Files
smallwebwaf/internal/sww/waf.go
T
clawbot bba3805372 waf: ban the clients on AbuseIPDB's blacklist (closes #411)
While SWW_WAF_ABUSEIPDB_KEY is set, waf fetches AbuseIPDB's blacklist at
the start and every SWW_WAF_ABUSEIPDB_BLACKLIST_REFRESH_INTERVAL_MINS
(60), cut at SWW_WAF_ABUSEIPDB_THRESHOLD (90, from 25 to 100). Each
listed client's netblock gets a ban of SWW_WAF_ABUSEIPDB_BAN_DAYS (30)
with the new cause abuseipdb. The blacklist itself is not kept.

These bans do not count toward SWW_WAF_MAX_BANS, so a 10,000-address
blacklist cannot push out the bans for limits and attacks. An ended
abuseipdb ban is forgotten at each fetch and each read of bans.json. A
netblock with an active ban is left alone, and so is one whose abuseipdb
ban an admin lifted, until that ban would have ended. Observe mode makes
no ban.

Model: opus-5-5
2026-11-19 11:13:01 +00:00

506 lines
15 KiB
Go

package sww
import (
"context"
"io"
"log/slog"
"net"
"net/http"
"time"
"go.uber.org/fx"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/anomaly"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/coreruleset"
"sneak.berlin/go/smallwebwaf/internal/geojs"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/metrics"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/remotelog"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/routewatch"
"sneak.berlin/go/smallwebwaf/internal/rules"
"sneak.berlin/go/smallwebwaf/internal/state"
"sneak.berlin/go/smallwebwaf/internal/waf"
)
// remoteLogStopTimeout is how long, as waf stops, the log lines still
// waiting are sent to SWW_WAF_LOG_REMOTE_URL before they are given up. stdout has
// carried them.
const remoteLogStopTimeout = 2 * time.Second
// RunWAF is `sww waf`: it reads the settings, the rule files,
// the lookup database and the state and cache files, then serves requests until
// ctx is done. Then it gives the requests in progress shutdownTimeout to
// finish, ends its background work and writes every state and cache file,
// alerts.json with the alerts still waiting. It returns the process's exit
// status, 1 when waf cannot start or stop in order.
func RunWAF(ctx context.Context, params Params) int {
// Until the settings are read, the one message is an invalid setting's
// error, which every SWW_WAF_LOG_LEVEL lets through.
processLog := requestlog.NewProcessLogger(params.Stdout,
config.InstanceName(params.Viper), slog.LevelError)
cfg, err := config.WAFFromEnvironment(params.Viper)
if err != nil {
return cannotStart(processLog, startError{"invalid setting", err})
}
// While SWW_WAF_LOG_REMOTE_URL is set, every line on stdout from here on
// is sent there too. The sender runs before any part is built, so that it
// sends why waf cannot start.
stdout := params.Stdout
var remote *remotelog.Sender
if cfg.LogRemoteURL != nil {
remote = newRemoteLogSender(cfg)
stdout = io.MultiWriter(params.Stdout, remote)
}
processLog = requestlog.NewProcessLogger(
stdout,
cfg.InstanceName,
cfg.LogLevel,
)
if remote != nil {
stopSending := startSending(ctx, remote, processLog)
defer stopSending()
}
var (
files *state.Files
listener net.Listener
)
failed := make(servingFailed, 1)
app := fx.New(
fx.Supply(
params,
cfg,
processLog,
requestLog{stdout},
remote,
failed,
),
fx.Provide(
newAlertQueue, newRuleFiles, newCoreRuleSet, newLookupFile,
newLimiter, newLedger, newAnomalyCounters,
newLists, newDNSBL, newAbuseIPDB, newRouteWatch,
newMetrics, newGeoJS, newWAFServer,
func(server *waf.Server) *http.Server { return server.Server },
newWAFListener, newStateFiles,
),
// fx stops hooks in the reverse of the order they were added in. The
// state files are read before serving is set up, so that serving
// stops before their loops do.
fx.Populate(&files),
fx.Invoke(serve),
fx.Populate(&listener),
fx.WithLogger(fxEventLogger(processLog)),
)
err = app.Err()
if err != nil {
return cannotStart(processLog, err)
}
processLog.Info("starting",
"version", params.Version,
"address", listener.Addr().String(),
"settings", cfg)
// The last write follows the stop of every hook, and so the end of every
// loop that changes the state or raises an alert. A hook of the state
// files would stop before the loops of the parts built ahead of them.
