Merge commit 'v2.6.36' into wip-merge-2.6.36

Conflicts:
	Makefile
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/syscall_table_32.S
	kernel/sched.c
	kernel/time/tick-sched.c

Relevant API and functions changes (solved in this commit):
- (API) .enqueue_task() (enqueue_task_litmus),
  dequeue_task() (dequeue_task_litmus),
  [litmus/sched_litmus.c]
- (API) .select_task_rq() (select_task_rq_litmus)
  [litmus/sched_litmus.c]
- (API) sysrq_dump_trace_buffer() and sysrq_handle_kill_rt_tasks()
  [litmus/sched_trace.c]
- struct kfifo internal buffer name changed (buffer -> buf)
  [litmus/sched_trace.c]
- add_wait_queue_exclusive_locked -> __add_wait_queue_tail_exclusive
  [litmus/fmlp.c]
- syscall numbers for both x86_32 and x86_64

7 files changed, 189 insertions, 112 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 95ed42951e0..f06a8a36564 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -6,7 +6,7 @@ config TICK_ONESHOT
 
 config NO_HZ
         bool "Tickless System (Dynamic Ticks)"
-        depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+        depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
         select TICK_ONESHOT
         help
           This option enables a tickless system: timer interrupts will
@@ -15,7 +15,7 @@ config NO_HZ
 
 config HIGH_RES_TIMERS
         bool "High Resolution Timer Support"
-        depends on GENERIC_TIME && GENERIC_CLOCKEVENTS
+        depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
         select TICK_ONESHOT
         help
           This option enables high resolution timer support. If your
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1f5dde63745..c18d7efa1b4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -531,7 +531,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
         return max_nsecs - (max_nsecs >> 5);
 }
 
-#ifdef CONFIG_GENERIC_TIME
+#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 
 /**
  * clocksource_select - Select the best clocksource available
@@ -577,7 +577,7 @@ static void clocksource_select(void)
         }
 }
 
-#else /* CONFIG_GENERIC_TIME */
+#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
 
 static inline void clocksource_select(void) { }
 
@@ -625,6 +625,73 @@ static void clocksource_enqueue(struct clocksource *cs)
         list_add(&cs->list, entry);
 }
 
+
+/*
+ * Maximum time we expect to go between ticks. This includes idle
+ * tickless time. It provides the trade off between selecting a
+ * mult/shift pair that is very precise but can only handle a short
+ * period of time, vs. a mult/shift pair that can handle long periods
+ * of time but isn't as precise.
+ *
+ * This is a subsystem constant, and actual hardware limitations
+ * may override it (ie: clocksources that wrap every 3 seconds).
+ */
+#define MAX_UPDATE_LENGTH 5 /* Seconds */
+
+/**
+ * __clocksource_updatefreq_scale - Used update clocksource with new freq
+ * @t:          clocksource to be registered
+ * @scale:      Scale factor multiplied against freq to get clocksource hz
+ * @freq:       clocksource frequency (cycles per second) divided by scale
+ *
+ * This should only be called from the clocksource->enable() method.
+ *
+ * This *SHOULD NOT* be called directly! Please use the
+ * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions.
+ */
+void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
+{
+        /*
+         * Ideally we want to use  some of the limits used in
+         * clocksource_max_deferment, to provide a more informed
+         * MAX_UPDATE_LENGTH. But for now this just gets the
+         * register interface working properly.
+         */
+        clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+                                      NSEC_PER_SEC/scale,
+                                      MAX_UPDATE_LENGTH*scale);
+        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
+ * @scale:      Scale factor multiplied against freq to get clocksource hz
+ * @freq:       clocksource frequency (cycles per second) divided by scale
+ *
+ * Returns -EBUSY if registration fails, zero otherwise.
+ *
+ * This *SHOULD NOT* be called directly! Please use the
+ * clocksource_register_hz() or clocksource_register_khz helper functions.
+ */
+int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
+{
+
+        /* Intialize mult/shift and max_idle_ns */
+        __clocksource_updatefreq_scale(cs, scale, freq);
+
+        /* Add clocksource to the clcoksource list */
+        mutex_lock(&clocksource_mutex);
+        clocksource_enqueue(cs);
+        clocksource_select();
+        clocksource_enqueue_watchdog(cs);
+        mutex_unlock(&clocksource_mutex);
+        return 0;
+}
+EXPORT_SYMBOL_GPL(__clocksource_register_scale);
+
+
 /**
  * clocksource_register - Used to install new clocksources
  * @t:          clocksource to be registered
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7c0f180d6e9..c63116863a8 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -69,7 +69,7 @@ static s64			time_freq;
 /* time at last adjustment (secs):                                      */
 static long                     time_reftime;
 
