Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  MAINTAINERS: Update timer related entries
  timers: Use this_cpu_read
  timerqueue: Make timerqueue_getnext() static inline
  hrtimer: fix timerqueue conversion flub
  hrtimers: Convert hrtimers to use timerlist infrastructure
  timers: Fixup allmodconfig build issue
  timers: Rename timerlist infrastructure to timerqueue
  timers: Introduce timerlist infrastructure.
  hrtimer: Remove stale comment on curr_timer
  timer: Warn when del_timer_sync() is called in hardirq context
  timer: Del_timer_sync() can be used in softirq context
  timer: Make try_to_del_timer_sync() the same on SMP and UP
  posix-timers: Annotate lock_timer()
  timer: Permit statically-declared work with deferrable timers
  time: Use ARRAY_SIZE macro in timecompare.c
  timer: Initialize the field slack of timer_list
  timer_list: Remove alignment padding on 64 bit when CONFIG_TIMER_STATS
  time: Compensate for rounding on odd-frequency clocksources

Fix up trivial conflict in MAINTAINERS

6 files changed, 63 insertions, 102 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 72206cf5c6cf..f2429fc3438c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -516,10 +516,13 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
                 struct hrtimer *timer;
+                struct timerqueue_node *next;
 
-                if (!base->first)
+                next = timerqueue_getnext(&base->active);
+                if (!next)
                         continue;
-                timer = rb_entry(base->first, struct hrtimer, node);
+                timer = container_of(next, struct hrtimer, node);
+
                 expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                 /*
                  * clock_was_set() has changed base->offset so the
@@ -840,48 +843,17 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
 static int enqueue_hrtimer(struct hrtimer *timer,
                            struct hrtimer_clock_base *base)
 {
-        struct rb_node **link = &base->active.rb_node;
-        struct rb_node *parent = NULL;
-        struct hrtimer *entry;
-        int leftmost = 1;
-
         debug_activate(timer);
 
-        /*
-         * Find the right place in the rbtree:
-         */
-        while (*link) {
-                parent = *link;
-                entry = rb_entry(parent, struct hrtimer, node);
-                /*
-                 * We dont care about collisions. Nodes with
-                 * the same expiry time stay together.
-                 */
-                if (hrtimer_get_expires_tv64(timer) <
-                                hrtimer_get_expires_tv64(entry)) {
-                        link = &(*link)->rb_left;
-                } else {
-                        link = &(*link)->rb_right;
-                        leftmost = 0;
-                }
-        }
-
-        /*
-         * Insert the timer to the rbtree and check whether it
-         * replaces the first pending timer
-         */
-        if (leftmost)
-                base->first = &timer->node;
+        timerqueue_add(&base->active, &timer->node);
 
-        rb_link_node(&timer->node, parent, link);
-        rb_insert_color(&timer->node, &base->active);
         /*
          * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
          * state of a possibly running callback.
          */
         timer->state |= HRTIMER_STATE_ENQUEUED;
 
-        return leftmost;
+        return (&timer->node == base->active.next);
 }
 
 /*
@@ -901,12 +873,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
         if (!(timer->state & HRTIMER_STATE_ENQUEUED))
                 goto out;
 
-        /*
-         * Remove the timer from the rbtree and replace the first
-         * entry pointer if necessary.
-         */
-        if (base->first == &timer->node) {
-                base->first = rb_next(&timer->node);
+        if (&timer->node == timerqueue_getnext(&base->active)) {
 #ifdef CONFIG_HIGH_RES_TIMERS
                 /* Reprogram the clock event device. if enabled */
                 if (reprogram && hrtimer_hres_active()) {
@@ -919,7 +886,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
                 }
 #endif
         }
-        rb_erase(&timer->node, &base->active);
+        timerqueue_del(&base->active, &timer->node);
 out:
         timer->state = newstate;
 }
@@ -1128,11 +1095,13 @@ ktime_t hrtimer_get_next_event(void)
         if (!hrtimer_hres_active()) {
                 for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
                         struct hrtimer *timer;
+                        struct timerqueue_node *next;
 
-                        if (!base->first)
+                        next = timerqueue_getnext(&base->active);
+                        if (!next)
                                 continue;
 
-                        timer = rb_entry(base->first, struct hrtimer, node);
+                        timer = container_of(next, struct hrtimer, node);
                         delta.tv64 = hrtimer_get_expires_tv64(timer);
                         delta = ktime_sub(delta, base->get_time());
                         if (delta.tv64 < mindelta.tv64)
@@ -1162,6 +1131,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 
         timer->base = &cpu_base->clock_base[clock_id];
         hrtimer_init_timer_hres(timer);
+        timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
         timer->start_site = NULL;
@@ -1278,14 +1248,14 @@ retry:
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 ktime_t basenow;
-                struct rb_node *node;
+                struct timerqueue_node *node;
 
                 basenow = ktime_add(now, base->offset);
 
