Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer core changes from Ingo Molnar:
 "Continued cleanups of the core time and NTP code, plus more nohz work
  preparing for tick-less userspace execution."

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  time: Rework timekeeping functions to take timekeeper ptr as argument
  time: Move xtime_nsec adjustment underflow handling timekeeping_adjust
  time: Move arch_gettimeoffset() usage into timekeeping_get_ns()
  time: Refactor accumulation of nsecs to secs
  time: Condense timekeeper.xtime into xtime_sec
  time: Explicitly use u32 instead of int for shift values
  time: Whitespace cleanups per Ingo%27s requests
  nohz: Move next idle expiry time record into idle logic area
  nohz: Move ts->idle_calls incrementation into strict idle logic
  nohz: Rename ts->idle_tick to ts->last_tick
  nohz: Make nohz API agnostic against idle ticks cputime accounting
  nohz: Separate idle sleeping time accounting from nohz logic
  timers: Improve get_next_timer_interrupt()
  timers: Add accounting of non deferrable timers
  timers: Consolidate base->next_timer update
  timers: Create detach_if_pending() and use it

include/linux/tick.h

@@ -31,10 +31,10 @@ enum tick_nohz_mode {
  * struct tick_sched - sched tick emulation and no idle tick control/stats
  * @sched_timer:	hrtimer to schedule the periodic tick in high
  *			resolution mode
- * @idle_tick:		Store the last idle tick expiry time when the tick
- *			timer is modified for idle sleeps. This is necessary
+ * @last_tick:		Store the last tick expiry time when the tick
+ *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
- *			when the CPU returns from idle
+ *			when the CPU returns from nohz sleep.
  * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
@@ -51,7 +51,7 @@ struct tick_sched {
 	struct hrtimer			sched_timer;
 	unsigned long			check_clocks;
 	enum tick_nohz_mode		nohz_mode;
-	ktime_t				idle_tick;
+	ktime_t				last_tick;
 	int				inidle;
 	int				tick_stopped;
 	unsigned long			idle_jiffies;

kernel/time/tick-sched.c

@@ -271,50 +271,15 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
-static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
+static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
+					 ktime_t now, int cpu)
 {
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
+	ktime_t last_update, expires, ret = { .tv64 = 0 };
 	unsigned long rcu_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;
-
-	cpu = smp_processor_id();
-	ts = &per_cpu(tick_cpu_sched, cpu);
-
-	now = tick_nohz_start_idle(cpu, ts);
-
-	/*
-	 * If this cpu is offline and it is the one which updates
-	 * jiffies, then give up the assignment and let it be taken by
-	 * the cpu which runs the tick timer next. If we don't drop
-	 * this here the jiffies might be stale and do_timer() never
-	 * invoked.
-	 */
-	if (unlikely(!cpu_online(cpu))) {
-		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-	}
-
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
-		return;
 
-	if (need_resched())
-		return;
-
-	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
-		static int ratelimit;
-
-		if (ratelimit < 10) {
-			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       (unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
-		return;
-	}
-
-	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&xtime_lock);
@@ -397,6 +362,8 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
 			goto out;
 
+		ret = expires;
+
 		/*
 		 * nohz_stop_sched_tick can be called several times before
 		 * the nohz_restart_sched_tick is called. This happens when
@@ -408,16 +375,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 			select_nohz_load_balancer(1);
 			calc_load_enter_idle();
 
-			ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
+			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 			ts->tick_stopped = 1;
-			ts->idle_jiffies = last_jiffies;
 		}
 
-		ts->idle_sleeps++;
-
-		/* Mark expires */
-		ts->idle_expires = expires;
-
 		/*
 		 * If the expiration time == KTIME_MAX, then
 		 * in this case we simply stop the tick timer.
@@ -448,6 +409,65 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 	ts->next_jiffies = next_jiffies;
 	ts->last_jiffies = last_jiffies;
 	ts->sleep_length = ktime_sub(dev->next_event, now);
+
+	return ret;
+}
+
+static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
+{
+	/*
+	 * If this cpu is offline and it is the one which updates
+	 * jiffies, then give up the assignment and let it be taken by
+	 * the cpu which runs the tick timer next. If we don't drop
+	 * this here the jiffies might be stale and do_timer() never
+	 * invoked.
+	 */
+	if (unlikely(!cpu_online(cpu))) {
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+	}
+
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+		return false;
+
+	if (need_resched())
+		return false;
+
+	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
+		static int ratelimit;
+
+		if (ratelimit < 10) {
+			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+			       (unsigned int) local_softirq_pending());
+			ratelimit++;
+		}
+		return false;
+	}
+
+	return true;
+}
+
+static void __tick_nohz_idle_enter(struct tick_sched *ts)
+{
+	ktime_t now, expires;
+	int cpu = smp_processor_id();
+
+	now = tick_nohz_start_idle(cpu, ts);
+
+	if (can_stop_idle_tick(cpu, ts)) {
+		int was_stopped = ts->tick_stopped;
+
+		ts->idle_calls++;
+
+		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
+		if (expires.tv64 > 0LL) {
+			ts->idle_sleeps++;
+			ts->idle_expires = expires;
+		}
+
+		if (!was_stopped && ts->tick_stopped)
+			ts->idle_jiffies = ts->last_jiffies;
+	}
 }
 
 /**
@@ -485,7 +505,7 @@ void tick_nohz_idle_enter(void)
 	 * update of the idle time accounting in tick_nohz_start_idle().
 	 */
 	ts->inidle = 1;
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 
 	local_irq_enable();
 }
@@ -505,7 +525,7 @@ void tick_nohz_irq_exit(void)
 	if (!ts->inidle)
 		return;
 
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 }
 
 /**
@@ -523,7 +543,7 @@ ktime_t tick_nohz_get_sleep_length(void)
 static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 {
 	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
 
 	while (1) {
 		/* Forward the time to expire in the future */
@@ -546,6 +566,41 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	}
 }
 
