AS number and country looked up for every client (closes #95)

GeoJS's geo.json is asked about every new visitor unless
SWWAF_LOOKUP_SOURCE is off. A request waits for its client's first
answer only while a country list or SWWAF_ADD_LOOKUP_HEADERS needs it;
otherwise the answer reaches the client's history and ban notes when it
comes. The AS number and name go beside the country in the request log,
history, ban notes, alerts and lookups.json, with metrics by AS number;
64512 counts as unknown. A client's own X-Client-ASN and
X-Client-Country never reach the app, whatever the setting says, and
make example-app sends no address to GeoJS.

Judgement call: AS numbers are written AS64496, as SPEC's settings write them.
Judgement call: SWWAF_LOOKUP_TIMEOUT is added, default 1s, and cannot be off.

Model: opus-5-5

internal/proxy/bans.go

@@ -64,6 +64,8 @@ func (rq *request) limitBroken(now time.Time) bool {
 	}
 
 	notes := bans.Notes{
+		ASN:      rq.line.ASN,
+		ASName:   rq.line.ASName,
 		Country:  rq.line.Country,
 		Limit:    hit.Limit,
 		Window:   hit.Window,
@@ -103,6 +105,8 @@ func (rq *request) banForAttack(now time.Time, rule rules.Rule) {
 	}
 
 	notes := bans.Notes{
+		ASN:      rq.line.ASN,
+		ASName:   rq.line.ASName,
 		Country:  rq.line.Country,
 		RuleID:   rule.ID,
 		Target:   rule.Target,
@@ -165,6 +169,8 @@ func (rq *request) alertBan(ban bans.Ban) {
 		Event:    event,
 		Client:   rq.client,
 		Netblock: ban.Netblock,
+		ASN:      ban.Notes.ASN,
+		ASName:   ban.Notes.ASName,
 		Country:  ban.Notes.Country,
 		Reason:   ban.Reason,
 		Detail:   detail,

internal/proxy/bans_test.go

@@ -281,6 +281,8 @@ func TestBanNotes(t *testing.T) {
 		Cause:    bans.CauseLimit,
 		Reason:   "requests per minute over the limit of 1",
 		Notes: bans.Notes{
+			ASN:     asnDE,
+			ASName:  asNameDE,
 			Country: "DE",
 			Limit:   1,
 			Window:  minute,
@@ -362,8 +364,9 @@ func (c *clock) advance(d time.Duration) {
 
 // startWithClock starts smallwebwaf in front of an app that answers 200,
 // with the settings in env on top of trusting localhost's
-// X-Forwarded-For, clients' countries looked up at geojsURL, and a clock
-// set to midnight, the start of a bucket in every window.
+// X-Forwarded-For, clients' AS numbers and countries looked up at
+// geojsURL, and a clock set to midnight, the start of a bucket in every
+// window.
 func startWithClock(
 	t *testing.T, geojsURL string, env map[string]string,
 ) (*sender, *clock, *proxy.Server) {

internal/proxy/countries.go

@@ -1,31 +1,17 @@
 package proxy
 
 import (
-	"context"
-	"net/netip"
 	"slices"
 )
 
-// countryDenied reports whether the country lists refuse the request.
-// The client's country is looked up only while a list is set, and never
-// for a client on a private, loopback or link-local address, which has
-// no country. A client without a country, or whose country cannot be
-// found, is refused only by SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES. ctx is
-// the request's own context.
-func (rq *request) countryDenied(ctx context.Context) bool {
+// countryDenied reports whether the country lists refuse the request, by
+// the client's country as it was looked up. A client without a country,
+// or whose country cannot be found, is refused only by
+// SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES.
+func (rq *request) countryDenied() bool {
 	denied := rq.h.config.DeniedCountries
 	allowed := rq.h.config.ExclusivelyAllowedCountries
-
-	if len(denied) == 0 && len(allowed) == 0 {
-		return false
-	}
-
-	var country string
-	if hasCountry(rq.client) {
-		country = rq.h.geojs.Country(ctx, clientGroup(rq.client))
-	}
-
-	rq.line.Country = country
+	country := rq.line.Country
 
 	if slices.Contains(denied, country) {
 		return true
@@ -33,9 +19,3 @@ func (rq *request) countryDenied(ctx context.Context) bool {
 
 	return len(allowed) > 0 && !slices.Contains(allowed, country)
 }
-
-// hasCountry reports whether addr can be placed in a country: private,
-// loopback and link-local addresses cannot.
-func hasCountry(addr netip.Addr) bool {
-	return !addr.IsPrivate() && !addr.IsLoopback() && !addr.IsLinkLocalUnicast()
-}

internal/proxy/countries_test.go

@@ -56,16 +56,21 @@ func TestCountryLists(t *testing.T) {
 			maps.Copy(env, tc.env)
 			addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, env)
 
