Linux-libre 4.6.2-gnu

9 files changed, 489 insertions, 148 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 664de5392..56ece145a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		/* cs is a watchdog. */
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+	struct clocksource *cs, *old_wd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	/* save current watchdog */
+	old_wd = watchdog;
+	if (fallback)
+		watchdog = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* cs is a clocksource to be watched. */
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+			continue;
+
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_wd)
+			continue;
+
 		/* Pick the best watchdog. */
-		if (!watchdog || cs->rating > watchdog->rating) {
+		if (!watchdog || cs->rating > watchdog->rating)
 			watchdog = cs;
-			/* Reset watchdog cycles */
-			clocksource_reset_watchdog();
-		}
 	}
+	/* If we failed to find a fallback restore the old one. */
+	if (!watchdog)
+		watchdog = old_wd;
+
+	/* If we changed the watchdog we need to reset cycles. */
+	if (watchdog != old_wd)
+		clocksource_reset_watchdog();
+
 	/* Check if the watchdog timer needs to be started. */
 	clocksource_start_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
-	/*
-	 * I really can't convince myself to support this on hardware
-	 * designed by lobotomized monkeys.
-	 */
-	if (clocksource_is_watchdog(cs))
-		return -EBUSY;
+	if (clocksource_is_watchdog(cs)) {
+		/* Select and try to install a replacement watchdog. */
+		clocksource_select_watchdog(true);
+		if (clocksource_is_watchdog(cs))
+			return -EBUSY;
+	}
 
 	if (cs == curr_clocksource) {
 		/* Select and try to install a replacement clock source */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index fa909f9fd..fa0b98329 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -515,7 +515,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 /*
  * High resolution timer enabled ?
  */
-static int hrtimer_hres_enabled __read_mostly  = 1;
+static bool hrtimer_hres_enabled __read_mostly  = true;
 unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
 EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
@@ -524,13 +524,7 @@ EXPORT_SYMBOL_GPL(hrtimer_resolution);
  */
 static int __init setup_hrtimer_hres(char *str)
 {
-	if (!strcmp(str, "off"))
-		hrtimer_hres_enabled = 0;
-	else if (!strcmp(str, "on"))
-		hrtimer_hres_enabled = 1;
-	else
-		return 0;
-	return 1;
+	return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
 }
 
 __setup("highres=", setup_hrtimer_hres);
@@ -979,7 +973,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
  *		relative (HRTIMER_MODE_REL)
  */
 void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-			    unsigned long delta_ns, const enum hrtimer_mode mode)
+			    u64 delta_ns, const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
@@ -1548,7 +1542,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
 	int ret = 0;
-	unsigned long slack;
+	u64 slack;
 
 	slack = current->timer_slack_ns;
 	if (dl_task(current) || rt_task(current))
@@ -1724,7 +1718,7 @@ void __init hrtimers_init(void)
  * @clock:	timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
  */
 int __sched
-schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 			       const enum hrtimer_mode mode, int clock)
 {
 	struct hrtimer_sleeper t;
@@ -1792,7 +1786,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
  *
  * Returns 0 when the timer has expired otherwise -EINTR
  */
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
 				     const enum hrtimer_mode mode)
 {
 	return schedule_hrtimeout_range_clock(expires, delta, mode,
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 347fecf86..555e21f7b 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -68,7 +68,7 @@ static struct clocksource clocksource_jiffies = {
 	.name		= "jiffies",
 	.rating		= 1, /* lowest valid rating*/
 	.read		= jiffies_read,
-	.mask		= 0xffffffff, /*32bits*/
+	.mask		= CLOCKSOURCE_MASK(32),
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
 	.max_cycles	= 10,
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 7a48442ed..e284c2316 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -333,7 +333,6 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 	return err;
 }
 