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
+{
+	/* Update jiffies first */
+	select_nohz_load_balancer(0);
+	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
+
+	touch_softlockup_watchdog();
+	/*
+	 * Cancel the scheduled timer and restore the tick
+	 */
+	ts->tick_stopped  = 0;
+	ts->idle_exittime = now;
+
+	tick_nohz_restart(ts, now);
+}
+
+static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	unsigned long ticks;
+	/*
+	 * We stopped the tick in idle. Update process times would miss the
+	 * time we slept as update_process_times does only a 1 tick
+	 * accounting. Enforce that this is accounted to idle !
+	 */
+	ticks = jiffies - ts->idle_jiffies;
+	/*
+	 * We might be one off. Do not randomly account a huge number of ticks!
+	 */
+	if (ticks && ticks < LONG_MAX)
+		account_idle_ticks(ticks);
+#endif
+}
+
 /**
  * tick_nohz_idle_exit - restart the idle tick from the idle task
  *
@@ -557,9 +612,6 @@ void tick_nohz_idle_exit(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	unsigned long ticks;
-#endif
 	ktime_t now;
 
 	local_irq_disable();
@@ -574,40 +626,11 @@ void tick_nohz_idle_exit(void)
 	if (ts->idle_active)
 		tick_nohz_stop_idle(cpu, now);
 
-	if (!ts->tick_stopped) {
-		local_irq_enable();
-		return;
+	if (ts->tick_stopped) {
+		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_account_idle_ticks(ts);
 	}
 
-	/* Update jiffies first */
-	select_nohz_load_balancer(0);
-	tick_do_update_jiffies64(now);
-	update_cpu_load_nohz();
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	/*
-	 * We stopped the tick in idle. Update process times would miss the
-	 * time we slept as update_process_times does only a 1 tick
-	 * accounting. Enforce that this is accounted to idle !
-	 */
-	ticks = jiffies - ts->idle_jiffies;
-	/*
-	 * We might be one off. Do not randomly account a huge number of ticks!
-	 */
-	if (ticks && ticks < LONG_MAX)
-		account_idle_ticks(ticks);
-#endif
-
-	calc_load_exit_idle();
-	touch_softlockup_watchdog();
-	/*
-	 * Cancel the scheduled timer and restore the tick
-	 */
-	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;
-
-	tick_nohz_restart(ts, now);
-
 	local_irq_enable();
 }
 
@@ -811,7 +834,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 		 */
 		if (ts->tick_stopped) {
 			touch_softlockup_watchdog();
-			ts->idle_jiffies++;
+			if (idle_cpu(cpu))
+				ts->idle_jiffies++;
 		}
 		update_process_times(user_mode(regs));
 		profile_tick(CPU_PROFILING);

kernel/time/timekeeping.c

@@ -24,32 +24,32 @@
 /* Structure holding internal timekeeping values. */
 struct timekeeper {
 	/* Current clocksource used for timekeeping. */
-	struct clocksource *clock;
+	struct clocksource	*clock;
 	/* NTP adjusted clock multiplier */
-	u32	mult;
+	u32			mult;
 	/* The shift value of the current clocksource. */
-	int	shift;
-
+	u32			shift;
 	/* Number of clock cycles in one NTP interval. */
-	cycle_t cycle_interval;
+	cycle_t			cycle_interval;
 	/* Number of clock shifted nano seconds in one NTP interval. */
-	u64	xtime_interval;
+	u64			xtime_interval;
 	/* shifted nano seconds left over when rounding cycle_interval */
-	s64	xtime_remainder;
+	s64			xtime_remainder;
 	/* Raw nano seconds accumulated per NTP interval. */
-	u32	raw_interval;
+	u32			raw_interval;
+
+	/* Current CLOCK_REALTIME time in seconds */
+	u64			xtime_sec;
+	/* Clock shifted nano seconds */
+	u64			xtime_nsec;
 
-	/* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */
-	u64	xtime_nsec;
 	/* Difference between accumulated time and NTP time in ntp
 	 * shifted nano seconds. */
-	s64	ntp_error;
+	s64			ntp_error;
 	/* Shift conversion between clock shifted nano seconds and
 	 * ntp shifted nano seconds. */
-	int	ntp_error_shift;
+	u32			ntp_error_shift;
 
-	/* The current time */
-	struct timespec xtime;
 	/*
 	 * wall_to_monotonic is what we need to add to xtime (or xtime corrected
 	 * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
@@ -64,20 +64,17 @@ struct timekeeper {
 	 * - wall_to_monotonic is no longer the boot time, getboottime must be
 	 * used instead.
 	 */
-	struct timespec wall_to_monotonic;
+	struct timespec		wall_to_monotonic;
 	/* time spent in suspend */
-	struct timespec total_sleep_time;
+	struct timespec		total_sleep_time;
 	/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
-	struct timespec raw_time;
-
+	struct timespec		raw_time;
 	/* Offset clock monotonic -> clock realtime */
-	ktime_t offs_real;
-
+	ktime_t			offs_real;
 	/* Offset clock monotonic -> clock boottime */
-	ktime_t offs_boot;
-
+	ktime_t			offs_boot;
 	/* Seqlock for all timekeeper values */
-	seqlock_t lock;
+	seqlock_t		lock;
 };
 
 static struct timekeeper timekeeper;
@@ -88,11 +85,37 @@ static struct timekeeper timekeeper;
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
 
-
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
+static inline void tk_normalize_xtime(struct timekeeper *tk)
+{
+	while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) {
+		tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift;
+		tk->xtime_sec++;
+	}
+}
 
+static struct timespec tk_xtime(struct timekeeper *tk)
+{
+	struct timespec ts;
+
+	ts.tv_sec = tk->xtime_sec;
+	ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
+	return ts;
+}
+
+static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts)
+{
+	tk->xtime_sec = ts->tv_sec;
+	tk->xtime_nsec = ts->tv_nsec << tk->shift;
+}
+
+static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts)
+{
+	tk->xtime_sec += ts->tv_sec;
+	tk->xtime_nsec += ts->tv_nsec << tk->shift;
+}
 
 /**
  * timekeeper_setup_internals - Set up internals to use clocksource clock.
@@ -104,12 +127,14 @@ int __read_mostly timekeeping_suspended;
  *
  * Unless you're the timekeeping code, you should not be using this!
  */
-static void timekeeper_setup_internals(struct clocksource *clock)
+static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 {
 	cycle_t interval;
 	u64 tmp, ntpinterval;
+	struct clocksource *old_clock;
 
