timers: add mod_timer_pending()

Impact: new timer API

Based on an idea from Martin Josefsson with the help of
Patrick McHardy and Stephen Hemminger:

introduce the mod_timer_pending() API which is a mod_timer()
offspring that is an invariant on already removed timers.

(regular mod_timer() re-activates non-pending timers.)

This is useful for the networking code in that it can
allow unserialized mod_timer_pending() timer-forwarding
calls, but a single del_timer*() will stop the timer
from being reactivated again.

Also while at it:

- optimize the regular mod_timer() path some more, the
  timer-stat and a debug check was needlessly duplicated
  in __mod_timer().

- make the exports come straight after the function, as
  most other exports in timer.c already did.

- eliminate __mod_timer() as an external API, change the
  users to mod_timer().

The regular mod_timer() code path is not impacted
significantly, due to inlining optimizations and due to
the simplifications.

Based-on-patch-from: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Patrick McHardy <kaber@trash.net>
Cc: netdev@vger.kernel.org
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 73 insertions, 37 deletions

diff --git a/kernel/timer.c b/kernel/timer.c
index 13dd64fe143d..9b77fc9a9ac8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -589,11 +589,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
         }
 }
 
-int __mod_timer(struct timer_list *timer, unsigned long expires)
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 {
         struct tvec_base *base, *new_base;
         unsigned long flags;
-        int ret = 0;
+        int ret;
+
+        ret = 0;
 
         timer_stats_timer_set_start_info(timer);
         BUG_ON(!timer->function);
@@ -603,6 +606,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer_pending(timer)) {
                 detach_timer(timer, 0);
                 ret = 1;
+        } else {
+                if (pending_only)
+                        goto out_unlock;
         }
 
         debug_timer_activate(timer);
@@ -629,42 +635,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
         timer->expires = expires;
         internal_add_timer(base, timer);
+
+out_unlock:
         spin_unlock_irqrestore(&base->lock, flags);
 
         return ret;
 }
 
-EXPORT_SYMBOL(__mod_timer);
-
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
  */
-void add_timer_on(struct timer_list *timer, int cpu)
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-        struct tvec_base *base = per_cpu(tvec_bases, cpu);
-        unsigned long flags;
-
-        timer_stats_timer_set_start_info(timer);
-        BUG_ON(timer_pending(timer) || !timer->function);
-        spin_lock_irqsave(&base->lock, flags);
-        timer_set_base(timer, base);
-        debug_timer_activate(timer);
-        internal_add_timer(base, timer);
-        /*
-         * Check whether the other CPU is idle and needs to be
-         * triggered to reevaluate the timer wheel when nohz is
-         * active. We are protected against the other CPU fiddling
-         * with the timer by holding the timer base lock. This also
-         * makes sure that a CPU on the way to idle can not evaluate
-         * the timer wheel.
-         */
-        wake_up_idle_cpu(cpu);
-        spin_unlock_irqrestore(&base->lock, flags);
+        return __mod_timer(timer, expires, true);
 }
+EXPORT_SYMBOL(mod_timer_pending);
 
 /**
  * mod_timer - modify a timer's timeout
@@ -688,9 +680,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-        BUG_ON(!timer->function);
-
-        timer_stats_timer_set_start_info(timer);
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -699,12 +688,62 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer->expires == expires && timer_pending(timer))
                 return 1;
 
-        return __mod_timer(timer, expires);
+        return __mod_timer(timer, expires, false);
 }
-
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+        BUG_ON(timer_pending(timer));
+        mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+        struct tvec_base *base = per_cpu(tvec_bases, cpu);
+        unsigned long flags;
+
+        timer_stats_timer_set_start_info(timer);
+        BUG_ON(timer_pending(timer) || !timer->function);
+        spin_lock_irqsave(&base->lock, flags);
+        timer_set_base(timer, base);
+        debug_timer_activate(timer);
+        internal_add_timer(base, timer);
+        /*
+         * Check whether the other CPU is idle and needs to be
+         * triggered to reevaluate the timer wheel when nohz is
+         * active. We are protected against the other CPU fiddling
+         * with the timer by holding the timer base lock. This also
+         * makes sure that a CPU on the way to idle can not evaluate
+         * the timer wheel.
+         */
+        wake_up_idle_cpu(cpu);
+        spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
  *
@@ -733,7 +772,6 @@ int del_timer(struct timer_list *timer)
 
         return ret;
 }
-
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
@@ -767,7 +805,6 @@ out:
 
         return ret;
 }
-
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 /**
@@ -796,7 +833,6 @@ int del_timer_sync(struct timer_list *timer)
                 cpu_relax();
         }
 }
-
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
@@ -1268,7 +1304,7 @@ signed long __sched schedule_timeout(signed long timeout)
         expire = timeout + jiffies;
 
         setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-        __mod_timer(&timer, expire);
+        __mod_timer(&timer, expire, false);
         schedule();
         del_singleshot_timer_sync(&timer);