All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ralf Baechle <ralf@linux-mips.org>
To: Imran Badr <imran.badr@cavium.com>
Cc: "'Alan Cox'" <alan@lxorguk.ukuu.org.uk>, linux-kernel@vger.kernel.org
Subject: Re: Cache coherency and snooping
Date: Wed, 14 Aug 2002 10:16:54 +0200	[thread overview]
Message-ID: <20020814101654.B14197@linux-mips.org> (raw)
In-Reply-To: <0aa401c2432e$04a95cc0$9e10a8c0@IMRANPC>; from imran.badr@cavium.com on Tue, Aug 13, 2002 at 06:00:43PM -0700

On Tue, Aug 13, 2002 at 06:00:43PM -0700, Imran Badr wrote:

> Please advise if following sequence of operations are going to help:
> 
> alloc memory
> reserve the page
> flush every cache

That's an extremly expensive operation on some platforms and there's no
portable kernel API to do it.

Note that the flush_cache_*() functions are not suitable for I/O as you
want to do it.  Many platforms such as i386 implement these functions
as empty functions.

> call ioremap_nocache

You said you intend to remap memory, that is RAM.  The ioremap*() functions
will refuse to remap RAM; they're only suitable for other types of memory
such as PCI boards.  If the latter was your intension then ioremap_nocache()
will work as intended.

Again, unless your hardware is fucked beyond recognition it'll do a better
job at keeping cache coherence than software.

  Ralf

  parent reply	other threads:[~2002-08-14  8:13 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-08-13 22:57 patch 04/38: SUNRPC: support for GSSD client Kendrick M. Smith
2002-08-13 22:57 ` Kendrick M. Smith
2002-08-13 23:22 ` Cache coherency and snooping Imran Badr
2002-08-13 23:38   ` Alan Cox
2002-08-14  0:08   ` Ralf Baechle
2002-08-14  0:19     ` Imran Badr
2002-08-14  0:29       ` Ralf Baechle
2002-08-14  1:00         ` Imran Badr
2002-08-14  1:38           ` Rik van Riel
2002-08-14  1:56             ` Imran Badr
2002-08-14  8:16           ` Ralf Baechle [this message]
2002-08-14  9:00             ` 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=20020814101654.B14197@linux-mips.org \
    --to=ralf@linux-mips.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=imran.badr@cavium.com \
    --cc=linux-kernel@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.