-	timekeeper.clock = clock;
+	old_clock = tk->clock;
+	tk->clock = clock;
 	clock->cycle_last = clock->read(clock);
 
 	/* Do the ns -> cycle conversion first, using original mult */
@@ -122,80 +147,96 @@ static void timekeeper_setup_internals(struct clocksource *clock)
 		tmp = 1;
 
 	interval = (cycle_t) tmp;
-	timekeeper.cycle_interval = interval;
+	tk->cycle_interval = interval;
 
 	/* Go back from cycles -> shifted ns */
-	timekeeper.xtime_interval = (u64) interval * clock->mult;
-	timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval;
-	timekeeper.raw_interval =
+	tk->xtime_interval = (u64) interval * clock->mult;
+	tk->xtime_remainder = ntpinterval - tk->xtime_interval;
+	tk->raw_interval =
 		((u64) interval * clock->mult) >> clock->shift;
 
-	timekeeper.xtime_nsec = 0;
-	timekeeper.shift = clock->shift;
+	 /* if changing clocks, convert xtime_nsec shift units */
+	if (old_clock) {
+		int shift_change = clock->shift - old_clock->shift;
+		if (shift_change < 0)
+			tk->xtime_nsec >>= -shift_change;
+		else
+			tk->xtime_nsec <<= shift_change;
+	}
+	tk->shift = clock->shift;
 
-	timekeeper.ntp_error = 0;
-	timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
+	tk->ntp_error = 0;
+	tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
 
 	/*
 	 * The timekeeper keeps its own mult values for the currently
 	 * active clocksource. These value will be adjusted via NTP
 	 * to counteract clock drifting.
 	 */
-	timekeeper.mult = clock->mult;
+	tk->mult = clock->mult;
 }
 
 /* Timekeeper helper functions. */
-static inline s64 timekeeping_get_ns(void)
+static inline s64 timekeeping_get_ns(struct timekeeper *tk)
 {
 	cycle_t cycle_now, cycle_delta;
 	struct clocksource *clock;
+	s64 nsec;
 
 	/* read clocksource: */
-	clock = timekeeper.clock;
+	clock = tk->clock;
 	cycle_now = clock->read(clock);
 
 	/* 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 clocksource_cyc2ns(cycle_delta, timekeeper.mult,
-				  timekeeper.shift);
+	nsec = cycle_delta * tk->mult + tk->xtime_nsec;
+	nsec >>= tk->shift;
+
+	/* If arch requires, add in gettimeoffset() */
+	return nsec + arch_gettimeoffset();
 }
 
-static inline s64 timekeeping_get_ns_raw(void)
+static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
 {
 	cycle_t cycle_now, cycle_delta;
 	struct clocksource *clock;
+	s64 nsec;
 
 	/* read clocksource: */
-	clock = timekeeper.clock;
+	clock = tk->clock;
 	cycle_now = clock->read(clock);
 
 	/* calculate the delta since the last update_wall_time: */
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
 
-	/* return delta convert to nanoseconds. */
-	return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+	/* convert delta to nanoseconds. */
+	nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
+
+	/* If arch requires, add in gettimeoffset() */
+	return nsec + arch_gettimeoffset();
 }
 
-static void update_rt_offset(void)
+static void update_rt_offset(struct timekeeper *tk)
 {
-	struct timespec tmp, *wtm = &timekeeper.wall_to_monotonic;
+	struct timespec tmp, *wtm = &tk->wall_to_monotonic;
 
 	set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
-	timekeeper.offs_real = timespec_to_ktime(tmp);
+	tk->offs_real = timespec_to_ktime(tmp);
 }
 
 /* must hold write on timekeeper.lock */
-static void timekeeping_update(bool clearntp)
+static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
+	struct timespec xt;
+
 	if (clearntp) {
-		timekeeper.ntp_error = 0;
+		tk->ntp_error = 0;
 		ntp_clear();
 	}
-	update_rt_offset();
-	update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic,
-			 timekeeper.clock, timekeeper.mult);
+	update_rt_offset(tk);
+	xt = tk_xtime(tk);
+	update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult);
 }
 
 
@@ -206,27 +247,26 @@ static void timekeeping_update(bool clearntp)
  * update_wall_time(). This is useful before significant clock changes,
  * as it avoids having to deal with this time offset explicitly.
  */
-static void timekeeping_forward_now(void)
+static void timekeeping_forward_now(struct timekeeper *tk)
 {
 	cycle_t cycle_now, cycle_delta;
 	struct clocksource *clock;
 	s64 nsec;
 
-	clock = timekeeper.clock;
+	clock = tk->clock;
 	cycle_now = clock->read(clock);
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
 	clock->cycle_last = cycle_now;
 
-	nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult,
-				  timekeeper.shift);
+	tk->xtime_nsec += cycle_delta * tk->mult;
 
 	/* If arch requires, add in gettimeoffset() */
-	nsec += arch_gettimeoffset();
+	tk->xtime_nsec += arch_gettimeoffset() << tk->shift;
 
-	timespec_add_ns(&timekeeper.xtime, nsec);
+	tk_normalize_xtime(tk);
 
 	nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
-	timespec_add_ns(&timekeeper.raw_time, nsec);
+	timespec_add_ns(&tk->raw_time, nsec);
 }
 
 /**
@@ -238,18 +278,15 @@ static void timekeeping_forward_now(void)
 void getnstimeofday(struct timespec *ts)
 {
 	unsigned long seq;
-	s64 nsecs;
+	s64 nsecs = 0;
 
 	WARN_ON(timekeeping_suspended);
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
 
-		*ts = timekeeper.xtime;
-		nsecs = timekeeping_get_ns();
-
-		/* If arch requires, add in gettimeoffset() */
-		nsecs += arch_gettimeoffset();
+		ts->tv_sec = timekeeper.xtime_sec;
+		ts->tv_nsec = timekeeping_get_ns(&timekeeper);
 
 	} while (read_seqretry(&timekeeper.lock, seq));
 
