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

Pull timer updates from Thomas Gleixner:
 "A rather largish update for everything time and timer related:

   - Cache footprint optimizations for both hrtimers and timer wheel

   - Lower the NOHZ impact on systems which have NOHZ or timer migration
     disabled at runtime.

   - Optimize run time overhead of hrtimer interrupt by making the clock
     offset updates smarter

   - hrtimer cleanups and removal of restrictions to tackle some
     problems in sched/perf

   - Some more leap second tweaks

   - Another round of changes addressing the 2038 problem

   - First step to change the internals of clock event devices by
     introducing the necessary infrastructure

   - Allow constant folding for usecs/msecs_to_jiffies()

   - The usual pile of clockevent/clocksource driver updates

  The hrtimer changes contain updates to sched, perf and x86 as they
  depend on them plus changes all over the tree to cleanup API changes
  and redundant code, which got copied all over the place.  The y2038
  changes touch s390 to remove the last non 2038 safe code related to
  boot/persistant clock"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  clocksource: Increase dependencies of timer-stm32 to limit build wreckage
  timer: Minimize nohz off overhead
  timer: Reduce timer migration overhead if disabled
  timer: Stats: Simplify the flags handling
  timer: Replace timer base by a cpu index
  timer: Use hlist for the timer wheel hash buckets
  timer: Remove FIFO "guarantee"
  timers: Sanitize catchup_timer_jiffies() usage
  hrtimer: Allow hrtimer::function() to free the timer
  seqcount: Introduce raw_write_seqcount_barrier()
  seqcount: Rename write_seqcount_barrier()
  hrtimer: Fix hrtimer_is_queued() hole
  hrtimer: Remove HRTIMER_STATE_MIGRATE
  selftest: Timers: Avoid signal deadlock in leap-a-day
  timekeeping: Copy the shadow-timekeeper over the real timekeeper last
  clockevents: Check state instead of mode in suspend/resume path
  selftests: timers: Add leap-second timer edge testing to leap-a-day.c
  ntp: Do leapsecond adjustment in adjtimex read path
  time: Prevent early expiry of hrtimers[CLOCK_REALTIME] at the leap second edge
  ntp: Introduce and use SECS_PER_DAY macro instead of 86400
  ...

1 files changed, 325 insertions, 374 deletions

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 93ef7190bdeaad..5c7ae4b641c44a 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -66,33 +66,29 @@
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
-
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+	.seq = SEQCNT_ZERO(hrtimer_bases.seq),
 	.clock_base =
 	{
 		{
 			.index = HRTIMER_BASE_MONOTONIC,
 			.clockid = CLOCK_MONOTONIC,
 			.get_time = &ktime_get,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_REALTIME,
 			.clockid = CLOCK_REALTIME,
 			.get_time = &ktime_get_real,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_BOOTTIME,
 			.clockid = CLOCK_BOOTTIME,
 			.get_time = &ktime_get_boottime,
-			.resolution = KTIME_LOW_RES,
 		},
 		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
-			.resolution = KTIME_LOW_RES,
 		},
 	}
 };
@@ -109,27 +105,6 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 	return hrtimer_clock_to_base_table[clock_id];
 }
 
-
-/*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
-static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
-{
-	ktime_t xtim, mono, boot, tai;
-	ktime_t off_real, off_boot, off_tai;
-
-	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
-	boot = ktime_add(mono, off_boot);
-	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(mono, off_tai);
-
-	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
-	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
-	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
-	base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -137,6 +112,18 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 #ifdef CONFIG_SMP
 
 /*
+ * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
+ * such that hrtimer_callback_running() can unconditionally dereference
+ * timer->base->cpu_base
+ */
+static struct hrtimer_cpu_base migration_cpu_base = {
+	.seq = SEQCNT_ZERO(migration_cpu_base),
+	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
+};
+
+#define migration_base	migration_cpu_base.clock_base[0]
+
+/*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
  * locked, and the base itself is locked too.
@@ -145,8 +132,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
  * be found on the lists/queues.
  *
  * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * possible to set timer->base = &migration_base and drop the lock: the timer
+ * remains locked.
  */
 static
 struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
@@ -156,7 +143,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 
 	for (;;) {
 		base = timer->base;
-		if (likely(base != NULL)) {
+		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
 				return base;
@@ -190,6 +177,24 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 #endif
 }
 
