linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: catalin.marinas@arm.com (Catalin Marinas)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2] ARM: realview: basic device tree implementation
Date: Thu, 22 May 2014 17:09:08 +0100	[thread overview]
Message-ID: <20140522160908.GD27931@arm.com> (raw)
In-Reply-To: <5057707.jNCXlqf9dH@wuerfel>

On Thu, May 22, 2014 at 04:49:16PM +0100, Arnd Bergmann wrote:
> On Thursday 22 May 2014 15:45:03 Catalin Marinas wrote:
> > On Thu, May 22, 2014 at 09:31:37AM +0100, Arnd Bergmann wrote:
> > > commit 42c4dafe803dcad82980fd8b0831a89032156f93
> > > Author: Catalin Marinas <catalin.marinas@arm.com>
> > > Date:   Thu Jul 1 13:22:48 2010 +0100
> > > 
> > >     ARM: 6202/1: Do not ARM_DMA_MEM_BUFFERABLE on RealView boards with L210/L220
> > >     
> > >     RealView boards with certain revisions of the L210/L220 cache controller
> > >     may have issues (hardware deadlock) with the mandatory barriers (DSB
> > >     followed by an L2 cache sync) when ARM_DMA_MEM_BUFFERABLE is enabled.
> > >     The patch disables ARM_DMA_MEM_BUFFERABLE for these boards.
> > >     
> > >     Tested-by: Linus Walleij <linus.walleij@stericsson.com>
> > >     Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
> > >     Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
> > 
> > Looking through the L220 errata document, I think this relates to 425331
> > which says that a cache sync can deadlock the system if the write buffer
> > is not empty.
> 
> Hmm, but isn't the write buffer empty here because we have just issued
> a dsb()?

The problem with these outer caches is that DSB doesn't propagate to
them (and I hope to never see such caches again ;)). So an mb() on such
systems needs to be dsb()+outer_sync(). The dsb() pushes data from the
CPU write buffer into the L2x0 write buffer and outer_sync() does the
flushing out of the outer cache write buffer (which strangely enough
buffers even if the memory access is Normal NonCacheable).

> > If we only use the DMA coherent buffers for CLCD on these boards, we
> > don't really need the outer_sync() either so we could go back to
> > bufferable DMA memory (strangely enough, this L2 cache workaround looks
> > similar to Marvell's PCI+PL310 problem where we want to avoid
> > outer_sync()).
> 
> Ah, so you think we can add another hook to NULL out outer_cache.sync
> per platform?

Yes, with the note that mb() no longer guarantees the write being
flushed to RAM but just to the L2 write buffer. If CLCD framebuffer is
the only DMA device, we don't need to worry about such barriers since we
map it as writecombine anyway (hence bufferable).

Unless Linus or Pawel think there are other DMA capable devices in use
here, I'm happy to enable ARM_DMA_MEM_BUFFERABLE for these boards.

-- 
Catalin

  reply	other threads:[~2014-05-22 16:09 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-08 22:08 [PATCH v2] ARM: realview: basic device tree implementation Linus Walleij
2014-05-09 10:44 ` Arnd Bergmann
2014-05-22  7:41   ` Linus Walleij
2014-05-22  8:31     ` Arnd Bergmann
2014-05-22 13:04       ` Linus Walleij
2014-05-22 13:38         ` Arnd Bergmann
2014-05-22 14:45       ` Catalin Marinas
2014-05-22 15:49         ` Arnd Bergmann
2014-05-22 16:09           ` Catalin Marinas [this message]
2014-05-22 18:09           ` Nicolas Pitre
2014-05-22 18:26             ` Arnd Bergmann
2014-05-22 18:39               ` Nicolas Pitre
2014-05-22 20:25                 ` Arnd Bergmann
2014-05-22 18:52           ` Linus Walleij
2014-05-22 20:35             ` Arnd Bergmann
2014-05-29  9:38               ` Linus Walleij
2014-05-22 22:34     ` Sebastian Hesselbarth
2014-05-29  9:44       ` Linus Walleij
2014-05-29 10:10         ` Sebastian Hesselbarth
2014-05-29 14:13           ` Linus Walleij
2014-05-29 14:47             ` Sebastian Hesselbarth
2014-05-22 13:17 ` Rob Herring
2014-05-22 13:30   ` Linus Walleij
2014-05-22 13:36     ` Arnd Bergmann
2014-05-22 13:41 ` Jason Cooper

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=20140522160908.GD27931@arm.com \
    --to=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@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 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).