banger/internal/roothelper/roothelper.go

package roothelper

import (
	"bufio"
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"log/slog"
	"net"
	"os"
	"path/filepath"
	"strconv"
	"strings"
	"time"

	"golang.org/x/sys/unix"

	"banger/internal/daemon/dmsnap"
	"banger/internal/daemon/fcproc"
	"banger/internal/firecracker"
	"banger/internal/hostnat"
	"banger/internal/installmeta"
	"banger/internal/paths"
	"banger/internal/rpc"
	"banger/internal/system"
)

const (
	methodEnsureBridge           = "priv.ensure_bridge"
	methodCreateTap              = "priv.create_tap"
	methodDeleteTap              = "priv.delete_tap"
	methodSyncResolverRouting    = "priv.sync_resolver_routing"
	methodClearResolverRouting   = "priv.clear_resolver_routing"
	methodEnsureNAT              = "priv.ensure_nat"
	methodCreateDMSnapshot       = "priv.create_dm_snapshot"
	methodCleanupDMSnapshot      = "priv.cleanup_dm_snapshot"
	methodRemoveDMSnapshot       = "priv.remove_dm_snapshot"
	methodFsckSnapshot           = "priv.fsck_snapshot"
	methodReadExt4File           = "priv.read_ext4_file"
	methodWriteExt4Files         = "priv.write_ext4_files"
	methodResolveFirecrackerBin  = "priv.resolve_firecracker_binary"
	methodLaunchFirecracker      = "priv.launch_firecracker"
	methodEnsureSocketAccess     = "priv.ensure_socket_access"
	methodFindFirecrackerPID     = "priv.find_firecracker_pid"
	methodKillProcess            = "priv.kill_process"
	methodSignalProcess          = "priv.signal_process"
	methodProcessRunning         = "priv.process_running"
	methodCleanupJailerChroot    = "priv.cleanup_jailer_chroot"
	rootfsDMNamePrefix           = "fc-rootfs-"
	vmTapPrefix                  = "tap-fc-"
	tapPoolPrefix                = "tap-pool-"
	vmResolverRouteDomain        = "~vm"
	defaultFirecrackerBinaryName = "firecracker"
)

type NetworkConfig struct {
	BridgeName string `json:"bridge_name"`
	BridgeIP   string `json:"bridge_ip"`
	CIDR       string `json:"cidr"`
}

type Ext4Write struct {
	GuestPath string `json:"guest_path"`
	Data      []byte `json:"data"`
	Mode      uint32 `json:"mode"`
}

type FirecrackerLaunchRequest struct {
	BinaryPath      string                    `json:"binary_path"`
	VMID            string                    `json:"vm_id"`
	SocketPath      string                    `json:"socket_path"`
	LogPath         string                    `json:"log_path"`
	MetricsPath     string                    `json:"metrics_path"`
	KernelImagePath string                    `json:"kernel_image_path"`
	InitrdPath      string                    `json:"initrd_path,omitempty"`
	KernelArgs      string                    `json:"kernel_args"`
	Drives          []firecracker.DriveConfig `json:"drives"`
	TapDevice       string                    `json:"tap_device"`
	VSockPath       string                    `json:"vsock_path"`
	VSockCID        uint32                    `json:"vsock_cid"`
	VCPUCount       int                       `json:"vcpu_count"`
	MemoryMiB       int                       `json:"memory_mib"`
	Network         NetworkConfig             `json:"network"`
	Jailer          *JailerLaunchOpts         `json:"jailer,omitempty"`
}

// JailerLaunchOpts mirrors firecracker.JailerOpts for the RPC wire. UID
// and GID are the (un)privileged target the jailer drops to; the helper
// enforces they match the registered owner so the daemon can't ask the
// helper to run firecracker as an arbitrary user.
type JailerLaunchOpts struct {
	Binary        string `json:"binary"`
	ChrootBaseDir string `json:"chroot_base_dir"`
	UID           int    `json:"uid"`
	GID           int    `json:"gid"`
}

type findPIDResult struct {
	PID int `json:"pid"`
}

type processRunningResult struct {
	Running bool `json:"running"`
}

type readExt4FileResult struct {
	Data []byte `json:"data"`
}

type resolveFirecrackerResult struct {
	Path string `json:"path"`
}

type launchFirecrackerResult struct {
	PID int `json:"pid"`
}

type Client struct {
	socketPath string
}

func NewClient(socketPath string) *Client {
	return &Client{socketPath: strings.TrimSpace(socketPath)}
}

func (c *Client) EnsureBridge(ctx context.Context, cfg NetworkConfig) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodEnsureBridge, cfg)
	return err
}

func (c *Client) CreateTap(ctx context.Context, cfg NetworkConfig, tapName string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodCreateTap, struct {
		NetworkConfig
		TapName string `json:"tap_name"`
	}{NetworkConfig: cfg, TapName: tapName})
	return err
}

func (c *Client) DeleteTap(ctx context.Context, tapName string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodDeleteTap, struct {
		TapName string `json:"tap_name"`
	}{TapName: tapName})
	return err
}

func (c *Client) SyncResolverRouting(ctx context.Context, bridgeName, serverAddr string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodSyncResolverRouting, struct {
		BridgeName string `json:"bridge_name"`
		ServerAddr string `json:"server_addr"`
	}{BridgeName: bridgeName, ServerAddr: serverAddr})
	return err
}

func (c *Client) ClearResolverRouting(ctx context.Context, bridgeName string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodClearResolverRouting, struct {
		BridgeName string `json:"bridge_name"`
	}{BridgeName: bridgeName})
	return err
}

func (c *Client) EnsureNAT(ctx context.Context, guestIP, tap string, enable bool) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodEnsureNAT, struct {
		GuestIP string `json:"guest_ip"`
		Tap     string `json:"tap"`
		Enable  bool   `json:"enable"`
	}{GuestIP: guestIP, Tap: tap, Enable: enable})
	return err
}

