servewaf answers rproxy's question about each request and takes its report (closes #170)

`smallwebwaf servewaf` runs today's checks on the visitor's request each
question carries, answers rproxy, and passes nothing to an app. rproxy reports
every request servewaf answered. A report counts an allowed request's bytes and
writes servewaf's second log line. The table holds a copy of what a report
needs, never the request, so a report cannot reach a request being handled.

Judgement call: a question's body is read before any check; over 64 KiB gets 400.
Judgement call: a report's bytes and durations have ceilings, so they cannot overflow.
Judgement call: a `close` disposition for SWWAF_BAN_RESPONSE=close.

Model: opus-5-5

internal/alerts/alerts.go

@@ -150,13 +150,16 @@ type Params struct {
 
 // Alert is one alert, as the webhook is sent it and alerts.json holds it,
 // with the fields of "The JSON object" in docs/alerts.md. ASN, ASName and
-// Country are, for a ban, the client's as the ban's notes give them.
+// Country are, for a ban, the client's as the ban's notes give them. Host is
+// the site of the request that raised the alert, while one servewaf serves
+// many sites, and "" otherwise.
 //
 //nolint:tagliatelle // docs/alerts.md names the alert's fields in snake_case
 type Alert struct {
 	Instance string       `json:"instance"`
 	Time     time.Time    `json:"time"`
 	Event    string       `json:"event"`
+	Host     string       `json:"host,omitempty"`
 	Client   netip.Addr   `json:"client"`
 	Netblock netip.Prefix `json:"netblock"`
 	ASN      string       `json:"asn"`
@@ -899,12 +902,16 @@ func title(alert *Alert) string {
 }
 
 // text returns the text of alert in Slack and ntfy: its reason, then a
-// line for each of its client, netblock and country, the file, source,
-// error and mode its detail gives, and its suppressed repeats, that it
-// has.
+// line for each of its host, client, netblock and country, the file,
+// source, error and mode its detail gives, and its suppressed repeats, that
+// it has.
 func text(alert *Alert) string {
 	lines := []string{alert.Reason}
 
+	if alert.Host != "" {
+		lines = append(lines, "host: "+alert.Host)
+	}
+
 	if alert.Client.IsValid() {
 		lines = append(lines, "client: "+alert.Client.String())
 	}

internal/alerts/alerts_test.go

@@ -1284,9 +1284,11 @@ func anAlertForEachEvent() []eventMessage {
 				Event: alerts.EventWAFBlock, Client: netip.MustParseAddr("192.0.2.1"),
 				Netblock: netip.MustParsePrefix("192.0.2.1/32"),
 				Reason:   "refused by the Core Rule Set",
+				Host:     "app.example",
 			},
 			"fsn1app1/gitea: waf_block", "default shield",
-			"refused by the Core Rule Set\nclient: 192.0.2.1\nnetblock: 192.0.2.1/32",
+			"refused by the Core Rule Set\nhost: app.example\nclient: 192.0.2.1\n" +
+				"netblock: 192.0.2.1/32",
 		},
 		{
 			alerts.Alert{

internal/anomaly/anomaly.go

@@ -103,6 +103,8 @@ type Counter struct {
 
 // Request is a request that has ended, as the counters count it.
 type Request struct {
+	// Host is the site the alert names, "" for none.
+	Host string
 	// Client is the client's address, and ClientGroup the client it is
 	// counted as: its IPv4 address, or the IPv6 netblock of
 	// SWWAF_IPV6_GROUP_PREFIX its address is in.
@@ -396,6 +398,7 @@ func alertFor(r Request, k key, o overThreshold) alerts.Alert {
 
 	return alerts.Alert{
 		Event:    alerts.EventAnomaly,
+		Host:     r.Host,
 		Client:   r.Client,
 		Netblock: k.netblock,
 		ASN:      r.ASN,

internal/metrics/metrics.go

@@ -403,28 +403,21 @@ func (m *Metrics) RequestEnded(
 	line *requestlog.Line, limit string, duration, upstreamDuration time.Duration,
 ) {
 	m.inFlight.Dec()
+	m.count(line, limit, duration, upstreamDuration)
+}
 
-	class := statusClass(line.Status)
-	m.requests.WithLabelValues(class, line.Action).Inc()
-	m.requestBytes.WithLabelValues(class, line.Action).Add(float64(line.RequestBytes))
-	m.responseBytes.WithLabelValues(class, line.Action).Add(float64(line.ResponseBytes))
-	m.requestDuration.Observe(duration.Seconds())
+// RequestAllowed counts a question of rproxy's, answered allow, as no longer
+// under way. RequestReported counts the request it was about.
+func (m *Metrics) RequestAllowed() {
+	m.inFlight.Dec()
+}
 
-	if upstreamDuration > 0 {
-		m.upstreamDuration.Observe(upstreamDuration.Seconds())
-	}
-
-	if limit != "" {
-		m.sizeAndTimeLimitHits.WithLabelValues(limit).Inc()
-	}
-
-	if line.Country != "" {
-		m.countries.add(line.Country, line)
-	}
-
-	if line.ASN != "" {
-		m.asns.add(line.ASN, line)
-	}
+// RequestReported counts a request rproxy passed to the app, as RequestEnded
+// does, from what its report says, which line holds.
+func (m *Metrics) RequestReported(
+	line *requestlog.Line, duration, upstreamDuration time.Duration,
+) {
+	m.count(line, "", duration, upstreamDuration)
 }
 
 // LimitHit counts a request that broke a rate limit, a byte limit or the
@@ -493,6 +486,33 @@ func (m *Metrics) StateFileEditSetAside(name string) {
 	m.stateFileEditsSetAside.WithLabelValues(name).Inc()
 }
 
+// count counts a request that has ended, as RequestEnded describes.
+func (m *Metrics) count(
+	line *requestlog.Line, limit string, duration, upstreamDuration time.Duration,
+) {
+	class := statusClass(line.Status)
+	m.requests.WithLabelValues(class, line.Action).Inc()
+	m.requestBytes.WithLabelValues(class, line.Action).Add(float64(line.RequestBytes))
+	m.responseBytes.WithLabelValues(class, line.Action).Add(float64(line.ResponseBytes))
+	m.requestDuration.Observe(duration.Seconds())
+
+	if upstreamDuration > 0 {
+		m.upstreamDuration.Observe(upstreamDuration.Seconds())
+	}
+
+	if limit != "" {
+		m.sizeAndTimeLimitHits.WithLabelValues(limit).Inc()
+	}
+
+	if line.Country != "" {
+		m.countries.add(line.Country, line)
+	}
+
+	if line.ASN != "" {
+		m.asns.add(line.ASN, line)
+	}
+}
+
 // addReputationQueries adds the counter of the queries to source, a DNSBL
 // zone, or of the checks of clients with AbuseIPDB, which count tells.
 func (m *Metrics) addReputationQueries(source prometheus.Labels, count func() int) {

internal/proxy/admin.go

@@ -41,6 +41,15 @@ var (
 	errNotAddress = errors.New("is not an address, such as 203.0.113.9")
 )
 
+// answerHealth answers a request for the health endpoint.
+func (rq *request) answerHealth() {
+	rq.line.Action = requestlog.ActionAdmin
+	// Set here rather than left to Go's server, which would set it only
+	// after the log line has taken the response's headers.
+	rq.out.Header().Set("Content-Type", "text/plain; charset=utf-8")
+	_, _ = io.WriteString(rq.out, "ok\n")
+}
+
 // answerAdmin answers a request for smallwebwaf itself, under
 // /_smallwebwaf/, once it has passed the checks. Each endpoint needs a
 // token, sent as Authorization: Bearer <token>: the metrics

internal/proxy/anomaly_internal_test.go

@@ -15,9 +15,11 @@ func TestWithEveryAnomalyThresholdOffARequestIsNotCounted(t *testing.T) {
 	// anomaly counters, nor a clock, and the request no response: reading
 	// any of them to count the request panics.
 	rq := &request{
-		h:        &handler{config: &config.Config{LookupSource: "geojs"}},
-		client:   netip.MustParseAddr("203.0.113.9"),
-		lookedUp: true,
+		decision: decision{
+			client:   netip.MustParseAddr("203.0.113.9"),
+			lookedUp: true,
+		},
+		h: &handler{config: &config.Config{LookupSource: "geojs"}},
 	}
 
 	defer func() {

internal/proxy/bans.go

@@ -323,6 +323,7 @@ func (rq *request) alertBan(ban bans.Ban) {
 
 	rq.h.alerts.Raise(alerts.Alert{
 		Event:    event,
+		Host:     rq.site,
 		Client:   rq.client,
 		Netblock: ban.Netblock,
 		ASN:      ban.Notes.ASN,
@@ -339,11 +340,11 @@ func (rq *request) alertBan(ban bans.Ban) {
 func (rq *request) noted(now time.Time, status int) bans.Request {
 	return bans.Request{
 		Time:      now,
-		Method:    rq.in.Method,
-		Host:      rq.in.Host,
-		Path:      rq.in.URL.RequestURI(),
+		Method:    rq.line.Method,
+		Host:      rq.line.Host,
+		Path:      rq.requestURI,
 		Status:    status,
-		UserAgent: rq.in.UserAgent(),
+		UserAgent: rq.line.UserAgent,
 	}
 }
 

internal/proxy/bans_test.go

@@ -25,6 +25,8 @@ const (
 	userAgent = "ban-test/1.0"
 	// permanent is the log line's ban_expires for a permanent ban.
 	permanent = "permanent"
+	// banResponseClose is the SWWAF_BAN_RESPONSE that closes the connection.
+	banResponseClose = "close"
 )
 
 func TestBrokenLimitBansTheClient(t *testing.T) {
@@ -237,7 +239,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 		{"", http.StatusForbidden},
 		{"403", http.StatusForbidden},
 		{"429", http.StatusTooManyRequests},
-		{"close", 0},
+		{banResponseClose, 0},
 	} {
 		t.Run(banResponse+"="+tc.setting, func(t *testing.T) {
 			t.Parallel()

internal/proxy/coreruleset.go

@@ -113,6 +113,7 @@ func (rq *request) alertWAFBlock(result waf.Result) {
 
 	rq.h.alerts.Raise(alerts.Alert{
 		Event:    alerts.EventWAFBlock,
+		Host:     rq.site,
 		Client:   rq.client,
 		Netblock: rq.h.clientGroup(rq.client),
 		ASN:      rq.line.ASN,

internal/proxy/metrics_test.go

@@ -207,7 +207,7 @@ func TestMetricsCountLimitsAndBans(t *testing.T) {
 		rateLimitPerMinute:  "1",
 		rateLimitExemptNets: scraper,
 		denyNets:            denied,
-		banResponse:         "close",
+		banResponse:         banResponseClose,
 		limitBanDuration:    "1h",
 		maxBanDuration:      "2h",
 	})

internal/proxy/proxy.go

@@ -1,6 +1,8 @@
-// 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 runs the checks on each request and writes its request log
+// line. New passes each request it lets through to the app and the app's
+// answer back, unchanged, within the size and time limits. NewServeWAF instead
+// answers rproxy's question about each request, and takes rproxy's report once
+// the visitor's answer has ended, which writes the request a second log line.
 package proxy
 
 import (
@@ -11,6 +13,8 @@ import (
 	"strings"
 	"time"
 
+	lru "github.com/hashicorp/golang-lru/v2"
+
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/anomaly"
 	"sneak.berlin/go/smallwebwaf/internal/bans"
@@ -19,7 +23,6 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 	"sneak.berlin/go/smallwebwaf/internal/reputation"
-	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 	"sneak.berlin/go/smallwebwaf/internal/waf"
 )
@@ -53,7 +56,8 @@ const ClientsPath = "/_smallwebwaf/clients/"
 // Params are what New needs.
 type Params struct {
 	Config *config.Config
-	// RequestLog receives one JSON line per request.
+	// RequestLog receives one JSON line per request, and from servewaf a second
+	// when the request's report comes.
 	RequestLog io.Writer
 	// ProcessLog receives the process's own messages.
 	ProcessLog *slog.Logger
@@ -109,6 +113,23 @@ type Server struct {
 // SWWAF_CLIENT_REQUEST_TIMEOUT while the headers arrive; the proxy
 // applies the timeouts and size limits from then on.
 func New(params Params) *Server {
+	h := newHandler(params)
+
+	return h.server(&http.Server{
+		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),
+	})
+}
+
+// newHandler returns the handler with what every request shares, as the
+// settings in params make it.
+func newHandler(params Params) *handler {
 	errorLog := slog.NewLogLogger(params.ProcessLog.Handler(), slog.LevelWarn)
 	m := metrics.New(params.Config.MetricsTopN, params.Config.InstanceName)
 	lists, dnsbl, abuseIPDB := newReputation(params, m)
@@ -171,29 +192,7 @@ func New(params Params) *Server {
 	m.AddBansAndClients(h.ledger, h.limiter, params.Now)
 	m.AddRules(params.Rules)
 
-	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,
-		Anomalies:  h.anomalies,
-		LookupFile: h.lookupFile,
-		Lists:      h.lists,
-		DNSBL:      h.dnsbl,
-		AbuseIPDB:  h.abuseIPDB,
-		Metrics:    m,
-	}
+	return h
 }
 
 // newReputation returns the lists fetched from URLs, the DNSBL zones'
@@ -274,6 +273,10 @@ type handler struct {
 	rules       *rules.Files
 	coreRuleSet *waf.CoreRuleSet
 	alerts      *alerts.Queue
+	// awaitingReport holds, in servewaf, the decision on each answered
+	// question by its id until its report comes, and nil for a question still
+	// being handled.
+	awaitingReport *lru.Cache[string, *decision]
 }
 
 // newTransport returns what carries requests to the app. It never goes
@@ -299,11 +302,7 @@ func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	// 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
-		// Set here rather than left to Go's server, which would set it only
-		// after the log line has taken the response's headers.
-		rq.out.Header().Set("Content-Type", "text/plain; charset=utf-8")
-		_, _ = io.WriteString(rq.out, "ok\n")
+		rq.answerHealth()
 
 		return
 	}
@@ -339,3 +338,23 @@ func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 
 	rq.forward(r.Context())
 }
+
+// server returns the Server of h, which listens at SWWAF_LISTEN_ADDR and
+// logs through h, with what httpServer sets.
+func (h *handler) server(httpServer *http.Server) *Server {
+	httpServer.Addr = h.config.ListenAddr
+	httpServer.ErrorLog = h.errorLog
+
+	return &Server{
+		Server:     httpServer,
+		Ledger:     h.ledger,
+		Limiter:    h.limiter,
+		GeoJS:      h.geojs,
+		Anomalies:  h.anomalies,
+		LookupFile: h.lookupFile,
+		Lists:      h.lists,
+		DNSBL:      h.dnsbl,
+		AbuseIPDB:  h.abuseIPDB,
+		Metrics:    h.metrics,
+	}
+}

internal/proxy/proxy_test.go

@@ -284,6 +284,16 @@ func newProxy(
 ) (*proxy.Server, *output, *alerts.Queue) {
 	t.Helper()
 
+	return newServerWith(t, proxy.New, appURL, geojsURL, now, env)
+}
+
+// newServerWith is newProxy for the server build makes.
+func newServerWith(
+	t *testing.T, build func(proxy.Params) *proxy.Server,
+	appURL, geojsURL string, now func() time.Time, env map[string]string,
+) (*proxy.Server, *output, *alerts.Queue) {
+	t.Helper()
+
 	settings := map[string]string{
 		"SWWAF_UPSTREAM_URL": appURL, rulesDir: t.TempDir(), instanceName: "app",
 		wafMode: off,
@@ -334,7 +344,7 @@ func newProxy(
 		}
 	}
 
-	server := proxy.New(proxy.Params{
+	server := build(proxy.Params{
 		Config:       cfg,
 		RequestLog:   out,
 		ProcessLog:   processLog,

internal/proxy/reputation.go

@@ -110,6 +110,7 @@ func (rq *request) noteHit(hit bans.ReputationHit, reason string) {
 	rq.h.metrics.ReputationHit(hit.Source)
 	rq.h.alerts.Raise(alerts.Alert{
 		Event:    alerts.EventReputationHit,
+		Host:     rq.site,
 		Client:   rq.client,
 		Netblock: rq.h.clientGroup(rq.client),
 		ASN:      rq.line.ASN,

internal/proxy/request.go

@@ -39,20 +39,20 @@ type refusal struct {
 	limit  string
 }
 
-// request is one request on its way through smallwebwaf, from the moment
-// its headers have been read to its log line.
-type request struct {
-	h  *handler
-	in *http.Request
-	// rc sets the deadlines of the connection to the client.
-	rc   *http.ResponseController
-	out  *responseWriter
-	body *requestBody // nil for a request without a body
-	line requestlog.Line
-
-	client      netip.Addr
-	peer        netip.Addr
-	peerTrusted bool
+// decision is what the checks note of a request: its log line, and what
+// counting the request needs once it has ended. servewaf keeps a copy of it
+// until the request's report comes. It holds no credentials, since the log line
+// never does, and neither the request's objects nor their bodies.
+type decision struct {
+	line   requestlog.Line
+	client netip.Addr
+	// requestURI is the path with the query, as a ban's notes keep it.
+	requestURI string
+	// site is, in servewaf, the host the visitor asked for, which the
+	// alerts name, since one servewaf serves many sites. It is "" otherwise.
+	site string
+	// allowed is true for a question answered with DispositionAllow.
+	allowed bool
 	// lookedUp is true once the client's AS number and country have been
 	// looked up, whether or not an answer was there, and lookupAnswer is
 	// what the lookup gave then, the zero Answer while GeoJS had given none.
@@ -65,18 +65,37 @@ type request struct {
 	counted                    bool
 	limitPercent, bytesPercent percentage
 	// attack is true for a request that matched a ban rule or asked for a
-	// trap path, ruleBlocked for one a block rule refused, wafBlocked for
-	// one the Core Rule Set refused, and tokenRefused for one refused for a
-	// missing or wrong token, each an offence its client's history counts.
-	attack, ruleBlocked, wafBlocked, tokenRefused bool
+	// trap path, ruleBlocked for one a block rule refused, and wafBlocked for
+	// one the Core Rule Set refused, each an offence its client's history
+	// counts.
+	attack, ruleBlocked, wafBlocked bool
+	// reputation is the reputation sources that list the client, for the
+	// notes of a ban the request makes.
+	reputation []bans.ReputationHit
+}
+
+// request is one request on its way through smallwebwaf, from the moment
+// its headers have been read to its log line.
+type request struct {
+	decision
+
+	h  *handler
+	in *http.Request
+	// rc sets the deadlines of the connection to the client.
+	rc   *http.ResponseController
+	out  *responseWriter
+	body *requestBody // nil for a request without a body
+
+	peer        netip.Addr
+	peerTrusted bool
+	// tokenRefused is true for a request refused for a missing or wrong
+	// token, an offence its client's history counts.
+	tokenRefused bool
 	// blocklisted is true once a blocklist is found to list the client,
 	// dnsblListed once a DNSBL zone's verdict is, and abuseIPDBHit once
 	// AbuseIPDB's score of it is a hit.
 	blocklisted, dnsblListed, abuseIPDBHit bool
-	// reputation is the reputation sources that list the client, for the
-	// notes of a ban the request makes.
-	reputation []bans.ReputationHit
-	start      time.Time
+	start                                  time.Time
 	// checked is when the checks were done, and upstreamStart when the
 	// request was handed to the app.
 	checked       time.Time
@@ -108,50 +127,62 @@ type request struct {
 	answerStarted time.Time
 }
 
