Blocklists and an AS percentage file fetched by URL (closes #29)
check / check (push) Waiting to run

SWWAF_BLOCKLIST_URLS names lists of addresses and netblocks, fetched every
SWWAF_BLOCKLIST_REFRESH (24h, never under 1h); an IPv4-mapped line stands
for its IPv4 address or netblock. reputation.json keeps each list's last
try, failed or not, even one cut off by a stop, which a restart waits on
as a running instance does, and its last good copy, whole, used while a
fetch fails. SWWAF_BLOCKLIST_ACTION denies, limits or only logs a listed
client; the log line names the lists, each raises reputation_hit, and a
failed fetch raises source_failure. SWWAF_ASN_LIMIT_PERCENT_URL is fetched
the same way and counts as SWWAF_ASN_LIMIT_PERCENT does, the lower winning.

Judgement call: a failed fetch is retried after the refresh, not sooner.
Not done: ban notes do not name the lists yet.

Model: opus-5-5
This commit was merged in pull request #108.
This commit is contained in:
2026-10-07 19:09:41 +02:00
parent 82e20e0cb5
commit 2b8c98ba1f
19 changed files with 2588 additions and 322 deletions
+33 -18
View File
@@ -17,33 +17,48 @@ type percentage struct {
}
// biasedThresholdsSet reports whether a biased threshold can lower a
// client's limits: one of its lists is not empty, or
// SWWAF_UNKNOWN_LIMIT_PERCENT is below 100. The client's lookup is then
// needed before its request goes on.
// client's limits: one of its lists is not empty,
// SWWAF_UNKNOWN_LIMIT_PERCENT is below 100, or SWWAF_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 ||
cfg.UnknownLimitPercent < whole
cfg.UnknownLimitPercent < whole || cfg.ASNLimitPercentURL != ""
}
// limitPercentages returns a client's limit percentages, for the rate
// 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. Each is the lowest of those the settings give
// it, the first of them in the order below when several are lowest: the
// percentage SWWAF_ASN_LIMIT_PERCENT gives its AS number, the one
// SWWAF_COUNTRY_LIMIT_PERCENT gives its country, and, for a client
// without a country, SWWAF_UNKNOWN_LIMIT_PERCENT. For the byte limits,
// SWWAF_ASN_BYTES_PERCENT and SWWAF_COUNTRY_BYTES_PERCENT take the place
// of the first two for an AS number or a country they list.
func limitPercentages(
cfg *config.Config, asn, country string,
) (percentage, percentage) {
// up, each "" when unknown, and the blocklists 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 SWWAF_ASN_LIMIT_PERCENT
// gives its AS number, the one the file SWWAF_ASN_LIMIT_PERCENT_URL names
// gives it, the one SWWAF_COUNTRY_LIMIT_PERCENT gives its country, for a
// client without a country, SWWAF_UNKNOWN_LIMIT_PERCENT, and for a client
// a blocklist lists, the percentage of SWWAF_BLOCKLIST_ACTION while it is
// limit. For the byte limits, SWWAF_ASN_BYTES_PERCENT and
// SWWAF_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
unknown := percentage{percent: whole}
if country == "" {
unknown = percentage{cfg.UnknownLimitPercent, "SWWAF_UNKNOWN_LIMIT_PERCENT"}
}
asnRequests := given(cfg.ASNLimitPercent, asn, "SWWAF_ASN_LIMIT_PERCENT")
fetched := percentage{percent: whole}
if percent, listed := rq.h.lists.ASNLimitPercent(asn); listed {
fetched = percentage{percent, "SWWAF_ASN_LIMIT_PERCENT_URL"}
}
listed := percentage{percent: whole}
if len(rq.line.Reputation) > 0 && cfg.BlocklistAction == "limit" {
listed = percentage{cfg.BlocklistLimitPercent, "SWWAF_BLOCKLIST_ACTION"}
}
asnRequests := lowest(given(cfg.ASNLimitPercent, asn, "SWWAF_ASN_LIMIT_PERCENT"),
fetched)
countryRequests := given(cfg.CountryLimitPercent, country,
"SWWAF_COUNTRY_LIMIT_PERCENT")
@@ -56,8 +71,8 @@ func limitPercentages(
countryBytes = given(cfg.CountryBytesPercent, country, "SWWAF_COUNTRY_BYTES_PERCENT")
}
return lowest(asnRequests, countryRequests, unknown),
lowest(asnBytes, countryBytes, unknown)
return lowest(asnRequests, countryRequests, unknown, listed),
lowest(asnBytes, countryBytes, unknown, listed)
}
// given returns the percentage percents, the setting named setting, gives
+1
View File
@@ -310,6 +310,7 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
{asnBytesPercent, asnDEHalf, true},
{countryBytesPercent, countryDEHalf, true},
{unknownLimitPercent, "99", true},
{asnLimitPercentURL, asnURL, true},
// At 100, its default, it lowers no limit.
