From: Ingo Molnar <mingo@elte.hu>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Andi Kleen <ak@suse.de>, Arjan van de Ven <arjan@intel.linux.com>,
linux-kernel@vger.kernel.org, akpm@osdl.org
Subject: Re: [Patch 3/3] prepopulate/cache cleared pages
Date: Thu, 23 Feb 2006 14:29:54 +0100 [thread overview]
Message-ID: <20060223132954.GA16074@elte.hu> (raw)
In-Reply-To: <43FDB55E.7090607@yahoo.com.au>
* Nick Piggin <nickpiggin@yahoo.com.au> wrote:
> I'm worried about the situation where we allocate but don't use the
> new page: it blows quite a bit of cache. Then, when we do get around
> to using it, it will be cold(er).
couldnt the new pte be flipped in atomically via cmpxchg? That way we
could do the page clearing close to where we are doing it now, but
without holding the mmap_sem.
to solve the pte races we could use a bit in the [otherwise empty] pte
to signal "this pte can be flipped in from now on", which bit would
automatically be cleared if mprotect() or munmap() is called over that
range (without any extra changes to those codepaths). (in the rare case
if the cmpxchg() fails, we go into a slowpath that drops the newly
allocated page, re-lookups the vma and the pte, etc.)
Ingo
next prev parent reply other threads:[~2006-02-23 13:31 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-02-23 9:17 [Patch 0/3] threaded mmap tweaks Arjan van de Ven
2006-02-23 9:29 ` [Patch 3/3] prepopulate/cache cleared pages Arjan van de Ven
2006-02-23 9:41 ` Andi Kleen
2006-02-23 12:41 ` Ingo Molnar
2006-02-23 13:06 ` Andi Kleen
2006-02-23 13:15 ` Nick Piggin
2006-02-23 13:29 ` Ingo Molnar [this message]
2006-02-24 6:36 ` Nick Piggin
2006-02-24 6:49 ` Ingo Molnar
2006-02-24 7:01 ` Nick Piggin
2006-02-24 12:33 ` Andi Kleen
2006-02-24 12:55 ` Hugh Dickins
2006-02-24 9:15 ` Arjan van de Ven
2006-02-24 9:26 ` Nick Piggin
2006-02-24 12:27 ` Andi Kleen
2006-02-24 15:31 ` Andrea Arcangeli
2006-02-25 16:48 ` Nick Piggin
2006-02-25 17:22 ` Nick Piggin
2006-02-28 22:30 ` Pavel Machek
2006-02-23 18:25 ` Paul Jackson
2006-02-23 9:30 ` [Patch 2/3] fast VMA recycling Arjan van de Ven
2006-02-23 9:42 ` Andi Kleen
2006-02-23 9:48 ` Arjan van de Ven
2006-02-23 10:05 ` Andi Kleen
2006-02-23 10:15 ` Arjan van de Ven
2006-02-23 11:00 ` Andi Kleen
2006-02-23 11:22 ` Arjan van de Ven
2006-02-23 11:57 ` Andi Kleen
2006-02-24 18:52 ` Christoph Hellwig
2006-02-24 19:05 ` Andi Kleen
2006-02-24 19:09 ` Christoph Hellwig
2006-02-23 16:37 ` Benjamin LaHaise
2006-02-23 20:02 [Patch 3/3] prepopulate/cache cleared pages Chuck Ebbert
2006-02-23 21:10 Chuck Ebbert
2006-02-23 21:18 ` Arjan van de Ven
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=20060223132954.GA16074@elte.hu \
--to=mingo@elte.hu \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=arjan@intel.linux.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).