Add DNSSEC signing, key backups and Porkbun support

Zones get a DNSSEC setting: named signs them with BIND's default (or a
custom) dnssec-policy and inline signing, with keys in a per-view key
directory. Jarl shows the keys, the DS record and when it is safe to
publish it, checks the parent's DS records (check-ds, which also tells
named), and refuses steps that would break a signed domain: switching
straight to unsigned, finishing a turn-off too early, deleting or moving
a signed zone, TTLs above max-zone-ttl. Turning off goes through the
insecure policy; wipe starts over once the parent has no DS.

Backups store the DNSSEC keys and restore puts them back for named; the
backup unit gets CAP_DAC_READ_SEARCH to read them. Jarl raises a zone's
serial above named's whenever it writes an older one (after a restore).
The serials check compares the signed serial.

With a Porkbun API key in jarl.yaml, the registrar's name servers, glue
records and DS records can be shown and changed, each change checked
first (dry run, force to override).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

cmd/jarld/backup.go

@@ -7,8 +7,11 @@ import (
 	"fmt"
 	"io"
 	"os"
+	"os/user"
 	"path/filepath"
+	"strconv"
 	"strings"
+	"syscall"
 	"text/tabwriter"
 	"time"
 
@@ -18,11 +21,13 @@ import (
 	"jarl/internal/auth"
 	"jarl/internal/backup"
 	"jarl/internal/config"
+	"jarl/internal/render"
 	"jarl/internal/store"
 )
 
 func backupCmd() *cobra.Command {
-	return &cobra.Command{
+	var withoutKeys bool
+	cmd := &cobra.Command{
 		Use:   "backup [FILE]",
 		Short: "Back up the database (safe while jarld runs)",
 		Long: `Writes a consistent copy of Jarl's database and checks it.
@@ -35,10 +40,18 @@ say. This is what the jarl-backup.timer systemd timer runs every day.
 With FILE it writes a single copy there, which is never deleted
 automatically.
 
+Each backup also holds the DNSSEC keys of signed zones (from Jarl's key
+directory, private keys included), so that 'jarld restore' can put them
+back: a zone whose keys are lost stops validating while its parent still
+has a DS record for them. named's private keys are readable only by named's
+user, so run this as root; jarl-backup.service has the capability to read
+them. --without-keys backs up only the database.
+
 Every backup is recorded in the database, and the dashboard shows the newest.
 Restore one with 'jarld restore'.`,
-		Example: `  sudo -u jarl jarld backup
-  sudo -u jarl jarld backup /root/jarl-before-upgrade.db`,
+		Example: `  sudo jarld backup
+  sudo jarld backup /root/jarl-before-upgrade.db
+  sudo systemctl start jarl-backup.service`,
 		Args: cobra.MaximumNArgs(1),
 		RunE: func(cmd *cobra.Command, args []string) error {
 			cfg, err := config.Load(configPath, true)
@@ -59,7 +72,14 @@ Restore one with 'jarld restore'.`,
 			defer newDirOwner(filepath.Dir(cfg.Database)).fix(filepath.Dir(cfg.Database))
 			ctx := context.Background()
 			now := time.Now()
+			keysDir := render.Paths{ZoneDir: cfg.BIND.ZoneDir}.KeysDir()
+			if withoutKeys {
+				keysDir = ""
+			}
 			fail := func(err error) error {
+				if strings.Contains(err.Error(), "DNSSEC keys") {
+					err = fmt.Errorf("%w; or back up only the database with --without-keys", err)
+				}
 				if rerr := st.RecordBackup(ctx, store.BackupRecord{At: now, Error: err.Error()}); rerr != nil {
 					fmt.Fprintln(os.Stderr, "warning: couldn't record the failure in the database:", rerr)
 				}
@@ -74,27 +94,33 @@ Restore one with 'jarld restore'.`,
 					os.Remove(dst)
 					return fail(fmt.Errorf("backing up %s: %w", cfg.Database, err))
 				}
+				if keysDir != "" {
+					if _, err := backup.AddFiles(ctx, dst, keysDir); err != nil {
+						os.Remove(dst)
+						return fail(err)
+					}
+				}
 				if err := backup.Verify(ctx, dst); err != nil {
 					os.Remove(dst)
 					return fail(fmt.Errorf("the backup failed its check: %w", err))
 				}
 				fi, _ := os.Stat(dst)
 				st.RecordBackup(ctx, store.BackupRecord{At: now, File: dst, Size: fi.Size()})
-				fmt.Printf("Database backed up to %s (%s)\n", dst, size(fi.Size()))
+				fmt.Printf("Database backed up to %s (%s)%s\n", dst, size(fi.Size()), keysNote(ctx, dst))
 				return nil
 			}
 
