Warp/server/internal/setup/server.go

// Package setup wires the components together into a running server: it
// opens storage, loads the signing key, builds the runtime-settings service
// and the HTTP stack, and owns the graceful shutdown.
package setup

import (
	"context"
	"errors"
	"fmt"
	"log/slog"
	"net"
	"net/http"
	"sync/atomic"
	"time"

	"github.com/dariuszjaniak/warp/server/internal/buildinfo"
	"github.com/dariuszjaniak/warp/server/internal/config"
	"github.com/dariuszjaniak/warp/server/internal/federation"
	"github.com/dariuszjaniak/warp/server/internal/httputil"
	"github.com/dariuszjaniak/warp/server/internal/matrix/signing"
	"github.com/dariuszjaniak/warp/server/internal/metrics"
	"github.com/dariuszjaniak/warp/server/internal/settings"
	"github.com/dariuszjaniak/warp/server/internal/storage"
	_ "github.com/dariuszjaniak/warp/server/internal/storage/drivers" // link in the storage drivers
)

// Server is a configured, not yet listening homeserver.
type Server struct {
	cfg *config.Config
	log *slog.Logger

	db         storage.Database
	settings   *settings.Service
	metrics    *metrics.Registry
	federation *federation.Gate
	signingKey *signing.KeyPair

	handler http.Handler

	// addr is the address Run is listening on; empty until then.
	addr atomic.Pointer[string]

	// ownsDB is false when the caller supplied the database and will close
	// it itself.
	ownsDB bool
}

// Options are the knobs tests and commands need beyond the config file.
type Options struct {
	// Logger receives everything the server logs.
	Logger *slog.Logger

	// Database, when set, is used instead of opening one from the config.
	// Tests pass an in-memory SQLite database this way.
	Database storage.Database

	// SkipSigningKey starts the server without loading the signing key.
	// Only tests and `warp migrate` use it: a real server must be able to
	// sign.
	SkipSigningKey bool
}

// New builds the server: storage, migrations, settings, routes. It does not
// listen; call Run for that.
func New(ctx context.Context, cfg *config.Config, opts Options) (*Server, error) {
	log := opts.Logger
	if log == nil {
		log = slog.Default()
	}

	s := &Server{cfg: cfg, log: log, metrics: metrics.NewRegistry()}

	if opts.Database != nil {
		s.db = opts.Database
	} else {
		db, err := storage.Open(ctx, storage.Config{
			Driver:           cfg.Database.Driver,
			ConnectionString: cfg.Database.ConnectionString,
			MaxOpenConns:     cfg.Database.MaxOpenConns,
			MaxIdleConns:     cfg.Database.MaxIdleConns,
			ConnMaxLifetime:  cfg.Database.ConnMaxLifetime,
		}, log)
		if err != nil {
			return nil, err
		}
		s.db, s.ownsDB = db, true
	}

	if err := s.prepareSchema(ctx); err != nil {
		_ = s.closeDB()
		return nil, err
	}

	if !opts.SkipSigningKey {
		key, err := signing.Load(cfg.Global.PrivateKeyPath)
		if err != nil {
			_ = s.closeDB()
			return nil, fmt.Errorf("%w\nrun `warp generate-keys --config <file>` to create one", err)
		}
		s.signingKey = key
		log.Info("loaded signing key", "key_id", key.KeyID(), "path", cfg.Global.PrivateKeyPath)
	}

	settingsService, err := settings.New(ctx, s.db.Settings(), settings.Defaults{
		FederationEnabled:              cfg.Federation.Enabled,
		FederationAllowRuntimeToggle:   cfg.Federation.AllowRuntimeToggle,
		RegistrationEnabled:            cfg.Registration.Enabled,
		RegistrationAllowRuntimeToggle: cfg.Registration.AllowRuntimeToggle,
	}, log)
	if err != nil {
		_ = s.closeDB()
		return nil, err
	}
	s.settings = settingsService

	s.federation = federation.NewGate(
		settingsService.FederationEnabled,
		federation.NewPolicy(cfg.Federation.Allowlist, cfg.Federation.Denylist),
	)
	// Phase 5 replaces this with starting and stopping the federation
	// module; for now it is the audit trail for a runtime toggle.
	settingsService.Subscribe(func(snap settings.Snapshot) {
		log.Info("federation switch applied", "enabled", snap.FederationEnabled)
	})

	s.handler = httputil.Chain(s.routes(),
		httputil.Recoverer,
		httputil.RequestLogger(log),
		s.metrics.InFlight(),
		httputil.CORS(httputil.CORSOptions{AllowedOrigins: cfg.ClientAPI.CORSAllowedOrigins}),
	)
	return s, nil
}