-// newRequest starts handling r: it notes the time, counts the request as
-// under way, works out the client, and starts the log line with what is
-// known of the request.
+// newRequest starts handling r: it works out the client from the TCP peer
+// and X-Forwarded-For, and goes on as startRequest does.
 func (h *handler) newRequest(w http.ResponseWriter, r *http.Request) *request {
+	peer := peerAddress(r)
+	trusted := h.config.TrustedProxies
+	client := clientAddress(peer, r.Header.Values("X-Forwarded-For"), trusted)
+
+	return h.startRequest(w, r, client, peer, isInside(peer, trusted))
+}
+
+// startRequest starts handling r from client, which came through peer: it
+// notes the time, counts the request as under way, and starts the log line
+// with what is known of the request. peerTrusted says whether to believe
+// the request's id and scheme, which r's headers give.
+func (h *handler) startRequest(
+	w http.ResponseWriter, r *http.Request, client, peer netip.Addr, peerTrusted bool,
+) *request {
 	h.metrics.RequestStarted()
 
 	start := time.Now()
-	peer := peerAddress(r)
-	trusted := h.config.TrustedProxies
-	peerTrusted := isInside(peer, trusted)
 	forwardedFor := r.Header.Values("X-Forwarded-For")
-	client := clientAddress(peer, forwardedFor, trusted)
 
 	rq := &request{
+		decision: decision{
+			client:     client,
+			requestURI: r.URL.RequestURI(),
+			line: requestlog.Line{
+				Time:             requestlog.FormatTime(start),
+				Instance:         h.config.InstanceName,
+				ClientIP:         client.String(),
+				Method:           r.Method,
+				Scheme:           scheme(r, peerTrusted),
+				Host:             r.Host,
+				Path:             rules.Path(r),
+				Query:            r.URL.RawQuery,
+				Protocol:         r.Proto,
+				Referer:          r.Referer(),
+				UserAgent:        r.UserAgent(),
+				RequestID:        requestID(r, peerTrusted),
+				PeerIP:           peer.String(),
+				ForwardedFor:     strings.Join(forwardedFor, ", "),
+				ClientGroup:      h.clientGroup(client).String(),
+				ContentType:      r.Header.Get("Content-Type"),
+				RequestHeaders:   requestHeaders(r, h.config.LogRequestHeaders),
+				HasAuthorization: len(r.Header.Values("Authorization")) > 0,
+				HasCookie:        len(r.Header.Values("Cookie")) > 0,
+				Action:           requestlog.ActionForward,
+			},
+		},
 		h:           h,
 		in:          r,
 		rc:          http.NewResponseController(w),
 		out:         &responseWriter{ResponseWriter: w},
-		client:      client,
 		peer:        peer,
 		peerTrusted: peerTrusted,
 		start:       start,
-		line: requestlog.Line{
-			Time:             requestlog.FormatTime(start),
-			Instance:         h.config.InstanceName,
-			ClientIP:         client.String(),
-			Method:           r.Method,
-			Scheme:           scheme(r, peerTrusted),
-			Host:             r.Host,
-			Path:             rules.Path(r),
-			Query:            r.URL.RawQuery,
-			Protocol:         r.Proto,
-			Referer:          r.Referer(),
-			UserAgent:        r.UserAgent(),
-			RequestID:        requestID(r, peerTrusted),
-			PeerIP:           peer.String(),
-			ForwardedFor:     strings.Join(forwardedFor, ", "),
-			ClientGroup:      h.clientGroup(client).String(),
-			ContentType:      r.Header.Get("Content-Type"),
-			RequestHeaders:   requestHeaders(r, h.config.LogRequestHeaders),
-			HasAuthorization: len(r.Header.Values("Authorization")) > 0,
-			HasCookie:        len(r.Header.Values("Cookie")) > 0,
-			Action:           requestlog.ActionForward,
-		},
 	}
 
 	// A length of -1 is a body whose length was not announced.
@@ -569,10 +600,20 @@ func (rq *request) finish() {
 	}
 
 	// Counted before the log line is written, so that the metrics count
-	// every request whose line is out.
-	rq.h.metrics.RequestEnded(line, limit, duration, upstreamDuration)
+	// every request whose line is out. An allowed request is the exception:
+	// its report gives the status, bytes and times the metrics count.
+	if rq.allowed {
+		rq.h.metrics.RequestAllowed()
+	} else {
+		rq.h.metrics.RequestEnded(line, limit, duration, upstreamDuration)
+	}
 
-	err := requestlog.Write(rq.h.requestLog, line)
+	rq.writeLine()
+}
+
+// writeLine writes the request's log line.
+func (rq *request) writeLine() {
+	err := requestlog.Write(rq.h.requestLog, &rq.line)
 	if err != nil {
 		rq.h.processLog.Error("writing the request log failed", "error", err.Error())
 	}
@@ -634,6 +675,7 @@ func (rq *request) countAnomalies() {
 	answer, _ := rq.answerAtTheEnd()
 
 	rq.h.anomalies.Count(rq.h.now(), anomaly.Request{
+		Host:        rq.site,
 		Client:      rq.client,
 		ClientGroup: rq.h.clientGroup(rq.client),
 		ASN:         answer.ASN,