-			for i, sent := range []struct{ client, country string }{
-				{fromDE, "DE"}, {fromKP, "KP"}, {unplaced, ""},
+			// The AS number GeoJS gives unplaced, 64512, counts as unknown.
+			for i, sent := range []struct{ client, asn, asName, country string }{
+				{fromDE, asnDE, asNameDE, "DE"}, {fromKP, asnKP, asNameKP, "KP"},
+				{unplaced, "", "", ""},
 			} {
 				req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
 				req.Header.Set(forwardedFor, sent.client)
 				got := do(t, req)
 
 				line := out.requestLines(t, i+1)[i]
-				if line.Country != sent.country {
-					t.Errorf("log line has country %q, want %q", line.Country, sent.country)
+				if line.ASN != sent.asn || line.ASName != sent.asName ||
+					line.Country != sent.country {
+					t.Errorf("log line has %q, %q and %q, want %q, %q and %q",
+						line.ASN, line.ASName, line.Country,
+						sent.asn, sent.asName, sent.country)
 				}
 
 				if slices.Contains(tc.refused, sent.client) {
@@ -130,7 +135,7 @@ func TestRequestRefusedByCountryIsNotCounted(t *testing.T) {
 				return
 			}
 
-			answer := []map[string]string{{"ip": r.URL.Query().Get("ip"), "country": "DE"}}
+			answer := []geojsAnswer{{IP: r.URL.Query().Get("ip"), CountryCode: "DE"}}
 
 			err := json.NewEncoder(w).Encode(answer)
 			if err != nil {
@@ -174,20 +179,15 @@ func TestRequestRefusedByCountryIsNotCounted(t *testing.T) {
 	wantStatus(t, got, http.StatusOK)
 }
 
-func TestCountryNotLookedUpWithoutAListOrForAPrivateAddress(t *testing.T) {
+func TestPrivateAddressIsNeverLookedUp(t *testing.T) {
 	t.Parallel()
 
 	for _, tc := range []struct {
-		name    string
-		env     map[string]string
-		clients []string // "" sends no X-Forwarded-For: the client is 127.0.0.1
+		name string
+		env  map[string]string
 	}{
-		{"no country list is set", nil, []string{fromKP, fromDE}},
-		{
-			"private, loopback and link-local addresses",
-			map[string]string{deniedCountries: "kp"},
-			[]string{"10.0.0.5", "192.168.1.9", "fd00::5", "", "169.254.0.9", "fe80::9"},
-		},
+		{"no setting needs the lookup", nil},
+		{"a country list is set", map[string]string{deniedCountries: "kp"}},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()
@@ -198,7 +198,10 @@ func TestCountryNotLookedUpWithoutAListOrForAPrivateAddress(t *testing.T) {
 			maps.Copy(env, tc.env)
 			addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, env)
 
-			for i, sent := range tc.clients {
+			// "" sends no X-Forwarded-For: the client is 127.0.0.1.
+			for i, sent := range []string{
+				"10.0.0.5", "192.168.1.9", "fd00::5", "", "169.254.0.9", "fe80::9",
+			} {
 				req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
 				if sent != "" {
 					req.Header.Set(forwardedFor, sent)
@@ -209,15 +212,26 @@ func TestCountryNotLookedUpWithoutAListOrForAPrivateAddress(t *testing.T) {
 				line := out.requestLines(t, i+1)[i]
 				wantLine(t, line, http.StatusOK, requestlog.ActionForward)
 
-				country, present := line.fields["country"]
-				if !present || country != "" {
-					t.Errorf("log line for %q has country %v, want an empty one",
-						line.ClientIP, country)
+				for _, field := range []string{"asn", "as_name", "country"} {
+					value, present := line.fields[field]
+					if !present || value != "" {
+						t.Errorf("log line for %q has %s %v, want an empty one",
+							line.ClientIP, field, value)
+					}
 				}
 			}
 
-			if len(asked()) != 0 {
-				t.Errorf("GeoJS was asked about %v, want nothing", asked())
+			// GeoJS is asked about up to 200 waiting clients at once, so once it
+			// has been asked about fromDE, which comes last, it has been asked
+			// about every client before it that waited for an answer.
+			req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
+			req.Header.Set(forwardedFor, fromDE)
+			wantStatus(t, do(t, req), http.StatusOK)
+
+			waitUntil(func() bool { return slices.Contains(asked(), fromDE) })
+
+			if got := asked(); !slices.Equal(got, []string{fromDE}) {
+				t.Errorf("GeoJS was asked about %v, want %s alone", got, fromDE)
 			}
 		})
 	}
@@ -264,18 +278,31 @@ func TestExclusiveListRefusesAPrivateAddressUnlessAllowed(t *testing.T) {
 	}
 }
 
-// startGeoJS starts a stand-in for GeoJS, which places fromDE and fromKP
-// and no other address. It returns its URL, and what returns the
-// addresses it has been asked about.
+// startGeoJS starts a stand-in for GeoJS, which places fromDE and fromKP,
+// each in an AS of its own, and no other address. It returns its URL, and
+// what returns the addresses it has been asked about.
 func startGeoJS(t *testing.T) (string, func() []string) {
 	t.Helper()
 
-	places := map[string]string{fromDE: "DE", fromKP: "KP"}
+	geojsURL, asked, release := startHeldGeoJS(t)
+	release()
 
