linux-mips
[Top] [All Lists]

Re: [PATCH] Fix TCP/UDP checksums on the Broadcom SB-1

To: Michael Uhler <uhler@mips.com>
Subject: Re: [PATCH] Fix TCP/UDP checksums on the Broadcom SB-1
From: Ralf Baechle <ralf@linux-mips.org>
Date: Tue, 20 Sep 2005 15:59:48 +0100
Cc: "'Matej Kupljen'" <matej.kupljen@ultra.si>, "'Maciej W. Rozycki'" <macro@linux-mips.org>, "'Daniel Jacobowitz'" <dan@debian.org>, linux-mips@linux-mips.org
In-reply-to: <00da01c5bdef$596ee380$0502a8c0@MIPS.COM>
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <20050920110609.GB3159@linux-mips.org> <00da01c5bdef$596ee380$0502a8c0@MIPS.COM>
Sender: linux-mips-bounce@linux-mips.org
User-agent: Mutt/1.4.2.1i
On Tue, Sep 20, 2005 at 07:26:54AM -0700, Michael Uhler wrote:

> For what it's worth, the 64-bit architecture, both prior to and with MIPS64,
> has always required that 64-bit GPRs be sign-extended when used with 32-bit
> operations.  I'm surprised that this wasn't seen on more 64-bit CPUs than
> just the SB1.

Usually resends will paper over this kind of problem.  It's only a question
of time until they succeed for any protocol that changed the packet
content sufficiently to make the checksum work eventually.  But of course
performance will suffer and as a matter of statistics certain IP address
and port ranges are going to suffer more than others.

  Ralf

<Prev in Thread] Current Thread [Next in Thread>