[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <AANLkTikE_OU_qiBUdiDP39js8jQzGqqo1FYW2uHmw3He@mail.gmail.com>
Date: Thu, 24 Feb 2011 16:07:48 +0800
From: Po-Yu Chuang <ratbert.chuang@...il.com>
To: David Miller <davem@...emloft.net>
Cc: mirqus@...il.com, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org, bhutchings@...arflare.com,
eric.dumazet@...il.com, joe@...ches.com, dilinger@...ued.net,
ratbert@...aday-tech.com
Subject: Re: [PATCH v4] net: add Faraday FTMAC100 10/100 Ethernet driver
Hi David,
On Thu, Feb 24, 2011 at 3:51 PM, David Miller <davem@...emloft.net> wrote:
> From: Po-Yu Chuang <ratbert.chuang@...il.com>
> Date: Thu, 24 Feb 2011 15:27:55 +0800
>
>> I guess the problem is because a HW restriction that the rx buffer must be
>> 64 bits aligned. Since I cannot make rx buffer starts at offset 2 bytes, the
>> IP header, TCP header and data are not 4 bytes aligned. The performance
>> drops drastically.
>
> I cannot believe that after 20 years of commodity ethernet networking
> chips were first designed, people are still designing hardware that
> doesn't do this right.
Ha ha...
Well, this restriction was removed in the later IPs of our company. :-p
>
> Just emit garbage bytes into the sub-word alignment padding if the chip
> wants to word align it's DMA writes.
Not sure what do you mean. The problem is that HW does not accept a
base address of RX buffer which is not 8 bytes aligned.
> Even the 15 year old Dec Tulip chips do this properly.
best regards,
Po-Yu Chuang
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists