From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 1ACA17EB0 for ; Thu, 4 Dec 2014 17:21:38 +0100 (CET) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP; 04 Dec 2014 08:20:27 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.07,516,1413270000"; d="scan'208";a="642421062" Received: from irsmsx106.ger.corp.intel.com ([163.33.3.31]) by fmsmga002.fm.intel.com with ESMTP; 04 Dec 2014 08:20:26 -0800 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.144]) by IRSMSX106.ger.corp.intel.com ([169.254.8.18]) with mapi id 14.03.0195.001; Thu, 4 Dec 2014 16:20:23 +0000 From: "Ananyev, Konstantin" To: "Richardson, Bruce" Thread-Topic: [dpdk-dev] [PATCH 2/2] ixgbe: don't override mbuf buffer length Thread-Index: AQHQD85vrzKVJNav6E2ecmauZYfKoZx/gkeggAAIQACAAAIlgIAAAqGAgAABBFA= Date: Thu, 4 Dec 2014 16:20:22 +0000 Message-ID: <2601191342CEEE43887BDE71AB977258213BCB2D@IRSMSX105.ger.corp.intel.com> References: <1417703181-23093-1-git-send-email-jean-mickael.guerin@6wind.com> <1417703181-23093-3-git-send-email-jean-mickael.guerin@6wind.com> <2601191342CEEE43887BDE71AB977258213BCA29@IRSMSX105.ger.corp.intel.com> <20141204151500.GC9300@bricha3-MOBL3> <2601191342CEEE43887BDE71AB977258213BCA80@IRSMSX105.ger.corp.intel.com> <20141204153204.GD9300@bricha3-MOBL3> In-Reply-To: <20141204153204.GD9300@bricha3-MOBL3> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.180] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] [PATCH 2/2] ixgbe: don't override mbuf buffer length 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: Thu, 04 Dec 2014 16:21:39 -0000 > -----Original Message----- > From: Richardson, Bruce > Sent: Thursday, December 04, 2014 3:32 PM > To: Ananyev, Konstantin > Cc: Jean-Mickael Guerin; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 2/2] ixgbe: don't override mbuf buffer len= gth >=20 > On Thu, Dec 04, 2014 at 03:29:04PM +0000, Ananyev, Konstantin wrote: > > > > > > > -----Original Message----- > > > From: Richardson, Bruce > > > Sent: Thursday, December 04, 2014 3:15 PM > > > To: Ananyev, Konstantin > > > Cc: Jean-Mickael Guerin; dev@dpdk.org > > > Subject: Re: [dpdk-dev] [PATCH 2/2] ixgbe: don't override mbuf buffer= length > > > > > > On Thu, Dec 04, 2014 at 02:50:11PM +0000, Ananyev, Konstantin wrote: > > > > Hi, > > > > > > > > > -----Original Message----- > > > > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Jean-Mickael= Guerin > > > > > Sent: Thursday, December 04, 2014 2:26 PM > > > > > To: dev@dpdk.org > > > > > Subject: [dpdk-dev] [PATCH 2/2] ixgbe: don't override mbuf buffer= length > > > > > > > > > > The template mbuf_initializer is hard coded with a buflen which > > > > > might have been set differently by the application at the time of > > > > > mbuf pool creation. > > > > > > > > > > Switch to a mbuf allocation, to fetch the correct default values. > > > > > There is no performance impact because this is not a data-plane A= PI. > > > > > > > > > > Signed-off-by: Jean-Mickael Guerin > > > > > Acked-by: David Marchand > > > > > Fixes: 0ff3324da2 ("ixgbe: rework vector pmd following mbuf chang= es") > > > > > --- > > > > > lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 19 ++++++++++++------- > > > > > 1 file changed, 12 insertions(+), 7 deletions(-) > > > > > > > > > > diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_p= md_ixgbe/ixgbe_rxtx_vec.c > > > > > index c1b5a78..f7b02f5 100644 > > > > > --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c > > > > > +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c > > > > > @@ -732,17 +732,22 @@ static struct ixgbe_txq_ops vec_txq_ops =3D= { > > > > > int > > > > > ixgbe_rxq_vec_setup(struct igb_rx_queue *rxq) > > > > > { > > > > > - struct rte_mbuf mb_def =3D { .buf_addr =3D 0 }; /* zeroed mbuf = */ > > > > > + struct rte_mbuf *mb_def; > > > > > > > > > > - mb_def.nb_segs =3D 1; > > > > > - mb_def.data_off =3D RTE_PKTMBUF_HEADROOM; > > > > > - mb_def.buf_len =3D rxq->mb_pool->elt_size - sizeof(struct rte_m= buf); > > > > > - mb_def.port =3D rxq->port_id; > > > > > - rte_mbuf_refcnt_set(&mb_def, 1); > > > > > + mb_def =3D rte_pktmbuf_alloc(rxq->mb_pool); > > > > > > > > Could you explain to me, what is an advantage of using dynamic allo= cation vs local struct here? > > > > I don't see any. > > > > > > It means that we get an mbuf that is initialized as done by the initi= alization > > > function passed to the mempool_create call. The static variable metho= d assumes > > > that we configure the mbuf using default setting for buf_len etc. > > > > > > > I understand that, but why it can't be done in some other way? > > Without allocating/freeing? > > Let say, at mempool_create() store obj_init() and then add ability to c= all it again? > > Anyway, it doesn't look to me like a critical problem, that requires an= urgent patch for 1.8. > > > > > > Plus if rte_pktmbuf_alloc() would fail, we'll leave our rx queue no= t configured properly. > > > > As I can see ixgbe_dev_rx_queue_setup() doesn't check the return va= lue of > ixgbe_rxq_vec_setup() > > > > (as it is just not supposed to fail). > > > > So ixgbe_dev_rx_queue_setup() will return OK for unconfigured RX qu= eue. > > > > > > Good catch, that's something that should perhaps be looked at in a V2= patch, I > > > think. > > > > > > > > > > > > + if (mb_def =3D=3D NULL) { > > > > > + PMD_INIT_LOG(ERR, "ixgbe_rxq_vec_setup: could not allocate one= mbuf"); > > > > > + return -1; > > > > > + } > > > > > + /* nb_segs, refcnt, data_off and buf_len are already set */ > > > > > + mb_def->port =3D rxq->port_id; > > > > > > > > > > /* prevent compiler reordering: rearm_data covers previous fiel= ds */ > > > > > rte_compiler_barrier(); > > > > > > > > I don't think we need it here. > > > > > > I think we might, as the compiler doesn't know that the rearm data ov= erlaps > > > with the previously set fields, so may reorder the reads and writes t= hinking > > > they are independent. > > > > Why it doesn't? > > I suppose compiler has all the knowledge of the mbuf structure layout a= t that point. > > Or there is a some sort of bug in some version of the compiler? > > >=20 > No, we're just violating the layout here by dereferencing past the end of= the array :-) So are you saying, that any code like: extern uint64_t *p; struct {uint32_t a[1], b;} x; x.b =3D 2; L1: =20 *p =3D (uint64_t *)&x.a;=20 Would require a compiler barrier at L1? >=20 > /Bruce >=20 > > > > > > > > > - rxq->mbuf_initializer =3D *((uint64_t *)&mb_def.rearm_data); > > > > > + rxq->mbuf_initializer =3D *((uint64_t *)&mb_def->rearm_data); > > > > > + > > > > > + rte_pktmbuf_free(mb_def); > > > > > + > > > > > return 0; > > > > > } > > > > > > > > > > -- > > > > > 2.1.3 > > > > > > > > Somy vote - NACK for the whole series. > > > > Konstantin > > > >