+#if defined(CONFIG_SMP) && defined(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 this_cpu_ptr(&hrtimer_bases);
+	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)
+{
+	return this_cpu_ptr(&hrtimer_bases);
+}
+#endif
+
 /*
  * Switch the timer base to the current CPU when possible.
  */
@@ -197,14 +202,13 @@ static inline struct hrtimer_clock_base *
 switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 		    int pinned)
 {
+	struct hrtimer_cpu_base *new_cpu_base, *this_base;
 	struct hrtimer_clock_base *new_base;
-	struct hrtimer_cpu_base *new_cpu_base;
-	int this_cpu = smp_processor_id();
-	int cpu = get_nohz_timer_target(pinned);
 	int basenum = base->index;
 
+	this_base = this_cpu_ptr(&hrtimer_bases);
+	new_cpu_base = get_target_base(this_base, pinned);
 again:
-	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
 	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
@@ -220,22 +224,24 @@ again:
 		if (unlikely(hrtimer_callback_running(timer)))
 			return base;
 
-		/* See the comment in lock_timer_base() */
-		timer->base = NULL;
+		/* See the comment in lock_hrtimer_base() */
+		timer->base = &migration_base;
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
-		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_base &&
+		    hrtimer_check_target(timer, new_base)) {
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
+			new_cpu_base = this_base;
 			timer->base = base;
 			goto again;
 		}
 		timer->base = new_base;
 	} else {
-		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
-			cpu = this_cpu;
+		if (new_cpu_base != this_base &&
+		    hrtimer_check_target(timer, new_base)) {
+			new_cpu_base = this_base;
 			goto again;
 		}
 	}
@@ -443,24 +449,35 @@ static inline void debug_deactivate(struct hrtimer *timer)
 }
 
 #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
+					     struct hrtimer *timer)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	cpu_base->next_timer = timer;
+#endif
+}
+
 static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 {
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
-	int i;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+	hrtimer_update_next_timer(cpu_base, NULL);
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *next;
 		struct hrtimer *timer;
 
-		next = timerqueue_getnext(&base->active);
-		if (!next)
+		if (!(active & 0x01))
 			continue;
 
+		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-		if (expires.tv64 < expires_next.tv64)
+		if (expires.tv64 < expires_next.tv64) {
 			expires_next = expires;
+			hrtimer_update_next_timer(cpu_base, timer);
+		}
 	}
 	/*
 	 * clock_was_set() might have changed base->offset of any of
@@ -473,6 +490,16 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 }
 #endif
 
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+	return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+					    offs_real, offs_boot, offs_tai);
+}
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -480,6 +507,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
  * High resolution timer enabled ?
  */
 static int hrtimer_hres_enabled __read_mostly  = 1;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
 /*
  * Enable / Disable high resolution mode
@@ -508,9 +537,14 @@ static inline int hrtimer_is_hres_enabled(void)
 /*
  * Is the high resolution mode active ?
  */
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+{
+	return cpu_base->hres_active;
+}
+
 static inline int hrtimer_hres_active(void)
 {
-	return __this_cpu_read(hrtimer_bases.hres_active);
+	return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
 }
 
 /*
@@ -521,7 +555,12 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-	ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+	ktime_t expires_next;
+
+	if (!cpu_base->hres_active)
+		return;
+
+	expires_next = __hrtimer_get_next_event(cpu_base);
 
 	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
 		return;
@@ -545,63 +584,53 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 	if (cpu_base->hang_detected)
 		return;
 
