patches/timers-prepare-for-full-preemption.patch

From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:34 -0500
Subject: timers: Prepare for full preemption

When softirqs can be preempted we need to make sure that cancelling
the timer from the active thread can not deadlock vs. a running timer
callback. Add a waitqueue to resolve that.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/timer.h |    2 +-
 kernel/sched/core.c   |    8 ++++++--
 kernel/time/timer.c   |   37 ++++++++++++++++++++++++++++++++++---
 3 files changed, 41 insertions(+), 6 deletions(-)

--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -241,7 +241,7 @@ extern void add_timer(struct timer_list
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
   extern int del_timer_sync(struct timer_list *timer);
 #else
 # define del_timer_sync(t)		del_timer(t)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -641,12 +641,14 @@ void resched_cpu(int cpu)
  */
 int get_nohz_timer_target(int pinned)
 {
-	int cpu = smp_processor_id();
+	int cpu;
 	int i;
 	struct sched_domain *sd;
 
+	preempt_disable_rt();
+	cpu = smp_processor_id();
 	if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
-		return cpu;
+		goto preempt_en_rt;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
@@ -659,6 +661,8 @@ int get_nohz_timer_target(int pinned)
 	}
 unlock:
 	rcu_read_unlock();
+preempt_en_rt:
+	preempt_enable_rt();
 	return cpu;
 }
 /*
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -78,6 +78,9 @@ struct tvec_root {
 struct tvec_base {
 	spinlock_t lock;
 	struct timer_list *running_timer;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	wait_queue_head_t wait_for_running_timer;
+#endif
 	unsigned long timer_jiffies;
 	unsigned long next_timer;
 	unsigned long active_timers;
@@ -979,6 +982,29 @@ void add_timer_on(struct timer_list *tim
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Wait for a running timer
+ */
+static void wait_for_running_timer(struct timer_list *timer)
+{
+	struct tvec_base *base = timer->base;
+
+	if (base->running_timer == timer)
+		wait_event(base->wait_for_running_timer,
+			   base->running_timer != timer);
+}
+
+# define wakeup_timer_waiters(b)	wake_up(&(b)->wait_for_running_timer)
+#else
+static inline void wait_for_running_timer(struct timer_list *timer)
+{
+	cpu_relax();
+}
+
+# define wakeup_timer_waiters(b)	do { } while (0)
+#endif
+
 /**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
@@ -1036,7 +1062,7 @@ int try_to_del_timer_sync(struct timer_l
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
 static DEFINE_PER_CPU(struct tvec_base, __tvec_bases);
 
 /**
@@ -1098,7 +1124,7 @@ int del_timer_sync(struct timer_list *ti
 		int ret = try_to_del_timer_sync(timer);
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		wait_for_running_timer(timer);
 	}
 }
 EXPORT_SYMBOL(del_timer_sync);
@@ -1219,15 +1245,17 @@ static inline void __run_timers(struct t
 			if (irqsafe) {
 				spin_unlock(&base->lock);
 				call_timer_fn(timer, fn, data);
+				base->running_timer = NULL;
 				spin_lock(&base->lock);
 			} else {
 				spin_unlock_irq(&base->lock);
 				call_timer_fn(timer, fn, data);
+				base->running_timer = NULL;
 				spin_lock_irq(&base->lock);
 			}
 		}
 	}
-	base->running_timer = NULL;
+	wakeup_timer_waiters(base);
 	spin_unlock_irq(&base->lock);
 }
 
@@ -1625,6 +1653,9 @@ static void __init init_timer_cpu(struct
 	base->cpu = cpu;
 	per_cpu(tvec_bases, cpu) = base;
 	spin_lock_init(&base->lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	init_waitqueue_head(&base->wait_for_running_timer);
+#endif
 
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);