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

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

Model: opus-5-5

Dockerfile

@@ -136,10 +136,19 @@ RUN mkdir /etc/sysusers.d \
 # ca-certificates, nix-bin and runit, from Ubuntu's archive. apt fetches
 # them over plain HTTP and checks each one against the archive's signed
 # package lists, so no CA certificates are needed.
-RUN apt-get update \
+#
+# nix-bin depends on xz-utils, whose install links man pages with
+# update-alternatives. The image's dpkg config drops man pages, so each
+# link warns. z-man, read after /etc/dpkg/dpkg.cfg.d/excludes, re-includes
+# the man1 pages for this install alone; the same step deletes them again,
+# so no man page or package is added.
+RUN echo 'path-include=/usr/share/man/man1/*' > /etc/dpkg/dpkg.cfg.d/z-man \
+    && apt-get update \
     && DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
         ca-certificates nix-bin runit \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /etc/dpkg/dpkg.cfg.d/z-man \
+    && 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
 # create; with the setting empty, root's builds run without them.

README.md

@@ -256,14 +256,14 @@ Every setting the code reads, with its default:
 | `SWW_LOOKUP_DB_PATH`                     | empty                                                                          | The IPinfo Lite database file, in its `.mmdb` form, read while the source is `file`.                                                                              |
 | `SWW_LOOKUP_TIMEOUT`                     | `800ms`                                                                        | How long a request waits for its client's first GeoJS answer when a setting needs it, and how long a request to GeoJS may take.                                   |
 | `SWW_ADD_LOOKUP_HEADERS`                 | `false`                                                                        | `true` passes the app the client's AS number and country in `X-Client-ASN` and `X-Client-Country`.                                                                |
-| `SWW_DENIED_COUNTRIES`                   | empty                                                                          | Countries whose clients are refused, such as `cn,ru`.                                                                                                             |
 | `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES`      | empty                                                                          | When set, the only countries whose clients get through; a client the lookup cannot place is refused too.                                                          |
-| `SWW_ASN_LIMIT_PERCENT`                  | empty                                                                          | AS numbers whose clients get a percentage of every request and byte limit, such as `AS14061:50,AS16276:25`.                                                       |
+| `SWW_TAG_LISTS`                          | empty                                                                          | Address lists that each add a tag to their clients' requests, as `name=URL` pairs, such as `torexit=https://example.com/tor.txt`.                                 |
-| `SWW_COUNTRY_LIMIT_PERCENT`              | empty                                                                          | The same by country, such as `cn:25`.                                                                                                                             |
+| `SWW_TAG_DENY`                           | empty                                                                          | Tags whose requests are refused, such as `torexit,country=cn`.                                                                                                    |
-| `SWW_ASN_BYTES_PERCENT`                  | empty                                                                          | A percentage of the byte limits alone for the AS numbers listed, in place of their `SWW_ASN_LIMIT_PERCENT`.                                                       |
+| `SWW_TAG_LIMIT_PERCENT`                  | empty                                                                          | Tags whose clients get a percentage, from 1 to 99, of every request and byte limit, such as `vpn:50,asn=14061:25`; the lowest applies.                            |
-| `SWW_COUNTRY_BYTES_PERCENT`              | empty                                                                          | A percentage of the byte limits alone for the countries listed, in place of their `SWW_COUNTRY_LIMIT_PERCENT`.                                                    |
+| `SWW_ASN_BYTES_PERCENT`                  | empty                                                                          | A percentage of the byte limits alone for the AS numbers listed, in place of their `asn=` tag's percentage.                                                       |
+| `SWW_COUNTRY_BYTES_PERCENT`              | empty                                                                          | A percentage of the byte limits alone for the countries listed, in place of their `country=` tag's percentage.                                                    |
 | `SWW_UNKNOWN_LIMIT_PERCENT`              | `100`                                                                          | The percentage of every limit a client without a country gets.                                                                                                    |
-| `SWW_ASN_LIMIT_PERCENT_URL`              | unset                                                                          | The URL of a text file of `AS<number>:<percent>` lines, fetched like a blocklist; where it and `SWW_ASN_LIMIT_PERCENT` both give a percentage, the lower applies. |
+| `SWW_ASN_LIMIT_PERCENT_URL`              | unset                                                                          | The URL of a text file of `AS<number>:<percent>` lines, fetched like a blocklist; each line counts as an `asn=` tag in `SWW_TAG_LIMIT_PERCENT` (the lowest wins). |
 | `SWW_RULES_DIR`                          | `/etc/sww/rules.d`                                                             | The directory of the rule files, read at start and again when a file there changes.                                                                               |
 | `SWW_RULES_ENABLED`                      | `true`                                                                         | `false` reads no rule file.                                                                                                                                       |
 | `SWW_TRAP_PATHS`                         | empty                                                                          | Paths only scanners ask for, such as `/wp-login.php,/xmlrpc.php`; a request for one bans the client.                                                              |
@@ -413,8 +413,7 @@ services:
             SWW_RATE_LIMIT_PER_HOUR: "600"
             SWW_RATE_LIMIT_PER_DAY: "3000"
             # Hosting networks and one country get a share of those limits.
-            SWW_ASN_LIMIT_PERCENT: AS14061:50,AS16276:25
+            SWW_TAG_LIMIT_PERCENT: asn=14061:50,asn=16276:25,country=cn:25
-            SWW_COUNTRY_LIMIT_PERCENT: cn:25
             # Paths only scanners ask for; one request bans the client.
             SWW_TRAP_PATHS: /wp-login.php,/xmlrpc.php
             # Answer a refused client with 429 rather than 403.
@@ -509,28 +508,31 @@ of the request reaches the app.
 3. The static lists, `SWW_ALLOW_NETS` and `SWW_DENY_NETS`.
 4. The bans.
 5. The lookup of the client's AS number and country.
-6. The country lists.
+6. The tag lists.
-7. The reputation sources.
+7. The country list.
-8. The client's limit percentage, from its AS number, its country or a
+8. The reputation sources.
-   reputation hit.
+9. The tag refusals of `SWW_TAG_DENY`.
-9. The rate limits.
+10. The client's limit percentage, from its tags, its AS number, its country or
-10. The trap paths.
+    a reputation hit.
-11. The rule files.
+11. The rate limits.
-12. The header limits, and then the Core Rule Set.
+12. The trap paths.
-13. A path under `/_sww/` is answered `404`, so that the app never sees that
+13. The rule files.
+14. The header limits, and then the Core Rule Set.
+15. The tag refusals again, so that `exploitsignature` can refuse too.
+16. A path under `/_sww/` is answered `404`, so that the app never sees that
     prefix.
 
