fleet-agent: on-host TPM-mTLS telemetry client (v1)
Build the on-host agent that pairs with fleet-hostapi and feeds the fleet-manager control plane (TODO #14 "STILL TO BUILD (a)"). Nothing on the workstation talked to the manager before this; Monitor + InfluxDB stayed empty. Scope: telemetry only. The agent reuses the host TPM identity for mTLS (read-only tpmkey.LoadSigner at 0x81000100 + cert from NV 0x01800100; the private key never leaves the TPM), opens the long-lived FleetAgent.Session bidi stream, sends Hello + periodic HealthSnapshot (load/cpu/temp/mem/tmpfs/nvme/auth/selinux/chrony/kiosk, probed read-only from /proc+/sys plus hostapi facts), and LOGS but does not act on the DesiredState/Command it receives. Reconcile actuators (kiosk URL, reboot, drain) are deferred until the telemetry half is bench-verified. - files/agent/: new module (go-tpm + grpc), static CGO_ENABLED=0 like enrol/hostapi. Copies the enrol tpmkey (+ read-only LoadSigner) and the generated fleet.agent.v1 proto so it stays self-contained without importing the initramfs enrol module. - files/agent/simtest/: proves the TPM-signed cert completes a real mTLS client-auth handshake (RequireAndVerifyClientCert) against the go-tpm software simulator. - files/etc/fleet-agent/agent.env: fleet-generic config (manager DNS name, fleet CA reused from radius-ca.pem, TPM handle/nvindex, interval). No per-host state. - fleet-agent.service: hardened unit (tss group for /dev/tpmrm0, INET egress). - CI builds fleet-agent out-of-VM + runs vet/test + the simulator handshake test. - Packer: enable_agent flag (default on) + 2b-agent provisioner + fapolicyd trust. Post-switch-root only, so no dracut/initramfs changes. - docs: TODO #14 + fleet-management-design as-built updated. Requires the host already enrolled (broker approve births the inventory row) — else the manager returns PermissionDenied, the correct "not enrolled yet" signal.
This commit is contained in:
Audiobuzz
@@ -0,0 +1,21 @@
|
||||
// fleet-agent-simtest — a SEPARATE module so the go-tpm software simulator (CGO +
|
||||
// the MS TPM reference C) and go-tpm-tools stay OUT of the shipped fleet-agent
|
||||
// module. Run from this dir:
|
||||
// go test ./... (needs CGO + a C toolchain for the simulator)
|
||||
// It proves the agent's reused TPM identity (tpmkey.LoadSigner) completes a real
|
||||
// mTLS client-auth handshake against a server that RequireAndVerifyClientCert —
|
||||
// exactly what the fleet-manager agent plane does — so the go-tpm signer is proven
|
||||
// in the TLS path off-hardware without bloating the image build.
|
||||
module fleet-agent-simtest
|
||||
|
||||
go 1.26
|
||||
|
||||
require (
|
||||
fleet-agent v0.0.0
|
||||
github.com/google/go-tpm v0.9.8
|
||||
github.com/google/go-tpm-tools v0.4.9
|
||||
)
|
||||
|
||||
require golang.org/x/sys v0.43.0 // indirect
|
||||
|
||||
replace fleet-agent => ../
|
||||
@@ -0,0 +1,26 @@
|
||||
github.com/GoogleCloudPlatform/confidential-space/server v0.0.0-20260522213940-e5c6d01a3007 h1:DoeEFwEGBdqcawmpiWtSsSVVZ+wk3zpqvcvssO2JLmY=
|
||||
github.com/GoogleCloudPlatform/confidential-space/server v0.0.0-20260522213940-e5c6d01a3007/go.mod h1:s8F0JYEods/WL03WxZaGsWCnumZeeLD+WKHzspOV9u0=
|
||||
github.com/google/go-configfs-tsm v0.3.3-0.20240919001351-b4b5b84fdcbc h1:SG12DWUUM5igxm+//YX5Yq4vhdoRnOG9HkCodkOn+YU=
|
||||