 			dir := cfg.Backup.Dir
 			defer newDirOwner(dir).fix(dir)
-			f, err := backup.Write(ctx, cfg.Database, dir, backup.KindJarl, now)
+			f, err := backup.Write(ctx, cfg.Database, dir, backup.KindJarl, now, keysDir)
 			if err != nil {
 				return fail(fmt.Errorf("backing up %s: %w", cfg.Database, err))
 			}
-			fmt.Printf("Database backed up to %s (%s)\n", f.Path, size(f.Size))
+			fmt.Printf("Database backed up to %s (%s)%s\n", f.Path, size(f.Size), keysNote(ctx, f.Path))
 			kinds := []string{backup.KindJarl}
 			if cfg.Backup.Stats {
 				if _, err := os.Stat(cfg.Stats.Database); err == nil {
-					sf, err := backup.Write(ctx, cfg.Stats.Database, dir, backup.KindStats, now)
+					sf, err := backup.Write(ctx, cfg.Stats.Database, dir, backup.KindStats, now, "")
 					if err != nil {
 						return fail(fmt.Errorf("backing up the statistics database %s: %w", cfg.Stats.Database, err))
 					}
@@ -117,10 +143,20 @@ Restore one with 'jarld restore'.`,
 			return nil
 		},
 	}
+	cmd.Flags().BoolVar(&withoutKeys, "without-keys", false, "back up only the database, not the DNSSEC keys")
+	return cmd
+}
+
+// keysNote says how many DNSSEC key files a backup holds.
+func keysNote(ctx context.Context, path string) string {
+	if in, err := backup.Inspect(ctx, path); err == nil && in.KeyFiles > 0 {
+		return ", with " + plural(in.KeyFiles, "DNSSEC key file")
+	}
+	return ""
 }
 
 func restoreCmd() *cobra.Command {
-	var yes bool
+	var yes, withoutKeys bool
 	cmd := &cobra.Command{
 		Use:   "restore [FILE | latest]",
 		Short: "Replace the database with a backup (jarld must be stopped)",
@@ -132,13 +168,20 @@ confirm replaces the database with it. jarld must be stopped first. The
 current database is kept as DATABASE.before-restore-<UTC time>, and the
 restore is recorded in the restored database's audit log.
 
+The DNSSEC keys stored in the backup go back into Jarl's key directory,
+owned by named's user (bind.named_user), which needs root. Key files that
+are there but not in the backup are left alone. --without-keys restores
+only the database.
+
 Then start jarld and bring named's files in line with the restored database:
 
   systemctl start jarl
   jarl resync --dry-run     # what differs
   jarl resync --force       # write everything and reload named
 
