Re: [PATCH 2/2] cpuhotplug: make get_online_cpus() scalability byusing percpu counter

From: Lai Jiangshan
Date: Wed Apr 07 2010 - 09:35:46 EST

Oleg Nesterov wrote:
> On 04/05, Oleg Nesterov wrote:
>> On 04/05, Lai Jiangshan wrote:
>>> 1) get_online_cpus() must be allowed to be called recursively, so I added
>>> get_online_cpus_nest for every task for new code.
>> Well, iirc one of the goals of
>> cpu-hotplug: replace lock_cpu_hotplug() with get_online_cpus()
>> 86ef5c9a8edd78e6bf92879f32329d89b2d55b5a
>> was avoiding the new members in task_struct. I leave this up to you
>> and Gautham.

Old get_online_cpus() is read-preference, I think the goal of this ability
is allow get_online_cpus()/put_online_cpus() to be called nested.

But read-preference RWL may cause write side starvation, so I abandon this ability,
and use per-task counter for allowing get_online_cpus()/put_online_cpus()
to be called nested, I think this deal is absolutely worth.

>> Lai, I didn't read this patch carefully yet (and I can't apply it to
>> Linus's tree). But at first glance,
> because I tried to apply it without 1/2 ;)
>>> void put_online_cpus(void)
>>> {
>>> ...
>>> + if (!--current->get_online_cpus_nest) {
>>> + preempt_disable();
>>> + __get_cpu_var(refcount)--;
>>> + if (cpu_hotplug_task)
>>> + wake_up_process(cpu_hotplug_task);
>> This looks unsafe. In theory nothing protects cpu_hotplug_task from
>> exiting if refcount_sum() becomes zero, this means wake_up_process()
>> can hit the freed/reused/unmapped task_struct. Probably cpu_hotplug_done()
>> needs another synhronize_sched() before return.
> Yes, I think this is true, at least in theory.

preempt_disable() prevent cpu_hotplug_task from exiting.

Thanks, Lai
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at