Gotcha. I'm working on it. I've created a function that creates
sk_buff from xdp_buff. But still getting an error while the sk_buff is
being processed by tcp. I will send you the patch once I'm done.
Thanks!
On Thu, Apr 5, 2018 at 10:55 PM, David Ahern <dsah...@gmail.com> wrote:
> On 4/3/18 9:15 PM, Md. Islam wrote:
>>> Have you looked at what I would consider a more interesting use case of
>>> packets into a node and delivered to a namespace via veth?
>>>
>>> +--------------------------+---------------
>>> | Host | container
>>> | |
>>> | +-------{ veth1 }-|-{veth2}----
>>> | | |
>>> +----{ eth1 }------------------
>>>
>>> Can xdp / bpf on eth1 be used to speed up delivery to the container?
>>
>> I didn't consider that, but it sounds like an important use case. How
>> do we determine which namespace gets the packet?
>>
>
> FIB lookups of course. Starting with my patch set that handles
> forwarding on eth1, what is needed for XDP with veth? ie., a program on
> eth1 does the lookup and redirects the packet to veth1 for Tx.
> ndo_xdp_xmit for veth knows the packet needs to be forwarded to veth2
> internally and there is no skb allocated for the packet yet.
--
Tamim
PhD Candidate,
Kent State University
http://web.cs.kent.edu/~mislam4/
