Re: [RFC 00/12] io_uring zerocopy send

[David Ahern]

On 12/1/21 12:11 PM, Pavel Begunkov wrote:
> btw, why a dummy device would ever go through loopback? It doesn't
> seem to make sense, though may be missing something.

You are sending to a local ip address, so the fib_lookup returns
RTN_LOCAL. The code makes dev_out the loopback:

https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/tree/net/ipv4/route.c#n2773

(you are not using vrf so ignore the l3mdev reference). loopback device
has the logic to put the skb back in the stack for Rx processing:

https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/tree/drivers/net/loopback.c#n68