R-1124 + R-1012: forget a decommissioned drive that is gone; name an orphan thin device in a backup failure

R-1124: ForgetRetiredDrives (start-up + the 20 s tick) disables and removes the host mount unit of a DECOMMISSIONED drive whose disk is absent and unmounted; the agent then no longer lists it. A present decommissioned drive keeps its unit (one-click re-enroll). The file goes only through the new felhom-priv-apply verb `unit-forget`, which re-checks marker, disabled, unmounted and absent as root. R-1012: the read-only root helper felhom-thin-check <vg> <pool> (bundle) lists the pool's thin ids (metadata snapshot reserved and released) next to LVM's before and after. BackupRunner.SetThinCheck runs it before a snapshot-mode backup (log) and again after a failure, appending the finding in plain words to the error the controller mails to the operator. Two reads, intersected; fails open; never removes. Red-proofs: felhom.eu audits/agent-allowlist-rotation-2026-10-17/P1/. Code only; the CHANGELOG entry follows the release. Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
2026-10-17 15:20:34 +02:00
1 parent 344c4f9030
commit e15d1d30ea
@@ -0,0 +1,85 @@
+package storage
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+// ForgetRetiredDrives (R-1124) removes the host mount unit of every DECOMMISSIONED drive that is physically gone, so a
+// later host boot no longer waits for it and the agent stops listing it (RegistryKnownTargets and
+// ReassertEnrolledMounts both enumerate the units — no unit, no entry, no „absent by UUID" line every 20 s).
+//
+// Only a drive that is BOTH decommissioned (the operator's or the customer's permanent removal) AND absent (its
+// /dev/disk/by-uuid link does not resolve) AND not mounted is forgotten. A decommissioned drive that is still plugged in
+// keeps its unit and its raw host mount — that is what makes the one-click re-enroll (H3) work, and decommission stays a
+// logical retire (`03` §storage). The intent record stays `decommissioned`: a forgotten drive that comes back is a new
+// candidate, never auto-mounted. The root half (`felhom-priv-apply unit-forget`) re-checks every one of these conditions
+// and refuses otherwise. Called at agent start, on the 20-second storage tick, and right after a decommission. Best
+// effort per unit; returns how many units it removed. Pinned by TestForgetRetiredDrives_*.
+func (h *SudoHostOps) ForgetRetiredDrives(ctx context.Context, intent IntentReader) int {
+	if intent == nil {
+		return 0 // no intent store → we cannot know a drive was retired; forget nothing
+	}
+	entries, err := os.ReadDir(h.unitDir)
+	if err != nil {
+		h.logger.Warn("storage: forget retired drives — cannot read unit dir", "dir", h.unitDir, "err", err)
+		return 0
+	}
+	mounted := map[string]bool{}
+	if ms, merr := h.host.Mounts(); merr == nil {
+		for _, m := range ms {
+			mounted[m.MountPoint] = true
+		}
+	} else {
+		h.logger.Warn("storage: forget retired drives — mount table unreadable; forgetting nothing", "err", merr)
+		return 0
+	}
+	removed := 0
+	for _, e := range entries {
+		name := e.Name()
+		if !strings.HasSuffix(name, ".mount") {
+			continue
+		}
+		data, rerr := os.ReadFile(filepath.Join(h.unitDir, name))
+		if rerr != nil {
+			continue
+		}
+		spec, ok := parseFelhomMountUnit(string(data))
+		if !ok {
+			continue // not one of our by-UUID drive units (network units are refused by the parser)
+		}
+		durableID := "uuid:" + spec.UUID
+		if intent.Get(durableID) != IntentDecommissioned {
+			continue
+		}
+		if mounted[spec.Where] {
+			h.logger.Debug("storage: decommissioned drive still mounted — keeping its unit", "where", spec.Where)
+			continue
+		}
+		if _, derr := ResolveStorageDevice(durableID); derr == nil {
+			h.logger.Debug("storage: decommissioned drive is present — keeping its unit (re-enroll stays one click)", "where", spec.Where)
+			continue
+		}
+		if h.unitEnabled(name) {
+			if err := h.run(ctx, h.bins.Systemctl, "disable", "--", name); err != nil {
+				h.logger.Warn("storage: forget retired drive — disable failed", "where", spec.Where, "unit", name, "err", err)
+				continue
+			}
+		}
+		if err := h.run(ctx, h.bins.PrivApply, "unit-forget", name); err != nil {
+			h.logger.Warn("storage: forget retired drive — unit removal refused or failed", "where", spec.Where, "unit", name, "err", err)
+			continue
+		}
+		removed++
+		h.logger.Info("storage: forgot a decommissioned drive that is gone — its mount unit is removed",
+			"name", spec.Name, "where", spec.Where, "uuid", spec.UUID, "unit", name)
+	}
+	if removed > 0 {
+		if err := h.run(ctx, h.bins.Systemctl, "daemon-reload"); err != nil {
+			h.logger.Warn("storage: daemon-reload after forgetting retired drives failed", "err", err)
+		}
+	}
+	return removed
+}
@@ -0,0 +1,155 @@
+package storage
+
+import (
+	"context"
+	"io"
+	"os"
+	"path/filepath"
+	"reflect"
+	"testing"
+)
+
+// forgetRunner records every privileged call and plays the root half of `felhom-priv-apply unit-forget`: the unit file
+// disappears from the unit dir, so the CONSEQUENCE (the drive is no longer listed) is observable, not just the calls.