 `rproxy` takes the rest, with `discriminator` counting at the end:
 
-14. The request is passed to the app, streaming.
+17. The request is passed to the app, streaming.
-15. After the answer, `rproxy` sends `discriminator` a report with the status
+18. After the answer, `rproxy` sends `discriminator` a report with the status
     and the bytes each way. For an allowed request, `discriminator` counts the
     bytes toward the byte limits and adds the request to the client's history.
 
 A refused visitor is answered with `SWW_BAN_RESPONSE`. A `block` rule or a Core
 Rule Set match answers `403` and bans nobody, since the Core Rule Set has false
 positives; such refusals count toward `SWW_ERROR_BURST_THRESHOLD` instead. A
-request over the header limits of step 12 is answered `431`, and bans nobody
+request over the header limits of step 14 is answered `431`, and bans nobody
 either. `rproxy` itself answers `405` to a method it does not pass on, and the
 status for a size or time limit, such as `413` for a body too large.
 
@@ -549,6 +551,21 @@ status for a size or time limit, such as `413` for a body too large.
   bans. An admin adds, keeps or lifts a ban by editing `bans.json` or through
   the ban endpoints (see [`docs/admin-endpoints.md`](docs/admin-endpoints.md)).
 
+### Request tags
+
+Each request gets tags from what `discriminator` knows of its client, written in
+the `tags` field of its log line:
+
+- `asn=<number>` and `country=<code>`, from the lookup;
+- one tag per list of `SWW_TAG_LISTS` that holds the client, such as `torexit`
+  or `vpn=mullvad`;
+- `crowdsec`, `dnsbl=<zone>` and `abuseipdb`, when that reputation source lists
+  the client;
+- `exploitsignature`, when a rule file or the Core Rule Set matched the request.
+
+`SWW_TAG_DENY` refuses requests by tag, and `SWW_TAG_LIMIT_PERCENT` lowers a
+client's limits by tag. See "Request tags" in [`SPEC.md`](SPEC.md).
+
 ### Attack detection
 
 - The Core Rule Set reads the method, the URL with its query string, and the

SPEC.md

@@ -119,12 +119,14 @@ to them.
 
 ## What happens to a request
 
-`rproxy` runs steps 1, 2 and 14, and sends the report of step 15.
+`rproxy` runs steps 1, 2 and 17, and sends the report of step 18.
-`discriminator` runs steps 3 to 13, and does the counting of step 15. The first
+`discriminator` runs steps 3 to 16, and does the counting of step 18. The first
-step that produces a final answer ends the checks. Step 15 runs for each request
+step that produces a final answer ends the checks. Step 18 runs for each request
 `discriminator` answers with `allow`, `deny` or `close`. `rproxy`'s size and
 time limits apply to the whole exchange. Each step names the section that holds
-its rules.
+its rules. A step that names a heuristic in parentheses runs that heuristic. The
+request log's `heuristic` field gives that name. `refusal_limit` and
+`byte_limits` give theirs in `after_answer_heuristic` instead.
 
 1. `GET /_sww/healthz` is answered at once by `rproxy`, before any check, so a
    health checker never needs an exemption and is never refused.
@@ -141,55 +143,67 @@ its rules.
     - An IPv6 client is its group: the netblock of `SWW_IPV6_GROUP_PREFIX`
       around its address, a /64 by default, since one abuser usually controls a
       whole /64. A client is therefore one IPv4 address or one IPv6 group.
-3. The static lists. A client in `SWW_ALLOW_NETS` skips steps 4 to 12, the byte
+3. The static lists. A client in `SWW_ALLOW_NETS` skips steps 4 to 15, the byte
-   limits and the error burst. A client in `SWW_DENY_NETS` is refused; a client
+   limits and the error burst. A client in `SWW_DENY_NETS` is refused
-   in both lists is let through.
+   (`deny_nets`); a client in both lists is let through.
-4. Bans. A client under a ban is refused (see "Bans").
+4. Bans. A client under a ban is refused (`active_ban`; see "Bans").
 5. The lookup, unless `SWW_LOOKUP_SOURCE` is `off` (see "Lookup of AS number and
    country"). The request goes on at once. It waits for the first GeoJS answer,
    up to `SWW_LOOKUP_TIMEOUT`, only when one of these needs it:
-    - a country list;
+    - the country list;
     - a biased threshold;
+    - `SWW_TAG_DENY` or `SWW_TAG_LIMIT_PERCENT` naming an `asn=` or `country=`
+      tag;
     - `SWW_ADD_LOOKUP_HEADERS`.
 
     A request that ends before the answer comes is logged without it.
 
-6. The country lists (see "Country lists").
+6. The tag lists (`tag_lists`; see "Request tags"). Each list that holds the
-7. The reputation sources (see "Reputation"). A client on a fetched blocklist
+   client adds its tag.
-   gets `SWW_BLOCKLIST_ACTION`. A client on the CrowdSec decision list is
+7. The country list (`countries`; see "Country list").
-   banned. A client listed by a DNS blocklist, or scored at least
+8. The reputation sources (see "Reputation"), in this order:
-   `SWW_ABUSEIPDB_MIN_SCORE` by AbuseIPDB, gets `SWW_REPUTATION_ACTION`.
+    - A client on a fetched blocklist gets `SWW_BLOCKLIST_ACTION`
-8. The client's limit percentage (see "Biased thresholds").
+      (`blocklists`).
-9. Rate limiting (see "Request rate limits, per client"). A request over a limit
+    - A client on the CrowdSec decision list is banned (`crowdsec`).
-   times the percentage is refused and bans the client.
+    - A client listed by a DNS blocklist gets `SWW_REPUTATION_ACTION` (`dnsbl`).
-10. The trap paths (see "Attack detection"). A request for one is refused and
+    - A client scored at least `SWW_ABUSEIPDB_MIN_SCORE` by AbuseIPDB gets
-    bans the client.
+      `SWW_REPUTATION_ACTION` (`abuseipdb`).
-11. The rule files (see "Rule files"). Matching stops at the first rule that
+9. The tag refusals (`tag_deny`; see "Request tags"). A request carrying a tag
-    refuses.
+   in `SWW_TAG_DENY` is refused.
-12. The header limits (see "Answering in time"), and then the Core Rule Set (see
+10. The client's limit percentage (see "Biased thresholds").
-    "Attack detection"). A Core Rule Set match is refused with `403` while
+11. Rate limiting (`rate_limits`; see "Request rate limits, per client"). A
-    `SWW_WAF_MODE` is `block`, and only logged and alerted while it is `detect`.
+    request over a limit times the percentage is refused and bans the client.
-13. A path under `/_sww/` is answered `404`, so that the app never sees that
+12. The trap paths (`trap_paths`; see "Attack detection"). A request for one is
+    refused and bans the client.
+13. The rule files (`rule_files`; see "Rule files"). Matching stops at the first
+    rule that refuses.
+14. The header limits (`header_limits`; see "Answering in time"), and then the
+    Core Rule Set (`core_rule_set`; see "Attack detection"). A Core Rule Set
+    match is refused with `403` while `SWW_WAF_MODE` is `block`, and only logged
+    and alerted while it is `detect`.
+15. The tag refusals again (`tag_deny`), so that `exploitsignature` can refuse
+    too.
+16. A path under `/_sww/` is answered `404`, so that the app never sees that
     prefix.
-14. `rproxy` passes the request to `SWRP_UPSTREAM_URL`, streaming (see "Passing
+17. `rproxy` passes the request to `SWRP_UPSTREAM_URL`, streaming (see "Passing
     a request to the app"). With `SWW_ADD_LOOKUP_HEADERS`, `X-Client-ASN` and
     `X-Client-Country` are added for the app's own logs; a header whose value is
     unknown is left out. Whatever that setting says, any such header the client
     sent is removed.
-15. After the visitor's answer has ended, `rproxy` sends the report (see "The
+18. After the visitor's answer has ended, `rproxy` sends the report (see "The
     report"). `discriminator` then counts:
     - For a request it allowed, the response bytes, the request bytes or both
       are added to the byte counters, as `SWW_BYTES_COUNT` says. For a
       WebSocket, what it carried each way counts once it closes. A client whose
       total passes a byte limit times the percentage has broken that limit and
-      is banned. The response in progress is not cut off.
+      is banned (`byte_limits`). The response in progress is not cut off.
     - For a request it allowed, the client's history and the anomaly counters
       are updated, and the alert thresholds are evaluated.
 
     For a request it refused, `discriminator` adds nothing to the byte limits.
     It updates the history and the anomaly counters at its decision. It counts
-    the refusals the error burst counts at the decision too (see "Attack
+    the refusals the error burst counts at the decision too (`refusal_limit`;
-    detection").
+    see "Attack detection").
 
 In `SWW_MODE=observe`, every refusal above is logged as what would have
 happened, nothing is refused, and `discriminator` makes no ban of its own. A
@@ -279,7 +293,8 @@ no offence:
 
 - `SWW_DENY_NETS`;
 - a blocklist or reputation hit whose action is `deny`;
-- the country lists.
+- the country list;
+- `SWW_TAG_DENY`.
 
 Every ban carries notes with what an admin needs to decide whether to lift it,
 drawn from what `discriminator` already knows. No lookup is made for the notes
@@ -436,7 +451,7 @@ the same way.
 By default there is no minute limit, so a client can download in a burst at full
 speed. The hour limit defaults to 50 GiB and the day limit to 100 GiB. They
 allow several downloads of a few GiB each. A response's bytes are counted when
-it ends (see step 15).
+it ends (see step 18).
 
 ### Lookup of AS number and country
 
@@ -470,7 +485,7 @@ service that keeps its visitors' addresses on its own host.
   until it comes, and its later requests do not wait. Its address is asked about
   again in the background.
 - A client the lookup cannot place has an unknown country and AS number, which
-  the country lists and the biased thresholds treat as described there. Nothing
+  the country list and the biased thresholds treat as described there. Nothing
   else treats it differently.
 - GeoJS publishes no rate limit, but its terms forbid "an excessive amount of
   API requests", judged by GeoJS alone, and let it block a caller. While GeoJS
@@ -490,12 +505,12 @@ service that keeps its visitors' addresses on its own host.
   `file_error` alert and ignored. The database already loaded stays in use. A
   client whose address the file does not hold counts as unknown.
 
-### Country lists
+### Country list
 
-Both are empty by default: the defaults judge a client by what it does, not by
+`SWW_EXCLUSIVELY_ALLOWED_COUNTRIES` is empty by default: the defaults judge a
-where it comes from.
+client by what it does, not by where it comes from. A `country=` tag in
+`SWW_TAG_DENY` refuses one country (see "Request tags").
 
-- `SWW_DENIED_COUNTRIES` refuses every request from a listed country.
 - `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES` lets through only clients placed in a
   listed country. Every request from any other country is refused. So is every
   request from a client the lookup cannot place, such as internal monitoring or
@@ -504,34 +519,70 @@ where it comes from.
   client in whenever GeoJS stops answering. The cost: while GeoJS fails, this
   list refuses every new client. No other failure of GeoJS, a reputation source
   or an alert destination comes this close to taking the service down.
-- Both may be set. `SWW_DENIED_COUNTRIES` then adds nothing, since the exclusive
+- A code in this list whose `country=` tag is in `SWW_TAG_DENY` stops the start
-  list already refuses every other country. A code on both lists stops the start
   with a message naming it.
 - A refused request is answered with `SWW_BAN_RESPONSE`, as soon as the client's
   address has been looked up. It is logged with the action `country_denied`, and
   counted in the metrics.
 
