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

Pull scheduler fixes from Ingo Molnar:
 "Three CPU hotplug related fixes and a debugging improvement"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/debug: Add debugfs knob for "sched_debug"
  sched/core: WARN() when migrating to an offline CPU
  sched/fair: Plug hole between hotplug and active_load_balance()
  sched/fair: Avoid newidle balance for !active CPUs

5 files changed, 25 insertions, 3 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 136a76d..18a6966 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1173,6 +1173,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
 				      lockdep_is_held(&task_rq(p)->lock)));
 #endif
+	/*
+	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
+	 */
+	WARN_ON_ONCE(!cpu_online(new_cpu));
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8e536d9..01217fb 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -181,11 +181,16 @@ static const struct file_operations sched_feat_fops = {
 	.release	= single_release,
 };
 
+__read_mostly bool sched_debug_enabled;
+
 static __init int sched_init_debug(void)
 {
 	debugfs_create_file("sched_features", 0644, NULL, NULL,
 			&sched_feat_fops);
 
+	debugfs_create_bool("sched_debug", 0644, NULL,
+			&sched_debug_enabled);
+
 	return 0;
 }
 late_initcall(sched_init_debug);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0a85641..70ba32e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8437,6 +8437,12 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	this_rq->idle_stamp = rq_clock(this_rq);
 
 	/*
+	 * Do not pull tasks towards !active CPUs...
+	 */
+	if (!cpu_active(this_cpu))
+		return 0;
+
+	/*
 	 * This is OK, because current is on_cpu, which avoids it being picked
 	 * for load-balance and preemption/IRQs are still disabled avoiding
 	 * further scheduler activity on it and we're being very careful to
@@ -8543,6 +8549,13 @@ static int active_load_balance_cpu_stop(void *data)
 	struct rq_flags rf;
 
 	rq_lock_irq(busiest_rq, &rf);
+	/*
+	 * Between queueing the stop-work and running it is a hole in which
+	 * CPUs can become inactive. We should not move tasks from or to
+	 * inactive CPUs.
+	 */
+	if (!cpu_active(busiest_cpu) || !cpu_active(target_cpu))
+		goto out_unlock;
 
 	/* make sure the requested cpu hasn't gone down in the meantime */
 	if (unlikely(busiest_cpu != smp_processor_id() ||
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 746ac78..14db76c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1951,6 +1951,8 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
 #ifdef	CONFIG_SCHED_DEBUG
+extern bool sched_debug_enabled;
+
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 5d0062c..f1cf4f3 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -14,11 +14,9 @@ cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
-static __read_mostly int sched_debug_enabled;
-
 static int __init sched_debug_setup(char *str)
 {
-	sched_debug_enabled = 1;
+	sched_debug_enabled = true;
 
 	return 0;
 }