Files
mesh-controller/internal/identity/authority_test.go
T
jschoubben 646609c1b2 The mesh certifies names inside it
08-connectivity keeps two authorities apart on purpose: a public one for
names the outside world reaches, and the mesh's own for names only the
mesh knows. Nothing implemented the second, so anything between machines
was plaintext or trust-on-first-use — which the design refuses everywhere
else.

A node now generates a fourth key at enrolment and reports the public
half. A fourth, because a key used for two purposes is one rotation away
from breaking the other: the identity key signs messages to the mesh and
would do for TLS, and reusing it would mean rotating a node's identity
every time its certificate is replaced.

**Nothing secret travels and nothing is sealed.** A certificate authority
says "this name belongs to the holder of this key", so the mesh signs a
public half it cannot use, and the certificate it issues is public. A
module asks for one and is given the certificate and, if it wants,
the mesh's own — the private key is a path to a file the machine already
has, the same arrangement the private network's key uses.

Asserted by verifying rather than inspecting, because a certificate that
parses and does not chain fails at the moment something connects:

- what the mesh issues verifies against the mesh, for the name asked for
- the name is in the subject alternative names, since a certificate
  carrying it only in the common name is refused by every modern client
- it certifies the key the node generated and no other
- another mesh's certificate does not verify, which is the whole point of
  two authorities being separate
- the authority cannot sign another authority — one that could is one
  that can be delegated without anybody deciding to
- two control planes starting together agree on one authority, or a mesh
  has certificates half its machines refuse

Certificates last ten years, which is a choice: a short life needs
something to renew it, and a renewal that fails silently is a mesh that
stops trusting itself on a date nobody wrote down. What makes one
replaceable is that the mesh reissues on demand, not that it expires.
2026-08-31 00:09:13 +02:00

