Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "A migrate_tasks() locking fix, and a late-coming nohz change plus a
  nohz debug check"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: 'Annotate' migrate_tasks()
  nohz: Assert existing housekeepers when nohz full enabled
  nohz: Affine unpinned timers to housekeepers

2 files changed, 42 insertions, 9 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3595403..97d276f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -621,18 +621,21 @@ int get_nohz_timer_target(void)
 	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu))
+	if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i)) {
+			if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
+
+	if (!is_housekeeping_cpu(cpu))
+		cpu = housekeeping_any_cpu();
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -5178,24 +5181,47 @@ static void migrate_tasks(struct rq *dead_rq)
 			break;
 
 		/*
-		 * Ensure rq->lock covers the entire task selection
-		 * until the migration.
+		 * pick_next_task assumes pinned rq->lock.
 		 */
 		lockdep_pin_lock(&rq->lock);
 		next = pick_next_task(rq, &fake_task);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
+		/*
+		 * Rules for changing task_struct::cpus_allowed are holding
+		 * both pi_lock and rq->lock, such that holding either
+		 * stabilizes the mask.
+		 *
+		 * Drop rq->lock is not quite as disastrous as it usually is
+		 * because !cpu_active at this point, which means load-balance
+		 * will not interfere. Also, stop-machine.
+		 */
+		lockdep_unpin_lock(&rq->lock);
+		raw_spin_unlock(&rq->lock);
+		raw_spin_lock(&next->pi_lock);
+		raw_spin_lock(&rq->lock);
+
+		/*
+		 * Since we're inside stop-machine, _nothing_ should have
+		 * changed the task, WARN if weird stuff happened, because in
+		 * that case the above rq->lock drop is a fail too.
+		 */
+		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
+			raw_spin_unlock(&next->pi_lock);
+			continue;
+		}
+
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
-		lockdep_unpin_lock(&rq->lock);
 		rq = __migrate_task(rq, next, dest_cpu);
 		if (rq != dead_rq) {
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
 		}
+		raw_spin_unlock(&next->pi_lock);
 	}
 
 	rq->stop = stop;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3319e16..7c7ec45 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -290,16 +290,17 @@ static int __init tick_nohz_full_setup(char *str)
 __setup("nohz_full=", tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
-						 unsigned long action,
-						 void *hcpu)
+				       unsigned long action,
+				       void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
 		/*
-		 * If we handle the timekeeping duty for full dynticks CPUs,
-		 * we can't safely shutdown that CPU.
+		 * The boot CPU handles housekeeping duty (unbound timers,
+		 * workqueues, timekeeping, ...) on behalf of full dynticks
+		 * CPUs. It must remain online when nohz full is enabled.
 		 */
 		if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
 			return NOTIFY_BAD;
@@ -370,6 +371,12 @@ void __init tick_nohz_init(void)
 	cpu_notifier(tick_nohz_cpu_down_callback, 0);
 	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
 		cpumask_pr_args(tick_nohz_full_mask));
+
+	/*
+	 * We need at least one CPU to handle housekeeping work such
+	 * as timekeeping, unbound timers, workqueues, ...
+	 */
+	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
 }
 #endif