1 files changed, 310 insertions, 245 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0086628b6e9..3ab28993f6e 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -32,7 +32,7 @@
  */
 
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
 #include <linux/notifier.h>
@@ -44,7 +44,11 @@
 #include <linux/err.h>
 #include <linux/debugobjects.h>
 #include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
+#include <linux/freezer.h>
 
 #include <asm/uaccess.h>
 
@@ -53,51 +57,78 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
 	.clock_base =
 	{
 		{
-			.index = CLOCK_REALTIME,
+			.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 = CLOCK_MONOTONIC,
-			.get_time = &ktime_get,
+			.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,
 		},
 	}
 };
 
+static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
+	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
+	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
+	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
+};
+
+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, tomono;
-	struct timespec xts, tom;
-	unsigned long seq;
+	ktime_t xtim, mono, boot;
+	struct timespec xts, tom, slp;
+	s32 tai_offset;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		xts = current_kernel_time();
-		tom = wall_to_monotonic;
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
+	tai_offset = timekeeping_get_tai_offset();
 
 	xtim = timespec_to_ktime(xts);
-	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
-		ktime_add(xtim, tomono);
+	mono = ktime_add(xtim, timespec_to_ktime(tom));
+	boot = ktime_add(mono, timespec_to_ktime(slp));
+	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 =
+				ktime_add(xtim,	ktime_set(tai_offset, 0));
 }
 
 /*
@@ -137,23 +168,6 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 	}
 }
 
-
-/*
- * Get the preferred target CPU for NOHZ
- */
-static int hrtimer_get_target(int this_cpu, int pinned)
-{
-#ifdef CONFIG_NO_HZ
-	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
-		int preferred_cpu = get_nohz_load_balancer();
-
-		if (preferred_cpu >= 0)
-			return preferred_cpu;
-	}
-#endif
-	return this_cpu;
-}
-
 /*
  * With HIGHRES=y we do not migrate the timer when it is expiring
  * before the next event on the target cpu because we cannot reprogram
@@ -187,11 +201,12 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_clock_base *new_base;
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
-	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int cpu = get_nohz_timer_target(pinned);
+	int basenum = base->index;
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -219,6 +234,11 @@ again:
 			goto again;
 		}
 		timer->base = new_base;
+	} else {
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			goto again;
+		}
 	}
 	return new_base;
 }
@@ -261,6 +281,10 @@ ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
 	} else {
 		unsigned long rem = do_div(nsec, NSEC_PER_SEC);
 
+		/* Make sure nsec fits into long */
+		if (unlikely(nsec > KTIME_SEC_MAX))
+			return (ktime_t){ .tv64 = KTIME_MAX };
+
 		tmp = ktime_set((long)nsec, rem);
 	}
 
@@ -338,6 +362,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
 
 static struct debug_obj_descr hrtimer_debug_descr;
 
+static void *hrtimer_debug_hint(void *addr)
+{
+	return ((struct hrtimer *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -397,6 +426,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr hrtimer_debug_descr = {
 	.name		= "hrtimer",
+	.debug_hint	= hrtimer_debug_hint,
 	.fixup_init	= hrtimer_fixup_init,
 	.fixup_activate	= hrtimer_fixup_activate,
 	.fixup_free	= hrtimer_fixup_free,
@@ -501,7 +531,7 @@ static inline int hrtimer_is_hres_enabled(void)
  */
 static inline int hrtimer_hres_active(void)
 {
-	return __get_cpu_var(hrtimer_bases).hres_active;
+	return __this_cpu_read(hrtimer_bases.hres_active);
 }
 
 /*
@@ -520,10 +550,13 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
 		struct hrtimer *timer;
+		struct timerqueue_node *next;
 
-		if (!base->first)
+		next = timerqueue_getnext(&base->active);
+		if (!next)
 			continue;
-		timer = rb_entry(base->first, struct hrtimer, node);
+		timer = container_of(next, struct hrtimer, node);
+
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
 		/*
 		 * clock_was_set() has changed base->offset so the
@@ -541,6 +574,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	cpu_base->expires_next.tv64 = expires_next.tv64;
 
