timers: Add accounting of non deferrable timers

The code in get_next_timer_interrupt() is suboptimal as it has to run
through the cascade to find the next expiring timer. On a completely
idle core we should only do that when there is an active timer
enqueued and base->next_timer does not give us a fast answer.

Add accounting of the active timers to the now consolidated
attach/detach code. I deliberately avoided sanity checks because the
code is fully symetric and any fiddling with timers w/o using the API
functions will lead to cute explosions anyway. ulong is big enough
even on 32bit and if we really run into the situation to have more
than 1<<32 timers enqueued there, then we are definitely not in a
state to go idle and run through that code.

This allows us to fix another shortcoming of get_next_timer_interrupt().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20120525214819.236377028@linutronix.de

diff --git a/kernel/timer.c b/kernel/timer.c
index 7207690b53530907b66bd4bc1e217c4bed187229..7fada698bd1a54d015ae7a14fc4badb54cf7d624 100644 (file)
--- a/kernel/timer.c
+++ b/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;
@@ -377,11 +378,13 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
        __internal_add_timer(base, timer);
        /*
-        * Update base->next_timer if this is the earliest one.
+        * Update base->active_timers and base->next_timer
         */
-       if (time_before(timer->expires, base->next_timer) &&
-           !tbase_get_deferrable(timer->base))
-               base->next_timer = timer->expires;
+       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
@@ -678,6 +681,14 @@ static inline void detach_timer(struct timer_list *timer, bool clear_pending)
        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)
 {
@@ -685,9 +696,11 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
                return 0;
 
        detach_timer(timer, clear_pending);
-       if (timer->expires == base->next_timer &&
-           !tbase_get_deferrable(timer->base))
-               base->next_timer = base->timer_jiffies;
+       if (!tbase_get_deferrable(timer->base)) {
+               timer->base->active_timers--;
+               if (timer->expires == base->next_timer)
+                       base->next_timer = base->timer_jiffies;
+       }
        return 1;
 }
 
@@ -1175,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base)
                        timer_stats_account_timer(timer);
 
                        base->running_timer = timer;
-                       detach_timer(timer, true);
+                       detach_expired_timer(timer, base);
 
                        spin_unlock_irq(&base->lock);
                        call_timer_fn(timer, fn, data);
@@ -1701,6 +1714,7 @@ static int __cpuinit init_timers_cpu(int cpu)
 
        base->timer_jiffies = jiffies;
        base->next_timer = base->timer_jiffies;
+       base->active_timers = 0;
        return 0;
 }
 
@@ -1711,6 +1725,7 @@ 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);
+               /* We ignore the accounting on the dying cpu */
                detach_timer(timer, false);
                timer_set_base(timer, new_base);
                internal_add_timer(new_base, timer);