linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Scott Wood <scottwood@freescale.com>
To: Jia Hongtao-B38951 <B38951@freescale.com>
Cc: Wood Scott-B07421 <B07421@freescale.com>,
	"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
	Stuart Yoder <b08248@gmail.com>
Subject: Re: [PATCH V4] powerpc/85xx: Add machine check handler to fix PCIe erratum on mpc85xx
Date: Tue, 5 Mar 2013 12:47:42 -0600	[thread overview]
Message-ID: <1362509262.25308.0@snotra> (raw)
In-Reply-To: <412C8208B4A0464FA894C5F0C278CD5D01BE952E@039-SN1MPN1-002.039d.mgd.msft.net> (from B38951@freescale.com on Tue Mar  5 04:12:30 2013)

On 03/05/2013 04:12:30 AM, Jia Hongtao-B38951 wrote:
>=20
>=20
> > -----Original Message-----
> > From: Wood Scott-B07421
> > Sent: Tuesday, March 05, 2013 7:46 AM
> > To: Stuart Yoder
> > Cc: Jia Hongtao-B38951; linuxppc-dev@lists.ozlabs.org; Kumar Gala
> > Subject: Re: [PATCH V4] powerpc/85xx: Add machine check handler to =20
> fix
> > PCIe erratum on mpc85xx
> >
> > On 03/04/2013 10:16:10 AM, Stuart Yoder wrote:
> > > On Mon, Mar 4, 2013 at 2:40 AM, Jia Hongtao <B38951@freescale.com>
> > > wrote:
> > > > A PCIe erratum of mpc85xx may causes a core hang when a link of =20
> PCIe
> > > > goes down. when the link goes down, Non-posted transactions =20
> issued
> > > > via the ATMU requiring completion result in an instruction =20
> stall.
> > > > At the same time a machine-check exception is generated to the =20
> core
> > > > to allow further processing by the handler. We implements the
> > > handler
> > > > which skips the instruction caused the stall.
> > >
> > > Can you explain at a high level how just skipping an instruction
> > > solves
> > > anything?   If you just skip a load/store and continue like =20
> nothing is
> > > wrong, isn't your system possibly in a really bad state.
> >
> > If the instruction was a load, we probably at least want to fill the
> > destination register with 0xffffffff or similar.
>=20
> You discuss this with Liu Shuo about a year ago.
> here is the log:
>=20
> "
> On 02/01/2012 02:18 AM, shuo.liu@freescale.com wrote:
> > v3 : Skip the instruction only. Don't access the user space memory =20
> in
> >      mechine check.
>=20
> It may be the least bad option for now, but be aware that there's a
> small chance that this will cause a leak of sensitive information =20
> (such
> as a piece of a crypto key that happened to be sitting in the register
> to be loaded into).

Yes, that's (one reason) why you'd want to fill in a known value.  Note =20
the "for now". :-)

-Scott=

  reply	other threads:[~2013-03-05 18:47 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-04  8:40 [PATCH V4] powerpc/85xx: Add machine check handler to fix PCIe erratum on mpc85xx Jia Hongtao
2013-03-04 16:16 ` Stuart Yoder
2013-03-04 23:45   ` Scott Wood
2013-03-05 10:12     ` Jia Hongtao-B38951
2013-03-05 18:47       ` Scott Wood [this message]
2013-03-06  8:28         ` Jia Hongtao-B38951
2013-03-06 10:24           ` David Laight
2013-03-07  8:06             ` Jia Hongtao-B38951
2013-03-07 10:04               ` David Laight
2013-03-07 16:37               ` Scott Wood
2013-03-08  8:01                 ` Jia Hongtao-B38951
2013-03-09  0:49                   ` Scott Wood
2013-03-12  7:40                     ` Jia Hongtao-B38951
2013-03-12  9:47                       ` David Laight
2013-03-12 21:24                       ` Scott Wood
2013-03-13  9:40                         ` David Laight
2013-03-13 16:37                           ` Scott Wood
2013-03-15  2:47                             ` Jia Hongtao-B38951
2013-03-15 16:34                               ` Scott Wood
2013-03-29  8:03                                 ` Jia Hongtao-B38951
2013-03-29 16:33                                   ` Scott Wood
2013-04-02  9:28                                     ` Jia Hongtao-B38951
2013-04-02 19:46                                       ` Scott Wood
2013-03-04 17:15 ` David Laight
2013-03-05 10:12   ` Jia Hongtao-B38951

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=1362509262.25308.0@snotra \
    --to=scottwood@freescale.com \
    --cc=B07421@freescale.com \
    --cc=B38951@freescale.com \
    --cc=b08248@gmail.com \
    --cc=linuxppc-dev@lists.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).