feat(monitoring): restrict syslog ingress to the sending networks

alloy-syslog accepted syslog from any world source. Senders seen in
Hubble and Loki over the last 7 days: switches and APs on Management,
SLZB coordinators and edge hosts on IoT, and the UDM, which sources from
its k8s-ingress address 10.2.47.1. The LB is ETP=Local, so those client
addresses reach the pod.

Refs S28-19

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

ansible/inventory/pve_hosts.yml

@@ -49,20 +49,11 @@ edge-1.iot.renner.uno
 zwave_gateway
 heating_can
 
-# NTP servers. edge-1 was added here so the role would survive the PVE hosts
-# being retired for bare-metal Talos, which cannot run chrony or keepalived
-# itself. That retirement has now happened, so edge-1 is the ONLY member.
-#
-# THIS IS NO LONGER HIGHLY AVAILABLE. The group was jupiter (MASTER, prio 100),
-# saturn (90), neptune (80) and edge-1 (BACKUP, 70); the first three are gone.
-# A single VRRP member takes the address regardless of its configured state, so
-# the service address is still served, but by one thin client with
-# no failover behind it. install-ntp-ha.yml still carries the four-host
-# ntp_servers priority map, which now describes hosts that do not exist.
-#
-# Restoring redundancy needs a second chrony host that is not a Talos node.
-# See plays/install-ntp-ha.yml for why keepalived is scoped more narrowly than
-# chrony within this group.
+# NTP servers: every edge host (edge-1 BACKUP prio 70, edge-2 BACKUP prio 60;
+# see the ntp_servers map in plays/install-ntp-ha.yml). Talos nodes cannot run
+# chrony or keepalived. The jupiter/saturn/neptune entries in that map
+# describe retired PVE hosts. See plays/install-ntp-ha.yml for why keepalived
+# is scoped more narrowly than chrony within this group.
 [ntp_cluster:children]
 edge_host
 

ansible/plays/install-edge-host.yml

@@ -34,6 +34,7 @@
   roles:
     - certificates
     - common
+    - pacman-cache
     - edge-flash-wear
     - docker-install
     - edge-log-shipper

ansible/roles/pacman-cache/files/pacman-cache.hook

@@ -0,0 +1,14 @@
+# Managed by ansible (roles/pacman-cache).
+# Downloaded packages are not kept; older versions come from the Arch Linux
+# Archive.
+[Trigger]
+Operation = Install
+Operation = Upgrade
+Operation = Remove
+Type = Package
+Target = *
+
+[Action]
+Description = Removing downloaded packages from the cache...
+When = PostTransaction
+Exec = /usr/bin/find /var/cache/pacman/pkg -mindepth 1 -delete

ansible/roles/pacman-cache/tasks/main.yml

@@ -0,0 +1,21 @@
+---
+# Keep the pacman package cache empty. pacman keeps every downloaded package;
+# on a 7 GB eMMC root the cache grows to gigabytes. Arch hosts only.
+
+- name: Ensure the pacman hook directory exists
+  ansible.builtin.file:
+    path: /etc/pacman.d/hooks
+    state: directory
+    mode: "0755"
+
+- name: Empty the package cache after every transaction
+  ansible.builtin.copy:
+    src: pacman-cache.hook
+    dest: /etc/pacman.d/hooks/pacman-cache.hook
+    mode: "0644"
+
+- name: Empty the package cache
+  ansible.builtin.command:
+    argv: [find, /var/cache/pacman/pkg, -mindepth, "1", -delete, -print]
+  register: pacman_cache_clean
+  changed_when: pacman_cache_clean.stdout | length > 0

kubernetes/infrastructure/network-policies/cidr-groups.yaml

@@ -0,0 +1,150 @@
+# Client networks as Cilium CIDR groups, referenced from CNPs via
+# fromCIDRSet.cidrGroupRef. ULA + IPv4 only: the ISP-delegated GUA prefixes
+# change and are not listed.
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-default
+spec:
+  externalCIDRs:
+    - fd00::/64
+    - 192.168.8.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-management
+spec:
+  externalCIDRs:
+    - fd02:10::/64
+    - 10.2.10.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-radius
+spec:
+  externalCIDRs:
+    - fd02:11::/64
+    - 10.2.11.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-video
+spec:
+  externalCIDRs:
+    - 10.2.20.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-iot
+spec:
+  externalCIDRs:
+    - fd02:30::/64
+    - 10.2.30.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-server
+spec:
+  externalCIDRs:
+    - fd02:40::/64
+    - fd40::/64
+    - 10.2.40.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-k8s-node
+spec:
+  externalCIDRs:
+    - fd02:46::/64
+    - 10.2.46.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-k8s-ingress
+spec:
+  externalCIDRs:
+    - fd02:47::/64
+    - 10.2.47.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-k8s-pod
+spec:
+  externalCIDRs:
+    - fd02:48::/64
+    - 10.2.48.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-privat
+spec:
+  externalCIDRs:
+    - fd02:50::/64
+    - 10.2.50.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-phone
+spec:
+  externalCIDRs:
+    - 10.2.60.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-access
+spec:
+  externalCIDRs:
+    - 10.2.70.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-vpn
+spec:
+  externalCIDRs:
+    - 10.2.80.0/24
+    - 192.168.32.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-guest
+spec:
+  externalCIDRs:
+    - 10.2.90.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-multi-transfer
+spec:
+  externalCIDRs:
+    - 10.2.122.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-multi-lan
+spec:
+  externalCIDRs:
+    - 10.2.123.0/24
+---
+apiVersion: cilium.io/v2
+kind: CiliumCIDRGroup
+metadata:
+  name: net-mutti
+spec:
+  externalCIDRs:
+    - 10.2.200.0/24

kubernetes/infrastructure/network-policies/kustomization.yaml

@@ -1,6 +1,7 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
+  - cidr-groups.yaml
   - default-deny.yaml
   - allow-ingress.yaml
   - ingress-isolation.yaml

kubernetes/infrastructure/network-policies/monitoring-alloy-syslog.yaml

@@ -1,13 +1,6 @@
-# Targeted carve-out: alloy-syslog needs world ingress on the syslog
-# ports specifically. The Service is ETP=Cluster, so external syslog
-# senders (Proxmox, LXC hosts, network gear) hit the LB IP, get DNAT'd
-# to an alloy pod, and get SNAT'd to the receiving node's cilium_host
-# address. Cilium then sees the source as `world-ipv4` identity (the
-# cilium_host IP isn't a known endpoint), NOT `host` — so the broad
-# monitoring CNP's `fromEntities: host` rule doesn't catch it.
-#
-# Scoped via endpointSelector so this only widens ingress on the
-# alloy-syslog pod, not the whole namespace.
+# Syslog senders reaching the alloy-syslog LB (ETP=Local, client address
+# reaches the pod): network gear on Management, the SLZB coordinators on
+# IoT, and the UDM itself, which sources from its k8s-ingress address.
 apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
@@ -19,8 +12,10 @@ spec:
       app.kubernetes.io/instance: alloy-syslog
       app.kubernetes.io/name: alloy
   ingress:
-    - fromEntities:
-        - world
+    - fromCIDRSet:
+        - cidrGroupRef: net-management
+        - cidrGroupRef: net-iot
+        - cidrGroupRef: net-k8s-ingress
       toPorts:
         - ports:
             - port: "514"

kubernetes/infrastructure/network-policies/trmnl-ns.yaml

@@ -62,9 +62,10 @@ spec:
 # CA, so this bypasses Traefik entirely and the namespace default-deny has
 # to be opened for it — same shape as paperless's allow-ftp-scanner.
 #
-# Scoped to the terminus pods and port 2345 only. Requests still have to
-# carry a known device MAC in the `ID` header plus its api_key; this rule
-# opens the port, not the application.
+# Scoped to the terminus pods, port 2345 and the IoT network (the panel's
+# network; the LB is ETP=Local, so the client address reaches the pod).
+# Requests still have to carry a known device MAC in the `ID` header plus
+# its api_key; this rule opens the port, not the application.
 apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
@@ -75,8 +76,13 @@ spec:
     matchLabels:
       app.kubernetes.io/name: terminus
   ingress:
+    - fromCIDRSet:
+        - cidrGroupRef: net-iot
+      toPorts:
+        - ports:
+            - port: "2345"
+              protocol: TCP
     - fromEntities:
-        - world
         - host
         - remote-node
       toPorts:

opentofu/unifi_nat_hairpin.tf

@@ -68,13 +68,14 @@ locals {
   # idx is a static per-network slot for rule_index derivation — never
   # reuse a freed idx for a new network.
   #
-  # Deliberately absent: (40) Server idx=4, (42) Ingress idx=5, and
-  # (49) k8s Ceph idx=6. The cluster nodes have interfaces on those VLANs,
-  # so a DNATed flow's reply would go directly over the shared L2 and
-  # bypass the UDM's conntrack (asymmetric, connection drops) — and
-  # clients there are the nodes themselves, whose DNS chain (CoreDNS ->
-  # k8s_gateway) already resolves the public names in-cluster. Their idx
-  # slots stay reserved.
+  # Deliberately absent: (40) Server idx=4, (49) k8s Ceph idx=6,
+  # (46) k8s Node, (47) k8s Ingress and (48) k8s Pod. The cluster nodes
+  # have interfaces on those VLANs (mgmt0, node0, ingress0, pod0), so a
+  # DNATed flow's reply would go directly over the shared L2 and bypass
+  # the UDM's conntrack (asymmetric, connection drops) — and clients there
+  # are the nodes themselves, whose DNS chain (CoreDNS -> k8s_gateway)
+  # already resolves the public names in-cluster. idx=5 stays reserved
+  # (its network, (42) Ingress, no longer exists).
   hairpin_networks = {
     "Default"              = { id = "5d4fba77ce63ee614841d53d", idx = 0 }
     "(10) Management"      = { id = "600334abf9ee0c059da6be8f", idx = 1 }