Files
cc-ci/nix/modules/acme-dns.nix
T
2026-09-21 16:56:00 +00:00

221 lines
8.5 KiB
Nix

# Restricted DNS-01 certificate issuance for ci.autonomic.zone (+ legacy ci.commoninternet.net).
#
# This host is authoritative only for acme.commoninternet.net. Gandi continues
# to own commoninternet.net AND autonomic.zone; both zones delegate their narrow
# _acme-challenge CNAME to the same acme-dns account. No Gandi credential is present here.
#
# Domain cutover 2026-09: ONE cert now covers BOTH zones (SANs: ci/*.ci.autonomic.zone +
# ci/*.ci.commoninternet.net) — a single secret pair flows through the unchanged
# warm_reconcile._traefik_setup ssl_cert/ssl_key flow, avoiding dual-cert SNI entirely.
# The legacy commoninternet.net SANs are dropped in Phase 4 (post-bake reissue).
{ config, pkgs, ... }:
let
publicIPv4 = config.cc-ci.publicIPv4;
acmeDnsConfig = pkgs.writeText "cc-ci-acme-dns.conf" ''
[general]
listen = "${publicIPv4}:53"
protocol = "both4"
domain = "acme.commoninternet.net"
nsname = "ns-acme.commoninternet.net"
nsadmin = "hostmaster.commoninternet.net"
records = [
"acme.commoninternet.net. NS ns-acme.commoninternet.net.",
"ns-acme.commoninternet.net. A ${publicIPv4}",
]
debug = false
[database]
# acme-dns 2.x registers the embedded driver under `sqlite` (not the
# legacy `sqlite3` identifier).
engine = "sqlite"
connection = "/var/lib/acme-dns/acme-dns.db"
[api]
ip = "127.0.0.1"
port = "8080"
tls = "none"
# The one Lego account was bootstrapped before this configuration was
# hardened. Updates authenticated by that account remain available.
disable_registration = true
corsorigins = []
[logconfig]
loglevel = "info"
logtype = "stdout"
logformat = "json"
'';
# These are wiring values only. The acme-dns account JSON is generated by
# Lego below /var/lib/acme and never enters Nix, git, or /etc.
# Storage path points at the NEW cert's dir; cc-ci-acme-storage-seed.service
# (below) clones the legacy account entry into it under the new zone key so
# Lego can write the new zone's TXT via the same (registration-disabled)
# acme-dns account — the CNAME for _acme-challenge.ci.autonomic.zone already
# delegates to that account's subdomain.
legoEnvironment = pkgs.writeText "cc-ci-acme-dns-lego.env" ''
ACME_DNS_API_BASE=http://127.0.0.1:8080
ACME_DNS_STORAGE_PATH=/var/lib/acme/ci.autonomic.zone/acme-dns-accounts.json
ACME_DNS_ALLOWLIST=127.0.0.1/32
'';
# Seed the new cert's acmedns storage from the legacy one: same acme-dns
# account (same subdomain/credentials — the only thing the DNS CNAME points
# at), re-keyed for the new zone. Idempotent; runs before the ACME unit.
acmeStorageSeed = pkgs.writeShellApplication {
name = "cc-ci-acme-storage-seed";
runtimeInputs = with pkgs; [ jq coreutils ];
text = ''
src=/var/lib/acme/ci.commoninternet.net/acme-dns-accounts.json
dst=/var/lib/acme/ci.autonomic.zone/acme-dns-accounts.json
install -d -m 0700 /var/lib/acme/ci.autonomic.zone
if [ ! -s "$src" ]; then
echo "storage seed: no legacy accounts.json — skipping (fresh host?)"
exit 0
fi
jq 'if has("ci.autonomic.zone") then .
elif has("ci.commoninternet.net") then
. + { "ci.autonomic.zone": .["ci.commoninternet.net"] }
else . end' "$src" > "$dst.tmp"
mv "$dst.tmp" "$dst"
chmod 0600 "$dst"
echo "storage seed: ok"
'';
};
in
{
imports = [ ./options.nix ];
users.groups.acme-dns = { };
users.users.acme-dns = {
isSystemUser = true;
group = "acme-dns";
home = "/var/lib/acme-dns";
};
environment.etc."acme-dns/lego.env".source = legoEnvironment;
networking.firewall = {
allowedTCPPorts = [ 53 ];
allowedUDPPorts = [ 53 ];
};