func (c *Client) CreateDMSnapshot(ctx context.Context, rootfsPath, cowPath, dmName string) (dmsnap.Handles, error) {
	return rpc.Call[dmsnap.Handles](ctx, c.socketPath, methodCreateDMSnapshot, struct {
		RootfsPath string `json:"rootfs_path"`
		COWPath    string `json:"cow_path"`
		DMName     string `json:"dm_name"`
	}{RootfsPath: rootfsPath, COWPath: cowPath, DMName: dmName})
}

func (c *Client) CleanupDMSnapshot(ctx context.Context, handles dmsnap.Handles) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodCleanupDMSnapshot, handles)
	return err
}

func (c *Client) RemoveDMSnapshot(ctx context.Context, target string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodRemoveDMSnapshot, struct {
		Target string `json:"target"`
	}{Target: target})
	return err
}

func (c *Client) FsckSnapshot(ctx context.Context, dmDev string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodFsckSnapshot, struct {
		DMDev string `json:"dm_dev"`
	}{DMDev: dmDev})
	return err
}

func (c *Client) ReadExt4File(ctx context.Context, imagePath, guestPath string) ([]byte, error) {
	result, err := rpc.Call[readExt4FileResult](ctx, c.socketPath, methodReadExt4File, struct {
		ImagePath string `json:"image_path"`
		GuestPath string `json:"guest_path"`
	}{ImagePath: imagePath, GuestPath: guestPath})
	if err != nil {
		return nil, err
	}
	return result.Data, nil
}

func (c *Client) WriteExt4Files(ctx context.Context, imagePath string, files []Ext4Write) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodWriteExt4Files, struct {
		ImagePath string      `json:"image_path"`
		Files     []Ext4Write `json:"files"`
	}{ImagePath: imagePath, Files: files})
	return err
}

func (c *Client) ResolveFirecrackerBinary(ctx context.Context, requested string) (string, error) {
	result, err := rpc.Call[resolveFirecrackerResult](ctx, c.socketPath, methodResolveFirecrackerBin, struct {
		Requested string `json:"requested"`
	}{Requested: requested})
	if err != nil {
		return "", err
	}
	return result.Path, nil
}

func (c *Client) LaunchFirecracker(ctx context.Context, req FirecrackerLaunchRequest) (int, error) {
	result, err := rpc.Call[launchFirecrackerResult](ctx, c.socketPath, methodLaunchFirecracker, req)
	if err != nil {
		return 0, err
	}
	return result.PID, nil
}

func (c *Client) CleanupJailerChroot(ctx context.Context, chrootRoot string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodCleanupJailerChroot, struct {
		ChrootRoot string `json:"chroot_root"`
	}{ChrootRoot: chrootRoot})
	return err
}

func (c *Client) EnsureSocketAccess(ctx context.Context, socketPath, label string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodEnsureSocketAccess, struct {
		SocketPath string `json:"socket_path"`
		Label      string `json:"label"`
	}{SocketPath: socketPath, Label: label})
	return err
}

func (c *Client) FindFirecrackerPID(ctx context.Context, apiSock string) (int, error) {
	result, err := rpc.Call[findPIDResult](ctx, c.socketPath, methodFindFirecrackerPID, struct {
		APISock string `json:"api_sock"`
	}{APISock: apiSock})
	if err != nil {
		return 0, err
	}
	return result.PID, nil
}

func (c *Client) KillProcess(ctx context.Context, pid int) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodKillProcess, struct {
		PID int `json:"pid"`
	}{PID: pid})
	return err
}

func (c *Client) SignalProcess(ctx context.Context, pid int, signal string) error {
	_, err := rpc.Call[struct{}](ctx, c.socketPath, methodSignalProcess, struct {
		PID    int    `json:"pid"`
		Signal string `json:"signal"`
	}{PID: pid, Signal: signal})
	return err
}

func (c *Client) ProcessRunning(ctx context.Context, pid int, apiSock string) (bool, error) {
	result, err := rpc.Call[processRunningResult](ctx, c.socketPath, methodProcessRunning, struct {
		PID     int    `json:"pid"`
		APISock string `json:"api_sock"`
	}{PID: pid, APISock: apiSock})
	if err != nil {
		return false, err
	}
	return result.Running, nil
}

type Server struct {
	meta     installmeta.Metadata
	runner   system.CommandRunner
	logger   *slog.Logger
	listener net.Listener
}

func Open() (*Server, error) {
	meta, err := installmeta.Load(installmeta.DefaultPath)
	if err != nil {
		return nil, err
	}
	if err := os.MkdirAll(installmeta.DefaultRootHelperRuntimeDir, 0o711); err != nil {
		return nil, err
	}
	if err := os.Chmod(installmeta.DefaultRootHelperRuntimeDir, 0o711); err != nil {
		return nil, err
	}
	return &Server{
		meta:   meta,
		runner: system.NewRunner(),
		// JSON to match bangerd. Mixed text/JSON streams in the
		// merged journalctl made the daemon side painful to grep;
		// this aligns the helper so a single greppable shape spans
		// both units.
		logger: slog.New(slog.NewJSONHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelInfo})),
	}, nil
}

func (s *Server) Close() error {
	if s == nil || s.listener == nil {
		return nil
	}
	return s.listener.Close()
}

func (s *Server) Serve(ctx context.Context) error {
	_ = os.Remove(installmeta.DefaultRootHelperSocketPath)
	listener, err := net.Listen("unix", installmeta.DefaultRootHelperSocketPath)
	if err != nil {
		return err
	}
	s.listener = listener
	defer listener.Close()
	defer os.Remove(installmeta.DefaultRootHelperSocketPath)
	if err := os.Chmod(installmeta.DefaultRootHelperSocketPath, 0o600); err != nil {
		return err
	}
	if err := os.Chown(installmeta.DefaultRootHelperSocketPath, s.meta.OwnerUID, s.meta.OwnerGID); err != nil {
		return err
	}

	done := make(chan struct{})
	defer close(done)
	go func() {
		select {
		case <-ctx.Done():
			_ = listener.Close()
		case <-done:
		}
	}()

	for {
		conn, err := listener.Accept()
		if err != nil {
			select {
			case <-ctx.Done():
				return nil
			default:
			}
			var netErr net.Error
			if errors.As(err, &netErr) && netErr.Temporary() {
				time.Sleep(100 * time.Millisecond)
				continue
			}
			return err
		}
		go s.handleConn(conn)
	}
}

func (s *Server) handleConn(conn net.Conn) {
	defer conn.Close()
	if err := s.authorizeConn(conn); err != nil {
		_ = json.NewEncoder(conn).Encode(rpc.NewError("unauthorized", err.Error()))
		return
	}
	var req rpc.Request
	if err := json.NewDecoder(bufio.NewReader(conn)).Decode(&req); err != nil {
		_ = json.NewEncoder(conn).Encode(rpc.NewError("bad_request", err.Error()))
		return
	}
	// Adopt the daemon's op id so a single greppable id covers the
	// whole call chain (CLI → daemon → helper). Entry log at debug
	// level keeps production quiet; the completion log fires at
	// info-on-success / error-on-failure with duration so an
	// operator can see at a glance how long each privileged op
	// took.
	ctx := rpc.WithOpID(context.Background(), req.OpID)
	start := time.Now()
	if s.logger != nil {
		s.logger.Debug("helper rpc", "method", req.Method, "op_id", req.OpID)
	}
	resp := s.dispatch(ctx, req)
	if !resp.OK && resp.Error != nil && resp.Error.OpID == "" && req.OpID != "" {
		resp.Error.OpID = req.OpID
	}
	if s.logger != nil {
		duration := time.Since(start).Milliseconds()
		if !resp.OK && resp.Error != nil {
			s.logger.Error("helper rpc failed", "method", req.Method, "op_id", req.OpID, "duration_ms", duration, "code", resp.Error.Code, "message", resp.Error.Message)
		} else {
			s.logger.Info("helper rpc completed", "method", req.Method, "op_id", req.OpID, "duration_ms", duration)
		}
	}
	_ = json.NewEncoder(conn).Encode(resp)
}

func (s *Server) authorizeConn(conn net.Conn) error {
	unixConn, ok := conn.(*net.UnixConn)
	if !ok {
		return errors.New("root helper requires unix connections")
	}
	rawConn, err := unixConn.SyscallConn()
	if err != nil {
		return err
	}
	var cred *unix.Ucred
	var controlErr error
	if err := rawConn.Control(func(fd uintptr) {
		cred, controlErr = unix.GetsockoptUcred(int(fd), unix.SOL_SOCKET, unix.SO_PEERCRED)
	}); err != nil {
		return err
	}
	if controlErr != nil {
		return controlErr
	}
	if cred == nil {
		return errors.New("missing peer credentials")
	}
	if int(cred.Uid) == 0 || int(cred.Uid) == s.meta.OwnerUID {
		return nil
	}
	return fmt.Errorf("uid %d is not allowed to use the root helper", cred.Uid)
}

