Re: Q: select_fallback_rq() && cpuset_lock()

[Peter Zijlstra <peterz@infradead.org>]

On Tue, 2010-03-09 at 19:06 +0100, Oleg Nesterov wrote:
> Hello.
> 
> I tried to remove the deadlockable cpuset_lock() many times, but my
> attempts were ignored by cpuset maintainers ;)

Yeah, this appears to be an issue, there's no real maintainer atm, parts
are done by the sched folks, parts by the cgroup folks, and I guess
neither really knows everything..

> In particular, see http://marc.info/?l=linux-kernel&m=125261083613103

/me puts it on the to-review stack.

> But now I have another question. Since 5da9a0fb673a0ea0a093862f95f6b89b3390c31e
> cpuset_cpus_allowed_locked() is called without callback_mutex held by
> try_to_wake_up().
> 
> And, without callback_mutex held, isn't it possible to race with, say,
> update_cpumask() which changes cpuset->cpus_allowed? Yes, update_tasks_cpumask()
> should fixup task->cpus_allowed later. But isn't it possible (at least
> in theory) that try_to_wake_up() gets, say, all-zeroes in task->cpus_allowed
> after select_fallback_rq()->cpuset_cpus_allowed_locked() if we race with
> update_cpumask()->cpumask_copy() ?

Hurmm,.. good point,.. yes I think that might be possible.
p->cpus_allowed is synchronized properly, but cs->cpus_allowed is not,
bugger.

I guess the quick fix is to really bail and always use cpu_online_mask
in select_fallback_rq().