-See "Restoring" in docs/operations.md, also for zone serials and secondaries.`,
+Jarl raises the serials of zones whose data goes back to an older state
+above what named and the secondaries have, so they pick it up. See
+"Restoring" in docs/operations.md.`,
 		Example: `  sudo jarld restore
   sudo systemctl stop jarl
   sudo jarld restore latest
@@ -180,6 +223,24 @@ See "Restoring" in docs/operations.md, also for zone serials and secondaries.`,
 			if info.Schema > store.SchemaVersion() {
 				return fmt.Errorf("%s was made by a newer Jarl (schema %d, this one knows %d); install that version to restore it", src, info.Schema, store.SchemaVersion())
 			}
+			keysDir := render.Paths{ZoneDir: cfg.BIND.ZoneDir}.KeysDir()
+			var keyFiles []backup.StoredFile
+			if !withoutKeys {
+				var root string
+				root, keyFiles, err = backup.Files(ctx, src)
+				if err != nil {
+					return fmt.Errorf("reading the DNSSEC keys in %s: %w", src, err)
+				}
+				if len(keyFiles) > 0 && os.Geteuid() != 0 && !runningAs(cfg.BIND.NamedUser) {
+					return fmt.Errorf("the backup holds %s, and putting them back for named needs root: run this as root (or add --without-keys to restore only the database)", plural(len(keyFiles), "DNSSEC key file"))
+				}
+				if root != "" && root != keysDir && len(keyFiles) > 0 {
+					fmt.Printf("The keys were backed up from %s; they go to %s now.\n", root, keysDir)
+				}
+			}
+			if info.SignedZones > 0 && len(keyFiles) == 0 && !withoutKeys {
+				fmt.Fprintf(os.Stderr, "warning: the backup has %s but no DNSSEC keys (it was made with --without-keys, or before Jarl backed them up). Unless the keys are still in %s, named makes new ones, and a DS record for the old ones at the parent stops matching.\n", plural(info.SignedZones, "signed zone"), keysDir)
+			}
 			unlock, err := lockDatabase(cfg.Database)
 			if errors.Is(err, errInUse) {
 				return fmt.Errorf("jarld is running; stop it first (systemctl stop jarl), then run this again")
@@ -192,6 +253,9 @@ See "Restoring" in docs/operations.md, also for zone serials and secondaries.`,
 			w := tabwriter.NewWriter(os.Stdout, 0, 0, 2, ' ', 0)
 			fmt.Fprintf(w, "Backup:\t%s\n", src)
 			describe(w, info, backupTime(src))
+			if len(keyFiles) > 0 {
+				fmt.Fprintf(w, "  DNSSEC keys\t%s (go back to %s)\n", plural(len(keyFiles), "file"), keysDir)
+			}
 			if cur, err := backup.Inspect(ctx, cfg.Database); err == nil {
 				fmt.Fprintf(w, "\nCurrent database:\t%s\n", cfg.Database)
 				describe(w, cur, time.Time{})
@@ -224,13 +288,27 @@ See "Restoring" in docs/operations.md, also for zone serials and secondaries.`,
 					moved = true
 				}
 			}
-			if err := copyFile(src, db, 0o640); err != nil {
+			restoreErr := copyFile(src, db, 0o640)
+			if restoreErr == nil {
+				// The keys go back to their own files, not into the
+				// live database.
+				restoreErr = backup.DropFiles(ctx, db)
+			}
+			if restoreErr != nil {
+				os.Remove(db)
 				if moved {
 					os.Rename(aside, db)
 					os.Rename(aside+"-wal", db+"-wal")
 					os.Rename(aside+"-shm", db+"-shm")
 				}
-				return fmt.Errorf("restoring: %w (the current database was left in place)", err)
+				return fmt.Errorf("restoring: %w (the current database was left in place)", restoreErr)
+			}
+			if len(keyFiles) > 0 {
+				n, err := restoreKeys(cfg, keysDir, keyFiles)
+				if err != nil {
+					return fmt.Errorf("the database was restored, but putting back the DNSSEC keys failed after %d files: %w", n, err)
+				}
+				fmt.Printf("Put back %s in %s.\n", plural(n, "DNSSEC key file"), keysDir)
 			}
 			// Open it as jarld will: an older backup gets the current
 			// schema now, and the restore goes into its audit log.
@@ -255,17 +333,89 @@ Next:
   jarl resync --dry-run     # what differs between the restored database and named's files
   jarl resync --force       # write them and reload named
 
-If you have secondary servers, zone serials older than what they last saw
-are ignored by them: raise them with 'jarl zone update ZONE --serial N'
-(see "Restoring" in docs/operations.md).
+Zones whose data goes back to an older state get a serial above the one
+named has, so named and the secondaries load them (see "Restoring" in
+docs/operations.md).
 `)
 			return nil
 		},
 	}
 	cmd.Flags().BoolVarP(&yes, "yes", "y", false, "don't ask for confirmation")
+	cmd.Flags().BoolVar(&withoutKeys, "without-keys", false, "restore only the database, not the DNSSEC keys")
 	return cmd
 }
 