# One `systemd` attrset (statix W20): the tmpfiles marker, the acme-dns daemon and the
# traefik handoff oneshot.
systemd = {
# The staging order has completed successfully. This marker permits the
# production ACME post-run hook to hand a renewed certificate to Traefik.
tmpfiles.rules = [
"f /var/lib/ci-certs/acme-production-enabled 0600 root root -"
];
services.acme-dns = {
description = "Restricted authoritative DNS for cc-ci ACME DNS-01";
wantedBy = [ "multi-user.target" ];
after = [ "network-online.target" ];
wants = [ "network-online.target" ];
serviceConfig = {
User = "acme-dns";
Group = "acme-dns";
StateDirectory = "acme-dns";
StateDirectoryMode = "0700";
WorkingDirectory = "/var/lib/acme-dns";
ExecStart = "${pkgs.acme-dns}/bin/acme-dns -c ${acmeDnsConfig}";
Restart = "on-failure";
RestartSec = "5s";
AmbientCapabilities = [ "CAP_NET_BIND_SERVICE" ];
CapabilityBoundingSet = [ "CAP_NET_BIND_SERVICE" ];
NoNewPrivileges = true;
PrivateTmp = true;
PrivateDevices = true;
ProtectHome = true;
ProtectSystem = "strict";
ReadWritePaths = [ "/var/lib/acme-dns" ];
RestrictAddressFamilies = [ "AF_INET" "AF_UNIX" ];
};
};
# Seed the new cert's acmedns storage before the ACME unit first runs (see
# acmeStorageSeed above). Ordering via the generated acme unit name.
services.cc-ci-acme-storage-seed = {
description = "Seed ci.autonomic.zone acme-dns storage from the legacy account";
after = [ "acme-dns.service" ];
wantedBy = [ "acme-ci.autonomic.zone.service" ];
before = [ "acme-ci.autonomic.zone.service" ];
serviceConfig = {
Type = "oneshot";
UMask = "0077";
};
script = "${acmeStorageSeed}/bin/cc-ci-acme-storage-seed";
};
# Traefik consumes its wildcard as immutable Swarm secrets, so a renewed
# host certificate must be copied and reconciled rather than merely reloaded.
# This service is started only by the production-mode ACME postRun hook.
services.cc-ci-acme-traefik-handoff = {
description = "Install renewed cc-ci wildcard into Traefik Swarm secrets";
after = [ "docker.service" "deploy-proxy.service" ];
requires = [ "docker.service" ];
path = [ pkgs.coreutils pkgs.docker pkgs.systemd pkgs.gnugrep ];
serviceConfig = {
Type = "oneshot";
UMask = "0077";
};
script = ''
src=/var/lib/acme/ci.autonomic.zone
dst=/var/lib/ci-certs/live
test -s "$src/fullchain.pem"
test -s "$src/key.pem"
install -d -m 0700 "$dst"
install -m 0444 "$src/fullchain.pem" "$dst/fullchain.pem.new"
install -m 0400 "$src/key.pem" "$dst/privkey.pem.new"
mv -f "$dst/fullchain.pem.new" "$dst/fullchain.pem"
mv -f "$dst/privkey.pem.new" "$dst/privkey.pem"
# deploy-proxy performs the health-gated Swarm rollout. Its reconciler
# derives a fresh version from the public certificate chain and inserts
# the matching ssl_cert/ssl_key secrets before deploying Traefik.
systemctl restart deploy-proxy.service
# A successful rollout no longer references old wildcard versions. Best
# effort removal retains any secret Docker still reports as in use.
keep="v$(sha256sum "$dst/fullchain.pem" | cut -c1-16)"
docker secret ls --format '{{.Name}}' | \
grep -E '^traefik_ci_commoninternet_net_ssl_(cert|key)_v' | \
grep -v -E "_(ssl_cert|ssl_key)_$keep\$" | \
while IFS= read -r stale; do docker secret rm "$stale" || true; done
'';
};
};
security.acme = {
acceptTerms = true;
certs."ci.autonomic.zone" = {
domain = "ci.autonomic.zone";
# Dual-zone SANs: the new zone + the legacy one. One cert = one ssl_cert/ssl_key
# secret pair = zero traefik reconciler changes. Phase 4 drops the legacy SANs.
extraDomainNames = [
"*.ci.autonomic.zone"
"ci.commoninternet.net"
"*.ci.commoninternet.net"
];
# Staging issuance proved the permanent, narrowly delegated CNAME and the
# restricted acme-dns account. Production uses the same account (re-keyed
# for the new zone by cc-ci-acme-storage-seed.service).
dnsProvider = "acmedns";
environmentFile = "/etc/acme-dns/lego.env";
dnsResolver = "1.1.1.1:53";
server = "https://acme-v02.api.letsencrypt.org/directory";
postRun = ''
# The production marker is deployed only after staging proves the
# permanent CNAME and restricted acme-dns account work end to end.
if [ -e /var/lib/ci-certs/acme-production-enabled ]; then
${pkgs.systemd}/bin/systemctl --no-block start cc-ci-acme-traefik-handoff.service
fi
'';
};
};
}