From 950680b1d7b6d31c07a15fefb32df89477b9122c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:34 -0500
Subject: [PATCH] hrtimers: Prepare full preemption

Make cancellation of a running callback in softirq context safe
against preemption.

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

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 3214d9ac2002..2f977fc8b679 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
+#include <linux/wait.h>
 
 /*
  * Clock ids for hrtimers which expire in softirq context. These clock ids
@@ -212,6 +213,9 @@ struct hrtimer_cpu_base {
 	ktime_t				expires_next;
 	struct hrtimer			*next_timer;
 	ktime_t				softirq_expires_next;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	wait_queue_head_t		wait;
+#endif
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
 } ____cacheline_aligned;
 
@@ -426,6 +430,13 @@ static inline void hrtimer_restart(struct hrtimer *timer)
 	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/* Softirq preemption could deadlock timer removal */
+#ifdef CONFIG_PREEMPT_RT_BASE
+  extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
+#else
+# define hrtimer_wait_for_timer(timer)	do { cpu_relax(); } while (0)
+#endif
+
 /* Query timers: */
 extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
 
@@ -450,7 +461,7 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  * Helper function to check, whether the timer is running the callback
  * function
  */
-static inline int hrtimer_callback_running(struct hrtimer *timer)
+static inline int hrtimer_callback_running(const struct hrtimer *timer)
 {
 	return timer->base->running == timer;
 }
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index f2815da015d8..e54dfd1aa231 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -862,6 +862,33 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(hrtimer_forward);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define wake_up_timer_waiters(b)	wake_up(&(b)->wait)
+
+/**
+ * hrtimer_wait_for_timer - Wait for a running timer
+ *
+ * @timer:	timer to wait for
+ *
+ * The function waits in case the timers callback function is
+ * currently executed on the waitqueue of the timer base. The
+ * waitqueue is woken up after the timer callback function has
+ * finished execution.
+ */
+void hrtimer_wait_for_timer(const struct hrtimer *timer)
+{
+	struct hrtimer_clock_base *base = timer->base;
+
+	if (base && base->cpu_base &&
+	    base->index >= HRTIMER_BASE_MONOTONIC_SOFT)
+		wait_event(base->cpu_base->wait,
+				!(hrtimer_callback_running(timer)));
+}
+
+#else
+# define wake_up_timer_waiters(b)	do { } while (0)
+#endif
+
 /*
  * enqueue_hrtimer - internal function to (re)start a timer
  *
@@ -1109,7 +1136,7 @@ int hrtimer_cancel(struct hrtimer *timer)
 
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_wait_for_timer(timer);
 	}
 }
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1385,6 +1412,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
 	hrtimer_update_softirq_timer(cpu_base, true);
 
 	raw_spin_unlock_irq(&cpu_base->lock);
+	wake_up_timer_waiters(cpu_base);
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -1729,6 +1757,9 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->hres_active = 0;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	init_waitqueue_head(&cpu_base->wait);
+#endif
 	return 0;
 }
 
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 087d6a1279b8..48b57e458294 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -195,6 +195,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 		/* We are sharing ->siglock with it_real_fn() */
 		if (hrtimer_try_to_cancel(timer) < 0) {
 			spin_unlock_irq(&tsk->sighand->siglock);
+			hrtimer_wait_for_timer(&tsk->signal->real_timer);
 			goto again;
 		}
 		expires = timeval_to_ktime(value->it_value);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 2e608587bd1e..651bd0b53352 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -831,6 +831,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	return overrun;
 }
 
+/*
+ * Protected by RCU!
+ */
+static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (kc->timer_set == common_timer_set)
+		hrtimer_wait_for_timer(&timr->it.real.timer);
+	else
+		/* FIXME: Whacky hack for posix-cpu-timers */
+		schedule_timeout(1);
+#endif
+}
+
 /* Set a POSIX.1b interval timer. */
 /* timr->it_lock is taken. */
 static int
@@ -910,6 +924,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	if (!timr)
 		return -EINVAL;
 
+	rcu_read_lock();
 	kc = clockid_to_kclock(timr->it_clock);
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
@@ -918,9 +933,12 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
+		timer_wait_for_callback(kc, timr);
 		rtn = NULL;	// We already got the old time...
+		rcu_read_unlock();
 		goto retry;
 	}
+	rcu_read_unlock();
 
 	old_spec = itimerspec64_to_itimerspec(&old_spec64);
 	if (old_setting && !error &&
@@ -959,10 +977,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
 	if (!timer)
 		return -EINVAL;
 
+	rcu_read_lock();
 	if (timer_delete_hook(timer) == TIMER_RETRY) {
 		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
+	rcu_read_unlock();
 
 	spin_lock(&current->sighand->siglock);
 	list_del(&timer->list);
@@ -988,8 +1011,18 @@ static void itimer_delete(struct k_itimer *timer)
 retry_delete:
 	spin_lock_irqsave(&timer->it_lock, flags);
 
+	/* On RT we can race with a deletion */
+	if (!timer->it_signal) {
+		unlock_timer(timer, flags);
+		return;
+	}
+
 	if (timer_delete_hook(timer) == TIMER_RETRY) {
+		rcu_read_lock();
 		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
 	list_del(&timer->list);
-- 
2.1.4