From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: linux-kernel@vger.kernel.org, nico@marvell.com,
jamie@shareable.org, saeed@marvell.com, jejb@parisc-linux.org,
santosh.shilimkar@ti.com, akpm@linux-foundation.org,
linux-ext4@vger.kernel.org, linux-arm-kernel@lists.infradead.org
Subject: Re: Rampant ext3/4 corruption on 2.6.34-rc7 with VIVT ARM (Marvell 88f5182)
Date: Thu, 13 May 2010 14:42:31 +1000 [thread overview]
Message-ID: <1273725751.21352.176.camel@pasglop> (raw)
In-Reply-To: <20100513121302Z.fujita.tomonori@lab.ntt.co.jp>
On Thu, 2010-05-13 at 12:12 +0900, FUJITA Tomonori wrote:
> X86 OOSTORE uses a memory barrier dma_sync_single_for_device (seems
> that some mips archs also use it and do cache operations).
>
> I think that the DMA-API says that
>
> - dma_sync_single_for_device() makes sure the data ready for DMA.
>
> - dma_sync_single_for_cpu() makes sure that drivers doesn't get the
> stale data after DMA.
>
> I guess, it means if an architecture need a memory barrier (not only
> cache operations) to guarantee the above, the architecture needs to
> take care of it.
Right, but doing an indirect function pointer call for a memory barrier
in what can be a pretty hot code path doesn't sound like a great idea
if it can be avoided. I'd rather we define some inline that the arch
can stick in there if it wishes so.
Cheers,
Ben.
next prev parent reply other threads:[~2010-05-13 4:42 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-11 9:23 Rampant ext3/4 corruption on 2.6.34-rc7 with VIVT ARM (Marvell 88f5182) Benjamin Herrenschmidt
2010-05-11 10:16 ` Jamie Lokier
2010-05-11 10:47 ` Benjamin Herrenschmidt
2010-05-11 10:57 ` Benjamin Herrenschmidt
2010-05-11 11:14 ` Shilimkar, Santosh
2010-05-12 22:21 ` Jamie Lokier
2010-05-12 22:47 ` Benjamin Herrenschmidt
2010-05-12 23:08 ` Russell King - ARM Linux
2010-05-14 17:41 ` Jamie Lokier
2010-05-14 17:59 ` Russell King - ARM Linux
2010-05-12 23:41 ` James Bottomley
2010-05-13 0:18 ` Benjamin Herrenschmidt
2010-05-13 15:39 ` James Bottomley
2010-05-13 23:53 ` Benjamin Herrenschmidt
2010-05-13 3:12 ` FUJITA Tomonori
2010-05-13 4:42 ` Benjamin Herrenschmidt [this message]
2010-05-12 15:00 ` Jan Kara
2010-05-12 22:13 ` Benjamin Herrenschmidt
2010-05-13 0:15 ` Benjamin Herrenschmidt
2010-05-13 15:12 ` Jan Kara
2010-05-13 21:33 ` Benjamin Herrenschmidt
2010-05-13 23:51 ` Benjamin Herrenschmidt
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=1273725751.21352.176.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=akpm@linux-foundation.org \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=jamie@shareable.org \
--cc=jejb@parisc-linux.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nico@marvell.com \
--cc=saeed@marvell.com \
--cc=santosh.shilimkar@ti.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).