From: Stephen Hemminger <shemminger@linux-foundation.org>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Johannes Berg <johannes@sipsolutions.net>,
dsd@gentoo.org, davem@davemloft.net, netdev@vger.kernel.org,
linux-wireless@vger.kernel.org
Subject: Re: wireless vs. alignment requirements
Date: Sun, 25 Nov 2007 13:21:44 -0800 [thread overview]
Message-ID: <4749E768.9040002@linux-foundation.org> (raw)
In-Reply-To: <20071125010814.GD31668@gondor.apana.org.au>
Herbert Xu wrote:
> On Sat, Nov 24, 2007 at 12:11:08PM -0800, Stephen Hemminger wrote:
>
>> Then what about hardware that can't dma ethernet to non-aligned address.
>> Sky2 hardware breaks if DMA is not 8 byte aligned. IMHO the IP stack should
>> handle any alignment, and do the appropriate memove if the CPU requires
>> alignment.
>>
>
> Luckily all sky2 users have been on x86 so far :)
>
> Here's an idea. Put the data of the packet into the page frags
> where alignment is not an issue but copy the header so that it
> is aligned.
>
> Would that work?
>
> Cheers,
>
No too wasteful. I'm working a patch to eth_type_trans to realign if
needed for any device.
WARNING: multiple messages have this Message-ID (diff)
From: Stephen Hemminger <shemminger-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
To: Herbert Xu <herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
Cc: Johannes Berg <johannes-cdvu00un1VgdHxzADdlk8Q@public.gmane.org>,
dsd-aBrp7R+bbdUdnm+yROfE0A@public.gmane.org,
davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-wireless-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: wireless vs. alignment requirements
Date: Sun, 25 Nov 2007 13:21:44 -0800 [thread overview]
Message-ID: <4749E768.9040002@linux-foundation.org> (raw)
In-Reply-To: <20071125010814.GD31668-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
Herbert Xu wrote:
> On Sat, Nov 24, 2007 at 12:11:08PM -0800, Stephen Hemminger wrote:
>
>> Then what about hardware that can't dma ethernet to non-aligned address.
>> Sky2 hardware breaks if DMA is not 8 byte aligned. IMHO the IP stack should
>> handle any alignment, and do the appropriate memove if the CPU requires
>> alignment.
>>
>
> Luckily all sky2 users have been on x86 so far :)
>
> Here's an idea. Put the data of the packet into the page frags
> where alignment is not an issue but copy the header so that it
> is aligned.
>
> Would that work?
>
> Cheers,
>
No too wasteful. I'm working a patch to eth_type_trans to realign if
needed for any device.
next prev parent reply other threads:[~2007-11-25 21:23 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-23 0:09 [PATCH] add compare_ether_addr_unaligned Daniel Drake
2007-11-23 4:11 ` Stephen Hemminger
2007-11-23 13:26 ` Herbert Xu
2007-11-26 10:39 ` Herbert Xu
2007-11-23 20:33 ` wireless vs. alignment requirements Johannes Berg
2007-11-24 6:15 ` Herbert Xu
2007-11-24 6:15 ` Herbert Xu
2007-11-24 8:33 ` Johannes Berg
2007-11-24 13:32 ` Herbert Xu
2007-11-24 13:49 ` Johannes Berg
2007-11-24 13:49 ` Johannes Berg
2007-11-24 13:51 ` David Miller
2007-11-24 14:13 ` Herbert Xu
2007-11-24 20:11 ` Stephen Hemminger
2007-11-24 20:11 ` Stephen Hemminger
2007-11-24 21:33 ` Johannes Berg
2007-11-24 21:33 ` Johannes Berg
2007-11-25 1:08 ` Herbert Xu
2007-11-25 1:08 ` Herbert Xu
2007-11-25 21:21 ` Stephen Hemminger [this message]
2007-11-25 21:21 ` Stephen Hemminger
2007-11-26 1:38 ` Herbert Xu
2007-11-26 1:38 ` Herbert Xu
2007-11-27 17:16 ` H. Peter Anvin
2007-11-27 17:16 ` H. Peter Anvin
2007-11-27 17:16 ` H. Peter Anvin
2007-11-27 18:39 ` Stephen Hemminger
2007-11-27 18:39 ` Stephen Hemminger
2007-11-28 2:42 ` H. Peter Anvin
2007-11-28 2:42 ` H. Peter Anvin
2007-11-29 13:11 ` Herbert Xu
2007-11-29 13:11 ` Herbert Xu
2007-11-29 17:50 ` H. Peter Anvin
2007-11-30 0:26 ` Herbert Xu
2007-11-30 0:28 ` H. Peter Anvin
2007-11-30 0:28 ` H. Peter Anvin
2007-11-30 0:34 ` Herbert Xu
2007-11-30 0:34 ` Herbert Xu
2007-11-30 0:41 ` H. Peter Anvin
2007-11-30 0:41 ` H. Peter Anvin
2007-11-24 21:13 ` Johannes Berg
2007-11-24 21:13 ` Johannes Berg
2007-11-25 1:44 ` Herbert Xu
2007-11-25 1:44 ` Herbert Xu
2007-11-25 11:00 ` Johannes Berg
2007-11-25 11:00 ` Johannes Berg
2007-11-25 11:22 ` Herbert Xu
2007-11-25 11:22 ` Herbert Xu
2007-11-25 13:54 ` Johannes Berg
2007-11-25 14:01 ` Herbert Xu
2007-11-25 14:01 ` Herbert Xu
2007-11-25 17:04 ` Johannes Berg
2007-11-26 1:36 ` Herbert Xu
2007-11-26 1:36 ` Herbert Xu
2007-11-24 13:11 ` Ulrich Kunitz
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=4749E768.9040002@linux-foundation.org \
--to=shemminger@linux-foundation.org \
--cc=davem@davemloft.net \
--cc=dsd@gentoo.org \
--cc=herbert@gondor.apana.org.au \
--cc=johannes@sipsolutions.net \
--cc=linux-wireless@vger.kernel.org \
--cc=netdev@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.