mesh-controller/internal/identity/authority_test.go

//go:build integration

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)
	}
}

// Asking twice gives the same certificate, to the byte.
//
// Every signing carries a fresh random serial, so a mesh that signed per composition composed a
// different declaration each time it was asked what a machine should be — and every machine
// carrying a certificate stood eternally "waiting", pushed seconds ago and already behind. Found
// live on a kept mesh: two plans seconds apart, identical but for one serial.
func TestACertificateIsIssuedOnceAndKept(t *testing.T) {
	ident := fresh(t)
	ctx := context.Background()
	public, _ := aServingKey(t)

	if _, err := ident.RecordNodeKey(ctx, "1b7e0000-0000-4000-8000-000000000001", make(ed25519.PublicKey, ed25519.PublicKeySize)); err != nil {
		t.Fatal(err)
	}
	if err := ident.RecordServingKey(ctx, "1b7e0000-0000-4000-8000-000000000001", public); err != nil {
		t.Fatal(err)
	}

	first, err := ident.Certify(ctx, "a", "a.internal", public)
	if err != nil {
		t.Fatal(err)
	}
	second, err := ident.Certify(ctx, "a", "a.internal", public)
	if err != nil {
		t.Fatal(err)
	}
	if first != second {
		t.Fatal("two askings gave two certificates; every composition then differs by a serial " +
			"and a machine carrying one is eternally behind")
	}

	// And a new key is a new world: the kept answer must not outlive what it certifies.
	fresh2, _ := aServingKey(t)
	if err := ident.RecordServingKey(ctx, "1b7e0000-0000-4000-8000-000000000001", fresh2); err != nil {
		t.Fatal(err)
	}
	third, err := ident.Certify(ctx, "a", "a.internal", fresh2)
	if err != nil {
		t.Fatal(err)
	}
	if third == first {
		t.Fatal("the node rejoined with a new key and was handed the certificate of its old one")
	}
}