From: Vladislav Yasevich <vyasev...@gmail.com>
Date: Thu, 18 May 2017 09:31:03 -0400
> It appears that since commit 8cb65d000, Q-in-Q vlans have been
> broken. The series that commit is part of enabled TSO and checksum
> offloading on Q-in-Q vlans. However, most HW we support can't handle
> it. To work around the issue, the above commit added a function that
> turns off offloads on Q-in-Q devices, but it left the checksum offload.
> That will cause issues with most older devices that supprort very basic
> checksum offload capabilities as well as some newer devices (we've
> reproduced te problem with both be2net and bnx).
>
> To solve this for everyone, turn off checksum offloading feature
> by default when sending Q-in-Q traffic. Devices that are proven to
> work can provided a corrected ndo_features_check implemetation.
>
> Fixes: 8cb65d000 ("net: Move check for multiple vlans to drivers")
> CC: Toshiaki Makita <makita.toshi...@lab.ntt.co.jp>
> Signed-off-by: Vladislav Yasevich <vyase...@redhat.com>
This is a tough one. I can certainly sympathize with your frustration
trying to track this down.
Clearing NETIF_F_HW_CSUM completely is the most conservative change.
However, for all the (perhaps many) cards upon which the checksumming
does work properly in Q-in-Q situations, this change could be
introducing non-trivial performance regressions.
So I think Toshiaki's suggestion to drop IP_CSUM and IPV6_CSUM is,
on balance, the best way forward.
Thanks.
