testsAndMisc/linux_configuration/features/lib/dot_resolver_install.sh

#!/bin/bash
# Certificate sync, stunnel and unit installation for the DoT resolver.
#
# Sourced by setup_dot_resolver.sh; split out to keep it under the 250-line cap.
# Sourced rather than run, so it inherits the caller's strict mode and
# the helper functions and variables defined above the source line.

install_cert_sync() {
	# Caddy renews on its own schedule; stunnel reads files from disk and must
	# be told. A timer copies the current cert out of the container and
	# reloads stunnel only when the content actually changed.
	# The script is the tracked scripts/sync-dot-cert.sh, installed as-is; the
	# values it used to have baked in are now its arguments (sync_script_args).
	sudo install -d -m 700 "$CERT_DIR"
	[[ -f $SYNC_SCRIPT_SRC ]] || die "tracked sync script missing: $SYNC_SCRIPT_SRC"
	sudo install -m 755 "$SYNC_SCRIPT_SRC" "$SYNC_SCRIPT"
}

# The arguments every caller of $SYNC_SCRIPT passes, so a non-default --domain
# reaches the timer's runs too.
sync_script_args() {
	printf '%s %s %s' "$DOMAIN" "$CADDY_CONTAINER" "$CERT_DIR"
}

install_stunnel_conf() {
	sudo tee "$STUNNEL_CONF" >/dev/null <<EOF
; DNS-over-TLS front end for the local dnsmasq blocklist.
; Generated by $SCRIPT_NAME - edit that instead.
foreground = yes
syslog = yes
[dns-over-tls]
accept = $BIND_ADDR:$DOT_PORT
connect = 127.0.0.1:53
cert = $CERT_DIR/combined.pem
; DoT is TLS 1.2+ only in practice; Android requires a publicly trusted cert.
sslVersionMin = TLSv1.2
EOF
}

install_units() {
	sudo tee /etc/systemd/system/stunnel-dot.service >/dev/null <<EOF
[Unit]
Description=DNS-over-TLS front end for dnsmasq blocklist
After=network-online.target dnsmasq.service wg-quick@wg0.service
Wants=network-online.target
; Wants, not Requires: stunnel only forwards to 127.0.0.1:53 per connection,
; and a Requires= turned one failed dnsmasq start at boot into a DoT outage
; that lasted until someone restarted stunnel by hand.
Wants=dnsmasq.service
; Binding to the WireGuard address fails if the interface is not up yet.
After=sys-devices-virtual-net-wg0.device

[Service]
ExecStart=/usr/bin/stunnel $STUNNEL_CONF
ExecReload=/bin/kill -HUP \$MAINPID
Restart=on-failure
RestartSec=5

[Install]
WantedBy=multi-user.target
EOF

	sudo tee /etc/systemd/system/dot-cert-sync.service >/dev/null <<EOF
[Unit]
Description=Copy the Caddy certificate for $DOMAIN to stunnel

[Service]
Type=oneshot
ExecStart=$SYNC_SCRIPT $(sync_script_args)
EOF

	sudo tee /etc/systemd/system/dot-cert-sync.timer >/dev/null <<EOF
[Unit]
Description=Daily certificate sync for the DoT resolver

[Timer]
OnCalendar=daily
Persistent=true

[Install]
WantedBy=timers.target
EOF
	sudo systemctl daemon-reload
}

open_firewall() {
	# Binding to the WireGuard address is NOT sufficient on its own. The
	# input chain has `policy drop` and admits only specific ports over wg0
	# (ssh), so a DoT connection from the phone is dropped even though the
	# tunnel itself is up and ICMP replies fine. That combination is
	# confusing to debug -- ping works, the port does not -- so the rule is
	# added explicitly, scoped to the tunnel interface.
	if [[ "$BIND_ADDR" != "0.0.0.0" ]]; then
		if command -v nft >/dev/null 2>&1 && sudo nft list table inet filter >/dev/null 2>&1; then
			# Through the firewall's owner, which persists ALLOW_DOT and renders
			# the rule: an 'nft add rule' here vanished at the next re-apply.
			if sudo bash "${WG_SCRIPT:-${SCRIPT_DIR}/setup_wireguard_ssh.sh}" allow-dot; then
				log "Permitted TCP $DOT_PORT on wg0 only (persisted)"
			else
				log "WARNING: could not open $DOT_PORT on wg0 (setup_wireguard_ssh.sh allow-dot)"
			fi
		fi
		log "No router port-forward needed - $BIND_ADDR is WireGuard-only."
		return
	fi
	if command -v nft >/dev/null 2>&1 && sudo nft list table inet filter >/dev/null 2>&1; then
		if ! sudo nft list table inet filter | grep -q "dport $DOT_PORT"; then
			# Rate limited, because a publicly bound DoT endpoint is an open
			# resolver: TCP-only so not usable for classic UDP amplification,
			# but still someone else's free DNS and a standing attack surface.
			# A phone issues a handful of lookups a second at worst; 25/second
			# with a burst of 50 is far above real use and far below abuse.
			sudo nft add rule inet filter input tcp dport "$DOT_PORT" \
				limit rate 25/second burst 50 packets accept ||
				log "WARNING: could not add rate-limited nftables rule for $DOT_PORT"
			log "Permitted TCP $DOT_PORT (rate limited 25/s, burst 50)"
		fi
	fi
	log "Ensure your router forwards TCP $DOT_PORT to this host."
}

run_check() {
	local ok=0
	systemctl is-active --quiet stunnel-dot.service ||
		{
			log "FAIL stunnel-dot.service not active"
			ok=1
		}
	ss -lnt 2>/dev/null | grep -qE ":$DOT_PORT\b" ||
		{
			log "FAIL nothing listening on $DOT_PORT"
			ok=1
		}
	# $CERT_DIR is mode 700 and owned by root because it holds a private key,
	# so an unprivileged [[ -s ]] reports "missing" for a file that is
	# present. Test as root, or --check reports a false failure on a healthy
	# install.
	sudo test -s "$CERT_DIR/combined.pem" ||
		{
			log "FAIL certificate missing at $CERT_DIR/combined.pem"
			ok=1
		}
	if command -v kdig >/dev/null 2>&1; then
		kdig +tls "@$BIND_ADDR" -p "$DOT_PORT" +short example.com >/dev/null 2>&1 ||
			{
				log "FAIL DoT query did not answer"
				ok=1
			}
	fi
	[[ $ok -eq 0 ]] && log "OK - DoT resolver healthy on $DOMAIN:$DOT_PORT"
	return "$ok"
}