-	if (cpu_base->expires_next.tv64 != KTIME_MAX)
-		tick_program_event(cpu_base->expires_next, 1);
+	tick_program_event(cpu_base->expires_next, 1);
 }
 
 /*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
  * When a timer is enqueued and expires earlier than the already enqueued
  * timers, we have to check, whether it expires earlier than the timer for
  * which the clock event device was armed.
  *
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
  * Called with interrupts disabled and base->cpu_base.lock held
  */
-static int hrtimer_reprogram(struct hrtimer *timer,
-			     struct hrtimer_clock_base *base)
+static void hrtimer_reprogram(struct hrtimer *timer,
+			      struct hrtimer_clock_base *base)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-	int res;
 
 	WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
 	/*
-	 * When the callback is running, we do not reprogram the clock event
-	 * device. The timer callback is either running on a different CPU or
-	 * the callback is executed in the hrtimer_interrupt context. The
-	 * reprogramming is handled either by the softirq, which called the
-	 * callback or at the end of the hrtimer_interrupt.
+	 * If the timer is not on the current cpu, we cannot reprogram
+	 * the other cpus clock event device.
 	 */
-	if (hrtimer_callback_running(timer))
-		return 0;
+	if (base->cpu_base != cpu_base)
+		return;
+
+	/*
+	 * If the hrtimer interrupt is running, then it will
+	 * reevaluate the clock bases and reprogram the clock event
+	 * device. The callbacks are always executed in hard interrupt
+	 * context so we don't need an extra check for a running
+	 * callback.
+	 */
+	if (cpu_base->in_hrtirq)
+		return;
 
 	/*
 	 * CLOCK_REALTIME timer might be requested with an absolute
-	 * expiry time which is less than base->offset. Nothing wrong
-	 * about that, just avoid to call into the tick code, which
-	 * has now objections against negative expiry values.
+	 * expiry time which is less than base->offset. Set it to 0.
 	 */
 	if (expires.tv64 < 0)
-		return -ETIME;
+		expires.tv64 = 0;
 
 	if (expires.tv64 >= cpu_base->expires_next.tv64)
-		return 0;
+		return;
 
-	/*
-	 * When the target cpu of the timer is currently executing
-	 * hrtimer_interrupt(), then we do not touch the clock event
-	 * device. hrtimer_interrupt() will reevaluate all clock bases
-	 * before reprogramming the device.
-	 */
-	if (cpu_base->in_hrtirq)
-		return 0;
+	/* Update the pointer to the next expiring timer */
+	cpu_base->next_timer = timer;
 
 	/*
 	 * If a hang was detected in the last timer interrupt then we
@@ -610,15 +639,14 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	 * to make progress.
 	 */
 	if (cpu_base->hang_detected)
-		return 0;
+		return;
 
 	/*
-	 * Clockevents returns -ETIME, when the event was in the past.
+	 * Program the timer hardware. We enforce the expiry for
+	 * events which are already in the past.
 	 */
-	res = tick_program_event(expires, 0);
-	if (!IS_ERR_VALUE(res))
-		cpu_base->expires_next = expires;
-	return res;
+	cpu_base->expires_next = expires;
+	tick_program_event(expires, 1);
 }
 
 /*
@@ -630,15 +658,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 	base->hres_active = 0;
 }
 
-static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
-{
-	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
-	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
-	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
-
-	return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai);
-}
-
 /*
  * Retrigger next event is called after clock was set
  *
@@ -648,7 +667,7 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-	if (!hrtimer_hres_active())
+	if (!base->hres_active)
 		return;
 
 	raw_spin_lock(&base->lock);
@@ -662,29 +681,19 @@ static void retrigger_next_event(void *arg)
  */
 static int hrtimer_switch_to_hres(void)
 {
-	int i, cpu = smp_processor_id();
-	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
-	unsigned long flags;
-
-	if (base->hres_active)
-		return 1;
-
-	local_irq_save(flags);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		local_irq_restore(flags);
 		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", cpu);
+				    "mode on CPU %d\n", base->cpu);
 		return 0;
 	}
 	base->hres_active = 1;
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
-		base->clock_base[i].resolution = KTIME_HIGH_RES;
+	hrtimer_resolution = HIGH_RES_NSEC;
 
 	tick_setup_sched_timer();
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
-	local_irq_restore(flags);
 	return 1;
 }
 
@@ -706,6 +715,7 @@ void clock_was_set_delayed(void)
 
 #else
 
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
 static inline int hrtimer_hres_active(void) { return 0; }
 static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline int hrtimer_switch_to_hres(void) { return 0; }
@@ -803,6 +813,14 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
  *
  * Forward the timer expiry so it will expire in the future.
  * Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
  */
 u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 {
@@ -814,8 +832,11 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 	if (delta.tv64 < 0)
 		return 0;
 
-	if (interval.tv64 < timer->base->resolution.tv64)
-		interval.tv64 = timer->base->resolution.tv64;
+	if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
+		return 0;
+
+	if (interval.tv64 < hrtimer_resolution)
+		interval.tv64 = hrtimer_resolution;
 
 	if (unlikely(delta.tv64 >= interval.tv64)) {
 		s64 incr = ktime_to_ns(interval);
@@ -849,16 +870,11 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 {
 	debug_activate(timer);
 
-	timerqueue_add(&base->active, &timer->node);
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	/*
-	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
-	 * state of a possibly running callback.
-	 */
-	timer->state |= HRTIMER_STATE_ENQUEUED;
+	timer->state = HRTIMER_STATE_ENQUEUED;
 
-	return (&timer->node == base->active.next);
+	return timerqueue_add(&base->active, &timer->node);
 }
 
 /*
@@ -875,39 +891,38 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
-	struct timerqueue_node *next_timer;
-	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
-		goto out;
+	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+	unsigned int state = timer->state;
+
+	timer->state = newstate;
+	if (!(state & HRTIMER_STATE_ENQUEUED))
+		return;
+
+	if (!timerqueue_del(&base->active, &timer->node))
+		cpu_base->active_bases &= ~(1 << base->index);
 
-	next_timer = timerqueue_getnext(&base->active);
-	timerqueue_del(&base->active, &timer->node);
-	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
-		/* Reprogram the clock event device. if enabled */
-		if (reprogram && hrtimer_hres_active()) {
-			ktime_t expires;
-
-			expires = ktime_sub(hrtimer_get_expires(timer),
-					    base->offset);
-			if (base->cpu_base->expires_next.tv64 == expires.tv64)
-				hrtimer_force_reprogram(base->cpu_base, 1);
-		}
+	/*
+	 * Note: If reprogram is false we do not update
+	 * cpu_base->next_timer. This happens when we remove the first
+	 * timer on a remote cpu. No harm as we never dereference
+	 * cpu_base->next_timer. So the worst thing what can happen is
+	 * an superflous call to hrtimer_force_reprogram() on the
+	 * remote cpu later on if the same timer gets enqueued again.
+	 */
+	if (reprogram && timer == cpu_base->next_timer)
+		hrtimer_force_reprogram(cpu_base, 1);
 #endif
-	}
-	if (!timerqueue_getnext(&base->active))
-		base->cpu_base->active_bases &= ~(1 << base->index);
-out:
-	timer->state = newstate;
 }
 
 /*
  * remove hrtimer, called with base lock held
  */
 static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
 	if (hrtimer_is_queued(timer)) {
-		unsigned long state;
+		unsigned long state = timer->state;
 		int reprogram;
 
 		/*
@@ -921,30 +936,35 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
-		/*
-		 * We must preserve the CALLBACK state flag here,
-		 * otherwise we could move the timer base in
-		 * switch_hrtimer_base.
-		 */
-		state = timer->state & HRTIMER_STATE_CALLBACK;
+
+		if (!restart)
+			state = HRTIMER_STATE_INACTIVE;
+
 		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
 }
 