// prepareSchema migrates the database, or refuses to start when migrations
// are pending and auto-migration is off.
func (s *Server) prepareSchema(ctx context.Context) error {
	if s.cfg.Database.AutoMigrate {
		if err := s.db.Migrate(ctx); err != nil {
			return fmt.Errorf("migrate database: %w", err)
		}
		return nil
	}
	pending, err := s.db.PendingMigrations(ctx)
	if err != nil {
		return fmt.Errorf("check migrations: %w", err)
	}
	if len(pending) > 0 {
		return fmt.Errorf("database has %d pending migration(s): %v; run `warp migrate`", len(pending), pending)
	}
	return nil
}

// Addr reports the address Run is listening on, or "" before it starts.
// Tests and `warp serve` on port 0 use it to find the chosen port.
func (s *Server) Addr() string {
	if p := s.addr.Load(); p != nil {
		return *p
	}
	return ""
}

// Handler exposes the fully wrapped HTTP handler, for tests.
func (s *Server) Handler() http.Handler { return s.handler }

// Settings exposes the runtime-settings service; the admin API in Phase 1
// is its first user.
func (s *Server) Settings() *settings.Service { return s.settings }

// Database exposes the storage handle.
func (s *Server) Database() storage.Database { return s.db }

// SigningKey returns the server signing key, or nil when it was skipped.
func (s *Server) SigningKey() *signing.KeyPair { return s.signingKey }

// Run listens and serves until ctx is cancelled, then shuts down
// gracefully: it stops accepting connections and gives in-flight requests
// up to listen.shutdown_timeout to finish.
func (s *Server) Run(ctx context.Context) error {
	listener, err := net.Listen("tcp", s.cfg.Listen.Address)
	if err != nil {
		return fmt.Errorf("listen on %s: %w", s.cfg.Listen.Address, err)
	}

	addr := listener.Addr().String()
	s.addr.Store(&addr)
	defer s.addr.Store(nil)

	httpServer := &http.Server{
		Handler:           s.handler,
		ReadHeaderTimeout: s.cfg.Listen.ReadHeaderTimeout,
		ReadTimeout:       s.cfg.Listen.ReadTimeout,
		WriteTimeout:      s.cfg.Listen.WriteTimeout,
		IdleTimeout:       s.cfg.Listen.IdleTimeout,
		MaxHeaderBytes:    s.cfg.Listen.MaxHeaderBytes,
		ErrorLog:          slog.NewLogLogger(s.log.Handler(), slog.LevelDebug),
		BaseContext:       func(net.Listener) context.Context { return ctx },
	}

	s.log.Info("warp is listening",
		"address", addr,
		"server_name", s.cfg.Global.ServerName,
		"version", buildinfo.String(),
		"database", s.db.Driver(),
		"federation", s.settings.FederationEnabled(),
		"registration", s.settings.RegistrationEnabled(),
	)

	errCh := make(chan error, 1)
	go func() {
		err := httpServer.Serve(listener)
		if errors.Is(err, http.ErrServerClosed) {
			err = nil
		}
		errCh <- err
	}()

	select {
	case err := <-errCh:
		return err
	case <-ctx.Done():
	}

	s.log.Info("shutting down", "timeout", s.cfg.Listen.ShutdownTimeout)
	shutdownCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), s.cfg.Listen.ShutdownTimeout)
	defer cancel()

	if err := httpServer.Shutdown(shutdownCtx); err != nil {
		s.log.Warn("graceful shutdown timed out; closing connections", "error", err)
		_ = httpServer.Close()
	}
	// Serve has returned by now; surface anything it reported.
	if err := <-errCh; err != nil {
		return err
	}
	s.log.Info("stopped")
	return nil
}

// Close releases the resources New acquired.
func (s *Server) Close() error {
	return s.closeDB()
}

func (s *Server) closeDB() error {
	if s.db == nil || !s.ownsDB {
		return nil
	}
	err := s.db.Close()
	s.db = nil
	return err
}

// contextWithTimeout is a thin wrapper so handlers do not import context
// just for a deadline.
func contextWithTimeout(ctx context.Context, d time.Duration) (context.Context, context.CancelFunc) {
	return context.WithTimeout(ctx, d)
}