From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH net-next-2.6] gro: __napi_gro_receive() optimizations Date: Thu, 26 Aug 2010 11:03:54 +0200 Message-ID: <1282813434.2476.200.camel@edumazet-laptop> References: <1282768431.2681.144.camel@edumazet-laptop> <20100825.135726.189708768.davem@davemloft.net> <1282770911.2681.205.camel@edumazet-laptop> <20100826.005139.183034040.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org, herbert@gondor.apana.org.au To: David Miller Return-path: Received: from mail-wy0-f174.google.com ([74.125.82.174]:34926 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753442Ab0HZJD7 (ORCPT ); Thu, 26 Aug 2010 05:03:59 -0400 Received: by wyb35 with SMTP id 35so1928422wyb.19 for ; Thu, 26 Aug 2010 02:03:57 -0700 (PDT) In-Reply-To: <20100826.005139.183034040.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: Le jeudi 26 ao=C3=BBt 2010 =C3=A0 00:51 -0700, David Miller a =C3=A9cri= t : > From: Eric Dumazet > Date: Wed, 25 Aug 2010 23:15:11 +0200 >=20 > > Yes, we can inline it, this will speedup the non vlan case as well = :) >=20 > Agreed. >=20 > But I believe you can find a better place to put __napi_gro_receive() > than etherdevice.h, even though yes it does have a hard dependency on > that thing. :-) >=20 I tried but failed :( Or move __napi_gro_receive() in a new header, because etherdevice.h needs to include netdevice.h (is_etherdev_addr(), dev_hw_addr_random())