func (s *Server) dispatch(ctx context.Context, req rpc.Request) rpc.Response {
	switch req.Method {
	case methodEnsureBridge:
		params, err := rpc.DecodeParams[NetworkConfig](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.ensureBridge(ctx, params))
	case methodCreateTap:
		params, err := rpc.DecodeParams[struct {
			NetworkConfig
			TapName string `json:"tap_name"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.createTap(ctx, params.NetworkConfig, params.TapName))
	case methodDeleteTap:
		params, err := rpc.DecodeParams[struct {
			TapName string `json:"tap_name"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.deleteTap(ctx, params.TapName))
	case methodSyncResolverRouting:
		params, err := rpc.DecodeParams[struct {
			BridgeName string `json:"bridge_name"`
			ServerAddr string `json:"server_addr"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		// syncResolverRouting short-circuits on empty input; only
		// validate when actually doing something. This stops a
		// compromised daemon from flapping arbitrary system-managed
		// links via resolvectl.
		if strings.TrimSpace(params.BridgeName) != "" || strings.TrimSpace(params.ServerAddr) != "" {
			if err := validateLinuxIfaceName(params.BridgeName); err != nil {
				return rpc.NewError("bad_params", err.Error())
			}
			if err := validateResolverAddr(params.ServerAddr); err != nil {
				return rpc.NewError("bad_params", err.Error())
			}
		}
		return marshalResultOrError(struct{}{}, s.syncResolverRouting(ctx, params.BridgeName, params.ServerAddr))
	case methodClearResolverRouting:
		params, err := rpc.DecodeParams[struct {
			BridgeName string `json:"bridge_name"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if strings.TrimSpace(params.BridgeName) != "" {
			if err := validateLinuxIfaceName(params.BridgeName); err != nil {
				return rpc.NewError("bad_params", err.Error())
			}
		}
		return marshalResultOrError(struct{}{}, s.clearResolverRouting(ctx, params.BridgeName))
	case methodEnsureNAT:
		params, err := rpc.DecodeParams[struct {
			GuestIP string `json:"guest_ip"`
			Tap     string `json:"tap"`
			Enable  bool   `json:"enable"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		// Without these the helper installs iptables rules with
		// daemon-supplied identifiers; argv-style exec rules out
		// command injection, but a compromised daemon could still
		// install MASQUERADE rules tied to arbitrary IPs/interfaces.
		if err := validateIPv4(params.GuestIP); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := validateTapName(params.Tap); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, hostnat.Ensure(ctx, s.runner, params.GuestIP, params.Tap, params.Enable))
	case methodCreateDMSnapshot:
		params, err := rpc.DecodeParams[struct {
			RootfsPath string `json:"rootfs_path"`
			COWPath    string `json:"cow_path"`
			DMName     string `json:"dm_name"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := s.validateManagedPath(params.RootfsPath, paths.ResolveSystem().StateDir); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := s.validateManagedPath(params.COWPath, paths.ResolveSystem().StateDir); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := validateDMName(params.DMName); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		result, err := dmsnap.Create(ctx, s.runner, params.RootfsPath, params.COWPath, params.DMName)
		return marshalResultOrError(result, err)
	case methodCleanupDMSnapshot:
		params, err := rpc.DecodeParams[dmsnap.Handles](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		// Each Handles field flows into a `dmsetup remove` /
		// `losetup -d` shell-out as root. Without these checks a
		// compromised daemon could ask the helper to detach
		// arbitrary loop devices or remove unrelated DM targets.
		if err := validateDMSnapshotHandles(params); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, dmsnap.Cleanup(ctx, s.runner, params))
	case methodRemoveDMSnapshot:
		params, err := rpc.DecodeParams[struct {
			Target string `json:"target"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := validateDMRemoveTarget(params.Target); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, dmsnap.Remove(ctx, s.runner, params.Target))
	case methodFsckSnapshot:
		params, err := rpc.DecodeParams[struct {
			DMDev string `json:"dm_dev"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.fsckSnapshot(ctx, params.DMDev))
	case methodReadExt4File:
		params, err := rpc.DecodeParams[struct {
			ImagePath string `json:"image_path"`
			GuestPath string `json:"guest_path"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		// Without this validation a compromised daemon can drive
		// debugfs as root against any path on the host; it would have
		// to be a real ext4 image to leak data, but the constraint is
		// trivially expressed and adds no operational cost.
		if err := s.validateExt4ImagePath(params.ImagePath); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		data, readErr := system.ReadExt4File(ctx, s.runner, params.ImagePath, params.GuestPath)
		return marshalResultOrError(readExt4FileResult{Data: data}, readErr)
	case methodWriteExt4Files:
		params, err := rpc.DecodeParams[struct {
			ImagePath string      `json:"image_path"`
			Files     []Ext4Write `json:"files"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := s.validateExt4ImagePath(params.ImagePath); err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.writeExt4Files(ctx, params.ImagePath, params.Files))
	case methodResolveFirecrackerBin:
		params, err := rpc.DecodeParams[struct {
			Requested string `json:"requested"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		path, resolveErr := s.resolveFirecrackerBinary(params.Requested)
		return marshalResultOrError(resolveFirecrackerResult{Path: path}, resolveErr)
	case methodLaunchFirecracker:
		params, err := rpc.DecodeParams[FirecrackerLaunchRequest](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		pid, launchErr := s.launchFirecracker(ctx, params)
		return marshalResultOrError(launchFirecrackerResult{PID: pid}, launchErr)
	case methodEnsureSocketAccess:
		params, err := rpc.DecodeParams[struct {
			SocketPath string `json:"socket_path"`
			Label      string `json:"label"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		// Without these checks the helper's chown/chmod becomes an
		// arbitrary file-ownership primitive: a daemon-uid attacker
		// could plant a symlink at any path under RuntimeDir (or just
		// pass /etc/shadow) and have the helper transfer ownership to
		// the daemon UID. The fcproc layer also chowns/chmods via
		// O_PATH|O_NOFOLLOW so the leaf can't be a symlink at the time
		// of the syscall — these checks are belt + braces and give a
		// clear error before we even open the path.
		if err := s.validateManagedPath(params.SocketPath, paths.ResolveSystem().RuntimeDir); err != nil {
			return rpc.NewError("invalid_path", err.Error())
		}
		if err := validateNotSymlink(params.SocketPath); err != nil {
			return rpc.NewError("invalid_path", err.Error())
		}
		return marshalResultOrError(struct{}{}, s.ensureSocketAccess(ctx, params.SocketPath, params.Label))
	case methodFindFirecrackerPID:
		params, err := rpc.DecodeParams[struct {
			APISock string `json:"api_sock"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		pid, findErr := fcproc.New(s.runner, fcproc.Config{}, s.logger).FindPID(ctx, params.APISock)
		return marshalResultOrError(findPIDResult{PID: pid}, findErr)
	case methodKillProcess:
		params, err := rpc.DecodeParams[struct {
			PID int `json:"pid"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := validateFirecrackerPID(params.PID); err != nil {
			return rpc.NewError("invalid_pid", err.Error())
		}
		_, killErr := s.runner.Run(ctx, "kill", "-KILL", strconv.Itoa(params.PID))
		return marshalResultOrError(struct{}{}, killErr)
	case methodSignalProcess:
		params, err := rpc.DecodeParams[struct {
			PID    int    `json:"pid"`
			Signal string `json:"signal"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		if err := validateFirecrackerPID(params.PID); err != nil {
			return rpc.NewError("invalid_pid", err.Error())
		}
		signal := strings.TrimSpace(params.Signal)
		if signal == "" {
			signal = "TERM"
		}
		_, signalErr := s.runner.Run(ctx, "kill", "-"+signal, strconv.Itoa(params.PID))
		return marshalResultOrError(struct{}{}, signalErr)
	case methodProcessRunning:
		params, err := rpc.DecodeParams[struct {
			PID     int    `json:"pid"`
			APISock string `json:"api_sock"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		return marshalResultOrError(processRunningResult{Running: system.ProcessRunning(params.PID, params.APISock)}, nil)
	case methodCleanupJailerChroot:
		params, err := rpc.DecodeParams[struct {
			ChrootRoot string `json:"chroot_root"`
		}](req)
		if err != nil {
			return rpc.NewError("bad_params", err.Error())
		}
		systemLayout := paths.ResolveSystem()
		if err := s.validateManagedPath(params.ChrootRoot, systemLayout.StateDir, systemLayout.RuntimeDir); err != nil {
			return rpc.NewError("invalid_path", err.Error())
		}
		// validateManagedPath only does textual prefix matching. A
		// symlink at e.g. /var/lib/banger/jail/x → / would pass the
		// prefix check, and the subsequent `umount --recursive --lazy`
		// would detach real host mounts. Reject leaf symlinks before
		// we go anywhere near unmount/rm.
		if err := validateNotSymlink(params.ChrootRoot); err != nil {
			return rpc.NewError("invalid_path", err.Error())
		}
		err = fcproc.New(s.runner, fcproc.Config{}, s.logger).CleanupJailerChroot(ctx, params.ChrootRoot)
		return marshalResultOrError(struct{}{}, err)
	default:
		return rpc.NewError("unknown_method", req.Method)
	}
}

func (s *Server) ensureBridge(ctx context.Context, cfg NetworkConfig) error {
	return fcproc.New(s.runner, fcproc.Config{
		BridgeName: cfg.BridgeName,
		BridgeIP:   cfg.BridgeIP,
		CIDR:       cfg.CIDR,
	}, s.logger).EnsureBridge(ctx)
}