+	/*
+	 * If a hang was detected in the last timer interrupt then we
+	 * leave the hang delay active in the hardware. We want the
+	 * system to make progress. That also prevents the following
+	 * scenario:
+	 * T1 expires 50ms from now
+	 * T2 expires 5s from now
+	 *
+	 * T1 is removed, so this code is called and would reprogram
+	 * the hardware to 5s from now. Any hrtimer_start after that
+	 * will not reprogram the hardware due to hang_detected being
+	 * set. So we'd effectivly block all timers until the T2 event
+	 * fires.
+	 */
+	if (cpu_base->hang_detected)
+		return;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }
@@ -603,68 +653,6 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	return res;
 }
 
-
-/*
- * Retrigger next event is called after clock was set
- *
- * Called with interrupts disabled via on_each_cpu()
- */
-static void retrigger_next_event(void *arg)
-{
-	struct hrtimer_cpu_base *base;
-	struct timespec realtime_offset;
-	unsigned long seq;
-
-	if (!hrtimer_hres_active())
-		return;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		set_normalized_timespec(&realtime_offset,
-					-wall_to_monotonic.tv_sec,
-					-wall_to_monotonic.tv_nsec);
-	} while (read_seqretry(&xtime_lock, seq));
-
-	base = &__get_cpu_var(hrtimer_bases);
-
-	/* Adjust CLOCK_REALTIME offset */
-	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
-		timespec_to_ktime(realtime_offset);
-
-	hrtimer_force_reprogram(base, 0);
-	raw_spin_unlock(&base->lock);
-}
-
-/*
- * Clock realtime was set
- *
- * Change the offset of the realtime clock vs. the monotonic
- * clock.
- *
- * We might have to reprogram the high resolution timer interrupt. On
- * SMP we call the architecture specific code to retrigger _all_ high
- * resolution timer interrupts. On UP we just disable interrupts and
- * call the high resolution interrupt code.
- */
-void clock_was_set(void)
-{
-	/* Retrigger the CPU local events everywhere */
-	on_each_cpu(retrigger_next_event, NULL, 1);
-}
-
-/*
- * During resume we might have to reprogram the high resolution timer
- * interrupt (on the local CPU):
- */
-void hres_timers_resume(void)
-{
-	WARN_ONCE(!irqs_disabled(),
-		  KERN_INFO "hres_timers_resume() called with IRQs enabled!");
-
-	retrigger_next_event(NULL);
-}
-
 /*
  * Initialize the high resolution related parts of cpu_base
  */
@@ -675,35 +663,42 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 }
 
 /*
- * Initialize the high resolution related parts of a hrtimer
+ * When High resolution timers are active, try to reprogram. 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.
  */
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+					    struct hrtimer_clock_base *base)
 {
+	return base->cpu_base->hres_active && hrtimer_reprogram(timer, base);
 }
 
+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(offs_real, offs_boot, offs_tai);
+}
 
 /*
- * When High resolution timers are active, try to reprogram. 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.
+ * Retrigger next event is called after clock was set
+ *
+ * Called with interrupts disabled via on_each_cpu()
  */
-static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base,
-					    int wakeup)
+static void retrigger_next_event(void *arg)
 {
-	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-		if (wakeup) {
-			raw_spin_unlock(&base->cpu_base->lock);
-			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-			raw_spin_lock(&base->cpu_base->lock);
-		} else
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
 
-		return 1;
-	}
+	if (!hrtimer_hres_active())
+		return;
 
-	return 0;
+	raw_spin_lock(&base->lock);
+	hrtimer_update_base(base);
+	hrtimer_force_reprogram(base, 0);
+	raw_spin_unlock(&base->lock);
 }
 
 /*
@@ -711,7 +706,7 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
  */
 static int hrtimer_switch_to_hres(void)
 {
-	int cpu = smp_processor_id();
+	int i, cpu = smp_processor_id();
 	struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
 	unsigned long flags;
 
@@ -727,17 +722,32 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+		base->clock_base[i].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
-
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 	local_irq_restore(flags);
 	return 1;
 }
 
