From: Roland Dreier <rdreier@cisco.com>
To: David Miller <davem@davemloft.net>
Cc: benh@kernel.crashing.org, James.Bottomley@HansenPartnership.com,
linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org,
rmk@arm.linux.org.uk
Subject: Re: SCSI breakage on non-cache coherent architectures
Date: Mon, 19 Nov 2007 18:10:14 -0800 [thread overview]
Message-ID: <ada8x4ty8e1.fsf@cisco.com> (raw)
In-Reply-To: <20071119.164611.64664648.davem@davemloft.net> (David Miller's message of "Mon, 19 Nov 2007 16:46:11 -0800 (PST)")
> 2) Add the __dma_cacheline_aligned tag.
>
> But note that with #2 it could get quite ugly because the
> alignment and size both have a minimum that needs to be
> enforced, not just the alignment alone. So either:
>
> struct foo {
> unsigned int other_unrelated_stuff;
>
> struct object dma_thing __dma_cacheline_aligned;
>
> unsigned int more_nondma_stuff __dma_cacheline_aligned;
> };
>
> or:
>
> struct foo {
> unsigned int other_unrelated_stuff;
>
> union {
> struct object dma_thing __dma_cacheline_aligned;
> char __pad[(sizeof(object) + DMA_CACHELINE_SIZE &
> ~DMA_CACHELINE_SIZE)];
> } u;
>
> unsigned int more_nondma_stuff __dma_cacheline_aligned;
> };
I wrapped this ugliness up inside the macro back in what I posted in
2002 (http://lkml.org/lkml/2002/6/12/234):
#define __dma_buffer __dma_buffer_line(__LINE__)
#define __dma_buffer_line(line) __dma_buffer_expand_line(line)
#define __dma_buffer_expand_line(line) \
__attribute__ ((aligned(L1_CACHE_BYTES))); \
char __dma_pad_ ## line [0] __attribute__ ((aligned(L1_CACHE_BYTES)))
then you just need to tag the actual member like:
char foo[3] __dma_buffer;
- R.
next prev parent reply other threads:[~2007-11-20 2:16 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-19 5:35 SCSI breakage on non-cache coherent architectures Benjamin Herrenschmidt
2007-11-19 8:38 ` David Miller
2007-11-19 19:51 ` Benjamin Herrenschmidt
2007-11-19 22:31 ` David Miller
2007-11-20 0:34 ` Benjamin Herrenschmidt
2007-11-20 0:46 ` David Miller
2007-11-20 0:55 ` Benjamin Herrenschmidt
2007-11-20 0:57 ` David Miller
2007-11-20 2:10 ` Roland Dreier [this message]
2007-11-20 2:35 ` Benjamin Herrenschmidt
2007-11-20 3:14 ` Benjamin Herrenschmidt
2007-11-20 19:35 ` James Bottomley
2007-11-20 8:29 ` Thomas Bogendoerfer
2007-11-20 14:36 ` James Bottomley
2007-11-20 20:05 ` Roland Dreier
2007-11-20 21:10 ` James Bottomley
2007-11-20 22:39 ` Benjamin Herrenschmidt
2007-11-20 23:09 ` James Bottomley
2007-11-19 12:32 ` Matthew Wilcox
2007-11-19 15:09 ` James Bottomley
2007-11-19 19:54 ` Benjamin Herrenschmidt
2007-11-19 19:55 ` Benjamin Herrenschmidt
2007-11-19 19:53 ` Benjamin Herrenschmidt
2007-11-19 21:43 ` Roland Dreier
2007-11-19 21:55 ` 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=ada8x4ty8e1.fsf@cisco.com \
--to=rdreier@cisco.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=benh@kernel.crashing.org \
--cc=davem@davemloft.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=rmk@arm.linux.org.uk \
/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