{{- /* NetworkPolicy for freesailarr (Gitea #5). TEN CONTAINERS IN ONE POD, BEHIND A VPN, AND THE POLICY IS SIMPLER THAN THAT SOUNDS - for one reason worth stating first: the containers talk to each other over LOCALHOST. They share a network namespace, so none of that traffic ever reaches a network interface and NO NetworkPolicy has anything to say about it. Prowlarr reaching Radarr, Recyclarr reaching Sonarr, every one of those hops is invisible here. What this policy governs is only what enters or leaves the pod. INBOUND is the eight published web interfaces plus gluetun's health server, and almost all of them are probe ports - the kubelet opens an HTTP connection to each container's own interface - so they are one rule on the probe path. The newznab port of mediathekarr is the exception: nothing probes it, and its only consumer is Prowlarr in this same pod over localhost, so it is restricted by source and that costs nothing. OUTBOUND IS WHERE THIS CHART IS UNLIKE EVERY OTHER ONE HERE, because the pod's network namespace belongs to gluetun. Every connection the *arr containers make goes into the WireGuard tunnel and leaves the pod as UDP to the VPN endpoint - so a NetworkPolicy sees the OUTER packets and almost nothing else. Three rules cover it: DNS, UDP 51820 for the tunnel itself, and 443 for gluetun's own server-list API. Indexer and tracker traffic needs no rule of its own; it is already inside the tunnel. AND THE TUNNEL RULE IS THE ONE THAT CAN BREAK THIS CHART, which is also why it is well covered: gluetun's health server returns 200 only while the tunnel is up, and all three of its probes address it. A blocked UDP 51820 therefore means a pod that never becomes Ready - visibly, in the install-test, which brings up a real tunnel. 51820 is WireGuard's standard port and Mullvad's; Mullvad also offers 53, 123, 500 and 4500 for obfuscation, and a release using one of those needs networkPolicy.egress.extraPorts. Note that extraPorts is TCP only, so an alternative UDP port needs the rule here widened instead - said plainly, because it is a limit of the shared values shape and not an oversight. WHAT THIS OBJECT IS: a ceiling on reachability, not an authentication layer. Only the ports declared below are reachable at all - whatever else the process binds, now or after the next app update, is blocked without anyone having to notice it exists. WHAT IT IS NOT: - EGRESS IS COARSE. A NetworkPolicy matches CIDRs and selectors and NEVER hostnames, so "only to the database host" cannot be expressed at all. This cluster's CNI is Canal (Flannel plus Calico for policy) and has no FQDN rule; Calico's GlobalNetworkSet could express one but would bind this chart to Calico, the same argument that kept implementation-specific objects out of the Gateway-API sweep (#114). Each egress rule therefore permits its PORT to any destination. - NOT A BOUNDARY WHERE THE CNI DOES NOT ENFORCE ONE. An unenforced policy is accepted by the API server and filters nothing, so everything reads as configured while nothing is filtered. - THE REASONING IS IN TEMPLATE COMMENTS, not in "#" comments: those are part of the rendered object, travel into the cluster and appear in every release diff. ci/run-networkpolicy-test.sh fails on a rendered "#". THE PORT NUMBERS BELOW ARE POD PORTS, NEVER NODEPORTS. A NetworkPolicy is evaluated at the pod's network interface, after kube-proxy has already translated a NodePort to the targetPort, so a NodePort number here would match nothing while looking strict - and, being the only rule for that port, would block every inbound connection instead. ci/run-networkpolicy-test.sh asserts every port here against the containerPorts of the pod spec this policy selects. */ -}} {{- if .Values.networkPolicy.enabled }} {{- $np := .Values.networkPolicy }} {{- $ns := .Release.Namespace }} {{- $probeSources := $np.probeSources | default list }} {{- $allowedNs := $np.allowedNamespaces | default list }} {{- $ic := $np.ingressController | default dict }} {{- $routed := or .Values.ingress.enabled .Values.httpRoute.enabled }} {{- /* networkPolicy.ingress - the policy's INBOUND side, and not the same thing as networkPolicy.ingressController (the SOURCE SELECTOR for the ingress controller's pods, a SIBLING of it and no part of it) nor as the top-level .Values.ingress (the Ingress object). All three match a search for "ingress"; one round of this work already mistook the second for an inbound escape hatch on the strength of the substring. */}} {{- $npIngress := $np.ingress | default dict }} {{- /* NULL-SAFE ON PURPOSE (#99): ambientMesh is an OBJECT, so every read goes through a fallback reproducing THIS chart's declared defaults. An operator who deletes the object, or writes only "enabled: true", must land on the defaults and not in a nil dereference - #136 shipped exactly that defect one value away, where the NOTES.txt branch dereferenced .networkPolicy.egress directly. Clearing the probe-source list restores the constant rather than removing the ipBlock, deliberately: the two halves are not separable, and enabled: false is how you open nothing. */}} {{- $ambient := $npIngress.ambientMesh | default dict }} {{- $ambientEnabled := $ambient.enabled }} {{- $ambientPort := $ambient.port | default 15008 }} {{- $ambientProbeSources := $ambient.redirectedProbeSources | default (list "169.254.7.127/32") }} apiVersion: networking.k8s.io/v1 kind: NetworkPolicy metadata: name: {{ .Release.Name }}-{{ .Chart.Name }}-networkpolicy labels: app: {{ .Release.Name }}-{{ .Chart.Name }}-networkpolicy spec: {{- /* Selects the StatefulSet's pods. ci/run-networkpolicy-test.sh fails if this matches no pod spec of the same render - which is the mistake that would otherwise leave a policy in the namespace filtering nothing, and its usual cause is a label renamed in the workload template. */}} podSelector: matchLabels: app: {{ .Release.Name }}-{{ .Chart.Name }}-sfs policyTypes: - Ingress {{- /* Egress is listed, and for this chart it is unusually meaningful: because the pod's network namespace belongs to gluetun, the only things that leave it are the tunnel, DNS and gluetun's control-plane calls. Everything the applications do is encapsulated. So three narrow rules really do describe the pod's whole outbound surface - which is rare here. */}} - Egress ingress: {{- /* THE PROBE PATH, nine ports of it. gluetun's health server (9999) plus the eight web interfaces the kubelet probes directly: qBittorrent (8080), Prowlarr (9696), FlareSolverr (8191), Radarr (7878), Sonarr (8989), Seerr (5055), Bazarr (6767) and Mediathekarr (5007). Every one of them is addressed by at least one httpGet probe, so none of them can be restricted by source without the worker node's IP. Recyclarr is absent from this list on purpose: it declares no port and its probes are exec probes, so there is nothing to allow. */}} - ports: - protocol: TCP port: 9999 - protocol: TCP port: 8080 - protocol: TCP port: 9696 - protocol: TCP port: 8191 - protocol: TCP port: 7878 - protocol: TCP port: 8989 - protocol: TCP port: 5055 - protocol: TCP port: 6767 - protocol: TCP port: 5007 {{- if $ambientEnabled }} {{- /* FIRST HALF OF networkPolicy.ingress.ambientMesh (Gitea #143). 15008/TCP is ztunnel's HBONE tunnel, the port every inbound connection arrives on once the namespace carries istio.io/dataplane-mode - ambient "does not and will never bypass Kubernetes NetworkPolicy enforcement", so without it a pod in the mesh is simply unreachable. It is the one port here that is NOT a containerPort of the selected pod spec: ztunnel terminates it, not the application. ci/run-networkpolicy- test.sh therefore holds a NAMED exception for exactly this number, gated on exactly this value - and assertion 7 of that script proves, on a second render, that 15008 stays the ONLY such port and that it is absent while the value is false. AN ISTIO CONSTANT, NOT A STANDARD: 15008 is not registered with IANA for this, no protocol prescribes it, and Kubernetes knows nothing about it - Istio picked it for HBONE and Istio can change it. Hence a VALUE with a documented default rather than a literal here, so an operator can correct it without a chart release. Read for ztunnel 1.30.6. The exception ci/run-networkpolicy-test.sh grants is pinned to the number THAT TEST names, plus a check that this chart declares the same default - never to whatever the value says, because that would let a mistyped port ride in through a configurable field (design A of #143). NOT MEASURED: that 15008 alone suffices comes from Istio's documentation. Measured on this cluster is only which listeners ztunnel opens. Provable at the first namespace to join the mesh; none has. */}} - protocol: TCP port: {{ int $ambientPort }} {{- end }} {{- if $probeSources }} {{- /* RESTRICTED, because the operator supplied probeSources. The kubelet's probes come from the IP of the WORKER NODE running the pod, so that address has to be in the list or the pod never becomes Ready - and a pod that is never Ready reads as a broken application rather than as a policy. The ingress controller is added to the same rule - this chart renders TWO Ingresses, the main one and qBittorrent's, and both go dark the moment this list is filled without it. */}} from: - namespaceSelector: matchLabels: {{- /* Set by Kubernetes itself on every namespace (>= 1.21), so this needs no labelling work on a namespace this chart does not own. */}} kubernetes.io/metadata.name: {{ $ns }} {{- if and $routed $ic.namespace }} {{- /* ONE from-entry with TWO selectors, which is an AND: pods carrying these labels IN that namespace. Written as two list entries it would be an OR, and would open the port to every pod in kube-system. */}} - namespaceSelector: matchLabels: kubernetes.io/metadata.name: {{ $ic.namespace | quote }} {{- with $ic.podLabels }} podSelector: matchLabels: {{- toYaml . | nindent 14 }} {{- end }} {{- end }} {{- range $allowedNs }} - namespaceSelector: matchLabels: kubernetes.io/metadata.name: {{ . | quote }} {{- end }} {{- range $probeSources }} - ipBlock: cidr: {{ . | quote }} {{- end }} {{- if $ambientEnabled }} {{- /* SECOND HALF OF networkPolicy.ingress.ambientMesh, and the reason it is one value and not two. Inside the mesh the kubelet's probes are redirected and no longer arrive from the worker node's address: they arrive from 169.254.7.127. An operator who only opens 15008 by hand writes a policy that passes review - and the moment probeSources is non-empty every probe is dropped, the pod never becomes Ready, and the symptom reads as a broken application rather than as a policy. That is assertion 4 of ci/run-networkpolicy-test.sh one value further along. A switch whose halves can only be had together cannot be set halfway. Only in this branch, because this is the only branch with a "from" list: with no sources restricted the rule is open and needs no peer. The IPv6 counterpart is deliberately absent - this cluster is SingleStack IPv4, and an ipBlock of the wrong family is accepted and matches nothing. WHERE 169.254.7.127 COMES FROM - vendor magic, not protocol: it is LINK-LOCAL (169.254.0.0/16, RFC 3927), a range reserved for node-local use and never routed; Istio's IPv6 counterpart fd16:9254:7127:1337:ffff:ffff:ffff:ffff carries the SAME DIGITS plus 1337; and KUBERNETES DOES NOT KNOW THE ADDRESS - neither the NetworkPolicy API nor the kubelet - only Istio's data plane rewrites the probe source onto it. Read for ztunnel 1.30.6, and if Istio changes it THE FAILURE IS SILENT: probes dropped, and only where probeSources is non-empty, which is nowhere today. A LIST, not a string, and the one case where that does not contradict "a constant, not a configuration": a DUAL-STACK cluster needs BOTH entries at once. This cluster is SingleStack IPv4, so the IPv6 counterpart is left out - an ipBlock of the wrong family is accepted and matches nothing. Add it ALONGSIDE, never instead. UNPROVEN IN OPERATION: probeSources is empty in every chart here, so no release reaches this branch. CI proves its render, through the overlays in ci/networkpolicy. */}} {{- range $ambientProbeSources }} - ipBlock: cidr: {{ . | quote }} {{- end }} {{- end }} {{- else }} {{- /* NO "from" SELECTOR, WHICH MEANS OPEN - deliberately, and only inside the cluster, because this port carries no NodePort. The alternative was to guess the worker node CIDRs, and a wrong guess blocks every kubelet probe: the pod stays un-Ready, the rollout times out, and the cause looks like the application. An empty "from: []" would be worse than either - it allows everything too, but while reading as a restriction. Narrow it with networkPolicy.probeSources. */}} {{- end }} {{- /* MEDIATHEKARR'S NEWZNAB PORT, and the one inbound port here that can be restricted: no probe addresses it. Its only consumer is Prowlarr, which runs in THIS pod and reaches it over localhost - traffic no NetworkPolicy sees at all - so restricting this rule to the release's own namespace plus allowedNamespaces costs nothing and removes a port from the cluster's reach. */}} - ports: - protocol: TCP port: 5008 from: - namespaceSelector: matchLabels: {{- /* Set by Kubernetes itself on every namespace (>= 1.21), so this needs no labelling work on a namespace this chart does not own. */}} kubernetes.io/metadata.name: {{ $ns }} {{- range $allowedNs }} - namespaceSelector: matchLabels: kubernetes.io/metadata.name: {{ . | quote }} {{- end }} egress: {{- /* DNS, unconditionally. There is no value to switch this off, and that is deliberate: a knob whose only other setting breaks every name lookup in the pod is a trap and not a feature. */}} - ports: - protocol: UDP port: 53 - protocol: TCP port: 53 {{- /* THE WIREGUARD TUNNEL, and the rule this chart cannot live without. Everything the *arr containers do leaves the pod inside this tunnel, so blocking it blocks all of them at once - and gluetun's health server, which all three of its probes address, returns 200 only while the tunnel is up. The pod would never become Ready. 51820 is WireGuard's standard port and Mullvad's. Mullvad also offers 53, 123, 500 and 4500 for obfuscation; a release using one of those must widen THIS rule, because networkPolicy.egress.extraPorts is TCP only. */}} - ports: - protocol: UDP port: 51820 {{- /* Outbound HTTPS, for gluetun's own control-plane traffic: it fetches and caches the provider's server list over the API before the tunnel exists, so this cannot go through the tunnel. Indexer and tracker traffic does NOT need a rule here - it is already inside the tunnel by the time it leaves the pod. */}} - ports: - protocol: TCP port: 443 {{- with $np.egress }} {{- with .extraPorts }} {{- /* Ports only, to any destination - see the header. This is the operator's escape hatch from the egress cap, and the only alternative to switching the whole policy off. */}} - ports: {{- range . }} - protocol: TCP port: {{ int . }} {{- end }} {{- end }} {{- end }} {{- end }}