router: allow SSH on the staging port

The staging uplink is in no VLAN zone and was fully default-deny; admit
TCP 22 on it so the box is reachable from the old LAN before the mgmt
VLAN or the mesh are up. Everything else on the port stays closed.

docs/src/gateways.md

@@ -28,7 +28,7 @@ mgmt-only trust model, SSH exposure and the Wi-Fi bridge ports. Run it with
 | DHCP         | Kea, one subnet per VLAN                                                                                                                                                                                                                                                                                                      |
 | DNS          | Blocky (blocklist resolver), metrics on :4000 scraped by control                                                                                                                                                                                                                                                              |
 | IPv6         | DHCPv6-PD on ppp0, /64 per VLAN via SLAAC                                                                                                                                                                                                                                                                                     |
-| Bans         | Optional per site (`crowdsec.enable`): CrowdSec + nftables bouncer (sshd log parsing)                                                                                                                                                                                                                                         |
+| Bans         | CrowdSec + nftables bouncer (sshd log parsing)                                                                                                                                                                                                                                                                                |
 | Omada        | Optional per site: TP-Link Omada controller as a podman container                                                                                                                                                                                                                                                             |
 | Wi-Fi        | Optional: hostapd on the router's radios; each SSID (`wifi.networks`) is an untagged access port of its VLAN, passphrases via vars prompts — see `modules/clan/router/README.md`                                                                                                                                              |
 | Proxy        | Optional: Caddy reverse proxy for internal services under `*.<site><n>.cnx.network` with a real Let's Encrypt wildcard (DNS-01 against ns1)                                                                                                                                                                                   |
@@ -71,7 +71,7 @@ Trust model: mgmt → everything; other VLANs → router DNS/DHCP + internet onl
    installer: `ls -l /dev/disk/by-id/`).
 2. Add the machine to `inventory.machines` in `clan.nix`, to the `router`
    instance in `inventory.nix` (`roles.default.machines.gw-<city>-<n>.settings`: `site`,
-   `siteId` (next free number), port names, VLANs, `omada.enable`, `crowdsec.enable`; keep the
+   `siteId` (next free number), port names, VLANs, `omada.enable`; keep the
    `mgmt`/`lan` VLANs), and to the machine list in `modules/mesh-hosts.nix`.
    Do **not** add it to `modules/hosts.nix` (dynamic PPPoE IP; clan connects
    over the mesh).

inventory.nix

@@ -77,8 +77,6 @@ in
       };
       # This site runs the Omada controller for its APs/switches.
       omada.enable = true;
-      # sshd ban engine (was unconditional before the option existed).
-      crowdsec.enable = true;
 
       # Internal reverse proxy: real wildcard cert *.cnx1.cnx.network; Blocky
       # resolves the names to the router's LAN address for mgmt+lan clients.

modules/clan/router/README.md

@@ -3,11 +3,10 @@
 Turns a machine with several NICs into a site gateway: PPPoE WAN (ISP
 credentials via vars prompts), a VLAN-filtering bridge over the LAN ports with
 one L3 interface per VLAN, Kea DHCP and Blocky DNS per VLAN, nftables
-firewall/NAT, DHCPv6-PD, an iperf3 server and a WAN speed-test timer.
+firewall/NAT, DHCPv6-PD, CrowdSec, an iperf3 server and a WAN speed-test
-Optional: a Wi-Fi access point on the router's own radios (hostapd), CrowdSec
+timer. Optional: a Wi-Fi access point on the router's own radios (hostapd),
-with the nftables bouncer (sshd log parsing), the TP-Link Omada controller
+the TP-Link Omada controller (podman) and an internal Caddy reverse proxy
-(podman) and an internal Caddy reverse proxy with a real wildcard certificate
+with a real wildcard certificate (ACME DNS-01).
-(ACME DNS-01).
 