-long                            time_adjust;
+static long                     time_adjust;
 
 /* constant (boot-param configurable) NTP tick adjustment (upscaled)    */
 static s64                      ntp_tick_adj;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b3bafd5fc66..48b2761b566 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -188,7 +188,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
         /*
          * Setup the next period for devices, which do not have
          * periodic mode. We read dev->next_event first and add to it
-         * when the event alrady expired. clockevents_program_event()
+         * when the event already expired. clockevents_program_event()
          * sets dev->next_event only when the event is really
          * programmed to the device.
          */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0adc54bd7c7..bb2d8b7850a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,35 +150,65 @@ static void tick_nohz_update_jiffies(ktime_t now)
         touch_softlockup_watchdog();
 }
 
+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
+{
+        ktime_t delta;
+
+        if (ts->idle_active) {
+                delta = ktime_sub(now, ts->idle_entrytime);
+                ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+                if (nr_iowait_cpu(cpu) > 0)
+                        ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+                ts->idle_entrytime = now;
+        }
+
+        if (last_update_time)
+                *last_update_time = ktime_to_us(now);
+
+}
+
 static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-        ktime_t delta;
 
-        delta = ktime_sub(now, ts->idle_entrytime);
-        ts->idle_lastupdate = now;
-        ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+        update_ts_time_stats(cpu, ts, now, NULL);
         ts->idle_active = 0;
 
         sched_clock_idle_wakeup_event(0);
 }
 
-static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
 {
-        ktime_t now, delta;
+        ktime_t now;
 
         now = ktime_get();
-        if (ts->idle_active) {
-                delta = ktime_sub(now, ts->idle_entrytime);
-                ts->idle_lastupdate = now;
-                ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-        }
+
+        update_ts_time_stats(cpu, ts, now, NULL);
+
         ts->idle_entrytime = now;
         ts->idle_active = 1;
         sched_clock_idle_sleep_event();
         return now;
 }
 
+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
         if (!tick_nohz_enabled)
                 return -1;
 
-        if (ts->idle_active)
-                *last_update_time = ktime_to_us(ts->idle_lastupdate);
-        else
-                *last_update_time = ktime_to_us(ktime_get());
+        update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
 
         return ktime_to_us(ts->idle_sleeptime);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
+/*
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+        if (!tick_nohz_enabled)
+                return -1;
+
+        update_ts_time_stats(cpu, ts, ktime_get(), last_update_time);
+
+        return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
  *
@@ -231,7 +284,7 @@ void tick_nohz_stop_sched_tick(int inidle)
          */
         ts->inidle = 1;
 
-        now = tick_nohz_start_idle(ts);
+        now = tick_nohz_start_idle(cpu, ts);
 
         /*
          * If this cpu is offline and it is the one which updates
@@ -352,13 +405,7 @@ void tick_nohz_stop_sched_tick(int inidle)
                  * the scheduler tick in nohz_restart_sched_tick.
                  */
                 if (!ts->tick_stopped) {
-                        if (select_nohz_load_balancer(1)) {
-                                /*
-                                 * sched tick not stopped!
-                                 */
-                                cpumask_clear_cpu(cpu, nohz_cpu_mask);
-                                goto out;
-                        }
+                        select_nohz_load_balancer(1);
 
