Date: Mon, 06 Feb 2006 08:03:04 -0800 From: Paul Saab <ps@freebsd.org> To: Gleb Smirnoff <glebius@FreeBSD.org> Cc: Oleg Bulyzhin <oleg@FreeBSD.org>, src-committers@FreeBSD.org, Alan Cox <alc@cs.rice.edu>, cvs-all@FreeBSD.org, cvs-src@FreeBSD.org Subject: Re: cvs commit: src/sys/dev/bge if_bge.c Message-ID: <43E77338.5070404@freebsd.org> In-Reply-To: <20060206105328.GA27193@cell.sick.ru> References: <200602020958.k129wWtc066930@repoman.freebsd.org> <20060202100637.GB24350@lath.rinet.ru> <20060205235817.GQ5499@cs.rice.edu> <20060206081519.GL60276@FreeBSD.org> <20060206082645.GS5499@cs.rice.edu> <20060206083112.GM60276@FreeBSD.org> <20060206105328.GA27193@cell.sick.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
revision 1.17 date: 2002/07/04 23:19:20; author: jdp; state: Exp; lines: +1 -1 Disable hardware checksum offloading of IP fragments in the bge driver. I tried a few obvious experiments, but was unable to make the 3c996B-T generate correct UDP checksums for transmitted fragmented packets. I'm not so sure the device is even capable of it. This fixes NFS over UDP. MFC after: 1 day Gleb Smirnoff wrote: > On Mon, Feb 06, 2006 at 11:31:12AM +0300, Gleb Smirnoff wrote: > T> On Mon, Feb 06, 2006 at 02:26:45AM -0600, Alan Cox wrote: > T> A> > A> Unfortunately, it also breaks NFS over UDP. Let me know if you need > T> A> > A> details. > T> A> > > T> A> > The 1.123 revision, or the previous one? bge(4) must be on server side or > T> A> > on client? > T> A> > > T> A> > T> A> Revision 1.123; bge(4) is the client. > T> > T> I will try to look at it today. > > Looks like the problem is with receiving fragmented UDP packet. In chip > documentation it is said, that it will not calculated checksum for > fragmented UDP packet, however from the context it looks like this > is related only to transmitting. > >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?43E77338.5070404>