8 files changed, 108 insertions, 23 deletions

diff --git a/kernel/kernel/time/clocksource.c b/kernel/kernel/time/clocksource.c
index 1347882d1..b98810d2f 100644
--- a/kernel/kernel/time/clocksource.c
+++ b/kernel/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/kernel/time/hrtimer.c b/kernel/kernel/time/hrtimer.c
index 2659c632a..549526e9f 100644
--- a/kernel/kernel/time/hrtimer.c
+++ b/kernel/kernel/time/hrtimer.c
@@ -96,6 +96,9 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	/* Make sure we catch unsupported clockids */
+	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
+
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
@@ -104,7 +107,9 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
-	return hrtimer_clock_to_base_table[clock_id];
+	int base = hrtimer_clock_to_base_table[clock_id];
+	BUG_ON(base == HRTIMER_MAX_CLOCK_BASES);
+	return base;
 }
 
 /*
diff --git a/kernel/kernel/time/ntp.c b/kernel/kernel/time/ntp.c
index cd925efb2..0f6868fd2 100644
--- a/kernel/kernel/time/ntp.c
+++ b/kernel/kernel/time/ntp.c
@@ -717,8 +717,24 @@ int ntp_validate_timex(struct timex *txc)
 			return -EINVAL;
 	}
 
-	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
-		return -EPERM;
+	if (txc->modes & ADJ_SETOFFSET) {
+		/* In order to inject time, you gotta be super-user! */
+		if (!capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		if (txc->modes & ADJ_NANO) {
+			struct timespec ts;
+
+			ts.tv_sec = txc->time.tv_sec;
+			ts.tv_nsec = txc->time.tv_usec;
+			if (!timespec_inject_offset_valid(&ts))
+				return -EINVAL;
+
+		} else {
+			if (!timeval_inject_offset_valid(&txc->time))
+				return -EINVAL;
+		}
+	}
 
 	/*
 	 * Check for potential multiplication overflows that can
diff --git a/kernel/kernel/time/posix-cpu-timers.c b/kernel/kernel/time/posix-cpu-timers.c
index bf28ef601..b7342b6e6 100644
--- a/kernel/kernel/time/posix-cpu-timers.c
+++ b/kernel/kernel/time/posix-cpu-timers.c
@@ -809,6 +809,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			timer->it.cpu.expires = 0;
 			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
 					   &itp->it_value);
+			return;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
 			unlock_task_sighand(p, &flags);
diff --git a/kernel/kernel/time/tick-broadcast.c b/kernel/kernel/time/tick-broadcast.c
index f6aae7977..d2a20e83e 100644
--- a/kernel/kernel/time/tick-broadcast.c
+++ b/kernel/kernel/time/tick-broadcast.c
@@ -871,6 +871,9 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
 	int cpu = smp_processor_id();
 
+	if (!bc)
+		return;
+
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
 		int was_periodic = clockevent_state_periodic(bc);
diff --git a/kernel/kernel/time/timekeeping.c b/kernel/kernel/time/timekeeping.c
index a1c5c6fc2..e060b34d5 100644
--- a/kernel/kernel/time/timekeeping.c
+++ b/kernel/kernel/time/timekeeping.c
@@ -298,17 +298,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+					  cycle_t delta)
+{
+	u64 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);
 }
 
 /**
@@ -383,7 +400,13 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+		now = ktime_to_ns(tkr->base);
+
+		now += timekeeping_delta_to_ns(tkr,
+				clocksource_delta(
+					tkr->read(tkr->clock),
+					tkr->cycle_last,
+					tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;
@@ -958,7 +981,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	struct timespec64 ts64, tmp;
 	int ret = 0;
 
-	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_inject_offset_valid(ts))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*ts);
diff --git a/kernel/kernel/time/timekeeping_debug.c b/kernel/kernel/time/timekeeping_debug.c
index f6bd65236..107310a6f 100644
--- a/kernel/kernel/time/timekeeping_debug.c
+++ b/kernel/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
 
 #include "timekeeping_internal.h"
 
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
 {
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
 
 void tk_debug_account_sleep_time(struct timespec64 *t)
 {
-	sleep_time_bin[fls(t->tv_sec)]++;
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
 }
 
diff --git a/kernel/kernel/time/timer.c b/kernel/kernel/time/timer.c
index 016a0bf52..8b757541a 100644
--- a/kernel/kernel/time/timer.c
+++ b/kernel/kernel/time/timer.c
@@ -1051,7 +1051,7 @@ static void wait_for_running_timer(struct timer_list *timer)
 		   base->running_timer != timer);
 }
 
-# define wakeup_timer_waiters(b)	wake_up(&(b)->wait_for_running_timer)
+# define wakeup_timer_waiters(b)	wake_up_all(&(b)->wait_for_running_timer)
 #else
 static inline void wait_for_running_timer(struct timer_list *timer)
 {
@@ -1313,8 +1313,8 @@ static inline void __run_timers(struct tvec_base *base)
 			}
 		}
 	}
-	wakeup_timer_waiters(base);
 	spin_unlock_irq(&base->lock);
+	wakeup_timer_waiters(base);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON