Request tags, with refusing and limits per tag (closes #175)

Each request gets sorted tags from the lookup, new address lists, the
reputation sources and the rule matches, logged as `tags`. New settings:
`SWW_TAG_LISTS`, `SWW_TAG_DENY`, `SWW_TAG_LIMIT_PERCENT`. They replace
`SWW_ASN_LIMIT_PERCENT`, `SWW_COUNTRY_LIMIT_PERCENT` and
`SWW_DENIED_COUNTRIES`. New heuristics `tag_lists` and `tag_deny`; the
latter runs before the rate limits and again after the Core Rule Set.

Model: opus-5-5

internal/config/config.go

@@ -93,29 +93,30 @@ type Config struct {
 	LookupDBPath     string
 	LookupTimeout    time.Duration
 	AddLookupHeaders bool
-	// DeniedCountries are the countries whose clients are refused
-	// (SWW_DENIED_COUNTRIES). ExclusivelyAllowedCountries, when not
-	// empty, are the only countries whose clients are let through
-	// (SWW_EXCLUSIVELY_ALLOWED_COUNTRIES). Both hold two-letter codes in
-	// capitals, as GeoJS gives them.
-	DeniedCountries             []string
+	// ExclusivelyAllowedCountries, when not empty, are the only countries
+	// whose clients are let through (SWW_EXCLUSIVELY_ALLOWED_COUNTRIES),
+	// two-letter codes in capitals, as GeoJS gives them.
 	ExclusivelyAllowedCountries []string
-	// The biased thresholds. ASNLimitPercent and CountryLimitPercent give
-	// the clients of the AS numbers and the countries they list that
-	// percentage of every rate limit and byte limit
-	// (SWW_ASN_LIMIT_PERCENT and SWW_COUNTRY_LIMIT_PERCENT).
-	// ASNBytesPercent and CountryBytesPercent give those they list a
-	// percentage of the byte limits in place of that one
+	// TagLists are the address lists that each add a tag to the requests of
+	// the clients they hold (SWW_TAG_LISTS). TagDeny are the tags whose
+	// requests are refused (SWW_TAG_DENY). TagLimitPercent gives the clients
+	// with a tag that percentage of every rate limit and byte limit, from 1
+	// to 99 (SWW_TAG_LIMIT_PERCENT). All hold tags in lower case, as requests
+	// carry them.
+	TagLists        []TagList
+	TagDeny         []string
+	TagLimitPercent map[string]int64
+	// The biased thresholds. ASNBytesPercent and CountryBytesPercent give
+	// those they list a percentage of the byte limits in place of the one
+	// TagLimitPercent gives their asn= or country= tag
 	// (SWW_ASN_BYTES_PERCENT and SWW_COUNTRY_BYTES_PERCENT). Each holds
 	// percentages from 0 to 100, by AS number, written as AS64496, or by
 	// country, a two-letter code in capitals, as the lookup gives them.
 	// UnknownLimitPercent is the percentage of every limit a client without
 	// a country gets (SWW_UNKNOWN_LIMIT_PERCENT). ASNLimitPercentURL is
 	// where a file of AS:percent lines is fetched from, whose percentages
-	// count as those of ASNLimitPercent do (SWW_ASN_LIMIT_PERCENT_URL), ""
-	// while it is unset.
-	ASNLimitPercent     map[string]int64
-	CountryLimitPercent map[string]int64
+	// count as asn= tags in TagLimitPercent do (SWW_ASN_LIMIT_PERCENT_URL),
+	// "" while it is unset.
 	ASNBytesPercent     map[string]int64
 	CountryBytesPercent map[string]int64
 	UnknownLimitPercent int64
@@ -367,7 +368,7 @@ var (
 	errHeaderTakenOut = errors.New(
 		"is taken out of every request by Go's HTTP server, so it can never " +
 			"be logged")
-	errOnBothLists     = errors.New("is in SWW_DENIED_COUNTRIES too")
+	errOnBothLists     = errors.New("is in SWW_TAG_DENY too")
 	errNotLookupSource = errors.New("is not geojs, file or off")
 	errNeedsLookups    = errors.New("it needs each client looked up")
 	errNeedsDBPath     = errors.New("it names the file to look clients up in")
@@ -451,6 +452,18 @@ var (
 	errLAPIKeyUnused = errors.New("it is sent only to the engine at that URL")
 	errAnotherList   = errors.New(
 		"is in SWW_BLOCKLIST_URLS or is SWW_ASN_LIMIT_PERCENT_URL too")
+	errFetchedOtherwise = errors.New("is in SWW_BLOCKLIST_URLS, is " +
+		"SWW_ASN_LIMIT_PERCENT_URL or is the CrowdSec decision list too")
+	errNotTagList = errors.New(
+		"is not a name, = and an http or https URL, such as " +
+			"torexit=https://example.com/tor.txt")
+	errNotTagPercentItem = errors.New(
+		"is not a tag, : and a percentage, such as vpn:50 or asn=14061:25")
+	errNotTagPercent = errors.New("is not a percentage from 1 to 99")
+	errNotASNTag     = errors.New("is not asn= and a number, such as asn=14061")
+	errExploitTag    = errors.New(
+		"cannot lower limits: the rate limits count a request before its " +
+			"rules are matched")
 )
 
 // FromEnvironment reads the settings with lookupEnv, normally
@@ -483,11 +496,11 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		LookupDBPath:         env.value("SWW_LOOKUP_DB_PATH", ""),
 		LookupTimeout:        env.durationNotOff("SWW_LOOKUP_TIMEOUT", "800ms"),
 		AddLookupHeaders:     env.boolean("SWW_ADD_LOOKUP_HEADERS", "false"),
-		DeniedCountries:      env.countries("SWW_DENIED_COUNTRIES", ""),
 		ExclusivelyAllowedCountries: env.countries(
 			"SWW_EXCLUSIVELY_ALLOWED_COUNTRIES", ""),
-		ASNLimitPercent:      env.percents("SWW_ASN_LIMIT_PERCENT", ParseASN),
-		CountryLimitPercent:  env.percents("SWW_COUNTRY_LIMIT_PERCENT", parseCountry),
+		TagLists:             env.tagLists("SWW_TAG_LISTS"),
+		TagDeny:              env.tags("SWW_TAG_DENY"),
+		TagLimitPercent:      env.tagPercents("SWW_TAG_LIMIT_PERCENT"),
 		ASNBytesPercent:      env.percents("SWW_ASN_BYTES_PERCENT", ParseASN),
 		CountryBytesPercent:  env.percents("SWW_COUNTRY_BYTES_PERCENT", parseCountry),
 		UnknownLimitPercent:  env.percent("SWW_UNKNOWN_LIMIT_PERCENT", "100"),
@@ -567,6 +580,7 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 	env.checkCountriesAndLookups(cfg)
 	env.checkASNLimitPercentURL(cfg)
 	env.checkCrowdSec(cfg)
+	env.checkTagLists(cfg)
 
 	if env.err != nil {
 		return nil, env.err
@@ -841,6 +855,31 @@ func (e *environment) percents(
 	return percents
 }
 
+// tagLists reads SWW_TAG_LISTS, which is empty by default.
+func (e *environment) tagLists(name string) []TagList {
+	lists, err := parseTagLists(e.value(name, ""))
+	e.check(name, err)
+
+	return lists
+}
+
+// tags reads a setting that is a list of tags. It is empty by default.
+func (e *environment) tags(name string) []string {
+	tags, err := parseTags(e.value(name, ""))
+	e.check(name, err)
+
+	return tags
+}
+
+// tagPercents reads a setting that is a list of tags, each with a
+// percentage. It is empty by default.
+func (e *environment) tagPercents(name string) map[string]int64 {
+	percents, err := parseTagPercents(e.value(name, ""))
+	e.check(name, err)
+
+	return percents
+}
+
 // percent reads a setting that is a percentage, from 0 to 100.
 func (e *environment) percent(name, defaultValue string) int64 {
 	percent, err := ParsePercent(e.value(name, defaultValue))
@@ -975,15 +1014,17 @@ func (e *environment) checkLookupDBPath(cfg *Config) {
 	}
 }
 
-// checkCountriesAndLookups refuses a country on both country lists, and,
+// checkCountriesAndLookups refuses a country in
+// SWW_EXCLUSIVELY_ALLOWED_COUNTRIES whose tag is in SWW_TAG_DENY, and,
 // while SWW_LOOKUP_SOURCE is off, each setting that needs clients looked
-// up: the country lists, SWW_ADD_LOOKUP_HEADERS, the biased thresholds,
+// up: the country list, SWW_ADD_LOOKUP_HEADERS, the tag settings that name
+// an asn= or country= tag, the biased thresholds,
 // SWW_ASN_LIMIT_PERCENT_URL among them, of which
 // SWW_UNKNOWN_LIMIT_PERCENT needs them only below 100, where it lowers a
 // limit, and the anomaly thresholds per AS number.
 func (e *environment) checkCountriesAndLookups(cfg *Config) {
 	for _, country := range cfg.ExclusivelyAllowedCountries {
-		if slices.Contains(cfg.DeniedCountries, country) {
+		if slices.Contains(cfg.TagDeny, countryTagPrefix+strings.ToLower(country)) {
 			e.check("SWW_EXCLUSIVELY_ALLOWED_COUNTRIES",
 				fmt.Errorf("%q %w", country, errOnBothLists))
 		}
@@ -997,11 +1038,10 @@ func (e *environment) checkCountriesAndLookups(cfg *Config) {
 		name string
 		set  bool
 	}{
-		{"SWW_DENIED_COUNTRIES", len(cfg.DeniedCountries) > 0},
 		{"SWW_EXCLUSIVELY_ALLOWED_COUNTRIES", len(cfg.ExclusivelyAllowedCountries) > 0},
 		{"SWW_ADD_LOOKUP_HEADERS", cfg.AddLookupHeaders},
-		{"SWW_ASN_LIMIT_PERCENT", len(cfg.ASNLimitPercent) > 0},
-		{"SWW_COUNTRY_LIMIT_PERCENT", len(cfg.CountryLimitPercent) > 0},
+		{"SWW_TAG_DENY", slices.ContainsFunc(cfg.TagDeny, isLookupTag)},
+		{"SWW_TAG_LIMIT_PERCENT", tagLimitNeedsLookups(cfg)},
 		{"SWW_ASN_BYTES_PERCENT", len(cfg.ASNBytesPercent) > 0},
 		{"SWW_COUNTRY_BYTES_PERCENT", len(cfg.CountryBytesPercent) > 0},
 		{"SWW_UNKNOWN_LIMIT_PERCENT", cfg.UnknownLimitPercent < 100},
@@ -1047,6 +1087,40 @@ func (e *environment) checkCrowdSec(cfg *Config) {
 	}
 }
 
+// checkTagLists refuses a list of SWW_TAG_LISTS whose URL is fetched as
+// another list too: the file at a URL is read as one kind of list.
+func (e *environment) checkTagLists(cfg *Config) {
+	for _, list := range cfg.TagLists {
+		if slices.Contains(cfg.BlocklistURLs, list.URL) ||
+			list.URL == cfg.ASNLimitPercentURL || list.URL == cfg.CrowdSecDecisionsURL {
+			e.check("SWW_TAG_LISTS", fmt.Errorf("%q %w", list.URL, errFetchedOtherwise))
+		}
+	}
+}
+
+// TagsNeedLookup reports whether SWW_TAG_DENY or SWW_TAG_LIMIT_PERCENT
+// names an asn= or country= tag, which only the lookup can give a request.
+func (c *Config) TagsNeedLookup() bool {
+	return slices.ContainsFunc(c.TagDeny, isLookupTag) || tagLimitNeedsLookups(c)
+}
+
+// tagLimitNeedsLookups reports whether SWW_TAG_LIMIT_PERCENT names an asn=
+// or country= tag.
+func tagLimitNeedsLookups(cfg *Config) bool {
+	for tag := range cfg.TagLimitPercent {
+		if isLookupTag(tag) {
+			return true
+		}
+	}
+
+	return false
+}
+
+// isLookupTag reports whether tag is an asn= or country= tag.
+func isLookupTag(tag string) bool {
+	return strings.HasPrefix(tag, asnTagPrefix) || strings.HasPrefix(tag, countryTagPrefix)
+}
+
 // headerNames reads a setting that is a list of header names, and
 // returns them in lower case.
 func (e *environment) headerNames(name, defaultValue string) []string {
@@ -1752,6 +1826,149 @@ func ParseASN(value string) (string, error) {
 	return "AS" + strconv.FormatUint(number, 10), nil
 }
 
