Author SHA1 Message Date
sneak 4f1ad1ffc9 README rewritten from scratch so a newcomer can follow it (closes #154, closes #155)
check / check (push) Canceled after 0s
The old README opened with project history and one list of a hundred
settings. The new one leads with what smallwebwaf is, what it protects
against, how to build and deploy it, what happens to a request, what a
refused visitor and the operator see, and how to check it works. The
settings follow, grouped by topic, each with its default and what a bad
value does. The rest is reference. Every statement was checked against
the code on next. Short sentences, bulleted lists in place of comma
chains, no tables, identifiers in backticks.

Model: fable-5-1
2026-10-22 20:03:29 +00:00
152 changed files with 10797 additions and 21677 deletions

No files matched your search

+42 -31
View File
@@ -87,7 +87,7 @@ COPY . .
# .git present, a version that is still empty, dev or unknown fails the # .git present, a version that is still empty, dev or unknown fails the
# build: git is missing or could not read the checkout. The no_fs_access # build: git is missing or could not read the checkout. The no_fs_access
# tag keeps Coraza from writing the files of a multipart body to the # tag keeps Coraza from writing the files of a multipart body to the
# system's temporary directory, since sww writes only to its state # system's temporary directory, since smallwebwaf writes only to its state
# directory. # directory.
ARG VERSION ARG VERSION
RUN VERSION="${VERSION:-$(git describe --tags --always)}"; \ RUN VERSION="${VERSION:-$(git describe --tags --always)}"; \
@@ -99,7 +99,7 @@ RUN VERSION="${VERSION:-$(git describe --tags --always)}"; \
fi; \ fi; \
CGO_ENABLED=0 go build -tags no_fs_access -trimpath \ CGO_ENABLED=0 go build -tags no_fs_access -trimpath \
-ldflags="-s -w -X main.Version=${VERSION}" \ -ldflags="-s -w -X main.Version=${VERSION}" \
-o /usr/local/bin/sww ./cmd/sww -o /usr/local/bin/smallwebwaf ./cmd/smallwebwaf
# runsvinit, the image's entrypoint, built at the last commit of its # runsvinit, the image's entrypoint, built at the last commit of its
# archived repository. It has no go.mod, and `go build` of its directory # archived repository. It has no go.mod, and `go build` of its directory
@@ -117,9 +117,8 @@ RUN git checkout --quiet --detach b4b2c785308b1ce785b6155c7fe5f16879080193 \
&& CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" \ && CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" \
-o /usr/local/bin/runsvinit . -o /usr/local/bin/runsvinit .
# The image, described under "Deployment" in SPEC.md. It runs rproxy unless # The image an app's Dockerfile builds FROM, described under "Deployment"
# SWW_COMMAND says discriminator, and an app's Dockerfile can build FROM it. # in SPEC.md. It is the last stage, so a plain `docker build .` builds it.
# It is the last stage, so a plain `docker build .` builds it.
# #
# ubuntu 26.04, 2026-09-27 # ubuntu 26.04, 2026-09-27
FROM ubuntu@sha256:f144425ff09be612d6d9ad965196e9cdc23dae1f42110a8a11a3e9a8198759f7 FROM ubuntu@sha256:f144425ff09be612d6d9ad965196e9cdc23dae1f42110a8a11a3e9a8198759f7
@@ -133,22 +132,34 @@ RUN mkdir /etc/sysusers.d \
&& echo 'u _runit-log - "runit svlogd user" /nonexistent /sbin/nologin' \ && echo 'u _runit-log - "runit svlogd user" /nonexistent /sbin/nologin' \
> /etc/sysusers.d/runit.conf > /etc/sysusers.d/runit.conf
# ca-certificates, nix-bin and runit, from Ubuntu's archive. apt fetches # ca-certificates, nix-bin and runit, from Ubuntu's archive as it was at
# them over plain HTTP and checks each one against the archive's signed # the snapshot moment, which is never earlier than the Ubuntu image above.
# package lists, so no CA certificates are needed. # apt checks every package against the snapshot's InRelease files, and
# # this step checks those against the hashes named here, which are those
# nix-bin depends on xz-utils, whose install links man pages with # of the amd64 archive: other architectures use Ubuntu's ports archive.
# update-alternatives. The image's dpkg config drops man pages, so each # apt also fetches the live archive's InRelease files, which change daily
# link warns. z-man, read after /etc/dpkg/dpkg.cfg.d/excludes, re-includes # and which the install does not use. The snapshot service is HTTPS only
# the man1 pages for this install alone; the same step deletes them again, # and this image has no CA certificates yet, so this step uses the Go
# so no man page or package is added. # image's. The snapshot service answers 503 at times; apt retries a
RUN echo 'path-include=/usr/share/man/man1/*' > /etc/dpkg/dpkg.cfg.d/z-man \ # failed download, waiting twice as long before each retry, and this
&& apt-get update \ # step gives it five retries, about half a minute in all, where its
# default of three gives up after seven seconds.
RUN --mount=type=bind,from=builder,source=/etc/ssl/certs/ca-certificates.crt,target=/tmp/go-image-ca.crt \
apt-get update --snapshot 20261001T000000Z \
-o Acquire::https::CaInfo=/tmp/go-image-ca.crt \
-o Acquire::Retries=5 \
&& printf '%s\n' \
'45f95ce276cdba3e41870516a130e03c58b8b7a79e9546b0efe9e526d255740c snapshot.ubuntu.com_ubuntu_20261001T000000Z_dists_resolute_InRelease' \
'802e675dd9de4c7f3916434a95e7c1d8eec0e82886622d7805ab19a2c6fe0365 snapshot.ubuntu.com_ubuntu_20261001T000000Z_dists_resolute-updates_InRelease' \
'64b3353f0bd4970b4f7271962245bcea9ff24d4cc7bea16b433f8a60e42ca3dd snapshot.ubuntu.com_ubuntu_20261001T000000Z_dists_resolute-backports_InRelease' \
'1d5041572116a8b23aabf79ac7439ad8af83d57ad3fb0f9aa0d4523ec10c5908 snapshot.ubuntu.com_ubuntu_20261001T000000Z_dists_resolute-security_InRelease' \
| (cd /var/lib/apt/lists && sha256sum --check --strict) \
&& DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \ && DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
--snapshot 20261001T000000Z \
-o Acquire::https::CaInfo=/tmp/go-image-ca.crt \
-o Acquire::Retries=5 \
ca-certificates nix-bin runit \ ca-certificates nix-bin runit \
&& rm -rf /var/lib/apt/lists/* /etc/dpkg/dpkg.cfg.d/z-man \ && rm -rf /var/lib/apt/lists/*
&& find /usr/share/man/man1 ! -type d -delete \
&& find /etc/alternatives -type l -xtype l -delete
# Nix run by root expects a group of build users, which nix-bin does not # Nix run by root expects a group of build users, which nix-bin does not
# create; with the setting empty, root's builds run without them. # create; with the setting empty, root's builds run without them.
@@ -175,27 +186,27 @@ RUN curl -fsSL -o /tmp/nixexprs.tar.xz \
ENV PATH=${PATH}:/nix/var/nix/profiles/default/bin ENV PATH=${PATH}:/nix/var/nix/profiles/default/bin
COPY --from=runsvinit /usr/local/bin/runsvinit /usr/local/bin/runsvinit COPY --from=runsvinit /usr/local/bin/runsvinit /usr/local/bin/runsvinit
COPY --from=builder /usr/local/bin/sww /usr/local/bin/sww COPY --from=builder /usr/local/bin/smallwebwaf /usr/local/bin/smallwebwaf
# 65532 is above the uids Ubuntu keeps for system users, which end at # 65532 is above the uids Ubuntu keeps for system users, which end at
# 999; useradd warns about it unless --key raises that end for this call. # 999; useradd warns about it unless --key raises that end for this call.
RUN groupadd --system --gid 65532 sww \ RUN groupadd --system --gid 65532 smallwebwaf \
&& useradd --system --key SYS_UID_MAX=65532 --uid 65532 \ && useradd --system --key SYS_UID_MAX=65532 --uid 65532 \
--gid sww --no-create-home --shell /usr/sbin/nologin \ --gid smallwebwaf --no-create-home --shell /usr/sbin/nologin \
sww smallwebwaf
# The state files' directory, SWW_STATE_DIR by default, where a volume # The state files' directory, SWWAF_STATE_DIR by default, where a volume
# is mounted to keep them across deploys. The run script gives it to the # is mounted to keep them across deploys. The run script gives it to the
# sww user at each start of discriminator. # smallwebwaf user at each start.
RUN mkdir /var/lib/sww RUN mkdir /var/lib/smallwebwaf
# The default rule file, in SWW_RULES_DIR by default, where a Dockerfile # The default rule file, in SWWAF_RULES_DIR by default, where an app's
# built FROM this image can copy rule files of its own beside it. # Dockerfile can copy rule files of its own beside it.
COPY share/rules.d/00-default.rules /etc/sww/rules.d/00-default.rules COPY share/rules.d/00-default.rules /etc/smallwebwaf/rules.d/00-default.rules
# runsvinit starts runit's runsvdir on /etc/service, where Ubuntu's sv # runsvinit starts runit's runsvdir on /etc/service, where Ubuntu's sv
# looks too. # looks too.
COPY --chmod=755 share/sww.run /etc/service/sww/run COPY --chmod=755 share/smallwebwaf.run /etc/service/smallwebwaf/run
EXPOSE 8080 EXPOSE 8080
@@ -203,6 +214,6 @@ EXPOSE 8080
# check runs every second from the start until it first passes, for up # check runs every second from the start until it first passes, for up
# to a minute, and every 30 seconds after that. # to a minute, and every 30 seconds after that.
HEALTHCHECK --start-period=1m --start-interval=1s \ HEALTHCHECK --start-period=1m --start-interval=1s \
CMD ["/usr/local/bin/sww", "healthcheck"] CMD ["/usr/local/bin/smallwebwaf", "healthcheck"]
ENTRYPOINT ["/usr/local/bin/runsvinit"] ENTRYPOINT ["/usr/local/bin/runsvinit"]
+46 -58
View File
@@ -12,8 +12,8 @@ configured only by environment variables, that provides:
- R1: rate limits per minute, per hour and per day - R1: rate limits per minute, per hour and per day
- R2: netblocks that bypass rate limiting - R2: netblocks that bypass rate limiting
- R3: alerts on attacks through webhook, Slack or ntfy - R3: alerts on attacks through webhook, Slack or ntfy
- R4: alerts on anomalies: requests made or bytes transferred per minute or - R4: alerts on anomalies: requests or bytes per minute or hour, for given IPs
hour, for given IPs or netblocks, crossing a threshold or netblocks, crossing a threshold
- R5: temporary blocks for abusers, permanent bans for repeat offenders - R5: temporary blocks for abusers, permanent bans for repeat offenders
- R6: one or more RBLs or IP reputation APIs - R6: one or more RBLs or IP reputation APIs
- R7: AS number lookup - R7: AS number lookup
@@ -24,19 +24,14 @@ configured only by environment variables, that provides:
## Verdict ## Verdict
Nothing existing is suitable. No surveyed tool meets R8, which asks for limits Nothing existing is suitable. No surveyed tool meets R8 (scaling limits by AS
scaled by AS number or country. None meets R4's alerts on bytes transferred. The number or country) or the bytes half of R4 at all, and the tools that come
tools that come closest on the rest fail R10: they need several containers, YAML closest on the rest fail R10: they need several containers, YAML or a web UI.
or a web UI. The recommendation is to build a small single-binary sidecar; The recommendation is to build a small single-binary sidecar; `SPEC.md` in this
`SPEC.md` in this directory begins that spec. directory begins that spec. It reuses the mature parts of the surveyed field as
libraries and data sources (Coraza and the OWASP Core Rule Set for attack
The sidecar reuses the mature parts of the surveyed field instead of detection, DNSBLs, AbuseIPDB, optionally a CrowdSec decision feed) instead of
reimplementing them. It takes these as libraries and data sources: reimplementing them.
- Coraza and the OWASP Core Rule Set, for attack detection
- DNSBLs
- AbuseIPDB
- optionally, a CrowdSec decision feed
Closest existing options, and why each still falls short: Closest existing options, and why each still falls short:
@@ -50,16 +45,13 @@ Closest existing options, and why each still falls short:
external blacklist URLs, optional CrowdSec), R7 partly (AS number used for external blacklist URLs, optional CrowdSec), R7 partly (AS number used for
blacklist and whitelist decisions), R9 (ModSecurity with the Core Rule blacklist and whitelist decisions), R9 (ModSecurity with the Core Rule
Set, or Coraza plugin), env-var settings. Set, or Coraza plugin), env-var settings.
- Fails: - Fails: R8 (AS number and country can only allow or deny, never scale a
- R8: AS number and country can only allow or deny, never scale a limit. limit), R4 (no volume or byte threshold alerts in the free edition;
- R4: no alerts on request-count or byte thresholds in the free edition; reporting is a paid feature), R5 escalation, and R10 in spirit: since 1.6
reporting is a paid feature. it needs a `bunkerweb` container plus a `bw-scheduler` container and a
- R5: no escalation for repeat offenders. database, or the all-in-one image that bundles nginx, scheduler, UI and
- R10: since 1.6 it is not one plain sidecar. It needs a `bunkerweb` Redis in one container. It is designed to be the front door for many
container, a `bw-scheduler` container and a database, or the sites, not a per-app sidecar. AGPL-3.0.
all-in-one image that bundles nginx, the scheduler, the UI and Redis.
- It is designed as the proxy in front of many sites, not as a sidecar for
one app. AGPL-3.0.
- Unverified: whether several rates (minute, hour, day) can be stacked on - Unverified: whether several rates (minute, hour, day) can be stacked on
the same URL pattern; the documented design is one rate per URL pattern. the same URL pattern; the documented design is one rate per URL pattern.
- CrowdSec is the strongest detection and ban engine, but it is not a proxy. - CrowdSec is the strongest detection and ban engine, but it is not a proxy.
@@ -74,20 +66,16 @@ Closest existing options, and why each still falls short:
listed AS numbers is possible, but each is a hand-written YAML scenario, listed AS numbers is possible, but each is a hand-written YAML scenario,
it reacts after the fact by banning, and it is not an inline limiter that it reacts after the fact by banning, and it is not an inline limiter that
answers 429. answers 429.
- Fails: - Fails: R10 (needs the security engine container with persistent state, log
- R10, because it needs: acquisition from traefik, a bouncer such as the traefik plugin, and YAML
- the security engine container with persistent state for acquisition, profiles, scenarios and notifications), bytes half of R4.
- log acquisition from traefik
- a bouncer such as the traefik plugin
- YAML for acquisition, profiles, scenarios and notifications
- R4's alerts on bytes.
- CrowdSec plus traefik's own `rateLimit` middleware is the best combination - CrowdSec plus traefik's own `rateLimit` middleware is the best combination
with no new code. It gives inline limiting (one window per middleware, keyed with no new code. It gives inline limiting (one window per middleware, keyed
by IP, with `sourceCriterion` exclusions), bans with escalation, alerts and by IP, with `sourceCriterion` exclusions), bans with escalation, alerts and
reputation lookups. It still fails R8, R4's alerts on bytes, and R10 entirely: reputation. It still fails R8, the bytes half of R4, R1's three stacked
the configuration lives in traefik labels and CrowdSec YAML on each host, not windows only by chaining three middlewares per router, and R10 entirely: the
in one sidecar's environment. It meets R1's three windows only by chaining configuration lives in traefik labels and CrowdSec YAML on each host, not in
three middlewares per router. one sidecar's environment.
## Candidate by candidate ## Candidate by candidate
@@ -99,10 +87,10 @@ Closest existing options, and why each still falls short:
cached, streamed decision list (recommended), standalone against the cached, streamed decision list (recommended), standalone against the
central API, or AppSec only. Supports captcha remediation. central API, or AppSec only. Supports captcha remediation.
- Covers: R5, R6, R9, R3 and R7 through the engine (see Verdict). - Covers: R5, R6, R9, R3 and R7 through the engine (see Verdict).
- Misses: the plugin itself does no rate limiting; R8; R4's alerts on bytes. - Misses: the plugin itself does no rate limiting; R8; R4 bytes.
- Configuration: traefik static config to load the plugin, dynamic config or - Configuration: traefik static config to load the plugin, dynamic config or
labels for the middleware, CrowdSec YAML for everything else. labels for the middleware, CrowdSec YAML for everything else.
- Sidecar fit: no. It runs inside traefik and needs a separate engine - Sidecar fit: no. It lives inside traefik, plus a separate engine
container. container.
- Maturity: widely used (about 900 stars, listed in the traefik plugin - Maturity: widely used (about 900 stars, listed in the traefik plugin
catalog, documented by CrowdSec itself), actively maintained. Traefik catalog, documented by CrowdSec itself), actively maintained. Traefik
@@ -127,7 +115,7 @@ Closest existing options, and why each still falls short:
- What it is: nginx-derived (Tengine) reverse proxy with a proprietary - What it is: nginx-derived (Tengine) reverse proxy with a proprietary
semantic detection engine and a web console. About 22,000 stars. semantic detection engine and a web console. About 22,000 stars.
- Covers: R9 well, basic per-IP rate limiting with block duration, bot - Covers: R9 well, basic per-IP rate limiting with block duration, bot
challenge, authentication in front of the app. challenge, authentication gate.
- Misses: R8, R7, R4; R1 has one window per rule. Country blocking, alert - Misses: R8, R7, R4; R1 has one window per rule. Country blocking, alert
messages, syslog forwarding and the better reputation database are paid messages, syslog forwarding and the better reputation database are paid
(Lite about 10 USD per month, Pro about 100 USD per month); the free (Lite about 10 USD per month, Pro about 100 USD per month); the free
@@ -140,7 +128,7 @@ Closest existing options, and why each still falls short:
- Coraza (`corazawaf/coraza`) and Coraza-based proxies - Coraza (`corazawaf/coraza`) and Coraza-based proxies
- What it is: a Go library that implements the ModSecurity rule language and - What it is: a Go library that implements the ModSecurity rule language and
runs the OWASP Core Rule Set. OWASP project, actively maintained, the runs the OWASP Core Rule Set. OWASP project, actively maintained, the
successor to ModSecurity, which is now in maintenance only. successor path now that ModSecurity is in maintenance only.
- Packagings: `coraza-caddy` (Caddy module), `coraza-spoa` (HAProxy), - Packagings: `coraza-caddy` (Caddy module), `coraza-spoa` (HAProxy),
`coraza-proxy-wasm` (Envoy), a traefik WASM plugin, and `coraza-proxy-wasm` (Envoy), a traefik WASM plugin, and
`coreruleset/coraza-crs-docker` (Caddy plus Coraza plus the Core Rule Set, `coreruleset/coraza-crs-docker` (Caddy plus Coraza plus the Core Rule Set,
@@ -154,7 +142,7 @@ Closest existing options, and why each still falls short:
- ModSecurity Core Rule Set containers (`owasp/modsecurity-crs`) - ModSecurity Core Rule Set containers (`owasp/modsecurity-crs`)
- What it is: official images of Apache or nginx with ModSecurity and the - What it is: official images of Apache or nginx with ModSecurity and the
Core Rule Set, as a reverse proxy configured by env vars (`BACKEND`, Core Rule Set, as a reverse proxy configured by env vars (`BACKEND`,
paranoia level, anomaly thresholds, many more). Current images contain paranoia level, anomaly thresholds, many more). Current images carry
ModSecurity 2.9.x on Apache and Core Rule Set 4.x. ModSecurity 2.9.x on Apache and Core Rule Set 4.x.
- Covers: R9, and R10 (single container, env vars, one backend). - Covers: R9, and R10 (single container, env vars, one backend).
- Misses: R1 to R8. - Misses: R1 to R8.
@@ -164,16 +152,16 @@ Closest existing options, and why each still falls short:
- Anubis (`TecharoHQ/anubis`), 1.27 current - Anubis (`TecharoHQ/anubis`), 1.27 current
- What it is: a single-binary reverse proxy that makes browsers solve a - What it is: a single-binary reverse proxy that makes browsers solve a
proof-of-work challenge before passing them to `TARGET`. Aimed at proof-of-work challenge before passing them to `TARGET`. Aimed at
scrapers, which are likely a large share of the unwanted traffic on a scrapers, which is likely a large share of unwanted traffic on a public
public code forge. gitea.
- Covers: R10 well (one container, env vars for listener, target, - Covers: R10 well (one container, env vars for listener, target,
difficulty, cookies). Policy rules can match on path, user agent, headers, difficulty, cookies). Policy rules can match on path, user agent, headers,
IP ranges, and with the vendor's hosted data service also AS number and IP ranges, and with the vendor's hosted data service also AS number and
country, and can weigh a request toward a harder challenge. country, and can weigh a request toward a harder challenge.
- Misses: R1, R3, R4, R5, R6, R9. Bot policy needs a YAML file, not env - Misses: R1, R3, R4, R5, R6, R9. Bot policy needs a YAML file, not env
vars. AS number and country matching depend on the vendor's hosted vars. AS number and country matching depend on the vendor's hosted
service. Breaks non-browser clients unless paths are exempted; for a code service. Breaks non-browser clients unless paths are exempted; for gitea,
forge, git-over-HTTP and API paths must be allowed through by rule. git-over-HTTP and API paths must be allowed through by rule.
- Maturity: very active, widely deployed on code forges since 2025. - Maturity: very active, widely deployed on code forges since 2025.
- Value here: complementary. It can be chained (traefik, then the sidecar, - Value here: complementary. It can be chained (traefik, then the sidecar,
then Anubis, then the app) if challenge pages are wanted. then Anubis, then the app) if challenge pages are wanted.
@@ -192,13 +180,13 @@ Closest existing options, and why each still falls short:
temporary ban, no escalation, state lost on traefik restart) and R2 temporary ban, no escalation, state lost on traefik restart) and R2
(allowlist). Nothing else. (allowlist). Nothing else.
- `juitde/traefik-plugin-fail2ban`, fail2ban connector plugins, GeoBlock - `juitde/traefik-plugin-fail2ban`, fail2ban connector plugins, GeoBlock
plugins (country allow or deny through an external lookup API): each adds plugins (country allow or deny through an external lookup API): same
one small feature, is configured in traefik and keeps its state in memory. shape, each one small feature, configured in traefik, state in memory.
- Sidecar fit: no; they live inside traefik. - Sidecar fit: no; they live inside traefik.
- Traefik built-in middlewares - Traefik built-in middlewares
- `rateLimit` (one average-and-burst window per middleware, optional Redis - `rateLimit` (one average-and-burst window per middleware, optional Redis
in traefik 3.x), `inFlightReq`, `ipAllowList`. No bans, alerts, reputation in traefik 3.x), `inFlightReq`, `ipAllowList`. No bans, alerts, reputation
lookups or AS number lookups. or AS number awareness.
- caddy-waf (`fabriziosalmi/caddy-waf`), 0.4.x - caddy-waf (`fabriziosalmi/caddy-waf`), 0.4.x
- What it is: a Caddy module with regex rules and anomaly scoring, per-IP - What it is: a Caddy module with regex rules and anomaly scoring, per-IP
and per-path rate limiting with one configurable window, IP and DNS and per-path rate limiting with one configurable window, IP and DNS
@@ -210,12 +198,12 @@ Closest existing options, and why each still falls short:
- open-appsec (Check Point) - open-appsec (Check Point)
- Machine-learning WAF agent attached to nginx, Kong, Envoy or similar, with - Machine-learning WAF agent attached to nginx, Kong, Envoy or similar, with
a declarative policy file or the vendor's cloud console. Covers R9 only; a declarative policy file or the vendor's cloud console. Covers R9 only;
rate limiting and richer features are in paid tiers. It attaches to an rate limiting and richer features are in paid tiers. Not a sidecar in the
existing proxy, so it is not the sidecar R10 asks for. required sense.
- iocaine - iocaine
- Serves generated garbage pages to clients the fronting proxy classifies as - Serves generated garbage pages to clients the fronting proxy classifies as
scrapers. Not a limiter, WAF or ban tool; out of scope, and only of scrapers. Not a limiter, WAF or ban tool; out of scope except as a
passing interest for scraper traffic. curiosity for scraper traffic.
- Pangolin - Pangolin
- A tunnelled access platform that bundles traefik and optionally CrowdSec. - A tunnelled access platform that bundles traefik and optionally CrowdSec.
Replaces the ingress rather than adding a sidecar; out of scope. Replaces the ingress rather than adding a sidecar; out of scope.
@@ -226,17 +214,17 @@ Closest existing options, and why each still falls short:
Everyone else offers one window per rule or none. Everyone else offers one window per rule or none.
- R2 bypass netblocks: BunkerWeb, CrowdSec, traefik, fail2ban plugins. - R2 bypass netblocks: BunkerWeb, CrowdSec, traefik, fail2ban plugins.
- R3 alerts: CrowdSec (best), BunkerWeb (denied requests only), SafeLine (paid). - R3 alerts: CrowdSec (best), BunkerWeb (denied requests only), SafeLine (paid).
- R4 alerts on request counts and bytes: none. CrowdSec can approximate alerts - R4 volume and byte anomalies: none. CrowdSec can approximate request-count
on request counts with a custom scenario; no surveyed tool alerts on bytes. anomalies with a custom scenario; nothing handles bytes.
- R5 temporary then permanent: CrowdSec only. BunkerWeb's ban is either one - R5 temporary then permanent: CrowdSec only. BunkerWeb has fixed or permanent,
fixed length or permanent, and does not change with a client's history. not both by history.
- R6 reputation: CrowdSec, BunkerWeb, go-away, caddy-waf (static lists). - R6 reputation: CrowdSec, BunkerWeb, go-away, caddy-waf (static lists).
- R7 AS number lookup: CrowdSec (enrichment), BunkerWeb and caddy-waf (allow or - R7 AS number lookup: CrowdSec (enrichment), BunkerWeb and caddy-waf (allow or
deny), Anubis (hosted service). deny), Anubis (hosted service).
- R8 biased thresholds: none. - R8 biased thresholds: none.
- R9 attack detection: Coraza or ModSecurity with the Core Rule Set (open, - R9 attack detection: Coraza or ModSecurity with the Core Rule Set (open,
standard), CrowdSec AppSec, SafeLine (closed engine), BunkerWeb (wraps Coraza standard), CrowdSec AppSec, SafeLine (closed engine), BunkerWeb (wraps the
or ModSecurity). first).
- R10 env-var sidecar: `owasp/modsecurity-crs`, `coraza-crs-docker`, Anubis. - R10 env-var sidecar: `owasp/modsecurity-crs`, `coraza-crs-docker`, Anubis.
None of these covers anything beyond its one job. None of these covers anything beyond its one job.
+7 -7
View File
@@ -1,12 +1,12 @@
.PHONY: bootstrap setup test lint fmt fmt-check tidy check docker publish \ .PHONY: bootstrap setup test lint fmt fmt-check tidy check docker hooks build \
hooks build run example-app run example-app gitea-requests
# Makefile targets are thin shims; the implementations live in script/ # Makefile targets are thin shims; the implementations live in script/
# per the scripts-to-rule-them-all pattern (see the Entrypoints section # per the scripts-to-rule-them-all pattern (see the Entrypoints section
# of README.md). tidy writes go.mod and go.sum as `go mod tidy` does, # of README.md). tidy writes go.mod and go.sum as `go mod tidy` does,
# which test checks. build and run are for working on the code by hand; # which test checks. build and run are for working on the code by hand;
# example-app checks the image with an app built on it; publish builds # example-app checks the image with an app built on it; gitea-requests
# the image on the Docker host and pushes it to the registry. # reports the gitea requests the Core Rule Set refuses at the defaults.
bootstrap: bootstrap:
@script/bootstrap @script/bootstrap
@@ -35,9 +35,6 @@ check:
docker: docker:
@script/docker @script/docker
publish:
@script/publish
hooks: hooks:
@script/install-precommit @script/install-precommit
@@ -49,3 +46,6 @@ run:
example-app: example-app:
@script/example-app @script/example-app
gitea-requests:
@script/gitea-requests
+1618 -588
View File
File diff suppressed because it is too large. Load diff
+1613 -1806
View File
File diff suppressed because it is too large. Load diff
+18
View File
@@ -0,0 +1,18 @@
// Command smallwebwaf is a web application firewall for one app: it runs
// between traefik and the app, and passes requests through within its
// limits. Everything it does is in internal/smallwebwaf.
package main
import (
"os"
"sneak.berlin/go/smallwebwaf/internal/smallwebwaf"
)
// Version is the version of the binary, set when it is built with
// -ldflags "-X main.Version=...".
var Version = "dev" //nolint:gochecknoglobals // the linker sets it
func main() {
os.Exit(smallwebwaf.Main(Version))
}
-20
View File
@@ -1,20 +0,0 @@
// Command sww is a web application firewall. `sww rproxy` is the reverse
// proxy in front of one app, which asks discriminator about each request.
// `sww discriminator` decides, for many sites, and keeps what lasts. `sww
// healthcheck` is the container's health check. Everything it does is in
// internal/sww.
package main
import (
"os"
"sneak.berlin/go/smallwebwaf/internal/sww"
)
// Version is the version of the binary, set when it is built with
// -ldflags "-X main.Version=...".
var Version = "dev" //nolint:gochecknoglobals // the linker sets it
func main() {
os.Exit(sww.Main(Version))
}
+2 -2
View File
@@ -6,8 +6,8 @@
# A real app names the smallwebwaf image by digest. This one takes the # A real app names the smallwebwaf image by digest. This one takes the
# image script/example-app has just built, or else the one `make docker` # image script/example-app has just built, or else the one `make docker`
# builds. # builds.
ARG SWW_IMAGE=smallwebwaf ARG SMALLWEBWAF_IMAGE=smallwebwaf
FROM ${SWW_IMAGE} FROM ${SMALLWEBWAF_IMAGE}
# Packages the app needs, from the nixpkgs in the image. # Packages the app needs, from the nixpkgs in the image.
RUN nix-env -iA nixpkgs.busybox RUN nix-env -iA nixpkgs.busybox
-60
View File
@@ -1,60 +0,0 @@
# Admin endpoints
The endpoints under `/_sww/`, what each takes and what each answers.
`sww discriminator` answers them at its own address, on the private network.
"Admin endpoints" in [`SPEC.md`](../SPEC.md) says how their tokens work.
- `GET /_sww/healthz`: `200` and `ok`, to anyone.
- `GET /_sww/metrics`: the metrics, for `SWW_METRICS_TOKEN` (see
[`metrics.md`](metrics.md)).
- `GET /_sww/bans`: every ban held, under `bans`, each as `bans.json` lists it.
Needs `SWW_ADMIN_TOKEN`, as do the three below.
- `POST /_sww/bans`: bans a netblock. The body is a JSON object of `netblock`,
`duration` and, if you like, `reason`. `netblock` is a netblock such as
`203.0.113.0/24`, or a client's address, which bans its IPv4 netblock
(`SWW_BAN_SCOPE_V4_PREFIX`) or its IPv6 group. `duration` is a duration such
as `1h` or `7d`, or `permanent`. A bad body is answered `400`, saying what is
wrong:
- one that is not such an object, or has another field;
- one longer than 4 KiB;
- one that names an IPv4-mapped netblock, or an address with a zone.
- `DELETE /_sww/bans/<client>`: lifts every active ban covering the address
`<client>`. It answers `404` when none is active.
- `GET /_sww/clients/<ip>`: what `discriminator` knows of the client. Under
`client`, its counters and history as `clients.json` holds them, or `null`
when `clients.json` does not hold it. Under `bans`, every ban covering the
address, with its notes.
- `POST /_sww/report`: takes `rproxy`'s report, without a token. It answers
`204`, or `400` to a body that is no report (see "The report" in
[`SPEC.md`](../SPEC.md)).
No check runs on these requests. A missing or wrong token is answered `401`. An
endpoint whose token is unset answers `404`, as does any other path.
`sww rproxy` answers only the health check of these, at its own address. It asks
`discriminator` about any other request under `/_sww/`. One that passes the
checks is answered `404`, so that the app never sees that prefix (see "`rproxy`"
in [`SPEC.md`](../SPEC.md)).
## Examples
With `SWW_ADMIN_TOKEN` set, the token in `$TOKEN`, and `discriminator` reached
as `discriminator:8080` on its network:
```sh
# Every ban.
curl -H "Authorization: Bearer $TOKEN" http://discriminator:8080/_sww/bans
# Ban 203.0.113.0/24 for seven days.
curl -H "Authorization: Bearer $TOKEN" \
--json '{"netblock": "203.0.113.0/24", "duration": "7d", "reason": "probes for logins"}' \
http://discriminator:8080/_sww/bans
# Lift the bans on 203.0.113.9.
curl -H "Authorization: Bearer $TOKEN" -X DELETE \
http://discriminator:8080/_sww/bans/203.0.113.9
# What discriminator knows of 203.0.113.9.
curl -H "Authorization: Bearer $TOKEN" \
http://discriminator:8080/_sww/clients/203.0.113.9
```
-137
View File
@@ -1,137 +0,0 @@
# Alerts
The alert events, the JSON object the webhook gets, and the messages Slack and
ntfy get. "Alerting" in [`SPEC.md`](../SPEC.md) says when an alert is sent, held
back or dropped.
## Events
- `ban`: a ban `discriminator` made.
- `permanent_ban`: a permanent ban it made, or an existing ban made permanent by
a request.
- `waf_block`: the Core Rule Set scored a request at or over the threshold. The
request was refused unless the alert's `detail` gives `mode`: `detect` or
`observe`.
- `anomaly`: a count over an anomaly threshold.
- `reputation_hit`: a request from a client on a blocklist, the CrowdSec
decision list or a DNS blocklist, or with an AbuseIPDB score that is a hit.
One alert per source.
- `source_failure`: one of:
- GeoJS failing;
- a list that cannot be fetched;
- a DNS blocklist or AbuseIPDB failing or refusing a query;
- the day's AbuseIPDB checks used up.
- `file_error`: one of:
- a rule file or state file edit with an error;
- a state file that cannot be written;
- a replacement lookup database that cannot be read.
- `summary`: the hourly summary of alerts held back.
## The JSON object
This is the alert for a ban for a broken rate limit, shown indented; it is sent
on one line:
```json
{
"instance": "fsn1/discriminator",
"time": "2026-10-06T12:00:50.123461Z",
"event": "ban",
"host": "app.example",
"client": "203.0.113.9",
"netblock": "203.0.113.9/32",
"asn": "",
"as_name": "",
"country": "",
"reason": "requests per minute over the limit of 500",
"detail": {
"ban_expires": "2026-10-06T13:00:50.123Z",
"cause": "limit",
"notes": {
"asn": "",
"as_name": "",
"country": "",
"kind": "requests",
"limit": 500,
"window": "minute",
"count": 501,
"request": {
"time": "2026-10-06T12:00:50.123456789Z",
"method": "GET",
"host": "app.example",
"path": "/owner/repo/commits/branch/main?page=501",
"status": 403,
"user_agent": "scraper/1.0"
},
"requests": 501,
"refused": 0,
"earlier_bans": {
"limit": 0,
"attack": 0,
"admin": 0,
"crowdsec": 0
}
}
},
"suppressed_repeats": 0
}
```
- `instance`: `SWW_INSTANCE_NAME`. `time`: when the alert was raised. `event`:
one of the events above.
- `host`: the site of the request that raised the alert, since one
`discriminator` serves many sites. It is left out of `source_failure`,
`file_error` and `summary`.
- `client`: the address whose request raised the alert. Empty for
`source_failure`, `file_error` and `summary`.
- `netblock`: empty for `source_failure`, `file_error` and `summary`; otherwise
one of:
- the ban's netblock;
- the netblock an anomaly counted, empty in the `asn` and `total` scopes;
- for the other events, the client as rate limiting counts it: an IPv4
address as a /32, or an IPv6 group.
- `asn`, `as_name` and `country`: the client's, as known when the alert was
raised. They are empty when GeoJS had not answered yet.
- `reason`: a short sentence, such as
`requests per minute over the limit of 500` or `listed by a blocklist`.
- `detail`: what is particular to the event:
- for a ban, its `cause`, `ban_expires` and `notes` (the notes are listed
under `bans.json` in [`state-files.md`](state-files.md));
- for an anomaly, the `scope`, `window`, `kind`, `count` and `threshold`;
- for a reputation hit, the `source` and, for AbuseIPDB, the `score`;
- for a Core Rule Set match, the `rule_ids`, `score`, `method` and `path`;
- for a source failure, the `source` and `error`;
- for a file error, the `file` and `error`;
- for a summary, the `hour` it covers, the `count` of alerts held back, and
that count by event in `events`;
- `mode`, when the request was not refused: `detect` or `observe`.
- `suppressed_repeats`: how many repeats the cooldown held back before this
alert.
## Slack and ntfy
Slack and ntfy get a message with a title and a text. The title is the instance
and the event, such as `fsn1/discriminator: ban`. The text is the `reason`, then
one line for each of these that the alert has:
- the host, the client, the netblock and the country;
- the file, the source, the error and the mode from `detail`;
- the suppressed repeats, if any.
Slack gets the title in bold and the text below it, with `&`, `<` and `>`
escaped. ntfy gets the text as the message, with these headers:
- `Title`: the title;
- `Authorization`: the token, as `Bearer <token>`, while `SWW_ALERT_NTFY_TOKEN`
is set;
- `Priority` and `Tags`: by event, as listed below.
The priority and tag by event:
- `ban`: priority `default`, tag `no_entry`.
- `permanent_ban`: priority `high`, tag `no_entry`.
- `waf_block`: priority `default`, tag `shield`.
- `anomaly`: priority `high`, tag `chart_with_upwards_trend`.
- `reputation_hit`: priority `low`, tag `label`.
- `source_failure` and `file_error`: priority `high`, tag `warning`.
- `summary`: priority `default`, tag `bar_chart`.
-35
View File
@@ -1,35 +0,0 @@
# What the image holds
The contents of the `smallwebwaf` image, and how each part is pinned. The image
runs `rproxy` by default, or `discriminator` with `SWW_COMMAND=discriminator`.
"Deployment" in [`SPEC.md`](../SPEC.md) says why each part is there and why it
is pinned that way.
## Contents
- Ubuntu 26.04 LTS, pinned by digest.
- `ca-certificates`, `nix-bin` and `runit` from Ubuntu's archive.
- Nix, with nixpkgs `nixos-26.05.11045.774debe7a0d1` set up for root as
`nixpkgs`. No Nix daemon; `build-users-group =` in `/etc/nix/nix.conf`. Root's
Nix profile, `/nix/var/nix/profiles/default/bin`, last on the `PATH`.
Unpacked, nixpkgs takes about 500 MiB.
- `runsvinit` as the entrypoint, built from `github.com/peterbourgon/runsvinit`
at a fixed commit hash.
- The `sww` binary, and the user `sww` (uid and gid 65532).
- The service directory `/etc/service/sww`, with the `run` script
`share/sww.run`.
- `/var/lib/sww` for `discriminator`'s state files, and `/etc/sww/rules.d` with
the default rule file `share/rules.d/00-default.rules`.
- `EXPOSE 8080`, and the `HEALTHCHECK` that runs `sww healthcheck`.
## Pins
- Ubuntu's packages are not pinned: they come from the live archive, whose
packages change with every update.
- nixpkgs: the release file `nixexprs.tar.xz` of
`nixos-26.05.11045.774debe7a0d1` on `releases.nixos.org`, named with its
SHA-256 hash.
- `runsvinit`: the archived repository, unchanged since 2015, at its last commit
(`b4b2c78`, eight commits after `v2.0.0`), by commit hash, with a `go.mod` the
build writes.
- The Go image that builds `sww`: by digest.
-87
View File
@@ -1,87 +0,0 @@
# The metrics
What `GET /_sww/metrics` answers with, at `discriminator`'s own address.
"Metrics endpoint" in [`SPEC.md`](../SPEC.md) describes the endpoint. Prometheus
keeps the `instance` label as `exported_instance` unless the scrape sets
`honor_labels: true`. `rproxy` has no metrics.
Every `sww_*request_bytes_total` and `sww_*response_bytes_total` series counts
body bytes, never headers, whatever `SWW_BYTES_COUNT` says.
## Traffic
- `sww_requests_total`, `sww_request_bytes_total` and
`sww_response_bytes_total`, by `status_class` such as `2xx` and by `action`;
- `sww_request_duration_seconds` and `sww_upstream_duration_seconds`, as
histograms;
- `sww_requests_in_flight`: the questions and requests to its own endpoints that
`discriminator` is handling.
## Limits and bans
- `sww_rate_limit_hits_total`, by `window` and by `kind` (`requests`, `bytes` or
`refusals`);
- `sww_offences_total`, by `kind`;
- `sww_bans_made_total`, by `cause`;
- `sww_active_bans` and `sww_permanent_bans`.
## Attack detection
- `sww_rule_matches_total`, by `rule_id` and `action`, and `sww_rules_loaded`;
- `sww_waf_matches_total`, by `mode` and `rule_id`, for the rules that fired.
## Countries and AS numbers
For the `SWW_METRICS_TOP_N` busiest of each, the rest as `other`:
- `sww_country_requests_total`, `sww_country_request_bytes_total`,
`sww_country_response_bytes_total` and `sww_country_list_refusals_total`, by
`country`;
- `sww_asn_requests_total`, `sww_asn_request_bytes_total` and
`sww_asn_response_bytes_total`, by `asn`.
## Lookups
- `sww_geojs_requests_total` and `sww_geojs_failures_total`;
- `sww_geojs_unanswered_total`: the requests that needed an answer and went on
without it;
- with the file source, `sww_lookup_database_last_read_timestamp_seconds` and
`sww_lookup_database_read_failures_total`.
## Reputation sources
By `source`: each list's URL, each zone, and `abuseipdb`:
- `sww_reputation_hits_total`, `sww_reputation_queries_total` and
`sww_reputation_failures_total`;
- `sww_reputation_last_fetch_timestamp_seconds`, for a list;
- `sww_reputation_daily_budget_remaining`, for AbuseIPDB.
## State files
By `file`:
- `sww_state_file_writes_total`, `sww_state_file_write_failures_total`,
`sww_state_file_last_write_timestamp_seconds` and `sww_state_file_size_bytes`;
- `sww_state_file_edits_taken_in_total` and
`sww_state_file_edits_set_aside_total`;
- `sww_tracked_clients`: the clients in the table.
## Remote log, alerts and the process
- while a syslog server is set, `sww_remote_log_lines_sent_total`,
`sww_remote_log_lines_dropped_total` and `sww_remote_log_buffer_depth`;
- by `destination`, `sww_alerts_sent_total`, `sww_alerts_failed_total`,
`sww_alerts_suppressed_total` and `sww_alerts_dropped_total`;
- Go's own `go_` metrics and the process's `process_` metrics.
## When a request is counted
`discriminator` counts a denied request at its decision, and a request to its
own endpoints when it is answered. It counts an allowed request when its report
comes, with the status, bytes and times the report gives. These are not counted:
- a report itself;
- an allowed request whose report never comes;
- a question refused with `400`;
- a question whose body stopped arriving.
-249
View File
@@ -1,249 +0,0 @@
# The request log's fields
The fields of the JSON objects `rproxy` and `discriminator` write about each
request. "Request log" and "The log" in [`SPEC.md`](../SPEC.md) say when a line
is written and how the log is sent to a syslog server. A field that does not
apply to a request is left out.
## `discriminator`'s lines
`sww discriminator` writes two lines for each question it answers, joined by
`request_id`. The field `discriminator_line` says which of the two a line is:
- `decision`: the line it writes once it has answered the question;
- `report`: the line it writes when `rproxy`'s report comes, with everything
known. The repetition is intended.
A request to its own endpoints writes one line, without `discriminator_line`. A
report writes no line but the `report` line of the request it names.
These questions write no line:
- a question refused with `400` (see "The question" under "`discriminator`" in
[`SPEC.md`](../SPEC.md));
- a question whose body stopped arriving, which gets no answer.
A `report` line:
```
{"type":"request","discriminator_line":"report","time":"2026-10-03T12:00:00.123Z","instance":"fsn1/discriminator","client_ip":"203.0.113.9","method":"GET","scheme":"https","host":"app.example","path":"/","query":"","protocol":"HTTP/1.1","status":200,"request_bytes":0,"response_bytes":5120,"referer":"","user_agent":"curl/8.9.1","request_id":"7Q2NHZ4KJ3VXW5YB6R3MEFTD2A","peer_ip":"172.18.0.2","forwarded_for":"203.0.113.9","client_group":"203.0.113.9/32","asn":"AS64496","as_name":"Example Net","country":"DE","request_headers":{"accept":"*/*"},"action":"forward","counts":{"minute":1,"hour":12,"day":40,"minute_bytes":5120,"hour_bytes":61440,"day_bytes":204800},"waf_score":0,"duration_total":3.217,"duration_checks":0.041,"duration_waf":0.029,"duration_upstream_total":3.104}
```
### Every line
Every one of these lines has:
- `type`: `request` (the process's own messages have `process`);
- the standard web log fields;
- `request_id`, `peer_ip` and `client_group`;
- `asn`, `as_name` and `country`;
- `action` and `duration_total`.
### Standard web log fields
- `time`: when `discriminator` had read the question's body, RFC 3339 with
milliseconds, in UTC. The `report` line gives the same time as the `decision`
line.
- `instance`: `SWW_INSTANCE_NAME`.
- `client_ip`: the visitor's address, as `rproxy` worked it out.
- `method`, `path` and `query`: the visitor's request.
- `scheme`: how the visitor reached `rproxy` or the trusted proxy in front of
it.
- `host`: the site the visitor asked for.
- `protocol`: the question's own, `HTTP/1.1`.
- `status`:
- on the `decision` line, what `discriminator` answered: `200` for `allow`,
the status of `deny`, or `0` for `close`, as the visitor is then sent
nothing;
- on the `report` line, what the visitor got, `0` if nothing.
- `request_bytes`:
- on the `decision` line, how much of the question's body the Core Rule Set
read;
- on the `report` line, the bytes of the visitor's body that `rproxy` read,
with what a WebSocket carried from the visitor.
- `response_bytes`:
- on the `decision` line, the body of `discriminator`'s answer;
- on the `report` line, the bytes of the answer's body, with what a
WebSocket carried from the app.
- `referer` and `user_agent`.
### Request detail
- `request_id`: the id `rproxy` made for the request when it arrived.
- `peer_ip`: the address of `rproxy`'s TCP peer, normally traefik.
- `forwarded_for`: the `X-Forwarded-For` header the visitor's request came with.
- `client_group`: the client as rate limiting counts it, an IPv4 address as a
/32 or an IPv6 group.
- `asn`, `as_name` and `country`: the client's, as looked up. Each is empty
when:
- lookups are off;
- the client is not looked up;
- the source cannot place the client;
- GeoJS had not answered by the time `discriminator` answered.
- `content_type`: the visitor's `Content-Type`.
- `content_length`: the body length the visitor announced.
- `request_headers`: the headers listed in `SWW_LOG_REQUEST_HEADERS`, by name in
lower case.
- `has_authorization` and `has_cookie`: true when the request had those headers.
Their values are never logged.
### Response detail
- `response_content_type`: the type of `discriminator`'s own answer.
- `aborted`: true when `rproxy` went away before the answer.
### Decision
- `action`: what was done:
- `forward`: answered `allow`, so that `rproxy` passes it to the app;
- `client_denied`: refused for `SWW_DENY_NETS`, for a reputation source with
the action `deny`, or for a tag in `SWW_TAG_DENY`;
- `temporarily_banned`: refused under a ban that runs out, or for a `ban`
rule, a trap path or a CrowdSec decision that made such a ban;
- `permanently_banned`: refused under a ban that never runs out, including a
ban this request made or made permanent;
- `country_denied`, `client_is_rate_limited`, `blocked_by_block_rule` and
`waf_blocked`: refused by that check;
- `request_header_too_large`: over a header limit;
- `admin`: answered at one of `discriminator`'s own endpoints, or `404` for
a path under `/_sww/`.
- `would_action`: in `observe` mode, what `enforce` mode would have done with a
request it would have refused. `action` then names what was done, normally
`forward`.
- `heuristic`: the heuristic that refused the request, in `observe` mode too. It
is left out when none did.
- `heuristic_figures`: an object of the figures that heuristic acted on. Each
heuristic and its figures:
- `deny_nets`: `netblock`, the entry of `SWW_DENY_NETS` the client is in;
- `active_ban`: `netblock`, the ban's netblock, and `ban_expires`;
- `countries`: `country`, and `setting`, the country list that refused it;
- `tag_deny`: `tag`, the tag of `SWW_TAG_DENY` the request carries;
- `blocklists`: `lists`, the blocklist URLs that list the client;
- `crowdsec`: `scenario`, the decision's scenario, and `expires`, when the
decision ends;
- `dnsbl`: `zones`, the DNS blocklist zones that list the client, their keys
masked;
- `abuseipdb`: `score`, and `min_score`, `SWW_ABUSEIPDB_MIN_SCORE`;
- `rate_limits`: `window`, `count` and `limit`;
- `trap_paths`: `path`, the trap path asked for;
- `rule_files`: `rule_id` and `rule_action`, of the rule that refused it;
- `header_limits`: `fields`, `fields_limit`, `cookies` and `cookies_limit`;
- `core_rule_set`: `score`, and `threshold`, `SWW_WAF_ANOMALY_THRESHOLD`;
- `refusal_limit`: `window`, `count` and `limit`, of the error burst;
- `byte_limits`: `window`, `count` and `limit`, the count in bytes.
- `after_answer_heuristic`: the heuristic that banned the client after
`discriminator` answered the request, in `observe` mode too: `refusal_limit`
or `byte_limits`.
- `after_answer_heuristic_figures`: an object of the figures that heuristic
acted on, as listed above.
`byte_limits` bans when the report comes, so only the `report` line names
it.
- `limit_percent` and `limit_percent_setting`: the client's percentage of the
rate limits and the setting that lowered it, when one did. `bytes_percent` and
`bytes_percent_setting` do the same for the byte limits.
- `counts`: the client's totals as rate limiting counts them, this request
included. It is left out when rate limiting did not count the request. It
holds:
- `minute`, `hour` and `day`: requests;
- `minute_bytes`, `hour_bytes` and `day_bytes`: the body bytes
`SWW_BYTES_COUNT` names, in that window.
A count can have a fraction (see "Counting method" in
[`SPEC.md`](../SPEC.md)). The bytes counted for an allowed request and its
response are added when its report comes. So on the `decision` line, the
three byte totals leave them out.
- `limit_hit`: the limit broken:
- `minute`, `hour` or `day` for a rate limit;
- `minute_bytes`, `hour_bytes` or `day_bytes` for a byte limit;
- `error_burst`.
When the bytes counted for a request and its response break a limit, the
request has been passed on whole, so its `action` stays `forward`. Only its
`report` line gives that limit.
- `rule_ids`: the rule file rules that matched, in order, up to the one that
refused.
- `waf_score` and `waf_rule_ids`: the Core Rule Set's score and the rules that
matched, for a request it inspected.
- `reputation`: the sources the client is on, in this order:
- blocklist URLs;
- the CrowdSec decision list's URL;
- DNS blocklist zones;
- `abuseipdb`.
- `tags`: the request's tags, sorted, left out when it has none. Each tag and
where it comes from is under "Request tags" in [`SPEC.md`](../SPEC.md).
- `routewatch_tags_missing`: why the request got no tags from routewatch,
present only while `SWW_ROUTEWATCH_URL` is set:
- `no_answer_yet`: routewatch has not answered about this client yet;
- `request_failed`: a query to routewatch failed within the last minute, and
the process log says why;
- `no_route`: routewatch knows no live route for the address.
- `offence`: `limit`, for a request that broke a limit.
- `ban_expires`: when the client's ban ends, for a request that made one or was
refused under one: a time, or `permanent`.
### Timings
All in milliseconds:
- `duration_total`:
- on the `decision` line, from `discriminator` having read the question's
body to the line;
- on the `report` line, from `rproxy` having read the request's headers to
the end of the answer.
- `duration_checks`: to the end of the checks;
- `duration_waf`: the part of that the Core Rule Set took;
- `duration_upstream_total`: on the `report` line of an allowed request, from
the hand-over to the app to the end of the answer.
### Requests to its own endpoints
The line of a request to `discriminator`'s own endpoints has these fields, with
these meanings where they differ:
- `client_ip` and `peer_ip`: the request's TCP peer.
- `request_id`: a new random one of 26 letters and digits.
- `scheme`: `http`.
- `time`: when the request's headers had been read.
- `request_bytes`: the bytes read of a ban to add, and otherwise `0`.
- `action`: `admin`.
- `duration_total`: from the request's headers being read to the line.
## `rproxy`'s line
`sww rproxy` writes one short line for each request. `request_id` joins it to
`discriminator`'s two. It has these fields and no others:
- `type`: `request`.
- `time`: when the request arrived, RFC 3339 with milliseconds, in UTC.
- `request_id`: the id `rproxy` made for the request when it arrived.
- `client_ip`: the visitor's address.
- `host` and `method`.
- `path` and `query`: as the visitor sent them.
- `status`: what the visitor got, `0` if nothing.
- `request_bytes`: the bytes of the visitor's body that `rproxy` read, with what
a WebSocket carried from the visitor.
- `response_bytes`: the bytes of the answer's body, with what a WebSocket
carried from the app.
- `duration_request`: milliseconds from the request's headers being read until
the app had been sent the whole request, or the answer started if that was
sooner. It includes the wait for `discriminator`.
- `duration_response`: milliseconds from then until the end of the answer.
- `disposition`: what was done with the request: `allow`, `deny` or `close`. It
is `discriminator`'s answer, or the value of `SWRP_DEFAULT_DISPOSITION`. It is
left out when:
- `discriminator` was not asked, as for the health check;
- the visitor went away while `discriminator` was being asked;
- `discriminator`'s answer had no valid `X-Sww-Disposition`;
- `rproxy` could not pass on `discriminator`'s answer, and answered `502`.
- `default_disposition`: `true` when `SWRP_DEFAULT_DISPOSITION` gave
`disposition`, and otherwise left out.
For example:
```
{"type":"request","time":"2026-10-03T12:00:00.123Z","request_id":"7Q2NHZ4KJ3VXW5YB6R3MEFTD2A","client_ip":"203.0.113.9","host":"app.example","method":"GET","path":"/","query":"","status":200,"request_bytes":0,"response_bytes":5120,"duration_request":1.204,"duration_response":3.104,"disposition":"allow"}
```
-73
View File
@@ -1,73 +0,0 @@
# Rule files
The format of a rule file, and the default file the image ships. "Rule files" in
[`SPEC.md`](../SPEC.md) says how the files are read, watched and mounted, and
what each action leads to.
## The format
A rule is a line of four fields separated by spaces or tabs: an id, a target, an
action and a regex. The regex runs to the end of the line. Blank lines and lines
starting with `#` are ignored.
```
# id target action regex
env-file path ban (?i)^/\.env(\.[a-z]+)?$
scanner-agent user_agent ban (?i)\b(sqlmap|nikto|nuclei|wpscan)\b
```
- The id is letters, digits, `-` and `_`, unique across all files. The log line,
the metrics, the alerts and a ban's notes name the rule by it.
- The target is what the regex is matched against:
- `path`: the path without the query;
- `uri`: the path and the query together;
- `query`: the query as sent;
- `method`, `host`, `user_agent` and `referer`;
- `header:<Name>`: any one request header but `Host` and
`Transfer-Encoding`.
- The action is `log`, `block` or `ban`.
- The regex is in Go's syntax, RE2. It matches anywhere in the target unless
anchored with `^` and `$`. `(?i)` at its front makes it ignore case.
## The default file
The image ships one file, `share/rules.d/00-default.rules`, installed as
`/etc/sww/rules.d/00-default.rules`:
```
# 00-default.rules: probes no real visitor sends, anchored at the site root
# id target action regex
env-file path ban (?i)^/\.env(\.[a-z]+)?$
vcs-dir path ban (?i)^/\.(git|svn|hg|bzr)(/|$)
secrets-dir path ban (?i)^/\.(aws|ssh|docker|kube)/
secret-file path ban (?i)^/\.(htpasswd|htaccess|npmrc|netrc|pgpass|git-credentials|bash_history|DS_Store)$
editor-dir path ban (?i)^/\.(vscode|idea)/
backup-file path ban (?i)^/[^/]+\.(php(\.[a-z0-9]+|~)|sql(\.[a-z0-9]+)?)$
log-file path ban (?i)^/(debug|error|access)\.log$
compose-file path ban (?i)^/(docker-)?compose\.ya?ml$
php-shell path ban (?i)^/(shell|c99|r57|wso|alfa)\.php$
scanner-agent user_agent ban (?i)\b(sqlmap|nikto|nuclei|masscan|zgrab|wpscan)\b
path-traversal uri block (\.\./){2,}
empty-agent user_agent log ^$
```
## A file of your own
`discriminator` reads the rule files in its own container. Rules of your own go
in a file named to sort after the default, such as `50-site.rules`:
```
# 50-site.rules: WordPress probes, which this site never serves
wp-probe path ban (?i)^/(wp-login\.php|xmlrpc\.php|wp-admin/)
```
A `Dockerfile` built on the `smallwebwaf` image, for `discriminator` to run
from, adds it:
```dockerfile
COPY 50-site.rules /etc/sww/rules.d/50-site.rules
```
Or mount it there. A `path` rule applies on every site behind that
`discriminator`.
-471
View File
@@ -1,471 +0,0 @@
# Settings
Every setting, its default and the values it takes, in the groups of "Settings"
in [`SPEC.md`](../SPEC.md). That section gives the conventions, the settings
that take `off`, the `_FILE` form, and what each group does and why.
The settings that start with `SWW_` are `discriminator`'s. Those that start with
`SWRP_` are `rproxy`'s, and are under "`rproxy`" below. `SWW_COMMAND` chooses
between the two (see "The image's command" below).
## Forms of values
- A duration is Go's syntax, with `d` for days: `90s`, `15m`, `24h`, `7d`. Zero
and negative durations are refused.
- A size is a number of bytes with an optional `K`, `M` or `G`, which are powers
of 1024, so `1K` is 1024 bytes. Examples: `512K`, `100M`, `5G`.
- A count is a whole number of requests, such as `1000`.
- A list is comma separated, with spaces around items ignored. An empty item is
refused.
- A netblock is an address and a prefix length, such as `10.0.0.0/8`. A bare
address stands for itself alone.
- A country is a two-letter code of ISO 3166-1, in either case: `de` and `DE`
are the same. `xk` stands for Kosovo. A code that is not a country is refused,
such as `nk` (North Korea is `kp`) or the withdrawn `su`.
- An AS number is `AS` and the number, in either case, such as `AS64496`.
- A percentage is a whole number from 0 to 100.
- A path prefix starts with `/`, such as `/assets/`.
## Core
- `SWW_LISTEN_ADDR` (default `:8080`): where `discriminator` listens: `:` and a
port, such as `:9000`. Leave the host out (see "Ports" in
[`SPEC.md`](../SPEC.md)).
- `SWW_INSTANCE_NAME` (default: the container's host name): the `instance` name
in each line `discriminator` logs, and in each alert and metric, such as
`fsn1/discriminator`. Valid UTF-8. No control character while
`SWW_ALERT_NTFY_URL` is set. 1 to 48 printable ASCII characters without a
space while `SWW_LOG_REMOTE_URL` is set and `SWW_LOG_REMOTE_APP_NAME` is not.
- `SWW_MODE` (default `enforce`): `enforce` or `observe`.
- `SWW_IPV6_GROUP_PREFIX` (default `64`): the prefix length of an IPv6 client's
group, from 32 to 128.
- `SWW_MAX_TRACKED_CLIENTS` (default `20000`): the most clients kept, a whole
number above zero.
- `SWW_MAX_BANS` (default `5000`): how many of its own bans `discriminator`
keeps, a whole number above zero.
## Tokens
- `SWW_ADMIN_TOKEN` (default unset): the token for the ban endpoints and
`/_sww/clients/<ip>`. At least 32 characters.
- `SWW_METRICS_TOKEN` (default unset): the token for `/_sww/metrics`. At least
32 characters.
## State files
- `SWW_STATE_DIR` (default `/var/lib/sww`): the directory of the state files, an
absolute path that exists and can be written.
- `SWW_STATE_WRITE_DELAY` (default `10s`): how long `bans.json` waits to be
written after a ban is made, lifted or made permanent. A duration.
- `SWW_STATE_COUNTER_INTERVAL` (default `15m`): how often every state file is
written. A duration.
## Logging
- `SWW_LOG_LEVEL` (default `info`): the least severe of `discriminator`'s own
messages that are written: `debug`, `info`, `warn` or `error`.
- `SWW_LOG_REQUEST_HEADERS` (default
`accept,accept-language,accept-encoding,content-type,origin,range`): the
request headers recorded in the log line, in either case. `Host` and
`Transfer-Encoding` are refused; the host is the field `host`.
- `SWW_LOG_REMOTE_URL` (default unset): a syslog server that also gets every
line written to stdout: `syslog+udp://`, `syslog+tcp://` or `syslog+tls://`,
each with a host and a port and nothing more.
- `SWW_LOG_REMOTE_TLS_CA_FILE` (default unset): a file of PEM certificates that
a `syslog+tls` server's certificate must chain to, instead of the host's own.
A file that cannot be read, or holds no certificate, is refused.
- `SWW_LOG_REMOTE_BUFFER` (default `10000`): the most lines held while they wait
to be sent, a whole number above zero.
- `SWW_LOG_REMOTE_FACILITY` (default `local0`): the syslog facility: `kern`,
`user`, `mail`, `daemon`, `auth`, `syslog`, `lpr`, `news`, `uucp`, `cron`,
`authpriv`, `ftp`, or `local0` to `local7`.
- `SWW_LOG_REMOTE_APP_NAME` (default: `SWW_INSTANCE_NAME`): the app name in each
syslog record, 1 to 48 printable ASCII characters without a space.
## Metrics
- `SWW_METRICS_TOP_N` (default `50`): how many AS numbers and how many countries
get series of their own. A whole number above zero.
## Static lists
- `SWW_ALLOW_NETS` (default empty): netblocks you trust, such as your monitoring
(see step 4 in [`SPEC.md`](../SPEC.md)).
- `SWW_RATE_LIMIT_EXEMPT_NETS` (default empty): netblocks whose clients are
exempt from rate limiting and the byte limits.
- `SWW_DENY_NETS` (default empty): netblocks whose clients are refused (see step
4 in [`SPEC.md`](../SPEC.md)).
## Request rate limits, per client
The request past one of these limits is refused, and the client is banned.
- `SWW_RATE_LIMIT_PER_MINUTE` (default `120`, 2 a second): the most requests a
client may make in a minute. A count or `off`. The default leaves room for a
person opening two pages at once with an empty cache, up to 60 files each.
- `SWW_RATE_LIMIT_PER_HOUR` (default `1500`): the most requests a client may
make in an hour. A count or `off`. It is the main limit against scrapers. A
person reading a site for an hour, a page every 20 seconds, makes about 900. A
scraper making one request every 2 seconds makes 1,800 an hour, more than the
limit.
- `SWW_RATE_LIMIT_PER_DAY` (default `6000`): the most requests a client may make
in a day. A count or `off`. The default is four hours at the hour limit. A
scraper making one request every 10 seconds makes 8,640 a day, more than the
limit.
- A CI runner asks its code forge for work all day and can pass the limits. Put
the runners' addresses in `SWW_RATE_LIMIT_EXEMPT_NETS`. Do the same for a
network where many people share one address, such as an office.
- Counting cannot catch a client that stays under all three limits (see "Request
rate limits, per client" in [`SPEC.md`](../SPEC.md)).
- `SWW_RATE_LIMIT_EXEMPT_PATHS` (default empty): path prefixes exempt from rate
limiting and the byte limits, such as `/assets/`.
## Byte limits, per client
These count body bytes, never headers. What the visitor sent over a WebSocket
counts as request bytes, and what the app sent as response bytes. The bytes
counted for a request and its response are added to the client's total once the
response has ended. The request that takes a client's total past a limit is not
cut off; the client is banned.
- `SWW_BYTES_LIMIT_PER_MINUTE` (default `off`), `SWW_BYTES_LIMIT_PER_HOUR`
(default `50G`) and `SWW_BYTES_LIMIT_PER_DAY` (default `100G`): the most bytes
counted for a client in each window, a size or `off`. `SWW_BYTES_COUNT` says
which bytes count: response bodies, request bodies or both. The request that
passes the limit is not cut off, and the client is banned when its response
ends.
- `SWW_BYTES_COUNT` (default `both`): what the byte limits and the byte anomaly
thresholds count: `response`, the app's response bodies; `request`, the
visitors' request bodies; or `both`. What the visitor sent over a WebSocket
counts as request bytes, and what the app sent as response bytes.
## Lookup of AS number and country
- `SWW_LOOKUP_SOURCE` (default `geojs`): `geojs`, `file` or `off`. `off` stops
the start while a setting that needs a lookup is set:
- `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES`;
- `SWW_ADD_LOOKUP_HEADERS`;
- `SWW_TAG_DENY` or `SWW_TAG_LIMIT_PERCENT` naming a `country=` tag, or an
`asn=` tag while `SWW_ROUTEWATCH_URL` is unset;
- the two byte percentage lists and `SWW_ASN_LIMIT_PERCENT_URL`;
- `SWW_UNKNOWN_LIMIT_PERCENT` below `100`;
- an anomaly threshold per AS number.
- `SWW_LOOKUP_DB_PATH` (default empty): the IPinfo Lite database file, in its
`.mmdb` form, for `SWW_LOOKUP_SOURCE=file`.
- `SWW_LOOKUP_TIMEOUT` (default `800ms`): how long a request waits for its
client's first answer from GeoJS, and how long a request to GeoJS may take. A
duration; never `off`.
- `SWW_ADD_LOOKUP_HEADERS` (default `false`): `true` has `rproxy` pass the app
the client's AS number in `X-Client-ASN` and its country in
`X-Client-Country`.
## Country list
- `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES` (default empty): when set, the only
countries whose clients get through, such as `us,de`. A country whose
`country=` tag is in `SWW_TAG_DENY` stops the start.
## Request tags
Every request gets tags from what `discriminator` knows of its client. See
"Request tags" in [`SPEC.md`](../SPEC.md).
- `SWW_TAG_LISTS` (default empty): address lists that each add a tag, as
`name=URL` pairs, such as `torexit=https://example.com/tor.txt`. A name is the
tag, and may hold `=`, such as `vpn=mullvad`. Each list is an `http` or
`https` URL fetched like a blocklist. A name or URL listed twice is refused.
So is a URL that is also in `SWW_BLOCKLIST_URLS`, `SWW_ASN_LIMIT_PERCENT_URL`,
or the CrowdSec decision list.
- `SWW_TAG_DENY` (default empty): tags whose requests are refused, such as
`torexit,country=CN`. A tag listed twice, an `asn=` tag without a number, or a
`country=` tag without a country, is refused.
- `SWW_TAG_LIMIT_PERCENT` (default empty): tags that lower a client's limits, as
tag and percentage pairs, such as `vpn:50,asn=14061:25`. A percentage is from
`1` to `99`, of every rate limit and byte limit. The lowest percentage among a
client's tags applies. A tag listed twice is refused. So is
`exploitsignature`: a request gets that tag after the rate limits have counted
it.
- `SWW_ROUTEWATCH_URL` (default unset): the `http` or `https` URL of a
routewatch instance. [routewatch](https://git.eeqj.de/sneak/routewatch) is a
service that gives an address's announced netblock and origin AS.
`discriminator` asks it about each client, in the background, and adds the
tags `asn=<number>` and `prefix=<netblock>` from its answer. While it is
unset, nothing asks routewatch and no request gets a `prefix=` tag.
`SWW_TAG_DENY` and `SWW_TAG_LIMIT_PERCENT` accept tags in either case. A tag
that no request can get stops the start. A request can get only these:
- a name in `SWW_TAG_LISTS`;
- an `asn=` or `country=` tag;
- a `prefix=` tag with a netblock, while `SWW_ROUTEWATCH_URL` is set. It matches
only that exact announced netblock, such as `prefix=192.0.2.0/24`;
- a `dnsbl=` tag of a zone in `SWW_DNSBL_ZONES`, in lower case, with a key
masked as the `reputation` field shows it;
- `abuseipdb`, while `SWW_ABUSEIPDB_KEY` is set;
- `exploitsignature`, in `SWW_TAG_DENY` only, while `SWW_RULES_ENABLED` is
`true`, or while neither `SWW_WAF_MODE` nor `SWW_WAF_ANOMALY_THRESHOLD` is
`off`.
`crowdsec` stops the start in both settings, because a CrowdSec decision refuses
the request first.
## Biased thresholds
- `SWW_ASN_BYTES_PERCENT` and `SWW_COUNTRY_BYTES_PERCENT` (default empty): a
percentage of the byte limits alone, for the AS numbers or countries listed,
such as `AS14061:50` or `cn:25`. It takes the place of the percentage
`SWW_TAG_LIMIT_PERCENT` gives their `asn=` or `country=` tag. An AS number or
country listed twice is refused.
- `SWW_UNKNOWN_LIMIT_PERCENT` (default `100`): the percentage for a client the
lookup cannot place.
- `SWW_ASN_LIMIT_PERCENT_URL` (default unset): the `http` or `https` URL of a
text file with one AS number and percentage on each line, such as
`AS64496:50`. Each entry counts like an `asn=` tag in `SWW_TAG_LIMIT_PERCENT`.
A URL that is also in `SWW_BLOCKLIST_URLS` is refused.
## Attack detection
- `SWW_RULES_DIR` (default `/etc/sww/rules.d`): the directory of the rule files.
- `SWW_RULES_ENABLED` (default `true`): `false` reads no rule file.
- `SWW_TRAP_PATHS` (default empty): paths only scanners ask for, such as
`/wp-login.php,/xmlrpc.php`. Each starts with `/` and holds no `?`.
- `SWW_WAF_MODE` (default `block`): `off`, `detect` or `block`.
- `SWW_WAF_PARANOIA_LEVEL` (default `1`): the Core Rule Set's paranoia level,
from 1 to 4.
- `SWW_WAF_ANOMALY_THRESHOLD` (default `5`): the score at which a request is a
match. A whole number above zero, or `off`.
- `SWW_WAF_DISABLED_RULES` (default
`920340,920420,920440,920640,930130,930140`): the ids of Core Rule Set rules
to switch off. Each a whole number above zero. An id from 900000 to 900999 is
refused: those are the rules that set the Core Rule Set up, and
`smallwebwaf`'s own.
- `SWW_WAF_EXEMPT_PATHS` (default empty): path prefixes the Core Rule Set does
not inspect.
- `SWW_WAF_BODY_LIMIT` (default `off`): `off`, or how much of a request body the
Core Rule Set reads, a size of at most `64K`. A question carries no more of a
body than 64 KiB, and the Core Rule Set reads at most 64 KiB less one byte of
it, whatever the value (see "The answer" in [`SPEC.md`](../SPEC.md)).
- `SWW_CORE_RULE_SET_EXCLUSIONS_FILE` (default unset): a file of Core Rule Set
exclusions, written as Coraza directives. It is loaded before the Core Rule
Set's rules, so it holds only `SecAction` and `SecRule` lines that exclude
with `ctl:ruleRemoveTargetById` or `ctl:ruleRemoveById`. A file that cannot be
read or does not parse stops the start, whatever `SWW_WAF_MODE` is. So does a
file that names a number from 900000 to 900999 outside a comment, alone or in
a range. So does a directive that removes or changes rules as the file loads,
such as `SecRuleRemoveById`, since none of the Core Rule Set's rules is loaded
yet. It has no `_FILE` form.
- `SWW_ERROR_BURST_THRESHOLD` (default `30`): the most refusals a client may get
in a minute from a rule file, a trap path or the Core Rule Set, a count or
`off`. The next one bans the client (see "Attack detection" in `SPEC.md`).
## Ban lengths, response and scope
- `SWW_BAN_RESPONSE` (default `403`): `403`, `429` or `close`.
- `SWW_LIMIT_BAN_DURATION` (default `1h`): the ban for a first broken limit. A
duration.
- `SWW_LIMIT_BAN_REPEAT_WINDOW` (default `24h`): the time after a ban ends
within which breaking a limit again lengthens the next ban. A duration.
- `SWW_MAX_BAN_DURATION` (default `7d`): the longest ban for a broken limit; one
that would be longer is permanent. A duration.
- `SWW_ATTACK_BAN_DURATION` (default `7d`): the ban for a first clear sign of
attack. A duration.
- `SWW_BAN_SCOPE_V4_PREFIX` (default `32`): how much a ban on an IPv4 client
covers: the prefix length of its netblock, from 0 to 32.
## Reputation
- `SWW_BLOCKLIST_URLS` (default empty): blocklists to fetch, such as
`https://www.spamhaus.org/drop/drop.txt`. Each an `http` or `https` URL
without a user or a fragment. A URL listed twice is refused.
- `SWW_BLOCKLIST_REFRESH` (default `24h`): how long a list waits after its last
try before it is fetched again. A duration of `1h` or more.
- `SWW_BLOCKLIST_ACTION` (default `deny`): `deny`, `limit:<percent>` or `log`.
- `SWW_DNSBL_ZONES` (default empty): the DNS blocklists to ask, such as
`dnsbl.dronebl.org`. Each a DNS name of at most 189 characters. A Spamhaus
zone carries its key, as in `<key>.xbl.dq.spamhaus.net`. A zone listed twice
is refused, whatever its case or key.
- `SWW_DNSBL_RESOLVER` (default unset): the resolver to ask the zones through,
such as `192.0.2.53` or `[2001:db8::53]:5353`. An IP address with an optional
port, 53 when none is given. Unset, the host's resolver is used.
- `SWW_ABUSEIPDB_KEY` (default unset): the key of your AbuseIPDB account. A
control character in it is refused.
- `SWW_ABUSEIPDB_MIN_SCORE` (default `75`): the least abuse confidence score,
from 0 to 100, that is a hit.
- `SWW_ABUSEIPDB_DAILY_BUDGET` (default `900`): the most checks made in a day, a
whole number above zero. AbuseIPDB's free accounts may make 1,000.
- `SWW_CROWDSEC_LAPI_URL` (default unset): the local API of a CrowdSec engine
you run, such as `http://172.17.0.1:8080`. An `http` or `https` URL without a
user or a fragment; its decision list is at `v1/decisions` under it. Set
without the key, it is refused. So is a decision list URL that is also in
`SWW_BLOCKLIST_URLS`, or that is `SWW_ASN_LIMIT_PERCENT_URL`.
- `SWW_CROWDSEC_LAPI_KEY` (default unset): the key the engine gave for
`smallwebwaf`, as `cscli bouncers add smallwebwaf` prints it. Set without the
URL, it is refused.
- `SWW_REPUTATION_ACTION` (default `limit:25`): `deny`, `limit:<percent>` or
`log`, for DNS blocklist and AbuseIPDB hits.
- `SWW_REPUTATION_CACHE_TTL` (default `24h`): how long a zone's verdict or
AbuseIPDB's score is used. A duration.
- `SWW_REPUTATION_TIMEOUT` (default `2s`): how long a query to a zone or a check
with AbuseIPDB may take. A duration.
## Alerting
- `SWW_ALERT_WEBHOOK_URL` (default unset): the webhook that receives each alert
as a JSON object. An `http` or `https` URL without a user or a fragment.
- `SWW_ALERT_WEBHOOK_HEADERS` (default empty): headers sent with each post, such
as `Authorization:Bearer 0123456789abcdef`. A list of name, `:` and value. A
value cannot hold a comma.
- `SWW_ALERT_SLACK_WEBHOOK_URL` (default unset): the Slack incoming webhook that
receives each alert as a message, checked as the webhook URL is.
- `SWW_ALERT_NTFY_URL` (default unset): the ntfy topic that receives each alert,
as the topic's full URL, such as `https://ntfy.sh/my-alerts`, checked as the
webhook URL is.
- `SWW_ALERT_NTFY_TOKEN` (default unset): an ntfy access token. A control
character in it is refused.
- `SWW_ALERT_EVENTS` (default
`ban,permanent_ban,waf_block,anomaly,reputation_hit,source_failure,file_error`):
the event types alerts are sent for, from those in [`alerts.md`](alerts.md)
but `summary`. Any other name is refused.
- `SWW_ALERT_COOLDOWN` (default `15m`): how long after an alert is sent its
repeats are held back. A duration or `off`.
- `SWW_ALERT_MAX_PER_HOUR` (default `60`): the most alerts sent in an hour. A
whole number above zero, or `off`.
## Anomaly thresholds
Each scope has four thresholds: the most requests and the most body bytes
counted in a minute and in an hour. The bytes are those `SWW_BYTES_COUNT` names.
Requests are counts, bytes are sizes. Each is `off` by default. The four
thresholds per client are:
- `SWW_ANOMALY_CLIENT_REQUESTS_PER_MINUTE`;
- `SWW_ANOMALY_CLIENT_REQUESTS_PER_HOUR`;
- `SWW_ANOMALY_CLIENT_BYTES_PER_MINUTE`;
- `SWW_ANOMALY_CLIENT_BYTES_PER_HOUR`.
The other scopes' names have another prefix before the same four endings, such
as `REQUESTS_PER_MINUTE`:
- `SWW_ANOMALY_NET_...`: per netblock around a client. Two settings give the
netblock's length:
- `SWW_ANOMALY_NET_V4_PREFIX` (default `24`, from 0 to 32) for an IPv4
client;
- `SWW_ANOMALY_NET_V6_PREFIX` (default `48`, from 0 to 128) for an IPv6
client.
- `SWW_ANOMALY_ASN_...`: per AS number.
- `SWW_ANOMALY_TOTAL_...`: the whole service.
- `SWW_WATCH_...`: each netblock in `SWW_WATCH_NETS`, as a whole.
`SWW_WATCH_NETS` (default empty) is a list of name, `=` and netblock, such as
`office=203.0.113.0/24,scraper-x=198.51.100.0/22`. An item without `=` or a
name, or with a bad netblock, is refused. So is a name used twice.
## Settings given as files
To give a token as a file, as "Tokens" under "Deployment" in
[`SPEC.md`](../SPEC.md) describes, make the file on the host:
```sh
mkdir -p /srv/app/tokens
openssl rand -hex 32 > /srv/app/tokens/metrics
chown 65532:65532 /srv/app/tokens/metrics
chmod 0400 /srv/app/tokens/metrics
```
Then mount its directory into the container read-only, and name the file:
```sh
docker run \
-v /srv/app/tokens:/etc/sww/tokens:ro \
-e SWW_COMMAND=discriminator \
-e SWW_METRICS_TOKEN_FILE=/etc/sww/tokens/metrics \
...
```
## Fixed limits
A few limits are fixed rather than settings:
- at most 100,000 GeoJS answers are kept;
- at most 100,000 DNS blocklist verdicts and 100,000 AbuseIPDB scores are kept;
- at most 1,000 DNS blocklist queries are under way at once;
- at most 20,000 anomaly counters are kept;
- each alert destination's queue holds at most 1,000 alerts;
- `discriminator` holds at most 10,000 answered requests awaiting their reports;
- `discriminator` refuses a request with more than 50 cookies or more than 100
header fields (see "Answering in time" under "`discriminator`" in
[`SPEC.md`](../SPEC.md));
- `rproxy` takes a request line and headers of at most 32 KiB, and closes a
kept-open connection idle for 120 seconds;
- `rproxy` reads at most 1 MiB of the body of `discriminator`'s answer, and
answers `502` to a longer one.
## `discriminator`'s answer and `rproxy`'s wait
`SWW_LOOKUP_TIMEOUT` is the longest a question waits on an outside source. Keep
it well under `rproxy`'s `SWRP_TIMEOUT_MS`, as the default is. No question waits
for `SWW_REPUTATION_TIMEOUT`, since the DNS blocklists and AbuseIPDB are asked
in the background (see "Answering in time" under "`discriminator`" in
[`SPEC.md`](../SPEC.md)).
## `rproxy`
`sww rproxy` reads the settings below and no others. They are read once at
start, and an invalid value stops the start. None can be given as a file, since
`rproxy` never touches disk. "`rproxy`" in [`SPEC.md`](../SPEC.md) says what
they do.
A time here is a whole number of milliseconds above zero, such as `2000`.
- `SWRP_WAF_BACKEND` (required, no default): `discriminator`'s URL. An `http` or
`https` URL with a host and an optional port, and nothing more. `rproxy`
speaks HTTP/1.1 to it.
- `SWRP_TIMEOUT_MS` (default `2000`): how long `rproxy` waits for
`discriminator`'s answer, to a question and to a report. A time; never `off`.
- `SWRP_DEFAULT_DISPOSITION` (default `allow`): what is done with a request when
`discriminator` cannot be connected to, does not answer at all, or does not
answer within `SWRP_TIMEOUT_MS`. `allow` passes it to the app, and `deny`
answers `503`. It does not apply to an answer `discriminator` gives, such as
an error.
- `SWRP_MAX_REQUEST_SIZE` (default `100M`): the largest request body. A size or
`off`.
- `SWRP_MAX_RESPONSE_SIZE` (default `1G`): the largest response body. A size or
`off`.
- `SWRP_MAX_REQUEST_TIME_MS` (default `60000`): how long the visitor may take to
send its request line and headers. It then also bounds, from the end of the
headers, the time until the app has been sent the whole request. A time or
`off`.
- `SWRP_MAX_RESPONSE_TIME_MS` (default `1800000`): how long the answer may take,
from the end of the request to its last byte reaching the visitor. A time or
`off`.
- `SWRP_LISTEN_ADDR` (default `:8080`): where `rproxy` listens, such as `:9000`.
- `SWRP_UPSTREAM_URL` (default `http://127.0.0.1:8081`): the app. An `http` or
`https` URL with a host and an optional port, and nothing more.
- `SWRP_TRUSTED_PROXIES` (default `10.0.0.0/8,172.16.0.0/12,192.168.0.0/16`):
the netblocks whose `X-Forwarded-For` is believed. Set but empty, it trusts
nothing. A client outside these netblocks cannot claim another address. Where
other containers reach `rproxy` directly, or visitors on a private network
reach traefik, they can name another address in the header. Narrowing the
setting to traefik's own network closes that gap.
## The image's command
`SWW_COMMAND` (default `rproxy`) chooses what the image runs and what its health
check checks: `rproxy` or `discriminator` (see "Deployment" in
[`SPEC.md`](../SPEC.md)). It cannot be given as a file.
## Where earlier settings went
Nothing reads these names any more:
- `SWW_UPSTREAM_URL` is `SWRP_UPSTREAM_URL`.
- `SWW_TRUSTED_PROXIES` is `SWRP_TRUSTED_PROXIES`.
- `SWW_REQUEST_MAX_BYTES` is `SWRP_MAX_REQUEST_SIZE`.
- `SWW_RESPONSE_MAX_BYTES` is `SWRP_MAX_RESPONSE_SIZE`.
- `SWW_CLIENT_REQUEST_TIMEOUT` and `SWW_UPSTREAM_REQUEST_TIMEOUT` are
`SWRP_MAX_REQUEST_TIME_MS`, in milliseconds.