+### Request tags
+
+Each request gets tags from what `discriminator` knows of its client and what
+the checks found. The operator refuses or slows clients by tag. Tags appear in
+the log line as `tags`, sorted, with empty lists left out (see
+`docs/request-log.md`).
+
+Each tag and where it comes from:
+
+- `asn=<number>` and `country=<code>`, in lower case, such as `asn=64496` and
+  `country=de`, from the lookup. A client the lookup cannot place has neither.
+- One tag per list of `SWW_TAG_LISTS` that holds the client (`tag_lists`), the
+  tag being the list's name, such as `torexit` or `vpn=mullvad`. These lists are
+  fetched and kept like a blocklist. `discriminator` ships none of its own.
+- `crowdsec`, `dnsbl=<zone>` and `abuseipdb`, when that reputation source lists
+  the client, whatever the source's action. A zone with a key is named with the
+  key masked, as the `reputation` field gives it.
+- `exploitsignature`, when a rule file or the Core Rule Set matched the request.
+  For the Core Rule Set a match is a score at or over
+  `SWW_WAF_ANOMALY_THRESHOLD`.
+
+A client in `SWW_ALLOW_NETS` skips the checks and gets no tag. `SWW_TAG_DENY`
+and `SWW_TAG_LIMIT_PERCENT` are read case-insensitively.
+
+Two settings act on tags:
+
+- `SWW_TAG_DENY` lists tags whose requests are refused with the action `denied`
+  (`tag_deny`). The check runs twice: just before the rate limits, and again
+  after the Core Rule Set, so that `exploitsignature` can refuse too.
+- `SWW_TAG_LIMIT_PERCENT` lists tags with a percentage from 1 to 99. Their
+  clients get that percentage of every request and byte limit. The lowest
+  percentage among a client's tags applies. `exploitsignature` cannot be listed,
+  since a request gets it only after the rate limits have counted it.
+
+The tag settings are empty by default, for the same reason as the country list.
+The lookup waits for GeoJS when either names an `asn=` or `country=` tag. A
+setting that names one stops the start while `SWW_LOOKUP_SOURCE` is `off`.
+
 ### Biased thresholds
 
-The biased thresholds lower the limits of clients in listed AS numbers and
+The biased thresholds lower the limits of clients by AS number, country and tag.
-countries. The lists are empty by default, for the same reason as the country
+The lists are empty by default, for the same reason as the country list. The
-lists. The request log and the metrics show which AS numbers and countries a
+request log and the metrics show which AS numbers and countries a service's
-service's abuse comes from.
+abuse comes from.
 
-- Each list gives AS numbers or countries a percentage, such as `AS14061:50`.
+- `SWW_TAG_LIMIT_PERCENT` gives a tag a percentage, such as `asn=14061:50` (see
-  Their clients get that percentage of every request and byte limit
+  "Request tags"). A lowered limit is rounded down.
-  (`SWW_ASN_LIMIT_PERCENT`, `SWW_COUNTRY_LIMIT_PERCENT`). A lowered limit is
+- `SWW_UNKNOWN_LIMIT_PERCENT` at `0` is a zero allowance: the client's first
-  rounded down. `0` is a zero allowance: the client's first request breaks a
+  request breaks a limit and bans it.
-  limit and bans it.
 - `SWW_ASN_BYTES_PERCENT` and `SWW_COUNTRY_BYTES_PERCENT` set the byte limits'
   percentage alone, when it should differ from the request limits'. For an AS
-  number they list, they replace its percentage from `SWW_ASN_LIMIT_PERCENT` and
+  number they list, they replace its `asn=` tag's percentage and its entry in
-  `SWW_ASN_LIMIT_PERCENT_URL`; for a country, the one from
+  `SWW_ASN_LIMIT_PERCENT_URL`; for a country, its `country=` tag's percentage.
-  `SWW_COUNTRY_LIMIT_PERCENT`.
 - `SWW_ASN_LIMIT_PERCENT_URL` names a text file of `AS:percent` lines, so one
   abuse-source list can be shared by every `discriminator` in the fleet. It is
-  fetched and kept like a blocklist (see "Reputation"). Where it and
+  fetched and kept like a blocklist (see "Reputation"). Each entry counts as an
-  `SWW_ASN_LIMIT_PERCENT` both give a percentage, the lower applies.
+  `asn=` tag in `SWW_TAG_LIMIT_PERCENT` does. Where both give a percentage, the
+  lower applies.
 - A client's limit percentage is the lowest of those that apply to it: its AS
   number's, its country's, or a reputation hit's `limit:<percent>`. A client
   without a country gets `SWW_UNKNOWN_LIMIT_PERCENT` in place of a country's.
@@ -542,7 +593,7 @@ service's abuse comes from.
 - No budget is shared by a whole country or AS number. One abuser could use it
   up and lock out everyone else there: a denial of service nobody chose, and the
   one this tool exists to prevent. Refusing a whole country is left to the
-  operator's choice, through the country lists.
+  operator's choice, through `SWW_TAG_DENY` or the country list.
 
 ### Attack detection
 
@@ -897,7 +948,7 @@ left unset sends no alert. An alert needs a destination only the operator can
 supply, and what counts as unusual depends on each service's normal traffic,
 which the metrics show. They reveal a widely distributed scraper, thousands of
 addresses at low rates each, which the per-client limits do not see. A low
-`SWW_ASN_LIMIT_PERCENT` for its AS number is the response.
+percentage for its `asn=` tag in `SWW_TAG_LIMIT_PERCENT` is the response.
 
 - Requests and bytes are counted per minute and per hour, for each of:
     - a client;
@@ -1175,7 +1226,7 @@ the metrics.
 
 ### The answer
 
-`discriminator` runs steps 3 to 13 of "What happens to a request", in that
+`discriminator` runs steps 3 to 16 of "What happens to a request", in that
 order. Every answer but the last below carries `X-Sww-Disposition`.
 
 - `X-Sww-Disposition: allow`, status `200`, no body. `rproxy` passes the request
@@ -1219,8 +1270,8 @@ milliseconds. A client without an answer by then counts as unknown. No question
 waits on these, which run in the background:
 
 - the DNS blocklists and AbuseIPDB;
-- fetching the blocklists, the CrowdSec decision list and the file
+- fetching the blocklists, the tag lists, the CrowdSec decision list and the
-  `SWW_ASN_LIMIT_PERCENT_URL` names.
+  file `SWW_ASN_LIMIT_PERCENT_URL` names.
 