+// The prefixes of the tags the lookup gives a request.
+const (
+	asnTagPrefix     = "asn="
+	countryTagPrefix = "country="
+)
+
+// ExploitSignatureTag is the tag of a request a rule file or the Core Rule
+// Set matched.
+const ExploitSignatureTag = "exploitsignature"
+
+// TagList is an address list of SWW_TAG_LISTS: the tag it adds to the
+// requests of the clients it holds, and the URL it is fetched from.
+type TagList struct {
+	Name string
+	URL  string
+}
+
+// parseTagLists reads a comma-separated list of name=URL pairs, such as
+// torexit=https://example.com/tor.txt, and returns each list with its name
+// in lower case. A name can hold a =, as vpn=mullvad does, and ends at the
+// = before http. A name or a URL listed twice is an error.
+func parseTagLists(value string) ([]TagList, error) {
+	items, err := parseList(value)
+	if err != nil {
+		return nil, err
+	}
+
+	lists := make([]TagList, 0, len(items))
+
+	for _, item := range items {
+		end := strings.Index(item, "=http")
+		if end <= 0 || !isListURL(item[end+1:]) {
+			return nil, fmt.Errorf("%q %w", item, errNotTagList)
+		}
+
+		list := TagList{Name: strings.ToLower(item[:end]), URL: item[end+1:]}
+
+		if slices.ContainsFunc(lists, func(earlier TagList) bool {
+			return earlier.Name == list.Name || earlier.URL == list.URL
+		}) {
+			return nil, fmt.Errorf("%q %w", item, errListedTwice)
+		}
+
+		lists = append(lists, list)
+	}
+
+	return lists, nil
+}
+
+// parseTags reads a comma-separated list of tags, which parseTag reads. A
+// tag listed twice is an error.
+func parseTags(value string) ([]string, error) {
+	items, err := parseList(value)
+	if err != nil {
+		return nil, err
+	}
+
+	tags := make([]string, 0, len(items))
+
+	for _, item := range items {
+		tag, err := parseTag(item)
+		if err != nil {
+			return nil, err
+		}
+
+		if slices.Contains(tags, tag) {
+			return nil, fmt.Errorf("%q %w", item, errListedTwice)
+		}
+
+		tags = append(tags, tag)
+	}
+
+	return tags, nil
+}
+
+// parseTag reads a tag in either case, and returns it as a request carries
+// it: in lower case, an asn= tag's number without leading zeros. An asn= or
+// country= tag must name a number or a country, so that a mistyped one
+// stops the start instead of never matching.
+func parseTag(value string) (string, error) {
+	tag := strings.ToLower(value)
+
+	if digits, isASN := strings.CutPrefix(tag, asnTagPrefix); isASN {
+		number, err := strconv.ParseUint(digits, 10, 32)
+		if err != nil {
+			return "", fmt.Errorf("%q %w", value, errNotASNTag)
+		}
+
+		return asnTagPrefix + strconv.FormatUint(number, 10), nil
+	}
+
+	if code, isCountry := strings.CutPrefix(tag, countryTagPrefix); isCountry {
+		_, err := parseCountry(code)
+		if err != nil {
+			return "", err
+		}
+	}
+
+	return tag, nil
+}
+
+// parseTagPercents reads a comma-separated list of tags, each with : and a
+// percentage from 1 to 99, such as vpn:50 or asn=14061:25. A tag listed
+// twice is an error, and so is ExploitSignatureTag, which a request gets
+// only after the rate limits have counted it.
+func parseTagPercents(value string) (map[string]int64, error) {
+	items, err := parseList(value)
+	if err != nil {
+		return nil, err
+	}
+
+	percents := make(map[string]int64, len(items))
+
+	for _, item := range items {
+		colon := strings.LastIndex(item, ":")
+		if colon <= 0 {
+			return nil, fmt.Errorf("%q %w", item, errNotTagPercentItem)
+		}
+
+		tag, err := parseTag(item[:colon])
+		if err != nil {
+			return nil, err
+		}
+
+		percent, err := strconv.ParseInt(item[colon+1:], 10, 64)
+		if err != nil || percent < 1 || percent > 99 {
+			return nil, fmt.Errorf("%q %w", item[colon+1:], errNotTagPercent)
+		}
+
+		if tag == ExploitSignatureTag {
+			return nil, fmt.Errorf("%q %w", tag, errExploitTag)
+		}
+
+		if _, listed := percents[tag]; listed {
+			return nil, fmt.Errorf("%q %w", item[:colon], errListedTwice)
+		}
+
+		percents[tag] = percent
+	}
+
+	return percents, nil
+}
+
 // parsePercents reads a comma-separated list of items, each an AS number
 // or a country, which parseCode reads, then : and a percentage, such as
 // AS64496:50 or cn:25, and returns each one's percentage. An empty value

internal/config/config_test.go

@@ -42,10 +42,10 @@ const (
 	lookupDBPath         = "SWW_LOOKUP_DB_PATH"
 	lookupTimeout        = "SWW_LOOKUP_TIMEOUT"
 	addLookupHeaders     = "SWW_ADD_LOOKUP_HEADERS"
-	deniedCountries      = "SWW_DENIED_COUNTRIES"
 	allowedCountries     = "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"
-	asnLimitPercent      = "SWW_ASN_LIMIT_PERCENT"
-	countryLimitPercent  = "SWW_COUNTRY_LIMIT_PERCENT"
+	tagLists             = "SWW_TAG_LISTS"
+	tagDeny              = "SWW_TAG_DENY"
+	tagLimitPercent      = "SWW_TAG_LIMIT_PERCENT"
 	asnBytesPercent      = "SWW_ASN_BYTES_PERCENT"
 	countryBytesPercent  = "SWW_COUNTRY_BYTES_PERCENT"
 	unknownLimitPercent  = "SWW_UNKNOWN_LIMIT_PERCENT"
@@ -274,9 +274,13 @@ func TestDefaults(t *testing.T) {
 	wantNetblocks(t, cfg.AllowNets)
 	wantNetblocks(t, cfg.RateLimitExemptNets)
 	wantNetblocks(t, cfg.DenyNets)
-	wantCountries(t, deniedCountries, cfg.DeniedCountries)
 	wantCountries(t, allowedCountries, cfg.ExclusivelyAllowedCountries)
 
+	if len(cfg.TagLists) != 0 || len(cfg.TagDeny) != 0 || len(cfg.TagLimitPercent) != 0 {
+		t.Errorf("tag settings %v, %v and %v by default, want all empty",
+			cfg.TagLists, cfg.TagDeny, cfg.TagLimitPercent)
+	}
+
 	hostname, err := os.Hostname()
 	if err != nil || hostname == "" || cfg.InstanceName != hostname {
 		t.Errorf("%s is %q, want the host's name %q (%v)", instanceName,
@@ -327,7 +331,6 @@ func TestValuesAsSet(t *testing.T) {
 		rateLimitPerMinute:   "60",
 		rateLimitPerHour:     "600",
 		rateLimitPerDay:      "6000",
-		deniedCountries:      "cn, RU,kp,Xk",
 		allowedCountries:     "de",
 		banResponse:          "429",
 		limitBanDuration:     "15m",
@@ -370,7 +373,6 @@ func TestValuesAsSet(t *testing.T) {
 	wantNetblocks(t, cfg.AllowNets, "192.0.2.7/32")
 	wantNetblocks(t, cfg.RateLimitExemptNets, "2001:db8::/48", "10.9.8.7/32")
 	wantNetblocks(t, cfg.DenyNets, "198.51.100.0/24")
-	wantCountries(t, deniedCountries, cfg.DeniedCountries, "CN", "RU", "KP", "XK")
 	wantCountries(t, allowedCountries, cfg.ExclusivelyAllowedCountries, "DE")
 }
 
@@ -1101,7 +1103,7 @@ func TestCodeOnBothCountryListsStopsTheStart(t *testing.T) {
 	t.Parallel()
 
 	_, err := config.FromEnvironment(environment{
-		deniedCountries:  "cn,ru",
+		tagDeny:          "country=cn,country=ru",
 		allowedCountries: "de,RU",
 	}.lookupEnv)
 	if err == nil {
@@ -1176,12 +1178,11 @@ func TestSettingNeedingLookupsStopsTheStartWhileTheyAreOff(t *testing.T) {
 	t.Parallel()
 
 	for name, value := range map[string]string{
-		deniedCountries:                "kp",
 		allowedCountries:               "de",
 		addLookupHeaders:               enabled,
+		tagDeny:                        "country=kp",
+		tagLimitPercent:                "asn=64496:50",
 		asnLimitPercentURL:             asnURL,
-		asnLimitPercent:                "AS64496:50",
-		countryLimitPercent:            "cn:25",
 		asnBytesPercent:                "AS64496:50",
 		countryBytesPercent:            "cn:25",
 		unknownLimitPercent:            "99",
@@ -1204,12 +1205,12 @@ func TestSettingNeedingLookupsStopsTheStartWhileTheyAreOff(t *testing.T) {
 	}
 
 	// Set empty, the lists need nothing looked up, and nor does
-	// SWW_UNKNOWN_LIMIT_PERCENT at 100, which lowers no limit, an anomaly
-	// threshold per AS number that is off, any other anomaly threshold, or
-	// a blocklist.
+	// SWW_UNKNOWN_LIMIT_PERCENT at 100, which lowers no limit, a tag the
+	// lookup does not give, an anomaly threshold per AS number that is off,
+	// any other anomaly threshold, or a blocklist.
 	env := environment{
-		lookupSource: off, deniedCountries: "", allowedCountries: "",
-		asnLimitPercent: "", countryLimitPercent: "", asnBytesPercent: "",
+		lookupSource: off, allowedCountries: "", asnBytesPercent: "",
+		tagDeny: torExitTag, tagLimitPercent: "vpn:50",
 		countryBytesPercent: "", unknownLimitPercent: "100", asnLimitPercentURL: "",
 		blocklistURLs: dropURL,
 	}
@@ -1355,34 +1356,96 @@ func TestInvalidAnomalySettingStopsTheStartSayingWhatIsWrong(t *testing.T) {
 	}
 }
 