-
 /*
  * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
  * This is called from sys_timer_create() and do_cpu_nanosleep() with the
@@ -517,6 +516,10 @@ static void arm_timer(struct k_itimer *timer)
 				cputime_expires->sched_exp = exp;
 			break;
 		}
+		if (CPUCLOCK_PERTHREAD(timer->it_clock))
+			tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER);
+		else
+			tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER);
 	}
 }
 
@@ -582,39 +585,6 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 	return 0;
 }
 
-#ifdef CONFIG_NO_HZ_FULL
-static void nohz_kick_work_fn(struct work_struct *work)
-{
-	tick_nohz_full_kick_all();
-}
-
-static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
-
-/*
- * We need the IPIs to be sent from sane process context.
- * The posix cpu timers are always set with irqs disabled.
- */
-static void posix_cpu_timer_kick_nohz(void)
-{
-	if (context_tracking_is_enabled())
-		schedule_work(&nohz_kick_work);
-}
-
-bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
-{
-	if (!task_cputime_zero(&tsk->cputime_expires))
-		return false;
-
-	/* Check if cputimer is running. This is accessed without locking. */
-	if (READ_ONCE(tsk->signal->cputimer.running))
-		return false;
-
-	return true;
-}
-#else
-static inline void posix_cpu_timer_kick_nohz(void) { }
-#endif
-
 /*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
@@ -761,8 +731,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 		sample_to_timespec(timer->it_clock,
 				   old_incr, &old->it_interval);
 	}
-	if (!ret)
-		posix_cpu_timer_kick_nohz();
+
 	return ret;
 }
 
@@ -911,6 +880,8 @@ static void check_thread_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 		}
 	}
+	if (task_cputime_zero(tsk_expires))
+		tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static inline void stop_process_timers(struct signal_struct *sig)
@@ -919,6 +890,7 @@ static inline void stop_process_timers(struct signal_struct *sig)
 
 	/* Turn off cputimer->running. This is done without locking. */
 	WRITE_ONCE(cputimer->running, false);
+	tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static u32 onecputick;
@@ -1095,8 +1067,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	arm_timer(timer);
 	unlock_task_sighand(p, &flags);
 
-	/* Kick full dynticks CPUs in case they need to tick on the new timer */
-	posix_cpu_timer_kick_nohz();
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1270,7 +1240,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		}
 
 		if (!*newval)
-			goto out;
+			return;
 		*newval += now;
 	}
 
@@ -1288,8 +1258,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			tsk->signal->cputime_expires.virt_exp = *newval;
 		break;
 	}
-out:
-	posix_cpu_timer_kick_nohz();
+
+	tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0b1742434..58e3310c9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
-#include <linux/perf_event.h>
 #include <linux/context_tracking.h>
 
 #include <asm/irq_regs.h>
@@ -158,54 +157,61 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 cpumask_var_t tick_nohz_full_mask;
 cpumask_var_t housekeeping_mask;
 bool tick_nohz_full_running;
+static atomic_t tick_dep_mask;
 
-static bool can_stop_full_tick(void)
+static bool check_tick_dependency(atomic_t *dep)
+{
+	int val = atomic_read(dep);
+
+	if (val & TICK_DEP_MASK_POSIX_TIMER) {
+		trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
+		return true;
+	}
+
+	if (val & TICK_DEP_MASK_PERF_EVENTS) {
+		trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
+		return true;
+	}
+
+	if (val & TICK_DEP_MASK_SCHED) {
+		trace_tick_stop(0, TICK_DEP_MASK_SCHED);
+		return true;
+	}
+
+	if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) {
+		trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
+		return true;
+	}
+
+	return false;
+}
+
+static bool can_stop_full_tick(struct tick_sched *ts)
 {
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (!sched_can_stop_tick()) {
-		trace_tick_stop(0, "more than 1 task in runqueue\n");
+	if (check_tick_dependency(&tick_dep_mask))
 		return false;
-	}
 
-	if (!posix_cpu_timers_can_stop_tick(current)) {
-		trace_tick_stop(0, "posix timers running\n");
+	if (check_tick_dependency(&ts->tick_dep_mask))
 		return false;
-	}
 