internal/proxy/servewaf.go

@@ -0,0 +1,464 @@
+package proxy
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/netip"
+	"strconv"
+	"strings"
+	"time"
+	"unicode/utf8"
+
+	lru "github.com/hashicorp/golang-lru/v2"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// The headers of rproxy's question and of servewaf's answer, as
+// "servewaf" in SPEC.md gives them.
+const (
+	// ClientHeader marks a request as rproxy's question, and gives the
+	// visitor's address.
+	ClientHeader = "X-Smallwebwaf-Client"
+	// PeerHeader gives the address of rproxy's own TCP peer.
+	PeerHeader = "X-Smallwebwaf-Peer"
+	// ContentLengthHeader gives the body length the visitor announced.
+	ContentLengthHeader = "X-Smallwebwaf-Content-Length"
+	// DispositionHeader gives servewaf's answer.
+	DispositionHeader = "X-Smallwebwaf-Disposition"
+)
+
+// The values of DispositionHeader.
+const (
+	// DispositionAllow tells rproxy to pass the request to the app.
+	DispositionAllow = "allow"
+	// DispositionDeny tells rproxy to give the visitor the answer's status,
+	// headers and body.
+	DispositionDeny = "deny"
+	// DispositionClose tells rproxy to close the visitor's connection
+	// without an answer, which SWWAF_BAN_RESPONSE asks for when it is close.
+	// servewaf closing the question's connection instead would read as
+	// servewaf being down, and rproxy would then let the request through.
+	DispositionClose = "close"
+)
+
+// ReportPath is where rproxy sends the report of each request servewaf
+// answered.
+const ReportPath = "/_smallwebwaf/report"
+
+// QuestionBodyMaxBytes is the most of a visitor's body a question carries.
+const QuestionBodyMaxBytes = 64 << 10
+
+const (
+	// maxAwaitingReport is the most answered requests held until their
+	// reports come. Past it, the request answered longest ago is dropped.
+	maxAwaitingReport = 10000
+	// maxRequestIDBytes is the longest id a question may give.
+	maxRequestIDBytes = 128
+	// reportBodyMaxBytes is the most of a report's body that is read. It is
+	// far above any report's.
+	reportBodyMaxBytes = 1 << 20
+	// maxHTTPStatus is the highest status a report may give.
+	maxHTTPStatus = 599
+	// maxReportedBytes is the most bytes a report may give for each way, 1
+	// PiB, so that adding them up cannot overflow.
+	maxReportedBytes = 1 << 50
+	// maxReportedMilliseconds is the longest duration a report may give,
+	// about 31 years, so that it fits a time.Duration.
+	maxReportedMilliseconds = 1e12
+	// serveWAFTimeout bounds how long a request to servewaf takes to arrive,
+	// and its answer to leave, and serveWAFIdleTimeout how long a kept-open
+	// connection waits for its next request.
+	serveWAFTimeout     = 60 * time.Second
+	serveWAFIdleTimeout = 120 * time.Second
+)
+
+var (
+	errReportFieldMissing = errors.New("a field is missing")
+	errReportValue        = errors.New("a value is out of range")
+)
+
+// Report is the JSON object rproxy posts to ReportPath once the visitor's
+// answer has ended, its fields named as the request log's of the same
+// meaning. RequestID is the question's id. Status is what the visitor got, 0
+// if nothing. The durations are in milliseconds.
+//
+//nolint:tagliatelle // docs/request-log.md names the fields in snake_case
+type Report struct {
+	RequestID             string  `json:"request_id"`
+	Status                int     `json:"status"`
+	RequestBytes          int64   `json:"request_bytes"`
+	ResponseBytes         int64   `json:"response_bytes"`
+	DurationTotal         float64 `json:"duration_total"`
+	DurationUpstreamTotal float64 `json:"duration_upstream_total"`
+}
+
+// NewServeWAF returns the server `smallwebwaf servewaf` runs. It answers
+// rproxy's questions with the checks New runs, takes rproxy's reports and
+// answers its own endpoints. It passes nothing to an app. rproxy applies
+// the size and time limits to the visitor, so their settings do not apply
+// here. Go's default limit on a request's line and headers, 1 MiB, stays:
+// it is far above rproxy's, and a question refused for its size would have
+// rproxy let the request through.
+func NewServeWAF(params Params) *Server {
+	cfg := *params.Config
+	cfg.RequestMaxBytes = 0
+	cfg.ClientRequestTimeout = serveWAFTimeout
+	// The server's WriteTimeout does this. It sets a new deadline for each
+	// request, where a deadline a handler sets stays on a kept-open
+	// connection, and would run out under a later request's answer.
+	cfg.ClientResponseTimeout = 0
+	// A question's body of QuestionBodyMaxBytes may be cut short, and the
+	// Core Rule Set does not read a JSON or XML body over its limit.
+	cfg.WAFBodyLimit = min(cfg.WAFBodyLimit, QuestionBodyMaxBytes-1)
+	params.Config = &cfg
+
+	h := newHandler(params)
+
+	awaitingReport, err := lru.New[string, *decision](maxAwaitingReport)
+	if err != nil {
+		panic(err) // New fails only for a size below one
+	}
+
+	h.awaitingReport = awaitingReport
+
+	return h.server(&http.Server{
+		Handler:      http.HandlerFunc(h.serveWAF),
+		ReadTimeout:  serveWAFTimeout,
+		WriteTimeout: serveWAFTimeout,
+		IdleTimeout:  serveWAFIdleTimeout,
+	})
+}
+
+// serveWAF handles one request to servewaf: a request carrying
+// ClientHeader is rproxy's question, and any other is for servewaf itself.
+func (h *handler) serveWAF(w http.ResponseWriter, r *http.Request) {
+	if len(r.Header.Values(ClientHeader)) > 0 {
+		h.answerQuestion(w, r)
+
+		return
+	}
+
+	h.answerOwnEndpoint(w, r)
+}
+
+// answerQuestion runs the checks on the visitor's request a question
+// carries, and answers rproxy what to do with it. A denied request's counting
+// is finished here, and an allowed one's by its report.
+func (h *handler) answerQuestion(w http.ResponseWriter, r *http.Request) {
+	client, body, ok := h.readQuestion(w, r)
+	if !ok {
+		return
+	}
+
+	// One that cannot be read leaves the log line's peer_ip invalid.
+	peer, _ := netip.ParseAddr(r.Header.Get(PeerHeader))
+
+	rq := h.startRequest(w, asTheVisitorSentIt(r, body), client.Unmap(), peer.Unmap(),
+		true)
+	// The last deferred runs first, so that what is held has the finished log
+	// line. Go's server sends the answer only once this function has
+	// returned, so the report cannot come before it is held.
+	defer rq.holdForReport()
+	defer rq.finish()
+
+	rq.site = r.Host
+	rq.line.ServeWAFLine = requestlog.ServeWAFLineDecision
+	refused := rq.check(r.Context())
+	rq.checked = time.Now()
+	underOwnPrefix := strings.HasPrefix(r.URL.Path, adminPrefix)
+
+	if refused == nil && !underOwnPrefix {
+		// In observe mode, what enforce mode would have refused counts here.
+		defer rq.countRefusal()
+
+		rq.allow()
+
+		return
+	}
+
+	// The last deferred runs first, as in ServeHTTP.
+	defer rq.addToHistory()
+	defer rq.countAnomalies()
+	defer rq.countRefusal()
+
+	if refused != nil {
+		rq.deny(*refused)
+
+		return
+	}
+
+	// The app never sees this prefix. servewaf's own endpoints are at its
+	// own address, so this answers as a path with no endpoint does.
+	rq.line.Action = requestlog.ActionAdmin
+	rq.out.Header().Set(DispositionHeader, DispositionDeny)
+	http.Error(rq.out, http.StatusText(http.StatusNotFound), http.StatusNotFound)
+}
+
+// readQuestion returns the visitor's address and the body a question carries,
+// and whether servewaf takes the question. It answers a question it does not
+// take with 400 and no disposition, which rproxy treats as it treats no
+// answer. The id of a question it takes is held from here on, without a
+// decision yet, so that another question with that id is refused while this
+// one is being handled.
+//
+// The body is read before any check, since Go's server does not send an answer
+// until it has read the body. A question whose body stops arriving gets no
+// answer, and is not looked at.
+func (h *handler) readQuestion(
+	w http.ResponseWriter, r *http.Request,
+) (netip.Addr, []byte, bool) {
+	client, err := netip.ParseAddr(r.Header.Get(ClientHeader))
+	if err != nil || client.Zone() != "" {