-	var asked struct {
-		mu    sync.Mutex
-		addrs []string
-	}
+	return geojsURL, asked
+}
+
+// startHeldGeoJS is startGeoJS for a stand-in that answers nothing until
+// release is called. Each request to it waits until then.
+func startHeldGeoJS(t *testing.T) (string, func() []string, func()) {
+	t.Helper()
+
+	var (
+		asked struct {
+			mu    sync.Mutex
+			addrs []string
+		}
+		released = make(chan struct{})
+		once     sync.Once
+	)
 
 	geojs := httptest.NewServer(http.HandlerFunc(
 		func(w http.ResponseWriter, r *http.Request) {
@@ -285,11 +312,11 @@ func startGeoJS(t *testing.T) (string, func() []string) {
 			asked.addrs = append(asked.addrs, addrs...)
 			asked.mu.Unlock()
 
-			answers := make([]map[string]string, 0, len(addrs))
+			<-released
+
+			answers := make([]geojsAnswer, 0, len(addrs))
 			for _, addr := range addrs {
-				answers = append(answers, map[string]string{
-					"ip": addr, "country": places[addr],
-				})
+				answers = append(answers, answerAbout(addr))
 			}
 
 			err := json.NewEncoder(w).Encode(answers)
@@ -299,10 +326,48 @@ func startGeoJS(t *testing.T) (string, func() []string) {
 		}))
 	t.Cleanup(geojs.Close)
 
+	release := func() { once.Do(func() { close(released) }) }
+	// Run before geojs.Close, which waits for every request to be answered.
+	t.Cleanup(release)
+
 	return geojs.URL, func() []string {
 		asked.mu.Lock()
 		defer asked.mu.Unlock()
 
 		return slices.Clone(asked.addrs)
+	}, release
+}
+
+// The AS numbers and names the stand-in for GeoJS gives fromDE and
+// fromKP, as they are logged.
+const (
+	asnDE    = "AS64496"
+	asNameDE = "Example Net"
+	asnKP    = "AS64511"
+	asNameKP = "Other Net"
+)
+
+// geojsAnswer is an answer of GeoJS about one address, with the fields
+// smallwebwaf reads.
+//
+//nolint:tagliatelle // GeoJS's own names
+type geojsAnswer struct {
+	IP          string `json:"ip"`
+	ASN         int    `json:"asn"`
+	ASName      string `json:"organization_name"`
+	CountryCode string `json:"country_code,omitempty"`
+}
+
+// answerAbout is what the stand-in for GeoJS answers about addr: for an
+// address it cannot place, the AS number 64512 and the AS name Unknown
+// with no country, as GeoJS does.
+func answerAbout(addr string) geojsAnswer {
+	switch addr {
+	case fromDE:
+		return geojsAnswer{IP: addr, ASN: 64496, ASName: asNameDE, CountryCode: "DE"}
+	case fromKP:
+		return geojsAnswer{IP: addr, ASN: 64511, ASName: asNameKP, CountryCode: "KP"}
 	}
+
+	return geojsAnswer{IP: addr, ASN: 64512, ASName: "Unknown"}
 }

internal/proxy/history_test.go

@@ -24,7 +24,9 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
 	start := clk.Now()
 
 	// Two let through, one over the limit, which bans the client, and one
-	// refused under that ban, for which the country is not looked up.
+	// refused under that ban, for which the client is not looked up. GeoJS
+	// answers about the client at its first request, and its later ones
+	// use that answer.
 	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
 	clk.advance(time.Second)
 	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
@@ -35,8 +37,10 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
 	want := ratelimit.History{
 		FirstSeen: start,
 		LastSeen:  start.Add(2 * time.Second),
+		ASN:       asnDE,
+		ASName:    asNameDE,
 		Country:   "DE",
-		LookedUp:  start.Add(time.Second),
+		LookedUp:  start,
 		Requests:  4,
 		Forwarded: 2,
 		Refused:   2,

internal/proxy/lookup.go

@@ -0,0 +1,64 @@
+package proxy
+
+import (
+	"context"
+	"net/http"
+	"net/netip"
+
+	"sneak.berlin/go/smallwebwaf/internal/lookup"
+)
+
+// The headers in which the app is passed the client's AS number and
+// country while SWWAF_ADD_LOOKUP_HEADERS is set. Go writes every header
+// name in this form, as it sends it and as it receives it, so X-Client-ASN
+// arrives as X-Client-Asn, and Del removes a client's own whatever their
+// case; header names are not case-sensitive.
+const (
+	asnHeader     = "X-Client-Asn"
+	countryHeader = "X-Client-Country"
+)
+
+// lookUp looks up the client's AS number and country, and notes them for
+// the log line, unless SWWAF_LOOKUP_SOURCE is off or the client is on a
+// private, loopback or link-local address, which no lookup can place.
+// While a setting needs the answer, a new client's request waits for it.
+// ctx is the request's own context.
+func (rq *request) lookUp(ctx context.Context) {
+	if rq.h.config.LookupSource == "off" || !canBePlaced(rq.client) {
+		return
+	}
+
+	answer := rq.h.geojs.LookUp(ctx, clientGroup(rq.client))
+	rq.lookedUp = true
+	rq.line.ASN = answer.ASN
+	rq.line.ASName = answer.ASName
+	rq.line.Country = answer.Country
+}
+
+// addLookup adds answer, GeoJS's answer about a client, to the client's
+// history, and to the notes of the bans on its netblock that have no AS
+// number, AS name or country yet.
+func (h *handler) addLookup(answer lookup.Answer) {
+	h.limiter.AddLookup(answer.Client, answer.Answered,
+		answer.ASN, answer.ASName, answer.Country)
+	h.ledger.AddLookup(h.netblock(answer.Client.Addr()),
+		answer.ASN, answer.ASName, answer.Country)
+}
+
+// setLookupHeaders sets the headers in which the app is passed the
+// client's AS number and country, leaving out one that is unknown.
+func setLookupHeaders(header http.Header, asn, country string) {
+	if asn != "" {
+		header.Set(asnHeader, asn)
+	}
+
+	if country != "" {
+		header.Set(countryHeader, country)
+	}
+}
+
+// canBePlaced reports whether a lookup can place addr: private, loopback
+// and link-local addresses have no AS number or country.
+func canBePlaced(addr netip.Addr) bool {
+	return !addr.IsPrivate() && !addr.IsLoopback() && !addr.IsLinkLocalUnicast()
+}

