From: Olof Johansson <olof@lixom•net>
To: Becky Bruce <becky.bruce@freescale•com>
Cc: linuxppc-dev@ozlabs•org
Subject: Re: [PATCH] Avoid unpaired stwcx. on some processors
Date: Fri, 9 Nov 2007 17:19:27 -0600 [thread overview]
Message-ID: <20071109231927.GA19415@lixom.net> (raw)
In-Reply-To: <11946460863124-git-send-email-becky.bruce@freescale.com>
On Fri, Nov 09, 2007 at 04:08:06PM -0600, Becky Bruce wrote:
> The context switch code in the kernel issues a dummy stwcx. to clear the
> reservation, as recommended by the architecture. However, some processors
> can have issues if this stwcx to address A occurs while the reservation
> is already held to a different address B. To avoid this problem, the dummy
> stwcx. needs to be paired with a dummy lwarx to the same address.
>
> This patch adds the dummy lwarx, and creates a cpu feature bit to indicate
> which cpus are affected. Tested on mpc8641_hpcn_defconfig in arch/powerpc;
> build tested in arch/ppc.
You're still exposed even with this patch. The stwcx is there to protect
from the cases where process 1 does lwarx and get context switched
out to process 2 that by pure random chance does a stwcx. to the same
reservation granule and succeeds, in spite of not having done the lwarx
(on this side of the context switch).
In exactly that case, process 2 will instead of doing a store to a
reservation it didn't take on it's own, do a dangling stwcx, which is
your erratum. Right?
Seems like a "better" (but still ugly) workaround would be to create a
_new_ reservation to a RA that's unavailable to any userspace process,
so that they could never do a successful store to it. That way you would
have stray reservations, but never dangling stwcx:es. No?
-Olof
next prev parent reply other threads:[~2007-11-09 23:19 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-09 22:08 [PATCH] Avoid unpaired stwcx. on some processors Becky Bruce
2007-11-09 23:19 ` Olof Johansson [this message]
2007-11-09 23:52 ` Becky Bruce
2007-11-10 0:18 ` Olof Johansson
2007-11-11 4:46 ` Benjamin Herrenschmidt
2007-11-11 7:14 ` Olof Johansson
-- strict thread matches above, loose matches on Subject: below --
2007-11-09 22:17 Becky Bruce
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=20071109231927.GA19415@lixom.net \
--to=olof@lixom$(echo .)net \
--cc=becky.bruce@freescale$(echo .)com \
--cc=linuxppc-dev@ozlabs$(echo .)org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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