-	if (!perf_event_can_stop_tick()) {
-		trace_tick_stop(0, "perf events running\n");
+	if (check_tick_dependency(&current->tick_dep_mask))
 		return false;
-	}
 
-	/* sched_clock_tick() needs us? */
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-	/*
-	 * TODO: kick full dynticks CPUs when
-	 * sched_clock_stable is set.
-	 */
-	if (!sched_clock_stable()) {
-		trace_tick_stop(0, "unstable sched clock\n");
-		/*
-		 * Don't allow the user to think they can get
-		 * full NO_HZ with this machine.
-		 */
-		WARN_ONCE(tick_nohz_full_running,
-			  "NO_HZ FULL will not work with unstable sched clock");
+	if (check_tick_dependency(&current->signal->tick_dep_mask))
 		return false;
-	}
-#endif
 
 	return true;
 }
 
-static void nohz_full_kick_work_func(struct irq_work *work)
+static void nohz_full_kick_func(struct irq_work *work)
 {
 	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
 }
 
 static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
-	.func = nohz_full_kick_work_func,
+	.func = nohz_full_kick_func,
 };
 
 /*
@@ -214,7 +220,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
  * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
  * is NMI safe.
  */
-void tick_nohz_full_kick(void)
+static void tick_nohz_full_kick(void)
 {
 	if (!tick_nohz_full_cpu(smp_processor_id()))
 		return;
@@ -234,27 +240,112 @@ void tick_nohz_full_kick_cpu(int cpu)
 	irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
 }
 
-static void nohz_full_kick_ipi(void *info)
-{
-	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
-}
-
 /*
  * Kick all full dynticks CPUs in order to force these to re-evaluate
  * their dependency on the tick and restart it if necessary.
  */
-void tick_nohz_full_kick_all(void)
+static void tick_nohz_full_kick_all(void)
 {
+	int cpu;
+
 	if (!tick_nohz_full_running)
 		return;
 
 	preempt_disable();
-	smp_call_function_many(tick_nohz_full_mask,
-			       nohz_full_kick_ipi, NULL, false);
-	tick_nohz_full_kick();
+	for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
+		tick_nohz_full_kick_cpu(cpu);
 	preempt_enable();
 }
 
+static void tick_nohz_dep_set_all(atomic_t *dep,
+				  enum tick_dep_bits bit)
+{
+	int prev;
+
+	prev = atomic_fetch_or(dep, BIT(bit));
+	if (!prev)
+		tick_nohz_full_kick_all();
+}
+
+/*
+ * Set a global tick dependency. Used by perf events that rely on freq and
+ * by unstable clock.
+ */
+void tick_nohz_dep_set(enum tick_dep_bits bit)
+{
+	tick_nohz_dep_set_all(&tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear(enum tick_dep_bits bit)
+{
+	atomic_andnot(BIT(bit), &tick_dep_mask);
+}
+
+/*
+ * Set per-CPU tick dependency. Used by scheduler and perf events in order to
+ * manage events throttling.
+ */
+void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
+{
+	int prev;
+	struct tick_sched *ts;
+
+	ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	prev = atomic_fetch_or(&ts->tick_dep_mask, BIT(bit));
+	if (!prev) {
+		preempt_disable();
+		/* Perf needs local kick that is NMI safe */
+		if (cpu == smp_processor_id()) {
+			tick_nohz_full_kick();
+		} else {
+			/* Remote irq work not NMI-safe */
+			if (!WARN_ON_ONCE(in_nmi()))
+				tick_nohz_full_kick_cpu(cpu);
+		}
+		preempt_enable();
+	}
+}
+
+void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
+{
+	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	atomic_andnot(BIT(bit), &ts->tick_dep_mask);
+}
+
+/*
+ * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
+ * per task timers.
+ */
+void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
+{
+	/*
+	 * We could optimize this with just kicking the target running the task
+	 * if that noise matters for nohz full users.
+	 */
+	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
+{
+	atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
+}
+
+/*
+ * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
+ * per process timers.
+ */
+void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit)
+{
+	tick_nohz_dep_set_all(&sig->tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
+{
+	atomic_andnot(BIT(bit), &sig->tick_dep_mask);
+}
+
 /*
  * Re-evaluate the need for the tick as we switch the current task.
  * It might need the tick due to per task/process properties:
@@ -263,15 +354,20 @@ void tick_nohz_full_kick_all(void)
 void __tick_nohz_task_switch(void)
 {
 	unsigned long flags;
+	struct tick_sched *ts;
 
