From: Jamie Lokier <jamie@shareable.org>
To: "David S. Miller" <davem@redhat.com>
Cc: mfedyk@matchmail.com, lm@bitmover.com, linux-kernel@vger.kernel.org
Subject: Re: x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this
Date: Mon, 1 Sep 2003 07:42:31 +0100 [thread overview]
Message-ID: <20030901064231.GJ748@mail.jlokier.co.uk> (raw)
In-Reply-To: <20030831223102.3affcb34.davem@redhat.com>
David S. Miller wrote:
> On Sun, 31 Aug 2003 23:49:37 +0100
> Jamie Lokier <jamie@shareable.org> wrote:
>
> > It uses POSIX shared memory and (necessarily) MAP_SHARED, which
> > doesn't constrain the mapping alignment.
>
> That's wrong. If a platform needs to, it should properly
> align the mapping when MAP_SHARED is used on a file.
>
> If you look in arch/sparc64/kernel/sys_sparc.c, you'll see
> that when we're mmap()'ing a file and MAP_SHARED is specified,
> we align things to SHMLBA.
Then you have a bug in the Sparc code. It looks like it should return
-EINVAL when a misaligned mapping is used with MAP_FIXED|MAP_SHARED,
but the test program is clearly getting mappings that aren't aligned
to SHMLBA.
> If userspace purposefully violates this alignment attempt,
> then it's at it's own peril to keep the mappings coherent,
> there is simply nothing the kernel should be doing to help
> out that case.
I understand that userspace needs to keep it coherent, or map to a
multiple of SHMLBA. I don't mind whether the kernel constrains the
mapping address or not, with a slight preference for userspace
flexibility.
Thus I have three Sparc-specific questions:
1. How does userspace find out the value of SHMLBA?
On Sparc, it is not a compile-time constant.
2. Is flushing part of the data cache something I can do from
userspace? (I'll figure out the exact machine instructions
myself if I need to do this, but it'd be nice to know if
it's possible before I have a go).
3. Is there a kernel bug on Sparc, because the test program
is either getting mappings that aren't aligned to run time
SHMLBA, or the kernel's run time SHMLBA value is not correct.
Thanks,
-- Jamie
next prev parent reply other threads:[~2003-09-01 6:42 UTC|newest]
Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-29 5:35 x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this Jamie Lokier
2003-08-29 10:03 ` J.A. Magallon
2003-08-29 10:36 ` Alan Cox
2003-09-01 4:49 ` Jamie Lokier
2003-08-29 10:04 ` Sergey S. Kostyliov
2003-08-29 10:15 ` J.A. Magallon
2003-08-29 10:21 ` J.A. Magallon
2003-08-29 10:34 ` CaT
2003-08-29 10:37 ` CaT
2003-08-29 10:49 ` Mikael Pettersson
2003-08-29 11:41 ` Gianni Tedesco
2003-08-29 11:51 ` James Morris
2003-08-29 15:41 ` Larry McVoy
2003-08-29 23:05 ` Mike Fedyk
2003-08-31 5:10 ` David S. Miller
2003-08-31 22:49 ` Jamie Lokier
2003-09-01 5:31 ` David S. Miller
2003-09-01 6:42 ` Jamie Lokier [this message]
2003-09-01 7:06 ` David S. Miller
2003-09-01 8:29 ` Jamie Lokier
2003-09-01 9:02 ` David S. Miller
2003-09-01 10:04 ` Jamie Lokier
2003-09-01 10:02 ` David S. Miller
2003-09-03 17:36 ` bill davidsen
2003-09-04 22:50 ` Jamie Lokier
