bpf: Reset Pod's queue mapping in host veth to fix phys dev mq selection

[borkmann]

Fix TX queue selection problem on the phys device as reported by Laurent.
At high throughput, they noticed a significant amount of TCP retransmissions
that they tracked back to qdic drops (fq_codel was used).

Suspicion is that kernel commit edbea9220251 ("veth: Store queue_mapping
independently of XDP prog presence") caused this due to its unconditional
skb_record_rx_queue() which sets queue mapping to 1, and thus this gets
propagated all the way to the physical device hitting only single queue
in a mq device.

Lets have bpf_lxc reset it as a workaround until we have a kernel fix.
Doing this unconditionally is good anyway in order to avoid Pods messing
with TX queue selection.

Related: #18311
Reported-by: Laurent Bernaille laurent.bernaille@datadoghq.com
Signed-off-by: Daniel Borkmann daniel@iogearbox.net
Link: torvalds/linux@edbea92

[borkmann]

/test

Job 'Cilium-PR-K8s-1.22-kernel-4.19' failed and has not been observed before, so may be related to your PR:

Click to show.

Test Name

K8sServicesTest Checks graceful termination of service endpoints Checks client terminates gracefully on service endpoint deletion

Failure Output

FAIL: Timed out after 60.000s.

If it is a flake, comment /mlh new-flake Cilium-PR-K8s-1.22-kernel-4.19 so I can create a new GitHub issue to track it.

Job 'Cilium-PR-K8s-GKE' hit: #17628 (96.35% similarity)

[lbernail]

I tested this patch on a test cluster and it worked great (details on the test here : #18311 (comment))