Re: [PATCH 2/2] cpusets: update tasks' cpus_allowed and mems_allowed after CPU/NODE offline/online

[Paul Jackson <pj@sgi.com>]

David wrote:
> That would only identify kthreads that have been created with a subsequent 
> call to set_cpus_allowed() or kthread_bind().
> 
> The PF_CPU_BOUND change targets only the latter since there are kthreads, 
> such as kstopmachine, that can continue to manipulate their cpus_allowed 
> during their lifetime.

Would your first sentence be more clearly written as:

> That would identify both kthreads that have been created with a subsequent 
> call to set_cpus_allowed() or kthread_bind().

Or do I misunderstand?

If I am reading you correctly, then would it work to have a check in the
cpuset code (rather than in the lower set_cpus_allowed() routine),
where that check refused to move tasks out of the root cpuset if they
were (1) kernel threads (mm NULL) and (2) had cpus_allowed that were a
strict subset of the root cpusets 'cpus' (the online cpus).

-- 
                  I won't rest till it's the best ...
                  Programmer, Linux Scalability
                  Paul Jackson <pj@sgi.com> 1.940.382.4214