2003-09-01 5:44 ` Jamie Lokier
2003-09-01 14:43 ` Larry McVoy
2003-09-01 16:33 ` Jamie Lokier
2003-09-01 16:58 ` Larry McVoy
2003-09-02 20:29 ` Jamie Lokier
2003-08-29 15:47 ` Herbert Poetzl
2003-08-30 1:48 ` Stuart Longland
2003-08-29 16:27 ` Geert Uytterhoeven
2003-09-01 5:58 ` Jamie Lokier
2003-09-01 8:34 ` Geert Uytterhoeven
2003-09-01 9:09 ` Kars de Jong
2003-09-01 10:08 ` Jamie Lokier
2003-09-01 11:13 ` Roman Zippel
2003-09-02 20:42 ` Kars de Jong
2003-09-02 21:39 ` Jamie Lokier
2003-09-03 7:59 ` Geert Uytterhoeven
2003-09-03 9:13 ` Jamie Lokier
2003-09-03 9:26 ` Geert Uytterhoeven
2003-09-03 12:17 ` Roman Zippel
2003-09-03 12:36 ` Geert Uytterhoeven
2003-09-03 13:29 ` Jamie Lokier
2003-09-03 16:07 ` Nagendra Singh Tomar
2003-09-04 5:03 ` Davide Libenzi
2003-09-03 18:03 ` Nagendra Singh Tomar
2003-09-04 6:38 ` Davide Libenzi
2003-09-04 11:19 ` Alan Cox
2003-09-05 21:24 ` Pavel Machek
2003-09-06 23:09 ` Jamie Lokier
2003-09-07 13:10 ` Pavel Machek
2003-09-07 13:35 ` Jamie Lokier
2003-09-07 13:40 ` Pavel Machek
2003-09-07 13:53 ` Jamie Lokier
2003-09-07 17:56 ` Alan Cox
2003-09-03 12:13 ` Jan-Benedict Glaw
2003-09-01 10:35 ` Sam Creasey
2003-09-01 10:48 ` Jamie Lokier
2003-09-01 12:23 ` Sam Creasey
2003-09-03 8:00 ` Kars de Jong
2003-09-03 8:05 ` Geert Uytterhoeven
2003-09-03 9:24 ` Kars de Jong
2003-08-29 16:31 ` Brian Jackson
2003-08-29 17:39 ` Matt Porter
2003-09-01 6:00 ` Jamie Lokier
2003-09-01 11:17 ` Alan Cox
2003-09-01 17:22 ` Roland Dreier
2003-09-02 2:16 ` Matt Porter
2003-09-02 5:40 ` Jamie Lokier
2003-08-29 19:37 ` Thorsten Kranzkowski
2003-08-29 20:03 ` Sean Neakums
2003-08-29 20:14 ` Iulian Musat
2003-08-29 20:26 ` Paul J.Y. Lahaie
2003-09-01 8:15 ` Russell King
2003-09-01 10:12 ` Jamie Lokier
2003-09-01 11:30 ` Geert Uytterhoeven
2003-09-01 14:17 ` Russell King
2003-09-01 14:51 ` Russell King
2003-09-01 19:09 ` Guennadi Liakhovetski
2003-09-01 16:52 ` Jamie Lokier
2003-09-01 17:11 ` Russell King
2003-09-02 5:34 ` Jamie Lokier
2003-09-02 8:15 ` Russell King
2003-09-02 11:57 ` Jamie Lokier
2003-09-02 18:52 ` Russell King
2003-09-02 23:59 ` Larry McVoy
2003-09-03 7:31 ` Russell King
2003-09-03 7:41 ` Jamie Lokier
2003-09-03 18:05 ` Russell King
2003-09-04 22:20 ` Jamie Lokier
2003-09-04 17:37 ` Maciej W. Rozycki
2003-08-29 22:35 ` Kenneth Johansson
2003-08-29 23:47 ` Kurt Wall
2003-09-01 0:24 ` Paul Mundt
2003-09-01 0:37 ` Jamie Lokier
2003-09-01 1:00 ` Paul Mundt
2003-09-01 1:58 ` Jamie Lokier
2003-09-01 1:13 ` dean gaudet
2003-09-01 4:29 ` Jamie Lokier
2003-09-02 10:08 ` Jan Rychter
[not found] <20030829053510.GA12663@mail.jlokier.co.uk.suse.lists.linux.kernel>
2003-08-29 11:08 ` Andi Kleen
2003-08-29 11:17 ` Russell King
2003-09-01 5:03 ` Jamie Lokier
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=20030901064231.GJ748@mail.jlokier.co.uk \
--to=jamie@shareable.org \
--cc=davem@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lm@bitmover.com \
--cc=mfedyk@matchmail.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;
as well as URLs for NNTP newsgroup(s).