- `SWW_CLIENT_RESPONSE_TIMEOUT` and `SWW_UPSTREAM_RESPONSE_TIMEOUT` are
`SWRP_MAX_RESPONSE_TIME_MS`, in milliseconds.
- `SWW_CLIENT_IDLE_TIMEOUT` and `SWW_CLIENT_REQUEST_HEADER_MAX_BYTES` have no
setting. `rproxy` closes a kept-open connection idle for 120 seconds, and
takes a request line and headers of at most 32 KiB.
-105
View File
@@ -1,105 +0,0 @@
# State files
The five JSON files in `SWW_STATE_DIR`, and what each holds. "Persistent state"
in [`SPEC.md`](../SPEC.md) says how they are written, read and edited. Each has
a top-level `version` of 1.
## `bans.json`
Active and past bans: every ban an admin made, and up to `SWW_MAX_BANS` of those
`discriminator` made. Per entry:
- `netblock`, `start` and `expires` (`null` for a permanent ban);
- `cause`: `attack`, `limit`, `admin` or `crowdsec`;
- `reason`: a short reason;
- `lifted`: when an admin lifted it, if one did;
- `notes`: the notes below.
An entry an admin adds needs `netblock`, `start` and `expires`; `reason`,
`notes` and `cause` may be left out, and the cause is then `admin`:
```json
{
"version": 1,
"bans": [
{
"netblock": "203.0.113.0/24",
"start": "2026-10-06T12:00:00Z",
"expires": null,
"reason": "probes for logins"
}
]
}
```
"Bans" in [`SPEC.md`](../SPEC.md) says how an edit lifts, keeps or forgets a
ban. The notes:
- `asn`, `as_name` and `country`: the client's, added when the lookup answers
(empty when lookups are off);
- for a broken limit, `kind` (`requests`, `bytes` or `refusals`), `limit`,
`window` and `count`: what the limit was on, the limit, its window and the
count reached;
- `limit_percent` and `limit_percent_setting`: the client's percentage of that
limit and the setting that gave it, when a setting lowered it;
- for a clear sign of attack, `rule_id` and `target`, or `trap_path`;
- `reputation`: the sources the client was on, each with its `source` and, for
AbuseIPDB, its `score`;
- `request`: the request that caused the ban, each text cut to 256 bytes:
- `time`, `method` and `host`;
- `path`, with its query string;
- `status` and `user_agent`;
- `requests` and `refused`: the netblock's requests since it was first seen, and
how many this ban has refused so far, kept up to date while the ban lasts;
- `earlier_bans`: how many earlier bans the netblock had, by cause.
## `clients.json`
Per client, one per line: its minute, hour and day counters, and its history
since it was first seen:
- the first and last time seen;
- the AS number, AS name and country last looked up, and when;
- total requests, and how many were forwarded and how many refused;
- body bytes of its requests, and of the responses it was sent;
- responses by status class;
- offences by kind: `limit`, `attack`, `blocked_by_block_rule` and
`waf_blocked`. A file may also hold `token_refused`, which is kept, and which
nothing adds to.
## `lookups.json`
GeoJS answers, one per line:
- `client`;
- `asn`, `as_name` and `country`;
- `answered`: when GeoJS answered;
- `used`: when the answer was last used.
## `reputation.json`
- the last good copy of each list fetched from a URL, with when it was last
tried;
- each DNS blocklist verdict still in use;
- AbuseIPDB's scores, and the checks spent today.
## `alerts.json`
- the anomaly counters;
- the alert cooldowns: for each event and netblock, source, file or anomaly
scope, when it was last sent and the count of repeats held back since;
- the alerts sent and held back in the current hour;
- the alerts waiting for each destination.
## Sizes
- `clients.json`: about 1 KiB per client, about 20 MiB at the default
`SWW_MAX_TRACKED_CLIENTS`. Written every 15 minutes, that is under 2 GiB of
disk writes a day.
- `bans.json`: about 1.2 KiB per ban, at most about 2.5 KiB, so about 6 MiB at
the default `SWW_MAX_BANS`. Written every 15 minutes, a full file comes to
about 600 MiB of writes a day, and a hundred new bans a day add about 600 MiB
more.
- `lookups.json`: about 150 bytes per answer, under 1.5 GiB of writes a day when
full.
- `reputation.json` and `alerts.json`: usually a few MiB or less.
+43 -49
View File
@@ -1,12 +1,12 @@
// Package alerts sends alerts on bans, on traffic over an anomaly // Package alerts sends alerts on bans, on traffic over an anomaly
// threshold, on a source that fails and on a file with an error to each // threshold, on a source that fails and on a file with an error to each
// destination set: to the webhook // destination set: to the webhook
// SWW_ALERT_WEBHOOK_URL names, each as one JSON object, as "The JSON // SWWAF_ALERT_WEBHOOK_URL names, each as one JSON object, as the "Alert
// object" in docs/alerts.md describes, to the Slack incoming // webhook schema" section of SPEC.md describes, to the Slack incoming
// webhook SWW_ALERT_SLACK_WEBHOOK_URL names, as a message, and to the // webhook SWWAF_ALERT_SLACK_WEBHOOK_URL names, as a message, and to the
// ntfy topic SWW_ALERT_NTFY_URL names. A repeat within // ntfy topic SWWAF_ALERT_NTFY_URL names. A repeat within
// SWW_ALERT_COOLDOWN is held back, and so is an alert past // SWWAF_ALERT_COOLDOWN is held back, and so is an alert past
// SWW_ALERT_MAX_PER_HOUR, for the hour's summary. The others wait in a // SWWAF_ALERT_MAX_PER_HOUR, for the hour's summary. The others wait in a
// bounded queue of each destination's own, so that a destination that is // bounded queue of each destination's own, so that a destination that is
// slow or unreachable holds up neither the others nor any request. The // slow or unreachable holds up neither the others nor any request. The
// state is written to alerts.json and read from it by the state package. // state is written to alerts.json and read from it by the state package.
@@ -34,41 +34,41 @@ import (
"time" "time"
) )
// The events an alert is for, as SWW_ALERT_EVENTS names them. // The events an alert is for, as SWWAF_ALERT_EVENTS names them.
const ( const (
// EventBan is a ban sww made. // EventBan is a ban smallwebwaf made.
EventBan = "ban" EventBan = "ban"
// EventPermanentBan is a permanent ban sww made, or a ban it // EventPermanentBan is a permanent ban smallwebwaf made, or a ban it
// made permanent. // made permanent.
EventPermanentBan = "permanent_ban" EventPermanentBan = "permanent_ban"
// EventAnomaly is a count of requests or bytes over an anomaly // EventAnomaly is a count of requests or bytes over an anomaly
// threshold. // threshold.
EventAnomaly = "anomaly" EventAnomaly = "anomaly"
// EventWAFBlock is a request the Core Rule Set scored at or over // EventWAFBlock is a request the Core Rule Set scored at or over
// SWW_WAF_ANOMALY_THRESHOLD, refused in block mode, let through in // SWWAF_WAF_ANOMALY_THRESHOLD, refused in block mode, let through in
// detect mode. // detect mode.
EventWAFBlock = "waf_block" EventWAFBlock = "waf_block"
// EventReputationHit is a request whose client a blocklist, the // EventReputationHit is a request whose client a blocklist, the
// CrowdSec decision list or a DNSBL zone lists, or whose AbuseIPDB score // CrowdSec decision list or a DNSBL zone lists, or whose AbuseIPDB score
// is a hit. // is a hit.
EventReputationHit = "reputation_hit" EventReputationHit = "reputation_hit"
// EventSourceFailure is GeoJS failing or refusing sww, a fetch // EventSourceFailure is GeoJS failing or refusing smallwebwaf, a fetch
// of a list failing, a query to a DNSBL zone or a check with AbuseIPDB // of a list failing, a query to a DNSBL zone or a check with AbuseIPDB
// failing or refused, or the day's AbuseIPDB checks used up. // failing or refused, or the day's AbuseIPDB checks used up.
EventSourceFailure = "source_failure" EventSourceFailure = "source_failure"
// EventFileError is a rule file or state file edited while sww // EventFileError is a rule file or state file edited while smallwebwaf
// runs that does not parse, a replacement of the lookup database that // runs that does not parse, a replacement of the lookup database that
// cannot be read, or a state file that cannot be written. // cannot be read, or a state file that cannot be written.
EventFileError = "file_error" EventFileError = "file_error"
// EventSummary is the summary sent as an hour ends: of the alerts held // EventSummary is the summary sent as an hour ends: of the alerts held
// back in it past SWW_ALERT_MAX_PER_HOUR, and of the repeats held // back in it past SWWAF_ALERT_MAX_PER_HOUR, and of the repeats held
// back by the cooldowns dropped as it ends, which no alert let through // back by the cooldowns dropped as it ends, which no alert let through
// has given. It is sent with SWW_ALERT_MAX_PER_HOUR off too, for // has given. It is sent with SWWAF_ALERT_MAX_PER_HOUR off too, for
// those repeats. SWW_ALERT_EVENTS does not name it. // those repeats. SWWAF_ALERT_EVENTS does not name it.
EventSummary = "summary" EventSummary = "summary"
) )
// Events returns every event SWW_ALERT_EVENTS can name, which is its // Events returns every event SWWAF_ALERT_EVENTS can name, which is its
// default. // default.
func Events() []string { func Events() []string {
return []string{ return []string{
@@ -80,12 +80,12 @@ func Events() []string {
// The destinations alerts are sent to, as the metrics and alerts.json // The destinations alerts are sent to, as the metrics and alerts.json
// name them. // name them.
const ( const (
// DestinationWebhook is the webhook SWW_ALERT_WEBHOOK_URL names. // DestinationWebhook is the webhook SWWAF_ALERT_WEBHOOK_URL names.
DestinationWebhook = "webhook" DestinationWebhook = "webhook"
// DestinationSlack is the Slack incoming webhook // DestinationSlack is the Slack incoming webhook
// SWW_ALERT_SLACK_WEBHOOK_URL names. // SWWAF_ALERT_SLACK_WEBHOOK_URL names.
DestinationSlack = "slack" DestinationSlack = "slack"
// DestinationNtfy is the ntfy topic SWW_ALERT_NTFY_URL names. // DestinationNtfy is the ntfy topic SWWAF_ALERT_NTFY_URL names.
DestinationNtfy = "ntfy" DestinationNtfy = "ntfy"
) )
@@ -121,26 +121,26 @@ var (
// NtfyURL set, no alert is sent. // NtfyURL set, no alert is sent.
type Params struct { type Params struct {
// WebhookURL is where each alert is posted as JSON // WebhookURL is where each alert is posted as JSON
// (SWW_ALERT_WEBHOOK_URL), nil while it is unset. WebhookHeaders // (SWWAF_ALERT_WEBHOOK_URL), nil while it is unset. WebhookHeaders
// are sent with each (SWW_ALERT_WEBHOOK_HEADERS). // are sent with each (SWWAF_ALERT_WEBHOOK_HEADERS).
WebhookURL *url.URL WebhookURL *url.URL
WebhookHeaders http.Header WebhookHeaders http.Header
// SlackURL is the Slack incoming webhook each alert is posted to as a // SlackURL is the Slack incoming webhook each alert is posted to as a
// message (SWW_ALERT_SLACK_WEBHOOK_URL), nil while it is unset. // message (SWWAF_ALERT_SLACK_WEBHOOK_URL), nil while it is unset.
SlackURL *url.URL SlackURL *url.URL
// NtfyURL is the ntfy topic each alert is published to // NtfyURL is the ntfy topic each alert is published to
// (SWW_ALERT_NTFY_URL), nil while it is unset. NtfyToken, unless // (SWWAF_ALERT_NTFY_URL), nil while it is unset. NtfyToken, unless
// empty, is sent with each as a bearer token (SWW_ALERT_NTFY_TOKEN). // empty, is sent with each as a bearer token (SWWAF_ALERT_NTFY_TOKEN).
NtfyURL *url.URL NtfyURL *url.URL
NtfyToken string NtfyToken string
// Events are the events alerts are sent for (SWW_ALERT_EVENTS). // Events are the events alerts are sent for (SWWAF_ALERT_EVENTS).
Events []string Events []string
// Cooldown is how long a repeat of an alert is held back // Cooldown is how long a repeat of an alert is held back
// (SWW_ALERT_COOLDOWN), 0 for no time. MaxPerHour is the most alerts // (SWWAF_ALERT_COOLDOWN), 0 for no time. MaxPerHour is the most alerts
// sent in an hour (SWW_ALERT_MAX_PER_HOUR), 0 for no limit. // sent in an hour (SWWAF_ALERT_MAX_PER_HOUR), 0 for no limit.
Cooldown time.Duration Cooldown time.Duration
MaxPerHour int MaxPerHour int
// Instance is SWW_INSTANCE_NAME, which every alert gives. // Instance is SWWAF_INSTANCE_NAME, which every alert gives.
Instance string Instance string
// Now tells the time of an alert, normally time.Now in UTC. // Now tells the time of an alert, normally time.Now in UTC.
Now func() time.Time Now func() time.Time
@@ -149,17 +149,15 @@ type Params struct {
} }
// Alert is one alert, as the webhook is sent it and alerts.json holds it, // Alert is one alert, as the webhook is sent it and alerts.json holds it,
// with the fields of "The JSON object" in docs/alerts.md. ASN, ASName and // with the fields of the "Alert webhook schema" section of SPEC.md. ASN,
// Country are, for a ban, the client's as the ban's notes give them. Host is // ASName and Country are, for a ban, the client's as the ban's notes give
// the site of the request that raised the alert, while one discriminator serves // them.
// many sites, and "" otherwise.
// //
//nolint:tagliatelle // docs/alerts.md names the alert's fields in snake_case //nolint:tagliatelle // SPEC.md's alert webhook schema names its fields in snake_case
type Alert struct { type Alert struct {
Instance string `json:"instance"` Instance string `json:"instance"`
Time time.Time `json:"time"` Time time.Time `json:"time"`
Event string `json:"event"` Event string `json:"event"`
Host string `json:"host,omitempty"`
Client netip.Addr `json:"client"` Client netip.Addr `json:"client"`
Netblock netip.Prefix `json:"netblock"` Netblock netip.Prefix `json:"netblock"`
ASN string `json:"asn"` ASN string `json:"asn"`
@@ -301,17 +299,17 @@ func New(params Params) *Queue {
} }
if params.WebhookURL != nil { if params.WebhookURL != nil {
q.addDestination(DestinationWebhook, "SWW_ALERT_WEBHOOK_URL", q.addDestination(DestinationWebhook, "SWWAF_ALERT_WEBHOOK_URL",
params.WebhookURL, q.webhookMessage) params.WebhookURL, q.webhookMessage)
} }
if params.SlackURL != nil { if params.SlackURL != nil {
q.addDestination(DestinationSlack, "SWW_ALERT_SLACK_WEBHOOK_URL", q.addDestination(DestinationSlack, "SWWAF_ALERT_SLACK_WEBHOOK_URL",
params.SlackURL, slackMessage) params.SlackURL, slackMessage)
} }
if params.NtfyURL != nil { if params.NtfyURL != nil {
q.addDestination(DestinationNtfy, "SWW_ALERT_NTFY_URL", q.addDestination(DestinationNtfy, "SWWAF_ALERT_NTFY_URL",
params.NtfyURL, q.ntfyMessage) params.NtfyURL, q.ntfyMessage)
} }
@@ -319,7 +317,7 @@ func New(params Params) *Queue {
} }
// Raise sends alert, which names its event and what is particular to it, // Raise sends alert, which names its event and what is particular to it,
// unless no destination is set or SWW_ALERT_EVENTS leaves its event // unless no destination is set or SWWAF_ALERT_EVENTS leaves its event
// out. It gives alert the instance and the time. An alert that repeats // out. It gives alert the instance and the time. An alert that repeats
// the last one let through less than Cooldown before is held back and // the last one let through less than Cooldown before is held back and
// counted. The next one let through gives that count, unless an hour of // counted. The next one let through gives that count, unless an hour of
@@ -363,7 +361,7 @@ func (q *Queue) Raise(alert Alert) {
} }
// WouldSend reports whether Raise would let an alert for event on // WouldSend reports whether Raise would let an alert for event on
// netblock through now: a destination is set, SWW_ALERT_EVENTS chooses // netblock through now: a destination is set, SWWAF_ALERT_EVENTS chooses
// event, no alert for event on netblock was let through less than // event, no alert for event on netblock was let through less than
// Cooldown before, and fewer than MaxPerHour alerts have been let through // Cooldown before, and fewer than MaxPerHour alerts have been let through
// in the hour under way. Unlike Raise, it counts nothing. // in the hour under way. Unlike Raise, it counts nothing.
@@ -606,13 +604,13 @@ func (q *Queue) endHour(now time.Time) {
if heldBack > 0 { if heldBack > 0 {
reasons = append(reasons, fmt.Sprintf("%d alerts held back in the hour from %s, "+ reasons = append(reasons, fmt.Sprintf("%d alerts held back in the hour from %s, "+
"past the %d an hour SWW_ALERT_MAX_PER_HOUR allows", heldBack, "past the %d an hour SWWAF_ALERT_MAX_PER_HOUR allows", heldBack,
q.hour.Start.Format(time.RFC3339), q.params.MaxPerHour)) q.hour.Start.Format(time.RFC3339), q.params.MaxPerHour))
} }
if repeats > 0 { if repeats > 0 {
reasons = append(reasons, fmt.Sprintf("%d repeats held back by "+ reasons = append(reasons, fmt.Sprintf("%d repeats held back by "+
"SWW_ALERT_COOLDOWN that no later alert gives", repeats)) "SWWAF_ALERT_COOLDOWN that no later alert gives", repeats))
} }
if len(reasons) > 0 { if len(reasons) > 0 {
@@ -683,7 +681,7 @@ func (d *destination) run(ctx context.Context) {
d.processLog.Warn("gave up an alert "+d.setting+" refused", d.processLog.Warn("gave up an alert "+d.setting+" refused",
"event", alert.Event, "error", err.Error()) "event", alert.Event, "error", err.Error())
case ctx.Err() == nil: // not cut off as sww stops case ctx.Err() == nil: // not cut off as smallwebwaf stops
d.failed.Add(1) d.failed.Add(1)
retryDelay = min(max(retryDelayFactor*retryDelay, firstRetryDelay), retryDelay = min(max(retryDelayFactor*retryDelay, firstRetryDelay),
@@ -902,16 +900,12 @@ func title(alert *Alert) string {
} }
// text returns the text of alert in Slack and ntfy: its reason, then a // text returns the text of alert in Slack and ntfy: its reason, then a
// line for each of its host, client, netblock and country, the file, // line for each of its client, netblock and country, the file, source,
// source, error and mode its detail gives, and its suppressed repeats, that // error and mode its detail gives, and its suppressed repeats, that it
// it has. // has.
func text(alert *Alert) string { func text(alert *Alert) string {
lines := []string{alert.Reason} lines := []string{alert.Reason}
if alert.Host != "" {
lines = append(lines, "host: "+alert.Host)
}
if alert.Client.IsValid() { if alert.Client.IsValid() {
lines = append(lines, "client: "+alert.Client.String()) lines = append(lines, "client: "+alert.Client.String())
} }
+26 -28
View File
@@ -34,12 +34,12 @@ const (
// webhookURL is where the alerts are posted, slackURL the Slack // webhookURL is where the alerts are posted, slackURL the Slack
// incoming webhook, and ntfyURL the ntfy topic. ntfyToken is the ntfy // incoming webhook, and ntfyURL the ntfy topic. ntfyToken is the ntfy
// token of the tests that set one. // token of the tests that set one.
webhookURL = "https://alerts.example/sww?team=ops" webhookURL = "https://alerts.example/smallwebwaf?team=ops"
slackURL = "https://hooks.slack.example/services/T0123/B4567/abcdef" slackURL = "https://hooks.slack.example/services/T0123/B4567/abcdef"
ntfyURL = "https://ntfy.example/sww-alerts" ntfyURL = "https://ntfy.example/smallwebwaf-alerts"
ntfyToken = "tk_0123456789abcdefghijklmnopq" ntfyToken = "tk_0123456789abcdefghijklmnopq"
// instance is the instance name every alert gives. // instance is the instance name every alert gives.
instance = "fsn1app1/blog" instance = "fsn1app1/gitea"
// started is when each test starts, as an alert gives it, and // started is when each test starts, as an alert gives it, and
// anHourOn an hour later. // anHourOn an hour later.
started = "2000-01-01T00:00:00Z" started = "2000-01-01T00:00:00Z"
@@ -132,7 +132,7 @@ func TestWouldSendOnlyForTheChosenEvents(t *testing.T) {
if q.WouldSend(alerts.EventBan, netblock(1)) || if q.WouldSend(alerts.EventBan, netblock(1)) ||
q.WouldSend(alerts.EventPermanentBan, netblock(1)) { q.WouldSend(alerts.EventPermanentBan, netblock(1)) {
t.Error("a ban alert would be sent, though SWW_ALERT_EVENTS leaves it out") t.Error("a ban alert would be sent, though SWWAF_ALERT_EVENTS leaves it out")
} }
if !q.WouldSend(alerts.EventFileError, netip.Prefix{}) { if !q.WouldSend(alerts.EventFileError, netip.Prefix{}) {
@@ -184,8 +184,8 @@ func TestWouldSendWithOnlySlackOrOnlyNtfySet(t *testing.T) {
onlyNtfy.NtfyURL = parseURL(ntfyURL) onlyNtfy.NtfyURL = parseURL(ntfyURL)
for setting, params := range map[string]alerts.Params{ for setting, params := range map[string]alerts.Params{
"SWW_ALERT_SLACK_WEBHOOK_URL": onlySlack, "SWWAF_ALERT_SLACK_WEBHOOK_URL": onlySlack,
"SWW_ALERT_NTFY_URL": onlyNtfy, "SWWAF_ALERT_NTFY_URL": onlyNtfy,
} { } {
if !alerts.New(params).WouldSend(alerts.EventBan, netblock(1)) { if !alerts.New(params).WouldSend(alerts.EventBan, netblock(1)) {
t.Errorf("a ban alert would not be sent with only %s set", setting) t.Errorf("a ban alert would not be sent with only %s set", setting)
@@ -359,7 +359,7 @@ func TestAlertsPastTheHourlyLimitAreRolledIntoOneSummary(t *testing.T) {
"as_name": "", "as_name": "",
"country": "", "country": "",
"reason": "3 alerts held back in the hour from 2000-01-01T00:00:00Z, " + "reason": "3 alerts held back in the hour from 2000-01-01T00:00:00Z, " +
"past the 2 an hour SWW_ALERT_MAX_PER_HOUR allows", "past the 2 an hour SWWAF_ALERT_MAX_PER_HOUR allows",
"detail": map[string]any{ "detail": map[string]any{
"hour": started, "hour": started,
"count": float64(3), "count": float64(3),
@@ -525,7 +525,7 @@ func TestFailedRequestIsSentAgainWithBackoff(t *testing.T) {
wantCounts(t, q, 0, int64(len(want)), 0, 0) wantCounts(t, q, 0, int64(len(want)), 0, 0)
if !strings.Contains(log.String(), if !strings.Contains(log.String(),
`"msg":"sending an alert to SWW_ALERT_WEBHOOK_URL failed"`) { `"msg":"sending an alert to SWWAF_ALERT_WEBHOOK_URL failed"`) {
t.Errorf("process log %q names no failure", log.String()) t.Errorf("process log %q names no failure", log.String())
} }
@@ -595,7 +595,7 @@ func TestRefusedAlertIsGivenUpAndTheNextSent(t *testing.T) {
wantCounts(t, q, 1, 3, 0, 1) wantCounts(t, q, 1, 3, 0, 1)
if !strings.Contains(log.String(), if !strings.Contains(log.String(),
`"msg":"gave up an alert SWW_ALERT_WEBHOOK_URL refused"`) { `"msg":"gave up an alert SWWAF_ALERT_WEBHOOK_URL refused"`) {
t.Errorf("process log %q names no alert given up", log.String()) t.Errorf("process log %q names no alert given up", log.String())
} }
}) })
@@ -619,7 +619,7 @@ func TestFailedRequestIsLoggedWithoutTheURL(t *testing.T) {
logged := log.String() logged := log.String()
if !strings.Contains(logged, if !strings.Contains(logged,
`"msg":"sending an alert to SWW_ALERT_WEBHOOK_URL failed"`) || `"msg":"sending an alert to SWWAF_ALERT_WEBHOOK_URL failed"`) ||
strings.Contains(logged, "alerts.example") || strings.Contains(logged, "team=ops") { strings.Contains(logged, "alerts.example") || strings.Contains(logged, "team=ops") {
t.Errorf("process log %q names no failure, or names the URL", logged) t.Errorf("process log %q names no failure, or names the URL", logged)
} }
@@ -782,8 +782,8 @@ func TestSlackAndNtfyAreSentTheSummaryAndTheRepeatsHeldBack(t *testing.T) {
} }
const summary = "1 alerts held back in the hour from 2000-01-01T00:00:00Z, " + const summary = "1 alerts held back in the hour from 2000-01-01T00:00:00Z, " +
"past the 1 an hour SWW_ALERT_MAX_PER_HOUR allows; 1 repeats held back " + "past the 1 an hour SWWAF_ALERT_MAX_PER_HOUR allows; 1 repeats held back " +
"by SWW_ALERT_COOLDOWN that no later alert gives\nsuppressed repeats: 1" "by SWWAF_ALERT_COOLDOWN that no later alert gives\nsuppressed repeats: 1"
wantSlackMessage(t, slack[1], "*"+instance+": summary*\n"+summary) wantSlackMessage(t, slack[1], "*"+instance+": summary*\n"+summary)
wantNtfyMessage(t, ntfy[1], instance+": summary", "default bar_chart", summary) wantNtfyMessage(t, ntfy[1], instance+": summary", "default bar_chart", summary)
@@ -901,7 +901,7 @@ func TestDestinationThatDoesNotAnswerHoldsUpNeitherOther(t *testing.T) {
logged := log.String() logged := log.String()
if !strings.Contains(logged, if !strings.Contains(logged,
`"msg":"sending an alert to SWW_ALERT_SLACK_WEBHOOK_URL failed"`) || `"msg":"sending an alert to SWWAF_ALERT_SLACK_WEBHOOK_URL failed"`) ||
strings.Contains(logged, "hooks.slack.example") || strings.Contains(logged, "hooks.slack.example") ||
strings.Contains(logged, "T0123") { strings.Contains(logged, "T0123") {
t.Errorf("process log %q names no failure, or names the URL", logged) t.Errorf("process log %q names no failure, or names the URL", logged)
@@ -965,8 +965,8 @@ func TestEachDestinationIsSentOnlyTheAlertsWaitingForIt(t *testing.T) {
synctest.Wait() synctest.Wait()
wantBodies(t, standIns[alerts.DestinationSlack], wantBodies(t, standIns[alerts.DestinationSlack],
`{"text":"*fsn1app1/blog: file_error*\nsecond"}`, `{"text":"*fsn1app1/gitea: file_error*\nsecond"}`,
`{"text":"*fsn1app1/blog: file_error*\nthird"}`) `{"text":"*fsn1app1/gitea: file_error*\nthird"}`)
wantBodies(t, standIns[alerts.DestinationNtfy], "fourth") wantBodies(t, standIns[alerts.DestinationNtfy], "fourth")
// alerts.json then lists Slack and ntfy alone, with no alert waiting. // alerts.json then lists Slack and ntfy alone, with no alert waiting.
@@ -1254,7 +1254,7 @@ type eventMessage struct {
title, priorityAndTag, text string title, priorityAndTag, text string
} }
// anAlertForEachEvent returns an alert for each event SWW_ALERT_EVENTS // anAlertForEachEvent returns an alert for each event SWWAF_ALERT_EVENTS
// names, the first in observe mode, each with its message. // names, the first in observe mode, each with its message.
func anAlertForEachEvent() []eventMessage { func anAlertForEachEvent() []eventMessage {
return []eventMessage{ return []eventMessage{
@@ -1265,7 +1265,7 @@ func anAlertForEachEvent() []eventMessage {
Reason: "requests per hour over the limit of 10000", Reason: "requests per hour over the limit of 10000",
Detail: map[string]any{"mode": "observe"}, Detail: map[string]any{"mode": "observe"},
}, },
"fsn1app1/blog: ban", "default no_entry", "fsn1app1/gitea: ban", "default no_entry",
"requests per hour over the limit of 10000\nclient: 203.0.113.9\n" + "requests per hour over the limit of 10000\nclient: 203.0.113.9\n" +
"netblock: 203.0.113.0/24\ncountry: DE\nmode: observe", "netblock: 203.0.113.0/24\ncountry: DE\nmode: observe",
}, },
@@ -1275,7 +1275,7 @@ func anAlertForEachEvent() []eventMessage {
Netblock: netip.MustParsePrefix("198.51.100.7/32"), Country: "FR", Netblock: netip.MustParsePrefix("198.51.100.7/32"), Country: "FR",
Reason: "matched the rule env-file", Reason: "matched the rule env-file",
}, },
"fsn1app1/blog: permanent_ban", "high no_entry", "fsn1app1/gitea: permanent_ban", "high no_entry",
"matched the rule env-file\nclient: 198.51.100.7\n" + "matched the rule env-file\nclient: 198.51.100.7\n" +
"netblock: 198.51.100.7/32\ncountry: FR", "netblock: 198.51.100.7/32\ncountry: FR",
}, },
@@ -1284,18 +1284,16 @@ func anAlertForEachEvent() []eventMessage {
Event: alerts.EventWAFBlock, Client: netip.MustParseAddr("192.0.2.1"), Event: alerts.EventWAFBlock, Client: netip.MustParseAddr("192.0.2.1"),
Netblock: netip.MustParsePrefix("192.0.2.1/32"), Netblock: netip.MustParsePrefix("192.0.2.1/32"),
Reason: "refused by the Core Rule Set", Reason: "refused by the Core Rule Set",
Host: "app.example",
}, },
"fsn1app1/blog: waf_block", "default shield", "fsn1app1/gitea: waf_block", "default shield",
"refused by the Core Rule Set\nhost: app.example\nclient: 192.0.2.1\n" + "refused by the Core Rule Set\nclient: 192.0.2.1\nnetblock: 192.0.2.1/32",
"netblock: 192.0.2.1/32",
}, },
{ {
alerts.Alert{ alerts.Alert{
Event: alerts.EventAnomaly, Netblock: netip.MustParsePrefix("192.0.2.0/24"), Event: alerts.EventAnomaly, Netblock: netip.MustParsePrefix("192.0.2.0/24"),
Reason: "requests per minute over the threshold of 5000", Reason: "requests per minute over the threshold of 5000",
}, },
"fsn1app1/blog: anomaly", "high chart_with_upwards_trend", "fsn1app1/gitea: anomaly", "high chart_with_upwards_trend",
"requests per minute over the threshold of 5000\nnetblock: 192.0.2.0/24", "requests per minute over the threshold of 5000\nnetblock: 192.0.2.0/24",
}, },
{ {
@@ -1304,7 +1302,7 @@ func anAlertForEachEvent() []eventMessage {
Netblock: netip.MustParsePrefix("192.0.2.2/32"), Netblock: netip.MustParsePrefix("192.0.2.2/32"),
Reason: "listed by a DNS blocklist", Reason: "listed by a DNS blocklist",
}, },
"fsn1app1/blog: reputation_hit", "low label", "fsn1app1/gitea: reputation_hit", "low label",
"listed by a DNS blocklist\nclient: 192.0.2.2\nnetblock: 192.0.2.2/32", "listed by a DNS blocklist\nclient: 192.0.2.2\nnetblock: 192.0.2.2/32",
}, },
{ {
@@ -1312,7 +1310,7 @@ func anAlertForEachEvent() []eventMessage {
Event: alerts.EventSourceFailure, Reason: "asking GeoJS failed", Event: alerts.EventSourceFailure, Reason: "asking GeoJS failed",
Detail: map[string]any{"source": "geojs"}, Detail: map[string]any{"source": "geojs"},
}, },
"fsn1app1/blog: source_failure", "high warning", "fsn1app1/gitea: source_failure", "high warning",
"asking GeoJS failed\nsource: geojs", "asking GeoJS failed\nsource: geojs",
}, },
{ {
@@ -1320,12 +1318,12 @@ func anAlertForEachEvent() []eventMessage {
Event: alerts.EventFileError, Event: alerts.EventFileError,
Reason: "a rule file has an error, and the rules stay as they were", Reason: "a rule file has an error, and the rules stay as they were",
Detail: map[string]any{ Detail: map[string]any{
"file": "/etc/sww/rules.d/50-app.rules", "error": "line 2: no action", "file": "/etc/smallwebwaf/rules.d/50-app.rules", "error": "line 2: no action",
}, },
}, },
"fsn1app1/blog: file_error", "high warning", "fsn1app1/gitea: file_error", "high warning",
"a rule file has an error, and the rules stay as they were\n" + "a rule file has an error, and the rules stay as they were\n" +
"file: /etc/sww/rules.d/50-app.rules\nerror: line 2: no action", "file: /etc/smallwebwaf/rules.d/50-app.rules\nerror: line 2: no action",
}, },
} }
} }
+14 -17
View File
@@ -1,8 +1,8 @@
// Package anomaly counts requests and bytes over a minute and an hour, per // Package anomaly counts requests and bytes over a minute and an hour, per
// client, per surrounding netblock, per AS number, for the whole service // client, per surrounding netblock, per AS number, for the whole service
// and per named netblock, and raises an anomaly alert for a count over its // and per named netblock, and raises an anomaly alert for a count over its
// threshold, as "Anomaly thresholds" under "Settings" in SPEC.md // threshold, as "Anomaly thresholds" under "Configuration surface" in
// describes. It refuses and bans nothing. At most 20,000 counters // SPEC.md describes. It refuses and bans nothing. At most 20,000 counters
// are kept, in memory, and written to alerts.json and read from it by the // are kept, in memory, and written to alerts.json and read from it by the
// state package. // state package.
package anomaly package anomaly
@@ -28,16 +28,16 @@ const maxCounters = 20000
// alerts name them. // alerts name them.
const ( const (
// ScopeClient is one client: an IPv4 address, or an IPv6 netblock of // ScopeClient is one client: an IPv4 address, or an IPv6 netblock of
// SWW_IPV6_GROUP_PREFIX. // SWWAF_IPV6_GROUP_PREFIX.
ScopeClient = "client" ScopeClient = "client"
// ScopeNet is the netblock around a client, SWW_ANOMALY_NET_V4_PREFIX // ScopeNet is the netblock around a client, SWWAF_ANOMALY_NET_V4_PREFIX
// or SWW_ANOMALY_NET_V6_PREFIX long. // or SWWAF_ANOMALY_NET_V6_PREFIX long.
ScopeNet = "net" ScopeNet = "net"
// ScopeASN is an AS number. // ScopeASN is an AS number.
ScopeASN = "asn" ScopeASN = "asn"
// ScopeTotal is the whole service. // ScopeTotal is the whole service.
ScopeTotal = "total" ScopeTotal = "total"
// ScopeWatch is a named netblock of SWW_WATCH_NETS. // ScopeWatch is a named netblock of SWWAF_WATCH_NETS.
ScopeWatch = "watch" ScopeWatch = "watch"
) )
@@ -62,7 +62,7 @@ type Thresholds struct {
BytesPerHour int64 BytesPerHour int64
} }
// NamedNetblock is a netblock SWW_WATCH_NETS names. // NamedNetblock is a netblock SWWAF_WATCH_NETS names.
type NamedNetblock struct { type NamedNetblock struct {
Name string Name string
Netblock netip.Prefix Netblock netip.Prefix
@@ -70,14 +70,14 @@ type NamedNetblock struct {
// Params are what New needs. // Params are what New needs.
type Params struct { type Params struct {
// The thresholds of each scope: SWW_ANOMALY_CLIENT_*, // The thresholds of each scope: SWWAF_ANOMALY_CLIENT_*,
// SWW_ANOMALY_NET_*, SWW_ANOMALY_ASN_*, SWW_ANOMALY_TOTAL_* and // SWWAF_ANOMALY_NET_*, SWWAF_ANOMALY_ASN_*, SWWAF_ANOMALY_TOTAL_* and
// SWW_WATCH_*. // SWWAF_WATCH_*.
Client, Net, ASN, Total, Watch Thresholds Client, Net, ASN, Total, Watch Thresholds
// NetV4Prefix and NetV6Prefix are the lengths of the netblock around a // NetV4Prefix and NetV6Prefix are the lengths of the netblock around a
// client (SWW_ANOMALY_NET_V4_PREFIX and SWW_ANOMALY_NET_V6_PREFIX). // client (SWWAF_ANOMALY_NET_V4_PREFIX and SWWAF_ANOMALY_NET_V6_PREFIX).
NetV4Prefix, NetV6Prefix int NetV4Prefix, NetV6Prefix int
// NamedNetblocks are SWW_WATCH_NETS. // NamedNetblocks are SWWAF_WATCH_NETS.
NamedNetblocks []NamedNetblock NamedNetblocks []NamedNetblock
// Alerts receive the anomaly alerts. // Alerts receive the anomaly alerts.
Alerts *alerts.Queue Alerts *alerts.Queue
@@ -103,17 +103,15 @@ type Counter struct {
// Request is a request that has ended, as the counters count it. // Request is a request that has ended, as the counters count it.
type Request struct { type Request struct {
// Host is the site the alert names, "" for none.
Host string
// Client is the client's address, and ClientGroup the client it is // Client is the client's address, and ClientGroup the client it is
// counted as: its IPv4 address, or the IPv6 netblock of // counted as: its IPv4 address, or the IPv6 netblock of
// SWW_IPV6_GROUP_PREFIX its address is in. // SWWAF_IPV6_GROUP_PREFIX its address is in.
Client netip.Addr Client netip.Addr
ClientGroup netip.Prefix ClientGroup netip.Prefix
// ASN, ASName and Country are the client's as looked up, each "" when // ASN, ASName and Country are the client's as looked up, each "" when
// unknown. // unknown.
ASN, ASName, Country string ASN, ASName, Country string
// Bytes are the request's bytes, as SWW_BYTES_COUNT counts them. // Bytes are the request's bytes, as SWWAF_BYTES_COUNT counts them.
Bytes int64 Bytes int64
} }
@@ -398,7 +396,6 @@ func alertFor(r Request, k key, o overThreshold) alerts.Alert {
return alerts.Alert{ return alerts.Alert{
Event: alerts.EventAnomaly, Event: alerts.EventAnomaly,
Host: r.Host,
Client: r.Client, Client: r.Client,
Netblock: k.netblock, Netblock: k.netblock,
ASN: r.ASN, ASN: r.ASN,
+4 -49
View File
@@ -33,7 +33,7 @@ func TestAdminsBansAreNeverDroppedAndDoNotCountTowardMaxBans(t *testing.T) {
third := netip.MustParsePrefix("203.0.113.3/32") third := netip.MustParsePrefix("203.0.113.3/32")
// Seen longest ago, a netblock with two of an admin's bans alone, and // Seen longest ago, a netblock with two of an admin's bans alone, and
// then one with an admin's ban before a ban sww made: the one // then one with an admin's ban before a ban smallwebwaf made: the one
// ban counted toward MaxBans. // ban counted toward MaxBans.
ledger.Load([]bans.Ban{ ledger.Load([]bans.Ban{
{Netblock: adminsOnly, Start: midnight().Add(-3 * time.Hour), Cause: bans.CauseAdmin}, {Netblock: adminsOnly, Start: midnight().Add(-3 * time.Hour), Cause: bans.CauseAdmin},
@@ -48,7 +48,7 @@ func TestAdminsBansAreNeverDroppedAndDoNotCountTowardMaxBans(t *testing.T) {
}) })
wantBans(t, ledger, map[netip.Prefix]int{adminsOnly: 2, both: 2}) wantBans(t, ledger, map[netip.Prefix]int{adminsOnly: 2, both: 2})
// A new ban drops the ban sww made, and only that one. // A new ban drops the ban smallwebwaf made, and only that one.
ledger.BanForLimit(second, midnight(), bans.Notes{}) ledger.BanForLimit(second, midnight(), bans.Notes{})
wantBans(t, ledger, map[netip.Prefix]int{adminsOnly: 2, both: 1, second: 1}) wantBans(t, ledger, map[netip.Prefix]int{adminsOnly: 2, both: 1, second: 1})
@@ -114,7 +114,7 @@ func TestEarlierBansCountABanAnAdminKeepsOnce(t *testing.T) {
} }
} }
func TestReasonOfTheBansSwwMakes(t *testing.T) { func TestReasonOfTheBansSmallwebwafMakes(t *testing.T) {
t.Parallel() t.Parallel()
ledger := bans.New(defaultRules()) ledger := bans.New(defaultRules())
@@ -226,7 +226,7 @@ func TestLoadEditCountsTheBansAnAdminMade(t *testing.T) {
t.Fatalf("%d bans made by an admin after the start's, want none", got) t.Fatalf("%d bans made by an admin after the start's, want none", got)
} }
// The admin keeps the ban sww made, keeps the one read at the // The admin keeps the ban smallwebwaf made, keeps the one read at the
// start, and adds one without a cause: that one alone is made. // start, and adds one without a cause: that one alone is made.
kept := made kept := made
kept.Cause = bans.CauseAdmin kept.Cause = bans.CauseAdmin
@@ -341,48 +341,3 @@ func TestLiftLiftsEveryActiveBanCoveringTheClient(t *testing.T) {
wantChanged(t, ledger, false) wantChanged(t, ledger, false)
} }
func TestPermanentBanOnAWiderNetblockIsReturnedOverATemporaryBan(t *testing.T) {
t.Parallel()
client := netip.MustParseAddr("203.0.113.9")
ledger := bans.New(defaultRules())
// The temporary ban is made first, so that its netblock is looked at first.
ledger.BanForLimit(netip.MustParsePrefix("203.0.113.9/32"), midnight(), bans.Notes{})
ledger.BanForAdmin(netip.MustParsePrefix("203.0.113.0/24"), midnight(), time.Time{},
"for good")
wantPermanentBan(t, ledger, client, midnight().Add(time.Minute))
}
func TestOlderPermanentBanIsReturnedOverANewerTemporaryBan(t *testing.T) {
t.Parallel()
netblock := netip.MustParsePrefix("203.0.113.0/24")
ledger := bans.New(defaultRules())
ledger.BanForAdmin(netblock, midnight(), time.Time{}, "for good")
ledger.BanForAdmin(netblock, midnight().Add(time.Minute), midnight().Add(time.Hour),
"for an hour")
wantPermanentBan(t, ledger, netblock.Addr(), midnight().Add(2*time.Minute))
}
// wantPermanentBan checks that Find and Check return a permanent ban for
// client at now.
func wantPermanentBan(
t *testing.T, ledger *bans.Ledger, client netip.Addr, now time.Time,
) {
t.Helper()
for name, look := range map[string]func(netip.Addr, time.Time) (bans.Ban, bool, bool){
"Find": ledger.Find,
"Check": ledger.Check,
} {
ban, banned, _ := look(client, now)
if !banned || !ban.Permanent() {
t.Errorf("%s returned %+v and banned %v, want a permanent ban", name, ban, banned)
}
}
}
+16 -38
View File
@@ -1,4 +1,4 @@
// Package bans is the ban ledger: the bans sww makes on the // Package bans is the ban ledger: the bans smallwebwaf makes on the
// netblocks of clients that break a rate limit, a byte limit or the error // netblocks of clients that break a rate limit, a byte limit or the error
// burst, show a clear sign of attack or are listed by the CrowdSec // burst, show a clear sign of attack or are listed by the CrowdSec
// decision list, and // decision list, and
@@ -21,14 +21,14 @@ import (
// The causes of bans. // The causes of bans.
const ( const (
// CauseLimit is a ban sww made for a broken limit. // CauseLimit is a ban smallwebwaf made for a broken limit.
CauseLimit = "limit" CauseLimit = "limit"
// CauseAttack is a ban sww made for a clear sign of attack. // CauseAttack is a ban smallwebwaf made for a clear sign of attack.
CauseAttack = "attack" CauseAttack = "attack"
// CauseAdmin is a ban an admin made, or one sww made that an // CauseAdmin is a ban an admin made, or one smallwebwaf made that an
// admin keeps. It is never dropped. // admin keeps. It is never dropped.
CauseAdmin = "admin" CauseAdmin = "admin"
// CauseCrowdSec is a ban sww made for a client the CrowdSec // CauseCrowdSec is a ban smallwebwaf made for a client the CrowdSec
// decision list lists. It ends when CrowdSec's decision does. // decision list lists. It ends when CrowdSec's decision does.
CauseCrowdSec = "crowdsec" CauseCrowdSec = "crowdsec"
) )
@@ -70,7 +70,7 @@ type Ban struct {
Expires time.Time Expires time.Time
// Cause is CauseLimit, CauseAttack, CauseAdmin or CauseCrowdSec. // Cause is CauseLimit, CauseAttack, CauseAdmin or CauseCrowdSec.
Cause string Cause string
// Reason is a short text: for a ban sww made, the limit broken, // Reason is a short text: for a ban smallwebwaf made, the limit broken,
// the rule that matched or the scenario of CrowdSec's decision; for an // the rule that matched or the scenario of CrowdSec's decision; for an
// admin's, what the admin wrote. // admin's, what the admin wrote.
Reason string Reason string
@@ -123,7 +123,7 @@ type Notes struct {
LimitPercentSetting string `json:"limit_percent_setting,omitempty"` LimitPercentSetting string `json:"limit_percent_setting,omitempty"`
// RuleID and Target are, for a ban for a clear sign of attack, the id // RuleID and Target are, for a ban for a clear sign of attack, the id
// of the rule file rule that matched, and its target; TrapPath is, for // of the rule file rule that matched, and its target; TrapPath is, for
// one for a request for a path in SWW_TRAP_PATHS, that path as the // one for a request for a path in SWWAF_TRAP_PATHS, that path as the
// client sent it. // client sent it.
RuleID string `json:"rule_id,omitempty"` RuleID string `json:"rule_id,omitempty"`
Target string `json:"target,omitempty"` Target string `json:"target,omitempty"`
@@ -199,7 +199,7 @@ type Ledger struct {
// v4Lengths and v6Lengths are the lengths of the IPv4 and IPv6 // v4Lengths and v6Lengths are the lengths of the IPv4 and IPv6
// netblocks that have been banned. Check looks for a ban at each of // netblocks that have been banned. Check looks for a ban at each of
// them, so that a ban read from bans.json refuses every client in its // them, so that a ban read from bans.json refuses every client in its
// netblock even when it was made with another SWW_BAN_SCOPE_V4_PREFIX, // netblock even when it was made with another SWWAF_BAN_SCOPE_V4_PREFIX,
// or another length of an IPv6 client's netblock. // or another length of an IPv6 client's netblock.
v4Lengths, v6Lengths []int v4Lengths, v6Lengths []int
} }
@@ -274,27 +274,16 @@ func (l *Ledger) Find(client netip.Addr, now time.Time) (Ban, bool, bool) {
// activeBan returns the ban in bans, a netblock's bans oldest first, that // activeBan returns the ban in bans, a netblock's bans oldest first, that
// is active at now, or nil when none is. If several are, it returns the // is active at now, or nil when none is. If several are, it returns the
// newest permanent one, or the newest when none is permanent. Every ban is // one that started last. Every ban is looked at, since a ban an admin adds
// looked at, since a ban an admin adds to bans.json can start before the // to bans.json can start before the netblock's others and outlast them.
// netblock's others and outlast them.
func activeBan(bans []Ban, now time.Time) *Ban { func activeBan(bans []Ban, now time.Time) *Ban {
var newest *Ban
for i := len(bans) - 1; i >= 0; i-- { for i := len(bans) - 1; i >= 0; i-- {
if !bans[i].ActiveAt(now) { if bans[i].ActiveAt(now) {
continue
}
if bans[i].Permanent() {
return &bans[i] return &bans[i]
} }
if newest == nil {
newest = &bans[i]
}
} }
return newest return nil
} }
// BanForLimit bans netblock at now for a broken limit, with notes, and // BanForLimit bans netblock at now for a broken limit, with notes, and
@@ -592,7 +581,7 @@ func (l *Ledger) Load(bans []Ban) {
} }
// LoadEdit is Load for an admin's edit of bans.json, taken in while // LoadEdit is Load for an admin's edit of bans.json, taken in while
// sww runs. Each ban in it whose cause is CauseAdmin, and which // smallwebwaf runs. Each ban in it whose cause is CauseAdmin, and which
// the ledger did not hold, with the same netblock and start, is one the // the ledger did not hold, with the same netblock and start, is one the
// admin made, and is counted among the bans made. // admin made, and is counted among the bans made.
func (l *Ledger) LoadEdit(bans []Ban) { func (l *Ledger) LoadEdit(bans []Ban) {
@@ -754,16 +743,13 @@ func (l *Ledger) markChanged() {
} }
// active returns the ban active at now on a netblock client is in, or // active returns the ban active at now on a netblock client is in, or
// nil. If several netblocks have one, it returns a permanent ban when // nil.
// there is one.
func (l *Ledger) active(client netip.Addr, now time.Time) *Ban { func (l *Ledger) active(client netip.Addr, now time.Time) *Ban {
lengths := l.v6Lengths lengths := l.v6Lengths
if client.Is4() { if client.Is4() {
lengths = l.v4Lengths lengths = l.v4Lengths
} }
var first *Ban
for _, length := range lengths { for _, length := range lengths {
bans, found := l.netblocks.Get(netip.PrefixFrom(client, length).Masked()) bans, found := l.netblocks.Get(netip.PrefixFrom(client, length).Masked())
if !found { if !found {
@@ -771,20 +757,12 @@ func (l *Ledger) active(client netip.Addr, now time.Time) *Ban {
} }
ban := activeBan(*bans, now) ban := activeBan(*bans, now)
if ban == nil { if ban != nil {
continue
}
if ban.Permanent() {
return ban return ban
} }
if first == nil {
first = ban
}
} }
return first return nil
} }
// covering returns the bans of each netblock held that client is in, // covering returns the bans of each netblock held that client is in,
+1 -1
View File
@@ -173,7 +173,7 @@ func TestPermanentBanStartedBeforeAnEndedOneRefuses(t *testing.T) {
func TestNextBanWorkedOutFromTheBanThatEndedLast(t *testing.T) { func TestNextBanWorkedOutFromTheBanThatEndedLast(t *testing.T) {
t.Parallel() t.Parallel()
// A 9-hour ban sww made, the third in a row, and an admin's // A 9-hour ban smallwebwaf made, the third in a row, and an admin's
// 1-hour ban added to bans.json over it, with no cause and no notes. // 1-hour ban added to bans.json over it, with no cause and no notes.
netblock := netip.MustParsePrefix("203.0.113.9/32") netblock := netip.MustParsePrefix("203.0.113.9/32")
nineHours := bans.Ban{ nineHours := bans.Ban{
+379 -731
View File
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
-192
View File
@@ -1,192 +0,0 @@
package config
import (
"errors"
"fmt"
"log/slog"
"math"
"net/netip"
"net/url"
"strconv"
"strings"
"time"
)
// RProxy is the settings of `sww rproxy`. A size or time limit of zero
// is off.
type RProxy struct {
// ListenAddr is where rproxy listens (SWRP_LISTEN_ADDR).
ListenAddr string
// UpstreamURL is the app (SWRP_UPSTREAM_URL).
UpstreamURL *url.URL
// TrustedProxies are the netblocks whose X-Forwarded-For is believed
// (SWRP_TRUSTED_PROXIES).
TrustedProxies []netip.Prefix
// WAFBackend is discriminator's URL (SWRP_WAF_BACKEND).
WAFBackend *url.URL
// Timeout is how long rproxy waits for discriminator's answer to a question,
// and to a report (SWRP_TIMEOUT_MS). It cannot be off.
Timeout time.Duration
// DefaultDisposition is what is done with a request when discriminator cannot be
// connected to, does not answer at all, or does not answer within Timeout:
// allow or deny (SWRP_DEFAULT_DISPOSITION).
DefaultDisposition string
// MaxRequestSize is the largest request body (SWRP_MAX_REQUEST_SIZE), and
// MaxResponseSize the largest response body (SWRP_MAX_RESPONSE_SIZE).
MaxRequestSize int64
MaxResponseSize int64
// MaxRequestTime bounds sending the whole request: the visitor's request
// line and headers, and then, from their end, its body on its way to the
// app (SWRP_MAX_REQUEST_TIME_MS). MaxResponseTime bounds the answer, from
// the end of the request to its last byte reaching the visitor
// (SWRP_MAX_RESPONSE_TIME_MS).
MaxRequestTime time.Duration
MaxResponseTime time.Duration
// settings are the values read, as given or by default, for the log line
// at start.
settings []slog.Attr
}
var (
errNeedsWAFBackend = errors.New(
"is required: it is discriminator's URL, such as http://discriminator:8080")
errNotDisposition = errors.New("is not allow or deny")
errNotMilliseconds = errors.New(
"is not a whole number of milliseconds above zero, such as 2000")
errNotMillisecondsOrOff = errors.New(
"is not a whole number of milliseconds above zero, such as 60000, or off")
)
// RProxyFromEnvironment reads rproxy's settings with lookupEnv, normally
// os.LookupEnv. A setting that is not set takes its default, and
// SWRP_WAF_BACKEND, which has none, must be set. A setting that is set but
// invalid is an error that names it. Since rproxy never touches disk, its
// settings have no _FILE form.
func RProxyFromEnvironment(lookupEnv func(string) (string, bool)) (*RProxy, error) {
env := &environment{lookupEnv: withoutFileForms(lookupEnv)}
cfg := &RProxy{
ListenAddr: env.address("SWRP_LISTEN_ADDR"),
UpstreamURL: env.appURL("SWRP_UPSTREAM_URL", defaultUpstreamURL),
TrustedProxies: env.netblocks("SWRP_TRUSTED_PROXIES", privateRanges),
WAFBackend: env.wafBackend("SWRP_WAF_BACKEND"),
Timeout: env.milliseconds("SWRP_TIMEOUT_MS", "2000"),
DefaultDisposition: env.disposition("SWRP_DEFAULT_DISPOSITION", "allow"),
MaxRequestSize: env.size("SWRP_MAX_REQUEST_SIZE", "100M"),
MaxResponseSize: env.size("SWRP_MAX_RESPONSE_SIZE", "1G"),
MaxRequestTime: env.millisecondsOrOff("SWRP_MAX_REQUEST_TIME_MS", "60000"),
MaxResponseTime: env.millisecondsOrOff("SWRP_MAX_RESPONSE_TIME_MS", "1800000"),
}
if env.err != nil {
return nil, env.err
}
cfg.settings = env.settings
return cfg, nil
}
// RProxyListenAddrAndUpstreamURL reads only SWRP_LISTEN_ADDR and
// SWRP_UPSTREAM_URL. The health check in rproxy's container needs no other
// setting, so it reads no other.
func RProxyListenAddrAndUpstreamURL(
lookupEnv func(string) (string, bool),
) (string, *url.URL, error) {
env := &environment{lookupEnv: withoutFileForms(lookupEnv)}
listenAddr := env.address("SWRP_LISTEN_ADDR")
upstreamURL := env.appURL("SWRP_UPSTREAM_URL", defaultUpstreamURL)
if env.err != nil {
return "", nil, env.err
}
return listenAddr, upstreamURL, nil
}
// withoutFileForms returns lookupEnv finding no setting named with _FILE, since
// rproxy never touches disk.
func withoutFileForms(
lookupEnv func(string) (string, bool),
) func(string) (string, bool) {
return func(name string) (string, bool) {
if strings.HasSuffix(name, "_FILE") {
return "", false
}
return lookupEnv(name)
}
}
// LogValue makes an RProxy log as each setting's name with the value it was
// given, or its default.
func (c *RProxy) LogValue() slog.Value {
return slog.GroupValue(c.settings...)
}
// wafBackend reads the setting that is discriminator's URL, which must be set.
func (e *environment) wafBackend(name string) *url.URL {
value := e.value(name, "")
if value == "" {
e.check(name, errNeedsWAFBackend)
return nil
}
backend, err := parseUpstreamURL(value)
e.check(name, err)
return backend
}
// disposition reads the setting that is what is done with a request when discriminator
// cannot be connected to, does not answer at all, or does not answer in time:
// allow or deny.
func (e *environment) disposition(name, defaultValue string) string {
value := e.value(name, defaultValue)
if value != "allow" && value != "deny" {
e.check(name, fmt.Errorf("%q %w", value, errNotDisposition))
}
return value
}
// milliseconds reads a setting that is a whole number of milliseconds above
// zero.
func (e *environment) milliseconds(name, defaultValue string) time.Duration {
value := e.value(name, defaultValue)
duration, valid := parseMilliseconds(value)
if !valid {
e.check(name, fmt.Errorf("%q %w", value, errNotMilliseconds))
}
return duration
}
// millisecondsOrOff reads a setting that is a whole number of milliseconds
// above zero, or off, which is 0.
func (e *environment) millisecondsOrOff(name, defaultValue string) time.Duration {
value := e.value(name, defaultValue)
if value == off {
return 0
}
duration, valid := parseMilliseconds(value)
if !valid {
e.check(name, fmt.Errorf("%q %w", value, errNotMillisecondsOrOff))
}
return duration
}
// parseMilliseconds reads a whole number of milliseconds above zero, and
// reports whether it is one.
func parseMilliseconds(value string) (time.Duration, bool) {
n, err := strconv.ParseInt(value, 10, 64)
if err != nil || n <= 0 || n > math.MaxInt64/int64(time.Millisecond) {
return 0, false
}
return time.Duration(n) * time.Millisecond, true
}
-231
View File
@@ -1,231 +0,0 @@
package config_test
import (
"net/netip"
"os"
"path/filepath"
"slices"
"strings"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/config"
)
// rproxy's settings, by name, and their values in these tests.
const (
wafBackend = "SWRP_WAF_BACKEND"
rproxyTimeout = "SWRP_TIMEOUT_MS"
rproxyDefault = "SWRP_DEFAULT_DISPOSITION"
rproxyListen = "SWRP_LISTEN_ADDR"
rproxyUpstream = "SWRP_UPSTREAM_URL"
rproxyTrusted = "SWRP_TRUSTED_PROXIES"
rproxyMaxRequest = "SWRP_MAX_REQUEST_SIZE"
rproxyMaxResponse = "SWRP_MAX_RESPONSE_SIZE"
rproxyRequestTime = "SWRP_MAX_REQUEST_TIME_MS"
rproxyAnswerTime = "SWRP_MAX_RESPONSE_TIME_MS"
backendURL = "http://discriminator:8080"
rproxyDefaultAddr = ":8080"
rproxyDefaultApp = "http://127.0.0.1:8081"
notASize = "a lot"
)
// rproxyConfig reads rproxy's settings from env.
func rproxyConfig(env map[string]string) (*config.RProxy, error) {
return config.RProxyFromEnvironment(func(name string) (string, bool) {
value, ok := env[name]
return value, ok
})
}
func TestRProxyDefaults(t *testing.T) {
t.Parallel()
cfg, err := rproxyConfig(map[string]string{wafBackend: backendURL})
if err != nil {
t.Fatalf("settings: %v", err)
}
if cfg.ListenAddr != rproxyDefaultAddr ||
cfg.UpstreamURL.String() != rproxyDefaultApp ||
cfg.WAFBackend.String() != backendURL {
t.Errorf("addresses %q, %v, %v", cfg.ListenAddr, cfg.UpstreamURL, cfg.WAFBackend)
}
if cfg.Timeout != 2*time.Second || cfg.DefaultDisposition != "allow" {
t.Errorf("timeout %v, default disposition %q", cfg.Timeout, cfg.DefaultDisposition)
}
if cfg.MaxRequestSize != 100<<20 || cfg.MaxResponseSize != 1<<30 {
t.Errorf("sizes %d and %d", cfg.MaxRequestSize, cfg.MaxResponseSize)
}
if cfg.MaxRequestTime != time.Minute || cfg.MaxResponseTime != 30*time.Minute {
t.Errorf("times %v and %v", cfg.MaxRequestTime, cfg.MaxResponseTime)
}
want := []netip.Prefix{
netip.MustParsePrefix("10.0.0.0/8"),
netip.MustParsePrefix("172.16.0.0/12"),
netip.MustParsePrefix("192.168.0.0/16"),
}
if !slices.Equal(cfg.TrustedProxies, want) {
t.Errorf("trusted proxies %v, want %v", cfg.TrustedProxies, want)
}
}
func TestRProxySettingsAreRead(t *testing.T) {
t.Parallel()
cfg, err := rproxyConfig(map[string]string{
wafBackend: "https://waf.example:8443",
rproxyListen: ":9000",
rproxyUpstream: "http://app:3000",
rproxyTrusted: "192.0.2.0/24",
rproxyTimeout: "150",
rproxyDefault: "deny",
rproxyMaxRequest: "1K",
rproxyMaxResponse: off,
rproxyRequestTime: off,
rproxyAnswerTime: "250",
})
if err != nil {
t.Fatalf("settings: %v", err)
}
if cfg.ListenAddr != ":9000" || cfg.UpstreamURL.Host != "app:3000" ||
cfg.WAFBackend.Host != "waf.example:8443" ||
cfg.TrustedProxies[0] != netip.MustParsePrefix("192.0.2.0/24") {
t.Errorf("addresses %+v", cfg)
}
if cfg.Timeout != 150*time.Millisecond || cfg.DefaultDisposition != "deny" ||
cfg.MaxRequestSize != 1024 || cfg.MaxResponseSize != 0 ||
cfg.MaxRequestTime != 0 || cfg.MaxResponseTime != 250*time.Millisecond {
t.Errorf("limits %+v", cfg)
}
}
func TestRProxyInvalidSettingsAreRefused(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name, value string
}{
{wafBackend, ""},
{wafBackend, "discriminator:8080"},
{wafBackend, "http://discriminator:8080/path"},
{rproxyTimeout, "0"},
{rproxyTimeout, "-1"},
{rproxyTimeout, off},
{rproxyTimeout, "2s"},
{rproxyTimeout, "1.25"},
{rproxyTimeout, "99999999999999999"},
{rproxyDefault, "maybe"},
{rproxyListen, "8080"},
{rproxyUpstream, "app"},
{rproxyUpstream, "127.0.0.1:8081"},
{rproxyUpstream, "ftp://127.0.0.1:8081"},
{rproxyUpstream, "http://"},
{rproxyUpstream, "http://:8081"},
{rproxyUpstream, "http://127.0.0.1:0"},
{rproxyUpstream, "http://127.0.0.1:99999"},
{rproxyUpstream, "http://127.0.0.1:8081/app"},
{rproxyUpstream, "http://127.0.0.1:8081/?a=1"},
{rproxyUpstream, "http://user:secret@127.0.0.1:8081"},
{rproxyTrusted, "not a netblock"},
{rproxyTrusted, "10.0.0.0/33"},
{rproxyTrusted, "10.0.0.0/8,,192.168.0.0/16"},
{rproxyTrusted, "fe80::1%eth0"},
{rproxyMaxRequest, notASize},
{rproxyMaxResponse, notASize},
{rproxyRequestTime, "0"},
{rproxyRequestTime, "1m"},
{rproxyAnswerTime, "0"},
} {
t.Run(tc.name+"="+tc.value, func(t *testing.T) {
t.Parallel()
_, err := rproxyConfig(map[string]string{wafBackend: backendURL, tc.name: tc.value})
if err == nil || !strings.HasPrefix(err.Error(), tc.name+": ") {
t.Errorf("error %v, want one naming %s", err, tc.name)
}
})
}
}
func TestRProxyTrustedProxiesSetButEmptyTrustNothing(t *testing.T) {
t.Parallel()
cfg, err := rproxyConfig(map[string]string{wafBackend: backendURL, rproxyTrusted: ""})
if err != nil {
t.Fatalf("settings: %v", err)
}
if len(cfg.TrustedProxies) != 0 {
t.Errorf("trusted proxies %v, want none", cfg.TrustedProxies)
}
}
func TestRProxyNeedsItsBackend(t *testing.T) {
t.Parallel()
_, err := rproxyConfig(nil)
if err == nil || !strings.HasPrefix(err.Error(), wafBackend+": is required") {
t.Errorf("error %v, want one saying %s is required", err, wafBackend)
}
}
func TestRProxyReadsNoFile(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "backend")
err := os.WriteFile(path, []byte("http://from-a-file:8080\n"), 0o600)
if err != nil {
t.Fatalf("write: %v", err)
}
_, err = rproxyConfig(map[string]string{wafBackend + "_FILE": path})
if err == nil || !strings.HasPrefix(err.Error(), wafBackend+": is required") {
t.Errorf("error %v, want %s still required", err, wafBackend)
}
cfg, err := rproxyConfig(map[string]string{
wafBackend: backendURL,
rproxyTimeout + "_FILE": "/nonexistent/timeout",
})
if err != nil {
t.Fatalf("settings: %v, with the file left unread", err)
}
if cfg.Timeout != 2*time.Second {
t.Errorf("timeout %v, want the default", cfg.Timeout)
}
}
func TestRProxySettingsAreLoggedByName(t *testing.T) {
t.Parallel()
cfg, err := rproxyConfig(map[string]string{wafBackend: backendURL})
if err != nil {
t.Fatalf("settings: %v", err)
}
group := cfg.LogValue().Group()
names := make([]string, 0, len(group))
for _, attr := range group {
names = append(names, attr.Key)
}
for _, name := range []string{
rproxyListen, rproxyUpstream, rproxyTrusted, wafBackend, rproxyTimeout, rproxyDefault,
rproxyMaxRequest, rproxyMaxResponse, rproxyRequestTime, rproxyAnswerTime,
} {
if !slices.Contains(names, name) {
t.Errorf("%s is not logged, only %v", name, names)
}
}
}
-58
View File
@@ -1,58 +0,0 @@
package discriminator
// The heuristic abuseipdb. It reads SWW_ABUSEIPDB_KEY,
// SWW_ABUSEIPDB_MIN_SCORE and SWW_REPUTATION_ACTION.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// 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" }
func (abuseIPDB) check(ctx context.Context, rq *request, _ time.Time) *verdict {
if rq.h.config.AbuseIPDBKey == "" {
return nil
}
client := rq.h.clientGroup(rq.client)
held, _ := rq.h.limiter.Client(client)
offender := held.History.Offences != ratelimit.Offences{}
score, hit := rq.h.abuseIPDB.Hit(ctx, client, rq.client, offender)
if !hit {
return nil
}
rq.abuseIPDBHit = true
rq.addTag(config.AbuseIPDBTag)
rq.noteHit(bans.ReputationHit{Source: reputation.AbuseIPDBSource, Score: &score},
"scored by AbuseIPDB at or over SWW_ABUSEIPDB_MIN_SCORE")
if rq.h.config.ReputationAction != deny {
return nil
}
return &verdict{
action: requestlog.ActionClientDenied,
figures: map[string]any{
figureScore: score, "min_score": rq.h.config.AbuseIPDBMinScore,
},
}
}
-588
View File
@@ -1,588 +0,0 @@
package discriminator_test
import (
"fmt"
"maps"
"net"
"net/http"
"net/http/httptest"
"net/netip"
"slices"
"strconv"
"strings"
"testing"
"testing/synctest"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
const (
// answerTimeLimit is the default of rproxy's SWRP_TIMEOUT_MS, the time
// discriminator has to answer.
answerTimeLimit = 2 * time.Second
// defaultLookupWait is the default of SWW_LOOKUP_TIMEOUT.
defaultLookupWait = 800 * time.Millisecond
// The header limits SPEC.md gives.
cookieLimit = 50
headerFieldLimit = 100
// cookieHeader is the header the cookie limit counts.
cookieHeader = "Cookie"
// tooLarge is how discriminator refuses a request over the header limits.
tooLarge = http.StatusRequestHeaderFieldsTooLarge
// silentAbuseIPDBURL is where AbuseIPDB never answers: at the stand-in
// that unansweredGeoJSURL names too.
silentAbuseIPDBURL = "unanswered://abuseipdb/api/v2/check"
// wholeLimit is the percentage of a rate limit that lowers it not at all.
wholeLimit = 100
// clientsDecision is the CrowdSec decision list holding client alone.
clientsDecision = `[{"duration": "4h0m0s", "scenario": "crowdsecurity/ssh-bf", ` +
`"scope": "Ip", "type": "ban", "value": "` + client + `"}]`
)
// cookies returns a Cookie header's value with count cookies.
func cookies(count int) string {
parts := make([]string, 0, count)
for i := range count {
parts = append(parts, "c"+strconv.Itoa(i)+"=1")
}
return strings.Join(parts, "; ")
}
// fillHeaders adds headers to a question until the checks see total header
// fields: all but ClientHeader and PeerHeader, which discriminator removes. Go's
// client sends nothing else but Host, which the limit does not count, once
// User-Agent is set.
func fillHeaders(req *http.Request, total int) {
req.Header.Set("User-Agent", "test")
for i := len(req.Header) - 2; i < total; i++ {
req.Header.Set("X-Filler-"+strconv.Itoa(i), "1")
}
}
func TestSixteenThousandCookiesAreRefusedWellWithinTheTimeLimit(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{wafMode: block})
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, strings.Repeat("a;", 16000))
began := time.Now()
got := do(t, req)
if took := time.Since(began); took >= answerTimeLimit/2 {
t.Errorf("answered after %s, want well within %s", took, answerTimeLimit)
}
wantDisposition(t, got, tooLarge, discriminator.DispositionDeny)
line := s.out.requestLine(t)
wantLine(t, line, tooLarge, requestlog.ActionRequestHeaderTooLarge)
if line.DurationWAF != nil {
t.Errorf("the Core Rule Set read the request, for %f ms", *line.DurationWAF)
}
}
func TestHeaderLimitRefusalNamesItsHeuristicCountsAndLimits(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", nil)
req := s.question(siteA, client, "/")
fillHeaders(req, headerFieldLimit+1)
do(t, req)
wantHeuristic(t, s.out.requestLine(t), "header_limits",
`{"fields": 101, "fields_limit": 100, "cookies": 0, "cookies_limit": 50}`)
}
func TestEachHeaderLimitRefusesARequestOverIt(t *testing.T) {
t.Parallel()
repeated := make([]string, headerFieldLimit)
for i := range repeated {
repeated[i] = "1"
}
for _, tc := range []struct {
name string
make func(*http.Request)
// refused is true for a request over a limit, and false for one at it.
refused bool
}{
{"cookies at the limit", func(req *http.Request) {
req.Header.Set(cookieHeader, cookies(cookieLimit))
}, false},
{"cookies over the limit", func(req *http.Request) {
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
}, true},
{"parts empty or only spaces and tabs are no cookies", func(req *http.Request) {
req.Header.Set(cookieHeader, cookies(cookieLimit)+"; \t;;")
}, false},
{"parts of no-break spaces count", func(req *http.Request) {
req.Header.Set(cookieHeader, strings.Repeat(" ;", cookieLimit+1))
}, true},
{"cookies over the limit across two headers", func(req *http.Request) {
req.Header[cookieHeader] = []string{cookies(cookieLimit), "last=1"}
}, true},
{"cookies without a value count", func(req *http.Request) {
req.Header.Set(cookieHeader, strings.Repeat("a;", cookieLimit+1))
}, true},
{"header fields at the limit", func(req *http.Request) {
fillHeaders(req, headerFieldLimit)
}, false},
{"header fields over the limit", func(req *http.Request) {
fillHeaders(req, headerFieldLimit+1)
}, true},
{"a header sent many times counts each time", func(req *http.Request) {
req.Header["X-Filler"] = repeated
}, true},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{wafMode: block})
req := s.question(siteA, client, "/")
tc.make(req)
got := do(t, req)
line := s.out.requestLine(t)
if tc.refused {
wantDisposition(t, got, tooLarge, discriminator.DispositionDeny)
wantLine(t, line, tooLarge, requestlog.ActionRequestHeaderTooLarge)
return
}
wantDisposition(t, got, http.StatusOK, discriminator.DispositionAllow)
wantLine(t, line, http.StatusOK, requestlog.ActionForward)
if line.DurationWAF == nil {
t.Error("the Core Rule Set did not read a request within the limits")
}
})
}
}
func TestHeaderLimitsHoldWhateverTheCoreRuleSetSettingsSay(t *testing.T) {
t.Parallel()
for _, env := range []map[string]string{
{wafMode: off},
{wafMode: "detect"},
{wafMode: block, "SWW_WAF_EXEMPT_PATHS": "/"},
} {
t.Run(fmt.Sprint(env), func(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", env)
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
wantDisposition(t, do(t, req), tooLarge, discriminator.DispositionDeny)
})
}
}
func TestClientInTheAllowNetsSkipsTheHeaderLimits(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{wafMode: block, allowNets: client})
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
wantDisposition(t, do(t, req), http.StatusOK, discriminator.DispositionAllow)
}
func TestObserveModeAllowsARequestOverTheHeaderLimitsUnread(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{mode: observe, wafMode: block})
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, strings.Repeat("a;", 16000))
began := time.Now()
got := do(t, req)
if took := time.Since(began); took >= answerTimeLimit/2 {
t.Errorf("answered after %s, want well within %s", took, answerTimeLimit)
}
wantDisposition(t, got, http.StatusOK, discriminator.DispositionAllow)
line := s.out.requestLine(t)
if line.WouldAction != requestlog.ActionRequestHeaderTooLarge ||
line.DurationWAF != nil {
t.Errorf("would_action %q and duration_waf %v, want %q and none",
line.WouldAction, line.DurationWAF, requestlog.ActionRequestHeaderTooLarge)
}
}
func TestRequestsOverTheHeaderLimitsCountTowardTheRateLimits(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{rateLimitPerMinute: "1"})
ask := func() answer {
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
return do(t, req)
}
wantDisposition(t, ask(), tooLarge, discriminator.DispositionDeny)
wantDisposition(t, ask(), http.StatusForbidden, discriminator.DispositionDeny)
lines := s.out.requestLines(t, 2)
wantLine(t, lines[1], http.StatusForbidden, requestlog.ActionClientIsRateLimited)
}
func TestTheHeaderLimitsComeAfterTheTrapPathsAndTheRuleFiles(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name, path, action string
}{
{"a trap path", "/wp-login.php", requestlog.ActionTemporarilyBanned},
{"a block rule", "/blocked", requestlog.ActionBlockedByBlockRule},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
s := startDiscriminator(t, "", map[string]string{
trapPaths: trapPathList, rulesDir: writeRules(t, testRules),
})
req := s.question(siteA, client, tc.path)
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
wantDisposition(t, do(t, req), http.StatusForbidden, discriminator.DispositionDeny)
wantLine(t, s.out.requestLine(t), http.StatusForbidden, tc.action)
})
}
}
func TestNotWaitingForGeoJSNeverLowersAClientsLimit(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s := startDiscriminator(t, geojsURL, map[string]string{
unknownLimitPercent: "0", lookupTimeout: "1h",
})
req := s.question(siteA, fromDE, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
wantDisposition(t, do(t, req), tooLarge, discriminator.DispositionDeny)
line := s.out.requestLine(t)
wantLine(t, line, tooLarge, requestlog.ActionRequestHeaderTooLarge)
if line.LimitPercent != nil {
t.Errorf("limit percentage %d, want none", *line.LimitPercent)
}
// The client is under no ban, and GeoJS places it in a country.
wantDisposition(t, s.ask(fromDE, "/"), http.StatusOK, discriminator.DispositionAllow)
}
func TestAClientGeoJSPlacedInNoCountryCountsAsUnknownWithoutWaiting(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s := startDiscriminator(t, geojsURL, map[string]string{unknownLimitPercent: "0"})
s.server.GeoJS.Load([]lookup.Answer{{
Client: netip.MustParsePrefix(client + "/32"), ASN: "AS64512",
Answered: s.clock.Now(), Used: s.clock.Now(),
}})
req := s.question(siteA, client, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
wantDisposition(t, do(t, req), http.StatusForbidden, discriminator.DispositionDeny)
wantLine(t, s.out.requestLine(t), http.StatusForbidden,
requestlog.ActionClientIsRateLimited)
}
func TestObserveModeWaitsForGeoJSForARequestOverTheHeaderLimits(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s := startDiscriminator(t, geojsURL, map[string]string{
mode: observe, addLookupHeaders: on, lookupTimeout: "1h",
})
req := s.question(siteA, fromDE, "/")
req.Header.Set(cookieHeader, cookies(cookieLimit+1))
got := do(t, req)
wantDisposition(t, got, http.StatusOK, discriminator.DispositionAllow)
asn, country := got.header.Get("X-Client-Asn"), got.header.Get("X-Client-Country")
if asn != asnDE || country != "DE" {
t.Errorf("answered with the AS number %q and the country %q, want %q and DE",
asn, country, asnDE)
}
}
// newDiscriminatorInBubble makes a discriminator for a synctest bubble: GeoJS never
// answers, a setting needs its answer, and everything is at its default but
// for env. No request to it may use the network.
func newDiscriminatorInBubble(
t *testing.T, env map[string]string,
) (*discriminator.Server, *output) {
t.Helper()
settings := map[string]string{tagDeny: "country=KP"}
maps.Copy(settings, env)
server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, settings)
return server, out
}
// askDirectly hands a question about a request from client straight to server,
// as change leaves it, and returns the answer's status and how long it took.
func askDirectly(
t *testing.T, server *discriminator.Server, change func(*http.Request),
) (int, time.Duration) {
t.Helper()
req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", http.NoBody)
req.RemoteAddr = net.JoinHostPort(rproxyPeer, "1234")
req.Header.Set(discriminator.ClientHeader, client)
req.Header.Set(requestIDHeader, "the-id")
change(req)
recorder := httptest.NewRecorder()
began := time.Now()
server.Handler.ServeHTTP(recorder, req)
return recorder.Code, time.Since(began)
}
// banClient bans client at now.
func banClient(_ *testing.T, server *discriminator.Server, now time.Time) {
server.Ledger.BanForLimit(netip.MustParsePrefix(client+"/32"), now, bans.Notes{})
}
// countClient counts one request from client at now for the rate limits.
func countClient(_ *testing.T, server *discriminator.Server, now time.Time) {
server.Limiter.Count(netip.MustParsePrefix(client+"/32"), now, wholeLimit)
}
// listClient puts client on the blocklist at dropURL.
func listClient(t *testing.T, server *discriminator.Server, now time.Time) {
t.Helper()
err := server.Lists.Load([]reputation.List{{
URL: dropURL, Tried: now, Fetched: now, Lines: []string{client},
}})
if err != nil {
t.Fatalf("load the blocklist: %v", err)
}
}
// decideOnClient puts client on the CrowdSec decision list.
func decideOnClient(t *testing.T, server *discriminator.Server, now time.Time) {
t.Helper()
loadDecisions(t, server, now, clientsDecision)
}
// leaveAsItIs prepares nothing.
func leaveAsItIs(*testing.T, *discriminator.Server, time.Time) {}
func TestARefusedRequestDoesNotWaitForASlowGeoJS(t *testing.T) {
t.Parallel()
const forbidden = http.StatusForbidden
for _, tc := range []struct {
name string
env map[string]string
// prepare gets the server ready, at now, before the question.
prepare func(t *testing.T, server *discriminator.Server, now time.Time)
// cookie is the request's Cookie header.
cookie string
status int
action string
}{
{
name: "SWW_DENY_NETS", env: map[string]string{denyNets: client},
prepare: leaveAsItIs, status: forbidden, action: requestlog.ActionClientDenied,
},
{
name: "a ban",
prepare: banClient, status: forbidden, action: requestlog.ActionTemporarilyBanned,
},
{
name: "the rate limits", env: map[string]string{rateLimitPerMinute: "1"},
prepare: countClient, status: forbidden,
action: requestlog.ActionClientIsRateLimited,
},
{
name: "the rate limits, with a biased threshold",
env: map[string]string{rateLimitPerMinute: "1", unknownLimitPercent: "50"},
prepare: countClient, status: forbidden,
action: requestlog.ActionClientIsRateLimited,
},
{
name: "a blocklist", env: map[string]string{blocklistURLs: dropURL},
prepare: listClient, status: forbidden, action: requestlog.ActionClientDenied,
},
{
name: "the CrowdSec decision list",
env: map[string]string{crowdSecURL: lapi, crowdSecKey: bouncerKey},
prepare: decideOnClient, status: forbidden,
action: requestlog.ActionTemporarilyBanned,
},
{
name: "the header limits", cookie: cookies(cookieLimit + 1),
prepare: leaveAsItIs, status: tooLarge,
action: requestlog.ActionRequestHeaderTooLarge,
},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
// In a synctest bubble, as TestRequestWaitsAsLongAsTheLookupTimeoutSays
// says, so that a request that does not wait takes no time at all.
synctest.Test(t, func(t *testing.T) {
server, out := newDiscriminatorInBubble(t, tc.env)
tc.prepare(t, server, time.Now())
status, took := askDirectly(t, server, func(req *http.Request) {
req.Header.Set(cookieHeader, tc.cookie)
})
if status != tc.status || took != 0 {
t.Errorf("answered %d after %s, want %d at once; output:\n%s",
status, took, tc.status, out.text())
}
wantLine(t, out.requestLine(t), tc.status, tc.action)
// GeoJS's request is abandoned before the bubble ends.
time.Sleep(defaultLookupWait)
})
})
}
}
func TestAQuestionWaitsForASlowGeoJSOnlyAsLongAsTheDefaultSays(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name string
env map[string]string
// prepare gets the server ready, at now, before the question.
prepare func(t *testing.T, server *discriminator.Server, now time.Time)
status int
action string
}{
{"nothing refuses it", nil, leaveAsItIs, http.StatusOK, requestlog.ActionForward},
{
"a country list needs the answer", map[string]string{allowedCountries: "DE"},
leaveAsItIs, http.StatusForbidden, requestlog.ActionCountryDenied,
},
{
"a blocklist that only logs",
map[string]string{blocklistURLs: dropURL, blocklistAction: actionLog},
listClient, http.StatusOK, requestlog.ActionForward,
},
{
"a blocklist that only limits",
map[string]string{blocklistURLs: dropURL, blocklistAction: limitQuarter},
listClient, http.StatusOK, requestlog.ActionForward,
},
{
"over a rate limit on an exempt path",
map[string]string{rateLimitPerMinute: "1", rateLimitExemptPaths: "/"},
countClient, http.StatusOK, requestlog.ActionForward,
},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
server, out := newDiscriminatorInBubble(t, tc.env)
tc.prepare(t, server, time.Now())
status, took := askDirectly(t, server, func(*http.Request) {})
if status != tc.status || took != defaultLookupWait {
t.Errorf("answered %d after %s, want %d after %s; output:\n%s",
status, took, tc.status, defaultLookupWait, out.text())
}
wantLine(t, out.requestLine(t), tc.status, tc.action)
})
})
}
}
func TestDiscriminatorAnswersWithinTheTimeLimitWhileEveryOutsideSourceHangs(
t *testing.T,
) {
t.Parallel()
held, askedGeoJS, _ := startHeldGeoJS(t)
// A resolver that takes every query and answers none.
resolver, err := (&net.ListenConfig{}).ListenPacket(t.Context(), "udp", localhost+":0")
if err != nil {
t.Fatalf("listen: %v", err)
}
t.Cleanup(func() { _ = resolver.Close() })
server, out, _ := newDiscriminatorWith(t, func(
params discriminator.Params,
) *discriminator.Server {
params.AbuseIPDBURL = silentAbuseIPDBURL
return discriminator.New(params)
}, held, time.Now, map[string]string{
tagDeny: "country=KP", wafMode: block,
dnsblZones: dnsblZone, dnsblResolver: resolver.LocalAddr().String(),
abuseIPDBKey: accountKey,
blocklistURLs: held + "/drop.txt", asnLimitPercentURL: held + "/asn.txt",
crowdSecURL: held, crowdSecKey: bouncerKey,
})
// AbuseIPDB is asked only about a client with an offence.
group := netip.MustParsePrefix(client + "/32")
server.Limiter.AddToHistory(group, time.Now(), ratelimit.Request{Attack: true})
go server.Lists.Run(t.Context())
status, took := askDirectly(t, server, func(req *http.Request) {
req.Header.Set("User-Agent", "test")
req.Header.Set("Accept", "*/*")
req.Host = siteA
})
if status != http.StatusOK || took >= answerTimeLimit {
t.Errorf("answered %d after %s, want %d within %s; output:\n%s",
status, took, http.StatusOK, answerTimeLimit, out.text())
}
// Each outside source was asked, and none has answered. The stand-in for
// GeoJS is the lists' too, which name no address.
if !slices.Contains(askedGeoJS(), client) {
t.Errorf("GeoJS was asked about %q, not %s", askedGeoJS(), client)
}
if queries := server.DNSBL.Queries(dnsblZone); queries != 1 {
t.Errorf("%d queries to the DNS blocklist, want 1", queries)
}
if checked := server.AbuseIPDB.Checked(); checked != 1 {
t.Errorf("%d checks with AbuseIPDB, want 1", checked)
}
}
-41
View File
@@ -1,41 +0,0 @@
package discriminator
// The heuristic blocklists. It reads SWW_BLOCKLIST_ACTION, and the blocklists
// through the reputation lists.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// blocklists notes the blocklists that list the client, as noteListed does,
// and refuses the request when SWW_BLOCKLIST_ACTION is deny. Being limit, it
// lowers the client's limits instead (see limitPercentages), and being log, it
// does nothing more. Its figure is the blocklists that list the client.
type blocklists struct{}
func (blocklists) name() string { return "blocklists" }
func (blocklists) check(_ context.Context, rq *request, _ time.Time) *verdict {
listedBy := rq.h.lists.ListedBy(rq.client)
rq.blocklisted = len(listedBy) > 0
rq.noteListed(listedBy, "listed by a blocklist")
if !rq.refusedByBlocklists(listedBy) {
return nil
}
return &verdict{
action: requestlog.ActionClientDenied,
figures: map[string]any{"lists": listedBy},
}
}
// refusedByBlocklists reports whether the heuristic blocklists refuses a
// client, given listedBy, the blocklists that list it: it does when one lists
// it and SWW_BLOCKLIST_ACTION is deny.
func (rq *request) refusedByBlocklists(listedBy []string) bool {
return len(listedBy) > 0 && rq.h.config.BlocklistAction == deny
}
-41
View File
@@ -1,41 +0,0 @@
package discriminator
// The heuristic byte_limits. It reads SWW_BYTES_COUNT, and the byte limits
// and biased thresholds through the limiter and limitPercentages.
import (
"context"
"time"
)
// byteLimits counts the request's bytes, as countedBytes gives them, for the
// byte limits, once its report has come, and notes the client's byte totals for
// the log line; its requests stay there as the rate limits counted them. Only
// an allowed request has them counted, and only one the rate limits counted; in
// observe mode, not one that enforce mode would have refused. Bytes that take
// the client over a byte limit, as its limit percentage for the byte limits
// lowers it, break it, which bans the client; the response was passed on whole.
