Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753695AbYKXVEt (ORCPT ); Mon, 24 Nov 2008 16:04:49 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752199AbYKXVEi (ORCPT ); Mon, 24 Nov 2008 16:04:38 -0500 Received: from mga09.intel.com ([134.134.136.24]:35692 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752776AbYKXVEh convert rfc822-to-8bit (ORCPT ); Mon, 24 Nov 2008 16:04:37 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.33,661,1220252400"; d="scan'208";a="363825890" From: "Brandeburg, Jesse" To: Ben Hutchings , Jan-Bernd Themann CC: "netdev@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "tklein@de.ibm.com" , Christoph Raisch , "jb.billaud@gmail.com" , "hering2@de.ibm.com" Date: Mon, 24 Nov 2008 13:04:33 -0800 Subject: RE: [RFC PATCH] lro: ip fragment checking Thread-Topic: [RFC PATCH] lro: ip fragment checking Thread-Index: AclOVOr84U585F5cSvCCirNHQnfJ+QAIuSiA Message-ID: References: <492ACEC4.3020702@de.ibm.com> <1227545468.3162.4.camel@achroite> In-Reply-To: <1227545468.3162.4.camel@achroite> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1360 Lines: 25 Ben Hutchings wrote: > On Mon, 2008-11-24 at 16:56 +0100, Jan-Bernd Themann wrote: >> Currently there is no checking in the LRO receive path whether >> TCP packets are ip fragmented. We should not consider >> those packets for aggregation. >> I'm not sure if this checking is actually required. Does anyone >> know if it is possible to get fragmented TCP packets without >> the tcp stack changing the MSS size? >> This patch introduces explicit checking. Any objections? > > LRO depends on the hardware performing TCP checksum offload, and the > TCP checksum cannot be verified for IP fragments in isolation. So I > think drivers should not be passing fragments into inet_lro or should > reject them in its get_frag_header() or get_skb_header() method. > Certainly sfc doesn't pass fragments into inet_lro because they have > not been checksummed. The fragments, definitely will not have checksums offloaded, but what about the first packet in the chain? I haven't verified in ixgbe or igb whether or not it could try and aggregate a packet with MF set if it was the first fragment in a series of IP fragments.-- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/