platform/scripts/setup/machine-setup/lib/tailscale.sh

#!/bin/bash
# =============================================================================
# machine-setup — Tailscale
# =============================================================================
#
# Definitions only, like the other lib/ files.
#
# ── Why this runs early ──
#
# It is a second way into the machine. The section that can lock you out is SSH
# hardening, and everything after this one can break networking in some smaller
# way; having the tailnet up first means a mistake is recoverable rather than a
# trip to a rescue console.
#
# ── Why it matters to Officer specifically ──
#
# The platform's CLAUDE.md is explicit: the perimeter IS the tailnet.
# ALLOW_ANY_ORIGIN defaults ON, and that is only defensible because the machine is
# not reachable from the open internet in the first place — a valid token plus the
# tailnet is the lock. An Officer install with no tailnet is an Officer install
# with one fewer layer than it was designed around.
#
# ── Why the original hung ──
#
# It passed --authkey unconditionally, and its prompt accepted an empty answer.
# `tailscale up --authkey ""` falls back to interactive login: it prints a URL and
# blocks, with no timeout, forever. Nothing here passes an empty key, every call
# has a timeout, and the state is read before anything is run.

[[ -n "${MACHINE_SETUP_TAILSCALE_LOADED:-}" ]] && return 0
MACHINE_SETUP_TAILSCALE_LOADED=1

TS_EXIT_SYSCTL=/etc/sysctl.d/99-tailscale-exit.conf
TS_DISPATCHER=/etc/networkd-dispatcher/routable.d/50-tailscale-exit

# Printed only when asked for. The section leads with the question rather than
# with ten lines of explanation: somebody who runs Tailscale already does not need
# to be told what it is, and somebody who does not can type ?.
tailscale_help() {
  echo "     Tailscale is a private network between your own machines, over"
  echo "     WireGuard. Every device you enrol gets a stable 100.x address and"
  echo "     can reach every other, wherever they are — through NAT, across"
  echo "     providers, without either end having a public address."
  echo ""
  echo "     Nothing is published to the open internet to make that work: no"
  echo "     port forwarding, no exposed ports, no holes in the firewall."
  echo ""
  echo "     For Officer it is not a convenience. The platform is built assuming"
  echo "     the tailnet IS the perimeter — ALLOW_ANY_ORIGIN defaults on, and"
  echo "     that is only defensible because the machine is not reachable from"
  echo "     outside in the first place. A valid token plus the tailnet is the"
  echo "     lock; without the tailnet it is one layer short of its design."
  echo ""
  echo "     It is installed at this point in the run, before anything that can"
  echo "     lock you out of the machine, so there is always a second way in."
}

# The menu itself, in a function because it is shown twice — once to ask, and
# again after ? has printed the long answer, so the reader is not dropped back at
# a bare prompt having forgotten what the options were.
tailscale_network_menu() {
  info "Which network should this machine join?"
  echo ""
  echo "     [1] set up your own network — offscale"
  echo "         Your own coordination server. The protocol on the wire is"
  echo "         Tailscale's and the encryption is WireGuard's; offscale changes"
  echo "         neither — it runs headscale's open-source code. What changes is"
  echo "         the work: managed from an app rather than a terminal, and"
  echo "         enrolling a device is a link and a tap."
  echo "         offscale — just like headscale, and just like Tailscale's own"
  echo "         service — needs to run on a publicly reachable server of its"
  echo "         own. A small VPS is enough. Not this machine, not behind a home"
  echo "         router: every device that joins has to find it, including phones"
  echo "         on mobile data. The only difference from option 3 is who runs"
  echo "         that server."
  echo "         Follow that setup through first, then come back here with its"
  echo "         address and a key."
  echo "         https://officer.dev/infrastructure/offscale.html#install"
  echo ""
  echo "     [2] use a network you already run — headscale or offscale"
  echo "         You already have a coordination server somewhere. Point this"
  echo "         machine at it and it joins that network alongside the rest."
  echo ""
  echo "     [3] the easy route — tailscale.com"
  echo "         Tailscale runs the coordination for you. Nothing to host and"
  echo "         nothing to maintain, free for personal use; the trade is that"
  echo "         the list of your machines lives with them."
  echo ""
  echo "     [4] no private network at all"
  echo "         This machine is reached over the open internet, or not at all."
  echo "         Everything the tailnet was doing becomes yours to do."
  echo ""
  echo "     [?] what are tailscale, headscale and offscale?"
  echo ""
}

