From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: "Tan, Jianfeng" <jianfeng.tan@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "thomas.monjalon@6wind.com" <thomas.monjalon@6wind.com>,
"De Lara Guarch, Pablo" <pablo.de.lara.guarch@intel.com>,
"Wu, Jingjing" <jingjing.wu@intel.com>,
"Zhang, Helin" <helin.zhang@intel.com>,
"Tao, Zhe" <zhe.tao@intel.com>
Subject: Re: [dpdk-dev] [PATCH v4 3/3] app/testpmd: fix Tx offload on tunneling packet
Date: Mon, 19 Sep 2016 12:09:41 +0000 [thread overview]
Message-ID: <2601191342CEEE43887BDE71AB9772583F0B57BD@irsmsx105.ger.corp.intel.com> (raw)
In-Reply-To: <1470023815-23108-4-git-send-email-jianfeng.tan@intel.com>
Hi Jainfeng,
> -----Original Message-----
> From: Tan, Jianfeng
> Sent: Monday, August 1, 2016 4:57 AM
> To: dev@dpdk.org
> Cc: thomas.monjalon@6wind.com; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Ananyev, Konstantin
> <konstantin.ananyev@intel.com>; Wu, Jingjing <jingjing.wu@intel.com>; Zhang, Helin <helin.zhang@intel.com>; Tan, Jianfeng
> <jianfeng.tan@intel.com>; Tao, Zhe <zhe.tao@intel.com>
> Subject: [PATCH v4 3/3] app/testpmd: fix Tx offload on tunneling packet
>
> Tx offload on tunneling packet now requires applications to correctly set tunneling type. Without setting it, i40e driver does not parse
> tunneling parameters. Besides that, add a check to see if NIC supports TSO on tunneling packet when executing "csum parse_tunnel on
> _port"
> after "tso set _size _port" or the other way around.
>
> Fixes: b51c47536a9e ("app/testpmd: support TSO in checksum forward engine")
>
> Signed-off-by: Zhe Tao <zhe.tao@intel.com>
> Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
> ---
> app/test-pmd/cmdline.c | 42 ++++++++++++++++++++++++++++++++++++------
> app/test-pmd/csumonly.c | 37 +++++++++++++++++++++++++++++--------
> 2 files changed, 65 insertions(+), 14 deletions(-)
>
> diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c index f90befc..561839f 100644
> --- a/app/test-pmd/cmdline.c
> +++ b/app/test-pmd/cmdline.c
> @@ -3426,6 +3426,26 @@ struct cmd_csum_tunnel_result { };
>
> static void
> +check_tunnel_tso_support(uint8_t port_id) {
> + struct rte_eth_dev_info dev_info;
> +
> + rte_eth_dev_info_get(port_id, &dev_info);
> + if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_VXLAN_TNL_TSO))
> + printf("Warning: TSO enabled but VXLAN TUNNEL TSO not "
> + "supported by port %d\n", port_id);
> + if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_GRE_TNL_TSO))
> + printf("Warning: TSO enabled but GRE TUNNEL TSO not "
> + "supported by port %d\n", port_id);
> + if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_IPIP_TNL_TSO))
> + printf("Warning: TSO enabled but IPIP TUNNEL TSO not "
> + "supported by port %d\n", port_id);
> + if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_GENEVE_TNL_TSO))
> + printf("Warning: TSO enabled but GENEVE TUNNEL TSO not "
> + "supported by port %d\n", port_id); }
> +
> +static void
> cmd_csum_tunnel_parsed(void *parsed_result,
> __attribute__((unused)) struct cmdline *cl,
> __attribute__((unused)) void *data) @@ -3435,10 +3455,13 @@ cmd_csum_tunnel_parsed(void *parsed_result,
> if (port_id_is_invalid(res->port_id, ENABLED_WARN))
> return;
>
> - if (!strcmp(res->onoff, "on"))
> + if (!strcmp(res->onoff, "on")) {
> ports[res->port_id].tx_ol_flags |=
> TESTPMD_TX_OFFLOAD_PARSE_TUNNEL;
> - else
> +
> + if (ports[res->port_id].tso_segsz != 0)
> + check_tunnel_tso_support(res->port_id);
> + } else
> ports[res->port_id].tx_ol_flags &=
> (~TESTPMD_TX_OFFLOAD_PARSE_TUNNEL);
>
> @@ -3502,10 +3525,17 @@ cmd_tso_set_parsed(void *parsed_result,
>
> /* display warnings if configuration is not supported by the NIC */
> rte_eth_dev_info_get(res->port_id, &dev_info);
> - if ((ports[res->port_id].tso_segsz != 0) &&
> - (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_TCP_TSO) == 0) {
