path: root/kernel/cgroup.c
diff options
authorTejun Heo <>2016-04-21 19:06:48 -0400
committerTejun Heo <>2016-04-25 15:45:14 -0400
commit5cf1cacb49aee39c3e02ae87068fc3c6430659b0 (patch)
tree569518d16093a55169e4ef1cd5399e9a3f620d06 /kernel/cgroup.c
parentbcc981e9ed84c678533299d7eff17d2c81e4d5de (diff)
cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback
Since e93ad19d0564 ("cpuset: make mm migration asynchronous"), cpuset kicks off asynchronous NUMA node migration if necessary during task migration and flushes it from cpuset_post_attach_flush() which is called at the end of __cgroup_procs_write(). This is to avoid performing migration with cgroup_threadgroup_rwsem write-locked which can lead to deadlock through dependency on kworker creation. memcg has a similar issue with charge moving, so let's convert it to an official callback rather than the current one-off cpuset specific function. This patch adds cgroup_subsys->post_attach callback and makes cpuset register cpuset_post_attach_flush() as its ->post_attach. The conversion is mostly one-to-one except that the new callback is called under cgroup_mutex. This is to guarantee that no other migration operations are started before ->post_attach callbacks are finished. cgroup_mutex is one of the outermost mutex in the system and has never been and shouldn't be a problem. We can add specialized synchronization around __cgroup_procs_write() but I don't think there's any noticeable benefit. Signed-off-by: Tejun Heo <> Cc: Li Zefan <> Cc: Johannes Weiner <> Cc: Michal Hocko <> Cc: <> # 4.4+ prerequisite for the next patch
Diffstat (limited to 'kernel/cgroup.c')
1 files changed, 5 insertions, 2 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 671dc05c0b0f..909a7d31ffd3 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2825,9 +2825,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off, bool threadgroup)
struct task_struct *tsk;
+ struct cgroup_subsys *ss;
struct cgroup *cgrp;
pid_t pid;
- int ret;
+ int ssid, ret;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
@@ -2875,8 +2876,10 @@ out_unlock_rcu:
+ for_each_subsys(ss, ssid)
+ if (ss->post_attach)
+ ss->post_attach();
- cpuset_post_attach_flush();
return ret ?: nbytes;