summaryrefslogtreecommitdiffstats
path: root/kernel/time
diff options
context:
space:
mode:
authorDmitry Torokhov <dmitry.torokhov@gmail.com>2012-03-09 10:55:17 -0800
committerDmitry Torokhov <dmitry.torokhov@gmail.com>2012-03-09 10:55:17 -0800
commitb675b3667f6729dcd1036a2a129b35445947f905 (patch)
tree0d58791e9063d3ca2c352da6f3e7df2bdb876f9d /kernel/time
parent104a5f3cad8f2f27cadbdf0029400ecd9e17ccc0 (diff)
parent192cfd58774b4d17b2fe8bdc77d89c2ef4e0591d (diff)
downloadlinux-b675b3667f6729dcd1036a2a129b35445947f905.tar.gz
linux-b675b3667f6729dcd1036a2a129b35445947f905.tar.bz2
linux-b675b3667f6729dcd1036a2a129b35445947f905.zip
Merge commit 'v3.3-rc6' into next
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Kconfig2
-rw-r--r--kernel/time/alarmtimer.c2
-rw-r--r--kernel/time/clockevents.c1
-rw-r--r--kernel/time/clocksource.c111
-rw-r--r--kernel/time/tick-broadcast.c2
-rw-r--r--kernel/time/tick-sched.c105
-rw-r--r--kernel/time/timekeeping.c94
7 files changed, 241 insertions, 76 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index b26c2228fe92..2cf9cc7aa103 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -25,7 +25,7 @@ config HIGH_RES_TIMERS
config GENERIC_CLOCKEVENTS_BUILD
bool
default y
- depends on GENERIC_CLOCKEVENTS || GENERIC_CLOCKEVENTS_MIGR
+ depends on GENERIC_CLOCKEVENTS
config GENERIC_CLOCKEVENTS_MIN_ADJUST
bool
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index c436e790b21b..8a46f5d64504 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -195,7 +195,7 @@ 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);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ecd6ba36d6c..9cd928f7a7c6 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -17,7 +17,6 @@
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/smp.h>
-#include <linux/sysdev.h>
#include "tick-internal.h"
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cf52fda2e096..a45ca167ab24 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -23,8 +23,8 @@
* o Allow clocksource drivers to be unregistered
*/
+#include <linux/device.h>
#include <linux/clocksource.h>
-#include <linux/sysdev.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
@@ -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,
@@ -529,7 +548,7 @@ 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
@@ -628,7 +647,7 @@ static void clocksource_enqueue(struct clocksource *cs)
/**
* __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -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
@@ -651,7 +669,7 @@ 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)
@@ -661,13 +679,27 @@ 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);
/**
* __clocksource_register_scale - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -695,12 +727,18 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
/**
* clocksource_register - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
*
* Returns -EBUSY if registration fails, zero otherwise.
*/
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);
@@ -723,6 +761,8 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
/**
* clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs: clocksource to be changed
+ * @rating: new rating
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
@@ -734,6 +774,7 @@ EXPORT_SYMBOL(clocksource_change_rating);
/**
* clocksource_unregister - remove a registered clocksource
+ * @cs: clocksource to be unregistered
*/
void clocksource_unregister(struct clocksource *cs)
{
@@ -749,13 +790,14 @@ EXPORT_SYMBOL(clocksource_unregister);
/**
* sysfs_show_current_clocksources - sysfs interface for current clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing current clocksource.
*/
static ssize_t
-sysfs_show_current_clocksources(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+sysfs_show_current_clocksources(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
ssize_t count = 0;
@@ -769,14 +811,15 @@ sysfs_show_current_clocksources(struct sys_device *dev,
/**
* sysfs_override_clocksource - interface for manually overriding clocksource
* @dev: unused
+ * @attr: unused
* @buf: name of override clocksource
* @count: length of buffer
*
* Takes input from sysfs interface for manually overriding the default
* clocksource selection.
*/
-static ssize_t sysfs_override_clocksource(struct sys_device *dev,
- struct sysdev_attribute *attr,
+static ssize_t sysfs_override_clocksource(struct device *dev,
+ struct device_attribute *attr,
const char *buf, size_t count)
{
size_t ret = count;
@@ -804,13 +847,14 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
/**
* sysfs_show_available_clocksources - sysfs interface for listing clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing registered clocksources
*/
static ssize_t
-sysfs_show_available_clocksources(struct sys_device *dev,
- struct sysdev_attribute *attr,
+sysfs_show_available_clocksources(struct device *dev,
+ struct device_attribute *attr,
char *buf)
{
struct clocksource *src;
@@ -839,35 +883,36 @@ sysfs_show_available_clocksources(struct sys_device *dev,
/*
* Sysfs setup bits:
*/
-static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
+static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
sysfs_override_clocksource);
-static SYSDEV_ATTR(available_clocksource, 0444,
+static DEVICE_ATTR(available_clocksource, 0444,
sysfs_show_available_clocksources, NULL);
-static struct sysdev_class clocksource_sysclass = {
+static struct bus_type clocksource_subsys = {
.name = "clocksource",
+ .dev_name = "clocksource",
};
-static struct sys_device device_clocksource = {
+static struct device device_clocksource = {
.id = 0,
- .cls = &clocksource_sysclass,
+ .bus = &clocksource_subsys,
};
static int __init init_clocksource_sysfs(void)
{
- int error = sysdev_class_register(&clocksource_sysclass);
+ int error = subsys_system_register(&clocksource_subsys, NULL);
if (!error)
- error = sysdev_register(&device_clocksource);
+ error = device_register(&device_clocksource);
if (!error)
- error = sysdev_create_file(
+ error = device_create_file(
&device_clocksource,
- &attr_current_clocksource);
+ &dev_attr_current_clocksource);
if (!error)
- error = sysdev_create_file(
+ error = device_create_file(
&device_clocksource,
- &attr_available_clocksource);
+ &dev_attr_available_clocksource);
return error;
}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f954282d9a82..fd4a7b1625a2 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/tick-sched.c b/kernel/time/tick-sched.c
index 40420644d0ba..7656642e4b8e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -275,42 +275,17 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
-/**
- * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
- *
- * When the next event is more than a tick into the future, stop the idle tick
- * Called either from the idle loop or from irq_exit() when an idle period was
- * just interrupted by an interrupt which did not cause a reschedule.
