x)
 		memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
 		x1->km.dying = 0;
 
-		tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		if (x1->curlft.use_time)
 			xfrm_state_check_expire(x1);
 
@@ -1610,7 +1616,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
 		return -EINVAL;
 	}