+		h.refuseQuestion(w, ClientHeader+" is not an address without a zone")
+
+		return netip.Addr{}, nil, false
+	}
+
+	id := r.Header.Get(requestIDHeader)
+	if id == "" || len(id) > maxRequestIDBytes || !utf8.ValidString(id) {
+		h.refuseQuestion(w, requestIDHeader+" is not a valid id")
+
+		return netip.Addr{}, nil, false
+	}
+
+	body, err := io.ReadAll(http.MaxBytesReader(w, r.Body, QuestionBodyMaxBytes))
+
+	if _, tooLarge := errors.AsType[*http.MaxBytesError](err); tooLarge {
+		h.refuseQuestion(w, "the body is over 64 KiB")
+
+		return netip.Addr{}, nil, false
+	}
+
+	if err != nil {
+		h.processLog.Warn("a question's body stopped arriving", "error", err.Error())
+		// This panic has Go's server close the connection without an answer,
+		// and log nothing.
+		panic(http.ErrAbortHandler)
+	}
+
+	held, _ := h.awaitingReport.ContainsOrAdd(id, nil)
+	if held {
+		h.refuseQuestion(w, requestIDHeader+" is the id of a request servewaf holds")
+
+		return netip.Addr{}, nil, false
+	}
+
+	return client, body, true
+}
+
+// refuseQuestion answers a question servewaf does not take, for reason.
+func (h *handler) refuseQuestion(w http.ResponseWriter, reason string) {
+	h.processLog.Warn("a question is refused", "reason", reason)
+	http.Error(w, reason, http.StatusBadRequest)
+}
+
+// asTheVisitorSentIt returns a copy of r, a question, as the checks and the
+// log line are to see it: without the headers rproxy adds for servewaf, with
+// body, which has been read of r, and with the length the visitor announced,
+// as -1 when it announced none. The question's own length covers only the part
+// of the body it carries.
+func asTheVisitorSentIt(r *http.Request, body []byte) *http.Request {
+	sent := r.Clone(r.Context())
+	announced := sent.Header.Get(ContentLengthHeader)
+
+	sent.Header.Del(ClientHeader)
+	sent.Header.Del(PeerHeader)
+	sent.Header.Del(ContentLengthHeader)
+	sent.Header.Del("Content-Length")
+
+	sent.ContentLength = -1
+
+	length, err := strconv.ParseInt(announced, 10, 64)
+	if err == nil && length >= 0 {
+		sent.ContentLength = length
+		sent.Header.Set("Content-Length", announced)
+	}
+
+	sent.Body = http.NoBody
+	if len(body) > 0 {
+		sent.Body = io.NopCloser(bytes.NewReader(body))
+	}
+
+	return sent
+}
+
+// allow answers a question with DispositionAllow and, while
+// SWWAF_ADD_LOOKUP_HEADERS is set, the client's AS number and country.
+func (rq *request) allow() {
+	rq.allowed = true
+
+	header := rq.out.Header()
+	header.Set(DispositionHeader, DispositionAllow)
+
+	if rq.h.config.AddLookupHeaders {
+		setLookupHeaders(header, rq.line.ASN, rq.line.Country)
+	}
+
+	rq.out.WriteHeader(http.StatusOK)
+}
+
+// holdForReport holds a copy of what the report's steps need, by the request's
+// id. A report only ever reaches that copy, never the request being handled.
+func (rq *request) holdForReport() {
+	held := rq.decision
+	rq.h.awaitingReport.Add(rq.line.RequestID, &held)
+}
+
+// deny answers a question with what the visitor is to get for r.
+func (rq *request) deny(r refusal) {
+	if r.status == 0 {
+		// SWWAF_BAN_RESPONSE is close. Written past rq.out, since the log line's
+		// status stays 0: the visitor is sent nothing.
+		rq.refused.CompareAndSwap(nil, &r)
+		rq.out.Header().Set(DispositionHeader, DispositionClose)
+		rq.out.ResponseWriter.WriteHeader(http.StatusOK)
+
+		return
+	}
+
+	rq.out.Header().Set(DispositionHeader, DispositionDeny)
+	rq.answer(r)
+}
+
+// answerOwnEndpoint answers a request to servewaf's own address. No check
+// runs on it: the address is on the private network, where the peers are
+// rproxy and the admin's tools, not visitors.
+func (h *handler) answerOwnEndpoint(w http.ResponseWriter, r *http.Request) {
+	if r.Method == http.MethodPost && r.URL.Path == ReportPath {
+		h.takeReport(w, r)
+
+		return
+	}
+
+	peer := peerAddress(r)
+
+	rq := h.startRequest(w, r, peer, peer, false)
+	defer rq.finish()
+
+	if r.Method == http.MethodGet && r.URL.Path == HealthPath {
+		rq.answerHealth()
+
+		return
+	}
+
+	rq.answerAdmin()
+}
+
+// takeReport answers POST ReportPath: it finishes the request the report
+// names, if it holds that request's decision, and ignores the report
+// otherwise.
+func (h *handler) takeReport(w http.ResponseWriter, r *http.Request) {
+	report, err := readReport(w, r)
+	if err != nil {
+		h.processLog.Warn("a report is refused", "error", err.Error())
+		http.Error(w, "the body is not a report", http.StatusBadRequest)
+
+		return
+	}
+
+	held, found := h.awaitingReport.Peek(report.RequestID)
+	// Remove reports true to one report only, of several that name the id.
+	if found && held != nil && h.awaitingReport.Remove(report.RequestID) {
+		h.finishWith(held, report)
+	}
+
+	w.WriteHeader(http.StatusNoContent)
+}
+
+// readReport reads a report from r's body, which must be one JSON object with
+// all of Report's fields, in the ranges SPEC.md gives.
+func readReport(w http.ResponseWriter, r *http.Request) (Report, error) {
+	var report Report
+
+	body, err := io.ReadAll(http.MaxBytesReader(w, r.Body, reportBodyMaxBytes))
+	if err != nil {
+		return report, fmt.Errorf("read the body: %w", err)
+	}
+
+	var fields map[string]json.RawMessage
+
+	err = json.Unmarshal(body, &fields)
+	if err != nil {
+		return report, fmt.Errorf("decode the body: %w", err)
+	}
+
+	for _, name := range []string{
+		"request_id", "status", "request_bytes", "response_bytes",
+		"duration_total", "duration_upstream_total",
+	} {
+		value, there := fields[name]
+		if !there || string(value) == "null" {
+			return report, fmt.Errorf("%w: %s", errReportFieldMissing, name)
+		}
+	}
+
+	err = json.Unmarshal(body, &report)
+	if err != nil {
+		return report, fmt.Errorf("decode the body: %w", err)
+	}
+
+	return report, report.checkRanges()
+}
+
+// checkRanges returns an error for a value of the report that cannot be true.
+func (report *Report) checkRanges() error {
+	switch {
+	case report.Status != 0 &&
+		(report.Status < http.StatusContinue || report.Status > maxHTTPStatus):
+		return fmt.Errorf("%w: status", errReportValue)
+	case report.RequestBytes < 0 || report.RequestBytes > maxReportedBytes:
+		return fmt.Errorf("%w: request_bytes", errReportValue)
+	case report.ResponseBytes < 0 || report.ResponseBytes > maxReportedBytes:
+		return fmt.Errorf("%w: response_bytes", errReportValue)
+	case report.DurationTotal < 0 || report.DurationTotal > maxReportedMilliseconds:
+		return fmt.Errorf("%w: duration_total", errReportValue)
+	case report.DurationUpstreamTotal < 0 ||
+		report.DurationUpstreamTotal > maxReportedMilliseconds:
+		return fmt.Errorf("%w: duration_upstream_total", errReportValue)
+	}
+
+	return nil
+}
+
+// finishWith finishes a request with what its report says, and writes the
+// request's last log line, which holds its decision's fields and the report's.
+// For an allowed request it first takes the steps ServeHTTP takes once a
+// request passed to the app has ended, with the status and bytes of the report
+// in place of those it would have seen. A denied request's counting was
+// finished at its decision.
+func (h *handler) finishWith(held *decision, report Report) {
+	rq := &request{
+		decision: *held,
+		h:        h,
+		out:      &responseWriter{status: report.Status, bytes: report.ResponseBytes},
+		body:     &requestBody{},
+	}
+	rq.body.bytes.Store(report.RequestBytes)
+
+	rq.line.ServeWAFLine = requestlog.ServeWAFLineReport
+	rq.line.Status = report.Status
+	rq.line.RequestBytes = report.RequestBytes
+	rq.line.ResponseBytes = report.ResponseBytes
+	rq.line.DurationTotal = report.DurationTotal
+
+	if rq.allowed {
+		rq.line.DurationUpstreamTotal = &report.DurationUpstreamTotal
+		// addToHistory goes by this for whether the request reached the app.
+		rq.upstreamStart = time.Now()
+
+		rq.countBytes()
+		rq.countAnomalies()
+		rq.addToHistory()
+
+		rq.h.metrics.RequestReported(&rq.line,
+			time.Duration(report.DurationTotal*float64(time.Millisecond)),
+			time.Duration(report.DurationUpstreamTotal*float64(time.Millisecond)))
+	}
+
+	rq.writeLine()
+}