> - printf("Warning: TSO enabled but not "
> - "supported by port %d\n", res->port_id);
> + if (ports[res->port_id].tso_segsz != 0) {
> + if (ports[res->port_id].tx_ol_flags &
> + TESTPMD_TX_OFFLOAD_PARSE_TUNNEL)
> + check_tunnel_tso_support(res->port_id);
> + /* For packets,
> + * (1) when tnl parse is disabled;
> + * (2) when tnl parse is enabled but not deemed as tnl pkts
> + */
> + if (!(dev_info.tx_offload_capa & DEV_TX_OFFLOAD_TCP_TSO))
> + printf("Warning: TSO enabled but not "
> + "supported by port %d\n", res->port_id);
> }
> }
>
> diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c index ac4bd8f..0a1f95d 100644
> --- a/app/test-pmd/csumonly.c
> +++ b/app/test-pmd/csumonly.c
> @@ -412,12 +412,10 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
> return ol_flags;
> }
>
> -/* Calculate the checksum of outer header (only vxlan is supported,
> - * meaning IP + UDP). The caller already checked that it's a vxlan
> - * packet */
> +/* Calculate the checksum of outer header */
> 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, int tso_enabled)
> {
> struct ipv4_hdr *ipv4_hdr = outer_l3_hdr;
> struct ipv6_hdr *ipv6_hdr = outer_l3_hdr; @@ -438,10 +436,20 @@ process_outer_cksums(void *outer_l3_hdr, struct
> testpmd_offload_info *info,
> if (info->outer_l4_proto != IPPROTO_UDP)
> return ol_flags;
>
> - /* outer UDP checksum is always done in software as we have no
> - * hardware supporting it today, and no API for it. */
> -
> udp_hdr = (struct udp_hdr *)((char *)outer_l3_hdr + info->outer_l3_len);
> +
> + /* outer UDP checksum is done in software as we have no hardware
> + * supporting it today, and no API for it. In the other side, for
> + * UDP tunneling, like VXLAN or Geneve, outer UDP checksum can be
> + * set to zero.
> + *
> + * If a packet will be TSOed into small packets by NIC, we cannot
> + * set/calculate a non-zero checksum, because it will be a wrong
> + * value after the packet be split into several small packets.
> + */
> + if (tso_enabled)
> + udp_hdr->dgram_cksum = 0;
> +
> /* do not recalculate udp cksum if it was 0 */
> if (udp_hdr->dgram_cksum != 0) {
> udp_hdr->dgram_cksum = 0;
> @@ -704,18 +712,27 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_PARSE_TUNNEL) {
> if (info.l4_proto == IPPROTO_UDP) {
> struct udp_hdr *udp_hdr;
> +
> udp_hdr = (struct udp_hdr *)((char *)l3_hdr +
> info.l3_len);
> parse_vxlan(udp_hdr, &info, m->packet_type);
> + if (info.is_tunnel)
> + ol_flags |= PKT_TX_TUNNEL_VXLAN;
> } else if (info.l4_proto == IPPROTO_GRE) {
> struct simple_gre_hdr *gre_hdr;
> +
> gre_hdr = (struct simple_gre_hdr *)
> ((char *)l3_hdr + info.l3_len);
> parse_gre(gre_hdr, &info);
> + if (info.is_tunnel)
> + ol_flags |= PKT_TX_TUNNEL_GRE;
> } else if (info.l4_proto == IPPROTO_IPIP) {
> void *encap_ip_hdr;
> +
> encap_ip_hdr = (char *)l3_hdr + info.l3_len;
> parse_encap_ip(encap_ip_hdr, &info);
> + if (info.is_tunnel)
> + ol_flags |= PKT_TX_TUNNEL_IPIP;
> }
> }
>
> @@ -745,7 +762,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> * processed in hardware. */
> if (info.is_tunnel == 1) {
> ol_flags |= process_outer_cksums(outer_l3_hdr, &info,
> - testpmd_ol_flags);
> + testpmd_ol_flags, ol_flags & PKT_TX_TCP_SEG);
> }
>
> /* step 4: fill the mbuf meta data (flags and header lengths) */ @@ -806,6 +823,10 @@
It was a while since I looked a t it closely, but shouldn't you also update step 4 below:
if (info.is_tunnel == 1) {
if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) {
m->outer_l2_len = info.outer_l2_len;
m->outer_l3_len = info.outer_l3_len;
m->l2_len = info.l2_len;
m->l3_len = info.l3_len;
m->l4_len = info.l4_len;
}
else {
/* if there is a outer UDP cksum
processed in sw and the inner in hw,
the outer checksum will be wrong as
the payload will be modified by the
hardware */
m->l2_len = info.outer_l2_len +
info.outer_l3_len + info.l2_len;
m->l3_len = info.l3_len;
m->l4_len = info.l4_len;
}
?