- */
-void tick_nohz_stop_sched_tick(int inidle)
+static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
- unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
- struct tick_sched *ts;
+ unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
- local_irq_save(flags);
-
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
- /*
- * Call to tick_nohz_start_idle stops the last_update_time from being
- * updated. Thus, it must not be called in the event we are called from
- * irq_exit() with the prior state different than idle.
- */
- if (!inidle && !ts->inidle)
- goto end;
-
- /*
- * Set ts->inidle unconditionally. Even if the system did not
- * switch to NOHZ mode the cpu frequency governers rely on the
- * update of the idle time accounting in tick_nohz_start_idle().
- */
- ts->inidle = 1;
-
now = tick_nohz_start_idle(cpu, ts);
/*
@@ -326,10 +301,10 @@ void tick_nohz_stop_sched_tick(int inidle)
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
- goto end;
+ return;
if (need_resched())
- goto end;
+ return;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
@@ -339,7 +314,7 @@ void tick_nohz_stop_sched_tick(int inidle)
(unsigned int) local_softirq_pending());
ratelimit++;
}
- goto end;
+ return;
}
ts->idle_calls++;
@@ -434,7 +409,6 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
- rcu_enter_nohz();
}
ts->idle_sleeps++;
@@ -472,8 +446,64 @@ out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
-end:
- local_irq_restore(flags);
+}
+
+/**
+ * tick_nohz_idle_enter - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ * Called when we start the idle loop.
+ *
+ * The arch is responsible of calling:
+ *
+ * - rcu_idle_enter() after its last use of RCU before the CPU is put
+ * to sleep.
+ * - rcu_idle_exit() before the first use of RCU after the CPU is woken up.
+ */
+void tick_nohz_idle_enter(void)
+{
+ struct tick_sched *ts;
+
+ WARN_ON_ONCE(irqs_disabled());
+
+ /*
+ * Update the idle state in the scheduler domain hierarchy
+ * when tick_nohz_stop_sched_tick() is called from the idle loop.
+ * State will be updated to busy during the first busy tick after
+ * exiting idle.
+ */
+ set_cpu_sd_state_idle();
+
+ local_irq_disable();
+
+ ts = &__get_cpu_var(tick_cpu_sched);
+ /*
+ * set ts->inidle unconditionally. even if the system did not
+ * switch to nohz mode the cpu frequency governers rely on the
+ * update of the idle time accounting in tick_nohz_start_idle().
+ */
+ ts->inidle = 1;
+ tick_nohz_stop_sched_tick(ts);
+
+ local_irq_enable();
+}
+
+/**
+ * tick_nohz_irq_exit - update next tick event from interrupt exit
+ *
+ * When an interrupt fires while we are idle and it doesn't cause
+ * a reschedule, it may still add, modify or delete a timer, enqueue
+ * an RCU callback, etc...
+ * So we need to re-calculate and reprogram the next tick event.
+ */
+void tick_nohz_irq_exit(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+ if (!ts->inidle)
+ return;
+
+ tick_nohz_stop_sched_tick(ts);
}
/**
@@ -515,11 +545,13 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
}
/**
- * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
+ * tick_nohz_idle_exit - restart the idle tick from the idle task
*
* Restart the idle tick when the CPU is woken up from idle
+ * This also exit the RCU extended quiescent state. The CPU
+ * can use RCU again after this function is called.
*/
-void tick_nohz_restart_sched_tick(void)
+void tick_nohz_idle_exit(void)
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -529,6 +561,7 @@ void tick_nohz_restart_sched_tick(void)
ktime_t now;
local_irq_disable();
+
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
@@ -543,8 +576,6 @@ void tick_nohz_restart_sched_tick(void)
ts->inidle = 0;
- rcu_exit_nohz();
-
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 169479994755..e6a5a6bc2769 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -131,7 +131,7 @@ static inline s64 timekeeping_get_ns_raw(void)
/* calculate the delta since the last update_wall_time: */
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- /* return delta convert to nanoseconds using ntp adjusted mult. */
+ /* return delta convert to nanoseconds. */
return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
}
@@ -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) interval twice, but keeps the
+ * (error > interval) comparison as still measuring if error is
+ * larger then half an interval.
+ *
+ * Note: It does not "save" on aggravation 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 proper fix 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;