felhom-controller/controller/internal/backup/recovery_unit.go

package backup

import (
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"fmt"
	"io"
	"os"
	"path/filepath"
	"sort"
	"strings"
	"time"

	"gopkg.in/yaml.v3"
)

// RecoveryManifest describes an app's self-contained, SECRET-FREE recovery unit (Phase 2).
//
// The unit on a drive is `<nsRoot>/backups/primary/<app>/` and contains:
//   compose/      docker-compose.yml + .felhom.yml + a SECRET-STRIPPED app.yaml
//   db-dumps/     app-consistent DB dump(s)        (written by the dump flow)
//   volume-dumps/ named-volume tars                (written by the dump flow)
//   manifest.json this file
//
// The unit holds NO secret values, NO data-encrypting keys, and NOT the Docker image — only the
// pinned image tag(s) (re-pulled on restore) and the NAMES of the secret/data-key env vars. The
// secret values are recovered at restore time from the guest's own app.yaml (live on the rootfs,
// or via the PBS whole-guest snapshot) — see Restore. "Restore from the unit alone" is therefore
// honestly "unit + the guest's app.yaml"; SecretSource records that dependency explicitly.
type RecoveryManifest struct {
	SchemaVersion  int               `json:"schema_version"`
	AppName        string            `json:"app_name"`
	DisplayName    string            `json:"display_name"`
	ControllerVer  string            `json:"controller_version"`
	CreatedAt      string            `json:"created_at"`
	Drive          string            `json:"drive"`          // HDD_PATH (in-guest mount)
	NamespaceRoot  string            `json:"namespace_root"` // resolved felhom-data namespace root
	ImagePins      []string          `json:"image_pins"`     // image NOT stored — re-pulled on restore
	SecretEnvVars  []string          `json:"secret_env_vars"`   // NAMES only — recovered from guest/PBS
	DataKeyEnvVars []string          `json:"data_key_env_vars"` // fail-closed gate on restore
	SecretSource   string            `json:"secret_source"`     // human note: where secrets come from
	ConfigFiles    []string          `json:"config_files"`      // captured into compose/
	DBDumps        []string          `json:"db_dumps"`
	VolumeDumps    []string          `json:"volume_dumps"`
	Checksums      map[string]string `json:"checksums"` // sha256 of captured compose/ files
}

// SetVersion records the controller version stamped into recovery-unit manifests.
func (m *Manager) SetVersion(v string) {
	m.mu.Lock()
	m.version = v
	m.mu.Unlock()
}

// SetTier2Notifier wires the notification callback invoked after each Tier 2 copy.
func (m *Manager) SetTier2Notifier(fn func(stackName, destLabel string, dur time.Duration, err error)) {
	m.tier2Notify = fn
}

// CaptureRecoveryUnit writes/refreshes an app's secret-free recovery unit: it captures the
// compose + metadata + a secret-stripped app.yaml into compose/, enumerates the DB/volume dumps
// already present, and writes manifest.json. It NEVER writes a secret value or the Docker image.
//
// Idempotent: it builds the captured content in memory first and SKIPS all writes when the unit is
// already current (same config checksums, same dump set, same controller version) — so it can run on
// the periodic status refresh without thrashing a spinning USB drive.
func (m *Manager) CaptureRecoveryUnit(stackName string) error {
	if m.stackProvider == nil {
		return fmt.Errorf("no stack provider")
	}
	info, ok := m.stackProvider.GetStackRecoveryInfo(stackName)
	if !ok {
		return fmt.Errorf("stack %q not found", stackName)
	}
	drivePath := m.GetAppDrivePath(stackName)
	if drivePath == "" || !filepath.IsAbs(drivePath) {
		return fmt.Errorf("cannot determine absolute drive path for %s", stackName)
	}
	nsRoot := m.namespaceRoot(drivePath)

	// Build the captured config CONTENT in memory (no writes yet) so we can checksum-compare.
	type capFile struct {
		name string
		data []byte
		perm os.FileMode
	}
	var files []capFile
	checksums := make(map[string]string)
	var configFiles []string
	for _, fname := range []string{"docker-compose.yml", ".felhom.yml"} {
		data, err := os.ReadFile(filepath.Join(info.StackDir, fname))
		if err != nil {
			continue // optional — capture whichever exist
		}
		files = append(files, capFile{fname, data, 0644})
		checksums[fname] = sha256Hex(data)
		configFiles = append(configFiles, fname)
	}
	appYaml := buildStrippedAppYaml(info)
	files = append(files, capFile{"app.yaml", appYaml, 0600})
	checksums["app.yaml"] = sha256Hex(appYaml)
	configFiles = append(configFiles, "app.yaml")

	dbDumps := listFileNames(AppDBDumpPath(nsRoot, stackName), ".sql")
	volDumps := listFileNames(AppVolumeDumpPath(nsRoot, stackName), ".tar")
	version := m.versionLocked()

	manifestPath := RecoveryUnitManifestPath(nsRoot, stackName)

