R-124 recipe root namespace as PBS spells it; R-118 no root size for an absent drive; R-269 rotated-out token rejected at once; R-317 dnsmasq install probed by its unit (burn-down round 2)

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

internal/localapi/disks.go

@@ -398,9 +398,16 @@ func (s *Server) handleDisks(w http.ResponseWriter, r *http.Request, vmid int) {
 						di.Smart = &sm
 					}
 				}
-				if total, used, okc := statfsCapacity(d.MountPath); okc {
-					di.TotalBytes, di.UsedBytes = total, used
-					di.UsedFraction = float64(used) / float64(total)
+				// R-118: statfs ONLY while the drive's device is present. With the device gone the raw
+				// mountpoint reverts to a bare directory on the ROOT filesystem, and statfs would report
+				// pve-root's size as this drive's (measured: a 4 GB drive advertising 46 GiB). Same trap
+				// observe.go guards on the Observe path. Absent → capacity left zero (unknown), never root's.
+				// Pinned by TestDisks_UnionPath_AbsentDeviceReportsNoRootCapacity.
+				if s.devicePresent(d.MountPath) {
+					if total, used, okc := statfsCapacity(d.MountPath); okc {
+						di.TotalBytes, di.UsedBytes = total, used
+						di.UsedFraction = float64(used) / float64(total)
+					}
 				}
 				out = append(out, di)
 			}

internal/localapi/disks_device_presence_test.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"io"
 	"log/slog"
+	"runtime"
 	"strings"
 	"testing"
 
@@ -184,3 +185,39 @@ func TestDisks_DevicePresence_WireFieldIsFalseOnDeviceLoss(t *testing.T) {
 		t.Fatalf("the drive never reached the wire: %s", body)
 	}
 }
+
+// ── R-118 — an absent drive must not advertise the ROOT filesystem's capacity ───────────────────
+
+// TestDisks_UnionPath_AbsentDeviceReportsNoRootCapacity drives the REAL statfsCapacity (no capacity
+// seam): the registry drive's mount path is a real, bare temp directory — exactly what /mnt/<name>
+// becomes once its device is gone (a plain directory on the host's filesystem). With the device absent
+// the row must carry NO capacity; before R-118 the union path statfs'd that bare directory and reported
+// the host filesystem's size and usage as the drive's (46 GiB at 9.2 % for a 4 GB drive, measured).
+// The present half proves the test is not hollow: the same directory DOES yield capacity when the
+// device is there, so a zero on the absent half is the guard's doing, not a statfs failure.
+//
+// RED-PROOF: drop the `if s.devicePresent(d.MountPath)` guard around statfsCapacity in disks.go → the
+// absent subtest fails with "advertises ... bytes".
+func TestDisks_UnionPath_AbsentDeviceReportsNoRootCapacity(t *testing.T) {
+	if runtime.GOOS != "linux" {
+		t.Skip("statfsCapacity is linux-only; production target is linux")
+	}
+	bare := t.TempDir()
+	known := []storage.KnownTarget{
+		{Name: "cel", Type: hub.StorageTypeUSB, MountPath: bare, DurableID: "uuid:4242", UUID: "4242"},
+	}
+	t.Run("absent", func(t *testing.T) {
+		di := diskByMount(t, presenceServer(t, nil, known, true, false), bare)
+		if di.TotalBytes != 0 || di.UsedBytes != 0 || di.UsedFraction != 0 {
+			t.Errorf("absent drive advertises total=%d used=%d frac=%.3f — that is the filesystem UNDER "+
+				"the bare mountpoint, not the drive (R-118)", di.TotalBytes, di.UsedBytes, di.UsedFraction)
+		}
+	})
+	t.Run("present", func(t *testing.T) {
+		di := diskByMount(t, presenceServer(t, nil, known, true, true), bare)
+		if di.TotalBytes <= 0 {
+			t.Errorf("present drive reports no capacity (total=%d) — the guard over-corrected and the "+
+				"size bar is gone for every healthy registry drive", di.TotalBytes)
+		}
+	})
+}

