10 files changed, 151 insertions, 99 deletions

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 67932ea78c17..76212b2a99de 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -274,72 +274,3 @@ void clockevents_notify(unsigned long reason, void *arg)
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
 
-#ifdef CONFIG_SYSFS
-
-/**
- * clockevents_show_registered - sysfs interface for listing clockevents
- * @dev:        unused
- * @buf:        char buffer to be filled with clock events list
- *
- * Provides sysfs interface for listing registered clock event devices
- */
-static ssize_t clockevents_show_registered(struct sys_device *dev, char *buf)
-{
-        struct list_head *tmp;
-        char *p = buf;
-        int cpu;
-
-        spin_lock(&clockevents_lock);
-
-        list_for_each(tmp, &clockevent_devices) {
-                struct clock_event_device *ce;
-
-                ce = list_entry(tmp, struct clock_event_device, list);
-                p += sprintf(p, "%-20s F:%04x M:%d", ce->name,
-                             ce->features, ce->mode);
-                p += sprintf(p, " C:");
-                if (!cpus_equal(ce->cpumask, cpu_possible_map)) {
-                        for_each_cpu_mask(cpu, ce->cpumask)
-                                p += sprintf(p, " %d", cpu);
-                } else {
-                        /*
-                         * FIXME: Add the cpu which is handling this sucker
-                         */
-                }
-                p += sprintf(p, "\n");
-        }
-
-        spin_unlock(&clockevents_lock);
-
-        return p - buf;
-}
-
-/*
- * Sysfs setup bits:
- */
-static SYSDEV_ATTR(registered, 0600,
-                   clockevents_show_registered, NULL);
-
-static struct sysdev_class clockevents_sysclass = {
-        set_kset_name("clockevents"),
-};
-
-static struct sys_device clockevents_sys_device = {
-        .id     = 0,
-        .cls    = &clockevents_sysclass,
-};
-
-static int __init clockevents_sysfs_init(void)
-{
-        int error = sysdev_class_register(&clockevents_sysclass);
-
-        if (!error)
-                error = sysdev_register(&clockevents_sys_device);
-        if (!error)
-                error = sysdev_create_file(
-                                &clockevents_sys_device,
-                                &attr_registered);
-        return error;
-}
-device_initcall(clockevents_sysfs_init);
-#endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 193a0793af95..fe5c7db24247 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -55,16 +55,18 @@ static DEFINE_SPINLOCK(clocksource_lock);
 static char override_name[32];
 static int finished_booting;
 
-/* clocksource_done_booting - Called near the end of bootup
+/* clocksource_done_booting - Called near the end of core bootup
  *
- * Hack to avoid lots of clocksource churn at boot time
+ * Hack to avoid lots of clocksource churn at boot time.
+ * We use fs_initcall because we want this to start before
+ * device_initcall but after subsys_initcall.
  */
 static int __init clocksource_done_booting(void)
 {
         finished_booting = 1;
         return 0;
 }
-late_initcall(clocksource_done_booting);
+fs_initcall(clocksource_done_booting);
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static LIST_HEAD(watchdog_list);
@@ -149,7 +151,8 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                         watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
                         add_timer(&watchdog_timer);
                 }
-        } else if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) {
+        } else {
+                if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
                         cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 
                 if (!watchdog || cs->rating > watchdog->rating) {
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 3be8da8fed7e..4c256fdb8875 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -69,4 +69,4 @@ static int __init init_jiffies_clocksource(void)
         return clocksource_register(&clocksource_jiffies);
 }
 