func (s *Server) createTap(ctx context.Context, cfg NetworkConfig, tapName string) error {
	if err := validateTapName(tapName); err != nil {
		return err
	}
	return fcproc.New(s.runner, fcproc.Config{
		BridgeName: cfg.BridgeName,
		BridgeIP:   cfg.BridgeIP,
		CIDR:       cfg.CIDR,
	}, s.logger).CreateTapOwned(ctx, tapName, s.meta.OwnerUID, s.meta.OwnerGID)
}

func (s *Server) deleteTap(ctx context.Context, tapName string) error {
	if err := validateTapName(tapName); err != nil {
		return err
	}
	_, err := s.runner.Run(ctx, "ip", "link", "del", tapName)
	return err
}

func (s *Server) syncResolverRouting(ctx context.Context, bridgeName, serverAddr string) error {
	if strings.TrimSpace(bridgeName) == "" || strings.TrimSpace(serverAddr) == "" {
		return nil
	}
	if _, err := system.LookupExecutable("resolvectl"); err != nil {
		return nil
	}
	if _, err := s.runner.Run(ctx, "resolvectl", "dns", bridgeName, serverAddr); err != nil {
		return err
	}
	if _, err := s.runner.Run(ctx, "resolvectl", "domain", bridgeName, vmResolverRouteDomain); err != nil {
		return err
	}
	_, err := s.runner.Run(ctx, "resolvectl", "default-route", bridgeName, "no")
	return err
}

func (s *Server) clearResolverRouting(ctx context.Context, bridgeName string) error {
	if strings.TrimSpace(bridgeName) == "" {
		return nil
	}
	if _, err := system.LookupExecutable("resolvectl"); err != nil {
		return nil
	}
	_, err := s.runner.Run(ctx, "resolvectl", "revert", bridgeName)
	return err
}

func (s *Server) fsckSnapshot(ctx context.Context, dmDev string) error {
	// Helper runs as root with -fy (auto-yes); without the prefix check
	// a compromised daemon could fsck arbitrary block devices like
	// /dev/sda1 and corrupt the host filesystem.
	if err := validateDMDevicePath(dmDev); err != nil {
		return err
	}
	if _, err := s.runner.Run(ctx, "e2fsck", "-fy", dmDev); err != nil {
		if code := system.ExitCode(err); code < 0 || code > 1 {
			return fmt.Errorf("fsck snapshot: %w", err)
		}
	}
	return nil
}

func (s *Server) writeExt4Files(ctx context.Context, imagePath string, files []Ext4Write) error {
	for _, file := range files {
		mode := os.FileMode(file.Mode)
		if mode == 0 {
			mode = 0o644
		}
		if err := system.WriteExt4FileOwned(ctx, s.runner, imagePath, file.GuestPath, mode, 0, 0, file.Data); err != nil {
			return err
		}
	}
	return nil
}

func (s *Server) resolveFirecrackerBinary(requested string) (string, error) {
	requested = strings.TrimSpace(requested)
	if requested == "" {
		requested = defaultFirecrackerBinaryName
	}
	cfg := fcproc.Config{FirecrackerBin: requested}
	resolved, err := fcproc.New(s.runner, cfg, s.logger).ResolveBinary()
	if err != nil {
		return "", err
	}
	if err := validateRootExecutable(resolved); err != nil {
		return "", err
	}
	return resolved, nil
}

func (s *Server) launchFirecracker(ctx context.Context, req FirecrackerLaunchRequest) (int, error) {
	systemLayout := paths.ResolveSystem()
	for _, path := range []string{req.SocketPath, req.VSockPath} {
		if err := s.validateManagedPath(path, systemLayout.RuntimeDir); err != nil {
			return 0, err
		}
	}
	for _, path := range []string{req.LogPath, req.MetricsPath, req.KernelImagePath} {
		if err := s.validateManagedPath(path, systemLayout.StateDir); err != nil {
			return 0, err
		}
	}
	if strings.TrimSpace(req.InitrdPath) != "" {
		if err := s.validateManagedPath(req.InitrdPath, systemLayout.StateDir); err != nil {
			return 0, err
		}
	}
	if err := validateTapName(req.TapDevice); err != nil {
		return 0, err
	}
	if err := validateRootExecutable(req.BinaryPath); err != nil {
		return 0, err
	}
	for _, drive := range req.Drives {
		if err := s.validateLaunchDrivePath(drive, systemLayout.StateDir); err != nil {
			return 0, err
		}
	}
	mgr := fcproc.New(s.runner, fcproc.Config{BridgeName: req.Network.BridgeName, BridgeIP: req.Network.BridgeIP, CIDR: req.Network.CIDR}, s.logger)
	mc, err := s.buildLaunchMachineConfig(ctx, req, systemLayout, mgr)
	if err != nil {
		return 0, err
	}
	// Pre-Start symlink: see localPrivilegedOps.LaunchFirecracker for
	// the AF_UNIX sun_path-length rationale.
	if err := s.exposeJailerSockets(req); err != nil {
		return 0, fmt.Errorf("expose jailer sockets: %w", err)
	}
	machine, err := firecracker.NewMachine(ctx, mc)
	if err != nil {
		return 0, err
	}
	if err := machine.Start(ctx); err != nil {
		if pid := mgr.ResolvePID(context.Background(), machine, mc.SocketPath); pid > 0 {
			_, _ = s.runner.Run(context.Background(), "kill", "-KILL", strconv.Itoa(pid))
		}
		return 0, err
	}
	if req.Jailer == nil {
		// Belt-and-suspenders only on the legacy direct-firecracker path;
		// the jailer drops to the configured uid before creating the
		// socket, so its perms are correct by construction.
		if err := mgr.EnsureSocketAccessFor(ctx, mc.SocketPath, "firecracker api socket", s.meta.OwnerUID, s.meta.OwnerGID); err != nil {
			return 0, err
		}
		if strings.TrimSpace(mc.VSockPath) != "" {
			if err := mgr.EnsureSocketAccessFor(ctx, mc.VSockPath, "firecracker vsock socket", s.meta.OwnerUID, s.meta.OwnerGID); err != nil {
				return 0, err
			}
		}
	}
	pid := mgr.ResolvePID(context.Background(), machine, mc.SocketPath)
	if pid <= 0 {
		return 0, errors.New("firecracker started but pid could not be resolved")
	}
	return pid, nil
}

