From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <jingjing.wu@intel.com>
Received: from mga05.intel.com (mga05.intel.com [192.55.52.43])
 by dpdk.org (Postfix) with ESMTP id 8EF2E19F5
 for <dev@dpdk.org>; Mon, 10 Oct 2016 05:59:01 +0200 (CEST)
Received: from fmsmga001.fm.intel.com ([10.253.24.23])
 by fmsmga105.fm.intel.com with ESMTP; 09 Oct 2016 20:59:00 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.31,470,1473145200"; d="scan'208";a="1051606769"
Received: from fmsmsx108.amr.corp.intel.com ([10.18.124.206])
 by fmsmga001.fm.intel.com with ESMTP; 09 Oct 2016 20:59:01 -0700
Received: from fmsmsx157.amr.corp.intel.com (10.18.116.73) by
 FMSMSX108.amr.corp.intel.com (10.18.124.206) with Microsoft SMTP Server (TLS)
 id 14.3.248.2; Sun, 9 Oct 2016 20:59:00 -0700
Received: from shsmsx152.ccr.corp.intel.com (10.239.6.52) by
 FMSMSX157.amr.corp.intel.com (10.18.116.73) with Microsoft SMTP Server (TLS)
 id 14.3.248.2; Sun, 9 Oct 2016 20:58:59 -0700
Received: from shsmsx103.ccr.corp.intel.com ([169.254.4.234]) by
 SHSMSX152.ccr.corp.intel.com ([169.254.6.95]) with mapi id 14.03.0248.002;
 Mon, 10 Oct 2016 11:58:57 +0800
From: "Wu, Jingjing" <jingjing.wu@intel.com>
To: Zhe Tao <zhe.tao@intel.com>, "dev@dpdk.org" <dev@dpdk.org>, "Yigit,
 Ferruh" <ferruh.yigit@intel.com>
Thread-Topic: [dpdk-dev] [PATCH v2] i40: fix the VXLAN TSO issue
Thread-Index: AQHR2AfRhPBmlmFBoU+42Dq8j2MSdKChpKtQ
Date: Mon, 10 Oct 2016 03:58:57 +0000
Message-ID: <9BB6961774997848B5B42BEC655768F80E2779DA@SHSMSX103.ccr.corp.intel.com>
References: <1467752375-25984-1-git-send-email-zhe.tao@intel.com>
 <1467865627-23524-1-git-send-email-zhe.tao@intel.com>
In-Reply-To: <1467865627-23524-1-git-send-email-zhe.tao@intel.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
x-originating-ip: [10.239.127.40]
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: Re: [dpdk-dev] [PATCH v2] i40: fix the VXLAN TSO issue
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: Mon, 10 Oct 2016 03:59:02 -0000

NACK.

This fix has been done by a new one which is already merged:  http://dpdk.o=
rg/dev/patchwork/patch/15059/


> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Zhe Tao
> Sent: Thursday, July 7, 2016 12:27 PM
> To: dev@dpdk.org
> Cc: zhe.tao@intel.com; Wu, Jingjing <jingjing.wu@intel.com>
> Subject: [dpdk-dev] [PATCH v2] i40: fix the VXLAN TSO issue
>=20
> Problem:
> When using the TSO + VXLAN feature in i40e, the outer UDP length fields i=
n
> the multiple UDP segments which are TSOed by the i40e will have the wrong
> value.
>=20
> Fix this problem by adding the tunnel type field in the i40e descriptor w=
hich
> was missed before.
>=20
> Fixes: 77b8301733c3 ("i40e: VXLAN Tx checksum offload")
>=20
> Signed-off-by: Zhe Tao <zhe.tao@intel.com>
> ---
> V2: Edited some comments for mbuf structure and i40e driver.
