Patch "cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback" has been added to the 4.5-stable tree

This is a note to let you know that I've just added the patch titled

    cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback

to the 4.5-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
cgroup-cpuset-replace-cpuset_post_attach_flush-with-cgroup_subsys-post_attach-callback.patch
and it can be found in the queue-4.5 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Tejun Heo <[email protected]>
Date: Thu, 21 Apr 2016 19:06:48 -0400
Subject: cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback

From: Tejun Heo <[email protected]>

commit 5cf1cacb49aee39c3e02ae87068fc3c6430659b0 upstream.

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.

---
 include/linux/cgroup-defs.h |    1 +
 include/linux/cpuset.h      |    6 ------
 kernel/cgroup.c             |    7 +++++--
 kernel/cpuset.c             |    4 ++--
 4 files changed, 8 insertions(+), 10 deletions(-)

@@ -442,6 +442,7 @@ struct cgroup_subsys {
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);
+	void (*post_attach)(void);
 	int (*can_fork)(struct task_struct *task);
 	void (*cancel_fork)(struct task_struct *task);
 	void (*fork)(struct task_struct *task);

@@ -137,8 +137,6 @@ static inline void set_mems_allowed(node
 	task_unlock(current);
 }
 
-extern void cpuset_post_attach_flush(void);
-
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }

@@ -245,10 +243,6 @@ static inline bool read_mems_allowed_ret
 	return false;
 }
 
-static inline void cpuset_post_attach_flush(void)
-{
-}
-
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */

@@ -2697,9 +2697,10 @@ static ssize_t __cgroup_procs_write(stru
 				    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;

@@ -2747,8 +2748,10 @@ out_unlock_rcu:
 	rcu_read_unlock();
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	for_each_subsys(ss, ssid)
+		if (ss->post_attach)
+			ss->post_attach();
 	cgroup_kn_unlock(of->kn);
-	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 

@@ -58,7 +58,6 @@
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 

@@ -1016,7 +1015,7 @@ static void cpuset_migrate_mm(struct mm_
 	}
 }
 
-void cpuset_post_attach_flush(void)
+static void cpuset_post_attach(void)
 {
 	flush_workqueue(cpuset_migrate_mm_wq);
 }

@@ -2087,6 +2086,7 @@ struct cgroup_subsys cpuset_cgrp_subsys
 	.can_attach	= cpuset_can_attach,
 	.cancel_attach	= cpuset_cancel_attach,
 	.attach		= cpuset_attach,
+	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
 	.legacy_cftypes	= files,
 	.early_init	= 1,

Patches currently in stable-queue which might be from [email protected] are

queue-4.5/sched-cgroup-fix-cleanup-cgroup-teardown-init.patch queue-4.5/workqueue-fix-ghost-pending-flag-while-doing-mq-io.patch queue-4.5/cgroup-cpuset-replace-cpuset_post_attach_flush-with-cgroup_subsys-post_attach-callback.patch queue-4.5/memcg-relocate-charge-moving-from-attach-to-post_attach.patch