// Its figures are the window, the count and the limit.
type byteLimits struct{}
func (byteLimits) name() string { return "byte_limits" }
func (byteLimits) check(_ context.Context, rq *request, now time.Time) *verdict {
if !rq.counted || rq.line.WouldAction != "" {
return nil
}
counts, hit, over := rq.h.limiter.CountBytes(rq.h.clientGroup(rq.client), now,
rq.countedBytes(), rq.bytesPercent.percent)
rq.line.Counts.MinuteBytes = counts.MinuteBytes
rq.line.Counts.HourBytes = counts.HourBytes
rq.line.Counts.DayBytes = counts.DayBytes
if !over {
return nil
}
rq.banForLimit(now, hit, rq.out.status)
return &verdict{figures: limitFigures(hit)}
}
-62
View File
@@ -1,62 +0,0 @@
package discriminator
import (
"crypto/rand"
"net/http"
"net/netip"
"slices"
)
// peerAddress is the address of the request's TCP peer.
func peerAddress(r *http.Request) netip.Addr {
addrPort, err := netip.ParseAddrPort(r.RemoteAddr)
if err != nil {
return netip.Addr{}
}
return addrPort.Addr().Unmap()
}
// requestIDHeader carries the request's id, from rproxy.
const requestIDHeader = "X-Request-ID"
// requestID is the request's id: the one a question gives, or for any other
// request a new random one.
func requestID(r *http.Request, isQuestion bool) string {
if isQuestion {
return r.Header.Get(requestIDHeader)
}
return rand.Text()
}
// scheme is how the visitor reached rproxy, or the trusted proxy in front of
// it, as a question says in X-Forwarded-Proto, or otherwise http.
func scheme(r *http.Request, isQuestion bool) string {
proto := r.Header.Get("X-Forwarded-Proto")
if !isQuestion || proto == "" {
return "http"
}
return proto
}
// clientGroup is the client a request is counted toward: its IPv4
// address, or its IPv6 group, the netblock its IPv6 address is in of the
// length SWW_IPV6_GROUP_PREFIX sets, a /64 by default, since one abuser
// usually holds a whole /64. An IPv4 address in IPv6 form counts as IPv4.
func (h *handler) clientGroup(addr netip.Addr) netip.Prefix {
addr = addr.Unmap()
if addr.Is6() {
return netip.PrefixFrom(addr, h.config.IPv6GroupPrefix).Masked()
}
return netip.PrefixFrom(addr, addr.BitLen())
}
// isInside reports whether addr is in one of the netblocks.
func isInside(addr netip.Addr, netblocks []netip.Prefix) bool {
return slices.ContainsFunc(netblocks, func(netblock netip.Prefix) bool {
return netblock.Contains(addr)
})
}
-100
View File
@@ -1,100 +0,0 @@
package discriminator
// The heuristic core_rule_set. It reads SWW_WAF_MODE, SWW_WAF_EXEMPT_PATHS
// and SWW_WAF_ANOMALY_THRESHOLD.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/waf"
)
// coreRuleSet inspects the request with the Core Rule Set, unless
// 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 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" }
func (coreRuleSet) check(_ context.Context, rq *request, _ time.Time) *verdict {
cfg := rq.h.config
if cfg.WAFMode == config.WAFModeOff || pathExempt(rq.in, cfg.WAFExemptPaths) {
return nil
}
start := time.Now()
// A question's body has been read into memory, so that reading it here
// cannot fail.
result, read, _ := rq.h.coreRuleSet.Inspect(rq.in, rq.client, rq.in.Body)
rq.requestBytes = int64(len(read))
rq.line.DurationWAF = new(requestlog.Milliseconds(time.Since(start)))
rq.line.WAFRuleIDs = result.RuleIDs
rq.line.WAFScore = &result.Score
for _, id := range result.RuleIDs {
rq.h.metrics.WAFMatched(cfg.WAFMode, id)
}
threshold := cfg.WAFAnomalyThreshold
if threshold == 0 || result.Score < threshold {
return nil
}
rq.addTag(config.ExploitSignatureTag)
rq.alertWAFBlock(result)
if cfg.WAFMode == config.WAFModeDetect {
return nil
}
rq.wafBlocked = true
return &verdict{
action: requestlog.ActionWAFBlocked,
figures: map[string]any{figureScore: result.Score, "threshold": threshold},
}
}
// alertWAFBlock raises the waf_block alert for the request, which the Core
// Rule Set scored at result, at or over SWW_WAF_ANOMALY_THRESHOLD. Its
// detail gives the rule ids, the score, the method and the path with the
// query, and, for a request that is not refused for it, the mode: detect,
// or observe in observe mode.
func (rq *request) alertWAFBlock(result waf.Result) {
detail := map[string]any{
"rule_ids": result.RuleIDs,
"score": result.Score,
"method": rq.in.Method,
"path": rq.in.URL.RequestURI(),
}
switch {
case rq.h.config.WAFMode == config.WAFModeDetect:
detail["mode"] = config.WAFModeDetect
case rq.h.config.Observe:
detail["mode"] = "observe"
}
rq.h.alerts.Raise(alerts.Alert{
Event: alerts.EventWAFBlock,
Host: rq.site,
Client: rq.client,
Netblock: rq.h.clientGroup(rq.client),
ASN: rq.line.ASN,
ASName: rq.line.ASName,
Country: rq.line.Country,
Reason: "scored by the Core Rule Set at or over SWW_WAF_ANOMALY_THRESHOLD",
Detail: detail,
})
}
-35
View File
@@ -1,35 +0,0 @@
package discriminator
// The heuristic countries. It reads SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
import (
"context"
"slices"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// 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 {
allowed := rq.h.config.ExclusivelyAllowedCountries
country := rq.line.Country
if len(allowed) == 0 || slices.Contains(allowed, country) {
return nil
}
return &verdict{
action: requestlog.ActionCountryDenied,
figures: map[string]any{
"country": country, "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES",
},
}
}
-50
View File
@@ -1,50 +0,0 @@
package discriminator
// The heuristic crowdsec. It reads SWW_CROWDSEC_LAPI_URL, and the decisions
// through the reputation lists.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// crowdSec refuses a request when a decision of the CrowdSec decision list on
// 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" }
func (crowdSec) check(_ context.Context, rq *request, now time.Time) *verdict {
decision, listed := rq.crowdSecDecisionInForce(now)
if !listed {
return nil
}
rq.addTag(config.CrowdSecTag)
rq.noteHit(bans.ReputationHit{Source: rq.h.config.CrowdSecDecisionsURL},
"listed by the CrowdSec decision list")
return &verdict{
action: rq.banForCrowdSec(now, decision),
figures: map[string]any{
"scenario": decision.Scenario,
"expires": requestlog.FormatTime(decision.Expires),
},
}
}
// crowdSecDecisionInForce returns the decision of the CrowdSec decision list on
// the client that is in force at now, and reports whether there is one, which
// the heuristic crowdsec refuses the request for.
func (rq *request) crowdSecDecisionInForce(
now time.Time,
) (reputation.Decision, bool) {
return rq.h.lists.CrowdSecDecision(rq.client, now)
}
-29
View File
@@ -1,29 +0,0 @@
package discriminator
// The heuristic deny_nets. It reads SWW_DENY_NETS.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// denyNets refuses a client in SWW_DENY_NETS. Its figure is the netblock of
// the setting the client is in.
type denyNets struct{}
func (denyNets) name() string { return "deny_nets" }
func (denyNets) check(_ context.Context, rq *request, _ time.Time) *verdict {
for _, netblock := range rq.h.config.DenyNets {
if netblock.Contains(rq.client) {
return &verdict{
action: requestlog.ActionClientDenied,
figures: map[string]any{figureNetblock: netblock.String()},
}
}
}
return nil
}
-477
View File
@@ -1,477 +0,0 @@
package discriminator
import (
"bytes"
"context"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
"net/http"
"net/netip"
"strconv"
"strings"
"time"
"unicode/utf8"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// The headers of rproxy's question and of discriminator's answer, as
// "discriminator" in SPEC.md gives them.
const (
// ClientHeader marks a request as rproxy's question, and gives the
// visitor's address.
ClientHeader = "X-Sww-Client"
// PeerHeader gives the address of rproxy's own TCP peer.
PeerHeader = "X-Sww-Peer"
// ContentLengthHeader gives the body length the visitor announced.
ContentLengthHeader = "X-Sww-Content-Length"
// DispositionHeader gives discriminator's answer.
DispositionHeader = "X-Sww-Disposition"
)
// The values of DispositionHeader.
const (
// DispositionAllow tells rproxy to pass the request to the app.
DispositionAllow = "allow"
// DispositionDeny tells rproxy to give the visitor the answer's status,
// headers and body.
DispositionDeny = "deny"
// DispositionClose tells rproxy to close the visitor's connection
// without an answer, which SWW_BAN_RESPONSE asks for when it is close.
// discriminator closing the question's connection instead would read as
// discriminator being down, and rproxy would then let the request through.
DispositionClose = "close"
)
// ReportPath is where rproxy sends the report of each request discriminator
// answered.
const ReportPath = "/_sww/report"
// QuestionBodyMaxBytes is the most of a visitor's body a question carries.
const QuestionBodyMaxBytes = 64 << 10
const (
// maxAwaitingReport is the most answered requests held until their
// reports come. Past it, the request answered longest ago is dropped.
maxAwaitingReport = 10000
// maxRequestIDBytes is the longest id a question may give.
maxRequestIDBytes = 128
// reportBodyMaxBytes is the most of a report's body that is read. It is
// far above any report's.
reportBodyMaxBytes = 1 << 20
// maxHTTPStatus is the highest status a report may give.
maxHTTPStatus = 599
// maxReportedBytes is the most bytes a report may give for each way, 1
// PiB, so that adding them up cannot overflow.
maxReportedBytes = 1 << 50
// maxReportedMilliseconds is the longest duration a report may give,
// about 31 years, so that it fits a time.Duration.
maxReportedMilliseconds = 1e12
// discriminatorTimeout bounds how long a request to discriminator takes to
// arrive, and its answer to leave, and discriminatorIdleTimeout how long a
// kept-open connection waits for its next request.
discriminatorTimeout = 60 * time.Second
discriminatorIdleTimeout = 120 * time.Second
)
var (
errReportFieldMissing = errors.New("a field is missing")
errReportValue = errors.New("a value is out of range")
)
// Report is the JSON object rproxy posts to ReportPath once the visitor's
// answer has ended, its fields named as the request log's of the same
// meaning. RequestID is the question's id. Status is what the visitor got, 0
// if nothing. The durations are in milliseconds.
//
//nolint:tagliatelle // docs/request-log.md names the fields in snake_case
type Report struct {
RequestID string `json:"request_id"`
Status int `json:"status"`
RequestBytes int64 `json:"request_bytes"`
ResponseBytes int64 `json:"response_bytes"`
DurationTotal float64 `json:"duration_total"`
DurationUpstreamTotal float64 `json:"duration_upstream_total"`
}
// New returns the server `sww discriminator` runs. It answers
// rproxy's questions, takes rproxy's reports and answers its own endpoints. It
// passes nothing to an app. rproxy applies the size and time limits to the
// visitor. Go's default limit on a request's line and headers, 1 MiB, stays: it
// is far above rproxy's, and a question refused for its size would have rproxy
// let the request through.
func New(params Params) *Server {
h := newHandler(params)
return &Server{
Server: &http.Server{
Addr: params.Config.ListenAddr,
Handler: h,
ErrorLog: slog.NewLogLogger(params.ProcessLog.Handler(), slog.LevelWarn),
ReadTimeout: discriminatorTimeout,
WriteTimeout: discriminatorTimeout,
IdleTimeout: discriminatorIdleTimeout,
},
Ledger: h.ledger,
Limiter: h.limiter,
GeoJS: h.geojs,
Anomalies: h.anomalies,
LookupFile: h.lookupFile,
Lists: h.lists,
DNSBL: h.dnsbl,
AbuseIPDB: h.abuseIPDB,
RouteWatch: h.routeWatch,
Metrics: h.metrics,
}
}
// ServeHTTP handles one request to discriminator: a request carrying
// ClientHeader is rproxy's question, and any other is for discriminator
// itself.
func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
if len(r.Header.Values(ClientHeader)) > 0 {
h.answerQuestion(w, r)
return
}
h.answerOwnEndpoint(w, r)
}
// refusedWhateverTheAnswer reports whether the request is one that does not wait
// for GeoJS, since the checks will refuse it at now whatever GeoJS answers about
// its client: the heuristic crowdsec, header_limits, blocklists or rate_limits
// will refuse it, as a function in that heuristic's file says. In observe mode,
// which refuses nothing, none is. rproxy lets a request through when
// discriminator answers too late.
func (rq *request) refusedWhateverTheAnswer(now time.Time) bool {
if rq.h.config.Observe {
return false
}
_, decided := rq.crowdSecDecisionInForce(now)
return decided || overHeaderLimits(rq.headerCounts()) ||
rq.refusedByBlocklists(rq.h.lists.ListedBy(rq.client)) ||
rq.overAWholeRateLimit(now)
}
// answerQuestion runs the checks on the visitor's request a question
// carries, and answers rproxy what to do with it. A denied request's counting
// is finished here, and an allowed one's by its report.
func (h *handler) answerQuestion(w http.ResponseWriter, r *http.Request) {
client, body, ok := h.readQuestion(w, r)
if !ok {
return
}
// One that cannot be read leaves the log line's peer_ip invalid.
peer, _ := netip.ParseAddr(r.Header.Get(PeerHeader))
rq := h.startRequest(w, asTheVisitorSentIt(r, body), client.Unmap(), peer.Unmap(),
true)
// The last deferred runs first, so that what is held has the finished log
// line. Go's server sends the answer only once this function has
// returned, so the report cannot come before it is held.
defer rq.holdForReport()
defer rq.finish()
rq.site = r.Host
rq.line.DiscriminatorLine = requestlog.DiscriminatorLineDecision
refused := rq.check(r.Context())
rq.checked = time.Now()
underOwnPrefix := strings.HasPrefix(r.URL.Path, adminPrefix)
if refused == nil && !underOwnPrefix {
// In observe mode, what enforce mode would have refused counts here.
defer rq.runAfterAnswer(r.Context())
rq.allow()
return
}
// The last deferred runs first: runAfterAnswer before addToHistory, so that
// a broken refusal limit is in the client's history.
defer rq.addToHistory()
defer rq.countAnomalies()
defer rq.runAfterAnswer(r.Context())
if refused != nil {
rq.deny(*refused)
return
}
// The app never sees this prefix. discriminator's own endpoints are at its
// own address, so this answers as a path with no endpoint does.
rq.line.Action = requestlog.ActionAdmin
rq.out.Header().Set(DispositionHeader, DispositionDeny)
http.Error(rq.out, http.StatusText(http.StatusNotFound), http.StatusNotFound)
}
// readQuestion returns the visitor's address and the body a question carries,
// and whether discriminator takes the question. It answers a question it does not
// take with 400 and no disposition, which rproxy treats as it treats no
// answer. The id of a question it takes is held from here on, without a
// decision yet, so that another question with that id is refused while this
// one is being handled.
//
// The body is read before any check, since Go's server does not send an answer
// until it has read the body. A question whose body stops arriving gets no
// answer, and is not looked at.
func (h *handler) readQuestion(
w http.ResponseWriter, r *http.Request,
) (netip.Addr, []byte, bool) {
client, err := netip.ParseAddr(r.Header.Get(ClientHeader))
if err != nil || client.Zone() != "" {
h.refuseQuestion(w, ClientHeader+" is not an address without a zone")
return netip.Addr{}, nil, false
}
id := r.Header.Get(requestIDHeader)
if id == "" || len(id) > maxRequestIDBytes || !utf8.ValidString(id) {
h.refuseQuestion(w, requestIDHeader+" is not a valid id")
return netip.Addr{}, nil, false
}
body, err := io.ReadAll(http.MaxBytesReader(w, r.Body, QuestionBodyMaxBytes))
if _, tooLarge := errors.AsType[*http.MaxBytesError](err); tooLarge {
h.refuseQuestion(w, "the body is over 64 KiB")
return netip.Addr{}, nil, false
}
if err != nil {
h.processLog.Warn("a question's body stopped arriving", "error", err.Error())
// This panic has Go's server close the connection without an answer,
// and log nothing.
panic(http.ErrAbortHandler)
}
held, _ := h.awaitingReport.ContainsOrAdd(id, nil)
if held {
h.refuseQuestion(w, requestIDHeader+" is the id of a request discriminator holds")
return netip.Addr{}, nil, false
}
return client, body, true
}
// refuseQuestion answers a question discriminator does not take, for reason.
func (h *handler) refuseQuestion(w http.ResponseWriter, reason string) {
h.processLog.Warn("a question is refused", "reason", reason)
http.Error(w, reason, http.StatusBadRequest)
}
// asTheVisitorSentIt returns a copy of r, a question, as the checks and the
// log line are to see it: without the headers rproxy adds for discriminator,
// with body, which has been read of r, and with the length the visitor
// announced, as -1 when it announced none. The question's own length covers
// only the part of the body it carries.
func asTheVisitorSentIt(r *http.Request, body []byte) *http.Request {
sent := r.Clone(r.Context())
announced := sent.Header.Get(ContentLengthHeader)
sent.Header.Del(ClientHeader)
sent.Header.Del(PeerHeader)
sent.Header.Del(ContentLengthHeader)
sent.Header.Del("Content-Length")
sent.ContentLength = -1
length, err := strconv.ParseInt(announced, 10, 64)
if err == nil && length >= 0 {
sent.ContentLength = length
sent.Header.Set("Content-Length", announced)
}
sent.Body = http.NoBody
if len(body) > 0 {
sent.Body = io.NopCloser(bytes.NewReader(body))
}
return sent
}
// allow answers a question with DispositionAllow and, while
// SWW_ADD_LOOKUP_HEADERS is set, the client's AS number and country.
func (rq *request) allow() {
rq.allowed = true
header := rq.out.Header()
header.Set(DispositionHeader, DispositionAllow)
if rq.h.config.AddLookupHeaders {
setLookupHeaders(header, rq.line.ASN, rq.line.Country)
}
rq.out.WriteHeader(http.StatusOK)
}
// holdForReport holds a copy of what the report's steps need, by the request's
// id. A report only ever reaches that copy, never the request being handled.
func (rq *request) holdForReport() {
held := rq.decision
rq.h.awaitingReport.Add(rq.line.RequestID, &held)
}
// deny answers a question with what the visitor is to get for r.
func (rq *request) deny(r refusal) {
rq.refused = &r
if r.status == 0 {
// SWW_BAN_RESPONSE is close. Written past rq.out, since the log line's
// status stays 0: the visitor is sent nothing.
rq.out.Header().Set(DispositionHeader, DispositionClose)
rq.out.ResponseWriter.WriteHeader(http.StatusOK)
return
}
rq.out.Header().Set(DispositionHeader, DispositionDeny)
http.Error(rq.out, http.StatusText(r.status), r.status)
}
// answerOwnEndpoint answers a request to discriminator's own address. No check
// runs on it: the address is on the private network, where the peers are
// rproxy and the admin's tools, not visitors.
func (h *handler) answerOwnEndpoint(w http.ResponseWriter, r *http.Request) {
if r.Method == http.MethodPost && r.URL.Path == ReportPath {
h.takeReport(w, r)
return
}
peer := peerAddress(r)
rq := h.startRequest(w, r, peer, peer, false)
defer rq.finish()
if r.Method == http.MethodGet && r.URL.Path == HealthPath {
rq.answerHealth()
return
}
rq.answerAdmin()
}
// takeReport answers POST ReportPath: it finishes the request the report
// names, if it holds that request's decision, and ignores the report
// otherwise.
func (h *handler) takeReport(w http.ResponseWriter, r *http.Request) {
report, err := readReport(w, r)
if err != nil {
h.processLog.Warn("a report is refused", "error", err.Error())
http.Error(w, "the body is not a report", http.StatusBadRequest)
return
}
held, found := h.awaitingReport.Peek(report.RequestID)
// Remove reports true to one report only, of several that name the id. A
// question still being handled is held as nil.
if found && held != nil && h.awaitingReport.Remove(report.RequestID) {
h.finishWith(r.Context(), held, report)
}
w.WriteHeader(http.StatusNoContent)
}
// readReport reads a report from r's body, which must be one JSON object with
// all of Report's fields, in the ranges SPEC.md gives.
func readReport(w http.ResponseWriter, r *http.Request) (Report, error) {
var report Report
body, err := io.ReadAll(http.MaxBytesReader(w, r.Body, reportBodyMaxBytes))
if err != nil {
return report, fmt.Errorf("read the body: %w", err)
}
var fields map[string]json.RawMessage
err = json.Unmarshal(body, &fields)
if err != nil {
return report, fmt.Errorf("decode the body: %w", err)
}
for _, name := range []string{
"request_id", "status", "request_bytes", "response_bytes",
"duration_total", "duration_upstream_total",
} {
value, there := fields[name]
if !there || string(value) == "null" {
return report, fmt.Errorf("%w: %s", errReportFieldMissing, name)
}
}
err = json.Unmarshal(body, &report)
if err != nil {
return report, fmt.Errorf("decode the body: %w", err)
}
return report, report.checkRanges()
}
// checkRanges returns an error for a value of the report that cannot be true.
func (report *Report) checkRanges() error {
switch {
case report.Status != 0 &&
(report.Status < http.StatusContinue || report.Status > maxHTTPStatus):
return fmt.Errorf("%w: status", errReportValue)
case report.RequestBytes < 0 || report.RequestBytes > maxReportedBytes:
return fmt.Errorf("%w: request_bytes", errReportValue)
case report.ResponseBytes < 0 || report.ResponseBytes > maxReportedBytes:
return fmt.Errorf("%w: response_bytes", errReportValue)
case report.DurationTotal < 0 || report.DurationTotal > maxReportedMilliseconds:
return fmt.Errorf("%w: duration_total", errReportValue)
case report.DurationUpstreamTotal < 0 ||
report.DurationUpstreamTotal > maxReportedMilliseconds:
return fmt.Errorf("%w: duration_upstream_total", errReportValue)
}
return nil
}
// finishWith finishes a request with what its report says, and writes the
// request's last log line, which holds its decision's fields and the report's.
// For an allowed request it first runs the heuristics of onReport, and adds the
// request to its client's history, the anomaly counters and the metrics, with
// the status and bytes the report gives. A denied request's counting was
// finished at its decision. ctx is the report's own context.
func (h *handler) finishWith(ctx context.Context, held *decision, report Report) {
rq := &request{
decision: *held,
h: h,
out: &responseWriter{status: report.Status, bytes: report.ResponseBytes},
requestBytes: report.RequestBytes,
}
rq.line.DiscriminatorLine = requestlog.DiscriminatorLineReport
rq.line.Status = report.Status
rq.line.RequestBytes = report.RequestBytes
rq.line.ResponseBytes = report.ResponseBytes
rq.line.DurationTotal = report.DurationTotal
if rq.allowed {
rq.line.DurationUpstreamTotal = &report.DurationUpstreamTotal
rq.runBanningHeuristics(ctx, onReport())
rq.countAnomalies()
rq.addToHistory()
rq.h.metrics.RequestReported(&rq.line,
time.Duration(report.DurationTotal*float64(time.Millisecond)),
time.Duration(report.DurationUpstreamTotal*float64(time.Millisecond)))
}
rq.writeLine()
}
File diff suppressed because it is too large. Load diff
-43
View File
@@ -1,43 +0,0 @@
package discriminator
// The heuristic dnsbl. It reads SWW_REPUTATION_ACTION, and the DNSBL zones'
// verdicts through the DNSBL checker.
import (
"context"
"strings"
"time"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// dnsbl notes the DNSBL zones whose verdict lists the client, as noteListed
// 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
// answer. Its figure is the zones that list the client, their keys masked.
type dnsbl struct{}
func (dnsbl) name() string { return "dnsbl" }
func (dnsbl) check(ctx context.Context, rq *request, _ time.Time) *verdict {
listedBy := rq.h.dnsbl.ListedBy(ctx, rq.client)
rq.dnsblListed = len(listedBy) > 0
rq.noteListed(listedBy, "listed by a DNSBL zone")
for _, zone := range listedBy {
rq.addTag(config.DNSBLTagPrefix + strings.ToLower(zone))
}
if !rq.dnsblListed || rq.h.config.ReputationAction != deny {
return nil
}
return &verdict{
action: requestlog.ActionClientDenied,
figures: map[string]any{"zones": listedBy},
}
}
-71
View File
@@ -1,71 +0,0 @@
package discriminator
// The heuristic header_limits. It reads no setting: its limits are fixed.
import (
"context"
"strings"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// The header limits: the most cookies and header fields a request may have
// when the checks reach the Core Rule Set. Real clients never reach them.
const (
maxCookies = 50
maxHeaderFields = 100
)
// headerLimits refuses a request over the header limits, with 431. Its figures
// are the request's header fields and cookies, and the limit of each.
type headerLimits struct{}
func (headerLimits) name() string { return "header_limits" }
func (headerLimits) check(_ context.Context, rq *request, _ time.Time) *verdict {
fields, cookies := rq.headerCounts()
if !overHeaderLimits(fields, cookies) {
return nil
}
return &verdict{
action: requestlog.ActionRequestHeaderTooLarge,
figures: map[string]any{
"fields": fields, "fields_limit": maxHeaderFields,
"cookies": cookies, "cookies_limit": maxCookies,
},
}
}
// overHeaderLimits reports whether a request with these counts of header fields
// and cookies, as headerCounts counts them, is over the header limits: it has
// more than maxHeaderFields fields or more than maxCookies cookies.
func overHeaderLimits(fields, cookies int) bool {
return fields > maxHeaderFields || cookies > maxCookies
}
// headerCounts returns the request's header fields, each value of a header sent
// twice being one, and its cookies, each part of a Cookie header between
// semicolons being one unless it is empty or only spaces and tabs. The Core
// Rule Set runs each of its rules on each cookie, so that thousands of small
// cookies keep it busy for over a second. It trims only spaces and control
// characters, of which a header value can hold only tabs, so a part of Unicode
// spaces is a cookie to it.
func (rq *request) headerCounts() (int, int) {
fields, cookies := 0, 0
for _, values := range rq.in.Header {
fields += len(values)
}
for _, value := range rq.in.Header.Values("Cookie") {
for part := range strings.SplitSeq(value, ";") {
if strings.Trim(part, " \t") != "" {
cookies++
}
}
}
return fields, cookies
}
-40
View File
@@ -1,40 +0,0 @@
package discriminator_test
import (
"net/http"
"testing"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
func TestHealthEndpointCountsTowardNoLimit(t *testing.T) {
t.Parallel()
// With a limit of one request a minute, any request counted before
// the last one would have it refused.
s, _, _ := startWithClock(t, "", map[string]string{rateLimitPerMinute: "1"})
const (
healthChecks = 3
contentType = "text/plain; charset=utf-8"
)
for range healthChecks {
got := s.adminRequest("", http.MethodGet, discriminator.HealthPath, "", http.StatusOK)
if string(got.body) != "ok\n" || got.header.Get("Content-Type") != contentType {
t.Errorf("health endpoint answered %q with Content-Type %q, want ok "+
"with %q", got.body, got.header.Get("Content-Type"), contentType)
}
}
s.get(client, http.StatusOK, requestlog.ActionForward)
for _, line := range s.out.endedLines(t, healthChecks)[:healthChecks] {
if line.ResponseContentType != contentType {
t.Errorf("health check's log line has response_content_type %q, "+
"want %q", line.ResponseContentType, contentType)
}
}
}
-140
View File
@@ -1,140 +0,0 @@
package discriminator
import (
"context"
"time"
)
// To add a heuristic, write one file with a type that implements heuristic,
// and add one line for it to one of the lists below. Its settings go in
// config.Config, and the comment at the top of its file names them.
// heuristic is one of the checks that decide what discriminator does with a
// request.
type heuristic interface {
// name is the heuristic's name, which the log line gives.
name() string
// check looks at the request at now, and returns nil to let it through.
// ctx is the request's own context.
check(ctx context.Context, rq *request, now time.Time) *verdict
}
// verdict is a heuristic refusing a request, or banning its client: the action
// the log line names, one of requestlog's Action constants, and the figures the
// heuristic acted on, by name, such as the count and the limit.
type verdict struct {
action string
figures map[string]any
}
// The names of the figures that more than one heuristic gives.
const (
figureWindow = "window"
figureCount = "count"
figureLimit = "limit"
figureScore = "score"
figureNetblock = "netblock"
)
// The lists of heuristics, each in the order its heuristics run. A client in
// SWW_ALLOW_NETS skips them all.
// beforeLookup are the heuristics that run before the client's AS number and
// country are looked up, so that a client they refuse is not looked up.
func beforeLookup() []heuristic {
return []heuristic{
tagLists{},
routeWatchTags{},
denyNets{},
activeBan{},
}
}
// 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{
countries{},
blocklists{},
crowdSec{},
dnsbl{},
abuseIPDB{},
tagDeny{},
rateLimits{},
trapPaths{},
ruleFiles{},
headerLimits{},
coreRuleSet{},
tagDeny{},
}
}
// afterAnswer are the heuristics that run on a request once discriminator has
// answered it, before its decision line is written. They ban the client, and do
// not change what the request got: their verdict's action is not used.
func afterAnswer() []heuristic {
return []heuristic{
refusalLimit{},
}
}
// onReport are the heuristics that run on an allowed request when rproxy's
// report of it comes, before its report line is written. Like afterAnswer, they
// only ban.
func onReport() []heuristic {
return []heuristic{
byteLimits{},
}
}
// runAfterAnswer runs the heuristics of afterAnswer on the request, at the time
// it is called.
func (rq *request) runAfterAnswer(ctx context.Context) {
rq.runBanningHeuristics(ctx, afterAnswer())
}
// runHeuristics runs list, beforeLookup or afterLookup, on the request at now,
// and returns the first verdict, or nil when none gives one. The log line's
// heuristic and heuristic_figures name the heuristic that gave it, and give its
// figures. ctx is the request's own context.
func (rq *request) runHeuristics(
ctx context.Context, list []heuristic, now time.Time,
) *verdict {
name, v := rq.firstVerdict(ctx, list, now)
if v != nil {
rq.line.Heuristic = name
rq.line.HeuristicFigures = v.figures
}
return v
}
// runBanningHeuristics runs list, afterAnswer or onReport, on the request at
// the time it is called. The log line's after_answer_heuristic and
// after_answer_heuristic_figures name the heuristic that gave a verdict, and
// give its figures, so that heuristic and heuristic_figures still name the one
// that refused the request. ctx is the request's own context.
func (rq *request) runBanningHeuristics(ctx context.Context, list []heuristic) {
name, v := rq.firstVerdict(ctx, list, rq.h.now())
if v != nil {
rq.line.AfterAnswerHeuristic = name
rq.line.AfterAnswerHeuristicFigures = v.figures
}
}
// firstVerdict runs list on the request at now, in order, until a heuristic
// gives a verdict, and returns that heuristic's name and its verdict, or "" and
// nil when none gives one. ctx is the request's own context.
func (rq *request) firstVerdict(
ctx context.Context, list []heuristic, now time.Time,
) (string, *verdict) {
for _, each := range list {
v := each.check(ctx, rq, now)
if v != nil {
return each.name(), v
}
}
return "", nil
}
-109
View File
@@ -1,109 +0,0 @@
package discriminator
import (
"context"
"net/http"
"net/netip"
"strings"
"time"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/lookup"
)
// The headers in which an answer of allow gives rproxy the client's AS number
// and country, for the app, while SWW_ADD_LOOKUP_HEADERS is set. Go writes
// every header name in this form, as it sends it and as it receives it, so
// X-Client-ASN arrives as X-Client-Asn; header names are not case-sensitive.
const (
asnHeader = "X-Client-Asn"
countryHeader = "X-Client-Country"
)
// lookUp looks up the client's AS number and country, in the lookup
// 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
// country list or a biased threshold, a new client's request waits for it,
// unless refusedWhateverTheAnswer reports true. ctx is the request's own
// context.
func (rq *request) lookUp(ctx context.Context, now time.Time) {
if rq.h.config.LookupSource == "off" || !canBePlaced(rq.client) {
return
}
client := rq.h.clientGroup(rq.client)
switch {
case rq.h.config.LookupSource == "file":
rq.lookupAnswer = rq.h.lookupFile.LookUp(client)
case rq.refusedWhateverTheAnswer(now):
rq.lookupAnswer = rq.h.geojs.LookUpWithoutWaiting(ctx, client)
rq.skippedLookupWait = rq.lookupAnswer.Answered.IsZero()
default:
rq.lookupAnswer = rq.h.geojs.LookUp(ctx, client)
}
rq.lookedUp = true
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 config.ASNTagPrefix + 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 config.CountryTagPrefix + country
}
// addLookup adds answer, an answer about a client from the lookup
// database or GeoJS, to the client's history, and to the notes of the bans
// on its netblock that have no AS number, AS name or country yet.
func (h *handler) addLookup(answer lookup.Answer) {
h.limiter.AddLookup(answer.Client, answer.Answered,
answer.ASN, answer.ASName, answer.Country)
h.ledger.AddLookup(h.netblock(answer.Client.Addr()),
answer.ASN, answer.ASName, answer.Country)
}
// setLookupHeaders sets the headers that give the client's AS number and
// country, leaving out one that is unknown.
func setLookupHeaders(header http.Header, asn, country string) {
if asn != "" {
header.Set(asnHeader, asn)
}
if country != "" {
header.Set(countryHeader, country)
}
}
// canBePlaced reports whether a lookup can place addr: private, loopback
// and link-local addresses have no AS number or country.
func canBePlaced(addr netip.Addr) bool {
return !addr.IsPrivate() && !addr.IsLoopback() && !addr.IsLinkLocalUnicast()
}
-432
View File
@@ -1,432 +0,0 @@
package discriminator_test
import (
"io"
"net/http"
"net/http/httptest"
"net/netip"
"strconv"
"strings"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
const (
metricsToken = "SWW_METRICS_TOKEN" //nolint:gosec // the setting's name
metricsTopN = "SWW_METRICS_TOP_N"
// token is the SWW_METRICS_TOKEN the tests set, and bearer how a
// request carries it.
token = "0123456789abcdef0123456789abcdef"
bearer = "Bearer " + token
)
func TestMetricsAreOffWhileTheTokenIsUnset(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", nil)
// An empty token does not match the unset one either.
for _, authorization := range []string{bearer, "Bearer ", ""} {
s.adminRequest(authorization, http.MethodGet, discriminator.MetricsPath, "",
http.StatusNotFound)
}
}
func TestMetricsNeedTheTokenAndOtherPathsAreNotFound(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{metricsToken: token})
for _, tc := range []struct {
method, path, authorization string
status int
}{
{http.MethodGet, discriminator.MetricsPath, "", http.StatusUnauthorized},
{
http.MethodGet, discriminator.MetricsPath, "Bearer " + strings.ToUpper(token),
http.StatusUnauthorized,
},
{http.MethodGet, discriminator.MetricsPath, "Basic " + token,
http.StatusUnauthorized},
{http.MethodGet, discriminator.MetricsPath, bearer, http.StatusOK},
{http.MethodGet, discriminator.MetricsPath, "bearer " + token, http.StatusOK},
{http.MethodPost, discriminator.MetricsPath, bearer, http.StatusNotFound},
{http.MethodGet, discriminator.MetricsPath + "/", bearer, http.StatusNotFound},
{http.MethodGet, "/_sww/bans", bearer, http.StatusNotFound},
{http.MethodPost, discriminator.HealthPath, "", http.StatusNotFound},
} {
got := s.adminRequest(tc.authorization, tc.method, tc.path, "", tc.status)
if tc.status == http.StatusUnauthorized &&
got.header.Get("WWW-Authenticate") != "Bearer" {
t.Errorf("%q was answered without WWW-Authenticate: Bearer",
tc.authorization)
}
if tc.status == http.StatusOK &&
!strings.Contains(string(got.body), "# TYPE sww_requests_total counter") {
t.Errorf("the metrics are\n%s", got.body)
}
}
}
func TestMetricsCountTheTraffic(t *testing.T) {
t.Parallel()
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
_, _ = io.Copy(io.Discard, r.Body)
_, _ = io.WriteString(w, "hello")
})
addr, out, server := startProxyWithClock(t, app.URL, "", time.Now,
map[string]string{metricsToken: token})
got := do(t, newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc")))
wantStatus(t, got, http.StatusOK)
wantStatus(t, get(t, addr, "/_sww/nothing"), http.StatusNotFound)
out.endedLines(t, 2)
forward := `{action="forward",instance="app",status_class="2xx"}`
notFound := `{action="admin",instance="app",status_class="4xx"}`
// The request for the metrics is itself under way.
metrics := scrape(t, server.Addr)
wantMetric(t, metrics, "sww_requests_total"+forward, 1)
wantMetric(t, metrics, "sww_requests_total"+notFound, 1)
wantMetric(t, metrics, "sww_request_bytes_total"+forward, 3)
wantMetric(t, metrics, "sww_response_bytes_total"+forward, 5)
wantMetric(t, metrics, "sww_response_bytes_total"+notFound,
float64(len("Not Found\n")))
wantMetric(t, metrics,
`sww_request_duration_seconds_count{instance="app"}`, 2)
wantMetric(t, metrics,
`sww_upstream_duration_seconds_count{instance="app"}`, 1)
wantMetric(t, metrics, `sww_requests_in_flight{instance="app"}`, 1)
metric(t, metrics, `go_goroutines{instance="app"}`)
metric(t, metrics, `process_start_time_seconds{instance="app"}`)
}
func TestMetricsCountLimitsAndBans(t *testing.T) {
t.Parallel()
const denied = "192.0.2.50" // in SWW_DENY_NETS
s, clk, _ := startWithClock(t, "", map[string]string{
metricsToken: token,
rateLimitPerMinute: "1",
denyNets: denied,
banResponse: banResponseClose,
limitBanDuration: "1h",
maxBanDuration: "2h",
})
// SWW_BAN_RESPONSE=close sends no status at all.
s.get(denied, 0, requestlog.ActionClientDenied)
// A first broken limit bans for an hour.
s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, 0, requestlog.ActionClientIsRateLimited)
metrics := s.scrape()
wantMetric(t, metrics,
`sww_requests_total{action="client_denied",instance="app",status_class="none"}`, 1)
wantMetric(t, metrics, `sww_rate_limit_hits_total{instance="app",`+
`kind="requests",window="minute"}`, 1)
wantMetric(t, metrics, `sww_offences_total{instance="app",kind="limit"}`, 1)
wantMetric(t, metrics, `sww_bans_made_total{cause="limit",instance="app"}`, 1)
wantMetric(t, metrics, `sww_active_bans{instance="app"}`, 1)
wantMetric(t, metrics, `sww_permanent_bans{instance="app"}`, 0)
clk.advance(time.Hour)
wantMetric(t, s.scrape(), `sww_active_bans{instance="app"}`, 0)
// A limit broken again right after would ban for three hours, longer
// than SWW_MAX_BAN_DURATION, so the ban is permanent.
s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, 0, requestlog.ActionClientIsRateLimited)
metrics = s.scrape()
wantMetric(t, metrics, `sww_rate_limit_hits_total{instance="app",`+
`kind="requests",window="minute"}`, 2)
wantMetric(t, metrics, `sww_offences_total{instance="app",kind="limit"}`, 2)
wantMetric(t, metrics, `sww_bans_made_total{cause="limit",instance="app"}`, 2)
wantMetric(t, metrics, `sww_active_bans{instance="app"}`, 1)
wantMetric(t, metrics, `sww_permanent_bans{instance="app"}`, 1)
// denied and client.
wantMetric(t, metrics, `sww_tracked_clients{instance="app"}`, 2)
}
func TestMetricsCountTheBansAnAdminMakes(t *testing.T) {
t.Parallel()
s, clk, server := startWithClock(t, "", map[string]string{
metricsToken: token,
adminToken: adminSecret,
})
const admins = `sww_bans_made_total{cause="admin",instance="app"}`
wantMetric(t, s.scrape(), admins, 0)
// As an admin's edit of bans.json that adds a ban is taken in.
server.Ledger.LoadEdit([]bans.Ban{{
Netblock: netip.MustParsePrefix(client + "/32"),
Start: clk.Now(),
}})
wantMetric(t, s.scrape(), admins, 1)
// And a ban made through the endpoint.
s.admin(http.MethodPost, discriminator.BansPath, banOtherClient, http.StatusOK)
wantMetric(t, s.scrape(), admins, 2)
}
func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
t.Parallel()
const fromFR = "198.51.100.20"
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
_, _ = io.Copy(io.Discard, r.Body)
_, _ = io.WriteString(w, "hello")
})
env := map[string]string{
trustedProxies: trustLocalhost,
metricsToken: token,
metricsTopN: "2",
allowedCountries: "de,fr",
}
geojsURL, _ := startGeoJS(t)
addr, out, server := startProxyWithClock(t, app.URL, geojsURL, time.Now, env)
// The answers are kept before the requests, so that none waits for
// GeoJS.
server.GeoJS.Load([]lookup.Answer{
keptAnswer(fromKP, "KP"), keptAnswer(fromDE, "DE"), keptAnswer(fromFR, "FR"),
})
lines := 0
send := func(from string, times, status int) {
t.Helper()
for range times {
req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc"))
req.Header.Set(forwardedFor, from)
wantStatus(t, do(t, req), status)
// Each is counted before the next is sent, so that the
// countries are ranked in the order sent.
lines++
out.endedLines(t, lines)
}
}
// With two countries of their own, the third is counted as other.
send(fromKP, 3, http.StatusForbidden)
send(fromDE, 2, http.StatusOK)
send(fromFR, 1, http.StatusOK)
metrics := scrape(t, server.Addr)
lines++
wantMetric(t, metrics,
`sww_country_requests_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`sww_country_requests_total{country="DE",instance="app"}`, 2)
wantMetric(t, metrics,
`sww_country_requests_total{country="other",instance="app"}`, 1)
wantMetric(t, metrics,
`sww_country_list_refusals_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`sww_country_request_bytes_total{country="KP",instance="app"}`, 0)
wantMetric(t, metrics,
`sww_country_request_bytes_total{country="DE",instance="app"}`, 6)
wantMetric(t, metrics,
`sww_country_response_bytes_total{country="KP",instance="app"}`,
float64(3*len("Forbidden\n")))
wantMetric(t, metrics,
`sww_country_response_bytes_total{country="other",instance="app"}`,
float64(len("hello")))
wantNoSeries(t, metrics,
`sww_country_requests_total{country="FR",instance="app"}`)
// Once FR is busier than DE, it takes DE's place: its series counts
// from then on, and DE's is gone.
send(fromFR, 3, http.StatusOK)
metrics = scrape(t, server.Addr)
wantMetric(t, metrics,
`sww_country_requests_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`sww_country_requests_total{country="FR",instance="app"}`, 2)
wantMetric(t, metrics,
`sww_country_requests_total{country="other",instance="app"}`, 2)
wantNoSeries(t, metrics,
`sww_country_requests_total{country="DE",instance="app"}`)
wantNoSeries(t, metrics,
`sww_country_request_bytes_total{country="DE",instance="app"}`)
}
func TestMetricsByASNumberKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s, clk, server := startWithClock(t, geojsURL, map[string]string{
metricsToken: token,
metricsTopN: "1",
})
// The answers are kept before the requests, so that GeoJS gives none
// of its own. Each client is in an AS of its own.
answer := func(addr, asn string) lookup.Answer {
return lookup.Answer{
Client: netip.MustParsePrefix(addr + "/32"), ASN: asn,
Answered: clk.Now(), Used: clk.Now(),
}
}
server.GeoJS.Load([]lookup.Answer{
answer(fromDE, "AS64501"), answer(fromKP, "AS64502"),
})
// With one AS number of its own, the other is counted as other.
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromKP, http.StatusOK, requestlog.ActionForward)
metrics := s.scrape()
wantMetric(t, metrics,
`sww_asn_requests_total{asn="AS64501",instance="app"}`, 2)
wantMetric(t, metrics,
`sww_asn_requests_total{asn="other",instance="app"}`, 1)
wantMetric(t, metrics,
`sww_asn_request_bytes_total{asn="AS64501",instance="app"}`, 0)
wantMetric(t, metrics,
`sww_asn_response_bytes_total{asn="other",instance="app"}`, 0)
wantNoSeries(t, metrics,
`sww_asn_requests_total{asn="AS64502",instance="app"}`)
}
func TestMetricsCountGeoJSRequestsAndFailures(t *testing.T) {
t.Parallel()
geojs := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusServiceUnavailable)
}))
t.Cleanup(geojs.Close)
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,
tagDeny: denyKP,
})
// 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)
// The client stops waiting for GeoJS once SWW_LOOKUP_TIMEOUT is up, so
// GeoJS's failure can come after its request has ended.
deadline := time.Now().Add(waitLimit)
metrics := scrape(t, server.Addr)
for metric(t, metrics, `sww_geojs_failures_total{instance="app"}`) == 0 &&
time.Now().Before(deadline) {
time.Sleep(pollInterval)
metrics = scrape(t, server.Addr)
}
wantMetric(t, metrics, `sww_geojs_requests_total{instance="app"}`, 1)
wantMetric(t, metrics, `sww_geojs_failures_total{instance="app"}`, 1)
wantMetric(t, metrics, `sww_geojs_unanswered_total{instance="app"}`, 1)
}
// keptAnswer returns GeoJS's answer that the client at addr is in
// country, given now.
func keptAnswer(addr, country string) lookup.Answer {
now := time.Now()
return lookup.Answer{
Client: netip.MustParsePrefix(addr + "/32"), Country: country,
Answered: now, Used: now,
}
}
// scrape asks discriminator at addr for the metrics, with the token, and returns
// them.
func scrape(t *testing.T, addr string) string {
t.Helper()
req := newRequest(t, http.MethodGet, addr, discriminator.MetricsPath, http.NoBody)
req.Header.Set("Authorization", bearer)
got := do(t, req)
if got.status != http.StatusOK {
t.Fatalf("the metrics were answered %d", got.status)
}
return string(got.body)
}
// scrape asks for the metrics, with the token, and returns them.
func (s *sender) scrape() string {
s.t.Helper()
return string(s.adminRequest(bearer, http.MethodGet, discriminator.MetricsPath, "",
http.StatusOK).body)
}
// metric returns the value of series in metrics, which are in the
// Prometheus text format. series is a name and its labels in the order of
// their names, such as
// sww_offences_total{instance="app",kind="limit"}. It fails the
// test if there is no such series.
func metric(t *testing.T, metrics, series string) float64 {
t.Helper()
for line := range strings.Lines(metrics) {
value, found := strings.CutPrefix(strings.TrimSuffix(line, "\n"), series+" ")
if !found {
continue
}
number, err := strconv.ParseFloat(value, 64)
if err != nil {
t.Fatalf("%s has the value %q", series, value)
}
return number
}
t.Fatalf("no series %s in the metrics:\n%s", series, metrics)
return 0
}
// wantMetric checks the value of series in metrics, as metric reads it.
func wantMetric(t *testing.T, metrics, series string, want float64) {
t.Helper()
got := metric(t, metrics, series)
if got != want {
t.Errorf("%s is %v, want %v", series, got, want)
}
}
// wantNoSeries checks that metrics have no series series.
func wantNoSeries(t *testing.T, metrics, series string) {
t.Helper()
if strings.Contains(metrics, "\n"+series+" ") {
t.Errorf("there is a series %s", series)
}
}
-274
View File
@@ -1,274 +0,0 @@
// Package discriminator is the server the discriminator command runs. It answers
// rproxy's questions, takes rproxy's reports and answers its own endpoints, and
// writes a log line for each.
package discriminator
import (
"fmt"
"io"
"log/slog"
"net/http"
"time"
lru "github.com/hashicorp/golang-lru/v2"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/anomaly"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"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/routewatch"
"sneak.berlin/go/smallwebwaf/internal/rules"
"sneak.berlin/go/smallwebwaf/internal/waf"
)
// adminPrefix starts the path of each of discriminator's own endpoints. The app never
// sees a path under it.
const adminPrefix = "/_sww/"
// HealthPath is the health endpoint of discriminator and of rproxy, which the
// container's health check asks.
const HealthPath = "/_sww/healthz"
// MetricsPath is where the metrics are, for a request that carries
// SWW_METRICS_TOKEN.
const MetricsPath = "/_sww/metrics"
// BansPath is where an admin lists and adds bans, and, followed by / and
// a client's address, lifts them, with SWW_ADMIN_TOKEN.
const BansPath = "/_sww/bans"
// ClientsPath is where an admin asks what discriminator knows of a client, by
// the client's address after it, with SWW_ADMIN_TOKEN.
const ClientsPath = "/_sww/clients/"
// Params are what New needs.
type Params struct {
Config *config.Config
// RequestLog receives two JSON lines per question, one at its decision and
// one when its report comes, and one per request to discriminator's own
// endpoints.
RequestLog io.Writer
// ProcessLog receives the process's own messages.
ProcessLog *slog.Logger
// GeoJSURL is where clients' AS numbers and countries are looked up
// while SWW_LOOKUP_SOURCE is geojs, normally lookup.URL.
GeoJSURL string
// AbuseIPDBURL is where clients are checked with AbuseIPDB while
// SWW_ABUSEIPDB_KEY is set, normally reputation.AbuseIPDBURL.
AbuseIPDBURL string
// LookupFile is the lookup database they are looked up in while
// SWW_LOOKUP_SOURCE is file, and nil otherwise.
LookupFile *lookup.File
// CoreRuleSet is what NewCoreRuleSet returns: what inspects requests
// while SWW_WAF_MODE is not off, and nil while it is.
CoreRuleSet *waf.CoreRuleSet
// Now tells the time by which requests are counted for the rate
// limits, bans are made and run out, and GeoJS's answers are kept,
// normally time.Now in UTC, the time the state files give.
Now func() time.Time
// Rules are the rule files' rules, which each request is checked
// against.
Rules *rules.Files
// Alerts receive the alert for each ban discriminator makes or makes
// permanent, for each count over an anomaly threshold, for each request
// whose client a blocklist, the CrowdSec decision list, a DNSBL zone or
// AbuseIPDB lists, for each request the Core Rule Set scores at or over
// SWW_WAF_ANOMALY_THRESHOLD, and for GeoJS failing, a fetch of a list
// failing, a query to a DNSBL zone or a check with AbuseIPDB failing,
// or the day's AbuseIPDB checks used up.
Alerts *alerts.Queue
}
// Server is the server discriminator runs, with the parts whose state the state
// files keep, the lookup database, nil unless SWW_LOOKUP_SOURCE is file, the
// lists fetched from URLs, which its Run fetches, the DNSBL zones' verdicts,
// AbuseIPDB's scores and checks spent, and the metrics. RouteWatch, nil while
// SWW_ROUTEWATCH_URL is unset, keeps its answers in memory only.
type Server struct {
*http.Server
Ledger *bans.Ledger
Limiter *ratelimit.Limiter
GeoJS *lookup.GeoJS
Anomalies *anomaly.Counters
LookupFile *lookup.File
Lists *reputation.Lists
DNSBL *reputation.DNSBL
AbuseIPDB *reputation.AbuseIPDB
RouteWatch *routewatch.Client
Metrics *metrics.Metrics
}
// newHandler returns the handler with what every request shares, as the
// settings in params make it.
func newHandler(params Params) *handler {
m := metrics.New(params.Config.MetricsTopN, params.Config.InstanceName)
lists, dnsbl, abuseIPDB := newReputation(params, m)
awaitingReport, err := lru.New[string, *decision](maxAwaitingReport)
if err != nil {
panic(err) // New fails only for a size below one
}
h := &handler{
config: params.Config,
requestLog: params.RequestLog,
processLog: params.ProcessLog,
now: params.Now,
metrics: m,
awaitingReport: awaitingReport,
limiter: ratelimit.New(ratelimit.Limits{
PerMinute: params.Config.RateLimitPerMinute,
PerHour: params.Config.RateLimitPerHour,
PerDay: params.Config.RateLimitPerDay,
BytesPerMinute: params.Config.BytesLimitPerMinute,
BytesPerHour: params.Config.BytesLimitPerHour,
BytesPerDay: params.Config.BytesLimitPerDay,
}, params.Config.MaxTrackedClients),
ledger: bans.New(bans.Rules{
LimitBanDuration: params.Config.LimitBanDuration,
LimitBanRepeatWindow: params.Config.LimitBanRepeatWindow,
MaxBanDuration: params.Config.MaxBanDuration,
AttackBanDuration: params.Config.AttackBanDuration,
MaxBans: params.Config.MaxBans,
}),
anomalies: anomaly.New(anomaly.Params{
Client: params.Config.AnomalyClient,
Net: params.Config.AnomalyNet,
ASN: params.Config.AnomalyASN,
Total: params.Config.AnomalyTotal,
Watch: params.Config.AnomalyWatch,
NetV4Prefix: params.Config.AnomalyNetV4Prefix,
NetV6Prefix: params.Config.AnomalyNetV6Prefix,
NamedNetblocks: params.Config.WatchNets,
Alerts: params.Alerts,
}),
lookupFile: params.LookupFile,
lists: lists,
dnsbl: dnsbl,
abuseIPDB: abuseIPDB,
rules: params.Rules,
coreRuleSet: params.CoreRuleSet,
alerts: params.Alerts,
}
if params.Config.RouteWatchURL != "" {
h.routeWatch = routewatch.New(routewatch.Params{
URL: params.Config.RouteWatchURL, Now: params.Now, ProcessLog: params.ProcessLog,
})
}
h.geojs = lookup.New(lookup.Params{
URL: params.GeoJSURL,
Timeout: params.Config.LookupTimeout,
// 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,
Metrics: m,
Alerts: params.Alerts,
})
m.AddBansAndClients(h.ledger, h.limiter, params.Now)
m.AddRules(params.Rules)
return h
}
// newReputation returns the lists fetched from URLs, the DNSBL zones'
// verdicts and AbuseIPDB's scores, as the settings in params name them,
// with none fetched, asked for or checked yet, and adds their metrics to
// m, AbuseIPDB's while SWW_ABUSEIPDB_KEY is set.
func newReputation(
params Params, m *metrics.Metrics,
) (*reputation.Lists, *reputation.DNSBL, *reputation.AbuseIPDB) {
cfg := params.Config
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,
})
dnsbl := reputation.NewDNSBL(reputation.DNSBLParams{
Zones: cfg.DNSBLZones, Resolver: cfg.DNSBLResolver, CacheTTL: cfg.ReputationCacheTTL,
Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
Alerts: params.Alerts,
})
abuseIPDB := reputation.NewAbuseIPDB(reputation.AbuseIPDBParams{
URL: params.AbuseIPDBURL, Key: cfg.AbuseIPDBKey, MinScore: cfg.AbuseIPDBMinScore,
DailyBudget: cfg.AbuseIPDBDailyBudget, CacheTTL: cfg.ReputationCacheTTL,
Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
Alerts: params.Alerts,
})
m.AddReputation(lists, dnsbl)
if cfg.AbuseIPDBKey != "" {
m.AddAbuseIPDB(abuseIPDB)
}
return lists, dnsbl, abuseIPDB
}
// NewCoreRuleSet returns the Core Rule Set at SWW_WAF_PARANOIA_LEVEL,
// without the rules SWW_WAF_DISABLED_RULES switches off, reading bodies
// up to SWW_WAF_BODY_LIMIT, with the exclusions in
// SWW_CORE_RULE_SET_EXCLUSIONS_FILE, or nil while SWW_WAF_MODE is off. It
// reads at most QuestionBodyMaxBytes less one byte: a question's body of
// QuestionBodyMaxBytes may be cut short, and the Core Rule Set does not read a
// JSON or XML body over its limit. An exclusions file that waf.New refuses is
// an error in every mode. While the mode is off, a set file is loaded with the
// Core Rule Set only to check it.
func NewCoreRuleSet(cfg *config.Config) (*waf.CoreRuleSet, error) {
if cfg.WAFMode == config.WAFModeOff && cfg.CoreRuleSetExclusionsFile == "" {
return nil, nil //nolint:nilnil // off is no Core Rule Set, and no error
}
coreRuleSet, err := waf.New(waf.Params{
ParanoiaLevel: cfg.WAFParanoiaLevel, DisabledRules: cfg.WAFDisabledRules,
BodyLimit: min(cfg.WAFBodyLimit, QuestionBodyMaxBytes-1),
ExclusionsFile: cfg.CoreRuleSetExclusionsFile,
})
if err != nil {
return nil, fmt.Errorf("SWW_CORE_RULE_SET_EXCLUSIONS_FILE: %w", err)
}
if cfg.WAFMode == config.WAFModeOff {
return nil, nil //nolint:nilnil // off is no Core Rule Set, and no error
}
return coreRuleSet, nil
}
// handler is discriminator's handler. It holds what every request shares; what
// belongs to one request is in a request.
type handler struct {
config *config.Config
requestLog io.Writer
processLog *slog.Logger
now func() time.Time
metrics *metrics.Metrics
limiter *ratelimit.Limiter
ledger *bans.Ledger
geojs *lookup.GeoJS
anomalies *anomaly.Counters
lookupFile *lookup.File
lists *reputation.Lists
dnsbl *reputation.DNSBL
abuseIPDB *reputation.AbuseIPDB
routeWatch *routewatch.Client
rules *rules.Files
coreRuleSet *waf.CoreRuleSet
alerts *alerts.Queue
// awaitingReport holds the decision on each answered question by its id
// until its report comes, and nil for a question still being handled.
awaitingReport *lru.Cache[string, *decision]
}
-67
View File
@@ -1,67 +0,0 @@
package discriminator
// The heuristic rate_limits. It reads SWW_RATE_LIMIT_EXEMPT_NETS,
// SWW_RATE_LIMIT_EXEMPT_PATHS and SWW_BAN_RESPONSE, and the rate limits and
// biased thresholds through the limiter and limitPercentages.
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// rateLimits counts the request for the rate limits, unless
// countedByRateLimits exempts it, by the client's limit percentages, which it
// notes for the log line with the client's counts. A request that takes the
// client over a rate limit, as its limit percentage lowers it, breaks it: it is
// refused, and bans the client. A request exempt from the rate limits is exempt
// from the byte limits too. Its figures are the window, the count and the
// limit.
type rateLimits struct{}
func (rateLimits) name() string { return "rate_limits" }
func (rateLimits) check(_ context.Context, rq *request, now time.Time) *verdict {
rq.counted = rq.countedByRateLimits()
if !rq.counted {
return nil
}
rq.limitPercent, rq.bytesPercent = rq.limitPercentages()
rq.line.LimitPercent, rq.line.LimitPercentSetting = rq.limitPercent.logged()
rq.line.BytesPercent, rq.line.BytesPercentSetting = rq.bytesPercent.logged()
counts, hit, over := rq.h.limiter.Count(rq.h.clientGroup(rq.client), now,
rq.limitPercent.percent)
rq.line.Counts = counts
if !over {
return nil
}
rq.banForLimit(now, hit, rq.h.config.BanResponse)
return &verdict{
action: requestlog.ActionClientIsRateLimited, figures: limitFigures(hit),
}
}
// overAWholeRateLimit reports whether the heuristic rate_limits will refuse the
// request at now, whatever its client's limit percentages: the rate limits
// count it, and one more request from its client takes it over a whole rate
// limit. It counts nothing.
func (rq *request) overAWholeRateLimit(now time.Time) bool {
return rq.countedByRateLimits() &&
rq.h.limiter.OverARateLimit(rq.h.clientGroup(rq.client), now)
}
// countedByRateLimits reports whether the rate limits count the request: its
// client is not in SWW_RATE_LIMIT_EXEMPT_NETS, and its path is not exempt
// under SWW_RATE_LIMIT_EXEMPT_PATHS.
func (rq *request) countedByRateLimits() bool {
cfg := rq.h.config
return !isInside(rq.client, cfg.RateLimitExemptNets) &&
!pathExempt(rq.in, cfg.RateLimitExemptPaths)
}
-54
View File
@@ -1,54 +0,0 @@
package discriminator
// The heuristic refusal_limit. It reads SWW_ERROR_BURST_THRESHOLD and
// SWW_BAN_RESPONSE.
import (
"context"
"net/http"
"time"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// refusalLimit counts the request once it has been answered, if discriminator
// refused it after a rule file match, a trap path or a Core Rule Set match, and
// in observe mode if enforce mode would have: more than
// SWW_ERROR_BURST_THRESHOLD such refusals of the client within a minute break
// a limit, which bans the client. A client in SWW_ALLOW_NETS, which the
// heuristics skip, is not counted, and nothing is while the threshold is off.
// Its figures are the window, the count and the limit.
type refusalLimit struct{}
func (refusalLimit) name() string { return "refusal_limit" }
func (refusalLimit) check(_ context.Context, rq *request, now time.Time) *verdict {
cfg := rq.h.config
if cfg.ErrorBurstThreshold == 0 {
return nil
}
if !rq.attack && !rq.blockedByBlockRule && !rq.wafBlocked {
return nil
}
hit, over := rq.h.limiter.CountRefusal(rq.h.clientGroup(rq.client), now,
cfg.ErrorBurstThreshold)
if !over {
return nil
}
// What the client was sent, or in observe mode would have been.
status := rq.out.status
switch rq.line.WouldAction {
case requestlog.ActionBlockedByBlockRule, requestlog.ActionWAFBlocked:
status = http.StatusForbidden
case requestlog.ActionTemporarilyBanned, requestlog.ActionPermanentlyBanned:
status = cfg.BanResponse
}
rq.banForLimit(now, hit, status)
return &verdict{figures: limitFigures(hit)}
}
-48
View File
@@ -1,48 +0,0 @@
package discriminator
// What the reputation heuristics share: blocklists, crowdsec, dnsbl and
// abuseipdb.
import (
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans"
)
// deny is the SWW_BLOCKLIST_ACTION and the SWW_REPUTATION_ACTION that
// refuses the requests of a client a source lists.
const deny = "deny"
// noteListed notes each of sources, the URLs of the blocklists or the
// DNSBL zones, their keys masked, that list the client, as noteHit does,
// with reason.
func (rq *request) noteListed(sources []string, reason string) {
for _, source := range sources {
rq.noteHit(bans.ReputationHit{Source: source}, reason)
}
}
// noteHit adds hit's source, which lists the client, to the log line's
// reputation, and hit to the notes of a ban the request makes, counts the
// source in the metrics, and raises a reputation_hit alert with reason,
// whose detail gives hit's source and score.
func (rq *request) noteHit(hit bans.ReputationHit, reason string) {
detail := map[string]any{"source": hit.Source}
if hit.Score != nil {
detail["score"] = *hit.Score
}
rq.line.Reputation = append(rq.line.Reputation, hit.Source)
rq.reputation = append(rq.reputation, hit)
rq.h.metrics.ReputationHit(hit.Source)
rq.h.alerts.Raise(alerts.Alert{
Event: alerts.EventReputationHit,
Host: rq.site,
Client: rq.client,
Netblock: rq.h.clientGroup(rq.client),
ASN: rq.line.ASN,
ASName: rq.line.ASName,
Country: rq.line.Country,
Reason: reason,
Detail: detail,
})
}
-410
View File
@@ -1,410 +0,0 @@
package discriminator
import (
"context"
"net/http"
"net/netip"
"slices"
"strings"
"time"
"sneak.berlin/go/smallwebwaf/internal/anomaly"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/rules"
)
// refusal is discriminator refusing a request: the status the visitor is to get, 0
// to close its connection without an answer, and the action the log line names.
type refusal struct {
status int
action string
}
// decision is what the checks note of a request: its log line, and what
// counting the request needs once it has ended. discriminator keeps a copy of it
// until the request's report comes. It holds no credentials, since the log line
// never does, and neither the request's objects nor their bodies.
type decision struct {
line requestlog.Line
client netip.Addr
// requestURI is the path with the query, as a ban's notes keep it.
requestURI string
// site is, for a question, the host the visitor asked for, which the
// alerts name, since one discriminator serves many sites.
site string
// allowed is true for a question answered with DispositionAllow.
allowed bool
// lookedUp is true once the client's AS number and country have been
// looked up, whether or not an answer was there, and lookupAnswer is
// what the lookup gave then, the zero Answer while GeoJS had given none.
lookedUp bool
lookupAnswer lookup.Answer
// skippedLookupWait is true for a request that did not wait for GeoJS and
// found no answer kept. SWW_UNKNOWN_LIMIT_PERCENT does not apply to it,
// so that not waiting never lowers its client's limits.
skippedLookupWait bool
// counted is true for a request the rate limits counted, whose bytes
// the byte limits count once it has ended. limitPercent and
// bytesPercent are then its client's limit percentages for the rate
// limits and for the byte limits.
counted bool
limitPercent, bytesPercent percentage
// attack is true for a request that matched a ban rule or asked for a
// trap path, blockedByBlockRule for one a block rule refused, and
// wafBlocked for one the Core Rule Set refused, each an offence its
// client's history counts.
attack, blockedByBlockRule, wafBlocked bool
// reputation is the reputation sources that list the client, for the
// notes of a ban the request makes.
reputation []bans.ReputationHit
}
// request is one request to discriminator, from the moment its headers have been
// read to its log line.
type request struct {
decision
h *handler
in *http.Request
out *responseWriter
// blocklisted is true once a blocklist is found to list the client,
// dnsblListed once a DNSBL zone's verdict is, and abuseIPDBHit once
// AbuseIPDB's score of it is a hit.
blocklisted, dnsblListed, abuseIPDBHit bool
start time.Time
// checked is when the checks were done.
checked time.Time
// refused is what the request was refused with, nil if it was not.
refused *refusal
// requestBytes is how many bytes of the request's body have been read.
requestBytes int64
}
// startRequest starts handling r from client, which came through peer: it
// notes the time, counts the request as under way, and starts the log line
// with what is known of the request. isQuestion says whether r is a question,
// whose headers give the request's id and scheme.
func (h *handler) startRequest(
w http.ResponseWriter, r *http.Request, client, peer netip.Addr, isQuestion bool,
) *request {
h.metrics.RequestStarted()
start := time.Now()
forwardedFor := r.Header.Values("X-Forwarded-For")
rq := &request{
decision: decision{
client: client,
requestURI: r.URL.RequestURI(),
line: requestlog.Line{
Time: requestlog.FormatTime(start),
Instance: h.config.InstanceName,
ClientIP: client.String(),
Method: r.Method,
Scheme: scheme(r, isQuestion),
Host: r.Host,
Path: rules.Path(r),
Query: r.URL.RawQuery,
Protocol: r.Proto,
Referer: r.Referer(),
UserAgent: r.UserAgent(),
RequestID: requestID(r, isQuestion),
PeerIP: peer.String(),
ForwardedFor: strings.Join(forwardedFor, ", "),
ClientGroup: h.clientGroup(client).String(),
ContentType: r.Header.Get("Content-Type"),
RequestHeaders: requestHeaders(r, h.config.LogRequestHeaders),
HasAuthorization: len(r.Header.Values("Authorization")) > 0,
HasCookie: len(r.Header.Values("Cookie")) > 0,
Action: requestlog.ActionForward,
},
},
h: h,
in: r,
out: &responseWriter{ResponseWriter: w},
start: start,
}
// A length of -1 is a body whose length was not announced.
if r.ContentLength > 0 {
rq.line.ContentLength = r.ContentLength
}
return rq
}
// addTag adds tag to the request's tags, which stay sorted and hold each tag
// once.
func (rq *request) addTag(tag string) {
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.
func requestHeaders(r *http.Request, names []string) map[string]string {
headers := map[string]string{}
for _, name := range names {
switch name {
case "authorization", "cookie", "set-cookie":
continue
}
values := r.Header.Values(name)
if len(values) > 0 {
headers[name] = strings.Join(values, ", ")
}
}
return headers
}
// check is the one place where a request can be refused. It returns nil to let
// the request through. The heuristics of checkClient decide: a request they
// refuse is answered with SWW_BAN_RESPONSE, 403 for a block rule or the Core
// Rule Set, or 431 for the header limits. In observe mode nothing is refused,
// and the log line names what enforce mode would have done. ctx is the
// request's own context.
func (rq *request) check(ctx context.Context) *refusal {
v := rq.checkClient(ctx)
if v == nil {
return nil
}
action := v.action
switch {
case rq.h.config.Observe:
rq.line.WouldAction = action
return nil
case action == requestlog.ActionBlockedByBlockRule ||
action == requestlog.ActionWAFBlocked:
return &refusal{status: http.StatusForbidden, action: action}
case action == requestlog.ActionRequestHeaderTooLarge:
return &refusal{status: http.StatusRequestHeaderFieldsTooLarge, action: action}
default:
return rq.banResponse(action)
}
}
// checkClient runs the heuristics of beforeLookup on the request, then looks
// up the client's AS number and country, then runs those of afterLookup. It
// returns the first verdict, or nil when none gives one. A client in
// SWW_ALLOW_NETS skips them all, and is not looked up. ctx is the request's
// own context.
func (rq *request) checkClient(ctx context.Context) *verdict {
if isInside(rq.client, rq.h.config.AllowNets) {
return nil
}
now := rq.h.now()
v := rq.runHeuristics(ctx, beforeLookup(), now)
if v != nil {
return v
}
rq.lookUp(ctx, now)
// The lookup can wait for GeoJS, so the checks after it read the time
// again: a request counted at the time it arrived could be counted
// after a later one of its client's, which the rate limits would take
// for the clock set back.
return rq.runHeuristics(ctx, afterLookup(), rq.h.now())
}
// pathExempt reports whether r is exempt under prefixes,
// SWW_RATE_LIMIT_EXEMPT_PATHS or SWW_WAF_EXEMPT_PATHS: whether its
// path as sent, the path the app receives, not percent-decoded, starts
// with one of prefixes, so that /%61ssets/x is not under /assets/ for an
// app whose router matches the path as received. A request whose decoded
// path contains .. anywhere or a backslash, or whose path as sent holds an
// encoded slash (%2F or %2f), never is, since an app may act on it as a
// path outside every prefix: /assets/..%2Flogin as /login, or /assets%2Fx
// as one path segment, as Go's router does.
func pathExempt(r *http.Request, prefixes []string) bool {
decoded := r.URL.Path
sent := rules.Path(r)
if strings.Contains(decoded, "..") || strings.Contains(decoded, `\`) ||
strings.Contains(strings.ToLower(sent), "%2f") {
return false
}
return slices.ContainsFunc(prefixes, func(prefix string) bool {
return strings.HasPrefix(sent, prefix)
})
}
// finish counts the request in the metrics and writes its log line.
func (rq *request) finish() {
line := &rq.line
line.Status = rq.out.status
line.ResponseBytes = rq.out.bytes
line.ResponseContentType = rq.out.Header().Get("Content-Type")
line.RequestBytes = rq.requestBytes
switch {
case rq.refused != nil:
line.Action = rq.refused.action
case rq.out.err != nil || rq.in.Context().Err() != nil:
line.Aborted = true
}
duration := time.Since(rq.start)
line.DurationTotal = requestlog.Milliseconds(duration)
line.DurationChecks = timing(rq.start, rq.checked)
// Counted before the log line is written, so that the metrics count
// every request whose line is out. An allowed request is the exception:
// its report gives the status, bytes and times the metrics count.
if rq.allowed {
rq.h.metrics.RequestAllowed()
} else {
rq.h.metrics.RequestEnded(line, duration)
}
rq.writeLine()
}
// writeLine writes the request's log line.
func (rq *request) writeLine() {
err := requestlog.Write(rq.h.requestLog, &rq.line)
if err != nil {
rq.h.processLog.Error("writing the request log failed", "error", err.Error())
}
}
// timing is the time from start to end in milliseconds, for one of the
// log line's timings, or nil when end is zero: what it times never
// happened.
func timing(start, end time.Time) *float64 {
if end.IsZero() {
return nil
}
return new(requestlog.Milliseconds(end.Sub(start)))
}
// addToHistory adds the request, which has ended, to its client's
// history, and counts its offences in the metrics, and then the lookup's
// answer about the client, as answerAtTheEnd gives it, to that history and
// to the notes of the bans on its netblock: an answer may have come
// before either was there, and one from GeoJS that comes later is added
// when it comes.
func (rq *request) addToHistory() {
request := ratelimit.Request{
Forwarded: rq.allowed,
Refused: rq.refused != nil,
Status: rq.out.status,
RequestBytes: rq.requestBytes,
ResponseBytes: rq.out.bytes,
BrokeLimit: rq.line.Offence == requestlog.OffenceLimit,
Attack: rq.attack,
BlockedByBlockRule: rq.blockedByBlockRule,
WAFBlocked: rq.wafBlocked,
}
rq.h.limiter.AddToHistory(rq.h.clientGroup(rq.client), rq.h.now(), request)
rq.h.metrics.Offences(request)
answer, found := rq.answerAtTheEnd()
if found {
rq.h.addLookup(answer)
}
}
// countAnomalies counts the request, which has ended, and its bytes, as
// countedBytes gives them, for the anomaly thresholds, whatever was done
// with it: a request refused, one from a client in SWW_ALLOW_NETS or
// SWW_RATE_LIMIT_EXEMPT_NETS, and one for a path in
// SWW_RATE_LIMIT_EXEMPT_PATHS are counted too. It is counted for its
// client's AS number when answerAtTheEnd gives one. With every anomaly
// threshold off, the default, it does nothing.
func (rq *request) countAnomalies() {
if !anomalyThresholdsSet(rq.h.config) {
return
}
answer, _ := rq.answerAtTheEnd()
rq.h.anomalies.Count(rq.h.now(), anomaly.Request{
Host: rq.site,
Client: rq.client,
ClientGroup: rq.h.clientGroup(rq.client),
ASN: answer.ASN,
ASName: answer.ASName,
Country: answer.Country,
Bytes: rq.countedBytes(),
})
}
// anomalyThresholdsSet reports whether any anomaly threshold is set.
func anomalyThresholdsSet(cfg *config.Config) bool {
off := anomaly.Thresholds{}
return cfg.AnomalyClient != off || cfg.AnomalyNet != off || cfg.AnomalyASN != off ||
cfg.AnomalyTotal != off || cfg.AnomalyWatch != off
}
// answerAtTheEnd returns, for a client that was looked up, the lookup's
// answer about it as the request ends, and whether there is one: the
// lookup database's, which was there at once, or the one GeoJS has given
// by then, which a request does not wait for unless a setting needs it.
func (rq *request) answerAtTheEnd() (lookup.Answer, bool) {
if !rq.lookedUp {
return lookup.Answer{}, false
}
if rq.h.config.LookupSource == "file" {
return rq.lookupAnswer, true
}
return rq.h.geojs.Kept(rq.h.clientGroup(rq.client))
}
// responseWriter is discriminator's answer to a request. It notes the status and
// size for the log line, and the first error writing the answer.
type responseWriter struct {
http.ResponseWriter
// status is the status sent, or zero before one is.
status int
bytes int64
err error
}
// WriteHeader sends the status and headers.
func (w *responseWriter) WriteHeader(status int) {
if w.status == 0 {
w.status = status
}
w.ResponseWriter.WriteHeader(status)
}
// Write sends part of the body.
func (w *responseWriter) Write(p []byte) (int, error) {
if w.status == 0 {
w.status = http.StatusOK
}
n, err := w.ResponseWriter.Write(p)
w.bytes += int64(n)
if w.err == nil {
w.err = err
}
return n, err
}
-42
View File
@@ -1,42 +0,0 @@
package discriminator
// The heuristic routewatch_tags. It reads SWW_ROUTEWATCH_URL.
import (
"context"
"strconv"
"time"
"sneak.berlin/go/smallwebwaf/internal/config"
)
// routeWatchTags adds to the request the tags asn=<number> and prefix=<netblock>
// from what routewatch answered about the client. It refuses nothing, and the
// request does not wait for routewatch. A request that gets no tags from it has
// the reason in the log line's routewatch_tags_missing. While SWW_ROUTEWATCH_URL
// is unset it does nothing. Answers are kept by client and asked for by the
// request's address, and a route without an origin AS gives only the prefix= tag.
type routeWatchTags struct{}
func (routeWatchTags) name() string { return "routewatch_tags" }
func (routeWatchTags) check(ctx context.Context, rq *request, _ time.Time) *verdict {
if rq.h.routeWatch == nil {
return nil
}
route, missing := rq.h.routeWatch.Route(ctx, rq.h.clientGroup(rq.client), rq.client)
if missing != "" {
rq.line.RouteWatchTagsMissing = string(missing)
return nil
}
rq.addTag(config.PrefixTagPrefix + route.Netblock.String())
if route.ASN != 0 {
rq.addTag(config.ASNTagPrefix + strconv.FormatUint(uint64(route.ASN), 10))
}
return nil
}
@@ -1,245 +0,0 @@
package discriminator_test
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"net/netip"
"strings"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// routeWatchURL is SWW_ROUTEWATCH_URL, and tagsMissing the log line's field
// that says why a request got no tags from routewatch.
const (
routeWatchURL = "SWW_ROUTEWATCH_URL"
tagsMissing = "routewatch_tags_missing"
fromV6 = "2001:db8:1::5"
prefixV6 = "2001:db8::/32"
prefixDE = "203.0.113.0/24"
prefixKP = "198.51.100.0/24"
)
// standInRoute is what the stand-in for routewatch answers about an address.
type standInRoute struct {
Netblock string `json:"netblock"`
ASN int `json:"asn"`
}
// startRouteWatch starts a stand-in for routewatch's IP info API that knows the
// routes given by address, and returns its URL.
func startRouteWatch(t *testing.T, routes map[string]standInRoute) string {
t.Helper()
server := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, r *http.Request) {
address := strings.TrimPrefix(r.URL.Path, "/api/v1/ip/")
result := map[string]any{"ip": address}
if route, known := routes[address]; known {
result["netblock"], result["asn"] = route.Netblock, route.ASN
}
_ = json.NewEncoder(w).Encode(map[string]any{
"status": "ok",
"data": map[string]any{"results": []any{result}},
})
}))
t.Cleanup(server.Close)
return server.URL
}
// waitForRouteWatch waits until routewatch's answer about from, in the client
// group of the given length, is kept, so that the next request gets its tags.
func waitForRouteWatch(
t *testing.T, server *discriminator.Server, from string, bits int,
) {
t.Helper()
addr := netip.MustParseAddr(from)
client := netip.PrefixFrom(addr, bits).Masked()
deadline := time.Now().Add(5 * time.Second)
for {
_, missing := server.RouteWatch.Route(context.Background(), client, addr)
if missing == "" {
return
}
if time.Now().After(deadline) {
t.Fatalf("routewatch's answer about %s not kept: %q", from, missing)
}
time.Sleep(time.Millisecond)
}
}
func wantTagsMissing(t *testing.T, line logLine, want string) {
t.Helper()
got, _ := line.fields[tagsMissing].(string)
if got != want {
t.Errorf("log line has %s %q, want %q", tagsMissing, got, want)
}
}
func TestRouteWatchTagsAreOnTheLogLineWithTheLookupsTags(t *testing.T) {
t.Parallel()
url := startRouteWatch(t, map[string]standInRoute{fromDE: {prefixDE, 64496}})
s, server, _ := startWithLookups(t, map[string]string{routeWatchURL: url})
waitForRouteWatch(t, server, fromDE, 32)
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
wantTags(t, line, "asn=64496", "country=DE", "prefix="+prefixDE)
wantTagsMissing(t, line, "")
}
func TestRouteWatchTagsAreOnALineDenyNetsRefused(t *testing.T) {
t.Parallel()
url := startRouteWatch(t, map[string]standInRoute{fromKP: {prefixKP, 64511}})
s, _, server := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: url, denyNets: fromKP,
})
waitForRouteWatch(t, server, fromKP, 32)
line := s.get(fromKP, http.StatusForbidden, requestlog.ActionClientDenied)
wantHeuristic(t, line, "deny_nets", `{"netblock": "`+fromKP+`/32"}`)
wantTags(t, line, "asn=64511", "prefix="+prefixKP)
}
func TestRouteWithoutAnOriginASGivesOnlyThePrefixTag(t *testing.T) {
t.Parallel()
url := startRouteWatch(t, map[string]standInRoute{fromDE: {prefixDE, 0}})
s, _, server := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: url,
})
waitForRouteWatch(t, server, fromDE, 32)
wantTags(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
"prefix="+prefixDE)
}
func TestUnsetRouteWatchChangesNothing(t *testing.T) {
t.Parallel()
s, _, server := startWithClock(t, "", map[string]string{lookupSource: off})
if server.RouteWatch != nil {
t.Error("RouteWatch is set while SWW_ROUTEWATCH_URL is unset")
}
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
if _, present := line.fields[tagsMissing]; present {
t.Errorf("log line has %s", tagsMissing)
}
if _, present := line.fields["tags"]; present {
t.Errorf("log line has tags %v", line.fields["tags"])
}
}
func TestUnreachableRouteWatchLetsTheRequestThroughAndSaysWhy(t *testing.T) {
t.Parallel()
// A stand-in that is closed at once, so that the port refuses connections.
dead := httptest.NewServer(http.NotFoundHandler())
url := dead.URL
dead.Close()
s, _, _ := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: url,
})
wantTagsMissing(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
"no_answer_yet")
deadline := time.Now().Add(5 * time.Second)
for {
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
missing, _ := line.fields[tagsMissing].(string)
if missing == "request_failed" {
return
}
if time.Now().After(deadline) {
t.Fatalf("still %q, want request_failed", missing)
}
time.Sleep(time.Millisecond)
}
}
func TestAddressWithoutARouteHasNoTagsAndTheLineSaysSo(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: startRouteWatch(t, nil),
})
deadline := time.Now().Add(5 * time.Second)
for {
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
missing, _ := line.fields[tagsMissing].(string)
if missing == "no_route" {
return
}
if time.Now().After(deadline) {
t.Fatalf("still %q, want no_route", missing)
}
time.Sleep(time.Millisecond)
}
}
func TestTagDenyRefusesOnARouteWatchPrefix(t *testing.T) {
t.Parallel()
url := startRouteWatch(t, map[string]standInRoute{
fromDE: {prefixDE, 64496}, fromKP: {prefixKP, 64511},
})
s, _, server := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: url, tagDeny: "prefix=" + prefixKP,
})
waitForRouteWatch(t, server, fromKP, 32)
waitForRouteWatch(t, server, fromDE, 32)
wantHeuristic(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionClientDenied),
"tag_deny", `{"tag": "prefix=`+prefixKP+`"}`)
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
}
func TestTagLimitPercentWorksWithAnIPv6Prefix(t *testing.T) {
t.Parallel()
url := startRouteWatch(t, map[string]standInRoute{fromV6: {prefixV6, 64496}})
s, _, server := startWithClock(t, "", map[string]string{
lookupSource: off, routeWatchURL: url, rateLimitPerMinute: "2",
tagLimitPercent: "prefix=" + prefixV6 + ":50",
})
waitForRouteWatch(t, server, fromV6, 64)
// Half of two is one: the second request breaks the limit.
line := s.get(fromV6, http.StatusOK, requestlog.ActionForward)
wantTags(t, line, "asn=64496", "prefix="+prefixV6)
s.get(fromV6, http.StatusForbidden, requestlog.ActionClientIsRateLimited)
}
-62
View File
@@ -1,62 +0,0 @@
package discriminator
// The heuristic rule_files. It reads the rules of the rule files, which
// SWW_RULES_DIR and SWW_RULES_ENABLED name.
import (
"context"
"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, adds the tag
// exploitsignature when it matches any, and refuses the request
// when the last rule it matches refuses it: with ActionBlockedByBlockRule for a
// block rule, and for a ban rule with the action for the ban it makes. A ban
// rule bans the client's netblock for a clear sign of attack, or in observe
// mode raises the alert for the ban
// it would have made. Either rule's match is noted as an offence, for the
// client's history. Its figures are the rule's id and action.
type ruleFiles struct{}
func (ruleFiles) name() string { return "rule_files" }
func (ruleFiles) check(_ context.Context, rq *request, now time.Time) *verdict {
matched := rq.h.rules.Match(rq.in)
for _, rule := range matched {
rq.line.RuleIDs = append(rq.line.RuleIDs, rule.ID)
rq.h.metrics.RuleMatched(rule.ID, rule.Action)
}
if len(matched) == 0 {
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}
switch last.Action {
case rules.ActionBlock:
rq.blockedByBlockRule = true
return &verdict{action: requestlog.ActionBlockedByBlockRule, figures: figures}
case rules.ActionBan:
rq.attack = true
return &verdict{
action: rq.banForAttack(now, bans.Notes{RuleID: last.ID, Target: last.Target}),
figures: figures,
}
default:
return nil
}
}
-30
View File
@@ -1,30 +0,0 @@
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.ActionClientDenied,
figures: map[string]any{"tag": tag},
}
}
}
return nil
}
-121
View File
@@ -1,121 +0,0 @@
package discriminator_test
import (
"net/http"
"testing"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
func TestTagDenyRefusesALookupTagAndNamesTheTag(t *testing.T) {
t.Parallel()
// The setting takes a country code in either case; the request's tag is
// in capitals.
s, _, _ := startWithLookups(t, map[string]string{tagDeny: "Country=kp"})
line := s.get(fromKP, http.StatusForbidden, requestlog.ActionClientDenied)
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.ActionClientDenied),
"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.ActionClientDenied),
"tag_deny", `{"tag": "torexit"}`)
}
}
func TestTagDenyRefusesAMixedCaseZoneByItsLowerCaseTag(t *testing.T) {
t.Parallel()
const mixedCaseZone = "DNSBL.example"
// The zone's tag is in lower case, however SWW_DNSBL_ZONES writes it.
s, server, _ := startWithLookups(t, map[string]string{
dnsblZones: mixedCaseZone, dnsblResolver: noResolver,
reputationAction: actionLog, tagDeny: "dnsbl=" + dnsblZone,
})
loadVerdicts(server, map[string][]string{fromDE: {mixedCaseZone}})
wantHeuristic(t, s.get(fromDE, http.StatusForbidden, requestlog.ActionClientDenied),
"tag_deny", `{"tag": "dnsbl=`+dnsblZone+`"}`)
}
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.ActionClientDenied)
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.ActionClientIsRateLimited)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
"25 from "+tagLimitPercent)
}
func TestTagLimitPercentLowersAByteLimitByAListTag(t *testing.T) {
t.Parallel()
s, server, _ := startWithLookups(t, map[string]string{
bytesLimitPerMinute: twoUploads,
tagLists: "vpn=" + vpnList,
tagLimitPercent: "vpn:50",
})
loadLists(t, server, map[string][]string{vpnList: {fromDE}})
// The upload's 100 bytes are over half of 199, 99.
line := s.uploadFrom(fromDE)
if line.LimitHit != minuteBytes {
t.Errorf("log line has limit_hit %q, want %s", line.LimitHit, minuteBytes)
}
wantPercent(t, "bytes_percent", line.BytesPercent, line.BytesPercentSetting,
"50 from "+tagLimitPercent)
// fromKP, which the list does not hold, has the whole limit.
line = s.uploadFrom(fromKP)
if line.LimitHit != "" {
t.Errorf("log line for %s has limit_hit %q, want none", fromKP, line.LimitHit)
}
wantPercent(t, "bytes_percent", line.BytesPercent, line.BytesPercentSetting, none)
}
-24
View File
@@ -1,24 +0,0 @@
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
}
-100
View File
@@ -1,100 +0,0 @@
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")
}
func TestTagListsTagARequestRefusedBeforeTheLookup(t *testing.T) {
t.Parallel()
s, server, _ := startWithLookups(t, map[string]string{
tagLists: "vpn=" + vpnList, denyNets: fromKP, rateLimitPerMinute: "1",
})
loadLists(t, server, map[string][]string{vpnList: {fromDE, fromKP}})
line := s.get(fromKP, http.StatusForbidden, requestlog.ActionClientDenied)
if line.Heuristic != "deny_nets" {
t.Errorf("log line has heuristic %q, want deny_nets", line.Heuristic)
}
wantTags(t, line, "vpn")
// The second request breaks the limit of one a minute, which bans the client.
