LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Dave Hansen <haveblue@us.ibm.com>
To: Matt Mackall <mpm@selenic.com>
Cc: Hans Rosenfeld <hans.rosenfeld@amd.com>,
	linux-kernel@vger.kernel.org, Adam Litke <aglitke@gmail.com>,
	nacc <nacc@linux.vnet.ibm.com>,
	Jon Tollefson <kniht@linux.vnet.ibm.com>,
	Adam Litke <agl@linux.vnet.ibm.com>
Subject: Re: [RFC][PATCH] make /proc/pid/pagemap work with huge pages and return page size
Date: Fri, 29 Feb 2008 14:30:34 -0800	[thread overview]
Message-ID: <1204324234.2086.14.camel@nimitz.home.sr71.net> (raw)
In-Reply-To: <1204247745.4021.41.camel@cinder.waste.org>

On Thu, 2008-02-28 at 17:15 -0800, Matt Mackall wrote:
> > The only issue is that this is *after* the code has decided that a
> > particular virtual area is for huge pages.  The best arch-generic
> > interface I know for that is: is_vm_hugetlb_page(), but that is
> > VMA-based.  Perhaps we should change the pagemap walk to pass the VMA
> > around. 
> 
> I'd rather avoid that. Requiring a VMA to poke at these things shouldn't
> -really- be necessary.

Yeah, this is strictly true.  But, it also assumes that we have all of
the data about where large pages are based on the contents of the
pagetables alone.  It's possible that we can derive this, or code up a
bunch of arch-specific functions to do this, but it certainly doesn't
exist today.  I'm just not keen on going and learning about how each and
every architecture encodes hugetlb information in their pagetables. :(

The fact is that we treat pagetables in hugetlb areas completely
differently than normal pages.  All of the generic functions that deal
with pagetables magically punt over to the hugetlb code when they see a
hugetlb VMA.

I think although it isn't strictly necessary, it is going to save a ton
of work to just pass the VMAs around.

-- Dave


  reply	other threads:[~2008-02-29 22:30 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-02-20 13:57 Hans Rosenfeld
2008-02-23  2:18 ` Matt Mackall
2008-02-23 18:31   ` Dave Hansen
2008-02-25 12:09     ` Hans Rosenfeld
2008-02-25 18:39       ` Dave Hansen
2008-02-26 20:25         ` Hans Rosenfeld
2008-02-27 17:44           ` Dave Hansen
2008-02-28 12:00             ` Hans Rosenfeld
2008-02-29  0:49               ` Dave Hansen
2008-02-29  1:15                 ` Matt Mackall
2008-02-29 22:30                   ` Dave Hansen [this message]
2008-02-29 22:46                     ` Matt Mackall
2008-03-05 16:00                       ` Hans Rosenfeld
2008-03-05 16:32                         ` Dave Hansen
2008-03-05 17:22                           ` Hans Rosenfeld
2008-02-23  8:06 ` Andrew Morton
2008-02-23 15:25   ` Matt Mackall

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1204324234.2086.14.camel@nimitz.home.sr71.net \
    --to=haveblue@us.ibm.com \
    --cc=agl@linux.vnet.ibm.com \
    --cc=aglitke@gmail.com \
    --cc=hans.rosenfeld@amd.com \
    --cc=kniht@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mpm@selenic.com \
    --cc=nacc@linux.vnet.ibm.com \
    --subject='Re: [RFC][PATCH] make /proc/pid/pagemap work with huge pages and return page size' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).