daemon: Add option --bpf-lb-external-clusterip

Documentation/gettingstarted/kubeproxy-free.rst

@@ -1183,6 +1183,13 @@ working, take a look at `this KEP
     free mode, make sure that default Kubernetes services like ``kube-dns`` and ``kubernetes``
     have the required label value.
 
+External Access To ClusterIP Services
+*************************************
+
+As per `k8s Service <https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types>`__,
+Cilium's eBPF kube-proxy replacement by default disallows access to a ClusterIP service from outside the cluster.
+This can be allowed by setting ``bpf.lbExternalClusterIP=true``.
+
 Limitations
 ###########
 
@@ -1213,9 +1220,6 @@ Limitations
       release introduces ``EndpointSliceMirroring`` controller that mirrors custom ``Endpoints``
       resources to corresponding ``EndpointSlices`` and thus allowing backing ``Endpoints``
       to work. For a more detailed discussion see :gh-issue:`12438`.
-    * As per `k8s Service <https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types>`__,
-      Cilium's eBPF kube-proxy replacement disallow access of a ClusterIP service
-      from outside a cluster.
 
 Further Readings
 ################

bpf/lib/lb.h

@@ -325,29 +325,9 @@ bool lb6_svc_is_affinity(const struct lb6_service *svc)
 	return svc->flags & SVC_FLAG_AFFINITY;
 }
 
-static __always_inline
-__u8 svc_is_routable_mask(void)
-{
-	__u8 mask = SVC_FLAG_ROUTABLE;
-
-#ifdef ENABLE_LOADBALANCER
-	mask |= SVC_FLAG_LOADBALANCER;
-#endif
-#ifdef ENABLE_NODEPORT
-	mask |= SVC_FLAG_NODEPORT;
-#endif
-#ifdef ENABLE_EXTERNAL_IP
-	mask |= SVC_FLAG_EXTERNAL_IP;
-#endif
-#ifdef ENABLE_HOSTPORT
-	mask |= SVC_FLAG_HOSTPORT;
-#endif
-	return mask;
-}
-
 static __always_inline bool __lb_svc_is_routable(__u8 flags)
 {
-	return (flags & svc_is_routable_mask()) > SVC_FLAG_ROUTABLE;
+	return (flags & SVC_FLAG_ROUTABLE) != 0;
 }
 
 static __always_inline

daemon/cmd/daemon_main.go

@@ -985,6 +985,9 @@ func init() {
 	flags.String(option.BGPConfigPath, "/var/lib/cilium/bgp/config.yaml", "Path to file containing the BGP configuration")
 	option.BindEnv(option.BGPConfigPath)
 
+	flags.Bool(option.ExternalClusterIPName, false, "Enable external access to ClusterIP services (default false)")
+	option.BindEnv(option.ExternalClusterIPName)
+
 	viper.BindPFlags(flags)
 }
 

install/kubernetes/cilium/README.md

@@ -63,6 +63,7 @@ contributors across the globe, there is almost always someone available to help.
 | bgp.announce.loadbalancerIP | bool | `false` | Enable allocation and announcement of service LoadBalancer IPs |
 | bgp.enabled | bool | `false` | Enable BGP support inside Cilium; embeds a new ConfigMap for BGP inside cilium-agent and cilium-operator |
 | bpf.clockProbe | bool | `false` |  |
+| bpf.lbExternalClusterIP | bool | `false` | Allow cluster external access to ClusterIP services. |
 | bpf.lbMapMax | int | `65536` | Configure the maximum number of entries in the TCP connection tracking table. ctTcpMax: '524288' -- Configure the maximum number of entries for the non-TCP connection tracking table. ctAnyMax: '262144' -- Configure the maximum number of service entries in the load balancer maps. |
 | bpf.monitorAggregation | string | `"medium"` | Configure auto-sizing for all BPF maps based on available memory. ref: https://docs.cilium.io/en/v1.9/concepts/ebpf/maps/#ebpf-maps -- Configure the level of aggregation for monitor notifications. Valid options are none, low, medium, maximum |
 | bpf.monitorFlags | string | `"all"` | Configure which TCP flags trigger notifications when seen for the first time in a connection. |