internal/requestlog/requestlog.go

@@ -1,6 +1,6 @@
 // Package requestlog writes the lines smallwebwaf prints on stdout: one
-// JSON object per request, marked "type":"request", and the process's own
-// messages as JSON lines marked "type":"process".
+// JSON object per request, or two from servewaf, marked "type":"request", and
+// the process's own messages as JSON lines marked "type":"process".
 package requestlog
 
 import (
@@ -60,6 +60,16 @@ const OffenceLimit = "limit"
 // that broke the error burst.
 const LimitHitErrorBurst = "error_burst"
 
+// The servewaf_line a request line names, which says which of servewaf's two
+// lines about a question it is.
+const (
+	// ServeWAFLineDecision is servewaf's line at its decision.
+	ServeWAFLineDecision = "decision"
+	// ServeWAFLineReport is servewaf's line when rproxy's report comes, with
+	// the decision's fields and the report's together.
+	ServeWAFLineReport = "report"
+)
+
 // timeLayout is RFC 3339 with milliseconds.
 const timeLayout = "2006-01-02T15:04:05.000Z07:00"
 
@@ -70,6 +80,9 @@ const timeLayout = "2006-01-02T15:04:05.000Z07:00"
 //nolint:tagliatelle // docs/request-log.md names the fields in snake_case
 type Line struct {
 	Type string `json:"type"`
+	// ServeWAFLine is ServeWAFLineDecision or ServeWAFLineReport on servewaf's
+	// two lines about a question.
+	ServeWAFLine string `json:"servewaf_line,omitempty"`
 
 	// The standard web log fields. Scheme is how the client reached
 	// smallwebwaf, or the trusted proxy in front of it.

internal/smallwebwaf/servewaf_test.go

@@ -0,0 +1,210 @@
+package smallwebwaf_test
+
+import (
+	"context"
+	"crypto/rand"
+	"io"
+	"net/http"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"syscall"
+	"testing"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/proxy"
+	"sneak.berlin/go/smallwebwaf/internal/smallwebwaf"
+)
+
+// commandForMain, while set in the environment, has this test binary run Main
+// with the command it gives, in place of the tests, so that a test can run
+// Main in a process of its own.
+const commandForMain = "SMALLWEBWAF_TEST_COMMAND"
+
+func TestMain(m *testing.M) {
+	command, set := os.LookupEnv(commandForMain)
+	if !set {
+		os.Exit(m.Run())
+	}
+
+	os.Args = strings.Fields("smallwebwaf " + command)
+
+	os.Exit(smallwebwaf.Main(testVersion))
+}
+
+func TestMainAnswersQuestionsOnlyAsServeWAF(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		command, disposition string
+	}{
+		{"servewaf", proxy.DispositionAllow},
+		{"", ""},
+	} {
+		t.Run("command "+tc.command, func(t *testing.T) {
+			t.Parallel()
+
+			binary, err := os.Executable()
+			if err != nil {
+				t.Fatalf("find the test binary: %v", err)
+			}
+
+			ctx, cancel := context.WithTimeout(t.Context(), 3*waitLimit)
+			defer cancel()
+
+			out := &output{}
+			cmd := exec.CommandContext(ctx, binary) //nolint:gosec // this test binary
+			cmd.Stdout = out
+
+			cmd.Env = append(os.Environ(),
+				commandForMain+"="+tc.command,
+				listenAddr+"="+localhost+":0",
+				upstreamURL+"="+startApp(t),
+				stateDir+"="+t.TempDir(),
+				rulesDir+"="+t.TempDir(),
+				lookupSource+"=off")
+
+			err = cmd.Start()
+			if err != nil {
+				t.Fatalf("start: %v", err)
+			}
+
+			t.Cleanup(func() {
+				_ = cmd.Process.Kill()
+				_ = cmd.Wait()
+			})
+
+			addr, _ := out.line(t, "msg", "starting")["address"].(string)
+			ask(t, addr, "/", http.StatusOK, tc.disposition)
+
+			err = cmd.Process.Signal(syscall.SIGTERM)
+			if err != nil {
+				t.Fatalf("signal: %v", err)
+			}
+
+			err = cmd.Wait()
+			if err != nil {
+				t.Errorf("exit: %v; output:\n%s", err, out.text())
+			}
+		})
+	}
+}
+
+// ask sends servewaf at addr rproxy's question about a request for path from
+// placed, checks the answer's status and disposition, and closes it.
+func ask(t *testing.T, addr, path string, status int, disposition string) {
+	t.Helper()
+
+	req, err := http.NewRequestWithContext(t.Context(), http.MethodGet,
+		"http://"+addr+path, http.NoBody)
+	if err != nil {
+		t.Fatalf("new request: %v", err)
+	}
+
+	req.Header.Set(proxy.ClientHeader, placed)
+	req.Header.Set("X-Request-ID", rand.Text())
+
+	transport := &http.Transport{}
+	defer transport.CloseIdleConnections()
+
+	res, err := (&http.Client{Transport: transport}).Do(req)
+	if err != nil {
+		t.Fatalf("question: %v", err)
+	}
+
+	_, _ = io.Copy(io.Discard, res.Body)
+	_ = res.Body.Close()
+
+	if res.StatusCode != status ||
+		res.Header.Get(proxy.DispositionHeader) != disposition {
+		t.Errorf("answered %d with disposition %q, want %d with %q", res.StatusCode,
+			res.Header.Get(proxy.DispositionHeader), status, disposition)
+	}
+}
+
+// runServeWAF runs `smallwebwaf servewaf` with the settings in env, has use
+// send it requests at the address it listens on, stops it as SIGTERM does, and
+// checks that it stopped in order.
+func runServeWAF(t *testing.T, env map[string]string, use func(addr string)) {
+	t.Helper()
+
+	ctx, stop := context.WithCancel(t.Context())
+	out := &output{}
+	exited := make(chan int, 1)
+
+	go func() {
+		exited <- runAs(ctx, true, env, out)
+	}()
+
+	addr, _ := out.line(t, "msg", "starting")["address"].(string)
+	use(addr)
+	stop()
+
+	select {
+	case status := <-exited:
+		if status != 0 {
+			t.Fatalf("exit status %d, want 0; output:\n%s", status, out.text())
+		}
+	case <-time.After(waitLimit):
+		t.Fatal("still running after being told to stop")
+	}
+
+	out.line(t, "msg", "stopped")
+}
+
+func TestServeWAFKeepsItsBansAcrossARestartAndNeedsNoApp(t *testing.T) {
+	t.Parallel()
+
+	env := map[string]string{
+		listenAddr: localhost + ":0",
+		stateDir:   t.TempDir(),
+		rulesDir:   filepath.Join("..", "..", "share", "rules.d"),
+	}
+
+	runServeWAF(t, env, func(addr string) {
+		ask(t, addr, "/", http.StatusOK, proxy.DispositionAllow)
+		// The default rule file bans a probe for this.
+		ask(t, addr, "/.env", http.StatusForbidden, proxy.DispositionDeny)
+	})
+
+	runServeWAF(t, env, func(addr string) {
+		ask(t, addr, "/", http.StatusForbidden, proxy.DispositionDeny)
+	})
+}
+
+func TestWithoutACommandTheClientHeaderIsNoQuestion(t *testing.T) {
+	t.Parallel()
+
+	runUntilStopped(t, map[string]string{
+		listenAddr:  localhost + ":0",
+		upstreamURL: startApp(t),
+		stateDir:    t.TempDir(),
+		rulesDir:    t.TempDir(),
+	}, func(url string) {
+		req, err := http.NewRequestWithContext(t.Context(), http.MethodGet, url,
+			http.NoBody)
+		if err != nil {
+			t.Fatalf("new request: %v", err)
+		}
+
+		req.Header.Set(proxy.ClientHeader, placed)
+
+		transport := &http.Transport{}
+		defer transport.CloseIdleConnections()
+
+		res, err := (&http.Client{Transport: transport}).Do(req)
+		if err != nil {
+			t.Fatalf("request: %v", err)
+		}
+
+		body, err := io.ReadAll(res.Body)
+		_ = res.Body.Close()
+
+		if err != nil || string(body) != greeting ||
+			res.Header.Get(proxy.DispositionHeader) != "" {
+			t.Errorf("answered %q (%v) with disposition %q, want the app's greeting",
+				body, err, res.Header.Get(proxy.DispositionHeader))
+		}
+	})
+}

