cgroup: fix exit() vs rmdir() race

In cgroup_exit() put_css_set_taskexit() is called without any lock,
which might lead to accessing a freed cgroup:

thread1                           thread2
---------------------------------------------
exit()
  cgroup_exit()
    put_css_set_taskexit()
      atomic_dec(cgrp->count);
                                   rmdir();
      /* not safe !! */
      check_for_release(cgrp);

rcu_read_lock() can be used to make sure the cgroup is alive.

Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 800852282c210b5b184ef616d8080c218c75b938..5d4c92ead691fa52e0e820ce1e50b36f5151cbc8 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -422,12 +422,20 @@ static void __put_css_set(struct css_set *cg, int taskexit)
                struct cgroup *cgrp = link->cgrp;
                list_del(&link->cg_link_list);
                list_del(&link->cgrp_link_list);
+
+               /*
+                * We may not be holding cgroup_mutex, and if cgrp->count is
+                * dropped to 0 the cgroup can be destroyed at any time, hence
+                * rcu_read_lock is used to keep it alive.
+                */
+               rcu_read_lock();
                if (atomic_dec_and_test(&cgrp->count) &&
                    notify_on_release(cgrp)) {
                        if (taskexit)
                                set_bit(CGRP_RELEASABLE, &cgrp->flags);
                        check_for_release(cgrp);
                }
+               rcu_read_unlock();
 
                kfree(link);
        }