install/kubernetes/cilium/templates/cilium-configmap.yaml

@@ -289,6 +289,10 @@ data:
 {{- if hasKey .Values.bpf "lbBypassFIBLookup" }}
   bpf-lb-bypass-fib-lookup: {{ .Values.bpf.lbBypassFIBLookup | quote }}
 {{- end }}
+{{- if hasKey .Values.bpf "lbExternalClusterIP" }}
+  bpf-lb-external-clusterip: {{ .Values.bpf.lbExternalClusterIP | quote }}
+{{- end }}
+
   # Pre-allocation of map entries allows per-packet latency to be reduced, at
   # the expense of up-front memory allocation for the entries in the maps. The
   # default value below will minimize memory usage in the default installation;

install/kubernetes/cilium/values.yaml

@@ -274,6 +274,9 @@ bpf:
   # first time in a connection.
   monitorFlags: "all"
 
+  # -- Allow cluster external access to ClusterIP services.
+  lbExternalClusterIP: false
+
   # -- Enable native IP masquerade support in eBPF
   #masquerade: true
 

pkg/defaults/defaults.go

@@ -433,4 +433,8 @@ const (
 
 	// WireguardSubnetV6 is a default wireguard tunnel subnet
 	WireguardSubnetV6 = "fdc9:281f:04d7:9ee9::1/64"
+
+	// ExternalClusterIP enables cluster external access to ClusterIP services.
+	// Defaults to false to retain prior behaviour of not routing external packets to ClusterIPs.
+	ExternalClusterIP = false
 )

pkg/maps/lbmap/lbmap.go

@@ -504,6 +504,10 @@ func updateMasterService(fe ServiceKey, nbackends int, revNATID int, svcType loa
 	svcLocal bool, sessionAffinity bool, sessionAffinityTimeoutSec uint32,
 	checkSourceRange bool) error {
 
+	// isRoutable denotes whether this service can be accessed from outside the cluster.
+	isRoutable := !fe.IsSurrogate() &&
+		(svcType != loadbalancer.SVCTypeClusterIP || option.Config.ExternalClusterIP)
+
 	fe.SetBackendSlot(0)
 	zeroValue := fe.NewValue().(ServiceValue)
 	zeroValue.SetCount(nbackends)
@@ -512,7 +516,7 @@ func updateMasterService(fe ServiceKey, nbackends int, revNATID int, svcType loa
 		SvcType:          svcType,
 		SvcLocal:         svcLocal,
 		SessionAffinity:  sessionAffinity,
-		IsRoutable:       !fe.IsSurrogate(),
+		IsRoutable:       isRoutable,
 		CheckSourceRange: checkSourceRange,
 	})
 	zeroValue.SetFlags(flag.UInt16())

pkg/option/config.go

@@ -952,6 +952,10 @@ const (
 	// BGPConfigPath is the file path to the BGP configuration. It is
 	// compatible with MetalLB's configuration.
 	BGPConfigPath = "bgp-config-path"
+
+	// ExternalClusterIPName is the name of the option to enable
+	// cluster external access to ClusterIP services.
+	ExternalClusterIPName = "bpf-lb-external-clusterip"
 )
 
 // Default string arguments
@@ -1941,6 +1945,10 @@ type DaemonConfig struct {
 	// BGPConfigPath is the file path to the BGP configuration. It is
 	// compatible with MetalLB's configuration.
 	BGPConfigPath string
+
+	// ExternalClusterIP enables routing to ClusterIP services from outside
+	// the cluster. This mirrors the behaviour of kube-proxy.
+	ExternalClusterIP bool
 }
 
 var (
@@ -1985,6 +1993,8 @@ var (
 
 		k8sEnableLeasesFallbackDiscovery: defaults.K8sEnableLeasesFallbackDiscovery,
 		APIRateLimit:                     make(map[string]string),
+
+		ExternalClusterIP: defaults.ExternalClusterIP,
 	}
 )
 