// buildLaunchMachineConfig assembles the firecracker.MachineConfig used by
// launchFirecracker, performing the chroot staging when jailer is enabled.
// In the non-jailer case it's a straight field copy from the request.
//
// In the jailer case it:
//   - validates JailerLaunchOpts (binary executable, chroot under RuntimeDir,
//     uid/gid match the registered owner — the daemon can't ask the helper to
//     drop firecracker into an arbitrary uid)
//   - calls fcproc.PrepareJailerChroot to build the chroot tree
//   - rewrites SocketPath and VSockPath to host-visible chroot paths and
//     KernelImagePath/InitrdPath/Drives[].Path to chroot-internal names
func (s *Server) buildLaunchMachineConfig(ctx context.Context, req FirecrackerLaunchRequest, layout paths.Layout, mgr *fcproc.Manager) (firecracker.MachineConfig, error) {
	mc := firecracker.MachineConfig{
		BinaryPath:      req.BinaryPath,
		VMID:            req.VMID,
		SocketPath:      req.SocketPath,
		LogPath:         req.LogPath,
		MetricsPath:     req.MetricsPath,
		KernelImagePath: req.KernelImagePath,
		InitrdPath:      req.InitrdPath,
		KernelArgs:      req.KernelArgs,
		Drives:          req.Drives,
		TapDevice:       req.TapDevice,
		VSockPath:       req.VSockPath,
		VSockCID:        req.VSockCID,
		VCPUCount:       req.VCPUCount,
		MemoryMiB:       req.MemoryMiB,
		Logger:          s.logger,
	}
	if req.Jailer == nil {
		return mc, nil
	}
	if err := s.validateJailerOpts(*req.Jailer, layout); err != nil {
		return firecracker.MachineConfig{}, err
	}
	chrootRoot := firecracker.JailerChrootRoot(req.Jailer.ChrootBaseDir, req.VMID)
	driveSpecs := make([]fcproc.ChrootDriveSpec, 0, len(req.Drives))
	chrootDrives := make([]firecracker.DriveConfig, 0, len(req.Drives))
	for _, d := range req.Drives {
		name := chrootDriveName(d)
		driveSpecs = append(driveSpecs, fcproc.ChrootDriveSpec{ChrootName: name, HostPath: d.Path})
		chrootDrives = append(chrootDrives, firecracker.DriveConfig{
			ID:       d.ID,
			Path:     "/" + name,
			ReadOnly: d.ReadOnly,
			IsRoot:   d.IsRoot,
		})
	}
	wantVSock := strings.TrimSpace(req.VSockPath) != ""
	if err := mgr.PrepareJailerChroot(ctx, chrootRoot,
		req.Jailer.UID, req.Jailer.GID,
		req.BinaryPath,
		req.KernelImagePath, "vmlinux",
		req.InitrdPath, "initrd",
		driveSpecs, wantVSock,
	); err != nil {
		return firecracker.MachineConfig{}, fmt.Errorf("prepare jailer chroot: %w", err)
	}
	// See localPrivilegedOps.buildLaunchMachineConfig for why SocketPath
	// stays the short req path but VSockPath becomes chroot-internal.
	_ = chrootRoot
	if wantVSock {
		mc.VSockPath = firecracker.JailerVSockName
	}
	mc.KernelImagePath = "/vmlinux"
	if strings.TrimSpace(req.InitrdPath) != "" {
		mc.InitrdPath = "/initrd"
	} else {
		mc.InitrdPath = ""
	}
	mc.Drives = chrootDrives
	// LogPath stays set so buildProcessRunner's openLogFile captures firecracker
	// stderr via cmd.Stderr. buildConfig clears sdk.Config.LogPath for jailer
	// mode to avoid PUT /logger with a host path firecracker can't open.
	mc.MetricsPath = ""
	mc.Jailer = &firecracker.JailerOpts{
		Binary:        req.Jailer.Binary,
		ChrootBaseDir: req.Jailer.ChrootBaseDir,
		UID:           req.Jailer.UID,
		GID:           req.Jailer.GID,
	}
	return mc, nil
}

func (s *Server) validateJailerOpts(opts JailerLaunchOpts, layout paths.Layout) error {
	if err := validateRootExecutable(opts.Binary); err != nil {
		return fmt.Errorf("jailer binary: %w", err)
	}
	// Chroot base must live under StateDir so hard-links into the chroot
	// share a filesystem with the image cache (RuntimeDir is tmpfs and
	// would EXDEV on os.Link). RuntimeDir is also accepted because the
	// jailer is happy on tmpfs when the kernel/drives happen to colocate
	// (e.g. tests).
	if err := s.validateManagedPath(opts.ChrootBaseDir, layout.StateDir, layout.RuntimeDir); err != nil {
		return fmt.Errorf("jailer chroot base: %w", err)
	}
	if opts.UID != s.meta.OwnerUID || opts.GID != s.meta.OwnerGID {
		return fmt.Errorf("jailer uid/gid (%d:%d) must match registered owner (%d:%d)", opts.UID, opts.GID, s.meta.OwnerUID, s.meta.OwnerGID)
	}
	return nil
}

// exposeJailerSockets makes the chroot-internal sockets reachable at the
// host paths the daemon already references (sc.apiSock, vm.Runtime.VSockPath).
// AF_UNIX connect(2) follows symlinks, so a symlink keeps the rest of the
// daemon code unchanged. Computes both host targets from the chroot root and
// the chroot-internal name, so the API socket and the vsock socket stay in
// sync regardless of how the launch request laid them out.
func (s *Server) exposeJailerSockets(req FirecrackerLaunchRequest) error {
	if req.Jailer == nil {
		return nil
	}
	chrootRoot := firecracker.JailerChrootRoot(req.Jailer.ChrootBaseDir, req.VMID)
	hostAPI := filepath.Join(chrootRoot, strings.TrimPrefix(firecracker.JailerSocketName, "/"))
	if err := atomicSymlink(hostAPI, req.SocketPath); err != nil {
		return fmt.Errorf("api socket symlink: %w", err)
	}
	if strings.TrimSpace(req.VSockPath) != "" {
		hostVSock := filepath.Join(chrootRoot, strings.TrimPrefix(firecracker.JailerVSockName, "/"))
		if err := atomicSymlink(hostVSock, req.VSockPath); err != nil {
			return fmt.Errorf("vsock symlink: %w", err)
		}
	}
	return nil
}

func atomicSymlink(target, link string) error {
	if err := os.Remove(link); err != nil && !os.IsNotExist(err) {
		return err
	}
	return os.Symlink(target, link)
}