 In `enforce` mode, a question does not wait for GeoJS when it is a request:
 

docs/request-log.md

@@ -96,8 +96,8 @@ Every one of these lines has:
 
 - `action`: what was done:
     - `forward`: answered `allow`, so that `rproxy` passes it to the app;
-    - `denied`: refused for `SWW_DENY_NETS`, or for a reputation source with the
+    - `denied`: refused for `SWW_DENY_NETS`, for a reputation source with the
-      action `deny`;
+      action `deny`, or for a tag in `SWW_TAG_DENY`;
     - `banned`: refused under a ban, or for a `ban` rule, a trap path or a
       CrowdSec decision, each of which bans the client;
     - `country_denied`, `rate_limited`, `rule_blocked` and `waf_blocked`:
@@ -108,6 +108,36 @@ Every one of these lines has:
 - `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.
@@ -139,6 +169,8 @@ Every one of these lines has:
     - 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).
 - `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`.

docs/settings.md

@@ -130,9 +130,11 @@ between the two (see "The image's command" below).
 
 - `SWW_LOOKUP_SOURCE` (default `geojs`): `geojs`, `file` or `off`. `off` stops
   the start while a setting that needs a lookup is set:
-    - the two country lists;
+    - `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES`;
     - `SWW_ADD_LOOKUP_HEADERS`;
-    - the four biased threshold lists and `SWW_ASN_LIMIT_PERCENT_URL`;
+    - `SWW_TAG_DENY` or `SWW_TAG_LIMIT_PERCENT` naming an `asn=` or `country=`
+      tag;
+    - 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
@@ -144,28 +146,46 @@ between the two (see "The image's command" below).
   the client's AS number in `X-Client-ASN` and its country in
   `X-Client-Country`.
 
-## Country lists
+## Country list
 
-- `SWW_DENIED_COUNTRIES` (default empty): countries whose clients are refused,
-  such as `cn,ru,kp`.
 - `SWW_EXCLUSIVELY_ALLOWED_COUNTRIES` (default empty): when set, the only
-  countries whose clients get through, such as `us,de`. A country on both lists
+  countries whose clients get through, such as `us,de`. A country whose
-  stops the start.
+  `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.
 
 ## Biased thresholds
 
-- `SWW_ASN_LIMIT_PERCENT` (default empty): a list of AS numbers, each with `:`
+- `SWW_ASN_BYTES_PERCENT` and `SWW_COUNTRY_BYTES_PERCENT` (default empty): a
-  and a percentage, such as `AS14061:50,AS16276:50,AS45102:25`. An AS number
+  percentage of the byte limits alone, for the AS numbers or countries listed,
-  listed twice is refused.
+  such as `AS14061:50` or `cn:25`. It takes the place of the percentage
-- `SWW_COUNTRY_LIMIT_PERCENT` (default empty): the same by country, such as
+  `SWW_TAG_LIMIT_PERCENT` gives their `asn=` or `country=` tag. An AS number or
-  `cn:25,ru:50`.
+  country listed twice is refused.
-- `SWW_ASN_BYTES_PERCENT` and `SWW_COUNTRY_BYTES_PERCENT` (default empty): the
-  same, for the byte limits alone.
 - `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`. A URL that is also in `SWW_BLOCKLIST_URLS` is refused.
+  `AS64496:50`. Each entry counts as an `asn=` tag in `SWW_TAG_LIMIT_PERCENT`
+  does. A URL that is also in `SWW_BLOCKLIST_URLS` is refused.
 
 ## Attack detection
 

internal/config/config.go

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

internal/config/config_test.go

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

internal/discriminator/abuseipdb.go

@@ -0,0 +1,57 @@
+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/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("abuseipdb")
+	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.ActionDenied,
+		figures: map[string]any{
+			figureScore: score, "min_score": rq.h.config.AbuseIPDBMinScore,
+		},
+	}
+}

internal/discriminator/answertime_test.go

@@ -91,6 +91,18 @@ func TestSixteenThousandCookiesAreRefusedWellWithinTheTimeLimit(t *testing.T) {
 	}
 }
 
+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()
 
@@ -323,7 +335,7 @@ func newDiscriminatorInBubble(
 ) (*discriminator.Server, *output) {
 	t.Helper()
 
-	settings := map[string]string{deniedCountries: "KP"}
+	settings := map[string]string{tagDeny: "country=KP"}
 	maps.Copy(settings, env)
 
 	server, out, _ := newDiscriminator(t, unansweredGeoJSURL, time.Now, settings)
@@ -530,7 +542,7 @@ func TestDiscriminatorAnswersWithinTheTimeLimitWhileEveryOutsideSourceHangs(
 
 		return discriminator.New(params)
 	}, held, time.Now, map[string]string{
-		deniedCountries: "KP", wafMode: block,
+		tagDeny: "country=KP", wafMode: block,
 		dnsblZones: dnsblZone, dnsblResolver: resolver.LocalAddr().String(),
 		abuseIPDBKey:  accountKey,
 		blocklistURLs: held + "/drop.txt", asnLimitPercentURL: held + "/asn.txt",

internal/discriminator/bans.go

@@ -1,7 +1,10 @@
 package discriminator
 
+// 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 (
-	"net/http"
+	"context"
 	"net/netip"
 	"time"
 
@@ -18,11 +21,15 @@ func (rq *request) banResponse(action string) *refusal {
 	return &refusal{status: rq.h.config.BanResponse, action: action}
 }
 
-// banned reports whether a ban on a netblock the client is in covers the
+// activeBan refuses a client a ban covers: a ban on a netblock the client is
-// request at now, and notes for the log line when that ban ends. A
+// in, in force at now. It notes for the log line when that ban ends. A request
-// request that makes the ban permanent, or in observe mode would have,
+// that makes the ban permanent, or in observe mode would have, raises the alert
-// raises the alert for it.
+// for it. Its figures are the ban's netblock and when it ends.
-func (rq *request) banned(now time.Time) bool {
+type activeBan struct{}
+
+func (activeBan) name() string { return "active_ban" }
+
+func (activeBan) check(_ context.Context, rq *request, now time.Time) *verdict {
 	check := rq.h.ledger.Check
 	if rq.h.config.Observe {
 		check = rq.h.ledger.Find // the ban refuses nothing, and stays as it is
@@ -38,85 +45,24 @@ func (rq *request) banned(now time.Time) bool {
 		rq.alertBan(ban)
 	}
 
