smallwebwaf/internal/proxy/proxy.go

// Package proxy passes each request to the app and the app's answer back,
// unchanged, within the size and time limits, and writes one request log
// line for each request.
package proxy

import (
	"io"
	"log"
	"log/slog"
	"net/http"
	"strings"
	"time"

	"sneak.berlin/go/smallwebwaf/internal/bans"
	"sneak.berlin/go/smallwebwaf/internal/config"
	"sneak.berlin/go/smallwebwaf/internal/lookup"
	"sneak.berlin/go/smallwebwaf/internal/metrics"
	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
	"sneak.berlin/go/smallwebwaf/internal/requestlog"
)

// How smallwebwaf keeps connections to the app open between requests.
const (
	appIdleConns       = 100
	appIdleConnTimeout = 90 * time.Second
)

// adminPrefix starts the path of every request for smallwebwaf itself,
// which never reaches the app.
const adminPrefix = "/_smallwebwaf/"

// HealthPath is smallwebwaf's health endpoint, which the container's
// health check asks.
const HealthPath = "/_smallwebwaf/healthz"

// MetricsPath is where the metrics are, for a request that carries
// SWWAF_METRICS_TOKEN.
const MetricsPath = "/_smallwebwaf/metrics"

// Params are what New needs.
type Params struct {
	Config *config.Config
	// RequestLog receives one JSON line per request.
	RequestLog io.Writer
	// ProcessLog receives the process's own messages.
	ProcessLog *slog.Logger
	// GeoJSURL is where clients' countries are looked up, normally
	// lookup.URL. GeoJS is asked only while a country list is set.
	GeoJSURL string
	// Now tells the time by which requests are counted for the rate
	// limits, bans are made and run out, and GeoJS's answers are kept,
	// normally time.Now in UTC, the time the state files give.
	Now func() time.Time
}

// Server is the server smallwebwaf runs, with the parts of the proxy
// whose state the state files keep, and the metrics.
type Server struct {
	*http.Server

	Ledger  *bans.Ledger
	Limiter *ratelimit.Limiter
	GeoJS   *lookup.GeoJS
	Metrics *metrics.Metrics
}

// New returns the server smallwebwaf runs: each request it reads passes
// through the proxy. Go's server itself refuses a request line and
// headers over SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES, with 431, closes a
// connection idle for SWWAF_CLIENT_IDLE_TIMEOUT, and applies
// SWWAF_CLIENT_REQUEST_TIMEOUT while the headers arrive; the proxy
// applies the timeouts and size limits from then on.
func New(params Params) *Server {
	errorLog := slog.NewLogLogger(params.ProcessLog.Handler(), slog.LevelWarn)
	m := metrics.New(params.Config.MetricsTopN)
	h := &handler{
		config:     params.Config,
		requestLog: params.RequestLog,
		processLog: params.ProcessLog,
		errorLog:   errorLog,
		transport:  newTransport(),
		now:        params.Now,
		metrics:    m,
		limiter: ratelimit.New(ratelimit.Limits{
			PerMinute: params.Config.RateLimitPerMinute,
			PerHour:   params.Config.RateLimitPerHour,
			PerDay:    params.Config.RateLimitPerDay,
		}),
		ledger: bans.New(bans.Rules{
			LimitBanDuration:     params.Config.LimitBanDuration,
			LimitBanRepeatWindow: params.Config.LimitBanRepeatWindow,
			MaxBanDuration:       params.Config.MaxBanDuration,
			MaxBans:              params.Config.MaxBans,
		}),
		geojs: lookup.New(lookup.Params{
			URL:        params.GeoJSURL,
			Now:        params.Now,
			ProcessLog: params.ProcessLog,
			Metrics:    m,
		}),
	}
	m.AddBansAndClients(h.ledger, h.limiter, params.Now)

	return &Server{
		Server: &http.Server{
			Addr:              params.Config.ListenAddr,
			Handler:           h,
			ReadHeaderTimeout: params.Config.ClientRequestTimeout,
			// Off is an IdleTimeout of 0, which Go's server replaces with
			// ReadTimeout: no limit, as long as ReadTimeout stays unset.
			IdleTimeout: params.Config.ClientIdleTimeout,
			// Go's server reads 4 KiB past MaxHeaderBytes before it
			// refuses, so the limit a client meets is the setting.
			MaxHeaderBytes: int(params.Config.ClientRequestHeaderMaxBytes - 4<<10),
			ErrorLog:       errorLog,
		},
		Ledger:  h.ledger,
		Limiter: h.limiter,
		GeoJS:   h.geojs,
		Metrics: m,
	}
}

// handler is the proxy. It holds what every request shares; what belongs
// to one request is in a request.
type handler struct {
	config     *config.Config
	requestLog io.Writer
	processLog *slog.Logger
	errorLog   *log.Logger
	transport  http.RoundTripper
	now        func() time.Time
	metrics    *metrics.Metrics
	limiter    *ratelimit.Limiter
	ledger     *bans.Ledger
	geojs      *lookup.GeoJS
}

// newTransport returns what carries requests to the app. It never goes
// through a proxy named in the environment, and leaves the app's answers
// compressed or not as the app sent them.
func newTransport() *http.Transport {
	return &http.Transport{
		MaxIdleConns:        appIdleConns,
		MaxIdleConnsPerHost: appIdleConns,
		IdleConnTimeout:     appIdleConnTimeout,
		DisableCompression:  true,
	}
}

// ServeHTTP handles one request: it works out the client, runs the
// checks, passes the request to the app and the answer back within the
// limits, or answers it itself if it is for smallwebwaf, and writes the
// request's log line.
func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
	rq := h.newRequest(w, r)
	defer rq.finish()

	// The health endpoint is answered at once, before any check, so that
	// a health checker is never refused. It does not ask the app.
	if r.Method == http.MethodGet && r.URL.Path == HealthPath {
		rq.line.Action = requestlog.ActionAdmin
		_, _ = io.WriteString(rq.out, "ok\n")

		return
	}

	// Once the request has ended, before its log line is written.
	defer rq.addToHistory()

	refused := rq.check(r.Context())
	if refused != nil {
		rq.answer(*refused)

		return
	}

	// A request for smallwebwaf itself is answered where another would be
	// passed to the app, so that it goes through every check first.
	if strings.HasPrefix(r.URL.Path, adminPrefix) {
		rq.answerAdmin()

		return
	}

	rq.forward(r.Context())
}