mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-05 19:18:25 +00:00
Johnathan Corgan
4a1d583653
A kernel built without CONFIG_NF_CONNTRACK_PROCFS, such as Ubuntu's, has no /proc/net/nf_conntrack. The gateway then counted zero sessions for every mapping, so a mapping still carrying traffic was reclaimed on its TTL and grace period alone. When the proc file is absent, the gateway now dumps the IPv6 conntrack table over NETLINK_NETFILTER, the request conntrack -L makes, and counts each entry once per distinct destination, the same rule the proc parser applies. The choice is made on every read, because the proc file appears only once nf_conntrack is loaded. Any other proc error is still reported without falling back. When both sources fail, the per-tick warning carries the netlink error, and the startup line names both errors. The dump uses netlink-packet-netfilter 0.3, the release built on the netlink-packet-core 0.8 that rtnetlink already uses. The gateway suite now expects the netlink source line when the container has no proc file, and checks that the gateway counts the session left by the HTTP request through the first virtual IP.