From: "David S. Miller" <davem@redhat.com>
To: manfred@colorfullife.com, masp0008@stud.uni-saarland.de
Cc: drobbins@gentoo.org, linux-kernel@vger.kernel.org
Subject: Re: Athlon/AGP issue update
Date: Wed, 23 Jan 2002 03:44:11 -0800 (PST) [thread overview]
Message-ID: <20020123.034411.71089598.davem@redhat.com> (raw)
In-Reply-To: <3C4E9291.8DA0BD7F@stud.uni-saarland.de>
In-Reply-To: <3C4E9291.8DA0BD7F@stud.uni-saarland.de>
From: Studierende der Universitaet des Saarlandes <masp0008@stud.uni-saarland.de>
Date: Wed, 23 Jan 2002 10:38:09 +0000
Then "nopentium" only works by chance: I assume that speculative
operations do not walk the page tables, thus the probability that a
valid TLB entry is found for the GART mapped page is slim. But if there
is an entry, then the corruption would still occur.
This isn't true. The speculative store won't get data into the
cache if there is a TLB miss.
4MB pages map the GART pages and "other stuff", ie. memory used by
other subsystems, user pages and whatever else. This is the only
way the bug can be thus triggered for kernel mappings, which is why
turning off 4MB pages fixes this part.
The only unresolved bit is the fact that we map these GART pages
cacheable into user space. That ought to cause the problem too.
next prev parent reply other threads:[~2002-01-23 11:45 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-01-23 10:38 Athlon/AGP issue update Studierende der Universitaet des Saarlandes
2002-01-23 11:44 ` David S. Miller [this message]
2002-01-23 12:32 ` Momchil Velikov
2002-01-23 12:34 ` David S. Miller
2002-01-23 12:41 ` Momchil Velikov
2002-01-23 14:50 ` Manfred Spraul
2002-01-23 11:44 ` David Woodhouse
2002-01-23 11:49 ` David S. Miller
-- strict thread matches above, loose matches on Subject: below --
2002-01-23 9:52 Daniel Robbins
2002-01-23 10:18 ` David S. Miller
2002-01-23 2:46 ` benh
2002-01-23 14:08 ` David S. Miller
2002-01-23 15:47 ` benh
2002-01-25 18:34 ` Val Henson
2002-01-26 0:20 ` Benjamin Herrenschmidt
2002-01-27 19:22 ` Val Henson
2002-01-27 19:32 ` Benjamin Herrenschmidt
2002-01-23 16:31 ` Albert D. Cahalan
2002-01-23 16:57 ` Daniel Robbins
2002-01-23 17:14 ` benh
2002-01-23 23:14 ` Albert D. Cahalan
2002-01-25 18:17 ` Val Henson
2002-01-23 19:20 ` Oliver Neukum
[not found] ` <200201231010.g0NAAuE05886@Port.imtp.ilyichevsk.odessa.ua>
2002-01-23 10:24 ` David S. Miller
2002-01-23 10:31 ` Rik van Riel
2002-01-23 11:39 ` David S. Miller
2002-01-23 11:39 ` William Lee Irwin III
2002-01-23 11:47 ` David S. Miller
2002-01-23 17:09 ` Albert D. Cahalan
2002-01-23 18:38 ` David S. Miller
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=20020123.034411.71089598.davem@redhat.com \
--to=davem@redhat.com \
--cc=drobbins@gentoo.org \
--cc=linux-kernel@vger.kernel.org \
--cc=manfred@colorfullife.com \
--cc=masp0008@stud.uni-saarland.de \
/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