From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <konstantin.ananyev@intel.com>
Received: from mga14.intel.com (mga14.intel.com [192.55.52.115])
by dpdk.org (Postfix) with ESMTP id E83FF7F0C
for <dev@dpdk.org>; Fri, 21 Nov 2014 20:24:20 +0100 (CET)
Received: from fmsmga003.fm.intel.com ([10.253.24.29])
by fmsmga103.fm.intel.com with ESMTP; 21 Nov 2014 11:27:59 -0800
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="4.97,862,1389772800"; d="scan'208";a="419938943"
Received: from irsmsx107.ger.corp.intel.com ([163.33.3.99])
by FMSMGA003.fm.intel.com with ESMTP; 21 Nov 2014 11:25:23 -0800
Received: from irsmsx105.ger.corp.intel.com ([169.254.7.144]) by
IRSMSX107.ger.corp.intel.com ([169.254.10.117]) with mapi id 14.03.0195.001;
Fri, 21 Nov 2014 19:34:54 +0000
From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: "Chilikin, Andrey" <andrey.chilikin@intel.com>, "Wu, Jingjing"
<jingjing.wu@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Thread-Topic: [dpdk-dev] [PATCH v6 09/22] mbuf: extend fdir field
Thread-Index: AQHQBa0SBpxA0kbXTkORy3DLb8wnIpxrdwDA
Date: Fri, 21 Nov 2014 19:34:53 +0000
Message-ID: <2601191342CEEE43887BDE71AB977258213B87A6@IRSMSX105.ger.corp.intel.com>
References: <1414654006-7472-1-git-send-email-jingjing.wu@intel.com>
<1416530816-2159-1-git-send-email-jingjing.wu@intel.com>
<1416530816-2159-10-git-send-email-jingjing.wu@intel.com>
<AAC06825A3B29643AF5372F5E0DDF0533503494E@IRSMSX106.ger.corp.intel.com>
In-Reply-To: <AAC06825A3B29643AF5372F5E0DDF0533503494E@IRSMSX106.ger.corp.intel.com>
Accept-Language: en-IE, en-US
Content-Language: en-US
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
x-originating-ip: [163.33.239.182]
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: Re: [dpdk-dev] [PATCH v6 09/22] mbuf: extend fdir field
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
<mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
<mailto:dev-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Fri, 21 Nov 2014 19:24:21 -0000
Hi Andrey,
> -----Original Message-----
> From: Chilikin, Andrey
> Sent: Friday, November 21, 2014 5:03 PM
> To: Wu, Jingjing; dev@dpdk.org
> Cc: Ananyev, Konstantin
> Subject: RE: [dpdk-dev] [PATCH v6 09/22] mbuf: extend fdir field
>=20
> This patch adds extra 32bits to rte_mbuf::hash=20
Yes.
>- so 'uint32_t usr' will move to the second cache line?
>
Why is that?
hash is a union, so:
offsetof(struct rte_mbuf, hash.rss) =3D=3D offsetof(struct rte_mbuf, hash.u=
sr) =3D=3D 44
before and after patch.
As there still exists free space before rte_mbuf::userdata, whole rte_mbuf:=
:hash stays on the first cache line.
Konstantin
=20
=20
> Regards,
> Andrey
>=20
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Jingjing Wu
> Sent: Friday, November 21, 2014 12:47 AM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH v6 09/22] mbuf: extend fdir field
>=20
> fdir field in rte_mbuf is extened to support flex bytes reported when fdi=
r match.
> 8 flex bytes can be reported in maximum.
> The reported flex bytes are part of flexible payload.
>=20
> Signed-off-by: jingjing.wu <jingjing.wu@intel.com>
> ---
> lib/librte_mbuf/rte_mbuf.h | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>=20
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h inde=
x f5f8658..5899e5c 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -77,7 +77,7 @@ extern "C" {
> */
> #define PKT_RX_VLAN_PKT (1ULL << 0) /**< RX packet is a 802.1q VLA=
N packet. */
> #define PKT_RX_RSS_HASH (1ULL << 1) /**< RX packet with RSS hash r=
esult. */
> -#define PKT_RX_FDIR (1ULL << 2) /**< RX packet with FDIR infos=
. */
> +#define PKT_RX_FDIR (1ULL << 2) /**< RX packet with FDIR match=
indicate. */
> #define PKT_RX_L4_CKSUM_BAD (1ULL << 3) /**< L4 cksum of RX pkt. is no=
t OK. */ #define PKT_RX_IP_CKSUM_BAD (1ULL << 4)
> /**< IP cksum of RX pkt. is not OK. */ #define PKT_RX_EIP_CKSUM_BAD (0UL=
L << 0) /**< External IP header checksum error. */ @@
> -93,6 +93,8 @@ extern "C" { #define PKT_RX_IEEE1588_TMST (1ULL << 10) /*=
*< RX IEEE1588 L2/L4 timestamped packet.*/ #define
> PKT_RX_TUNNEL_IPV4_HDR (1ULL << 11) /**< RX tunnel packet with IPv4 heade=
r.*/ #define PKT_RX_TUNNEL_IPV6_HDR (1ULL <<
> 12) /**< RX tunnel packet with IPv6 header. */
> +#define PKT_RX_FDIR_ID (1ULL << 13) /**< FD id reported if FDIR ma=
tch. */
> +#define PKT_RX_FDIR_FLX (1ULL << 14) /**< Flexible bytes reported i=
f FDIR match. */
>=20
> #define PKT_TX_VLAN_PKT (1ULL << 55) /**< TX packet is a 802.1q VLA=
N packet. */
> #define PKT_TX_IP_CKSUM (1ULL << 54) /**< IP cksum of TX pkt. compu=
ted by NIC. */
> @@ -181,8 +183,17 @@ struct rte_mbuf {
> union {
> uint32_t rss; /**< RSS hash result if RSS enabled */
> struct {
> - uint16_t hash;
> - uint16_t id;
> + union {
> + struct {
> + uint16_t hash;
> + uint16_t id;
> + };
> + uint32_t lo;
> + /**< Second 4 flexible bytes */
> + };
> + uint32_t hi;
> + /**< First 4 flexible bytes or FD ID, dependent on
> + PKT_RX_FDIR_* flag in ol_flags. */
> } fdir; /**< Filter identifier if FDIR enabled */
> uint32_t sched; /**< Hierarchical scheduler */
> uint32_t usr; /**< User defined tags. See @rte_distributor_process *=
/
> --
> 1.8.1.4