internal/proxy/lookup_test.go

@@ -0,0 +1,313 @@
+package proxy_test
+
+import (
+	"net"
+	"net/http"
+	"net/http/httptest"
+	"net/netip"
+	"slices"
+	"sync"
+	"testing"
+	"testing/synctest"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/lookup"
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// asnAndCountry is what a lookup gives a client: its AS number, AS name
+// and country.
+type asnAndCountry struct{ asn, asName, country string }
+
+func TestEveryClientIsLookedUpWithoutWaitingWhileNoSettingNeedsIt(t *testing.T) {
+	t.Parallel()
+
+	// The stand-in for GeoJS answers only once released. A request that
+	// waited for it would wait an hour, and get no answer within
+	// waitLimit.
+	geojsURL, asked, release := startHeldGeoJS(t)
+	s, _, server := startWithClock(t, geojsURL, map[string]string{
+		lookupTimeout:      "1h",
+		rateLimitPerMinute: "1",
+	})
+
+	// fromDE's second request breaks the limit and bans it, and fromKP
+	// comes too. None waits for GeoJS.
+	for _, line := range []logLine{
+		s.get(fromDE, http.StatusOK, requestlog.ActionForward),
+		s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited),
+		s.get(fromKP, http.StatusOK, requestlog.ActionForward),
+	} {
+		got := asnAndCountry{line.ASN, line.ASName, line.Country}
+		if got != (asnAndCountry{}) {
+			t.Errorf("log line has %+v before GeoJS answered, want nothing", got)
+		}
+	}
+
+	// Once GeoJS answers, each answer reaches the client's history, and
+	// fromDE's reaches the notes of its ban.
+	release()
+
+	netblock := netip.MustParsePrefix(fromDE + "/32")
+
+	waitUntil(func() bool {
+		return historyOf(t, server, fromDE).ASN != "" &&
+			historyOf(t, server, fromKP).ASN != "" &&
+			server.Ledger.Bans(netblock)[0].Notes.ASN != ""
+	})
+
+	de := asnAndCountry{asnDE, asNameDE, "DE"}
+
+	for addr, want := range map[string]asnAndCountry{
+		fromDE: de, fromKP: {asnKP, asNameKP, "KP"},
+	} {
+		h := historyOf(t, server, addr)
+		if got := (asnAndCountry{h.ASN, h.ASName, h.Country}); got != want {
+			t.Errorf("%s's history has %+v, want %+v", addr, got, want)
+		}
+	}
+
+	notes := server.Ledger.Bans(netblock)[0].Notes
+	if got := (asnAndCountry{notes.ASN, notes.ASName, notes.Country}); got != de {
+		t.Errorf("the ban's notes have %+v, want %+v", got, de)
+	}
+
+	// GeoJS was asked about each client once, fromKP after fromDE, whose
+	// request was under way when fromKP came.
+	if got := asked(); !slices.Equal(got, []string{fromDE, fromKP}) {
+		t.Errorf("GeoJS was asked about %v, want %s and %s", got, fromDE, fromKP)
+	}
+}
+
+func TestASNumberAndNameInTheLogLineTheHistoryTheBanNotesAndTheAlert(t *testing.T) {
+	t.Parallel()
+
+	geojsURL, _ := startGeoJS(t)
+	app := startApp(t, func(http.ResponseWriter, *http.Request) {})
+	clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 0, 0, time.UTC)}
+	addr, out, server, queue := startProxyWithAlerts(t, app.URL, geojsURL, clk.Now,
+		map[string]string{
+			trustedProxies:     trustLocalhost,
+			alertWebhookURL:    "https://alerts.example/smallwebwaf",
+			rateLimitPerMinute: "1",
+		})
+	s := &sender{t: t, addr: addr, out: out}
+
+	// The answer is kept before the requests, so GeoJS is not asked, and
+	// gives no answer of its own.
+	netblock := netip.MustParsePrefix(fromDE + "/32")
+	server.GeoJS.Load([]lookup.Answer{{
+		Client: netblock, ASN: asnDE, ASName: asNameDE, Country: "DE",
+		Answered: clk.Now(), Used: clk.Now(),
+	}})
+
+	want := asnAndCountry{asnDE, asNameDE, "DE"}
+
+	for _, line := range []logLine{
+		s.get(fromDE, http.StatusOK, requestlog.ActionForward),
+		s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited),
+	} {
+		if got := (asnAndCountry{line.ASN, line.ASName, line.Country}); got != want {
+			t.Errorf("log line has %+v, want %+v", got, want)
+		}
+	}
+
+	h := historyOf(t, server, fromDE)
+	if got := (asnAndCountry{h.ASN, h.ASName, h.Country}); got != want ||
+		!h.LookedUp.Equal(clk.Now()) {
+		t.Errorf("history has %+v, looked up at %s; want %+v, at %s",
+			got, h.LookedUp, want, clk.Now())
+	}
+
+	notes := server.Ledger.Bans(netblock)[0].Notes
+	if got := (asnAndCountry{notes.ASN, notes.ASName, notes.Country}); got != want {
+		t.Errorf("the ban's notes have %+v, want %+v", got, want)
+	}
+
+	waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
+	if len(waiting) != 1 {
+		t.Fatalf("alerts waiting %+v, want the ban's alone", waiting)
+	}
+
+	alert := waiting[0]
+	if got := (asnAndCountry{alert.ASN, alert.ASName, alert.Country}); got != want {
+		t.Errorf("the ban's alert has %+v, want %+v", got, want)
+	}
+}
+
+func TestLookupSourceOffLooksNoClientUp(t *testing.T) {
+	t.Parallel()
+
+	geojsURL, asked := startGeoJS(t)
+	s, clk, server := startWithClock(t, geojsURL, map[string]string{lookupSource: "off"})
+
+	// Even an answer kept from before is not used.
+	server.GeoJS.Load([]lookup.Answer{{
+		Client: netip.MustParsePrefix(fromDE + "/32"), ASN: asnDE, ASName: asNameDE,
+		Country: "DE", Answered: clk.Now(), Used: clk.Now(),
+	}})
+
+	for _, from := range []string{fromDE, fromKP} {
+		line := s.get(from, http.StatusOK, requestlog.ActionForward)
+
