From bb78a92f47696b2da49f2692b6a9fa56d07c444a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 28 Aug 2013 16:31:23 -0700 Subject: cgroup: fix rmdir EBUSY regression in 3.11 On 3.11-rc we are seeing cgroup directories left behind when they should have been removed. Here's a trivial reproducer: cd /sys/fs/cgroup/memory mkdir parent parent/child; rmdir parent/child parent rmdir: failed to remove `parent': Device or resource busy It's because cgroup_destroy_locked() (step 1 of destruction) leaves cgroup on parent's children list, letting cgroup_offline_fn() (step 2 of destruction) remove it; but step 2 is run by work queue, which may not yet have removed the children when parent destruction checks the list. Fix that by checking through a non-empty list of children: if every one of them has already been marked CGRP_DEAD, then it's safe to proceed: those children are invisible to userspace, and should not obstruct rmdir. (I didn't see any reason to keep the cgrp->children checks under the unrelated css_set_lock, so moved them out.) tj: Flattened nested ifs a bit and updated comment so that it's correct on both for-3.11-fixes and for-3.12. Signed-off-by: Hugh Dickins Signed-off-by: Tejun Heo --- kernel/cgroup.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) 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); @@ -4490,11 +4491,27 @@ 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 -- cgit v1.2.3-18-g5258