cgroupns: Close race between cgroup_post_fork and copy_cgroup_ns

In most code paths involving cgroup migration cgroup_threadgroup_rwsem
is taken.  There are two exceptions:

- remove_tasks_in_empty_cpuset calls cgroup_transfer_tasks
- vhost_attach_cgroups_work calls cgroup_attach_task_all

With cgroup_threadgroup_rwsem held it is guaranteed that cgroup_post_fork
and copy_cgroup_ns will reference the same css_set from the process calling
fork.

Without such an interlock there process after fork could reference one
css_set from it's new cgroup namespace and another css_set from
task->cgroups, which semantically is nonsensical.

Cc: stable@vger.kernel.org
Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5f01e00cffc4982879368e01afec3f2fcf59c1b8..e75efa819911a087228234c96a87dbfea68f323d 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2962,6 +2962,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
        int retval = 0;
 
        mutex_lock(&cgroup_mutex);
+       percpu_down_write(&cgroup_threadgroup_rwsem);
        for_each_root(root) {
                struct cgroup *from_cgrp;
 
@@ -2976,6 +2977,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
                if (retval)
                        break;
        }
+       percpu_up_write(&cgroup_threadgroup_rwsem);
        mutex_unlock(&cgroup_mutex);
 
        return retval;
@@ -4343,6 +4345,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 
        mutex_lock(&cgroup_mutex);
 
+       percpu_down_write(&cgroup_threadgroup_rwsem);
+
        /* all tasks in @from are being moved, all csets are source */
        spin_lock_irq(&css_set_lock);
        list_for_each_entry(link, &from->cset_links, cset_link)
@@ -4371,6 +4375,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
        } while (task && !ret);
 out_err:
        cgroup_migrate_finish(&preloaded_csets);
+       percpu_up_write(&cgroup_threadgroup_rwsem);
        mutex_unlock(&cgroup_mutex);
        return ret;
 }