+static void clock_was_set_work(struct work_struct *work)
+{
+	clock_was_set();
+}
+
+static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+
+/*
+ * Called from timekeeping and resume code to reprogramm the hrtimer
+ * interrupt device on all cpus.
+ */
+void clock_was_set_delayed(void)
+{
+	schedule_work(&hrtimer_work);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -746,16 +756,52 @@ static inline int hrtimer_switch_to_hres(void) { return 0; }
 static inline void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base,
-					    int wakeup)
+					    struct hrtimer_clock_base *base)
 {
 	return 0;
 }
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
+static inline void retrigger_next_event(void *arg) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
+/*
+ * Clock realtime was set
+ *
+ * Change the offset of the realtime clock vs. the monotonic
+ * clock.
+ *
+ * We might have to reprogram the high resolution timer interrupt. On
+ * SMP we call the architecture specific code to retrigger _all_ high
+ * resolution timer interrupts. On UP we just disable interrupts and
+ * call the high resolution interrupt code.
+ */
+void clock_was_set(void)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	/* Retrigger the CPU local events everywhere */
+	on_each_cpu(retrigger_next_event, NULL, 1);
+#endif
+	timerfd_clock_was_set();
+}
+
+/*
+ * During resume we might have to reprogram the high resolution timer
+ * interrupt on all online CPUs.  However, all other CPUs will be
+ * stopped with IRQs interrupts disabled so the clock_was_set() call
+ * must be deferred.
+ */
+void hrtimers_resume(void)
+{
+	WARN_ONCE(!irqs_disabled(),
+		  KERN_INFO "hrtimers_resume() called with IRQs enabled!");
+
+	/* Retrigger on the local CPU */
+	retrigger_next_event(NULL);
+	/* And schedule a retrigger for all others */
+	clock_was_set_delayed();
+}
+
 static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
 {
 #ifdef CONFIG_TIMER_STATS
@@ -845,48 +891,18 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
 static int enqueue_hrtimer(struct hrtimer *timer,
 			   struct hrtimer_clock_base *base)
 {
-	struct rb_node **link = &base->active.rb_node;
-	struct rb_node *parent = NULL;
-	struct hrtimer *entry;
-	int leftmost = 1;
-
 	debug_activate(timer);
 
-	/*
-	 * Find the right place in the rbtree:
-	 */
-	while (*link) {
-		parent = *link;
-		entry = rb_entry(parent, struct hrtimer, node);
-		/*
-		 * We dont care about collisions. Nodes with
-		 * the same expiry time stay together.
-		 */
-		if (hrtimer_get_expires_tv64(timer) <
-				hrtimer_get_expires_tv64(entry)) {
-			link = &(*link)->rb_left;
-		} else {
-			link = &(*link)->rb_right;
-			leftmost = 0;
-		}
-	}
-
-	/*
-	 * Insert the timer to the rbtree and check whether it
-	 * replaces the first pending timer
-	 */
-	if (leftmost)
-		base->first = &timer->node;
+	timerqueue_add(&base->active, &timer->node);
+	base->cpu_base->active_bases |= 1 << base->index;
 
-	rb_link_node(&timer->node, parent, link);
-	rb_insert_color(&timer->node, &base->active);
 	/*
 	 * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
 	 * state of a possibly running callback.
 	 */
 	timer->state |= HRTIMER_STATE_ENQUEUED;
 
-	return leftmost;
+	return (&timer->node == base->active.next);
 }
 
 /*
@@ -903,15 +919,13 @@ 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;
 
-	/*
-	 * Remove the timer from the rbtree and replace the first
-	 * entry pointer if necessary.
-	 */
-	if (base->first == &timer->node) {
-		base->first = rb_next(&timer->node);
+	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()) {
@@ -924,7 +938,8 @@ static void __remove_hrtimer(struct hrtimer *timer,
 		}
 #endif
 	}
-	rb_erase(&timer->node, &base->active);
+	if (!timerqueue_getnext(&base->active))
+		base->cpu_base->active_bases &= ~(1 << base->index);
 out:
 	timer->state = newstate;
 }
@@ -936,6 +951,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
 	if (hrtimer_is_queued(timer)) {
+		unsigned long state;
 		int reprogram;
 
 		/*
@@ -949,8 +965,13 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
-		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
-				 reprogram);
+		/*
+		 * 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;
+		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
@@ -969,11 +990,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -988,6 +1006,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
@@ -998,20 +1019,35 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	 *
 	 * XXX send_remote_softirq() ?
 	 */
-	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
-		hrtimer_enqueue_reprogram(timer, new_base, wakeup);
+	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
+		&& hrtimer_enqueue_reprogram(timer, new_base)) {
+		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);
+		}
+	}
 
 	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_ABS) or relative (HRTIMER_REL)
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
  *
  * Returns:
  *  0 on success
@@ -1028,7 +1064,8 @@ 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_ABS) or relative (HRTIMER_REL)
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
  *
  * Returns:
  *  0 on success
@@ -1096,11 +1133,10 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
  */
 ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
-	struct hrtimer_clock_base *base;
 	unsigned long flags;
 	ktime_t rem;
 