-int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode,
-		int wakeup)
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			    unsigned long delta_ns, const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
-	int ret, leftmost;
+	int leftmost;
 
 	base = lock_hrtimer_base(timer, &flags);
 
 	/* Remove an active timer from the queue: */
-	ret = remove_hrtimer(timer, base);
+	remove_hrtimer(timer, base, true);
 
 	if (mode & HRTIMER_MODE_REL) {
 		tim = ktime_add_safe(tim, base->get_time());
@@ -956,7 +976,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * timeouts. This will go away with the GTOD framework.
 		 */
 #ifdef CONFIG_TIME_LOW_RES
-		tim = ktime_add_safe(tim, base->resolution);
+		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
 #endif
 	}
 
@@ -968,85 +988,25 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
-
-	if (!leftmost) {
-		unlock_hrtimer_base(timer, &flags);
-		return ret;
-	}
+	if (!leftmost)
+		goto unlock;
 
 	if (!hrtimer_is_hres_active(timer)) {
 		/*
 		 * Kick to reschedule the next tick to handle the new timer
 		 * on dynticks target.
 		 */
-		wake_up_nohz_cpu(new_base->cpu_base->cpu);
-	} else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
-			hrtimer_reprogram(timer, new_base)) {
-		/*
-		 * Only allow reprogramming if the new base is on this CPU.
-		 * (it might still be on another CPU if the timer was pending)
-		 *
-		 * XXX send_remote_softirq() ?
-		 */
-		if (wakeup) {
-			/*
-			 * We need to drop cpu_base->lock to avoid a
-			 * lock ordering issue vs. rq->lock.
-			 */
-			raw_spin_unlock(&new_base->cpu_base->lock);
-			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-			local_irq_restore(flags);
-			return ret;
-		} else {
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-		}
+		if (new_base->cpu_base->nohz_active)
+			wake_up_nohz_cpu(new_base->cpu_base->cpu);
+	} else {
+		hrtimer_reprogram(timer, new_base);
 	}
-
+unlock:
 	unlock_hrtimer_base(timer, &flags);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
-
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-		unsigned long delta_ns, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
 
 /**
- * hrtimer_start - (re)start an hrtimer on the current CPU
- * @timer:	the timer to be added
- * @tim:	expiry time
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
- *
- * Returns:
- *  0 on success
- *  1 when the timer was active
- */
-int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
-{
-	return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
-}
-EXPORT_SYMBOL_GPL(hrtimer_start);
-
-
-/**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:	hrtimer to stop
  *
@@ -1062,10 +1022,19 @@ int hrtimer_try_to_cancel(struct hrtimer *timer)
 	unsigned long flags;
 	int ret = -1;
 
+	/*
+	 * Check lockless first. If the timer is not active (neither
+	 * enqueued nor running the callback, nothing to do here.  The
+	 * base lock does not serialize against a concurrent enqueue,
+	 * so we can avoid taking it.
+	 */
+	if (!hrtimer_active(timer))
+		return 0;
+
 	base = lock_hrtimer_base(timer, &flags);
 
 	if (!hrtimer_callback_running(timer))
-		ret = remove_hrtimer(timer, base);
+		ret = remove_hrtimer(timer, base, false);
 
 	unlock_hrtimer_base(timer, &flags);
 
@@ -1115,26 +1084,22 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
- * Returns the delta to the next expiry event or KTIME_MAX if no timer
- * is pending.
+ * Returns the next expiry time or KTIME_MAX if no timer is pending.
  */
-ktime_t hrtimer_get_next_event(void)
+u64 hrtimer_get_next_event(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t mindelta = { .tv64 = KTIME_MAX };
+	u64 expires = KTIME_MAX;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!hrtimer_hres_active())
-		mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
-				     ktime_get());
+	if (!__hrtimer_hres_active(cpu_base))
+		expires = __hrtimer_get_next_event(cpu_base).tv64;
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
-	if (mindelta.tv64 < 0)
-		mindelta.tv64 = 0;
-	return mindelta;
+	return expires;
 }
 #endif
 