+		got := asnAndCountry{line.ASN, line.ASName, line.Country}
+		if got != (asnAndCountry{}) {
+			t.Errorf("log line has %+v, want nothing", got)
+		}
+	}
+
+	if h := historyOf(t, server, fromDE); h.ASN != "" || !h.LookedUp.IsZero() {
+		t.Errorf("history has %q, looked up at %s, want no lookup", h.ASN, h.LookedUp)
+	}
+
+	if len(asked()) != 0 {
+		t.Errorf("GeoJS was asked about %v, want nothing", asked())
+	}
+}
+
+func TestLookupHeadersArePassedToTheAppAndTheClientsOwnRemoved(t *testing.T) {
+	t.Parallel()
+
+	var (
+		mu  sync.Mutex
+		got [][2][]string // each request's X-Client-ASN and X-Client-Country
+	)
+
+	app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
+		mu.Lock()
+		defer mu.Unlock()
+
+		got = append(got, [2][]string{
+			r.Header.Values("X-Client-Asn"), r.Header.Values("X-Client-Country"),
+		})
+	})
+	geojsURL, _ := startGeoJS(t)
+	addr, out, _ := startProxyWithClock(t, app.URL, geojsURL, time.Now, map[string]string{
+		trustedProxies:   trustLocalhost,
+		addLookupHeaders: "true",
+	})
+	s := &sender{t: t, addr: addr, out: out}
+
+	// Each client sends headers of its own. fromDE's first request waits
+	// for its answer, which the app is passed; unplaced has none to pass,
+	// and a client on a private address is not looked up.
+	for _, from := range []string{fromDE, unplaced, "10.0.0.8"} {
+		s.requestWithHeader(from, "/", clientsOwnLookupHeaders,
+			http.StatusOK, requestlog.ActionForward)
+	}
+
+	mu.Lock()
+	defer mu.Unlock()
+
+	want := [][2][]string{{{asnDE}, {"DE"}}, {nil, nil}, {nil, nil}}
+	if !slices.EqualFunc(got, want, func(a, b [2][]string) bool {
+		return slices.Equal(a[0], b[0]) && slices.Equal(a[1], b[1])
+	}) {
+		t.Errorf("the app was passed %v, want %v", got, want)
+	}
+}
+
+func TestClientsOwnLookupHeadersAreRemovedWhileTheSettingIsOff(t *testing.T) {
+	t.Parallel()
+
+	var (
+		mu           sync.Mutex
+		asn, country []string
+	)
+
+	app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
+		mu.Lock()
+		defer mu.Unlock()
+
+		asn, country = r.Header.Values("X-Client-Asn"), r.Header.Values("X-Client-Country")
+	})
+	geojsURL, _ := startGeoJS(t)
+	addr, out, _ := startProxyWithClock(t, app.URL, geojsURL, time.Now, map[string]string{
+		trustedProxies: trustLocalhost,
+	})
+	s := &sender{t: t, addr: addr, out: out}
+
+	s.requestWithHeader(fromDE, "/", clientsOwnLookupHeaders,
+		http.StatusOK, requestlog.ActionForward)
+
+	mu.Lock()
+	defer mu.Unlock()
+
+	if asn != nil || country != nil {
+		t.Errorf("the app was passed X-Client-ASN %v and X-Client-Country %v, want neither",
+			asn, country)
+	}
+}
+
+func TestRequestWaitsAsLongAsTheLookupTimeoutSays(t *testing.T) {
+	t.Parallel()
+
+	// The test runs in a synctest bubble, where the time package runs on a
+	// clock of the test's own: the wait lasts exactly as long as it should,
+	// however slowly the test process runs. Nothing in it may wait on the
+	// network, which would keep that clock from moving on: the request is
+	// handed to the proxy's handler, and GeoJS is one that never answers.
+	synctest.Test(t, func(t *testing.T) {
+		// Not the default second. The exclusive list needs the answer, and
+		// the app is never reached.
+		const timeout = 3 * time.Second
+
+		server, out, _ := newProxy(t, "http://app.invalid", unansweredGeoJSURL,
+			time.Now, map[string]string{
+				lookupTimeout:    timeout.String(),
+				allowedCountries: "DE",
+			})
+
+		req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/",
+			http.NoBody)
+		req.RemoteAddr = net.JoinHostPort(fromDE, "1234")
+		began := time.Now()
+
+		server.Handler.ServeHTTP(httptest.NewRecorder(), req)
+
+		if waited := time.Since(began); waited != timeout {
+			t.Errorf("the request waited %s for its answer, want %s", waited, timeout)
+		}
+
+		// Without an answer, the client is in no country the list allows.
+		wantLine(t, out.requestLine(t), http.StatusForbidden,
+			requestlog.ActionCountryDenied)
+	})
+}
+
+// unansweredGeoJSURL is where a GeoJS that never answers is asked: a
+// request to it waits, without the network, until it is abandoned.
+// TestMain registers it with Go's default transport, through which GeoJS
+// is asked.
+const unansweredGeoJSURL = "unanswered://geojs/v1/ip/geo.json"
+
+func TestMain(m *testing.M) {
+	transport, _ := http.DefaultTransport.(*http.Transport)
+	transport.RegisterProtocol("unanswered", unansweredGeoJS{})
+
+	m.Run()
+}
+
+// unansweredGeoJS is the GeoJS at unansweredGeoJSURL.
+type unansweredGeoJS struct{}
+
+// RoundTrip waits until req is abandoned.
+func (unansweredGeoJS) RoundTrip(req *http.Request) (*http.Response, error) {
+	<-req.Context().Done()
+
+	return nil, req.Context().Err()
+}
+
+// clientsOwnLookupHeaders are the X-Client-ASN and X-Client-Country a
+// client sends of its own, each twice, in two cases.
+const clientsOwnLookupHeaders = "X-Client-ASN: AS1\r\nx-client-asn: AS2\r\n" +
+	"X-CLIENT-COUNTRY: KP\r\nx-client-country: CN"
+
+// waitUntil waits until done reports true, for at most waitLimit.
+func waitUntil(done func() bool) {
+	deadline := time.Now().Add(waitLimit)
+	for !done() && time.Now().Before(deadline) {
+		time.Sleep(pollInterval)
+	}
+}