 Addressing convention: a site owns `10.<siteId>.0.0/16`; VLAN `<id>` defaults
 to `10.<siteId>.<id>.0/24`, router at `.1`, DHCP pool `.100-.199`. The `mgmt`

modules/clan/router/crowdsec.nix

@@ -1,14 +1,12 @@
 # CrowdSec security engine + nftables bouncer: parses sshd auth attempts from
 # the journal and bans offending source IPs at the firewall. Log-based (no
-# inline DPI) so it costs the N300 next to nothing. Opt-in per site
+# inline DPI) so it costs the N300 next to nothing.
-# (`crowdsec.enable`): the hub sync needs internet at activation time.
 { settings }:
-{ lib, ... }:
+{ ... }:
 let
   cfg = settings;
 in
 {
-  config = lib.mkIf cfg.crowdsec.enable {
   services.crowdsec = {
     enable = true;
     autoUpdateService = true;
@@ -45,5 +43,4 @@ in
     registerBouncer.enable = true;
     settings.mode = "nftables";
   };
-  };
 }

modules/clan/router/dns-dhcp.nix

@@ -12,19 +12,7 @@ in
   services.kea.dhcp4 = {
     enable = true;
     settings = {
-      interfaces-config = {
+      interfaces-config.interfaces = lib.mapAttrsToList (name: _: "vlan-${name}") dhcpVlans;
-        interfaces = lib.mapAttrsToList (name: _: "vlan-${name}") dhcpVlans;
-        # The unit orders after network-online.target, which under networkd
-        # only waits for the WAN carrier (the vlan-* links are
-        # RequiredForOnline=no), so Kea can start before vlan-* have their
-        # addresses. By default it then logs the failed bind and runs with no
-        # socket at all: clients' DISCOVERs reach vlan-lan and nobody answers.
-        # Insist on every socket and keep retrying while networkd catches up;
-        # if it still cannot bind, exit and let systemd restart the unit.
-        service-sockets-require-all = true;
-        service-sockets-max-retries = 60;
-        service-sockets-retry-wait-time = 1000;
-      };
       lease-database = {
         type = "memfile";
         persist = true;
@@ -56,10 +44,6 @@ in
     };
   };
 
-  # The nixpkgs unit already has Restart=on-failure; space the restarts out so
-  # a persistent bind failure does not trip the start-rate limit.
-  systemd.services.kea-dhcp4-server.serviceConfig.RestartSec = 5;
-
   services.blocky = {
     enable = true;
     settings = {

modules/clan/router/firewall.nix

@@ -3,8 +3,7 @@
 #   other VLANs -> DNS/DHCP on the router + WAN (if allowWan); no inter-VLAN
 #   WAN (ppp0) -> nothing inbound beyond established/related
 #   mesh       -> admin SSH + metrics scrapes (same trust boundary as the fleet)
-#   staging    -> admin SSH only inbound (pre-cutover uplink into the old LAN);
+#   staging    -> admin SSH only (pre-cutover uplink into the old LAN)
-#                 allowWan VLANs are NATed out through it while ppp0 is down
 { settings }:
 { lib, ... }:
 let
@@ -15,13 +14,6 @@ let
     lib.filterAttrs (_: vlan: vlan.allowWan) cfg.vlans
   );
   nonMgmtIfs = lib.filter (i: i != "vlan-mgmt") vlanIfs;
-
-  # allowWan VLANs may also leave through the staging uplink. Same set as
-  # networking.nat.internalInterfaces below, so `allowWan` holds on both
-  # exits. The kernel picks the exit: ppp0 (metric 0, see pppoe.nix) while
-  # the session is up, the staging DHCP route (metric 1024) otherwise.
-  stagingExit = cfg.stagingPort != null && wanVlanIfs != [ ];
-  wanVlanSet = "{ ${lib.concatMapStringsSep ", " (i: ''"${i}"'') wanVlanIfs} }";
 in
 {
   networking.nftables.enable = true;
@@ -58,9 +50,6 @@ in
     extraForwardRules = ''
       tcp flags syn tcp option maxseg size set rt mtu comment "MSS clamp for PPPoE mtu 1492"
       iifname "vlan-mgmt" accept comment "mgmt reaches all VLANs and the WAN"
-    ''
-    + lib.optionalString stagingExit ''
-      iifname ${wanVlanSet} oifname "${cfg.stagingPort}" accept comment "allowWan VLANs out via the staging uplink"
     '';
   };
 
