5 files changed, 105 insertions, 20 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index e2fd74b8e8c..cae2ad7491b 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,5 +1,5 @@
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
-obj-y += timeconv.o posix-clock.o alarmtimer.o
+obj-y += timeconv.o posix-clock.o #alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)         += clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 59f369f98a0..8b70c76910a 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -181,7 +181,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
                 struct alarm *alarm;
                 ktime_t expired = next->expires;
 
-                if (expired.tv64 >= now.tv64)
+                if (expired.tv64 > now.tv64)
                         break;
 
                 alarm = container_of(next, struct alarm, node);
@@ -441,6 +441,8 @@ static int alarm_timer_create(struct k_itimer *new_timer)
 static void alarm_timer_get(struct k_itimer *timr,
                                 struct itimerspec *cur_setting)
 {
+        memset(cur_setting, 0, sizeof(struct itimerspec));
+
         cur_setting->it_interval =
                         ktime_to_timespec(timr->it.alarmtimer.period);
         cur_setting->it_value =
@@ -479,11 +481,17 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
         if (!rtcdev)
                 return -ENOTSUPP;
 
-        /* Save old values */
-        old_setting->it_interval =
-                        ktime_to_timespec(timr->it.alarmtimer.period);
-        old_setting->it_value =
-                        ktime_to_timespec(timr->it.alarmtimer.node.expires);
+        /*
+         * XXX HACK! Currently we can DOS a system if the interval
+         * period on alarmtimers is too small. Cap the interval here
+         * to 100us and solve this properly in a future patch! -jstultz
+         */
+        if ((new_setting->it_interval.tv_sec == 0) &&
+                        (new_setting->it_interval.tv_nsec < 100000))
+                new_setting->it_interval.tv_nsec = 100000;
+
+        if (old_setting)
+                alarm_timer_get(timr, old_setting);
 
         /* If the timer was already set, cancel it */
         alarm_cancel(&timr->it.alarmtimer);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index e0980f0d9a0..8f77da18fef 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -494,6 +494,22 @@ void clocksource_touch_watchdog(void)
 }
 
 /**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+        u64 ret;
+        /*
+         * We won't try to correct for more then 11% adjustments (110,000 ppm),
+         */
+        ret = (u64)cs->mult * 11;
+        do_div(ret,100);
+        return (u32)ret;
+}
+
+/**
  * clocksource_max_deferment - Returns max time the clocksource can be deferred
  * @cs:         Pointer to clocksource
  *
@@ -505,25 +521,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
         /*
          * Calculate the maximum number of cycles that we can pass to the
          * cyc2ns function without overflowing a 64-bit signed result. The
-         * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-         * is equivalent to the below.
-         * max_cycles < (2^63)/cs->mult
-         * max_cycles < 2^(log2((2^63)/cs->mult))
-         * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-         * max_cycles < 2^(63 - log2(cs->mult))
-         * max_cycles < 1 << (63 - log2(cs->mult))
+         * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+         * which is equivalent to the below.
+         * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+         * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+         * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+         * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+         * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
          * Please note that we add 1 to the result of the log2 to account for
          * any rounding errors, ensure the above inequality is satisfied and
          * no overflow will occur.
          */
-        max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+        max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
 
         /*
          * The actual maximum number of cycles we can defer the clocksource is
          * determined by the minimum of max_cycles and cs->mask.
+         * Note: Here we subtract the maxadj to make sure we don't sleep for
+         * too long if there's a large negative adjustment.
          */
         max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-        max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+        max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+                                        cs->shift);
 
