Re: [PATCH v2 2/5] mm: introduce external memory hinting API

[Oleksandr Natalenko]

On Wed, Jan 22, 2020 at 05:43:16PM -0800, Minchan Kim wrote:
> > It seems I've overlooked an important piece of this submission: one
> > cannot apply the hint to all the anonymous mapping regardless of address
> > range. For KSM I'd rather either have a possibility to hint all the
> > anonymous mappings, or, as it was suggested previously, be able to iterate
> > over existing mappings using some (fd-based?) API.
> 
> Thing is how you could identify a certan range is better for KSM than
> others from external process?

I think the info like this is kinda available via /proc/pid/smaps. It
lists the ranges and the vmflags. But using it raises 2 concerns: one is
the absence of guarantee the mappings won't change after smaps is read
and the second one is that there's no separate vmflag for marking a vma
as non-meregable (and IIRC from previous attempts on addressing this,
we've already exhausted all the flags on 32-bit arches, so it is not
something that can be trivially addressed).

-- 
  Best regards,
    Oleksandr Natalenko (post-factum)
    Senior Software Maintenance Engineer