From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:34 -0500
Subject: timers: Prepare for full preemption
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git
Git-commit: 2be2c6b6f5458cedf10f9a26a56960a129f06811
Patch-mainline: Queued in subsystem maintainer repository
References: SLE Realtime Extension

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>
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
---
 include/linux/timer.h |    2 +-
 kernel/sched/core.c   |    9 +++++++--
 kernel/time/timer.c   |   45 +++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 49 insertions(+), 7 deletions(-)

--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -227,7 +227,7 @@ 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
@@ -563,11 +563,14 @@ void resched_cpu(int cpu)
  */
 int get_nohz_timer_target(void)
 {
-	int i, cpu = smp_processor_id();
+	int i, cpu;
 	struct sched_domain *sd;
 
+	preempt_disable_rt();
+	cpu = smp_processor_id();
+
 	if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
-		return cpu;
+		goto preempt_en_rt;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
@@ -586,6 +589,8 @@ int get_nohz_timer_target(void)
 		cpu = housekeeping_any_cpu();
 unlock:
 	rcu_read_unlock();
+preempt_en_rt:
+	preempt_enable_rt();
 	return cpu;
 }
 
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -45,6 +45,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/random.h>
+#include <linux/swait.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -198,6 +199,9 @@ EXPORT_SYMBOL(jiffies_64);
 struct timer_base {
 	raw_spinlock_t		lock;
 	struct timer_list	*running_timer;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	struct swait_queue_head	wait_for_running_timer;
+#endif
 	unsigned long		clk;
 	unsigned long		next_expiry;
 	unsigned int		cpu;
@@ -1162,6 +1166,33 @@ 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 timer_base *base;
+	u32 tf = timer->flags;
+
+	if (tf & TIMER_MIGRATING)
+		return;
+
+	base = get_timer_base(tf);
+	swait_event(base->wait_for_running_timer,
+		   base->running_timer != timer);
+}
+
+# define wakeup_timer_waiters(b)	swake_up_all(&(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 - deactivate a timer.
  * @timer: the timer to be deactivated
@@ -1217,7 +1248,7 @@ 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)
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1277,7 +1308,7 @@ 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);
@@ -1341,13 +1372,16 @@ static void expire_timers(struct timer_b
 		fn = timer->function;
 		data = timer->data;
 
-		if (timer->flags & TIMER_IRQSAFE) {
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL) &&
+		    timer->flags & TIMER_IRQSAFE) {
 			raw_spin_unlock(&base->lock);
 			call_timer_fn(timer, fn, data);
+			base->running_timer = NULL;
 			raw_spin_lock(&base->lock);
 		} else {
 			raw_spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn, data);
+			base->running_timer = NULL;
 			raw_spin_lock_irq(&base->lock);
 		}
 	}
@@ -1656,8 +1690,8 @@ static inline void __run_timers(struct t
 		while (levels--)
 			expire_timers(base, heads + levels);
 	}
-	base->running_timer = NULL;
 	raw_spin_unlock_irq(&base->lock);
+	wakeup_timer_waiters(base);
 }
 
 /*
@@ -1903,6 +1937,9 @@ static void __init init_timer_cpu(int cp
 		base->cpu = cpu;
 		raw_spin_lock_init(&base->lock);
 		base->clk = jiffies;
+#ifdef CONFIG_PREEMPT_RT_FULL
+		init_swait_queue_head(&base->wait_for_running_timer);
+#endif
 	}
 }