sched,rt: fix isolated CPUs leaving root_task_group indefinitely throttled

commit e221d028bb08b47e624c5f0a31732c642db9d19a upstream.

Root task group bandwidth replenishment must service all CPUs, regardless of
where the timer was last started, and regardless of the isolation mechanism,
lest 'Quoth the Raven, "Nevermore"' become rt scheduling policy.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1344326558.6968.25.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Li Zefan <lizefan@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4a3bec80b9e2825edd2089839ec34d4f2122d49d..dd1c7e9d7fb080a752041c5807ec038593590f0d 100644 (file)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -782,6 +782,19 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
        const struct cpumask *span;
 
        span = sched_rt_period_mask();
+#ifdef CONFIG_RT_GROUP_SCHED
+       /*
+        * FIXME: isolated CPUs should really leave the root task group,
+        * whether they are isolcpus or were isolated via cpusets, lest
+        * the timer run on a CPU which does not service all runqueues,
+        * potentially leaving other CPUs indefinitely throttled.  If
+        * isolation is really required, the user will turn the throttle
+        * off to kill the perturbations it causes anyway.  Meanwhile,
+        * this maintains functionality for boot and/or troubleshooting.
+        */
+       if (rt_b == &root_task_group.rt_bandwidth)
+               span = cpu_online_mask;
+#endif
        for_each_cpu(i, span) {
                int enqueue = 0;
                struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);