-	return banned
+	if !banned {
+		return nil
 	}
 
-// limitBroken counts the request for the rate limits at now, notes the
+	return &verdict{
-// client's counts for the log line, and reports whether the request takes
+		action: requestlog.ActionBanned,
-// the client over a rate limit, as its limit percentage lowers it, which
+		figures: map[string]any{
-// breaks it.
+			figureNetblock: ban.Netblock.String(), "ban_expires": rq.line.BanExpires,
-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 over
-}
-
-// countBytes 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; 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)
 	}
 }
 
-// countRefusal counts the request for the error burst once it has been
+// limitFigures are the figures of a heuristic that broke hit, a limit: its
-// answered, if discriminator refused it after a rule file match, a trap path or a
+// window, the count and the limit.
-// Core Rule Set match, and in observe mode if enforce mode would have: more than
+func limitFigures(hit ratelimit.Hit) map[string]any {
-// SWW_ERROR_BURST_THRESHOLD such refusals of the client within a minute
+	return map[string]any{
-// break a limit. A client in SWW_ALLOW_NETS, which the checks skip, is
+		figureWindow: hit.Window, figureCount: hit.Count, figureLimit: hit.Limit,
-// not counted, and nothing is while the threshold is off.
-func (rq *request) countRefusal() {
-	cfg := rq.h.config
-	if cfg.ErrorBurstThreshold == 0 {
-		return
 	}
-
-	if !rq.attack && !rq.ruleBlocked && !rq.wafBlocked {
-		return
-	}
-
-	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

internal/discriminator/bans_test.go

@@ -211,7 +211,7 @@ func TestBannedClientIsRefusedBeforeItsCountryIsLookedUp(t *testing.T) {
 		lookupTimeout:      "1h",
 		rateLimitPerMinute: "1",
 		banScopeV4Prefix:   "24",
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 	})
 
 	// fromDE's ban covers otherClient, which is refused unasked about.
@@ -228,6 +228,22 @@ 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.ActionRateLimited)
+
+	line := s.get(otherClient, http.StatusForbidden, requestlog.ActionBanned)
+	wantHeuristic(t, line, "active_ban",
+		`{"netblock": "`+clientsNet+`", "ban_expires": "`+expires+`"}`)
+}
+
 func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 	t.Parallel()
 
@@ -250,7 +266,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 				lookupTimeout:      "1h",
 				rateLimitPerMinute: "1",
 				denyNets:           denied,
-				deniedCountries:    "kp",
+				tagDeny:            denyKP,
 			}
 
 			if tc.setting != "" {
@@ -260,7 +276,7 @@ func TestBanResponseAnswersEveryRefusalButTheSizeLimits(t *testing.T) {
 			s, _, _ := startWithClock(t, geojsURL, env)
 
 			s.get(denied, tc.status, requestlog.ActionDenied)
-			s.get(fromKP, tc.status, requestlog.ActionCountryDenied)
+			s.get(fromKP, tc.status, requestlog.ActionDenied)
 			s.get(fromDE, http.StatusOK, requestlog.ActionForward)
 			s.get(fromDE, tc.status, requestlog.ActionRateLimited)
 			s.get(fromDE, tc.status, requestlog.ActionBanned)
@@ -275,7 +291,7 @@ func TestBanNotes(t *testing.T) {
 	s, clk, server := startWithClock(t, geojsURL, map[string]string{
 		lookupTimeout:      "1h",
 		rateLimitPerMinute: "1",
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 	})
 	start := clk.Now()
 

internal/discriminator/biased.go

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

internal/discriminator/biased_test.go

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

internal/discriminator/blocklists.go

@@ -0,0 +1,41 @@
+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.ActionDenied,
+		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
+}

internal/discriminator/bytelimits.go

@@ -0,0 +1,43 @@
+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"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// 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{action: requestlog.ActionBanned, figures: limitFigures(hit)}
+}

internal/discriminator/bytelimits_test.go

@@ -98,6 +98,21 @@ func TestEachByteLimitBansOnceTheResponseHasEnded(t *testing.T) {
 	}
 }
 
+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) {
 	t.Parallel()
 

internal/discriminator/coreruleset.go

@@ -1,6 +1,10 @@
 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"
@@ -9,18 +13,22 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/waf"
 )
 
-// checkCoreRuleSet inspects the request with the Core Rule Set, unless
+// 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 raises the waf_block alert,
+// SWW_WAF_ANOMALY_THRESHOLD is a match: it adds the tag exploitsignature,
-// and in block mode refuses the request, which is an offence its client's
+// raises the waf_block alert, and in block mode refuses the request with 403,
-// history counts, and so returns ActionWAFBlocked. It returns "" for a
+// which is an offence its client's history counts. Its figures are the score
-// request it does not refuse.
+// and the threshold.
-func (rq *request) checkCoreRuleSet() string {
+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 ""
+		return nil
 	}
 
 	start := time.Now()
@@ -40,18 +48,22 @@ func (rq *request) checkCoreRuleSet() string {
 
 	threshold := cfg.WAFAnomalyThreshold
 	if threshold == 0 || result.Score < threshold {
-		return ""
+		return nil
 	}
 
+	rq.addTag(config.ExploitSignatureTag)
 	rq.alertWAFBlock(result)
 
 	if cfg.WAFMode == config.WAFModeDetect {
-		return ""
+		return nil
 	}
 
 	rq.wafBlocked = true
 
-	return requestlog.ActionWAFBlocked
+	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

internal/discriminator/coreruleset_test.go

@@ -61,6 +61,41 @@ func wantWAF(t *testing.T, line logLine, score *int, ruleIDs ...int) {
 	}
 }
 