internal/proxy/metrics_test.go

@@ -291,7 +291,8 @@ func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
 		metricsTopN:     "2",
 		deniedCountries: "kp",
 	}
-	addr, out, server := startProxyWithClock(t, app.URL, "", time.Now, env)
+	geojsURL, _ := startGeoJS(t)
+	addr, out, server := startProxyWithClock(t, app.URL, geojsURL, time.Now, env)
 
 	// The answers are kept before the requests, so that none waits for
 	// GeoJS.
@@ -361,6 +362,46 @@ func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
 		`smallwebwaf_country_request_bytes_total{country="DE",instance="app"}`)
 }
 
+func TestMetricsByASNumberKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
+	t.Parallel()
+
+	geojsURL, _ := startGeoJS(t)
+	s, clk, server := startWithClock(t, geojsURL, map[string]string{
+		metricsToken: token,
+		metricsTopN:  "1",
+	})
+
+	// The answers are kept before the requests, so that GeoJS gives none
+	// of its own. Each client is in an AS of its own.
+	answer := func(addr, asn string) lookup.Answer {
+		return lookup.Answer{
+			Client: netip.MustParsePrefix(addr + "/32"), ASN: asn,
+			Answered: clk.Now(), Used: clk.Now(),
+		}
+	}
+	server.GeoJS.Load([]lookup.Answer{
+		answer(fromDE, "AS64501"), answer(fromKP, "AS64502"),
+	})
+
+	// With one AS number of its own, the other is counted as other. The
+	// metrics are asked for from a private address, which has no AS number.
+	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+	s.get(fromKP, http.StatusOK, requestlog.ActionForward)
+
+	metrics := s.scrape("10.0.0.9")
+	wantMetric(t, metrics,
+		`smallwebwaf_asn_requests_total{asn="AS64501",instance="app"}`, 2)
+	wantMetric(t, metrics,
+		`smallwebwaf_asn_requests_total{asn="other",instance="app"}`, 1)
+	wantMetric(t, metrics,
+		`smallwebwaf_asn_request_bytes_total{asn="AS64501",instance="app"}`, 0)
+	wantMetric(t, metrics,
+		`smallwebwaf_asn_response_bytes_total{asn="other",instance="app"}`, 0)
+	wantNoSeries(t, metrics,
+		`smallwebwaf_asn_requests_total{asn="AS64502",instance="app"}`)
+}
+
 func TestMetricsCountGeoJSRequestsAndFailures(t *testing.T) {
 	t.Parallel()
 

