All of lore.kernel.org
 help / color / mirror / Atom feed
From: Don Zickus <dzickus@redhat.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Andi Kleen <andi@firstfloor.org>,
	Huang Ying <ying.huang@intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [RFC 5/6] x86, NMI, Add support to notify hardware error with unknown NMI
Date: Tue, 14 Sep 2010 09:45:14 -0400	[thread overview]
Message-ID: <20100914134514.GJ26290@redhat.com> (raw)
In-Reply-To: <20100914122131.GF12425@elte.hu>

On Tue, Sep 14, 2010 at 02:21:31PM +0200, Ingo Molnar wrote:
> 
> * Don Zickus <dzickus@redhat.com> wrote:
> 
> > > > > At least on PCI-E it may be enough to simply dump all recent AER 
> > > > > data.
> > > > 
> > > > This assumes AER is supported on the bridge?  Which for newer 
> > > > chips is probably true, but I wasn't sure about older ones.
> > > 
> > > Today's servers should usually have AER at least.
> > > 
> > > For old systems you only can get the few bits in PCI space.
> > > 
> > > > How would I dump AER data from within the kernel?
> > > 
> > > Would need a buffer that is dumped for past events and reading the 
> > > registers for not yet reported. Right now some infrastructure is 
> > > needed.
> > 
> > Oh ok.
> 
> The proper approach would be not to add hacks to the NMI code but to 
> implement southbridge drivers - which would also have NMI callbacks. 
> These are unchartered waters, but variance in that space is reducing 
> systematically so it would be worth a shot.

Interesting.  I think the only southbridge I see regularly are Intel, AMD
and Nvidia (with Nvidia being more problematic than others).
Unfortunately, getting specs for Nvidia is very difficult.

But that might help narrow down where the NMI problem is.

Cheers,
Don

> 
> Thanks,
> 
> 	Ingo

  reply	other threads:[~2010-09-14 13:45 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-10  2:51 [RFC 1/6] x86, NMI, Add symbol definition for NMI magic constants Huang Ying
2010-09-10  2:51 ` [RFC 2/6] x86, NMI, Add touch_nmi_watchdog to io_check_error delay Huang Ying
2010-09-10  2:51 ` [RFC 3/6] x86, NMI, Rename memory parity error to PCI SERR error Huang Ying
2010-09-13  1:02   ` Robert Richter
2010-09-13  2:02     ` Huang Ying
2010-09-16  8:18       ` Robert Richter
2010-09-17  0:08         ` Huang Ying
2010-09-17  9:14           ` Robert Richter
2010-09-19  0:20             ` Huang Ying
2010-09-20  8:00               ` Robert Richter
2010-09-20 12:59                 ` Borislav Petkov
2010-09-21  0:22                   ` Huang Ying
2010-09-21  6:37                     ` Borislav Petkov
2010-09-21 14:08                       ` Doug Thompson
2010-09-21 23:04   ` Maciej W. Rozycki
2010-09-23  5:37     ` huang ying
2010-09-29  0:26       ` Maciej W. Rozycki
2010-09-10  2:51 ` [RFC 4/6] x86, NMI, Rewrite NMI handler Huang Ying
2010-09-10 15:56   ` Don Zickus
2010-09-10 16:03     ` Andi Kleen
2010-09-10 18:29       ` Don Zickus
2010-09-13  2:09         ` Huang Ying
2010-09-13 14:04           ` Don Zickus
2010-09-14  5:12             ` Huang Ying
2010-09-14 13:37               ` Don Zickus
2010-09-13  1:16   ` Robert Richter
2010-09-10  2:51 ` [RFC 5/6] x86, NMI, Add support to notify hardware error with unknown NMI Huang Ying
2010-09-10 16:02   ` Don Zickus
2010-09-10 16:19     ` Andi Kleen
2010-09-10 18:40       ` Don Zickus
2010-09-13  2:19         ` Huang Ying
2010-09-13 14:11           ` Don Zickus
2010-09-13 15:24             ` Andi Kleen
2010-09-13 15:47               ` Don Zickus
2010-09-13 16:57                 ` Andi Kleen
2010-09-13 17:53                   ` Don Zickus
2010-09-13 18:07                     ` Andi Kleen
2010-09-13 18:23                       ` Don Zickus
2010-09-13 18:36                         ` Andi Kleen
2010-09-13 19:36                           ` Don Zickus
2010-09-13 20:49                             ` Andi Kleen
2010-09-13 21:25                               ` Valdis.Kletnieks
2010-09-14  7:48                                 ` Andi Kleen
2010-09-14 17:54                                   ` Valdis.Kletnieks
2010-09-14 12:21                             ` Ingo Molnar
2010-09-14 13:45                               ` Don Zickus [this message]
2010-09-14 19:34                               ` Cyrill Gorcunov
2010-09-15  9:29                                 ` Ingo Molnar
2010-09-10  2:51 ` [RFC 6/6] x86, NMI, Remove do_nmi_callback logic Huang Ying
2010-09-10 16:13   ` Don Zickus
2010-09-13  2:27     ` Huang Ying
2010-09-13  6:24       ` Ingo Molnar
2010-09-10 20:37 ` [RFC 1/6] x86, NMI, Add symbol definition for NMI magic constants Peter Zijlstra
2010-09-10 22:58   ` H. Peter Anvin
2010-09-11  8:50   ` Andi Kleen
2010-09-13  1:30     ` Robert Richter
2010-09-21 21:48 ` Don Zickus
2010-09-21 22:19   ` Andi Kleen
2010-09-22 16:07     ` Don Zickus
2010-09-23  9:29       ` huang ying
2010-09-23 14:16         ` Don Zickus
2010-09-24 11:50           ` huang ying
2010-09-24 14:29             ` Don Zickus
2010-09-23  9:51   ` huang ying
2010-09-14 14:31 [RFC 5/6] x86, NMI, Add support to notify hardware error with unknown NMI Andi Kleen
2010-09-14 15:17 ` Don Zickus
2010-09-14 17:40   ` Andi Kleen
2010-09-14 17:48 ` Ingo Molnar
2010-09-15  5:06   ` Huang Ying

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=20100914134514.GJ26290@redhat.com \
    --to=dzickus@redhat.com \
    --cc=andi@firstfloor.org \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=ying.huang@intel.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.