+func TestCoreRuleSetMatchAddsTheExploitSignatureTag(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name   string
+		mode   string
+		status int
+		action string
+	}{
+		{block, block, http.StatusForbidden, requestlog.ActionWAFBlocked},
+		{detect, detect, http.StatusOK, requestlog.ActionForward},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s, _, _ := startWithClock(t, "", map[string]string{wafMode: tc.mode})
+
+			wantTags(t, s.request(client, sqlInjection, tc.status, tc.action),
+				"exploitsignature")
+			wantTags(t, s.get(client, http.StatusOK, requestlog.ActionForward))
+		})
+	}
+}
+
+func TestDetectedAttackIsRefusedByTagDenyLast(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		wafMode: detect, tagDeny: "exploitsignature",
+	})
+
+	line := s.request(client, sqlInjection, http.StatusForbidden, requestlog.ActionDenied)
+	wantHeuristic(t, line, "tag_deny", `{"tag": "exploitsignature"}`)
+}
+
 func TestCoreRuleSetRefusesAttacksInBlockModeAndOnlyLogsThemInDetectMode(t *testing.T) {
 	t.Parallel()
 
@@ -110,6 +145,16 @@ 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) {
 	t.Parallel()
 

internal/discriminator/countries.go

@@ -1,21 +1,35 @@
 package discriminator
 
+// The heuristic countries. It reads SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
+
 import (
+	"context"
 	"slices"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 )
 
-// countryDenied reports whether the country lists refuse the request, by
+// countries refuses a request when SWW_EXCLUSIVELY_ALLOWED_COUNTRIES is set and
-// the client's country as it was looked up. A client without a country,
+// does not hold the client's country as it was looked up. A client without a
-// or whose country cannot be found, is refused only by
+// country, or whose country cannot be found, is refused. Its figures are the
-// SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
+// country and the setting that refused it.
-func (rq *request) countryDenied() bool {
+type countries struct{}
-	denied := rq.h.config.DeniedCountries
+
+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 slices.Contains(denied, country) {
+	if len(allowed) == 0 || slices.Contains(allowed, country) {
-		return true
+		return nil
 	}
 
-	return len(allowed) > 0 && !slices.Contains(allowed, country)
+	return &verdict{
+		action: requestlog.ActionCountryDenied,
+		figures: map[string]any{
+			"country": country, "setting": "SWW_EXCLUSIVELY_ALLOWED_COUNTRIES",
+		},
+	}
 }

internal/discriminator/countries_test.go

@@ -33,13 +33,13 @@ func TestCountryLists(t *testing.T) {
 		env     map[string]string
 		refused []string
 	}{
-		{"denied", map[string]string{deniedCountries: "kp"}, []string{fromKP}},
 		{
 			"exclusively allowed", map[string]string{allowedCountries: "DE"},
 			[]string{fromKP, unplaced},
 		},
 		{
-			"both", map[string]string{deniedCountries: "kp", allowedCountries: "de,fr"},
+			"with a country in SWW_TAG_DENY",
+			map[string]string{tagDeny: denyKP, allowedCountries: "de,fr"},
 			[]string{fromKP, unplaced},
 		},
 	} {
@@ -90,6 +90,23 @@ func TestCountryLists(t *testing.T) {
 	}
 }
 
+func TestCountryRefusalNamesItsHeuristicCountryAndSetting(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()
 
@@ -102,7 +119,7 @@ func TestCountryRefusalKeepsARequestFromTheApp(t *testing.T) {
 	addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
 		trustedProxies:   trustLocalhost,
 		lookupTimeout:    "1h",
-		deniedCountries: "kp",
+		allowedCountries: "de",
 	})
 
 	req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
@@ -185,7 +202,7 @@ func TestPrivateAddressIsNeverLookedUp(t *testing.T) {
 		env  map[string]string
 	}{
 		{"no setting needs the lookup", nil},
-		{"a country list is set", map[string]string{deniedCountries: "kp"}},
+		{"a tag setting needs it", map[string]string{tagDeny: denyKP}},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()

internal/discriminator/crowdsec.go

@@ -0,0 +1,50 @@
+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/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("crowdsec")
+	rq.noteHit(bans.ReputationHit{Source: rq.h.config.CrowdSecDecisionsURL},
+		"listed by the CrowdSec decision list")
+	rq.banForCrowdSec(now, decision)
+
+	return &verdict{
+		action: requestlog.ActionBanned,
+		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)
+}

internal/discriminator/crowdsec_test.go

@@ -95,6 +95,22 @@ func TestClientTheCrowdSecDecisionListListsIsBannedUntilTheDecisionEnds(t *testi
 		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.ActionBanned)
+	wantHeuristic(t, line, "crowdsec", `{"scenario": "crowdsecurity/ssh-bf", `+
+		`"expires": "`+requestlog.FormatTime(clk.Now().Add(4*time.Hour))+`"}`)
+	wantTags(t, line, "crowdsec")
+}
+
 func TestEndedCrowdSecDecisionNoLongerBansThoughTheCopyStillHoldsIt(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/denynets.go

@@ -0,0 +1,29 @@
+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.ActionDenied,
+				figures: map[string]any{figureNetblock: netblock.String()},
+			}
+		}
+	}
+
+	return nil
+}

internal/discriminator/discriminator.go

@@ -2,6 +2,7 @@ package discriminator
 
 import (
 	"bytes"
+	"context"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -52,13 +53,6 @@ const ReportPath = "/_sww/report"
 // QuestionBodyMaxBytes is the most of a visitor's body a question carries.
 const QuestionBodyMaxBytes = 64 << 10
 
-// 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
-)
-
 const (
 	// maxAwaitingReport is the most answered requests held until their
 	// reports come. Past it, the request answered longest ago is dropped.
@@ -148,48 +142,20 @@ func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 
 // 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: it is over the header limits, a blocklist lists its client while
+// its client: the heuristic crowdsec, header_limits, blocklists or rate_limits
-// SWW_BLOCKLIST_ACTION is deny, the CrowdSec decision list lists it, or it is
+// will refuse it, as a function in that heuristic's file says. In observe mode,
-// over a whole rate limit. In observe mode, which refuses nothing, none is.
+// which refuses nothing, none is. rproxy lets a request through when
-// rproxy lets a request through when discriminator answers too late.
+// discriminator answers too late.
 func (rq *request) refusedWhateverTheAnswer(now time.Time) bool {
 	if rq.h.config.Observe {
 		return false
 	}
 