	// Skip if the unit is already current — avoids needless drive writes on the periodic refresh.
	if cur := readManifest(manifestPath); cur != nil &&
		cur.ControllerVer == version &&
		stringMapEqual(cur.Checksums, checksums) &&
		stringSliceEqual(cur.DBDumps, dbDumps) &&
		stringSliceEqual(cur.VolumeDumps, volDumps) {
		return nil
	}

	composeDir := RecoveryUnitComposePath(nsRoot, stackName)
	if err := os.MkdirAll(composeDir, 0755); err != nil {
		return fmt.Errorf("creating recovery-unit compose dir: %w", err)
	}
	for _, f := range files {
		if err := atomicWrite(filepath.Join(composeDir, f.name), f.data, f.perm); err != nil {
			return fmt.Errorf("capturing %s: %w", f.name, err)
		}
	}

	manifest := &RecoveryManifest{
		SchemaVersion:  1,
		AppName:        stackName,
		DisplayName:    info.DisplayName,
		ControllerVer:  version,
		CreatedAt:      time.Now().UTC().Format(time.RFC3339),
		Drive:          drivePath,
		NamespaceRoot:  nsRoot,
		ImagePins:      info.ImagePins,
		SecretEnvVars:  info.SecretEnvVars,
		DataKeyEnvVars: info.DataKeyEnvVars,
		SecretSource:   "guest app.yaml (live rootfs) or PBS whole-guest snapshot — never stored in this unit",
		ConfigFiles:    configFiles,
		DBDumps:        dbDumps,
		VolumeDumps:    volDumps,
		Checksums:      checksums,
	}
	if err := writeManifest(manifestPath, manifest); err != nil {
		return fmt.Errorf("writing manifest: %w", err)
	}

	m.logger.Printf("[INFO] [backup] Recovery unit captured for %s → %s (images=%d, secrets-referenced=%d, data_keys=%d)",
		stackName, RecoveryUnitPath(nsRoot, stackName), len(info.ImagePins), len(info.SecretEnvVars), len(info.DataKeyEnvVars))
	return nil
}

// captureAllRecoveryUnits refreshes the recovery unit for every deployed stack. Best-effort:
// a per-app failure is logged and does not abort the others.
func (m *Manager) captureAllRecoveryUnits() {
	if m.stackProvider == nil {
		return
	}
	for _, stack := range m.stackProvider.ListDeployedStacks() {
		drivePath := m.GetAppDrivePath(stack.Name)
		if m.settings != nil && (m.settings.IsDisconnected(drivePath) || m.settings.IsDecommissioned(drivePath)) {
			continue // drive not writable — skip, the existing unit stays as-is
		}
		if err := m.CaptureRecoveryUnit(stack.Name); err != nil {
			m.logger.Printf("[WARN] [backup] Recovery unit capture failed for %s: %v", stack.Name, err)
		}
	}
}

func (m *Manager) versionLocked() string {
	m.mu.Lock()
	defer m.mu.Unlock()
	return m.version
}

// strippedAppYaml is the on-disk shape of the secret-free app.yaml captured into the unit.
type strippedAppYaml struct {
	Deployed bool              `yaml:"deployed"`
	Env      map[string]string `yaml:"env"`
}

// buildStrippedAppYaml renders a secret-free app.yaml (non-secret env only) as bytes. Deterministic:
// yaml.v3 sorts map keys and the secret-name list comes in stable metadata order, so identical input
// yields identical bytes (needed for the checksum-skip guard).
func buildStrippedAppYaml(info RecoveryInfo) []byte {
	body, err := yaml.Marshal(strippedAppYaml{Deployed: true, Env: info.NonSecretEnv})
	if err != nil {
		body = []byte("deployed: true\nenv: {}\n")
	}
	header := "# Captured by felhom-controller recovery unit — SECRET-FREE.\n" +
		"# Secret/data-key values are intentionally omitted; recover them at restore from the\n" +
		"# guest's own app.yaml (live rootfs, or the PBS whole-guest snapshot). Stripped names:\n"
	if len(info.SecretEnvVars) > 0 {
		header += "#   " + strings.Join(info.SecretEnvVars, ", ") + "\n"
	}
	return []byte(header + string(body))
}

// writeManifest writes the manifest JSON atomically.
func writeManifest(dst string, manifest *RecoveryManifest) error {
	data, err := json.MarshalIndent(manifest, "", "  ")
	if err != nil {
		return err
	}
	return atomicWrite(dst, append(data, '\n'), 0644)
}

// readManifest reads an existing recovery-unit manifest (nil if absent or unparseable).
func readManifest(path string) *RecoveryManifest {
	data, err := os.ReadFile(path)
	if err != nil {
		return nil
	}
	var m RecoveryManifest
	if json.Unmarshal(data, &m) != nil {
		return nil
	}
	return &m
}

func sha256Hex(data []byte) string {
	sum := sha256.Sum256(data)
	return hex.EncodeToString(sum[:])
}

func stringMapEqual(a, b map[string]string) bool {
	if len(a) != len(b) {
		return false
	}
	for k, v := range a {
		if b[k] != v {
			return false
		}
	}
	return true
}

func stringSliceEqual(a, b []string) bool {
	if len(a) != len(b) {
		return false
	}
	for i := range a {
		if a[i] != b[i] {
			return false
		}
	}
	return true
}

// listFileNames returns the names of files with the given suffix in dir (sorted, none if absent).
func listFileNames(dir, suffix string) []string {
	entries, err := os.ReadDir(dir)
	if err != nil {
		return nil
	}
	var names []string
	for _, e := range entries {
		if !e.IsDir() && strings.HasSuffix(e.Name(), suffix) {
			names = append(names, e.Name())
		}
	}
	sort.Strings(names)
	return names
}

// atomicWrite writes data to path via a .tmp file + rename.
func atomicWrite(path string, data []byte, perm os.FileMode) error {
	tmp := path + ".tmp"
	f, err := os.OpenFile(tmp, os.O_CREATE|os.O_TRUNC|os.O_WRONLY, perm)
	if err != nil {
		return err
	}
	if _, err := io.Copy(f, strings.NewReader(string(data))); err != nil {
		f.Close()
		os.Remove(tmp)
		return err
	}
	if err := f.Close(); err != nil {
		os.Remove(tmp)
		return err
	}
	if err := os.Rename(tmp, path); err != nil {
		os.Remove(tmp)
		return err
	}
	return nil
}