mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-05 19:18:25 +00:00
Johnathan Corgan
72159a911d
Both OpenWrt packages and the SDK feed Makefile installed /etc/dnsmasq.d/fips.conf. As shipped it forwarded .fips to 127.0.0.1#5354, an address the daemon's DNS responder does not listen on, since it binds ::1. On a device that has ever run the gateway the file says something else: the gateway init script rewrote its server line to ::1#5353 on every start and left the comments above it naming 127.0.0.1:5354. Neither version was ever read, because OpenWrt's dnsmasq init script builds its config from UCI and never loads that directory. What forwards .fips is the UCI server entry. 90-fips-setup adds it pointing at the daemon on ::1#5354, and the gateway init script points it at the gateway on ::1#5353 when the gateway starts and back at the daemon when it stops. This change leaves both writers of that entry alone; which port it should name while the gateway runs is a separate question. The drop-in is removed from the payload, the builders, the Makefile, the README and the packaging workflow's path lists. fips-gateway no longer rewrites it on every start and stop. The 90-fips-setup comment now says that the UCI entry is the forwarding path and that the gateway repoints it, and the shipped fips.yaml comment on the gateway, which said the fips init script configures that forwarding, now names the fips-gateway init script. An opkg upgrade removes the old file; an apk upgrade keeps it only if it was modified, as it is on a device that ran the gateway. Either way nothing reads it. package-test.sh now also builds the .ipk and checks that neither package installs anything under /etc/dnsmasq.d, with a positive control on files both packages must ship, and that no OpenWrt packaging file still names the drop-in, which is the only check covering the SDK Makefile.