-                while ((node = base->first)) {
+                while ((node = timerqueue_getnext(&base->active))) {
                         struct hrtimer *timer;
 
-                        timer = rb_entry(node, struct hrtimer, node);
+                        timer = container_of(node, struct hrtimer, node);
 
                         /*
                          * The immediate goal for using the softexpires is
@@ -1441,7 +1411,7 @@ void hrtimer_run_pending(void)
  */
 void hrtimer_run_queues(void)
 {
-        struct rb_node *node;
+        struct timerqueue_node *node;
         struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
         struct hrtimer_clock_base *base;
         int index, gettime = 1;
@@ -1451,8 +1421,7 @@ void hrtimer_run_queues(void)
 
         for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
                 base = &cpu_base->clock_base[index];
-
-                if (!base->first)
+                if (!timerqueue_getnext(&base->active))
                         continue;
 
                 if (gettime) {
@@ -1462,10 +1431,10 @@ void hrtimer_run_queues(void)
 
                 raw_spin_lock(&cpu_base->lock);
 
-                while ((node = base->first)) {
+                while ((node = timerqueue_getnext(&base->active))) {
                         struct hrtimer *timer;
 
-                        timer = rb_entry(node, struct hrtimer, node);
+                        timer = container_of(node, struct hrtimer, node);
                         if (base->softirq_time.tv64 <=
                                         hrtimer_get_expires_tv64(timer))
                                 break;
@@ -1630,8 +1599,10 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 
         raw_spin_lock_init(&cpu_base->lock);
 
-        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+        for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 cpu_base->clock_base[i].cpu_base = cpu_base;
+                timerqueue_init_head(&cpu_base->clock_base[i].active);
+        }
 
         hrtimer_init_hres(cpu_base);
 }
@@ -1642,10 +1613,10 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                                 struct hrtimer_clock_base *new_base)
 {
         struct hrtimer *timer;
-        struct rb_node *node;
+        struct timerqueue_node *node;
 
-        while ((node = rb_first(&old_base->active))) {
-                timer = rb_entry(node, struct hrtimer, node);
+        while ((node = timerqueue_getnext(&old_base->active))) {
+                timer = container_of(node, struct hrtimer, node);
                 BUG_ON(hrtimer_callback_running(timer));
                 debug_deactivate(timer);
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 9ca4973f736d..93bd2eb2bc53 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -145,7 +145,13 @@ static int common_timer_del(struct k_itimer *timer);
 
 static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
 
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);
+
+#define lock_timer(tid, flags)                                             \
+({      struct k_itimer *__timr;                                           \
+        __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags));  \
+        __timr;                                                            \
+})
 
 static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 {
@@ -619,7 +625,7 @@ out:
  * the find to the timer lock.  To avoid a dead lock, the timer id MUST
  * be release with out holding the timer lock.
  */
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
 {
         struct k_itimer *timr;
         /*
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index ac38fbb176cc..a9ae369925ce 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/math64.h>
+#include <linux/kernel.h>
 
 /*
  * fixed point arithmetic scale factor for skew
@@ -57,11 +58,11 @@ int timecompare_offset(struct timecompare *sync,
         int index;
         int num_samples = sync->num_samples;
 
-        if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
+        if (num_samples > ARRAY_SIZE(buffer)) {
                 samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
                 if (!samples) {
                         samples = buffer;
-                        num_samples = sizeof(buffer)/sizeof(buffer[0]);
+                        num_samples = ARRAY_SIZE(buffer);
                 }
         } else {
                 samples = buffer;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 49010d822f72..5bb86da82003 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -32,6 +32,8 @@ struct timekeeper {
         cycle_t cycle_interval;
         /* Number of clock shifted nano seconds in one NTP interval. */
         u64     xtime_interval;
+        /* shifted nano seconds left over when rounding cycle_interval */
+        s64     xtime_remainder;
         /* Raw nano seconds accumulated per NTP interval. */
         u32     raw_interval;
 
@@ -62,7 +64,7 @@ struct timekeeper timekeeper;
 static void timekeeper_setup_internals(struct clocksource *clock)
 {
         cycle_t interval;
-        u64 tmp;
+        u64 tmp, ntpinterval;
 
         timekeeper.clock = clock;
         clock->cycle_last = clock->read(clock);
@@ -70,6 +72,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
         /* Do the ns -> cycle conversion first, using original mult */
         tmp = NTP_INTERVAL_LENGTH;
         tmp <<= clock->shift;
+        ntpinterval = tmp;
         tmp += clock->mult/2;
         do_div(tmp, clock->mult);
         if (tmp == 0)
@@ -80,6 +83,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
 
         /* Go back from cycles -> shifted ns */
         timekeeper.xtime_interval = (u64) interval * clock->mult;
+        timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval;
         timekeeper.raw_interval =
                 ((u64) interval * clock->mult) >> clock->shift;
 