github.com/google/go-configfs-tsm v0.3.3-0.20240919001351-b4b5b84fdcbc/go.mod h1:EL1GTDFMb5PZQWDviGfZV9n87WeGTR/JUg13RfwkgRo=
|
||||
github.com/google/go-eventlog v0.0.3-0.20260416001248-6807b85eecf0 h1:STyioPkz8nqMMIk3+YlyJ/WyEJZxho1YUZXu99uAbQ0=
|
||||
github.com/google/go-eventlog v0.0.3-0.20260416001248-6807b85eecf0/go.mod h1:7huE5P8w2NTObSwSJjboHmB7ioBNblkijdzoVa2skfQ=
|
||||
github.com/google/go-sev-guest v0.14.0 h1:dCb4F3YrHTtrDX3cYIPTifEDz7XagZmXQioxRBW4wOo=
|
||||
github.com/google/go-sev-guest v0.14.0/go.mod h1:SK9vW+uyfuzYdVN0m8BShL3OQCtXZe/JPF7ZkpD3760=
|
||||
github.com/google/go-tdx-guest v0.3.2-0.20250814004405-ffb0869e6f4d h1:Ff8goEP/ue2/rZT5qyoRicuySCYDbAXEZS8Cf1fgsUo=
|
||||
github.com/google/go-tdx-guest v0.3.2-0.20250814004405-ffb0869e6f4d/go.mod h1:uHy3VaNXNXhl0fiPxKqTxieeouqQmW6A0EfLcaeCYBk=
|
||||
github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo=
|
||||
github.com/google/go-tpm v0.9.8/go.mod h1:h9jEsEECg7gtLis0upRBQU+GhYVH6jMjrFxI8u6bVUY=
|
||||
github.com/google/go-tpm-tools v0.4.9 h1:jZEhnE4WRFbomSssBH2gWaIViIHU1gjH1jz76+xC9bI=
|
||||
github.com/google/go-tpm-tools v0.4.9/go.mod h1:Omb8zosA8qY9URn1gsrO2i4b6DFqGp29BqNx18V66c4=
|
||||
github.com/google/logger v1.1.1 h1:+6Z2geNxc9G+4D4oDO9njjjn2d0wN5d7uOo0vOIW1NQ=
|
||||
github.com/google/logger v1.1.1/go.mod h1:BkeJZ+1FhQ+/d087r4dzojEg1u2ZX+ZqG1jTUrLM+zQ=
|
||||
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
|
||||
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
|
||||
go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
|
||||
go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
|
||||
golang.org/x/crypto v0.45.0 h1:jMBrvKuj23MTlT0bQEOBcAE0mjg8mK9RXFhRH6nyF3Q=
|
||||
golang.org/x/crypto v0.45.0/go.mod h1:XTGrrkGJve7CYK7J8PEww4aY7gM3qMCElcJQ8n8JdX4=
|
||||
golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
|
||||
golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
|
||||
google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
|
||||
google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
|
||||
@@ -0,0 +1,207 @@
|
||||
// Package simtest validates the agent's reused-TPM mTLS identity against the
|
||||
// go-tpm software simulator (the MS TPM 2.0 reference). It lives in its own module
|
||||
// so the CGO simulator never enters the shipped fleet-agent build; see go.mod.
|
||||
//
|
||||
// The crux it proves: crypto/tls can drive tpmkey's go-tpm crypto.Signer to sign
|
||||
// the TLS CertificateVerify, so a host holding ONLY a TPM key (no exportable
|
||||
// private key) authenticates to a server doing RequireAndVerifyClientCert against
|
||||
// the fleet CA — the exact posture of the fleet-manager agent plane (agent.go).
|
||||
package simtest
|
||||
|
||||
import (
|
||||
"crypto"
|
||||
"crypto/ecdsa"
|
||||
"crypto/elliptic"
|
||||
"crypto/rand"
|
||||
"crypto/tls"
|
||||
"crypto/x509"
|
||||
"crypto/x509/pkix"
|
||||
"math/big"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"fleet-agent/tpmkey"
|
||||
|
||||
"github.com/google/go-tpm-tools/simulator"
|
||||
"github.com/google/go-tpm/tpm2"
|
||||
"github.com/google/go-tpm/tpm2/transport"
|
||||
)
|
||||
|
||||
func openSim(t *testing.T) transport.TPM {
|
||||
t.Helper()
|
||||
sim, err := simulator.Get()
|
||||
if err != nil {
|
||||
t.Fatalf("simulator: %v", err)
|
||||
}
|
||||
t.Cleanup(func() { sim.Close() })
|
||||
return transport.FromReadWriter(sim)
|
||||
}
|
||||
|
||||
// testCA is a throwaway fleet CA for the handshake.