@@ -1176,37 +1141,73 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
 
-/**
- * hrtimer_get_res - get the timer resolution for a clock
- * @which_clock: which clock to query
- * @tp:		 pointer to timespec variable to store the resolution
+/*
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
  *
- * Store the resolution of the clock selected by @which_clock in the
- * variable pointed to by @tp.
+ * It is important for this function to not return a false negative.
  */
-int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+bool hrtimer_active(const struct hrtimer *timer)
 {
 	struct hrtimer_cpu_base *cpu_base;
-	int base = hrtimer_clockid_to_base(which_clock);
+	unsigned int seq;
 
-	cpu_base = raw_cpu_ptr(&hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+	do {
+		cpu_base = READ_ONCE(timer->base->cpu_base);
+		seq = raw_read_seqcount_begin(&cpu_base->seq);
 
-	return 0;
+		if (timer->state != HRTIMER_STATE_INACTIVE ||
+		    cpu_base->running == timer)
+			return true;
+
+	} while (read_seqcount_retry(&cpu_base->seq, seq) ||
+		 cpu_base != READ_ONCE(timer->base->cpu_base));
+
+	return false;
 }
-EXPORT_SYMBOL_GPL(hrtimer_get_res);
+EXPORT_SYMBOL_GPL(hrtimer_active);
 
-static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+/*
+ * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
+ * distinct sections:
+ *
+ *  - queued:	the timer is queued
+ *  - callback:	the timer is being ran
+ *  - post:	the timer is inactive or (re)queued
+ *
+ * On the read side we ensure we observe timer->state and cpu_base->running
+ * from the same section, if anything changed while we looked at it, we retry.
+ * This includes timer->base changing because sequence numbers alone are
+ * insufficient for that.
+ *
+ * The sequence numbers are required because otherwise we could still observe
+ * a false negative if the read side got smeared over multiple consequtive
+ * __run_hrtimer() invocations.
+ */
+
+static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
+			  struct hrtimer_clock_base *base,
+			  struct hrtimer *timer, ktime_t *now)
 {
-	struct hrtimer_clock_base *base = timer->base;
-	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
 
-	WARN_ON(!irqs_disabled());
+	lockdep_assert_held(&cpu_base->lock);
 
 	debug_deactivate(timer);
-	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+	cpu_base->running = timer;
+
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
+
+	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
 	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
 
@@ -1222,58 +1223,43 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 	raw_spin_lock(&cpu_base->lock);
 
 	/*
-	 * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+	 * Note: We clear the running state after enqueue_hrtimer and
 	 * we do not reprogramm the event hardware. Happens either in
 	 * hrtimer_start_range_ns() or in hrtimer_interrupt()
+	 *
+	 * Note: Because we dropped the cpu_base->lock above,
+	 * hrtimer_start_range_ns() can have popped in and enqueued the timer
+	 * for us already.
 	 */
-	if (restart != HRTIMER_NORESTART) {
-		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+	if (restart != HRTIMER_NORESTART &&
+	    !(timer->state & HRTIMER_STATE_ENQUEUED))
 		enqueue_hrtimer(timer, base);
-	}
 
-	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+	/*
+	 * Separate the ->running assignment from the ->state assignment.
+	 *
+	 * As with a regular write barrier, this ensures the read side in
+	 * hrtimer_active() cannot observe cpu_base->running == NULL &&
+	 * timer->state == INACTIVE.
+	 */
+	raw_write_seqcount_barrier(&cpu_base->seq);
 