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited)
line = s.get(fromDE, http.StatusForbidden, requestlog.ActionTemporarilyBanned)
if line.Heuristic != "active_ban" {
t.Errorf("log line has heuristic %q, want active_ban", line.Heuristic)
}
wantTags(t, line, "vpn")
}
-37
View File
@@ -1,37 +0,0 @@
package discriminator
// The heuristic trap_paths. It reads SWW_TRAP_PATHS.
import (
"context"
"slices"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/rules"
)
// trapPaths refuses a request for a path in SWW_TRAP_PATHS: its path as a
// path rule sees it, without the query, as sent or once percent-decoded, is one
// of them. Such a request is a clear sign of attack, as a ban rule's match is:
// it bans the client's netblock, or in observe mode raises the alert for the
// ban it would have made. The ban's notes give the path as sent, and so does
// its figure.
type trapPaths struct{}
func (trapPaths) name() string { return "trap_paths" }
func (trapPaths) check(_ context.Context, rq *request, now time.Time) *verdict {
path := rules.Path(rq.in)
if !slices.Contains(rq.h.config.TrapPaths, path) &&
!slices.Contains(rq.h.config.TrapPaths, rules.DecodeOnce(path)) {
return nil
}
rq.attack = true
return &verdict{
action: rq.banForAttack(now, bans.Notes{TrapPath: path}),
figures: map[string]any{"path": path},
}
}
+8 -18
View File
@@ -24,7 +24,7 @@ const quietTime = 2 * time.Second
// FileParams are what OpenFile needs. // FileParams are what OpenFile needs.
type FileParams struct { type FileParams struct {
// Path is the lookup database, the IPinfo Lite file in its .mmdb form // Path is the lookup database, the IPinfo Lite file in its .mmdb form
// (SWW_LOOKUP_DB_PATH). // (SWWAF_LOOKUP_DB_PATH).
Path string Path string
// Now tells the time, normally time.Now. // Now tells the time, normally time.Now.
Now func() time.Time Now func() time.Time
@@ -51,7 +51,7 @@ type File struct {
} }
// record is what the lookup database holds about a network, of the fields // record is what the lookup database holds about a network, of the fields
// sww reads. // smallwebwaf reads.
type record struct { type record struct {
ASN string `maxminddb:"asn"` ASN string `maxminddb:"asn"`
ASName string `maxminddb:"as_name"` ASName string `maxminddb:"as_name"`
@@ -133,11 +133,8 @@ func (f *File) Watch(ctx context.Context) {
} }
if err != nil { if err != nil {
f.params.ProcessLog.Error( f.params.ProcessLog.Error("cannot watch the lookup database for replacements",
"cannot watch the lookup database for replacements", "error", err.Error())
"error",
err.Error(),
)
return return
} }
@@ -197,10 +194,7 @@ func (f *File) readAgain() {
f.params.Alerts.Raise(alerts.Alert{ f.params.Alerts.Raise(alerts.Alert{
Event: alerts.EventFileError, Event: alerts.EventFileError,
Reason: kept, Reason: kept,
Detail: map[string]any{ Detail: map[string]any{"file": f.params.Path, "error": err.Error()},
"file": f.params.Path,
"error": err.Error(),
},
}) })
f.params.ProcessLog.Error(kept, "error", err.Error()) f.params.ProcessLog.Error(kept, "error", err.Error())
@@ -218,11 +212,7 @@ func (f *File) use(reader *maxminddb.Reader) {
f.lastRead = f.params.Now() f.lastRead = f.params.Now()
f.mu.Unlock() f.mu.Unlock()
f.params.ProcessLog.Info( f.params.ProcessLog.Info("read the lookup database", "file", f.params.Path)
"read the lookup database",
"file",
f.params.Path,
)
} }
// read reads the lookup database at path. The whole file is read into // read reads the lookup database at path. The whole file is read into
@@ -231,12 +221,12 @@ func (f *File) use(reader *maxminddb.Reader) {
func read(path string) (*maxminddb.Reader, error) { func read(path string) (*maxminddb.Reader, error) {
data, err := os.ReadFile(path) //nolint:gosec // the file the admin names data, err := os.ReadFile(path) //nolint:gosec // the file the admin names
if err != nil { if err != nil {
return nil, fmt.Errorf("SWW_LOOKUP_DB_PATH cannot be read: %w", err) return nil, fmt.Errorf("SWWAF_LOOKUP_DB_PATH cannot be read: %w", err)
} }
reader, err := maxminddb.OpenBytes(data) reader, err := maxminddb.OpenBytes(data)
if err != nil { if err != nil {
return nil, fmt.Errorf("SWW_LOOKUP_DB_PATH %s is not a .mmdb file: %w", path, err) return nil, fmt.Errorf("SWWAF_LOOKUP_DB_PATH %s is not a .mmdb file: %w", path, err)
} }
return reader, nil return reader, nil
+3 -3
View File
@@ -99,9 +99,9 @@ func TestFileThatCannotBeReadIsAnError(t *testing.T) {
writeFile(t, notDatabase, "not a lookup database\n") writeFile(t, notDatabase, "not a lookup database\n")
for path, want := range map[string]string{ for path, want := range map[string]string{
missing: "SWW_LOOKUP_DB_PATH cannot be read: open " + missing + missing: "SWWAF_LOOKUP_DB_PATH cannot be read: open " + missing +
": no such file or directory", ": no such file or directory",
notDatabase: "SWW_LOOKUP_DB_PATH " + notDatabase + notDatabase: "SWWAF_LOOKUP_DB_PATH " + notDatabase +
" is not a .mmdb file: error opening database: invalid MaxMind DB file", " is not a .mmdb file: error opening database: invalid MaxMind DB file",
} { } {
_, err := OpenFile(FileParams{ _, err := OpenFile(FileParams{
@@ -216,7 +216,7 @@ func TestReplacementThatCannotBeReadLeavesTheFileInUseWithOneAlert(t *testing.T)
Reason: "the lookup database cannot be read, and the one read before stays in use", Reason: "the lookup database cannot be read, and the one read before stays in use",
Detail: map[string]any{ Detail: map[string]any{
"file": path, "file": path,
"error": "SWW_LOOKUP_DB_PATH " + path + " is not a .mmdb file: " + "error": "SWWAF_LOOKUP_DB_PATH " + path + " is not a .mmdb file: " +
"error opening database: invalid MaxMind DB file", "error opening database: invalid MaxMind DB file",
}, },
}) })
+6 -14
View File
@@ -1,6 +1,6 @@
// Package lookup looks up each client's AS number and country, through // Package lookup looks up each client's AS number and country, through
// the GeoJS web service or in the lookup database, the IPinfo Lite file // the GeoJS web service or in the lookup database, the IPinfo Lite file
// SWW_LOOKUP_DB_PATH names. GeoJS's answers are kept in memory, for at // SWWAF_LOOKUP_DB_PATH names. GeoJS's answers are kept in memory, for at
// most 100,000 clients and for 7 days each, and are written to // most 100,000 clients and for 7 days each, and are written to
// lookups.json and read from it by the state package. // lookups.json and read from it by the state package.
package lookup package lookup
@@ -66,7 +66,7 @@ type Params struct {
URL string URL string
// Timeout is how long a request waits for its client's first answer, // Timeout is how long a request waits for its client's first answer,
// and how long a request to GeoJS may take before it is abandoned // and how long a request to GeoJS may take before it is abandoned
// (SWW_LOOKUP_TIMEOUT). // (SWWAF_LOOKUP_TIMEOUT).
Timeout time.Duration Timeout time.Duration
// Wait is true when a setting needs each request's answer before the // Wait is true when a setting needs each request's answer before the
// request goes on. Otherwise no request waits for one. // request goes on. Otherwise no request waits for one.
@@ -179,7 +179,7 @@ func New(params Params) *GeoJS {
// own address for IPv4, and an address in the same place for an IPv6 // own address for IPv4, and an address in the same place for an IPv6
// netblock. // netblock.
func (g *GeoJS) LookUp(ctx context.Context, client netip.Prefix) Answer { func (g *GeoJS) LookUp(ctx context.Context, client netip.Prefix) Answer {
answer, asked := g.answerOrWait(ctx, client, g.wait) answer, asked := g.answerOrWait(ctx, client)
if asked == nil { if asked == nil {
return answer return answer
} }
@@ -209,14 +209,6 @@ func (g *GeoJS) LookUp(ctx context.Context, client netip.Prefix) Answer {
return answer return answer
} }
// LookUpWithoutWaiting is LookUp for a request that does not need the answer,
// whatever Wait says: it returns the zero Answer at once when none is kept.
func (g *GeoJS) LookUpWithoutWaiting(ctx context.Context, client netip.Prefix) Answer {
answer, _ := g.answerOrWait(ctx, client, false)
return answer
}
// Kept returns client's answer, if one is kept, without asking GeoJS. // Kept returns client's answer, if one is kept, without asking GeoJS.
func (g *GeoJS) Kept(client netip.Prefix) (Answer, bool) { func (g *GeoJS) Kept(client netip.Prefix) (Answer, bool) {
g.mu.Lock() g.mu.Lock()
@@ -271,9 +263,9 @@ func (g *GeoJS) Load(answers []Answer) {
// answerOrWait returns client's kept answer if it has one. Otherwise it // answerOrWait returns client's kept answer if it has one. Otherwise it
// puts the client among those waiting if there is room, has GeoJS asked // puts the client among those waiting if there is room, has GeoJS asked
// about them if it can be, and returns what to wait on for the answer, or // about them if it can be, and returns what to wait on for the answer, or
// nil when there is nothing to wait for or mustWait is false. // nil when there is nothing to wait for.
func (g *GeoJS) answerOrWait( func (g *GeoJS) answerOrWait(
ctx context.Context, client netip.Prefix, mustWait bool, ctx context.Context, client netip.Prefix,
) (Answer, <-chan struct{}) { ) (Answer, <-chan struct{}) {
g.mu.Lock() g.mu.Lock()
defer g.mu.Unlock() defer g.mu.Unlock()
@@ -291,7 +283,7 @@ func (g *GeoJS) answerOrWait(
g.ask(ctx) g.ask(ctx)
if !mustWait { if !g.wait {
return Answer{}, nil // the answer is not needed before the request goes on return Answer{}, nil // the answer is not needed before the request goes on
} }
+2 -35
View File
@@ -72,39 +72,6 @@ func TestKeptAnswerIsUsedFor7DaysThenAskedAgain(t *testing.T) {
}) })
} }
func TestLookUpWithoutWaitingAsksGeoJSAndGoesOnAtOnce(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
geojs, clock, g := start()
client := netip.MustParsePrefix("203.0.113.9/32")
// Wait is set, and GeoJS does not answer.
geojs.set(hanging)
began := time.Now()
answer := g.LookUpWithoutWaiting(t.Context(), client)
if waited := time.Since(began); waited != 0 || answer != (lookup.Answer{}) {
t.Errorf("got %+v after %s, want no answer at once", answer, waited)
}
waitForRequests(t, geojs, 1)
wantAsked(t, geojs, 0, "203.0.113.9")
// That request is abandoned, and has failed once this returns. GeoJS
// answers when it is asked again, and the answer is kept.
time.Sleep(timeout)
synctest.Wait()
geojs.set(answering)
waitForCountry(t, g, clock, client, germany)
if got := g.LookUpWithoutWaiting(t.Context(), client).Country; got != germany {
t.Errorf("the kept answer gives the country %q, want %q", got, germany)
}
})
}
func TestNewClientWaitsAtMostOneSecondThenCountsAsNotFound(t *testing.T) { func TestNewClientWaitsAtMostOneSecondThenCountsAsNotFound(t *testing.T) {
t.Parallel() t.Parallel()
@@ -156,8 +123,8 @@ func TestRequestWaitsAsLongAsTheTimeoutSaysAndGeoJSIsAbandonedAfterIt(t *testing
t.Parallel() t.Parallel()
synctest.Test(t, func(t *testing.T) { synctest.Test(t, func(t *testing.T) {
// A timeout longer than the default, and a GeoJS that does not // A timeout longer than the default second, and a GeoJS that does
// answer. // not answer.
const longerTimeout = 3 * time.Second const longerTimeout = 3 * time.Second
m := metrics.New(1, "app") m := metrics.New(1, "app")
+1 -1
View File
@@ -17,7 +17,7 @@ import (
const fileMode = 0o600 const fileMode = 0o600
// Network is what a lookup database holds about a netblock, of the fields // Network is what a lookup database holds about a netblock, of the fields
// sww reads: its AS number, such as AS64496, the AS's name, and // smallwebwaf reads: its AS number, such as AS64496, the AS's name, and
// its country, such as DE. // its country, such as DE.
type Network struct { type Network struct {
ASN string ASN string
+7 -7
View File
@@ -25,7 +25,7 @@ type busiest struct {
requests *prometheus.CounterVec requests *prometheus.CounterVec
requestBytes *prometheus.CounterVec requestBytes *prometheus.CounterVec
responseBytes *prometheus.CounterVec responseBytes *prometheus.CounterVec
// refused are, by country, the requests the country list refused; nil // refused are, by country, the requests the country lists refused; nil
// by AS number. // by AS number.
refused *prometheus.CounterVec refused *prometheus.CounterVec
@@ -41,8 +41,8 @@ type busiest struct {
// for the topN busiest countries. // for the topN busiest countries.
func newCountries(topN int) *busiest { func newCountries(topN int) *busiest {
countries := newBusiest(topN, "country", "the client's country") countries := newBusiest(topN, "country", "the client's country")
countries.refused = counterVec("sww_country_list_refusals_total", countries.refused = counterVec("smallwebwaf_country_list_refusals_total",
"Requests SWW_EXCLUSIVELY_ALLOWED_COUNTRIES refused, by the client's country.", "Requests the country lists refused, by the client's country.",
[]string{"country"}) []string{"country"})
return countries return countries
@@ -61,11 +61,11 @@ func newBusiest(topN int, label, description string) *busiest {
return &busiest{ return &busiest{
topN: topN, topN: topN,
requests: counterVec("sww_"+label+"_requests_total", requests: counterVec("smallwebwaf_"+label+"_requests_total",
"Requests, by "+description+".", by), "Requests, by "+description+".", by),
requestBytes: counterVec("sww_"+label+"_request_bytes_total", requestBytes: counterVec("smallwebwaf_"+label+"_request_bytes_total",
"Request body bytes, by "+description+".", by), "Request body bytes, by "+description+".", by),
responseBytes: counterVec("sww_"+label+"_response_bytes_total", responseBytes: counterVec("smallwebwaf_"+label+"_response_bytes_total",
"Response body bytes, by "+description+".", by), "Response body bytes, by "+description+".", by),
seen: map[string]int64{}, seen: map[string]int64{},
top: map[string]bool{}, top: map[string]bool{},
@@ -88,7 +88,7 @@ func (b *busiest) Collect(ch chan<- prometheus.Metric) {
} }
// vecs returns the metrics: by AS number, those of requests and bytes; by // vecs returns the metrics: by AS number, those of requests and bytes; by
// country, the refusals by the country list as well. // country, the refusals by the country lists as well.
func (b *busiest) vecs() []*prometheus.CounterVec { func (b *busiest) vecs() []*prometheus.CounterVec {
vecs := []*prometheus.CounterVec{b.requests, b.requestBytes, b.responseBytes} vecs := []*prometheus.CounterVec{b.requests, b.requestBytes, b.responseBytes}
if b.refused != nil { if b.refused != nil {
+101 -111
View File
@@ -1,7 +1,6 @@
// Package metrics keeps sww's Prometheus metrics, as // Package metrics keeps smallwebwaf's Prometheus metrics, as the "Metrics
// docs/metrics.md lists them, and serves them in the Prometheus text // endpoint" section of SPEC.md lists them, and serves them in the
// format, as the "Metrics endpoint" section of SPEC.md requires. No // Prometheus text format. No metric carries a client's address.
// metric carries a client's address.
package metrics package metrics
import ( import (
@@ -22,21 +21,22 @@ import (
"sneak.berlin/go/smallwebwaf/internal/rules" "sneak.berlin/go/smallwebwaf/internal/rules"
) )
// Metrics are sww's metrics. They are safe for concurrent use. // Metrics are smallwebwaf's metrics. They are safe for concurrent use.
type Metrics struct { type Metrics struct {
// registry gives every metric registered with it the label instance. // registry gives every metric registered with it the label instance.
registry prometheus.Registerer registry prometheus.Registerer
handler http.Handler handler http.Handler
inFlight prometheus.Gauge inFlight prometheus.Gauge
requests *prometheus.CounterVec requests *prometheus.CounterVec
requestBytes *prometheus.CounterVec requestBytes *prometheus.CounterVec
responseBytes *prometheus.CounterVec responseBytes *prometheus.CounterVec
requestDuration prometheus.Histogram requestDuration prometheus.Histogram
upstreamDuration prometheus.Histogram upstreamDuration prometheus.Histogram
rateLimitHits *prometheus.CounterVec rateLimitHits *prometheus.CounterVec
offences *prometheus.CounterVec sizeAndTimeLimitHits *prometheus.CounterVec
wafMatches *prometheus.CounterVec offences *prometheus.CounterVec
wafMatches *prometheus.CounterVec
// ruleMatches are made by AddRules, and reputationHits by // ruleMatches are made by AddRules, and reputationHits by
// AddReputation. // AddReputation.
ruleMatches *prometheus.CounterVec ruleMatches *prometheus.CounterVec
@@ -62,8 +62,8 @@ type Metrics struct {
// New returns the metrics, with the Go runtime's and the process's own. // New returns the metrics, with the Go runtime's and the process's own.
// topN is how many countries and how many AS numbers get series of their // topN is how many countries and how many AS numbers get series of their
// own (SWW_METRICS_TOP_N). Every metric carries instanceName // own (SWWAF_METRICS_TOP_N). Every metric carries instanceName
// (SWW_INSTANCE_NAME) as its label instance. // (SWWAF_INSTANCE_NAME) as its label instance.
// //
//nolint:funlen // a few lines for each metric, a list that grows with them //nolint:funlen // a few lines for each metric, a list that grows with them
func New(topN int, instanceName string) *Metrics { func New(topN int, instanceName string) *Metrics {
@@ -76,60 +76,63 @@ func New(topN int, instanceName string) *Metrics {
prometheus.Labels{"instance": instanceName}, registry), prometheus.Labels{"instance": instanceName}, registry),
handler: promhttp.HandlerFor(registry, promhttp.HandlerOpts{}), handler: promhttp.HandlerFor(registry, promhttp.HandlerOpts{}),
inFlight: prometheus.NewGauge(prometheus.GaugeOpts{ inFlight: prometheus.NewGauge(prometheus.GaugeOpts{
Name: "sww_requests_in_flight", Name: "smallwebwaf_requests_in_flight",
Help: "Requests under way.", Help: "Requests under way.",
}), }),
requests: counterVec("sww_requests_total", requests: counterVec("smallwebwaf_requests_total",
"Requests, by the class of their status and their action.", byStatus), "Requests, by the class of their status and their action.", byStatus),
requestBytes: counterVec("sww_request_bytes_total", requestBytes: counterVec("smallwebwaf_request_bytes_total",
"Request body bytes, by the class of the status and the action.", "Request body bytes, by the class of the status and the action.",
byStatus), byStatus),
responseBytes: counterVec("sww_response_bytes_total", responseBytes: counterVec("smallwebwaf_response_bytes_total",
"Response body bytes, by the class of the status and the action.", "Response body bytes, by the class of the status and the action.",
byStatus), byStatus),
requestDuration: prometheus.NewHistogram(prometheus.HistogramOpts{ requestDuration: prometheus.NewHistogram(prometheus.HistogramOpts{
Name: "sww_request_duration_seconds", Name: "smallwebwaf_request_duration_seconds",
Help: "How long requests took, from their arrival to their end.", Help: "How long requests took, from their arrival to their end.",
}), }),
upstreamDuration: prometheus.NewHistogram(prometheus.HistogramOpts{ upstreamDuration: prometheus.NewHistogram(prometheus.HistogramOpts{
Name: "sww_upstream_duration_seconds", Name: "smallwebwaf_upstream_duration_seconds",
Help: "How long requests passed to the app took, from then to their end.", Help: "How long requests passed to the app took, from then to their end.",
}), }),
rateLimitHits: counterVec("sww_rate_limit_hits_total", rateLimitHits: counterVec("smallwebwaf_rate_limit_hits_total",
"Requests that broke a rate limit, a byte limit or the error burst, by "+ "Requests that broke a rate limit, a byte limit or the error burst, by "+
"its window and its kind, requests, bytes or refusals.", "its window and its kind, requests, bytes or refusals.",
[]string{"window", "kind"}), []string{"window", "kind"}),
offences: counterVec("sww_offences_total", sizeAndTimeLimitHits: counterVec("smallwebwaf_size_and_time_limit_hits_total",
"Requests that passed a size or time limit, by its setting.",
[]string{"limit"}),
offences: counterVec("smallwebwaf_offences_total",
"Offences, by kind.", []string{"kind"}), "Offences, by kind.", []string{"kind"}),
wafMatches: counterVec("sww_waf_matches_total", wafMatches: counterVec("smallwebwaf_waf_matches_total",
"Requests that matched a rule of the Core Rule Set, by SWW_WAF_MODE "+ "Requests that matched a rule of the Core Rule Set, by SWWAF_WAF_MODE "+
"and the rule's id.", []string{"mode", "rule_id"}), "and the rule's id.", []string{"mode", "rule_id"}),
countries: newCountries(topN), countries: newCountries(topN),
asns: newASNs(topN), asns: newASNs(topN),
GeoJSRequests: prometheus.NewCounter(prometheus.CounterOpts{ GeoJSRequests: prometheus.NewCounter(prometheus.CounterOpts{
Name: "sww_geojs_requests_total", Name: "smallwebwaf_geojs_requests_total",
Help: "Requests to GeoJS.", Help: "Requests to GeoJS.",
}), }),
GeoJSFailures: prometheus.NewCounter(prometheus.CounterOpts{ GeoJSFailures: prometheus.NewCounter(prometheus.CounterOpts{
Name: "sww_geojs_failures_total", Name: "smallwebwaf_geojs_failures_total",
Help: "Requests to GeoJS that failed.", Help: "Requests to GeoJS that failed.",
}), }),
GeoJSUnanswered: prometheus.NewCounter(prometheus.CounterOpts{ GeoJSUnanswered: prometheus.NewCounter(prometheus.CounterOpts{
Name: "sww_geojs_unanswered_total", Name: "smallwebwaf_geojs_unanswered_total",
Help: "Requests that needed their client's answer from GeoJS and " + Help: "Requests that needed their client's answer from GeoJS and " +
"went on without it, because GeoJS had not given it in time.", "went on without it, because GeoJS had not given it in time.",
}), }),
stateFileWrites: counterVec("sww_state_file_writes_total", stateFileWrites: counterVec("smallwebwaf_state_file_writes_total",
"Writes of each state file.", byFile), "Writes of each state file.", byFile),
stateFileWriteFailures: counterVec("sww_state_file_write_failures_total", stateFileWriteFailures: counterVec("smallwebwaf_state_file_write_failures_total",
"Writes of each state file that failed.", byFile), "Writes of each state file that failed.", byFile),
stateFileLastWrite: gaugeVec("sww_state_file_last_write_timestamp_seconds", stateFileLastWrite: gaugeVec("smallwebwaf_state_file_last_write_timestamp_seconds",
"When each state file was last written, in seconds since 1970.", byFile), "When each state file was last written, in seconds since 1970.", byFile),
stateFileSize: gaugeVec("sww_state_file_size_bytes", stateFileSize: gaugeVec("smallwebwaf_state_file_size_bytes",
"The size of each state file, as it was last written.", byFile), "The size of each state file, as it was last written.", byFile),
stateFileEditsTakenIn: counterVec("sww_state_file_edits_taken_in_total", stateFileEditsTakenIn: counterVec("smallwebwaf_state_file_edits_taken_in_total",
"Edits of each state file taken in while running.", byFile), "Edits of each state file taken in while running.", byFile),
stateFileEditsSetAside: counterVec("sww_state_file_edits_set_aside_total", stateFileEditsSetAside: counterVec("smallwebwaf_state_file_edits_set_aside_total",
"Edits of each state file renamed to <name>.bad because they did not parse.", "Edits of each state file renamed to <name>.bad because they did not parse.",
byFile), byFile),
} }
@@ -139,7 +142,7 @@ func New(topN int, instanceName string) *Metrics {
collectors.NewProcessCollector(collectors.ProcessCollectorOpts{}), collectors.NewProcessCollector(collectors.ProcessCollectorOpts{}),
m.inFlight, m.requests, m.requestBytes, m.responseBytes, m.inFlight, m.requests, m.requestBytes, m.responseBytes,
m.requestDuration, m.upstreamDuration, m.requestDuration, m.upstreamDuration,
m.rateLimitHits, m.offences, m.wafMatches, m.rateLimitHits, m.sizeAndTimeLimitHits, m.offences, m.wafMatches,
m.countries, m.asns, m.countries, m.asns,
m.GeoJSRequests, m.GeoJSFailures, m.GeoJSUnanswered, m.GeoJSRequests, m.GeoJSFailures, m.GeoJSUnanswered,
m.stateFileWrites, m.stateFileWriteFailures, m.stateFileWrites, m.stateFileWriteFailures,
@@ -161,7 +164,7 @@ func (m *Metrics) AddBansAndClients(
bans.CauseLimit, bans.CauseAttack, bans.CauseAdmin, bans.CauseCrowdSec, bans.CauseLimit, bans.CauseAttack, bans.CauseAdmin, bans.CauseCrowdSec,
} { } {
m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{ m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_bans_made_total", Name: "smallwebwaf_bans_made_total",
Help: "Bans made, by cause.", Help: "Bans made, by cause.",
ConstLabels: prometheus.Labels{"cause": cause}, ConstLabels: prometheus.Labels{"cause": cause},
}, func() float64 { }, func() float64 {
@@ -171,7 +174,7 @@ func (m *Metrics) AddBansAndClients(
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_active_bans", Name: "smallwebwaf_active_bans",
Help: "Bans active now, the permanent ones included.", Help: "Bans active now, the permanent ones included.",
}, func() float64 { }, func() float64 {
active, _ := ledger.Count(now()) active, _ := ledger.Count(now())
@@ -179,7 +182,7 @@ func (m *Metrics) AddBansAndClients(
return float64(active) return float64(active)
}), }),
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_permanent_bans", Name: "smallwebwaf_permanent_bans",
Help: "Permanent bans not lifted.", Help: "Permanent bans not lifted.",
}, func() float64 { }, func() float64 {
_, permanent := ledger.Count(now()) _, permanent := ledger.Count(now())
@@ -187,7 +190,7 @@ func (m *Metrics) AddBansAndClients(
return float64(permanent) return float64(permanent)
}), }),
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_tracked_clients", Name: "smallwebwaf_tracked_clients",
Help: "Clients in the table of clients.", Help: "Clients in the table of clients.",
}, func() float64 { }, func() float64 {
return float64(limiter.Len()) return float64(limiter.Len())
@@ -200,13 +203,13 @@ func (m *Metrics) AddBansAndClients(
// ruleFiles, read as the metrics are asked for. It is called once, before // ruleFiles, read as the metrics are asked for. It is called once, before
// RuleMatched. // RuleMatched.
func (m *Metrics) AddRules(ruleFiles *rules.Files) { func (m *Metrics) AddRules(ruleFiles *rules.Files) {
m.ruleMatches = counterVec("sww_rule_matches_total", m.ruleMatches = counterVec("smallwebwaf_rule_matches_total",
"Requests that matched a rule of the rule files, by its id and action.", "Requests that matched a rule of the rule files, by its id and action.",
[]string{"rule_id", "action"}) []string{"rule_id", "action"})
m.registry.MustRegister(m.ruleMatches, m.registry.MustRegister(m.ruleMatches,
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_rules_loaded", Name: "smallwebwaf_rules_loaded",
Help: "Rules loaded from the rule files.", Help: "Rules loaded from the rule files.",
}, func() float64 { }, func() float64 {
return float64(ruleFiles.Len()) return float64(ruleFiles.Len())
@@ -214,25 +217,25 @@ func (m *Metrics) AddRules(ruleFiles *rules.Files) {
} }
// AddRemoteLog adds the metrics of sending the log lines to // AddRemoteLog adds the metrics of sending the log lines to
// SWW_LOG_REMOTE_URL, read from remote as the metrics are asked for: the // SWWAF_LOG_REMOTE_URL, read from remote as the metrics are asked for: the
// lines sent, those dropped, and those waiting in the buffer. // lines sent, those dropped, and those waiting in the buffer.
func (m *Metrics) AddRemoteLog(remote *remotelog.Sender) { func (m *Metrics) AddRemoteLog(remote *remotelog.Sender) {
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_remote_log_lines_sent_total", Name: "smallwebwaf_remote_log_lines_sent_total",
Help: "Log lines sent to SWW_LOG_REMOTE_URL.", Help: "Log lines sent to SWWAF_LOG_REMOTE_URL.",
}, func() float64 { }, func() float64 {
return float64(remote.Sent()) return float64(remote.Sent())
}), }),
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_remote_log_lines_dropped_total", Name: "smallwebwaf_remote_log_lines_dropped_total",
Help: "Log lines dropped: the oldest in a full buffer, and those " + Help: "Log lines dropped: the oldest in a full buffer, and those " +
"whose sending failed.", "whose sending failed.",
}, func() float64 { }, func() float64 {
return float64(remote.Dropped()) return float64(remote.Dropped())
}), }),
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_remote_log_buffer_depth", Name: "smallwebwaf_remote_log_buffer_depth",
Help: "Log lines in the buffer, waiting to be sent.", Help: "Log lines in the buffer, waiting to be sent.",
}, func() float64 { }, func() float64 {
return float64(remote.Depth()) return float64(remote.Depth())
@@ -248,13 +251,13 @@ func (m *Metrics) AddRemoteLog(remote *remotelog.Sender) {
func (m *Metrics) AddLookupFile(lastRead func() time.Time, readFailures func() int) { func (m *Metrics) AddLookupFile(lastRead func() time.Time, readFailures func() int) {
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_lookup_database_last_read_timestamp_seconds", Name: "smallwebwaf_lookup_database_last_read_timestamp_seconds",
Help: "When the lookup database in use was read, in seconds since 1970.", Help: "When the lookup database in use was read, in seconds since 1970.",
}, func() float64 { }, func() float64 {
return float64(lastRead().Unix()) return float64(lastRead().Unix())
}), }),
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_lookup_database_read_failures_total", Name: "smallwebwaf_lookup_database_read_failures_total",
Help: "Replacements of the lookup database that could not be read.", Help: "Replacements of the lookup database that could not be read.",
}, func() float64 { }, func() float64 {
return float64(readFailures()) return float64(readFailures())
@@ -275,7 +278,7 @@ const sourceLabel = "source"
// copy in use was fetched, and for a zone, the queries made and those that // copy in use was fetched, and for a zone, the queries made and those that
// failed. It is called once, before ReputationHit. // failed. It is called once, before ReputationHit.
func (m *Metrics) AddReputation(lists *reputation.Lists, dnsbl *reputation.DNSBL) { func (m *Metrics) AddReputation(lists *reputation.Lists, dnsbl *reputation.DNSBL) {
m.reputationHits = counterVec("sww_reputation_hits_total", m.reputationHits = counterVec("smallwebwaf_reputation_hits_total",
"Requests whose client a blocklist, the CrowdSec decision list, a DNSBL "+ "Requests whose client a blocklist, the CrowdSec decision list, a DNSBL "+
"zone or AbuseIPDB lists, by the list's URL, the zone, or abuseipdb.", "zone or AbuseIPDB lists, by the list's URL, the zone, or abuseipdb.",
[]string{sourceLabel}) []string{sourceLabel})
@@ -294,7 +297,7 @@ func (m *Metrics) AddReputation(lists *reputation.Lists, dnsbl *reputation.DNSBL
m.addReputationFailures(source, func() int { return lists.Failures(listURL) }) m.addReputationFailures(source, func() int { return lists.Failures(listURL) })
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_reputation_last_fetch_timestamp_seconds", Name: "smallwebwaf_reputation_last_fetch_timestamp_seconds",
Help: "When the copy of the list in use was fetched, in seconds since " + Help: "When the copy of the list in use was fetched, in seconds since " +
"1970, or 0 while there is none.", "1970, or 0 while there is none.",
ConstLabels: source, ConstLabels: source,
@@ -313,7 +316,7 @@ func (m *Metrics) AddReputation(lists *reputation.Lists, dnsbl *reputation.DNSBL
// AddAbuseIPDB adds the metrics of AbuseIPDB, with the source abuseipdb, // AddAbuseIPDB adds the metrics of AbuseIPDB, with the source abuseipdb,
// read from abuseIPDB as the metrics are asked for: the checks made, those // read from abuseIPDB as the metrics are asked for: the checks made, those
// that failed, and how many checks the day's budget has left. It is // that failed, and how many checks the day's budget has left. It is
// called once, after AddReputation, while SWW_ABUSEIPDB_KEY is set. // called once, after AddReputation, while SWWAF_ABUSEIPDB_KEY is set.
func (m *Metrics) AddAbuseIPDB(abuseIPDB *reputation.AbuseIPDB) { func (m *Metrics) AddAbuseIPDB(abuseIPDB *reputation.AbuseIPDB) {
source := prometheus.Labels{sourceLabel: reputation.AbuseIPDBSource} source := prometheus.Labels{sourceLabel: reputation.AbuseIPDBSource}
@@ -321,8 +324,8 @@ func (m *Metrics) AddAbuseIPDB(abuseIPDB *reputation.AbuseIPDB) {
m.addReputationFailures(source, abuseIPDB.Failures) m.addReputationFailures(source, abuseIPDB.Failures)
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewGaugeFunc(prometheus.GaugeOpts{ prometheus.NewGaugeFunc(prometheus.GaugeOpts{
Name: "sww_reputation_daily_budget_remaining", Name: "smallwebwaf_reputation_daily_budget_remaining",
Help: "Checks of the day's SWW_ABUSEIPDB_DAILY_BUDGET not yet spent.", Help: "Checks of the day's SWWAF_ABUSEIPDB_DAILY_BUDGET not yet spent.",
ConstLabels: source, ConstLabels: source,
}, func() float64 { }, func() float64 {
return float64(abuseIPDB.BudgetLeft()) return float64(abuseIPDB.BudgetLeft())
@@ -348,29 +351,29 @@ func (m *Metrics) AddAlerts(queue *alerts.Queue) {
m.registry.MustRegister( m.registry.MustRegister(
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_alerts_sent_total", Name: "smallwebwaf_alerts_sent_total",
Help: "Alerts the destination took.", Help: "Alerts the destination took.",
ConstLabels: destination, ConstLabels: destination,
}, func() float64 { }, func() float64 {
return float64(queue.Counts(name).Sent) return float64(queue.Counts(name).Sent)
}), }),
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_alerts_failed_total", Name: "smallwebwaf_alerts_failed_total",
Help: "Requests to the destination that failed.", Help: "Requests to the destination that failed.",
ConstLabels: destination, ConstLabels: destination,
}, func() float64 { }, func() float64 {
return float64(queue.Counts(name).Failed) return float64(queue.Counts(name).Failed)
}), }),
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_alerts_suppressed_total", Name: "smallwebwaf_alerts_suppressed_total",
Help: "Alerts held back: repeats within SWW_ALERT_COOLDOWN, and " + Help: "Alerts held back: repeats within SWWAF_ALERT_COOLDOWN, and " +
"alerts past SWW_ALERT_MAX_PER_HOUR, for the hour's summary.", "alerts past SWWAF_ALERT_MAX_PER_HOUR, for the hour's summary.",
ConstLabels: destination, ConstLabels: destination,
}, func() float64 { }, func() float64 {
return float64(queue.Suppressed()) return float64(queue.Suppressed())
}), }),
prometheus.NewCounterFunc(prometheus.CounterOpts{ prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_alerts_dropped_total", Name: "smallwebwaf_alerts_dropped_total",
Help: "Alerts dropped, the oldest first, from a full queue, and " + Help: "Alerts dropped, the oldest first, from a full queue, and " +
"alerts given up as the destination refused them.", "alerts given up as the destination refused them.",
ConstLabels: destination, ConstLabels: destination,
@@ -391,26 +394,36 @@ func (m *Metrics) RequestStarted() {
m.inFlight.Inc() m.inFlight.Inc()
} }
// RequestEnded counts a request that has ended without being passed to the app, // RequestEnded counts a request that has ended, from its log line. limit
// from its log line. duration is how long the request took. // is the setting whose size or time limit the request passed, "" if none.
func (m *Metrics) RequestEnded(line *requestlog.Line, duration time.Duration) { // duration is how long the request took, and upstreamDuration how long it
m.inFlight.Dec() // took from when it was passed to the app, zero if it was not.
m.count(line, duration, 0) func (m *Metrics) RequestEnded(
} line *requestlog.Line, limit string, duration, upstreamDuration time.Duration,
// RequestAllowed counts a question of rproxy's, answered allow, as no longer
// under way. RequestReported counts the request it was about.
func (m *Metrics) RequestAllowed() {
m.inFlight.Dec()
}
// RequestReported counts a request rproxy passed to the app, from what its
// report says, which line holds: duration is how long the request took, and
// upstreamDuration how long it took from when it was passed to the app.
func (m *Metrics) RequestReported(
line *requestlog.Line, duration, upstreamDuration time.Duration,
) { ) {
m.count(line, duration, upstreamDuration) m.inFlight.Dec()
class := statusClass(line.Status)
m.requests.WithLabelValues(class, line.Action).Inc()
m.requestBytes.WithLabelValues(class, line.Action).Add(float64(line.RequestBytes))
m.responseBytes.WithLabelValues(class, line.Action).Add(float64(line.ResponseBytes))
m.requestDuration.Observe(duration.Seconds())
if upstreamDuration > 0 {
m.upstreamDuration.Observe(upstreamDuration.Seconds())
}
if limit != "" {
m.sizeAndTimeLimitHits.WithLabelValues(limit).Inc()
}
if line.Country != "" {
m.countries.add(line.Country, line)
}
if line.ASN != "" {
m.asns.add(line.ASN, line)
}
} }
// LimitHit counts a request that broke a rate limit, a byte limit or the // LimitHit counts a request that broke a rate limit, a byte limit or the
@@ -424,10 +437,11 @@ func (m *Metrics) LimitHit(hit ratelimit.Hit) {
// them. // them.
func (m *Metrics) Offences(r ratelimit.Request) { func (m *Metrics) Offences(r ratelimit.Request) {
for kind, committed := range map[string]bool{ for kind, committed := range map[string]bool{
"limit": r.BrokeLimit, "limit": r.BrokeLimit,
"attack": r.Attack, "attack": r.Attack,
"blocked_by_block_rule": r.BlockedByBlockRule, "rule_blocked": r.RuleBlocked,
"waf_blocked": r.WAFBlocked, "waf_blocked": r.WAFBlocked,
"token_refused": r.TokenRefused,
} { } {
if committed { if committed {
m.offences.WithLabelValues(kind).Inc() m.offences.WithLabelValues(kind).Inc()
@@ -442,7 +456,7 @@ func (m *Metrics) RuleMatched(id, action string) {
} }
// WAFMatched counts a request that matched the Core Rule Set's rule id, // WAFMatched counts a request that matched the Core Rule Set's rule id,
// with SWW_WAF_MODE at mode. // with SWWAF_WAF_MODE at mode.
func (m *Metrics) WAFMatched(mode string, id int) { func (m *Metrics) WAFMatched(mode string, id int) {
m.wafMatches.WithLabelValues(mode, strconv.Itoa(id)).Inc() m.wafMatches.WithLabelValues(mode, strconv.Itoa(id)).Inc()
} }
@@ -467,7 +481,7 @@ func (m *Metrics) StateFileWritten(name string, size int, err error) {
} }
// StateFileEditTakenIn counts an admin's edit of the state file name // StateFileEditTakenIn counts an admin's edit of the state file name
// taken in while sww runs. // taken in while smallwebwaf runs.
func (m *Metrics) StateFileEditTakenIn(name string) { func (m *Metrics) StateFileEditTakenIn(name string) {
m.stateFileEditsTakenIn.WithLabelValues(name).Inc() m.stateFileEditsTakenIn.WithLabelValues(name).Inc()
} }
@@ -478,35 +492,11 @@ func (m *Metrics) StateFileEditSetAside(name string) {
m.stateFileEditsSetAside.WithLabelValues(name).Inc() m.stateFileEditsSetAside.WithLabelValues(name).Inc()
} }
// count counts a request that has ended, as RequestEnded and RequestReported
// describe.
func (m *Metrics) count(
line *requestlog.Line, duration, upstreamDuration time.Duration,
) {
class := statusClass(line.Status)
m.requests.WithLabelValues(class, line.Action).Inc()
m.requestBytes.WithLabelValues(class, line.Action).Add(float64(line.RequestBytes))
m.responseBytes.WithLabelValues(class, line.Action).Add(float64(line.ResponseBytes))
m.requestDuration.Observe(duration.Seconds())
if upstreamDuration > 0 {
m.upstreamDuration.Observe(upstreamDuration.Seconds())
}
if line.Country != "" {
m.countries.add(line.Country, line)
}
if line.ASN != "" {
m.asns.add(line.ASN, line)
}
}
// addReputationQueries adds the counter of the queries to source, a DNSBL // addReputationQueries adds the counter of the queries to source, a DNSBL
// zone, or of the checks of clients with AbuseIPDB, which count tells. // zone, or of the checks of clients with AbuseIPDB, which count tells.
func (m *Metrics) addReputationQueries(source prometheus.Labels, count func() int) { func (m *Metrics) addReputationQueries(source prometheus.Labels, count func() int) {
m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{ m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_reputation_queries_total", Name: "smallwebwaf_reputation_queries_total",
Help: "Queries to the DNSBL zone, or checks of clients with AbuseIPDB.", Help: "Queries to the DNSBL zone, or checks of clients with AbuseIPDB.",
ConstLabels: source, ConstLabels: source,
}, func() float64 { }, func() float64 {
@@ -519,7 +509,7 @@ func (m *Metrics) addReputationQueries(source prometheus.Labels, count func() in
// that failed, which count tells. // that failed, which count tells.
func (m *Metrics) addReputationFailures(source prometheus.Labels, count func() int) { func (m *Metrics) addReputationFailures(source prometheus.Labels, count func() int) {
m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{ m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{
Name: "sww_reputation_failures_total", Name: "smallwebwaf_reputation_failures_total",
Help: "Fetches of the list, queries to the DNSBL zone, or checks with " + Help: "Fetches of the list, queries to the DNSBL zone, or checks with " +
"AbuseIPDB, that failed.", "AbuseIPDB, that failed.",
ConstLabels: source, ConstLabels: source,
@@ -1,4 +1,4 @@
package discriminator package proxy
import ( import (
"bytes" "bytes"
@@ -9,6 +9,7 @@ import (
"io" "io"
"net/http" "net/http"
"net/netip" "net/netip"
"os"
"strings" "strings"
"time" "time"
@@ -40,22 +41,16 @@ var (
errNotAddress = errors.New("is not an address, such as 203.0.113.9") errNotAddress = errors.New("is not an address, such as 203.0.113.9")
) )
// answerHealth answers a request for the health endpoint. // answerAdmin answers a request for smallwebwaf itself, under
func (rq *request) answerHealth() { // /_smallwebwaf/, once it has passed the checks. Each endpoint needs a
rq.line.Action = requestlog.ActionAdmin // token, sent as Authorization: Bearer <token>: the metrics
// Set here rather than left to Go's server, which would set it only // SWWAF_METRICS_TOKEN, the others SWWAF_ADMIN_TOKEN. A request without
// after the log line has taken the response's headers. // it is refused with 401, which counts toward the error burst. An
rq.out.Header().Set("Content-Type", "text/plain; charset=utf-8") // endpoint whose token is unset answers 404, as any other request under
_, _ = io.WriteString(rq.out, "ok\n") // /_smallwebwaf/ does.
}
// answerAdmin answers a request for one of discriminator's own endpoints. Each
// needs a token, sent as Authorization: Bearer <token>: the metrics
// SWW_METRICS_TOKEN, the others SWW_ADMIN_TOKEN. A request without it is
// refused with 401. An endpoint whose token is unset answers 404, as any other
// path does.
func (rq *request) answerAdmin() { func (rq *request) answerAdmin() {
rq.line.Action = requestlog.ActionAdmin rq.line.Action = requestlog.ActionAdmin
rq.startClientResponseTimeout()
token, answer := rq.endpoint() token, answer := rq.endpoint()
@@ -63,8 +58,12 @@ func (rq *request) answerAdmin() {
case token == "": case token == "":
http.Error(rq.out, http.StatusText(http.StatusNotFound), http.StatusNotFound) http.Error(rq.out, http.StatusText(http.StatusNotFound), http.StatusNotFound)
case !hasToken(rq.in, token): case !hasToken(rq.in, token):
rq.tokenRefused = true
rq.out.Header().Set("WWW-Authenticate", "Bearer") rq.out.Header().Set("WWW-Authenticate", "Bearer")
http.Error(rq.out, http.StatusText(http.StatusUnauthorized), http.StatusUnauthorized) rq.answer(refusal{
status: http.StatusUnauthorized,
action: requestlog.ActionAdmin,
})
default: default:
answer() answer()
} }
@@ -121,7 +120,26 @@ type banToAdd struct {
// an admin, from now for the duration the body gives, with its reason, // an admin, from now for the duration the body gives, with its reason,
// and answers with that ban. // and answers with that ban.
func (rq *request) addBan() { func (rq *request) addBan() {
// The body must arrive within SWWAF_CLIENT_REQUEST_TIMEOUT, as any
// other request's must.
rq.stopReadingBody(rq.clientRequestDeadline())
toAdd, err := rq.readBanToAdd() toAdd, err := rq.readBanToAdd()
if refused := rq.refused.Load(); refused != nil {
rq.answer(*refused) // the body is over SWWAF_REQUEST_MAX_BYTES
return
}
if errors.Is(err, os.ErrDeadlineExceeded) {
rq.answer(refusal{
status: http.StatusRequestTimeout,
action: requestlog.ActionTimedOut,
limit: "SWWAF_CLIENT_REQUEST_TIMEOUT",
})
return
}
var ( var (
netblock netip.Prefix netblock netip.Prefix
@@ -150,9 +168,12 @@ func (rq *request) addBan() {
// readBanToAdd reads the body of POST BansPath: a JSON object with // readBanToAdd reads the body of POST BansPath: a JSON object with
// nothing but whitespace after it, in at most banBodyMaxBytes. // nothing but whitespace after it, in at most banBodyMaxBytes.
func (rq *request) readBanToAdd() (banToAdd, error) { func (rq *request) readBanToAdd() (banToAdd, error) {
data, err := io.ReadAll(http.MaxBytesReader(nil, rq.in.Body, banBodyMaxBytes)) var body io.ReadCloser = http.NoBody
rq.requestBytes = int64(len(data)) if rq.body != nil {
body = rq.body
}
data, err := io.ReadAll(http.MaxBytesReader(nil, body, banBodyMaxBytes))
if err != nil { if err != nil {
return banToAdd{}, fmt.Errorf("%w: %w", errNotBanToAdd, err) return banToAdd{}, fmt.Errorf("%w: %w", errNotBanToAdd, err)
} }
@@ -250,9 +271,9 @@ type clientAnswer struct {
Bans []state.BanEntry `json:"bans"` Bans []state.BanEntry `json:"bans"`
} }
// showClient answers GET ClientsPath<ip> with what discriminator knows of the client: // showClient answers GET ClientsPath<ip> with what smallwebwaf knows of
// its counters, its history, which holds its country as last looked up and its // the client: its counters, its history, which holds its country as last
// offences, and its bans with their notes. // looked up and its offences, and its bans with their notes.
func (rq *request) showClient() { func (rq *request) showClient() {
addr, err := pathAddress(rq.in.URL.Path, ClientsPath) addr, err := pathAddress(rq.in.URL.Path, ClientsPath)
if err != nil { if err != nil {
@@ -1,27 +1,30 @@
package discriminator_test package proxy_test
import ( import (
"encoding/json" "encoding/json"
"net/http" "net/http"
"net/netip" "net/netip"
"reflect" "reflect"
"strconv"
"strings" "strings"
"testing" "testing"
"time" "time"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/state" "sneak.berlin/go/smallwebwaf/internal/state"
) )
const ( const (
adminToken = "SWW_ADMIN_TOKEN" //nolint:gosec // the setting's name adminToken = "SWWAF_ADMIN_TOKEN" //nolint:gosec // the setting's name
// adminSecret is the SWW_ADMIN_TOKEN the tests set, and adminBearer // adminSecret is the SWWAF_ADMIN_TOKEN the tests set, and adminBearer
// how a request carries it. // how a request carries it.
adminSecret = "fedcba9876543210fedcba9876543210" adminSecret = "fedcba9876543210fedcba9876543210"
adminBearer = "Bearer " + adminSecret adminBearer = "Bearer " + adminSecret
// adminClient is the client the tests' admin sends its requests from.
adminClient = "192.0.2.10"
// banOtherClient is the body of a request to ban otherClient for an // banOtherClient is the body of a request to ban otherClient for an
// hour. // hour.
banOtherClient = `{"netblock": "` + otherClient + `", "duration": "1h", ` + banOtherClient = `{"netblock": "` + otherClient + `", "duration": "1h", ` +
@@ -40,7 +43,8 @@ func TestAdminEndpointsAreOffWhileTheTokenIsUnset(t *testing.T) {
// An empty token does not match the unset one either. // An empty token does not match the unset one either.
for _, authorization := range []string{adminBearer, bearer, "Bearer ", ""} { for _, authorization := range []string{adminBearer, bearer, "Bearer ", ""} {
for _, e := range adminEndpoints() { for _, e := range adminEndpoints() {
s.adminRequest(authorization, e.method, e.path, e.body, http.StatusNotFound) s.adminRequest(adminClient, authorization, e.method, e.path, e.body,
http.StatusNotFound, requestlog.ActionAdmin)
} }
} }
@@ -67,8 +71,8 @@ func TestAdminEndpointsNeedTheAdminToken(t *testing.T) {
for _, authorization := range []string{ for _, authorization := range []string{
"", bearer, "Bearer " + strings.ToUpper(adminSecret), "Basic " + adminSecret, "", bearer, "Bearer " + strings.ToUpper(adminSecret), "Basic " + adminSecret,
} { } {
got := s.adminRequest(authorization, e.method, e.path, e.body, got := s.adminRequest(adminClient, authorization, e.method, e.path, e.body,
http.StatusUnauthorized) http.StatusUnauthorized, requestlog.ActionAdmin)
if got.header.Get("WWW-Authenticate") != "Bearer" { if got.header.Get("WWW-Authenticate") != "Bearer" {
t.Errorf("%s %s with %q was answered without WWW-Authenticate: Bearer", t.Errorf("%s %s with %q was answered without WWW-Authenticate: Bearer",
e.method, e.path, authorization) e.method, e.path, authorization)
@@ -86,13 +90,13 @@ func TestAdminEndpointsNeedTheAdminToken(t *testing.T) {
} }
} }
// Any other request under /_sww/ is not found. // Any other request under /_smallwebwaf/ is not found.
for _, e := range []adminEndpoint{ for _, e := range []adminEndpoint{
{http.MethodPut, discriminator.BansPath, banOtherClient}, {http.MethodPut, proxy.BansPath, banOtherClient},
{http.MethodDelete, discriminator.BansPath, ""}, {http.MethodDelete, proxy.BansPath, ""},
{http.MethodGet, discriminator.BansPath + "/" + otherClient, ""}, {http.MethodGet, proxy.BansPath + "/" + otherClient, ""},
{http.MethodPost, discriminator.ClientsPath + otherClient, ""}, {http.MethodPost, proxy.ClientsPath + otherClient, ""},
{http.MethodGet, strings.TrimSuffix(discriminator.ClientsPath, "/"), ""}, {http.MethodGet, strings.TrimSuffix(proxy.ClientsPath, "/"), ""},
} { } {
s.admin(e.method, e.path, e.body, http.StatusNotFound) s.admin(e.method, e.path, e.body, http.StatusNotFound)
} }
@@ -118,10 +122,10 @@ func TestBanAddedListedAndLiftedThroughTheEndpoints(t *testing.T) {
Reason: "probes for logins", Reason: "probes for logins",
} }
wantBans(t, s.admin(http.MethodPost, discriminator.BansPath, banOtherClient, wantBans(t, s.admin(http.MethodPost, proxy.BansPath, banOtherClient, http.StatusOK),
http.StatusOK), want) want)
line := s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) line := s.get(client, http.StatusForbidden, requestlog.ActionBanned)
if line.BanExpires != requestlog.FormatTime(expires) { if line.BanExpires != requestlog.FormatTime(expires) {
t.Errorf("the ban ends at %s, want %s", line.BanExpires, expires) t.Errorf("the ban ends at %s, want %s", line.BanExpires, expires)
} }
@@ -129,7 +133,7 @@ func TestBanAddedListedAndLiftedThroughTheEndpoints(t *testing.T) {
// Its notes count the request it refused. // Its notes count the request it refused.
want.Notes.Requests, want.Notes.Refused = 1, 1 want.Notes.Requests, want.Notes.Refused = 1, 1
wantBans(t, s.admin(http.MethodGet, discriminator.BansPath, "", http.StatusOK), want) wantBans(t, s.admin(http.MethodGet, proxy.BansPath, "", http.StatusOK), want)
// Ten minutes on, lifting the bans on client lifts that one, which is // Ten minutes on, lifting the bans on client lifts that one, which is
// kept, marked lifted. // kept, marked lifted.
@@ -138,13 +142,13 @@ func TestBanAddedListedAndLiftedThroughTheEndpoints(t *testing.T) {
lifted := clk.Now() lifted := clk.Now()
want.Lifted = &lifted want.Lifted = &lifted
wantBans(t, s.admin(http.MethodDelete, discriminator.BansPath+"/"+client, "", wantBans(t, s.admin(http.MethodDelete, proxy.BansPath+"/"+client, "",
http.StatusOK), want) http.StatusOK), want)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
wantBans(t, s.admin(http.MethodGet, discriminator.BansPath, "", http.StatusOK), want) wantBans(t, s.admin(http.MethodGet, proxy.BansPath, "", http.StatusOK), want)
// No ban on it is active any more. // No ban on it is active any more.
s.admin(http.MethodDelete, discriminator.BansPath+"/"+client, "", http.StatusNotFound) s.admin(http.MethodDelete, proxy.BansPath+"/"+client, "", http.StatusNotFound)
} }
func TestBanToAddGivesItsNetblockAndDuration(t *testing.T) { func TestBanToAddGivesItsNetblockAndDuration(t *testing.T) {
@@ -181,8 +185,7 @@ func TestBanToAddGivesItsNetblockAndDuration(t *testing.T) {
want.Expires = &expires want.Expires = &expires
} }
wantBans(t, s.admin(http.MethodPost, discriminator.BansPath, body, http.StatusOK), wantBans(t, s.admin(http.MethodPost, proxy.BansPath, body, http.StatusOK), want)
want)
} }
} }
@@ -251,8 +254,7 @@ func TestBanToAddThatCannotBeReadIsRefused(t *testing.T) {
"request body too large", "request body too large",
}, },
} { } {
got := s.admin(http.MethodPost, discriminator.BansPath, tc.body, got := s.admin(http.MethodPost, proxy.BansPath, tc.body, http.StatusBadRequest)
http.StatusBadRequest)
if !strings.Contains(string(got.body), tc.want) { if !strings.Contains(string(got.body), tc.want) {
t.Errorf("%.80s was answered %q, want it to say %q", tc.body, got.body, tc.want) t.Errorf("%.80s was answered %q, want it to say %q", tc.body, got.body, tc.want)
} }
@@ -263,12 +265,64 @@ func TestBanToAddThatCannotBeReadIsRefused(t *testing.T) {
} }
} }
func TestBanToAddOverTheRequestSizeLimitIsRefused(t *testing.T) {
t.Parallel()
s, _, server := startWithClock(t, "", map[string]string{
adminToken: adminSecret,
requestMaxBytes: "16",
})
// Sent in a chunk, its length is not announced, so that it is found
// over SWWAF_REQUEST_MAX_BYTES only as it is read.
chunk := `{"netblock": "203.0.113.9", "duration": "1h"}`
s.adminRequest(adminClient, adminBearer+"\r\nTransfer-Encoding: chunked",
http.MethodPost, proxy.BansPath,
strconv.FormatInt(int64(len(chunk)), 16)+"\r\n"+chunk+"\r\n0\r\n\r\n",
http.StatusRequestEntityTooLarge, requestlog.ActionTooLarge)
if held := server.Ledger.Snapshot(); len(held) != 0 {
t.Errorf("the ledger holds %+v, want no ban", held)
}
}
func TestBanToAddSlowerThanTheClientRequestTimeoutIsRefused(t *testing.T) {
t.Parallel()
s, _, server := startWithClock(t, "", map[string]string{
adminToken: adminSecret,
metricsToken: token,
clientRequestTimeout: shortTimeoutSetting,
})
// The chunk announces 256 bytes and the rest of it never comes, so only
// the timeout ends the wait. A hold-up of the test process can only
// make the answer later, so the time is checked only for not being
// shorter than the timeout.
start := time.Now()
s.adminRequest(adminClient, adminBearer+"\r\nTransfer-Encoding: chunked",
http.MethodPost, proxy.BansPath, "100\r\n"+`{"netblock": "203.0.113.9", `,
http.StatusRequestTimeout, requestlog.ActionTimedOut)
if took := time.Since(start); took < shortTimeout {
t.Errorf("answered after %s, before the timeout of %s ran out", took, shortTimeout)
}
wantLimitHits(t, s.addr, clientRequestTimeout, 1)
if held := server.Ledger.Snapshot(); len(held) != 0 {
t.Errorf("the ledger holds %+v, want no ban", held)
}
}
func TestClientEndpointShowsTheClientAndItsBans(t *testing.T) { func TestClientEndpointShowsTheClientAndItsBans(t *testing.T) {
t.Parallel() t.Parallel()
s, clk, _ := startWithClock(t, "", map[string]string{ s, clk, _ := startWithClock(t, "", map[string]string{
adminToken: adminSecret, adminToken: adminSecret,
rateLimitPerMinute: "2", rateLimitPerMinute: "2",
rateLimitExemptNets: adminClient,
}) })
start := clk.Now() start := clk.Now()
@@ -276,7 +330,7 @@ func TestClientEndpointShowsTheClientAndItsBans(t *testing.T) {
// limit of two a minute, and bans it. // limit of two a minute, and bans it.
s.get(otherClient, http.StatusOK, requestlog.ActionForward) s.get(otherClient, http.StatusOK, requestlog.ActionForward)
s.get(otherClient, http.StatusOK, requestlog.ActionForward) s.get(otherClient, http.StatusOK, requestlog.ActionForward)
s.get(otherClient, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(otherClient, http.StatusForbidden, requestlog.ActionRateLimited)
// Asked about by its address in IPv6 form too. // Asked about by its address in IPv6 form too.
for _, addr := range []string{otherClient, "::ffff:" + otherClient} { for _, addr := range []string{otherClient, "::ffff:" + otherClient} {
@@ -285,8 +339,7 @@ func TestClientEndpointShowsTheClientAndItsBans(t *testing.T) {
Bans []state.BanEntry `json:"bans"` Bans []state.BanEntry `json:"bans"`
} }
decode(t, s.admin(http.MethodGet, discriminator.ClientsPath+addr, "", decode(t, s.admin(http.MethodGet, proxy.ClientsPath+addr, "", http.StatusOK), &got)
http.StatusOK), &got)
if got.Client == nil { if got.Client == nil {
t.Fatalf("%s: no client", addr) t.Fatalf("%s: no client", addr)
@@ -308,18 +361,71 @@ func TestClientEndpointShowsTheClientAndItsBans(t *testing.T) {
// Of an address no request came from and no ban covers, nothing is // Of an address no request came from and no ban covers, nothing is
// known. // known.
got := s.admin(http.MethodGet, discriminator.ClientsPath+"198.51.100.99", "", got := s.admin(http.MethodGet, proxy.ClientsPath+"198.51.100.99", "", http.StatusOK)
http.StatusOK)
if string(got.body) != "{\n \"client\": null,\n \"bans\": []\n}\n" { if string(got.body) != "{\n \"client\": null,\n \"bans\": []\n}\n" {
t.Errorf("an unknown client is answered\n%s", got.body) t.Errorf("an unknown client is answered\n%s", got.body)
} }
s.admin(http.MethodGet, discriminator.ClientsPath+"203.0.113", "", s.admin(http.MethodGet, proxy.ClientsPath+"203.0.113", "", http.StatusBadRequest)
http.StatusBadRequest) s.admin(http.MethodDelete, proxy.BansPath+"/203.0.113.0/24", "",
s.admin(http.MethodDelete, discriminator.BansPath+"/203.0.113.0/24", "",
http.StatusBadRequest) http.StatusBadRequest)
} }
func TestBannedClientIsRefusedAtTheEndpointsEvenWithTheToken(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{adminToken: adminSecret})
s.admin(http.MethodPost, proxy.BansPath, banOtherClient, http.StatusOK)
// otherClient cannot lift its own ban either.
for _, e := range adminEndpoints() {
s.adminRequest(otherClient, adminBearer, e.method, e.path, e.body,
http.StatusForbidden, requestlog.ActionBanned)
}
}
func TestAdminRequestsCountTowardTheLimits(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{
adminToken: adminSecret,
rateLimitPerMinute: "2",
})
// A request refused for a missing token and one answered count toward
// the limit of two a minute, so the next breaks it.
s.adminRequest(client, "", http.MethodGet, proxy.BansPath, "",
http.StatusUnauthorized, requestlog.ActionAdmin)
s.adminRequest(client, adminBearer, http.MethodGet, proxy.BansPath, "",
http.StatusOK, requestlog.ActionAdmin)
s.adminRequest(client, adminBearer, http.MethodGet, proxy.BansPath, "",
http.StatusForbidden, requestlog.ActionRateLimited)
}
func TestClientInAllowNetsSkipsTheChecksButNeedsTheToken(t *testing.T) {
t.Parallel()
const allowed = "192.0.2.60" // in SWWAF_ALLOW_NETS
s, clk, server := startWithClock(t, "", map[string]string{
adminToken: adminSecret,
allowNets: allowed,
rateLimitPerMinute: "1",
})
// A ban on it refuses nothing, and its requests are not counted.
server.Ledger.BanForAdmin(netip.MustParsePrefix(allowed+"/32"), clk.Now(),
time.Time{}, "")
for range 2 {
s.adminRequest(allowed, "", http.MethodGet, proxy.BansPath, "",
http.StatusUnauthorized, requestlog.ActionAdmin)
s.adminRequest(allowed, adminBearer, http.MethodGet, proxy.BansPath, "",
http.StatusOK, requestlog.ActionAdmin)
}
}
func TestAdminEndpointsNeedTheTokenInObserveMode(t *testing.T) { func TestAdminEndpointsNeedTheTokenInObserveMode(t *testing.T) {
t.Parallel() t.Parallel()
@@ -329,7 +435,8 @@ func TestAdminEndpointsNeedTheTokenInObserveMode(t *testing.T) {
}) })
for _, e := range adminEndpoints() { for _, e := range adminEndpoints() {
s.adminRequest("", e.method, e.path, e.body, http.StatusUnauthorized) s.adminRequest(adminClient, "", e.method, e.path, e.body,
http.StatusUnauthorized, requestlog.ActionAdmin)
} }
if held := server.Ledger.Snapshot(); len(held) != 0 { if held := server.Ledger.Snapshot(); len(held) != 0 {
@@ -337,50 +444,56 @@ func TestAdminEndpointsNeedTheTokenInObserveMode(t *testing.T) {
} }
} }
// adminEndpoint is a request to an endpoint SWW_ADMIN_TOKEN opens. // adminEndpoint is a request to an endpoint SWWAF_ADMIN_TOKEN opens.
type adminEndpoint struct { type adminEndpoint struct {
method, path, body string method, path, body string
} }
// adminEndpoints returns a request to each endpoint SWW_ADMIN_TOKEN // adminEndpoints returns a request to each endpoint SWWAF_ADMIN_TOKEN
// opens: listing the bans, banning otherClient for an hour, lifting the // opens: listing the bans, banning otherClient for an hour, lifting the
// bans on otherClient, and asking about otherClient. // bans on otherClient, and asking about otherClient.
func adminEndpoints() []adminEndpoint { func adminEndpoints() []adminEndpoint {
return []adminEndpoint{ return []adminEndpoint{
{http.MethodGet, discriminator.BansPath, ""}, {http.MethodGet, proxy.BansPath, ""},
{http.MethodPost, discriminator.BansPath, banOtherClient}, {http.MethodPost, proxy.BansPath, banOtherClient},
{http.MethodDelete, discriminator.BansPath + "/" + otherClient, ""}, {http.MethodDelete, proxy.BansPath + "/" + otherClient, ""},
{http.MethodGet, discriminator.ClientsPath + otherClient, ""}, {http.MethodGet, proxy.ClientsPath + otherClient, ""},
} }
} }
// admin sends a request with method for path, with body, to discriminator's own // admin sends a request with method for path, with body, from
// address, with the admin token, and checks that it is answered with status, its // adminClient, with the admin token, and checks that it is answered with
// log line's action admin. It returns the answer. // status, its log line's action admin. It returns the answer.
func (s *sender) admin(method, path, body string, status int) answer { func (s *sender) admin(method, path, body string, status int) answer {
s.t.Helper() s.t.Helper()
return s.adminRequest(adminBearer, method, path, body, status) return s.adminRequest(adminClient, adminBearer, method, path, body, status,
requestlog.ActionAdmin)
} }
// adminRequest is admin with authorization as the request's Authorization header // adminRequest sends a request with method for path, with body, from the
// unless it is "". // client at from, with authorization as its Authorization header unless
// it is "", and checks its answer's status and its log line's action, as
// request does. authorization may end in more header lines. A body that
// is not "" has its length announced, unless authorization names
// Transfer-Encoding. It returns the answer.
func (s *sender) adminRequest( func (s *sender) adminRequest(
authorization, method, path, body string, status int, from, authorization, method, path, body string, status int, action string,
) answer { ) answer {
s.t.Helper() s.t.Helper()
req := newRequest(s.t, method, s.discriminatorAddr, path, strings.NewReader(body)) var header []string
if authorization != "" { if authorization != "" {
req.Header.Set("Authorization", authorization) header = append(header, "Authorization: "+authorization)
} }
got := do(s.t, req) if body != "" && !strings.Contains(authorization, "Transfer-Encoding") {
wantStatus(s.t, got, status) header = append(header, "Content-Length: "+strconv.Itoa(len(body)))
}
line := s.out.endedLines(s.t, s.sent+1)[s.sent] _, got := s.requestWithBody(method, from, path, strings.Join(header, "\r\n"),
s.sent++ body, status, action)
wantLine(s.t, line, status, requestlog.ActionAdmin)
return got return got
} }
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"maps" "maps"
@@ -10,15 +10,15 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
const ( const (
alertWebhookURL = "SWW_ALERT_WEBHOOK_URL" alertWebhookURL = "SWWAF_ALERT_WEBHOOK_URL"
alertMaxPerHour = "SWW_ALERT_MAX_PER_HOUR" alertMaxPerHour = "SWWAF_ALERT_MAX_PER_HOUR"
// alertInstance is the instance every alert of these tests gives. // alertInstance is the instance every alert of these tests gives.
alertInstance = "fsn1app1/blog" alertInstance = "fsn1app1/gitea"
) )
func TestBanForABrokenLimitRaisesABanAlertWithItsNotes(t *testing.T) { func TestBanForABrokenLimitRaisesABanAlertWithItsNotes(t *testing.T) {
@@ -31,14 +31,14 @@ func TestBanForABrokenLimitRaisesABanAlertWithItsNotes(t *testing.T) {
start := clk.Now() start := clk.Now()
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
netblock := netip.MustParsePrefix("203.0.113.0/24") netblock := netip.MustParsePrefix("203.0.113.0/24")
ban := server.Ledger.Bans(netblock)[0] ban := server.Ledger.Bans(netblock)[0]
// A request refused under the ban raises no other alert. // A request refused under the ban raises no other alert.
clk.advance(time.Minute) clk.advance(time.Minute)
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
wantAlerts(t, queue, banAlert(alerts.EventBan, start, client, bans.Ban{ wantAlerts(t, queue, banAlert(alerts.EventBan, start, client, bans.Ban{
Netblock: netblock, Cause: bans.CauseLimit, Netblock: netblock, Cause: bans.CauseLimit,
@@ -62,24 +62,22 @@ func TestAttackBanRaisesABanAlertThenAPermanentBanAlert(t *testing.T) {
// The probe bans the client for seven days, and its next request makes // The probe bans the client for seven days, and its next request makes
// the ban permanent. The request after that changes nothing. // the ban permanent. The request after that changes nothing.
s.request(client, "/.env", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.request(client, "/.env", http.StatusForbidden, requestlog.ActionBanned)
attackBan := server.Ledger.Bans(netblock)[0] attackBan := server.Ledger.Bans(netblock)[0]
clk.advance(time.Minute) clk.advance(time.Minute)
s.get(client, http.StatusForbidden, requestlog.ActionPermanentlyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
permanentBan := server.Ledger.Bans(netblock)[0] permanentBan := server.Ledger.Bans(netblock)[0]
s.get(client, http.StatusForbidden, requestlog.ActionPermanentlyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
// Another client's probe after its first ban has run out without a // Another client's probe after its first ban has run out without a
// request makes a permanent ban at once. // request makes a permanent ban at once.
s.request(otherClient, "/.env", http.StatusForbidden, s.request(otherClient, "/.env", http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionTemporarilyBanned)
clk.advance(7 * 24 * time.Hour) clk.advance(7 * 24 * time.Hour)
s.request(otherClient, "/.env", http.StatusForbidden, s.request(otherClient, "/.env", http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionPermanentlyBanned)
otherBans := server.Ledger.Bans(other) otherBans := server.Ledger.Bans(other)
@@ -203,7 +201,7 @@ func TestObserveModeWorksOutABanOnlyWhenItsAlertWouldBeSent(t *testing.T) {
// never sent them, and returns the queue they wait in as well. // never sent them, and returns the queue they wait in as well.
func startWithAlerts( func startWithAlerts(
t *testing.T, env map[string]string, t *testing.T, env map[string]string,
) (*sender, *clock, *discriminator.Server, *alerts.Queue) { ) (*sender, *clock, *proxy.Server, *alerts.Queue) {
t.Helper() t.Helper()
return startAppWithAlerts(t, func(http.ResponseWriter, *http.Request) {}, env) return startAppWithAlerts(t, func(http.ResponseWriter, *http.Request) {}, env)
@@ -212,23 +210,21 @@ func startWithAlerts(
// startAppWithAlerts is startWithAlerts in front of the app handler. // startAppWithAlerts is startWithAlerts in front of the app handler.
func startAppWithAlerts( func startAppWithAlerts(
t *testing.T, handler http.HandlerFunc, env map[string]string, t *testing.T, handler http.HandlerFunc, env map[string]string,
) (*sender, *clock, *discriminator.Server, *alerts.Queue) { ) (*sender, *clock, *proxy.Server, *alerts.Queue) {
t.Helper() t.Helper()
app := startApp(t, handler) app := startApp(t, handler)
clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 0, 0, time.UTC)} clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 0, 0, time.UTC)}
settings := map[string]string{ settings := map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
alertWebhookURL: "https://alerts.example/sww", alertWebhookURL: "https://alerts.example/smallwebwaf",
instanceName: alertInstance, instanceName: alertInstance,
} }
maps.Copy(settings, env) maps.Copy(settings, env)
addr, out, server, queue := startProxyWithAlerts(t, app.URL, "", clk.Now, settings) addr, out, server, queue := startProxyWithAlerts(t, app.URL, "", clk.Now, settings)
s := &sender{t: t, addr: addr, discriminatorAddr: server.Addr, out: out} return &sender{t: t, addr: addr, out: out}, clk, server, queue
return s, clk, server, queue
} }
// banAlert returns the alert for event, raised by a request from client at // banAlert returns the alert for event, raised by a request from client at
@@ -241,7 +237,6 @@ func banAlert(
Instance: alertInstance, Instance: alertInstance,
Time: raised, Time: raised,
Event: event, Event: event,
Host: appHost,
Client: netip.MustParseAddr(client), Client: netip.MustParseAddr(client),
Netblock: ban.Netblock, Netblock: ban.Netblock,
Reason: ban.Reason, Reason: ban.Reason,
@@ -1,4 +1,4 @@
package discriminator package proxy
import ( import (
"net/netip" "net/netip"
@@ -15,11 +15,9 @@ func TestWithEveryAnomalyThresholdOffARequestIsNotCounted(t *testing.T) {
// anomaly counters, nor a clock, and the request no response: reading // anomaly counters, nor a clock, and the request no response: reading
// any of them to count the request panics. // any of them to count the request panics.
rq := &request{ rq := &request{
decision: decision{ h: &handler{config: &config.Config{LookupSource: "geojs"}},
client: netip.MustParseAddr("203.0.113.9"), client: netip.MustParseAddr("203.0.113.9"),
lookedUp: true, lookedUp: true,
},
h: &handler{config: &config.Config{LookupSource: "geojs"}},
} }
defer func() { defer func() {
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"maps" "maps"
@@ -13,7 +13,7 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/anomaly" "sneak.berlin/go/smallwebwaf/internal/anomaly"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
@@ -21,11 +21,11 @@ import (
// The anomaly thresholds: the prefix of a scope followed by the end of a // The anomaly thresholds: the prefix of a scope followed by the end of a
// count. // count.
