4 files changed, 145 insertions, 14 deletions

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 139c4db55f17..c86c940d1de3 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -156,6 +156,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @mult:               cycle to nanosecond multiplier
  * @shift:              cycle to nanosecond divisor (power of two)
  * @max_idle_ns:        max idle time permitted by the clocksource (nsecs)
+ * @maxadj              maximum adjustment value to mult (~11%)
  * @flags:              flags describing special properties
  * @archdata:           arch-specific data
  * @suspend:            suspend function for the clocksource, if necessary
@@ -172,7 +173,7 @@ struct clocksource {
         u32 mult;
         u32 shift;
         u64 max_idle_ns;
-
+        u32 maxadj;
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
         struct arch_clocksource_data archdata;
 #endif
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 422e567eecf6..ae34bf51682b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -885,10 +885,13 @@ 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;
 
-        if (&timer->node == timerqueue_getnext(&base->active)) {
+        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()) {
@@ -901,7 +904,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
                 }
 #endif
         }
-        timerqueue_del(&base->active, &timer->node);
         if (!timerqueue_getnext(&base->active))
                 base->cpu_base->active_bases &= ~(1 << base->index);
 out:
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cf52fda2e096..cfc65e1eb9fb 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -492,6 +492,22 @@ 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
  *
@@ -503,25 +519,28 @@ 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,
@@ -640,7 +659,6 @@ 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
@@ -661,6 +679,20 @@ 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);
@@ -701,6 +733,12 @@ 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/timekeeping.c b/kernel/time/timekeeping.c
index 2b021b0e8507..237841378c03 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));
 
@@ -802,14 +806,44 @@ static void timekeeping_adjust(s64 offset)
         s64 error, interval = timekeeper.cycle_interval;
         int adj;
 
+        /*
+         * The point of this is to check if the error is greater then half
+         * an interval.
+         *
+         * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+         *
+         * Note we subtract one in the shift, so that error is really error*2.
+         * This "saves" dividing(shifting) intererval twice, but keeps the
+         * (error > interval) comparision as still measuring if error is
+         * larger then half an interval.
+         *
+         * Note: It does not "save" on aggrivation when reading the code.
+         */
         error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
         if (error > interval) {
+                /*
+                 * We now divide error by 4(via shift), which checks if
+                 * the error is greater then twice the interval.
+                 * If it is greater, we need a bigadjust, if its smaller,
+                 * we can adjust by 1.
+                 */
                 error >>= 2;
+                /*
+                 * XXX - In update_wall_time, we round up to the next
+                 * nanosecond, and store the amount rounded up into
+                 * the error. This causes the likely below to be unlikely.
+                 *
+                 * The properfix is to avoid rounding up by using
+                 * the high precision timekeeper.xtime_nsec instead of
+                 * xtime.tv_nsec everywhere. Fixing this will take some
+                 * time.
+                 */
                 if (likely(error <= interval))
                         adj = 1;
                 else
                         adj = timekeeping_bigadjust(error, &interval, &offset);
         } else if (error < -interval) {
+                /* See comment above, this is just switched for the negative */
                 error >>= 2;
                 if (likely(error >= -interval)) {
                         adj = -1;
@@ -817,9 +851,65 @@ static void timekeeping_adjust(s64 offset)
                         offset = -offset;
                 } else
                         adj = timekeeping_bigadjust(error, &interval, &offset);
-        } else
+        } else /* No adjustment needed */
                 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);
+        /*
+         * So the following can be confusing.
+         *
+         * To keep things simple, lets assume adj == 1 for now.
+         *
+         * When adj != 1, remember that the interval and offset values
+         * have been appropriately scaled so the math is the same.
+         *
+         * The basic idea here is that we're increasing the multiplier
+         * by one, this causes the xtime_interval to be incremented by
+         * one cycle_interval. This is because:
+         *      xtime_interval = cycle_interval * mult
+         * So if mult is being incremented by one:
+         *      xtime_interval = cycle_interval * (mult + 1)
+         * Its the same as:
+         *      xtime_interval = (cycle_interval * mult) + cycle_interval
+         * Which can be shortened to:
+         *      xtime_interval += cycle_interval
+         *
+         * So offset stores the non-accumulated cycles. Thus the current
+         * time (in shifted nanoseconds) is:
+         *      now = (offset * adj) + xtime_nsec
+         * Now, even though we're adjusting the clock frequency, we have
+         * to keep time consistent. In other words, we can't jump back
+         * in time, and we also want to avoid jumping forward in time.
+         *
+         * So given the same offset value, we need the time to be the same
+         * both before and after the freq adjustment.
+         *      now = (offset * adj_1) + xtime_nsec_1
+         *      now = (offset * adj_2) + xtime_nsec_2
+         * So:
+         *      (offset * adj_1) + xtime_nsec_1 =
+         *              (offset * adj_2) + xtime_nsec_2
+         * And we know:
+         *      adj_2 = adj_1 + 1
+         * So:
+         *      (offset * adj_1) + xtime_nsec_1 =
+         *              (offset * (adj_1+1)) + xtime_nsec_2
+         *      (offset * adj_1) + xtime_nsec_1 =
+         *              (offset * adj_1) + offset + xtime_nsec_2
+         * Canceling the sides:
+         *      xtime_nsec_1 = offset + xtime_nsec_2
+         * Which gives us:
+         *      xtime_nsec_2 = xtime_nsec_1 - offset
+         * Which simplfies to:
+         *      xtime_nsec -= offset
+         *
+         * XXX - TODO: Doc ntp_error calculation.
+         */
         timekeeper.mult += adj;
         timekeeper.xtime_interval += interval;
         timekeeper.xtime_nsec -= offset;