-	timer->state &= ~HRTIMER_STATE_CALLBACK;
+	WARN_ON_ONCE(cpu_base->running != timer);
+	cpu_base->running = NULL;
 }
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-
-/*
- * High resolution timer interrupt
- * Called with interrupts disabled
- */
-void hrtimer_interrupt(struct clock_event_device *dev)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 {
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	ktime_t expires_next, now, entry_time, delta;
-	int i, retries = 0;
-
-	BUG_ON(!cpu_base->hres_active);
-	cpu_base->nr_events++;
-	dev->next_event.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
-	entry_time = now = hrtimer_update_base(cpu_base);
-retry:
-	cpu_base->in_hrtirq = 1;
-	/*
-	 * We set expires_next to KTIME_MAX here with cpu_base->lock
-	 * held to prevent that a timer is enqueued in our queue via
-	 * the migration code. This does not affect enqueueing of
-	 * timers which run their callback and need to be requeued on
-	 * this CPU.
-	 */
-	cpu_base->expires_next.tv64 = KTIME_MAX;
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
+	unsigned int active = cpu_base->active_bases;
 
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		struct hrtimer_clock_base *base;
+	for (; active; base++, active >>= 1) {
 		struct timerqueue_node *node;
 		ktime_t basenow;
 
-		if (!(cpu_base->active_bases & (1 << i)))
+		if (!(active & 0x01))
 			continue;
 
-		base = cpu_base->clock_base + i;
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = timerqueue_getnext(&base->active))) {
@@ -1296,9 +1282,42 @@ retry:
 			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
 				break;
 
-			__run_hrtimer(timer, &basenow);
+			__run_hrtimer(cpu_base, base, timer, &basenow);
 		}
 	}
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t expires_next, now, entry_time, delta;
+	int retries = 0;
+
+	BUG_ON(!cpu_base->hres_active);
+	cpu_base->nr_events++;
+	dev->next_event.tv64 = KTIME_MAX;
+
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
+retry:
+	cpu_base->in_hrtirq = 1;
+	/*
+	 * We set expires_next to KTIME_MAX here with cpu_base->lock
+	 * held to prevent that a timer is enqueued in our queue via
+	 * the migration code. This does not affect enqueueing of
+	 * timers which run their callback and need to be requeued on
+	 * this CPU.
+	 */
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
+	__hrtimer_run_queues(cpu_base, now);
+
 	/* Reevaluate the clock bases for the next expiry */
 	expires_next = __hrtimer_get_next_event(cpu_base);
 	/*
@@ -1310,8 +1329,7 @@ retry:
 	raw_spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
-	if (expires_next.tv64 == KTIME_MAX ||
-	    !tick_program_event(expires_next, 0)) {
+	if (!tick_program_event(expires_next, 0)) {
 		cpu_base->hang_detected = 0;
 		return;
 	}
@@ -1344,8 +1362,8 @@ retry:
 	cpu_base->hang_detected = 1;
 	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
-	if (delta.tv64 > cpu_base->max_hang_time.tv64)
-		cpu_base->max_hang_time = delta;
+	if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
+		cpu_base->max_hang_time = (unsigned int) delta.tv64;
 	/*
 	 * Limit it to a sensible value as we enforce a longer
 	 * delay. Give the CPU at least 100ms to catch up.
@@ -1363,7 +1381,7 @@ retry:
  * local version of hrtimer_peek_ahead_timers() called with interrupts
  * disabled.
  */
-static void __hrtimer_peek_ahead_timers(void)
+static inline void __hrtimer_peek_ahead_timers(void)
 {
 	struct tick_device *td;
 
@@ -1375,29 +1393,6 @@ static void __hrtimer_peek_ahead_timers(void)
 		hrtimer_interrupt(td->evtdev);
 }
 
-/**
- * hrtimer_peek_ahead_timers -- run soft-expired timers now
- *
- * hrtimer_peek_ahead_timers will peek at the timer queue of
- * the current cpu and check if there are any timers for which
- * the soft expires time has passed. If any such timers exist,
- * they are run immediately and then removed from the timer queue.
- *
- */
-void hrtimer_peek_ahead_timers(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__hrtimer_peek_ahead_timers();
-	local_irq_restore(flags);
-}
-
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
-	hrtimer_peek_ahead_timers();
-}
-
 #else /* CONFIG_HIGH_RES_TIMERS */
 
 static inline void __hrtimer_peek_ahead_timers(void) { }
@@ -1405,66 +1400,32 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 #endif	/* !CONFIG_HIGH_RES_TIMERS */
 