-	base = lock_hrtimer_base(timer, &flags);
+	lock_hrtimer_base(timer, &flags);
 	rem = hrtimer_expires_remaining(timer);
 	unlock_hrtimer_base(timer, &flags);
 
@@ -1108,7 +1144,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /**
  * hrtimer_get_next_event - get the time until next expiry event
  *
@@ -1128,11 +1164,13 @@ ktime_t hrtimer_get_next_event(void)
 	if (!hrtimer_hres_active()) {
 		for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
 			struct hrtimer *timer;
+			struct timerqueue_node *next;
 
-			if (!base->first)
+			next = timerqueue_getnext(&base->active);
+			if (!next)
 				continue;
 
-			timer = rb_entry(base->first, struct hrtimer, node);
+			timer = container_of(next, struct hrtimer, node);
 			delta.tv64 = hrtimer_get_expires_tv64(timer);
 			delta = ktime_sub(delta, base->get_time());
 			if (delta.tv64 < mindelta.tv64)
@@ -1152,6 +1190,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1160,8 +1199,9 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
-	hrtimer_init_timer_hres(timer);
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
+	timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;
@@ -1195,9 +1235,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
@@ -1237,6 +1278,9 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
 		enqueue_hrtimer(timer, base);
 	}
+
+	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+
 	timer->state &= ~HRTIMER_STATE_CALLBACK;
 }
 
@@ -1249,7 +1293,6 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 void hrtimer_interrupt(struct clock_event_device *dev)
 {
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-	struct hrtimer_clock_base *base;
 	ktime_t expires_next, now, entry_time, delta;
 	int i, retries = 0;
 
@@ -1257,11 +1300,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->nr_events++;
 	dev->next_event.tv64 = KTIME_MAX;
 
-	entry_time = now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
 	expires_next.tv64 = KTIME_MAX;
-
-	raw_spin_lock(&cpu_base->lock);
 	/*
 	 * We set expires_next to KTIME_MAX here with cpu_base->lock
 	 * held to prevent that a timer is enqueued in our queue via
@@ -1271,18 +1313,21 @@ retry:
 	 */
 	cpu_base->expires_next.tv64 = KTIME_MAX;
 
-	base = cpu_base->clock_base;
-
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		struct hrtimer_clock_base *base;
+		struct timerqueue_node *node;
 		ktime_t basenow;
-		struct rb_node *node;
 
+		if (!(cpu_base->active_bases & (1 << i)))
+			continue;
+
+		base = cpu_base->clock_base + i;
 		basenow = ktime_add(now, base->offset);
 
-		while ((node = base->first)) {
+		while ((node = timerqueue_getnext(&base->active))) {
 			struct hrtimer *timer;
 
-			timer = rb_entry(node, struct hrtimer, node);
+			timer = container_of(node, struct hrtimer, node);
 
 			/*
 			 * The immediate goal for using the softexpires is
@@ -1302,6 +1347,8 @@ retry:
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
 						    base->offset);
+				if (expires.tv64 < 0)
+					expires.tv64 = KTIME_MAX;
 				if (expires.tv64 < expires_next.tv64)
 					expires_next = expires;
 				break;
@@ -1309,7 +1356,6 @@ retry:
 
 			__run_hrtimer(timer, &basenow);
 		}
-		base++;
 	}
 
 	/*
@@ -1335,8 +1381,12 @@ retry:
 	 * We need to prevent that we loop forever in the hrtimer
 	 * interrupt routine. We give it 3 attempts to avoid
 	 * overreacting on some spurious event.
+	 *
+	 * Acquire base lock for updating the offsets and retrieving
+	 * the current time.
 	 */
-	now = ktime_get();
+	raw_spin_lock(&cpu_base->lock);
+	now = hrtimer_update_base(cpu_base);
 	cpu_base->nr_retries++;
 	if (++retries < 3)
 		goto retry;
@@ -1348,6 +1398,7 @@ retry:
 	 */
 	cpu_base->nr_hangs++;
 	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;
@@ -1438,7 +1489,7 @@ void hrtimer_run_pending(void)
  */
 void hrtimer_run_queues(void)
 {
-	struct rb_node *node;
+	struct timerqueue_node *node;
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	int index, gettime = 1;
@@ -1448,8 +1499,7 @@ void hrtimer_run_queues(void)
 