         /*
          * To ensure that the clocksource does not wrap whilst we are idle,
@@ -531,7 +550,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
          * note a margin of 12.5% is used because this can be computed with
          * a shift, versus say 10% which would require division.
          */
-        return max_nsecs - (max_nsecs >> 5);
+        return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -642,7 +661,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
         u64 sec;
-
         /*
          * Calc the maximum number of seconds which we can run before
          * wrapping around. For clocksources which have a mask > 32bit
@@ -653,7 +671,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
          * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
          * margin as we do in clocksource_max_deferment()
          */
-        sec = (cs->mask - (cs->mask >> 5));
+        sec = (cs->mask - (cs->mask >> 3));
         do_div(sec, freq);
         do_div(sec, scale);
         if (!sec)
@@ -663,6 +681,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 
         clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
                                NSEC_PER_SEC / scale, sec * scale);
+
+        /*
+         * for clocksources that have large mults, to avoid overflow.
+         * Since mult may be adjusted by ntp, add an safety extra margin
+         *
+         */
+        cs->maxadj = clocksource_max_adjustment(cs);
+        while ((cs->mult + cs->maxadj < cs->mult)
+                || (cs->mult - cs->maxadj > cs->mult)) {
+                cs->mult >>= 1;
+                cs->shift--;
+                cs->maxadj = clocksource_max_adjustment(cs);
+        }
+
         cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -703,6 +735,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
  */
 int clocksource_register(struct clocksource *cs)
 {
+        /* calculate max adjustment for given mult/shift */
+        cs->maxadj = clocksource_max_adjustment(cs);
+        WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+                "Clocksource %s might overflow on 11%% adjustment\n",
+                cs->name);
+
         /* calculate max idle time permitted for this clocksource */
         cs->max_idle_ns = clocksource_max_deferment(cs);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index c7218d13273..7a90d021b79 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -71,7 +71,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
              (dev->features & CLOCK_EVT_FEAT_C3STOP))
                 return 0;
 
-        clockevents_exchange_device(NULL, dev);
+        clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
         tick_broadcast_device.evtdev = dev;
         if (!cpumask_empty(tick_get_broadcast_mask()))
                 tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 342408cf68d..6f9798bf240 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -249,6 +249,8 @@ ktime_t ktime_get(void)
                 secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
                 nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
                 nsecs += timekeeping_get_ns();
+                /* If arch requires, add in gettimeoffset() */
+                nsecs += arch_gettimeoffset();
 
         } while (read_seqretry(&xtime_lock, seq));
         /*
@@ -280,6 +282,8 @@ void ktime_get_ts(struct timespec *ts)
                 *ts = xtime;
                 tomono = wall_to_monotonic;
                 nsecs = timekeeping_get_ns();
+                /* If arch requires, add in gettimeoffset() */
+                nsecs += arch_gettimeoffset();
 
         } while (read_seqretry(&xtime_lock, seq));
 
@@ -604,6 +608,12 @@ static struct timespec timekeeping_suspend_time;
  */
 static void __timekeeping_inject_sleeptime(struct timespec *delta)
 {
+        if (!timespec_valid(delta)) {
+                printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
+                                        "sleep delta value!\n");
+                return;
+        }
+
         xtime = timespec_add(xtime, *delta);
         wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
         total_sleep_time = timespec_add(total_sleep_time, *delta);
@@ -686,12 +696,34 @@ static void timekeeping_resume(void)
 static int timekeeping_suspend(void)
 {
         unsigned long flags;
+        struct timespec         delta, delta_delta;
+        static struct timespec  old_delta;
 
         read_persistent_clock(&timekeeping_suspend_time);
 
         write_seqlock_irqsave(&xtime_lock, flags);
         timekeeping_forward_now();
         timekeeping_suspended = 1;
+
+        /*
+         * To avoid drift caused by repeated suspend/resumes,
+         * which each can add ~1 second drift error,
+         * try to compensate so the difference in system time
+         * and persistent_clock time stays close to constant.
+         */
+        delta = timespec_sub(xtime, timekeeping_suspend_time);
+        delta_delta = timespec_sub(delta, old_delta);
+        if (abs(delta_delta.tv_sec)  >= 2) {
+                /*
+                 * if delta_delta is too large, assume time correction
+                 * has occured and set old_delta to the current delta.
+                 */
+                old_delta = delta;
+        } else {
+                /* Otherwise try to adjust old_system to compensate */
+                timekeeping_suspend_time =
+                        timespec_add(timekeeping_suspend_time, delta_delta);
+        }
         write_sequnlock_irqrestore(&xtime_lock, flags);
 
         clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
@@ -792,6 +824,13 @@ static void timekeeping_adjust(s64 offset)
         } else
                 return;
 
+        WARN_ONCE(timekeeper.clock->maxadj &&
+                        (timekeeper.mult + adj > timekeeper.clock->mult +
+                                                timekeeper.clock->maxadj),
+                        "Adjusting %s more then 11%% (%ld vs %ld)\n",
+                        timekeeper.clock->name, (long)timekeeper.mult + adj,
+                        (long)timekeeper.clock->mult +
+                                timekeeper.clock->maxadj);
         timekeeper.mult += adj;
         timekeeper.xtime_interval += interval;
         timekeeper.xtime_nsec -= offset;