public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: Chris Wright <chrisw@sous-sol.org>
Cc: Neil Horman <nhorman@tuxdriver.com>,
	iommu@lists.linux-foundation.org, joerg.roedel@amd.com,
	hbabu@us.ibm.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] amd iommu: force flush of iommu prior during shutdown
Date: Wed, 31 Mar 2010 22:44:21 -0400	[thread overview]
Message-ID: <20100401024421.GA5877@redhat.com> (raw)
In-Reply-To: <20100331212535.GR29241@sequoia.sous-sol.org>

On Wed, Mar 31, 2010 at 02:25:35PM -0700, Chris Wright wrote:
> * Neil Horman (nhorman@tuxdriver.com) wrote:
> > Flush iommu during shutdown
> > 
> > When using an iommu, its possible, if a kdump kernel boot follows a primary
> > kernel crash, that dma operations might still be in flight from the previous
> > kernel during the kdump kernel boot.  This can lead to memory corruption,
> > crashes, and other erroneous behavior, specifically I've seen it manifest during
> > a kdump boot as endless iommu error log entries of the form:
> > AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.1 domain=0x000d
> > address=0x000000000245a0c0 flags=0x0070]
> 
> We've already fixed this problem once before, so some code shift must
> have brought it back.  Personally, I prefer to do this on the bringup
> path than the teardown path.  Besides keeping the teardown path as
> simple as possible (goal is to get to kdump kernel asap), there's also
> reason to competely flush on startup in genernal in case BIOS has done
> anything unsavory.

Can we flush domains (all the I/O TLBs assciated with each domain), during
initialization? I think all the domain data built by previous kernel will
be lost and new kernel will have no idea about. 

Thanks
Vivek

  parent reply	other threads:[~2010-04-01  2:44 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-31 15:24 [PATCH] amd iommu: force flush of iommu prior during shutdown Neil Horman
2010-03-31 15:54 ` Vivek Goyal
2010-03-31 18:28   ` Neil Horman
2010-03-31 18:57     ` Eric W. Biederman
2010-03-31 19:18       ` Neil Horman
2010-03-31 19:51         ` Eric W. Biederman
2010-03-31 20:27           ` Neil Horman
2010-04-01  4:04             ` Eric W. Biederman
2010-04-01 12:49               ` Neil Horman
2010-04-01 14:29             ` Joerg Roedel
2010-04-01 14:47               ` Neil Horman
2010-04-01 15:56                 ` Joerg Roedel
2010-04-01 17:11                   ` Neil Horman
2010-04-01 20:14                     ` Joerg Roedel
2010-04-02  0:00                       ` Neil Horman
2010-04-02  0:30                         ` Chris Wright
2010-04-02  1:23                           ` [PATCH 1/2] x86/amd-iommu: enable iommu before attaching devices Chris Wright
2010-04-02  1:31                             ` [PATCH 2/2] x86/amd-iommu: warn when issuing command to uninitiailed cmd buffer Chris Wright
2010-04-02  1:35                             ` [PATCH 1/2] x86/amd-iommu: enable iommu before attaching devices Neil Horman
2010-04-02  1:38                               ` Chris Wright
2010-04-02  9:11                             ` Joerg Roedel
2010-04-02 23:59                               ` Chris Wright
2010-04-02 15:59                             ` Vivek Goyal
2010-04-02 22:38                               ` Chris Wright
2010-04-02 22:55                                 ` Eric W. Biederman
2010-04-02 23:57                                   ` Chris Wright
2010-04-03 17:38                               ` Joerg Roedel
2010-04-05 14:17                                 ` Vivek Goyal
2010-04-05 14:32                                   ` Joerg Roedel
2010-04-05 15:34                             ` Neil Horman
2010-03-31 18:43   ` [PATCH] amd iommu: force flush of iommu prior during shutdown Eric W. Biederman
2010-03-31 21:25 ` Chris Wright
2010-04-01  1:13   ` Neil Horman
2010-04-01  1:39     ` Chris Wright
2010-04-01  2:24     ` Vivek Goyal
2010-04-01 12:53       ` Neil Horman
2010-04-01 15:02         ` Vivek Goyal
2010-04-01 15:13           ` Neil Horman
2010-04-01  2:44   ` Vivek Goyal [this message]
2010-04-01  7:10     ` Chris Wright
2010-04-01 12:56       ` Neil Horman

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=20100401024421.GA5877@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=chrisw@sous-sol.org \
    --cc=hbabu@us.ibm.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joerg.roedel@amd.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nhorman@tuxdriver.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox