router/tests: cover the staging uplink as NATed fallback exit

Neither regression fixed by the previous commit was observable: the VM
test had no staging port, and pinging the ISP's PPPoE address only needs
ppp0's connected route, not the default route pppd refused to install.

Add a fifth node, `oldlan`: a networkd DHCP server on vlan 4 handing gw
its staging lease, with a second address (203.0.113.1) that gw can only
reach through that lease's default route. It has no route back to the
VLANs, so client pings only work if gw masquerades.

Proven: pppd's metric-0 default wins over the DHCP one while ppp0 is up;
lan reaches the old LAN via the staging port and iot (allowWan = false)
does not; after stopping pppd the staging route carries WAN traffic with
the same allowWan split; restarting pppd makes ppp0 preferred again.

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

@@ -1,14 +1,17 @@
 # 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`,
-# and an untagged access port carries mgmt to `admin`.
+# an untagged access port carries mgmt to `admin`, and `oldlan` is the DHCP
+# 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, and the
+# answering on the VLAN with the blocklist active, NAT to the WAN, 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
@@ -20,6 +23,10 @@ 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";
@@ -36,6 +43,7 @@ in
         isp = { };
         client = { };
         admin = { };
+        oldlan = { };
       };
 
       instances.router = {
@@ -48,6 +56,7 @@ in
           wan.interface = "wan";
           trunkPorts = [ "trunk" ];
           accessPorts.access = "mgmt";
+          stagingPort = "staging";
           vlans = {
             mgmt = {
               id = 10;
@@ -111,6 +120,10 @@ in
           vlan = 3;
           assignIP = false;
         };
+        staging = {
+          vlan = 4;
+          assignIP = false;
+        };
       };
 
       # Something must listen on 22 for the mgmt-only SSH rule to be observable
@@ -251,6 +264,32 @@ 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 = ''
@@ -302,5 +341,21 @@ 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'")
   '';
 }