Date: Thu, 30 Apr 2009 17:33:00 +0400 From: pluknet <pluknet@gmail.com> To: Nikolay Denev <ndenev@gmail.com> Cc: freebsd-net@freebsd.org Subject: Re: bce(4) and lagg(4) fix [was: bce(4) sees all incoming frames as 2026 bytes in length] Message-ID: <a31046fc0904300633n5e983d34l10d7e6daa723df41@mail.gmail.com> In-Reply-To: <DE46D03C-2996-42EB-A92D-2DA35F2E1FD3@gmail.com> References: <5E915E92-2B82-4331-9493-739568CC6E8C@gmail.com> <a31046fc0904290659h3c831abcy14318b73c1462068@mail.gmail.com> <2e77fc10904290733m4858172ayd96654f3a9a3a8a@mail.gmail.com> <a31046fc0904290904x796a7d44ne66514f777d2237f@mail.gmail.com> <FAC395EB-BEE6-4981-85D2-82ADFC2DF441@gmail.com> <5FD800FE-23E5-482E-8491-564FE52D91D5@gmail.com> <DE46D03C-2996-42EB-A92D-2DA35F2E1FD3@gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
2009/4/30 Nikolay Denev <ndenev@gmail.com>: > On Apr 30, 2009, at 3:04 PM, Nikolay Denev wrote: > [snip] >>> >>> I think I got it. >>> >>> It seems that the mbuf fields m_pkthdr.len and m_len are not updated to >>> the real packet size pkt_len. >>> Well, actually they are updated, but only if we have ZERO_COPY_SOCKETS >>> defined. >>> >>> After I added this : >>> >>> =A0 m0->m_pkthdr.len =3D m0->m_len =3D pkt_len; >>> >>> at about line 5930 in if_bce.c, the frame length reported by tcpdump >>> seems correct. >>> >>> P.S.: I guess this could be the cause for the lagg(4) over bce(4) >>> problems too? >>> >>> P.S.2: This fix will probably break the ZERO_COPY_SOCKETS case, but >>> should be fairly easy to make it a "proper" fix. >>> >>> Regards, >>> Niki Denev >>> >> >> I can confirm that with this fix I was able to create lagg(4) interface = in >> "failover" mode with only one member, a =A0bce(4) interface, and it seem= s to >> work OK. >> >> > > Here is the patch : > > --- sys/dev/bce/if_bce.c.orig =A0 2009-04-30 14:06:54.000000000 +0200 > +++ sys/dev/bce/if_bce.c =A0 =A0 =A0 =A02009-04-30 14:11:32.000000000 +02= 00 > @@ -5926,6 +5926,11 @@ > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0goto bce_rx_int_next_rx; > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0} > > +#ifndef ZERO_COPY_SOCKETS > + =A0 =A0 =A0 =A0 =A0 =A0 =A0 /* Adjust the packet length to match the re= ceived data. */ > + =A0 =A0 =A0 =A0 =A0 =A0 =A0 m0->m_pkthdr.len =3D m0->m_len =3D pkt_len; > +#endif > + > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0/* Send the packet to the appropriate inte= rface. */ > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0m0->m_pkthdr.rcvif =3D ifp; > Ha-ha, you was fast! The only note: I think the comment part should be consistent with ZERO_COPY_SOCKETS case. Thank you. --=20 wbr, pluknet
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?a31046fc0904300633n5e983d34l10d7e6daa723df41>