[PATCH 14/33] sched/isolation: Flush memcg workqueues on cpuset isolated partition change

[Frederic Weisbecker]

Le Tue, Oct 21, 2025 at 03:16:45PM -0400, Waiman Long a écrit :
> > @@ -5134,6 +5141,9 @@ int __init mem_cgroup_init(void)
> >   	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
> >   				  memcg_hotplug_cpu_dead);
> > +	memcg_wq = alloc_workqueue("memcg", 0, 0);
> 
> Should we explicitly mark the memcg_wq as WQ_PERCPU even though I think
> percpu is the default. The schedule_work_on() schedules work on the
> system_percpu_wq.

Good catch, percpu is the default but that behaviour is scheduled for
deprecation. I'm adding WQ_PERCPU.

Thanks!

-- 
Frederic Weisbecker
SUSE Labs