# The long answer, printed when somebody types ?. Covers all three names,
# because the menu offers all three and two of them are not words anyone outside
# this project would know.
tailscale_networks_help() {
  echo "     Tailscale, headscale and offscale are three answers to one question:"
  echo "     who keeps the list of your machines and hands out the keys they use"
  echo "     to find each other."
  echo ""
  echo "     The network itself is the same in all three cases. Machines talk"
  echo "     directly to each other over WireGuard, encrypted end to end. What"
  echo "     differs is only the coordination server — the thing that knows which"
  echo "     machines are yours. It never carries your traffic."
  echo ""
  echo "  TAILSCALE"
  echo "     The company's own coordination server. Nothing to run, nothing to"
  echo "     maintain, free for personal use. You sign in with an existing"
  echo "     identity and your machines appear in their admin console."
  echo "     The trade is that the list of your machines lives with them."
  echo ""
  echo "  HEADSCALE"
  echo "     An open-source coordination server you run yourself. The same"
  echo "     Tailscale clients connect to it, so the machines behave identically;"
  echo "     the difference is that nobody else holds the list. The cost is that"
  echo "     it is now a service you host, and it needs to be reachable."
  echo ""
  echo "  OFFSCALE"
  echo "     Our own distribution of headscale, which is to say: headscale. The"
  echo "     protocol on the wire is Tailscale's and the encryption is"
  echo "     WireGuard's, and offscale changes neither — it runs the same"
  echo "     open-source project. A machine on an offscale network behaves"
  echo "     exactly as it would on either of the other two. There is no offscale"
  echo "     protocol to be locked into, because there is no offscale protocol."
  echo ""
  echo "     Clients: stock Tailscale on computers. On iPhone, iPad and Android"
  echo "     there is our own app — the Tailscale client, our branding, and one"
  echo "     real difference: it takes an invite from the server directly. That"
  echo "     is the part of running headscale people give up at, because the"
  echo "     official app has to be talked into using a server that is not"
  echo "     Tailscale's. Desktop apps of our own are not there yet; on a"
  echo "     computer you point the official client at your own server."
  echo ""
  # Where it runs matters more than how it installs, and is the thing people
  # get wrong: a coordination server at home is unreachable from exactly the
  # devices a private network exists to reach.
  echo "     Where it runs: on a publicly reachable server of its own — a small"
  echo "     VPS is enough. Not on this machine, and not behind a home router."
  echo "     Every device that joins has to find it, including phones on mobile"
  echo "     data and laptops in other buildings, so it needs an address that"
  echo "     resolves from anywhere."
  echo ""
  echo "     This is not something offscale asks for and the others do not. It"
  echo "     is true of headscale, and it is true of Tailscale — their"
  echo "     coordination server is publicly reachable too, they simply run it"
  echo "     for you. That is the whole of the difference between choosing"
  echo "     option 3 and choosing to host it yourself."
  echo ""
  echo "     What it does that plain headscale does not:"
  echo "       · installs in one command on that server, certificates included"
  echo "       · health, logs, restarts and access policies from the app,"
  echo "         instead of a config file and a CLI"
  echo "       · enrolling a device is a link and a tap — the key is minted"
  echo "         and handed over for you"
  echo "       · several networks at once, and services reachable across them"
  echo ""
  echo "     https://officer.dev/infrastructure/offscale.html"
  echo ""
  echo "  FOR OFFICER"
  echo "     Whichever you pick, the tailnet is what Officer treats as its"
  echo "     perimeter. ALLOW_ANY_ORIGIN defaults on, and that is only"
  echo "     defensible because the machine is not reachable from the open"
  echo "     internet in the first place. Installed at this point in the run,"
  echo "     before anything that can lock you out, so there is always a second"
  echo "     way in."
  echo ""
  echo "     Officer also administers it. Its Headscale app talks to headscale"
  echo "     and offscale servers alike: register as many as you run, see which"
  echo "     are actually up — each is probed, not remembered — and switch"
  echo "     between them. On whichever is active you get the nodes, the users,"
  echo "     the pre-auth keys, the invites and the ACL policy, with an"
  echo "     assistant for writing it, plus a console and diagnostics. So the"
  echo "     server this section sets up is managed from the same place as"
  echo "     everything else on this machine, rather than over ssh and a CLI."
}

tailscale_is_installed() { command -v tailscale &>/dev/null; }

# NeedsLogin, Running, Stopped, NoState… Read before acting, because the original's
# failure was running `up` blindly against a node that was already up.
tailscale_state() {
  tailscale status --json 2>/dev/null | awk -F'"' '/"BackendState"/ { print $4; exit }'
}

tailscale_ip() { tailscale ip -4 2>/dev/null | head -1; }

# Which control plane this node is talking to. Empty means Tailscale's own.
tailscale_control_url() {
  tailscale debug prefs 2>/dev/null | awk -F'"' '/"ControlURL"/ { print $4; exit }'
}

tailscale_install() { curl -fsSL https://tailscale.com/install.sh | sh; }

# Tailscale's own coordination server, spelled out.
#
# Passed explicitly even when it is the default, because `tailscale up` with no
# --login-server keeps whatever ControlURL is already stored. On a node already
# pointed at a self-hosted server, choosing "the easy route" would otherwise
# leave it exactly where it was — no error, no message, wrong answer.
TS_DEFAULT_CONTROL_URL="https://controlplane.tailscale.com"