 	local_irq_save(flags);
 
 	if (!tick_nohz_full_cpu(smp_processor_id()))
 		goto out;
 
-	if (tick_nohz_tick_stopped() && !can_stop_full_tick())
-		tick_nohz_full_kick();
+	ts = this_cpu_ptr(&tick_cpu_sched);
 
+	if (ts->tick_stopped) {
+		if (atomic_read(&current->tick_dep_mask) ||
+		    atomic_read(&current->signal->tick_dep_mask))
+			tick_nohz_full_kick();
+	}
 out:
 	local_irq_restore(flags);
 }
@@ -281,7 +377,7 @@ static int __init tick_nohz_full_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
 	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
-		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
+		pr_warn("NO_HZ: Incorrect nohz_full cpumask\n");
 		free_bootmem_cpumask_var(tick_nohz_full_mask);
 		return 1;
 	}
@@ -349,8 +445,7 @@ void __init tick_nohz_init(void)
 	 * interrupts to avoid circular dependency on the tick
 	 */
 	if (!arch_irq_work_has_interrupt()) {
-		pr_warning("NO_HZ: Can't run full dynticks because arch doesn't "
-			   "support irq work self-IPIs\n");
+		pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
 		cpumask_clear(tick_nohz_full_mask);
 		cpumask_copy(housekeeping_mask, cpu_possible_mask);
 		tick_nohz_full_running = false;
@@ -360,7 +455,8 @@ void __init tick_nohz_init(void)
 	cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
+		pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
+			cpu);
 		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
 	}
 
@@ -389,20 +485,14 @@ void __init tick_nohz_init(void)
 /*
  * NO HZ enabled ?
  */
-int tick_nohz_enabled __read_mostly = 1;
+bool tick_nohz_enabled __read_mostly  = true;
 unsigned long tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
 static int __init setup_tick_nohz(char *str)
 {
-	if (!strcmp(str, "off"))
-		tick_nohz_enabled = 0;
-	else if (!strcmp(str, "on"))
-		tick_nohz_enabled = 1;
-	else
-		return 0;
-	return 1;
+	return (kstrtobool(str, &tick_nohz_enabled) == 0);
 }
 
 __setup("nohz=", setup_tick_nohz);
@@ -689,7 +779,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 		ts->tick_stopped = 1;
-		trace_tick_stop(1, " ");
+		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
 	/*
@@ -740,7 +830,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
 		return;
 
-	if (can_stop_full_tick())
+	if (can_stop_full_tick(ts))
 		tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
 	else if (ts->tick_stopped)
 		tick_nohz_restart_sched_tick(ts, ktime_get(), 1);
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index a4a8d4e9b..bf38226e5 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -60,6 +60,7 @@ struct tick_sched {
 	u64				next_timer;
 	ktime_t				idle_expires;
 	int				do_timer_last;
+	atomic_t			tick_dep_mask;
 };
 