{unknownLimitPercent, "100", false},
} {
+17 -5
View File
@@ -18,6 +18,7 @@ import (
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/metrics"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/rules"
)
@@ -69,14 +70,16 @@ type Params struct {
// against.
Rules *rules.Files
// Alerts receive the alert for each ban the proxy makes or makes
// permanent, for each count over an anomaly threshold, and for GeoJS
// failing.
// permanent, for each count over an anomaly threshold, for each request
// whose client a blocklist lists, and for GeoJS failing or a fetch of a
// list failing.
Alerts *alerts.Queue
}
// Server is the server smallwebwaf runs, with the parts of the proxy
// whose state the state files keep, the lookup database, nil unless
// SWWAF_LOOKUP_SOURCE is file, and the metrics.
// SWWAF_LOOKUP_SOURCE is file, the lists fetched from URLs, which its Run
// fetches, and the metrics.
type Server struct {
*http.Server
@@ -85,6 +88,7 @@ type Server struct {
GeoJS *lookup.GeoJS
Anomalies *anomaly.Counters
LookupFile *lookup.File
Lists *reputation.Lists
Metrics *metrics.Metrics
}
@@ -132,8 +136,13 @@ func New(params Params) *Server {
Alerts: params.Alerts,
}),
lookupFile: params.LookupFile,
rules: params.Rules,
alerts: params.Alerts,
lists: reputation.New(reputation.Params{
BlocklistURLs: params.Config.BlocklistURLs, Refresh: params.Config.BlocklistRefresh,
ASNLimitPercentURL: params.Config.ASNLimitPercentURL, Now: params.Now,
ProcessLog: params.ProcessLog, Alerts: params.Alerts,
}),
rules: params.Rules,
alerts: params.Alerts,
}
h.geojs = lookup.New(lookup.Params{
URL: params.GeoJSURL,
@@ -151,6 +160,7 @@ func New(params Params) *Server {
})
m.AddBansAndClients(h.ledger, h.limiter, params.Now)
m.AddRules(params.Rules)
m.AddReputation(h.lists)
return &Server{
Server: &http.Server{
@@ -170,6 +180,7 @@ func New(params Params) *Server {
GeoJS: h.geojs,
Anomalies: h.anomalies,
LookupFile: h.lookupFile,
Lists: h.lists,
Metrics: m,
}
}
@@ -189,6 +200,7 @@ type handler struct {
geojs *lookup.GeoJS
anomalies *anomaly.Counters
lookupFile *lookup.File
lists *reputation.Lists
rules *rules.Files
alerts *alerts.Queue
}
+32
View File
@@ -0,0 +1,32 @@
package proxy
import (
"sneak.berlin/go/smallwebwaf/internal/alerts"
)
// blocklistDenied notes in the log line the URLs of the blocklists that
// list the client, counts each of them in the metrics and raises a
// reputation_hit alert for it, and reports whether SWWAF_BLOCKLIST_ACTION,
// being deny, refuses the request. Being limit, it lowers the client's
// limits instead (see limitPercentages), and being log, it does nothing
// more.
func (rq *request) blocklistDenied() bool {
listedBy := rq.h.lists.ListedBy(rq.client)
rq.line.Reputation = listedBy
for _, listURL := range listedBy {
rq.h.metrics.ReputationHit(listURL)
rq.h.alerts.Raise(alerts.Alert{
Event: alerts.EventReputationHit,
Client: rq.client,
Netblock: clientGroup(rq.client),
ASN: rq.line.ASN,
ASName: rq.line.ASName,
Country: rq.line.Country,
Reason: "listed by a blocklist",
Detail: map[string]any{"source": listURL},
})
}
return len(listedBy) > 0 && rq.h.config.BlocklistAction == "deny"
}
+333
View File
@@ -0,0 +1,333 @@
package proxy_test
import (
"maps"
"net/http"
"net/netip"
"slices"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// The reputation settings.
const (
blocklistURLs = "SWWAF_BLOCKLIST_URLS"
blocklistAction = "SWWAF_BLOCKLIST_ACTION"
asnLimitPercentURL = "SWWAF_ASN_LIMIT_PERCENT_URL"
)
// The actions of SWWAF_BLOCKLIST_ACTION but limit, which has a
// percentage.
const (
actionDeny = "deny"
actionLog = "log"
)
// The lists these tests name, which are never fetched: each test puts in
// the copies it needs, as reputation.json would at start.
const (
dropURL = "https://lists.example/drop.txt"
torURL = "https://lists.example/tor.txt"
asnURL = "https://lists.example/asn.txt"
)
func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) {
t.Parallel()
forward, denied := requestlog.ActionForward, requestlog.ActionDenied
for _, tc := range []struct {
action string
// statuses and actions are those of a listed client's three
// requests, and percent their limit_percent, as percentText gives it.
statuses []int
actions []string
percent string
}{
{
actionDeny, []int{http.StatusForbidden, http.StatusForbidden, http.StatusForbidden},
[]string{denied, denied, denied}, none,
},
{
// Half of 4 requests a minute: the third breaks the limit.
"limit:50", []int{http.StatusOK, http.StatusOK, http.StatusForbidden},
[]string{forward, forward, requestlog.ActionRateLimited},
"50 from " + blocklistAction,
},
{
actionLog, []int{http.StatusOK, http.StatusOK, http.StatusOK},
[]string{forward, forward, forward}, none,
},
} {
t.Run(tc.action, func(t *testing.T) {
t.Parallel()
s, server, _ := startWithLookups(t, map[string]string{
rateLimitPerMinute: fourAMinute, blocklistURLs: dropURL,
blocklistAction: tc.action,
})
// fromDE is listed as an address, and fromKP in a netblock.
loadLists(t, server, map[string][]string{
dropURL: {"; DROP", fromDE, "198.51.100.0/24 ; SBL1"},
})
for _, from := range []string{fromDE, fromKP} {
for i := range 3 {
line := s.get(from, tc.statuses[i], tc.actions[i])
wantReputation(t, line, dropURL)
wantPercent(t, "limit_percent", line.LimitPercent,
line.LimitPercentSetting, tc.percent)
// A request refused for the list is not counted.
counted := line.fields["counts"] != nil
if counted != (tc.actions[i] != denied) {
t.Errorf("request from %s counted %t, logged %s", from, counted,
tc.actions[i])
}
}
}
// A client no list lists has the whole limit.
for range 3 {
line := s.get(unplaced, http.StatusOK, forward)
wantReputation(t, line)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
none)
}
// A refusal for the list makes no ban.
if held := server.Ledger.Snapshot(); tc.action == actionDeny && len(held) != 0 {
t.Errorf("bans %+v, want none", held)
}
})
}
}
func TestBlocklistsComeAfterTheCountryListsAndSkipAllowNets(t *testing.T) {
t.Parallel()
s, server, queue := startWithLookups(t, map[string]string{
blocklistURLs: dropURL, deniedCountries: "kp", allowNets: fromDE,
})
loadLists(t, server, map[string][]string{dropURL: {fromDE, fromKP}})
// fromKP's country refuses it before the list is looked at, and fromDE,
// in SWWAF_ALLOW_NETS, is not checked at all: neither is noted, nor
// alerted.
wantReputation(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied))
wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward))
wantAlerts(t, queue)
}
func TestObserveModeForwardsAClientABlocklistDeniesAndAlertsIt(t *testing.T) {
t.Parallel()
s, server, queue := startWithLookups(t, map[string]string{
blocklistURLs: dropURL, mode: observe,
})
loadLists(t, server, map[string][]string{dropURL: {fromDE}})
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionDenied)
wantReputation(t, line, dropURL)
waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
if len(waiting) != 1 || waiting[0].Event != alerts.EventReputationHit {
t.Errorf("alerts waiting %+v, want a reputation_hit alert", waiting)
}
}
func TestBlocklistLimitTakesPartInTheLowestPercentageOfEveryLimit(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
action, asnPercent string
// want is the upload's limit_percent and bytes_percent, as
// percentText gives them, and limitHit its limit_hit.
want, limitHit string
}{
{"limit:50", asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
{"limit:25", asnDEHalf, "25 from " + blocklistAction, minuteBytes},
// The AS number's, the first of two alike.
{"limit:25", asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
{actionLog, asnDE + ":100", 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,
})
loadLists(t, server, map[string][]string{dropURL: {fromDE}})
// The upload's 100 bytes are over 49, a quarter of 199, and 99,
// half of it, and within 199.
line := s.uploadFrom(fromDE)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
tc.want)
wantPercent(t, "bytes_percent", line.BytesPercent, line.BytesPercentSetting,
tc.want)
if line.LimitHit != tc.limitHit {
t.Errorf("log line has limit_hit %q, want %q", line.LimitHit, tc.limitHit)
}
})
}
}
func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T) {
t.Parallel()
const (
fromURL = "25 from " + asnLimitPercentURL
fromSetting = "25 from " + asnLimitPercent
)
for _, tc := range []struct {
name string
env map[string]string
file string
// limitPercent and bytesPercent are the upload's, as percentText
// gives them.
limitPercent, bytesPercent string
}{
{"the file's alone", nil, asnDEQuarter, fromURL, fromURL},
{
"the file's, lower than the setting's",
map[string]string{asnLimitPercent: asnDEHalf}, asnDEQuarter, fromURL, fromURL,
},
{
"the setting's, lower than the file's",
map[string]string{asnLimitPercent: asnDEQuarter}, asnDEHalf,
fromSetting, fromSetting,
},
{
"the setting's, the first of two alike",
map[string]string{asnLimitPercent: asnDEQuarter}, asnDEQuarter,
fromSetting, fromSetting,
},
{"none, for an AS number the file does not list", nil, asnKP + ":25", none, none},
{
"SWWAF_ASN_BYTES_PERCENT's in place of the file's for the byte limits",
map[string]string{asnBytesPercent: asnDE + ":100"}, asnDEQuarter, fromURL, none,
},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
env := map[string]string{asnLimitPercentURL: asnURL}
maps.Copy(env, tc.env)
s, server, _ := startWithLookups(t, env)
loadLists(t, server, map[string][]string{asnURL: {"# by AS number", tc.file}})
line := s.uploadFrom(fromDE)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
tc.limitPercent)
wantPercent(t, "bytes_percent", line.BytesPercent, line.BytesPercentSetting,
tc.bytesPercent)
})
}
}
func TestEachBlocklistThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
t *testing.T,
) {
t.Parallel()
const emptyURL = "https://lists.example/empty.txt"
s, clk, server, queue := startWithLookupsAndClock(t, map[string]string{
blocklistURLs: dropURL + "," + torURL + "," + emptyURL,
blocklistAction: actionLog,
metricsToken: token,
})
loadLists(t, server, map[string][]string{dropURL: {fromDE}, torURL: {fromDE}})
// The second request's alerts are repeats, which the cooldown holds
// back.
for range 2 {
wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
dropURL, torURL)
}
hit := func(source string) alerts.Alert {
return alerts.Alert{
Instance: alertInstance,
Time: clk.Now(),
Event: alerts.EventReputationHit,
Client: netip.MustParseAddr(fromDE),
Netblock: netip.MustParsePrefix(fromDE + "/32"),
ASN: asnDE,
ASName: asNameDE,
Country: "DE",
Reason: "listed by a blocklist",
Detail: map[string]any{"source": source},
}
}
wantAlerts(t, queue, hit(dropURL), hit(torURL))
if queue.Suppressed() != 2 {
t.Errorf("%d alerts held back, want the second request's 2", queue.Suppressed())
}
// Each list's hits, none of its fetches failed, and when its copy was
// fetched, 0 for the one without.
metrics := s.scrape(unplaced)
fetched := float64(listsFetched().Unix())
for listURL, want := range map[string]struct{ hits, fetched float64 }{
dropURL: {2, fetched}, torURL: {2, fetched}, emptyURL: {0, 0},
} {
labels := `{instance="` + alertInstance + `",source="` + listURL + `"}`
if want.hits == 0 {
wantNoSeries(t, metrics, "smallwebwaf_reputation_hits_total"+labels)
} else {
wantMetric(t, metrics, "smallwebwaf_reputation_hits_total"+labels, want.hits)
}
wantMetric(t, metrics, "smallwebwaf_reputation_failures_total"+labels, 0)
wantMetric(t, metrics, "smallwebwaf_reputation_last_fetch_timestamp_seconds"+labels,
want.fetched)
}
}
// listsFetched is when loadLists has the copies fetched.
func listsFetched() time.Time {
return time.Date(2026, 10, 5, 0, 0, 0, 0, time.UTC)
}
// loadLists puts copies of lists into server's lists, by URL, each with
// its lines, fetched at listsFetched, as reputation.json would at start.
func loadLists(t *testing.T, server *proxy.Server, copies map[string][]string) {
t.Helper()
lists := make([]reputation.List, 0, len(copies))
for listURL, lines := range copies {
lists = append(lists, reputation.List{
URL: listURL, Fetched: listsFetched(), Lines: lines,
})
}
err := server.Lists.Load(lists)
if err != nil {
t.Fatalf("load the lists: %v", err)
}
}
// wantReputation checks the URLs of the blocklists the log line names in
// its reputation.
func wantReputation(t *testing.T, line logLine, want ...string) {
t.Helper()
if !slices.Equal(line.Reputation, want) {
t.Errorf("log line has reputation %v, want %v", line.Reputation, want)
}
}
+13 -9
View File
@@ -213,14 +213,14 @@ func (rq *request) check(ctx context.Context) *refusal {
// 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, each of them by the client's limit
// percentages, and last the rule files. A request exempt from the rate
// limits is exempt from the byte limits too. ctx is the request's own
// context.
// its AS number and country, then the country lists, and then the
// blocklists; 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,
// each of them by the client's limit percentages, and last the rule
// files. A request exempt from the rate limits is exempt from the byte
// limits too. 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) {
@@ -243,10 +243,14 @@ func (rq *request) checkClient(ctx context.Context) string {
return requestlog.ActionCountryDenied
}
if rq.blocklistDenied() {
return requestlog.ActionDenied
}
rq.counted = !isInside(rq.client, cfg.RateLimitExemptNets) &&
!pathExempt(rq.in.URL, cfg.RateLimitExemptPaths)
if rq.counted {
rq.limitPercent, rq.bytesPercent = limitPercentages(cfg, rq.line.ASN, rq.line.Country)
rq.limitPercent, rq.bytesPercent = rq.limitPercentages()
rq.line.LimitPercent, rq.line.LimitPercentSetting = rq.limitPercent.logged()
rq.line.BytesPercent, rq.line.BytesPercentSetting = rq.bytesPercent.logged()
}