[dpdk-dev] 回复: ixgbe and UDP with zero checksum

Hi, Haiyue

We will release the patch to support zero checksum  in arm neon path later.

Best Regards
Feifei

-----邮件原件-----
发件人: Wang, Haiyue [off-list ref]
发送时间: 2021年2月2日 15:42
收件人: Feifei Wang [off-list ref]; Ruifeng Wang
[off-list ref]
抄送: Guo, Jia [off-list ref]; Aaron Conole [off-list ref];
dev@dpdk.org; Yang, Qiming [off-list ref]; Paolo Valerio
[off-list ref]
主题: RE: ixgbe and UDP with zero checksum

+ ARM experts, Feifei and Ruifeng.

Need your further support for ARM NEON path.

https://patchwork.dpdk.org/patch/87617/

quoted

-----Original Message-----
From: Paolo Valerio <redacted>
Sent: Friday, January 29, 2021 22:20
To: Wang, Haiyue <redacted>; Yang, Qiming
[off-list ref]
Cc: Guo, Jia <redacted>; Aaron Conole <aconole@redhat.com>;
dev@dpdk.org
Subject: RE: ixgbe and UDP with zero checksum

"Wang, Haiyue" [off-list ref] writes:

quoted

Hi Paolo,

quoted

-----Original Message-----
From: Wang, Haiyue
Sent: Friday, January 29, 2021 10:02
To: Paolo Valerio <redacted>
Cc: Guo, Jia <redacted>; Aaron Conole
[off-list ref]; dev@dpdk.org
Subject: RE: ixgbe and UDP with zero checksum

quoted

-----Original Message-----
From: Paolo Valerio <redacted>
Sent: Thursday, January 28, 2021 05:35
To: Wang, Haiyue <redacted>
Cc: Guo, Jia <redacted>; Aaron Conole
[off-list ref]; dev@dpdk.org
Subject: RE: ixgbe and UDP with zero checksum

"Wang, Haiyue" [off-list ref] writes:

quoted

Hi Paolo,

quoted

-----Original Message-----
From: Paolo Valerio <redacted>
Sent: Wednesday, January 27, 2021 21:50
To: dev@dpdk.org
Cc: Guo, Jia <redacted>; Wang, Haiyue
[off-list ref]; Aaron Conole [off-list ref]
Subject: ixgbe and UDP with zero checksum

Hi,

performing some tests, I noticed that on ixgbe when receiving
UDP packets with zero checksum (no checksum) over IPv4, the
corresponding ol_flag for the l4 checksum is set to

PKT_RX_L4_CKSUM_BAD.

quoted

quoted

quoted

quoted

quoted

quoted

In particular, this apparently has an impact on OvS using ct()
action where UDP packets with zero checksum are not tracked

because of that.

quoted

quoted

quoted

quoted

quoted

quoted

[1]

https://patchwork.ozlabs.org/project/netdev/patch/20090724040031.30202

quoted

.1531.stgit@localhost.localdomai

quoted

quoted

quoted

quoted

quoted

n/

About 12 years old patch, it is hardware errata. For fixing
this, have to always disable vector Rx path for 82599, it seems
not a good idea to bring in this workaround. :(

Thanks for the answer.
Yes, as I mentioned, the patch is old although still meaningful.
I linked it mostly because it mentions the hw errata.

What's your PCI device ID ? My worked ixgbe:

Sorry, I missed the PKT_RX_L4_CKSUM_BAD information, yes, my NIC

have the issue.

quoted

quoted

quoted

86:00.0 Ethernet controller [0200]: Intel Corporation 82599ES
10-Gigabit SFI/SFP+ Network

Connection

quoted

quoted

[8086:10fb] (rev 01)

I'm wondering if people will complain that the patch will mark the
real bad checksum UDP as

Zero checksum is more popular case, please file a bug on

https://bugs.dpdk.org/ to trace the fix.

quoted

quoted

Thanks for pointing it out.

ack, I'm going to file it.

Thanks,
Paolo

quoted

quoted

GOOD. For handling this correctly, looks like driver needs to check
the UDP's checksum value, if zero, then skip the error information, but

this makes driver do the network stack things ...

quoted

quoted

quoted