+// torExitTag is a tag these tests name.
+const torExitTag = "torexit"
+
+func TestTagSettingsAsSet(t *testing.T) {
+	t.Parallel()
+
+	const torURL = "https://example.com/tor.txt"
+
+	// Names and tags in either case, an AS number with leading zeros, and a
+	// name holding a =.
+	cfg := fromEnvironment(t, environment{
+		tagLists: "TorExit=" + torURL +
+			", vpn=mullvad=https://example.com/mullvad.txt",
+		tagDeny:         "TorExit, Country=KP, asn=014061",
+		tagLimitPercent: "vpn:50, asn=014061:25, COUNTRY=cn:1, dnsbl=zen.example:99",
+	})
+
+	wantLists := []config.TagList{
+		{Name: torExitTag, URL: torURL},
+		{Name: "vpn=mullvad", URL: "https://example.com/mullvad.txt"},
+	}
+	if !slices.Equal(cfg.TagLists, wantLists) {
+		t.Errorf("%s gave %+v, want %+v", tagLists, cfg.TagLists, wantLists)
+	}
+
+	wantDeny := []string{torExitTag, "country=kp", "asn=14061"}
+	if !slices.Equal(cfg.TagDeny, wantDeny) {
+		t.Errorf("%s gave %v, want %v", tagDeny, cfg.TagDeny, wantDeny)
+	}
+
+	wantPercents := map[string]int64{
+		"vpn": 50, "asn=14061": 25, "country=cn": 1, "dnsbl=zen.example": 99,
+	}
+	if !maps.Equal(cfg.TagLimitPercent, wantPercents) {
+		t.Errorf("%s gave %v, want %v", tagLimitPercent, cfg.TagLimitPercent, wantPercents)
+	}
+}
+
+func TestTagListURLFetchedAsAnotherListStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	const lapi = "http://172.17.0.1:8080"
+
+	for _, tc := range []struct {
+		name, listURL string
+		env           environment
+	}{
+		{"a blocklist", dropURL, environment{blocklistURLs: dropURL}},
+		{"the file of AS:percent lines", asnURL, environment{asnLimitPercentURL: asnURL}},
+		{
+			"the CrowdSec decision list", lapi + "/v1/decisions",
+			environment{"SWW_CROWDSEC_LAPI_URL": lapi, "SWW_CROWDSEC_LAPI_KEY": "key"},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			tc.env[tagLists] = "dup=" + tc.listURL
+
+			want := tagLists + `: "` + tc.listURL + `" is in SWW_BLOCKLIST_URLS, is ` +
+				"SWW_ASN_LIMIT_PERCENT_URL or is the CrowdSec decision list too"
+
+			_, err := config.FromEnvironment(tc.env.lookupEnv)
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
 func TestBiasedThresholdsAsSet(t *testing.T) {
 	t.Parallel()
 
 	cfg := fromEnvironment(t, environment{})
-	if len(cfg.ASNLimitPercent) != 0 || len(cfg.CountryLimitPercent) != 0 ||
-		len(cfg.ASNBytesPercent) != 0 || len(cfg.CountryBytesPercent) != 0 ||
+	if len(cfg.ASNBytesPercent) != 0 || len(cfg.CountryBytesPercent) != 0 ||
 		cfg.UnknownLimitPercent != 100 {
-		t.Errorf("biased thresholds %v, %v, %v, %v and %d by default, "+
-			"want four empty lists and 100", cfg.ASNLimitPercent, cfg.CountryLimitPercent,
+		t.Errorf("biased thresholds %v, %v and %d by default, "+
+			"want two empty lists and 100",
 			cfg.ASNBytesPercent, cfg.CountryBytesPercent, cfg.UnknownLimitPercent)
 	}
 
 	// AS numbers and countries in either case, an AS number with leading
 	// zeros, 0 and 100.
 	cfg = fromEnvironment(t, environment{
-		asnLimitPercent:     "AS14061:50, as16276:0,AS045102:100",
-		countryLimitPercent: "cn:25,RU:50",
 		asnBytesPercent:     "as16276:75",
 		countryBytesPercent: "ru:10",
 		unknownLimitPercent: "0",
 	})
 
 	for name, tc := range map[string]struct{ got, want map[string]int64 }{
-		asnLimitPercent: {
-			cfg.ASNLimitPercent,
-			map[string]int64{"AS14061": 50, "AS16276": 0, "AS45102": 100},
-		},
-		countryLimitPercent: {cfg.CountryLimitPercent, map[string]int64{"CN": 25, "RU": 50}},
 		asnBytesPercent:     {cfg.ASNBytesPercent, map[string]int64{"AS16276": 75}},
 		countryBytesPercent: {cfg.CountryBytesPercent, map[string]int64{"RU": 10}},
 	} {
@@ -1406,16 +1469,16 @@ func TestInvalidBiasedThresholdStopsTheStartSayingWhatIsWrong(t *testing.T) {
 	)
 
 	for _, tc := range []struct{ name, value, want string }{
-		{asnLimitPercent, "14061:50", `"14061"` + notASN},
-		{asnLimitPercent, "AS4294967296:50", `"AS4294967296"` + notASN},
-		{asnLimitPercent, "AS14061", `"AS14061"` + notItem},
-		{asnLimitPercent, "AS14061:101", `"101"` + notPercent},
-		{asnLimitPercent, "AS14061:50,as14061:25", `"as14061" is listed twice`},
+		{asnBytesPercent, "14061:50", `"14061"` + notASN},
+		{asnBytesPercent, "AS4294967296:50", `"AS4294967296"` + notASN},
+		{asnBytesPercent, "AS14061", `"AS14061"` + notItem},
+		{asnBytesPercent, "AS14061:101", `"101"` + notPercent},
+		{asnBytesPercent, "AS14061:50,as14061:25", `"as14061" is listed twice`},
 		{
-			countryLimitPercent, "nk:25",
+			countryBytesPercent, "nk:25",
 			`"nk" is not a two-letter country code such as de or kp`,
 		},
-		{countryLimitPercent, "cn:25,CN:50", `"CN" is listed twice`},
+		{countryBytesPercent, "cn:25,CN:50", `"CN" is listed twice`},
 		{asnBytesPercent, "AS14061:-1", `"-1"` + notPercent},
 		{countryBytesPercent, "cn:50%", `"50%"` + notPercent},
 		{unknownLimitPercent, "101", `"101"` + notPercent},
@@ -2003,23 +2066,34 @@ func TestInvalidValueStopsTheStart(t *testing.T) {
 		{lookupSource, "ipinfo"}, {lookupSource, "GeoJS"}, {lookupSource, ""},
 		{lookupTimeout, off}, {lookupTimeout, "0s"}, {lookupTimeout, "1"},
 		{addLookupHeaders, "yes"},
-		{deniedCountries, "nk"},
-		{deniedCountries, "kp,,ir"},
-		{deniedCountries, "prk"},
-		{deniedCountries, "408"},
-		{deniedCountries, "k"},
-		{deniedCountries, "eu"},
-		{deniedCountries, "un"},
-		{deniedCountries, "su"},
+		{allowedCountries, "nk"},
+		{allowedCountries, "kp,,ir"},
+		{allowedCountries, "prk"},
+		{allowedCountries, "408"},
+		{allowedCountries, "k"},
+		{allowedCountries, "eu"},
+		{allowedCountries, "un"},
+		{allowedCountries, "su"},
 		{allowedCountries, "ac"},
 		{allowedCountries, "uk"},
 		{allowedCountries, "zz"},
 		{allowedCountries, "de,germany"},
-		{asnLimitPercent, "AS14061:50,,AS16276:50"}, {asnLimitPercent, "ASX:50"},
-		{asnLimitPercent, "AS14061:"}, {asnLimitPercent, "AS14061 :50"},
-		{asnLimitPercent, "AS14061:1.5"}, {asnLimitPercent, "AS-1:50"},
-		{countryLimitPercent, "cn"}, {countryLimitPercent, "cn:"},
-		{countryLimitPercent, "cn:25:50"}, {countryLimitPercent, "china:25"},
+		{asnBytesPercent, "AS14061:50,,AS16276:50"}, {asnBytesPercent, "ASX:50"},
+		{asnBytesPercent, "AS14061:"}, {asnBytesPercent, "AS14061 :50"},
+		{asnBytesPercent, "AS14061:1.5"}, {asnBytesPercent, "AS-1:50"},
+		{countryBytesPercent, "cn"}, {countryBytesPercent, "cn:"},
+		{countryBytesPercent, "cn:25:50"}, {countryBytesPercent, "china:25"},
+		{tagDeny, "a,,b"}, {tagDeny, "country=nk"}, {tagDeny, "asn=abc"},
+		{tagDeny, "asn="}, {tagDeny, "torexit,TOREXIT"},
+		{tagLimitPercent, "vpn"}, {tagLimitPercent, ":50"}, {tagLimitPercent, "vpn:"},
+		{tagLimitPercent, "vpn:0"}, {tagLimitPercent, "vpn:100"},
+		{tagLimitPercent, "vpn:1.5"}, {tagLimitPercent, "vpn:50,VPN:25"},
+		{tagLimitPercent, "exploitsignature:50"}, {tagLimitPercent, "asn=abc:50"},
+		{tagLists, torExitTag}, {tagLists, "=https://example.com/a.txt"},
+		{tagLists, "a,b=https://example.com/a.txt"},
+		{tagLists, "a=ftp://example.com/a.txt"},
+		{tagLists, "a=https://example.com/a.txt,A=https://example.com/b.txt"},
+		{tagLists, "a=https://example.com/a.txt,b=https://example.com/a.txt"},
 		{asnBytesPercent, "AS14061:101"}, {countryBytesPercent, "su:50"},
 		{unknownLimitPercent, ""}, {unknownLimitPercent, "-1"},
 		{unknownLimitPercent, "50%"},
@@ -2286,10 +2360,10 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		lookupDBPath:         "",
 		lookupTimeout:        "800ms",
 		addLookupHeaders:     "false",
-		deniedCountries:      "",
 		allowedCountries:     "",
-		asnLimitPercent:      "",
-		countryLimitPercent:  "",
+		tagLists:             "",
+		tagDeny:              "",
+		tagLimitPercent:      "",
 		asnBytesPercent:      "",
 		countryBytesPercent:  "",
 		unknownLimitPercent:  "100",

internal/discriminator/abuseipdb.go

@@ -13,13 +13,14 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 )
 
-// abuseIPDB notes AbuseIPDB, as noteHit does, with the score, when its score
-// of the client is a hit, and refuses the request when SWW_REPUTATION_ACTION
-// is deny, as dnsbl does for a zone. While SWW_ABUSEIPDB_KEY is unset it does
-// nothing. A client without a score is checked in the background, by the
-// request's address, if its history counts an offence, and the request does
-// not wait for the answer. The score is then used for each address of the
-// client. Its figures are the score and SWW_ABUSEIPDB_MIN_SCORE.
+// abuseIPDB adds the tag abuseipdb and notes AbuseIPDB, as noteHit does, with
+// the score, when its score of the client is a hit, and refuses the request
+// when SWW_REPUTATION_ACTION is deny, as dnsbl does for a zone. While
+// SWW_ABUSEIPDB_KEY is unset it does nothing. A client without a score is
+// checked in the background, by the request's address, if its history counts
+// an offence, and the request does not wait for the answer. The score is then
+// used for each address of the client. Its figures are the score and
+// SWW_ABUSEIPDB_MIN_SCORE.
 type abuseIPDB struct{}
 
 func (abuseIPDB) name() string { return "abuseipdb" }
@@ -39,6 +40,7 @@ func (abuseIPDB) check(ctx context.Context, rq *request, _ time.Time) *verdict {
 	}
 
 	rq.abuseIPDBHit = true
+	rq.addTag("abuseipdb")
 	rq.noteHit(bans.ReputationHit{Source: reputation.AbuseIPDBSource, Score: &score},
 		"scored by AbuseIPDB at or over SWW_ABUSEIPDB_MIN_SCORE")
 

internal/discriminator/answertime_test.go

@@ -335,7 +335,7 @@ func newDiscriminatorInBubble(
 ) (*discriminator.Server, *output) {
 	t.Helper()
 