-module_init(init_jiffies_clocksource);
+core_initcall(init_jiffies_clocksource);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index eb12509e00bd..cb25649c6f50 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -32,7 +32,7 @@ static u64 tick_length, tick_length_base;
 /* TIME_ERROR prevents overwriting the CMOS clock */
 static int time_state = TIME_OK;        /* clock synchronization status */
 int time_status = STA_UNSYNC;           /* clock status bits            */
-static long time_offset;                /* time adjustment (ns)         */
+static s64 time_offset;         /* time adjustment (ns)         */
 static long time_constant = 2;          /* pll time constant            */
 long time_maxerror = NTP_PHASE_LIMIT;   /* maximum error (us)           */
 long time_esterror = NTP_PHASE_LIMIT;   /* estimated error (us)         */
@@ -196,7 +196,7 @@ void __attribute__ ((weak)) notify_arch_cmos_timer(void)
  */
 int do_adjtimex(struct timex *txc)
 {
-        long ltemp, mtemp, save_adjust;
+        long mtemp, save_adjust, rem;
         s64 freq_adj, temp64;
         int result;
 
@@ -277,14 +277,14 @@ int do_adjtimex(struct timex *txc)
                     time_adjust = txc->offset;
                 }
                 else if (time_status & STA_PLL) {
-                    ltemp = txc->offset * NSEC_PER_USEC;
+                    time_offset = txc->offset * NSEC_PER_USEC;
 
                     /*
                      * Scale the phase adjustment and
                      * clamp to the operating range.
                      */
-                    time_offset = min(ltemp, MAXPHASE * NSEC_PER_USEC);
-                    time_offset = max(time_offset, -MAXPHASE * NSEC_PER_USEC);
+                    time_offset = min(time_offset, (s64)MAXPHASE * NSEC_PER_USEC);
+                    time_offset = max(time_offset, (s64)-MAXPHASE * NSEC_PER_USEC);
 
                     /*
                      * Select whether the frequency is to be controlled
@@ -297,11 +297,11 @@ int do_adjtimex(struct timex *txc)
                     mtemp = xtime.tv_sec - time_reftime;
                     time_reftime = xtime.tv_sec;
 
-                    freq_adj = (s64)time_offset * mtemp;
+                    freq_adj = time_offset * mtemp;
                     freq_adj = shift_right(freq_adj, time_constant * 2 +
                                            (SHIFT_PLL + 2) * 2 - SHIFT_NSEC);
                     if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
-                        temp64 = (s64)time_offset << (SHIFT_NSEC - SHIFT_FLL);
+                        temp64 = time_offset << (SHIFT_NSEC - SHIFT_FLL);
                         if (time_offset < 0) {
                             temp64 = -temp64;
                             do_div(temp64, mtemp);
@@ -314,8 +314,10 @@ int do_adjtimex(struct timex *txc)
                     freq_adj += time_freq;
                     freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC);
                     time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC);
-                    time_offset = (time_offset / NTP_INTERVAL_FREQ)
-                                        << SHIFT_UPDATE;
+                    time_offset = div_long_long_rem_signed(time_offset,
+                                                           NTP_INTERVAL_FREQ,
+                                                           &rem);
+                    time_offset <<= SHIFT_UPDATE;
                 } /* STA_PLL */
             } /* txc->modes & ADJ_OFFSET */
             if (txc->modes & ADJ_TICK)
@@ -328,12 +330,12 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
                 result = TIME_ERROR;
 