@@ -266,13 +303,10 @@ ktime_t ktime_get(void)
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
-		secs = timekeeper.xtime.tv_sec +
+		secs = timekeeper.xtime_sec +
 				timekeeper.wall_to_monotonic.tv_sec;
-		nsecs = timekeeper.xtime.tv_nsec +
+		nsecs = timekeeping_get_ns(&timekeeper) +
 				timekeeper.wall_to_monotonic.tv_nsec;
-		nsecs += timekeeping_get_ns();
-		/* If arch requires, add in gettimeoffset() */
-		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&timekeeper.lock, seq));
 	/*
@@ -295,22 +329,19 @@ void ktime_get_ts(struct timespec *ts)
 {
 	struct timespec tomono;
 	unsigned int seq;
-	s64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
-		*ts = timekeeper.xtime;
+		ts->tv_sec = timekeeper.xtime_sec;
+		ts->tv_nsec = timekeeping_get_ns(&timekeeper);
 		tomono = timekeeper.wall_to_monotonic;
-		nsecs = timekeeping_get_ns();
-		/* If arch requires, add in gettimeoffset() */
-		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&timekeeper.lock, seq));
 
 	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
-				ts->tv_nsec + tomono.tv_nsec + nsecs);
+				ts->tv_nsec + tomono.tv_nsec);
 }
 EXPORT_SYMBOL_GPL(ktime_get_ts);
 
@@ -333,20 +364,14 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 	WARN_ON_ONCE(timekeeping_suspended);
 
 	do {
-		u32 arch_offset;
-
 		seq = read_seqbegin(&timekeeper.lock);
 
 		*ts_raw = timekeeper.raw_time;
-		*ts_real = timekeeper.xtime;
-
-		nsecs_raw = timekeeping_get_ns_raw();
-		nsecs_real = timekeeping_get_ns();
+		ts_real->tv_sec = timekeeper.xtime_sec;
+		ts_real->tv_nsec = 0;
 
-		/* If arch requires, add in gettimeoffset() */
-		arch_offset = arch_gettimeoffset();
-		nsecs_raw += arch_offset;
-		nsecs_real += arch_offset;
+		nsecs_raw = timekeeping_get_ns_raw(&timekeeper);
+		nsecs_real = timekeeping_get_ns(&timekeeper);
 
 	} while (read_seqretry(&timekeeper.lock, seq));
 
@@ -381,7 +406,7 @@ EXPORT_SYMBOL(do_gettimeofday);
  */
 int do_settimeofday(const struct timespec *tv)
 {
-	struct timespec ts_delta;
+	struct timespec ts_delta, xt;
 	unsigned long flags;
 
 	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
@@ -389,15 +414,18 @@ int do_settimeofday(const struct timespec *tv)
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
 
-	timekeeping_forward_now();
+	timekeeping_forward_now(&timekeeper);
+
+	xt = tk_xtime(&timekeeper);
+	ts_delta.tv_sec = tv->tv_sec - xt.tv_sec;
+	ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec;
 
-	ts_delta.tv_sec = tv->tv_sec - timekeeper.xtime.tv_sec;
-	ts_delta.tv_nsec = tv->tv_nsec - timekeeper.xtime.tv_nsec;
 	timekeeper.wall_to_monotonic =
 			timespec_sub(timekeeper.wall_to_monotonic, ts_delta);
 
-	timekeeper.xtime = *tv;
-	timekeeping_update(true);
+	tk_set_xtime(&timekeeper, tv);
+
+	timekeeping_update(&timekeeper, true);
 
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
@@ -424,13 +452,14 @@ int timekeeping_inject_offset(struct timespec *ts)
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
 
-	timekeeping_forward_now();
+	timekeeping_forward_now(&timekeeper);
+
 
-	timekeeper.xtime = timespec_add(timekeeper.xtime, *ts);
+	tk_xtime_add(&timekeeper, ts);
 	timekeeper.wall_to_monotonic =
 				timespec_sub(timekeeper.wall_to_monotonic, *ts);
 
-	timekeeping_update(true);
+	timekeeping_update(&timekeeper, true);
 
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
@@ -455,14 +484,14 @@ static int change_clocksource(void *data)
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
 
-	timekeeping_forward_now();
+	timekeeping_forward_now(&timekeeper);
 	if (!new->enable || new->enable(new) == 0) {
 		old = timekeeper.clock;
-		timekeeper_setup_internals(new);
+		tk_setup_internals(&timekeeper, new);
 		if (old->disable)
 			old->disable(old);
 	}
-	timekeeping_update(true);
+	timekeeping_update(&timekeeper, true);
 
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
@@ -512,7 +541,7 @@ void getrawmonotonic(struct timespec *ts)
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
-		nsecs = timekeeping_get_ns_raw();
+		nsecs = timekeeping_get_ns_raw(&timekeeper);
 		*ts = timekeeper.raw_time;
 
 	} while (read_seqretry(&timekeeper.lock, seq));
@@ -547,6 +576,7 @@ u64 timekeeping_max_deferment(void)
 {
 	unsigned long seq;
 	u64 ret;
+
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
 
@@ -607,19 +637,17 @@ void __init timekeeping_init(void)
 	clock = clocksource_default_clock();
 	if (clock->enable)
 		clock->enable(clock);
-	timekeeper_setup_internals(clock);
+	tk_setup_internals(&timekeeper, clock);
 
-	timekeeper.xtime.tv_sec = now.tv_sec;
-	timekeeper.xtime.tv_nsec = now.tv_nsec;
+	tk_set_xtime(&timekeeper, &now);
 	timekeeper.raw_time.tv_sec = 0;
 	timekeeper.raw_time.tv_nsec = 0;
-	if (boot.tv_sec == 0 && boot.tv_nsec == 0) {
-		boot.tv_sec = timekeeper.xtime.tv_sec;
-		boot.tv_nsec = timekeeper.xtime.tv_nsec;
-	}
+	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
+		boot = tk_xtime(&timekeeper);
+
 	set_normalized_timespec(&timekeeper.wall_to_monotonic,
 				-boot.tv_sec, -boot.tv_nsec);
-	update_rt_offset();
+	update_rt_offset(&timekeeper);
 	timekeeper.total_sleep_time.tv_sec = 0;
 	timekeeper.total_sleep_time.tv_nsec = 0;
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
@@ -641,7 +669,8 @@ static void update_sleep_time(struct timespec t)
  * Takes a timespec offset measuring a suspend interval and properly
  * adds the sleep offset to the timekeeping variables.
  */
-static void __timekeeping_inject_sleeptime(struct timespec *delta)
+static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
+							struct timespec *delta)
 {
 	if (!timespec_valid(delta)) {
 		printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
@@ -649,10 +678,9 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
 		return;
 	}
 