-	settings := map[string]string{deniedCountries: "KP"}
+	settings := map[string]string{tagDeny: "country=KP"}
 	maps.Copy(settings, env)
 
 	server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, settings)
@@ -542,7 +542,7 @@ func TestDiscriminatorAnswersWithinTheTimeLimitWhileEveryOutsideSourceHangs(
 
 		return discriminator.New(params)
 	}, held, time.Now, map[string]string{
-		deniedCountries: "KP", wafMode: block,
+		tagDeny: "country=KP", wafMode: block,
 		dnsblZones: dnsblZone, dnsblResolver: resolver.LocalAddr().String(),
 		abuseIPDBKey:  accountKey,
 		blocklistURLs: held + "/drop.txt", asnLimitPercentURL: held + "/asn.txt",

internal/discriminator/bans_test.go

@@ -211,7 +211,7 @@ func TestBannedClientIsRefusedBeforeItsCountryIsLookedUp(t *testing.T) {
 		lookupTimeout:      "1h",
 		rateLimitPerMinute: "1",
 		banScopeV4Prefix:   "24",
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 	})
 
 	// fromDE's ban covers otherClient, which is refused unasked about.
@@ -266,7 +266,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 				lookupTimeout:      "1h",
 				rateLimitPerMinute: "1",
 				denyNets:           denied,
-				deniedCountries:    "kp",
+				tagDeny:            denyKP,
 			}
 
 			if tc.setting != "" {
@@ -276,7 +276,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 			s, _, _ := startWithClock(t, geojsURL, env)
 
 			s.get(denied, tc.status, requestlog.ActionDenied)
-			s.get(fromKP, tc.status, requestlog.ActionCountryDenied)
+			s.get(fromKP, tc.status, requestlog.ActionDenied)
 			s.get(fromDE, http.StatusOK, requestlog.ActionForward)
 			s.get(fromDE, tc.status, requestlog.ActionRateLimited)
 			s.get(fromDE, tc.status, requestlog.ActionBanned)
@@ -291,7 +291,7 @@ func TestBanNotes(t *testing.T) {
 	s, clk, server := startWithClock(t, geojsURL, map[string]string{
 		lookupTimeout:      "1h",
 		rateLimitPerMinute: "1",
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 	})
 	start := clk.Now()
 

internal/discriminator/biased.go

@@ -17,30 +17,31 @@ type percentage struct {
 }
 
 // biasedThresholdsSet reports whether a biased threshold can lower a
-// client's limits: one of its lists is not empty,
-// SWW_UNKNOWN_LIMIT_PERCENT is below 100, or SWW_ASN_LIMIT_PERCENT_URL
-// is set. The client's lookup is then needed before its request goes on.
+// client's limits by its lookup: SWW_ASN_BYTES_PERCENT or
+// SWW_COUNTRY_BYTES_PERCENT is not empty, SWW_UNKNOWN_LIMIT_PERCENT is
+// below 100, or SWW_ASN_LIMIT_PERCENT_URL is set. The client's lookup is
+// then needed before its request goes on.
 func biasedThresholdsSet(cfg *config.Config) bool {
-	return len(cfg.ASNLimitPercent) > 0 || len(cfg.CountryLimitPercent) > 0 ||
-		len(cfg.ASNBytesPercent) > 0 || len(cfg.CountryBytesPercent) > 0 ||
+	return len(cfg.ASNBytesPercent) > 0 || len(cfg.CountryBytesPercent) > 0 ||
 		cfg.UnknownLimitPercent < whole || cfg.ASNLimitPercentURL != ""
 }
 
 // limitPercentages returns the client's limit percentages, for the rate
-// limits and for the byte limits, by its AS number and country as looked
-// up, each "" when unknown, and the blocklists, DNSBL zones and AbuseIPDB
-// that list it. Each is the lowest of those the settings give it, the
-// first of them in the order below when several are lowest: the
-// percentage SWW_ASN_LIMIT_PERCENT gives its AS number, the one the file
-// SWW_ASN_LIMIT_PERCENT_URL names gives it, the one
-// SWW_COUNTRY_LIMIT_PERCENT gives its country, for a client without a
-// country, unless its request skipped the wait for GeoJS,
-// SWW_UNKNOWN_LIMIT_PERCENT, for a client a blocklist lists, the
-// percentage of SWW_BLOCKLIST_ACTION while it is limit, and for a client
-// a DNSBL zone's verdict lists, or whose AbuseIPDB score is a hit, the
-// percentage of SWW_REPUTATION_ACTION while it is limit. For the byte
-// limits, SWW_ASN_BYTES_PERCENT and SWW_COUNTRY_BYTES_PERCENT take the
-// place of the first three for an AS number or a country they list.
+// limits and for the byte limits, by its tags, its AS number and country
+// as looked up, each "" when unknown, and the blocklists, DNSBL zones and
+// AbuseIPDB that list it. Each is the lowest of those the settings give
+// it, the first of them in the order below when several are lowest: the
+// percentage SWW_TAG_LIMIT_PERCENT gives its asn= tag, the one the file
+// SWW_ASN_LIMIT_PERCENT_URL names gives its AS number, the one
+// SWW_TAG_LIMIT_PERCENT gives its country= tag, the lowest it gives its
+// other tags, for a client without a country, unless its request skipped
+// the wait for GeoJS, SWW_UNKNOWN_LIMIT_PERCENT, for a client a blocklist
+// lists, the percentage of SWW_BLOCKLIST_ACTION while it is limit, and
+// for a client a DNSBL zone's verdict lists, or whose AbuseIPDB score is
+// a hit, the percentage of SWW_REPUTATION_ACTION while it is limit. For
+// the byte limits, SWW_ASN_BYTES_PERCENT and SWW_COUNTRY_BYTES_PERCENT
+// take the place of the first three for an AS number or a country they
+// list.
 func (rq *request) limitPercentages() (percentage, percentage) {
 	cfg := rq.h.config
 	asn, country := rq.line.ASN, rq.line.Country
@@ -65,10 +66,18 @@ func (rq *request) limitPercentages() (percentage, percentage) {
 		reputationListed = percentage{cfg.ReputationLimitPercent, "SWW_REPUTATION_ACTION"}
 	}
 
-	asnRequests := lowest(given(cfg.ASNLimitPercent, asn, "SWW_ASN_LIMIT_PERCENT"),
-		fetched)
-	countryRequests := given(cfg.CountryLimitPercent, country,
-		"SWW_COUNTRY_LIMIT_PERCENT")
+	const tagSetting = "SWW_TAG_LIMIT_PERCENT"
+
+	asnRequests := lowest(given(cfg.TagLimitPercent, asnTag(asn), tagSetting), fetched)
+	countryRequests := given(cfg.TagLimitPercent, countryTag(country), tagSetting)
+
+	otherTags := percentage{percent: whole}
+
+	for _, tag := range rq.line.Tags {
+		if tag != asnTag(asn) && tag != countryTag(country) {
+			otherTags = lowest(otherTags, given(cfg.TagLimitPercent, tag, tagSetting))
+		}
+	}
 
 	asnBytes, countryBytes := asnRequests, countryRequests
 	if _, listed := cfg.ASNBytesPercent[asn]; listed {
@@ -79,12 +88,13 @@ func (rq *request) limitPercentages() (percentage, percentage) {
 		countryBytes = given(cfg.CountryBytesPercent, country, "SWW_COUNTRY_BYTES_PERCENT")
 	}
 
-	return lowest(asnRequests, countryRequests, unknown, blocklisted, reputationListed),
-		lowest(asnBytes, countryBytes, unknown, blocklisted, reputationListed)
+	return lowest(asnRequests, countryRequests, otherTags, unknown, blocklisted,
+			reputationListed),
+		lowest(asnBytes, countryBytes, otherTags, unknown, blocklisted, reputationListed)
 }
 
 // given returns the percentage percents, the setting named setting, gives
-// code, an AS number or a country, or whole when it does not list code.
+// code, an AS number, a country or a tag, or whole when it does not list code.
 func given(percents map[string]int64, code, setting string) percentage {
 	percent, listed := percents[code]
 	if !listed {

internal/discriminator/biased_test.go

@@ -22,8 +22,7 @@ import (
 
 // The biased thresholds.
 const (
-	asnLimitPercent     = "SWW_ASN_LIMIT_PERCENT"
-	countryLimitPercent = "SWW_COUNTRY_LIMIT_PERCENT"
+	tagLimitPercent     = "SWW_TAG_LIMIT_PERCENT"
 	asnBytesPercent     = "SWW_ASN_BYTES_PERCENT"
 	countryBytesPercent = "SWW_COUNTRY_BYTES_PERCENT"
 	unknownLimitPercent = "SWW_UNKNOWN_LIMIT_PERCENT"
@@ -35,6 +34,11 @@ const (
 	asnDEHalf     = asnDE + ":50"
 	asnDEQuarter  = asnDE + ":25"
 	countryDEHalf = "de:50"
+	// The same, as SWW_TAG_LIMIT_PERCENT names fromDE's tags.
+	asnTagDEHalf        = "asn=64496:50"
+	asnTagDEQuarter     = "asn=64496:25"
+	countryTagDEHalf    = "country=de:50"
+	countryTagDEQuarter = "country=de:25"
 	// noCountry is in an AS of its own, AS64500, and in no country.
 	noCountry = "192.0.2.80"
 	// fourAMinute is the rate limit these tests set: half of it is 2
@@ -54,8 +58,8 @@ func TestEachBiasedThresholdLowersTheRateLimits(t *testing.T) {
 	for _, tc := range []struct {
 		setting, value, from string
 	}{
-		{asnLimitPercent, asnDEHalf, fromDE},
-		{countryLimitPercent, countryDEHalf, fromDE},
+		{tagLimitPercent, asnTagDEHalf, fromDE},
+		{tagLimitPercent, countryTagDEHalf, fromDE},
 		{unknownLimitPercent, "50", unplaced},
 	} {
 		t.Run(tc.setting, func(t *testing.T) {
@@ -96,8 +100,8 @@ func TestEachBiasedThresholdLowersTheByteLimits(t *testing.T) {
 	for _, tc := range []struct {
 		setting, value, from string
 	}{
-		{asnLimitPercent, asnDEHalf, fromDE},
-		{countryLimitPercent, "DE:50", fromDE},
+		{tagLimitPercent, asnTagDEHalf, fromDE},
+		{tagLimitPercent, "Country=DE:50", fromDE},
 		{unknownLimitPercent, "50", unplaced},
 		{asnBytesPercent, "as64496:50", fromDE},
 		{countryBytesPercent, countryDEHalf, fromDE},
@@ -151,13 +155,13 @@ func TestBytesPercentSettingsTakeThePlaceOfTheOthersForByteLimits(t *testing.T)
 		},
 		{
 			"raising the byte limits back",
-			map[string]string{asnLimitPercent: asnDEHalf, asnBytesPercent: asnDE + ":100"},
-			"50 from " + asnLimitPercent, none, "",
+			map[string]string{tagLimitPercent: asnTagDEHalf, asnBytesPercent: asnDE + ":100"},
+			"50 from " + tagLimitPercent, none, "",
 		},
 		{
 			"raising the byte limits back, by country",
-			map[string]string{countryLimitPercent: countryDEHalf, countryBytesPercent: "de:100"},
-			"50 from " + countryLimitPercent, none, "",
+			map[string]string{tagLimitPercent: countryTagDEHalf, countryBytesPercent: "de:100"},
+			"50 from " + tagLimitPercent, none, "",
 		},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
@@ -184,19 +188,19 @@ func TestBytesPercentSettingsTakeThePlaceOfTheOthersForByteLimits(t *testing.T)
 func TestZeroPercentIsAZeroAllowance(t *testing.T) {
 	t.Parallel()
 
-	s, _, _ := startWithLookups(t, map[string]string{asnLimitPercent: asnDE + ":0"})
+	s, _, _ := startWithLookups(t, map[string]string{unknownLimitPercent: "0"})
 
