[PATCH 6/6] posix-timers: Fix full dynticks CPUs kick on timer rescheduling

[Frederic Weisbecker]

A posix CPU timer can be rearmed while it is firing or after it is
notified with a signal. This can happen for example with timers that
were set with a non zero interval in timer_settime().

This rearming can happen in two places:

1) On timer firing time, which happens on the target's tick. If the timer
can't trigger a signal because it is ignored, it reschedules itself
to honour the timer interval.

2) On signal handling from the timer's notification target. This one
can be a different task than the timer's target itself. Once the
signal is notified, the notification target rearms the timer, again
to honour the timer interval.

When a timer is rearmed, we need to notify the full dynticks CPUs
such that they restart their tick in case they are running tasks that
may have a share in elapsing this timer.

Now the 1st case above handles full dynticks CPUs with a call to
posix_cpu_timer_kick_nohz() from the posix cpu timer firing code. But
the second case ignores the fact that some CPUs may run non-idle tasks
with their tick off. As a result, when a timer is resheduled after its signal
notification, the full dynticks CPUs may completely ignore it and not
tick on the timer as expected

This patch fixes this bug by handling both cases in one. All we need
is to move the kick to the rearming common code in posix_cpu_timer_schedule().

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Olivier Langlois <olivier@xxxxxxxxxxxxxxxxxxx>
---
 kernel/posix-cpu-timers.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 35509c5..79747b7 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1091,7 +1091,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			put_task_struct(p);
 			timer->it.cpu.task = p = NULL;
 			timer->it.cpu.expires = 0;
-			goto out_unlock;
+			read_unlock(&tasklist_lock);
+			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
 			/*
 			 * We've noticed that the thread is dead, but
@@ -1100,7 +1101,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			 */
 			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead_task(timer, now);
-			goto out_unlock;
+			read_unlock(&tasklist_lock);
+			goto out;
 		}
 		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
@@ -1114,10 +1116,11 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	BUG_ON(!irqs_disabled());
 	arm_timer(timer);
 	spin_unlock(&p->sighand->siglock);
-
-out_unlock:
 	read_unlock(&tasklist_lock);
 
+	/* Kick full dynticks CPUs in case they need to tick on the new timer */
+	posix_cpu_timer_kick_nohz();
+
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1257,13 +1260,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 			cpu_timer_fire(timer);
 		spin_unlock(&timer->it_lock);
 	}
-
-	/*
-	 * In case some timers were rescheduled after the queue got emptied,
-	 * wake up full dynticks CPUs.
-	 */
-	if (tsk->signal->cputimer.running)
-		posix_cpu_timer_kick_nohz();
 }
 
 /*
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/