jschoubben
76fcbda9a7
autocert keeps its account key at one fixed name, `acme_account+key`, in whatever directory it is given, and reuses it for ever. That is right while the authority stays the same and silently wrong the moment it does not. Re-initialising the internal CA makes a new authority with a new root: it has never heard of the account in the cache, rejects every use of it, and autocert has no path back from that. Nothing is re-registered, no order ever reaches the CA, and issuance stops with nothing saying why — until somebody guesses that deleting the cache directory by hand is the answer. Name the directory after the authority instead of sharing one between all of them: a digest of the ACME directory URL and the root this proxy was told to verify it with. A re-initialised CA has a new root, the mesh delivers it as a changed bundle, the proxy restarts on that file and lands in a directory with no account in it, so autocert registers afresh and orders again. The healing is that "is this account still valid" never has to be asked — an account is only ever found where it is still valid, which needs no error codes, no probe at startup and no network call that can itself fail. It closes a latent one of the same shape: pointing ACME_DIRECTORY at production after testing against staging reused the staging account, because the cache had no idea the two were different. Trailing whitespace around the delivered root is not a new authority — the mesh writes that file, and a newline coming or going must not throw away an account. Old directories are left on disk, unused: they hold the only copy of certificates that may still be valid, and this program is not the thing that should decide a certificate is finished with. A proxy already holding certificates orders them once more on the first start after this, because its account moves. Free against the lab's own CA and against staging; one issuance per name against a public authority. novox/hq ADR 0056 Claude-Session: https://claude.ai/code/session_01LrgweAeERJYBg88c5cKDzF
74 lines
3.5 KiB
Go
74 lines
3.5 KiB
Go
package main
|
|
|
|
import (
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// The lab's first root, and the one a re-initialised CA generates in its place.
|
|
const (
|
|
firstRoot = "-----BEGIN CERTIFICATE-----\nMIIBeFIRST\n-----END CERTIFICATE-----\n"
|
|
secondRoot = "-----BEGIN CERTIFICATE-----\nMIIBeSECOND\n-----END CERTIFICATE-----\n"
|
|
)
|
|
|
|
// A re-initialised CA does not need somebody to delete the cache by hand.
|
|
//
|
|
// autocert keeps its account key at one fixed name and reuses it for ever. When an internal CA is
|
|
// re-initialised it has never heard of that account, rejects every use of it, and autocert has no
|
|
// path back: nothing is re-registered, no order reaches the CA, and issuance stops with nothing
|
|
// saying why. Naming the cache after the authority means the account is only ever found where it is
|
|
// still valid — the new root lands in a directory with no account in it, and autocert registers.
|
|
func TestANewCARootMeansANewAccountCache(t *testing.T) {
|
|
const directory = "https://anchor.internal/acme/acme/directory"
|
|
before := forThisAuthority("/var/lib/route-proxy/acme", directory, []byte(firstRoot))
|
|
after := forThisAuthority("/var/lib/route-proxy/acme", directory, []byte(secondRoot))
|
|
if before == after {
|
|
t.Fatalf("a re-initialised CA reuses the account it was rejected for: %s", before)
|
|
}
|
|
}
|
|
|
|
// And the SAME authority keeps the account it registered, restart after restart.
|
|
//
|
|
// This is the whole reason ACME_CACHE is required in the first place: an account and its
|
|
// certificates that did not persist would be re-ordered on every restart, which works silently until
|
|
// a rate limit says it does not. Whitespace around the delivered root is not a new authority — the
|
|
// mesh writes that file, and a trailing newline coming or going must not throw away an account.
|
|
func TestTheSameAuthorityKeepsItsAccount(t *testing.T) {
|
|
const directory = "https://anchor.internal/acme/acme/directory"
|
|
first := forThisAuthority("/var/lib/route-proxy/acme", directory, []byte(firstRoot))
|
|
again := forThisAuthority("/var/lib/route-proxy/acme", directory, []byte("\n"+firstRoot+"\n\n"))
|
|
if first != again {
|
|
t.Errorf("the same authority was given two caches, so every restart orders again:\n%s\n%s",
|
|
first, again)
|
|
}
|
|
}
|
|
|
|
// Staging and production are different authorities, and were sharing one account.
|
|
//
|
|
// The latent fault of the same shape: pointing ACME_DIRECTORY at production after testing against
|
|
// staging reused the staging account, because the cache had no idea they were different.
|
|
func TestStagingAndProductionDoNotShareAnAccount(t *testing.T) {
|
|
staging := forThisAuthority("/acme", stagingDirectory, nil)
|
|
production := forThisAuthority("/acme", "https://acme-v02.api.letsencrypt.org/directory", nil)
|
|
if staging == production {
|
|
t.Errorf("two issuers share one account: %s", staging)
|
|
}
|
|
}
|
|
|
|
// It stays inside the directory the mesh gave it, and is a plain name.
|
|
//
|
|
// The mesh owns ACME_CACHE and mounts it; a name derived from a certificate that escaped it — or
|
|
// that carried a separator out of the PEM — would put an account somewhere nothing persists.
|
|
func TestTheAccountCacheStaysWhereTheMeshPutIt(t *testing.T) {
|
|
const cache = "/var/lib/route-proxy/acme"
|
|
got := forThisAuthority(cache, "https://anchor.internal/acme/acme/directory", []byte(firstRoot))
|
|
if !strings.HasPrefix(got, cache+"/") {
|
|
t.Fatalf("the account cache is not under %s: %s", cache, got)
|
|
}
|
|
name := strings.TrimPrefix(got, cache+"/")
|
|
if name != filepath.Base(got) || strings.ContainsAny(name, "/.") {
|
|
t.Errorf("the account cache is not a plain name: %q", name)
|
|
}
|
|
}
|