Date: Sun, 23 Mar 2008 15:11:46 +0900 From: Pyun YongHyeon <pyunyh@gmail.com> To: Artem Belevich <fbsdlist@src.cx> Cc: freebsd-net@freebsd.org, Anton Yuzhaninov <citrin@citrin.ru> Subject: Re: re TSO: data corruption Message-ID: <20080323061146.GA79693@cdnetworks.co.kr> In-Reply-To: <ed91d4a80803221601u75c837dfr52b492afbc112c61@mail.gmail.com> References: <47E57C8F.4090602@citrin.ru> <b1fa29170803221453n6c1f5b73g5f9e300c8655ab29@mail.gmail.com> <ed91d4a80803221601u75c837dfr52b492afbc112c61@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Mar 22, 2008 at 04:01:50PM -0700, Artem Belevich wrote: > TSO does seem to be broken on Realtek adapters. I ran into it on > Windows, went googling and found that I'm not the only one suffering: > > http://blogs.zdnet.com/Ou/?p=663 > http://www.mail-archive.com/netdev@vger.kernel.org/msg56764.html > Long time ago, I've read this article but the article is not clear to me. I know RealTek chips have several bugs not mentioned in datasheet and Tx checksum offload is one of the most serious bug in the hardware. But I didn't encounter any TSO related issues on my box. It could also be related checksum offload and padding but I have no clear evidence yet. Today, I commited pending changes in my local tree. This will address VLAN and unstability issues on PCIe based hardwares. But the stock version still does not have one important fix that is under actively testing. To rule out other possible bugs in stock driver, please download the follodwing files and set tunable hw.re.msi_disable="1" in /boot/loader.conf and let me know the result. http://people.freebsd.org/~yongari/re/if_re.c http://people.freebsd.org/~yongari/re/if_rlreg.h The above version has changed a way to work-around checksum offload bug of the hardware. -- Regards, Pyun YongHyeon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080323061146.GA79693>