hyperhive/nix/host-modules/glue-bao-tls.nix

# Glue: give the secret store a PKI of its own, and point it at it.
#
# ONE PAIRING PER FILE — `glue-<consumer>-<what>.nix`. A single module holding
# every co-location default becomes the file nobody dares change, because a
# reader cannot tell which of its rules their deployment is subject to. Each
# of these should be deletable on its own, and deleting this one leaves a
# store that takes operator-provided certificates and nothing else.
#
# ⚠️ Why the PKI lives HERE and not in ./swarm-bao.nix: the store must have no
# opinion about where its identity comes from. Minting is an opinion — the
# most consequential one available — so it belongs to the glue that decides
# this deployment self-signs, not to the service that merely serves what it is
# handed. A deployment with a real internal CA drops this file and names its
# own paths; nothing in the store changes.
#
# ⚠️ Not the hive CA and not the swarm CA. The store will eventually
# distribute both, and an authority you must already hold a certificate from
# cannot be one the store hands out — reach the store to get the CA material,
# need a cert from that CA to reach the store. This CA signs a fixed, short
# list of leaves and distributes nothing, so it cannot enter that cycle.
#
# ⚠️ Files like this are the only place a `deploy.<foo>` value may derive from
# a `deploy.<bar>.enable`. Everywhere else that is forbidden. The exception
# earns itself: the derivation happens either way, and the alternative is
# having it spread through the service modules where it is invisible.
#
# Everything is `mkDefault`. An operator naming their own paths wins.
{
  pkgs,
  lib,
  config,
  ...
}:
let
  hyperhiveCfg = config.services.hyperhive;
  deployCfg = hyperhiveCfg.deploy;
  cfg = hyperhiveCfg.swarm.bao;

  # Host-side, outside the container's tree, for the same reason the raft data
  # is: `nixos-container destroy` must not take it. Losing the CA key means
  # re-issuing every client certificate in the swarm.
  pkiDir = "/var/lib/swarm-bao-pki";

  # What a reader calls itself to the store. The hive's name, because a bao
  # cert-auth role matches on the CN — this is an interface, not a label.
  # No fallback: `hiveName` is asserted set for every hyperhive host, which is
  # the same condition this file's `config` is gated on. A fallback here reads
  # as a second supported spelling and there is no such thing.
  clientCn = hyperhiveCfg.hiveName;

  # $1 dir  $2 basename  $3 CN  $4 SAN or ""  $5 EKU
  signLeaf = pkgs.writeShellScript "swarm-bao-sign-leaf" ''
    set -euo pipefail
    d="$1"; base="$2"; cn="$3"; sans="$4"; eku="$5"
    csr="$(mktemp "$d/$base.csr.XXXXXX")"
    ext="$(mktemp "$d/$base.ext.XXXXXX")"
    trap 'rm -f "$csr" "$ext"' EXIT

    openssl req -newkey rsa:4096 -nodes -sha256 \
      -keyout "$d/$base-key.pem" -out "$csr" -subj "/CN=$cn"
    {
      [ -n "$sans" ] && printf 'subjectAltName=%s\n' "$sans"
      printf 'basicConstraints=critical,CA:FALSE\n'
      printf 'keyUsage=critical,digitalSignature,keyEncipherment\n'
      printf 'extendedKeyUsage=%s\n' "$eku"
    } > "$ext"
    openssl x509 -req -in "$csr" -CA "$d/ca.pem" -CAkey "$d/ca-key.pem" \
      -CAcreateserial -days 3650 -sha256 -extfile "$ext" -out "$d/$base.pem"
    chmod 0600 "$d/$base-key.pem"
    chmod 0644 "$d/$base.pem"
  '';
in
{
  config = lib.mkIf (hyperhiveCfg.enable && deployCfg.bao.enable) {
    services.hyperhive.deploy.bao = {
      serverCertFile = lib.mkDefault "${pkiDir}/server.pem";
      serverKeyFile = lib.mkDefault "${pkiDir}/server-key.pem";
      clientCaFile = lib.mkDefault "${pkiDir}/ca.pem";