 	// The first request breaks the limit, and bans the client; the log line
 	// gives the 0.
-	line := s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
+	line := s.get(unplaced, http.StatusForbidden, requestlog.ActionRateLimited)
 	if line.fields["limit_percent"] != float64(0) ||
-		line.fields["limit_percent_setting"] != asnLimitPercent {
+		line.fields["limit_percent_setting"] != unknownLimitPercent {
 		t.Errorf("log line has limit_percent %v from %v, want 0 from %s",
 			line.fields["limit_percent"], line.fields["limit_percent_setting"],
-			asnLimitPercent)
+			unknownLimitPercent)
 	}
 
-	s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
+	s.get(unplaced, http.StatusForbidden, requestlog.ActionBanned)
 }
 
 func TestLowestPercentageApplies(t *testing.T) {
@@ -211,29 +215,29 @@ func TestLowestPercentageApplies(t *testing.T) {
 	}{
 		{
 			"the country's",
-			map[string]string{asnLimitPercent: asnDEHalf, countryLimitPercent: "de:25"},
-			fromDE, "25 from " + countryLimitPercent,
+			map[string]string{tagLimitPercent: asnTagDEHalf + "," + countryTagDEQuarter},
+			fromDE, "25 from " + tagLimitPercent,
 		},
 		{
 			"the AS number's",
-			map[string]string{asnLimitPercent: asnDEQuarter, countryLimitPercent: countryDEHalf},
-			fromDE, "25 from " + asnLimitPercent,
+			map[string]string{tagLimitPercent: asnTagDEQuarter + "," + countryTagDEHalf},
+			fromDE, "25 from " + tagLimitPercent,
 		},
 		{
 			"the AS number's, the first of two alike",
-			map[string]string{asnLimitPercent: asnDEQuarter, countryLimitPercent: "de:25"},
-			fromDE, "25 from " + asnLimitPercent,
+			map[string]string{tagLimitPercent: asnTagDEQuarter + "," + countryTagDEQuarter},
+			fromDE, "25 from " + tagLimitPercent,
 		},
 		{
 			"that for a client without a country",
-			map[string]string{asnLimitPercent: "AS64500:50", unknownLimitPercent: "25"},
+			map[string]string{tagLimitPercent: "asn=64500:50", unknownLimitPercent: "25"},
 			noCountry, "25 from " + unknownLimitPercent,
 		},
 		{
 			// SWW_UNKNOWN_LIMIT_PERCENT is left at its default, 100.
 			"the AS number's, for a client without a country",
-			map[string]string{asnLimitPercent: "AS64500:25"},
-			noCountry, "25 from " + asnLimitPercent,
+			map[string]string{tagLimitPercent: "asn=64500:25"},
+			noCountry, "25 from " + tagLimitPercent,
 		},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
@@ -304,8 +308,12 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
 		setting, value string
 		waits          bool
 	}{
-		{asnLimitPercent, asnDEHalf, true},
-		{countryLimitPercent, countryDEHalf, true},
+		{tagLimitPercent, asnTagDEHalf, true},
+		{tagLimitPercent, countryTagDEHalf, true},
+		{tagDeny, denyKP, true},
+		// A tag the lookup does not give needs no answer.
+		{tagLimitPercent, "vpn:50", false},
+		{tagDeny, "vpn", false},
 		{asnBytesPercent, asnDEHalf, true},
 		{countryBytesPercent, countryDEHalf, true},
 		{unknownLimitPercent, "99", true},
@@ -363,15 +371,15 @@ func TestBanForALoweredLimitGivesThePercentageInItsNotesAndItsAlert(t *testing.T
 		{
 			// A quarter of 12 requests a minute is 3: the fourth breaks it.
 			"a rate limit",
-			map[string]string{rateLimitPerMinute: "12", asnLimitPercent: asnDEQuarter},
+			map[string]string{rateLimitPerMinute: "12", tagLimitPercent: asnTagDEQuarter},
 			3, http.StatusForbidden, requestlog.ActionRateLimited,
-			"requests per minute over the limit of 3", "25 from " + asnLimitPercent,
+			"requests per minute over the limit of 3", "25 from " + tagLimitPercent,
 		},
 		{
 			// The byte limits' percentage, not the rate limits'.
 			"a byte limit",
 			map[string]string{
-				bytesLimitPerMinute: twoUploads, asnLimitPercent: asnDEQuarter,
+				bytesLimitPerMinute: twoUploads, tagLimitPercent: asnTagDEQuarter,
 				asnBytesPercent: asnDEHalf,
 			},
 			0, http.StatusOK, requestlog.ActionForward,
@@ -487,7 +495,7 @@ func wantPercent(t *testing.T, what string, percent *int64, setting, want string
 }
 
 // percentText gives a limit percentage and the setting that gave it as
-// text, such as "50 from SWW_ASN_LIMIT_PERCENT", or none when both are
+// text, such as "50 from SWW_TAG_LIMIT_PERCENT", or none when both are
 // left out.
 func percentText(percent *int64, setting string) string {
 	switch {

internal/discriminator/coreruleset.go

@@ -17,9 +17,10 @@ import (
 // SWW_WAF_MODE is off or SWW_WAF_EXEMPT_PATHS exempts its path, as
 // pathExempt decides, and notes the rules it matched and its score in the
 // log line, and the rules in the metrics. A score at or over
-// SWW_WAF_ANOMALY_THRESHOLD is a match: it raises the waf_block alert,
-// and in block mode refuses the request with 403, which is an offence its
-// client's history counts. Its figures are the score and the threshold.
+// SWW_WAF_ANOMALY_THRESHOLD is a match: it adds the tag exploitsignature,
+// raises the waf_block alert, and in block mode refuses the request with 403,
+// which is an offence its client's history counts. Its figures are the score
+// and the threshold.
 type coreRuleSet struct{}
 
 func (coreRuleSet) name() string { return "core_rule_set" }
@@ -50,6 +51,7 @@ func (coreRuleSet) check(_ context.Context, rq *request, _ time.Time) *verdict {
 		return nil
 	}
 
+	rq.addTag(config.ExploitSignatureTag)
 	rq.alertWAFBlock(result)
 
 	if cfg.WAFMode == config.WAFModeDetect {

internal/discriminator/coreruleset_test.go

@@ -61,6 +61,41 @@ func wantWAF(t *testing.T, line logLine, score *int, ruleIDs ...int) {
 	}
 }
 
+func TestCoreRuleSetMatchAddsTheExploitSignatureTag(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name   string
+		mode   string
+		status int
+		action string
+	}{
+		{block, block, http.StatusForbidden, requestlog.ActionWAFBlocked},
+		{detect, detect, http.StatusOK, requestlog.ActionForward},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s, _, _ := startWithClock(t, "", map[string]string{wafMode: tc.mode})
+
+			wantTags(t, s.request(client, sqlInjection, tc.status, tc.action),
+				"exploitsignature")
+			wantTags(t, s.get(client, http.StatusOK, requestlog.ActionForward))
+		})
+	}
+}
+
+func TestDetectedAttackIsRefusedByTagDenyLast(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		wafMode: detect, tagDeny: "exploitsignature",
+	})
+
+	line := s.request(client, sqlInjection, http.StatusForbidden, requestlog.ActionDenied)
+	wantHeuristic(t, line, "tag_deny", `{"tag": "exploitsignature"}`)
+}
+
 func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/countries.go

@@ -1,7 +1,6 @@
 package discriminator
 
-// The heuristic countries. It reads SWW_DENIED_COUNTRIES and
-// SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
+// The heuristic countries. It reads SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
 
 import (
 	"context"
@@ -11,32 +10,26 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 )
 
-// countries refuses a 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 SWW_EXCLUSIVELY_ALLOWED_COUNTRIES. Its figures are the country and the
-// setting that refused it.
+// countries refuses a request when SWW_EXCLUSIVELY_ALLOWED_COUNTRIES is set and
+// does not hold the client's country as it was looked up. A client without a
+// country, or whose country cannot be found, is refused. Its figures are the
+// country and the setting that refused it.
 type countries struct{}
 
 func (countries) name() string { return "countries" }
 
 func (countries) check(_ context.Context, rq *request, _ time.Time) *verdict {
-	denied := rq.h.config.DeniedCountries
 	allowed := rq.h.config.ExclusivelyAllowedCountries
 	country := rq.line.Country
 
-	var setting string
-
-	switch {
-	case slices.Contains(denied, country):
-		setting = "SWW_DENIED_COUNTRIES"
-	case len(allowed) > 0 && !slices.Contains(allowed, country):
-		setting = "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"
-	default:
+	if len(allowed) == 0 || slices.Contains(allowed, country) {
 		return nil
 	}
 
 	return &verdict{
-		action:  requestlog.ActionCountryDenied,
-		figures: map[string]any{"country": country, "setting": setting},
+		action: requestlog.ActionCountryDenied,
+		figures: map[string]any{
+			"country": country, "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES",
+		},
 	}
 }

internal/discriminator/countries_test.go

@@ -33,13 +33,13 @@ func TestCountryLists(t *testing.T) {
 		env     map[string]string
 		refused []string
 	}{
-		{"denied", map[string]string{deniedCountries: "kp"}, []string{fromKP}},
 		{
 			"exclusively allowed", map[string]string{allowedCountries: "DE"},
 			[]string{fromKP, unplaced},
 		},
 		{
-			"both", map[string]string{deniedCountries: "kp", allowedCountries: "de,fr"},
+			"with a country in SWW_TAG_DENY",
+			map[string]string{tagDeny: denyKP, allowedCountries: "de,fr"},
 			[]string{fromKP, unplaced},
 		},
 	} {
@@ -95,12 +95,12 @@ func TestCountryRefusalNamesItsHeuristicCountryAndSetting(t *testing.T) {
 
 	geojsURL, _ := startGeoJS(t)
 	s, _, _ := startWithClock(t, geojsURL, map[string]string{
-		lookupTimeout: "1h", deniedCountries: "kp", allowedCountries: "de",
+		lookupTimeout: "1h", allowedCountries: "de",
 	})
 
 	line := s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied)
 	wantHeuristic(t, line, "countries",
-		`{"country": "KP", "setting": "SWW_DENIED_COUNTRIES"}`)
+		`{"country": "KP", "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"}`)
 
 	line = s.get(unplaced, http.StatusForbidden, requestlog.ActionCountryDenied)
 	wantHeuristic(t, line, "countries",
@@ -117,9 +117,9 @@ func TestCountryRefusalKeepsARequestFromTheApp(t *testing.T) {
 	})
 	geojsURL, _ := startGeoJS(t)
 	addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
-		trustedProxies:  trustLocalhost,
-		lookupTimeout:   "1h",
-		deniedCountries: "kp",
+		trustedProxies:   trustLocalhost,
+		lookupTimeout:    "1h",
+		allowedCountries: "de",
 	})
 
 	req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
@@ -202,7 +202,7 @@ func TestPrivateAddressIsNeverLookedUp(t *testing.T) {
 		env  map[string]string
 	}{
 		{"no setting needs the lookup", nil},
-		{"a country list is set", map[string]string{deniedCountries: "kp"}},
+		{"a tag setting needs it", map[string]string{tagDeny: denyKP}},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()

internal/discriminator/crowdsec.go

@@ -13,9 +13,9 @@ import (
 )
 
 // crowdSec refuses a request when a decision of the CrowdSec decision list on
-// the client is in force at now. It then notes the list, as noteHit does, and
-// bans the client until that decision ends. Its figures are the decision's
-// scenario and when it ends.
+// the client is in force at now. It then adds the tag crowdsec, notes the
+// list, as noteHit does, and bans the client until that decision ends. Its
+// figures are the decision's scenario and when it ends.
 type crowdSec struct{}
 
 func (crowdSec) name() string { return "crowdsec" }
@@ -26,6 +26,7 @@ func (crowdSec) check(_ context.Context, rq *request, now time.Time) *verdict {
 		return nil
 	}
 
