>>>  In most cases this would "work"
>>> because the packet wouldn't appear to be a TCP packet, however if the
>>> right data is in the right offsets (offsets of Ethertype, IP protocol)
>>> it seems like the device might incorrectly report a checksum error. If
>>> this is possible, it will be a very subtle bug!
>> Can you actually provide at least one example based in reality please?
>>
> https://github.com/adrianschroeter/kernel-source/blob/master/patches.drivers/i40e-0087-i40e-Rx-checksum-offload-for-VXLAN.patch

Another person doing per-protocol special "you need to buy a new adapter
for a new protocol" magic and not reading the documentation...

Instead of actually reading how it is supposed to be done so that _ANY_
encaps further downstream can take care of it.

http://lxr.free-electrons.com/source/include/linux/skbuff.h#L40

In any case, I agree, the fact that a software developer does not know
how to convert specific offload into a generic (including covering cases
which the card [or NPU] was never intended to cover) should of course be
taken into account. We should create all protocol specs in a manner such
that people who do not read documentation and the spec towards which
they are supposed to write should not have their software broken you
know... We should also invent a new protocol every time just in case
something somewhere breaks if we augment an old one.

Or maybe not...

A.



_______________________________________________
nvo3 mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/nvo3

Reply via email to