         if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
-            txc->offset    = save_adjust;
+                txc->offset = save_adjust;
         else
-            txc->offset    = shift_right(time_offset, SHIFT_UPDATE)
-                                * NTP_INTERVAL_FREQ / 1000;
-        txc->freq          = (time_freq / NSEC_PER_USEC)
-                                << (SHIFT_USEC - SHIFT_NSEC);
+                txc->offset = ((long)shift_right(time_offset, SHIFT_UPDATE)) *
+                                NTP_INTERVAL_FREQ / 1000;
+        txc->freq          = (time_freq / NSEC_PER_USEC) <<
+                                (SHIFT_USEC - SHIFT_NSEC);
         txc->maxerror      = time_maxerror;
         txc->esterror      = time_esterror;
         txc->status        = time_status;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 12b3efeb9f6f..eadfce2fff74 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -284,6 +284,49 @@ void tick_shutdown_broadcast(unsigned int *cpup)
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+void tick_suspend_broadcast(void)
+{
+        struct clock_event_device *bc;
+        unsigned long flags;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        bc = tick_broadcast_device.evtdev;
+        if (bc && tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
+
+int tick_resume_broadcast(void)
+{
+        struct clock_event_device *bc;
+        unsigned long flags;
+        int broadcast = 0;
+
+        spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+        bc = tick_broadcast_device.evtdev;
+
+        if (bc) {
+                switch (tick_broadcast_device.mode) {
+                case TICKDEV_MODE_PERIODIC:
+                        if(!cpus_empty(tick_broadcast_mask))
+                                tick_broadcast_start_periodic(bc);
+                        broadcast = cpu_isset(smp_processor_id(),
+                                              tick_broadcast_mask);
+                        break;
+                case TICKDEV_MODE_ONESHOT:
+                        broadcast = tick_resume_broadcast_oneshot(bc);
+                        break;
+                }
+        }
+        spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+
+        return broadcast;
+}
+
+
 #ifdef CONFIG_TICK_ONESHOT
 
 static cpumask_t tick_broadcast_oneshot_mask;
@@ -311,6 +354,16 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
         }
 }
 
+int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
+{
+        clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+        if(!cpus_empty(tick_broadcast_oneshot_mask))
+                tick_broadcast_set_event(ktime_get(), 1);
+
+        return cpu_isset(smp_processor_id(), tick_broadcast_oneshot_mask);
+}
+
 /*
  * Reprogram the broadcast device:
  *
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 4500e347f1bb..bfda3f7f0716 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -77,6 +77,7 @@ static void tick_periodic(int cpu)
 void tick_handle_periodic(struct clock_event_device *dev)
 {
         int cpu = smp_processor_id();
+        ktime_t next;
 
         tick_periodic(cpu);
 
@@ -86,12 +87,12 @@ void tick_handle_periodic(struct clock_event_device *dev)
          * Setup the next period for devices, which do not have
          * periodic mode:
          */
+        next = ktime_add(dev->next_event, tick_period);
         for (;;) {
-                ktime_t next = ktime_add(dev->next_event, tick_period);
-
                 if (!clockevents_program_event(dev, next, ktime_get()))
                         return;
                 tick_periodic(cpu);
+                next = ktime_add(next, tick_period);
         }
 }
 
@@ -297,6 +298,29 @@ static void tick_shutdown(unsigned int *cpup)
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
+static void tick_suspend(void)
+{
+        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        unsigned long flags;
+
+        spin_lock_irqsave(&tick_device_lock, flags);
+        clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+        spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
+static void tick_resume(void)
+{
+        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        unsigned long flags;
+
+        spin_lock_irqsave(&tick_device_lock, flags);
+        if (td->mode == TICKDEV_MODE_PERIODIC)
+                tick_setup_periodic(td->evtdev, 0);
+        else
+                tick_resume_oneshot();
+        spin_unlock_irqrestore(&tick_device_lock, flags);
+}
+
 /*
  * Notification about clock event devices
  */
@@ -324,6 +348,16 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
                 tick_shutdown(dev);
                 break;
 
+        case CLOCK_EVT_NOTIFY_SUSPEND:
+                tick_suspend();
+                tick_suspend_broadcast();
+                break;
+
+        case CLOCK_EVT_NOTIFY_RESUME:
+                if (!tick_resume_broadcast())
+                        tick_resume();
+                break;
+
         default:
                 break;
         }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 54861a0f29ff..c9d203bde518 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -19,12 +19,13 @@ extern void tick_setup_oneshot(struct clock_event_device *newdev,
 extern int tick_program_event(ktime_t expires, int force);
 extern void tick_oneshot_notify(void);
 extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
-
+extern void tick_resume_oneshot(void);
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 extern void tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
+extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -43,6 +44,10 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 {
         BUG();
 }
+static inline void tick_resume_oneshot(void)
+{
+        BUG();
+}
 static inline int tick_program_event(ktime_t expires, int force)
 {
         return 0;
@@ -54,6 +59,10 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 }
 static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
+{
+        return 0;
+}
 #endif /* !TICK_ONESHOT */
 
