Stop the UI before a silent Windows update and suppress the installer reboot

client/internal/updater/installer/doc.go

@@ -37,23 +37,25 @@
 // Updater Process (Setup):
 //
 //  1. Receives parameters from service via command-line arguments
-//  2. Runs installer with appropriate silent/quiet flags:
+//  2. Terminates the UI so the installer does not have to replace a locked image
+//     file, which would otherwise leave the install needing a reboot
+//  3. Runs installer with appropriate silent/quiet flags:
 //     - Windows EXE: installer.exe /S
-//     - Windows MSI: msiexec.exe /i installer.msi /quiet /qn /l*v msi.log
+//     - Windows MSI: msiexec.exe /i installer.msi /qn /norestart REBOOT=ReallySuppress /l*v msi.log
 //     - macOS PKG: installer -pkg installer.pkg -target /
 //     - macOS Homebrew: brew upgrade netbirdio/tap/netbird
-//  3. Installer terminates daemon and UI processes
-//  4. Installer replaces binaries with new version
-//  5. Updater waits for installer to complete
-//  6. Updater restarts daemon:
+//  4. Installer terminates the daemon
+//  5. Installer replaces binaries with new version
+//  6. Updater waits for installer to complete
+//  7. Updater restarts daemon:
 //     - Windows: netbird.exe service start
 //     - macOS/Linux: netbird service start
-//  7. Updater restarts UI:
+//  8. Updater restarts UI:
 //     - Windows: Launches netbird-ui.exe as active console user using CreateProcessAsUser
 //     - macOS: Uses launchctl asuser to launch NetBird.app for console user
 //     - Linux: Not implemented (UI typically auto-starts)
-//  8. Updater writes result.json with success/error status
-//  9. Updater process exits
+//  9. Updater writes result.json with success/error status
+//  10. Updater process exits
 //
 // # Result Communication
 //

client/internal/updater/installer/installer_run_windows.go

@@ -2,6 +2,7 @@ package installer
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"os"
 	"os/exec"
@@ -22,6 +23,12 @@ const (
 
 	msiLogFile = "msi.log"
 
+	// ERROR_SUCCESS_REBOOT_REQUIRED and ERROR_SUCCESS_REBOOT_INITIATED
+	msiRebootRequired  = 3010
+	msiRebootInitiated = 1641
+
+	processExitWait = 10 * time.Second
+
 	msiDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.msi"
 	exeDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.exe"
 )
@@ -75,6 +82,14 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 		return
 	}
 
+	// The UI holds an open handle on its own image. Left running, Restart Manager
+	// cannot shut it down (msiexec runs as LocalSystem here, the UI as the
+	// interactive user), so the MSI falls back to replacing the file on reboot and
+	// marks the install as restart-required. The deferred close-application action
+	// in the package runs too late to prevent that, it happens after
+	// InstallValidate has already registered the file as in use.
+	killUI()
+
 	var cmd *exec.Cmd
 	switch installerType {
 	case TypeExe:
@@ -84,7 +99,9 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 		installerDir := filepath.Dir(installerFile)
 		logPath := filepath.Join(installerDir, msiLogFile)
 		log.Infof("run msi installer: %s", installerFile)
-		cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/quiet", "/qn", "/l*v", logPath)
+		// REBOOT=ReallySuppress: a silent install has no way to ask, so without it
+		// msiexec reboots the machine on its own if it decides one is needed.
+		cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/qn", "/norestart", "REBOOT=ReallySuppress", "/l*v", logPath)
 	}
 
 	cmd.Dir = filepath.Dir(installerFile)
@@ -95,9 +112,13 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 	}
 
 	log.Infof("installer started with PID %d", cmd.Process.Pid)
-	if resultErr = cmd.Wait(); resultErr != nil {
-		log.Errorf("installer process finished with error: %v", resultErr)
-		return
+	if err := cmd.Wait(); err != nil {
+		if !isRebootPending(err) {
+			resultErr = err
+			log.Errorf("installer process finished with error: %v", err)
+			return
+		}
+		log.Warnf("installer completed but reported a pending reboot, some files will be replaced on the next restart")
 	}
 
 	return nil
@@ -201,6 +222,101 @@ func (u *Installer) startUIAsUser(daemonFolder string) error {
 	return nil
 }
 