@@ -73,19 +62,4 @@ in
     externalInterface = "ppp0";
     internalInterfaces = wanVlanIfs;
   };
-
-  # networking.nat only masquerades on its single externalInterface; the
-  # staging uplink needs its own postrouting chain (nixos-nat's is
-  # oifname-scoped to ppp0, so the two never both apply).
-  networking.nftables.tables = lib.optionalAttrs stagingExit {
-    router-staging-nat = {
-      family = "ip";
-      content = ''
-        chain post {
-          type nat hook postrouting priority srcnat;
-          iifname ${wanVlanSet} oifname "${cfg.stagingPort}" masquerade comment "allowWan VLANs out via the staging uplink"
-        }
-      '';
-    };
-  };
 }

modules/clan/router/interface.nix

@@ -256,15 +256,13 @@ in
       example = "enp3s0";
       description = ''
         Temporary DHCPv4-client uplink into the existing LAN while the box
-        runs alongside the router it replaces: gives it (and, NATed, the
+        runs alongside the router it replaces: gives it internet + mesh
-        allowWan VLANs) internet + mesh before the WAN port is cabled; once
+        before the WAN port is cabled (PPPoE simply retries until then). The
-        the PPPoE session is up its default route wins, and the staging
+        port is in no VLAN zone; the firewall admits only SSH on it. Do NOT
-        route only carries traffic again if the session drops (PPPoE simply
+        connect the trunk ports to the production switch while staging —
-        retries until then). The port is in no VLAN zone; inbound, the
+        Kea on the mgmt tag would fight the old router's DHCP in one
-        firewall admits only SSH on it. Do NOT connect the trunk ports to
+        broadcast domain. Set to null at cutover (and usually hand the port
-        the production switch while staging — Kea on the mgmt tag would
+        back to `trunkPorts`).
-        fight the old router's DHCP in one broadcast domain. Set to null at
-        cutover (and usually hand the port back to `trunkPorts`).
       '';
     };
 
@@ -285,8 +283,6 @@ in
 
     omada.enable = lib.mkEnableOption "TP-Link Omada SDN controller (podman container)";
 
-    crowdsec.enable = lib.mkEnableOption "CrowdSec (sshd log parsing) with the nftables bouncer";
-
     proxy = {
       enable = lib.mkEnableOption "internal reverse proxy (Caddy, wildcard cert via DNS-01)";
 

modules/clan/router/pppoe.nix

@@ -30,11 +30,6 @@ in
     '';
   };
 
-  # defaultroute-metric 0: pppd refuses `defaultroute` while any other
-  # default route exists (e.g. the staging uplink's DHCP route, metric 1024,
-  # network.nix) unless given a metric; with 0 it only checks for a metric-0
-  # route, installs its own as the preferred exit, and removes it again on
-  # hangup so the staging route takes over.
   services.pppd = {
     enable = true;
     peers.wan = {
@@ -45,7 +40,6 @@ in
         file ${creds.files."user-opts".path}
         noipdefault
         defaultroute
-        defaultroute-metric 0
         noauth
         hide-password
         persist