@@ -719,7 +723,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
         /* Accumulate error between NTP and clock interval */
         timekeeper.ntp_error += tick_length << shift;
-        timekeeper.ntp_error -= timekeeper.xtime_interval <<
+        timekeeper.ntp_error -=
+            (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
                                 (timekeeper.ntp_error_shift + shift);
 
         return offset;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ab8f5e33fa92..32a19f9397fc 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -79,26 +79,26 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 {
         struct hrtimer *timer, tmp;
         unsigned long next = 0, i;
-        struct rb_node *curr;
+        struct timerqueue_node *curr;
         unsigned long flags;
 
 next_one:
         i = 0;
         raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
 
-        curr = base->first;
+        curr = timerqueue_getnext(&base->active);
         /*
          * Crude but we have to do this O(N*N) thing, because
          * we have to unlock the base when printing:
          */
         while (curr && i < next) {
-                curr = rb_next(curr);
+                curr = timerqueue_iterate_next(curr);
                 i++;
         }
 
         if (curr) {
 
-                timer = rb_entry(curr, struct hrtimer, node);
+                timer = container_of(curr, struct hrtimer, node);
                 tmp = *timer;
                 raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 353b9227c2ec..43ca9936f2d0 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -88,18 +88,6 @@ struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
 static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
-/*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
- *
- * A deferrable timer will work normally when the system is busy, but
- * will not cause a CPU to come out of idle just to service it; instead,
- * the timer will be serviced when the CPU eventually wakes up with a
- * subsequent non-deferrable timer.
- */
-#define TBASE_DEFERRABLE_FLAG           (0x1)
-
 /* Functions below help us manage 'deferrable' flag */
 static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
 {
@@ -113,8 +101,7 @@ static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
 
 static inline void timer_set_deferrable(struct timer_list *timer)
 {
-        timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
-                                       TBASE_DEFERRABLE_FLAG));
+        timer->base = TBASE_MAKE_DEFERRED(timer->base);
 }
 
 static inline void
@@ -343,15 +330,6 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-
-static inline void set_running_timer(struct tvec_base *base,
-                                        struct timer_list *timer)
-{
-#ifdef CONFIG_SMP
-        base->running_timer = timer;
-#endif
-}
-
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
         unsigned long expires = timer->expires;
@@ -936,15 +914,12 @@ int del_timer(struct timer_list *timer)
 }
 EXPORT_SYMBOL(del_timer);
 
-#ifdef CONFIG_SMP
 /**
  * try_to_del_timer_sync - Try to deactivate a timer
  * @timer: timer do del
  *
  * This function tries to deactivate a timer. Upon successful (ret >= 0)
  * exit the timer is not queued and the handler is not running on any CPU.
- *
- * It must not be called from interrupt contexts.
  */
 int try_to_del_timer_sync(struct timer_list *timer)
 {
@@ -973,6 +948,7 @@ out:
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
+#ifdef CONFIG_SMP
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -983,7 +959,7 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
+ * hardirq contexts. The caller must not hold locks which would prevent
  * completion of the timer's handler. The timer's handler must not call
  * add_timer_on(). Upon exit the timer is not queued and the handler is
  * not running on any CPU.
@@ -993,14 +969,16 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
 int del_timer_sync(struct timer_list *timer)
 {
 #ifdef CONFIG_LOCKDEP
-        unsigned long flags;
-
-        local_irq_save(flags);
+        local_bh_disable();
         lock_map_acquire(&timer->lockdep_map);
         lock_map_release(&timer->lockdep_map);
-        local_irq_restore(flags);
+        local_bh_enable();
 #endif
-
+        /*
+         * don't use it in hardirq context, because it
+         * could lead to deadlock.
+         */
+        WARN_ON(in_irq());
         for (;;) {
                 int ret = try_to_del_timer_sync(timer);
                 if (ret >= 0)
@@ -1111,7 +1089,7 @@ static inline void __run_timers(struct tvec_base *base)
 
                         timer_stats_account_timer(timer);
 
-                        set_running_timer(base, timer);
+                        base->running_timer = timer;
                         detach_timer(timer, 1);
 
                         spin_unlock_irq(&base->lock);
@@ -1119,7 +1097,7 @@ static inline void __run_timers(struct tvec_base *base)
                         spin_lock_irq(&base->lock);
                 }
         }
-        set_running_timer(base, NULL);
+        base->running_timer = NULL;
         spin_unlock_irq(&base->lock);
 }
 
@@ -1249,7 +1227,7 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
  */
 unsigned long get_next_timer_interrupt(unsigned long now)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
         unsigned long expires;
 
         /*
@@ -1298,7 +1276,7 @@ void update_process_times(int user_tick)
  */
 static void run_timer_softirq(struct softirq_action *h)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
 
         hrtimer_run_pending();