+// isRebootPending reports whether the installer exit code means it succeeded but
+// left work for the next restart. The reboot itself is suppressed, so this is not
+// a failure.
+func isRebootPending(err error) bool {
+	var exitErr *exec.ExitError
+	if !errors.As(err, &exitErr) {
+		return false
+	}
+
+	switch exitErr.ExitCode() {
+	case msiRebootRequired, msiRebootInitiated:
+		return true
+	default:
+		return false
+	}
+}
+
+// killUI terminates any running netbird-ui process. Setup starts the UI again
+// once the installer is done.
+func killUI() {
+	pids, err := processIDsByName(uiName)
+	if err != nil {
+		log.Warnf("failed to look up %s processes: %v", uiName, err)
+		return
+	}
+
+	for _, pid := range pids {
+		if err := terminateProcess(pid); err != nil {
+			log.Warnf("failed to terminate %s (PID %d): %v", uiName, pid, err)
+			continue
+		}
+		log.Infof("terminated %s (PID %d)", uiName, pid)
+	}
+}
+
+func processIDsByName(name string) ([]uint32, error) {
+	snapshot, err := windows.CreateToolhelp32Snapshot(windows.TH32CS_SNAPPROCESS, 0)
+	if err != nil {
+		return nil, fmt.Errorf("create process snapshot: %w", err)
+	}
+	defer func() {
+		if err := windows.CloseHandle(snapshot); err != nil {
+			log.Warnf("failed to close process snapshot: %v", err)
+		}
+	}()
+
+	var entry windows.ProcessEntry32
+	entry.Size = uint32(unsafe.Sizeof(entry))
+
+	var pids []uint32
+	for err = windows.Process32First(snapshot, &entry); err == nil; err = windows.Process32Next(snapshot, &entry) {
+		if strings.EqualFold(windows.UTF16ToString(entry.ExeFile[:]), name) {
+			pids = append(pids, entry.ProcessID)
+		}
+	}
+	if !errors.Is(err, windows.ERROR_NO_MORE_FILES) {
+		return nil, fmt.Errorf("enumerate processes: %w", err)
+	}
+
+	return pids, nil
+}
+
+func terminateProcess(pid uint32) error {
+	handle, err := windows.OpenProcess(windows.PROCESS_TERMINATE|windows.SYNCHRONIZE, false, pid)
+	if err != nil {
+		// The process may have exited between enumeration and now.
+		if errors.Is(err, windows.ERROR_INVALID_PARAMETER) {
+			return nil
+		}
+		return fmt.Errorf("open process: %w", err)
+	}
+	defer func() {
+		if err := windows.CloseHandle(handle); err != nil {
+			log.Warnf("failed to close process handle: %v", err)
+		}
+	}()
+
+	if err := windows.TerminateProcess(handle, 0); err != nil {
+		return fmt.Errorf("terminate process: %w", err)
+	}
+
+	// Wait for the handle to signal so the image file is released before the
+	// installer tries to overwrite it. A timeout is reported through the returned
+	// event, not through err, which stays nil unless the wait itself failed.
+	event, err := windows.WaitForSingleObject(handle, uint32(processExitWait.Milliseconds()))
+	if err != nil {
+		return fmt.Errorf("wait for process exit: %w", err)
+	}
+	if event != windows.WAIT_OBJECT_0 {
+		return fmt.Errorf("wait for process exit: unexpected wait result %#x", event)
+	}
+
+	return nil
+}
+
 func urlWithVersionArch(it Type, version string) string {
 	var url string
 	if it == TypeExe {

client/internal/updater/installer/installer_run_windows_test.go

@@ -0,0 +1,108 @@
+package installer
+
+import (
+	"errors"
+	"os/exec"
+	"slices"
+	"strconv"
+	"testing"
+)
+
+// exitErrorWithCode returns a real *exec.ExitError carrying the given exit code.
+func exitErrorWithCode(t *testing.T, code int) error {
+	t.Helper()
+
+	err := exec.Command("cmd.exe", "/c", "exit "+strconv.Itoa(code)).Run()
+	if err == nil {
+		t.Fatalf("expected a non-zero exit for code %d", code)
+	}
+	return err
+}
+
+func TestIsRebootPending(t *testing.T) {
+	tests := []struct {
+		name string
+		code int
+		want bool
+	}{
+		{name: "reboot required", code: msiRebootRequired, want: true},
+		{name: "reboot initiated", code: msiRebootInitiated, want: true},
+		{name: "generic failure", code: 1603, want: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isRebootPending(exitErrorWithCode(t, tt.code)); got != tt.want {
+				t.Errorf("isRebootPending(exit %d) = %v, want %v", tt.code, got, tt.want)
+			}
+		})
+	}
+}
+
+// TestProcessIDsByNameAndTerminate spawns a long-running system process, finds it
+// by name and terminates it, covering the path the updater uses to release the UI
+// image file before the installer replaces it.
+func TestProcessIDsByNameAndTerminate(t *testing.T) {
+	cmd := exec.Command("ping.exe", "-n", "60", "127.0.0.1")
+	if err := cmd.Start(); err != nil {
+		t.Fatalf("start ping: %v", err)
+	}
+
+	pid := uint32(cmd.Process.Pid)
+	killed := false
+	t.Cleanup(func() {
+		if !killed {
+			_ = cmd.Process.Kill()
+		}
+		_ = cmd.Wait()
+	})
+
+	// Name matching must be case-insensitive: the snapshot reports PING.EXE.
+	pids, err := processIDsByName("ping.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName: %v", err)
+	}
+
+	if !slices.Contains(pids, pid) {
+		t.Fatalf("PID %d not among the ping.exe processes found: %v", pid, pids)
+	}
+
+	if err := terminateProcess(pid); err != nil {
+		t.Fatalf("terminateProcess: %v", err)
+	}
+	killed = true
+
+	// terminateProcess only returns once the handle has signalled, so the process
+	// is already gone and Wait must not block. It exits with the code passed to
+	// TerminateProcess, which is 0, so Wait reports no error.
+	if err := cmd.Wait(); err != nil {
+		t.Fatalf("wait for terminated ping: %v", err)
+	}
+	if !cmd.ProcessState.Exited() {
+		t.Error("process did not exit after terminateProcess")
+	}
+
+	remaining, err := processIDsByName("ping.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName after terminate: %v", err)
+	}
+	if slices.Contains(remaining, pid) {
+		t.Errorf("PID %d still listed after terminateProcess", pid)
+	}
+}
+
+func TestProcessIDsByNameNoMatch(t *testing.T) {
+	pids, err := processIDsByName("netbird-nonexistent-process.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName: %v", err)
+	}
+	if len(pids) != 0 {
+		t.Errorf("expected no matches, got %v", pids)
+	}
+}
+
+func TestIsRebootPendingNonExitError(t *testing.T) {
+	if isRebootPending(errors.New("start installer: file not found")) {
+		t.Error("a non-exit error must not be treated as a pending reboot")
+	}
+}