 extern struct tick_sched *tick_get_tick_sched(int cpu);
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 86751c68e..be115b020 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -322,6 +322,13 @@ EXPORT_SYMBOL(timespec_trunc);
  * -year/100+year/400 terms, and add 10.]
  *
  * This algorithm was first published by Gauss (I think).
+ *
+ * A leap second can be indicated by calling this function with sec as
+ * 60 (allowable under ISO 8601).  The leap second is treated the same
+ * as the following second since they don't exist in UNIX time.
+ *
+ * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight
+ * tomorrow - (allowable under ISO 8601) is supported.
  */
 time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 		const unsigned int day, const unsigned int hour,
@@ -338,7 +345,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 	return ((((time64_t)
 		  (year/4 - year/100 + year/400 + 367*mon/12 + day) +
 		  year*365 - 719499
-	    )*24 + hour /* now have hours */
+	    )*24 + hour /* now have hours - midnight tomorrow handled here */
 	  )*60 + min /* now have minutes */
 	)*60 + sec; /* finally seconds */
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 34b4cedfa..479d25cd3 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -131,7 +131,7 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 		printk_deferred("         timekeeping: Your kernel is sick, but tries to cope by capping time updates\n");
 	} else {
 		if (offset > (max_cycles >> 1)) {
-			printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n",
+			printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n",
 					offset, name, max_cycles >> 1);
 			printk_deferred("      timekeeping: Your kernel is still fine, but is feeling a bit nervous\n");
 		}
@@ -233,6 +233,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	u64 tmp, ntpinterval;
 	struct clocksource *old_clock;
 
+	++tk->cs_was_changed_seq;
 	old_clock = tk->tkr_mono.clock;
 	tk->tkr_mono.clock = clock;
 	tk->tkr_mono.read = clock->read;
@@ -298,17 +299,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
+static inline s64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+					  cycle_t delta)
+{
+	s64 nsec;
+
+	nsec = delta * tkr->mult + tkr->xtime_nsec;
+	nsec >>= tkr->shift;
+
+	/* If arch requires, add in get_arch_timeoffset() */
+	return nsec + arch_gettimeoffset();
+}
+
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
 	cycle_t delta;
-	s64 nsec;
 
 	delta = timekeeping_get_delta(tkr);
+	return timekeeping_delta_to_ns(tkr, delta);
+}
 
-	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
+static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
+					    cycle_t cycles)
+{
+	cycle_t delta;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
+	return timekeeping_delta_to_ns(tkr, delta);
 }
 
 /**
@@ -857,44 +875,262 @@ time64_t __ktime_get_real_seconds(void)
 	return tk->xtime_sec;
 }
 
+/**
+ * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
+ * @systime_snapshot:	pointer to struct receiving the system time snapshot
+ */
+void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned long seq;
+	ktime_t base_raw;
+	ktime_t base_real;
+	s64 nsec_raw;
+	s64 nsec_real;
+	cycle_t now;
 
-#ifdef CONFIG_NTP_PPS
+	WARN_ON_ONCE(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+
+		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
+		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
+		base_real = ktime_add(tk->tkr_mono.base,
+				      tk_core.timekeeper.offs_real);
+		base_raw = tk->tkr_raw.base;
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
+		nsec_raw  = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	systime_snapshot->cycles = now;
+	systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
+	systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
+}
+EXPORT_SYMBOL_GPL(ktime_get_snapshot);
+
+/* Scale base by mult/div checking for overflow */
+static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
+{
+	u64 tmp, rem;
+
+	tmp = div64_u64_rem(*base, div, &rem);
+
+	if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) ||
+	    ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
+		return -EOVERFLOW;
+	tmp *= mult;
+	rem *= mult;
+
+	do_div(rem, div);
+	*base = tmp + rem;
+	return 0;
+}
 
