timers: Framework for identifying pinned timers

* Arun R Bharadwaj <arun@linux.vnet.ibm.com> [2009-04-16 12:11:36]:

This patch creates a new framework for identifying cpu-pinned timers
and hrtimers.

This framework is needed because pinned timers are expected to fire on
the same CPU on which they are queued. So it is essential to identify
these and not migrate them, in case there are any.

For regular timers, the currently existing add_timer_on() can be used
queue pinned timers and subsequently mod_timer_pinned() can be used
to modify the 'expires' field.

For hrtimers, new modes HRTIMER_ABS_PINNED and HRTIMER_REL_PINNED are
added to queue cpu-pinned hrtimer.

[ tglx: use .._PINNED mode argument instead of creating tons of new
functions ]

Signed-off-by: Arun R Bharadwaj <arun@linux.vnet.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 31 insertions, 7 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cb8a15c..c71bcd5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -193,7 +193,8 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
  * Switch the timer base to the current CPU when possible.
  */
 static inline struct hrtimer_clock_base *
-switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base)
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
+		    int pinned)
 {
 	struct hrtimer_clock_base *new_base;
 	struct hrtimer_cpu_base *new_cpu_base;
@@ -907,9 +908,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	ret = remove_hrtimer(timer, base);
 
 	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base);
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
-	if (mode == HRTIMER_MODE_REL) {
+	if (mode & HRTIMER_MODE_REL) {
 		tim = ktime_add_safe(tim, new_base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
diff --git a/kernel/timer.c b/kernel/timer.c
index 5c1e84b..3424dfd 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -604,7 +604,8 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
 }
 
 static inline int
-__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
+__mod_timer(struct timer_list *timer, unsigned long expires,
+						bool pending_only, int pinned)
 {
 	struct tvec_base *base, *new_base;
 	unsigned long flags;
@@ -668,7 +669,7 @@ out_unlock:
  */
 int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-	return __mod_timer(timer, expires, true);
+	return __mod_timer(timer, expires, true, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer_pending);
 
@@ -702,11 +703,33 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer->expires == expires && timer_pending(timer))
 		return 1;
 
-	return __mod_timer(timer, expires, false);
+	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * mod_timer_pinned - modify a timer's timeout
+ * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer_pinned() is a way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ * and not allow the timer to be migrated to a different CPU.
+ *
+ * mod_timer_pinned(timer, expires) is equivalent to:
+ *
+ *     del_timer(timer); timer->expires = expires; add_timer(timer);
+ */
+int mod_timer_pinned(struct timer_list *timer, unsigned long expires)
+{
+	if (timer->expires == expires && timer_pending(timer))
+		return 1;
+
+	return __mod_timer(timer, expires, false, TIMER_PINNED);
+}
+EXPORT_SYMBOL(mod_timer_pinned);
+
+/**
  * add_timer - start a timer
  * @timer: the timer to be added
  *
@@ -1356,7 +1379,7 @@ 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, false);
+	__mod_timer(&timer, expire, false, TIMER_NOT_PINNED);
 	schedule();
 	del_singleshot_timer_sync(&timer);