-	timekeeper.xtime = timespec_add(timekeeper.xtime, *delta);
-	timekeeper.wall_to_monotonic =
-			timespec_sub(timekeeper.wall_to_monotonic, *delta);
-	update_sleep_time(timespec_add(timekeeper.total_sleep_time, *delta));
+	tk_xtime_add(tk, delta);
+	tk->wall_to_monotonic = timespec_sub(tk->wall_to_monotonic, *delta);
+	update_sleep_time(timespec_add(tk->total_sleep_time, *delta));
 }
 
 
@@ -678,11 +706,11 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
 
-	timekeeping_forward_now();
+	timekeeping_forward_now(&timekeeper);
 
-	__timekeeping_inject_sleeptime(delta);
+	__timekeeping_inject_sleeptime(&timekeeper, delta);
 
-	timekeeping_update(true);
+	timekeeping_update(&timekeeper, true);
 
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
@@ -711,13 +739,13 @@ static void timekeeping_resume(void)
 
 	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
 		ts = timespec_sub(ts, timekeeping_suspend_time);
-		__timekeeping_inject_sleeptime(&ts);
+		__timekeeping_inject_sleeptime(&timekeeper, &ts);
 	}
 	/* re-base the last cycle value */
 	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
 	timekeeper.ntp_error = 0;
 	timekeeping_suspended = 0;
-	timekeeping_update(false);
+	timekeeping_update(&timekeeper, false);
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 
 	touch_softlockup_watchdog();
@@ -737,7 +765,7 @@ static int timekeeping_suspend(void)
 	read_persistent_clock(&timekeeping_suspend_time);
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
-	timekeeping_forward_now();
+	timekeeping_forward_now(&timekeeper);
 	timekeeping_suspended = 1;
 
 	/*
@@ -746,7 +774,7 @@ static int timekeeping_suspend(void)
 	 * try to compensate so the difference in system time
 	 * and persistent_clock time stays close to constant.
 	 */
-	delta = timespec_sub(timekeeper.xtime, timekeeping_suspend_time);
+	delta = timespec_sub(tk_xtime(&timekeeper), timekeeping_suspend_time);
 	delta_delta = timespec_sub(delta, old_delta);
 	if (abs(delta_delta.tv_sec)  >= 2) {
 		/*
@@ -785,7 +813,8 @@ device_initcall(timekeeping_init_ops);
  * If the error is already larger, we look ahead even further
  * to compensate for late or lost adjustments.
  */
-static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
+static __always_inline int timekeeping_bigadjust(struct timekeeper *tk,
+						 s64 error, s64 *interval,
 						 s64 *offset)
 {
 	s64 tick_error, i;
@@ -801,7 +830,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
 	 * here.  This is tuned so that an error of about 1 msec is adjusted
 	 * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
 	 */
-	error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
+	error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
 	error2 = abs(error2);
 	for (look_ahead = 0; error2 > 0; look_ahead++)
 		error2 >>= 2;
@@ -810,8 +839,8 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
 	 * Now calculate the error in (1 << look_ahead) ticks, but first
 	 * remove the single look ahead already included in the error.
 	 */
-	tick_error = ntp_tick_length() >> (timekeeper.ntp_error_shift + 1);
-	tick_error -= timekeeper.xtime_interval >> 1;
+	tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1);
+	tick_error -= tk->xtime_interval >> 1;
 	error = ((error - tick_error) >> look_ahead) + tick_error;
 
 	/* Finally calculate the adjustment shift value.  */
@@ -836,9 +865,9 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval,
  * this is optimized for the most common adjustments of -1,0,1,
  * for other values we can do a bit more work.
  */
-static void timekeeping_adjust(s64 offset)
+static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 {
-	s64 error, interval = timekeeper.cycle_interval;
+	s64 error, interval = tk->cycle_interval;
 	int adj;
 
 	/*
@@ -854,7 +883,7 @@ static void timekeeping_adjust(s64 offset)
 	 *
 	 * Note: It does not "save" on aggravation when reading the code.
 	 */
-	error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
+	error = tk->ntp_error >> (tk->ntp_error_shift - 1);
 	if (error > interval) {
 		/*
 		 * We now divide error by 4(via shift), which checks if
@@ -876,7 +905,8 @@ static void timekeeping_adjust(s64 offset)
 		if (likely(error <= interval))
 			adj = 1;
 		else
-			adj = timekeeping_bigadjust(error, &interval, &offset);
+			adj = timekeeping_bigadjust(tk, error, &interval,
+							&offset);
 	} else if (error < -interval) {
 		/* See comment above, this is just switched for the negative */
 		error >>= 2;
@@ -885,18 +915,17 @@ static void timekeeping_adjust(s64 offset)
 			interval = -interval;
 			offset = -offset;
 		} else
-			adj = timekeeping_bigadjust(error, &interval, &offset);
-	} else /* No adjustment needed */
+			adj = timekeeping_bigadjust(tk, error, &interval,
+							&offset);
+	} else
 		return;
 
