On 8/24/22 1:10 AM, Eyal Birger wrote:
Hi Daniel,
On Wed, Aug 24, 2022 at 1:43 AM Daniel Borkmann <daniel@xxxxxxxxxxxxx> wrote:
On 8/22/22 3:08 PM, Eyal Birger wrote:
Port test_lwt_ip_encap.sh tests onto test_progs.
In addition, this commit adds "egress_md" tests which test a similar
flow as egress tests only they use gre devices in collect_md mode
for encapsulation and set the tunnel key using bpf_set_tunnel_key().
This introduces minor changes to test_lwt_ip_encap.{sh,c} for consistency
with the new tests:
- GRE key must exist as bpf_set_tunnel_key() explicitly sets the
TUNNEL_KEY flag
- Source address for GRE traffic is set to IP*_5 instead of IP*_1 since
GRE traffic is sent via veth5 so its address is selected when using
bpf_set_tunnel_key()
Note: currently these programs use the legacy section name convention
as iproute2 lwt configuration does not support providing function names.
Signed-off-by: Eyal Birger <eyal.birger@xxxxxxxxx>
[...]
Thanks for following up. Is there now anything that test_lwt_ip_encap.c
doesn't cover over test_lwt_ip_encap.sh? If not, I'd vote for removing
the latter given the port is then covered in CI via test_progs.
The .c version includes all tests in the .sh and two more.
At least when I tried using vmtest the .sh version seems broken.
I can resubmit with an additional patch removing it, or send a follow
up patch as you prefer.
+1, could you squash the removal into the single patch and submit as a v3?
Thanks a lot,
Daniel