internal/localapi/tokenstore.go

@@ -154,12 +154,15 @@ func (s *TokenStore) Mint(vmid int) (string, error) {
 // looks it up; the per-candidate comparison is constant-time to avoid a timing oracle on the
 // stored hash. ok is false for an unknown/empty token.
 //
-// Reload-on-miss (B3): the store FILE is shared across processes — the one-shot provisioner
-// (`--selftest=provision`) Mints into it while the long-lived daemon serves Lookup from an index
-// built at open. On a miss, re-read the file ONCE and re-check, so a token minted after this
-// process started authorizes without a daemon restart (the drill's fresh-install 401). The
-// append-only log makes an unchanged file size proof of no new records, so a genuinely unknown
-// token costs at most one stat once the index is current — never a reload loop.
+// Reload-on-change (B3, R-269): the store FILE is shared across processes — the one-shot
+// provisioner (`--selftest=provision`) Mints into it while the long-lived daemon serves Lookup from
+// an index built at open. Every Lookup stats the file first and re-reads it when the append-only
+// log has grown, BEFORE answering — so a token minted elsewhere authorizes without a restart AND a
+// token rotated out elsewhere stops authorizing on its very next presentation. (Before R-269 the
+// re-read ran only on a MISS, so a superseded token was a direct map hit and kept authorizing until
+// some unrelated miss forced the reload.) An unchanged size is proof of no new records, so the
+// steady state costs one stat per call and never a reload loop. Pinned by
+// TestTokenStore_RotatedOutTokenRejectedFirst.
 func (s *TokenStore) Lookup(token string) (int, bool) {
 	if token == "" {
 		return 0, false
@@ -167,23 +170,34 @@ func (s *TokenStore) Lookup(token string) (int, bool) {
 	want := hashToken(token)
 	s.mu.Lock()
 	defer s.mu.Unlock()
-	// Direct map hit is the common path; the constant-time compare guards against a timing
-	// side-channel by re-checking the matched key (map lookup itself is not the secret-bearing
-	// comparison — the hash of a random 256-bit token is not feasibly guessable regardless).
-	if vmid, ok := s.byHash[want]; ok {
-		if subtle.ConstantTimeCompare([]byte(want), []byte(s.byVMID[vmid])) == 1 {
-			return vmid, true
+	st, statErr := os.Stat(s.path)
+	if statErr == nil && st.Size() != s.loadedSize {
+		// The log changed under us (another process minted/rotated): converge first, then answer.
+		s.reloads++
+		if err := s.reloadLocked(); err != nil {
+			return 0, false // unreadable store: fail closed, never crash the auth path
 		}
+		return s.matchLocked(want)
 	}
-	// Miss: skip the re-read when the append-only log has not grown (nothing new to see).
-	// A stat error falls through to the reload, which handles a missing file as empty.
-	if st, err := os.Stat(s.path); err == nil && st.Size() == s.loadedSize {
-		return 0, false
+	if vmid, ok := s.matchLocked(want); ok {
+		return vmid, true
 	}
+	if statErr == nil {
+		return 0, false // file unchanged since the last (re)load: genuinely unknown
+	}
+	// Stat failed (e.g. the file vanished): reload, which treats a missing file as empty.
 	s.reloads++
 	if err := s.reloadLocked(); err != nil {
-		return 0, false // unreadable store: fail closed, never crash the auth path
+		return 0, false
 	}
+	return s.matchLocked(want)
+}
+
+// matchLocked answers from the in-memory index. Direct map hit is the common path; the
+// constant-time compare re-checks the matched key against the guest's CURRENT hash (map lookup
+// itself is not the secret-bearing comparison — the hash of a random 256-bit token is not
+// feasibly guessable regardless). Caller holds the mutex.
+func (s *TokenStore) matchLocked(want string) (int, bool) {
 	if vmid, ok := s.byHash[want]; ok {
 		if subtle.ConstantTimeCompare([]byte(want), []byte(s.byVMID[vmid])) == 1 {
 			return vmid, true

internal/localapi/tokenstore_test.go

@@ -210,6 +210,51 @@ func TestTokenStore_ReloadOnMiss_RemintCoherence(t *testing.T) {
 	}
 }
 
+// R-269: a token rotated out by ANOTHER process must stop authorizing on its very next
+// presentation — with NO intervening lookup of the new token. This is the order the operator hits
+// after rotating a leaked token: the leaked one is presented first. RemintCoherence above looks the
+// NEW token up first, and that miss is what used to evict the old hash, so it passed while the leaked
+// token kept returning HTTP 200 on hardware (2026-08-09) until something unrelated forced a reload.
+//
+// RED-PROOF: restore the reload-on-MISS-only Lookup (answer a map hit before stat-ing the file) and
+// this fails with "rotated-out token still authorizes".
+func TestTokenStore_RotatedOutTokenRejectedFirst(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "tokens.log")
+	daemon, err := OpenTokenStore(path)
+	if err != nil {
+		t.Fatalf("open daemon store: %v", err)
+	}
+	defer daemon.Close()
+	minter, err := OpenTokenStore(path)
+	if err != nil {
+		t.Fatalf("open minter store: %v", err)
+	}
+	defer minter.Close()
+
+	old, err := minter.Mint(130)
+	if err != nil {
+		t.Fatalf("mint old: %v", err)
+	}
+	if vmid, ok := daemon.Lookup(old); !ok || vmid != 130 { // the daemon has learned the old token
+		t.Fatalf("old token before rotation: (%d,%v), want (130,true)", vmid, ok)
+	}
+	fresh, err := minter.Mint(130) // rotation, written by another process
+	if err != nil {
+		t.Fatalf("mint fresh: %v", err)
+	}
+
+	if vmid, ok := daemon.Lookup(old); ok { // the leaked token FIRST
+		t.Fatalf("rotated-out token still authorizes vmid %d on its first presentation after rotation — "+
+			"Mint's 'any previous token for this guest is revoked' is false across processes (R-269)", vmid)
+	}
+	if vmid, ok := daemon.Lookup(fresh); !ok || vmid != 130 {
+		t.Fatalf("fresh token after rotation: (%d,%v), want (130,true)", vmid, ok)
+	}
+	if vmid, ok := daemon.Lookup(old); ok {
+		t.Fatalf("rotated-out token authorizes vmid %d after the fresh one was seen", vmid)
+	}
+}
+
 // §8 edge: the store file deleted between open and a miss — reload treats it as empty; Lookup
 // fails closed, no crash.
 func TestTokenStore_ReloadOnMiss_MissingFile(t *testing.T) {