internal/proxy/proxy.go

@@ -54,8 +54,8 @@ type Params struct {
 	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 is where clients' AS numbers and countries are looked up,
+	// normally lookup.URL, unless SWWAF_LOOKUP_SOURCE is off.
 	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,
@@ -109,16 +109,23 @@ func New(params Params) *Server {
 			AttackBanDuration:    params.Config.AttackBanDuration,
 			MaxBans:              params.Config.MaxBans,
 		}),
-		geojs: lookup.New(lookup.Params{
-			URL:        params.GeoJSURL,
-			Now:        params.Now,
-			ProcessLog: params.ProcessLog,
-			Metrics:    m,
-			Alerts:     params.Alerts,
-		}),
 		rules:  params.Rules,
 		alerts: params.Alerts,
 	}
+	h.geojs = lookup.New(lookup.Params{
+		URL:     params.GeoJSURL,
+		Timeout: params.Config.LookupTimeout,
+		// The country lists and the headers act on the answer before the
+		// request goes on.
+		Wait: len(params.Config.DeniedCountries) > 0 ||
+			len(params.Config.ExclusivelyAllowedCountries) > 0 ||
+			params.Config.AddLookupHeaders,
+		Answered:   h.addLookup,
+		Now:        params.Now,
+		ProcessLog: params.ProcessLog,
+		Metrics:    m,
+		Alerts:     params.Alerts,
+	})
 	m.AddBansAndClients(h.ledger, h.limiter, params.Now)
 	m.AddRules(params.Rules)
 

internal/proxy/proxy_test.go

@@ -66,6 +66,9 @@ const (
 	rateLimitPerMinute      = "SWWAF_RATE_LIMIT_PER_MINUTE"
 	rateLimitPerDay         = "SWWAF_RATE_LIMIT_PER_DAY"
 	rateLimitExemptPaths    = "SWWAF_RATE_LIMIT_EXEMPT_PATHS"
+	lookupSource            = "SWWAF_LOOKUP_SOURCE"
+	lookupTimeout           = "SWWAF_LOOKUP_TIMEOUT"
+	addLookupHeaders        = "SWWAF_ADD_LOOKUP_HEADERS"
 	deniedCountries         = "SWWAF_DENIED_COUNTRIES"
 	allowedCountries        = "SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES"
 	banResponse             = "SWWAF_BAN_RESPONSE"
@@ -203,8 +206,8 @@ func startProxy(t *testing.T, appURL string, env map[string]string) (string, *ou
 	return startProxyWithGeoJS(t, appURL, "", env)
 }
 
-// startProxyWithGeoJS is startProxy with clients' countries looked up at
-// geojsURL.
+// startProxyWithGeoJS is startProxy with clients' AS numbers and
+// countries looked up at geojsURL.
 func startProxyWithGeoJS(
 	t *testing.T, appURL, geojsURL string, env map[string]string,
 ) (string, *output) {
@@ -232,17 +235,50 @@ func startProxyWithClock(
 }
 
 // startProxyWithAlerts is startProxyWithClock, and returns the queue of
-// the alerts the proxy raises as well, as the settings in env make it. No
-// alert is sent from it: they wait in it, for the test to look at.
+// the alerts the proxy raises as well, as newProxy makes them.
 func startProxyWithAlerts(
 	t *testing.T, appURL, geojsURL string, now func() time.Time,
 	env map[string]string,
 ) (string, *output, *proxy.Server, *alerts.Queue) {
 	t.Helper()
 
+	server, out, alertQueue := newProxy(t, appURL, geojsURL, now, env)
+
+	listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+
+	go func() {
+		_ = server.Serve(listener)
+	}()
+
+	t.Cleanup(func() {
+		_ = server.Close()
+	})
+
+	return listener.Addr().String(), out, server, alertQueue
+}
+
+// newProxy makes the server startProxyWithClock starts, without starting
+// it, and returns it, what it writes, and the queue of the alerts the
+// proxy raises, as the settings in env make it. No alert is sent from the
+// queue: they wait in it, for the test to look at. With no geojsURL, there
+// is no stand-in for GeoJS to look clients up at, and SWWAF_LOOKUP_SOURCE
+// is off unless env sets it.
+func newProxy(
+	t *testing.T, 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",
 	}
+	if geojsURL == "" {
+		settings[lookupSource] = "off"
+	}
+
 	maps.Copy(settings, env)
 
 	cfg, err := config.FromEnvironment(func(name string) (string, bool) {
@@ -284,20 +320,7 @@ func startProxyWithAlerts(
 		Alerts:     alertQueue,
 	})
 
-	listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
-	if err != nil {
-		t.Fatalf("listen: %v", err)
-	}
-
-	go func() {
-		_ = server.Serve(listener)
-	}()
-
-	t.Cleanup(func() {
-		_ = server.Close()
-	})
-
-	return listener.Addr().String(), out, server, alertQueue
+	return server, out, alertQueue
 }
 
 // newClient returns an HTTP client that sends requests as they are made,

internal/proxy/ratelimits_test.go

@@ -77,7 +77,8 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 
 	const denied = "192.0.2.50" // in SWWAF_DENY_NETS
 