>=20
>  app/test-pmd/csumonly.c      | 26 +++++++++++++++++++-------
>  drivers/net/i40e/i40e_rxtx.c | 12 +++++++++---
>  lib/librte_mbuf/rte_mbuf.h   | 16 +++++++++++++++-
>  3 files changed, 43 insertions(+), 11 deletions(-)
>=20
> diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c index
> ac4bd8f..d423c20 100644
> --- a/app/test-pmd/csumonly.c
> +++ b/app/test-pmd/csumonly.c
> @@ -204,7 +204,8 @@ parse_ethernet(struct ether_hdr *eth_hdr, struct
> testpmd_offload_info *info)  static void  parse_vxlan(struct udp_hdr
> *udp_hdr,
>  	    struct testpmd_offload_info *info,
> -	    uint32_t pkt_type)
> +	    uint32_t pkt_type,
> +	    uint64_t *ol_flags)
>  {
>  	struct ether_hdr *eth_hdr;
>=20
> @@ -215,6 +216,7 @@ parse_vxlan(struct udp_hdr *udp_hdr,
>  		RTE_ETH_IS_TUNNEL_PKT(pkt_type) =3D=3D 0)
>  		return;
>=20
> +	*ol_flags |=3D PKT_TX_TUNNEL_VXLAN;
>  	info->is_tunnel =3D 1;
>  	info->outer_ethertype =3D info->ethertype;
>  	info->outer_l2_len =3D info->l2_len;
> @@ -231,7 +233,9 @@ parse_vxlan(struct udp_hdr *udp_hdr,
>=20
>  /* Parse a gre header */
>  static void
> -parse_gre(struct simple_gre_hdr *gre_hdr, struct testpmd_offload_info
> *info)
> +parse_gre(struct simple_gre_hdr *gre_hdr,
> +	  struct testpmd_offload_info *info,
> +	  uint64_t *ol_flags)
>  {
>  	struct ether_hdr *eth_hdr;
>  	struct ipv4_hdr *ipv4_hdr;
> @@ -242,6 +246,8 @@ parse_gre(struct simple_gre_hdr *gre_hdr, struct
> testpmd_offload_info *info)
>  	if ((gre_hdr->flags & _htons(~GRE_SUPPORTED_FIELDS)) !=3D 0)
>  		return;
>=20
> +	*ol_flags |=3D PKT_TX_TUNNEL_GRE;
> +
>  	gre_len +=3D sizeof(struct simple_gre_hdr);
>=20
>  	if (gre_hdr->flags & _htons(GRE_KEY_PRESENT)) @@ -417,7 +423,7
> @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info
> *info,
>   * packet */
>  static uint64_t
>  process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info
> *info,
> -	uint16_t testpmd_ol_flags)
> +	uint16_t testpmd_ol_flags, uint64_t orig_ol_flags)
>  {
>  	struct ipv4_hdr *ipv4_hdr =3D outer_l3_hdr;
>  	struct ipv6_hdr *ipv6_hdr =3D outer_l3_hdr; @@ -442,6 +448,9 @@
> process_outer_cksums(void *outer_l3_hdr, struct testpmd_offload_info
> *info,
>  	 * hardware supporting it today, and no API for it. */
>=20
>  	udp_hdr =3D (struct udp_hdr *)((char *)outer_l3_hdr + info-
> >outer_l3_len);
> +	if ((orig_ol_flags & PKT_TX_TCP_SEG) &&
> +	    ((orig_ol_flags & PKT_TX_TUNNEL_MASK) =3D=3D
> PKT_TX_TUNNEL_VXLAN))
> +		udp_hdr->dgram_cksum =3D 0;
>  	/* do not recalculate udp cksum if it was 0 */
>  	if (udp_hdr->dgram_cksum !=3D 0) {
>  		udp_hdr->dgram_cksum =3D 0;
> @@ -705,15 +714,18 @@ pkt_burst_checksum_forward(struct fwd_stream
> *fs)
>  			if (info.l4_proto =3D=3D IPPROTO_UDP) {
>  				struct udp_hdr *udp_hdr;
>  				udp_hdr =3D (struct udp_hdr *)((char *)l3_hdr
> +
> -					info.l3_len);
> -				parse_vxlan(udp_hdr, &info, m-
> >packet_type);
> +					   info.l3_len);
> +				parse_vxlan(udp_hdr, &info, m-
> >packet_type,
> +					    &ol_flags);
>  			} else if (info.l4_proto =3D=3D IPPROTO_GRE) {
>  				struct simple_gre_hdr *gre_hdr;
>  				gre_hdr =3D (struct simple_gre_hdr *)
>  					((char *)l3_hdr + info.l3_len);
> -				parse_gre(gre_hdr, &info);
> +				parse_gre(gre_hdr, &info, &ol_flags);
>  			} else if (info.l4_proto =3D=3D IPPROTO_IPIP) {
>  				void *encap_ip_hdr;
> +
> +				ol_flags |=3D PKT_TX_TUNNEL_IPIP;