                         ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
                         ts->tick_stopped = 1;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 39f6177fafa..49010d822f7 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -153,8 +153,8 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
  * - wall_to_monotonic is no longer the boot time, getboottime must be
  * used instead.
  */
-struct timespec xtime __attribute__ ((aligned (16)));
-struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
+static struct timespec xtime __attribute__ ((aligned (16)));
+static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
 static struct timespec total_sleep_time;
 
 /*
@@ -165,23 +165,15 @@ struct timespec raw_time;
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
-        xtime_cache = xtime;
-        timespec_add_ns(&xtime_cache, nsec);
-}
-
 /* must hold xtime_lock */
 void timekeeping_leap_insert(int leapsecond)
 {
         xtime.tv_sec += leapsecond;
         wall_to_monotonic.tv_sec -= leapsecond;
-        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
+        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+                        timekeeper.mult);
 }
 
-#ifdef CONFIG_GENERIC_TIME
-
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -332,12 +324,11 @@ int do_settimeofday(struct timespec *tv)
 
         xtime = *tv;
 
-        update_xtime_cache(0);
-
         timekeeper.ntp_error = 0;
         ntp_clear();
 
-        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
+        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+                                timekeeper.mult);
 
         write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -385,52 +376,6 @@ void timekeeping_notify(struct clocksource *clock)
         tick_clock_notify();
 }
 
-#else /* GENERIC_TIME */
-
-static inline void timekeeping_forward_now(void) { }
-
-/**
- * ktime_get - get the monotonic time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get(void)
-{
-        struct timespec now;
-
-        ktime_get_ts(&now);
-
-        return timespec_to_ktime(now);
-}
-EXPORT_SYMBOL_GPL(ktime_get);
-
-/**
- * ktime_get_ts - get the monotonic clock in timespec format
- * @ts:         pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime
- * clock and the wall_to_monotonic offset and stores the result
- * in normalized timespec format in the variable pointed to by @ts.
- */
-void ktime_get_ts(struct timespec *ts)
-{
-        struct timespec tomono;
-        unsigned long seq;
-
-        do {
-                seq = read_seqbegin(&xtime_lock);
-                getnstimeofday(ts);
-                tomono = wall_to_monotonic;
-
-        } while (read_seqretry(&xtime_lock, seq));
-
-        set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
-                                ts->tv_nsec + tomono.tv_nsec);
-}
-EXPORT_SYMBOL_GPL(ktime_get_ts);
-
-#endif /* !GENERIC_TIME */
-
 /**
  * ktime_get_real - get the real (wall-) time in ktime_t format
  *
@@ -559,7 +504,6 @@ void __init timekeeping_init(void)
         }
         set_normalized_timespec(&wall_to_monotonic,
                                 -boot.tv_sec, -boot.tv_nsec);
-        update_xtime_cache(0);
         total_sleep_time.tv_sec = 0;
         total_sleep_time.tv_nsec = 0;
         write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -589,11 +533,10 @@ static int timekeeping_resume(struct sys_device *dev)
 
         if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
                 ts = timespec_sub(ts, timekeeping_suspend_time);
-                xtime = timespec_add_safe(xtime, ts);
+                xtime = timespec_add(xtime, ts);
                 wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
-                total_sleep_time = timespec_add_safe(total_sleep_time, ts);
+                total_sleep_time = timespec_add(total_sleep_time, ts);
         }
-        update_xtime_cache(0);
         /* re-base the last cycle value */
         timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
         timekeeper.ntp_error = 0;
@@ -747,6 +690,7 @@ static void timekeeping_adjust(s64 offset)
 static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 {
         u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+        u64 raw_nsecs;
 
         /* If the offset is smaller then a shifted interval, do nothing */
         if (offset < timekeeper.cycle_interval<<shift)
@@ -763,12 +707,15 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
                 second_overflow();
         }
 
