Re: Possible dcache BUG

From: Linus Torvalds (torvalds_at_osdl.org)
Date: 08/06/04

  • Next message: Jeff Garzik: "Re: [PATCH] (IDE) restore access to low order LBA following error" 
    Date:	Fri, 6 Aug 2004 09:58:35 -0700 (PDT)
To: Gene Heskett <gene.heskett@verizon.net>

    On Fri, 6 Aug 2004, Gene Heskett wrote:
    >
    > Linus, Andrew, should I apply this patch too at the next remake?

    Might be worth it, but it's more important to see any oops at all, or lack
    of oopses..

    > FWIW, I'm still up (20:38) this morning, and showing plenty (127+
    > megs) of free memory. No crash, no odd log (other than samba
    > squawking about some option thats been changed & I haven't fixed the
    > smb.conf) so far.
    >
    > I'm beginning to like this test patch, Linus, thanks :)

    If the only thing you have done is add the list_del_init() debugging
    patch, then the only thing that has changed is really the access patterns
    to uncached memory.

    The original list_del_init() tries to only do a few single _writes_ to the
    dentries around it. The added debugging will do _reads_ (and thus bring it
    into the cache) of the dentry pointers of the dentries around it.

    If that change makes a real difference, I really only see two
    possibilities:
     - there really is a prefetch bug (or possibly, there's a bug in our
       prefetch fixup code, and the known prefetch bug just triggers the
       problem indirectly)
     - it just changes the timing enough that whatever bug you hit went away.

    Now, Chris Shoemaker reported dentry problems on a intel CPU and said that
    wli had seen something too, but I'm wondering whether Chris and wli might
    have been seeing the knfsd/xfs-related dentry bug that I found yesterday.
    So I think the prefetch theory is still alive, but we should check with
    Chris. Chris?

                    Linus
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Jeff Garzik: "Re: [PATCH] (IDE) restore access to low order LBA following error"

    Relevant Pages

    • Re: 2.6.25-rc6: BUG: unable to handle kernel NULL pointer dereference
      ... A dropped workaround for the prefetch bug in early X2s and ... Opterons. ... I could not repoduce the bug. ... I've applied your patch to -rc7 and no BUG so far:) ...
      (Linux-Kernel)
    • Weekly Python Patch/Bug Summary
      ... Patch / Bug Summary ... http://python.org/sf/606098 closed by rhettinger ... http://python.org/sf/1088716 closed by loewis ...
      (comp.lang.python)
    • [Full-Disclosure] RE: [kinda-but-not-really-Full-Disclosure-so-we-feel-warm-and-fuzzy] Re: <to va
      ... Because it must be realised that as soon as a patch and or advisory is ... there are global teams of people working to discover and exploit said bug. ... quiet and MS just released patches for 'undisclosed' problems... ... > engineer a ms patch to find the changed code and produce a working ...
      (Full-Disclosure)
    • RE: Mailslot bug (MS06-035) vs non-Mailslot bug (CVE-2006-3942)
      ... made patch for SRV.SYS. ... vulnerabilities that everyone is so afraid to talk about. ... the mailslot bug, and they didn't have any technical details to turn to, ... So keep on truckin Core Security, Michal Zalewski, and even ...
      (Bugtraq)
    • Re: Cant take skilled talent?
      ... least playing an easier version of the game than everyone else has. ... mind changing or removing the patch if TB emailed me about it. ... -fixing skilled bug is good ... The patch simply stops the monsters from growing too powerful compared to the ...
      (rec.games.roguelike.adom)