@@ -2492,6 +2502,7 @@ func (c *DaemonConfig) Populate() {
 	c.EnableCustomCalls = viper.GetBool(EnableCustomCallsName)
 	c.BGPAnnounceLBIP = viper.GetBool(BGPAnnounceLBIP)
 	c.BGPConfigPath = viper.GetString(BGPConfigPath)
+	c.ExternalClusterIP = viper.GetBool(ExternalClusterIPName)
 
 	err = c.populateMasqueradingSettings()
 	if err != nil {

test/k8sT/Services.go

@@ -579,6 +579,53 @@ var _ = Describe("K8sServicesTest", func() {
 				testCurlFromPods(echoPodLabel, url, 5, 0)
 			}
 		})
+
+		curlClusterIPFromExternalHost := func() *helpers.CmdRes {
+			clusterIP, _, err := kubectl.GetServiceHostPort(helpers.DefaultNamespace, serviceName)
+			ExpectWithOffset(1, err).Should(BeNil(), "Cannot get service %s", serviceName)
+			ExpectWithOffset(1, govalidator.IsIP(clusterIP)).Should(BeTrue(), "ClusterIP is not an IP")
+			httpSVCURL := fmt.Sprintf("http://%s/", net.JoinHostPort(clusterIP, "80"))
+
+			By("testing external connectivity via cluster IP %s", clusterIP)
+
+			status := kubectl.ExecInHostNetNS(context.TODO(), k8s1NodeName, helpers.CurlFail(httpSVCURL))
+			ExpectWithOffset(1, status).Should(helpers.CMDSuccess(), "cannot curl to service IP from host: %s", status.CombineOutput())
+
+			return kubectl.ExecInHostNetNS(context.TODO(), outsideNodeName, helpers.CurlFail(httpSVCURL))
+		}
+
+		SkipItIf(func() bool { return helpers.DoesNotExistNodeWithoutCilium() },
+			"ClusterIP cannot be accessed externally when access is disabled",
+			func() {
+				Expect(curlClusterIPFromExternalHost()).ShouldNot(helpers.CMDSuccess(),
+					"External host %s unexpectedly connected to ClusterIP when lbExternalClusterIP was unset", outsideNodeName)
+			})
+
+		SkipContextIf(func() bool { return helpers.DoesNotExistNodeWithoutCilium() }, "With ClusterIP external access", func() {
+			var (
+				svcIP string
+			)
+			BeforeAll(func() {
+				DeployCiliumOptionsAndDNS(kubectl, ciliumFilename, map[string]string{
+					"bpf.lbExternalClusterIP": "true",
+				})
+				clusterIP, _, err := kubectl.GetServiceHostPort(helpers.DefaultNamespace, serviceName)
+				svcIP = clusterIP
+				Expect(err).Should(BeNil(), "Cannot get service %s", serviceName)
+				res := kubectl.AddIPRoute(outsideNodeName, svcIP, k8s1IP, false)
+				Expect(res).Should(helpers.CMDSuccess(), "Error adding IP route for %s via %s", svcIP, k8s1IP)
+			})
+
+			AfterAll(func() {
+				res := kubectl.DelIPRoute(outsideNodeName, svcIP, k8s1IP)
+				Expect(res).Should(helpers.CMDSuccess(), "Error removing IP route for %s via %s", svcIP, k8s1IP)
+				DeployCiliumAndDNS(kubectl, ciliumFilename)
+			})
+
+			It("ClusterIP can be accessed when external access is enabled", func() {
+				Expect(curlClusterIPFromExternalHost()).Should(helpers.CMDSuccess(), "Could not curl ClusterIP %s from external host", svcIP)
+			})
+		})
 	})
 
 	SkipContextIf(func() bool { return !helpers.RunsOnNetNextOr419Kernel() }, "Checks local redirect policy", func() {