const ( const (
anomalyClient = "SWW_ANOMALY_CLIENT_" anomalyClient = "SWWAF_ANOMALY_CLIENT_"
anomalyNet = "SWW_ANOMALY_NET_" anomalyNet = "SWWAF_ANOMALY_NET_"
anomalyASN = "SWW_ANOMALY_ASN_" anomalyASN = "SWWAF_ANOMALY_ASN_"
anomalyTotal = "SWW_ANOMALY_TOTAL_" anomalyTotal = "SWWAF_ANOMALY_TOTAL_"
anomalyWatch = "SWW_WATCH_" anomalyWatch = "SWWAF_WATCH_"
requestsPerMinute = "REQUESTS_PER_MINUTE" requestsPerMinute = "REQUESTS_PER_MINUTE"
requestsPerHour = "REQUESTS_PER_HOUR" requestsPerHour = "REQUESTS_PER_HOUR"
@@ -35,9 +35,9 @@ const (
// The other anomaly settings. // The other anomaly settings.
const ( const (
anomalyNetV4Prefix = "SWW_ANOMALY_NET_V4_PREFIX" anomalyNetV4Prefix = "SWWAF_ANOMALY_NET_V4_PREFIX"
anomalyNetV6Prefix = "SWW_ANOMALY_NET_V6_PREFIX" anomalyNetV6Prefix = "SWWAF_ANOMALY_NET_V6_PREFIX"
watchNets = "SWW_WATCH_NETS" watchNets = "SWWAF_WATCH_NETS"
) )
const ( const (
@@ -117,7 +117,6 @@ func TestEachScopeAndWindowOverItsThresholdAlertsOncePerCooldown(t *testing.T) {
Instance: alertInstance, Instance: alertInstance,
Time: start, Time: start,
Event: alerts.EventAnomaly, Event: alerts.EventAnomaly,
Host: appHost,
Client: netip.MustParseAddr(client), Client: netip.MustParseAddr(client),
Netblock: scope.netblock, Netblock: scope.netblock,
ASN: asnDE, ASN: asnDE,
@@ -164,9 +163,9 @@ func TestEveryRequestIsCountedWhateverIsDoneWithIt(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
allowed = "192.0.2.7" // in SWW_ALLOW_NETS allowed = "192.0.2.7" // in SWWAF_ALLOW_NETS
exempt = "192.0.2.10" // in SWW_RATE_LIMIT_EXEMPT_NETS exempt = "192.0.2.10" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
denied = "192.0.2.20" // in SWW_DENY_NETS denied = "192.0.2.20" // in SWWAF_DENY_NETS
) )
s, _, _, queue := startAppWithAlerts(t, readAndAnswer, map[string]string{ s, _, _, queue := startAppWithAlerts(t, readAndAnswer, map[string]string{
@@ -187,7 +186,7 @@ func TestEveryRequestIsCountedWhateverIsDoneWithIt(t *testing.T) {
{allowed, "/", http.StatusOK, requestlog.ActionForward}, {allowed, "/", http.StatusOK, requestlog.ActionForward},
{exempt, "/", http.StatusOK, requestlog.ActionForward}, {exempt, "/", http.StatusOK, requestlog.ActionForward},
{client, "/static/app.js", http.StatusOK, requestlog.ActionForward}, {client, "/static/app.js", http.StatusOK, requestlog.ActionForward},
{denied, "/", http.StatusForbidden, requestlog.ActionClientDenied}, {denied, "/", http.StatusForbidden, requestlog.ActionDenied},
} { } {
for range 3 { for range 3 {
s.request(sent.from, sent.path, sent.status, sent.action) s.request(sent.from, sent.path, sent.status, sent.action)
@@ -319,7 +318,7 @@ func TestRequestCountsForTheASNumberGeoJSGivesBeforeItEnds(t *testing.T) {
// kept. // kept.
geojsURL, _, release := startHeldGeoJS(t) geojsURL, _, release := startHeldGeoJS(t)
var server atomic.Pointer[discriminator.Server] var server atomic.Pointer[proxy.Server]
app := startApp(t, func(http.ResponseWriter, *http.Request) { app := startApp(t, func(http.ResponseWriter, *http.Request) {
release() release()
@@ -1,10 +1,7 @@
package discriminator package proxy
// The heuristic active_ban, and the code that makes bans, which several
// heuristics share. active_ban reads SWW_MODE; the bans are the ban ledger's.
import ( import (
"context" "net/http"
"net/netip" "net/netip"
"time" "time"
@@ -15,21 +12,17 @@ import (
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// banResponse is a refusal answered with SWW_BAN_RESPONSE, and logged // banResponse is a refusal answered with SWWAF_BAN_RESPONSE, and logged
// with action. // with action.
func (rq *request) banResponse(action string) *refusal { func (rq *request) banResponse(action string) *refusal {
return &refusal{status: rq.h.config.BanResponse, action: action} return &refusal{status: rq.h.config.BanResponse, action: action}
} }
// activeBan refuses a client a ban covers: a ban on a netblock the client is // banned reports whether a ban on a netblock the client is in covers the
// in, in force at now. It notes for the log line when that ban ends. A request // request at now, and notes for the log line when that ban ends. A
// that makes the ban permanent, or in observe mode would have, raises the alert // request that makes the ban permanent, or in observe mode would have,
// for it. Its figures are the ban's netblock and when it ends. // raises the alert for it.
type activeBan struct{} func (rq *request) banned(now time.Time) bool {
func (activeBan) name() string { return "active_ban" }
func (activeBan) check(_ context.Context, rq *request, now time.Time) *verdict {
check := rq.h.ledger.Check check := rq.h.ledger.Check
if rq.h.config.Observe { if rq.h.config.Observe {
check = rq.h.ledger.Find // the ban refuses nothing, and stays as it is check = rq.h.ledger.Find // the ban refuses nothing, and stays as it is
@@ -45,41 +38,105 @@ func (activeBan) check(_ context.Context, rq *request, now time.Time) *verdict {
rq.alertBan(ban) rq.alertBan(ban)
} }
if !banned { return banned
return nil }
// limitBroken counts the request for the rate limits at now, notes the
// client's counts for the log line, and reports whether the request takes
// the client over a rate limit, as its limit percentage lowers it, which
// breaks it.
func (rq *request) limitBroken(now time.Time) bool {
counts, hit, over := rq.h.limiter.Count(rq.h.clientGroup(rq.client), now,
rq.limitPercent.percent)
rq.line.Counts = counts
if over {
rq.banForLimit(now, hit, rq.h.config.BanResponse)
} }
return &verdict{ return over
action: banAction(ban.Permanent()), }
figures: map[string]any{
figureNetblock: ban.Netblock.String(), "ban_expires": rq.line.BanExpires, // countBytes counts the request's bytes, as countedBytes gives them, for
}, // the byte limits, once its response has ended, and notes the client's
// byte totals for the log line; its requests stay there as the rate limits
// counted them. Only a request passed to the app has them counted, and
// only one the rate limits counted; in observe mode, not one that enforce
// mode would have refused. Bytes that take the client over a byte limit,
// as its limit percentage for the byte limits lowers it, break it; the
// response was passed on whole.
func (rq *request) countBytes() {
if !rq.counted || rq.line.WouldAction != "" {
return
}
now := rq.h.now()
counts, hit, over := rq.h.limiter.CountBytes(rq.h.clientGroup(rq.client), now,
rq.countedBytes(), rq.bytesPercent.percent)
rq.line.Counts.MinuteBytes = counts.MinuteBytes
rq.line.Counts.HourBytes = counts.HourBytes
rq.line.Counts.DayBytes = counts.DayBytes
if over {
rq.banForLimit(now, hit, rq.out.status)
} }
} }
// banAction is the action of a request refused under a ban or for making one: // countRefusal counts the request for the error burst once it has been
// permanent says the ban never runs out. // answered, if smallwebwaf refused it after a rule file match, a trap path
func banAction(permanent bool) string { // or a Core Rule Set match, or for a missing or wrong token, and in
if permanent { // observe mode if enforce mode would have: more than
return requestlog.ActionPermanentlyBanned // SWWAF_ERROR_BURST_THRESHOLD such refusals of the client within a minute
// break a limit. A client in SWWAF_ALLOW_NETS, which the checks skip, is
// not counted, and nothing is while the threshold is off.
func (rq *request) countRefusal() {
cfg := rq.h.config
if cfg.ErrorBurstThreshold == 0 {
return
} }
return requestlog.ActionTemporarilyBanned // In observe mode, a request that enforce mode would have refused
} // before it reached the endpoint has had no token refused there.
tokenRefused := rq.tokenRefused && rq.line.WouldAction == "" &&
// limitFigures are the figures of a heuristic that broke hit, a limit: its !isInside(rq.client, cfg.AllowNets)
// window, the count and the limit. if !rq.attack && !rq.ruleBlocked && !rq.wafBlocked && !tokenRefused {
func limitFigures(hit ratelimit.Hit) map[string]any { return
return map[string]any{
figureWindow: hit.Window, figureCount: hit.Count, figureLimit: hit.Limit,
} }
now := rq.h.now()
hit, over := rq.h.limiter.CountRefusal(rq.h.clientGroup(rq.client), now,
cfg.ErrorBurstThreshold)
if !over {
return
}
// What the client was sent, or in observe mode would have been.
status := rq.out.status
switch rq.line.WouldAction {
case requestlog.ActionRuleBlocked, requestlog.ActionWAFBlocked:
status = http.StatusForbidden
case requestlog.ActionBanned:
status = cfg.BanResponse
}
rq.banForLimit(now, hit, status)
} }
// countedBytes returns the request's bytes, once it has ended, as the // countedBytes returns the request's bytes, once it has ended, as the
// byte limits and the anomaly thresholds count them: the response's body // byte limits and the anomaly thresholds count them: the response's body
// bytes, the request's, or both, as SWW_BYTES_COUNT says. // bytes, the request's, or both, as SWWAF_BYTES_COUNT says. For an
// upgraded connection, such as a WebSocket, which has closed by then, what
// it carried from the app counts with the response's and what it carried
// from the client with the request's.
func (rq *request) countedBytes() int64 { func (rq *request) countedBytes() int64 {
response, request := rq.out.bytes, rq.requestBytes response, request := rq.out.bytes, rq.requestBytes()
if rq.upgraded != nil {
response += rq.upgraded.fromApp.Load()
request += rq.upgraded.toApp.Load()
}
switch rq.h.config.BytesCount { switch rq.h.config.BytesCount {
case "response": case "response":
@@ -94,7 +151,7 @@ func (rq *request) countedBytes() int64 {
// banForLimit bans the client's netblock at now for a broken limit, the // banForLimit bans the client's netblock at now for a broken limit, the
// one hit names, notes the offence for the log line and counts the hit in // one hit names, notes the offence for the log line and counts the hit in
// the metrics. status is what the client was sent, or is sent: // the metrics. status is what the client was sent, or is sent:
// SWW_BAN_RESPONSE for a request over a rate limit, what the report says for // SWWAF_BAN_RESPONSE for a request over a rate limit, the app's answer for
// one whose bytes broke a byte limit, the refusal for one that broke the // one whose bytes broke a byte limit, the refusal for one that broke the
// error burst. The ban's notes give the client's limit percentage for a // error burst. The ban's notes give the client's limit percentage for a
// rate limit or a byte limit; the error burst is not lowered. The ban sets // rate limit or a byte limit; the error burst is not lowered. The ban sets
@@ -161,11 +218,11 @@ func (rq *request) banForLimit(now time.Time, hit ratelimit.Hit, status int) {
// attack, which notes name: the ban rule that matched, or the trap path // attack, which notes name: the ban rule that matched, or the trap path
// asked for. It fills in the rest of the notes. In observe mode it makes // asked for. It fills in the rest of the notes. In observe mode it makes
// no ban, and raises the alert for the ban it would have made, if that // no ban, and raises the alert for the ban it would have made, if that
// alert would be sent. It returns the action for that ban. // alert would be sent.
func (rq *request) banForAttack(now time.Time, notes bans.Notes) string { func (rq *request) banForAttack(now time.Time, notes bans.Notes) {
netblock := rq.h.netblock(rq.client) netblock := rq.h.netblock(rq.client)
if rq.h.config.Observe && !rq.wouldAlertBan(netblock, now, bans.CauseAttack) { if rq.h.config.Observe && !rq.wouldAlertBan(netblock, now, bans.CauseAttack) {
return banAction(rq.h.ledger.WouldBePermanent(netblock, now, bans.CauseAttack)) return
} }
notes.ASN = rq.line.ASN notes.ASN = rq.line.ASN
@@ -181,7 +238,7 @@ func (rq *request) banForAttack(now time.Time, notes bans.Notes) string {
rq.alertBan(ban) rq.alertBan(ban)
} }
return banAction(ban.Permanent()) return
} }
ban, made := rq.h.ledger.BanForAttack(netblock, now, notes) ban, made := rq.h.ledger.BanForAttack(netblock, now, notes)
@@ -190,18 +247,16 @@ func (rq *request) banForAttack(now time.Time, notes bans.Notes) string {
if made { if made {
rq.alertBan(ban) rq.alertBan(ban)
} }
return banAction(ban.Permanent())
} }
// banForCrowdSec bans the client's netblock at now until decision, // banForCrowdSec bans the client's netblock at now until decision,
// CrowdSec's decision on the client, ends. In observe mode it makes no // CrowdSec's decision on the client, ends. In observe mode it makes no
// ban, and raises the alert for the ban it would have made, if that alert // ban, and raises the alert for the ban it would have made, if that alert
// would be sent. It returns the action for that ban. // would be sent.
func (rq *request) banForCrowdSec(now time.Time, decision reputation.Decision) string { func (rq *request) banForCrowdSec(now time.Time, decision reputation.Decision) {
netblock := rq.h.netblock(rq.client) netblock := rq.h.netblock(rq.client)
if rq.h.config.Observe && !rq.wouldAlertBan(netblock, now, bans.CauseCrowdSec) { if rq.h.config.Observe && !rq.wouldAlertBan(netblock, now, bans.CauseCrowdSec) {
return banAction(rq.h.ledger.WouldBePermanent(netblock, now, bans.CauseCrowdSec)) return
} }
notes := bans.Notes{ notes := bans.Notes{
@@ -220,7 +275,7 @@ func (rq *request) banForCrowdSec(now time.Time, decision reputation.Decision) s
rq.alertBan(ban) rq.alertBan(ban)
} }
return banAction(ban.Permanent()) return
} }
ban, made := rq.h.ledger.BanForCrowdSec(netblock, now, decision.Expires, ban, made := rq.h.ledger.BanForCrowdSec(netblock, now, decision.Expires,
@@ -230,14 +285,12 @@ func (rq *request) banForCrowdSec(now time.Time, decision reputation.Decision) s
if made { if made {
rq.alertBan(ban) rq.alertBan(ban)
} }
return banAction(ban.Permanent())
} }
// wouldAlertBan reports whether the alert for a ban on netblock for cause // wouldAlertBan reports whether the alert for a ban on netblock for cause
// made at now would be sent. In observe mode the ban the request would // made at now would be sent. In observe mode the ban the request would
// have made is worked out only then, at most once per // have made is worked out only then, at most once per
// SWW_ALERT_COOLDOWN and never with no webhook set: its notes count the // SWWAF_ALERT_COOLDOWN and never with no webhook set: its notes count the
// netblock's requests, which can mean going through every client. // netblock's requests, which can mean going through every client.
func (rq *request) wouldAlertBan( func (rq *request) wouldAlertBan(
netblock netip.Prefix, now time.Time, cause string, netblock netip.Prefix, now time.Time, cause string,
@@ -270,7 +323,6 @@ func (rq *request) alertBan(ban bans.Ban) {
rq.h.alerts.Raise(alerts.Alert{ rq.h.alerts.Raise(alerts.Alert{
Event: event, Event: event,
Host: rq.site,
Client: rq.client, Client: rq.client,
Netblock: ban.Netblock, Netblock: ban.Netblock,
ASN: ban.Notes.ASN, ASN: ban.Notes.ASN,
@@ -287,11 +339,11 @@ func (rq *request) alertBan(ban bans.Ban) {
func (rq *request) noted(now time.Time, status int) bans.Request { func (rq *request) noted(now time.Time, status int) bans.Request {
return bans.Request{ return bans.Request{
Time: now, Time: now,
Method: rq.line.Method, Method: rq.in.Method,
Host: rq.line.Host, Host: rq.in.Host,
Path: rq.requestURI, Path: rq.in.URL.RequestURI(),
Status: status, Status: status,
UserAgent: rq.line.UserAgent, UserAgent: rq.in.UserAgent(),
} }
} }
@@ -303,7 +355,7 @@ func (rq *request) netblockRequests(netblock netip.Prefix) int64 {
} }
// netblock is the netblock a ban on client covers: its IPv4 address, // netblock is the netblock a ban on client covers: its IPv4 address,
// widened to SWW_BAN_SCOPE_V4_PREFIX, or the IPv6 group clientGroup // widened to SWWAF_BAN_SCOPE_V4_PREFIX, or the IPv6 group clientGroup
// counts it in. // counts it in.
func (h *handler) netblock(client netip.Addr) netip.Prefix { func (h *handler) netblock(client netip.Addr) netip.Prefix {
addr := client.Unmap() addr := client.Unmap()
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"bufio" "bufio"
@@ -9,13 +9,12 @@ import (
"net/netip" "net/netip"
"reflect" "reflect"
"slices" "slices"
"strings"
"sync" "sync"
"testing" "testing"
"time" "time"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
@@ -26,8 +25,6 @@ const (
userAgent = "ban-test/1.0" userAgent = "ban-test/1.0"
// permanent is the log line's ban_expires for a permanent ban. // permanent is the log line's ban_expires for a permanent ban.
permanent = "permanent" permanent = "permanent"
// banResponseClose is the SWW_BAN_RESPONSE that closes the connection.
banResponseClose = "close"
) )
func TestBrokenLimitBansTheClient(t *testing.T) { func TestBrokenLimitBansTheClient(t *testing.T) {
@@ -40,7 +37,7 @@ func TestBrokenLimitBansTheClient(t *testing.T) {
// client for an hour, the default. // client for an hour, the default.
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
line := s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) line := s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
if line.LimitHit != minute || line.Offence != requestlog.OffenceLimit || if line.LimitHit != minute || line.Offence != requestlog.OffenceLimit ||
line.BanExpires != expires { line.BanExpires != expires {
t.Errorf("log line has limit_hit %q, offence %q and ban_expires %q, "+ t.Errorf("log line has limit_hit %q, offence %q and ban_expires %q, "+
@@ -51,7 +48,7 @@ func TestBrokenLimitBansTheClient(t *testing.T) {
// Every request while the ban lasts is refused. // Every request while the ban lasts is refused.
clk.advance(time.Hour - time.Second) clk.advance(time.Hour - time.Second)
line = s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) line = s.get(client, http.StatusForbidden, requestlog.ActionBanned)
if line.BanExpires != expires || line.Offence != "" || line.LimitHit != "" { if line.BanExpires != expires || line.Offence != "" || line.LimitHit != "" {
t.Errorf("log line has ban_expires %q, offence %q and limit_hit %q, "+ t.Errorf("log line has ban_expires %q, offence %q and limit_hit %q, "+
"want %s and neither of the others", line.BanExpires, line.Offence, "want %s and neither of the others", line.BanExpires, line.Offence,
@@ -78,9 +75,7 @@ func TestBanLengthsFollowTheSettings(t *testing.T) {
breakLimit := func() string { breakLimit := func() string {
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
line := s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) return s.get(client, http.StatusForbidden, requestlog.ActionRateLimited).BanExpires
return line.BanExpires
} }
wantExpires := func(got string, length time.Duration) { wantExpires := func(got string, length time.Duration) {
t.Helper() t.Helper()
@@ -91,19 +86,19 @@ func TestBanLengthsFollowTheSettings(t *testing.T) {
} }
} }
// A first ban lasts SWW_LIMIT_BAN_DURATION; one within // A first ban lasts SWWAF_LIMIT_BAN_DURATION; one within
// SWW_LIMIT_BAN_REPEAT_WINDOW after it ended, three times as long. // SWWAF_LIMIT_BAN_REPEAT_WINDOW after it ended, three times as long.
wantExpires(breakLimit(), 10*time.Minute) wantExpires(breakLimit(), 10*time.Minute)
clk.advance(10*time.Minute + time.Hour) clk.advance(10*time.Minute + time.Hour)
wantExpires(breakLimit(), 30*time.Minute) wantExpires(breakLimit(), 30*time.Minute)
// Later than that, SWW_LIMIT_BAN_DURATION again. // Later than that, SWWAF_LIMIT_BAN_DURATION again.
clk.advance(30*time.Minute + time.Hour + time.Second) clk.advance(30*time.Minute + time.Hour + time.Second)
wantExpires(breakLimit(), 10*time.Minute) wantExpires(breakLimit(), 10*time.Minute)
clk.advance(10 * time.Minute) clk.advance(10 * time.Minute)
wantExpires(breakLimit(), 30*time.Minute) wantExpires(breakLimit(), 30*time.Minute)
// 90 minutes would be longer than SWW_MAX_BAN_DURATION: the ban is // 90 minutes would be longer than SWWAF_MAX_BAN_DURATION: the ban is
// permanent. // permanent.
clk.advance(30 * time.Minute) clk.advance(30 * time.Minute)
@@ -113,7 +108,7 @@ func TestBanLengthsFollowTheSettings(t *testing.T) {
} }
clk.advance(365 * 24 * time.Hour) clk.advance(365 * 24 * time.Hour)
s.get(client, http.StatusForbidden, requestlog.ActionPermanentlyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
} }
func TestBanIsNotCountedAndResetsTheCounters(t *testing.T) { func TestBanIsNotCountedAndResetsTheCounters(t *testing.T) {
@@ -125,10 +120,10 @@ func TestBanIsNotCountedAndResetsTheCounters(t *testing.T) {
// client for an hour. // client for an hour.
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
for range 3 { for range 3 {
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
} }
// Later the same day the client has its whole allowance again: the // Later the same day the client has its whole allowance again: the
@@ -137,7 +132,7 @@ func TestBanIsNotCountedAndResetsTheCounters(t *testing.T) {
clk.advance(time.Hour) clk.advance(time.Hour)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
banned := server.Ledger.Bans(netip.MustParsePrefix(client + "/32")) banned := server.Ledger.Bans(netip.MustParsePrefix(client + "/32"))
if len(banned) != 2 || banned[0].Notes.Refused != 3 { if len(banned) != 2 || banned[0].Notes.Refused != 3 {
@@ -150,8 +145,8 @@ func TestBanCoversTheClientsNetblock(t *testing.T) {
// In the IPv4 cases, client breaks the limit; these two are next to it. // In the IPv4 cases, client breaks the limit; these two are next to it.
const ( const (
allowed = "203.0.113.60" // in SWW_ALLOW_NETS allowed = "203.0.113.60" // in SWWAF_ALLOW_NETS
exempt = "203.0.113.50" // in SWW_RATE_LIMIT_EXEMPT_NETS exempt = "203.0.113.50" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
) )
for _, tc := range []struct { for _, tc := range []struct {
@@ -166,7 +161,7 @@ func TestBanCoversTheClientsNetblock(t *testing.T) {
nil, []string{otherClient, exempt}, nil, []string{otherClient, exempt},
}, },
{ {
"the IPv4 netblock SWW_BAN_SCOPE_V4_PREFIX sets", "the IPv4 netblock SWWAF_BAN_SCOPE_V4_PREFIX sets",
map[string]string{banScopeV4Prefix: "24"}, client, map[string]string{banScopeV4Prefix: "24"}, client,
[]string{otherClient, exempt}, []string{"203.0.112.9", allowed}, []string{otherClient, exempt}, []string{"203.0.112.9", allowed},
}, },
@@ -175,7 +170,7 @@ func TestBanCoversTheClientsNetblock(t *testing.T) {
[]string{"2001:db8:5::ffff:1"}, []string{"2001:db8:5:1::1"}, []string{"2001:db8:5::ffff:1"}, []string{"2001:db8:5:1::1"},
}, },
{ {
"the IPv6 netblock SWW_IPV6_GROUP_PREFIX sets", "the IPv6 netblock SWWAF_IPV6_GROUP_PREFIX sets",
map[string]string{ipv6GroupPrefix: "48"}, "2001:db8:7::1", map[string]string{ipv6GroupPrefix: "48"}, "2001:db8:7::1",
[]string{"2001:db8:7:ffff::1"}, []string{"2001:db8:8::1"}, []string{"2001:db8:7:ffff::1"}, []string{"2001:db8:8::1"},
}, },
@@ -192,10 +187,10 @@ func TestBanCoversTheClientsNetblock(t *testing.T) {
s, _, _ := startWithClock(t, "", env) s, _, _ := startWithClock(t, "", env)
s.get(tc.breaker, http.StatusOK, requestlog.ActionForward) s.get(tc.breaker, http.StatusOK, requestlog.ActionForward)
s.get(tc.breaker, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(tc.breaker, http.StatusForbidden, requestlog.ActionRateLimited)
for _, sent := range tc.refused { for _, sent := range tc.refused {
s.get(sent, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(sent, http.StatusForbidden, requestlog.ActionBanned)
} }
for _, sent := range tc.let { for _, sent := range tc.let {
@@ -213,14 +208,14 @@ func TestBannedClientIsRefusedBeforeItsCountryIsLookedUp(t *testing.T) {
lookupTimeout: "1h", lookupTimeout: "1h",
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
banScopeV4Prefix: "24", banScopeV4Prefix: "24",
tagDeny: denyKP, deniedCountries: "kp",
}) })
// fromDE's ban covers otherClient, which is refused unasked about. // fromDE's ban covers otherClient, which is refused unasked about.
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
line := s.get(otherClient, http.StatusForbidden, requestlog.ActionTemporarilyBanned) line := s.get(otherClient, http.StatusForbidden, requestlog.ActionBanned)
if line.Country != "" { if line.Country != "" {
t.Errorf("log line has country %q, want none", line.Country) t.Errorf("log line has country %q, want none", line.Country)
} }
@@ -230,35 +225,19 @@ func TestBannedClientIsRefusedBeforeItsCountryIsLookedUp(t *testing.T) {
} }
} }
func TestRefusalUnderABanNamesItsHeuristicNetblockAndEnd(t *testing.T) {
t.Parallel()
s, clk, _ := startWithClock(t, "", map[string]string{
rateLimitPerMinute: "1", banScopeV4Prefix: "24",
})
expires := requestlog.FormatTime(clk.Now().Add(time.Hour))
s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited)
line := s.get(otherClient, http.StatusForbidden, requestlog.ActionTemporarilyBanned)
wantHeuristic(t, line, "active_ban",
`{"netblock": "`+clientsNet+`", "ban_expires": "`+expires+`"}`)
}
func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) { func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
t.Parallel() t.Parallel()
const denied = "192.0.2.50" // in SWW_DENY_NETS const denied = "192.0.2.50" // in SWWAF_DENY_NETS
for _, tc := range []struct { for _, tc := range []struct {
setting string // "" leaves SWW_BAN_RESPONSE at its default setting string // "" leaves SWWAF_BAN_RESPONSE at its default
status int // 0 is the connection closed without an answer status int // 0 is the connection closed without an answer
}{ }{
{"", http.StatusForbidden}, {"", http.StatusForbidden},
{"403", http.StatusForbidden}, {"403", http.StatusForbidden},
{"429", http.StatusTooManyRequests}, {"429", http.StatusTooManyRequests},
{banResponseClose, 0}, {"close", 0},
} { } {
t.Run(banResponse+"="+tc.setting, func(t *testing.T) { t.Run(banResponse+"="+tc.setting, func(t *testing.T) {
t.Parallel() t.Parallel()
@@ -268,7 +247,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
lookupTimeout: "1h", lookupTimeout: "1h",
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
denyNets: denied, denyNets: denied,
tagDeny: denyKP, deniedCountries: "kp",
} }
if tc.setting != "" { if tc.setting != "" {
@@ -277,11 +256,11 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
s, _, _ := startWithClock(t, geojsURL, env) s, _, _ := startWithClock(t, geojsURL, env)
s.get(denied, tc.status, requestlog.ActionClientDenied) s.get(denied, tc.status, requestlog.ActionDenied)
s.get(fromKP, tc.status, requestlog.ActionClientDenied) s.get(fromKP, tc.status, requestlog.ActionCountryDenied)
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, tc.status, requestlog.ActionClientIsRateLimited) s.get(fromDE, tc.status, requestlog.ActionRateLimited)
s.get(fromDE, tc.status, requestlog.ActionTemporarilyBanned) s.get(fromDE, tc.status, requestlog.ActionBanned)
}) })
} }
} }
@@ -293,15 +272,15 @@ func TestBanNotes(t *testing.T) {
s, clk, server := startWithClock(t, geojsURL, map[string]string{ s, clk, server := startWithClock(t, geojsURL, map[string]string{
lookupTimeout: "1h", lookupTimeout: "1h",
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
tagDeny: denyKP, deniedCountries: "kp",
}) })
start := clk.Now() start := clk.Now()
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.request(fromDE, "/repo/commits?page=2", s.request(fromDE, "/repo/commits?page=2",
http.StatusForbidden, requestlog.ActionClientIsRateLimited) http.StatusForbidden, requestlog.ActionRateLimited)
s.get(fromDE, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
s.get(fromDE, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
netblock := netip.MustParsePrefix(fromDE + "/32") netblock := netip.MustParsePrefix(fromDE + "/32")
want := bans.Ban{ want := bans.Ban{
@@ -344,7 +323,7 @@ func TestBanNotes(t *testing.T) {
// The next ban counts this one among the earlier. // The next ban counts this one among the earlier.
clk.advance(time.Hour) clk.advance(time.Hour)
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
got = ledger.Bans(netblock) got = ledger.Bans(netblock)
if len(got) != 2 || got[1].Notes.EarlierBans != (bans.EarlierBans{Limit: 1}) { if len(got) != 2 || got[1].Notes.EarlierBans != (bans.EarlierBans{Limit: 1}) {
@@ -362,15 +341,15 @@ func TestMaxBansDropsTheBanOfTheNetblockSeenLongestAgo(t *testing.T) {
// One ban is held, so otherClient's ban drops client's. // One ban is held, so otherClient's ban drops client's.
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
s.get(otherClient, http.StatusOK, requestlog.ActionForward) s.get(otherClient, http.StatusOK, requestlog.ActionForward)
s.get(otherClient, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(otherClient, http.StatusForbidden, requestlog.ActionRateLimited)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(otherClient, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(otherClient, http.StatusForbidden, requestlog.ActionBanned)
} }
// clock is the time a test sets, by which sww counts requests and // clock is the time a test sets, by which smallwebwaf counts requests and
// makes bans. // makes bans.
type clock struct { type clock struct {
mu sync.Mutex mu sync.Mutex
@@ -393,14 +372,14 @@ func (c *clock) advance(d time.Duration) {
c.now = c.now.Add(d) c.now = c.now.Add(d)
} }
// startWithClock starts discriminator, and rproxy in front of an app that answers 200, // startWithClock starts smallwebwaf in front of an app that answers 200,
// with the settings in env on top of trusting localhost's // with the settings in env on top of trusting localhost's
// X-Forwarded-For, clients' AS numbers and countries looked up at // X-Forwarded-For, clients' AS numbers and countries looked up at
// geojsURL, and a clock set to midnight, the start of a bucket in every // geojsURL, and a clock set to midnight, the start of a bucket in every
// window. // window.
func startWithClock( func startWithClock(
t *testing.T, geojsURL string, env map[string]string, t *testing.T, geojsURL string, env map[string]string,
) (*sender, *clock, *discriminator.Server) { ) (*sender, *clock, *proxy.Server) {
t.Helper() t.Helper()
app := startApp(t, func(http.ResponseWriter, *http.Request) {}) app := startApp(t, func(http.ResponseWriter, *http.Request) {})
@@ -410,20 +389,18 @@ func startWithClock(
addr, out, server := startProxyWithClock(t, app.URL, geojsURL, clk.Now, settings) addr, out, server := startProxyWithClock(t, app.URL, geojsURL, clk.Now, settings)
return &sender{t: t, addr: addr, discriminatorAddr: server.Addr, out: out}, clk, server return &sender{t: t, addr: addr, out: out}, clk, server
} }
// sender sends requests to rproxy one after another, each on a connection of its // sender sends requests to smallwebwaf one after another, each on a
// own, and checks each one's answer and log line. discriminatorAddr is where // connection of its own, and checks each one's answer and log line. They
// discriminator's own endpoints are, which adminRequest asks. Every request // must be the only requests smallwebwaf is sent, since the log lines are
// discriminator gets must come through the sender, since the log lines are
// matched to them in order. // matched to them in order.
type sender struct { type sender struct {
t *testing.T t *testing.T
addr string addr string
discriminatorAddr string out *output
out *output sent int
sent int
} }
// get sends a GET request for / from the client at from. // get sends a GET request for / from the client at from.
@@ -440,19 +417,22 @@ func (s *sender) get(from string, status int, action string) logLine {
func (s *sender) request(from, path string, status int, action string) logLine { func (s *sender) request(from, path string, status int, action string) logLine {
s.t.Helper() s.t.Helper()
return s.requestWithHeader(from, path, "", status, action) line, _ := s.requestWithHeader(from, path, "", status, action)
return line
} }
// requestWithHeader is request with header, such as "Authorization: // requestWithHeader is request with header, such as "Authorization:
// Bearer x", added to the request unless it is "". // Bearer x", added to the request unless it is "". It returns the body of
// the answer too.
func (s *sender) requestWithHeader( func (s *sender) requestWithHeader(
from, path, header string, status int, action string, from, path, header string, status int, action string,
) logLine { ) (logLine, string) {
s.t.Helper() s.t.Helper()
line, _ := s.requestWithBody(http.MethodGet, from, path, header, "", status, action) line, got := s.requestWithBody(http.MethodGet, from, path, header, "", status, action)
return line return line, string(got.body)
} }
// requestWithBody is requestWithHeader for a request with method, whose // requestWithBody is requestWithHeader for a request with method, whose
@@ -468,14 +448,10 @@ func (s *sender) requestWithBody(
header += "\r\n" header += "\r\n"
} }
// rproxy refuses a request with more than one.
if !strings.Contains(header, "User-Agent:") {
header += "User-Agent: " + userAgent + "\r\n"
}
conn := dial(s.t, s.addr) conn := dial(s.t, s.addr)
send(s.t, conn, method+" "+path+" HTTP/1.1\r\nHost: "+appHost+"\r\n"+ send(s.t, conn, method+" "+path+" HTTP/1.1\r\nHost: "+appHost+
forwardedFor+": "+from+"\r\n"+header+"\r\n"+body) "\r\nUser-Agent: "+userAgent+"\r\n"+forwardedFor+": "+from+"\r\n"+
header+"\r\n"+body)
err := conn.SetReadDeadline(time.Now().Add(waitLimit)) err := conn.SetReadDeadline(time.Now().Add(waitLimit))
if err != nil { if err != nil {
@@ -500,7 +476,7 @@ func (s *sender) requestWithBody(
got.status, status) got.status, status)
} }
line := s.out.endedLines(s.t, s.sent+1)[s.sent] line := s.out.requestLines(s.t, s.sent+1)[s.sent]
s.sent++ s.sent++
wantLine(s.t, line, status, action) wantLine(s.t, line, status, action)
@@ -1,4 +1,4 @@
package discriminator package proxy
import ( import (
"sneak.berlin/go/smallwebwaf/internal/config" "sneak.berlin/go/smallwebwaf/internal/config"
@@ -17,29 +17,28 @@ type percentage struct {
} }
// biasedThresholdsSet reports whether a biased threshold can lower a // biasedThresholdsSet reports whether a biased threshold can lower a
// client's limits by its lookup: SWW_ASN_BYTES_PERCENT or // client's limits: one of its lists is not empty,
// SWW_COUNTRY_BYTES_PERCENT is not empty, SWW_UNKNOWN_LIMIT_PERCENT is // SWWAF_UNKNOWN_LIMIT_PERCENT is below 100, or SWWAF_ASN_LIMIT_PERCENT_URL
// below 100, or SWW_ASN_LIMIT_PERCENT_URL is set. The client's lookup is // is set. The client's lookup is then needed before its request goes on.
// then needed before its request goes on.
func biasedThresholdsSet(cfg *config.Config) bool { func biasedThresholdsSet(cfg *config.Config) bool {
return len(cfg.ASNBytesPercent) > 0 || len(cfg.CountryBytesPercent) > 0 || return len(cfg.ASNLimitPercent) > 0 || len(cfg.CountryLimitPercent) > 0 ||
len(cfg.ASNBytesPercent) > 0 || len(cfg.CountryBytesPercent) > 0 ||
cfg.UnknownLimitPercent < whole || cfg.ASNLimitPercentURL != "" cfg.UnknownLimitPercent < whole || cfg.ASNLimitPercentURL != ""
} }
// limitPercentages returns the 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 tags, its AS number and country // limits and for the byte limits, by its AS number and country as looked
// as looked up, each "" when unknown, and the blocklists, DNSBL zones and // up, each "" when unknown, and the blocklists, DNSBL zones and AbuseIPDB
// AbuseIPDB that list it. Each is the lowest of those the settings give // that list it. Each is the lowest of those the settings give it, the
// it, the first of them in the order below when several are lowest: 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 // percentage SWWAF_ASN_LIMIT_PERCENT gives its AS number, the one the file
// SWW_ASN_LIMIT_PERCENT_URL names gives its AS number, the one // SWWAF_ASN_LIMIT_PERCENT_URL names gives it, the one
// SWW_TAG_LIMIT_PERCENT gives its country= tag, the lowest it gives its // SWWAF_COUNTRY_LIMIT_PERCENT gives its country, for a client without a
// other tags, for a client without a country, unless its request skipped // country, SWWAF_UNKNOWN_LIMIT_PERCENT, for a client a blocklist lists,
// the wait for GeoJS, SWW_UNKNOWN_LIMIT_PERCENT, for a client a blocklist // the percentage of SWWAF_BLOCKLIST_ACTION while it is limit, and for a
// lists, the percentage of SWW_BLOCKLIST_ACTION while it is limit, and // client a DNSBL zone's verdict lists, or whose AbuseIPDB score is a hit,
// for a client a DNSBL zone's verdict lists, or whose AbuseIPDB score is // the percentage of SWWAF_REPUTATION_ACTION while it is limit. For the
// a hit, the percentage of SWW_REPUTATION_ACTION while it is limit. For // byte limits, SWWAF_ASN_BYTES_PERCENT and SWWAF_COUNTRY_BYTES_PERCENT
// 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 // take the place of the first three for an AS number or a country they
// list. // list.
func (rq *request) limitPercentages() (percentage, percentage) { func (rq *request) limitPercentages() (percentage, percentage) {
@@ -47,54 +46,45 @@ func (rq *request) limitPercentages() (percentage, percentage) {
asn, country := rq.line.ASN, rq.line.Country asn, country := rq.line.ASN, rq.line.Country
unknown := percentage{percent: whole} unknown := percentage{percent: whole}
if country == "" && !rq.skippedLookupWait { if country == "" {
unknown = percentage{cfg.UnknownLimitPercent, "SWW_UNKNOWN_LIMIT_PERCENT"} unknown = percentage{cfg.UnknownLimitPercent, "SWWAF_UNKNOWN_LIMIT_PERCENT"}
} }
fetched := percentage{percent: whole} fetched := percentage{percent: whole}
if percent, listed := rq.h.lists.ASNLimitPercent(asn); listed { if percent, listed := rq.h.lists.ASNLimitPercent(asn); listed {
fetched = percentage{percent, "SWW_ASN_LIMIT_PERCENT_URL"} fetched = percentage{percent, "SWWAF_ASN_LIMIT_PERCENT_URL"}
} }
blocklisted := percentage{percent: whole} blocklisted := percentage{percent: whole}
if rq.blocklisted && cfg.BlocklistAction == "limit" { if rq.blocklisted && cfg.BlocklistAction == "limit" {
blocklisted = percentage{cfg.BlocklistLimitPercent, "SWW_BLOCKLIST_ACTION"} blocklisted = percentage{cfg.BlocklistLimitPercent, "SWWAF_BLOCKLIST_ACTION"}
} }
reputationListed := percentage{percent: whole} reputationListed := percentage{percent: whole}
if (rq.dnsblListed || rq.abuseIPDBHit) && cfg.ReputationAction == "limit" { if (rq.dnsblListed || rq.abuseIPDBHit) && cfg.ReputationAction == "limit" {
reputationListed = percentage{cfg.ReputationLimitPercent, "SWW_REPUTATION_ACTION"} reputationListed = percentage{cfg.ReputationLimitPercent, "SWWAF_REPUTATION_ACTION"}
} }
const tagSetting = "SWW_TAG_LIMIT_PERCENT" asnRequests := lowest(given(cfg.ASNLimitPercent, asn, "SWWAF_ASN_LIMIT_PERCENT"),
fetched)
asnRequests := lowest(given(cfg.TagLimitPercent, asnTag(asn), tagSetting), fetched) countryRequests := given(cfg.CountryLimitPercent, country,
countryRequests := given(cfg.TagLimitPercent, countryTag(country), tagSetting) "SWWAF_COUNTRY_LIMIT_PERCENT")
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 asnBytes, countryBytes := asnRequests, countryRequests
if _, listed := cfg.ASNBytesPercent[asn]; listed { if _, listed := cfg.ASNBytesPercent[asn]; listed {
asnBytes = given(cfg.ASNBytesPercent, asn, "SWW_ASN_BYTES_PERCENT") asnBytes = given(cfg.ASNBytesPercent, asn, "SWWAF_ASN_BYTES_PERCENT")
} }
if _, listed := cfg.CountryBytesPercent[country]; listed { if _, listed := cfg.CountryBytesPercent[country]; listed {
countryBytes = given(cfg.CountryBytesPercent, country, "SWW_COUNTRY_BYTES_PERCENT") countryBytes = given(cfg.CountryBytesPercent, country, "SWWAF_COUNTRY_BYTES_PERCENT")
} }
return lowest(asnRequests, countryRequests, otherTags, unknown, blocklisted, return lowest(asnRequests, countryRequests, unknown, blocklisted, reputationListed),
reputationListed), lowest(asnBytes, countryBytes, unknown, blocklisted, reputationListed)
lowest(asnBytes, countryBytes, otherTags, unknown, blocklisted, reputationListed)
} }
// given returns the percentage percents, the setting named setting, gives // given returns the percentage percents, the setting named setting, gives
// code, an AS number, a country or a tag, or whole when it does not list code. // code, an AS number or a country, or whole when it does not list code.
func given(percents map[string]int64, code, setting string) percentage { func given(percents map[string]int64, code, setting string) percentage {
percent, listed := percents[code] percent, listed := percents[code]
if !listed { if !listed {
@@ -1,9 +1,10 @@
package discriminator_test package proxy_test
import ( import (
"fmt" "fmt"
"io" "io"
"maps" "maps"
"net"
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/netip" "net/netip"
@@ -15,17 +16,18 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/lookup/lookuptest" "sneak.berlin/go/smallwebwaf/internal/lookup/lookuptest"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// The biased thresholds. // The biased thresholds.
const ( const (
tagLimitPercent = "SWW_TAG_LIMIT_PERCENT" asnLimitPercent = "SWWAF_ASN_LIMIT_PERCENT"
asnBytesPercent = "SWW_ASN_BYTES_PERCENT" countryLimitPercent = "SWWAF_COUNTRY_LIMIT_PERCENT"
countryBytesPercent = "SWW_COUNTRY_BYTES_PERCENT" asnBytesPercent = "SWWAF_ASN_BYTES_PERCENT"
unknownLimitPercent = "SWW_UNKNOWN_LIMIT_PERCENT" countryBytesPercent = "SWWAF_COUNTRY_BYTES_PERCENT"
unknownLimitPercent = "SWWAF_UNKNOWN_LIMIT_PERCENT"
) )
const ( const (
@@ -34,11 +36,6 @@ const (
asnDEHalf = asnDE + ":50" asnDEHalf = asnDE + ":50"
asnDEQuarter = asnDE + ":25" asnDEQuarter = asnDE + ":25"
countryDEHalf = "de:50" 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 is in an AS of its own, AS64500, and in no country.
noCountry = "192.0.2.80" noCountry = "192.0.2.80"
// fourAMinute is the rate limit these tests set: half of it is 2 // fourAMinute is the rate limit these tests set: half of it is 2
@@ -58,8 +55,8 @@ func TestEachBiasedThresholdLowersTheRateLimits(t *testing.T) {
for _, tc := range []struct { for _, tc := range []struct {
setting, value, from string setting, value, from string
}{ }{
{tagLimitPercent, asnTagDEHalf, fromDE}, {asnLimitPercent, asnDEHalf, fromDE},
{tagLimitPercent, countryTagDEHalf, fromDE}, {countryLimitPercent, countryDEHalf, fromDE},
{unknownLimitPercent, "50", unplaced}, {unknownLimitPercent, "50", unplaced},
} { } {
t.Run(tc.setting, func(t *testing.T) { t.Run(tc.setting, func(t *testing.T) {
@@ -76,7 +73,7 @@ func TestEachBiasedThresholdLowersTheRateLimits(t *testing.T) {
}{ }{
{http.StatusOK, requestlog.ActionForward}, {http.StatusOK, requestlog.ActionForward},
{http.StatusOK, requestlog.ActionForward}, {http.StatusOK, requestlog.ActionForward},
{http.StatusForbidden, requestlog.ActionClientIsRateLimited}, {http.StatusForbidden, requestlog.ActionRateLimited},
} { } {
line := s.get(tc.from, sent.status, sent.action) line := s.get(tc.from, sent.status, sent.action)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting, wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
@@ -100,8 +97,8 @@ func TestEachBiasedThresholdLowersTheByteLimits(t *testing.T) {
for _, tc := range []struct { for _, tc := range []struct {
setting, value, from string setting, value, from string
}{ }{
{tagLimitPercent, asnTagDEHalf, fromDE}, {asnLimitPercent, asnDEHalf, fromDE},
{tagLimitPercent, "Country=de:50", fromDE}, {countryLimitPercent, "DE:50", fromDE},
{unknownLimitPercent, "50", unplaced}, {unknownLimitPercent, "50", unplaced},
{asnBytesPercent, "as64496:50", fromDE}, {asnBytesPercent, "as64496:50", fromDE},
{countryBytesPercent, countryDEHalf, fromDE}, {countryBytesPercent, countryDEHalf, fromDE},
@@ -155,13 +152,13 @@ func TestBytesPercentSettingsTakeThePlaceOfTheOthersForByteLimits(t *testing.T)
}, },
{ {
"raising the byte limits back", "raising the byte limits back",
map[string]string{tagLimitPercent: asnTagDEHalf, asnBytesPercent: asnDE + ":100"}, map[string]string{asnLimitPercent: asnDEHalf, asnBytesPercent: asnDE + ":100"},
"50 from " + tagLimitPercent, none, "", "50 from " + asnLimitPercent, none, "",
}, },
{ {
"raising the byte limits back, by country", "raising the byte limits back, by country",
map[string]string{tagLimitPercent: countryTagDEHalf, countryBytesPercent: "de:100"}, map[string]string{countryLimitPercent: countryDEHalf, countryBytesPercent: "de:100"},
"50 from " + tagLimitPercent, none, "", "50 from " + countryLimitPercent, none, "",
}, },
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
@@ -188,19 +185,19 @@ func TestBytesPercentSettingsTakeThePlaceOfTheOthersForByteLimits(t *testing.T)
func TestZeroPercentIsAZeroAllowance(t *testing.T) { func TestZeroPercentIsAZeroAllowance(t *testing.T) {
t.Parallel() t.Parallel()
s, _, _ := startWithLookups(t, map[string]string{unknownLimitPercent: "0"}) s, _, _ := startWithLookups(t, map[string]string{asnLimitPercent: asnDE + ":0"})
// The first request breaks the limit, and bans the client; the log line // The first request breaks the limit, and bans the client; the log line
// gives the 0. // gives the 0.
line := s.get(unplaced, http.StatusForbidden, requestlog.ActionClientIsRateLimited) line := s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
if line.fields["limit_percent"] != float64(0) || if line.fields["limit_percent"] != float64(0) ||
line.fields["limit_percent_setting"] != unknownLimitPercent { line.fields["limit_percent_setting"] != asnLimitPercent {
t.Errorf("log line has limit_percent %v from %v, want 0 from %s", t.Errorf("log line has limit_percent %v from %v, want 0 from %s",
line.fields["limit_percent"], line.fields["limit_percent_setting"], line.fields["limit_percent"], line.fields["limit_percent_setting"],
unknownLimitPercent) asnLimitPercent)
} }
s.get(unplaced, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
} }
func TestLowestPercentageApplies(t *testing.T) { func TestLowestPercentageApplies(t *testing.T) {
@@ -215,29 +212,29 @@ func TestLowestPercentageApplies(t *testing.T) {
}{ }{
{ {
"the country's", "the country's",
map[string]string{tagLimitPercent: asnTagDEHalf + "," + countryTagDEQuarter}, map[string]string{asnLimitPercent: asnDEHalf, countryLimitPercent: "de:25"},
fromDE, "25 from " + tagLimitPercent, fromDE, "25 from " + countryLimitPercent,
}, },
{ {
"the AS number's", "the AS number's",
map[string]string{tagLimitPercent: asnTagDEQuarter + "," + countryTagDEHalf}, map[string]string{asnLimitPercent: asnDEQuarter, countryLimitPercent: countryDEHalf},
fromDE, "25 from " + tagLimitPercent, fromDE, "25 from " + asnLimitPercent,
}, },
{ {
"the AS number's, the first of two alike", "the AS number's, the first of two alike",
map[string]string{tagLimitPercent: asnTagDEQuarter + "," + countryTagDEQuarter}, map[string]string{asnLimitPercent: asnDEQuarter, countryLimitPercent: "de:25"},
fromDE, "25 from " + tagLimitPercent, fromDE, "25 from " + asnLimitPercent,
}, },
{ {
"that for a client without a country", "that for a client without a country",
map[string]string{tagLimitPercent: "asn=64500:50", unknownLimitPercent: "25"}, map[string]string{asnLimitPercent: "AS64500:50", unknownLimitPercent: "25"},
noCountry, "25 from " + unknownLimitPercent, noCountry, "25 from " + unknownLimitPercent,
}, },
{ {
// SWW_UNKNOWN_LIMIT_PERCENT is left at its default, 100. // SWWAF_UNKNOWN_LIMIT_PERCENT is left at its default, 100.
"the AS number's, for a client without a country", "the AS number's, for a client without a country",
map[string]string{tagLimitPercent: "asn=64500:25"}, map[string]string{asnLimitPercent: "AS64500:25"},
noCountry, "25 from " + tagLimitPercent, noCountry, "25 from " + asnLimitPercent,
}, },
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
@@ -250,7 +247,7 @@ func TestLowestPercentageApplies(t *testing.T) {
// A quarter of 4 requests a minute: the second breaks the limit. // A quarter of 4 requests a minute: the second breaks the limit.
s.get(tc.from, http.StatusOK, requestlog.ActionForward) s.get(tc.from, http.StatusOK, requestlog.ActionForward)
line := s.get(tc.from, http.StatusForbidden, requestlog.ActionClientIsRateLimited) line := s.get(tc.from, http.StatusForbidden, requestlog.ActionRateLimited)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting, wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
tc.want) tc.want)
}) })
@@ -269,7 +266,7 @@ func TestUnknownLimitPercentGivesEveryClientWithoutACountryItsPercentage(t *test
for _, from := range []string{unplaced, "10.0.0.8"} { for _, from := range []string{unplaced, "10.0.0.8"} {
s.get(from, http.StatusOK, requestlog.ActionForward) s.get(from, http.StatusOK, requestlog.ActionForward)
s.get(from, http.StatusOK, requestlog.ActionForward) s.get(from, http.StatusOK, requestlog.ActionForward)
s.get(from, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(from, http.StatusForbidden, requestlog.ActionRateLimited)
} }
// One in a country has the whole limit. // One in a country has the whole limit.
@@ -284,16 +281,16 @@ func TestClientWithoutAnAnswerInTimeHasTheUnknownLimitPercent(t *testing.T) {
// In a synctest bubble, as TestRequestWaitsAsLongAsTheLookupTimeoutSays // In a synctest bubble, as TestRequestWaitsAsLongAsTheLookupTimeoutSays
// says, with a GeoJS that never answers. // says, with a GeoJS that never answers.
synctest.Test(t, func(t *testing.T) { synctest.Test(t, func(t *testing.T) {
server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, server, out, _ := newProxy(t, "http://app.invalid", unansweredGeoJSURL,
map[string]string{unknownLimitPercent: "0"}) time.Now, map[string]string{unknownLimitPercent: "0"})
// Once the time the request waits for its answer is up, the client // Once the second the request waits for its answer is up, the client
// counts as without a country, and its zero allowance refuses the // counts as without a country, and its zero allowance refuses the
// request. // request before it reaches the app.
serveFromDE(t, server, http.MethodGet, http.NoBody) serveFromDE(t, server, http.MethodGet, http.NoBody)
line := out.requestLine(t) line := out.requestLine(t)
wantLine(t, line, http.StatusForbidden, requestlog.ActionClientIsRateLimited) wantLine(t, line, http.StatusForbidden, requestlog.ActionRateLimited)
wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting, wantPercent(t, "limit_percent", line.LimitPercent, line.LimitPercentSetting,
"0 from "+unknownLimitPercent) "0 from "+unknownLimitPercent)
}) })
@@ -308,12 +305,8 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
setting, value string setting, value string
waits bool waits bool
}{ }{
{tagLimitPercent, asnTagDEHalf, true}, {asnLimitPercent, asnDEHalf, true},
{tagLimitPercent, countryTagDEHalf, true}, {countryLimitPercent, countryDEHalf, true},
{tagDeny, denyKP, true},
// A tag the lookup does not give needs no answer.
{tagLimitPercent, "vpn:50", false},
{tagDeny, "vpn", false},
{asnBytesPercent, asnDEHalf, true}, {asnBytesPercent, asnDEHalf, true},
{countryBytesPercent, countryDEHalf, true}, {countryBytesPercent, countryDEHalf, true},
{unknownLimitPercent, "99", true}, {unknownLimitPercent, "99", true},
@@ -327,9 +320,12 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
// In a synctest bubble, as TestRequestWaitsAsLongAsTheLookupTimeoutSays // In a synctest bubble, as TestRequestWaitsAsLongAsTheLookupTimeoutSays
// says, with a GeoJS that never answers. // says, with a GeoJS that never answers.
synctest.Test(t, func(t *testing.T) { synctest.Test(t, func(t *testing.T) {
server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, // The request's body is over SWWAF_REQUEST_MAX_BYTES, so that it
map[string]string{ // is refused after the checks, and never reaches the app.
lookupTimeout: timeout.String(), tagLists: "vpn=" + vpnList, tc.setting: tc.value, server, out, _ := newProxy(t, "http://app.invalid", unansweredGeoJSURL,
time.Now, map[string]string{
lookupTimeout: timeout.String(), requestMaxBytes: "1",
tc.setting: tc.value,
}) })
began := time.Now() began := time.Now()
@@ -344,7 +340,8 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
t.Errorf("the request waited %s for its answer, want %s", waited, want) t.Errorf("the request waited %s for its answer, want %s", waited, want)
} }
wantLine(t, out.requestLine(t), http.StatusOK, requestlog.ActionForward) wantLine(t, out.requestLine(t), http.StatusRequestEntityTooLarge,
requestlog.ActionTooLarge)
// The bubble's clock stops once this function returns, so the // The bubble's clock stops once this function returns, so the
// request to GeoJS, which a request that did not wait leaves // request to GeoJS, which a request that did not wait leaves
@@ -373,15 +370,15 @@ func TestBanForALoweredLimitGivesThePercentageInItsNotesAndItsAlert(t *testing.T
{ {
// A quarter of 12 requests a minute is 3: the fourth breaks it. // A quarter of 12 requests a minute is 3: the fourth breaks it.
"a rate limit", "a rate limit",
map[string]string{rateLimitPerMinute: "12", tagLimitPercent: asnTagDEQuarter}, map[string]string{rateLimitPerMinute: "12", asnLimitPercent: asnDEQuarter},
3, http.StatusForbidden, requestlog.ActionClientIsRateLimited, 3, http.StatusForbidden, requestlog.ActionRateLimited,
"requests per minute over the limit of 3", "25 from " + tagLimitPercent, "requests per minute over the limit of 3", "25 from " + asnLimitPercent,
}, },
{ {
// The byte limits' percentage, not the rate limits'. // The byte limits' percentage, not the rate limits'.
"a byte limit", "a byte limit",
map[string]string{ map[string]string{
bytesLimitPerMinute: twoUploads, tagLimitPercent: asnTagDEQuarter, bytesLimitPerMinute: twoUploads, asnLimitPercent: asnDEQuarter,
asnBytesPercent: asnDEHalf, asnBytesPercent: asnDEHalf,
}, },
0, http.StatusOK, requestlog.ActionForward, 0, http.StatusOK, requestlog.ActionForward,
@@ -429,7 +426,7 @@ func TestBanForALoweredLimitGivesThePercentageInItsNotesAndItsAlert(t *testing.T
// clock. // clock.
func startWithLookups( func startWithLookups(
t *testing.T, env map[string]string, t *testing.T, env map[string]string,
) (*sender, *discriminator.Server, *alerts.Queue) { ) (*sender, *proxy.Server, *alerts.Queue) {
t.Helper() t.Helper()
s, _, server, queue := startWithLookupsAndClock(t, env) s, _, server, queue := startWithLookupsAndClock(t, env)
@@ -444,7 +441,7 @@ func startWithLookups(
// country, and no other address. // country, and no other address.
func startWithLookupsAndClock( func startWithLookupsAndClock(
t *testing.T, env map[string]string, t *testing.T, env map[string]string,
) (*sender, *clock, *discriminator.Server, *alerts.Queue) { ) (*sender, *clock, *proxy.Server, *alerts.Queue) {
t.Helper() t.Helper()
path := filepath.Join(t.TempDir(), "ipinfo_lite.mmdb") path := filepath.Join(t.TempDir(), "ipinfo_lite.mmdb")
@@ -470,17 +467,13 @@ func (s *sender) uploadFrom(from string) logLine {
return line return line
} }
// serveFromDE hands a question about a request from fromDE with method and body // serveFromDE hands a request from fromDE with method and body straight to
// straight to server's handler, without the network, and returns once it is // server's handler, without the network, and returns once it is answered.
// answered. func serveFromDE(t *testing.T, server *proxy.Server, method string, body io.Reader) {
func serveFromDE(
t *testing.T, server *discriminator.Server, method string, body io.Reader,
) {
t.Helper() t.Helper()
req := httptest.NewRequestWithContext(t.Context(), method, "/", body) req := httptest.NewRequestWithContext(t.Context(), method, "/", body)
req.Header.Set(discriminator.ClientHeader, fromDE) req.RemoteAddr = net.JoinHostPort(fromDE, "1234")
req.Header.Set(requestIDHeader, "the-id")
server.Handler.ServeHTTP(httptest.NewRecorder(), req) server.Handler.ServeHTTP(httptest.NewRecorder(), req)
} }
@@ -497,7 +490,7 @@ func wantPercent(t *testing.T, what string, percent *int64, setting, want string
} }
// percentText gives a limit percentage and the setting that gave it as // percentText gives a limit percentage and the setting that gave it as
// text, such as "50 from SWW_TAG_LIMIT_PERCENT", or none when both are // text, such as "50 from SWWAF_ASN_LIMIT_PERCENT", or none when both are
// left out. // left out.
func percentText(percent *int64, setting string) string { func percentText(percent *int64, setting string) string {
switch { switch {
@@ -1,4 +1,4 @@
package rproxy package proxy
import ( import (
"bufio" "bufio"
@@ -7,38 +7,39 @@ import (
"net" "net"
"net/http" "net/http"
"sync/atomic" "sync/atomic"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// errResponseTooLarge ends an app's response body that is longer than // errResponseTooLarge ends an app's response body that is longer than
// SWRP_MAX_RESPONSE_SIZE. // SWWAF_RESPONSE_MAX_BYTES.
var errResponseTooLarge = errors.New( var errResponseTooLarge = errors.New(
"the response body is over SWRP_MAX_RESPONSE_SIZE") "the response body is over SWWAF_RESPONSE_MAX_BYTES")
// requestBody is the visitor's request body. rproxy first reads up to the first // requestBody is the client's request body on its way to the app. The
// 64 KiB of it into held, and then, on its way to the app, the transport reads // transport reads it on a goroutine of its own.
// it on a goroutine of its own.
type requestBody struct { type requestBody struct {
// body is the visitor's body, ending in an *http.MaxBytesError past // body is the client's body, ending in an *http.MaxBytesError past
// SWRP_MAX_REQUEST_SIZE. // SWWAF_REQUEST_MAX_BYTES.
body io.ReadCloser body io.ReadCloser
rq *request rq *request
// held is the part read before the request goes to the app, which Read gives // readByCoreRuleSet is what the Core Rule Set read of the body before
// first. // the request went to the app, and Read gives first.
held []byte readByCoreRuleSet []byte
// waiting is true while a Read waits for the visitor to send more. // waiting is true while a Read waits for the client to send more.
waiting atomic.Bool waiting atomic.Bool
// received is true once the visitor has sent the whole body. // received is true once the client has sent the whole body.
received atomic.Bool received atomic.Bool
// bytes is how much of the body has been read. // bytes is how much of the body has been read.
bytes atomic.Int64 bytes atomic.Int64
} }
// Read reads from the visitor's body, after the part held, which has been // Read reads from the client's body, after what the Core Rule Set read of
// counted already. // it, which has been counted already.
func (b *requestBody) Read(p []byte) (int, error) { func (b *requestBody) Read(p []byte) (int, error) {
if len(b.held) > 0 { if len(b.readByCoreRuleSet) > 0 {
n := copy(p, b.held) n := copy(p, b.readByCoreRuleSet)
b.held = b.held[n:] b.readByCoreRuleSet = b.readByCoreRuleSet[n:]
return n, nil return n, nil
} }
@@ -53,22 +54,27 @@ func (b *requestBody) Read(p []byte) (int, error) {
switch { switch {
case errors.Is(err, io.EOF): case errors.Is(err, io.EOF):
b.received.Store(true) b.received.Store(true)
b.rq.bodyReceived()
case errors.As(err, &tooLarge): case errors.As(err, &tooLarge):
b.rq.refuse(http.StatusRequestEntityTooLarge) b.rq.refuse(refusal{
status: http.StatusRequestEntityTooLarge,
action: requestlog.ActionTooLarge,
limit: "SWWAF_REQUEST_MAX_BYTES",
})
} }
return n, err return n, err
} }
// Close closes the visitor's body. // Close closes the client's body.
func (b *requestBody) Close() error { func (b *requestBody) Close() error {
return b.body.Close() return b.body.Close()
} }
// responseBody is the app's response body on its way to the visitor. // responseBody is the app's response body on its way to the client.
type responseBody struct { type responseBody struct {
// body is the app's body, ending in an *http.MaxBytesError past // body is the app's body, ending in an *http.MaxBytesError past
// SWRP_MAX_RESPONSE_SIZE. // SWWAF_RESPONSE_MAX_BYTES.
body io.ReadCloser body io.ReadCloser
rq *request rq *request
} }
@@ -86,13 +92,20 @@ func (b *responseBody) Read(p []byte) (int, error) {
case errors.Is(err, io.EOF): case errors.Is(err, io.EOF):
b.rq.responseReceived() b.rq.responseReceived()
case errors.As(err, &tooLarge): case errors.As(err, &tooLarge):
b.rq.refuse(http.StatusBadGateway) b.rq.refuse(refusal{
status: http.StatusBadGateway,
action: requestlog.ActionTooLarge,
limit: "SWWAF_RESPONSE_MAX_BYTES",
})
return n, errResponseTooLarge return n, errResponseTooLarge
case b.rq.in.Context().Err() == nil: case b.rq.in.Context().Err() == nil:
// The answer broke off, not because the visitor went away. If a time // The answer broke off, not because the client went away. If a
// limit cut it, that refusal came first and is the one kept. // timeout cut it, that refusal came first and is the one kept.
b.rq.refuse(http.StatusBadGateway) b.rq.refuse(refusal{
status: http.StatusBadGateway,
action: requestlog.ActionUpstreamError,
})
} }
return n, err return n, err
@@ -104,14 +117,15 @@ func (b *responseBody) Close() error {
} }
// upgradedConn is the connection to the app once the app has switched // upgradedConn is the connection to the app once the app has switched
// protocols, as for a WebSocket. ReverseProxy writes to it what the visitor // protocols, as for a WebSocket. ReverseProxy writes to it what the client
// sends and reads from it what the app sends, on goroutines of its own, until // sends and reads from it what the app sends, on goroutines of its own,
// the connection closes; it counts the bytes each way, for the report. // until the connection closes; it counts the bytes each way, for the byte
// limits.
type upgradedConn struct { type upgradedConn struct {
io.ReadWriteCloser io.ReadWriteCloser
// fromApp is how many bytes the app has sent, and toApp how many the // fromApp is how many bytes the app has sent, and toApp how many the
// visitor has. // client has.
fromApp atomic.Int64 fromApp atomic.Int64
toApp atomic.Int64 toApp atomic.Int64
} }
@@ -124,7 +138,7 @@ func (c *upgradedConn) Read(p []byte) (int, error) {
return n, err return n, err
} }
// Write sends the app what the visitor sent. // Write sends the app what the client sent.
func (c *upgradedConn) Write(p []byte) (int, error) { func (c *upgradedConn) Write(p []byte) (int, error) {
n, err := c.ReadWriteCloser.Write(p) n, err := c.ReadWriteCloser.Write(p)
c.toApp.Add(int64(n)) c.toApp.Add(int64(n))
@@ -132,9 +146,9 @@ func (c *upgradedConn) Write(p []byte) (int, error) {
return n, err return n, err
} }
// CloseWrite tells the app that the visitor sends no more, while what the app // CloseWrite tells the app that the client sends no more, while what the
// sends still passes. ReverseProxy calls it once the visitor has stopped // app sends still passes. ReverseProxy calls it once the client has
// sending, and closes the connection there if it is not supported. // stopped sending, and closes the connection there if it is not supported.
func (c *upgradedConn) CloseWrite() error { func (c *upgradedConn) CloseWrite() error {
conn, ok := c.ReadWriteCloser.(interface{ CloseWrite() error }) conn, ok := c.ReadWriteCloser.(interface{ CloseWrite() error })
if !ok { if !ok {
@@ -144,8 +158,8 @@ func (c *upgradedConn) CloseWrite() error {
return conn.CloseWrite() return conn.CloseWrite()
} }
// limitBody returns body, cut off with an *http.MaxBytesError after maxBytes, or // limitBody returns body, cut off with an *http.MaxBytesError after
// unchanged if maxBytes is zero, which is off. // maxBytes, or unchanged if maxBytes is zero, which is off.
func limitBody(body io.ReadCloser, maxBytes int64) io.ReadCloser { func limitBody(body io.ReadCloser, maxBytes int64) io.ReadCloser {
if maxBytes == 0 { if maxBytes == 0 {
return body return body
@@ -155,18 +169,19 @@ func limitBody(body io.ReadCloser, maxBytes int64) io.ReadCloser {
return http.MaxBytesReader(nil, body, maxBytes) return http.MaxBytesReader(nil, body, maxBytes)
} }
// responseWriter is the response to the visitor. It notes the status and size // responseWriter is the response to the client. It notes the status and
// for the log line and the report. // size for the log line, and the first error writing to the client.
type responseWriter struct { type responseWriter struct {
http.ResponseWriter http.ResponseWriter
// status is the final status sent, or zero before one is. // status is the final status sent, or zero before one is.
status int status int
bytes int64 bytes int64
err error
} }
// WriteHeader sends the status and headers. An informational 1xx status is // WriteHeader sends the status and headers. An informational 1xx status
// passed on and the final status still comes later. // is passed on and the final status still comes later.
func (w *responseWriter) WriteHeader(status int) { func (w *responseWriter) WriteHeader(status int) {
if status >= http.StatusOK && w.status == 0 { if status >= http.StatusOK && w.status == 0 {
w.status = status w.status = status
@@ -181,20 +196,26 @@ func (w *responseWriter) Write(p []byte) (int, error) {
w.status = http.StatusOK w.status = http.StatusOK
} }
n, err := w.ResponseWriter.Write(p) //nolint:gosec // the answer, as it was given n, err := w.ResponseWriter.Write(p)
w.bytes += int64(n) w.bytes += int64(n)
w.noteError(err)
return n, err return n, err
} }
// FlushError sends what has been written so far. http.ResponseController calls // FlushError sends what has been written so far.
// it, as ReverseProxy does after each write. // http.ResponseController calls it, as ReverseProxy does after each
// write.
func (w *responseWriter) FlushError() error { func (w *responseWriter) FlushError() error {
return http.NewResponseController(w.ResponseWriter).Flush() err := http.NewResponseController(w.ResponseWriter).Flush()
w.noteError(err)
return err
} }
// Hijack takes over the connection to the visitor, which ReverseProxy does only // Hijack takes over the connection to the client, which ReverseProxy does
// to pass on the app's 101 Switching Protocols: that is then the status sent. // only to pass on the app's 101 Switching Protocols: that is then the
// status sent.
func (w *responseWriter) Hijack() (net.Conn, *bufio.ReadWriter, error) { func (w *responseWriter) Hijack() (net.Conn, *bufio.ReadWriter, error) {
conn, buffered, err := http.NewResponseController(w.ResponseWriter).Hijack() conn, buffered, err := http.NewResponseController(w.ResponseWriter).Hijack()
if err == nil { if err == nil {
@@ -204,8 +225,15 @@ func (w *responseWriter) Hijack() (net.Conn, *bufio.ReadWriter, error) {
return conn, buffered, err return conn, buffered, err
} }
// Unwrap lets http.ResponseController reach net/http's own ResponseWriter for // Unwrap lets http.ResponseController reach net/http's own
// what responseWriter does not do itself. // ResponseWriter for what responseWriter does not do itself.
func (w *responseWriter) Unwrap() http.ResponseWriter { func (w *responseWriter) Unwrap() http.ResponseWriter {
return w.ResponseWriter return w.ResponseWriter
} }
// noteError keeps the first error writing to the client.
func (w *responseWriter) noteError(err error) {
if w.err == nil {
w.err = err
}
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"bufio" "bufio"
@@ -19,13 +19,13 @@ import (
// The byte limit settings. // The byte limit settings.
const ( const (
bytesLimitPerMinute = "SWW_BYTES_LIMIT_PER_MINUTE" bytesLimitPerMinute = "SWWAF_BYTES_LIMIT_PER_MINUTE"
bytesLimitPerHour = "SWW_BYTES_LIMIT_PER_HOUR" bytesLimitPerHour = "SWWAF_BYTES_LIMIT_PER_HOUR"
bytesLimitPerDay = "SWW_BYTES_LIMIT_PER_DAY" bytesLimitPerDay = "SWWAF_BYTES_LIMIT_PER_DAY"
bytesCount = "SWW_BYTES_COUNT" bytesCount = "SWWAF_BYTES_COUNT"
) )
// The values of SWW_BYTES_COUNT. // The values of SWWAF_BYTES_COUNT.
const ( const (
countResponse = "response" countResponse = "response"
countRequest = "request" countRequest = "request"
@@ -40,13 +40,15 @@ const (
// byteLimit is the byte limit these tests set, as a setting: a request // byteLimit is the byte limit these tests set, as a setting: a request
// with a body and its answer, 100 bytes, go over it. // with a body and its answer, 100 bytes, go over it.
byteLimit = "99" byteLimit = "99"
// minuteBytes is limit_hit for SWW_BYTES_LIMIT_PER_MINUTE. // minuteBytes is limit_hit for SWWAF_BYTES_LIMIT_PER_MINUTE.
minuteBytes = "minute_bytes" minuteBytes = "minute_bytes"
) )
func TestEachByteLimitBansOnceTheResponseHasEnded(t *testing.T) { func TestEachByteLimitBansOnceTheResponseHasEnded(t *testing.T) {
t.Parallel() t.Parallel()
const scraper = "192.0.2.200"
for _, tc := range []struct { for _, tc := range []struct {
setting, window string setting, window string
// apart is the time between the two requests, which the window // apart is the time between the two requests, which the window
@@ -90,29 +92,14 @@ func TestEachByteLimitBansOnceTheResponseHasEnded(t *testing.T) {
line.BanExpires, tc.window, expires) line.BanExpires, tc.window, expires)
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
wantMetric(t, s.scrape(), `sww_rate_limit_hits_total{`+ wantMetric(t, s.scrape(scraper), `smallwebwaf_rate_limit_hits_total{`+
`instance="`+alertInstance+`",kind="bytes",window="`+tc.window+`"}`, 1) `instance="`+alertInstance+`",kind="bytes",window="`+tc.window+`"}`, 1)
}) })
} }
} }
func TestByteLimitBanNamesItsHeuristicWindowCountAndLimit(t *testing.T) {
t.Parallel()
s, _ := startWithAnswers(t, map[string]string{bytesLimitPerMinute: byteLimit})
line, _ := s.download()
wantAfterAnswerHeuristic(t, line, "", "null")
// Two answers of 70 bytes are over the limit of 99.
line, _ = s.download()
wantHeuristic(t, line, "", "null")
wantAfterAnswerHeuristic(t, line, "byte_limits",
`{"window": "minute", "count": 140, "limit": 99}`)
}
func TestResponseOverAByteLimitByItselfIsPassedOnWhole(t *testing.T) { func TestResponseOverAByteLimitByItselfIsPassedOnWhole(t *testing.T) {
t.Parallel() t.Parallel()
@@ -125,7 +112,7 @@ func TestResponseOverAByteLimitByItselfIsPassedOnWhole(t *testing.T) {
len(got.body), got.err, line.LimitHit, answerBytes, minuteBytes) len(got.body), got.err, line.LimitHit, answerBytes, minuteBytes)
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
} }
func TestBytesOfAnAnswerThatBreaksOffAreCounted(t *testing.T) { func TestBytesOfAnAnswerThatBreaksOffAreCounted(t *testing.T) {
@@ -139,7 +126,7 @@ func TestBytesOfAnAnswerThatBreaksOffAreCounted(t *testing.T) {
// The 70 bytes passed on before the app broke off are over the limit of // The 70 bytes passed on before the app broke off are over the limit of
// 50, and ban the client for an hour. // 50, and ban the client for an hour.
line, got := s.requestWithBody(http.MethodGet, client, "/", "", "", http.StatusOK, line, got := s.requestWithBody(http.MethodGet, client, "/", "", "", http.StatusOK,
requestlog.ActionForward) requestlog.ActionUpstreamError)
if len(got.body) != answerBytes || line.LimitHit != minuteBytes || if len(got.body) != answerBytes || line.LimitHit != minuteBytes ||
line.BanExpires != expires { line.BanExpires != expires {
t.Errorf("got %d bytes, and the log line has limit_hit %q and ban_expires %q, "+ t.Errorf("got %d bytes, and the log line has limit_hit %q and ban_expires %q, "+
@@ -147,7 +134,7 @@ func TestBytesOfAnAnswerThatBreaksOffAreCounted(t *testing.T) {
answerBytes, minuteBytes, expires) answerBytes, minuteBytes, expires)
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
} }
func TestWebSocketBytesAreCountedOnceItCloses(t *testing.T) { func TestWebSocketBytesAreCountedOnceItCloses(t *testing.T) {
@@ -176,11 +163,44 @@ func TestWebSocketBytesAreCountedOnceItCloses(t *testing.T) {
line.LimitHit, line.Counts.MinuteBytes, minuteBytes, tc.counted) line.LimitHit, line.Counts.MinuteBytes, minuteBytes, tc.counted)
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
}) })
} }
} }
func TestWebSocketPassesTheAnswerAfterTheClientStopsSending(t *testing.T) {
t.Parallel()
app := startApp(t, echoOnceTheClientStops)
addr, out := startProxy(t, app.URL,
map[string]string{trustedProxies: trustLocalhost})
s := &sender{t: t, addr: addr, out: out}
conn, reader := s.openWebSocket()
send(t, conn, uploadBody)
// The client closes its sending side and waits for the answer, which the
// app sends only once it has seen the client stop. smallwebwaf passes the
// close on to the app through CloseWrite on upgradedConn; without that,
// it closes both connections, and the answer is lost.
tcp, ok := conn.(*net.TCPConn)
if !ok {
t.Fatalf("connection is a %T, want a *net.TCPConn", conn)
}
err := tcp.CloseWrite()
if err != nil {
t.Fatalf("close the sending side: %v", err)
}
got, err := io.ReadAll(reader)
if err != nil || string(got) != uploadBody {
t.Errorf("got %q (%v), want %q", got, err, uploadBody)
}
s.closeWebSocket(conn)
}
func TestBytesCountSaysWhichBytesCount(t *testing.T) { func TestBytesCountSaysWhichBytesCount(t *testing.T) {
t.Parallel() t.Parallel()
@@ -218,7 +238,7 @@ func TestBytesCountSaysWhichBytesCount(t *testing.T) {
} }
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
}) })
} }
} }
@@ -227,8 +247,8 @@ func TestByteLimitsLeaveOutWhatTheRateLimitsLeaveOut(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
allowed = "192.0.2.7" // in SWW_ALLOW_NETS allowed = "192.0.2.7" // in SWWAF_ALLOW_NETS
exempt = "192.0.2.10" // in SWW_RATE_LIMIT_EXEMPT_NETS exempt = "192.0.2.10" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
) )
s, _ := startWithAnswers(t, map[string]string{ s, _ := startWithAnswers(t, map[string]string{
@@ -386,7 +406,7 @@ func TestObserveModeLeavesOutTheBytesOfARequestEnforceModeRefuses(t *testing.T)
// counted, and the byte limit is not broken. Its line gives the bytes // counted, and the byte limit is not broken. Its line gives the bytes
// counted before it. // counted before it.
line := s.upload() line := s.upload()
wantWouldAction(t, line, requestlog.ActionClientIsRateLimited) wantWouldAction(t, line, requestlog.ActionRateLimited)
if line.LimitHit != minute || line.Counts.MinuteBytes != bodyBytes+answerBytes { if line.LimitHit != minute || line.Counts.MinuteBytes != bodyBytes+answerBytes {
t.Errorf("log line has limit_hit %q and minute_bytes %v, want minute and %d", t.Errorf("log line has limit_hit %q and minute_bytes %v, want minute and %d",
@@ -445,6 +465,28 @@ func answerAfterUpgrade(w http.ResponseWriter, _ *http.Request) {
} }
} }
// echoOnceTheClientStops is an app that switches protocols, as for a
// WebSocket, reads what the client sends until the client stops sending,
// and then sends it all back.
func echoOnceTheClientStops(w http.ResponseWriter, _ *http.Request) {
conn, buffered, err := http.NewResponseController(w).Hijack()
if err != nil {
return
}
defer func() {
_ = conn.Close()
}()
_, _ = buffered.WriteString("HTTP/1.1 101 Switching Protocols\r\n" +
"Connection: Upgrade\r\nUpgrade: websocket\r\n\r\n")
_ = buffered.Flush()
received, _ := io.ReadAll(buffered)
_, _ = buffered.Write(received)
_ = buffered.Flush()
}
// webSocket opens a WebSocket from client to answerAfterUpgrade, sends a // webSocket opens a WebSocket from client to answerAfterUpgrade, sends a
// line of bodyBytes on it, reads the answer, and closes it. It checks the // line of bodyBytes on it, reads the answer, and closes it. It checks the
// answer, and the log line as request does, and returns the log line. // answer, and the log line as request does, and returns the log line.
@@ -501,7 +543,7 @@ func (s *sender) closeWebSocket(conn net.Conn) logLine {
_ = conn.Close() _ = conn.Close()
line := s.out.endedLines(s.t, s.sent+1)[s.sent] line := s.out.requestLines(s.t, s.sent+1)[s.sent]
s.sent++ s.sent++
wantLine(s.t, line, http.StatusSwitchingProtocols, requestlog.ActionForward) wantLine(s.t, line, http.StatusSwitchingProtocols, requestlog.ActionForward)
@@ -1,40 +1,30 @@
package rproxy package proxy
import ( import (
"crypto/rand"
"net/http" "net/http"
"net/netip" "net/netip"
"slices" "slices"
"strings" "strings"
) )
// The headers rproxy sets on the requests it passes to the app. Go writes every // peerAddress is the address of the request's TCP peer, normally traefik.
// header name in this form, as it sends it and as it receives it, so
// X-Client-ASN arrives as X-Client-Asn, and Del removes a visitor's own whatever
// their case; header names are not case-sensitive.
const (
requestIDHeader = "X-Request-ID"
asnHeader = "X-Client-Asn"
countryHeader = "X-Client-Country"
)
// peerAddress is the address of the request's TCP peer, normally traefik, without
// any IPv6 zone, which discriminator refuses.
func peerAddress(r *http.Request) netip.Addr { func peerAddress(r *http.Request) netip.Addr {
addrPort, err := netip.ParseAddrPort(r.RemoteAddr) addrPort, err := netip.ParseAddrPort(r.RemoteAddr)
if err != nil { if err != nil {
return netip.Addr{} return netip.Addr{}
} }
return addrPort.Addr().Unmap().WithZone("") return addrPort.Addr().Unmap()
} }
// clientAddress works out who the visitor is. A peer outside the trusted // clientAddress works out who the client is. A peer outside the trusted
// proxies is the visitor, and what it says in X-Forwarded-For is ignored. For a // proxies is the client, and what it says in X-Forwarded-For is ignored.
// peer inside them, X-Forwarded-For is read from the right, and the first // For a peer inside them, X-Forwarded-For is read from the right, and the
// address outside them is the visitor; if every address in it is inside, the // first address outside them is the client; if every address in it is
// leftmost is, and with no header, the peer. An entry that is not an address // inside, the leftmost is, and with no header, the peer. An entry that is
// ends the reading, since nothing to its left can be believed. The visitor's // not an address ends the reading, since nothing to its left can be
// address never has an IPv6 zone, which discriminator refuses. // believed.
func clientAddress( func clientAddress(
peer netip.Addr, forwardedFor []string, trusted []netip.Prefix, peer netip.Addr, forwardedFor []string, trusted []netip.Prefix,
) netip.Addr { ) netip.Addr {
@@ -50,7 +40,7 @@ func clientAddress(
break break
} }
client = addr.Unmap().WithZone("") client = addr.Unmap()
if !isInside(client, trusted) { if !isInside(client, trusted) {
break break
} }
@@ -59,8 +49,24 @@ func clientAddress(
return client return client
} }
// scheme is how the visitor reached traefik, as a trusted proxy says in // requestIDHeader carries the request's id, from traefik and to the app.