 /*
@@ -67,6 +76,8 @@ extern int tick_check_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
 extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
 extern void tick_shutdown_broadcast(unsigned int *cpup);
+extern void tick_suspend_broadcast(void);
+extern int tick_resume_broadcast(void);
 
 extern void
 tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
@@ -90,6 +101,8 @@ static inline int tick_device_uses_broadcast(struct clock_event_device *dev,
 static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
 static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
 static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
+static inline void tick_suspend_broadcast(void) { }
+static inline int tick_resume_broadcast(void) { return 0; }
 
 /*
  * Set the periodic handler in non broadcast mode
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 2e8b7ff863cc..f6997ab0c3c9 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -41,6 +41,18 @@ int tick_program_event(ktime_t expires, int force)
 }
 
 /**
+ * tick_resume_onshot - resume oneshot mode
+ */
+void tick_resume_oneshot(void)
+{
+        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct clock_event_device *dev = td->evtdev;
+
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+        tick_program_event(ktime_get(), 1);
+}
+
+/**
  * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
  */
 void tick_setup_oneshot(struct clock_event_device *newdev,
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 95e41f7f850b..51556b95f60f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -21,6 +21,8 @@
 #include <linux/sched.h>
 #include <linux/tick.h>
 
+#include <asm/irq_regs.h>
+
 #include "tick-internal.h"
 
 /*
@@ -165,7 +167,9 @@ void tick_nohz_stop_sched_tick(void)
                 goto end;
 
         cpu = smp_processor_id();
-        BUG_ON(local_softirq_pending());
+        if (unlikely(local_softirq_pending()))
+                printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+                       local_softirq_pending());
 
         now = ktime_get();
         /*
@@ -191,19 +195,19 @@ void tick_nohz_stop_sched_tick(void)
         next_jiffies = get_next_timer_interrupt(last_jiffies);
         delta_jiffies = next_jiffies - last_jiffies;
 
+        if (rcu_needs_cpu(cpu))
+                delta_jiffies = 1;
         /*
          * Do not stop the tick, if we are only one off
          * or if the cpu is required for rcu
          */
-        if (!ts->tick_stopped && (delta_jiffies == 1 || rcu_needs_cpu(cpu)))
+        if (!ts->tick_stopped && delta_jiffies == 1)
                 goto out;
 
         /* Schedule the tick, if we are at least one jiffie off */
         if ((long)delta_jiffies >= 1) {
 
-                if (rcu_needs_cpu(cpu))
-                        delta_jiffies = 1;
-                else
+                if (delta_jiffies > 1)
                         cpu_set(cpu, nohz_cpu_mask);
                 /*
                  * nohz_stop_sched_tick can be called several times before
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index f82c635c3d5c..59df5e8555a8 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -194,9 +194,9 @@ print_tickdevice(struct seq_file *m, struct tick_device *td)
                 return;
         }
         SEQ_printf(m, "%s\n", dev->name);
-        SEQ_printf(m, " max_delta_ns:   %ld\n", dev->max_delta_ns);
-        SEQ_printf(m, " min_delta_ns:   %ld\n", dev->min_delta_ns);
-        SEQ_printf(m, " mult:           %ld\n", dev->mult);
+        SEQ_printf(m, " max_delta_ns:   %lu\n", dev->max_delta_ns);
+        SEQ_printf(m, " min_delta_ns:   %lu\n", dev->min_delta_ns);
+        SEQ_printf(m, " mult:           %lu\n", dev->mult);
         SEQ_printf(m, " shift:          %d\n", dev->shift);
         SEQ_printf(m, " mode:           %d\n", dev->mode);
         SEQ_printf(m, " next_event:     %Ld nsecs\n",