All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: Jeff Garzik <jgarzik@mandrakesoft.com>
Cc: bjornw@axis.com, linux-kernel@vger.kernel.org,
	linux-mtd@lists.infradead.org
Subject: Re: Missing cache flush.
Date: Tue, 05 Jun 2001 00:29:22 +0100	[thread overview]
Message-ID: <14147.991697362@redhat.com> (raw)
In-Reply-To: <3B1C1872.8D8F1529@mandrakesoft.com>

jgarzik@mandrakesoft.com said:
> > I was pointed at Documentation/DMA-mapping.txt but that doesn't seem
> > very helpful - it's very PCI-specific, and a quick perusal of
> > pci_dma_sync() on i386 shows that it doesn't do what's required anyway.

> What should it do on i386?  mb()? 

For it to have any use in the situation I described, it would need to 
writeback and invalidate the dcache for the affected range. It doesn't seem 
to do so, so it seems that it isn't what I require.

The situation is simple - I have a paged RAM setup and I need it cached. 
All I want to do is flush and invalidate the cache when I'm about to waggle 
whatever I/O ports I waggle to change pages. 

There are other situations in which I need the cache flushed, but the above 
is one of the simplest.

Even flush_page_to_ram() doesn't seem to do what its name implies, on most 
architectures.

--
dwmw2

WARNING: multiple messages have this Message-ID (diff)
From: David Woodhouse <dwmw2@infradead.org>
To: Jeff Garzik <jgarzik@mandrakesoft.com>
Cc: bjornw@axis.com, linux-kernel@vger.kernel.org,
	linux-mtd@lists.infradead.org
Subject: Re: Missing cache flush.
Date: Tue, 05 Jun 2001 00:29:22 +0100	[thread overview]
Message-ID: <14147.991697362@redhat.com> (raw)
In-Reply-To: <3B1C1872.8D8F1529@mandrakesoft.com>
In-Reply-To: <3B1C1872.8D8F1529@mandrakesoft.com>  <13942.991696607@redhat.com>


jgarzik@mandrakesoft.com said:
> > I was pointed at Documentation/DMA-mapping.txt but that doesn't seem
> > very helpful - it's very PCI-specific, and a quick perusal of
> > pci_dma_sync() on i386 shows that it doesn't do what's required anyway.

> What should it do on i386?  mb()? 

For it to have any use in the situation I described, it would need to 
writeback and invalidate the dcache for the affected range. It doesn't seem 
to do so, so it seems that it isn't what I require.

The situation is simple - I have a paged RAM setup and I need it cached. 
All I want to do is flush and invalidate the cache when I'm about to waggle 
whatever I/O ports I waggle to change pages. 

There are other situations in which I need the cache flushed, but the above 
is one of the simplest.

Even flush_page_to_ram() doesn't seem to do what its name implies, on most 
architectures.

--
dwmw2



  reply	other threads:[~2001-06-04 23:25 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-06-04 23:16 Missing cache flush David Woodhouse
2001-06-04 23:23 ` Jeff Garzik
2001-06-04 23:29   ` David Woodhouse [this message]
2001-06-04 23:29     ` David Woodhouse
2001-06-05  2:04     ` David S. Miller
2001-06-05  2:04       ` David S. Miller
2001-06-05  2:03   ` David S. Miller
2001-06-05  2:03     ` David S. Miller
2001-06-05  3:55     ` Chris Wedgwood
2001-06-05  4:01       ` David S. Miller
2001-06-05  4:01         ` David S. Miller
2001-06-05  8:46         ` David Woodhouse
2001-06-05  8:46           ` David Woodhouse
2001-06-05  8:50           ` David S. Miller
2001-06-05  8:50             ` David S. Miller
2001-06-05  9:05             ` David Woodhouse
2001-06-05  9:05               ` David Woodhouse
2001-06-05  9:11               ` David S. Miller
2001-06-05  9:11                 ` David S. Miller
2001-06-05 12:42                 ` David Woodhouse
2001-06-05 12:42                   ` David Woodhouse
2001-06-05 12:48                   ` David S. Miller
2001-06-05 12:48                     ` David S. Miller
2001-06-05 12:52                     ` David Woodhouse
2001-06-05 12:52                       ` David Woodhouse
2001-06-06  8:32                     ` Albert D. Cahalan
2001-06-06 19:48               ` Pavel Machek
2001-06-05 17:01             ` Jamie Lokier
2001-06-05 23:24               ` Chris Wedgwood
2001-06-06  8:43                 ` James Sutherland
2001-06-05  9:29           ` kira brown
2001-06-05  9:29             ` kira brown
2001-06-05 17:16             ` Alan Cox
2001-06-06 19:44               ` Earyly Cyrix CPUs was " Pavel Machek
2001-06-08 16:00                 ` Alan Cox
2001-06-05  9:43           ` Johan Adolfsson
2001-06-05  5:28       ` Linus Torvalds
2001-06-05  6:49         ` Alan Cox
2001-06-05  8:29         ` Ingo Molnar
2001-06-05 15:10           ` Ralf Baechle
2001-06-05  9:17 ` Bjorn Wesen
2001-06-05 12:57   ` Chris Wedgwood
2001-06-05 15:17     ` Ralf Baechle
2001-06-05 17:41     ` Daniel Phillips
2001-06-05 14:22   ` Vipin Malik
2001-06-05 14:40     ` Chris Wedgwood

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=14147.991697362@redhat.com \
    --to=dwmw2@infradead.org \
    --cc=bjornw@axis.com \
    --cc=jgarzik@mandrakesoft.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mtd@lists.infradead.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.