+type forgetRunner struct {
+	unitDir string
+	calls   [][]string
+}
+
+func (r *forgetRunner) RunStdin(ctx context.Context, _ io.Reader, name string, args ...string) ([]byte, []byte, error) {
+	return r.Run(ctx, name, args...)
+}
+
+func (r *forgetRunner) Run(_ context.Context, name string, args ...string) ([]byte, []byte, error) {
+	r.calls = append(r.calls, append([]string{name}, args...))
+	if len(args) == 2 && args[0] == "unit-forget" {
+		_ = os.Remove(filepath.Join(r.unitDir, args[1]))
+	}
+	return nil, nil, nil
+}
+
+type forgetCase struct {
+	intent   DriveIntent
+	present  bool // the by-uuid link resolves
+	mounted  bool
+	enabled  bool // the wants-symlink exists
+	mountErr bool
+}
+
+const forgetUUID = "4ebfd36d-87d3-4b63-839e-a5a710fc799a"
+
+func runForget(t *testing.T, c forgetCase, intent IntentReader) (int, *forgetRunner, *RegistryKnownTargets, string) {
+	t.Helper()
+	unitDir := t.TempDir()
+	unit := "mnt-media_a.mount"
+	writeUnit(t, unitDir, unit, renderMountUnit(MountSpec{Name: forgetUUID, UUID: forgetUUID, Where: "/mnt/media_a", FSType: "ext4"}))
+	if c.enabled {
+		if err := os.MkdirAll(filepath.Join(unitDir, "multi-user.target.wants"), 0o755); err != nil {
+			t.Fatal(err)
+		}
+		if err := os.Symlink(filepath.Join(unitDir, unit), filepath.Join(unitDir, "multi-user.target.wants", unit)); err != nil {
+			t.Fatal(err)
+		}
+	}
+	devRoot := t.TempDir()
+	if err := os.MkdirAll(filepath.Join(devRoot, "by-uuid"), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if c.present {
+		dev := filepath.Join(devRoot, "sdz1")
+		if err := os.WriteFile(dev, nil, 0o600); err != nil {
+			t.Fatal(err)
+		}
+		if err := os.Symlink(dev, filepath.Join(devRoot, "by-uuid", forgetUUID)); err != nil {
+			t.Fatal(err)
+		}
+	}
+	withDevDiskRoot(t, devRoot)
+	hr := &fakeHostReader{}
+	if c.mounted {
+		hr.mounts = []Mount{{MountPoint: "/mnt/media_a", FSType: "ext4"}}
+	}
+	if c.mountErr {
+		hr.mountsErr = os.ErrPermission
+	}
+	rr := &forgetRunner{unitDir: unitDir}
+	ops := NewSudoHostOps(SudoHostOpsConfig{Runner: rr, Bins: Binaries{}.withDefaults(), UnitDir: unitDir,
+		StageDir: t.TempDir(), Host: hr, Logger: quietLogger()})
+	if intent == nil {
+		intent = &fakeIntent{m: map[string]DriveIntent{"uuid:" + forgetUUID: c.intent}}
+	}
+	n := ops.ForgetRetiredDrives(context.Background(), intent)
+	return n, rr, NewRegistryKnownTargets(unitDir, intent, quietLogger()), unitDir
+}
+
+// The R-1124 case: decommissioned, then unplugged. The unit is disabled and removed through the root checker, systemd
+// is reloaded, and the CONSEQUENCE — the agent no longer lists the drive — holds. RED-PROOF (P1/redproof-forget.txt):
+// with ForgetRetiredDrives' body replaced by `return 0` this test fails (the drive is still listed).
