hyperhive/nix/host-modules/hive-gateway/dnsmasq.nix
atlas d60a0585d6 refactor(3202): the forge declares its own vhost and dns name
Moves `forgeVhost` out of the gateway's vhosts.nix and the forge's
`address=` rule out of dnsmasq.nix, into nix/host-modules/hive-forge —
the module that already owns everything else about the forge.

The gateway keeps what is gateway knowledge (the listen set, which
issuer covers a name, the header block) and loses the last reason it
had to read `swarm.forge` at all: `forgeCfg` is gone from both files
and from the module's `let`.

Both halves stay gated on `behindGateway` — with it off the operator
fronts forgejo themselves, so this hive must neither claim the vhost nor
answer DNS for the name.
2026-08-13 16:14:36 +02:00

107 lines
5.2 KiB
Nix

# Hive-internal DNS resolver + DHCP, running on the host alongside the
# gateway's nginx — single front-door for both DNS and HTTP, and no
# container of its own. Listens on the bridge interface from
# `services.hyperhive.network`; authoritative for the hive domain +
# sub-domains, forwards everything else upstream. Returns the
# `services.dnsmasq` value (see ./default.nix); the DHCP pool bounds
# are computed by hive-network.
{
lib,
cfg, # services.hyperhive.gateway
networkCfg,
matrixCfg,
autheliaCfg,
uiCfg,
hyperhiveDomain,
}:
{
enable = true;
# ON for its *plumbing*, not for the address it publishes.
#
# This flag does two separable things upstream. The one that matters
# here: it points dnsmasq's own upstream servers at a SEPARATE file
# (`resolv-file = /etc/dnsmasq-resolv.conf`, kept current by
# resolvconf). Without that, dnsmasq reads `/etc/resolv.conf` for its
# upstreams — so the moment the host's resolver is pointed at dnsmasq,
# every non-hive query goes in a circle.
#
# The other thing it does is publish `127.0.0.1` as the host's
# nameserver, which is the wrong address for this hive: see the
# `nameservers` override in ./default.nix, where the reason lives.
resolveLocalQueries = true;
settings = {
# Bind only on the bridge interface (and lo for health-checks).
# Outside hosts can't even see the listener.
interface = [
networkCfg.bridgeName
"lo"
];
bind-interfaces = true;
port = 53;
# Authoritative for the hive domain via the `address` rules below —
# must not fall back to the host's /etc/hosts. dnsmasq reads
# /etc/hosts by default, and `gateway.localHostsEntry` populates it
# with 127.0.0.1 for every hive name (host-side dev convenience,
# see default.nix). Since moving dnsmasq onto the host, that
# file is now the *same* /etc/hosts dnsmasq reads for agent queries
# — its entries win over `address=`, so every agent resolves the
# hive's own domains back to itself (127.0.0.1 in its own netns)
# instead of the bridge IP, and can't reach the forge, matrix, or
# dashboard at all. `no-hosts = true` keeps the authoritative
# `address=` rules in charge for containers while leaving
# `networking.hosts` (the actual /etc/hosts entries) untouched for
# host-side browsing.
no-hosts = true;
# Hive authoritative records — answer queries for the hive domain
# + its sub-domains with the bridge IP, where nginx is reachable
# from every container netns.
#
# The matrix entry is redundant in the common case where
# `matrix.gatewayHost` is a sub-domain of `hyperhive.domain` —
# dnsmasq's `/<domain>/` rule already matches sub-domains. Kept
# explicit because an operator can override it to a cross-domain
# hostname (e.g. `git.example.com` for the forge); listing such a
# name explicitly keeps that case routed without an extra config
# block.
address = [
"/${hyperhiveDomain}/${networkCfg.bridgeIp}"
]
++ lib.optional (
matrixCfg.enable && matrixCfg.gatewayHost != null
) "/${matrixCfg.gatewayHost}/${networkCfg.bridgeIp}"
++ lib.optional autheliaCfg.enable "/${autheliaCfg.domain}/${networkCfg.bridgeIp}"
# The swarm UI's name is the swarm APEX by default — a sibling of
# the three above, not a child of anything this resolver already
# answers for, so the `/<hive domain>/` rule does not cover it.
#
# Published to agents deliberately (mara: publishing it is fine).
# Reachability is not the access control here: the vhost's
# `auth_request` + authelia's `group:operators` rule are, and an
# agent that resolves the name still cannot open the page.
++ lib.optional uiCfg.enable "/${uiCfg.domain}/${networkCfg.bridgeIp}"
# Names contributed by the modules that own them
# (`gateway.localNames`). Same address as everything above — the
# bridge IP is the gateway's answer for anything it fronts, and a
# contributing module neither knows nor should know it.
#
# `unique` is not tidiness: two modules claiming one name would
# otherwise emit two `address=` rules for it, and dnsmasq resolves
# that by precedence rather than by complaining. An assertion in
# ./default.nix makes the collision loud instead.
++ map (name: "/${name}/${networkCfg.bridgeIp}") (lib.unique cfg.localNames);
# DHCP pool covering all usable host addresses on the bridge
# subnet — bounds computed by hive-network.nix from
# bridgeIp/bridgePrefixLength. All containers (agents and service
# containers such as hive-ci) receive their IPs dynamically.
dhcp-range = "${networkCfg.dhcpRangeStart},${networkCfg.dhcpRangeEnd},1h";
dhcp-leasefile = "/var/lib/dnsmasq/dnsmasq.leases";
# No explicit upstream: non-hive queries follow dnsmasq's
# resolv.conf default — the host's own `/etc/resolv.conf`, so the
# hive always uses the host's resolvers and follows them live with
# no copy to go stale. Deliberately no fallback
# `server=`: dnsmasq queries
# all known upstreams in parallel, so a hardcoded public resolver
# would take a share of *normal* traffic, not just fill in when the
# host file is empty.
};
}