207 lines
6.1 KiB
Go

package identity
import (
"context"
"crypto/ed25519"
"crypto/rand"
"crypto/x509"
"encoding/base64"
"encoding/pem"
"strings"
"sync"
"testing"
)
// The authority that certifies names inside the mesh.
//
// Asserted by verifying, not by inspecting: a certificate that parses and does not chain is a
// certificate that fails at the moment something connects, which is the worst place to find out.
func aServingKey(t *testing.T) (public string, private ed25519.PrivateKey) {
t.Helper()
pub, priv, err := ed25519.GenerateKey(rand.Reader)
if err != nil {
t.Fatal(err)
}
return base64.StdEncoding.EncodeToString(pub), priv
}
func parsed(t *testing.T, certificate string) *x509.Certificate {
t.Helper()
block, _ := pem.Decode([]byte(certificate))
if block == nil {
t.Fatal("not a certificate")
}
got, err := x509.ParseCertificate(block.Bytes)
if err != nil {
t.Fatal(err)
}
return got
}
func TestACertificateChainsToTheMeshsOwnAuthority(t *testing.T) {
ident := fresh(t)
ctx := context.Background()
public, _ := aServingKey(t)
certificate, err := ident.Certify(ctx, "workstation", "workstation.internal", public)
if err != nil {
t.Fatal(err)
}
authority, err := ident.EstablishAuthority(ctx)
if err != nil {
t.Fatal(err)
}
roots := x509.NewCertPool()
if !roots.AppendCertsFromPEM([]byte(authority.Certificate)) {
t.Fatal("the mesh's authority is not usable as a root")
}
if _, err := parsed(t, certificate).Verify(x509.VerifyOptions{
Roots: roots, DNSName: "workstation.internal",
}); err != nil {
t.Fatalf("what the mesh issued does not verify against the mesh: %v", err)
}
}
func TestTheNameIsWhereEverythingLooksForIt(t *testing.T) {
// A certificate carrying the name only in its common name is one every modern client refuses.
ident := fresh(t)
public, _ := aServingKey(t)
certificate, err := ident.Certify(context.Background(), "a", "a.internal", public)
if err != nil {
t.Fatal(err)
}
got := parsed(t, certificate)
if len(got.DNSNames) != 1 || got.DNSNames[0] != "a.internal" {
t.Fatalf("the name is not in the subject alternative names: %v", got.DNSNames)
}
}
func TestItCertifiesTheKeyTheNodeGeneratedAndNoOther(t *testing.T) {
// A certificate authority's whole job is to say "this name belongs to the holder of this
// key". One that made the key would be saying something about a key it also holds.
ident := fresh(t)
public, private := aServingKey(t)
certificate, err := ident.Certify(context.Background(), "a", "a.internal", public)
if err != nil {
t.Fatal(err)
}
inside, ok := parsed(t, certificate).PublicKey.(ed25519.PublicKey)
if !ok {
t.Fatalf("the certificate carries a %T", parsed(t, certificate).PublicKey)
}
if !inside.Equal(private.Public()) {
t.Fatal("the certificate is for a key the node does not hold")
}
}
func TestAnAuthorityIsEstablishedOnceAndKept(t *testing.T) {
// Two authorities and nothing says which certificate to believe.
ident := fresh(t)
ctx := context.Background()
first, err := ident.EstablishAuthority(ctx)
if err != nil {
t.Fatal(err)
}
second, err := ident.EstablishAuthority(ctx)
if err != nil {
t.Fatal(err)
}
if first.Certificate != second.Certificate {
t.Fatal("asking twice made a second authority")
}
}
func TestSomethingThatIsNotAServingKeyIsRefused(t *testing.T) {
ident := fresh(t)
for _, bad := range []string{"", "not-base64!", base64.StdEncoding.EncodeToString([]byte("short"))} {
if _, err := ident.Certify(context.Background(), "a", "a.internal", bad); err == nil {
t.Fatalf("%q was certified", bad)
}
}
}
func TestTheAuthorityCannotBeUsedToMakeAnotherAuthority(t *testing.T) {
// An authority that could sign another is one that can be delegated without anybody deciding
// to. The path length says it cannot.
ident := fresh(t)
authority, err := ident.EstablishAuthority(context.Background())
if err != nil {
t.Fatal(err)
}
got := parsed(t, authority.Certificate)
if !got.IsCA {
t.Fatal("the authority is not an authority")
}
if got.MaxPathLen != 0 || !got.MaxPathLenZero {
t.Fatalf("the authority may sign another authority: path length %d", got.MaxPathLen)
}
}
func TestACertificateFromAnotherMeshDoesNotVerify(t *testing.T) {
// The whole point of two authorities being separate: one mesh's certificate means nothing to
// another, and the check that says so is the one that must not be skipped.
one, two := fresh(t), fresh(t)
public, _ := aServingKey(t)
certificate, err := one.Certify(context.Background(), "a", "a.internal", public)
if err != nil {
t.Fatal(err)
}
other, err := two.EstablishAuthority(context.Background())
if err != nil {
t.Fatal(err)
}
roots := x509.NewCertPool()
roots.AppendCertsFromPEM([]byte(other.Certificate))
if _, err := parsed(t, certificate).Verify(x509.VerifyOptions{
Roots: roots, DNSName: "a.internal",
}); err == nil {
t.Fatal("another mesh's certificate verified")
} else if !strings.Contains(err.Error(), "authority") && !strings.Contains(err.Error(), "signed") {
t.Fatalf("refused for the wrong reason: %v", err)
}
}
func TestTwoProcessesStartingTogetherAgreeOnOneAuthority(t *testing.T) {
// A restart while another copy is coming up. Both find nothing and both generate; only one
// insert may survive, and the loser must read back the winner rather than return the
// authority it generated and did not store — a mesh with two authorities has certificates
// half its machines refuse.
ident := fresh(t)
var wg sync.WaitGroup
authorities := make([]Authority, 6)
errs := make([]error, 6)
for i := range authorities {
wg.Add(1)
go func(i int) {
defer wg.Done()
authorities[i], errs[i] = ident.EstablishAuthority(context.Background())
}(i)
}
wg.Wait()
for i, err := range errs {
if err != nil {
t.Fatalf("establish %d failed: %v", i, err)
}
}
for i, a := range authorities {
if a.Certificate != authorities[0].Certificate {
t.Errorf("establish %d has a different authority from establish 0", i)
}
}
var count int
if err := ident.store.Pool().QueryRow(t.Context(),
`select count(*) from authority`).Scan(&count); err != nil {
t.Fatal(err)
}
if count != 1 {
t.Errorf("%d authorities exist; exactly one may", count)
}
}