+func TestForgetRetiredDrives_DecommissionedAndGone_UnitRemovedAndNotListed(t *testing.T) {
+	n, rr, known, _ := runForget(t, forgetCase{intent: IntentDecommissioned, enabled: true}, nil)
+	if n != 1 {
+		t.Fatalf("removed = %d, want 1 (calls %v)", n, rr.calls)
+	}
+	pa := Binaries{}.withDefaults()
+	want := [][]string{
+		{pa.Systemctl, "disable", "--", "mnt-media_a.mount"},
+		{pa.PrivApply, "unit-forget", "mnt-media_a.mount"},
+		{pa.Systemctl, "daemon-reload"},
+	}
+	if !reflect.DeepEqual(rr.calls, want) {
+		t.Fatalf("calls = %v\nwant    %v", rr.calls, want)
+	}
+	got, err := known.Known(context.Background())
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(got) != 0 {
+		t.Fatalf("the forgotten drive is still listed: %+v", got)
+	}
+}
+
+// Already disabled (the Tester 1 shape after a manual disable): no disable call, the removal still runs.
+func TestForgetRetiredDrives_AlreadyDisabled_NoDisableCall(t *testing.T) {
+	n, rr, _, _ := runForget(t, forgetCase{intent: IntentDecommissioned}, nil)
+	pa := Binaries{}.withDefaults()
+	want := [][]string{{pa.PrivApply, "unit-forget", "mnt-media_a.mount"}, {pa.Systemctl, "daemon-reload"}}
+	if n != 1 || !reflect.DeepEqual(rr.calls, want) {
+		t.Fatalf("n=%d calls=%v want %v", n, rr.calls, want)
+	}
+}
+
+// Everything that must KEEP its unit: a decommissioned drive still plugged in (re-enroll is one click — H3), one still
+// mounted, an enrolled or ejected drive that is merely absent (it comes back), a drive with no recorded intent, and an
+// unreadable mount table. No privileged call at all, and the drive stays listed where it was listed.
+// RED-PROOF: with the present-drive check removed, the "present" case calls unit-forget and fails.
+func TestForgetRetiredDrives_KeepsEveryOtherUnit(t *testing.T) {
+	for name, c := range map[string]forgetCase{
+		"decommissioned but present": {intent: IntentDecommissioned, present: true, enabled: true},
+		"decommissioned but mounted": {intent: IntentDecommissioned, mounted: true},
+		"enrolled and absent":        {intent: IntentEnrolled},
+		"ejected and absent":         {intent: IntentEjected},
+		"no intent":                  {intent: IntentNew},
+		"mount table unreadable":     {intent: IntentDecommissioned, mountErr: true},
+	} {
+		t.Run(name, func(t *testing.T) {
+			n, rr, _, unitDir := runForget(t, c, nil)
+			if n != 0 || len(rr.calls) != 0 {
+				t.Fatalf("n=%d calls=%v — this unit must be kept", n, rr.calls)
+			}
+			if _, err := os.Stat(filepath.Join(unitDir, "mnt-media_a.mount")); err != nil {
+				t.Fatalf("unit file gone: %v", err)
+			}
+		})
+	}
+}
+
+// No intent store on the host (open failure): nothing is known to be retired, so nothing is forgotten.
+func TestForgetRetiredDrives_NilIntent_ForgetsNothing(t *testing.T) {
+	unitDir := t.TempDir()
+	writeUnit(t, unitDir, "mnt-media_a.mount", renderMountUnit(MountSpec{Name: "x", UUID: forgetUUID, Where: "/mnt/media_a"}))
+	rr := &forgetRunner{unitDir: unitDir}
+	ops := NewSudoHostOps(SudoHostOpsConfig{Runner: rr, UnitDir: unitDir, StageDir: t.TempDir(), Host: &fakeHostReader{}, Logger: quietLogger()})
+	if n := ops.ForgetRetiredDrives(context.Background(), nil); n != 0 || len(rr.calls) != 0 {
+		t.Fatalf("n=%d calls=%v", n, rr.calls)
+	}
+}