3 files changed, 51 insertions, 18 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 781845a013a..e91963302c0 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4480,6 +4480,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	struct dentry *d = cgrp->dentry;
 	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
+	struct cgroup *child;
 	bool empty;
 
 	lockdep_assert_held(&d->d_inode->i_mutex);
@@ -4490,12 +4491,28 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 * @cgrp from being removed while __put_css_set() is in progress.
 	 */
 	read_lock(&css_set_lock);
-	empty = list_empty(&cgrp->cset_links) && list_empty(&cgrp->children);
+	empty = list_empty(&cgrp->cset_links);
 	read_unlock(&css_set_lock);
 	if (!empty)
 		return -EBUSY;
 
 	/*
+	 * Make sure there's no live children.  We can't test ->children
+	 * emptiness as dead children linger on it while being destroyed;
+	 * otherwise, "rmdir parent/child parent" may fail with -EBUSY.
+	 */
+	empty = true;
+	rcu_read_lock();
+	list_for_each_entry_rcu(child, &cgrp->children, sibling) {
+		empty = cgroup_is_dead(child);
+		if (!empty)
+			break;
+	}
+	rcu_read_unlock();
+	if (!empty)
+		return -EBUSY;
+
+	/*
 	 * Block new css_tryget() by killing css refcnts.  cgroup core
 	 * guarantees that, by the time ->css_offline() is invoked, no new
 	 * css reference will be given out via css_tryget().  We can't
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 3bdf2832301..61ed862cdd3 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -265,10 +265,9 @@ static inline void timer_list_header(struct seq_file *m, u64 now)
 static int timer_list_show(struct seq_file *m, void *v)
 {
 	struct timer_list_iter *iter = v;
-	u64 now = ktime_to_ns(ktime_get());
 
 	if (iter->cpu == -1 && !iter->second_pass)
-		timer_list_header(m, now);
+		timer_list_header(m, iter->now);
 	else if (!iter->second_pass)
 		print_cpu(m, iter->cpu, iter->now);
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -298,33 +297,41 @@ void sysrq_timer_list_show(void)
 	return;
 }
 
-static void *timer_list_start(struct seq_file *file, loff_t *offset)
+static void *move_iter(struct timer_list_iter *iter, loff_t offset)
 {
-	struct timer_list_iter *iter = file->private;
-
-	if (!*offset) {
-		iter->cpu = -1;
-		iter->now = ktime_to_ns(ktime_get());
-	} else if (iter->cpu >= nr_cpu_ids) {
+	for (; offset; offset--) {
+		iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+		if (iter->cpu >= nr_cpu_ids) {
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
-		if (!iter->second_pass) {
-			iter->cpu = -1;
-			iter->second_pass = true;
-		} else
-			return NULL;
+			if (!iter->second_pass) {
+				iter->cpu = -1;
+				iter->second_pass = true;
+			} else
+				return NULL;
 #else
-		return NULL;
+			return NULL;
 #endif
+		}
 	}
 	return iter;
 }
 
+static void *timer_list_start(struct seq_file *file, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+
+	if (!*offset)
+		iter->now = ktime_to_ns(ktime_get());
+	iter->cpu = -1;
+	iter->second_pass = false;
+	return move_iter(iter, *offset);
+}
+
 static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
 {
 	struct timer_list_iter *iter = file->private;
-	iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
 	++*offset;
-	return timer_list_start(file, offset);
+	return move_iter(iter, 1);
 }
 
 static void timer_list_stop(struct seq_file *seq, void *v)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 7f5d4be2203..e93f7b9067d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2201,6 +2201,15 @@ __acquires(&pool->lock)
 		dump_stack();
 	}
 
+	/*
+	 * The following prevents a kworker from hogging CPU on !PREEMPT
+	 * kernels, where a requeueing work item waiting for something to
+	 * happen could deadlock with stop_machine as such work item could
+	 * indefinitely requeue itself while all other CPUs are trapped in
+	 * stop_machine.
+	 */
+	cond_resched();
+
 	spin_lock_irq(&pool->lock);
 
 	/* clear cpu intensive status */