// chrootDriveName returns the bare filename a drive should appear as inside
// the chroot. We use the drive ID when present (rootfs, work, …) so the
// chroot listing is self-explanatory; falling back to the source's basename
// covers the unnamed case.
func chrootDriveName(d firecracker.DriveConfig) string {
	if id := strings.TrimSpace(d.ID); id != "" {
		return id
	}
	return filepath.Base(d.Path)
}

func (s *Server) validateLaunchDrivePath(drive firecracker.DriveConfig, stateDir string) error {
	if err := s.validateManagedPath(drive.Path, stateDir); err == nil {
		return nil
	}
	if drive.IsRoot {
		if err := validateDMDevicePath(drive.Path); err == nil {
			return nil
		}
	}
	return fmt.Errorf("path %q is outside banger-managed directories", drive.Path)
}

func (s *Server) ensureSocketAccess(ctx context.Context, socketPath, label string) error {
	return fcproc.New(s.runner, fcproc.Config{}, s.logger).EnsureSocketAccessFor(ctx, socketPath, label, s.meta.OwnerUID, s.meta.OwnerGID)
}

func (s *Server) validateManagedPath(path string, roots ...string) error {
	path = strings.TrimSpace(path)
	if path == "" {
		return errors.New("path is required")
	}
	if !filepath.IsAbs(path) {
		return fmt.Errorf("path %q must be absolute", path)
	}
	cleaned := filepath.Clean(path)
	for _, root := range roots {
		root = strings.TrimSpace(root)
		if root == "" {
			continue
		}
		root = filepath.Clean(root)
		if cleaned == root || strings.HasPrefix(cleaned, root+string(os.PathSeparator)) {
			return nil
		}
	}
	return fmt.Errorf("path %q is outside banger-managed directories", path)
}

// validateExt4ImagePath accepts a path that is either inside the
// banger StateDir (regular ext4 image files we manage) or a managed
// DM-snapshot device (/dev/mapper/fc-rootfs-*). Both shapes are
// legitimate inputs for the helper's debugfs/e2cp/e2rm RPCs; anything
// else would let a compromised daemon point those tools at arbitrary
// host files.
func (s *Server) validateExt4ImagePath(path string) error {
	if err := s.validateManagedPath(path, paths.ResolveSystem().StateDir); err == nil {
		return nil
	}
	if err := validateDMDevicePath(path); err == nil {
		return nil
	}
	return fmt.Errorf("path %q is not a banger-managed ext4 image", path)
}

// validateLoopDevicePath confirms path is `/dev/loopN` for some N≥0.
// dmsnap.Cleanup detaches loops via `losetup -d <path>`; without this
// a compromised daemon could ask the helper to detach an arbitrary
// device node.
func validateLoopDevicePath(path string) error {
	path = strings.TrimSpace(path)
	if path == "" {
		return errors.New("loop device path is required")
	}
	const prefix = "/dev/loop"
	if !strings.HasPrefix(path, prefix) {
		return fmt.Errorf("loop device %q must live under /dev/loop", path)
	}
	suffix := path[len(prefix):]
	if suffix == "" {
		return fmt.Errorf("loop device %q is missing its index", path)
	}
	for _, r := range suffix {
		if r < '0' || r > '9' {
			return fmt.Errorf("loop device %q has non-numeric suffix", path)
		}
	}
	return nil
}

// validateDMSnapshotHandles checks every non-empty field on a Handles
// passed to priv.cleanup_dm_snapshot. Empty fields are tolerated (the
// dmsnap layer treats them as "nothing to clean here") but anything
// set must look like a banger-managed object.
func validateDMSnapshotHandles(h dmsnap.Handles) error {
	if h.DMName != "" {
		if err := validateDMName(h.DMName); err != nil {
			return err
		}
	}
	if h.DMDev != "" {
		if err := validateDMDevicePath(h.DMDev); err != nil {
			return err
		}
	}
	if h.BaseLoop != "" {
		if err := validateLoopDevicePath(h.BaseLoop); err != nil {
			return err
		}
	}
	if h.COWLoop != "" {
		if err := validateLoopDevicePath(h.COWLoop); err != nil {
			return err
		}
	}
	return nil
}

// validateDMRemoveTarget covers the union accepted by `dmsetup remove`:
// either the bare DM name or the /dev/mapper/<name> path. Both shapes
// are produced by dmsnap.Cleanup; nothing else should reach the helper.
func validateDMRemoveTarget(target string) error {
	target = strings.TrimSpace(target)
	if target == "" {
		return errors.New("dm target is required")
	}
	if strings.HasPrefix(target, "/dev/mapper/") {
		return validateDMDevicePath(target)
	}
	return validateDMName(target)
}

// validateLinuxIfaceName mirrors the kernel's __dev_valid_name rules
// in a permissive subset: 1-15 chars, no whitespace, no slash, no
// colon, and not the special "." or "..". Used for bridge-name
// arguments to resolvectl. argv-style exec already prevents shell
// injection, but a compromised daemon could otherwise flap any
// system-managed link by passing its name here.
func validateLinuxIfaceName(name string) error {
	name = strings.TrimSpace(name)
	if name == "" {
		return errors.New("interface name is required")
	}
	if len(name) > 15 {
		return fmt.Errorf("interface %q exceeds 15 chars", name)
	}
	if name == "." || name == ".." {
		return fmt.Errorf("interface name %q is reserved", name)
	}
	for _, r := range name {
		if r <= ' ' || r == '/' || r == ':' || r == 0x7f {
			return fmt.Errorf("interface %q contains invalid char %q", name, r)
		}
	}
	return nil
}