# Moving a node between coordination servers is not something `up` will do while
# it is logged in to one. Logging out first is the documented way, and doing it
# unasked would be worse than saying so.
# What choosing "no private network" actually hands you, said before it is
# chosen rather than discovered afterwards.
tailscale_none_warning() {
  echo "     Without a tailnet, everything it was doing becomes yours:"
  echo ""
  echo "       · Anything you want to reach remotely has to be published to the"
  echo "         open internet deliberately, and kept closed otherwise."
  echo "       · TLS certificates are yours to obtain and to keep renewed."
  echo "       · Every exposed service needs its own authentication, because"
  echo "         there is no longer a network boundary in front of it."
  echo "       · This machine will be found. Anything listening on a public"
  echo "         address is scanned within minutes and attacked continuously."
  echo ""
  echo "     For Officer specifically, one setting stops being safe:"
  echo ""
  echo "       ALLOW_ANY_ORIGIN defaults ON, which means origin checking is off"
  echo "       unless it is explicitly set to false. That default is deliberate"
  echo "       and it is only defensible because the tailnet is the perimeter."
  echo "       With no tailnet you must set ALLOW_ANY_ORIGIN=false and put an"
  echo "       HTTPS reverse proxy in front of the platform, or it is running"
  echo "       with a check disabled that was disabled on the assumption you"
  echo "       are making false."
}

tailscale_needs_logout() {
  local current="$1" target="$2"
  [[ -n "$current" && -n "$target" && "$current" != "$target" ]]
}

# Routing has to be on before this machine can forward anyone else's packets,
# whether as an exit node or as a subnet router. Written as a drop-in so it is
# visible as this script's doing.
enable_ip_forwarding() {
  cat >"$TS_EXIT_SYSCTL" <<'EOF'
# Written by machine-setup: required to forward traffic for other tailnet nodes,
# as an exit node or as a subnet router.
net.ipv4.ip_forward = 1
net.ipv6.conf.all.forwarding = 1
EOF
  sysctl --system >/dev/null 2>&1
  # Returns 0 whatever happens. This is an optional improvement, and a
  # function that ends on a failing command is fatal under `set -e` when it
  # is called as a plain command — which would abort the remaining sections
  # over something the run could simply report. The caller checks the outcome.
  return 0
}

# UDP GRO forwarding, which Tailscale documents as roughly doubling throughput on
# a node that forwards for others. Applied on every routable event rather than
# once, because the settings are per-interface and do not survive the link going
# down and back up.
install_exit_node_tuning() {
  pkg_is_installed networkd-dispatcher || pkg_install_now networkd-dispatcher

  mkdir -p "$(dirname "$TS_DISPATCHER")"
  cat >"$TS_DISPATCHER" <<'EOF'
#!/usr/bin/env bash
# Written by machine-setup. NIC offload settings for a Tailscale exit node or
# subnet router — Tailscale's own recommendation for forwarding throughput.
set -Eeuo pipefail

IF="${IFACE:-}"
if [[ -z "${IF}" ]]; then
  IF="$(ip -o route get 8.8.8.8 2>/dev/null | awk '{for (i = 1; i <= NF; i++) if ($i == "dev") {print $(i + 1); exit}}')"
fi

[[ -n "${IF}" ]] || exit 0
command -v ethtool >/dev/null 2>&1 || exit 0

ethtool -k "${IF}" 2>/dev/null | grep -q "^generic-receive-offload: " && ethtool -K "${IF}" gro on || true
ethtool -k "${IF}" 2>/dev/null | grep -q "^rx-udp-gro-forwarding: " && ethtool -K "${IF}" rx-udp-gro-forwarding on || true
ethtool -k "${IF}" 2>/dev/null | grep -q "^large-receive-offload: " && ethtool -K "${IF}" lro off || true

exit 0
EOF
  chmod 755 "$TS_DISPATCHER"
  systemctl enable --now networkd-dispatcher >/dev/null 2>&1 || true

  # And once now, for the interface that is already up.
  IFACE="$(default_iface)" bash "$TS_DISPATCHER" >/dev/null 2>&1 || true
  # Returns 0 whatever happens. This is an optional improvement, and a
  # function that ends on a failing command is fatal under `set -e` when it
  # is called as a plain command — which would abort the remaining sections
  # over something the run could simply report. The caller checks the outcome.
  return 0
}

# The LAN this machine sits on, as a CIDR — the useful default for a subnet
# router, and the number nobody remembers offhand.
lan_cidr() {
  local iface
  iface="$(default_iface)"
  ip -4 route show dev "$iface" 2>/dev/null |
    awk '$1 ~ /\// && $1 !~ /^default/ { print $1; exit }'
}