// X-Forwarded-Proto, or otherwise http, the only scheme rproxy serves. const requestIDHeader = "X-Request-ID"
// requestID is the request's id: the one a trusted proxy sent, or a new
// random one. A peer outside the trusted proxies did not come through
// traefik, so the id it sends is its own claim, and is replaced.
func requestID(r *http.Request, peerTrusted bool) string {
id := r.Header.Get(requestIDHeader)
if !peerTrusted || id == "" {
id = rand.Text()
}
return id
}
// scheme is how the client reached traefik, as a trusted proxy says in
// X-Forwarded-Proto, or otherwise http, the only scheme smallwebwaf
// serves.
func scheme(r *http.Request, peerTrusted bool) string { func scheme(r *http.Request, peerTrusted bool) string {
proto := r.Header.Get("X-Forwarded-Proto") proto := r.Header.Get("X-Forwarded-Proto")
if !peerTrusted || proto == "" { if !peerTrusted || proto == "" {
@@ -70,6 +76,19 @@ func scheme(r *http.Request, peerTrusted bool) string {
return proto return proto
} }
// clientGroup is the client a request is counted toward: its IPv4
// address, or its IPv6 group, the netblock its IPv6 address is in of the
// length SWWAF_IPV6_GROUP_PREFIX sets, a /64 by default, since one abuser
// usually holds a whole /64. An IPv4 address in IPv6 form counts as IPv4.
func (h *handler) clientGroup(addr netip.Addr) netip.Prefix {
addr = addr.Unmap()
if addr.Is6() {
return netip.PrefixFrom(addr, h.config.IPv6GroupPrefix).Masked()
}
return netip.PrefixFrom(addr, addr.BitLen())
}
// isInside reports whether addr is in one of the netblocks. // isInside reports whether addr is in one of the netblocks.
func isInside(addr netip.Addr, netblocks []netip.Prefix) bool { func isInside(addr netip.Addr, netblocks []netip.Prefix) bool {
return slices.ContainsFunc(netblocks, func(netblock netip.Prefix) bool { return slices.ContainsFunc(netblocks, func(netblock netip.Prefix) bool {
@@ -78,11 +97,12 @@ func isInside(addr netip.Addr, netblocks []netip.Prefix) bool {
} }
// setForwardedHeaders sets the headers in which the app learns about the // setForwardedHeaders sets the headers in which the app learns about the
// visitor, so that it sees what it would see from traefik directly. A trusted // client, so that it sees what it would see from traefik directly. A
// proxy's forwarded headers pass on, with the proxy's own address added to // trusted proxy's forwarded headers pass on, with the proxy's own address
// X-Forwarded-For. Those of any other peer are its own claims and are replaced: // added to X-Forwarded-For. Those of any other peer are its own claims and
// X-Forwarded-For names the peer, X-Forwarded-Host the host it asked for, and // are replaced: X-Forwarded-For names the peer, X-Forwarded-Host the host
// X-Forwarded-Proto plain http, which is how it reached rproxy. // it asked for, and X-Forwarded-Proto plain http, which is how it reached
// smallwebwaf.
func setForwardedHeaders(in, out *http.Request, peer netip.Addr, trusted bool) { func setForwardedHeaders(in, out *http.Request, peer netip.Addr, trusted bool) {
forwardedFor := peer.String() forwardedFor := peer.String()
@@ -105,9 +125,9 @@ func setForwardedHeaders(in, out *http.Request, peer netip.Addr, trusted bool) {
return return
} }
// ReverseProxy has removed Forwarded and the three set below; these are the // ReverseProxy has removed Forwarded and the three set below; these
// other headers in which traefik tells the app about the visitor and its // are the other headers in which traefik tells the app about the
// request. // client and its request.
for _, name := range []string{ for _, name := range []string{
"X-Forwarded-Port", "X-Forwarded-Server", "X-Forwarded-Uri", "X-Forwarded-Port", "X-Forwarded-Server", "X-Forwarded-Uri",
"X-Forwarded-Method", "X-Forwarded-Prefix", "X-Forwarded-Tls-Client-Cert", "X-Forwarded-Method", "X-Forwarded-Prefix", "X-Forwarded-Tls-Client-Cert",
+165
View File
@@ -0,0 +1,165 @@
package proxy_test
import (
"encoding/json"
"net/http"
"testing"
)
const (
// trustLocalhost trusts the address every test connects from, and a
// network for proxies in front of it.
trustLocalhost = localhost + "/32,10.0.0.0/8"
// appHost is the host every test asks for.
appHost = "app.example"
// client is the client's address, as a proxy names it.
client = "203.0.113.9"
// forwardedFor is the header that lists the client and its proxies,
// and forwardedProto the one that gives the scheme the client used.
forwardedFor = "X-Forwarded-For"
forwardedProto = "X-Forwarded-Proto"
// secure is the scheme a client reached traefik with, and plain the
// one smallwebwaf serves.
secure = "https"
plain = "http"
)
// appHeaders is what the app tells about the headers it received.
type appHeaders struct {
Host string `json:"host"`
ForwardedFor string `json:"forwardedFor"`
ForwardedHost string `json:"forwardedHost"`
ForwardedProto string `json:"forwardedProto"`
RealIP string `json:"realIp"`
}
// clientAddressCase is a request and what smallwebwaf makes of it.
type clientAddressCase struct {
name string
env map[string]string
header http.Header
wantClient string
wantApp appHeaders
}
func TestClientAddressAndForwardedHeaders(t *testing.T) {
t.Parallel()
for _, tc := range clientAddressCases() {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
got, line := requestWithHeaders(t, tc.env, tc.header)
tc.wantApp.Host = appHost
if got != tc.wantApp {
t.Errorf("app received %+v, want %+v", got, tc.wantApp)
}
if line.ClientIP != tc.wantClient || line.PeerIP != localhost {
t.Errorf("log line has client_ip %q and peer_ip %q, want %q and %q",
line.ClientIP, line.PeerIP, tc.wantClient, localhost)
}
})
}
}
// clientAddressCases are the requests TestClientAddressAndForwardedHeaders
// sends, from 127.0.0.1, which the default trusted proxies leave out.
func clientAddressCases() []clientAddressCase {
trusted := map[string]string{trustedProxies: trustLocalhost}
forged := http.Header{
forwardedFor: {client},
"X-Forwarded-Host": {"forged.example"},
forwardedProto: {secure},
"X-Real-Ip": {client},
}
replaced := appHeaders{
ForwardedFor: localhost, ForwardedHost: appHost, ForwardedProto: plain,
}
return []clientAddressCase{{
name: "a peer outside the trusted proxies is the client, " +
"and its forwarded headers are replaced",
header: forged, wantClient: localhost, wantApp: replaced,
}, {
name: "set but empty, the trusted proxies trust nothing",
env: map[string]string{trustedProxies: ""},
header: forged, wantClient: localhost, wantApp: replaced,
}, {
name: "behind a trusted peer, the client is the first address " +
"outside the trusted proxies from the right",
env: trusted,
header: http.Header{
forwardedFor: {"198.51.100.7, " + client + ", 10.0.0.2"},
"X-Forwarded-Host": {appHost},
forwardedProto: {secure},
"X-Real-Ip": {client},
},
wantClient: client,
wantApp: appHeaders{
ForwardedFor: "198.51.100.7, " + client + ", 10.0.0.2, " + localhost,
ForwardedHost: appHost, ForwardedProto: secure, RealIP: client,
},
}, {
name: "when every address is a trusted proxy, the leftmost is the client",
env: trusted,
header: http.Header{forwardedFor: {"10.0.0.5, 10.0.0.2"}},
wantClient: "10.0.0.5",
wantApp: appHeaders{ForwardedFor: "10.0.0.5, 10.0.0.2, " + localhost},
}, {
name: "with no header, a trusted peer is the client",
env: trusted,
wantClient: localhost,
wantApp: appHeaders{ForwardedFor: localhost},
}, {
name: "an entry that is not an address ends the reading",
env: trusted,
header: http.Header{forwardedFor: {client + ", unknown, 10.0.0.2"}},
wantClient: "10.0.0.2",
wantApp: appHeaders{
ForwardedFor: client + ", unknown, 10.0.0.2, " + localhost,
},
}, {
name: "several header lines are read as one list",
env: trusted,
header: http.Header{forwardedFor: {"2001:db8::7", "10.0.0.2"}},
wantClient: "2001:db8::7",
wantApp: appHeaders{ForwardedFor: "2001:db8::7, 10.0.0.2, " + localhost},
}}
}
// requestWithHeaders sends a request for appHost with header through
// smallwebwaf, with the settings in env, and returns the headers the app
// received and the request's log line.
func requestWithHeaders(
t *testing.T, env map[string]string, header http.Header,
) (appHeaders, logLine) {
t.Helper()
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
_ = json.NewEncoder(w).Encode(appHeaders{
Host: r.Host,
ForwardedFor: r.Header.Get(forwardedFor),
ForwardedHost: r.Header.Get("X-Forwarded-Host"),
ForwardedProto: r.Header.Get(forwardedProto),
RealIP: r.Header.Get("X-Real-IP"),
})
})
addr, out := startProxy(t, app.URL, env)
req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
req.Host = appHost
req.Header = header.Clone()
answered := do(t, req)
var got appHeaders
err := json.Unmarshal(answered.body, &got)
if err != nil {
t.Fatalf("decode the app's answer %q: %v", answered.body, err)
}
return got, out.requestLine(t)
}
+124
View File
@@ -0,0 +1,124 @@
package proxy
import (
"errors"
"net/http"
"os"
"time"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/waf"
)
// checkCoreRuleSet inspects the request with the Core Rule Set, unless
// SWWAF_WAF_MODE is off or SWWAF_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
// SWWAF_WAF_ANOMALY_THRESHOLD is a match: it raises the waf_block alert,
// and in block mode refuses the request, which is an offence its client's
// history counts, and so returns ActionWAFBlocked. It returns "" for a
// request it does not refuse, and for one whose body meets a size or time
// limit while the Core Rule Set reads it, which it notes nothing of.
func (rq *request) checkCoreRuleSet() string {
cfg := rq.h.config
if cfg.WAFMode == config.WAFModeOff || pathExempt(rq.in, cfg.WAFExemptPaths) {
return ""
}
start := time.Now()
result := rq.inspect()
if rq.refused.Load() != nil {
return "" // the refusal for that limit, which check returns
}
rq.line.DurationWAF = new(requestlog.Milliseconds(time.Since(start)))
rq.line.WAFRuleIDs = result.RuleIDs
rq.line.WAFScore = &result.Score
for _, id := range result.RuleIDs {
rq.h.metrics.WAFMatched(cfg.WAFMode, id)
}
threshold := cfg.WAFAnomalyThreshold
if threshold == 0 || result.Score < threshold {
return ""
}
rq.alertWAFBlock(result)
if cfg.WAFMode == config.WAFModeDetect {
return ""
}
rq.wafBlocked = true
return requestlog.ActionWAFBlocked
}
// inspect runs the Core Rule Set on the request, which reads the part of
// its body it inspects within SWWAF_CLIENT_REQUEST_TIMEOUT, and keeps that
// part for the app. A client that runs out of time is refused with 408
// here, and a body over SWWAF_REQUEST_MAX_BYTES with 413 as it is read;
// check returns the refusal. A body that breaks off for any other reason
// is passed on as far as it came, and the request to the app fails there,
// as it would have without the Core Rule Set.
func (rq *request) inspect() waf.Result {
if rq.body == nil {
// Nothing is read of no body, so nothing can go wrong reading it.
result, _, _ := rq.h.coreRuleSet.Inspect(rq.in, rq.client, http.NoBody)
return result
}
_ = rq.rc.SetReadDeadline(rq.clientRequestDeadline())
result, read, err := rq.h.coreRuleSet.Inspect(rq.in, rq.client, rq.body)
// The timeouts that run while the request goes to the app take over.
_ = rq.rc.SetReadDeadline(time.Time{})
rq.body.readByCoreRuleSet = read
if errors.Is(err, os.ErrDeadlineExceeded) {
rq.refuse(refusal{
status: http.StatusRequestTimeout,
action: requestlog.ActionTimedOut,
limit: "SWWAF_CLIENT_REQUEST_TIMEOUT",
})
}
return result
}
// alertWAFBlock raises the waf_block alert for the request, which the Core
// Rule Set scored at result, at or over SWWAF_WAF_ANOMALY_THRESHOLD. Its
// detail gives the rule ids, the score, the method and the path with the
// query, and, for a request that is not refused for it, the mode: detect,
// or observe in observe mode.
func (rq *request) alertWAFBlock(result waf.Result) {
detail := map[string]any{
"rule_ids": result.RuleIDs,
"score": result.Score,
"method": rq.in.Method,
"path": rq.in.URL.RequestURI(),
}
switch {
case rq.h.config.WAFMode == config.WAFModeDetect:
detail["mode"] = config.WAFModeDetect
case rq.h.config.Observe:
detail["mode"] = "observe"
}
rq.h.alerts.Raise(alerts.Alert{
Event: alerts.EventWAFBlock,
Client: rq.client,
Netblock: rq.h.clientGroup(rq.client),
ASN: rq.line.ASN,
ASName: rq.line.ASName,
Country: rq.line.Country,
Reason: "scored by the Core Rule Set at or over SWWAF_WAF_ANOMALY_THRESHOLD",
Detail: detail,
})
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"io" "io"
@@ -8,19 +8,20 @@ import (
"strconv" "strconv"
"strings" "strings"
"testing" "testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// The Core Rule Set's settings the tests set, besides SWW_WAF_MODE, and // The Core Rule Set's settings the tests set, besides SWWAF_WAF_MODE, and
// its two modes that inspect requests. // its two modes that inspect requests.
const ( const (
wafAnomalyThreshold = "SWW_WAF_ANOMALY_THRESHOLD" wafAnomalyThreshold = "SWWAF_WAF_ANOMALY_THRESHOLD"
wafDisabledRules = "SWW_WAF_DISABLED_RULES" wafDisabledRules = "SWWAF_WAF_DISABLED_RULES"
wafExemptPaths = "SWW_WAF_EXEMPT_PATHS" wafExemptPaths = "SWWAF_WAF_EXEMPT_PATHS"
wafBodyLimit = "SWW_WAF_BODY_LIMIT" wafBodyLimit = "SWWAF_WAF_BODY_LIMIT"
block = "block" block = "block"
detect = "detect" detect = "detect"
) )
@@ -28,16 +29,9 @@ const (
// formData is the type of a form's body. // formData is the type of a form's body.
const formData = "application/x-www-form-urlencoded" const formData = "application/x-www-form-urlencoded"
// sizeLimit is SWW_WAF_BODY_LIMIT in the tests that read bodies, 1K as a
// setting.
const (
sizeLimit = 1 << 10
sizeLimitSetting = "1K"
)
// sqlInjection asks for / with an SQL injection in its query, which only // sqlInjection asks for / with an SQL injection in its query, which only
// the Core Rule Set's rule 942100 matches, with a score of 5, the default // the Core Rule Set's rule 942100 matches, with a score of 5, the default
// SWW_WAF_ANOMALY_THRESHOLD. // SWWAF_WAF_ANOMALY_THRESHOLD.
const sqlInjection = "/?id=1'%20OR%20'1'='1" const sqlInjection = "/?id=1'%20OR%20'1'='1"
// wantWAF checks the request log line's waf_rule_ids and waf_score, and // wantWAF checks the request log line's waf_rule_ids and waf_score, and
@@ -61,42 +55,6 @@ 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.ActionClientDenied)
wantHeuristic(t, line, "tag_deny", `{"tag": "exploitsignature"}`)
}
func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *testing.T) { func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *testing.T) {
t.Parallel() t.Parallel()
@@ -138,7 +96,7 @@ func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *test
} { } {
s, _, _ := startWithClock(t, "", map[string]string{wafMode: tc.mode}) s, _, _ := startWithClock(t, "", map[string]string{wafMode: tc.mode})
line := s.requestWithHeader(client, attack.path, attack.header, line, _ := s.requestWithHeader(client, attack.path, attack.header,
tc.status, tc.action) tc.status, tc.action)
wantWAF(t, line, &attack.score, attack.ruleIDs...) wantWAF(t, line, &attack.score, attack.ruleIDs...)
} }
@@ -146,16 +104,6 @@ func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *test
} }
} }
func TestCoreRuleSetRefusalNamesItsHeuristicScoreAndThreshold(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{wafMode: block})
line := s.request(client, sqlInjection, http.StatusForbidden,
requestlog.ActionWAFBlocked)
wantHeuristic(t, line, "core_rule_set", `{"score": 5, "threshold": 5}`)
}
func TestOrdinaryRequestIsInspectedAndPassed(t *testing.T) { func TestOrdinaryRequestIsInspectedAndPassed(t *testing.T) {
t.Parallel() t.Parallel()
@@ -171,7 +119,7 @@ func TestCoreRuleSetIsNotRunWhenOffOrForAnExemptClientPathOrRuleFileRefusal(
) { ) {
t.Parallel() t.Parallel()
const allowed = "192.0.2.60" // in SWW_ALLOW_NETS const allowed = "192.0.2.60" // in SWWAF_ALLOW_NETS
s, _, _ := startWithClock(t, "", map[string]string{ s, _, _ := startWithClock(t, "", map[string]string{
wafMode: block, wafMode: block,
@@ -180,7 +128,7 @@ func TestCoreRuleSetIsNotRunWhenOffOrForAnExemptClientPathOrRuleFileRefusal(
rulesDir: writeRules(t, testRules), rulesDir: writeRules(t, testRules),
}) })
// A client in SWW_ALLOW_NETS, and a path SWW_WAF_EXEMPT_PATHS // A client in SWWAF_ALLOW_NETS, and a path SWWAF_WAF_EXEMPT_PATHS
// exempts, are not inspected. // exempts, are not inspected.
line := s.request(allowed, sqlInjection, http.StatusOK, requestlog.ActionForward) line := s.request(allowed, sqlInjection, http.StatusOK, requestlog.ActionForward)
wantWAF(t, line, nil) wantWAF(t, line, nil)
@@ -196,10 +144,10 @@ func TestCoreRuleSetIsNotRunWhenOffOrForAnExemptClientPathOrRuleFileRefusal(
// A request a rule file refuses is not inspected. // A request a rule file refuses is not inspected.
line = s.request(otherClient, "/blocked?id=1'%20OR%20'1'='1", http.StatusForbidden, line = s.request(otherClient, "/blocked?id=1'%20OR%20'1'='1", http.StatusForbidden,
requestlog.ActionBlockedByBlockRule) requestlog.ActionRuleBlocked)
wantWAF(t, line, nil) wantWAF(t, line, nil)
// With SWW_WAF_MODE off, no request is. // With SWWAF_WAF_MODE off, no request is.
s, _, _ = startWithClock(t, "", map[string]string{wafMode: off}) s, _, _ = startWithClock(t, "", map[string]string{wafMode: off})
line = s.request(client, sqlInjection, http.StatusOK, requestlog.ActionForward) line = s.request(client, sqlInjection, http.StatusOK, requestlog.ActionForward)
wantWAF(t, line, nil) wantWAF(t, line, nil)
@@ -351,7 +299,7 @@ func TestBodiesReachTheAppAsSentWhileBodiesAreRead(t *testing.T) {
tc.name, len(got.body), got.status, len(tc.body)) tc.name, len(got.body), got.status, len(tc.body))
} }
line := out.endedLines(t, i+1)[i] line := out.requestLines(t, i+1)[i]
wantLine(t, line, http.StatusOK, requestlog.ActionForward) wantLine(t, line, http.StatusOK, requestlog.ActionForward)
if line.RequestBytes != int64(len(tc.body)) { if line.RequestBytes != int64(len(tc.body)) {
@@ -361,6 +309,119 @@ func TestBodiesReachTheAppAsSentWhileBodiesAreRead(t *testing.T) {
} }
} }
func TestFormBodyLongerThanTheLimitStreamsOnToTheApp(t *testing.T) {
t.Parallel()
const (
first = "a=" // and twice the limit of b's, then the rest
rest = 64 * sizeLimit
)
// past is closed once the app has received twice what the Core Rule
// Set reads, and got is the length of the whole body it received.
past := make(chan struct{})
got := make(chan int64, 1)
app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
n, _ := io.CopyN(io.Discard, r.Body, 2*sizeLimit)
close(past)
m, _ := io.Copy(io.Discard, r.Body)
got <- n + m
})
addr, out := startProxy(t, app.URL, map[string]string{
wafMode: block, wafBodyLimit: sizeLimitSetting,
})
// The client sends the rest only once the app has received the first
// part: were smallwebwaf to hold the body until the end, it would
// never come.
body, sender := io.Pipe()
go func() {
_, _ = io.WriteString(sender, first+strings.Repeat("b", 2*sizeLimit))
select {
case <-past:
case <-time.After(waitLimit):
t.Error("the app got no more than the Core Rule Set reads " +
"before the whole body was sent")
_ = sender.CloseWithError(io.ErrUnexpectedEOF)
return
}
_, _ = io.WriteString(sender, strings.Repeat("b", rest))
_ = sender.Close()
}()
req := newRequest(t, http.MethodPost, addr, "/", body)
req.Header.Set("Content-Type", formData)
wantStatus(t, do(t, req), http.StatusOK)
want := int64(len(first) + 2*sizeLimit + rest)
if n := <-got; n != want {
t.Errorf("the app got %d bytes, want %d", n, want)
}
wantLine(t, out.requestLine(t), http.StatusOK, requestlog.ActionForward)
}
func TestClientTooSlowToSendWhatTheCoreRuleSetReads(t *testing.T) {
t.Parallel()
app := startApp(t, func(http.ResponseWriter, *http.Request) {})
addr, out := startProxy(t, app.URL, map[string]string{
wafMode: block, wafBodyLimit: sizeLimitSetting,
clientRequestTimeout: shortTimeoutSetting, metricsToken: token,
})
conn := dial(t, addr)
send(t, conn, "POST /comment HTTP/1.1\r\nHost: app\r\nContent-Type: "+formData+
"\r\nContent-Length: 100\r\n\r\ncontent=the first bytes")
wantStatus(t, readResponse(t, conn), http.StatusRequestTimeout)
line := out.requestLine(t)
wantLine(t, line, http.StatusRequestTimeout, requestlog.ActionTimedOut)
wantNotSentToTheApp(t, line)
wantLimitHits(t, addr, clientRequestTimeout, 1)
}
func TestBodyOverTheSizeLimitWhileTheCoreRuleSetReadsIt(t *testing.T) {
t.Parallel()
app := startApp(t, func(http.ResponseWriter, *http.Request) {})
addr, out := startProxy(t, app.URL, map[string]string{
wafMode: block, wafBodyLimit: "4K",
requestMaxBytes: sizeLimitSetting, metricsToken: token,
})
// Sent in chunks, its length is not announced, and is found to be over
// the limit as the Core Rule Set reads it.
body := io.MultiReader(strings.NewReader("a=" + strings.Repeat("b", 2*sizeLimit)))
req := newRequest(t, http.MethodPost, addr, "/", body)
req.Header.Set("Content-Type", formData)
wantStatus(t, do(t, req), http.StatusRequestEntityTooLarge)
line := out.requestLine(t)
wantLine(t, line, http.StatusRequestEntityTooLarge, requestlog.ActionTooLarge)
wantNotSentToTheApp(t, line)
wantLimitHits(t, addr, requestMaxBytes, 1)
}
// wantNotSentToTheApp checks that the request of line was not sent to the
// app at all.
func wantNotSentToTheApp(t *testing.T, line logLine) {
t.Helper()
_, sent := line.fields["duration_upstream_total"]
if sent {
t.Error("log line has duration_upstream_total, for a request sent to the app")
}
}
func TestResponsesAreNotInspected(t *testing.T) { func TestResponsesAreNotInspected(t *testing.T) {
t.Parallel() t.Parallel()
@@ -380,12 +441,14 @@ func TestResponsesAreNotInspected(t *testing.T) {
t.Errorf("answered %d with %q, want 200 with the app's page", got.status, got.body) t.Errorf("answered %d with %q, want 200 with the app's page", got.status, got.body)
} }
wantLine(t, out.endedLine(t), http.StatusOK, requestlog.ActionForward) wantLine(t, out.requestLine(t), http.StatusOK, requestlog.ActionForward)
} }
func TestCoreRuleSetRefusalIsAnOffenceAndCountsTowardTheErrorBurst(t *testing.T) { func TestCoreRuleSetRefusalIsAnOffenceAndCountsTowardTheErrorBurst(t *testing.T) {
t.Parallel() t.Parallel()
const scraper = "192.0.2.200"
s, _, server := startWithClock(t, "", map[string]string{ s, _, server := startWithClock(t, "", map[string]string{
wafMode: block, errorBurstThreshold: "2", metricsToken: token, wafMode: block, errorBurstThreshold: "2", metricsToken: token,
}) })
@@ -404,25 +467,27 @@ func TestCoreRuleSetRefusalIsAnOffenceAndCountsTowardTheErrorBurst(t *testing.T)
line.LimitHit, line.Offence) line.LimitHit, line.Offence)
} }
s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
want := ratelimit.Offences{Limit: 1, WAFBlocked: 3} want := ratelimit.Offences{Limit: 1, WAFBlocked: 3}
if offences := historyOf(t, server, client).Offences; offences != want { if offences := historyOf(t, server, client).Offences; offences != want {
t.Errorf("history counts the offences %+v, want %+v", offences, want) t.Errorf("history counts the offences %+v, want %+v", offences, want)
} }
metrics := s.scrape() metrics := s.scrape(scraper)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_waf_matches_total{instance="app",mode="block",rule_id="942100"}`, 3) `smallwebwaf_waf_matches_total{instance="app",mode="block",rule_id="942100"}`, 3)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_offences_total{instance="app",kind="waf_blocked"}`, 3) `smallwebwaf_offences_total{instance="app",kind="waf_blocked"}`, 3)
wantMetric(t, metrics, `sww_requests_total{action="waf_blocked",`+ wantMetric(t, metrics, `smallwebwaf_requests_total{action="waf_blocked",`+
`instance="app",status_class="4xx"}`, 3) `instance="app",status_class="4xx"}`, 3)
} }
func TestDetectModeMatchIsNoOffenceAndNotCountedTowardTheErrorBurst(t *testing.T) { func TestDetectModeMatchIsNoOffenceAndNotCountedTowardTheErrorBurst(t *testing.T) {
t.Parallel() t.Parallel()
const scraper = "192.0.2.200"
s, _, server := startWithClock(t, "", map[string]string{ s, _, server := startWithClock(t, "", map[string]string{
wafMode: detect, errorBurstThreshold: "2", metricsToken: token, wafMode: detect, errorBurstThreshold: "2", metricsToken: token,
}) })
@@ -438,11 +503,11 @@ func TestDetectModeMatchIsNoOffenceAndNotCountedTowardTheErrorBurst(t *testing.T
t.Errorf("history counts the offences %+v, want none", offences) t.Errorf("history counts the offences %+v, want none", offences)
} }
metrics := s.scrape() metrics := s.scrape(scraper)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_waf_matches_total{instance="app",mode="detect",rule_id="942100"}`, 3) `smallwebwaf_waf_matches_total{instance="app",mode="detect",rule_id="942100"}`, 3)
wantNoSeries(t, metrics, wantNoSeries(t, metrics,
`sww_offences_total{instance="app",kind="waf_blocked"}`) `smallwebwaf_offences_total{instance="app",kind="waf_blocked"}`)
} }
func TestObserveModeLogsWhatTheCoreRuleSetWouldDo(t *testing.T) { func TestObserveModeLogsWhatTheCoreRuleSetWouldDo(t *testing.T) {
@@ -511,10 +576,9 @@ func TestCoreRuleSetMatchRaisesTheWAFBlockAlert(t *testing.T) {
Instance: alertInstance, Instance: alertInstance,
Time: clk.Now(), Time: clk.Now(),
Event: alerts.EventWAFBlock, Event: alerts.EventWAFBlock,
Host: appHost,
Client: netip.MustParseAddr(client), Client: netip.MustParseAddr(client),
Netblock: netip.MustParsePrefix(client + "/32"), Netblock: netip.MustParsePrefix(client + "/32"),
Reason: "scored by the Core Rule Set at or over SWW_WAF_ANOMALY_THRESHOLD", Reason: "scored by the Core Rule Set at or over SWWAF_WAF_ANOMALY_THRESHOLD",
Detail: detail, Detail: detail,
}) })
+21
View File
@@ -0,0 +1,21 @@
package proxy
import (
"slices"
)
// countryDenied reports whether the country lists refuse the request, by
// the client's country as it was looked up. A client without a country,
// or whose country cannot be found, is refused only by
// SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES.
func (rq *request) countryDenied() bool {
denied := rq.h.config.DeniedCountries
allowed := rq.h.config.ExclusivelyAllowedCountries
country := rq.line.Country
if slices.Contains(denied, country) {
return true
}
return len(allowed) > 0 && !slices.Contains(allowed, country)
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"encoding/json" "encoding/json"
@@ -33,13 +33,13 @@ func TestCountryLists(t *testing.T) {
env map[string]string env map[string]string
refused []string refused []string
}{ }{
{"denied", map[string]string{deniedCountries: "kp"}, []string{fromKP}},
{ {
"exclusively allowed", map[string]string{allowedCountries: "DE"}, "exclusively allowed", map[string]string{allowedCountries: "DE"},
[]string{fromKP, unplaced}, []string{fromKP, unplaced},
}, },
{ {
"with a country in SWW_TAG_DENY", "both", map[string]string{deniedCountries: "kp", allowedCountries: "de,fr"},
map[string]string{tagDeny: denyKP, allowedCountries: "de,fr"},
[]string{fromKP, unplaced}, []string{fromKP, unplaced},
}, },
} { } {
@@ -65,7 +65,7 @@ func TestCountryLists(t *testing.T) {
req.Header.Set(forwardedFor, sent.client) req.Header.Set(forwardedFor, sent.client)
got := do(t, req) got := do(t, req)
line := out.endedLines(t, i+1)[i] line := out.requestLines(t, i+1)[i]
if line.ASN != sent.asn || line.ASName != sent.asName || if line.ASN != sent.asn || line.ASName != sent.asName ||
line.Country != sent.country { line.Country != sent.country {
t.Errorf("log line has %q, %q and %q, want %q, %q and %q", t.Errorf("log line has %q, %q and %q, want %q, %q and %q",
@@ -90,24 +90,7 @@ func TestCountryLists(t *testing.T) {
} }
} }
func TestCountryRefusalNamesItsHeuristicCountryAndSetting(t *testing.T) { func TestCountryRefusalComesBeforeTheBody(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s, _, _ := startWithClock(t, geojsURL, map[string]string{
lookupTimeout: "1h", allowedCountries: "de",
})
line := s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied)
wantHeuristic(t, line, "countries",
`{"country": "KP", "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"}`)
line = s.get(unplaced, http.StatusForbidden, requestlog.ActionCountryDenied)
wantHeuristic(t, line, "countries",
`{"country": "", "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES"}`)
}
func TestCountryRefusalKeepsARequestFromTheApp(t *testing.T) {
t.Parallel() t.Parallel()
var calls atomic.Int32 var calls atomic.Int32
@@ -117,18 +100,22 @@ func TestCountryRefusalKeepsARequestFromTheApp(t *testing.T) {
}) })
geojsURL, _ := startGeoJS(t) geojsURL, _ := startGeoJS(t)
addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{ addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
lookupTimeout: "1h", lookupTimeout: "1h",
allowedCountries: "de", deniedCountries: "kp",
}) })
req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body")) req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
req.Header.Set(forwardedFor, fromKP) req.Header.Set(forwardedFor, fromKP)
wantStatus(t, do(t, req), http.StatusForbidden) wantStatus(t, do(t, req), http.StatusForbidden)
line := out.endedLine(t) line := out.requestLine(t)
wantLine(t, line, http.StatusForbidden, requestlog.ActionCountryDenied) wantLine(t, line, http.StatusForbidden, requestlog.ActionCountryDenied)
if line.RequestBytes != 0 {
t.Errorf("log line has request_bytes %d, want 0", line.RequestBytes)
}
if calls.Load() != 0 { if calls.Load() != 0 {
t.Errorf("the app was called %d times, want none", calls.Load()) t.Errorf("the app was called %d times, want none", calls.Load())
} }
@@ -202,7 +189,7 @@ func TestPrivateAddressIsNeverLookedUp(t *testing.T) {
env map[string]string env map[string]string
}{ }{
{"no setting needs the lookup", nil}, {"no setting needs the lookup", nil},
{"a tag setting needs it", map[string]string{tagDeny: denyKP}}, {"a country list is set", map[string]string{deniedCountries: "kp"}},
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
t.Parallel() t.Parallel()
@@ -224,7 +211,7 @@ func TestPrivateAddressIsNeverLookedUp(t *testing.T) {
wantStatus(t, do(t, req), http.StatusOK) wantStatus(t, do(t, req), http.StatusOK)
line := out.endedLines(t, i+1)[i] line := out.requestLines(t, i+1)[i]
wantLine(t, line, http.StatusOK, requestlog.ActionForward) wantLine(t, line, http.StatusOK, requestlog.ActionForward)
for _, field := range []string{"asn", "as_name", "country"} { for _, field := range []string{"asn", "as_name", "country"} {
@@ -262,11 +249,11 @@ func TestExclusiveListRefusesAPrivateAddressUnlessAllowed(t *testing.T) {
action string action string
}{ }{
{ {
"not in SWW_ALLOW_NETS", "", "not in SWWAF_ALLOW_NETS", "",
http.StatusForbidden, requestlog.ActionCountryDenied, http.StatusForbidden, requestlog.ActionCountryDenied,
}, },
{ {
"in SWW_ALLOW_NETS", "10.0.0.7,fd00::/8", "in SWWAF_ALLOW_NETS", "10.0.0.7,fd00::/8",
http.StatusOK, requestlog.ActionForward, http.StatusOK, requestlog.ActionForward,
}, },
} { } {
@@ -296,10 +283,10 @@ func TestExclusiveListRefusesAPrivateAddressUnlessAllowed(t *testing.T) {
// startGeoJS starts a stand-in for GeoJS, which places fromDE and fromKP, // startGeoJS starts a stand-in for GeoJS, which places fromDE and fromKP,
// each in an AS of its own, and no other address. It returns its URL, and // each in an AS of its own, and no other address. It returns its URL, and
// what returns the addresses it has been asked about. A test that needs // what returns the addresses it has been asked about. A test that needs
// the stand-in to be asked or to answer sets SWW_LOOKUP_TIMEOUT to an // the stand-in to be asked or to answer sets SWWAF_LOOKUP_TIMEOUT to an
// hour, whether or not a request waits for the answer: on the default, a // hour, whether or not a request waits for the answer: on the default
// hold-up of the test process can abandon the request to the stand-in, and // second, a hold-up of the test process can abandon the request to the
// leave the client unknown. // stand-in, and leave the client unknown.
func startGeoJS(t *testing.T) (string, func() []string) { func startGeoJS(t *testing.T) (string, func() []string) {
t.Helper() t.Helper()
@@ -367,7 +354,7 @@ const (
) )
// geojsAnswer is an answer of GeoJS about one address, with the fields // geojsAnswer is an answer of GeoJS about one address, with the fields
// sww reads. // smallwebwaf reads.
// //
//nolint:tagliatelle // GeoJS's own names //nolint:tagliatelle // GeoJS's own names
type geojsAnswer struct { type geojsAnswer struct {
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"net/http" "net/http"
@@ -9,7 +9,7 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/reputation" "sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
@@ -18,8 +18,8 @@ import (
// test puts in the copy of its decision list, at decisionsURL, that it // test puts in the copy of its decision list, at decisionsURL, that it
// needs, as reputation.json would at start. // needs, as reputation.json would at start.
const ( const (
crowdSecURL = "SWW_CROWDSEC_LAPI_URL" crowdSecURL = "SWWAF_CROWDSEC_LAPI_URL"
crowdSecKey = "SWW_CROWDSEC_LAPI_KEY" crowdSecKey = "SWWAF_CROWDSEC_LAPI_KEY"
lapi = "http://crowdsec.example:8080" lapi = "http://crowdsec.example:8080"
decisionsURL = lapi + "/v1/decisions" decisionsURL = lapi + "/v1/decisions"
bouncerKey = "crowdsec-key-0123456789abcdef" bouncerKey = "crowdsec-key-0123456789abcdef"
@@ -39,7 +39,7 @@ func TestClientTheCrowdSecDecisionListListsIsBannedUntilTheDecisionEnds(t *testi
expires := requestlog.FormatTime(fetched.Add(4 * time.Hour)) expires := requestlog.FormatTime(fetched.Add(4 * time.Hour))
// Its first request is refused, and bans it until the decision ends. // Its first request is refused, and bans it until the decision ends.
line := s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) line := s.get(client, http.StatusForbidden, requestlog.ActionBanned)
wantReputation(t, line, decisionsURL) wantReputation(t, line, decisionsURL)
if line.BanExpires != expires { if line.BanExpires != expires {
@@ -72,7 +72,7 @@ func TestClientTheCrowdSecDecisionListListsIsBannedUntilTheDecisionEnds(t *testi
// ban, and once it has ended the client is let through. // ban, and once it has ended the client is let through.
clk.advance(4*time.Hour - time.Second) clk.advance(4*time.Hour - time.Second)
line = s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned) line = s.get(client, http.StatusForbidden, requestlog.ActionBanned)
wantReputation(t, line) wantReputation(t, line)
if line.BanExpires != expires { if line.BanExpires != expires {
@@ -84,33 +84,17 @@ func TestClientTheCrowdSecDecisionListListsIsBannedUntilTheDecisionEnds(t *testi
// The ban and the hit are counted, and the list has the metrics of any // The ban and the hit are counted, and the list has the metrics of any
// list fetched from a URL. // list fetched from a URL.
metrics := s.scrape() metrics := s.scrape(unplaced)
labels := `{instance="` + alertInstance + `",source="` + decisionsURL + `"}` labels := `{instance="` + alertInstance + `",source="` + decisionsURL + `"}`
wantMetric(t, metrics, `sww_bans_made_total{cause="crowdsec",`+ wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="crowdsec",`+
`instance="`+alertInstance+`"}`, 1) `instance="`+alertInstance+`"}`, 1)
wantMetric(t, metrics, "sww_reputation_hits_total"+labels, 1) wantMetric(t, metrics, "smallwebwaf_reputation_hits_total"+labels, 1)
wantMetric(t, metrics, "sww_reputation_failures_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_failures_total"+labels, 0)
wantMetric(t, metrics, "sww_reputation_last_fetch_timestamp_seconds"+labels, wantMetric(t, metrics, "smallwebwaf_reputation_last_fetch_timestamp_seconds"+labels,
float64(fetched.Unix())) float64(fetched.Unix()))
} }
func TestCrowdSecBanNamesItsHeuristicScenarioAndEnd(t *testing.T) {
t.Parallel()
s, clk, server, _ := startWithAlerts(t, map[string]string{
crowdSecURL: lapi, crowdSecKey: bouncerKey,
})
loadDecisions(t, server, clk.Now(), `[{"duration": "4h0m0s", `+
`"scenario": "crowdsecurity/ssh-bf", "scope": "Ip", "type": "ban", `+
`"value": "`+client+`"}]`)
line := s.get(client, http.StatusForbidden, requestlog.ActionTemporarilyBanned)
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) { func TestEndedCrowdSecDecisionNoLongerBansThoughTheCopyStillHoldsIt(t *testing.T) {
t.Parallel() t.Parallel()
@@ -129,9 +113,9 @@ func TestEndedCrowdSecDecisionNoLongerBansThoughTheCopyStillHoldsIt(t *testing.T
// Just before its end, the decision bans a client in the netblock, and // Just before its end, the decision bans a client in the netblock, and
// one on an IPv6 address bans the address's group, the /64. // one on an IPv6 address bans the address's group, the /64.
clk.advance(time.Minute - time.Nanosecond) clk.advance(time.Minute - time.Nanosecond)
s.get("198.51.100.7", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get("198.51.100.7", http.StatusForbidden, requestlog.ActionBanned)
s.get("2001:db8::9", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get("2001:db8::9", http.StatusForbidden, requestlog.ActionBanned)
s.get("2001:db8::5", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get("2001:db8::5", http.StatusForbidden, requestlog.ActionBanned)
// Once it has ended, it bans no other client, and the bans it made end // Once it has ended, it bans no other client, and the bans it made end
// with it. // with it.
@@ -164,7 +148,7 @@ func TestObserveModeForwardsAClientTheCrowdSecDecisionListListsAndAlertsTheBan(
`"value": "`+client+`"}]`) `"value": "`+client+`"}]`)
line := s.get(client, http.StatusOK, requestlog.ActionForward) line := s.get(client, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionTemporarilyBanned) wantWouldAction(t, line, requestlog.ActionBanned)
wantReputation(t, line, decisionsURL) wantReputation(t, line, decisionsURL)
if held := server.Ledger.Snapshot(); len(held) != 0 { if held := server.Ledger.Snapshot(); len(held) != 0 {
@@ -184,7 +168,7 @@ func TestObserveModeForwardsAClientTheCrowdSecDecisionListListsAndAlertsTheBan(
// decisionsURL, answer, the engine's answer, fetched at fetched, as // decisionsURL, answer, the engine's answer, fetched at fetched, as
// reputation.json would at start. // reputation.json would at start.
func loadDecisions( func loadDecisions(
t *testing.T, server *discriminator.Server, fetched time.Time, answer string, t *testing.T, server *proxy.Server, fetched time.Time, answer string,
) { ) {
t.Helper() t.Helper()
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"maps" "maps"
@@ -10,15 +10,15 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
const errorBurstThreshold = "SWW_ERROR_BURST_THRESHOLD" const errorBurstThreshold = "SWWAF_ERROR_BURST_THRESHOLD"
// refused is a request the tests here send, which discriminator refuses after a rule // refused is a request the tests here send, which smallwebwaf refuses
// file match. // after a rule file match, or for a missing or wrong token.
type refused int type refused int
const ( const (
@@ -27,6 +27,11 @@ const (
// banRule is one its ban rule refuses with 403, and bans the client // banRule is one its ban rule refuses with 403, and bans the client
// for. // for.
banRule banRule
// noMetricsToken is one for the metrics without a token, and
// wrongAdminToken one for the bans with the metrics token, each
// refused with 401.
noMetricsToken
wrongAdminToken
) )
// send sends r from the client at from, checks its answer and log line as // send sends r from the client at from, checks its answer and log line as
@@ -37,10 +42,17 @@ func (r refused) send(s *sender, from string) logLine {
switch r { switch r {
case blockRule: case blockRule:
return s.request(from, blockedPath, http.StatusForbidden, return s.request(from, blockedPath, http.StatusForbidden,
requestlog.ActionBlockedByBlockRule) requestlog.ActionRuleBlocked)
case banRule: case banRule:
return s.request(from, probePath, http.StatusForbidden, return s.request(from, probePath, http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionTemporarilyBanned) case noMetricsToken:
return s.request(from, proxy.MetricsPath, http.StatusUnauthorized,
requestlog.ActionAdmin)
case wrongAdminToken:
line, _ := s.requestWithHeader(from, proxy.BansPath, "Authorization: "+bearer,
http.StatusUnauthorized, requestlog.ActionAdmin)
return line
} }
s.t.Fatalf("no request for the refusal %d", r) s.t.Fatalf("no request for the refusal %d", r)
@@ -48,16 +60,17 @@ func (r refused) send(s *sender, from string) logLine {
return logLine{} return logLine{}
} }
// startForErrorBurst is startWithClock with testRules, the metrics token and // startForErrorBurst is startWithClock with testRules, both tokens and
// SWW_ERROR_BURST_THRESHOLD at threshold, and the settings in env. // SWWAF_ERROR_BURST_THRESHOLD at threshold, and the settings in env.
func startForErrorBurst( func startForErrorBurst(
t *testing.T, threshold string, env map[string]string, t *testing.T, threshold string, env map[string]string,
) (*sender, *clock, *discriminator.Server) { ) (*sender, *clock, *proxy.Server) {
t.Helper() t.Helper()
settings := map[string]string{ settings := map[string]string{
errorBurstThreshold: threshold, errorBurstThreshold: threshold,
rulesDir: writeRules(t, testRules), rulesDir: writeRules(t, testRules),
adminToken: adminSecret,
metricsToken: token, metricsToken: token,
} }
maps.Copy(settings, env) maps.Copy(settings, env)
@@ -72,19 +85,15 @@ func TestErrorBurstBreaksAtOneOverTheThreshold(t *testing.T) {
name string name string
// refusals are four, one over the threshold of three. // refusals are four, one over the threshold of three.
refusals []refused refusals []refused
// nextAction is the action of the client's next request: the next
// request after a ban for a ban rule makes it permanent.
nextAction string
}{ }{
{"block rule", []refused{blockRule, blockRule, blockRule, blockRule}},
{ {
"block rule", "missing or wrong token",
[]refused{blockRule, blockRule, blockRule, blockRule}, []refused{noMetricsToken, wrongAdminToken, noMetricsToken, wrongAdminToken},
requestlog.ActionTemporarilyBanned,
}, },
{ {
"a ban rule last", "a mix ending in a ban rule",
[]refused{blockRule, blockRule, blockRule, banRule}, []refused{blockRule, noMetricsToken, blockRule, banRule},
requestlog.ActionPermanentlyBanned,
}, },
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
@@ -113,38 +122,21 @@ func TestErrorBurstBreaksAtOneOverTheThreshold(t *testing.T) {
"and limit", line.LimitHit, line.Offence) "and limit", line.LimitHit, line.Offence)
} }
s.get(client, http.StatusForbidden, tc.nextAction) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
}) })
} }
} }
func TestRefusalLimitBanNamesItsHeuristicWindowCountAndLimit(t *testing.T) {
t.Parallel()
s, _, _ := startForErrorBurst(t, "1", nil)
const ruleFigures = `{"rule_id": "blocked", "rule_action": "block"}`
line := blockRule.send(s, client)
wantHeuristic(t, line, "rule_files", ruleFigures)
wantAfterAnswerHeuristic(t, line, "", "null")
// The second refusal is the request refusal_limit bans for, and the line
// names both.
line = blockRule.send(s, client)
wantHeuristic(t, line, "rule_files", ruleFigures)
wantAfterAnswerHeuristic(t, line, "refusal_limit",
`{"window": "minute", "count": 2, "limit": 1}`)
}
func TestErrorBurstBanNotesHistoryAndMetrics(t *testing.T) { func TestErrorBurstBanNotesHistoryAndMetrics(t *testing.T) {
t.Parallel() t.Parallel()
const scraper = "192.0.2.200"
s, clk, server := startForErrorBurst(t, "2", nil) s, clk, server := startForErrorBurst(t, "2", nil)
start := clk.Now() start := clk.Now()
blockRule.send(s, client) blockRule.send(s, client)
blockRule.send(s, client) wrongAdminToken.send(s, client)
line := blockRule.send(s, client) line := blockRule.send(s, client)
expires := start.Add(time.Hour) expires := start.Add(time.Hour)
@@ -181,18 +173,20 @@ func TestErrorBurstBanNotesHistoryAndMetrics(t *testing.T) {
t.Fatalf("bans\n%+v\nwant\n%+v", got, want) t.Fatalf("bans\n%+v\nwant\n%+v", got, want)
} }
wantOffences := ratelimit.Offences{Limit: 1, BlockedByBlockRule: 3} wantOffences := ratelimit.Offences{Limit: 1, RuleBlocked: 2, TokenRefused: 1}
if offences := historyOf(t, server, client).Offences; offences != wantOffences { if offences := historyOf(t, server, client).Offences; offences != wantOffences {
t.Errorf("history counts the offences %+v, want %+v", offences, wantOffences) t.Errorf("history counts the offences %+v, want %+v", offences, wantOffences)
} }
metrics := s.scrape() metrics := s.scrape(scraper)
wantMetric(t, metrics, `sww_rate_limit_hits_total{instance="app",`+ wantMetric(t, metrics, `smallwebwaf_rate_limit_hits_total{instance="app",`+
`kind="refusals",window="minute"}`, 1) `kind="refusals",window="minute"}`, 1)
wantMetric(t, metrics, `sww_offences_total{instance="app",kind="limit"}`, 1) wantMetric(t, metrics, `smallwebwaf_offences_total{instance="app",kind="limit"}`, 1)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_offences_total{instance="app",kind="blocked_by_block_rule"}`, 3) `smallwebwaf_offences_total{instance="app",kind="rule_blocked"}`, 2)
wantMetric(t, metrics, `sww_bans_made_total{cause="limit",instance="app"}`, 1) wantMetric(t, metrics,
`smallwebwaf_offences_total{instance="app",kind="token_refused"}`, 1)
wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="limit",instance="app"}`, 1)
} }
func TestErrorBurstIsNotLoweredForAClientWithLowerLimits(t *testing.T) { func TestErrorBurstIsNotLoweredForAClientWithLowerLimits(t *testing.T) {
@@ -203,7 +197,7 @@ func TestErrorBurstIsNotLoweredForAClientWithLowerLimits(t *testing.T) {
lookupTimeout: "1h", lookupTimeout: "1h",
errorBurstThreshold: "2", errorBurstThreshold: "2",
rulesDir: writeRules(t, testRules), rulesDir: writeRules(t, testRules),
tagLimitPercent: countryTagDEHalf, countryLimitPercent: countryDEHalf,
}) })
// Half of the threshold would be one, which the second refusal is over. // Half of the threshold would be one, which the second refusal is over.
@@ -289,28 +283,32 @@ func TestErrorBurstCountsEachClientTheChecksApplyTo(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
allowed = "192.0.2.60" // in SWW_ALLOW_NETS allowed = "192.0.2.60" // in SWWAF_ALLOW_NETS
exempt = "192.0.2.50" // in SWW_RATE_LIMIT_EXEMPT_NETS exempt = "192.0.2.50" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
) )
s, _, _ := startForErrorBurst(t, "1", map[string]string{ s, _, _ := startForErrorBurst(t, "1", map[string]string{
allowNets: allowed, rateLimitExemptNets: exempt, allowNets: allowed, rateLimitExemptNets: exempt,
}) })
// A client in SWW_ALLOW_NETS is not refused, and so not counted. // A client in SWWAF_ALLOW_NETS still needs the token, but is not
// counted.
for range 3 { for range 3 {
s.request(allowed, blockedPath, http.StatusOK, requestlog.ActionForward) line := noMetricsToken.send(s, allowed)
if line.LimitHit != "" {
t.Errorf("log line has limit_hit %q, want none", line.LimitHit)
}
} }
// One the rate limits do not apply to is. // One the rate limits do not apply to is.
blockRule.send(s, exempt) noMetricsToken.send(s, exempt)
line := blockRule.send(s, exempt) line := wrongAdminToken.send(s, exempt)
if line.LimitHit != requestlog.LimitHitErrorBurst { if line.LimitHit != requestlog.LimitHitErrorBurst {
t.Errorf("log line has limit_hit %q, want error_burst", line.LimitHit) t.Errorf("log line has limit_hit %q, want error_burst", line.LimitHit)
} }
s.get(exempt, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(exempt, http.StatusForbidden, requestlog.ActionBanned)
} }
func TestErrorBurstBanSetsTheRefusalsBackToZero(t *testing.T) { func TestErrorBurstBanSetsTheRefusalsBackToZero(t *testing.T) {
@@ -338,6 +336,7 @@ func TestObserveModeLogsAndAlertsTheErrorBurst(t *testing.T) {
mode: observe, mode: observe,
errorBurstThreshold: "1", errorBurstThreshold: "1",
rulesDir: writeRules(t, testRules), rulesDir: writeRules(t, testRules),
adminToken: adminSecret,
}) })
start := clk.Now() start := clk.Now()
held := bans.Ban{ held := bans.Ban{
@@ -348,12 +347,11 @@ func TestObserveModeLogsAndAlertsTheErrorBurst(t *testing.T) {
} }
server.Ledger.Load([]bans.Ban{held}) server.Ledger.Load([]bans.Ban{held})
// Under a ban, enforce mode would have refused these before the rule, so // Under a ban, enforce mode would have refused these before the
// they are not counted. // endpoint, so their tokens are not counted.
for range 2 { for range 2 {
line := s.request(otherClient, blockedPath, http.StatusOK, line := wrongAdminToken.send(s, otherClient)
requestlog.ActionForward) wantWouldAction(t, line, requestlog.ActionBanned)
wantWouldAction(t, line, requestlog.ActionTemporarilyBanned)
if line.LimitHit != "" { if line.LimitHit != "" {
t.Errorf("log line has limit_hit %q, want none", line.LimitHit) t.Errorf("log line has limit_hit %q, want none", line.LimitHit)
@@ -362,10 +360,10 @@ func TestObserveModeLogsAndAlertsTheErrorBurst(t *testing.T) {
// The block rule's refusal, which enforce mode would have answered 403, // The block rule's refusal, which enforce mode would have answered 403,
// is the second of the client's, and would have banned it. // is the second of the client's, and would have banned it.
s.request(client, blockedPath, http.StatusOK, requestlog.ActionForward) wrongAdminToken.send(s, client)
line := s.request(client, blockedPath, http.StatusOK, requestlog.ActionForward) line := s.request(client, blockedPath, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionBlockedByBlockRule) wantWouldAction(t, line, requestlog.ActionRuleBlocked)
if line.LimitHit != requestlog.LimitHitErrorBurst || line.BanExpires != "" { if line.LimitHit != requestlog.LimitHitErrorBurst || line.BanExpires != "" {
t.Errorf("log line has limit_hit %q and ban_expires %q, want error_burst "+ t.Errorf("log line has limit_hit %q and ban_expires %q, want error_burst "+
+56
View File
@@ -0,0 +1,56 @@
package proxy_test
import (
"net/http"
"sync/atomic"
"testing"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
func TestHealthEndpointIsAnsweredBeforeAnyCheck(t *testing.T) {
t.Parallel()
var calls atomic.Int32
app := startApp(t, func(http.ResponseWriter, *http.Request) {
calls.Add(1)
})
// With a limit of one request a minute, any request counted before
// the last one would have it refused.
addr, out := startProxy(t, app.URL, map[string]string{rateLimitPerMinute: "1"})
const (
healthChecks = 3
contentType = "text/plain; charset=utf-8"
)
for range healthChecks {
got := get(t, addr, proxy.HealthPath)
wantStatus(t, got, http.StatusOK)
if string(got.body) != "ok\n" || got.header.Get("Content-Type") != contentType {
t.Errorf("health endpoint answered %q with Content-Type %q, want ok "+
"with %q", got.body, got.header.Get("Content-Type"), contentType)
}
}
wantStatus(t, get(t, addr, "/"), http.StatusOK)
lines := out.requestLines(t, healthChecks+1)
for _, line := range lines[:healthChecks] {
wantLine(t, line, http.StatusOK, requestlog.ActionAdmin)
if line.ResponseContentType != contentType {
t.Errorf("health check's log line has response_content_type %q, "+
"want %q", line.ResponseContentType, contentType)
}
}
wantLine(t, lines[healthChecks], http.StatusOK, requestlog.ActionForward)
if calls.Load() != 1 {
t.Errorf("the app was called %d times, want once", calls.Load())
}
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"io" "io"
@@ -8,7 +8,7 @@ import (
"testing" "testing"
"time" "time"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
@@ -20,7 +20,7 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
s, clk, server := startWithClock(t, geojsURL, map[string]string{ s, clk, server := startWithClock(t, geojsURL, map[string]string{
lookupTimeout: "1h", lookupTimeout: "1h",
rateLimitPerMinute: "2", rateLimitPerMinute: "2",
tagDeny: denyKP, deniedCountries: "kp",
}) })
start := clk.Now() start := clk.Now()
@@ -31,9 +31,9 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
clk.advance(time.Second) clk.advance(time.Second)
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
clk.advance(time.Second) clk.advance(time.Second)
s.get(fromDE, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
want := ratelimit.History{ want := ratelimit.History{
FirstSeen: start, FirstSeen: start,
@@ -45,7 +45,7 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
Requests: 4, Requests: 4,
Forwarded: 2, Forwarded: 2,
Refused: 2, Refused: 2,
// The app answers with no body, sww with its status text. // The app answers with no body, smallwebwaf with its status text.
ResponseBytes: 2 * int64(len("Forbidden\n")), ResponseBytes: 2 * int64(len("Forbidden\n")),
Responses: ratelimit.Responses{Status2xx: 2, Status4xx: 2}, Responses: ratelimit.Responses{Status2xx: 2, Status4xx: 2},
Offences: ratelimit.Offences{Limit: 1}, Offences: ratelimit.Offences{Limit: 1},
@@ -86,7 +86,7 @@ func TestHistoryCountsTheBodiesEachWay(t *testing.T) {
got := do(t, newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc"))) got := do(t, newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc")))
wantStatus(t, got, http.StatusOK) wantStatus(t, got, http.StatusOK)
out.endedLine(t) out.requestLine(t)
history := historyOf(t, server, localhost) history := historyOf(t, server, localhost)
if history.RequestBytes != 3 || history.ResponseBytes != 5 { if history.RequestBytes != 3 || history.ResponseBytes != 5 {
@@ -95,41 +95,43 @@ func TestHistoryCountsTheBodiesEachWay(t *testing.T) {
} }
} }
func TestOwnEndpointsAreNotInTheHistory(t *testing.T) { func TestHealthEndpointIsNotInTheHistory(t *testing.T) {
t.Parallel() t.Parallel()
s, _, server := startWithClock(t, "", map[string]string{metricsToken: token}) app := startApp(t, func(http.ResponseWriter, *http.Request) {})
addr, out, server := startProxyWithClock(t, app.URL, "", time.Now, nil)
s.adminRequest("", http.MethodGet, discriminator.HealthPath, "", http.StatusOK) wantStatus(t, get(t, addr, proxy.HealthPath), http.StatusOK)
s.adminRequest("", http.MethodGet, discriminator.MetricsPath, "", out.requestLine(t)
http.StatusUnauthorized)
s.scrape()
if clients := server.Limiter.Snapshot(); len(clients) != 0 { if clients := server.Limiter.Snapshot(); len(clients) != 0 {
t.Errorf("the table holds %+v, want no client", clients) t.Errorf("the table holds %+v, want no client", clients)
} }
} }
func TestPathUnderTheOwnPrefixIsNeitherForwardedNorRefused(t *testing.T) { func TestRequestForSmallwebwafIsRefusedOnlyWithoutTheToken(t *testing.T) {
t.Parallel() t.Parallel()
app := startApp(t, func(http.ResponseWriter, *http.Request) {}) app := startApp(t, func(http.ResponseWriter, *http.Request) {})
addr, out, server := startProxyWithClock(t, app.URL, "", time.Now, nil) addr, out, server := startProxyWithClock(t, app.URL, "", time.Now,
map[string]string{metricsToken: token})
wantStatus(t, get(t, addr, "/_sww/nothing"), http.StatusNotFound) // The metrics and the 404 are neither forwarded nor refused; the 401
out.endedLine(t) // is refused.
scrape(t, addr)
wantStatus(t, get(t, addr, "/_smallwebwaf/nothing"), http.StatusNotFound)
wantStatus(t, get(t, addr, proxy.MetricsPath), http.StatusUnauthorized)
out.requestLines(t, 3)
history := historyOf(t, server, localhost) history := historyOf(t, server, localhost)
if history.Requests != 1 || history.Forwarded != 0 || history.Refused != 0 { if history.Requests != 3 || history.Forwarded != 0 || history.Refused != 1 {
t.Errorf("history counts %d requests, %d forwarded and %d refused, "+ t.Errorf("history counts %d requests, %d forwarded and %d refused, "+
"want 1, 0 and 0", history.Requests, history.Forwarded, history.Refused) "want 3, 0 and 1", history.Requests, history.Forwarded, history.Refused)
} }
} }
// historyOf returns the history of the client at addr. // historyOf returns the history of the client at addr.
func historyOf( func historyOf(t *testing.T, server *proxy.Server, addr string) ratelimit.History {
t *testing.T, server *discriminator.Server, addr string,
) ratelimit.History {
t.Helper() t.Helper()
client := netip.MustParsePrefix(addr + "/32") client := netip.MustParsePrefix(addr + "/32")
+162
View File
@@ -0,0 +1,162 @@
package proxy_test
import (
"bytes"
"errors"
"io"
"net/http"
"strconv"
"sync/atomic"
"testing"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// sizeLimit is the size limit the tests set, 1K as a setting.
const (
sizeLimit = 1 << 10
sizeLimitSetting = "1K"
)
func TestRequestBodyLimit(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name string
size int
// announced sends the size in Content-Length; otherwise the body
// is sent in chunks with no length given.
announced bool
want int
action string
// refusedBeforeApp is a refusal before anything reaches the app.
// A body over the limit with no length given has already partly
// reached the app when it is refused.
refusedBeforeApp bool
}{
{"announced, over the limit", 2 * sizeLimit, true,
http.StatusRequestEntityTooLarge, requestlog.ActionTooLarge, true},
{"announced, at the limit", sizeLimit, true,
http.StatusOK, requestlog.ActionForward, false},
{"not announced, over the limit", 4 * sizeLimit, false,
http.StatusRequestEntityTooLarge, requestlog.ActionTooLarge, false},
{"not announced, at the limit", sizeLimit, false,
http.StatusOK, requestlog.ActionForward, false},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
var calls atomic.Int32
app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
calls.Add(1)
_, _ = io.Copy(io.Discard, r.Body)
})
addr, out := startProxy(t, app.URL, map[string]string{
requestMaxBytes: sizeLimitSetting,
metricsToken: token,
})
var body io.Reader = bytes.NewReader(make([]byte, tc.size))
if !tc.announced {
body = io.MultiReader(body) // hides the length
}
wantStatus(t, do(t, newRequest(t, http.MethodPost, addr, "/upload", body)),
tc.want)
wantLine(t, out.requestLine(t), tc.want, tc.action)
hits := 0
if tc.action == requestlog.ActionTooLarge {
hits = 1
}
wantLimitHits(t, addr, requestMaxBytes, hits)
if tc.refusedBeforeApp && calls.Load() != 0 {
t.Errorf("the app was called %d times, want never", calls.Load())
}
})
}
}
func TestResponseBodyLimit(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name string
size int
// announced sends the size in Content-Length; otherwise the body
// is sent in chunks with no length given.
announced bool
want int
action string
// received is how much of a body the client gets, and cutOff
// whether the connection is then cut.
received int
cutOff bool
}{
{"announced, over the limit", 2 * sizeLimit, true, http.StatusBadGateway,
requestlog.ActionTooLarge, len("Bad Gateway\n"), false},
{"announced, at the limit", sizeLimit, true, http.StatusOK,
requestlog.ActionForward, sizeLimit, false},
{"not announced, over the limit", 4 * sizeLimit, false, http.StatusOK,
requestlog.ActionTooLarge, sizeLimit, true},
{"not announced, at the limit", sizeLimit, false, http.StatusOK,
requestlog.ActionForward, sizeLimit, false},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
app := startApp(t, func(w http.ResponseWriter, _ *http.Request) {
answerWithSize(w, tc.size, tc.announced)
})
addr, out := startProxy(t, app.URL, map[string]string{
responseMaxBytes: sizeLimitSetting,
metricsToken: token,
})
got := get(t, addr, "/download")
wantStatus(t, got, tc.want)
if len(got.body) != tc.received ||
errors.Is(got.err, io.ErrUnexpectedEOF) != tc.cutOff {
t.Errorf("client got %d bytes (%v), want %d",
len(got.body), got.err, tc.received)
}
line := out.requestLine(t)
wantLine(t, line, tc.want, tc.action)
if line.UpstreamStatus != http.StatusOK {
t.Errorf("log line has upstream_status %d", line.UpstreamStatus)
}
hits := 0
if tc.action == requestlog.ActionTooLarge {
hits = 1
}
wantLimitHits(t, addr, responseMaxBytes, hits)
})
}
}
// answerWithSize answers with a body of size bytes, announced in
// Content-Length or sent in chunks with no length given.
func answerWithSize(w http.ResponseWriter, size int, announced bool) {
body := make([]byte, size)
if announced {
w.Header().Set("Content-Length", strconv.Itoa(size))
_, _ = w.Write(body)
return
}
// Sending part of it before the end keeps Go's server from working
// out the length.
_, _ = w.Write(body[:size/2])
_ = http.NewResponseController(w).Flush()
_, _ = w.Write(body[size/2:])
}
+71
View File
@@ -0,0 +1,71 @@
package proxy
import (
"context"
"net/http"
"net/netip"
"sneak.berlin/go/smallwebwaf/internal/lookup"
)
// The headers in which the app is passed the client's AS number and
// country while SWWAF_ADD_LOOKUP_HEADERS is set. Go writes every header
// name in this form, as it sends it and as it receives it, so X-Client-ASN
// arrives as X-Client-Asn, and Del removes a client's own whatever their
// case; header names are not case-sensitive.
const (
asnHeader = "X-Client-Asn"
countryHeader = "X-Client-Country"
)
// lookUp looks up the client's AS number and country, in the lookup
// database or through GeoJS, and notes them for the log line, unless
// SWWAF_LOOKUP_SOURCE is off or the client is on a private, loopback or
// link-local address, which no lookup can place. The lookup database
// answers at once. With GeoJS, while a setting needs the answer, such as a
// country list or a biased threshold, a new client's request waits for it.
// ctx is the request's own context.
func (rq *request) lookUp(ctx context.Context) {
if rq.h.config.LookupSource == "off" || !canBePlaced(rq.client) {
return
}
if rq.h.config.LookupSource == "file" {
rq.lookupAnswer = rq.h.lookupFile.LookUp(rq.h.clientGroup(rq.client))
} else {
rq.lookupAnswer = rq.h.geojs.LookUp(ctx, rq.h.clientGroup(rq.client))
}
rq.lookedUp = true
rq.line.ASN = rq.lookupAnswer.ASN
rq.line.ASName = rq.lookupAnswer.ASName
rq.line.Country = rq.lookupAnswer.Country
}
// addLookup adds answer, an answer about a client from the lookup
// database or GeoJS, to the client's history, and to the notes of the bans
// on its netblock that have no AS number, AS name or country yet.
func (h *handler) addLookup(answer lookup.Answer) {
h.limiter.AddLookup(answer.Client, answer.Answered,
answer.ASN, answer.ASName, answer.Country)
h.ledger.AddLookup(h.netblock(answer.Client.Addr()),
answer.ASN, answer.ASName, answer.Country)
}
// setLookupHeaders sets the headers in which the app is passed the
// client's AS number and country, leaving out one that is unknown.
func setLookupHeaders(header http.Header, asn, country string) {
if asn != "" {
header.Set(asnHeader, asn)
}
if country != "" {
header.Set(countryHeader, country)
}
}
// canBePlaced reports whether a lookup can place addr: private, loopback
// and link-local addresses have no AS number or country.
func canBePlaced(addr netip.Addr) bool {
return !addr.IsPrivate() && !addr.IsLoopback() && !addr.IsLinkLocalUnicast()
}
@@ -1,7 +1,9 @@
package discriminator_test package proxy_test
import ( import (
"net"
"net/http" "net/http"
"net/http/httptest"
"net/netip" "net/netip"
"path/filepath" "path/filepath"
"slices" "slices"
@@ -20,7 +22,7 @@ import (
// and country. // and country.
type asnAndCountry struct{ asn, asName, country string } type asnAndCountry struct{ asn, asName, country string }
// fileSource is the SWW_LOOKUP_SOURCE that looks clients up in the // fileSource is the SWWAF_LOOKUP_SOURCE that looks clients up in the
// lookup database. // lookup database.
const fileSource = "file" const fileSource = "file"
@@ -40,7 +42,7 @@ func TestEveryClientIsLookedUpWithoutWaitingWhileNoSettingNeedsIt(t *testing.T)
// comes too. None waits for GeoJS. // comes too. None waits for GeoJS.
for _, line := range []logLine{ for _, line := range []logLine{
s.get(fromDE, http.StatusOK, requestlog.ActionForward), s.get(fromDE, http.StatusOK, requestlog.ActionForward),
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited), s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited),
s.get(fromKP, http.StatusOK, requestlog.ActionForward), s.get(fromKP, http.StatusOK, requestlog.ActionForward),
} { } {
got := asnAndCountry{line.ASN, line.ASName, line.Country} got := asnAndCountry{line.ASN, line.ASName, line.Country}
@@ -94,9 +96,9 @@ func TestRequestThatWaitedForItsLookupIsCountedWhenItGoesOn(t *testing.T) {
clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 58, 0, time.UTC)} clk := &clock{now: time.Date(2026, 10, 6, 0, 0, 58, 0, time.UTC)}
addr, out, server := startProxyWithClock(t, app.URL, geojsURL, clk.Now, addr, out, server := startProxyWithClock(t, app.URL, geojsURL, clk.Now,
map[string]string{ map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
lookupTimeout: "1h", lookupTimeout: "1h",
tagDeny: denyKP, deniedCountries: "kp",
}) })
requestFromDE := func() *http.Request { requestFromDE := func() *http.Request {
@@ -140,7 +142,7 @@ func TestRequestThatWaitedForItsLookupIsCountedWhenItGoesOn(t *testing.T) {
t.Fatalf("first request: %v", err) t.Fatalf("first request: %v", err)
} }
wantLine(t, out.endedLines(t, 2)[1], http.StatusOK, requestlog.ActionForward) wantLine(t, out.requestLines(t, 2)[1], http.StatusOK, requestlog.ActionForward)
// The third request's count holds all three: the first was counted // The third request's count holds all three: the first was counted
// when it went on, in the minute under way, and the second's count // when it went on, in the minute under way, and the second's count
@@ -148,7 +150,7 @@ func TestRequestThatWaitedForItsLookupIsCountedWhenItGoesOn(t *testing.T) {
clk.advance(500 * time.Millisecond) clk.advance(500 * time.Millisecond)
wantStatus(t, do(t, requestFromDE()), http.StatusOK) wantStatus(t, do(t, requestFromDE()), http.StatusOK)
if got := out.endedLines(t, 3)[2].Counts.Minute; got != 3 { if got := out.requestLines(t, 3)[2].Counts.Minute; got != 3 {
t.Errorf("the third request's count in the minute is %v, want 3", got) t.Errorf("the third request's count in the minute is %v, want 3", got)
} }
} }
@@ -162,7 +164,7 @@ func TestASNumberAndNameInTheLogLineTheHistoryTheBanNotesAndTheAlert(t *testing.
addr, out, server, queue := startProxyWithAlerts(t, app.URL, geojsURL, clk.Now, addr, out, server, queue := startProxyWithAlerts(t, app.URL, geojsURL, clk.Now,
map[string]string{ map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
alertWebhookURL: "https://alerts.example/sww", alertWebhookURL: "https://alerts.example/smallwebwaf",
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
}) })
s := &sender{t: t, addr: addr, out: out} s := &sender{t: t, addr: addr, out: out}
@@ -179,7 +181,7 @@ func TestASNumberAndNameInTheLogLineTheHistoryTheBanNotesAndTheAlert(t *testing.
for _, line := range []logLine{ for _, line := range []logLine{
s.get(fromDE, http.StatusOK, requestlog.ActionForward), s.get(fromDE, http.StatusOK, requestlog.ActionForward),
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited), s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited),
} { } {
if got := (asnAndCountry{line.ASN, line.ASName, line.Country}); got != want { if got := (asnAndCountry{line.ASN, line.ASName, line.Country}); got != want {
t.Errorf("log line has %+v, want %+v", got, want) t.Errorf("log line has %+v, want %+v", got, want)
@@ -264,7 +266,7 @@ func TestClientsAreLookedUpInTheLookupDatabaseAndGeoJSIsNotAsked(t *testing.T) {
want asnAndCountry want asnAndCountry
}{ }{
{s.get(fromDE, http.StatusOK, requestlog.ActionForward), de}, {s.get(fromDE, http.StatusOK, requestlog.ActionForward), de},
{s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited), de}, {s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited), de},
{ {
s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied), s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied),
asnAndCountry{asnKP, asNameKP, "KP"}, asnAndCountry{asnKP, asNameKP, "KP"},
@@ -317,7 +319,7 @@ func TestLookupHeadersArePassedToTheAppAndTheClientsOwnRemoved(t *testing.T) {
addr, out, _ := startProxyWithClock(t, app.URL, geojsURL, time.Now, map[string]string{ addr, out, _ := startProxyWithClock(t, app.URL, geojsURL, time.Now, map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
lookupTimeout: "1h", lookupTimeout: "1h",
addLookupHeaders: on, addLookupHeaders: "true",
}) })
s := &sender{t: t, addr: addr, out: out} s := &sender{t: t, addr: addr, out: out}
@@ -379,21 +381,24 @@ func TestRequestWaitsAsLongAsTheLookupTimeoutSays(t *testing.T) {
// clock of the test's own: the wait lasts exactly as long as it should, // clock of the test's own: the wait lasts exactly as long as it should,
// however slowly the test process runs. Nothing in it may wait on the // however slowly the test process runs. Nothing in it may wait on the
// network, which would keep that clock from moving on: the request is // network, which would keep that clock from moving on: the request is
// handed to discriminator's handler, and GeoJS is one that never answers. // handed to the proxy's handler, and GeoJS is one that never answers.
synctest.Test(t, func(t *testing.T) { synctest.Test(t, func(t *testing.T) {
// Not the default. The exclusive list needs the answer, and the app // Not the default second. The exclusive list needs the answer, and
// is never reached. // the app is never reached.
const timeout = 3 * time.Second const timeout = 3 * time.Second
server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, server, out, _ := newProxy(t, "http://app.invalid", unansweredGeoJSURL,
map[string]string{ time.Now, map[string]string{
lookupTimeout: timeout.String(), lookupTimeout: timeout.String(),
allowedCountries: "DE", allowedCountries: "DE",
}) })
req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/",
http.NoBody)
req.RemoteAddr = net.JoinHostPort(fromDE, "1234")
began := time.Now() began := time.Now()
serveFromDE(t, server, http.MethodGet, http.NoBody) server.Handler.ServeHTTP(httptest.NewRecorder(), req)
if waited := time.Since(began); waited != timeout { if waited := time.Since(began); waited != timeout {
t.Errorf("the request waited %s for its answer, want %s", waited, timeout) t.Errorf("the request waited %s for its answer, want %s", waited, timeout)
+545
View File
@@ -0,0 +1,545 @@
package proxy_test
import (
"io"
"net/http"
"net/http/httptest"
"net/netip"
"strconv"
"strings"
"sync"
"sync/atomic"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
const (
metricsToken = "SWWAF_METRICS_TOKEN" //nolint:gosec // the setting's name
metricsTopN = "SWWAF_METRICS_TOP_N"
// token is the SWWAF_METRICS_TOKEN the tests set, and bearer how a
// request carries it.
token = "0123456789abcdef0123456789abcdef"
bearer = "Bearer " + token
)
func TestMetricsAreOffWhileTheTokenIsUnset(t *testing.T) {
t.Parallel()
var calls atomic.Int32
app := startApp(t, func(http.ResponseWriter, *http.Request) {
calls.Add(1)
})
addr, out := startProxy(t, app.URL, nil)
// An empty token does not match the unset one either.
for i, authorization := range []string{bearer, "Bearer ", ""} {
req := newRequest(t, http.MethodGet, addr, proxy.MetricsPath, http.NoBody)
if authorization != "" {
req.Header.Set("Authorization", authorization)
}
wantStatus(t, do(t, req), http.StatusNotFound)
wantLine(t, out.requestLines(t, i+1)[i], http.StatusNotFound,
requestlog.ActionAdmin)
}
if calls.Load() != 0 {
t.Errorf("the app was called %d times, want never", calls.Load())
}
}
func TestMetricsNeedTheTokenAndOtherPathsAreNotFound(t *testing.T) {
t.Parallel()
var calls atomic.Int32
app := startApp(t, func(http.ResponseWriter, *http.Request) {
calls.Add(1)
})
addr, out := startProxy(t, app.URL, map[string]string{metricsToken: token})
for i, tc := range []struct {
method, path, authorization string
status int
}{
{http.MethodGet, proxy.MetricsPath, "", http.StatusUnauthorized},
{
http.MethodGet, proxy.MetricsPath, "Bearer " + strings.ToUpper(token),
http.StatusUnauthorized,
},
{http.MethodGet, proxy.MetricsPath, "Basic " + token, http.StatusUnauthorized},
{http.MethodGet, proxy.MetricsPath, bearer, http.StatusOK},
{http.MethodGet, proxy.MetricsPath, "bearer " + token, http.StatusOK},
{http.MethodPost, proxy.MetricsPath, bearer, http.StatusNotFound},
{http.MethodGet, proxy.MetricsPath + "/", bearer, http.StatusNotFound},
{http.MethodGet, "/_smallwebwaf/bans", bearer, http.StatusNotFound},
{http.MethodPost, proxy.HealthPath, "", http.StatusNotFound},
} {
req := newRequest(t, tc.method, addr, tc.path, http.NoBody)
if tc.authorization != "" {
req.Header.Set("Authorization", tc.authorization)
}
got := do(t, req)
wantStatus(t, got, tc.status)
wantLine(t, out.requestLines(t, i+1)[i], tc.status, requestlog.ActionAdmin)
if tc.status == http.StatusUnauthorized &&
got.header.Get("WWW-Authenticate") != "Bearer" {
t.Errorf("%q was answered without WWW-Authenticate: Bearer",
tc.authorization)
}
if tc.status == http.StatusOK &&
!strings.Contains(string(got.body), "# TYPE smallwebwaf_requests_total counter") {
t.Errorf("the metrics are\n%s", got.body)
}
}
if calls.Load() != 0 {
t.Errorf("the app was called %d times, want never", calls.Load())
}
}
func TestMetricsAreAskedForThroughTheChecks(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{
metricsToken: token,
rateLimitPerMinute: "1",
})
// Asking for the metrics counts toward the client's limit of one
// request a minute, so its next request breaks it, and bans it. A
// banned client is refused the metrics too.
s.scrape(client)
s.get(client, http.StatusForbidden, requestlog.ActionRateLimited)
s.requestWithHeader(client, proxy.MetricsPath, "Authorization: "+bearer,
http.StatusForbidden, requestlog.ActionBanned)
}
func TestMetricsCountTheTraffic(t *testing.T) {
t.Parallel()
arrived, release := make(chan struct{}), make(chan struct{})
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
_, _ = io.Copy(io.Discard, r.Body)
if r.URL.Path == "/held" {
close(arrived)
<-release
}
_, _ = io.WriteString(w, "hello")
})
releaseApp := sync.OnceFunc(func() { close(release) })
t.Cleanup(releaseApp)
addr, out := startProxy(t, app.URL, map[string]string{metricsToken: token})
got := do(t, newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc")))
wantStatus(t, got, http.StatusOK)
wantStatus(t, get(t, addr, "/_smallwebwaf/nothing"), http.StatusNotFound)
out.requestLines(t, 2)
forward := `{action="forward",instance="app",status_class="2xx"}`
notFound := `{action="admin",instance="app",status_class="4xx"}`
// The request for the metrics is itself under way.
metrics := scrape(t, addr)
wantMetric(t, metrics, "smallwebwaf_requests_total"+forward, 1)
wantMetric(t, metrics, "smallwebwaf_requests_total"+notFound, 1)
wantMetric(t, metrics, "smallwebwaf_request_bytes_total"+forward, 3)
wantMetric(t, metrics, "smallwebwaf_response_bytes_total"+forward, 5)
wantMetric(t, metrics, "smallwebwaf_response_bytes_total"+notFound,
float64(len("Not Found\n")))
wantMetric(t, metrics,
`smallwebwaf_request_duration_seconds_count{instance="app"}`, 2)
wantMetric(t, metrics,
`smallwebwaf_upstream_duration_seconds_count{instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_requests_in_flight{instance="app"}`, 1)
metric(t, metrics, `go_goroutines{instance="app"}`)
metric(t, metrics, `process_start_time_seconds{instance="app"}`)
// A request the app holds is under way until it ends.
httpClient := newClient(t)
held := newRequest(t, http.MethodGet, addr, "/held", http.NoBody)
ended := make(chan error, 1)
go func() {
res, err := httpClient.Do(held)
if err == nil {
err = readAnswer(res).err
}
ended <- err
}()
<-arrived
wantMetric(t, scrape(t, addr), `smallwebwaf_requests_in_flight{instance="app"}`, 2)
releaseApp()
err := <-ended
if err != nil {
t.Fatalf("held request: %v", err)
}
out.requestLines(t, 5)
wantMetric(t, scrape(t, addr), `smallwebwaf_requests_in_flight{instance="app"}`, 1)
}
func TestMetricsCountLimitsAndBans(t *testing.T) {
t.Parallel()
const (
scraper = "192.0.2.200" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
denied = "192.0.2.50" // in SWWAF_DENY_NETS
)
s, clk, _ := startWithClock(t, "", map[string]string{
metricsToken: token,
rateLimitPerMinute: "1",
rateLimitExemptNets: scraper,
denyNets: denied,
banResponse: "close",
limitBanDuration: "1h",
maxBanDuration: "2h",
})
// SWWAF_BAN_RESPONSE=close sends no status at all.
s.get(denied, 0, requestlog.ActionDenied)
// A first broken limit bans for an hour.
s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, 0, requestlog.ActionRateLimited)
metrics := s.scrape(scraper)
wantMetric(t, metrics,
`smallwebwaf_requests_total{action="denied",instance="app",status_class="none"}`, 1)
wantMetric(t, metrics, `smallwebwaf_rate_limit_hits_total{instance="app",`+
`kind="requests",window="minute"}`, 1)
wantMetric(t, metrics, `smallwebwaf_offences_total{instance="app",kind="limit"}`, 1)
wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="limit",instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_active_bans{instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_permanent_bans{instance="app"}`, 0)
clk.advance(time.Hour)
wantMetric(t, s.scrape(scraper), `smallwebwaf_active_bans{instance="app"}`, 0)
// A limit broken again right after would ban for three hours, longer
// than SWWAF_MAX_BAN_DURATION, so the ban is permanent.
s.get(client, http.StatusOK, requestlog.ActionForward)
s.get(client, 0, requestlog.ActionRateLimited)
metrics = s.scrape(scraper)
wantMetric(t, metrics, `smallwebwaf_rate_limit_hits_total{instance="app",`+
`kind="requests",window="minute"}`, 2)
wantMetric(t, metrics, `smallwebwaf_offences_total{instance="app",kind="limit"}`, 2)
wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="limit",instance="app"}`, 2)
wantMetric(t, metrics, `smallwebwaf_active_bans{instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_permanent_bans{instance="app"}`, 1)
// denied, client, and the scraper as of its earlier requests.
wantMetric(t, metrics, `smallwebwaf_tracked_clients{instance="app"}`, 3)
}
func TestMetricsCountTheBansAnAdminMakes(t *testing.T) {
t.Parallel()
const scraper = "192.0.2.200" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
s, clk, server := startWithClock(t, "", map[string]string{
metricsToken: token,
adminToken: adminSecret,
rateLimitExemptNets: scraper,
})
const admins = `smallwebwaf_bans_made_total{cause="admin",instance="app"}`
wantMetric(t, s.scrape(scraper), admins, 0)
// As an admin's edit of bans.json that adds a ban is taken in.
server.Ledger.LoadEdit([]bans.Ban{{
Netblock: netip.MustParsePrefix(client + "/32"),
Start: clk.Now(),
}})
wantMetric(t, s.scrape(scraper), admins, 1)
// And a ban made through the endpoint.
s.admin(http.MethodPost, proxy.BansPath, banOtherClient, http.StatusOK)
wantMetric(t, s.scrape(scraper), admins, 2)
}
func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
t.Parallel()
const fromFR = "198.51.100.20"
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
_, _ = io.Copy(io.Discard, r.Body)
_, _ = io.WriteString(w, "hello")
})
env := map[string]string{
trustedProxies: trustLocalhost,
metricsToken: token,
metricsTopN: "2",
deniedCountries: "kp",
}
geojsURL, _ := startGeoJS(t)
addr, out, server := startProxyWithClock(t, app.URL, geojsURL, time.Now, env)
// The answers are kept before the requests, so that none waits for
// GeoJS.
server.GeoJS.Load([]lookup.Answer{
keptAnswer(fromKP, "KP"), keptAnswer(fromDE, "DE"), keptAnswer(fromFR, "FR"),
})
lines := 0
send := func(from string, times, status int) {
t.Helper()
for range times {
req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("abc"))
req.Header.Set(forwardedFor, from)
wantStatus(t, do(t, req), status)
// Each is counted before the next is sent, so that the
// countries are ranked in the order sent.
lines++
out.requestLines(t, lines)
}
}
// With two countries of their own, the third is counted as other.
send(fromKP, 3, http.StatusForbidden)
send(fromDE, 2, http.StatusOK)
send(fromFR, 1, http.StatusOK)
metrics := scrape(t, addr)
lines++
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="DE",instance="app"}`, 2)
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="other",instance="app"}`, 1)
wantMetric(t, metrics,
`smallwebwaf_country_list_refusals_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`smallwebwaf_country_request_bytes_total{country="KP",instance="app"}`, 0)
wantMetric(t, metrics,
`smallwebwaf_country_request_bytes_total{country="DE",instance="app"}`, 6)
wantMetric(t, metrics,
`smallwebwaf_country_response_bytes_total{country="KP",instance="app"}`,
float64(3*len("Forbidden\n")))
wantMetric(t, metrics,
`smallwebwaf_country_response_bytes_total{country="other",instance="app"}`,
float64(len("hello")))
wantNoSeries(t, metrics,
`smallwebwaf_country_requests_total{country="FR",instance="app"}`)
// Once FR is busier than DE, it takes DE's place: its series counts
// from then on, and DE's is gone.
send(fromFR, 3, http.StatusOK)
metrics = scrape(t, addr)
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="KP",instance="app"}`, 3)
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="FR",instance="app"}`, 2)
wantMetric(t, metrics,
`smallwebwaf_country_requests_total{country="other",instance="app"}`, 2)
wantNoSeries(t, metrics,
`smallwebwaf_country_requests_total{country="DE",instance="app"}`)
wantNoSeries(t, metrics,
`smallwebwaf_country_request_bytes_total{country="DE",instance="app"}`)
}
func TestMetricsByASNumberKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
t.Parallel()
geojsURL, _ := startGeoJS(t)
s, clk, server := startWithClock(t, geojsURL, map[string]string{
metricsToken: token,
metricsTopN: "1",
})
// The answers are kept before the requests, so that GeoJS gives none
// of its own. Each client is in an AS of its own.
answer := func(addr, asn string) lookup.Answer {
return lookup.Answer{
Client: netip.MustParsePrefix(addr + "/32"), ASN: asn,
Answered: clk.Now(), Used: clk.Now(),
}
}
server.GeoJS.Load([]lookup.Answer{
answer(fromDE, "AS64501"), answer(fromKP, "AS64502"),
})
// With one AS number of its own, the other is counted as other. The
// metrics are asked for from a private address, which has no AS number.