 	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
 		base = &cpu_base->clock_base[index];
-
-		if (!base->first)
+		if (!timerqueue_getnext(&base->active))
 			continue;
 
 		if (gettime) {
@@ -1459,10 +1509,10 @@ void hrtimer_run_queues(void)
 
 		raw_spin_lock(&cpu_base->lock);
 
-		while ((node = base->first)) {
+		while ((node = timerqueue_getnext(&base->active))) {
 			struct hrtimer *timer;
 
-			timer = rb_entry(node, struct hrtimer, node);
+			timer = container_of(node, struct hrtimer, node);
 			if (base->softirq_time.tv64 <=
 					hrtimer_get_expires_tv64(timer))
 				break;
@@ -1507,7 +1557,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 			t->task = NULL;
 
 		if (likely(t->task))
-			schedule();
+			freezable_schedule();
 
 		hrtimer_cancel(&t->timer);
 		mode = HRTIMER_MODE_ABS;
@@ -1541,7 +1591,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 	struct timespec __user  *rmtp;
 	int ret = 0;
 
-	hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
+	hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid,
 				HRTIMER_MODE_ABS);
 	hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 
@@ -1571,7 +1621,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
@@ -1593,7 +1643,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 
 	restart = &current_thread_info()->restart_block;
 	restart->fn = hrtimer_nanosleep_restart;
-	restart->nanosleep.index = t.timer.base->index;
+	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.rmtp = rmtp;
 	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
 
@@ -1620,15 +1670,15 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 /*
  * Functions related to boot-time initialization:
  */
-static void __cpuinit init_hrtimers_cpu(int cpu)
+static void init_hrtimers_cpu(int cpu)
 {
 	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
 
-	raw_spin_lock_init(&cpu_base->lock);
-
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		cpu_base->clock_base[i].cpu_base = cpu_base;
+		timerqueue_init_head(&cpu_base->clock_base[i].active);
+	}
 
 	hrtimer_init_hres(cpu_base);
 }
@@ -1639,10 +1689,10 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 				struct hrtimer_clock_base *new_base)
 {
 	struct hrtimer *timer;
-	struct rb_node *node;
+	struct timerqueue_node *node;
 
-	while ((node = rb_first(&old_base->active))) {
-		timer = rb_entry(node, struct hrtimer, node);
+	while ((node = timerqueue_getnext(&old_base->active))) {
+		timer = container_of(node, struct hrtimer, node);
 		BUG_ON(hrtimer_callback_running(timer));
 		debug_deactivate(timer);
 
@@ -1701,7 +1751,7 @@ static void migrate_hrtimers(int scpu)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
+static int hrtimer_cpu_notify(struct notifier_block *self,
 					unsigned long action, void *hcpu)
 {
 	int scpu = (long)hcpu;
@@ -1734,7 +1784,7 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata hrtimers_nb = {
+static struct notifier_block hrtimers_nb = {
 	.notifier_call = hrtimer_cpu_notify,
 };
 
@@ -1749,35 +1799,15 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout_range - sleep until timeout
+ * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
  * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
- *
- * Make the current task sleep until the given expiry time has
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
- *
- * The @delta argument gives the kernel the freedom to schedule the
- * actual wakeup to a time that is both power and performance friendly.
- * The kernel give the normal best effort behavior for "@expires+@delta",
- * but may decide to fire the timer earlier, but no earlier than @expires.
- *
- * You can set the task state as follows -
- *
- * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
- * pass before the routine returns.
- *
- * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
- * delivered to the current task.
- *
- * The current task state is guaranteed to be TASK_RUNNING when this
- * routine returns.
- *
- * Returns 0 when the timer has expired otherwise -EINTR
+ * @clock:	timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
  */
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
-			       const enum hrtimer_mode mode)
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+			       const enum hrtimer_mode mode, int clock)
 {
 	struct hrtimer_sleeper t;
 
@@ -1791,7 +1821,7 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 	}
 
 	/*
-	 * A NULL parameter means "inifinte"
+	 * A NULL parameter means "infinite"
 	 */
 	if (!expires) {
 		schedule();
@@ -1799,7 +1829,7 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 		return -EINTR;
 	}
 
-	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_init_on_stack(&t.timer, clock, mode);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
 	hrtimer_init_sleeper(&t, current);
@@ -1818,6 +1848,41 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 
 	return !t.task ? 0 : -EINTR;
 }
+
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+				     const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range_clock(expires, delta, mode,
+					      CLOCK_MONOTONIC);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
 
 /**