# The hive's own nftables table, `inet hive_egress`, loaded by a systemd
# oneshot. It is independent of the NixOS firewall: `networking.firewall`
# renders only the rules of the backend in use (`iptables` unless
# `networking.nftables.enable` is set), so a rule that has to hold on every
# host lives here, in a table no firewall backend writes. Only
# `networking.nftables.flushRuleset` removes it; the unit re-applies it then.
#
# The table holds one chain: traffic from the agent bridge to host
# loopback is dropped. The kernel does the same by default (a packet for
# 127.0.0.0/8 arriving on a non-loopback interface is a martian while
# `route_localnet` is 0); this rule is the second layer, and the assertion
# below keeps the first one on.
{
  lib,
  config,
  pkgs,
  ...
}:
let
  cfg = config.services.hyperhive.network;
  nft = lib.getExe pkgs.nftables;

  # One transaction: `add` + `delete` drop an old copy of the table and the
  # definition recreates it, so the file loads the same on first start, on a
  # reload and after something else flushed the ruleset.
  ruleset = pkgs.writeText "hive-egress.nft" ''
    add table inet hive_egress
    delete table inet hive_egress

    table inet hive_egress {
      chain input {
        type filter hook input priority filter - 10; policy accept;
        iifname "${cfg.bridgeName}" ip daddr 127.0.0.0/8 counter drop
        iifname "${cfg.bridgeName}" ip6 daddr ::1 counter drop
      }
    }
  '';

  routeLocalnetKeys = [
    "net.ipv4.conf.all.route_localnet"
    "net.ipv4.conf.default.route_localnet"
    "net.ipv4.conf.${cfg.bridgeName}.route_localnet"
  ];
  isOn =
    v:
    builtins.elem v [
      1
      "1"
      true
    ];
in
{
  config = lib.mkIf cfg.enable {
    assertions = [
      {
        assertion = !(lib.any (k: isOn (config.boot.kernel.sysctl.${k} or 0)) routeLocalnetKeys);
        message = ''
          boot.kernel.sysctl must not turn on route_localnet (${lib.concatStringsSep ", " routeLocalnetKeys}).
          With it on, the kernel routes a packet from the agent bridge to 127.0.0.0/8
          instead of dropping it as a martian, which leaves the hive_egress
          table as the only barrier between an agent and the host's loopback services.
        '';
      }
    ];

    systemd.services.hive-egress = {
      description = "hive nftables table (agent bridge to host loopback drop)";
      wantedBy = [ "multi-user.target" ];
      wants = [ "network-pre.target" ];
      before = [ "network-pre.target" ];
      # `nftables.service` runs `flush ruleset` where `networking.nftables.flushRuleset`
      # is on: start after it, follow its restarts and re-apply on its reload.
      after = [ "nftables.service" ];
      partOf = [ "nftables.service" ];
      unitConfig.ReloadPropagatedFrom = [ "nftables.service" ];
      reloadIfChanged = true;
      serviceConfig = {
        Type = "oneshot";
        RemainAfterExit = true;
        ExecStart = "${nft} -f ${ruleset}";
        ExecReload = "${nft} -f ${ruleset}";
        ExecStop = "-${nft} delete table inet hive_egress";
      };
    };
  };
}