+// runningAs reports whether this process runs as the named user.
+func runningAs(name string) bool {
+	u, err := user.Lookup(name)
+	return err == nil && u.Uid == strconv.Itoa(os.Geteuid())
+}
+
+// restoreKeys writes DNSSEC key files from a backup into keysDir, owned
+// by named's user and Jarl's file group with their backed-up modes, so
+// named can use them. Directories get the owner of the zone directory
+// (jarld's user), like the ones jarld makes. Files already there are
+// replaced; others are left alone.
+func restoreKeys(cfg *config.Config, keysDir string, files []backup.StoredFile) (int, error) {
+	uid, gid := -1, -1
+	if u, err := user.Lookup(cfg.BIND.NamedUser); err == nil {
+		uid, _ = strconv.Atoi(u.Uid)
+	} else {
+		return 0, fmt.Errorf("named's user %q (bind.named_user): %w", cfg.BIND.NamedUser, err)
+	}
+	if g, err := user.LookupGroup(cfg.BIND.FileGroup); err == nil {
+		gid, _ = strconv.Atoi(g.Gid)
+	}
+	dirUID, dirGID := -1, gid
+	if fi, err := os.Stat(cfg.BIND.ZoneDir); err == nil {
+		if st, ok := fi.Sys().(*syscall.Stat_t); ok {
+			dirUID = int(st.Uid)
+		}
+	}
+	var mkdir func(dir string) error
+	mkdir = func(dir string) error {
+		if _, err := os.Stat(dir); err == nil {
+			return nil
+		}
+		if err := mkdir(filepath.Dir(dir)); err != nil {
+			return err
+		}
+		if err := os.Mkdir(dir, 0o770); err != nil && !os.IsExist(err) {
+			return err
+		}
+		os.Chown(dir, dirUID, dirGID)
+		return os.Chmod(dir, 0o770|os.ModeSetgid)
+	}
+	n := 0
+	for _, f := range files {
+		if filepath.IsAbs(f.Path) || strings.HasPrefix(filepath.Clean(f.Path), "..") {
+			return n, fmt.Errorf("refusing the file name %q in the backup", f.Path)
+		}
+		dst := filepath.Join(keysDir, f.Path)
+		if err := mkdir(filepath.Dir(dst)); err != nil {
+			return n, err
+		}
+		tmp := dst + ".restore-tmp"
+		if err := os.WriteFile(tmp, f.Data, 0o600); err != nil {
+			return n, err
+		}
+		if err := os.Chown(tmp, uid, gid); err != nil {
+			os.Remove(tmp)
+			return n, err
+		}
+		if err := os.Chmod(tmp, f.Mode); err != nil {
+			os.Remove(tmp)
+			return n, err
+		}
+		if err := os.Rename(tmp, dst); err != nil {
+			os.Remove(tmp)
+			return n, err
+		}
+		n++
+	}
+	return n, nil
+}
+
 func listBackups(dir string) error {
 	files, err := backup.List(dir)
 	if err != nil {
@@ -290,6 +440,9 @@ func describe(w io.Writer, in *backup.Info, made time.Time) {
 		fmt.Fprintf(w, "  made\t%s (%s ago)\n", made.Local().Format("2006-01-02 15:04:05"), fmtDuration(time.Since(made)))
 	}
 	fmt.Fprintf(w, "  contents\t%s, %s, %s (schema %d)\n", plural(in.Zones, "zone"), plural(in.Records, "record"), plural(in.Users, "user"), in.Schema)
+	if in.SignedZones > 0 {
+		fmt.Fprintf(w, "  signed zones\t%d\n", in.SignedZones)
+	}
 	if in.LastChange != nil {
 		fmt.Fprintf(w, "  last change\t%s\n", in.LastChange.Local().Format("2006-01-02 15:04:05"))
 	}

cmd/jarld/main.go

@@ -27,6 +27,7 @@ import (
 	"jarl/internal/config"
 	"jarl/internal/engine"
 	"jarl/internal/model"
+	"jarl/internal/porkbun"
 	"jarl/internal/render"
 	"jarl/internal/server"
 	"jarl/internal/stats"
@@ -291,12 +292,20 @@ func serveCmd() *cobra.Command {
 				// database closes, however serving ends.
 				defer func() { cancel(); <-collectorDone }()
 			}
+			var pb *porkbun.Client
+			if a.cfg.Porkbun.Enabled() {
+				pb = &porkbun.Client{BaseURL: a.cfg.Porkbun.APIURL, APIKey: a.cfg.Porkbun.APIKey, Secret: a.cfg.Porkbun.SecretAPIKey}
+				if fi, err := os.Stat(configPath); err == nil && fi.Mode().Perm()&0o004 != 0 {
+					a.log.Warn("the configuration file holds the Porkbun API key and everyone can read it; make it readable only by root and jarld (chown root:jarl, chmod 640)", "file", configPath)
+				}
+			}
 			srv := server.New(server.Config{
 				Listen: a.cfg.Listen, TLSCertFile: a.cfg.TLS.CertFile, TLSKeyFile: a.cfg.TLS.KeyFile,
 				TrustedProxies: a.cfg.Proxies(), SessionLifetime: time.Duration(a.cfg.Session.Lifetime),
 				SessionIdle: time.Duration(a.cfg.Session.IdleTimeout), CookieSecure: a.cfg.Session.CookieSecure,
 				Version: version.Version, Stats: collector, Socket: a.cfg.Socket,
 				BackupDir: a.cfg.Backup.Dir, BackupWarnAfter: time.Duration(a.cfg.Backup.WarnAfter),
+				Porkbun: pb, PorkbunAllows: a.cfg.Porkbun.Allows,
 				HTTPReq: server.HTTPReq{
 					Enabled:           a.cfg.ACME.HTTPReq.Enabled,
 					AllowPlainHTTP:    !a.cfg.ACME.HTTPReq.RequireHTTPS,