-        /* Accumulate into raw time */
-        raw_time.tv_nsec += timekeeper.raw_interval << shift;;
-        while (raw_time.tv_nsec >= NSEC_PER_SEC) {
-                raw_time.tv_nsec -= NSEC_PER_SEC;
-                raw_time.tv_sec++;
+        /* Accumulate raw time */
+        raw_nsecs = timekeeper.raw_interval << shift;
+        raw_nsecs += raw_time.tv_nsec;
+        if (raw_nsecs >= NSEC_PER_SEC) {
+                u64 raw_secs = raw_nsecs;
+                raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
+                raw_time.tv_sec += raw_secs;
         }
+        raw_time.tv_nsec = raw_nsecs;
 
         /* Accumulate error between NTP and clock interval */
         timekeeper.ntp_error += tick_length << shift;
@@ -788,7 +735,6 @@ void update_wall_time(void)
 {
         struct clocksource *clock;
         cycle_t offset;
-        u64 nsecs;
         int shift = 0, maxshift;
 
         /* Make sure we're fully resumed: */
@@ -796,10 +742,11 @@ void update_wall_time(void)
                 return;
 
         clock = timekeeper.clock;
-#ifdef CONFIG_GENERIC_TIME
-        offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
-#else
+
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
         offset = timekeeper.cycle_interval;
+#else
+        offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
         timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
@@ -847,7 +794,9 @@ void update_wall_time(void)
                 timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
         }
 
-        /* store full nanoseconds into xtime after rounding it up and
+
+        /*
+         * Store full nanoseconds into xtime after rounding it up and
          * add the remainder to the error difference.
          */
         xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
@@ -855,11 +804,19 @@ void update_wall_time(void)
         timekeeper.ntp_error += timekeeper.xtime_nsec <<
                                 timekeeper.ntp_error_shift;
 
-        nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
-        update_xtime_cache(nsecs);
+        /*
+         * Finally, make sure that after the rounding
+         * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+         */
+        if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+                xtime.tv_nsec -= NSEC_PER_SEC;
+                xtime.tv_sec++;
+                second_overflow();
+        }
 
         /* check to see if there is a new clocksource to use */
-        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
+        update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+                                timekeeper.mult);
 }
 
 /**
@@ -890,19 +847,24 @@ EXPORT_SYMBOL_GPL(getboottime);
  */
 void monotonic_to_bootbased(struct timespec *ts)
 {
-        *ts = timespec_add_safe(*ts, total_sleep_time);
+        *ts = timespec_add(*ts, total_sleep_time);
 }
 EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
 
 unsigned long get_seconds(void)
 {
-        return xtime_cache.tv_sec;
+        return xtime.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-        return xtime_cache;
+        return xtime;
+}
+
+struct timespec __get_wall_to_monotonic(void)
+{
+        return wall_to_monotonic;
 }
 
 struct timespec current_kernel_time(void)
@@ -913,7 +875,7 @@ struct timespec current_kernel_time(void)
         do {
                 seq = read_seqbegin(&xtime_lock);
 
-                now = xtime_cache;
+                now = xtime;
         } while (read_seqretry(&xtime_lock, seq));
 
         return now;
@@ -928,7 +890,7 @@ struct timespec get_monotonic_coarse(void)
         do {
                 seq = read_seqbegin(&xtime_lock);
 
-                now = xtime_cache;
+                now = xtime;
                 mono = wall_to_monotonic;
         } while (read_seqretry(&xtime_lock, seq));
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1a4a7dd7877..ab8f5e33fa9 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -176,6 +176,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
                 P_ns(idle_waketime);
                 P_ns(idle_exittime);
                 P_ns(idle_sleeptime);
+                P_ns(iowait_sleeptime);
                 P(last_jiffies);
                 P(next_jiffies);
                 P_ns(idle_expires);