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromDE, http.StatusOK, requestlog.ActionForward)
s.get(fromKP, http.StatusOK, requestlog.ActionForward)
metrics := s.scrape("10.0.0.9")
wantMetric(t, metrics,
`smallwebwaf_asn_requests_total{asn="AS64501",instance="app"}`, 2)
wantMetric(t, metrics,
`smallwebwaf_asn_requests_total{asn="other",instance="app"}`, 1)
wantMetric(t, metrics,
`smallwebwaf_asn_request_bytes_total{asn="AS64501",instance="app"}`, 0)
wantMetric(t, metrics,
`smallwebwaf_asn_response_bytes_total{asn="other",instance="app"}`, 0)
wantNoSeries(t, metrics,
`smallwebwaf_asn_requests_total{asn="AS64502",instance="app"}`)
}
func TestMetricsCountGeoJSRequestsAndFailures(t *testing.T) {
t.Parallel()
geojs := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusServiceUnavailable)
}))
t.Cleanup(geojs.Close)
app := startApp(t, func(http.ResponseWriter, *http.Request) {})
addr, _ := startProxyWithGeoJS(t, app.URL, geojs.URL, map[string]string{
trustedProxies: trustLocalhost,
metricsToken: token,
deniedCountries: "kp",
})
// GeoJS fails, so the client counts as coming from an unknown country,
// which SWWAF_DENIED_COUNTRIES does not refuse.
req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
req.Header.Set(forwardedFor, fromDE)
wantStatus(t, do(t, req), http.StatusOK)
// The client stops waiting for GeoJS after a second, so GeoJS's
// failure can come after its request has ended.
deadline := time.Now().Add(waitLimit)
metrics := scrape(t, addr)
for metric(t, metrics, `smallwebwaf_geojs_failures_total{instance="app"}`) == 0 &&
time.Now().Before(deadline) {
time.Sleep(pollInterval)
metrics = scrape(t, addr)
}
wantMetric(t, metrics, `smallwebwaf_geojs_requests_total{instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_geojs_failures_total{instance="app"}`, 1)
wantMetric(t, metrics, `smallwebwaf_geojs_unanswered_total{instance="app"}`, 1)
}
// keptAnswer returns GeoJS's answer that the client at addr is in
// country, given now.
func keptAnswer(addr, country string) lookup.Answer {
now := time.Now()
return lookup.Answer{
Client: netip.MustParsePrefix(addr + "/32"), Country: country,
Answered: now, Used: now,
}
}
// scrape asks smallwebwaf at addr for the metrics, with the token, and
// returns them.
func scrape(t *testing.T, addr string) string {
t.Helper()
req := newRequest(t, http.MethodGet, addr, proxy.MetricsPath, http.NoBody)
req.Header.Set("Authorization", bearer)
got := do(t, req)
if got.status != http.StatusOK {
t.Fatalf("the metrics were answered %d", got.status)
}
return string(got.body)
}
// scrape asks for the metrics, with the token, from the client at from,
// and returns them.
func (s *sender) scrape(from string) string {
s.t.Helper()
_, metrics := s.requestWithHeader(from, proxy.MetricsPath, "Authorization: "+bearer,
http.StatusOK, requestlog.ActionAdmin)
return metrics
}
// metric returns the value of series in metrics, which are in the
// Prometheus text format. series is a name and its labels in the order of
// their names, such as
// smallwebwaf_offences_total{instance="app",kind="limit"}. It fails the
// test if there is no such series.
func metric(t *testing.T, metrics, series string) float64 {
t.Helper()
for line := range strings.Lines(metrics) {
value, found := strings.CutPrefix(strings.TrimSuffix(line, "\n"), series+" ")
if !found {
continue
}
number, err := strconv.ParseFloat(value, 64)
if err != nil {
t.Fatalf("%s has the value %q", series, value)
}
return number
}
t.Fatalf("no series %s in the metrics:\n%s", series, metrics)
return 0
}
// wantMetric checks the value of series in metrics, as metric reads it.
func wantMetric(t *testing.T, metrics, series string, want float64) {
t.Helper()
got := metric(t, metrics, series)
if got != want {
t.Errorf("%s is %v, want %v", series, got, want)
}
}
// wantNoSeries checks that metrics have no series series.
func wantNoSeries(t *testing.T, metrics, series string) {
t.Helper()
if strings.Contains(metrics, "\n"+series+" ") {
t.Errorf("there is a series %s", series)
}
}
// wantLimitHits checks that the metrics of smallwebwaf at addr count hits
// requests that passed the size or time limit of the setting limit, with
// no series for it when hits is 0.
func wantLimitHits(t *testing.T, addr, limit string, hits int) {
t.Helper()
series := `smallwebwaf_size_and_time_limit_hits_total{instance="app",limit="` +
limit + `"}`
metrics := scrape(t, addr)
if hits == 0 {
wantNoSeries(t, metrics, series)
return
}
wantMetric(t, metrics, series, float64(hits))
}
@@ -1,129 +1,33 @@
package discriminator_test package proxy_test
import ( import (
"bytes"
"io"
"net/http" "net/http"
"net/netip" "net/netip"
"reflect" "reflect"
"sync/atomic"
"testing" "testing"
"time" "time"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// observe is the value of SWW_MODE for observe mode. // observe is the value of SWWAF_MODE for observe mode.
const observe = "observe" const observe = "observe"
func TestBanActionSaysWhetherTheBanRunsOut(t *testing.T) {
t.Parallel()
const trapPath = "/wp-login.php"
for _, tc := range []struct {
name string
cause string
// endsIn is how long after the request the ban ends: negative for a
// ban that has ended, and zero for a permanent ban.
endsIn time.Duration
path string
want string
}{
{
"temporary ban", bans.CauseAdmin, time.Hour, "/",
requestlog.ActionTemporarilyBanned,
},
{"permanent ban", bans.CauseAdmin, 0, "/", requestlog.ActionPermanentlyBanned},
{
"request that makes a ban permanent", bans.CauseAttack, time.Hour, "/",
requestlog.ActionPermanentlyBanned,
},
{
"trap path after an attack ban ended", bans.CauseAttack, -time.Hour,
trapPath, requestlog.ActionPermanentlyBanned,
},
{
"first trap path after another ban ended", bans.CauseAdmin, -time.Hour,
trapPath, requestlog.ActionTemporarilyBanned,
},
} {
for _, modeValue := range []string{"enforce", observe} {
t.Run(tc.name+" in "+modeValue, func(t *testing.T) {
t.Parallel()
s, clk, server := startWithClock(t, "", map[string]string{
trapPaths: trapPathList, mode: modeValue,
})
ban := bans.Ban{
Netblock: netip.MustParsePrefix(client + "/32"),
Start: clk.Now().Add(-2 * time.Hour),
Cause: tc.cause,
}
if tc.endsIn != 0 {
ban.Expires = clk.Now().Add(tc.endsIn)
}
server.Ledger.Load([]bans.Ban{ban})
if modeValue == observe {
line := s.request(client, tc.path, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, tc.want)
return
}
s.request(client, tc.path, http.StatusForbidden, tc.want)
})
}
}
}
func TestObserveModeNamesAPermanentBanWhoseAlertWouldBeSent(t *testing.T) {
t.Parallel()
s, clk, server, queue := startWithAlerts(t, map[string]string{
trapPaths: trapPathList, mode: observe,
})
server.Ledger.Load([]bans.Ban{{
Netblock: netip.MustParsePrefix(client + "/32"),
Start: clk.Now().Add(-2 * time.Hour),
Expires: clk.Now().Add(-time.Hour),
Cause: bans.CauseAttack,
}})
line := s.request(client, "/wp-login.php", http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionPermanentlyBanned)
waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
if len(waiting) != 1 || waiting[0].Event != alerts.EventPermanentBan {
t.Errorf("alerts waiting are %+v, want one %s", waiting, alerts.EventPermanentBan)
}
}
func TestObserveModeNamesTheHeuristicThatWouldHaveRefused(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{
mode: observe, denyNets: client,
})
line := s.get(client, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionClientDenied)
wantHeuristic(t, line, "deny_nets", `{"netblock": "`+client+`/32"}`)
}
func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) { func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
denied = "192.0.2.50" // in SWW_DENY_NETS denied = "192.0.2.50" // in SWWAF_DENY_NETS
banned = otherClient // under a ban read from bans.json banned = otherClient // under a ban read from bans.json
) )
for _, tc := range []struct { for _, tc := range []struct {
setting string // "" leaves SWW_MODE at its default setting string // "" leaves SWWAF_MODE at its default
observe bool observe bool
}{ }{
{"", false}, {"", false},
@@ -138,7 +42,7 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
lookupTimeout: "1h", lookupTimeout: "1h",
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
denyNets: denied, denyNets: denied,
tagDeny: denyKP, deniedCountries: "kp",
} }
if tc.setting != "" { if tc.setting != "" {
@@ -157,10 +61,10 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
s.get(fromDE, http.StatusOK, requestlog.ActionForward) s.get(fromDE, http.StatusOK, requestlog.ActionForward)
for _, sent := range []struct{ from, refusal string }{ for _, sent := range []struct{ from, refusal string }{
{denied, requestlog.ActionClientDenied}, {denied, requestlog.ActionDenied},
{banned, requestlog.ActionTemporarilyBanned}, {banned, requestlog.ActionBanned},
{fromKP, requestlog.ActionClientDenied}, {fromKP, requestlog.ActionCountryDenied},
{fromDE, requestlog.ActionClientIsRateLimited}, {fromDE, requestlog.ActionRateLimited},
} { } {
if !tc.observe { if !tc.observe {
line := s.get(sent.from, http.StatusForbidden, sent.refusal) line := s.get(sent.from, http.StatusForbidden, sent.refusal)
@@ -172,6 +76,11 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
// Passed to the app, which answered it. // Passed to the app, which answered it.
line := s.get(sent.from, http.StatusOK, requestlog.ActionForward) line := s.get(sent.from, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, sent.refusal) wantWouldAction(t, line, sent.refusal)
if line.UpstreamStatus != http.StatusOK {
t.Errorf("log line has upstream_status %d, want 200",
line.UpstreamStatus)
}
} }
}) })
} }
@@ -198,7 +107,7 @@ func TestObserveModeMakesNoBanAndKeepsTheBansItHas(t *testing.T) {
for range 2 { for range 2 {
line := s.get(client, http.StatusOK, requestlog.ActionForward) line := s.get(client, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionClientIsRateLimited) wantWouldAction(t, line, requestlog.ActionRateLimited)
if line.LimitHit != minute || line.Offence != requestlog.OffenceLimit || if line.LimitHit != minute || line.Offence != requestlog.OffenceLimit ||
line.BanExpires != "" { line.BanExpires != "" {
@@ -211,7 +120,7 @@ func TestObserveModeMakesNoBanAndKeepsTheBansItHas(t *testing.T) {
// The ban read from bans.json refuses nothing, and so counts no // The ban read from bans.json refuses nothing, and so counts no
// refusal in its notes, but is kept. // refusal in its notes, but is kept.
line := s.get(otherClient, http.StatusOK, requestlog.ActionForward) line := s.get(otherClient, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionTemporarilyBanned) wantWouldAction(t, line, requestlog.ActionBanned)
if line.BanExpires != requestlog.FormatTime(kept.Expires) { if line.BanExpires != requestlog.FormatTime(kept.Expires) {
t.Errorf("log line has ban_expires %q, want %s", line.BanExpires, t.Errorf("log line has ban_expires %q, want %s", line.BanExpires,
@@ -224,6 +133,62 @@ func TestObserveModeMakesNoBanAndKeepsTheBansItHas(t *testing.T) {
} }
} }
func TestObserveModeKeepsTheSizeLimitsAndTheToken(t *testing.T) {
t.Parallel()
const denied = "192.0.2.50" // in SWWAF_DENY_NETS
var calls atomic.Int32
app := startApp(t, func(w http.ResponseWriter, _ *http.Request) {
calls.Add(1)
answerWithSize(w, 2*sizeLimit, true)
})
addr, out := startProxy(t, app.URL, map[string]string{
mode: observe,
trustedProxies: trustLocalhost,
denyNets: denied,
requestMaxBytes: sizeLimitSetting,
responseMaxBytes: sizeLimitSetting,
metricsToken: token,
})
// SWWAF_DENY_NETS would refuse each request; instead a size limit or
// the missing token does.
for i, tc := range []struct {
method, path string
body io.Reader
status int
action string
}{
{
http.MethodPost, "/upload", bytes.NewReader(make([]byte, 2*sizeLimit)),
http.StatusRequestEntityTooLarge, requestlog.ActionTooLarge,
},
{
http.MethodGet, "/download", http.NoBody,
http.StatusBadGateway, requestlog.ActionTooLarge,
},
{
http.MethodGet, proxy.MetricsPath, http.NoBody,
http.StatusUnauthorized, requestlog.ActionAdmin,
},
} {
req := newRequest(t, tc.method, addr, tc.path, tc.body)
req.Header.Set(forwardedFor, denied)
wantStatus(t, do(t, req), tc.status)
line := out.requestLines(t, i+1)[i]
wantLine(t, line, tc.status, tc.action)
wantWouldAction(t, line, requestlog.ActionDenied)
}
// The upload was refused before it reached the app.
if calls.Load() != 1 {
t.Errorf("the app was called %d times, want once", calls.Load())
}
}
// wantWouldAction checks the request log line's would_action, and that a // wantWouldAction checks the request log line's would_action, and that a
// line that should have none has no such field. // line that should have none has no such field.
func wantWouldAction(t *testing.T, line logLine, want string) { func wantWouldAction(t *testing.T, line logLine, want string) {
+556
View File
@@ -0,0 +1,556 @@
package proxy_test
import (
"bufio"
"bytes"
"errors"
"io"
"net/http"
"reflect"
"slices"
"strings"
"sync/atomic"
"testing"
"time"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
)
// A request target with an escaped slash and space in its path, and a
// query with a parameter ReverseProxy cannot parse.
const (
rawPath = "/some%2Fpath/with%20space"
rawQuery = "b=2&a=1&bad=%zz;x"
)
// chunkSize is the size of each part of a body a test sends in parts.
const chunkSize = 1 << 10
var errNotStreamed = errors.New("the first part never reached the app")
// appSaw is what the app received.
type appSaw struct {
method string
target string
header http.Header
body []byte
}
func TestPassesRequestAndAnswerUnchanged(t *testing.T) {
t.Parallel()
requestBody := bytes.Repeat([]byte("request body "), 8000)
answerBody := bytes.Repeat([]byte("answer body "), 8000)
saw := make(chan appSaw, 1)
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
body, _ := io.ReadAll(r.Body)
saw <- appSaw{r.Method, r.RequestURI, r.Header.Clone(), body}
w.Header().Set("X-App", "yes")
w.Header().Add("Set-Cookie", "a=1")
w.Header().Add("Set-Cookie", "b=2")
w.WriteHeader(http.StatusTeapot)
_, _ = w.Write(answerBody)
})
addr, out := startProxy(t, app.URL, nil)
req := newRequest(t, http.MethodPatch, addr, rawPath+"?"+rawQuery,
bytes.NewReader(requestBody))
req.Header.Add("X-Test", "one")
req.Header.Add("X-Test", "two")
req.Header.Set("User-Agent", "test-agent")
got := do(t, req)
wantAppSaw(t, <-saw, requestBody)
wantAnswer(t, got, answerBody)
line := out.requestLine(t)
wantLine(t, line, http.StatusTeapot, requestlog.ActionForward)
wantRequestFields(t, line, addr, len(requestBody), len(answerBody))
}
func TestPassesThePathAsSent(t *testing.T) {
t.Parallel()
for _, path := range []string{
// An encoded slash and a character Go escapes: |, ^, and é sent
// as its UTF-8 bytes.
"/a%2Fb|c", "/feat%2Fx/file^1", "/x%2Fy/café",
// A path starting with //, which Go would send as a scheme and
// host if it were put in URL.Opaque.
"//a%2Fb",
} {
t.Run(path, func(t *testing.T) {
t.Parallel()
saw := make(chan string, 1)
app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
saw <- r.RequestURI
})
addr, out := startProxy(t, app.URL, nil)
conn := dial(t, addr)
send(t, conn, "GET "+path+"?q=1 HTTP/1.1\r\nHost: "+appHost+"\r\n\r\n")
got := readResponse(t, conn)
if got.status != http.StatusOK {
t.Fatalf("status %d, want %d", got.status, http.StatusOK)
}
target := <-saw
if target != path+"?q=1" {
t.Errorf("app saw %s, want %s", target, path+"?q=1")
}
line := out.requestLine(t)
if line.Path != path {
t.Errorf("log line has path %s, want %s", line.Path, path)
}
})
}
}
// wantAppSaw checks that the app received the test's request unchanged.
func wantAppSaw(t *testing.T, saw appSaw, body []byte) {
t.Helper()
if saw.method != http.MethodPatch || saw.target != rawPath+"?"+rawQuery {
t.Errorf("app saw %s %s, want %s %s", saw.method, saw.target,
http.MethodPatch, rawPath+"?"+rawQuery)
}
if !slices.Equal(saw.header.Values("X-Test"), []string{"one", "two"}) {
t.Errorf("app saw X-Test %q", saw.header.Values("X-Test"))
}
if saw.header.Get("User-Agent") != "test-agent" {
t.Errorf("app saw User-Agent %q", saw.header.Get("User-Agent"))
}
if !bytes.Equal(saw.body, body) {
t.Errorf("app saw a body of %d bytes, want the %d sent",
len(saw.body), len(body))
}
}
// wantAnswer checks that the client received the app's answer unchanged.
func wantAnswer(t *testing.T, got answer, body []byte) {
t.Helper()
wantStatus(t, got, http.StatusTeapot)
if got.header.Get("X-App") != "yes" {
t.Errorf("client got X-App %q", got.header.Get("X-App"))
}
if !slices.Equal(got.header.Values("Set-Cookie"), []string{"a=1", "b=2"}) {
t.Errorf("client got Set-Cookie %q", got.header.Values("Set-Cookie"))
}
if got.err != nil || !bytes.Equal(got.body, body) {
t.Errorf("client got %d bytes (%v), want the %d the app sent",
len(got.body), got.err, len(body))
}
}
// wantRequestFields checks the log line's fields about the request. Its
// time, its id and its timings are checked only for being there.
func wantRequestFields(t *testing.T, line logLine, host string, sent, received int) {
t.Helper()
bytes := float64(sent + received)
want := withTimings(line, requestlog.Line{
Type: requestType, Time: line.Time, Instance: "app",
ClientIP: localhost, Method: http.MethodPatch, Scheme: plain, Host: host,
Path: rawPath, Query: rawQuery, Protocol: protocol,
Status: http.StatusTeapot, RequestBytes: int64(sent),
ResponseBytes: int64(received), UserAgent: "test-agent",
RequestID: line.RequestID, PeerIP: localhost, ClientGroup: localhost + "/32",
ContentLength: int64(sent), ResponseContentType: "text/plain; charset=utf-8",
UpstreamStatus: http.StatusTeapot, Action: requestlog.ActionForward,
Counts: ratelimit.Counts{
Minute: 1, Hour: 1, Day: 1,
MinuteBytes: bytes, HourBytes: bytes, DayBytes: bytes,
},
})
if !reflect.DeepEqual(line.Line, want) {
t.Errorf("log line\n%+v\nwant\n%+v", line.Line, want)
}
_, err := time.Parse(time.RFC3339, line.Time)
if err != nil || line.RequestID == "" || line.DurationTotal <= 0 ||
line.DurationUpstreamTotal == nil || *line.DurationUpstreamTotal <= 0 {
t.Errorf("log line has time %q, request_id %q and durations %v and %v",
line.Time, line.RequestID, line.DurationTotal,
line.fields["duration_upstream_total"])
}
}
func TestAddsNoContentTypeTheAppDidNotSend(t *testing.T) {
t.Parallel()
const typed = "text/plain"
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/typed" {
w.Header().Set("Content-Type", typed)
} else {
// The key with no value keeps Go's server from adding one.
w.Header()["Content-Type"] = nil
}
_, _ = io.WriteString(w, "<!doctype html><title>page</title>")
})
addr, _ := startProxy(t, app.URL, nil)
got := get(t, addr, "/")
if got.header.Values("Content-Type") != nil {
t.Errorf("client got Content-Type %q, want none",
got.header.Get("Content-Type"))
}
got = get(t, addr, "/typed")
if got.header.Get("Content-Type") != typed {
t.Errorf("client got Content-Type %q, want %q",
got.header.Get("Content-Type"), typed)
}
}
func TestStreamsTheRequestBody(t *testing.T) {
t.Parallel()
chunk := bytes.Repeat([]byte("x"), chunkSize)
firstArrived := make(chan struct{})
app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
first := make([]byte, len(chunk))
_, err := io.ReadFull(r.Body, first)
if err != nil {
return
}
close(firstArrived)
rest, _ := io.ReadAll(r.Body)
_, _ = w.Write(rest)
})
addr, _ := startProxy(t, app.URL, nil)
body, writer := io.Pipe()
go func() {
_, _ = writer.Write(chunk)
select {
case <-firstArrived:
_, _ = writer.Write(chunk)
_ = writer.Close()
case <-time.After(waitLimit):
_ = writer.CloseWithError(errNotStreamed)
}
}()
got := do(t, newRequest(t, http.MethodPost, addr, "/upload", body))
if got.err != nil || !bytes.Equal(got.body, chunk) {
t.Errorf("app read %d bytes after the first part (%v), want %d",
len(got.body), got.err, len(chunk))
}
}
func TestStreamsTheAnswerBody(t *testing.T) {
t.Parallel()
chunk := bytes.Repeat([]byte("y"), chunkSize)
firstArrived := make(chan struct{})
app := startApp(t, func(w http.ResponseWriter, _ *http.Request) {
_, _ = w.Write(chunk)
_ = http.NewResponseController(w).Flush()
select {
case <-firstArrived:
_, _ = w.Write(chunk)
case <-time.After(waitLimit):
}
})
addr, _ := startProxy(t, app.URL, nil)
req := newRequest(t, http.MethodGet, addr, "/download", http.NoBody)
res, err := newClient(t).Do(req)
if err != nil {
t.Fatalf("request: %v", err)
}
first := make([]byte, len(chunk))
_, err = io.ReadFull(res.Body, first)
close(firstArrived)
got := readAnswer(res)
if err != nil || got.err != nil || !bytes.Equal(got.body, chunk) {
t.Errorf("client read %d bytes after the first part (%v, %v), want %d",
len(got.body), err, got.err, len(chunk))
}
}
func TestUpgradedConnectionOutlastsTheTimeouts(t *testing.T) {
t.Parallel()
app := startApp(t, echoAfterUpgrade)
addr, out := startProxy(t, app.URL, map[string]string{
clientRequestTimeout: shortTimeoutSetting,
clientResponseTimeout: shortTimeoutSetting,
upstreamRequestTimeout: shortTimeoutSetting,
upstreamResponseTimeout: shortTimeoutSetting,
})
conn := dial(t, addr)
send(t, conn, "GET /socket HTTP/1.1\r\nHost: app\r\n"+
"Connection: Upgrade\r\nUpgrade: websocket\r\n\r\n")
reader := bufio.NewReader(conn)
res, err := http.ReadResponse(reader, nil)
if err != nil {
t.Fatalf("read the answer to the upgrade: %v", err)
}
answered := time.Now()
_ = res.Body.Close()
if res.StatusCode != http.StatusSwitchingProtocols {
t.Fatalf("status %d, want %d", res.StatusCode, http.StatusSwitchingProtocols)
}
// Every timeout started before the upgrade was answered, the response
// timeouts last, at the end of the request: wait until just past
// shortTimeout after the answer was read, then use the connection.
time.Sleep(time.Until(answered.Add(shortTimeout + 100*time.Millisecond)))
send(t, conn, "still here\n")
echoed, err := reader.ReadString('\n')
if err != nil || echoed != "still here\n" {
t.Errorf("echo %q (%v), want %q", echoed, err, "still here\n")
}
_ = conn.Close()
wantLine(t, out.requestLine(t), http.StatusSwitchingProtocols,
requestlog.ActionForward)
}
// echoAfterUpgrade is an app that switches protocols on request, and then
// sends back each line it receives.
func echoAfterUpgrade(w http.ResponseWriter, r *http.Request) {
if r.Header.Get("Upgrade") != "websocket" {
http.Error(w, "not an upgrade", http.StatusBadRequest)
return
}
conn, buffered, err := http.NewResponseController(w).Hijack()
if err != nil {
return
}
defer func() {
_ = conn.Close()
}()
_, _ = buffered.WriteString("HTTP/1.1 101 Switching Protocols\r\n" +
"Connection: Upgrade\r\nUpgrade: websocket\r\n\r\n")
_ = buffered.Flush()
for {
line, err := buffered.ReadString('\n')
if err != nil {
return
}
_, _ = buffered.WriteString(line)
_ = buffered.Flush()
}
}
func TestAnswers502WhenTheAppSwitchesToAnotherProtocol(t *testing.T) {
t.Parallel()
// answerAfterUpgrade switches to websocket whatever the client asked
// for, and ReverseProxy passes on a switch only to the protocol the
// client asked for, here "websocket, foo".
app := startApp(t, answerAfterUpgrade)
addr, out := startProxy(t, app.URL, nil)
conn := dial(t, addr)
send(t, conn, "GET /ws HTTP/1.1\r\nHost: app\r\n"+
"Connection: Upgrade\r\nUpgrade: websocket, foo\r\n\r\n")
wantStatus(t, readResponse(t, conn), http.StatusBadGateway)
wantLine(t, out.requestLine(t), http.StatusBadGateway, requestlog.ActionUpstreamError)
}
func TestServerHasTheDefaultLimits(t *testing.T) {
t.Parallel()
cfg, err := config.FromEnvironment(func(string) (string, bool) { return "", false })
if err != nil {
t.Fatalf("default settings: %v", err)
}
server := proxy.New(proxy.Params{
Config: cfg,
RequestLog: io.Discard,
ProcessLog: requestlog.NewProcessLogger(io.Discard, cfg.InstanceName, cfg.LogLevel),
})
if server.Addr != ":8080" || server.MaxHeaderBytes != 28<<10 ||
server.IdleTimeout != 2*time.Minute || server.ReadHeaderTimeout != time.Minute {
t.Errorf("server listens on %q with header limit %d, idle time %s and "+
"header timeout %s", server.Addr, server.MaxHeaderBytes,
server.IdleTimeout, server.ReadHeaderTimeout)
}
}
func TestRefusesHeadersOverTheLimit(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
name string
env map[string]string
limit int
}{
{"by default", nil, 32 << 10},
{"as set", map[string]string{clientHeaderMaxBytes: "8K"}, 8 << 10},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
var calls atomic.Int32
app := startApp(t, func(http.ResponseWriter, *http.Request) {
calls.Add(1)
})
addr, _ := startProxy(t, app.URL, tc.env)
// size counts every byte of the request: the request line,
// the headers and the blank line that ends them.
const (
start = "GET / HTTP/1.1\r\nHost: app\r\nX-Large: "
end = "\r\n\r\n"
)
for _, sent := range []struct{ size, want int }{
{tc.limit, http.StatusOK},
{tc.limit + 1, http.StatusRequestHeaderFieldsTooLarge},
} {
conn := dial(t, addr)
send(t, conn,
start+strings.Repeat("a", sent.size-len(start)-len(end))+end)
wantStatus(t, readResponse(t, conn), sent.want)
}
if calls.Load() != 1 {
t.Errorf("the app was called %d times, want once", calls.Load())
}
})
}
}
func TestAnswers502WhenTheAppCannotBeReached(t *testing.T) {
t.Parallel()
// No test can listen on port 1: listening on port 0 gets one from 32768 up.
addr, out := startProxy(t, "http://"+localhost+":1", nil)
wantStatus(t, get(t, addr, "/"), http.StatusBadGateway)
line := out.requestLine(t)
wantLine(t, line, http.StatusBadGateway, requestlog.ActionUpstreamError)
// There never was a connection to the app, nor an answer from it.
wantTimings(t, line, "duration_total", "duration_checks",
"duration_upstream_total")
logged := slices.ContainsFunc(out.lines(t), func(line map[string]any) bool {
return line["type"] == "process" && line["msg"] == "request to the app failed"
})
if !logged {
t.Errorf("no process line says the request to the app failed")
}
}
func TestLogLevelHoldsBackNoRequestLine(t *testing.T) {
t.Parallel()
// At error the warning that the request to the app failed is held back,
// and is written before the answer is.
addr, out := startProxy(t, "http://"+localhost+":1", map[string]string{
"SWWAF_LOG_LEVEL": "error",
})
wantStatus(t, get(t, addr, "/"), http.StatusBadGateway)
wantLine(t, out.requestLine(t), http.StatusBadGateway, requestlog.ActionUpstreamError)
for _, line := range out.lines(t) {
if line["type"] == "process" {
t.Errorf("process line %v, want none at error", line)
}
}
}
func TestLogsAnAnswerThatBrokeOff(t *testing.T) {
t.Parallel()
app := startApp(t, func(w http.ResponseWriter, _ *http.Request) {
_, _ = io.WriteString(w, "the first part")
_ = http.NewResponseController(w).Flush()
panic(http.ErrAbortHandler) // drops the connection mid-answer
})
addr, out := startProxy(t, app.URL, nil)
got := get(t, addr, "/")
if string(got.body) != "the first part" || !errors.Is(got.err, io.ErrUnexpectedEOF) {
t.Errorf("client read %q (%v), want the first part cut off", got.body, got.err)
}
wantLine(t, out.requestLine(t), http.StatusOK, requestlog.ActionUpstreamError)
}
func TestLogsAClientThatWentAway(t *testing.T) {
t.Parallel()
arrived := make(chan struct{})
app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
close(arrived)
<-r.Context().Done()
})
addr, out := startProxy(t, app.URL, nil)
conn := dial(t, addr)
send(t, conn, "GET /slow HTTP/1.1\r\nHost: app\r\n\r\n")
select {
case <-arrived:
case <-time.After(waitLimit):
t.Fatal("the request never reached the app")
}
_ = conn.Close()
line := out.requestLine(t)
if !line.Aborted || line.Status != 0 || line.Action != requestlog.ActionForward {
t.Errorf("log line has aborted %v, status %d and action %q, "+
"want true, 0 and %q",
line.Aborted, line.Status, line.Action, requestlog.ActionForward)
}
}
+341
View File
@@ -0,0 +1,341 @@
// Package proxy passes each request to the app and the app's answer back,
// unchanged, within the size and time limits, and writes one request log
// line for each request.
package proxy
import (
"io"
"log"
"log/slog"
"net/http"
"strings"
"time"
"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/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"
"sneak.berlin/go/smallwebwaf/internal/waf"
)
// How smallwebwaf keeps connections to the app open between requests.
const (
appIdleConns = 100
appIdleConnTimeout = 90 * time.Second
)
// adminPrefix starts the path of every request for smallwebwaf itself,
// which never reaches the app.
const adminPrefix = "/_smallwebwaf/"
// HealthPath is smallwebwaf's health endpoint, which the container's
// health check asks.
const HealthPath = "/_smallwebwaf/healthz"
// MetricsPath is where the metrics are, for a request that carries
// SWWAF_METRICS_TOKEN.
const MetricsPath = "/_smallwebwaf/metrics"
// BansPath is where an admin lists and adds bans, and, followed by / and
// a client's address, lifts them, with SWWAF_ADMIN_TOKEN.
const BansPath = "/_smallwebwaf/bans"
// ClientsPath is where an admin asks what smallwebwaf knows of a client,
// by the client's address after it, with SWWAF_ADMIN_TOKEN.
const ClientsPath = "/_smallwebwaf/clients/"
// Params are what New needs.
type Params struct {
Config *config.Config
// RequestLog receives one JSON line per request.
RequestLog io.Writer
// ProcessLog receives the process's own messages.
ProcessLog *slog.Logger
// GeoJSURL is where clients' AS numbers and countries are looked up
// while SWWAF_LOOKUP_SOURCE is geojs, normally lookup.URL.
GeoJSURL string
// AbuseIPDBURL is where clients are checked with AbuseIPDB while
// SWWAF_ABUSEIPDB_KEY is set, normally reputation.AbuseIPDBURL.
AbuseIPDBURL string
// LookupFile is the lookup database they are looked up in while
// SWWAF_LOOKUP_SOURCE is file, and nil otherwise.
LookupFile *lookup.File
// Now tells the time by which requests are counted for the rate
// limits, bans are made and run out, and GeoJS's answers are kept,
// normally time.Now in UTC, the time the state files give.
Now func() time.Time
// Rules are the rule files' rules, which each request is checked
// against.
Rules *rules.Files
// Alerts receive the alert for each ban the proxy makes or makes
// permanent, for each count over an anomaly threshold, for each request
// whose client a blocklist, the CrowdSec decision list, a DNSBL zone or
// AbuseIPDB lists, for each request the Core Rule Set scores at or over
// SWWAF_WAF_ANOMALY_THRESHOLD, and for GeoJS failing, a fetch of a list
// failing, a query to a DNSBL zone or a check with AbuseIPDB failing,
// or the day's AbuseIPDB checks used up.
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, the lists fetched from URLs, which its Run
// fetches, the DNSBL zones' verdicts, AbuseIPDB's scores and checks
// spent, and the metrics.
type Server struct {
*http.Server
Ledger *bans.Ledger
Limiter *ratelimit.Limiter
GeoJS *lookup.GeoJS
Anomalies *anomaly.Counters
LookupFile *lookup.File
Lists *reputation.Lists
DNSBL *reputation.DNSBL
AbuseIPDB *reputation.AbuseIPDB
Metrics *metrics.Metrics
}
// New returns the server smallwebwaf runs: each request it reads passes
// through the proxy. Go's server itself refuses a request line and
// headers over SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES, with 431, closes a
// connection idle for SWWAF_CLIENT_IDLE_TIMEOUT, and applies
// SWWAF_CLIENT_REQUEST_TIMEOUT while the headers arrive; the proxy
// applies the timeouts and size limits from then on.
func New(params Params) *Server {
errorLog := slog.NewLogLogger(params.ProcessLog.Handler(), slog.LevelWarn)
m := metrics.New(params.Config.MetricsTopN, params.Config.InstanceName)
lists, dnsbl, abuseIPDB := newReputation(params, m)
h := &handler{
config: params.Config,
requestLog: params.RequestLog,
processLog: params.ProcessLog,
errorLog: errorLog,
transport: newTransport(),
now: params.Now,
metrics: m,
limiter: ratelimit.New(ratelimit.Limits{
PerMinute: params.Config.RateLimitPerMinute,
PerHour: params.Config.RateLimitPerHour,
PerDay: params.Config.RateLimitPerDay,
BytesPerMinute: params.Config.BytesLimitPerMinute,
BytesPerHour: params.Config.BytesLimitPerHour,
BytesPerDay: params.Config.BytesLimitPerDay,
}, params.Config.MaxTrackedClients),
ledger: bans.New(bans.Rules{
LimitBanDuration: params.Config.LimitBanDuration,
LimitBanRepeatWindow: params.Config.LimitBanRepeatWindow,
MaxBanDuration: params.Config.MaxBanDuration,
AttackBanDuration: params.Config.AttackBanDuration,
MaxBans: params.Config.MaxBans,
}),
anomalies: anomaly.New(anomaly.Params{
Client: params.Config.AnomalyClient,
Net: params.Config.AnomalyNet,
ASN: params.Config.AnomalyASN,
Total: params.Config.AnomalyTotal,
Watch: params.Config.AnomalyWatch,
NetV4Prefix: params.Config.AnomalyNetV4Prefix,
NetV6Prefix: params.Config.AnomalyNetV6Prefix,
NamedNetblocks: params.Config.WatchNets,
Alerts: params.Alerts,
}),
lookupFile: params.LookupFile,
lists: lists,
dnsbl: dnsbl,
abuseIPDB: abuseIPDB,
rules: params.Rules,
coreRuleSet: newCoreRuleSet(params.Config),
alerts: params.Alerts,
}
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),
Answered: h.addLookup,
Now: params.Now,
ProcessLog: params.ProcessLog,
Metrics: m,
Alerts: params.Alerts,
})
m.AddBansAndClients(h.ledger, h.limiter, params.Now)
m.AddRules(params.Rules)
return &Server{
Server: &http.Server{
Addr: params.Config.ListenAddr,
Handler: h,
ReadHeaderTimeout: params.Config.ClientRequestTimeout,
// Off is an IdleTimeout of 0, which Go's server replaces with
// ReadTimeout: no limit, as long as ReadTimeout stays unset.
IdleTimeout: params.Config.ClientIdleTimeout,
// Go's server reads 4 KiB past MaxHeaderBytes before it
// refuses, so the limit a client meets is the setting.
MaxHeaderBytes: int(params.Config.ClientRequestHeaderMaxBytes - 4<<10),
ErrorLog: errorLog,
},
Ledger: h.ledger,
Limiter: h.limiter,
GeoJS: h.geojs,
Anomalies: h.anomalies,
LookupFile: h.lookupFile,
Lists: h.lists,
DNSBL: h.dnsbl,
AbuseIPDB: h.abuseIPDB,
Metrics: m,
}
}
// newReputation returns the lists fetched from URLs, the DNSBL zones'
// verdicts and AbuseIPDB's scores, as the settings in params name them,
// with none fetched, asked for or checked yet, and adds their metrics to
// m, AbuseIPDB's while SWWAF_ABUSEIPDB_KEY is set.
func newReputation(
params Params, m *metrics.Metrics,
) (*reputation.Lists, *reputation.DNSBL, *reputation.AbuseIPDB) {
cfg := params.Config
lists := reputation.New(reputation.Params{
BlocklistURLs: cfg.BlocklistURLs, Refresh: cfg.BlocklistRefresh,
ASNLimitPercentURL: cfg.ASNLimitPercentURL,
CrowdSecDecisionsURL: cfg.CrowdSecDecisionsURL, CrowdSecKey: cfg.CrowdSecKey,
Now: params.Now, ProcessLog: params.ProcessLog, Alerts: params.Alerts,
})
dnsbl := reputation.NewDNSBL(reputation.DNSBLParams{
Zones: cfg.DNSBLZones, Resolver: cfg.DNSBLResolver, CacheTTL: cfg.ReputationCacheTTL,
Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
Alerts: params.Alerts,
})
abuseIPDB := reputation.NewAbuseIPDB(reputation.AbuseIPDBParams{
URL: params.AbuseIPDBURL, Key: cfg.AbuseIPDBKey, MinScore: cfg.AbuseIPDBMinScore,
DailyBudget: cfg.AbuseIPDBDailyBudget, CacheTTL: cfg.ReputationCacheTTL,
Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
Alerts: params.Alerts,
})
m.AddReputation(lists, dnsbl)
if cfg.AbuseIPDBKey != "" {
m.AddAbuseIPDB(abuseIPDB)
}
return lists, dnsbl, abuseIPDB
}
// newCoreRuleSet returns the Core Rule Set at SWWAF_WAF_PARANOIA_LEVEL,
// without the rules SWWAF_WAF_DISABLED_RULES switches off, reading bodies
// up to SWWAF_WAF_BODY_LIMIT, or nil while SWWAF_WAF_MODE is off.
func newCoreRuleSet(cfg *config.Config) *waf.CoreRuleSet {
if cfg.WAFMode == config.WAFModeOff {
return nil
}
coreRuleSet, err := waf.New(waf.Params{
ParanoiaLevel: cfg.WAFParanoiaLevel, DisabledRules: cfg.WAFDisabledRules,
BodyLimit: cfg.WAFBodyLimit,
})
if err != nil {
// The Core Rule Set is built in, and the settings cannot break it:
// the paranoia level is from 1 to 4, the body limit at most 1G, and
// the id of no rule switches nothing off.
panic(err)
}
return coreRuleSet
}
// handler is the proxy. It holds what every request shares; what belongs
// to one request is in a request.
type handler struct {
config *config.Config
requestLog io.Writer
processLog *slog.Logger
errorLog *log.Logger
transport http.RoundTripper
now func() time.Time
metrics *metrics.Metrics
limiter *ratelimit.Limiter
ledger *bans.Ledger
geojs *lookup.GeoJS
anomalies *anomaly.Counters
lookupFile *lookup.File
lists *reputation.Lists
dnsbl *reputation.DNSBL
abuseIPDB *reputation.AbuseIPDB
rules *rules.Files
coreRuleSet *waf.CoreRuleSet
alerts *alerts.Queue
}
// newTransport returns what carries requests to the app. It never goes
// through a proxy named in the environment, and leaves the app's answers
// compressed or not as the app sent them.
func newTransport() *http.Transport {
return &http.Transport{
MaxIdleConns: appIdleConns,
MaxIdleConnsPerHost: appIdleConns,
IdleConnTimeout: appIdleConnTimeout,
DisableCompression: true,
}
}
// ServeHTTP handles one request: it works out the client, runs the
// checks, passes the request to the app and the answer back within the
// limits, or answers it itself if it is for smallwebwaf, and writes the
// request's log line.
func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
rq := h.newRequest(w, r)
defer rq.finish()
// The health endpoint is answered at once, before any check, so that
// a health checker is never refused. It does not ask the app.
if r.Method == http.MethodGet && r.URL.Path == HealthPath {
rq.line.Action = requestlog.ActionAdmin
// Set here rather than left to Go's server, which would set it only
// after the log line has taken the response's headers.
rq.out.Header().Set("Content-Type", "text/plain; charset=utf-8")
_, _ = io.WriteString(rq.out, "ok\n")
return
}
// Once the request has ended, before its log line is written. The
// last deferred runs first: countRefusal before addToHistory, so that
// a broken error burst is in the client's history.
defer rq.addToHistory()
defer rq.countAnomalies()
defer rq.countRefusal()
refused := rq.check(r.Context())
rq.checked = time.Now()
if refused != nil {
rq.answer(*refused)
return
}
// A request for smallwebwaf itself is answered where another would be
// passed to the app, so that it goes through every check first.
if strings.HasPrefix(r.URL.Path, adminPrefix) {
rq.answerAdmin()
return
}
// Once the response has ended, before the request is added to its
// client's history. Deferred, since ReverseProxy panics to end a
// response it cannot finish.
defer rq.countBytes()
rq.forward(r.Context())
}
@@ -1,11 +1,10 @@
package discriminator_test package proxy_test
import ( import (
"bufio" "bufio"
"bytes" "bytes"
"encoding/json" "encoding/json"
"io" "io"
"log/slog"
"maps" "maps"
"net" "net"
"net/http" "net/http"
@@ -17,88 +16,88 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/config" "sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/discriminator"
"sneak.berlin/go/smallwebwaf/internal/lookup" "sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/rproxy"
"sneak.berlin/go/smallwebwaf/internal/rules" "sneak.berlin/go/smallwebwaf/internal/rules"
) )
const ( const (
// shortTimeout is what a test sets a timeout to, to see it run out.
// It starts before the test has set up its case, such as an upgrade
// or the app's buffers filling, so it is as long as the hold-up of the
// test process that wantTimedOut allows: a shorter one can run out
// first on a busy host.
shortTimeout = waitLimit / 2
// longTimeoutSetting is a timeout that does not run out in a test.
longTimeoutSetting = "1m"
// waitLimit bounds how long a test waits for what should happen. // waitLimit bounds how long a test waits for what should happen.
waitLimit = 10 * time.Second waitLimit = 10 * time.Second
// pollInterval is how often a test looks for a log line. // pollInterval is how often a test looks for a log line.
pollInterval = 10 * time.Millisecond pollInterval = 10 * time.Millisecond
// localhost is where every test server listens, and so the address rproxy // localhost is where every test server listens, and so the address
// sees each test's requests come from. // smallwebwaf sees each test's requests come from.
localhost = "127.0.0.1" localhost = "127.0.0.1"
// requestType is the type that marks a request log line. // requestType is the type that marks a request log line.
requestType = "request" requestType = "request"
// protocol is the protocol of every question. // protocol is the protocol of every test's requests.
protocol = "HTTP/1.1" protocol = "HTTP/1.1"
// trustLocalhost trusts the address every test connects from, and a
// network for proxies in front of it.
trustLocalhost = localhost + "/32,10.0.0.0/8"
// appHost is the host every test asks for.
appHost = "app.example"
// client is the client's address, as a proxy names it.
client = "203.0.113.9"
// forwardedFor is the header that lists the client and its proxies,
// and forwardedProto the one that gives the scheme the client used.
forwardedFor = "X-Forwarded-For"
forwardedProto = "X-Forwarded-Proto"
// secure is the scheme a client reached traefik with, and plain the one
// rproxy serves.
secure = "https"
plain = "http"
) )
// shortTimeoutSetting is shortTimeout as a setting's value.
//
//nolint:gochecknoglobals // a constant cannot call String
var shortTimeoutSetting = shortTimeout.String()
// The settings the tests set. // The settings the tests set.
const ( const (
mode = "SWW_MODE" clientRequestTimeout = "SWWAF_CLIENT_REQUEST_TIMEOUT"
trustedProxies = "SWRP_TRUSTED_PROXIES" clientHeaderMaxBytes = "SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES"
ipv6GroupPrefix = "SWW_IPV6_GROUP_PREFIX" clientIdleTimeout = "SWWAF_CLIENT_IDLE_TIMEOUT"
maxTrackedClients = "SWW_MAX_TRACKED_CLIENTS" clientResponseTimeout = "SWWAF_CLIENT_RESPONSE_TIMEOUT"
allowNets = "SWW_ALLOW_NETS" upstreamRequestTimeout = "SWWAF_UPSTREAM_REQUEST_TIMEOUT"
rateLimitExemptNets = "SWW_RATE_LIMIT_EXEMPT_NETS" upstreamResponseTimeout = "SWWAF_UPSTREAM_RESPONSE_TIMEOUT"
denyNets = "SWW_DENY_NETS" mode = "SWWAF_MODE"
rateLimitPerMinute = "SWW_RATE_LIMIT_PER_MINUTE" requestMaxBytes = "SWWAF_REQUEST_MAX_BYTES"
rateLimitPerDay = "SWW_RATE_LIMIT_PER_DAY" responseMaxBytes = "SWWAF_RESPONSE_MAX_BYTES"
rateLimitExemptPaths = "SWW_RATE_LIMIT_EXEMPT_PATHS" trustedProxies = "SWWAF_TRUSTED_PROXIES"
lookupSource = "SWW_LOOKUP_SOURCE" ipv6GroupPrefix = "SWWAF_IPV6_GROUP_PREFIX"
lookupDBPath = "SWW_LOOKUP_DB_PATH" maxTrackedClients = "SWWAF_MAX_TRACKED_CLIENTS"
lookupTimeout = "SWW_LOOKUP_TIMEOUT" allowNets = "SWWAF_ALLOW_NETS"
addLookupHeaders = "SWW_ADD_LOOKUP_HEADERS" rateLimitExemptNets = "SWWAF_RATE_LIMIT_EXEMPT_NETS"
tagDeny = "SWW_TAG_DENY" denyNets = "SWWAF_DENY_NETS"
// denyKP is the value of SWW_TAG_DENY that refuses fromKP's country. rateLimitPerMinute = "SWWAF_RATE_LIMIT_PER_MINUTE"
denyKP = "country=KP" rateLimitPerDay = "SWWAF_RATE_LIMIT_PER_DAY"
allowedCountries = "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES" rateLimitExemptPaths = "SWWAF_RATE_LIMIT_EXEMPT_PATHS"
banResponse = "SWW_BAN_RESPONSE" lookupSource = "SWWAF_LOOKUP_SOURCE"
limitBanDuration = "SWW_LIMIT_BAN_DURATION" lookupDBPath = "SWWAF_LOOKUP_DB_PATH"
limitBanRepeatWindow = "SWW_LIMIT_BAN_REPEAT_WINDOW" lookupTimeout = "SWWAF_LOOKUP_TIMEOUT"
maxBanDuration = "SWW_MAX_BAN_DURATION" addLookupHeaders = "SWWAF_ADD_LOOKUP_HEADERS"
maxBans = "SWW_MAX_BANS" deniedCountries = "SWWAF_DENIED_COUNTRIES"
banScopeV4Prefix = "SWW_BAN_SCOPE_V4_PREFIX" allowedCountries = "SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES"
instanceName = "SWW_INSTANCE_NAME" banResponse = "SWWAF_BAN_RESPONSE"
logRequestHeaders = "SWW_LOG_REQUEST_HEADERS" limitBanDuration = "SWWAF_LIMIT_BAN_DURATION"
attackBanDuration = "SWW_ATTACK_BAN_DURATION" limitBanRepeatWindow = "SWWAF_LIMIT_BAN_REPEAT_WINDOW"
rulesDir = "SWW_RULES_DIR" maxBanDuration = "SWWAF_MAX_BAN_DURATION"
wafMode = "SWW_WAF_MODE" maxBans = "SWWAF_MAX_BANS"
banScopeV4Prefix = "SWWAF_BAN_SCOPE_V4_PREFIX"
instanceName = "SWWAF_INSTANCE_NAME"
logRequestHeaders = "SWWAF_LOG_REQUEST_HEADERS"
attackBanDuration = "SWWAF_ATTACK_BAN_DURATION"
rulesDir = "SWWAF_RULES_DIR"
wafMode = "SWWAF_WAF_MODE"
) )
// off is the value that switches a setting off. // off is the value that switches a setting off.
const off = "off" const off = "off"
// on is the value that switches a setting that takes true or false on. // output collects what smallwebwaf writes on stdout.
const on = "true"
// output collects what sww writes on stdout.
type output struct { type output struct {
mu sync.Mutex mu sync.Mutex
buf bytes.Buffer buf bytes.Buffer
} }
// Write adds lines sww writes. // Write adds lines smallwebwaf writes.
func (o *output) Write(p []byte) (int, error) { func (o *output) Write(p []byte) (int, error) {
o.mu.Lock() o.mu.Lock()
defer o.mu.Unlock() defer o.mu.Unlock()
@@ -177,73 +176,6 @@ func (o *output) requestLine(t *testing.T) logLine {
return o.requestLines(t, 1)[0] return o.requestLines(t, 1)[0]
} }
// endedLines waits for count requests that went through rproxy, or to discriminator's
// own endpoints, to have ended, and returns the last log line of each, in the
// order discriminator took them. A question's last line is the one its report writes.
func (o *output) endedLines(t *testing.T, count int) []logLine {
t.Helper()
deadline := time.Now().Add(waitLimit)
for time.Now().Before(deadline) {
found := o.lastLines(t)
ended := len(found) >= count
for _, line := range found[:min(count, len(found))] {
if line.DiscriminatorLine == requestlog.DiscriminatorLineDecision {
ended = false
}
}
if ended {
return found
}
time.Sleep(pollInterval)
}
t.Fatalf("fewer than %d requests have ended after %s", count, waitLimit)
return nil
}
// lastLines returns the last request log line written so far of each request,
// in the order discriminator took them.
func (o *output) lastLines(t *testing.T) []logLine {
t.Helper()
var found []logLine
places := map[string]int{}
for _, fields := range o.lines(t) {
if fields["type"] != requestType {
continue
}
line := decodeLine(t, fields)
place, seen := places[line.RequestID]
if seen {
found[place] = line
continue
}
places[line.RequestID] = len(found)
found = append(found, line)
}
return found
}
// endedLine waits for a test's one request to have ended, and returns its last
// log line.
func (o *output) endedLine(t *testing.T) logLine {
t.Helper()
return o.endedLines(t, 1)[0]
}
// decodeLine reads a request log line's fields into a logLine. // decodeLine reads a request log line's fields into a logLine.
func decodeLine(t *testing.T, fields map[string]any) logLine { func decodeLine(t *testing.T, fields map[string]any) logLine {
t.Helper() t.Helper()
@@ -263,7 +195,7 @@ func decodeLine(t *testing.T, fields map[string]any) logLine {
return line return line
} }
// startApp starts app as the app rproxy passes requests to. // startApp starts app as the app smallwebwaf passes requests to.
func startApp(t *testing.T, app http.HandlerFunc) *httptest.Server { func startApp(t *testing.T, app http.HandlerFunc) *httptest.Server {
t.Helper() t.Helper()
@@ -273,9 +205,9 @@ func startApp(t *testing.T, app http.HandlerFunc) *httptest.Server {
return server return server
} }
// startProxy starts discriminator, and rproxy in front of the app at appURL, each with // startProxy starts smallwebwaf in front of the app at appURL, with the
// the settings in env on top of the defaults, and returns where rproxy listens // settings in env on top of the defaults, and returns where it listens and
// and what discriminator writes. // what it writes.
func startProxy(t *testing.T, appURL string, env map[string]string) (string, *output) { func startProxy(t *testing.T, appURL string, env map[string]string) (string, *output) {
t.Helper() t.Helper()
@@ -295,14 +227,14 @@ func startProxyWithGeoJS(
} }
// startProxyWithClock is startProxyWithGeoJS with requests counted and // startProxyWithClock is startProxyWithGeoJS with requests counted and
// bans made by the time now tells, and returns discriminator's server as well, whose // bans made by the time now tells, and returns the server as well. Unless
// Addr is where discriminator listens. Unless env sets SWW_RULES_DIR, it is an empty // env sets SWWAF_RULES_DIR, it is an empty directory, of no rules, and
// directory, of no rules, and unless it sets SWW_INSTANCE_NAME, that is app, // unless it sets SWWAF_INSTANCE_NAME, that is app, the label instance of
// the label instance of every metric. // every metric.
func startProxyWithClock( func startProxyWithClock(
t *testing.T, appURL, geojsURL string, now func() time.Time, t *testing.T, appURL, geojsURL string, now func() time.Time,
env map[string]string, env map[string]string,
) (string, *output, *discriminator.Server) { ) (string, *output, *proxy.Server) {
t.Helper() t.Helper()
addr, out, server, _ := startProxyWithAlerts(t, appURL, geojsURL, now, env) addr, out, server, _ := startProxyWithAlerts(t, appURL, geojsURL, now, env)
@@ -311,70 +243,14 @@ func startProxyWithClock(
} }
// startProxyWithAlerts is startProxyWithClock, and returns the queue of // startProxyWithAlerts is startProxyWithClock, and returns the queue of
// the alerts discriminator raises as well, as newDiscriminator makes them. // the alerts the proxy raises as well, as newProxy makes them.
func startProxyWithAlerts( func startProxyWithAlerts(
t *testing.T, appURL, geojsURL string, now func() time.Time, t *testing.T, appURL, geojsURL string, now func() time.Time,
env map[string]string, env map[string]string,
) (string, *output, *discriminator.Server, *alerts.Queue) { ) (string, *output, *proxy.Server, *alerts.Queue) {
t.Helper() t.Helper()
server, out, alertQueue := newDiscriminator(t, geojsURL, now, env) server, out, alertQueue := newProxy(t, appURL, geojsURL, now, env)
serve(t, server)
return startRProxy(t, server.Addr, appURL, env), out, server, alertQueue
}
// serve serves server on a port of its own until the test ends, and sets its
// Addr to where it listens.
func serve(t *testing.T, server *discriminator.Server) {
t.Helper()
listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
if err != nil {
t.Fatalf("listen: %v", err)
}
server.Addr = listener.Addr().String()
go func() {
_ = server.Serve(listener)
}()
t.Cleanup(func() {
_ = server.Close()
})
}
// startRProxy starts rproxy in front of the app at appURL, asking the discriminator
// at discriminatorAddr, with the settings in env on top of the defaults, and returns
// where it listens. What it writes is dropped. SWRP_TIMEOUT_MS is a minute unless
// env sets it, so that on a busy host SWRP_DEFAULT_DISPOSITION does not decide.
func startRProxy(
t *testing.T, discriminatorAddr, appURL string, env map[string]string,
) string {
t.Helper()
settings := map[string]string{
"SWRP_WAF_BACKEND": "http://" + discriminatorAddr,
"SWRP_UPSTREAM_URL": appURL,
"SWRP_TIMEOUT_MS": "60000",
}
maps.Copy(settings, env)
cfg, err := config.RProxyFromEnvironment(func(name string) (string, bool) {
value, ok := settings[name]
return value, ok
})
if err != nil {
t.Fatalf("settings %v: %v", settings, err)
}
server := rproxy.New(rproxy.Params{
Config: cfg,
RequestLog: io.Discard,
ProcessLog: requestlog.NewProcessLogger(io.Discard, "rproxy", slog.LevelInfo),
})
listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0") listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
if err != nil { if err != nil {
@@ -389,36 +265,28 @@ func startRProxy(
_ = server.Close() _ = server.Close()
}) })
return listener.Addr().String() return listener.Addr().String(), out, server, alertQueue
} }
// newDiscriminator makes discriminator's server, without starting it, and // newProxy makes the server startProxyWithClock starts, without starting
// returns it, what it writes, and the queue of the alerts it raises, as the // it, and returns it, what it writes, and the queue of the alerts the
// settings in env make it. No alert is sent from the queue: they wait in it, // proxy raises, as the settings in env make it. No alert is sent from the
// for the test to look at. // queue: they wait in it, for the test to look at. With no geojsURL, there
// With no geojsURL, there is no stand-in for GeoJS to look clients up at, and // is no stand-in for GeoJS to look clients up at, and SWWAF_LOOKUP_SOURCE
// SWW_LOOKUP_SOURCE is off unless env sets it. While it is file, the lookup // is off unless env sets it. While it is file, the lookup database
// database SWW_LOOKUP_DB_PATH names is read. Clients are checked with AbuseIPDB // SWWAF_LOOKUP_DB_PATH names is read. Clients are checked with AbuseIPDB
// at abuseIPDBURL while env sets SWW_ABUSEIPDB_KEY. SWW_WAF_MODE is off unless // at abuseIPDBURL while env sets SWWAF_ABUSEIPDB_KEY. SWWAF_WAF_MODE is off
// env sets it, so that only the tests of the Core Rule Set have their requests // unless env sets it, so that only the tests of the Core Rule Set have
// inspected by it. // their requests inspected by it.
func newDiscriminator( func newProxy(
t *testing.T, geojsURL string, now func() time.Time, env map[string]string, t *testing.T, appURL, geojsURL string, now func() time.Time,
) (*discriminator.Server, *output, *alerts.Queue) { env map[string]string,
t.Helper() ) (*proxy.Server, *output, *alerts.Queue) {
return newDiscriminatorWith(t, discriminator.New, geojsURL, now, env)
}
// newDiscriminatorWith is newDiscriminator for the server build makes.
func newDiscriminatorWith(
t *testing.T, build func(discriminator.Params) *discriminator.Server,
geojsURL string, now func() time.Time, env map[string]string,
) (*discriminator.Server, *output, *alerts.Queue) {
t.Helper() t.Helper()
settings := map[string]string{ settings := map[string]string{
rulesDir: t.TempDir(), instanceName: "app", wafMode: off, "SWWAF_UPSTREAM_URL": appURL, rulesDir: t.TempDir(), instanceName: "app",
wafMode: off,
} }
if geojsURL == "" { if geojsURL == "" {
settings[lookupSource] = off settings[lookupSource] = off
@@ -466,19 +334,13 @@ func newDiscriminatorWith(
} }
} }
coreRuleSet, err := discriminator.NewCoreRuleSet(cfg) server := proxy.New(proxy.Params{
if err != nil {
t.Fatalf("Core Rule Set: %v", err)
}
server := build(discriminator.Params{
Config: cfg, Config: cfg,
RequestLog: out, RequestLog: out,
ProcessLog: processLog, ProcessLog: processLog,
GeoJSURL: geojsURL, GeoJSURL: geojsURL,
AbuseIPDBURL: abuseIPDBURL, AbuseIPDBURL: abuseIPDBURL,
LookupFile: lookupFile, LookupFile: lookupFile,
CoreRuleSet: coreRuleSet,
Now: now, Now: now,
Rules: ruleFiles, Rules: ruleFiles,
Alerts: alertQueue, Alerts: alertQueue,
@@ -516,7 +378,7 @@ func readAnswer(res *http.Response) answer {
return answer{status: res.StatusCode, header: res.Header, body: body, err: err} return answer{status: res.StatusCode, header: res.Header, body: body, err: err}
} }
// newRequest makes a request for path to addr, where rproxy or discriminator listens. // newRequest makes a request for path to smallwebwaf at addr.
func newRequest(t *testing.T, method, addr, path string, body io.Reader) *http.Request { func newRequest(t *testing.T, method, addr, path string, body io.Reader) *http.Request {
t.Helper() t.Helper()
@@ -540,15 +402,15 @@ func do(t *testing.T, req *http.Request) answer {
return readAnswer(res) return readAnswer(res)
} }
// get sends a GET request for path to addr. // get sends a GET request for path to smallwebwaf at addr.
func get(t *testing.T, addr, path string) answer { func get(t *testing.T, addr, path string) answer {
t.Helper() t.Helper()
return do(t, newRequest(t, http.MethodGet, addr, path, http.NoBody)) return do(t, newRequest(t, http.MethodGet, addr, path, http.NoBody))
} }
// dial opens a connection to addr, for requests the HTTP client cannot make, // dial opens a connection to smallwebwaf at addr, for requests the HTTP
// such as one that stops sending halfway. // client cannot make, such as one that stops sending halfway.
func dial(t *testing.T, addr string) net.Conn { func dial(t *testing.T, addr string) net.Conn {
t.Helper() t.Helper()
@@ -609,3 +471,14 @@ func wantStatus(t *testing.T, got answer, status int) {
t.Errorf("status %d, want %d", got.status, status) t.Errorf("status %d, want %d", got.status, status)
} }
} }
// wantTimedOut checks that what began at start ended once shortTimeout
// had run out, and not much later.
func wantTimedOut(t *testing.T, start time.Time) {
t.Helper()
took := time.Since(start)
if took < shortTimeout || took > shortTimeout+waitLimit/2 {
t.Errorf("took %s, want %s", took, shortTimeout)
}
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"net/http" "net/http"
@@ -10,7 +10,7 @@ import (
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
// minute is the window of SWW_RATE_LIMIT_PER_MINUTE, as a log line's // minute is the window of SWWAF_RATE_LIMIT_PER_MINUTE, as a log line's
// limit_hit names it. // limit_hit names it.
const minute = "minute" const minute = "minute"
@@ -51,7 +51,7 @@ func TestRateLimitRefusesBeforeTheApp(t *testing.T) {
req.Header.Set(forwardedFor, sent.client) req.Header.Set(forwardedFor, sent.client)
wantStatus(t, do(t, req), sent.want) wantStatus(t, do(t, req), sent.want)
line := out.endedLines(t, i+1)[i] line := out.requestLines(t, i+1)[i]
if line.ClientIP != sent.logged { if line.ClientIP != sent.logged {
t.Errorf("log line has client_ip %q, want %q", line.ClientIP, sent.logged) t.Errorf("log line has client_ip %q, want %q", line.ClientIP, sent.logged)
} }
@@ -59,7 +59,7 @@ func TestRateLimitRefusesBeforeTheApp(t *testing.T) {
if sent.want == http.StatusOK { if sent.want == http.StatusOK {
wantLine(t, line, http.StatusOK, requestlog.ActionForward) wantLine(t, line, http.StatusOK, requestlog.ActionForward)
} else { } else {
wantLine(t, line, http.StatusForbidden, requestlog.ActionClientIsRateLimited) wantLine(t, line, http.StatusForbidden, requestlog.ActionRateLimited)
if line.LimitHit != minute { if line.LimitHit != minute {
t.Errorf("log line has limit_hit %q, want minute", line.LimitHit) t.Errorf("log line has limit_hit %q, want minute", line.LimitHit)
@@ -72,21 +72,10 @@ func TestRateLimitRefusesBeforeTheApp(t *testing.T) {
} }
} }
func TestRateLimitRefusalNamesItsHeuristicWindowCountAndLimit(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{rateLimitPerMinute: "1"})
s.get(client, http.StatusOK, requestlog.ActionForward)
line := s.get(client, http.StatusForbidden, requestlog.ActionClientIsRateLimited)
wantHeuristic(t, line, "rate_limits", `{"window": "minute", "count": 2, "limit": 1}`)
}
func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) { func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) {
t.Parallel() t.Parallel()
// With SWW_IPV6_GROUP_PREFIX at 48, the first two addresses, in two // With SWWAF_IPV6_GROUP_PREFIX at 48, the first two addresses, in two
// /64s of one /48, are one client, and the second's request breaks the // /64s of one /48, are one client, and the second's request breaks the
// limit; the third, in the next /48, is another client. // limit; the third, in the next /48, is another client.
const ( const (
@@ -102,7 +91,7 @@ func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) {
status int status int
action string action string
}{ }{
{rateLimitPerMinute, "1", http.StatusForbidden, requestlog.ActionClientIsRateLimited}, {rateLimitPerMinute, "1", http.StatusForbidden, requestlog.ActionRateLimited},
{bytesLimitPerMinute, byteLimit, http.StatusOK, requestlog.ActionForward}, {bytesLimitPerMinute, byteLimit, http.StatusOK, requestlog.ActionForward},
} { } {
t.Run(tc.setting, func(t *testing.T) { t.Run(tc.setting, func(t *testing.T) {
@@ -129,14 +118,14 @@ func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) {
func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) { func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
t.Parallel() t.Parallel()
const denied = "192.0.2.50" // in SWW_DENY_NETS const denied = "192.0.2.50" // in SWWAF_DENY_NETS
geojsURL, _ := startGeoJS(t) geojsURL, _ := startGeoJS(t)
s, _, server := startWithClock(t, geojsURL, map[string]string{ s, _, server := startWithClock(t, geojsURL, map[string]string{
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
rateLimitExemptPaths: "/assets/,/favicon.ico", rateLimitExemptPaths: "/assets/,/favicon.ico",
denyNets: denied, denyNets: denied,
tagDeny: denyKP, deniedCountries: "kp",
}) })
// The answers are kept before the requests, so that none waits for // The answers are kept before the requests, so that none waits for
@@ -160,17 +149,14 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
// A path outside every prefix is counted: /assets is not under // A path outside every prefix is counted: /assets is not under
// /assets/, and breaks the limit. // /assets/, and breaks the limit.
s.request(client, "/assets", http.StatusForbidden, s.request(client, "/assets", http.StatusForbidden, requestlog.ActionRateLimited)
requestlog.ActionClientIsRateLimited)
// A ban, SWW_DENY_NETS and SWW_TAG_DENY still refuse a path under a // A ban, SWWAF_DENY_NETS and the country lists still refuse a path
// prefix. // under a prefix.
s.request(client, "/assets/app.js", http.StatusForbidden, s.request(client, "/assets/app.js", http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionTemporarilyBanned) s.request(denied, "/assets/app.js", http.StatusForbidden, requestlog.ActionDenied)
s.request(denied, "/assets/app.js", http.StatusForbidden,
requestlog.ActionClientDenied)
s.request(fromKP, "/assets/app.js", s.request(fromKP, "/assets/app.js",
http.StatusForbidden, requestlog.ActionClientDenied) http.StatusForbidden, requestlog.ActionCountryDenied)
} }
func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) { func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {
@@ -214,7 +200,7 @@ func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {
// Counted, the second request breaks the limit of one request // Counted, the second request breaks the limit of one request
// a minute. // a minute.
s.request(client, sent, http.StatusOK, requestlog.ActionForward) s.request(client, sent, http.StatusOK, requestlog.ActionForward)
s.request(client, sent, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.request(client, sent, http.StatusForbidden, requestlog.ActionRateLimited)
}) })
} }
} }
+121
View File
@@ -0,0 +1,121 @@
package proxy
import (
"context"
"time"
"sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/reputation"
)
// deny is the SWWAF_BLOCKLIST_ACTION and the SWWAF_REPUTATION_ACTION that
// refuses the requests of a client a source lists.
const deny = "deny"
// blocklistDenied notes the blocklists that list the client, as
// noteListed does, 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.blocklisted = len(listedBy) > 0
rq.noteListed(listedBy, "listed by a blocklist")
return rq.blocklisted && rq.h.config.BlocklistAction == deny
}
// crowdSecBanned reports whether a decision of the CrowdSec decision list
// on the client is in force at now. If one is, it notes the list, as
// noteHit does, and bans the client until that decision ends.
func (rq *request) crowdSecBanned(now time.Time) bool {
decision, listed := rq.h.lists.CrowdSecDecision(rq.client, now)
if !listed {
return false
}
rq.noteHit(bans.ReputationHit{Source: rq.h.config.CrowdSecDecisionsURL},
"listed by the CrowdSec decision list")
rq.banForCrowdSec(now, decision)
return true
}
// dnsblDenied notes the DNSBL zones whose verdict lists the client, as
// noteListed does, and reports whether SWWAF_REPUTATION_ACTION, being
// deny, refuses the request. 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 answer. ctx is the
// request's own context.
func (rq *request) dnsblDenied(ctx context.Context) bool {
listedBy := rq.h.dnsbl.ListedBy(ctx, rq.client)
rq.dnsblListed = len(listedBy) > 0
rq.noteListed(listedBy, "listed by a DNSBL zone")
return rq.dnsblListed && rq.h.config.ReputationAction == deny
}
// abuseIPDBDenied notes AbuseIPDB, as noteHit does, with the score, when
// its score of the client is a hit, and reports whether
// SWWAF_REPUTATION_ACTION, being deny, refuses the request, as dnsblDenied
// does for a zone. While SWWAF_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. ctx is the request's own context.
func (rq *request) abuseIPDBDenied(ctx context.Context) bool {
if rq.h.config.AbuseIPDBKey == "" {
return false
}
client := rq.h.clientGroup(rq.client)
held, _ := rq.h.limiter.Client(client)
offender := held.History.Offences != ratelimit.Offences{}
score, hit := rq.h.abuseIPDB.Hit(ctx, client, rq.client, offender)
if !hit {
return false
}
rq.abuseIPDBHit = true
rq.noteHit(bans.ReputationHit{Source: reputation.AbuseIPDBSource, Score: &score},
"scored by AbuseIPDB at or over SWWAF_ABUSEIPDB_MIN_SCORE")
return rq.h.config.ReputationAction == deny
}
// noteListed notes each of sources, the URLs of the blocklists or the
// DNSBL zones, their keys masked, that list the client, as noteHit does,
// with reason.
func (rq *request) noteListed(sources []string, reason string) {
for _, source := range sources {
rq.noteHit(bans.ReputationHit{Source: source}, reason)
}
}
// noteHit adds hit's source, which lists the client, to the log line's
// reputation, and hit to the notes of a ban the request makes, counts the
// source in the metrics, and raises a reputation_hit alert with reason,
// whose detail gives hit's source and score.
func (rq *request) noteHit(hit bans.ReputationHit, reason string) {
detail := map[string]any{"source": hit.Source}
if hit.Score != nil {
detail["score"] = *hit.Score
}
rq.line.Reputation = append(rq.line.Reputation, hit.Source)
rq.reputation = append(rq.reputation, hit)
rq.h.metrics.ReputationHit(hit.Source)
rq.h.alerts.Raise(alerts.Alert{
Event: alerts.EventReputationHit,
Client: rq.client,
Netblock: rq.h.clientGroup(rq.client),
ASN: rq.line.ASN,
ASName: rq.line.ASName,
Country: rq.line.Country,
Reason: reason,
Detail: detail,
})
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"fmt" "fmt"
@@ -15,7 +15,7 @@ import (
"sneak.berlin/go/smallwebwaf/internal/alerts" "sneak.berlin/go/smallwebwaf/internal/alerts"
"sneak.berlin/go/smallwebwaf/internal/bans" "sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/reputation" "sneak.berlin/go/smallwebwaf/internal/reputation"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
@@ -23,12 +23,12 @@ import (
// The reputation settings. // The reputation settings.
const ( const (
blocklistURLs = "SWW_BLOCKLIST_URLS" blocklistURLs = "SWWAF_BLOCKLIST_URLS"
blocklistAction = "SWW_BLOCKLIST_ACTION" blocklistAction = "SWWAF_BLOCKLIST_ACTION"
asnLimitPercentURL = "SWW_ASN_LIMIT_PERCENT_URL" asnLimitPercentURL = "SWWAF_ASN_LIMIT_PERCENT_URL"
) )
// The actions of SWW_BLOCKLIST_ACTION and SWW_REPUTATION_ACTION: // The actions of SWWAF_BLOCKLIST_ACTION and SWWAF_REPUTATION_ACTION:
// limitHalf gives a listed client half of every limit, and limitQuarter a // limitHalf gives a listed client half of every limit, and limitQuarter a
// quarter. // quarter.
const ( const (
@@ -49,7 +49,7 @@ const (
func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) { func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) {
t.Parallel() t.Parallel()
forward, denied := requestlog.ActionForward, requestlog.ActionClientDenied forward, denied := requestlog.ActionForward, requestlog.ActionDenied
for _, tc := range []struct { for _, tc := range []struct {
action string action string
@@ -66,7 +66,7 @@ func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) {
{ {
// Half of 4 requests a minute: the third breaks the limit. // Half of 4 requests a minute: the third breaks the limit.
limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden}, limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden},
[]string{forward, forward, requestlog.ActionClientIsRateLimited}, []string{forward, forward, requestlog.ActionRateLimited},
"50 from " + blocklistAction, "50 from " + blocklistAction,
}, },
{ {
@@ -118,66 +118,16 @@ func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) {
} }
} }
func TestReputationRefusalNamesItsHeuristicAndWhatListedTheClient(t *testing.T) { func TestBlocklistsComeAfterTheCountryListsAndSkipAllowNets(t *testing.T) {
t.Parallel()
for _, tc := range []struct {
heuristic string
env map[string]string
load func(*testing.T, *discriminator.Server)
figures string
}{
{
"blocklists",
map[string]string{blocklistURLs: dropURL, blocklistAction: actionDeny},
func(t *testing.T, server *discriminator.Server) {
t.Helper()
loadLists(t, server, map[string][]string{dropURL: {client}})
},
`{"lists": ["` + dropURL + `"]}`,
},
{
"dnsbl",
map[string]string{
dnsblZones: dnsblZone, dnsblResolver: noResolver,
reputationAction: actionDeny,
},
func(_ *testing.T, server *discriminator.Server) {
loadVerdicts(server, map[string][]string{client: {dnsblZone}})
},
`{"zones": ["` + dnsblZone + `"]}`,
},
{
"abuseipdb",
map[string]string{abuseIPDBKey: accountKey, reputationAction: actionDeny},
func(_ *testing.T, server *discriminator.Server) {
loadScores(server, map[string]int64{client: 80})
},
`{"score": 80, "min_score": 75}`,
},
} {
t.Run(tc.heuristic, func(t *testing.T) {
t.Parallel()
s, server, _ := startWithLookups(t, tc.env)
tc.load(t, server)
line := s.get(client, http.StatusForbidden, requestlog.ActionClientDenied)
wantHeuristic(t, line, tc.heuristic, tc.figures)
})
}
}
func TestBlocklistsComeAfterAllowedCountriesAndSkipAllowNets(t *testing.T) {
t.Parallel() t.Parallel()
s, server, queue := startWithLookups(t, map[string]string{ s, server, queue := startWithLookups(t, map[string]string{
blocklistURLs: dropURL, allowedCountries: "de", allowNets: fromDE, blocklistURLs: dropURL, deniedCountries: "kp", allowNets: fromDE,
}) })
loadLists(t, server, map[string][]string{dropURL: {fromDE, fromKP}}) loadLists(t, server, map[string][]string{dropURL: {fromDE, fromKP}})
// fromKP's country refuses it before the list is looked at, and fromDE, // fromKP's country refuses it before the list is looked at, and fromDE,
// in SWW_ALLOW_NETS, is not checked at all: neither is noted, nor // in SWWAF_ALLOW_NETS, is not checked at all: neither is noted, nor
// alerted. // alerted.
wantReputation(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied)) wantReputation(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionCountryDenied))
wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward)) wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward))
@@ -193,7 +143,7 @@ func TestObserveModeForwardsAClientABlocklistDeniesAndAlertsIt(t *testing.T) {
loadLists(t, server, map[string][]string{dropURL: {fromDE}}) loadLists(t, server, map[string][]string{dropURL: {fromDE}})
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward) line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionClientDenied) wantWouldAction(t, line, requestlog.ActionDenied)
wantReputation(t, line, dropURL) wantReputation(t, line, dropURL)
waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook] waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
@@ -211,18 +161,18 @@ func TestBlocklistLimitTakesPartInTheLowestPercentageOfEveryLimit(t *testing.T)
// percentText gives them, and limitHit its limit_hit. // percentText gives them, and limitHit its limit_hit.
want, limitHit string want, limitHit string
}{ }{
{limitHalf, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes}, {limitHalf, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
{limitQuarter, asnTagDEHalf, "25 from " + blocklistAction, minuteBytes}, {limitQuarter, asnDEHalf, "25 from " + blocklistAction, minuteBytes},
// The AS number's, the first of two alike. // The AS number's, the first of two alike.
