Linux MIPS Architecture development
 help / color / mirror / Atom feed
From: Hartvig Ekner <hartvige@mips.com>
To: alan@lxorguk.ukuu.org.uk (Alan Cox)
Cc: carstenl@mips.com (Carsten Langgaard),
	dom@algor.co.uk (Dominic Sweetman),
	ralf@linux-mips.org (Ralf Baechle),
	linux-mips@linux-mips.org
Subject: Re: Promblem with PREF (prefetching) in memcpy
Date: Fri, 4 Oct 2002 15:07:02 +0200 (MEST)	[thread overview]
Message-ID: <200210041307.g94D72G02838@copfs01.mips.com> (raw)
In-Reply-To: <1033736983.31861.26.camel@irongate.swansea.linux.org.uk> from "Alan Cox" at Oct 04, 2002 02:09:43 PM

Yes, I think that must be the safest solution.

Any kernel routine which uses PREF instructions (but actually also user
space code as Ralf's example pointed out), must guarantee that it does
not issue prefetches to addresses which it is not specifically being
asked to mess around with. 

The other solutions seem too fragile, and will break at some point.

/Hartvig

Alan Cox writes:
> 
> On Fri, 2002-10-04 at 13:35, Carsten Langgaard wrote:
> > That's exactly the problem.
> > The actually loads and stores in memcpy is fine, it's the prefetching that
> > prefetch too much.
> 
> Then fix your prefetching code 8). We had problems with that on x86 too,
> prefetching off the last page into ISA space -> death. Was umm fun to
> debug
> 
> 
> 


-- 
 _    _   _____  ____     Hartvig Ekner        Mailto:hartvige@mips.com
 |\  /| | |____)(____                          Direct: +45 4486 5503
 | \/ | | |     _____)    MIPS Denmark         Switch: +45 4486 5555
T E C H N O L O G I E S   http://www.mips.com  Fax...: +45 4486 5556

WARNING: multiple messages have this Message-ID (diff)
From: Hartvig Ekner <hartvige@mips.com>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Carsten Langgaard <carstenl@mips.com>,
	Dominic Sweetman <dom@algor.co.uk>,
	Ralf Baechle <ralf@linux-mips.org>,
	linux-mips@linux-mips.org
Subject: Re: Promblem with PREF (prefetching) in memcpy
Date: Fri, 4 Oct 2002 15:07:02 +0200 (MEST)	[thread overview]
Message-ID: <200210041307.g94D72G02838@copfs01.mips.com> (raw)
Message-ID: <20021004130702.njhUd8KAb-aXfUmIzZE0P0tJKlMKFTCremPCzpV5_jg@z> (raw)
In-Reply-To: <1033736983.31861.26.camel@irongate.swansea.linux.org.uk> from "Alan Cox" at Oct 04, 2002 02:09:43 PM

Yes, I think that must be the safest solution.

Any kernel routine which uses PREF instructions (but actually also user
space code as Ralf's example pointed out), must guarantee that it does
not issue prefetches to addresses which it is not specifically being
asked to mess around with. 

The other solutions seem too fragile, and will break at some point.

/Hartvig

Alan Cox writes:
> 
> On Fri, 2002-10-04 at 13:35, Carsten Langgaard wrote:
> > That's exactly the problem.
> > The actually loads and stores in memcpy is fine, it's the prefetching that
> > prefetch too much.
> 
> Then fix your prefetching code 8). We had problems with that on x86 too,
> prefetching off the last page into ISA space -> death. Was umm fun to
> debug
> 
> 
> 


-- 
 _    _   _____  ____     Hartvig Ekner        Mailto:hartvige@mips.com
 |\  /| | |____)(____                          Direct: +45 4486 5503
 | \/ | | |     _____)    MIPS Denmark         Switch: +45 4486 5555
T E C H N O L O G I E S   http://www.mips.com  Fax...: +45 4486 5556

  reply	other threads:[~2002-10-04 13:07 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-10-04  7:50 Promblem with PREF (prefetching) in memcpy Carsten Langgaard
2002-10-04 11:53 ` Dominic Sweetman
2002-10-04 12:11   ` Carsten Langgaard
2002-10-04 12:35     ` Dr. David Alan Gilbert
2002-10-04 12:36     ` Alan Cox
2002-10-04 12:35       ` Carsten Langgaard
2002-10-04 13:09         ` Alan Cox
2002-10-04 13:07           ` Hartvig Ekner [this message]
2002-10-04 13:07             ` Hartvig Ekner
2002-10-04 13:00       ` Kevin D. Kissell
2002-10-04 13:00         ` Kevin D. Kissell
2002-10-04 13:15         ` Alan Cox
2002-10-04 13:15           ` Kevin D. Kissell
2002-10-04 13:15             ` Kevin D. Kissell
2002-10-04 13:44             ` Alan Cox
2002-10-04 14:17               ` Kevin D. Kissell
2002-10-04 14:17                 ` Kevin D. Kissell
2002-10-04 14:54                 ` Alan Cox
2002-10-04 13:01       ` Maciej W. Rozycki
2002-10-04 13:17         ` Ralf Baechle
2002-10-04 13:32           ` Maciej W. Rozycki
2002-10-04 13:29     ` Dominic Sweetman
2002-10-04 13:46       ` Maciej W. Rozycki
2002-10-04 12:33   ` Hartvig Ekner
2002-10-04 12:33     ` Hartvig Ekner
2002-10-04 12:38     ` Ralf Baechle
2002-10-04 12:36   ` Kevin D. Kissell
2002-10-04 12:36     ` Kevin D. Kissell
2002-10-04 14:24     ` Dominic Sweetman
2002-10-04 14:24       ` Dominic Sweetman
2002-10-04 23:43     ` Ralf Baechle
2002-10-05 15:12       ` Hartvig Ekner
2002-10-05 15:12         ` Hartvig Ekner
2002-10-05 15:56         ` Alan Cox
2002-10-04 12:37   ` Kevin D. Kissell
2002-10-04 12:37     ` Kevin D. Kissell

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=200210041307.g94D72G02838@copfs01.mips.com \
    --to=hartvige@mips.com \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=carstenl@mips.com \
    --cc=dom@algor.co.uk \
    --cc=linux-mips@linux-mips.org \
    --cc=ralf@linux-mips.org \
    /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