+	rq.addTag("crowdsec")
 	rq.noteHit(bans.ReputationHit{Source: rq.h.config.CrowdSecDecisionsURL},
 		"listed by the CrowdSec decision list")
 	rq.banForCrowdSec(now, decision)

internal/discriminator/crowdsec_test.go

@@ -108,6 +108,7 @@ func TestCrowdSecBanNamesItsHeuristicScenarioAndEnd(t *testing.T) {
 	line := s.get(client, http.StatusForbidden, requestlog.ActionBanned)
 	wantHeuristic(t, line, "crowdsec", `{"scenario": "crowdsecurity/ssh-bf", `+
 		`"expires": "`+requestlog.FormatTime(clk.Now().Add(4*time.Hour))+`"}`)
+	wantTags(t, line, "crowdsec")
 }
 
 func TestEndedCrowdSecDecisionNoLongerBansThoughTheCopyStillHoldsIt(t *testing.T) {

internal/discriminator/discriminator_test.go

@@ -414,7 +414,7 @@ func TestReportNeverReachesAQuestionStillBeingHandled(t *testing.T) {
 
 	geojsURL, asked, release := startHeldGeoJS(t)
 	s := startDiscriminator(t, geojsURL, map[string]string{
-		lookupTimeout: "1h", deniedCountries: "kp", bytesLimitPerMinute: byteLimit,
+		lookupTimeout: "1h", tagDeny: denyKP, bytesLimitPerMinute: byteLimit,
 	})
 
 	first := s.question(siteA, client, "/")
@@ -765,7 +765,7 @@ func TestAllowCarriesTheLookupHeadersWhileTheSettingIsSet(t *testing.T) {
 
 			geojsURL, _ := startGeoJS(t)
 			s := startDiscriminator(t, geojsURL, map[string]string{
-				addLookupHeaders: tc.setting, lookupTimeout: "1h", deniedCountries: "kp",
+				addLookupHeaders: tc.setting, lookupTimeout: "1h", tagDeny: denyKP,
 			})
 
 			got := s.ask(fromDE, "/")

internal/discriminator/dnsbl.go

@@ -11,7 +11,8 @@ import (
 )
 
 // dnsbl notes the DNSBL zones whose verdict lists the client, as noteListed
-// does, and refuses the request when SWW_REPUTATION_ACTION is deny. Being
+// does, adds the tag dnsbl=<zone> for each, the zone's key masked, and refuses
+// the request when SWW_REPUTATION_ACTION is deny. Being
 // limit, it lowers the client's limits instead (see limitPercentages), and
 // being log, it does nothing more. A zone without a verdict on the client is
 // asked about it in the background, and the request does not wait for the
@@ -25,6 +26,10 @@ func (dnsbl) check(ctx context.Context, rq *request, _ time.Time) *verdict {
 	rq.dnsblListed = len(listedBy) > 0
 	rq.noteListed(listedBy, "listed by a DNSBL zone")
 
+	for _, zone := range listedBy {
+		rq.addTag("dnsbl=" + zone)
+	}
+
 	if !rq.dnsblListed || rq.h.config.ReputationAction != deny {
 		return nil
 	}

internal/discriminator/heuristics.go

@@ -49,18 +49,23 @@ func beforeLookup() []heuristic {
 }
 
 // afterLookup are the heuristics that run once the lookup has been made.
+// tag_deny runs twice: before the rate limits, on the tags known by then, and
+// last, on the tag rule_files and core_rule_set can add.
 func afterLookup() []heuristic {
 	return []heuristic{
+		tagLists{},
 		countries{},
 		blocklists{},
 		crowdSec{},
 		dnsbl{},
 		abuseIPDB{},
+		tagDeny{},
 		rateLimits{},
 		trapPaths{},
 		ruleFiles{},
 		headerLimits{},
 		coreRuleSet{},
+		tagDeny{},
 	}
 }
 

internal/discriminator/history_test.go

@@ -20,7 +20,7 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
 	s, clk, server := startWithClock(t, geojsURL, map[string]string{
 		lookupTimeout:      "1h",
 		rateLimitPerMinute: "2",
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 	})
 	start := clk.Now()
 

internal/discriminator/lookup.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"net/http"
 	"net/netip"
+	"strings"
 	"time"
 
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
@@ -19,7 +20,8 @@ const (
 )
 
 // lookUp looks up the client's AS number and country, in the lookup
-// database or through GeoJS, and notes them for the log line, unless
+// database or through GeoJS, and notes them for the log line and as the
+// request's asn= and country= tags, unless
 // SWW_LOOKUP_SOURCE is off or the client is on a private, loopback or
 // link-local address, which no lookup can place. The lookup database
 // answers at once. With GeoJS, while a setting needs the answer, such as a
@@ -47,6 +49,34 @@ func (rq *request) lookUp(ctx context.Context, now time.Time) {
 	rq.line.ASN = rq.lookupAnswer.ASN
 	rq.line.ASName = rq.lookupAnswer.ASName
 	rq.line.Country = rq.lookupAnswer.Country
+
+	if tag := asnTag(rq.line.ASN); tag != "" {
+		rq.addTag(tag)
+	}
+
+	if tag := countryTag(rq.line.Country); tag != "" {
+		rq.addTag(tag)
+	}
+}
+
+// asnTag returns the tag of asn, an AS number as the lookup gives it, such as
+// asn=64496 for AS64496, or "" for no AS number.
+func asnTag(asn string) string {
+	if asn == "" {
+		return ""
+	}
+
+	return "asn=" + strings.TrimPrefix(asn, "AS")
+}
+
+// countryTag returns the tag of country, a code as the lookup gives it, such
+// as country=de for DE, or "" for no country.
+func countryTag(country string) string {
+	if country == "" {
+		return ""
+	}
+
+	return "country=" + strings.ToLower(country)
 }
 
 // addLookup adds answer, an answer about a client from the lookup

internal/discriminator/lookup_test.go

@@ -94,9 +94,9 @@ func TestRequestThatWaitedForItsLookupIsCountedWhenItGoesOn(t *testing.T) {
 	clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 58, 0, time.UTC)}
 	addr, out, server := startProxyWithClock(t, app.URL, geojsURL, clk.Now,
 		map[string]string{
-			trustedProxies:  trustLocalhost,
-			lookupTimeout:   "1h",
-			deniedCountries: "kp",
+			trustedProxies: trustLocalhost,
+			lookupTimeout:  "1h",
+			tagDeny:        denyKP,
 		})
 
 	requestFromDE := func() *http.Request {

internal/discriminator/metrics_test.go

@@ -195,10 +195,10 @@ func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
 		_, _ = io.WriteString(w, "hello")
 	})
 	env := map[string]string{
-		trustedProxies:  trustLocalhost,
-		metricsToken:    token,
-		metricsTopN:     "2",
-		deniedCountries: "kp",
+		trustedProxies:   trustLocalhost,
+		metricsToken:     token,
+		metricsTopN:      "2",
+		allowedCountries: "de,fr",
 	}
 	geojsURL, _ := startGeoJS(t)
 	addr, out, server := startProxyWithClock(t, app.URL, geojsURL, time.Now, env)
@@ -322,13 +322,13 @@ func TestMetricsCountGeoJSRequestsAndFailures(t *testing.T) {
 	app := startApp(t, func(http.ResponseWriter, *http.Request) {})
 	addr, _, server := startProxyWithClock(t, app.URL, geojs.URL, time.Now,
 		map[string]string{
-			trustedProxies:  trustLocalhost,
-			metricsToken:    token,
-			deniedCountries: "kp",
+			trustedProxies: trustLocalhost,
+			metricsToken:   token,
+			tagDeny:        denyKP,
 		})
 
-	// GeoJS fails, so the client counts as coming from an unknown country,
-	// which SWW_DENIED_COUNTRIES does not refuse.
+	// GeoJS fails, so the client has no country= tag, and SWW_TAG_DENY does
+	// not refuse it.
 	req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
 	req.Header.Set(forwardedFor, fromDE)
 	wantStatus(t, do(t, req), http.StatusOK)

internal/discriminator/observe_test.go

@@ -50,7 +50,7 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
 				lookupTimeout:      "1h",
 				rateLimitPerMinute: "1",
 				denyNets:           denied,
-				deniedCountries:    "kp",
+				tagDeny:            denyKP,
 			}
 
 			if tc.setting != "" {
@@ -71,7 +71,7 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
 			for _, sent := range []struct{ from, refusal string }{
 				{denied, requestlog.ActionDenied},
 				{banned, requestlog.ActionBanned},
-				{fromKP, requestlog.ActionCountryDenied},
+				{fromKP, requestlog.ActionDenied},
 				{fromDE, requestlog.ActionRateLimited},
 			} {
 				if !tc.observe {

internal/discriminator/proxy.go

@@ -155,11 +155,12 @@ func newHandler(params Params) *handler {
 	h.geojs = lookup.New(lookup.Params{
 		URL:     params.GeoJSURL,
 		Timeout: params.Config.LookupTimeout,
-		// The country lists, the headers and the biased thresholds act on
-		// the answer before the request goes on.
-		Wait: len(params.Config.DeniedCountries) > 0 ||
-			len(params.Config.ExclusivelyAllowedCountries) > 0 ||
-			params.Config.AddLookupHeaders || biasedThresholdsSet(params.Config),
+		// The country list, the headers, the tag settings that name an asn=
+		// or country= tag and the biased thresholds act on the answer before
+		// the request goes on.
+		Wait: len(params.Config.ExclusivelyAllowedCountries) > 0 ||
+			params.Config.AddLookupHeaders || params.Config.TagsNeedLookup() ||
+			biasedThresholdsSet(params.Config),
 		Answered:   h.addLookup,
 		Now:        params.Now,
 		ProcessLog: params.ProcessLog,
@@ -183,6 +184,7 @@ func newReputation(
 	lists := reputation.New(reputation.Params{
 		BlocklistURLs: cfg.BlocklistURLs, Refresh: cfg.BlocklistRefresh,
 		ASNLimitPercentURL:   cfg.ASNLimitPercentURL,
+		TagLists:             cfg.TagLists,
 		CrowdSecDecisionsURL: cfg.CrowdSecDecisionsURL, CrowdSecKey: cfg.CrowdSecKey,
 		Now: params.Now, ProcessLog: params.ProcessLog, Alerts: params.Alerts,
 	})

internal/discriminator/proxy_test.go

@@ -69,7 +69,9 @@ const (
 	lookupDBPath         = "SWW_LOOKUP_DB_PATH"
 	lookupTimeout        = "SWW_LOOKUP_TIMEOUT"
 	addLookupHeaders     = "SWW_ADD_LOOKUP_HEADERS"
-	deniedCountries      = "SWW_DENIED_COUNTRIES"
+	tagDeny              = "SWW_TAG_DENY"
+	// denyKP is the value of SWW_TAG_DENY that refuses fromKP's country.
+	denyKP               = "country=kp"
 	allowedCountries     = "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"
 	banResponse          = "SWW_BAN_RESPONSE"
 	limitBanDuration     = "SWW_LIMIT_BAN_DURATION"

internal/discriminator/ratelimits_test.go

@@ -136,7 +136,7 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 		rateLimitPerMinute:   "1",
 		rateLimitExemptPaths: "/assets/,/favicon.ico",
 		denyNets:             denied,
-		deniedCountries:      "kp",
+		tagDeny:              denyKP,
 	})
 