{limitQuarter, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes}, {limitQuarter, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
{actionLog, "asn=64511:25", none, ""}, {actionLog, asnDE + ":100", none, ""},
} { } {
t.Run(tc.action+" "+tc.asnPercent, func(t *testing.T) { t.Run(tc.action+" "+tc.asnPercent, func(t *testing.T) {
t.Parallel() t.Parallel()
s, server, _ := startWithLookups(t, map[string]string{ s, server, _ := startWithLookups(t, map[string]string{
bytesLimitPerMinute: twoUploads, blocklistURLs: dropURL, bytesLimitPerMinute: twoUploads, blocklistURLs: dropURL,
blocklistAction: tc.action, tagLimitPercent: tc.asnPercent, blocklistAction: tc.action, asnLimitPercent: tc.asnPercent,
}) })
loadLists(t, server, map[string][]string{dropURL: {fromDE}}) loadLists(t, server, map[string][]string{dropURL: {fromDE}})
@@ -246,7 +196,7 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
const ( const (
fromURL = "25 from " + asnLimitPercentURL fromURL = "25 from " + asnLimitPercentURL
fromSetting = "25 from " + tagLimitPercent fromSetting = "25 from " + asnLimitPercent
) )
for _, tc := range []struct { for _, tc := range []struct {
@@ -260,21 +210,21 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
{"the file's alone", nil, asnDEQuarter, fromURL, fromURL}, {"the file's alone", nil, asnDEQuarter, fromURL, fromURL},
{ {
"the file's, lower than the setting's", "the file's, lower than the setting's",
map[string]string{tagLimitPercent: asnTagDEHalf}, asnDEQuarter, fromURL, fromURL, map[string]string{asnLimitPercent: asnDEHalf}, asnDEQuarter, fromURL, fromURL,
}, },
{ {
"the setting's, lower than the file's", "the setting's, lower than the file's",
map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEHalf, map[string]string{asnLimitPercent: asnDEQuarter}, asnDEHalf,
fromSetting, fromSetting, fromSetting, fromSetting,
}, },
{ {
"the setting's, the first of two alike", "the setting's, the first of two alike",
map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEQuarter, map[string]string{asnLimitPercent: asnDEQuarter}, asnDEQuarter,
fromSetting, fromSetting, fromSetting, fromSetting,
}, },
{"none, for an AS number the file does not list", nil, asnKP + ":25", none, none}, {"none, for an AS number the file does not list", nil, asnKP + ":25", none, none},
{ {
"SWW_ASN_BYTES_PERCENT's in place of the file's for the byte limits", "SWWAF_ASN_BYTES_PERCENT's in place of the file's for the byte limits",
map[string]string{asnBytesPercent: asnDE + ":100"}, asnDEQuarter, fromURL, none, map[string]string{asnBytesPercent: asnDE + ":100"}, asnDEQuarter, fromURL, none,
}, },
} { } {
@@ -322,7 +272,6 @@ func TestEachBlocklistThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
Instance: alertInstance, Instance: alertInstance,
Time: clk.Now(), Time: clk.Now(),
Event: alerts.EventReputationHit, Event: alerts.EventReputationHit,
Host: appHost,
Client: netip.MustParseAddr(fromDE), Client: netip.MustParseAddr(fromDE),
Netblock: netip.MustParsePrefix(fromDE + "/32"), Netblock: netip.MustParsePrefix(fromDE + "/32"),
ASN: asnDE, ASN: asnDE,
@@ -340,7 +289,7 @@ func TestEachBlocklistThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
// Each list's hits, none of its fetches failed, and when its copy was // Each list's hits, none of its fetches failed, and when its copy was
// fetched, 0 for the one without. // fetched, 0 for the one without.
metrics := s.scrape() metrics := s.scrape(unplaced)
fetched := float64(listsFetched().Unix()) fetched := float64(listsFetched().Unix())
for listURL, want := range map[string]struct{ hits, fetched float64 }{ for listURL, want := range map[string]struct{ hits, fetched float64 }{
@@ -349,22 +298,22 @@ func TestEachBlocklistThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
labels := `{instance="` + alertInstance + `",source="` + listURL + `"}` labels := `{instance="` + alertInstance + `",source="` + listURL + `"}`
if want.hits == 0 { if want.hits == 0 {
wantNoSeries(t, metrics, "sww_reputation_hits_total"+labels) wantNoSeries(t, metrics, "smallwebwaf_reputation_hits_total"+labels)
} else { } else {
wantMetric(t, metrics, "sww_reputation_hits_total"+labels, want.hits) wantMetric(t, metrics, "smallwebwaf_reputation_hits_total"+labels, want.hits)
} }
wantMetric(t, metrics, "sww_reputation_failures_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_failures_total"+labels, 0)
wantMetric(t, metrics, "sww_reputation_last_fetch_timestamp_seconds"+labels, wantMetric(t, metrics, "smallwebwaf_reputation_last_fetch_timestamp_seconds"+labels,
want.fetched) want.fetched)
} }
} }
// The DNSBL settings. // The DNSBL settings.
const ( const (
dnsblZones = "SWW_DNSBL_ZONES" dnsblZones = "SWWAF_DNSBL_ZONES"
dnsblResolver = "SWW_DNSBL_RESOLVER" dnsblResolver = "SWWAF_DNSBL_RESOLVER"
reputationAction = "SWW_REPUTATION_ACTION" reputationAction = "SWWAF_REPUTATION_ACTION"
) )
// The DNSBL zones these tests name, which are never asked about the // The DNSBL zones these tests name, which are never asked about the
@@ -380,7 +329,7 @@ const (
func TestEachReputationActionForAClientADNSBLZoneLists(t *testing.T) { func TestEachReputationActionForAClientADNSBLZoneLists(t *testing.T) {
t.Parallel() t.Parallel()
forward, denied := requestlog.ActionForward, requestlog.ActionClientDenied forward, denied := requestlog.ActionForward, requestlog.ActionDenied
for _, tc := range []struct { for _, tc := range []struct {
action string action string
@@ -397,7 +346,7 @@ func TestEachReputationActionForAClientADNSBLZoneLists(t *testing.T) {
{ {
// Half of 4 requests a minute: the third breaks the limit. // Half of 4 requests a minute: the third breaks the limit.
limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden}, limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden},
[]string{forward, forward, requestlog.ActionClientIsRateLimited}, []string{forward, forward, requestlog.ActionRateLimited},
"50 from " + reputationAction, "50 from " + reputationAction,
}, },
{ {
@@ -420,7 +369,7 @@ func TestEachReputationActionForAClientADNSBLZoneLists(t *testing.T) {
for _, from := range []string{fromDE, fromKP} { for _, from := range []string{fromDE, fromKP} {
for i := range 3 { for i := range 3 {
line := s.get(from, tc.statuses[i], tc.actions[i]) line := s.get(from, tc.statuses[i], tc.actions[i])
// In the order SWW_DNSBL_ZONES names them. // In the order SWWAF_DNSBL_ZONES names them.
wantReputation(t, line, listedBy[from]...) wantReputation(t, line, listedBy[from]...)
wantPercent(t, "limit_percent", line.LimitPercent, wantPercent(t, "limit_percent", line.LimitPercent,
line.LimitPercentSetting, tc.percent) line.LimitPercentSetting, tc.percent)
@@ -466,9 +415,9 @@ func TestDNSBLZonesComeAfterTheBlocklistsAndSkipAllowNets(t *testing.T) {
loadVerdicts(server, map[string][]string{fromKP: {dnsblZone}, fromDE: {dnsblZone}}) loadVerdicts(server, map[string][]string{fromKP: {dnsblZone}, fromDE: {dnsblZone}})
// The blocklist refuses fromKP before its verdict is looked at, and // The blocklist refuses fromKP before its verdict is looked at, and
// fromDE, in SWW_ALLOW_NETS, is not checked at all: neither is noted // fromDE, in SWWAF_ALLOW_NETS, is not checked at all: neither is noted
// for the zone, nor alerted, nor asked about. // for the zone, nor alerted, nor asked about.
wantReputation(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionClientDenied), wantReputation(t, s.get(fromKP, http.StatusForbidden, requestlog.ActionDenied),
dropURL) dropURL)
wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward)) wantReputation(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward))
@@ -482,46 +431,6 @@ 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) { func TestObserveModeForwardsAClientADNSBLZoneDeniesAndAlertsIt(t *testing.T) {
t.Parallel() t.Parallel()
@@ -532,7 +441,7 @@ func TestObserveModeForwardsAClientADNSBLZoneDeniesAndAlertsIt(t *testing.T) {
loadVerdicts(server, map[string][]string{fromDE: {dnsblZone}}) loadVerdicts(server, map[string][]string{fromDE: {dnsblZone}})
line := s.get(fromDE, http.StatusOK, requestlog.ActionForward) line := s.get(fromDE, http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionClientDenied) wantWouldAction(t, line, requestlog.ActionDenied)
wantReputation(t, line, dnsblZone) wantReputation(t, line, dnsblZone)
waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook] waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
@@ -604,7 +513,6 @@ func TestEachZoneThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
Instance: alertInstance, Instance: alertInstance,
Time: clk.Now(), Time: clk.Now(),
Event: alerts.EventReputationHit, Event: alerts.EventReputationHit,
Host: appHost,
Client: netip.MustParseAddr(fromDE), Client: netip.MustParseAddr(fromDE),
Netblock: netip.MustParsePrefix(fromDE + "/32"), Netblock: netip.MustParsePrefix(fromDE + "/32"),
ASN: asnDE, ASN: asnDE,
@@ -622,14 +530,14 @@ func TestEachZoneThatListsAClientRaisesAnAlertOncePerCooldownAndIsCounted(
// Each zone's hits, and its queries and their failures, none, since // Each zone's hits, and its queries and their failures, none, since
// every client had its verdicts. // every client had its verdicts.
metrics := s.scrape() metrics := s.scrape(unplaced)
for _, zone := range []string{dnsblZone, otherZone} { for _, zone := range []string{dnsblZone, otherZone} {
labels := `{instance="` + alertInstance + `",source="` + zone + `"}` labels := `{instance="` + alertInstance + `",source="` + zone + `"}`
wantMetric(t, metrics, "sww_reputation_hits_total"+labels, 2) wantMetric(t, metrics, "smallwebwaf_reputation_hits_total"+labels, 2)
wantMetric(t, metrics, "sww_reputation_queries_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_queries_total"+labels, 0)
wantMetric(t, metrics, "sww_reputation_failures_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_failures_total"+labels, 0)
} }
} }
@@ -656,8 +564,8 @@ func TestZoneKeyIsMaskedInTheLogTheAlertAndTheMetrics(t *testing.T) {
masked) masked)
} }
metrics := s.scrape() metrics := s.scrape(unplaced)
wantMetric(t, metrics, `sww_reputation_hits_total{instance="`+ wantMetric(t, metrics, `smallwebwaf_reputation_hits_total{instance="`+
alertInstance+`",source="`+masked+`"}`, 1) alertInstance+`",source="`+masked+`"}`, 1)
for name, shown := range map[string]string{ for name, shown := range map[string]string{
@@ -699,7 +607,7 @@ func TestRequestFromAClientWithoutAVerdictHasTheZoneAskedAboutIt(t *testing.T) {
// The AbuseIPDB settings, and accountKey, the key the tests set. // The AbuseIPDB settings, and accountKey, the key the tests set.
const ( const (
abuseIPDBKey = "SWW_ABUSEIPDB_KEY" abuseIPDBKey = "SWWAF_ABUSEIPDB_KEY"
accountKey = "abuseipdb-key-0123456789abcdef" accountKey = "abuseipdb-key-0123456789abcdef"
) )
@@ -707,7 +615,7 @@ const (
// AbuseIPDB. // AbuseIPDB.
const abuseipdb = reputation.AbuseIPDBSource const abuseipdb = reputation.AbuseIPDBSource
// abuseIPDBURL is where newDiscriminator has clients checked with AbuseIPDB: at // abuseIPDBURL is where newProxy has clients checked with AbuseIPDB: at
// abuseIPDBStandIn, which TestMain registers with Go's default transport, // abuseIPDBStandIn, which TestMain registers with Go's default transport,
// through which AbuseIPDB is asked. // through which AbuseIPDB is asked.
const abuseIPDBURL = "abuseipdb://stand-in/api/v2/check" const abuseIPDBURL = "abuseipdb://stand-in/api/v2/check"
@@ -741,8 +649,8 @@ func TestOnlyAClientThatHasCommittedAnOffenceIsCheckedWithAbuseIPDB(t *testing.T
s.get(fromDE, http.StatusOK, forward) s.get(fromDE, http.StatusOK, forward)
s.get(fromDE, http.StatusOK, forward) s.get(fromDE, http.StatusOK, forward)
s.get(fromKP, http.StatusOK, forward) s.get(fromKP, http.StatusOK, forward)
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
s.get(fromDE, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(fromDE, http.StatusForbidden, requestlog.ActionBanned)
wantAbuseIPDBChecks(t, server, 0) wantAbuseIPDBChecks(t, server, 0)
// Once the ban has ended, fromDE's first request has it checked in the // Once the ban has ended, fromDE's first request has it checked in the
@@ -781,7 +689,7 @@ func TestIPv6ClientCostsOneAbuseIPDBCheckWhicheverOfItsAddressesSends(t *testing
s.get(addresses[0], http.StatusOK, forward) s.get(addresses[0], http.StatusOK, forward)
} }
s.get(addresses[0], http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(addresses[0], http.StatusForbidden, requestlog.ActionRateLimited)
clk.advance(time.Hour) clk.advance(time.Hour)
// Once the ban has ended, which set its counters back to zero, a // Once the ban has ended, which set its counters back to zero, a
@@ -814,20 +722,24 @@ func TestClientRefusedForAnOffenceIsCheckedWithAbuseIPDBAtItsNextRequest(t *test
want ratelimit.Offences want ratelimit.Offences
}{ }{
{ {
"a block rule", blockedPath, http.StatusForbidden, "a block rule", blockedPath, http.StatusForbidden, requestlog.ActionRuleBlocked,
requestlog.ActionBlockedByBlockRule, ratelimit.Offences{BlockedByBlockRule: 1}, ratelimit.Offences{RuleBlocked: 1},
}, },
{ {
"the Core Rule Set", sqlInjection, http.StatusForbidden, "the Core Rule Set", sqlInjection, http.StatusForbidden,
requestlog.ActionWAFBlocked, ratelimit.Offences{WAFBlocked: 1}, requestlog.ActionWAFBlocked, ratelimit.Offences{WAFBlocked: 1},
}, },
{ {
"a ban rule", probePath, http.StatusForbidden, requestlog.ActionTemporarilyBanned, "a ban rule", probePath, http.StatusForbidden, requestlog.ActionBanned,
ratelimit.Offences{Attack: 1}, ratelimit.Offences{Attack: 1},
}, },
{ {
"a trap path", "/xmlrpc.php", http.StatusForbidden, "a trap path", "/xmlrpc.php", http.StatusForbidden, requestlog.ActionBanned,
requestlog.ActionTemporarilyBanned, ratelimit.Offences{Attack: 1}, ratelimit.Offences{Attack: 1},
},
{
"a missing token", proxy.MetricsPath, http.StatusUnauthorized,
requestlog.ActionAdmin, ratelimit.Offences{TokenRefused: 1},
}, },
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
@@ -836,7 +748,7 @@ func TestClientRefusedForAnOffenceIsCheckedWithAbuseIPDBAtItsNextRequest(t *test
s, clk, server := startWithClock(t, "", map[string]string{ s, clk, server := startWithClock(t, "", map[string]string{
abuseIPDBKey: accountKey, reputationAction: actionLog, abuseIPDBKey: accountKey, reputationAction: actionLog,
rulesDir: writeRules(t, testRules), attackBanDuration: "1h", rulesDir: writeRules(t, testRules), attackBanDuration: "1h",
trapPaths: trapPathList, wafMode: block, trapPaths: trapPathList, metricsToken: token, wafMode: block,
}) })
s.request(client, tc.path, tc.status, tc.action) s.request(client, tc.path, tc.status, tc.action)
@@ -858,7 +770,7 @@ func TestClientRefusedForAnOffenceIsCheckedWithAbuseIPDBAtItsNextRequest(t *test
func TestEachReputationActionForAClientAbuseIPDBScoresAtOrOverTheMinimum(t *testing.T) { func TestEachReputationActionForAClientAbuseIPDBScoresAtOrOverTheMinimum(t *testing.T) {
t.Parallel() t.Parallel()
forward, denied := requestlog.ActionForward, requestlog.ActionClientDenied forward, denied := requestlog.ActionForward, requestlog.ActionDenied
for _, tc := range []struct { for _, tc := range []struct {
action string action string
@@ -875,7 +787,7 @@ func TestEachReputationActionForAClientAbuseIPDBScoresAtOrOverTheMinimum(t *test
{ {
// Half of 4 requests a minute: the third breaks the limit. // Half of 4 requests a minute: the third breaks the limit.
limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden}, limitHalf, []int{http.StatusOK, http.StatusOK, http.StatusForbidden},
[]string{forward, forward, requestlog.ActionClientIsRateLimited}, []string{forward, forward, requestlog.ActionRateLimited},
"50 from " + reputationAction, "50 from " + reputationAction,
}, },
{ {
@@ -890,7 +802,7 @@ func TestEachReputationActionForAClientAbuseIPDBScoresAtOrOverTheMinimum(t *test
rateLimitPerMinute: fourAMinute, abuseIPDBKey: accountKey, rateLimitPerMinute: fourAMinute, abuseIPDBKey: accountKey,
reputationAction: tc.action, reputationAction: tc.action,
}) })
// At SWW_ABUSEIPDB_MIN_SCORE, 75 by default, and just under it. // At SWWAF_ABUSEIPDB_MIN_SCORE, 75 by default, and just under it.
loadScores(server, map[string]int64{fromDE: 75, fromKP: 74}) loadScores(server, map[string]int64{fromDE: 75, fromKP: 74})
for i := range 3 { for i := range 3 {
@@ -941,7 +853,7 @@ func TestAbuseIPDBHitRaisesAnAlertWithTheScoreOncePerCooldownAndIsCounted(
// The alert is made as a DNSBL zone's is, with the score besides. // The alert is made as a DNSBL zone's is, with the score besides.
waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook] waiting := queue.Snapshot().Waiting[alerts.DestinationWebhook]
if len(waiting) != 1 || waiting[0].Event != alerts.EventReputationHit || if len(waiting) != 1 || waiting[0].Event != alerts.EventReputationHit ||
waiting[0].Reason != "scored by AbuseIPDB at or over SWW_ABUSEIPDB_MIN_SCORE" || waiting[0].Reason != "scored by AbuseIPDB at or over SWWAF_ABUSEIPDB_MIN_SCORE" ||
waiting[0].Detail["source"] != abuseipdb || waiting[0].Detail["score"] != int64(90) || waiting[0].Detail["source"] != abuseipdb || waiting[0].Detail["score"] != int64(90) ||
queue.Suppressed() != 1 { queue.Suppressed() != 1 {
t.Errorf("alerts waiting %+v, %d held back, want AbuseIPDB's reputation_hit "+ t.Errorf("alerts waiting %+v, %d held back, want AbuseIPDB's reputation_hit "+
@@ -950,13 +862,13 @@ func TestAbuseIPDBHitRaisesAnAlertWithTheScoreOncePerCooldownAndIsCounted(
// The hits, and the checks, none, since no client committed an // The hits, and the checks, none, since no client committed an
// offence, so that the whole budget is left. // offence, so that the whole budget is left.
metrics := s.scrape() metrics := s.scrape(unplaced)
labels := `{instance="` + alertInstance + `",source="` + abuseipdb + `"}` labels := `{instance="` + alertInstance + `",source="` + abuseipdb + `"}`
wantMetric(t, metrics, "sww_reputation_hits_total"+labels, 2) wantMetric(t, metrics, "smallwebwaf_reputation_hits_total"+labels, 2)
wantMetric(t, metrics, "sww_reputation_queries_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_queries_total"+labels, 0)
wantMetric(t, metrics, "sww_reputation_failures_total"+labels, 0) wantMetric(t, metrics, "smallwebwaf_reputation_failures_total"+labels, 0)
wantMetric(t, metrics, "sww_reputation_daily_budget_remaining"+labels, 900) wantMetric(t, metrics, "smallwebwaf_reputation_daily_budget_remaining"+labels, 900)
} }
func TestWithoutAnAbuseIPDBKeyNoClientIsCheckedNorAScoreUsed(t *testing.T) { func TestWithoutAnAbuseIPDBKeyNoClientIsCheckedNorAScoreUsed(t *testing.T) {
@@ -972,12 +884,12 @@ func TestWithoutAnAbuseIPDBKeyNoClientIsCheckedNorAScoreUsed(t *testing.T) {
// fromDE's score is not used, and once it has committed an offence it // fromDE's score is not used, and once it has committed an offence it
// is not checked either. // is not checked either.
wantReputation(t, s.get(fromDE, http.StatusOK, forward)) wantReputation(t, s.get(fromDE, http.StatusOK, forward))
s.get(fromDE, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(fromDE, http.StatusForbidden, requestlog.ActionRateLimited)
clk.advance(time.Hour) clk.advance(time.Hour)
wantReputation(t, s.get(fromDE, http.StatusOK, forward)) wantReputation(t, s.get(fromDE, http.StatusOK, forward))
wantAbuseIPDBChecks(t, server, 0) wantAbuseIPDBChecks(t, server, 0)
wantNoSeries(t, s.scrape(), `sww_reputation_daily_budget_remaining{`+ wantNoSeries(t, s.scrape(unplaced), `smallwebwaf_reputation_daily_budget_remaining{`+
`instance="`+alertInstance+`",source="`+abuseipdb+`"}`) `instance="`+alertInstance+`",source="`+abuseipdb+`"}`)
} }
@@ -996,10 +908,10 @@ func TestBanNotesNameEachReputationSourceThatListedTheClient(t *testing.T) {
}{ }{
{"for a broken rate limit", func(s *sender, from string) { {"for a broken rate limit", func(s *sender, from string) {
s.get(from, http.StatusOK, requestlog.ActionForward) s.get(from, http.StatusOK, requestlog.ActionForward)
s.get(from, http.StatusForbidden, requestlog.ActionClientIsRateLimited) s.get(from, http.StatusForbidden, requestlog.ActionRateLimited)
}}, }},
{"for a clear sign of attack", func(s *sender, from string) { {"for a clear sign of attack", func(s *sender, from string) {
s.request(from, probePath, http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.request(from, probePath, http.StatusForbidden, requestlog.ActionBanned)
}}, }},
} { } {
t.Run(tc.name, func(t *testing.T) { t.Run(tc.name, func(t *testing.T) {
@@ -1012,7 +924,7 @@ func TestBanNotesNameEachReputationSourceThatListedTheClient(t *testing.T) {
abuseIPDBKey: accountKey, reputationAction: actionLog, abuseIPDBKey: accountKey, reputationAction: actionLog,
}) })
// Every source lists client, and none otherClient, whose score is // Every source lists client, and none otherClient, whose score is
// under SWW_ABUSEIPDB_MIN_SCORE, 75 by default. // under SWWAF_ABUSEIPDB_MIN_SCORE, 75 by default.
loadLists(t, server, map[string][]string{dropURL: {client}}) loadLists(t, server, map[string][]string{dropURL: {client}})
loadVerdicts(server, map[string][]string{client: {dnsblZone}, otherClient: nil}) loadVerdicts(server, map[string][]string{client: {dnsblZone}, otherClient: nil})
loadScores(server, map[string]int64{client: score, otherClient: 74}) loadScores(server, map[string]int64{client: score, otherClient: 74})
@@ -1061,11 +973,11 @@ func verdictsFetched() time.Time {
} }
// loadVerdicts puts into server's DNSBL, for each client listedBy names, // loadVerdicts puts into server's DNSBL, for each client listedBy names,
// a verdict of each zone SWW_DNSBL_ZONES names, fetched at // a verdict of each zone SWWAF_DNSBL_ZONES names, fetched at
// verdictsFetched, as reputation.json would at start: one that lists the // verdictsFetched, as reputation.json would at start: one that lists the
// client from each zone listedBy gives for it, and one that does not from // client from each zone listedBy gives for it, and one that does not from
// each other zone. // each other zone.
func loadVerdicts(server *discriminator.Server, listedBy map[string][]string) { func loadVerdicts(server *proxy.Server, listedBy map[string][]string) {
verdicts := make([]reputation.Verdict, 0, len(listedBy)*len(server.DNSBL.Zones())) verdicts := make([]reputation.Verdict, 0, len(listedBy)*len(server.DNSBL.Zones()))
for client, zones := range listedBy { for client, zones := range listedBy {
@@ -1083,7 +995,7 @@ func loadVerdicts(server *discriminator.Server, listedBy map[string][]string) {
// loadScores puts into server's AbuseIPDB the score scores gives each // loadScores puts into server's AbuseIPDB the score scores gives each
// client, an IPv4 address, fetched at verdictsFetched, as reputation.json // client, an IPv4 address, fetched at verdictsFetched, as reputation.json
// would at start. // would at start.
func loadScores(server *discriminator.Server, scores map[string]int64) { func loadScores(server *proxy.Server, scores map[string]int64) {
kept := make([]reputation.Score, 0, len(scores)) kept := make([]reputation.Score, 0, len(scores))
for client, score := range scores { for client, score := range scores {
kept = append(kept, reputation.Score{ kept = append(kept, reputation.Score{
@@ -1097,7 +1009,7 @@ func loadScores(server *discriminator.Server, scores map[string]int64) {
// wantAbuseIPDBChecks checks how many clients server has checked with // wantAbuseIPDBChecks checks how many clients server has checked with
// AbuseIPDB. // AbuseIPDB.
func wantAbuseIPDBChecks(t *testing.T, server *discriminator.Server, want int) { func wantAbuseIPDBChecks(t *testing.T, server *proxy.Server, want int) {
t.Helper() t.Helper()
if got := server.AbuseIPDB.Checked(); got != want { if got := server.AbuseIPDB.Checked(); got != want {
@@ -1107,7 +1019,7 @@ func wantAbuseIPDBChecks(t *testing.T, server *discriminator.Server, want int) {
// loadLists puts copies of lists into server's lists, by URL, each with // loadLists puts copies of lists into server's lists, by URL, each with
// its lines, fetched at listsFetched, as reputation.json would at start. // its lines, fetched at listsFetched, as reputation.json would at start.
func loadLists(t *testing.T, server *discriminator.Server, copies map[string][]string) { func loadLists(t *testing.T, server *proxy.Server, copies map[string][]string) {
t.Helper() t.Helper()
lists := make([]reputation.List, 0, len(copies)) lists := make([]reputation.List, 0, len(copies))
+894
View File
@@ -0,0 +1,894 @@
package proxy
import (
"context"
"errors"
"io"
"net/http"
"net/http/httptrace"
"net/http/httputil"
"net/netip"
"os"
"slices"
"strings"
"sync"
"sync/atomic"
"time"
"sneak.berlin/go/smallwebwaf/internal/anomaly"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/config"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/rules"
)
// flushAfterEachWrite has ReverseProxy pass on each part of the app's
// answer as soon as it arrives.
const flushAfterEachWrite time.Duration = -1
// refusal is smallwebwaf refusing a request, or refusing to go on with it:
// the status the client is answered if the response has not started yet,
// 0 to close the connection without an answer, the action the log line
// names, and the setting whose size or time limit the request passed, if
// that is why.
type refusal struct {
status int
action string
limit string
}
// request is one request on its way through smallwebwaf, from the moment
// its headers have been read to its log line.
type request struct {
h *handler
in *http.Request
// rc sets the deadlines of the connection to the client.
rc *http.ResponseController
out *responseWriter
body *requestBody // nil for a request without a body
line requestlog.Line
client netip.Addr
peer netip.Addr
peerTrusted bool
// lookedUp is true once the client's AS number and country have been
// looked up, whether or not an answer was there, and lookupAnswer is
// what the lookup gave then, the zero Answer while GeoJS had given none.
lookedUp bool
lookupAnswer lookup.Answer
// counted is true for a request the rate limits counted, whose bytes
// the byte limits count once it has ended. limitPercent and
// bytesPercent are then its client's limit percentages for the rate
// limits and for the byte limits.
counted bool
limitPercent, bytesPercent percentage
// attack is true for a request that matched a ban rule or asked for a
// trap path, ruleBlocked for one a block rule refused, wafBlocked for
// one the Core Rule Set refused, and tokenRefused for one refused for a
// missing or wrong token, each an offence its client's history counts.
attack, ruleBlocked, wafBlocked, tokenRefused bool
// blocklisted is true once a blocklist is found to list the client,
// dnsblListed once a DNSBL zone's verdict is, and abuseIPDBHit once
// AbuseIPDB's score of it is a hit.
blocklisted, dnsblListed, abuseIPDBHit bool
// reputation is the reputation sources that list the client, for the
// notes of a ban the request makes.
reputation []bans.ReputationHit
start time.Time
// checked is when the checks were done, and upstreamStart when the
// request was handed to the app.
checked time.Time
upstreamStart time.Time
// cancel ends the request to the app.
cancel context.CancelFunc
// refused is the first refusal, from whichever goroutine meets it.
refused atomic.Pointer[refusal]
// complete is true once the app's whole answer has been passed on.
complete bool
// upgraded is the connection to the app once the app has switched
// protocols, as for a WebSocket, and nil otherwise.
upgraded *upgradedConn
// mu guards what follows. The timeouts run on goroutines of their
// own, and the transport starts and stops them, and notes the times
// below, from its own; once timersStopped is set, none of the timeouts
// acts any more.
mu sync.Mutex
timersStopped bool
clientRequestTimer *time.Timer
upstreamRequestTimer *time.Timer
upstreamResponseTimer *time.Timer
// connected is when there was a connection to the app, requestSent
// when the app had been sent the whole request, and answerStarted
// when the first byte of its answer arrived.
connected time.Time
requestSent time.Time
answerStarted time.Time
}
// newRequest starts handling r: it notes the time, counts the request as
// under way, works out the client, and starts the log line with what is
// known of the request.
func (h *handler) newRequest(w http.ResponseWriter, r *http.Request) *request {
h.metrics.RequestStarted()
start := time.Now()
peer := peerAddress(r)
trusted := h.config.TrustedProxies
peerTrusted := isInside(peer, trusted)
forwardedFor := r.Header.Values("X-Forwarded-For")
client := clientAddress(peer, forwardedFor, trusted)
rq := &request{
h: h,
in: r,
rc: http.NewResponseController(w),
out: &responseWriter{ResponseWriter: w},
client: client,
peer: peer,
peerTrusted: peerTrusted,
start: start,
line: requestlog.Line{
Time: requestlog.FormatTime(start),
Instance: h.config.InstanceName,
ClientIP: client.String(),
Method: r.Method,
Scheme: scheme(r, peerTrusted),
Host: r.Host,
Path: rules.Path(r),
Query: r.URL.RawQuery,
Protocol: r.Proto,
Referer: r.Referer(),
UserAgent: r.UserAgent(),
RequestID: requestID(r, peerTrusted),
PeerIP: peer.String(),
ForwardedFor: strings.Join(forwardedFor, ", "),
ClientGroup: h.clientGroup(client).String(),
ContentType: r.Header.Get("Content-Type"),
RequestHeaders: requestHeaders(r, h.config.LogRequestHeaders),
HasAuthorization: len(r.Header.Values("Authorization")) > 0,
HasCookie: len(r.Header.Values("Cookie")) > 0,
Action: requestlog.ActionForward,
},
}
// A length of -1 is a body whose length was not announced.
if r.ContentLength > 0 {
rq.line.ContentLength = r.ContentLength
}
if r.Body != http.NoBody {
rq.body = &requestBody{body: limitBody(r.Body, h.config.RequestMaxBytes), rq: rq}
}
return rq
}
// 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.
func requestHeaders(r *http.Request, names []string) map[string]string {
headers := map[string]string{}
for _, name := range names {
switch name {
case "authorization", "cookie", "set-cookie":
continue
}
values := r.Header.Values(name)
if len(values) > 0 {
headers[name] = strings.Join(values, ", ")
}
}
return headers
}
// check is the one place where a request can be refused once its client
// is known, before anything reaches the app, and before its body is read,
// but for the part the Core Rule Set reads. It returns nil to let the
// request through. The checks of checkClient come first, answered with
// SWWAF_BAN_RESPONSE, or 403 for a block rule or the Core Rule Set, and
// then the size limit, so that a request the rate limits count is counted
// even when it is refused for its size. In observe mode a request
// checkClient refuses goes on to the size limit like any other. A size or
// time limit the Core Rule Set's reading of the body meets ends the
// request in either mode. ctx is the request's own context.
func (rq *request) check(ctx context.Context) *refusal {
action := rq.checkClient(ctx)
refused := rq.refused.Load()
if refused != nil {
return refused
}
switch {
case action == "":
case rq.h.config.Observe:
// The log line names what enforce mode would have done.
rq.line.WouldAction = action
case action == requestlog.ActionRuleBlocked || action == requestlog.ActionWAFBlocked:
return &refusal{status: http.StatusForbidden, action: action}
default:
return rq.banResponse(action)
}
maxBytes := rq.h.config.RequestMaxBytes
if maxBytes > 0 && rq.in.ContentLength > maxBytes {
return &refusal{
status: http.StatusRequestEntityTooLarge,
action: requestlog.ActionTooLarge,
limit: "SWWAF_REQUEST_MAX_BYTES",
}
}
return nil
}
// checkClient runs the checks on the request's client, and returns the
// action of the first that refuses the request, or "" when none does. A
// client in SWWAF_ALLOW_NETS skips them, 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, then the country lists, then the blocklists,
// then the CrowdSec decision list, which bans the client it lists, then
// the DNSBL zones' verdicts, and then AbuseIPDB's score; 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, then SWWAF_TRAP_PATHS, then the rule files, and last the
// Core Rule Set. 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) {
return ""
}
now := rq.h.now()
if isInside(rq.client, cfg.DenyNets) {
return requestlog.ActionDenied
}
if rq.banned(now) {
return requestlog.ActionBanned
}
rq.lookUp(ctx)
// The lookup can wait for GeoJS, so the checks after it read the time
// again: a request counted at the time it arrived could be counted
// after a later one of its client's, which the rate limits would take
// for the clock set back.
now = rq.h.now()
if rq.countryDenied() {
return requestlog.ActionCountryDenied
}
if rq.blocklistDenied() {
return requestlog.ActionDenied
}
if rq.crowdSecBanned(now) {
return requestlog.ActionBanned
}
if rq.dnsblDenied(ctx) || rq.abuseIPDBDenied(ctx) {
return requestlog.ActionDenied
}
rq.counted = !isInside(rq.client, cfg.RateLimitExemptNets) &&
!pathExempt(rq.in, cfg.RateLimitExemptPaths)
if rq.counted {
rq.limitPercent, rq.bytesPercent = rq.limitPercentages()
rq.line.LimitPercent, rq.line.LimitPercentSetting = rq.limitPercent.logged()
rq.line.BytesPercent, rq.line.BytesPercentSetting = rq.bytesPercent.logged()
}
if rq.counted && rq.limitBroken(now) {
return requestlog.ActionRateLimited
}
if rq.trapPath(now) {
return requestlog.ActionBanned
}
action := rq.checkRules(now)
if action != "" {
return action
}
return rq.checkCoreRuleSet()
}
// pathExempt reports whether r is exempt under prefixes,
// SWWAF_RATE_LIMIT_EXEMPT_PATHS or SWWAF_WAF_EXEMPT_PATHS: whether its
// path as sent, the path the app receives, not percent-decoded, starts
// with one of prefixes, so that /%61ssets/x is not under /assets/ for an
// app whose router matches the path as received. A request whose decoded
// path contains .. anywhere or a backslash, or whose path as sent holds an
// encoded slash (%2F or %2f), never is, since an app may act on it as a
// path outside every prefix: /assets/..%2Flogin as /login, or /assets%2Fx
// as one path segment, as Go's router does.
func pathExempt(r *http.Request, prefixes []string) bool {
decoded := r.URL.Path
sent := rules.Path(r)
if strings.Contains(decoded, "..") || strings.Contains(decoded, `\`) ||
strings.Contains(strings.ToLower(sent), "%2f") {
return false
}
return slices.ContainsFunc(prefixes, func(prefix string) bool {
return strings.HasPrefix(sent, prefix)
})
}
// forward passes the request to the app and the app's answer back. ctx
// is the request's own context.
func (rq *request) forward(ctx context.Context) {
ctx, cancel := context.WithCancel(ctx)
defer cancel()
rq.cancel = cancel
ctx = httptrace.WithClientTrace(ctx, &httptrace.ClientTrace{
GotConn: rq.gotConn,
WroteRequest: rq.wroteRequest,
GotFirstResponseByte: rq.gotFirstResponseByte,
})
out := rq.in.WithContext(ctx)
if rq.body != nil {
out.Body = rq.body
}
reverseProxy := &httputil.ReverseProxy{
Rewrite: rq.rewrite,
Transport: rq.h.transport,
FlushInterval: flushAfterEachWrite,
ErrorLog: rq.h.errorLog,
ModifyResponse: rq.modifyResponse,
ErrorHandler: rq.answerError,
}
rq.startRequestTimers()
rq.upstreamStart = time.Now()
reverseProxy.ServeHTTP(rq.out, out)
}
// rewrite makes the request the app receives: the client's request,
// unchanged, sent to SWWAF_UPSTREAM_URL, with the forwarded headers and
// the request's id set, without any X-Client-ASN or X-Client-Country the
// client sent, whatever SWWAF_ADD_LOOKUP_HEADERS says, and, while it is
// set, with the client's AS number and country in them.
func (rq *request) rewrite(pr *httputil.ProxyRequest) {
upstream := rq.h.config.UpstreamURL
pr.Out.URL.Scheme = upstream.Scheme
pr.Out.URL.Host = upstream.Host
// ReverseProxy drops query parameters it cannot parse; the app gets
// the query as the client sent it.
pr.Out.URL.RawQuery = pr.In.URL.RawQuery
// ReverseProxy sends the path URL.EscapedPath gives, which, for a path
// holding a character Go escapes, such as |, is the whole path decoded
// and escaped again, %2F turned into /. Opaque is sent as it is, so the
// app gets the path as the client sent it. Left out are a target that
// is no path, such as *, and a path starting with //, which Go would
// send in Opaque as a scheme and host.
path := rules.Path(pr.In)
if strings.HasPrefix(path, "/") && !strings.HasPrefix(path, "//") {
pr.Out.URL.Opaque = path
}
setForwardedHeaders(pr.In, pr.Out, rq.peer, rq.peerTrusted)
pr.Out.Header.Set(requestIDHeader, rq.line.RequestID)
pr.Out.Header.Del(asnHeader)
pr.Out.Header.Del(countryHeader)
if rq.h.config.AddLookupHeaders {
setLookupHeaders(pr.Out.Header, rq.line.ASN, rq.line.Country)
}
}
// modifyResponse looks at the app's answer before ReverseProxy passes it
// on.
func (rq *request) modifyResponse(res *http.Response) error {
rq.line.UpstreamStatus = res.StatusCode
if res.StatusCode == http.StatusSwitchingProtocols {
// An upgraded connection, such as a WebSocket, is not cut by the
// timeouts. ReverseProxy writes this answer straight to the
// connection it takes over, not through rq.out, and then copies
// what passes each way through res.Body, the connection to the app.
// It may still refuse the switch, as when the app's Upgrade is not
// the client's, so the status is noted only once it has taken over
// the connection, by rq.out's Hijack.
rq.stopTimers()
rq.line.Websocket = true
conn, ok := res.Body.(io.ReadWriteCloser)
if ok {
rq.upgraded = &upgradedConn{ReadWriteCloser: conn}
res.Body = rq.upgraded
}
return nil
}
maxBytes := rq.h.config.ResponseMaxBytes
if maxBytes > 0 && res.Body != http.NoBody && res.ContentLength > maxBytes {
rq.refuse(refusal{
status: http.StatusBadGateway,
action: requestlog.ActionTooLarge,
limit: "SWWAF_RESPONSE_MAX_BYTES",
})
return errResponseTooLarge
}
// Go's server adds a Content-Type it guesses from the body to a
// response whose headers have no Content-Type key. The key with no
// value sends none, as the app sent none.
if res.Header.Get("Content-Type") == "" {
rq.out.Header()["Content-Type"] = nil
}
res.Body = &responseBody{body: limitBody(res.Body, maxBytes), rq: rq}
rq.startClientResponseTimeout()
return nil
}
// answerError is ReverseProxy's ErrorHandler: the request could not be
// passed to the app, or the app's answer cannot be passed on.
func (rq *request) answerError(_ http.ResponseWriter, _ *http.Request, err error) {
if rq.upgraded != nil {
// The app switched protocols, but the switch was not passed on,
// and ReverseProxy leaves the app's connection open when it
// refuses it.
_ = rq.upgraded.Close()
}
refused := rq.refused.Load()
if refused == nil {
if rq.in.Context().Err() != nil {
return // the client has gone, and there is no one to answer
}
rq.h.processLog.Warn("request to the app failed", "error", err.Error())
refused = &refusal{
status: http.StatusBadGateway,
action: requestlog.ActionUpstreamError,
}
}
rq.answer(*refused)
}
// answer sends smallwebwaf's own answer, unless the response has already
// started, and records the refusal for the log line.
func (rq *request) answer(r refusal) {
rq.refused.CompareAndSwap(nil, &r)
if rq.out.status != 0 {
return // too late to answer: the connection can only be cut
}
if r.status == 0 {
// SWWAF_BAN_RESPONSE is close. This panic has Go's server close
// the connection without an answer, and log nothing; the log line
// is still written as the handler returns.
panic(http.ErrAbortHandler)
}
// A client found too slow is read no more; any other may go on
// sending until its time is up, so that Go's server can read the
// rest of the body and end the request cleanly.
deadline := rq.clientRequestDeadline()
if r.status == http.StatusRequestTimeout {
deadline = time.Now()
}
rq.stopReadingBody(deadline)
timeout := rq.h.config.ClientResponseTimeout
if timeout > 0 {
_ = rq.rc.SetWriteDeadline(time.Now().Add(timeout))
}
http.Error(rq.out, http.StatusText(r.status), r.status)
}
// refuse records r, unless an earlier refusal was, and ends the request
// to the app, if one was made: smallwebwaf reads the body of a request
// it answers itself too.
func (rq *request) refuse(r refusal) {
rq.refused.CompareAndSwap(nil, &r)
if rq.cancel != nil {
rq.cancel()
}
}
// finish ends the request's timeouts, counts it in the metrics and writes
// its log line.
func (rq *request) finish() {
rq.stopTimers()
refused := rq.refused.Load()
if refused == nil {
rq.stopReadingBody(rq.clientRequestDeadline())
}
line := &rq.line
line.Status = rq.out.status
line.ResponseBytes = rq.out.bytes
header := rq.out.Header()
line.ResponseContentType = header.Get("Content-Type")
line.CacheControl = header.Get("Cache-Control")
line.Location = header.Get("Location")
line.RequestBytes = rq.requestBytes()
// limit is the setting whose size or time limit the request passed.
var limit string
switch {
case refused != nil:
line.Action = refused.action
limit = refused.limit
case errors.Is(rq.out.err, os.ErrDeadlineExceeded):
// The client took longer than SWWAF_CLIENT_RESPONSE_TIMEOUT to
// take the response.
line.Action = requestlog.ActionTimedOut
limit = "SWWAF_CLIENT_RESPONSE_TIMEOUT"
case !rq.complete && (rq.out.err != nil || rq.in.Context().Err() != nil):
line.Aborted = true
}
now := time.Now()
duration := now.Sub(rq.start)
line.DurationTotal = requestlog.Milliseconds(duration)
line.DurationChecks = timing(rq.start, rq.checked)
var upstreamDuration time.Duration
if !rq.upstreamStart.IsZero() {
upstreamDuration = now.Sub(rq.upstreamStart)
line.DurationUpstreamTotal = new(requestlog.Milliseconds(upstreamDuration))
rq.mu.Lock()
line.DurationUpstreamConnect = timing(rq.upstreamStart, rq.connected)
line.DurationUpstreamFirstByte = timing(rq.upstreamStart, rq.answerStarted)
rq.mu.Unlock()
}
// Counted before the log line is written, so that the metrics count
// every request whose line is out.
rq.h.metrics.RequestEnded(line, limit, duration, upstreamDuration)
err := requestlog.Write(rq.h.requestLog, line)
if err != nil {
rq.h.processLog.Error("writing the request log failed", "error", err.Error())
}
}
// timing is the time from start to end in milliseconds, for one of the
// log line's timings, or nil when end is zero: what it times never
// happened.
func timing(start, end time.Time) *float64 {
if end.IsZero() {
return nil
}
return new(requestlog.Milliseconds(end.Sub(start)))
}
// addToHistory adds the request, which has ended, to its client's
// history, and counts its offences in the metrics, and then the lookup's
// answer about the client, as answerAtTheEnd gives it, to that history and
// to the notes of the bans on its netblock: an answer may have come
// before either was there, and one from GeoJS that comes later is added
// when it comes.
func (rq *request) addToHistory() {
forwarded := !rq.upstreamStart.IsZero()
request := ratelimit.Request{
Forwarded: forwarded,
Refused: !forwarded && rq.refused.Load() != nil,
Status: rq.out.status,
RequestBytes: rq.requestBytes(),
ResponseBytes: rq.out.bytes,
BrokeLimit: rq.line.Offence == requestlog.OffenceLimit,
Attack: rq.attack,
RuleBlocked: rq.ruleBlocked,
WAFBlocked: rq.wafBlocked,
TokenRefused: rq.tokenRefused,
}
rq.h.limiter.AddToHistory(rq.h.clientGroup(rq.client), rq.h.now(), request)
rq.h.metrics.Offences(request)
answer, found := rq.answerAtTheEnd()
if found {
rq.h.addLookup(answer)
}
}
// countAnomalies counts the request, which has ended, and its bytes, as
// countedBytes gives them, for the anomaly thresholds, whatever was done
// with it: a request refused, one from a client in SWWAF_ALLOW_NETS or
// SWWAF_RATE_LIMIT_EXEMPT_NETS, and one for a path in
// SWWAF_RATE_LIMIT_EXEMPT_PATHS are counted too. It is counted for its
// client's AS number when answerAtTheEnd gives one. With every anomaly
// threshold off, the default, it does nothing.
func (rq *request) countAnomalies() {
if !anomalyThresholdsSet(rq.h.config) {
return
}
answer, _ := rq.answerAtTheEnd()
rq.h.anomalies.Count(rq.h.now(), anomaly.Request{
Client: rq.client,
ClientGroup: rq.h.clientGroup(rq.client),
ASN: answer.ASN,
ASName: answer.ASName,
Country: answer.Country,
Bytes: rq.countedBytes(),
})
}
// anomalyThresholdsSet reports whether any anomaly threshold is set.
func anomalyThresholdsSet(cfg *config.Config) bool {
off := anomaly.Thresholds{}
return cfg.AnomalyClient != off || cfg.AnomalyNet != off || cfg.AnomalyASN != off ||
cfg.AnomalyTotal != off || cfg.AnomalyWatch != off
}
// answerAtTheEnd returns, for a client that was looked up, the lookup's
// answer about it as the request ends, and whether there is one: the
// lookup database's, which was there at once, or the one GeoJS has given
// by then, which a request does not wait for unless a setting needs it.
func (rq *request) answerAtTheEnd() (lookup.Answer, bool) {
if !rq.lookedUp {
return lookup.Answer{}, false
}
if rq.h.config.LookupSource == "file" {
return rq.lookupAnswer, true
}
return rq.h.geojs.Kept(rq.h.clientGroup(rq.client))
}
// requestBytes is how many bytes of the request's body have been read.
func (rq *request) requestBytes() int64 {
if rq.body == nil {
return 0
}
return rq.body.bytes.Load()
}
// clientRequestDeadline is when the client must have sent its whole
// request, or zero when SWWAF_CLIENT_REQUEST_TIMEOUT is off.
func (rq *request) clientRequestDeadline() time.Time {
timeout := rq.h.config.ClientRequestTimeout
if timeout == 0 {
return time.Time{}
}
return rq.start.Add(timeout)
}
// stopReadingBody ends, at deadline, the reading of a client body that has
// not arrived whole: Go's server then reads no more of it, and closes the
// connection after the answer.
func (rq *request) stopReadingBody(deadline time.Time) {
if rq.body == nil || rq.body.received.Load() {
return
}
_ = rq.rc.SetReadDeadline(deadline)
}
// startRequestTimers starts the timeouts that run while the request goes
// to the app: SWWAF_CLIENT_REQUEST_TIMEOUT until the client has sent its
// whole body, and SWWAF_UPSTREAM_REQUEST_TIMEOUT until the app has been
// sent the whole request.
func (rq *request) startRequestTimers() {
rq.mu.Lock()
defer rq.mu.Unlock()
if rq.body != nil && rq.h.config.ClientRequestTimeout > 0 {
rq.clientRequestTimer = time.AfterFunc(
time.Until(rq.clientRequestDeadline()), func() {
rq.requestTimedOut("SWWAF_CLIENT_REQUEST_TIMEOUT")
})
}
timeout := rq.h.config.UpstreamRequestTimeout
if timeout > 0 {
rq.upstreamRequestTimer = time.AfterFunc(timeout, func() {
rq.requestTimedOut("SWWAF_UPSTREAM_REQUEST_TIMEOUT")
})
}
}
// requestTimedOut is called when limit, SWWAF_CLIENT_REQUEST_TIMEOUT or
// SWWAF_UPSTREAM_REQUEST_TIMEOUT, runs out while the request is still on
// its way to the app. The answer names the side smallwebwaf was waiting
// on at that moment: 408 when it was waiting for the client to send more
// of its body, 504 when it was waiting for the app to be reached or to
// take what it had.
func (rq *request) requestTimedOut(limit string) {
rq.mu.Lock()
defer rq.mu.Unlock()
if rq.timersStopped {
return
}
if rq.body == nil || !rq.body.waiting.Load() {
// Once the app has answered, the transport, ReverseProxy and Go's
// server each close the client's body, and closing it reads what
// is left of a body under 256 KiB without requestBody.Read, so
// waiting is false while that read waits for the client. That
// read ends now, before refuse: should smallwebwaf still answer
// itself, answer then sets the deadline it gives its own answers.
if !rq.answerStarted.IsZero() {
rq.stopReadingBody(time.Now())
}
rq.refuse(refusal{
status: http.StatusGatewayTimeout,
action: requestlog.ActionTimedOut,
limit: limit,
})
return
}
rq.refuse(refusal{
status: http.StatusRequestTimeout,
action: requestlog.ActionTimedOut,
limit: limit,
})
// The transport gives up on the app only once its Read of the
// client's body returns, so that Read is ended now. The lock keeps
// this from reaching the connection after the request is handled.
_ = rq.rc.SetReadDeadline(time.Now())
}
// bodyReceived is called once the client has sent its whole body.
func (rq *request) bodyReceived() {
rq.mu.Lock()
defer rq.mu.Unlock()
stopTimer(rq.clientRequestTimer)
}
// gotConn is called once there is a connection to the app, a new one or
// one kept open from an earlier request.
func (rq *request) gotConn(httptrace.GotConnInfo) {
rq.mu.Lock()
defer rq.mu.Unlock()
rq.connected = time.Now()
}
// gotFirstResponseByte is called once the first byte of the app's answer
// has arrived.
func (rq *request) gotFirstResponseByte() {
rq.mu.Lock()
defer rq.mu.Unlock()
rq.answerStarted = time.Now()
}
// wroteRequest is called once the app has been sent the whole request:
// the request timeouts end and SWWAF_UPSTREAM_RESPONSE_TIMEOUT starts.
func (rq *request) wroteRequest(info httptrace.WroteRequestInfo) {
if info.Err != nil {
return // the transport gives up, or tries again
}
rq.mu.Lock()
defer rq.mu.Unlock()
if rq.timersStopped {
return
}
stopTimer(rq.clientRequestTimer)
stopTimer(rq.upstreamRequestTimer)
rq.requestSent = time.Now()
timeout := rq.h.config.UpstreamResponseTimeout
if timeout > 0 {
rq.upstreamResponseTimer = time.AfterFunc(timeout, rq.responseTimedOut)
}
}
// responseTimedOut is called when SWWAF_UPSTREAM_RESPONSE_TIMEOUT runs out
// before the app has sent its whole answer.
func (rq *request) responseTimedOut() {
rq.mu.Lock()
defer rq.mu.Unlock()
if !rq.timersStopped {
rq.refuse(refusal{
status: http.StatusGatewayTimeout,
action: requestlog.ActionTimedOut,
limit: "SWWAF_UPSTREAM_RESPONSE_TIMEOUT",
})
}
}
// responseReceived is called once the app has sent its whole answer. An
// app may answer before the client has sent its whole body, as with a 404
// it sends without reading it. The timeouts then run on: until the
// transport's read of the body returns, Go's server cannot send the
// answer, and SWWAF_CLIENT_REQUEST_TIMEOUT is what ends that read for a
// client that stops sending.
func (rq *request) responseReceived() {
rq.complete = true
if rq.body != nil && !rq.body.received.Load() {
return
}
rq.stopTimers()
}
// startClientResponseTimeout sets SWWAF_CLIENT_RESPONSE_TIMEOUT on the
// connection to the client: the response must reach the client within it
// of the end of the request, or of now if the app answers before it has
// the whole request.
func (rq *request) startClientResponseTimeout() {
timeout := rq.h.config.ClientResponseTimeout
if timeout == 0 {
return
}
from := rq.sentAt()
if from.IsZero() {
from = time.Now()
}
_ = rq.rc.SetWriteDeadline(from.Add(timeout))
}
// sentAt is when the app had been sent the whole request, or zero.
func (rq *request) sentAt() time.Time {
rq.mu.Lock()
defer rq.mu.Unlock()
return rq.requestSent
}
// stopTimers stops the request's timeouts and keeps any from starting
// later: the app's answer is complete, the connection upgraded, or the
// request handled.
func (rq *request) stopTimers() {
rq.mu.Lock()
defer rq.mu.Unlock()
rq.timersStopped = true
stopTimer(rq.clientRequestTimer)
stopTimer(rq.upstreamRequestTimer)
stopTimer(rq.upstreamResponseTimer)
}
// stopTimer stops t, which is nil when its timeout is off.
func stopTimer(t *time.Timer) {
if t != nil {
t.Stop()
}
}
+55
View File
@@ -0,0 +1,55 @@
package proxy
import (
"io"
"net/http"
"net/http/httptest"
"testing"
"sneak.berlin/go/smallwebwaf/internal/config"
)
func TestAnAnswerWithoutAContentTypeGetsNone(t *testing.T) {
t.Parallel()
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
rq := &request{
h: &handler{config: &config.Config{}},
out: &responseWriter{ResponseWriter: w},
}
app := &http.Response{
StatusCode: http.StatusOK,
Header: http.Header{},
Body: http.NoBody,
}
err := rq.modifyResponse(app)
if err != nil {
t.Errorf("modifyResponse: %v", err)
}
// The headers go out with this, the first part of the body,
// which Go's server would guess a Content-Type from.
_, _ = io.WriteString(w, "<!doctype html><title>page</title>")
}))
t.Cleanup(srv.Close)
req, err := http.NewRequestWithContext(t.Context(), http.MethodGet, srv.URL,
http.NoBody)
if err != nil {
t.Fatalf("new request: %v", err)
}
res, err := srv.Client().Do(req)
if err != nil {
t.Fatalf("get: %v", err)
}
_ = res.Body.Close()
if res.Header.Values("Content-Type") != nil {
t.Errorf("client got Content-Type %q, want none",
res.Header.Get("Content-Type"))
}
}
@@ -1,8 +1,8 @@
package discriminator_test package proxy_test
import ( import (
"encoding/json"
"io" "io"
"maps"
"math" "math"
"net/http" "net/http"
"reflect" "reflect"
@@ -11,7 +11,7 @@ import (
"testing" "testing"
"time" "time"
"sneak.berlin/go/smallwebwaf/internal/discriminator" "sneak.berlin/go/smallwebwaf/internal/proxy"
"sneak.berlin/go/smallwebwaf/internal/ratelimit" "sneak.berlin/go/smallwebwaf/internal/ratelimit"
"sneak.berlin/go/smallwebwaf/internal/requestlog" "sneak.berlin/go/smallwebwaf/internal/requestlog"
) )
@@ -19,8 +19,8 @@ import (
const ( const (
// requestIDHeader carries the request's id. // requestIDHeader carries the request's id.
requestIDHeader = "X-Request-ID" requestIDHeader = "X-Request-ID"
// instance is the SWW_INSTANCE_NAME a test sets. // instance is the SWWAF_INSTANCE_NAME a test sets.
instance = "fsn1app1/blog" instance = "fsn1app1/gitea"
// ipv6Client is a client on IPv6, and ipv6Group the netblock the rate // ipv6Client is a client on IPv6, and ipv6Group the netblock the rate
// limits count it as. // limits count it as.
ipv6Client = "2001:db8::7" ipv6Client = "2001:db8::7"
@@ -42,6 +42,9 @@ func TestLogLineHasEachFieldWhereItApplies(t *testing.T) {
return return
} }
w.Header().Set("Content-Type", "text/html")
w.Header().Set("Cache-Control", "no-store")
w.Header().Set("Location", "/elsewhere")
w.WriteHeader(http.StatusFound) w.WriteHeader(http.StatusFound)
_, _ = io.WriteString(w, "moved") _, _ = io.WriteString(w, "moved")
}) })
@@ -67,7 +70,7 @@ func TestLogLineHasEachFieldWhereItApplies(t *testing.T) {
// A request's log line can come after its answer: each is waited for // A request's log line can come after its answer: each is waited for
// before the next request, so that the lines are in order. // before the next request, so that the lines are in order.
full := out.endedLines(t, 1)[0] full := out.requestLines(t, 1)[0]
// This one comes from 127.0.0.1, which the rate limits do not count, // This one comes from 127.0.0.1, which the rate limits do not count,
// with a body of 4 bytes whose length it does not announce, so that its // with a body of 4 bytes whose length it does not announce, so that its
@@ -78,7 +81,7 @@ func TestLogLineHasEachFieldWhereItApplies(t *testing.T) {
"Transfer-Encoding: chunked\r\n\r\n4\r\nbody\r\n0\r\n\r\n") "Transfer-Encoding: chunked\r\n\r\n4\r\nbody\r\n0\r\n\r\n")
wantStatus(t, readResponse(t, conn), http.StatusNoContent) wantStatus(t, readResponse(t, conn), http.StatusNoContent)
bare := out.endedLines(t, 2)[1] bare := out.requestLines(t, 2)[1]
wantFullLine(t, full) wantFullLine(t, full)
wantBareLine(t, bare) wantBareLine(t, bare)
@@ -105,23 +108,24 @@ func wantFullLine(t *testing.T, line logLine) {
headers := map[string]string{"accept": "text/html", "x-custom": "one, two"} headers := map[string]string{"accept": "text/html", "x-custom": "one, two"}
want := withTimings(line, requestlog.Line{ want := withTimings(line, requestlog.Line{
Type: requestType, DiscriminatorLine: requestlog.DiscriminatorLineReport, Type: requestType, Time: line.Time, Instance: instance,
Time: line.Time, Instance: instance,
ClientIP: ipv6Client, Method: http.MethodPost, Scheme: secure, ClientIP: ipv6Client, Method: http.MethodPost, Scheme: secure,
Host: appHost, Path: "/full", Protocol: protocol, Host: appHost, Path: "/full", Protocol: protocol,
Status: http.StatusFound, RequestBytes: 3, ResponseBytes: 5, Status: http.StatusFound, RequestBytes: 3, ResponseBytes: 5,
RequestID: line.RequestID, PeerIP: localhost, RequestID: "from-traefik", PeerIP: localhost,
ForwardedFor: "198.51.100.7, " + ipv6Client, ClientGroup: ipv6Group, ForwardedFor: "198.51.100.7, " + ipv6Client, ClientGroup: ipv6Group,
ContentType: "application/x-www-form-urlencoded", ContentLength: 3, ContentType: "application/x-www-form-urlencoded", ContentLength: 3,
RequestHeaders: headers, HasAuthorization: true, HasCookie: true, RequestHeaders: headers, HasAuthorization: true, HasCookie: true,
ResponseContentType: "text/html", UpstreamStatus: http.StatusFound,
CacheControl: "no-store", Location: "/elsewhere",
Action: requestlog.ActionForward, Action: requestlog.ActionForward,
// Its 3 bytes in and 5 out, each way counted by default. // Its 3 bytes in and 5 out, each way counted by default.
Counts: ratelimit.Counts{ Counts: ratelimit.Counts{
Minute: 1, Hour: 1, Day: 1, MinuteBytes: 8, HourBytes: 8, DayBytes: 8, Minute: 1, Hour: 1, Day: 1, MinuteBytes: 8, HourBytes: 8, DayBytes: 8,
}, },
}) })
if !reflect.DeepEqual(line.Line, want) || line.RequestID == "from-traefik" { if !reflect.DeepEqual(line.Line, want) {
t.Errorf("log line\n%+v\nwant\n%+v, with a new request id", line.Line, want) t.Errorf("log line\n%+v\nwant\n%+v", line.Line, want)
} }
} }
@@ -131,13 +135,12 @@ func wantBareLine(t *testing.T, line logLine) {
t.Helper() t.Helper()
want := withTimings(line, requestlog.Line{ want := withTimings(line, requestlog.Line{
Type: requestType, DiscriminatorLine: requestlog.DiscriminatorLineReport, Type: requestType, Time: line.Time, Instance: instance,
Time: line.Time, Instance: instance,
ClientIP: localhost, Method: http.MethodPost, Scheme: plain, ClientIP: localhost, Method: http.MethodPost, Scheme: plain,
Host: appHost, Path: "/bare", Protocol: protocol, Host: appHost, Path: "/bare", Protocol: protocol,
Status: http.StatusNoContent, RequestBytes: 4, RequestID: line.RequestID, Status: http.StatusNoContent, RequestBytes: 4, RequestID: line.RequestID,
PeerIP: localhost, ClientGroup: localhost + "/32", PeerIP: localhost, ClientGroup: localhost + "/32",
Action: requestlog.ActionForward, UpstreamStatus: http.StatusNoContent, Action: requestlog.ActionForward,
}) })
if !reflect.DeepEqual(line.Line, want) || line.RequestID == "" { if !reflect.DeepEqual(line.Line, want) || line.RequestID == "" {
t.Errorf("log line\n%+v\nwant\n%+v, with a request id", line.Line, want) t.Errorf("log line\n%+v\nwant\n%+v, with a request id", line.Line, want)
@@ -145,7 +148,8 @@ func wantBareLine(t *testing.T, line logLine) {
for _, name := range []string{ for _, name := range []string{
"forwarded_for", "content_type", "content_length", "request_headers", "forwarded_for", "content_type", "content_length", "request_headers",
"has_authorization", "has_cookie", "response_content_type", "counts", "has_authorization", "has_cookie", "websocket", "response_content_type",
"cache_control", "location", "counts",
} { } {
_, present := line.fields[name] _, present := line.fields[name]
if present { if present {
@@ -158,6 +162,8 @@ func wantBareLine(t *testing.T, line logLine) {
func withTimings(line logLine, want requestlog.Line) requestlog.Line { func withTimings(line logLine, want requestlog.Line) requestlog.Line {
want.DurationTotal = line.DurationTotal want.DurationTotal = line.DurationTotal
want.DurationChecks = line.DurationChecks want.DurationChecks = line.DurationChecks
want.DurationUpstreamConnect = line.DurationUpstreamConnect
want.DurationUpstreamFirstByte = line.DurationUpstreamFirstByte
want.DurationUpstreamTotal = line.DurationUpstreamTotal want.DurationUpstreamTotal = line.DurationUpstreamTotal
return want return want
@@ -182,7 +188,7 @@ func TestHasAuthorizationAndHasCookieEachComeFromTheirOwnHeader(t *testing.T) {
req.Header.Set(tc.header, "secret") req.Header.Set(tc.header, "secret")
wantStatus(t, do(t, req), http.StatusOK) wantStatus(t, do(t, req), http.StatusOK)
line := out.endedLine(t) line := out.requestLine(t)
_, otherPresent := line.fields[tc.other] _, otherPresent := line.fields[tc.other]
if line.fields[tc.field] != true || otherPresent { if line.fields[tc.field] != true || otherPresent {
@@ -193,20 +199,81 @@ func TestHasAuthorizationAndHasCookieEachComeFromTheirOwnHeader(t *testing.T) {
} }
} }
func TestRequestIDAndSchemeComeOnlyFromATrustedProxy(t *testing.T) {
t.Parallel()
const sentID = "from-traefik"
sent := http.Header{requestIDHeader: {sentID}, forwardedProto: {secure}}
trusted := map[string]string{trustedProxies: trustLocalhost}
for _, tc := range []struct {
name string
env map[string]string
header http.Header
// wantID is the request id logged, "" for a new one.
wantID, wantScheme string
}{
{"a trusted proxy's are kept", trusted, sent, sentID, secure},
{"without them, the id is new and the scheme http", trusted, nil, "", plain},
{"another peer's are replaced", nil, sent, "", plain},
} {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
received := make(chan string, 2)
app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
received <- r.Header.Get(requestIDHeader)
})
addr, out := startProxy(t, app.URL, tc.env)
// Two requests, so that two new ids can be told apart.
ids := make([]string, 0, 2)
for i := range 2 {
req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
maps.Copy(req.Header, tc.header)
wantStatus(t, do(t, req), http.StatusOK)
line := out.requestLines(t, i+1)[i]
ids = append(ids, line.RequestID)
got := <-received
if line.RequestID != got || line.Scheme != tc.wantScheme {
t.Errorf("log line has request_id %q and scheme %q, and the "+
"app received id %q; want the same id and scheme %q",
line.RequestID, line.Scheme, got, tc.wantScheme)
}
}
switch {
case tc.wantID != "" && (ids[0] != tc.wantID || ids[1] != tc.wantID):
t.Errorf("request ids %q, want %q", ids, tc.wantID)
case tc.wantID == "" && (slices.Contains(ids, sentID) ||
slices.Contains(ids, "") || ids[0] == ids[1]):
t.Errorf("request ids %q, want two new ones", ids)
}
})
}
}
func TestTimingsAreInOrder(t *testing.T) { func TestTimingsAreInOrder(t *testing.T) {
t.Parallel() t.Parallel()
const denied = "192.0.2.50" // in SWW_DENY_NETS const denied = "192.0.2.50" // in SWWAF_DENY_NETS
app := startApp(t, func(w http.ResponseWriter, _ *http.Request) { app := startApp(t, func(w http.ResponseWriter, _ *http.Request) {
// The pause sets the times apart; a hold-up of the test only lengthens // The pauses set the times apart; a hold-up of the test only
// it. // lengthens them.
time.Sleep(time.Millisecond)
w.WriteHeader(http.StatusOK)
_ = http.NewResponseController(w).Flush()
time.Sleep(time.Millisecond) time.Sleep(time.Millisecond)
_, _ = io.WriteString(w, "done") _, _ = io.WriteString(w, "done")
}) })
addr, out := startProxy(t, app.URL, map[string]string{
addr, out, server := startProxyWithClock(t, app.URL, "", time.Now, map[string]string{
trustedProxies: trustLocalhost, trustedProxies: trustLocalhost,
denyNets: denied, denyNets: denied,
}) })
@@ -214,19 +281,20 @@ func TestTimingsAreInOrder(t *testing.T) {
// Each log line is waited for before the next request, so that the // Each log line is waited for before the next request, so that the
// lines are in order. // lines are in order.
wantStatus(t, get(t, addr, "/"), http.StatusOK) wantStatus(t, get(t, addr, "/"), http.StatusOK)
forwarded := out.endedLines(t, 1)[0] forwarded := out.requestLines(t, 1)[0]
req := newRequest(t, http.MethodGet, addr, "/", http.NoBody) req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
req.Header.Set(forwardedFor, denied) req.Header.Set(forwardedFor, denied)
wantStatus(t, do(t, req), http.StatusForbidden) wantStatus(t, do(t, req), http.StatusForbidden)
refused := out.endedLines(t, 2)[1] refused := out.requestLines(t, 2)[1]
wantStatus(t, get(t, server.Addr, discriminator.HealthPath), http.StatusOK) wantStatus(t, get(t, addr, proxy.HealthPath), http.StatusOK)
health := out.endedLines(t, 3)[2] health := out.requestLines(t, 3)[2]
// A request passed to the app has every timing; one refused, none of // A request passed to the app has every timing; one refused, none of
// the app's; the health check, which runs no check, only the total. // the app's; the health check, which runs no check, only the total.
wantTimings(t, forwarded, "duration_total", "duration_checks", wantTimings(t, forwarded, "duration_total", "duration_checks",
"duration_upstream_connect", "duration_upstream_first_byte",
"duration_upstream_total") "duration_upstream_total")
wantTimings(t, refused, "duration_total", "duration_checks") wantTimings(t, refused, "duration_total", "duration_checks")
wantTimings(t, health, "duration_total") wantTimings(t, health, "duration_total")
@@ -239,12 +307,17 @@ func TestTimingsAreInOrder(t *testing.T) {
// exact. // exact.
total := microseconds(forwarded.DurationTotal) total := microseconds(forwarded.DurationTotal)
checks := microseconds(*forwarded.DurationChecks) checks := microseconds(*forwarded.DurationChecks)
connect := microseconds(*forwarded.DurationUpstreamConnect)
firstByte := microseconds(*forwarded.DurationUpstreamFirstByte)
upstream := microseconds(*forwarded.DurationUpstreamTotal) upstream := microseconds(*forwarded.DurationUpstreamTotal)
// The checks end before the request is handed to the app. // The checks end before the request is handed to the app, and the
if checks+upstream > total { // connection comes before the answer, which the app ends after a
t.Errorf("timings in microseconds: total %d, checks %d, upstream total %d", // pause.
total, checks, upstream) if checks+upstream > total || connect >= firstByte || firstByte >= upstream {
t.Errorf("timings in microseconds: total %d, checks %d, connect %d, "+
"first byte %d, upstream total %d", total, checks, connect, firstByte,
upstream)
} }
if *refused.DurationChecks > refused.DurationTotal { if *refused.DurationChecks > refused.DurationTotal {
@@ -273,49 +346,26 @@ func wantTimings(t *testing.T, line logLine, want ...string) {
} }
} }
// wantHeuristic checks that line names heuristic as the one that refused the
// request, with figures, a JSON object. A heuristic of "" with figures "null" is
// a line that names none.
func wantHeuristic(t *testing.T, line logLine, heuristic, figures string) {
t.Helper()
if line.Heuristic != heuristic ||
!reflect.DeepEqual(line.HeuristicFigures, decodeFigures(t, figures)) {
t.Errorf("log line has heuristic %q with heuristic_figures %v, want %q with %s",
line.Heuristic, line.HeuristicFigures, heuristic, figures)
}
}
// wantAfterAnswerHeuristic checks after_answer_heuristic and
// after_answer_heuristic_figures as wantHeuristic checks heuristic and
// heuristic_figures.
func wantAfterAnswerHeuristic(t *testing.T, line logLine, heuristic, figures string) {
t.Helper()
if line.AfterAnswerHeuristic != heuristic ||
!reflect.DeepEqual(line.AfterAnswerHeuristicFigures, decodeFigures(t, figures)) {
t.Errorf("log line has after_answer_heuristic %q with "+
"after_answer_heuristic_figures %v, want %q with %s",
line.AfterAnswerHeuristic, line.AfterAnswerHeuristicFigures, heuristic, figures)
}
}
// decodeFigures decodes figures, a JSON object of a heuristic's figures, as
// the log line's figures are decoded.
func decodeFigures(t *testing.T, figures string) map[string]any {
t.Helper()
var decoded map[string]any
err := json.Unmarshal([]byte(figures), &decoded)
if err != nil {
t.Fatalf("decode %s: %v", figures, err)
}
return decoded
}
// microseconds is a timing in whole microseconds. // microseconds is a timing in whole microseconds.
func microseconds(milliseconds float64) int64 { func microseconds(milliseconds float64) int64 {
return int64(math.Round(milliseconds * 1000)) return int64(math.Round(milliseconds * 1000))
} }
func TestLogsAnUpgradedConnection(t *testing.T) {
t.Parallel()
app := startApp(t, echoAfterUpgrade)
addr, out := startProxy(t, app.URL, nil)
conn := dial(t, addr)
send(t, conn, "GET /socket HTTP/1.1\r\nHost: app\r\n"+
"Connection: Upgrade\r\nUpgrade: websocket\r\n\r\n")
wantStatus(t, readResponse(t, conn), http.StatusSwitchingProtocols)
_ = conn.Close()
line := out.requestLine(t)
if line.fields["websocket"] != true {
t.Errorf("log line has websocket %v, want true", line.fields["websocket"])
}
}
@@ -1,4 +1,4 @@
package discriminator_test package proxy_test
import ( import (
"net/http" "net/http"
@@ -34,17 +34,16 @@ func TestEachRuleAction(t *testing.T) {
line := s.get(client, http.StatusOK, requestlog.ActionForward) line := s.get(client, http.StatusOK, requestlog.ActionForward)
wantRuleIDs(t, line, "noted") wantRuleIDs(t, line, "noted")
// A block rule refuses with 403, whatever SWW_BAN_RESPONSE is, and // A block rule refuses with 403, whatever SWWAF_BAN_RESPONSE is, and
// bans no one. // bans no one.
line = s.request(client, "/blocked", http.StatusForbidden, line = s.request(client, "/blocked", http.StatusForbidden,
requestlog.ActionBlockedByBlockRule) requestlog.ActionRuleBlocked)
wantRuleIDs(t, line, "noted", "blocked") wantRuleIDs(t, line, "noted", "blocked")
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
// A ban rule refuses with SWW_BAN_RESPONSE, and bans the client for // A ban rule refuses with SWWAF_BAN_RESPONSE, and bans the client for
// seven days, the default. // seven days, the default.
line = s.request(client, "/.env", http.StatusTooManyRequests, line = s.request(client, "/.env", http.StatusTooManyRequests, requestlog.ActionBanned)
requestlog.ActionTemporarilyBanned)
wantRuleIDs(t, line, "noted", "probe") wantRuleIDs(t, line, "noted", "probe")
if line.BanExpires != requestlog.FormatTime(start.Add(7*24*time.Hour)) { if line.BanExpires != requestlog.FormatTime(start.Add(7*24*time.Hour)) {
@@ -83,7 +82,7 @@ func TestEachRuleAction(t *testing.T) {
// against the rules, and makes the ban permanent. // against the rules, and makes the ban permanent.
clk.advance(time.Hour) clk.advance(time.Hour)
line = s.get(client, http.StatusTooManyRequests, requestlog.ActionPermanentlyBanned) line = s.get(client, http.StatusTooManyRequests, requestlog.ActionBanned)
wantRuleIDs(t, line) wantRuleIDs(t, line)
if line.BanExpires != permanent { if line.BanExpires != permanent {
@@ -91,37 +90,7 @@ func TestEachRuleAction(t *testing.T) {
} }
clk.advance(365 * 24 * time.Hour) clk.advance(365 * 24 * time.Hour)
s.get(client, http.StatusTooManyRequests, requestlog.ActionPermanentlyBanned) 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.ActionBlockedByBlockRule), "exploitsignature")
wantTags(t, s.get(client, http.StatusOK, requestlog.ActionForward))
}
func TestRuleRefusalNamesItsHeuristicAndTheRule(t *testing.T) {
t.Parallel()
s, _, _ := startWithClock(t, "", map[string]string{
rulesDir: writeRules(t, "noted path log ^/\n"+testRules),
})
line := s.request(client, "/blocked", http.StatusForbidden,
requestlog.ActionBlockedByBlockRule)
wantHeuristic(t, line, "rule_files", `{"rule_id": "blocked", "rule_action": "block"}`)
line = s.request(client, "/.env", http.StatusForbidden,
requestlog.ActionTemporarilyBanned)
wantHeuristic(t, line, "rule_files", `{"rule_id": "probe", "rule_action": "ban"}`)
} }
func TestNextClearSignOfAttackAfterABanBansPermanently(t *testing.T) { func TestNextClearSignOfAttackAfterABanBansPermanently(t *testing.T) {
@@ -132,9 +101,8 @@ func TestNextClearSignOfAttackAfterABanBansPermanently(t *testing.T) {
attackBanDuration: "1h", attackBanDuration: "1h",
}) })
// The first probe bans for SWW_ATTACK_BAN_DURATION. // The first probe bans for SWWAF_ATTACK_BAN_DURATION.
line := s.request(client, "/.env", http.StatusForbidden, line := s.request(client, "/.env", http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionTemporarilyBanned)
if line.BanExpires != requestlog.FormatTime(clk.Now().Add(time.Hour)) { if line.BanExpires != requestlog.FormatTime(clk.Now().Add(time.Hour)) {
t.Errorf("log line has ban_expires %q, want an hour on", line.BanExpires) t.Errorf("log line has ban_expires %q, want an hour on", line.BanExpires)
} }
@@ -144,8 +112,7 @@ func TestNextClearSignOfAttackAfterABanBansPermanently(t *testing.T) {
clk.advance(time.Hour) clk.advance(time.Hour)
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
line = s.request(client, "/.env", http.StatusForbidden, line = s.request(client, "/.env", http.StatusForbidden, requestlog.ActionBanned)
requestlog.ActionPermanentlyBanned)
if line.BanExpires != permanent { if line.BanExpires != permanent {
t.Errorf("log line has ban_expires %q, want permanent", line.BanExpires) t.Errorf("log line has ban_expires %q, want permanent", line.BanExpires)
} }
@@ -155,8 +122,8 @@ func TestRulesComeAfterTheOtherChecks(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
allowed = "192.0.2.60" // in SWW_ALLOW_NETS allowed = "192.0.2.60" // in SWWAF_ALLOW_NETS
exempt = "192.0.2.50" // in SWW_RATE_LIMIT_EXEMPT_NETS exempt = "192.0.2.50" // in SWWAF_RATE_LIMIT_EXEMPT_NETS
) )
s, _, server := startWithClock(t, "", map[string]string{ s, _, server := startWithClock(t, "", map[string]string{
@@ -166,15 +133,14 @@ func TestRulesComeAfterTheOtherChecks(t *testing.T) {
rateLimitPerMinute: "1", rateLimitPerMinute: "1",
}) })
// A client in SWW_ALLOW_NETS is not checked. // A client in SWWAF_ALLOW_NETS is not checked.
line := s.request(allowed, "/.env", http.StatusOK, requestlog.ActionForward) line := s.request(allowed, "/.env", http.StatusOK, requestlog.ActionForward)
wantRuleIDs(t, line) wantRuleIDs(t, line)
// A probe over the rate limit breaks the limit before any rule sees // A probe over the rate limit breaks the limit before any rule sees
// it. // it.
s.get(client, http.StatusOK, requestlog.ActionForward) s.get(client, http.StatusOK, requestlog.ActionForward)
line = s.request(client, "/.env", http.StatusForbidden, line = s.request(client, "/.env", http.StatusForbidden, requestlog.ActionRateLimited)
requestlog.ActionClientIsRateLimited)
wantRuleIDs(t, line) wantRuleIDs(t, line)
limitBan := server.Ledger.Bans(netip.MustParsePrefix(client + "/32")) limitBan := server.Ledger.Bans(netip.MustParsePrefix(client + "/32"))
@@ -184,7 +150,7 @@ func TestRulesComeAfterTheOtherChecks(t *testing.T) {
// A client the rate limits do not apply to is still checked. // A client the rate limits do not apply to is still checked.
s.get(exempt, http.StatusOK, requestlog.ActionForward) s.get(exempt, http.StatusOK, requestlog.ActionForward)
s.request(exempt, "/.env", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.request(exempt, "/.env", http.StatusForbidden, requestlog.ActionBanned)
} }
func TestObserveModeLogsWhatTheRulesWouldDo(t *testing.T) { func TestObserveModeLogsWhatTheRulesWouldDo(t *testing.T) {
@@ -196,11 +162,11 @@ func TestObserveModeLogsWhatTheRulesWouldDo(t *testing.T) {
}) })
line := s.request(client, "/blocked", http.StatusOK, requestlog.ActionForward) line := s.request(client, "/blocked", http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionBlockedByBlockRule) wantWouldAction(t, line, requestlog.ActionRuleBlocked)
wantRuleIDs(t, line, "blocked") wantRuleIDs(t, line, "blocked")
line = s.request(client, "/.env", http.StatusOK, requestlog.ActionForward) line = s.request(client, "/.env", http.StatusOK, requestlog.ActionForward)
wantWouldAction(t, line, requestlog.ActionTemporarilyBanned) wantWouldAction(t, line, requestlog.ActionBanned)
wantRuleIDs(t, line, "probe") wantRuleIDs(t, line, "probe")
if line.BanExpires != "" { if line.BanExpires != "" {
@@ -219,30 +185,31 @@ func TestObserveModeLogsWhatTheRulesWouldDo(t *testing.T) {
func TestMetricsCountRuleMatchesAndBansForAnAttack(t *testing.T) { func TestMetricsCountRuleMatchesAndBansForAnAttack(t *testing.T) {
t.Parallel() t.Parallel()
const scraper = "192.0.2.200"
s, _, _ := startWithClock(t, "", map[string]string{ s, _, _ := startWithClock(t, "", map[string]string{
rulesDir: writeRules(t, testRules), rulesDir: writeRules(t, testRules),
metricsToken: token, metricsToken: token,
}) })
s.request(client, "/blocked", http.StatusForbidden, s.request(client, "/blocked", http.StatusForbidden, requestlog.ActionRuleBlocked)
requestlog.ActionBlockedByBlockRule) s.request(client, "/.env", http.StatusForbidden, requestlog.ActionBanned)
s.request(client, "/.env", http.StatusForbidden, requestlog.ActionTemporarilyBanned) s.get(client, http.StatusForbidden, requestlog.ActionBanned)
s.get(client, http.StatusForbidden, requestlog.ActionPermanentlyBanned)
metrics := s.scrape() metrics := s.scrape(scraper)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_rule_matches_total{action="block",instance="app",rule_id="blocked"}`, 1) `smallwebwaf_rule_matches_total{action="block",instance="app",rule_id="blocked"}`, 1)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_rule_matches_total{action="ban",instance="app",rule_id="probe"}`, 1) `smallwebwaf_rule_matches_total{action="ban",instance="app",rule_id="probe"}`, 1)
wantMetric(t, metrics, `sww_rules_loaded{instance="app"}`, 2) wantMetric(t, metrics, `smallwebwaf_rules_loaded{instance="app"}`, 2)
wantMetric(t, metrics, `sww_requests_total{action="blocked_by_block_rule",`+ wantMetric(t, metrics, `smallwebwaf_requests_total{action="rule_blocked",`+
`instance="app",status_class="4xx"}`, 1) `instance="app",status_class="4xx"}`, 1)
wantMetric(t, metrics, wantMetric(t, metrics,
`sww_offences_total{instance="app",kind="blocked_by_block_rule"}`, 1) `smallwebwaf_offences_total{instance="app",kind="rule_blocked"}`, 1)
wantMetric(t, metrics, `sww_offences_total{instance="app",kind="attack"}`, 1) wantMetric(t, metrics, `smallwebwaf_offences_total{instance="app",kind="attack"}`, 1)
wantMetric(t, metrics, `sww_bans_made_total{cause="attack",instance="app"}`, 1) wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="attack",instance="app"}`, 1)
wantMetric(t, metrics, `sww_bans_made_total{cause="limit",instance="app"}`, 0) wantMetric(t, metrics, `smallwebwaf_bans_made_total{cause="limit",instance="app"}`, 0)
wantMetric(t, metrics, `sww_permanent_bans{instance="app"}`, 1) wantMetric(t, metrics, `smallwebwaf_permanent_bans{instance="app"}`, 1)
} }
// writeRules writes content as a rule file into a new directory, and // writeRules writes content as a rule file into a new directory, and
+64
View File
@@ -0,0 +1,64 @@
package proxy
import (
"slices"
"time"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/requestlog"
"sneak.berlin/go/smallwebwaf/internal/rules"
)
// trapPath reports whether the request asks for a path in
// SWWAF_TRAP_PATHS: its path as a path rule sees it, without the query,
// as sent or once percent-decoded, is one of them. Such a request is a
// clear sign of attack, as a ban rule's match is: it bans the client's
// netblock, or in observe mode raises the alert for the ban it would have
// made. The ban's notes give the path as sent.
func (rq *request) trapPath(now time.Time) bool {
path := rules.Path(rq.in)
if !slices.Contains(rq.h.config.TrapPaths, path) &&
!slices.Contains(rq.h.config.TrapPaths, rules.DecodeOnce(path)) {
return false
}
rq.attack = true
rq.banForAttack(now, bans.Notes{TrapPath: path})
return true
}
// checkRules checks the request against the rules of the rule files at
// now, notes the ids of those it matches in the log line, and returns the
// action of the rule that refuses it, ActionRuleBlocked for a block rule
// and ActionBanned for a ban rule, or "" when none does. A ban rule bans
// the client's netblock for a clear sign of attack, or in observe mode
// raises the alert for the ban it would have made. Either rule's match
// is noted as an offence, for the client's history.
func (rq *request) checkRules(now time.Time) string {
matched := rq.h.rules.Match(rq.in)
for _, rule := range matched {
rq.line.RuleIDs = append(rq.line.RuleIDs, rule.ID)
rq.h.metrics.RuleMatched(rule.ID, rule.Action)
}
if len(matched) == 0 {
return ""
}
// Only the last rule matched can refuse the request.
switch last := matched[len(matched)-1]; last.Action {
case rules.ActionBlock:
rq.ruleBlocked = true
return requestlog.ActionRuleBlocked
case rules.ActionBan:
rq.attack = true
rq.banForAttack(now, bans.Notes{RuleID: last.ID, Target: last.Target})
return requestlog.ActionBanned
default:
return ""
}
}
Loaded 100 of 152 files, more files were not shown because too many files have changed in this diff. Show more