-	if (unlikely(timekeeper.clock->maxadj &&
-			(timekeeper.mult + adj >
-			timekeeper.clock->mult + timekeeper.clock->maxadj))) {
+	if (unlikely(tk->clock->maxadj &&
+		(tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
 		printk_once(KERN_WARNING
 			"Adjusting %s more than 11%% (%ld vs %ld)\n",
-			timekeeper.clock->name, (long)timekeeper.mult + adj,
-			(long)timekeeper.clock->mult +
-				timekeeper.clock->maxadj);
+			tk->clock->name, (long)tk->mult + adj,
+			(long)tk->clock->mult + tk->clock->maxadj);
 	}
 	/*
 	 * So the following can be confusing.
@@ -947,11 +976,60 @@ static void timekeeping_adjust(s64 offset)
 	 *
 	 * XXX - TODO: Doc ntp_error calculation.
 	 */
-	timekeeper.mult += adj;
-	timekeeper.xtime_interval += interval;
-	timekeeper.xtime_nsec -= offset;
-	timekeeper.ntp_error -= (interval - offset) <<
-				timekeeper.ntp_error_shift;
+	tk->mult += adj;
+	tk->xtime_interval += interval;
+	tk->xtime_nsec -= offset;
+	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
+
+	/*
+	 * It may be possible that when we entered this function, xtime_nsec
+	 * was very small.  Further, if we're slightly speeding the clocksource
+	 * in the code above, its possible the required corrective factor to
+	 * xtime_nsec could cause it to underflow.
+	 *
+	 * Now, since we already accumulated the second, cannot simply roll
+	 * the accumulated second back, since the NTP subsystem has been
+	 * notified via second_overflow. So instead we push xtime_nsec forward
+	 * by the amount we underflowed, and add that amount into the error.
+	 *
+	 * We'll correct this error next time through this function, when
+	 * xtime_nsec is not as small.
+	 */
+	if (unlikely((s64)tk->xtime_nsec < 0)) {
+		s64 neg = -(s64)tk->xtime_nsec;
+		tk->xtime_nsec = 0;
+		tk->ntp_error += neg << tk->ntp_error_shift;
+	}
+
+}
+
+
+/**
+ * accumulate_nsecs_to_secs - Accumulates nsecs into secs
+ *
+ * Helper function that accumulates a the nsecs greater then a second
+ * from the xtime_nsec field to the xtime_secs field.
+ * It also calls into the NTP code to handle leapsecond processing.
+ *
+ */
+static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+{
+	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+
+	while (tk->xtime_nsec >= nsecps) {
+		int leap;
+
+		tk->xtime_nsec -= nsecps;
+		tk->xtime_sec++;
+
+		/* Figure out if its a leap sec and apply if needed */
+		leap = second_overflow(tk->xtime_sec);
+		tk->xtime_sec += leap;
+		tk->wall_to_monotonic.tv_sec -= leap;
+		if (leap)
+			clock_was_set_delayed();
+
+	}
 }
 
 
@@ -964,46 +1042,36 @@ static void timekeeping_adjust(s64 offset)
  *
  * Returns the unconsumed cycles.
  */
-static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
+						u32 shift)
 {
-	u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
 	u64 raw_nsecs;
 
-	/* If the offset is smaller than a shifted interval, do nothing */
-	if (offset < timekeeper.cycle_interval<<shift)
+	/* If the offset is smaller then a shifted interval, do nothing */
+	if (offset < tk->cycle_interval<<shift)
 		return offset;
 
 	/* Accumulate one shifted interval */
-	offset -= timekeeper.cycle_interval << shift;
-	timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+	offset -= tk->cycle_interval << shift;
+	tk->clock->cycle_last += tk->cycle_interval << shift;
 
-	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
-	while (timekeeper.xtime_nsec >= nsecps) {
-		int leap;
-		timekeeper.xtime_nsec -= nsecps;
-		timekeeper.xtime.tv_sec++;
-		leap = second_overflow(timekeeper.xtime.tv_sec);
-		timekeeper.xtime.tv_sec += leap;
-		timekeeper.wall_to_monotonic.tv_sec -= leap;
-		if (leap)
-			clock_was_set_delayed();
-	}
+	tk->xtime_nsec += tk->xtime_interval << shift;
+	accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
-	raw_nsecs = timekeeper.raw_interval << shift;
-	raw_nsecs += timekeeper.raw_time.tv_nsec;
+	raw_nsecs = tk->raw_interval << shift;
+	raw_nsecs += tk->raw_time.tv_nsec;
 	if (raw_nsecs >= NSEC_PER_SEC) {
 		u64 raw_secs = raw_nsecs;
 		raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
-		timekeeper.raw_time.tv_sec += raw_secs;
+		tk->raw_time.tv_sec += raw_secs;
 	}
-	timekeeper.raw_time.tv_nsec = raw_nsecs;
+	tk->raw_time.tv_nsec = raw_nsecs;
 
 	/* Accumulate error between NTP and clock interval */
-	timekeeper.ntp_error += ntp_tick_length() << shift;
-	timekeeper.ntp_error -=
-	    (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
-				(timekeeper.ntp_error_shift + shift);
+	tk->ntp_error += ntp_tick_length() << shift;
+	tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
+						(tk->ntp_error_shift + shift);
 
 	return offset;
 }
@@ -1019,6 +1087,7 @@ static void update_wall_time(void)
 	cycle_t offset;
 	int shift = 0, maxshift;
 	unsigned long flags;
+	s64 remainder;
 
 	write_seqlock_irqsave(&timekeeper.lock, flags);
 
@@ -1033,8 +1102,6 @@ static void update_wall_time(void)
 #else
 	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
-	timekeeper.xtime_nsec = (s64)timekeeper.xtime.tv_nsec <<
-						timekeeper.shift;
 
 	/*
 	 * With NO_HZ we may have to accumulate many cycle_intervals
@@ -1050,64 +1117,36 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
-		offset = logarithmic_accumulation(offset, shift);
+		offset = logarithmic_accumulation(&timekeeper, offset, shift);
 		if(offset < timekeeper.cycle_interval<<shift)
 			shift--;
 	}
 
 	/* correct the clock when NTP error is too big */
-	timekeeping_adjust(offset);
-
-	/*
-	 * Since in the loop above, we accumulate any amount of time
-	 * in xtime_nsec over a second into xtime.tv_sec, its possible for
-	 * xtime_nsec to be fairly small after the loop. Further, if we're
-	 * slightly speeding the clocksource up in timekeeping_adjust(),
-	 * its possible the required corrective factor to xtime_nsec could
-	 * cause it to underflow.
-	 *
-	 * Now, we cannot simply roll the accumulated second back, since
-	 * the NTP subsystem has been notified via second_overflow. So
-	 * instead we push xtime_nsec forward by the amount we underflowed,
-	 * and add that amount into the error.
-	 *
-	 * We'll correct this error next time through this function, when
-	 * xtime_nsec is not as small.
-	 */
-	if (unlikely((s64)timekeeper.xtime_nsec < 0)) {
-		s64 neg = -(s64)timekeeper.xtime_nsec;
-		timekeeper.xtime_nsec = 0;
-		timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
-	}
+	timekeeping_adjust(&timekeeper, offset);
 