modules/clan/router/tests/vm/default.nix

@@ -1,17 +1,14 @@
 # End-to-end VM test of the router service: a PPPoE access concentrator plays
 # the ISP on the WAN port, a trunk carries tagged lan/iot VLANs to `client`,
-# an untagged access port carries mgmt to `admin`, and `oldlan` is the DHCP
+# and an untagged access port carries mgmt to `admin`.
-# network the box is staged in before cutover.
 #
 #   isp ---(vlan 1: PPPoE)--- wan [gw] trunk ---(vlan 2: tagged 20/40)--- client
 #                                    access --(vlan 3: untagged mgmt)--- admin
-#                                    staging -(vlan 4: DHCP client)--- oldlan
 #
 # What is proven: PPPoE dial-in with the vars-provided credentials, bridge
 # VLAN tagging/untagging, Kea leases and reservations per VLAN, Blocky
-# answering on the VLAN with the blocklist active, NAT to the WAN, the
+# answering on the VLAN with the blocklist active, NAT to the WAN, and the
-# firewall trust model (allowWan, mgmt-only SSH, no inter-VLAN forwarding),
+# firewall trust model (allowWan, mgmt-only SSH, no inter-VLAN forwarding).
-# and the staging uplink as NATed fallback exit behind ppp0.
 { pkgs, lib, ... }:
 let
   # The vars mock answers every prompt with "mock-prompt-value-<name>"; the
@@ -23,10 +20,6 @@ let
   clientAddress = "10.9.20.50";
   adminMac = "02:00:00:00:00:10";
   adminAddress = "10.9.10.50";
-  oldlanAddress = "192.168.88.1";
-  # Only reachable through oldlan's router role, i.e. via gw's staging
-  # default route (metric 1024); ppp0's metric-0 default must win while up.
-  beyondStaging = "203.0.113.1";
 in
 {
   name = "router";
@@ -43,7 +36,6 @@ in
         isp = { };
         client = { };
         admin = { };
-        oldlan = { };
       };
 
       instances.router = {
@@ -56,7 +48,6 @@ in
           wan.interface = "wan";
           trunkPorts = [ "trunk" ];
           accessPorts.access = "mgmt";
-          stagingPort = "staging";
           vlans = {
             mgmt = {
               id = 10;
@@ -120,10 +111,6 @@ in
           vlan = 3;
           assignIP = false;
         };
-        staging = {
-          vlan = 4;
-          assignIP = false;
-        };
       };
 
       # Something must listen on 22 for the mgmt-only SSH rule to be observable
@@ -131,11 +118,13 @@ in
       services.openssh.enable = true;
 
       # The sandbox has no internet: serve the blocklist from a local file
-      # instead of GitHub. (CrowdSec, whose hub sync needs the network too,
+      # instead of GitHub, and skip CrowdSec, whose hub sync needs the network
-      # is opt-in and stays off.)
+      # (it is not what this test exercises).
       services.blocky.settings.blocking.denylists.ads = lib.mkForce [
         (toString (pkgs.writeText "ads.hosts" "0.0.0.0 ads.example.com\n"))
       ];
+      services.crowdsec.enable = lib.mkForce false;
+      services.crowdsec-firewall-bouncer.enable = lib.mkForce false;
 
       # Two simulated radios: wlan0 is the AP (settings above), wlan1 plays a
       # wireless client. It lives in its own network namespace, like the
@@ -262,32 +251,6 @@ in
       };
       environment.systemPackages = [ pkgs.netcat ];
     };
-
-    # The LAN the box is staged in: a DHCP server handing gw its uplink
-    # lease, plus an address that is only reachable via that uplink's
-    # default route. No route back to 10.9.0.0/16: replies only reach the
-    # clients if gw masquerades them.
-    oldlan = {
-      virtualisation.interfaces.staging = {
-        vlan = 4;
-        assignIP = false;
-      };
-      networking.useDHCP = false;
-      networking.useNetworkd = true;
-      systemd.network.networks."10-staging" = {
-        matchConfig.Name = "staging";
-        address = [
-          "${oldlanAddress}/24"
-          "${beyondStaging}/32"
-        ];
-        networkConfig.DHCPServer = true;
-        dhcpServerConfig = {
-          PoolOffset = 100;
-          PoolSize = 50;
-        };
-      };
-      networking.firewall.allowedUDPPorts = [ 67 ];
-    };
   };
 
