summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2016-09-23 16:55:49 -0400
committerTejun Heo <tj@kernel.org>2016-09-23 16:55:49 -0400
commit9157056da8f8c4a6305f15619e269f164b63a6de (patch)
tree3b2cea5209fae8b62b46ab19c3ce4d4a897b9b40 /kernel/cgroup.c
parent8a15b81741879fa89601b03c0e50b0d780d65bc0 (diff)
downloadlinux-9157056da8f8c4a6305f15619e269f164b63a6de.tar.gz
linux-9157056da8f8c4a6305f15619e269f164b63a6de.tar.bz2
linux-9157056da8f8c4a6305f15619e269f164b63a6de.zip
cgroup: fix invalid controller enable rejections with cgroup namespace
On the v2 hierarchy, "cgroup.subtree_control" rejects controller enables if the cgroup has processes in it. The enforcement of this logic assumes that the cgroup wouldn't have any css_sets associated with it if there are no tasks in the cgroup, which is no longer true since a79a908fd2b0 ("cgroup: introduce cgroup namespaces"). When a cgroup namespace is created, it pins the css_set of the creating task to use it as the root css_set of the namespace. This extra reference stays as long as the namespace is around and makes "cgroup.subtree_control" think that the namespace root cgroup is not empty even when it is and thus reject controller enables. Fix it by making cgroup_subtree_control() walk and test emptiness of each css_set instead of testing whether the list_head is empty. While at it, update the comment of cgroup_task_count() to indicate that the returned value may be higher than the number of tasks, which has always been true due to temporary references and doesn't break anything. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Cc: Serge E. Hallyn <serge.hallyn@ubuntu.com> Cc: Aditya Kali <adityakali@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: stable@vger.kernel.org # v4.6+ Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Link: https://github.com/systemd/systemd/pull/3589#issuecomment-249089541
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c29
1 files changed, 25 insertions, 4 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d1c51b7f5221..0d4ee1ea5c31 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)
{