 	// The answers are kept before the requests, so that none waits for
@@ -167,7 +167,7 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 	s.request(client, "/assets/app.js", http.StatusForbidden, requestlog.ActionBanned)
 	s.request(denied, "/assets/app.js", http.StatusForbidden, requestlog.ActionDenied)
 	s.request(fromKP, "/assets/app.js",
-		http.StatusForbidden, requestlog.ActionCountryDenied)
+		http.StatusForbidden, requestlog.ActionDenied)
 }
 
 func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {

internal/discriminator/refusallimit_test.go

@@ -191,7 +191,7 @@ func TestErrorBurstIsNotLoweredForAClientWithLowerLimits(t *testing.T) {
 		lookupTimeout:       "1h",
 		errorBurstThreshold: "2",
 		rulesDir:            writeRules(t, testRules),
-		countryLimitPercent: countryDEHalf,
+		tagLimitPercent:     countryTagDEHalf,
 	})
 
 	// Half of the threshold would be one, which the second refusal is over.

internal/discriminator/reputation_test.go

@@ -172,7 +172,7 @@ func TestBlocklistsComeAfterTheCountryListsAndSkipAllowNets(t *testing.T) {
 	t.Parallel()
 
 	s, server, queue := startWithLookups(t, map[string]string{
-		blocklistURLs: dropURL, deniedCountries: "kp", allowNets: fromDE,
+		blocklistURLs: dropURL, allowedCountries: "de", allowNets: fromDE,
 	})
 	loadLists(t, server, map[string][]string{dropURL: {fromDE, fromKP}})
 
@@ -211,18 +211,18 @@ func TestBlocklistLimitTakesPartInTheLowestPercentageOfEveryLimit(t *testing.T)
 		// percentText gives them, and limitHit its limit_hit.
 		want, limitHit string
 	}{
-		{limitHalf, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
-		{limitQuarter, asnDEHalf, "25 from " + blocklistAction, minuteBytes},
+		{limitHalf, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes},
+		{limitQuarter, asnTagDEHalf, "25 from " + blocklistAction, minuteBytes},
 		// The AS number's, the first of two alike.
-		{limitQuarter, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
-		{actionLog, asnDE + ":100", none, ""},
+		{limitQuarter, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes},
+		{actionLog, "asn=64511:25", none, ""},
 	} {
 		t.Run(tc.action+" "+tc.asnPercent, func(t *testing.T) {
 			t.Parallel()
 
 			s, server, _ := startWithLookups(t, map[string]string{
 				bytesLimitPerMinute: twoUploads, blocklistURLs: dropURL,
-				blocklistAction: tc.action, asnLimitPercent: tc.asnPercent,
+				blocklistAction: tc.action, tagLimitPercent: tc.asnPercent,
 			})
 			loadLists(t, server, map[string][]string{dropURL: {fromDE}})
 
@@ -246,7 +246,7 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
 
 	const (
 		fromURL     = "25 from " + asnLimitPercentURL
-		fromSetting = "25 from " + asnLimitPercent
+		fromSetting = "25 from " + tagLimitPercent
 	)
 
 	for _, tc := range []struct {
@@ -260,16 +260,16 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
 		{"the file's alone", nil, asnDEQuarter, fromURL, fromURL},
 		{
 			"the file's, lower than the setting's",
-			map[string]string{asnLimitPercent: asnDEHalf}, asnDEQuarter, fromURL, fromURL,
+			map[string]string{tagLimitPercent: asnTagDEHalf}, asnDEQuarter, fromURL, fromURL,
 		},
 		{
 			"the setting's, lower than the file's",
-			map[string]string{asnLimitPercent: asnDEQuarter}, asnDEHalf,
+			map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEHalf,
 			fromSetting, fromSetting,
 		},
 		{
 			"the setting's, the first of two alike",
-			map[string]string{asnLimitPercent: asnDEQuarter}, asnDEQuarter,
+			map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEQuarter,
 			fromSetting, fromSetting,
 		},
 		{"none, for an AS number the file does not list", nil, asnKP + ":25", none, none},
@@ -482,6 +482,46 @@ func TestDNSBLZonesComeAfterTheBlocklistsAndSkipAllowNets(t *testing.T) {
 	}
 }
 
+func TestReputationSourcesTagTheRequestWhateverTheirAction(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name string
+		env  map[string]string
+		load func(*discriminator.Server)
+		want []string
+	}{
+		{
+			"dnsbl",
+			map[string]string{
+				dnsblZones: dnsblZone, dnsblResolver: noResolver, reputationAction: actionLog,
+			},
+			func(server *discriminator.Server) {
+				loadVerdicts(server, map[string][]string{fromDE: {dnsblZone}})
+			},
+			[]string{"asn=64496", "country=de", "dnsbl=" + dnsblZone},
+		},
+		{
+			abuseipdb,
+			map[string]string{abuseIPDBKey: accountKey, reputationAction: actionLog},
+			func(server *discriminator.Server) {
+				loadScores(server, map[string]int64{fromDE: 80})
+			},
+			[]string{abuseipdb, "asn=64496", "country=de"},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s, server, _ := startWithLookups(t, tc.env)
+			tc.load(server)
+
+			wantTags(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
+				tc.want...)
+		})
+	}
+}
+
 func TestObserveModeForwardsAClientADNSBLZoneDeniesAndAlertsIt(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/request.go

@@ -138,6 +138,17 @@ func (h *handler) startRequest(
 	return rq
 }
 
+// addTag adds tag, in lower case, to the request's tags, which stay sorted and
+// hold each tag once.
+func (rq *request) addTag(tag string) {
+	tag = strings.ToLower(tag)
+
+	at, found := slices.BinarySearch(rq.line.Tags, tag)
+	if !found {
+		rq.line.Tags = slices.Insert(rq.line.Tags, at, tag)
+	}
+}
+
 // requestHeaders returns the headers of r that names lists, by name in
 // lower case, each with its values joined by ", ". Authorization, Cookie
 // and Set-Cookie are never among them, whatever names says.

internal/discriminator/rulefiles.go

@@ -8,12 +8,14 @@ import (
 	"time"
 
 	"sneak.berlin/go/smallwebwaf/internal/bans"
+	"sneak.berlin/go/smallwebwaf/internal/config"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 )
 
 // ruleFiles checks the request against the rules of the rule files at now,
-// notes the ids of those it matches in the log line, and refuses the request
+// notes the ids of those it matches in the log line, adds the tag
+// exploitsignature when it matches any, and refuses the request
 // when the last rule it matches refuses it: with ActionRuleBlocked for a block
 // rule, and ActionBanned for a ban rule. A ban rule bans the client's netblock
 // for a clear sign of attack, or in observe mode raises the alert for the ban
@@ -35,6 +37,8 @@ func (ruleFiles) check(_ context.Context, rq *request, now time.Time) *verdict {
 		return nil
 	}
 
+	rq.addTag(config.ExploitSignatureTag)
+
 	// Only the last rule matched can refuse the request.
 	last := matched[len(matched)-1]
 	figures := map[string]any{"rule_id": last.ID, "rule_action": last.Action}

internal/discriminator/rulefiles_test.go

@@ -93,6 +93,20 @@ func TestEachRuleAction(t *testing.T) {
 	s.get(client, http.StatusTooManyRequests, requestlog.ActionBanned)
 }
 
+func TestEachRuleActionAddsTheExploitSignatureTag(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		rulesDir: writeRules(t, "noted path log ^/noted$\n"+testRules),
+	})
+
+	wantTags(t, s.request(client, "/noted", http.StatusOK, requestlog.ActionForward),
+		"exploitsignature")
+	wantTags(t, s.request(client, "/blocked", http.StatusForbidden,
+		requestlog.ActionRuleBlocked), "exploitsignature")
+	wantTags(t, s.get(client, http.StatusOK, requestlog.ActionForward))
+}
+
 func TestRuleRefusalNamesItsHeuristicAndTheRule(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/staticlists_test.go

@@ -32,7 +32,7 @@ func TestAllowNetsSkipEveryCheck(t *testing.T) {
 		trustedProxies:     trustLocalhost,
 		allowNets:          "198.51.100.0/24",
 		denyNets:           fromKP,
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 		rateLimitPerMinute: "1",
 	})
 
@@ -83,9 +83,9 @@ func TestDenyNetsRefuseBeforeTheLookup(t *testing.T) {
 	})
 	geojsURL, asked := startGeoJS(t)
 	addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
-		trustedProxies:  trustLocalhost,
-		denyNets:        "203.0.113.0/24",
-		deniedCountries: "kp",
+		trustedProxies: trustLocalhost,
+		denyNets:       "203.0.113.0/24",
+		tagDeny:        denyKP,
 	})
 
 	req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
@@ -142,7 +142,7 @@ func TestRateLimitExemptNetsAreNeitherCountedNorRefused(t *testing.T) {
 		trustedProxies:      trustLocalhost,
 		lookupTimeout:       "1h",
 		rateLimitExemptNets: listedAddr + "," + fromKP,
-		deniedCountries:     "kp",
+		tagDeny:             denyKP,
 		rateLimitPerMinute:  "1",
 	})
 
@@ -154,7 +154,7 @@ func TestRateLimitExemptNetsAreNeitherCountedNorRefused(t *testing.T) {
 		{listedAddr, http.StatusOK, requestlog.ActionForward},
 		{unlistedAddr, http.StatusOK, requestlog.ActionForward},
 		{unlistedAddr, http.StatusForbidden, requestlog.ActionRateLimited},
-		{fromKP, http.StatusForbidden, requestlog.ActionCountryDenied},
+		{fromKP, http.StatusForbidden, requestlog.ActionDenied},
 	})
 }
 

internal/discriminator/tagdeny.go

@@ -0,0 +1,30 @@
+package discriminator
+
+// The heuristic tag_deny. It reads SWW_TAG_DENY.
+
+import (
+	"context"
+	"slices"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// tagDeny refuses a request that carries a tag in SWW_TAG_DENY. Its figure is
+// the first such tag, in sorted order.
+type tagDeny struct{}
+
+func (tagDeny) name() string { return "tag_deny" }
+
+func (tagDeny) check(_ context.Context, rq *request, _ time.Time) *verdict {
+	for _, tag := range rq.line.Tags {
+		if slices.Contains(rq.h.config.TagDeny, tag) {
+			return &verdict{
+				action:  requestlog.ActionDenied,
+				figures: map[string]any{"tag": tag},
+			}
+		}
+	}
+
+	return nil
+}

internal/discriminator/tagdeny_test.go

@@ -0,0 +1,75 @@
+package discriminator_test
+
+import (
+	"net/http"
+	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+func TestTagDenyRefusesALookupTagAndNamesTheTag(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithLookups(t, map[string]string{tagDeny: "Country=KP"})
+
+	line := s.get(fromKP, http.StatusForbidden, requestlog.ActionDenied)
+	wantHeuristic(t, line, "tag_deny", `{"tag": "country=kp"}`)
+	wantTags(t, line, "asn=64511", "country=kp")
+
+	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+}
+
+func TestTagDenyRefusesAnASNTag(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithLookups(t, map[string]string{tagDeny: "asn=64511"})
+
+	wantHeuristic(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionDenied),
+		"tag_deny", `{"tag": "asn=64511"}`)
+	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+}
+
+func TestTagDenyRefusesAListTagBeforeTheRateLimitsCount(t *testing.T) {
+	t.Parallel()
+
+	s, server, _ := startWithLookups(t, map[string]string{
+		tagLists: "torexit=" + torList, tagDeny: "torexit", rateLimitPerMinute: "1",
+	})
+	loadLists(t, server, map[string][]string{torList: {fromDE}})
+
+	// Each is refused for its tag: none is counted to break the limit of one.
+	for range 3 {
+		wantHeuristic(t, s.get(fromDE, http.StatusForbidden, requestlog.ActionDenied),
+			"tag_deny", `{"tag": "torexit"}`)
+	}
+}
+
+func TestTagDenyRefusesAnExploitSignatureOfARuleThatOnlyLogs(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		rulesDir: writeRules(t, "noted path log ^/\n"), tagDeny: "exploitsignature",
+	})
+
+	line := s.get(client, http.StatusForbidden, requestlog.ActionDenied)
+	wantHeuristic(t, line, "tag_deny", `{"tag": "exploitsignature"}`)
+	wantTags(t, line, "exploitsignature")
+}
+
+func TestTagLimitPercentLowersALimitTheLowestWinning(t *testing.T) {
+	t.Parallel()
+
+	s, server, _ := startWithLookups(t, map[string]string{
+		rateLimitPerMinute: fourAMinute,
+		tagLists:           "vpn=" + vpnList + ",tor=" + torList,
+		tagLimitPercent:    "vpn:50,tor:25",
+	})
+	loadLists(t, server, map[string][]string{vpnList: {fromDE}, torList: {fromDE}})
+
+	// A quarter of 4 requests a minute: the second breaks the limit.
+	s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+
+	line := s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
+	wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
+		"25 from "+tagLimitPercent)
+}