In particular shouldn't it be something like:
if ((testpmd_ol_flags & TESTPMD_TX_OFFLOAD_OUTER_IP_CKSUM) != 0 ||
((testmpd_ol_flags & TESTPMD_TX_OFFLOAD_PARSE_TUNNEL) != 0 && info.tso_segsz != 0)) {
....
?
Another thought, might be it is worth to introduce new flag: TESTPMD_TX_OFFLOAD_TSO_TUNNEL,
and new command in cmdline.c, that would set/clear that flag.
Instead of trying to make assumptions does
user wants tso for tunneled packets based on 2 different things:
- enable/disable tso
- enable/disable tunneled packets parsing
?
Konstantin
> pkt_burst_checksum_forward(struct fwd_stream *fs)
> { PKT_TX_OUTER_IPV4, PKT_TX_OUTER_IPV4 },
> { PKT_TX_OUTER_IPV6, PKT_TX_OUTER_IPV6 },
> { PKT_TX_TCP_SEG, PKT_TX_TCP_SEG },
> + { PKT_TX_TUNNEL_VXLAN, PKT_TX_TUNNEL_MASK },
> + { PKT_TX_TUNNEL_GRE, PKT_TX_TUNNEL_MASK },
> + { PKT_TX_TUNNEL_IPIP, PKT_TX_TUNNEL_MASK },
> + { PKT_TX_TUNNEL_GENEVE, PKT_TX_TUNNEL_MASK },
> };
> unsigned j;
> const char *name;
> --
> 2.7.4
next prev parent reply other threads:[~2016-09-19 12:09 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-05 20:59 [dpdk-dev] [PATCH v1] i40: fix the VXLAN TSO issue Zhe Tao
2016-07-06 5:38 ` Wu, Jingjing
2016-07-07 4:27 ` [dpdk-dev] [PATCH v2] " Zhe Tao
2016-07-07 10:01 ` Ananyev, Konstantin
2016-07-07 10:50 ` Ananyev, Konstantin
2016-07-07 12:24 ` Ananyev, Konstantin
2016-07-15 15:40 ` Bruce Richardson
2016-07-18 2:57 ` Zhe Tao
2016-07-18 11:56 ` [dpdk-dev] [PATCH v3] " Zhe Tao
2016-07-19 10:29 ` Ananyev, Konstantin
2016-07-26 12:22 ` Tan, Jianfeng
2016-07-29 7:11 ` Tan, Jianfeng
2016-07-29 8:45 ` Ananyev, Konstantin
2016-07-29 10:11 ` Tan, Jianfeng
2016-10-10 3:58 ` [dpdk-dev] [PATCH v2] " Wu, Jingjing
2016-10-10 4:14 ` Yuanhan Liu
2016-08-01 3:56 ` [dpdk-dev] [PATCH v4 0/3] Add TSO on tunneling packet Jianfeng Tan
2016-08-01 3:56 ` [dpdk-dev] [PATCH v4 1/3] mbuf: add Tx side tunneling type Jianfeng Tan
2016-08-01 3:56 ` [dpdk-dev] [PATCH v4 2/3] net/i40e: add TSO support on tunneling packet Jianfeng Tan
2016-08-01 3:56 ` [dpdk-dev] [PATCH v4 3/3] app/testpmd: fix Tx offload " Jianfeng Tan
2016-09-19 12:09 ` Ananyev, Konstantin [this message]
2016-09-21 12:36 ` Tan, Jianfeng
2016-09-21 15:47 ` Ananyev, Konstantin
2016-09-22 1:29 ` Tan, Jianfeng
2016-09-22 9:15 ` Ananyev, Konstantin
[not found] ` <ED26CBA2FAD1BF48A8719AEF02201E364E5E09BC@SHSMSX103.ccr.corp.intel.com>
[not found] ` <2601191342CEEE43887BDE71AB97725836BA2698@irsmsx105.ger.corp.intel.com>
2016-09-27 17:29 ` [dpdk-dev] [PATCH v4 0/3] Add TSO " Ananyev, Konstantin
2016-09-27 17:52 ` Tan, Jianfeng
2016-09-27 19:47 ` Thomas Monjalon
2016-10-09 21:27 ` Thomas Monjalon
2016-09-26 13:48 ` [dpdk-dev] [PATCH v5 3/3] app/testpmd: support tunneled TSO in csum fwd engine Jianfeng Tan
2016-09-27 17:25 ` Ananyev, Konstantin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2601191342CEEE43887BDE71AB9772583F0B57BD@irsmsx105.ger.corp.intel.com \
--to=konstantin.ananyev@intel.com \
--cc=dev@dpdk.org \
--cc=helin.zhang@intel.com \
--cc=jianfeng.tan@intel.com \
--cc=jingjing.wu@intel.com \
--cc=pablo.de.lara.guarch@intel.com \
--cc=thomas.monjalon@6wind.com \
--cc=zhe.tao@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).