From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH 2.6.36] vlan: Avoid hwaccel vlan packets when vid not used Date: Fri, 07 Jan 2011 02:20:01 +0100 Message-ID: <1294363201.2704.19.camel@edumazet-laptop> References: <1291536233.2806.102.camel@edumazet-laptop> <20101205105528.49fa9a9f@xenia.leun.net> <20101205114404.7c0cddc2@xenia.leun.net> <20101206203437.54b550e0@xenia.leun.net> <20101206222703.32fbe852@xenia.leun.net> <20101213224510.GB17400@mcarlson.broadcom.com> <20101214191500.GD19951@mcarlson.broadcom.com> <1293901393.2535.49.camel@edumazet-laptop> <1293984348.2535.101.camel@edumazet-laptop> <1294356887.2704.13.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Matt Carlson , Michael Leun , Michael Chan , David Miller , Ben Greear , "linux-kernel@vger.kernel.org" , "netdev@vger.kernel.org" To: Jesse Gross Return-path: In-Reply-To: <1294356887.2704.13.camel@edumazet-laptop> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le vendredi 07 janvier 2011 =C3=A0 00:34 +0100, Eric Dumazet a =C3=A9cr= it : > Le jeudi 06 janvier 2011 =C3=A0 16:01 -0500, Jesse Gross a =C3=A9crit= : >=20 > > Hmm, I thought that it might be some interaction with a corner case= in > > the networking core but now it seems less likely. There weren't to= o > > many vlan changes between the working and non-working states. Plus= , > > since the rx counter isn't increasing, the packets probably aren't > > making it anywhere. > >=20 > > I see that tg3 increases the drop counter in one place, which also > > happens to be checking for vlan errors (at tg3.c:4753). That seems > > suspicious - maybe the NIC is only partially configured for vlan > > offloading. If we can confirm that is where the drop counter is be= ing > > incremented and what the error code is maybe it would shed some lig= ht. > >=20 >=20 > Hmm... I am pretty sure the drop counter is the dev rx_dropped (core > network handled, not tg3 one) incremented at the end of > __netif_receive_skb() : We found no suitable handler for packets. >=20 > atomic_long_inc(&skb->dev->rx_dropped); >=20 > But thats a guess, I'll have to check >=20 wrong guess. Its really the tg3 which drops frames increasing rx_missed_errors (get_stat64(&hw_stats->rx_discards) ip -s -s link show dev eth2 5: eth2: mtu 1500 qdisc mq master bond0 state UP qlen 1000 link/ether 00:1e:0b:92:78:50 brd ff:ff:ff:ff:ff:ff RX: bytes packets errors dropped overrun mcast =20 11627 167 0 0 0 2 =20 RX errors: length crc frame fifo missed 0 0 0 0 2713 =20 TX: bytes packets errors dropped carrier collsns=20 2274 31 0 0 0 0 =20 TX errors: aborted fifo window heartbeat 0 0 0 0 =20 It would be nice Broadcom guys could help a bit ?