DPDK usage discussions
 help / color / mirror / Atom feed
From: Yasin CANER <yasin.caner@ulakhaberlesme.com.tr>
To: "users@dpdk.org" <users@dpdk.org>
Subject: How to strip CRC  - FCS from message
Date: Wed, 20 Jul 2022 10:47:34 +0000	[thread overview]
Message-ID: <AM9P189MB1554BAEA57A1FAEB7E925916B98E9@AM9P189MB1554.EURP189.PROD.OUTLOOK.COM> (raw)

[-- Attachment #1: Type: text/plain, Size: 1965 bytes --]

Hello,

Enviroment information;

DPDK versiyon 17.05
Kernel version 4.4.0
OS - Ubuntu 16.05
INTEL NIC XL710
Last i40e driver and NVM is installed.

ethtool -k ens2f2 :
tx-checksumming: on
        tx-checksum-ipv4: on
        tx-checksum-ip-generic: off [fixed]
        tx-checksum-ipv6: on
        tx-checksum-fcoe-crc: off [fixed]
        tx-checksum-sctp: on
rx-fcs: off [fixed]
rx-all: off [fixed]

What is CRC or FCS :

https://www.firewall.cx/networking-topics/ethernet/ethernet-frame-formats/201-ethernet-ii.html

State:


  *   Even if strip_crc flag is up in port_config, NIC doesnt strip CRC.
  *   After stripping Ethernet Header from message-buf, CRC still there. So it breaks fragmentation when specific byte length income. For Example; Message with IP  header -> 1480, Ether Header 6+6+2 = 14 byte. Frame length looks 1498 byte.  Looks like 4 byte Crc, it has. After Ether header is stripped , 1488 byte left.
[code]
static struct rte_eth_conf port_conf = {
    .rxmode =
        {
            .header_split   = 0, /* Header Split disabled */
            .hw_ip_checksum = 0, /* IP checksum offload disabled */
            .hw_vlan_filter = 0, /* VLAN filtering disabled */
            .jumbo_frame    = 0, /* Jumbo Frame Support disabled */
            .hw_strip_crc   = 1, /* CRC stripped by hardware */
        },
    .txmode =
        {
            .mq_mode = ETH_MQ_TX_NONE,
        },
};
[/code]


Is there any function to strip CRC bytes or what is best way? Big thanks to help.

I have an idea that,

After stripping Ethernet Header ,

  *   If total length of message is bigger than IP header length , there is a CRC, it needs to strip somehow?
  *   If total length of message is equal to IP header length, no problem.
  *   If total length of message is less than IP header length, message is broken.

Best Regards.

___
Yasin CANER
Lider Mühendis
Ulak Haberleşme A.Ş. Ankara


[-- Attachment #2: Type: text/html, Size: 12891 bytes --]

                 reply	other threads:[~2022-07-22  7:25 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=AM9P189MB1554BAEA57A1FAEB7E925916B98E9@AM9P189MB1554.EURP189.PROD.OUTLOOK.COM \
    --to=yasin.caner@ulakhaberlesme.com.tr \
    --cc=users@dpdk.org \
    /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).