hyperhive/nix/container-modules/swarm-secret-publisher.nix

# The unit that puts swarm-level secrets into the swarm's secret store, so
# whoever needs one can read it there: a hive its own and its agents'
# credentials, a service or the controller its own. It mints nothing: every
# value is an OIDC client secret authelia minted, and this unit copies it.
#
# Imported inside authelia's container, beside the mint: it reads each secret
# where authelia writes it. The host module that declares the container sets
# the options below, as for ./swarm-journal-forwarder.nix.
#
# ⚠️ "Whoever", including a reader on authelia's own host. A swarm service's
# secret goes into the store even when the service runs beside authelia,
# because its reader fetches it from the store in every deployment —
# ../host-modules/swarm-grafana.nix states the ruling that made that the only
# route. Publishing "only when the reader is elsewhere" would be a second shape
# of this unit, gated on a fact about another host, to save a round trip on
# the one host that can afford it.
#
# ⚠️ ITS OWN STORE IDENTITY, not swarm-controller's. That principal may rewrite
# every hive's policy and login role; a unit that writes a handful of secrets
# has no business holding it. ../host-modules/swarm-bao.nix grants this one
# `create`/`update` under the hive prefix and nothing else — no `read`.
#
# ⚠️ THE SECRET NEVER REACHES `argv`. `bao` is an external binary, so every
# argument is world-readable in /proc for the life of the call — the value is
# passed as `@<path>` and read by bao itself.
#
# ⚠️ Nothing in the container waits for this unit. Authelia is the swarm's IdP
# and starts whether or not the store answers; a store that is down or sealed
# is a failed run that restarts.
{
  config,
  lib,
  pkgs,
  ...
}:
let
  cfg = config.services.hyperhive.swarmSecretPublisher;
in
{
  options.services.hyperhive.swarmSecretPublisher = {
    enable = lib.mkEnableOption "copying the OIDC client secrets authelia mints into the swarm secret store";

    clientSecretDir = lib.mkOption {
      type = lib.types.str;
      description = ''
        Directory authelia mints each client's plaintext into, as
        `<client id>.secret`. A path inside the container.
      '';
    };

    secrets = lib.mkOption {
      type = lib.types.listOf (
        lib.types.submodule {
          options = {
            clientId = lib.mkOption {
              type = lib.types.str;
              description = "The minted client, whose `<client id>.secret` is copied.";
            };
            path = lib.mkOption {
              type = lib.types.str;
              example = "secret/swarm/services/swarm-grafana/oidc/client";
              description = "KV path its reader fetches the value from.";
            };
            withClientId = lib.mkOption {
              type = lib.types.bool;
              default = false;
              description = ''
                Also store the client id beside the value, as `client_id`, for
                a reader that has to reconstruct it from the store alone.
              '';
            };
          };
        }
      );
      description = "Every secret this unit copies, and where to.";
    };

    store = {
      package = lib.mkOption {
        type = lib.types.package;
        description = "The `bao` CLI the unit logs in and writes with.";
      };
      addr = lib.mkOption {
        type = lib.types.str;
        description = "The swarm secret store's address, by name.";
      };
      clientCertFile = lib.mkOption {
        type = lib.types.str;
        description = ''
          The publisher's store identity, as a path inside the container. Its
          subject must be
          {option}`services.hyperhive.deploy.bao.secretPublisherCommonName`.
          A path, never a value.
        '';
      };
      clientKeyFile = lib.mkOption {
        type = lib.types.str;
        description = "Private key for `store.clientCertFile`. A path, never a value.";
      };
      caFile = lib.mkOption {
        type = lib.types.nullOr lib.types.str;
        default = null;
        description = "CA the store's server certificate chains to; null means the system trust store.";
      };
    };
  };

  config = lib.mkIf cfg.enable {
    # Re-publish when authelia rotates a secret. The mint writes the file, so
    # the file is the event — there is no signal from authelia to subscribe to.
    systemd.paths.swarm-secret-publish = {
      description = "watch for minted OIDC client secrets to publish";
      wantedBy = [ "multi-user.target" ];
      pathConfig = {
        PathChanged = cfg.clientSecretDir;
        Unit = "swarm-secret-publish.service";
      };
    };

    systemd.services.swarm-secret-publish = {
      description = "publish the swarm's minted secrets to the swarm secret store";
      wantedBy = [ "multi-user.target" ];
      after = [ "network.target" ];
      path = [
        cfg.store.package
        pkgs.coreutils
      ];
      # ⚠️ No `RemainAfterExit`. A oneshot that stays `active (exited)` turns
      # every later start from the path unit above into a no-op.
      serviceConfig = {
        Type = "oneshot";
        # Bounded here rather than left to systemd's default, so the number a
        # boot waits on is in the file that waits. A sealed store answers on
        # the port and never answers the write.
        TimeoutStartSec = 60;
        Restart = "on-failure";
        RestartSec = 30;
      };
      environment = {
        BAO_ADDR = cfg.store.addr;
        BAO_CLIENT_CERT = cfg.store.clientCertFile;
        BAO_CLIENT_KEY = cfg.store.clientKeyFile;
      }
      // lib.optionalAttrs (cfg.store.caFile != null) {
        BAO_CACERT = cfg.store.caFile;
      };
      script = ''
        set -euo pipefail

        # Cert auth is a login, not a transport setting. The `BAO_CLIENT_*`
        # variables above only decide which certificate the TLS handshake
        # presents; without a token `bao` asks its token helper instead, and
        # that is a `sh` this unit's `path` does not carry. `-token-only`
        # answers on stdout and skips the helper on both sides.
        #
        # Unhandled on purpose: `Restart=on-failure` above is what a store that
        # cannot authenticate this container should get. Degrading here would
        # report "published 0" as an ordinary quiet day.
        BAO_TOKEN="$(bao login -method=cert -token-only)"
        export BAO_TOKEN

        published=0
        skipped=0

        ${lib.concatMapStringsSep "\n" (s: ''
          src=${lib.escapeShellArg "${cfg.clientSecretDir}/${s.clientId}.secret"}
          if [ -s "$src" ]; then
            # `value=@$src` hands bao the PATH: bao opens the file itself, so
            # the plaintext is never an argument of this process. Writing it as
            # `value="$(cat "$src")"` would publish it to /proc for anyone in
            # the container to read.
            bao kv put ${lib.escapeShellArg s.path} \
              value=@"$src"${lib.optionalString s.withClientId " client_id=${lib.escapeShellArg s.clientId}"}
            published=$((published + 1))
          else
            # Not an error: authelia mints on its FIRST BOOT, so an absent file
            # is "not yet", and the path unit above re-runs this when it lands.
            # A client registered nowhere in this swarm is never minted at all.
            echo "no minted secret at $src yet; the path unit will re-run this" >&2
            skipped=$((skipped + 1))
          fi
        '') cfg.secrets}

        echo "published $published client secret(s), skipped $skipped"
      '';
    };
  };
}