 /*
- * Called from timer softirq every jiffy, expire hrtimers:
- *
- * For HRT its the fall back code to run the softirq in the timer
- * softirq context in case the hrtimer initialization failed or has
- * not been done yet.
+ * Called from run_local_timers in hardirq context every jiffy
  */
-void hrtimer_run_pending(void)
+void hrtimer_run_queues(void)
 {
-	if (hrtimer_hres_active())
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+	ktime_t now;
+
+	if (__hrtimer_hres_active(cpu_base))
 		return;
 
 	/*
-	 * This _is_ ugly: We have to check in the softirq context,
-	 * whether we can switch to highres and / or nohz mode. The
-	 * clocksource switch happens in the timer interrupt with
-	 * xtime_lock held. Notification from there only sets the
-	 * check bit in the tick_oneshot code, otherwise we might
-	 * deadlock vs. xtime_lock.
+	 * This _is_ ugly: We have to check periodically, whether we
+	 * can switch to highres and / or nohz mode. The clocksource
+	 * switch happens with xtime_lock held. Notification from
+	 * there only sets the check bit in the tick_oneshot code,
+	 * otherwise we might deadlock vs. xtime_lock.
 	 */
-	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
 		hrtimer_switch_to_hres();
-}
-
-/*
- * Called from hardirq context every jiffy
- */
-void hrtimer_run_queues(void)
-{
-	struct timerqueue_node *node;
-	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	struct hrtimer_clock_base *base;
-	int index, gettime = 1;
-
-	if (hrtimer_hres_active())
 		return;
-
-	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
-		base = &cpu_base->clock_base[index];
-		if (!timerqueue_getnext(&base->active))
-			continue;
-
-		if (gettime) {
-			hrtimer_get_softirq_time(cpu_base);
-			gettime = 0;
-		}
-
-		raw_spin_lock(&cpu_base->lock);
-
-		while ((node = timerqueue_getnext(&base->active))) {
-			struct hrtimer *timer;
-
-			timer = container_of(node, struct hrtimer, node);
-			if (base->softirq_time.tv64 <=
-					hrtimer_get_expires_tv64(timer))
-				break;
-
-			__run_hrtimer(timer, &base->softirq_time);
-		}
-		raw_spin_unlock(&cpu_base->lock);
 	}
+
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
+	__hrtimer_run_queues(cpu_base, now);
+	raw_spin_unlock(&cpu_base->lock);
 }
 
 /*
@@ -1497,8 +1458,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		hrtimer_start_expires(&t->timer, mode);
-		if (!hrtimer_active(&t->timer))
-			t->task = NULL;
 
 		if (likely(t->task))
 			freezable_schedule();
@@ -1642,11 +1601,11 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		debug_deactivate(timer);
 
 		/*
-		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+		 * Mark it as ENQUEUED not INACTIVE otherwise the
 		 * timer could be seen as !active and just vanish away
 		 * under us on another CPU
 		 */
-		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+		__remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
 		timer->base = new_base;
 		/*
 		 * Enqueue the timers on the new cpu. This does not
@@ -1657,9 +1616,6 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		 * event device.
 		 */
 		enqueue_hrtimer(timer, new_base);
-
-		/* Clear the migration state bit */
-		timer->state &= ~HRTIMER_STATE_MIGRATE;
 	}
 }
 
@@ -1731,9 +1687,6 @@ void __init hrtimers_init(void)
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
-	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
 /**
@@ -1772,8 +1725,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
 	hrtimer_init_sleeper(&t, current);
 
 	hrtimer_start_expires(&t.timer, mode);
-	if (!hrtimer_active(&t.timer))
-		t.task = NULL;
 
 	if (likely(t.task))
 		schedule();