|
||||
type testCA struct {
|
||||
cert *x509.Certificate
|
||||
key *ecdsa.PrivateKey
|
||||
pool *x509.CertPool
|
||||
}
|
||||
|
||||
func newTestCA(t *testing.T) *testCA {
|
||||
t.Helper()
|
||||
key, err := ecdsa.GenerateKey(elliptic.P256(), rand.Reader)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
tmpl := &x509.Certificate{
|
||||
SerialNumber: big.NewInt(1),
|
||||
Subject: pkix.Name{CommonName: "test fleet CA"},
|
||||
NotBefore: time.Now().Add(-time.Hour),
|
||||
NotAfter: time.Now().Add(time.Hour),
|
||||
IsCA: true,
|
||||
KeyUsage: x509.KeyUsageCertSign,
|
||||
BasicConstraintsValid: true,
|
||||
}
|
||||
der, err := x509.CreateCertificate(rand.Reader, tmpl, tmpl, key.Public(), key)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
cert, _ := x509.ParseCertificate(der)
|
||||
pool := x509.NewCertPool()
|
||||
pool.AddCert(cert)
|
||||
return &testCA{cert: cert, key: key, pool: pool}
|
||||
}
|
||||
|
||||
// issue signs a leaf cert for pub with the CA (as the enrol-broker/step-ca does).
|
||||
func (ca *testCA) issue(t *testing.T, tmpl *x509.Certificate, pub crypto.PublicKey) []byte {
|
||||
t.Helper()
|
||||
der, err := x509.CreateCertificate(rand.Reader, tmpl, ca.cert, pub, ca.key)
|
||||
if err != nil {
|
||||
t.Fatalf("CA issue: %v", err)
|
||||
}
|
||||
return der
|
||||
}
|
||||
|
||||
func TestTPMClientCertHandshake(t *testing.T) {
|
||||
tpm := openSim(t)
|
||||
const (
|
||||
keyHandle = tpm2.TPMHandle(0x81000100)
|
||||
nvIndex = tpm2.TPMHandle(0x01800100)
|
||||
)
|
||||
|
||||
// Enrolment side: create the persistent signing key (once).
|
||||
if _, _, err := tpmkey.EnsureKey(tpm, keyHandle); err != nil {
|
||||
t.Fatalf("EnsureKey: %v", err)
|
||||
}
|
||||
// Agent side: load it read-only (the function the agent actually uses).
|
||||
signer, err := tpmkey.LoadSigner(tpm, keyHandle)
|
||||
if err != nil {
|
||||
t.Fatalf("LoadSigner: %v", err)
|
||||
}
|
||||
|
||||
ca := newTestCA(t)
|
||||
|
||||
// The host's identity cert (CA-signed over the TPM public key). Its SERIAL is
|
||||
// the value the manager derives as the inventory key.
|
||||
wantSerial := big.NewInt(0xC0FFEE)
|
||||
leafDER := ca.issue(t, &x509.Certificate{
|
||||
SerialNumber: wantSerial,
|
||||
Subject: pkix.Name{CommonName: "fleet-host"},
|
||||
NotBefore: time.Now().Add(-time.Hour),
|
||||
NotAfter: time.Now().Add(time.Hour),
|
||||
KeyUsage: x509.KeyUsageDigitalSignature,
|
||||
ExtKeyUsage: []x509.ExtKeyUsage{x509.ExtKeyUsageClientAuth},
|
||||
}, signer.Public())
|
||||
|
||||
// Exercise the NV round-trip the agent's identity path uses.