 /**
- * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format
- * @ts_raw:	pointer to the timespec to be set to raw monotonic time
- * @ts_real:	pointer to the timespec to be set to the time of day
+ * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval
+ * @history:			Snapshot representing start of history
+ * @partial_history_cycles:	Cycle offset into history (fractional part)
+ * @total_history_cycles:	Total history length in cycles
+ * @discontinuity:		True indicates clock was set on history period
+ * @ts:				Cross timestamp that should be adjusted using
+ *	partial/total ratio
  *
- * This function reads both the time of day and raw monotonic time at the
- * same time atomically and stores the resulting timestamps in timespec
- * format.
+ * Helper function used by get_device_system_crosststamp() to correct the
+ * crosstimestamp corresponding to the start of the current interval to the
+ * system counter value (timestamp point) provided by the driver. The
+ * total_history_* quantities are the total history starting at the provided
+ * reference point and ending at the start of the current interval. The cycle
+ * count between the driver timestamp point and the start of the current
+ * interval is partial_history_cycles.
  */
-void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real)
+static int adjust_historical_crosststamp(struct system_time_snapshot *history,
+					 cycle_t partial_history_cycles,
+					 cycle_t total_history_cycles,
+					 bool discontinuity,
+					 struct system_device_crosststamp *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
-	s64 nsecs_raw, nsecs_real;
+	u64 corr_raw, corr_real;
+	bool interp_forward;
+	int ret;
 
-	WARN_ON_ONCE(timekeeping_suspended);
+	if (total_history_cycles == 0 || partial_history_cycles == 0)
+		return 0;
+
+	/* Interpolate shortest distance from beginning or end of history */
+	interp_forward = partial_history_cycles > total_history_cycles/2 ?
+		true : false;
+	partial_history_cycles = interp_forward ?
+		total_history_cycles - partial_history_cycles :
+		partial_history_cycles;
+
+	/*
+	 * Scale the monotonic raw time delta by:
+	 *	partial_history_cycles / total_history_cycles
+	 */
+	corr_raw = (u64)ktime_to_ns(
+		ktime_sub(ts->sys_monoraw, history->raw));
+	ret = scale64_check_overflow(partial_history_cycles,
+				     total_history_cycles, &corr_raw);
+	if (ret)
+		return ret;
+
+	/*
+	 * If there is a discontinuity in the history, scale monotonic raw
+	 *	correction by:
+	 *	mult(real)/mult(raw) yielding the realtime correction
+	 * Otherwise, calculate the realtime correction similar to monotonic
+	 *	raw calculation
+	 */
+	if (discontinuity) {
+		corr_real = mul_u64_u32_div
+			(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
+	} else {
+		corr_real = (u64)ktime_to_ns(
+			ktime_sub(ts->sys_realtime, history->real));
+		ret = scale64_check_overflow(partial_history_cycles,
+					     total_history_cycles, &corr_real);
+		if (ret)
+			return ret;
+	}
+
+	/* Fixup monotonic raw and real time time values */
+	if (interp_forward) {
+		ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw);
+		ts->sys_realtime = ktime_add_ns(history->real, corr_real);
+	} else {
+		ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw);
+		ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real);
+	}
+
+	return 0;
+}
+
+/*
+ * cycle_between - true if test occurs chronologically between before and after
+ */
+static bool cycle_between(cycle_t before, cycle_t test, cycle_t after)
+{
+	if (test > before && test < after)
+		return true;
+	if (test < before && before > after)
+		return true;
+	return false;
+}
+
+/**
+ * get_device_system_crosststamp - Synchronously capture system/device timestamp
+ * @get_time_fn:	Callback to get simultaneous device time and
+ *	system counter from the device driver
+ * @ctx:		Context passed to get_time_fn()
+ * @history_begin:	Historical reference point used to interpolate system
+ *	time when counter provided by the driver is before the current interval
+ * @xtstamp:		Receives simultaneously captured system and device time
+ *
+ * Reads a timestamp from a device and correlates it to system time
+ */
+int get_device_system_crosststamp(int (*get_time_fn)
+				  (ktime_t *device_time,
+				   struct system_counterval_t *sys_counterval,
+				   void *ctx),
+				  void *ctx,
+				  struct system_time_snapshot *history_begin,
+				  struct system_device_crosststamp *xtstamp)
+{
+	struct system_counterval_t system_counterval;
+	struct timekeeper *tk = &tk_core.timekeeper;
+	cycle_t cycles, now, interval_start;
+	unsigned int clock_was_set_seq = 0;
+	ktime_t base_real, base_raw;
+	s64 nsec_real, nsec_raw;
+	u8 cs_was_changed_seq;
+	unsigned long seq;
+	bool do_interp;
+	int ret;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
+		/*
+		 * Try to synchronously capture device time and a system
+		 * counter value calling back into the device driver
+		 */
+		ret = get_time_fn(&xtstamp->device, &system_counterval, ctx);
+		if (ret)
+			return ret;
+
+		/*
+		 * Verify that the clocksource associated with the captured
+		 * system counter value is the same as the currently installed
+		 * timekeeper clocksource
+		 */
+		if (tk->tkr_mono.clock != system_counterval.cs)
+			return -ENODEV;
+		cycles = system_counterval.cycles;
 
