[bug-n1wxwkrtcnds] Fix pod gateway NUD expiry #7

Merged
dfritz merged 1 commits from ops/bug-n1wxwkrtcnds/pod-link-local into main 2026-08-26 23:55:09 +00:00
4 changed files with 51 additions and 4 deletions
+4 -3
View File
@@ -70,9 +70,10 @@ both the kernel and BGP within one reconcile cycle (sub-second).
NIC ↔ upstream router. No conntrack, no SNAT, no encapsulation. NIC ↔ upstream router. No conntrack, no SNAT, no encapsulation.
For IPv6 the host side of every veth carries the deterministic link-local For IPv6 the host side of every veth carries the deterministic link-local
gateway `fe80::1`, so every pod can use a fixed default route. For IPv4 gateway `fe80::1`, and the isolated pod side carries `fe80::2` for neighbor
the host side answers ARP for `169.254.1.1`, providing the same fixed discovery. Every IPv6 pod can use a fixed default route without depending on
default route in v4. its global `/128` for gateway resolution. For IPv4 the host side answers ARP
for `169.254.1.1`, providing the same fixed default route in v4.
## Requirements ## Requirements
+1 -1
View File
@@ -6,6 +6,7 @@ require (
github.com/containernetworking/cni v1.3.0 github.com/containernetworking/cni v1.3.0
github.com/containernetworking/plugins v1.9.1 github.com/containernetworking/plugins v1.9.1
github.com/vishvananda/netlink v1.3.1 github.com/vishvananda/netlink v1.3.1
golang.org/x/sys v0.40.0
k8s.io/api v0.36.0 k8s.io/api v0.36.0
k8s.io/apimachinery v0.36.0 k8s.io/apimachinery v0.36.0
k8s.io/client-go v0.36.0 k8s.io/client-go v0.36.0
@@ -35,7 +36,6 @@ require (
go.yaml.in/yaml/v3 v3.0.4 // indirect go.yaml.in/yaml/v3 v3.0.4 // indirect
golang.org/x/net v0.49.0 // indirect golang.org/x/net v0.49.0 // indirect
golang.org/x/oauth2 v0.34.0 // indirect golang.org/x/oauth2 v0.34.0 // indirect
golang.org/x/sys v0.40.0 // indirect
golang.org/x/term v0.39.0 // indirect golang.org/x/term v0.39.0 // indirect
golang.org/x/text v0.33.0 // indirect golang.org/x/text v0.33.0 // indirect
golang.org/x/time v0.14.0 // indirect golang.org/x/time v0.14.0 // indirect
+21
View File
@@ -11,6 +11,7 @@ import (
"github.com/containernetworking/plugins/pkg/ns" "github.com/containernetworking/plugins/pkg/ns"
"github.com/vishvananda/netlink" "github.com/vishvananda/netlink"
"golang.org/x/sys/unix"
) )
// SetupRequest is the netlink setup input for one pod. // SetupRequest is the netlink setup input for one pod.
@@ -37,6 +38,11 @@ type SetupRequest struct {
// LL DAD on the host side. // LL DAD on the host side.
var linkLocalGW = net.ParseIP("fe80::1") var linkLocalGW = net.ParseIP("fe80::1")
// linkLocalPod is the deterministic pod-side address used for IPv6 neighbor
// discovery. Without a link-local source, gateway NUD probes use the pod's
// global /128 and the host does not answer them reliably after neighbor expiry.
var linkLocalPod = net.ParseIP("fe80::2")
// v4ProxyGW is the well-known link-local IPv4 used by container CNIs as a // v4ProxyGW is the well-known link-local IPv4 used by container CNIs as a
// next-hop for proxy-arp gateways (cilium, calico, kindnet — all use this). // next-hop for proxy-arp gateways (cilium, calico, kindnet — all use this).
var v4ProxyGW = net.IPv4(169, 254, 1, 1) var v4ProxyGW = net.IPv4(169, 254, 1, 1)
@@ -210,6 +216,14 @@ func configurePodSide(req SetupRequest) error {
} }
if req.IP6 != nil { if req.IP6 != nil {
// Keep automatic address generation disabled, but give every IPv6 pod
// veth a deterministic link-local address. This makes NUD for the
// fe80::1 gateway use an on-link source and prevents the default-route
// neighbor from aging into FAILED. DAD is unnecessary on a veth pair.
if err := netlink.AddrAdd(eth0, podLinkLocalAddr()); err != nil && !errors.Is(err, os.ErrExist) {
return fmt.Errorf("pod link-local add: %w", err)
}
a := &netlink.Addr{IPNet: &net.IPNet{IP: req.IP6, Mask: net.CIDRMask(128, 128)}} a := &netlink.Addr{IPNet: &net.IPNet{IP: req.IP6, Mask: net.CIDRMask(128, 128)}}
if err := netlink.AddrAdd(eth0, a); err != nil && !errors.Is(err, os.ErrExist) { if err := netlink.AddrAdd(eth0, a); err != nil && !errors.Is(err, os.ErrExist) {
return fmt.Errorf("pod ip6 add: %w", err) return fmt.Errorf("pod ip6 add: %w", err)
@@ -295,6 +309,13 @@ func configurePodSide(req SetupRequest) error {
}) })
} }
func podLinkLocalAddr() *netlink.Addr {
return &netlink.Addr{
IPNet: &net.IPNet{IP: linkLocalPod, Mask: net.CIDRMask(64, 128)},
Flags: unix.IFA_F_NODAD,
}
}
func setHostRoute(linkIndex int, ip net.IP, prefix int) error { func setHostRoute(linkIndex int, ip net.IP, prefix int) error {
r := &netlink.Route{ r := &netlink.Route{
LinkIndex: linkIndex, LinkIndex: linkIndex,
+25
View File
@@ -0,0 +1,25 @@
//go:build linux
package agent
import (
"testing"
"golang.org/x/sys/unix"
)
func TestPodLinkLocalAddr(t *testing.T) {
addr := podLinkLocalAddr()
if got, want := addr.IP.String(), "fe80::2"; got != want {
t.Fatalf("pod link-local IP = %s, want %s", got, want)
}
if ones, bits := addr.Mask.Size(); ones != 64 || bits != 128 {
t.Fatalf("pod link-local mask = %d/%d, want 64/128", ones, bits)
}
if addr.Flags&unix.IFA_F_NODAD == 0 {
t.Fatal("pod link-local address must disable DAD")
}
if addr.IP.Equal(linkLocalGW) {
t.Fatal("pod and gateway link-local addresses must differ")
}
}