internal/smallwebwaf/smallwebwaf.go

@@ -1,7 +1,8 @@
 // Package smallwebwaf runs the smallwebwaf process: it reads the settings,
 // the rule files, the lookup database and the state files, serves requests
 // until it is told to stop, and then stops in an orderly way, writing the
-// state files.
+// state files. It serves them in front of an app, or, as `smallwebwaf
+// servewaf`, by answering rproxy's questions about them.
 package smallwebwaf
 
 import (
@@ -45,11 +46,15 @@ type Params struct {
 	LookupEnv func(string) (string, bool)
 	// Stdout receives the request log and the process's own messages.
 	Stdout io.Writer
+	// ServeWAF makes it `smallwebwaf servewaf`, which answers rproxy's
+	// questions, rather than the proxy in front of an app.
+	ServeWAF bool
 }
 
 // Main runs smallwebwaf until SIGTERM or SIGINT, and returns the
-// process's exit status. Run as `smallwebwaf healthcheck`, it is the
-// container's health check instead.
+// process's exit status. Run as `smallwebwaf servewaf`, it answers
+// rproxy's questions rather than pass requests to an app. Run as
+// `smallwebwaf healthcheck`, it is the container's health check instead.
 func Main(version string) int {
 	if len(os.Args) > 1 && os.Args[1] == "healthcheck" {
 		return HealthCheck(context.Background(), os.Args[2:], os.LookupEnv, os.Stderr)
@@ -63,6 +68,7 @@ func Main(version string) int {
 		Version:   version,
 		LookupEnv: os.LookupEnv,
 		Stdout:    os.Stdout,
+		ServeWAF:  len(os.Args) > 1 && os.Args[1] == "servewaf",
 	})
 }
 
@@ -117,7 +123,12 @@ func Run(ctx context.Context, params Params) int {
 		return 1
 	}
 
-	server, err := newServer(cfg, stdout, processLog, now, ruleFiles, alertQueue)
+	newProxy := proxy.New
+	if params.ServeWAF {
+		newProxy = proxy.NewServeWAF
+	}
+
+	server, err := newServer(newProxy, cfg, stdout, processLog, now, ruleFiles, alertQueue)
 	if err != nil {
 		processLog.Error("cannot use the lookup database", "error", err.Error())
 
@@ -151,10 +162,12 @@ func Run(ctx context.Context, params Params) int {
 	return serve(ctx, server, listener, files, ruleFiles, alertQueue, processLog)
 }
 
-// newServer returns the server smallwebwaf runs, with the metrics of the
-// alerts, after reading the lookup database while SWWAF_LOOKUP_SOURCE is
-// file. A lookup database that cannot be read is an error.
+// newServer returns the server smallwebwaf runs, which newProxy makes, with
+// the metrics of the alerts, after reading the lookup database while
+// SWWAF_LOOKUP_SOURCE is file. A lookup database that cannot be read is an
+// error.
 func newServer(
+	newProxy func(proxy.Params) *proxy.Server,
 	cfg *config.Config, stdout io.Writer, processLog *slog.Logger,
 	now func() time.Time, ruleFiles *rules.Files, alertQueue *alerts.Queue,
 ) (*proxy.Server, error) {
@@ -174,7 +187,7 @@ func newServer(
 		}
 	}
 
-	server := proxy.New(proxy.Params{
+	server := newProxy(proxy.Params{
 		Config:       cfg,
 		RequestLog:   stdout,
 		ProcessLog:   processLog,

internal/smallwebwaf/smallwebwaf_test.go

@@ -113,6 +113,13 @@ func (o *output) text() string {
 // returns its exit status. SWWAF_LOOKUP_SOURCE is off unless env sets it,
 // so that no test sends GeoJS its clients' addresses.
 func run(ctx context.Context, env map[string]string, out *output) int {
+	return runAs(ctx, false, env, out)
+}
+
+// runAs is run as `smallwebwaf servewaf` while serveWAF is true.
+func runAs(
+	ctx context.Context, serveWAF bool, env map[string]string, out *output,
+) int {
 	return smallwebwaf.Run(ctx, smallwebwaf.Params{
 		Version: testVersion,
 		LookupEnv: func(name string) (string, bool) {
@@ -123,7 +130,8 @@ func run(ctx context.Context, env map[string]string, out *output) int {
 
 			return value, ok
 		},
-		Stdout: out,
+		Stdout:   out,
+		ServeWAF: serveWAF,
 	})
 }