internal/discriminator/taglists.go

@@ -0,0 +1,24 @@
+package discriminator
+
+// The heuristic tag_lists. It reads the address lists of SWW_TAG_LISTS through
+// the reputation lists.
+
+import (
+	"context"
+	"time"
+)
+
+// tagLists adds to the request one tag for each list of SWW_TAG_LISTS that
+// holds the client, the tag being the list's name. It refuses nothing, and runs
+// first so that every refusal's log line carries these tags.
+type tagLists struct{}
+
+func (tagLists) name() string { return "tag_lists" }
+
+func (tagLists) check(_ context.Context, rq *request, _ time.Time) *verdict {
+	for _, name := range rq.h.lists.TagsOf(rq.client) {
+		rq.addTag(name)
+	}
+
+	return nil
+}

internal/discriminator/taglists_test.go

@@ -0,0 +1,73 @@
+package discriminator_test
+
+import (
+	"net/http"
+	"slices"
+	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// tagLists is SWW_TAG_LISTS, and vpnList and torList lists it names.
+const (
+	tagLists = "SWW_TAG_LISTS"
+	vpnList  = "https://lists.example/vpn.txt"
+	torList  = "https://lists.example/torexit.txt"
+)
+
+// wantTags checks the log line's tags.
+func wantTags(t *testing.T, line logLine, want ...string) {
+	t.Helper()
+
+	got, _ := line.fields["tags"].([]any)
+
+	tags := make([]string, 0, len(got))
+	for _, tag := range got {
+		text, _ := tag.(string)
+		tags = append(tags, text)
+	}
+
+	if !slices.Equal(tags, want) {
+		t.Errorf("log line has tags %v, want %v", tags, want)
+	}
+}
+
+func TestLookupAndTagListsGiveTheRequestItsTagsSorted(t *testing.T) {
+	t.Parallel()
+
+	s, server, _ := startWithLookups(t, map[string]string{
+		tagLists: "vpn=mullvad=" + vpnList + ",TorExit=" + torList,
+	})
+	loadLists(t, server, map[string][]string{
+		vpnList: {fromDE}, torList: {fromDE + "/32", fromKP},
+	})
+
+	wantTags(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
+		"asn=64496", "country=de", "torexit", "vpn=mullvad")
+	wantTags(t, s.get(fromKP, http.StatusOK, requestlog.ActionForward),
+		"asn=64511", "country=kp", "torexit")
+}
+
+func TestRequestWithoutATagLeavesTheFieldOut(t *testing.T) {
+	t.Parallel()
+
+	// With no lookup, a client is not placed and no setting gives it a tag.
+	s, _, _ := startWithClock(t, "", map[string]string{lookupSource: "off"})
+
+	line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
+	if _, present := line.fields["tags"]; present {
+		t.Errorf("log line has tags %v, want none", line.fields["tags"])
+	}
+}
+
+func TestTagListsTagEvenARequestTheCountryListRefuses(t *testing.T) {
+	t.Parallel()
+
+	s, server, _ := startWithLookups(t, map[string]string{
+		tagLists: "vpn=" + vpnList, allowedCountries: "de",
+	})
+	loadLists(t, server, map[string][]string{vpnList: {fromKP}})
+
+	wantTags(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied),
+		"asn=64511", "country=kp", "vpn")
+}

internal/metrics/busiest.go

@@ -25,7 +25,7 @@ type busiest struct {
 	requests      *prometheus.CounterVec
 	requestBytes  *prometheus.CounterVec
 	responseBytes *prometheus.CounterVec
-	// refused are, by country, the requests the country lists refused; nil
+	// refused are, by country, the requests the country list refused; nil
 	// by AS number.
 	refused *prometheus.CounterVec
 
@@ -42,7 +42,7 @@ type busiest struct {
 func newCountries(topN int) *busiest {
 	countries := newBusiest(topN, "country", "the client's country")
 	countries.refused = counterVec("sww_country_list_refusals_total",
-		"Requests the country lists refused, by the client's country.",
+		"Requests SWW_EXCLUSIVELY_ALLOWED_COUNTRIES refused, by the client's country.",
 		[]string{"country"})
 
 	return countries

internal/reputation/reputation.go

@@ -1,7 +1,8 @@
 // Package reputation fetches the lists the settings name by URL: the
 // blocklists of SWW_BLOCKLIST_URLS, the file of AS:percent lines
-// SWW_ASN_LIMIT_PERCENT_URL names, and the decision list of the CrowdSec
-// engine SWW_CROWDSEC_LAPI_URL names. It keeps the last good copy of
+// SWW_ASN_LIMIT_PERCENT_URL names, the address lists of SWW_TAG_LISTS, and
+// the decision list of the CrowdSec engine SWW_CROWDSEC_LAPI_URL names. It
+// keeps the last good copy of
 // each, whole, comment lines included, which is used while a fetch fails,
 // and when each was last tried. It also asks the DNSBL zones of
 // SWW_DNSBL_ZONES about clients, and keeps their verdicts, and checks
@@ -71,6 +72,8 @@ type Params struct {
 	// (SWW_ASN_LIMIT_PERCENT_URL), "" while it is unset.
 	BlocklistURLs      []string
 	ASNLimitPercentURL string
+	// TagLists are the address lists that add a tag (SWW_TAG_LISTS).
+	TagLists []config.TagList
 	// CrowdSecDecisionsURL is the CrowdSec decision list, "" while
 	// SWW_CROWDSEC_LAPI_URL is unset, fetched with CrowdSecKey
 	// (SWW_CROWDSEC_LAPI_KEY).
@@ -152,14 +155,18 @@ func New(params Params) *Lists {
 }
 
 // URLs returns the URL of every list: the blocklists' in the order
-// SWW_BLOCKLIST_URLS names them, then SWW_ASN_LIMIT_PERCENT_URL, then
-// the CrowdSec decision list's.
+// SWW_BLOCKLIST_URLS names them, then SWW_ASN_LIMIT_PERCENT_URL, then the
+// tag lists', then the CrowdSec decision list's.
 func (l *Lists) URLs() []string {
 	urls := slices.Clone(l.params.BlocklistURLs)
 	if l.params.ASNLimitPercentURL != "" {
 		urls = append(urls, l.params.ASNLimitPercentURL)
 	}
 
+	for _, list := range l.params.TagLists {
+		urls = append(urls, list.URL)
+	}
+
 	if l.params.CrowdSecDecisionsURL != "" {
 		urls = append(urls, l.params.CrowdSecDecisionsURL)
 	}
@@ -184,6 +191,22 @@ func (l *Lists) ListedBy(addr netip.Addr) []string {
 	return listedBy
 }
 
+// TagsOf returns the names of the tag lists whose copy holds addr.
+func (l *Lists) TagsOf(addr netip.Addr) []string {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	var names []string
+
+	for _, list := range l.params.TagLists {
+		if l.lists[list.URL].entries.contain(addr) {
+			names = append(names, list.Name)
+		}
+	}
+
+	return names
+}
+
 // ASNLimitPercent returns the percentage the copy of the file of
 // AS:percent lines gives asn, and whether it lists asn.
 func (l *Lists) ASNLimitPercent(asn string) (int64, bool) {
@@ -551,7 +574,7 @@ func parseNetblock(text string) (netip.Prefix, bool) {
 }
 
 // parsePercents reads the lines of the file of AS:percent lines, each an
-// AS number, : and a percentage, as SWW_ASN_LIMIT_PERCENT takes them. An
+// AS number, : and a percentage, such as AS64496:50. An
 // AS number listed more than once gets the lowest of its percentages.
 func parsePercents(lines []string) (entries, error) {
 	found := entries{percents: map[string]int64{}}

internal/requestlog/requestlog.go

@@ -38,9 +38,10 @@ const (
 	// ActionDenied is a request refused because its client is in
 	// SWW_DENY_NETS, in a blocklist while SWW_BLOCKLIST_ACTION is deny,
 	// or listed by a DNSBL zone, or scored a hit by AbuseIPDB, while
-	// SWW_REPUTATION_ACTION is deny.
+	// SWW_REPUTATION_ACTION is deny, or that carries a tag in SWW_TAG_DENY.
 	ActionDenied = "denied"
-	// ActionCountryDenied is a request refused for its client's country.
+	// ActionCountryDenied is a request refused because its client's country
+	// is not in SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
 	ActionCountryDenied = "country_denied"
 	// ActionAdmin is a request discriminator answered at one of its own
 	// endpoints, or a question about a path under /_sww/.
@@ -172,6 +173,8 @@ type Line struct {
 	// whose verdict lists it, their keys masked, then abuseipdb when its
 	// score is a hit.
 	Reputation []string `json:"reputation,omitempty"`
+	// Tags are the request's tags, sorted.
+	Tags []string `json:"tags,omitempty"`
 	// Offence is the offence the request was held as, OffenceLimit.
 	Offence string `json:"offence,omitempty"`
 	// BanExpires is when the ban the request made, or was refused under,

internal/sww/sww_test.go

@@ -611,14 +611,14 @@ func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 	writeLookupDatabase(t, path, "DE")
 
 	env := map[string]string{
-		listenAddr:             localhost + ":0",
-		stateDir:               t.TempDir(),
-		rulesDir:               t.TempDir(),
-		metricsToken:           token,
-		instanceName:           instance,
-		lookupSource:           "file",
-		lookupDBPath:           path,
-		"SWW_DENIED_COUNTRIES": "kp",
+		listenAddr:     localhost + ":0",
+		stateDir:       t.TempDir(),
+		rulesDir:       t.TempDir(),
+		metricsToken:   token,
+		instanceName:   instance,
+		lookupSource:   "file",
+		lookupDBPath:   path,
+		"SWW_TAG_DENY": "country=kp",
 		// The requests sent until a replacement takes effect, and those
 		// for the metrics, must not break a rate limit, whose ban would
 		// refuse them too.
@@ -1280,7 +1280,7 @@ func wantStartingLine(t *testing.T, line map[string]any, dir string) {
 		"SWW_RATE_LIMIT_PER_HOUR":           "1500",
 		rateLimitPerDay:                     "6000",
 		"SWW_RATE_LIMIT_EXEMPT_PATHS":       "",
-		"SWW_DENIED_COUNTRIES":              "",
+		"SWW_TAG_DENY":                      "",
 		"SWW_EXCLUSIVELY_ALLOWED_COUNTRIES": "",
 		"SWW_BAN_RESPONSE":                  "403",
 		"SWW_LIMIT_BAN_DURATION":            "1h",