Merge branch 'for-4.8-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:
 "Three late fixes for cgroup: Two cpuset ones, one trivial and the
  other pretty obscure, and a cgroup core fix for a bug which impacts
  cgroup v2 namespace users"

* 'for-4.8-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: fix invalid controller enable rejections with cgroup namespace
  cpuset: fix non static symbol warning
  cpuset: handle race between CPU hotplug and cpuset_hotplug_work

2 files changed, 40 insertions, 8 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5e8dab5bf9ad..d6b729beba49 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3446,9 +3446,28 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
          * Except for the root, subtree_control must be zero for a cgroup
          * with tasks so that child cgroups don't compete against tasks.
          */
-        if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
-                ret = -EBUSY;
-                goto out_unlock;
+        if (enable && cgroup_parent(cgrp)) {
+                struct cgrp_cset_link *link;
+
+                /*
+                 * Because namespaces pin csets too, @cgrp->cset_links
+                 * might not be empty even when @cgrp is empty.  Walk and
+                 * verify each cset.
+                 */
+                spin_lock_irq(&css_set_lock);
+
+                ret = 0;
+                list_for_each_entry(link, &cgrp->cset_links, cset_link) {
+                        if (css_set_populated(link->cset)) {
+                                ret = -EBUSY;
+                                break;
+                        }
+                }
+
+                spin_unlock_irq(&css_set_lock);
+
+                if (ret)
+                        goto out_unlock;
         }
 
         /* save and update control masks and prepare csses */
@@ -3899,7 +3918,9 @@ void cgroup_file_notify(struct cgroup_file *cfile)
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
- * Return the number of tasks in the cgroup.
+ * Return the number of tasks in the cgroup.  The returned number can be
+ * higher than the actual number of tasks due to css_set references from
+ * namespace roots and temporary usages.
  */
 static int cgroup_task_count(const struct cgroup *cgrp)
 {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c27e53326bef..2b4c20ab5bbe 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -325,8 +325,7 @@ static struct file_system_type cpuset_fs_type = {
 /*
  * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.  The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
@@ -335,8 +334,20 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-        while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+        while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
                 cs = parent_cs(cs);
+                if (unlikely(!cs)) {
+                        /*
+                         * The top cpuset doesn't have any online cpu as a
+                         * consequence of a race between cpuset_hotplug_work
+                         * and cpu hotplug notifier.  But we know the top
+                         * cpuset's effective_cpus is on its way to to be
+                         * identical to cpu_online_mask.
+                         */
+                        cpumask_copy(pmask, cpu_online_mask);
+                        return;
+                }
+        }
         cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
@@ -2074,7 +2085,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
  * which could have been changed by cpuset just after it inherits the
  * state from the parent and before it sits on the cgroup's task list.
  */
-void cpuset_fork(struct task_struct *task)
+static void cpuset_fork(struct task_struct *task)
 {
         if (task_css_is_root(task, cpuset_cgrp_id))
                 return;