The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Jesse Barnes <jbarnes@engr.sgi.com>
To: Paul Mackerras <paulus@samba.org>
Cc: Keir Fraser <Keir.Fraser@cl.cam.ac.uk>,
	linux-kernel@vger.kernel.org, akpm@osdl.org, riel@redhat.com,
	kurt@garloff.de, Ian.Pratt@cl.cam.ac.uk,
	Christian.Limpach@cl.cam.ac.uk
Subject: Re: [PATCH] Xen/i386 cleanups - AGP bus/phys cleanups
Date: Wed, 16 Mar 2005 14:06:01 -0800	[thread overview]
Message-ID: <200503161406.01788.jbarnes@engr.sgi.com> (raw)
In-Reply-To: <16952.41973.751326.592933@cargo.ozlabs.ibm.com>

On Wednesday, March 16, 2005 1:24 pm, Paul Mackerras wrote:
> Keir Fraser writes:
> > This patch cleans up AGP driver treatment of bus/device memory. Every
> > use of virt_to_phys/phys_to_virt should properly be converting between
> > virtual and bus addresses: this distinction really matters for the Xen
> > hypervisor.
>
> I think you are misunderstanding the distinction between physical
> addresses and bus addresses.  Specifically, it seems wrong to me to be
> putting bus addresses into the GATT rather than physical addresses.
>
> For example, on my G5, physical addresses are 36 bits (in the
> hardware) but bus addresses are only 32 bits.  Using bus addresses in
> the GATT would mean that I couldn't put any memory above the 4GB point
> into the GATT.
>
> The distinction is that physical addresses are what are used to access
> physical memory, whereas bus addresses are what appears on some
> external bus (usually PCI).  The GATT sits between an external (AGP)
> bus and memory, so while the GATT is indexed using bus addresses, its
> entries contain physical addresses.  So in fact virt_to_phys is the
> correct thing to use to calculate values to put in GATT entries.

Thanks for the explanation Paul, now the code actually makes sense.  
Converting to the DMA mapping API doesn't make sense at all in this context 
then, since we're basically programming the GATT (an IOMMU type table) with 
physical addresses.  Ken, are you sure you need to make these changes at all?  
Does Xen break w/o them?

Jesse

  reply	other threads:[~2005-03-16 22:09 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-03-16 11:48 [PATCH] Xen/i386 cleanups - AGP bus/phys cleanups Keir Fraser
2005-03-16 14:31 ` Christoph Hellwig
2005-03-16 14:58   ` Keir Fraser
2005-03-16 15:01   ` Rik van Riel
2005-03-16 18:10     ` Christoph Hellwig
2005-03-16 18:35       ` Keir Fraser
2005-03-16 18:42         ` Jesse Barnes
2005-03-16 19:08           ` Keir Fraser
2005-03-16 19:06         ` Christoph Hellwig
2005-03-16 19:11           ` Keir Fraser
2005-03-16 17:40   ` Alan Cox
2005-03-16 17:54 ` Jesse Barnes
2005-03-16 21:24 ` Paul Mackerras
2005-03-16 22:06   ` Jesse Barnes [this message]
2005-03-16 23:55     ` Rik van Riel
2005-03-17  0:39       ` Paul Mackerras
2005-03-17  1:05         ` Tupshin Harper
2005-03-17  3:44         ` Rik van Riel
2005-03-17  4:42       ` Christoph Hellwig
2005-03-17  4:58         ` Rik van Riel
2005-03-17  9:16     ` Keir Fraser
2005-03-17  9:34       ` Paul Mackerras
2005-03-17 10:56         ` Keir Fraser
2005-03-19 10:07           ` Eric W. Biederman
2005-03-19 10:56             ` Christian Limpach
2005-03-19 13:01               ` Keir Fraser
2005-03-17 13:53         ` Alan Cox
2005-03-18  0:16           ` Paul Mackerras
2005-03-18  4:23             ` Rik van Riel
2005-03-18  9:05             ` Keir Fraser

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=200503161406.01788.jbarnes@engr.sgi.com \
    --to=jbarnes@engr.sgi.com \
    --cc=Christian.Limpach@cl.cam.ac.uk \
    --cc=Ian.Pratt@cl.cam.ac.uk \
    --cc=Keir.Fraser@cl.cam.ac.uk \
    --cc=akpm@osdl.org \
    --cc=kurt@garloff.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=riel@redhat.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