return run(ctx, app, failed, processLog, func() error {
err := files.WriteAll()
if err != nil {
processLog.Error("writing the state and cache files failed",
"error", err.Error())
}
return err
})
}
// newAlertQueue returns the queue of the alerts to the webhook, Slack and
// ntfy, with the settings for them. Until waf stops, it sends them.
func newAlertQueue(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
) *alerts.Queue {
alertQueue := alerts.New(alerts.Params{
WebhookURL: cfg.AlertWebhookURL,
WebhookHeaders: cfg.AlertWebhookHeaders,
SlackURL: cfg.AlertSlackWebhookURL,
NtfyURL: cfg.AlertNtfyURL,
NtfyToken: cfg.AlertNtfyToken,
Events: cfg.AlertEvents,
Cooldown: cfg.AlertCooldown,
MaxPerHour: cfg.AlertMaxPerHour,
Instance: cfg.InstanceName,
Now: utcNow,
ProcessLog: processLog,
})
lc.Append(background(alertQueue.Run))
return alertQueue
}
// newRuleFiles reads the rule files, and reads them again as they change
// until waf stops.
func newRuleFiles(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
alertQueue *alerts.Queue,
) (*rules.Files, error) {
ruleFiles, err := rules.Load(rules.Params{
Dir: cfg.RuleFilesDir,
Enabled: cfg.RuleFilesEnabled,
ProcessLog: processLog,
Alerts: alertQueue,
})
if err != nil {
return nil, startError{"cannot use the rule files", err}
}
lc.Append(background(ruleFiles.Watch))
return ruleFiles, nil
}
// newCoreRuleSet returns the Core Rule Set, as waf.NewCoreRuleSet does.
func newCoreRuleSet(cfg *config.WAF) (*coreruleset.CoreRuleSet, error) {
crs, err := waf.NewCoreRuleSet(cfg)
if err != nil {
return nil, startError{"cannot use the Core Rule Set", err}
}
return crs, nil
}
// newLookupFile reads the lookup database while SWW_WAF_LOOKUP_SOURCE is
// file, and reads it again when it is replaced until waf stops. It returns
// nil while the source is anything else.
func newLookupFile(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
alertQueue *alerts.Queue,
) (*lookup.File, error) {
if cfg.LookupSource != "file" {
return nil, nil //nolint:nilnil // no lookup database, and no error
}
lookupFile, err := lookup.OpenFile(lookup.FileParams{
Path: cfg.LookupDBPath,
Now: utcNow,
ProcessLog: processLog,
Alerts: alertQueue,
})
if err != nil {
return nil, startError{"cannot use the lookup database", err}
}
lc.Append(background(lookupFile.Watch))
return lookupFile, nil
}
// newLimiter returns the table of clients, with the rate and byte limits.
func newLimiter(cfg *config.WAF) *ratelimit.Limiter {
return ratelimit.New(ratelimit.Limits{
PerMinute: cfg.RateLimitPerMinute,
PerHour: cfg.RateLimitPerHour,
PerDay: cfg.RateLimitPerDay,
BytesPerMinute: cfg.BytesLimitPerMinute,
BytesPerHour: cfg.BytesLimitPerHour,
BytesPerDay: cfg.BytesLimitPerDay,
}, cfg.MaxTrackedClients)
}
// newLedger returns the ledger of the bans, with the settings for them.
func newLedger(cfg *config.WAF) *bans.Ledger {
return bans.New(bans.Params{
LimitBanDuration: cfg.LimitBanDuration,
LimitBanRepeatWindow: cfg.LimitBanRepeatWindow,
LimitBanPermanentAbove: cfg.LimitBanPermanentAbove,
AttackBanDuration: cfg.AttackBanDuration,
MaxBans: cfg.MaxBans,
})
}
// newAnomalyCounters returns the counters of the anomaly thresholds.
func newAnomalyCounters(
cfg *config.WAF, alertQueue *alerts.Queue,
) *anomaly.Counters {
return anomaly.New(anomaly.Params{
Client: cfg.AnomalyClient,
Net: cfg.AnomalyNet,
ASN: cfg.AnomalyASN,
Total: cfg.AnomalyTotal,
WatchedNet: cfg.AnomalyWatchedNet,
NetV4Prefix: cfg.AnomalyNetV4Prefix,
NetV6Prefix: cfg.AnomalyNetV6Prefix,
NamedNetblocks: cfg.AnomalyWatchedNets,
Alerts: alertQueue,
})
}
// newLists returns the lists the settings name by URL, none fetched yet.
