From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick McHardy Subject: Re: [PATCH v5 2/2] netfilter: save the hash of the tuple in the original direction for latter use Date: Mon, 20 Sep 2010 19:08:37 +0200 Message-ID: <4C979515.4060908@trash.net> References: <1282344540-5306-1-git-send-email-xiaosuo@gmail.com> <4C91B6BE.8020300@trash.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Cc: "David S. Miller" , Eric Dumazet , Mathieu Desnoyers , akpm@linux-foundation.org, netfilter-devel@vger.kernel.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org To: Changli Gao Return-path: Received: from stinky.trash.net ([213.144.137.162]:49412 "EHLO stinky.trash.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753584Ab0ITRIj (ORCPT ); Mon, 20 Sep 2010 13:08:39 -0400 In-Reply-To: Sender: netfilter-devel-owner@vger.kernel.org List-ID: On 20.09.2010 17:04, Changli Gao wrote: > On Thu, Sep 16, 2010 at 2:18 PM, Patrick McHardy wrote: >> On 21.08.2010 00:49, Changli Gao wrote: >>> Since we don't change the tuple in the original direction, we can save it >>> in ct->tuplehash[IP_CT_DIR_REPLY].hnode.pprev for __nf_conntrack_confirm() >>> use. >> >> I like this idea. We could actually do the same for the reply tuple >> and invalidate the saved hash in case the reply tuple is changed >> (nf_conntrack_alter_reply()), which only happens when NAT is used. >> > > We can't do that, as the unconfirmed ct owned maybe dropped, and > pre-computing will wast CPU cycles in this case. Sure we can, dropping unconfirmed conntracks is a rare exception, not a common case. Even under DoS we usually drop *unassured* conntracks, which have already enterered the hash. If we're unable to do that, we won't even allocate a new conntrack.