 
 	/*
-	 * Store full nanoseconds into xtime after rounding it up and
-	 * add the remainder to the error difference.
-	 */
-	timekeeper.xtime.tv_nsec = ((s64)timekeeper.xtime_nsec >>
-						timekeeper.shift) + 1;
-	timekeeper.xtime_nsec -= (s64)timekeeper.xtime.tv_nsec <<
-						timekeeper.shift;
-	timekeeper.ntp_error +=	timekeeper.xtime_nsec <<
-				timekeeper.ntp_error_shift;
+	* Store only full nanoseconds into xtime_nsec after rounding
+	* it up and add the remainder to the error difference.
+	* XXX - This is necessary to avoid small 1ns inconsistnecies caused
+	* by truncating the remainder in vsyscalls. However, it causes
+	* additional work to be done in timekeeping_adjust(). Once
+	* the vsyscall implementations are converted to use xtime_nsec
+	* (shifted nanoseconds), this can be killed.
+	*/
+	remainder = timekeeper.xtime_nsec & ((1 << timekeeper.shift) - 1);
+	timekeeper.xtime_nsec -= remainder;
+	timekeeper.xtime_nsec += 1 << timekeeper.shift;
+	timekeeper.ntp_error += remainder << timekeeper.ntp_error_shift;
 
 	/*
 	 * Finally, make sure that after the rounding
-	 * xtime.tv_nsec isn't larger than NSEC_PER_SEC
+	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
-		int leap;
-		timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
-		timekeeper.xtime.tv_sec++;
-		leap = second_overflow(timekeeper.xtime.tv_sec);
-		timekeeper.xtime.tv_sec += leap;
-		timekeeper.wall_to_monotonic.tv_sec -= leap;
-		if (leap)
-			clock_was_set_delayed();
-	}
+	accumulate_nsecs_to_secs(&timekeeper);
 
-	timekeeping_update(false);
+	timekeeping_update(&timekeeper, false);
 
 out:
 	write_sequnlock_irqrestore(&timekeeper.lock, flags);
@@ -1152,21 +1191,20 @@ void get_monotonic_boottime(struct timespec *ts)
 {
 	struct timespec tomono, sleep;
 	unsigned int seq;
-	s64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
-		*ts = timekeeper.xtime;
+		ts->tv_sec = timekeeper.xtime_sec;
+		ts->tv_nsec = timekeeping_get_ns(&timekeeper);
 		tomono = timekeeper.wall_to_monotonic;
 		sleep = timekeeper.total_sleep_time;
-		nsecs = timekeeping_get_ns();
 
 	} while (read_seqretry(&timekeeper.lock, seq));
 
 	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
-			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec);
 }
 EXPORT_SYMBOL_GPL(get_monotonic_boottime);
 
@@ -1199,13 +1237,13 @@ EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
 
 unsigned long get_seconds(void)
 {
-	return timekeeper.xtime.tv_sec;
+	return timekeeper.xtime_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-	return timekeeper.xtime;
+	return tk_xtime(&timekeeper);
 }
 
 struct timespec current_kernel_time(void)
@@ -1216,7 +1254,7 @@ struct timespec current_kernel_time(void)
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
 
-		now = timekeeper.xtime;
+		now = tk_xtime(&timekeeper);
 	} while (read_seqretry(&timekeeper.lock, seq));
 
 	return now;
@@ -1231,7 +1269,7 @@ struct timespec get_monotonic_coarse(void)
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
 
-		now = timekeeper.xtime;
+		now = tk_xtime(&timekeeper);
 		mono = timekeeper.wall_to_monotonic;
 	} while (read_seqretry(&timekeeper.lock, seq));
 
@@ -1266,7 +1304,7 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
 
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
-		*xtim = timekeeper.xtime;
+		*xtim = tk_xtime(&timekeeper);
 		*wtom = timekeeper.wall_to_monotonic;
 		*sleep = timekeeper.total_sleep_time;
 	} while (read_seqretry(&timekeeper.lock, seq));
@@ -1290,11 +1328,8 @@ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
 	do {
 		seq = read_seqbegin(&timekeeper.lock);
 
-		secs = timekeeper.xtime.tv_sec;
-		nsecs = timekeeper.xtime.tv_nsec;
-		nsecs += timekeeping_get_ns();
-		/* If arch requires, add in gettimeoffset() */
-		nsecs += arch_gettimeoffset();
+		secs = timekeeper.xtime_sec;
+		nsecs = timekeeping_get_ns(&timekeeper);
 
 		*offs_real = timekeeper.offs_real;
 		*offs_boot = timekeeper.offs_boot;

kernel/time/timer_list.c

@@ -167,7 +167,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	{
 		struct tick_sched *ts = tick_get_tick_sched(cpu);
 		P(nohz_mode);
-		P_ns(idle_tick);
+		P_ns(last_tick);
 		P(tick_stopped);
 		P(idle_jiffies);
 		P(idle_calls);
@@ -259,7 +259,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.6\n");
+	SEQ_printf(m, "Timer List Version: v0.7\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 

kernel/timer.c

@@ -77,6 +77,7 @@ struct tvec_base {
 	struct timer_list *running_timer;
 	unsigned long timer_jiffies;
 	unsigned long next_timer;
+	unsigned long active_timers;
 	struct tvec_root tv1;
 	struct tvec tv2;
 	struct tvec tv3;
@@ -330,7 +331,8 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+static void
+__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
 	unsigned long expires = timer->expires;
 	unsigned long idx = expires - base->timer_jiffies;
@@ -372,6 +374,19 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 	list_add_tail(&timer->entry, vec);
 }
 
