From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH] tunnel: eliminate recursion field Date: Thu, 24 Sep 2009 15:47:10 -0700 (PDT) Message-ID: <20090924.154710.248674101.davem@davemloft.net> References: <4ABA8254.9000701@gmail.com> <4ABA84F1.5000802@gmail.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org To: eric.dumazet@gmail.com Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:48665 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751289AbZIXWqv convert rfc822-to-8bit (ORCPT ); Thu, 24 Sep 2009 18:46:51 -0400 In-Reply-To: <4ABA84F1.5000802@gmail.com> Sender: netdev-owner@vger.kernel.org List-ID: =46rom: Eric Dumazet Date: Wed, 23 Sep 2009 22:28:33 +0200 > Eric Dumazet a =E9crit : >> It seems recursion field from "struct ip_tunnel" is not anymore need= ed. >> recursion prevention is done at the upper level (in dev_queue_xmit()= ), >> since we use HARD_TX_LOCK protection for tunnels. >>=20 >> This avoids a cache line ping pong on "struct ip_tunnel" : This stru= cture >> should be now mostly read on xmit and receive paths. >=20 > Oops I forgot ipv6 tunnels, silly me, here is an updated version. >=20 > Thanks >=20 > [PATCH] tunnel: eliminate recursion field >=20 > It seems recursion field from "struct ip_tunnel" is not anymore neede= d. > recursion prevention is done at the upper level (in dev_queue_xmit())= , > since we use HARD_TX_LOCK protection for tunnels. >=20 > This avoids a cache line ping pong on "struct ip_tunnel" : This struc= ture > should be now mostly read on xmit and receive paths. >=20 > Signed-off-by: Eric Dumazet Applied.