// validateIPv4 confirms ip parses as an IPv4 address. The NAT helpers
// build /32 iptables rules from this string; non-v4 input would
// produce malformed rules at best and unexpected ones at worst.
func validateIPv4(ip string) error {
	ip = strings.TrimSpace(ip)
	if ip == "" {
		return errors.New("ipv4 address is required")
	}
	parsed := net.ParseIP(ip)
	if parsed == nil || parsed.To4() == nil {
		return fmt.Errorf("invalid ipv4 address %q", ip)
	}
	return nil
}

// validateResolverAddr confirms s parses as an IP address (v4 or v6).
// resolvectl accepts either; reject anything that doesn't parse so a
// compromised daemon can't wedge resolved with garbage input.
func validateResolverAddr(s string) error {
	s = strings.TrimSpace(s)
	if s == "" {
		return errors.New("resolver address is required")
	}
	if net.ParseIP(s) == nil {
		return fmt.Errorf("invalid resolver address %q", s)
	}
	return nil
}

func validateTapName(tapName string) error {
	tapName = strings.TrimSpace(tapName)
	if strings.HasPrefix(tapName, vmTapPrefix) || strings.HasPrefix(tapName, tapPoolPrefix) {
		return nil
	}
	return fmt.Errorf("tap %q is outside banger-managed naming", tapName)
}

func validateDMName(dmName string) error {
	dmName = strings.TrimSpace(dmName)
	if strings.HasPrefix(dmName, rootfsDMNamePrefix) {
		return nil
	}
	return fmt.Errorf("dm target %q is outside banger-managed naming", dmName)
}

func validateDMDevicePath(path string) error {
	path = strings.TrimSpace(path)
	if path == "" {
		return errors.New("dm device path is required")
	}
	if !filepath.IsAbs(path) {
		return fmt.Errorf("dm device path %q must be absolute", path)
	}
	cleaned := filepath.Clean(path)
	if filepath.Dir(cleaned) != "/dev/mapper" {
		return fmt.Errorf("dm device path %q is outside /dev/mapper", path)
	}
	return validateDMName(filepath.Base(cleaned))
}

// validateNotSymlink rejects paths whose final component is a symlink.
// validateManagedPath does textual prefix matching only; pairing it
// with an Lstat check stops a daemon-uid attacker from planting a
// symlink at a managed path and using helper RPCs that operate on
// that path (chown/chmod sockets, umount/rm chroot trees) to reach
// arbitrary host objects. There is a small TOCTOU window between
// this check and the syscall that follows; for sockets the
// fcproc-level O_PATH|O_NOFOLLOW open closes that window, and for
// the chroot cleanup the umount step is bracketed by a findmnt
// guard inside fcproc.CleanupJailerChroot.
func validateNotSymlink(path string) error {
	info, err := os.Lstat(path)
	if err != nil {
		return fmt.Errorf("inspect %s: %w", path, err)
	}
	if info.Mode()&os.ModeSymlink != 0 {
		return fmt.Errorf("path %q must not be a symlink", path)
	}
	return nil
}

// validateFirecrackerPID confirms pid refers to a running process whose
// /proc/<pid>/cmdline mentions "firecracker". Both jailer and direct
// firecracker launches keep the binary name in cmdline, so substring
// match catches both. PID reuse is theoretically racey but the kill
// follows immediately, so the window is too narrow to weaponise.
func validateFirecrackerPID(pid int) error {
	if pid <= 0 {
		return fmt.Errorf("pid %d is invalid", pid)
	}
	data, err := os.ReadFile(filepath.Join("/proc", strconv.Itoa(pid), "cmdline"))
	if err != nil {
		return fmt.Errorf("inspect pid %d: %w", pid, err)
	}
	cmdline := strings.ReplaceAll(string(data), "\x00", " ")
	if !strings.Contains(cmdline, "firecracker") {
		return fmt.Errorf("pid %d is not a banger-managed firecracker process", pid)
	}
	return nil
}

// validateRootExecutable opens the path with O_PATH|O_NOFOLLOW and re-checks
// every constraint via Fstat on the resulting fd. Going through O_PATH (rather
// than the previous os.Stat) gives two improvements:
//
//   - O_NOFOLLOW rejects path-level symlinks outright, so a swap of the
//     binary's path component to point at an attacker-controlled target is
//     caught here rather than slipping through to the SDK.
//   - Fstat reads metadata from the inode the kernel just resolved, narrowing
//     the TOCTOU window between validation and exec to the time it takes the
//     SDK to fork+exec — sub-millisecond on a healthy host. The window can't
//     be fully closed without re-pointing the SDK at /proc/self/fd/N (the
//     known-good idiom), which would require keeping the fd alive across
//     fork+exec; we accept the tiny residual window for the simpler shape.
func validateRootExecutable(path string) error {
	fd, err := unix.Open(path, unix.O_PATH|unix.O_NOFOLLOW|unix.O_CLOEXEC, 0)
	if err != nil {
		return fmt.Errorf("open executable %q: %w", path, err)
	}
	defer unix.Close(fd)
	var st unix.Stat_t
	if err := unix.Fstat(fd, &st); err != nil {
		return fmt.Errorf("fstat executable %q: %w", path, err)
	}
	if st.Mode&unix.S_IFMT != unix.S_IFREG {
		return fmt.Errorf("firecracker binary %q is not a regular file", path)
	}
	if st.Mode&0o111 == 0 {
		return fmt.Errorf("firecracker binary %q is not executable", path)
	}
	if st.Mode&0o022 != 0 {
		return fmt.Errorf("firecracker binary %q must not be group/world writable", path)
	}
	if st.Uid != 0 {
		return fmt.Errorf("firecracker binary %q must be root-owned in system mode", path)
	}
	return nil
}

func marshalResultOrError(v any, err error) rpc.Response {
	if err != nil {
		return rpc.NewError("operation_failed", err.Error())
	}
	resp, marshalErr := rpc.NewResult(v)
	if marshalErr != nil {
		return rpc.NewError("marshal_failed", marshalErr.Error())
	}
	return resp
}