|
||||
if err := tpmkey.WriteNVCert(tpm, nvIndex, leafDER); err != nil {
|
||||
t.Fatalf("WriteNVCert: %v", err)
|
||||
}
|
||||
got, err := tpmkey.ReadNVCert(tpm, nvIndex)
|
||||
if err != nil {
|
||||
t.Fatalf("ReadNVCert: %v", err)
|
||||
}
|
||||
if string(got) != string(leafDER) {
|
||||
t.Fatalf("NV cert round-trip mismatch")
|
||||
}
|
||||
leaf, _ := x509.ParseCertificate(leafDER)
|
||||
|
||||
// TPM-backed client cert (private key = the TPM signer; never exported).
|
||||
clientCert := tls.Certificate{Certificate: [][]byte{leafDER}, PrivateKey: signer, Leaf: leaf}
|
||||
|
||||
// Server standing in for the manager agent plane: verify the client to the CA.
|
||||
serverKey, _ := ecdsa.GenerateKey(elliptic.P256(), rand.Reader)
|
||||
serverDER := ca.issue(t, &x509.Certificate{
|
||||
SerialNumber: big.NewInt(2),
|
||||
Subject: pkix.Name{CommonName: "fleet-manager"},
|
||||
DNSNames: []string{"fleet-manager"},
|
||||
NotBefore: time.Now().Add(-time.Hour),
|
||||
NotAfter: time.Now().Add(time.Hour),
|
||||
KeyUsage: x509.KeyUsageDigitalSignature,
|
||||
ExtKeyUsage: []x509.ExtKeyUsage{x509.ExtKeyUsageServerAuth},
|
||||
}, serverKey.Public())
|
||||
serverCfg := &tls.Config{
|
||||
Certificates: []tls.Certificate{{Certificate: [][]byte{serverDER}, PrivateKey: serverKey}},
|
||||
ClientAuth: tls.RequireAndVerifyClientCert,
|
||||
ClientCAs: ca.pool,
|
||||
MinVersion: tls.VersionTLS12,
|
||||
}
|
||||
clientCfg := &tls.Config{
|
||||
Certificates: []tls.Certificate{clientCert},
|
||||
RootCAs: ca.pool,
|
||||
ServerName: "fleet-manager",
|
||||
MinVersion: tls.VersionTLS12,
|
||||
}
|
||||
|
||||
ln, err := tls.Listen("tcp", "127.0.0.1:0", serverCfg)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer ln.Close()
|
||||
|
||||
serialCh := make(chan *big.Int, 1)
|
||||
errCh := make(chan error, 1)
|
||||
go func() {
|
||||
conn, err := ln.Accept()
|
||||
if err != nil {
|
||||
errCh <- err
|
||||
return
|
||||
}
|
||||
defer conn.Close()
|
||||
tc := conn.(*tls.Conn)
|
||||
tc.SetDeadline(time.Now().Add(5 * time.Second))
|
||||
if err := tc.Handshake(); err != nil {
|
||||
errCh <- err
|
||||
return
|
||||
}
|
||||
st := tc.ConnectionState()
|
||||
if len(st.PeerCertificates) == 0 {
|
||||
errCh <- err
|
||||
return
|
||||
}
|
||||
serialCh <- st.PeerCertificates[0].SerialNumber
|
||||
}()
|
||||
|
||||
conn, err := tls.Dial("tcp", ln.Addr().String(), clientCfg)
|
||||
if err != nil {
|
||||
t.Fatalf("client handshake with TPM cert failed: %v", err)
|
||||
}
|
||||
defer conn.Close()
|
||||
|
||||
select {
|
||||
case err := <-errCh:
|
||||
t.Fatalf("server rejected TPM client cert: %v", err)
|
||||
case serial := <-serialCh:
|
||||
if serial.Cmp(wantSerial) != 0 {
|
||||
t.Fatalf("server saw serial %x, want %x", serial, wantSerial)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("handshake timed out")
|
||||
}
|
||||
}
|
||||
|
||||
// TestLoadSignerRejectsEmptyHandle proves the agent fails clearly on a host that
|
||||
// isn't enrolled (no key at the handle) rather than creating one.
|
||||
func TestLoadSignerRejectsEmptyHandle(t *testing.T) {
|
||||
tpm := openSim(t)
|
||||
if _, err := tpmkey.LoadSigner(tpm, tpm2.TPMHandle(0x81000100)); err == nil {
|
||||
t.Fatal("LoadSigner on an empty handle should error (agent must not create a key)")
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user