+static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+{
+	__internal_add_timer(base, timer);
+	/*
+	 * Update base->active_timers and base->next_timer
+	 */
+	if (!tbase_get_deferrable(timer->base)) {
+		if (time_before(timer->expires, base->next_timer))
+			base->next_timer = timer->expires;
+		base->active_timers++;
+	}
+}
+
 #ifdef CONFIG_TIMER_STATS
 void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
 {
@@ -654,8 +669,7 @@ void init_timer_deferrable_key(struct timer_list *timer,
 }
 EXPORT_SYMBOL(init_timer_deferrable_key);
 
-static inline void detach_timer(struct timer_list *timer,
-				int clear_pending)
+static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 {
 	struct list_head *entry = &timer->entry;
 
@@ -667,6 +681,29 @@ static inline void detach_timer(struct timer_list *timer,
 	entry->prev = LIST_POISON2;
 }
 
+static inline void
+detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
+{
+	detach_timer(timer, true);
+	if (!tbase_get_deferrable(timer->base))
+		timer->base->active_timers--;
+}
+
+static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
+			     bool clear_pending)
+{
+	if (!timer_pending(timer))
+		return 0;
+
+	detach_timer(timer, clear_pending);
+	if (!tbase_get_deferrable(timer->base)) {
+		timer->base->active_timers--;
+		if (timer->expires == base->next_timer)
+			base->next_timer = base->timer_jiffies;
+	}
+	return 1;
+}
+
 /*
  * We are using hashed locking: holding per_cpu(tvec_bases).lock
  * means that all timers which are tied to this base via timer->base are
@@ -712,16 +749,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
 	base = lock_timer_base(timer, &flags);
 
-	if (timer_pending(timer)) {
-		detach_timer(timer, 0);
-		if (timer->expires == base->next_timer &&
-		    !tbase_get_deferrable(timer->base))
-			base->next_timer = base->timer_jiffies;
-		ret = 1;
-	} else {
-		if (pending_only)
-			goto out_unlock;
-	}
+	ret = detach_if_pending(timer, base, false);
+	if (!ret && pending_only)
+		goto out_unlock;
 
 	debug_activate(timer, expires);
 
@@ -752,9 +782,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 	}
 
 	timer->expires = expires;
-	if (time_before(timer->expires, base->next_timer) &&
-	    !tbase_get_deferrable(timer->base))
-		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 
 out_unlock:
@@ -920,9 +947,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	spin_lock_irqsave(&base->lock, flags);
 	timer_set_base(timer, base);
 	debug_activate(timer, timer->expires);
-	if (time_before(timer->expires, base->next_timer) &&
-	    !tbase_get_deferrable(timer->base))
-		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 	/*
 	 * Check whether the other CPU is idle and needs to be
@@ -959,13 +983,7 @@ int del_timer(struct timer_list *timer)
 	timer_stats_timer_clear_start_info(timer);
 	if (timer_pending(timer)) {
 		base = lock_timer_base(timer, &flags);
-		if (timer_pending(timer)) {
-			detach_timer(timer, 1);
-			if (timer->expires == base->next_timer &&
-			    !tbase_get_deferrable(timer->base))
-				base->next_timer = base->timer_jiffies;
-			ret = 1;
-		}
+		ret = detach_if_pending(timer, base, true);
 		spin_unlock_irqrestore(&base->lock, flags);
 	}
 
@@ -990,19 +1008,10 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	base = lock_timer_base(timer, &flags);
 
-	if (base->running_timer == timer)
-		goto out;
-
-	timer_stats_timer_clear_start_info(timer);
-	ret = 0;
-	if (timer_pending(timer)) {
-		detach_timer(timer, 1);
-		if (timer->expires == base->next_timer &&
-		    !tbase_get_deferrable(timer->base))
-			base->next_timer = base->timer_jiffies;
-		ret = 1;
+	if (base->running_timer != timer) {
+		timer_stats_timer_clear_start_info(timer);
+		ret = detach_if_pending(timer, base, true);
 	}
-out:
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
@@ -1089,7 +1098,8 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 	 */
 	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
 		BUG_ON(tbase_get_base(timer->base) != base);
-		internal_add_timer(base, timer);
+		/* No accounting, while moving them */
+		__internal_add_timer(base, timer);
 	}
 
 	return index;
@@ -1178,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base)
 			timer_stats_account_timer(timer);
 
 			base->running_timer = timer;
-			detach_timer(timer, 1);
+			detach_expired_timer(timer, base);
 
 			spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn, data);
@@ -1316,18 +1326,21 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
 unsigned long get_next_timer_interrupt(unsigned long now)
 {
 	struct tvec_base *base = __this_cpu_read(tvec_bases);
-	unsigned long expires;
+	unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
 	 * Possible pending timers will be migrated later to an active cpu.
 	 */
 	if (cpu_is_offline(smp_processor_id()))
-		return now + NEXT_TIMER_MAX_DELTA;
+		return expires;
+
 	spin_lock(&base->lock);
-	if (time_before_eq(base->next_timer, base->timer_jiffies))
-		base->next_timer = __next_timer_interrupt(base);
-	expires = base->next_timer;
+	if (base->active_timers) {
+		if (time_before_eq(base->next_timer, base->timer_jiffies))
+			base->next_timer = __next_timer_interrupt(base);
+		expires = base->next_timer;
+	}
 	spin_unlock(&base->lock);
 
 	if (time_before_eq(expires, now))
@@ -1704,6 +1717,7 @@ static int __cpuinit init_timers_cpu(int cpu)
 
 	base->timer_jiffies = jiffies;
 	base->next_timer = base->timer_jiffies;
+	base->active_timers = 0;
 	return 0;
 }
 
@@ -1714,11 +1728,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea
 
 	while (!list_empty(head)) {
 		timer = list_first_entry(head, struct timer_list, entry);
-		detach_timer(timer, 0);
+		/* We ignore the accounting on the dying cpu */
+		detach_timer(timer, false);
 		timer_set_base(timer, new_base);
-		if (time_before(timer->expires, new_base->next_timer) &&
-		    !tbase_get_deferrable(timer->base))
-			new_base->next_timer = timer->expires;
 		internal_add_timer(new_base, timer);
 	}
 }