[RFC PATCH] mmap.2: clarify MAP_LOCKED semantic (was: Re: Should mmap MAP_LOCKED fail if mm_poppulate fails?)

[Michal Hocko]

On Tue 28-04-15 11:38:35, Linus Torvalds wrote:
> On Tue, Apr 28, 2015 at 11:35 AM, Michal Hocko <mhocko@xxxxxxx> wrote:
> >
> > I am still not sure I see the problem here.
> 
> Basically, I absolutely hate the notion of us doing something
> unsynchronized, when I can see us undoing a mmap that another thread
> is doing. It's wrong.

OK, I have checked the mmap(2) man page and there is no single mention
about multi-threaded usage. So even though I personally think that
user fault handlers which do mmap(MAP_FIXED) without synchronization
to parallel mmaps are broken by definition we cannot simply rule them
out and it is not the kernel job to make them broken even more or in a
subtly different way.
So here is an RFC for the man page patch. I am not very good in the
format but man doesn't complain about any formating issues.
---