linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Eugene Surovegin <ebs@ebshome.net>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org, Kumar Gala <kumar.gala@freescale.com>
Subject: Re: Unsafe pte_update() in do_page_fault() (4xx and Book-E)
Date: Thu, 2 Mar 2006 19:55:12 -0800	[thread overview]
Message-ID: <20060303035512.GB19115@gate.ebshome.net> (raw)
In-Reply-To: <1141357383.3888.19.camel@localhost.localdomain>

On Fri, Mar 03, 2006 at 02:43:02PM +1100, Benjamin Herrenschmidt wrote:
> 
> > If this happens, pte_update() sets _PAGE_HWEXEC bit in just cleared 
> > PTE. Sometime later, another page fault happens for this page, but 
> > because of that set bit, pte_none() test in handle_pte_fault() fails, 
> > and we continue along the wrong path, thinking that this PTE was 
> > swapped out to the swap file, and this triggers swap_dup error I 
> > mentioned at the beginning.
> 
> Can we preempt at that point ? As tehre is no SMP 4xx that I know of
> preempt would be the only cause for such a race ...

Yes, as I mentioned in the original post, I'm running preempt enabled 
kernel.

-- 
Eugene

  reply	other threads:[~2006-03-03  3:55 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-03-02 20:26 Unsafe pte_update() in do_page_fault() (4xx and Book-E) Eugene Surovegin
2006-03-03  3:43 ` Benjamin Herrenschmidt
2006-03-03  3:55   ` Eugene Surovegin [this message]
2006-03-28  7:55 ` [PATCH] lock PTE before updating it in 440/BookE page fault handler Eugene Surovegin
2006-03-28 11:10   ` Paul Mackerras
2006-03-28 18:13     ` Eugene Surovegin

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=20060303035512.GB19115@gate.ebshome.net \
    --to=ebs@ebshome.net \
    --cc=benh@kernel.crashing.org \
    --cc=kumar.gala@freescale.com \
    --cc=linuxppc-dev@ozlabs.org \
    /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).