From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by dpdk.org (Postfix) with ESMTP id 5D9767EB0 for ; Tue, 2 Dec 2014 17:15:46 +0100 (CET) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga101.fm.intel.com with ESMTP; 02 Dec 2014 08:10:55 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.07,501,1413270000"; d="scan'208";a="641423053" Received: from irsmsx155.ger.corp.intel.com ([163.33.192.3]) by fmsmga002.fm.intel.com with ESMTP; 02 Dec 2014 07:36:49 -0800 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.144]) by IRSMSX155.ger.corp.intel.com ([169.254.14.228]) with mapi id 14.03.0195.001; Tue, 2 Dec 2014 15:36:48 +0000 From: "Ananyev, Konstantin" To: didier.pallard , "Liu, Jijiang" , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH v4 3/3] mbuf:replace the inner_l2_len and the inner_l3_len fields Thread-Index: AQHQDj/6HpZk5vbjdEW8W8awA8SRIpx8Z2ag Date: Tue, 2 Dec 2014 15:36:48 +0000 Message-ID: <2601191342CEEE43887BDE71AB977258213BC075@IRSMSX105.ger.corp.intel.com> References: <1417503172-18642-1-git-send-email-jijiang.liu@intel.com> <1417503172-18642-4-git-send-email-jijiang.liu@intel.com> <547DD269.2080500@6wind.com> In-Reply-To: <547DD269.2080500@6wind.com> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.181] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v4 3/3] mbuf:replace the inner_l2_len and the inner_l3_len fields X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 02 Dec 2014 16:15:47 -0000 Hi Didier > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of didier.pallard > Sent: Tuesday, December 02, 2014 2:53 PM > To: Liu, Jijiang; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v4 3/3] mbuf:replace the inner_l2_len and = the inner_l3_len fields >=20 > Hello, >=20 > On 12/02/2014 07:52 AM, Jijiang Liu wrote: > > Replace the inner_l2_len and the inner_l3_len field with the outer_l2_l= en and outer_l3_len field, and rework csum forward engine > and i40e PMD due to these changes. > > > > Signed-off-by: Jijiang Liu > [...] > > --- a/lib/librte_mbuf/rte_mbuf.h > > +++ b/lib/librte_mbuf/rte_mbuf.h > > @@ -276,8 +276,8 @@ struct rte_mbuf { > > uint64_t tso_segsz:16; /**< TCP TSO segment size */ > > > > /* fields for TX offloading of tunnels */ > > - uint64_t inner_l3_len:9; /**< inner L3 (IP) Hdr Length. */ > > - uint64_t inner_l2_len:7; /**< inner L2 (MAC) Hdr Length. */ > > + uint64_t outer_l3_len:9; /**< Outer L3 (IP) Hdr Length. */ > > + uint64_t outer_l2_len:7; /**< Outer L2 (MAC) Hdr Length. */ > > > > /* uint64_t unused:8; */ > > }; >=20 > Sorry for entering lately this discussion, but i'm not convinced by the > choice of outer_lx_len rather than inner_lx_len for new fields. > I agree with Olivier that new flags should only be related to the use of > new fields, to maintain coherency with oldest implementations. > But from a stack point of view, i think it is better to have lx_len > fields that target the outer layers, and to name new fields inner_lx_len. >=20 > Let's discuss the two possibilities. >=20 > 1) outer_lx_len fields are introduced. > In this case, the stack should have knowledge that it is processing > tunneled packets to use outer_lx_len rather than lx_len, > or stack should always use outer_lx_len packet and move those fields to > lx_len packets if no tunneling occurs... > I think it will induce extra processing that does not seem to be really > needed. >=20 > 2) inner_lx_len fields are introduced. > In this case, the stack first uses lx_len fields. When packet should be > tunneled, lx_len fields are moved to inner_lx_len fields. > Then the stack can process the outer layer and still use the lx_len field= s. Not sure, that I understood why 2) is better than 1). Let say, you have a 'normal' (non-tunnelling) packet: ether/IP/TCP In that case you still use mbuf's l2_len/l3_len/l4_len fields and setup ol_= flags as usual. Then later, you decided to 'tunnel' that packet. So you just fill mbuf's outer_l2_len/outer_l3_len, setup TX_OUTER_* and TX_= TUNNEL_* bits in ol_flags and probably update l2_len. l3_len/l4_len and ol_flags bits set for them remain intact. That's with 1) With 2) - you'll have to move l3_len/l4_len to inner_lx_len.=20 And I suppose ol_flags values too: ol_flags &=3D ~PKT_ IP_CKSUM; ol_flgas |=3D PKT_INNER_IP_CKSUM ? And same for L4_CKSUM flags too? Konstantin >=20 > For example: > an eth/IP/TCP forged packet will look like this: >=20 > Ether/IP/UDP/xxx > m->flags =3D IP_CKSUM > m->l2_len =3D sizeof(ether) > m->l3_len =3D sizeof(ip) > m->l4_len =3D sizeof(udp) > m->inner_l2_len =3D 0 > m->inner_l3_len =3D 0 >=20 > When entering tunnel for example a VXLAN interface, lx_len will be moved > to inner_lx_len >=20 > Ether/IP/UDP/xxx > m->flags =3D INNER_IP_CKSUM > m->l2_len =3D 0 > m->l3_len =3D 0 > m->l4_len =3D 0 > m->inner_l2_len =3D sizeof(ether) > m->inner_l3_len =3D sizeof(ip) >=20 >=20 > once complete encapsulation is processed by the stack, the packet will > look like >=20 > Ether/IP/UDP/VXLAN/Ether/IP/UDP/xxx > m->flags =3D IP_CKSUM | INNER_IP_CKSUM > m->l2_len =3D sizeof(ether) > m->l3_len =3D sizeof(ip) > m->l4_len =3D sizeof(udp) > m->inner_l2_len =3D sizeof(ether) + sizeof (vxlan) > m->inner_l3_len =3D sizeof(ip) >=20 >=20 > didier >=20