From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [RFC] gro: Is it ok to share a single napi from several devs ? Date: Sun, 29 Aug 2010 20:39:22 +0200 Message-ID: <1283107162.2297.32.camel@edumazet-laptop> References: <20100828101424.69c4c782@s6510> <20100828.144130.189711704.davem@davemloft.net> <20100829095951.GA3153@del.dom.local> <20100829.100653.70199372.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: jarkao2@gmail.com, shemminger@vyatta.com, herbert@gondor.apana.org.au, netdev@vger.kernel.org To: David Miller Return-path: Received: from mail-wy0-f174.google.com ([74.125.82.174]:41783 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753943Ab0H2Sj1 (ORCPT ); Sun, 29 Aug 2010 14:39:27 -0400 Received: by wyb35 with SMTP id 35so5936350wyb.19 for ; Sun, 29 Aug 2010 11:39:26 -0700 (PDT) In-Reply-To: <20100829.100653.70199372.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: Le dimanche 29 ao=C3=BBt 2010 =C3=A0 10:06 -0700, David Miller a =C3=A9= crit : > From: Jarek Poplawski > Date: Sun, 29 Aug 2010 11:59:51 +0200 >=20 > > Actually, when GRO compares napi->dev to skb->dev? >=20 > Hmmm, I thought the code made a skb->dev comparison with the > existing SKBs in the list when checking for same-flow matches. >=20 > It doesn't, probably based upon the assumption that a NAPI > instance maps to a unique device, the very topic we're > discussing right now :-/ >=20 >=20 It does the check, Stephen added it in the commit I mentioned to start this thread. With net-next-2.6 this now reads :