   testScript = ''
@@ -339,21 +302,5 @@ in
         gw.wait_until_succeeds("ip netns exec sta wpa_cli -i wlan1 status | grep -q wpa_state=COMPLETED")
         gw.succeed("timeout 60 sta-dhcp")
         gw.succeed("ip netns exec sta ip -4 addr show wlan1 | grep -q 'inet 10.9.20.1[0-9][0-9]/24'")
-
-    with subtest("Staging uplink: NATed exit for allowWan VLANs, behind ppp0 while it is up"):
-        gw.wait_until_succeeds("ip -4 route show default dev staging | grep -q 'via ${oldlanAddress}'")
-        # pppd installs its default route despite the DHCP one (defaultroute-metric 0).
-        gw.succeed("ip route get ${beyondStaging} | grep -q 'dev ppp0'")
-        # On-link old-LAN hosts are reached through the staging port regardless.
-        client.succeed("ping -c1 -W2 -I lan0 ${oldlanAddress}")
-        client.fail("ping -c1 -W2 -I iot0 ${oldlanAddress}")
-        # ppp0 down: the staging route carries the WAN traffic, allowWan still holds.
-        gw.systemctl("stop pppd-wan.service")
-        gw.wait_until_succeeds("ip route get ${beyondStaging} | grep -q 'dev staging'")
-        client.succeed("ping -c1 -W2 -I lan0 ${beyondStaging}")
-        client.fail("ping -c1 -W2 -I iot0 ${beyondStaging}")
-        # ppp0 back: preferred again.
-        gw.systemctl("start pppd-wan.service")
-        gw.wait_until_succeeds("ip route get ${beyondStaging} | grep -q 'dev ppp0'")
   '';
 }

modules/clan/router/wifi.nix

@@ -12,6 +12,7 @@
 {
   config,
   lib,
+  pkgs,
   ...
 }:
 let
@@ -120,18 +121,26 @@ in
         );
         message = "router: wifi.radios.<radio>.macAddress is required for radios broadcasting more than one network.";
       }
-      {
-        assertion =
-          !config.networking.wireless.enable
-          && !config.networking.wireless.iwd.enable
-          && !config.networking.networkmanager.enable;
-        message = "router: wifi.enable needs the radios for hostapd; disable networking.wireless (wpa_supplicant), iwd and NetworkManager.";
-      }
     ];
 
     # Regulatory database for the kernel, so countryCode actually applies.
     hardware.wirelessRegulatoryDatabase = true;
 
+    # The kernel refuses to bridge a wireless interface in station mode, and
+    # networkd stops retrying before hostapd switches the radio to AP mode;
+    # so put it in AP mode the moment it appears (kernel name or the renamed
+    # one, whichever the user configured). hostapd finds it already there.
+    services.udev.extraRules = lib.concatMapStrings (
+      radio:
+      let
+        run = ''RUN+="${pkgs.iw}/bin/iw dev ${radio} set type __ap"'';
+      in
+      ''
+        ACTION=="add", SUBSYSTEM=="net", KERNEL=="${radio}", ${run}
+        ACTION=="add", SUBSYSTEM=="net", NAME=="${radio}", ${run}
+      ''
+    ) (lib.attrNames wifi.radios);
+
     clan.core.vars.generators = lib.genAttrs (map (name: "wifi-${name}-passphrase") secured) (
       gen:
       let
@@ -175,22 +184,12 @@ in
     };
 
     # Each BSS is an untagged access port of its VLAN on br0 (cf. accessPorts
-    # in network.nix). The kernel refuses to bridge a wireless interface in
+    # in network.nix); networkd enslaves the interface once hostapd creates it.
-    # station mode (IFF_DONT_BRIDGE), and a failed enslave parks the link in
-    # networkd's `failed` state for good: networkd only re-evaluates a link
-    # when its matching .network file changes. So match on the AP interface
-    # type as well as the name: the radio's initial station-mode netdev
-    # matches nothing (unmanaged), and once hostapd switches it to AP and
-    # brings the carrier up, networkd matches this file for the first time
-    # and enslaves it. Extra BSSes are created by hostapd in AP mode already.
     systemd.network.networks = lib.listToAttrs (
       map (
         b:
         lib.nameValuePair "27-wifi-${b.iface}" {
-          matchConfig = {
+          matchConfig.Name = b.iface;
-            Name = b.iface;
-            WLANInterfaceType = "ap";
-          };
           networkConfig.Bridge = "br0";
           bridgeVLANs = [
             {