>  				encap_ip_hdr =3D (char *)l3_hdr + info.l3_len;
>  				parse_encap_ip(encap_ip_hdr, &info);
>  			}
> @@ -745,7 +757,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
>  		 * processed in hardware. */
>  		if (info.is_tunnel =3D=3D 1) {
>  			ol_flags |=3D process_outer_cksums(outer_l3_hdr,
> &info,
> -				testpmd_ol_flags);
> +				testpmd_ol_flags, ol_flags);
>  		}
>=20
>  		/* step 4: fill the mbuf meta data (flags and header lengths)
> */ diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx=
.c
> index 049a813..4c987f2 100644
> --- a/drivers/net/i40e/i40e_rxtx.c
> +++ b/drivers/net/i40e/i40e_rxtx.c
> @@ -801,6 +801,12 @@ i40e_txd_enable_checksum(uint64_t ol_flags,
>  			union i40e_tx_offload tx_offload,
>  			uint32_t *cd_tunneling)
>  {
> +	/* Tx pkts tunnel type*/
> +	if ((ol_flags & PKT_TX_TUNNEL_MASK) =3D=3D PKT_TX_TUNNEL_VXLAN)
> +		*cd_tunneling |=3D I40E_TXD_CTX_UDP_TUNNELING;
> +	else if ((ol_flags & PKT_TX_TUNNEL_MASK) =3D=3D
> PKT_TX_TUNNEL_GRE)
> +		*cd_tunneling |=3D I40E_TXD_CTX_GRE_TUNNELING;
> +
>  	/* UDP tunneling packet TX checksum offload */
>  	if (ol_flags & PKT_TX_OUTER_IP_CKSUM) {
>=20
> @@ -1510,7 +1516,8 @@ i40e_calc_context_desc(uint64_t flags)
>=20
>  /* set i40e TSO context descriptor */
>  static inline uint64_t
> -i40e_set_tso_ctx(struct rte_mbuf *mbuf, union i40e_tx_offload tx_offload=
)
> +i40e_set_tso_ctx(struct rte_mbuf *mbuf,
> +		 union i40e_tx_offload tx_offload)
>  {
>  	uint64_t ctx_desc =3D 0;
>  	uint32_t cd_cmd, hdr_len, cd_tso_len;
> @@ -1521,7 +1528,7 @@ i40e_set_tso_ctx(struct rte_mbuf *mbuf, union
> i40e_tx_offload tx_offload)
>  	}
>=20
>  	/**
> -	 * in case of tunneling packet, the outer_l2_len and
> +	 * in case of non tunneling packet, the outer_l2_len and
>  	 * outer_l3_len must be 0.
>  	 */
>  	hdr_len =3D tx_offload.outer_l2_len +
> @@ -1537,7 +1544,6 @@ i40e_set_tso_ctx(struct rte_mbuf *mbuf, union
> i40e_tx_offload tx_offload)
>  		 I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
>  		((uint64_t)mbuf->tso_segsz <<
>  		 I40E_TXD_CTX_QW1_MSS_SHIFT);
> -
>  	return ctx_desc;
>  }
>=20
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h inde=
x
> 15e3a10..8eb0d33 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -133,6 +133,17 @@ extern "C" {
>  /* add new TX flags here */
>=20
>  /**
> + * Bits 45:48 used for the tunnel type.
> + * When doing Tx offload like TSO or checksum, the HW needs to
> +configure the
> + * tunnel type into the HW descriptors.
> + */
> +#define PKT_TX_TUNNEL_VXLAN   (1ULL << 45)
> +#define PKT_TX_TUNNEL_GRE   (2ULL << 45)
> +#define PKT_TX_TUNNEL_IPIP    (3ULL << 45)
> +/* add new TX TUNNEL type here */
> +#define PKT_TX_TUNNEL_MASK    (0xFULL << 45)
> +
> +/**
>   * Second VLAN insertion (QinQ) flag.
>   */
>  #define PKT_TX_QINQ_PKT    (1ULL << 49)   /**< TX packet with double
> VLAN inserted. */
> @@ -867,7 +878,10 @@ struct rte_mbuf {
>  	union {
>  		uint64_t tx_offload;       /**< combined for easy fetch */
>  		struct {
> -			uint64_t l2_len:7; /**< L2 (MAC) Header Length. */
> +			/* L2 (MAC) Header Length if it is not a tunneling pkt.
> +			 * for tunnel it is outer L4 len+tunnel len+inner L2 len
> +			 */
> +			uint64_t l2_len:7;
>  			uint64_t l3_len:9; /**< L3 (IP) Header Length. */
>  			uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length.
> */
>  			uint64_t tso_segsz:16; /**< TCP TSO segment size */
> --
> 2.1.4