      # A reader on this host, which happens to be the host that mints. Only
      # these three are what a reader elsewhere needs placed by hand; that they
      # collapse to the same CA file here is a property of self-signing, not of
      # the pairing.
      clientCertFile = lib.mkDefault "${pkiDir}/client.pem";
      clientKeyFile = lib.mkDefault "${pkiDir}/client-key.pem";
      serverCaFile = lib.mkDefault "${pkiDir}/ca.pem";
    };

    # Idempotent on ABSENCE, never on content. Re-issuing the CA invalidates
    # every client certificate already trusting it, so a rebuild that
    # "refreshed" it would lock every reader in the swarm out at once — the
    # same rule the store's TPM PIN unit follows, for a sharper reason.
    # Declared beside the unit it names, not in the store's module: an entry
    # exists only where the unit does, and this one is minted by glue that not
    # every hive runs.
    services.hyperhive.swarm.otel.journaldUnits = [ "swarm-bao-pki" ];

    systemd.services.swarm-bao-pki = {
      description = "mint the swarm secret store's own CA and leaves";
      before = [ "swarm-bao-certs.service" ];
      requiredBy = [ "swarm-bao-certs.service" ];
      path = [
        pkgs.openssl
        pkgs.coreutils
      ];
      serviceConfig = {
        Type = "oneshot";
        RemainAfterExit = true;
      };
      script = ''
        set -euo pipefail
        install -d -m 0700 ${pkiDir}

        if [ ! -s ${pkiDir}/ca.pem ]; then
          openssl req -x509 -newkey rsa:4096 -nodes -sha256 -days 3650 \
            -keyout ${pkiDir}/ca-key.pem -out ${pkiDir}/ca.pem \
            -subj "/CN=swarm-bao-ca ${cfg.domain}" \
            -addext "basicConstraints=critical,CA:TRUE,pathlen:0" \
            -addext "keyUsage=critical,keyCertSign,cRLSign"
          chmod 0600 ${pkiDir}/ca-key.pem
          chmod 0644 ${pkiDir}/ca.pem
        fi

        # The store's own identity, and the identity of a reader on this host.
        # A reader elsewhere gets its leaf from this CA out of band — that is
        # what makes the store reachable from another machine at all, and why
        # the CA is a file rather than a service.
        [ -s ${pkiDir}/server.pem ] || ${signLeaf} ${pkiDir} server \
          ${lib.escapeShellArg cfg.domain} ${lib.escapeShellArg "DNS:${cfg.domain}"} serverAuth
        [ -s ${pkiDir}/client.pem ] || ${signLeaf} ${pkiDir} client \
          ${lib.escapeShellArg clientCn} "" clientAuth

        # Minted whether or not a controller runs here, because the case it
        # serves is the one where it does not: a controller elsewhere needs a
        # leaf from this CA and has no way to sign one. Issuing it here turns
        # "obtain a certificate out of band" into "copy this file".
        #
        # Its own CN rather than the reader's above: the controller's policy
        # lets it create roles for every hive, and the reader's leaf carries
        # this hive's name.
        [ -s ${pkiDir}/controller.pem ] || ${signLeaf} ${pkiDir} controller \
          ${lib.escapeShellArg deployCfg.bao.controllerCommonName} "" clientAuth

        # The secret publisher's, minted here for the reason the controller's
        # line above gives — and it serves that case more often, not less: the
        # publisher runs beside AUTHELIA, which is the one host guaranteed not
        # to be this one whenever the store has a host of its own.
        [ -s ${pkiDir}/secret-publisher.pem ] || ${signLeaf} ${pkiDir} secret-publisher \
          ${lib.escapeShellArg deployCfg.bao.secretPublisherCommonName} "" clientAuth
      '';
    };
  };
}