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

* 'timers-for-linus-migration' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  timers: Logic to move non pinned timers
  timers: /proc/sys sysctl hook to enable timer migration
  timers: Identifying the existing pinned timers
  timers: Framework for identifying pinned timers
  timers: allow deferrable timers for intervals tv2-tv5 to be deferred

Fix up conflicts in kernel/sched.c and kernel/timer.c manually

1 files changed, 44 insertions, 7 deletions

diff --git a/kernel/timer.c b/kernel/timer.c
index faf2db897de..54d3912f8ca 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -38,6 +38,7 @@
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
 #include <linux/perf_counter.h>
+#include <linux/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -605,13 +606,12 @@ 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;
-	int ret;
-
-	ret = 0;
+	int ret = 0 , cpu;
 
 	timer_stats_timer_set_start_info(timer);
 	BUG_ON(!timer->function);
@@ -630,6 +630,18 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 
 	new_base = __get_cpu_var(tvec_bases);
 
+	cpu = smp_processor_id();
+
+#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
+		int preferred_cpu = get_nohz_load_balancer();
+
+		if (preferred_cpu >= 0)
+			cpu = preferred_cpu;
+	}
+#endif
+	new_base = per_cpu(tvec_bases, cpu);
+
 	if (base != new_base) {
 		/*
 		 * We are trying to schedule the timer on the local CPU.
@@ -669,7 +681,7 @@ 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);
 
@@ -703,11 +715,33 @@ 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
  *
@@ -1017,6 +1051,9 @@ cascade:
 		index = slot = timer_jiffies & TVN_MASK;
 		do {
 			list_for_each_entry(nte, varp->vec + slot, entry) {
+				if (tbase_get_deferrable(nte->base))
+					continue;
+
 				found = 1;
 				if (time_before(nte->expires, expires))
 					expires = nte->expires;
@@ -1307,7 +1344,7 @@ 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);