[PATCH v5 2/2] testpmd: fix l4 sw csum over multi segments
Ferruh Yigit
ferruh.yigit at intel.com
Mon Jan 24 12:02:43 CET 2022
On 1/24/2022 10:30 AM, Kevin Traynor wrote:
> On 24/01/2022 09:16, Ferruh Yigit wrote:
>> On 1/21/2022 5:09 PM, Kevin Traynor wrote:
>>> On 06/01/2022 16:03, Xiaoyun Li wrote:
>>>> In csum forwarding mode, software UDP/TCP csum calculation only takes
>>>> the first segment into account while using the whole packet length so
>>>> the calculation will read invalid memory region with multi-segments
>>>> packets and will get wrong value.
>>>> This patch fixes this issue.
>>>
>>> There should be a 'Fixes:' tag and assuming you want this patch backported to LTS, 'Cc: stable at dpdk.org' too.
>>>
>>
>> It can't be, because fix relies on new APIs added in this release (patch 1/2).
>>
>
> ok, makes sense, thanks. Do you think it worth adding a Bz for it and listing it as a known issue in 21.11.1?
>
Was discussing with Xialong, it is in the gray area that if this is a fix
or new feature.
It is not the case that initial implementation says that multi segment
mbufs are supported, in that case this is not a fix but enabling multi
segment support.
So perhaps better to update commit log in this way to prevent confusion
for the fixing and fix tag..
More information about the dev
mailing list