-	s, _, server := startWithClock(t, "", map[string]string{
+	geojsURL, _ := startGeoJS(t)
+	s, _, server := startWithClock(t, geojsURL, map[string]string{
 		rateLimitPerMinute:   "1",
 		rateLimitExemptPaths: "/assets/,/favicon.ico",
 		denyNets:             denied,

internal/proxy/request.go

@@ -48,7 +48,10 @@ type request struct {
 	client      netip.Addr
 	peer        netip.Addr
 	peerTrusted bool
-	start       time.Time
+	// lookedUp is true once the client's AS number and country have been
+	// looked up, whether or not an answer was there.
+	lookedUp bool
+	start    time.Time
 	// checked is when the checks were done, and upstreamStart when the
 	// request was handed to the app.
 	checked       time.Time
@@ -192,14 +195,15 @@ func (rq *request) check(ctx context.Context) *refusal {
 
 // checkClient runs the checks on the request's client, and returns the
 // action of the first that refuses the request, or "" when none does. A
-// client in SWWAF_ALLOW_NETS skips them. For any other client,
-// SWWAF_DENY_NETS comes first, then a ban on its netblock, so that a
-// client either refuses is not looked up, and then the country lists; a
-// request any of them refuses is not counted for the rate limits. Then
-// come the rate limits, unless the client is in
-// SWWAF_RATE_LIMIT_EXEMPT_NETS or the request's path is exempt under
-// SWWAF_RATE_LIMIT_EXEMPT_PATHS, so that every other request is counted,
-// and last the rule files. ctx is the request's own context.
+// client in SWWAF_ALLOW_NETS skips them, and is not looked up. For any
+// other client, SWWAF_DENY_NETS comes first, then a ban on its netblock,
+// so that a client either refuses is not looked up, then the lookup of
+// its AS number and country, and then the country lists; a request any of
+// them refuses is not counted for the rate limits. Then come the rate
+// limits, unless the client is in SWWAF_RATE_LIMIT_EXEMPT_NETS or the
+// request's path is exempt under SWWAF_RATE_LIMIT_EXEMPT_PATHS, so that
+// every other request is counted, and last the rule files. ctx is the
+// request's own context.
 func (rq *request) checkClient(ctx context.Context) string {
 	cfg := rq.h.config
 	if isInside(rq.client, cfg.AllowNets) {
@@ -216,7 +220,9 @@ func (rq *request) checkClient(ctx context.Context) string {
 		return requestlog.ActionBanned
 	}
 
-	if rq.countryDenied(ctx) {
+	rq.lookUp(ctx)
+
+	if rq.countryDenied() {
 		return requestlog.ActionCountryDenied
 	}
 
@@ -287,7 +293,9 @@ func (rq *request) forward(ctx context.Context) {
 
 // rewrite makes the request the app receives: the client's request,
 // unchanged, sent to SWWAF_UPSTREAM_URL, with the forwarded headers and
-// the request's id set.
+// the request's id set, without any X-Client-ASN or X-Client-Country the
+// client sent, whatever SWWAF_ADD_LOOKUP_HEADERS says, and, while it is
+// set, with the client's AS number and country in them.
 func (rq *request) rewrite(pr *httputil.ProxyRequest) {
 	upstream := rq.h.config.UpstreamURL
 	pr.Out.URL.Scheme = upstream.Scheme
@@ -297,6 +305,12 @@ func (rq *request) rewrite(pr *httputil.ProxyRequest) {
 	pr.Out.URL.RawQuery = pr.In.URL.RawQuery
 	setForwardedHeaders(pr.In, pr.Out, rq.peer, rq.peerTrusted)
 	pr.Out.Header.Set(requestIDHeader, rq.line.RequestID)
+	pr.Out.Header.Del(asnHeader)
+	pr.Out.Header.Del(countryHeader)
+
+	if rq.h.config.AddLookupHeaders {
+		setLookupHeaders(pr.Out.Header, rq.line.ASN, rq.line.Country)
+	}
 }
 
 // modifyResponse looks at the app's answer before ReverseProxy passes it
@@ -474,7 +488,10 @@ func timing(start, end time.Time) *float64 {
 }
 
 // addToHistory adds the request, which has ended, to its client's
-// history.
+// history, and then, for a client that was looked up, the answer kept
+// about it to that history and to the notes of the bans on its netblock:
+// an answer that came during the request may have come before either was
+// there, and one that comes later is added when it comes.
 func (rq *request) addToHistory() {
 	var requestBytes int64
 	if rq.body != nil {
@@ -482,9 +499,9 @@ func (rq *request) addToHistory() {
 	}
 
 	forwarded := !rq.upstreamStart.IsZero()
+	group := clientGroup(rq.client)
 
-	rq.h.limiter.AddToHistory(clientGroup(rq.client), rq.h.now(), ratelimit.Request{
-		Country:       rq.line.Country,
+	rq.h.limiter.AddToHistory(group, rq.h.now(), ratelimit.Request{
 		Forwarded:     forwarded,
 		Refused:       !forwarded && rq.refused.Load() != nil,
 		Status:        rq.out.status,
@@ -492,6 +509,15 @@ func (rq *request) addToHistory() {
 		ResponseBytes: rq.out.bytes,
 		BrokeLimit:    rq.line.Offence == requestlog.OffenceLimit,
 	})
+
+	if !rq.lookedUp {
+		return
+	}
+
+	answer, kept := rq.h.geojs.Kept(group)
+	if kept {
+		rq.h.addLookup(answer)
+	}
 }
 
 // clientRequestDeadline is when the client must have sent its whole