-		*ts_raw = tk->raw_time;
-		ts_real->tv_sec = tk->xtime_sec;
-		ts_real->tv_nsec = 0;
+		/*
+		 * Check whether the system counter value provided by the
+		 * device driver is on the current timekeeping interval.
+		 */
+		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		interval_start = tk->tkr_mono.cycle_last;
+		if (!cycle_between(interval_start, cycles, now)) {
+			clock_was_set_seq = tk->clock_was_set_seq;
+			cs_was_changed_seq = tk->cs_was_changed_seq;
+			cycles = interval_start;
+			do_interp = true;
+		} else {
+			do_interp = false;
+		}
 
-		nsecs_raw  = timekeeping_get_ns(&tk->tkr_raw);
-		nsecs_real = timekeeping_get_ns(&tk->tkr_mono);
+		base_real = ktime_add(tk->tkr_mono.base,
+				      tk_core.timekeeper.offs_real);
+		base_raw = tk->tkr_raw.base;
 
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono,
+						     system_counterval.cycles);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw,
+						    system_counterval.cycles);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	timespec64_add_ns(ts_raw, nsecs_raw);
-	timespec64_add_ns(ts_real, nsecs_real);
-}
-EXPORT_SYMBOL(ktime_get_raw_and_real_ts64);
+	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
+	xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw);
 
-#endif /* CONFIG_NTP_PPS */
+	/*
+	 * Interpolate if necessary, adjusting back from the start of the
+	 * current interval
+	 */
+	if (do_interp) {
+		cycle_t partial_history_cycles, total_history_cycles;
+		bool discontinuity;
+
+		/*
+		 * Check that the counter value occurs after the provided
+		 * history reference and that the history doesn't cross a
+		 * clocksource change
+		 */
+		if (!history_begin ||
+		    !cycle_between(history_begin->cycles,
+				   system_counterval.cycles, cycles) ||
+		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
+			return -EINVAL;
+		partial_history_cycles = cycles - system_counterval.cycles;
+		total_history_cycles = cycles - history_begin->cycles;
+		discontinuity =
+			history_begin->clock_was_set_seq != clock_was_set_seq;
+
+		ret = adjust_historical_crosststamp(history_begin,
+						    partial_history_cycles,
+						    total_history_cycles,
+						    discontinuity, xtstamp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(get_device_system_crosststamp);
 
 /**
  * do_gettimeofday - Returns the time of day in a timeval
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index bbc5d1114..73164c3aa 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1566,6 +1566,17 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 }
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
+/*
+ * Like schedule_timeout_uninterruptible(), except this task will not contribute
+ * to load average.
+ */
+signed long __sched schedule_timeout_idle(signed long timeout)
+{
+	__set_current_state(TASK_IDLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_idle);
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head)
 {
@@ -1698,10 +1709,10 @@ EXPORT_SYMBOL(msleep_interruptible);
 static void __sched do_usleep_range(unsigned long min, unsigned long max)
 {
 	ktime_t kmin;
-	unsigned long delta;
+	u64 delta;
 
 	kmin = ktime_set(0, min * NSEC_PER_USEC);
-	delta = (max - min) * NSEC_PER_USEC;
+	delta = (u64)(max - min) * NSEC_PER_USEC;
 	schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
 }