// Until waf stops, it fetches them as they are due.
func newLists(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
alertQueue *alerts.Queue,
) *reputation.Lists {
lists := reputation.New(reputation.Params{
BlocklistURLs: cfg.BlocklistURLs,
Refresh: cfg.BlocklistRefresh,
ASNLimitPercentURL: cfg.ASNLimitPercentURL,
TagLists: cfg.TagLists,
Now: utcNow,
ProcessLog: processLog,
Alerts: alertQueue,
})
lc.Append(background(lists.Run))
return lists
}
// newDNSBL returns what asks the DNSBL zones, none asked yet.
func newDNSBL(
cfg *config.WAF, processLog *slog.Logger, alertQueue *alerts.Queue,
) *reputation.DNSBL {
return reputation.NewDNSBL(reputation.DNSBLParams{
Zones: cfg.DNSBLZones,
Resolver: cfg.DNSBLResolver,
CacheTTL: cfg.IPReputationCacheTTL,
Timeout: cfg.DNSBLAbuseIPDBTimeout,
Now: utcNow,
ProcessLog: processLog,
Alerts: alertQueue,
})
}
// newAbuseIPDB returns what checks clients with AbuseIPDB while
// SWW_WAF_ABUSEIPDB_KEY is set, none checked yet. Until waf stops, it
// fetches AbuseIPDB's blacklist as it is due, and bans the clients on it in
// ledger, as waf.BanAbuseIPDBBlacklist says.
func newAbuseIPDB(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
alertQueue *alerts.Queue, ledger *bans.Ledger,
) *reputation.AbuseIPDB {
abuseIPDB := reputation.NewAbuseIPDB(reputation.AbuseIPDBParams{
URL: reputation.AbuseIPDBURL,
Key: cfg.AbuseIPDBKey,
MinScore: cfg.AbuseIPDBMinScore,
DailyBudget: cfg.AbuseIPDBDailyBudget,
CacheTTL: cfg.IPReputationCacheTTL,
Timeout: cfg.DNSBLAbuseIPDBTimeout,
BlacklistURL: reputation.AbuseIPDBBlacklistURL,
Threshold: cfg.AbuseIPDBThreshold,
BlacklistRefresh: cfg.AbuseIPDBBlacklistRefresh,
Blacklisted: func(listed []reputation.BlacklistEntry) {
waf.BanAbuseIPDBBlacklist(
cfg, ledger, processLog, utcNow(), listed,
)
},
Now: utcNow,
ProcessLog: processLog,
Alerts: alertQueue,
})
lc.Append(background(abuseIPDB.RunBlacklist))
return abuseIPDB
}
// newRouteWatch returns what asks routewatch about clients, or nil while
// SWW_WAF_ROUTEWATCH_URL is unset.
func newRouteWatch(
cfg *config.WAF, processLog *slog.Logger,
) *routewatch.Client {
if cfg.RouteWatchURL == "" {
return nil
}
return routewatch.New(routewatch.Params{
URL: cfg.RouteWatchURL,
Now: utcNow,
ProcessLog: processLog,
})
}
// newMetrics returns the metrics, with those read from the other parts as
// the metrics are asked for: AbuseIPDB's while SWW_WAF_ABUSEIPDB_KEY is set,
// the lookup database's while there is one, and the remote log sender's
// while there is one.
func newMetrics(
cfg *config.WAF, ledger *bans.Ledger, limiter *ratelimit.Limiter,
ruleFiles *rules.Files, lists *reputation.Lists,
dnsbl *reputation.DNSBL, abuseIPDB *reputation.AbuseIPDB,
alertQueue *alerts.Queue, lookupFile *lookup.File,
remote *remotelog.Sender,
) *metrics.Metrics {
m := metrics.New(cfg.MetricsBusiestCountriesAndASNs, cfg.InstanceName)
m.AddBansAndClients(ledger, limiter, utcNow)
m.AddRules(ruleFiles)
m.AddReputation(lists, dnsbl)
if cfg.AbuseIPDBKey != "" {
m.AddAbuseIPDB(abuseIPDB)
}
m.AddAlerts(alertQueue)
if lookupFile != nil {
m.AddLookupFile(lookupFile.LastRead, lookupFile.ReadFailures)
}
if remote != nil {
m.AddRemoteLog(remote)
}
return m
}
// newGeoJS returns what looks clients up at GeoJS, none looked up yet. Each
// answer goes to the limiter and the ledger, as waf.AddLookup says, and each
// failure is handled as waf.GeoJSFailed says.
func newGeoJS(
cfg *config.WAF, m *metrics.Metrics, limiter *ratelimit.Limiter,
ledger *bans.Ledger, alertQueue *alerts.Queue, processLog *slog.Logger,
) *geojs.GeoJS {
return geojs.New(geojs.Params{
URL: geojs.URL,
Answered: func(answer geojs.Answer) {
waf.AddLookup(cfg, limiter, ledger, answer)
},
Now: utcNow,
Asked: m.GeoJSRequests.Inc,
Failed: func(err error, askingAgainIn time.Duration) {
waf.GeoJSFailed(processLog, alertQueue, m, err, askingAgainIn)
},
WentWithoutAnswer: m.RequestsWithoutGeoJSAnswer.Inc,
})
}
// newWAFServer returns the server waf runs, with its parts and the time
// limit params gives.
func newWAFServer(
params Params, cfg *config.WAF, out requestLog, processLog *slog.Logger,
m *metrics.Metrics, limiter *ratelimit.Limiter, ledger *bans.Ledger,
anomalies *anomaly.Counters, lists *reputation.Lists,
dnsbl *reputation.DNSBL, abuseIPDB *reputation.AbuseIPDB,
routeWatch *routewatch.Client, geoJS *geojs.GeoJS,
lookupFile *lookup.File, crs *coreruleset.CoreRuleSet,
ruleFiles *rules.Files, alertQueue *alerts.Queue,
) *waf.Server {
return waf.New(waf.Params{
Config: cfg,
RequestLog: out,
ProcessLog: processLog,
Metrics: m,
Limiter: limiter,
Ledger: ledger,
Anomalies: anomalies,
Lists: lists,
DNSBL: dnsbl,
AbuseIPDB: abuseIPDB,
RouteWatch: routeWatch,
GeoJS: geoJS,
LookupFile: lookupFile,
CoreRuleSet: crs,
Now: utcNow,
Rules: ruleFiles,
Alerts: alertQueue,
BesideLookupTimeLimit: params.BesideLookupTimeLimit,
})
}
// newWAFListener listens on SWW_WAF_LISTEN_ADDR.
func newWAFListener(cfg *config.WAF) (net.Listener, error) {
return listen(cfg.ListenAddr, "SWW_WAF_LISTEN_ADDR")
}
// newStateFiles reads the state and cache files into the parts and the
// alert queue, as state.Load does. Until waf stops, it writes them as they
// are due and takes in an admin's edits of them.
func newStateFiles(
lc fx.Lifecycle, cfg *config.WAF, processLog *slog.Logger,
m *metrics.Metrics, ledger *bans.Ledger, limiter *ratelimit.Limiter,
geoJS *geojs.GeoJS, lists *reputation.Lists, dnsbl *reputation.DNSBL,
abuseIPDB *reputation.AbuseIPDB, routeWatch *routewatch.Client,
alertQueue *alerts.Queue, anomalies *anomaly.Counters,
) (*state.Files, error) {
files, err := state.Load(state.Params{
Dir: cfg.StateDir,
CacheDir: cfg.CacheDir,
BansWriteDelay: cfg.BansWriteDelay,
WriteInterval: cfg.StateWriteInterval,
Ledger: ledger,
Limiter: limiter,
GeoJS: geoJS,
Lists: lists,
DNSBL: dnsbl,
AbuseIPDB: abuseIPDB,
RouteWatch: routeWatch,
Alerts: alertQueue,
Anomalies: anomalies,
Now: utcNow,
ProcessLog: processLog,
Metrics: m,
})
if err != nil {
return nil, startError{"cannot use the state and cache files", err}
}
lc.Append(background(files.Run))
lc.Append(background(files.Watch))
return files, nil
}
// newRemoteLogSender returns a sender of the log lines to
// SWW_WAF_LOG_REMOTE_URL, with the settings for it.
func newRemoteLogSender(cfg *config.WAF) *remotelog.Sender {
return remotelog.New(remotelog.Params{
URL: cfg.LogRemoteURL,
RootCAs: cfg.LogRemoteTLSCAs,
BufferLines: cfg.LogRemoteBufferLines,
Facility: cfg.LogRemoteFacility,
AppName: cfg.LogRemoteAppName,
})
}
// startSending runs remote until the function it returns is called, which
// then waits at most remoteLogStopTimeout for the lines still waiting to
// be sent. Sending goes on after ctx is done, so that the lines written
// while sww stops are sent too.
func startSending(
ctx context.Context, remote *remotelog.Sender, processLog *slog.Logger,
) func() {
sending, stop := context.WithCancel(context.WithoutCancel(ctx))
sent := make(chan struct{})
go func() {
remote.Run(sending, processLog)
close(sent)
}()
return func() {
stop()
select {
case <-sent:
case <-time.After(remoteLogStopTimeout):
}
}
}