cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys…

…->post_attach callback

Since e93ad19 ("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 <[email protected]>
Cc: Li Zefan <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: <[email protected]> # 4.4+ prerequisite for the next patch

include/linux/cgroup-defs.h

@@ -444,6 +444,7 @@ 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);

include/linux/cpuset.h

@@ -137,8 +137,6 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	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_retry(unsigned int seq)
 	return false;
 }
 
-static inline void cpuset_post_attach_flush(void)
-{
-}
-
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */

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 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	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;
 }
 

kernel/cpuset.c

@@ -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_struct *mm, const nodemask_t *from,
 	}
 }
 
-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	= true,