-	lists := rq.h.lists
+	_, decided := rq.crowdSecDecisionInForce(now)
-	_, decided := lists.CrowdSecDecision(rq.client, now)
 
-	return decided || rq.overHeaderLimits() ||
+	return decided || overHeaderLimits(rq.headerCounts()) ||
-		(rq.h.config.BlocklistAction == deny && len(lists.ListedBy(rq.client)) > 0) ||
+		rq.refusedByBlocklists(rq.h.lists.ListedBy(rq.client)) ||
-		(rq.countedByRateLimits() &&
+		rq.overAWholeRateLimit(now)
-			rq.h.limiter.OverARateLimit(rq.h.clientGroup(rq.client), now))
-}
-
-// overHeaderLimits reports whether discriminator refuses the request for its
-// headers: it has more than maxHeaderFields fields, each value of a header sent
-// twice being one, or more than maxCookies 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) overHeaderLimits() bool {
-	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 > maxHeaderFields || cookies > maxCookies
 }
 
 // answerQuestion runs the checks on the visitor's request a question
@@ -220,18 +186,18 @@ func (h *handler) answerQuestion(w http.ResponseWriter, r *http.Request) {
 
 	if refused == nil && !underOwnPrefix {
 		// In observe mode, what enforce mode would have refused counts here.
-		defer rq.countRefusal()
+		defer rq.runAfterAnswer(r.Context())
 
 		rq.allow()
 
 		return
 	}
 
-	// The last deferred runs first: countRefusal before addToHistory, so that a
+	// The last deferred runs first: runAfterAnswer before addToHistory, so that
-	// broken error burst is in the client's history.
+	// a broken refusal limit is in the client's history.
 	defer rq.addToHistory()
 	defer rq.countAnomalies()
-	defer rq.countRefusal()
+	defer rq.runAfterAnswer(r.Context())
 
 	if refused != nil {
 		rq.deny(*refused)
@@ -413,7 +379,7 @@ func (h *handler) takeReport(w http.ResponseWriter, r *http.Request) {
 	// 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(held, report)
+		h.finishWith(r.Context(), held, report)
 	}
 
 	w.WriteHeader(http.StatusNoContent)
@@ -476,11 +442,11 @@ func (report *Report) checkRanges() error {
 
 // 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 counts the request's bytes, and adds it to its
+// For an allowed request it first runs the heuristics of onReport, and adds the
-// client's history, the anomaly counters and the metrics, with the status and
+// request to its client's history, the anomaly counters and the metrics, with
-// bytes the report gives. A denied request's counting was finished at its
+// the status and bytes the report gives. A denied request's counting was
-// decision.
+// finished at its decision. ctx is the report's own context.
-func (h *handler) finishWith(held *decision, report Report) {
+func (h *handler) finishWith(ctx context.Context, held *decision, report Report) {
 	rq := &request{
 		decision:     *held,
 		h:            h,
@@ -497,7 +463,7 @@ func (h *handler) finishWith(held *decision, report Report) {
 	if rq.allowed {
 		rq.line.DurationUpstreamTotal = &report.DurationUpstreamTotal
 
-		rq.countBytes()
+		rq.runBanningHeuristics(ctx, onReport())
 		rq.countAnomalies()
 		rq.addToHistory()
 

internal/discriminator/discriminator_test.go

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

internal/discriminator/dnsbl.go

@@ -0,0 +1,41 @@
+package discriminator
+
+// The heuristic dnsbl. It reads SWW_REPUTATION_ACTION, and the DNSBL zones'
+// verdicts through the DNSBL checker.
+
+import (
+	"context"
+	"time"
+
+	"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("dnsbl=" + zone)
+	}
+
+	if !rq.dnsblListed || rq.h.config.ReputationAction != deny {
+		return nil
+	}
+
+	return &verdict{
+		action:  requestlog.ActionDenied,
+		figures: map[string]any{"zones": listedBy},
+	}
+}

internal/discriminator/headerlimits.go

@@ -0,0 +1,71 @@
+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.ActionTooLarge,
+		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
+}

internal/discriminator/heuristics.go

@@ -0,0 +1,139 @@
+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{
+		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{
+		tagLists{},
+		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
+}

internal/discriminator/history_test.go

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

internal/discriminator/lookup.go

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

internal/discriminator/lookup_test.go

@@ -96,7 +96,7 @@ func TestRequestThatWaitedForItsLookupIsCountedWhenItGoesOn(t *testing.T) {
 		map[string]string{
 			trustedProxies: trustLocalhost,
 			lookupTimeout:  "1h",
-			deniedCountries: "kp",
+			tagDeny:        denyKP,
 		})
 
 	requestFromDE := func() *http.Request {

internal/discriminator/metrics_test.go

@@ -198,7 +198,7 @@ func TestMetricsByCountryKeepTheBusiestAndCountTheRestAsOther(t *testing.T) {
 		trustedProxies:   trustLocalhost,
 		metricsToken:     token,
 		metricsTopN:      "2",
-		deniedCountries: "kp",
+		allowedCountries: "de,fr",
 	}
 	geojsURL, _ := startGeoJS(t)
 	addr, out, server := startProxyWithClock(t, app.URL, geojsURL, time.Now, env)
@@ -324,11 +324,11 @@ func TestMetricsCountGeoJSRequestsAndFailures(t *testing.T) {
 		map[string]string{
 			trustedProxies: trustLocalhost,
 			metricsToken:   token,
-			deniedCountries: "kp",
+			tagDeny:        denyKP,
 		})
 
-	// GeoJS fails, so the client counts as coming from an unknown country,
+	// GeoJS fails, so the client has no country= tag, and SWW_TAG_DENY does
-	// which SWW_DENIED_COUNTRIES does not refuse.
+	// not refuse it.
 	req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
 	req.Header.Set(forwardedFor, fromDE)
 	wantStatus(t, do(t, req), http.StatusOK)

internal/discriminator/observe_test.go

@@ -14,6 +14,18 @@ import (
 // observe is the value of SWW_MODE for observe mode.
 const observe = "observe"
 
+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.ActionDenied)
+	wantHeuristic(t, line, "deny_nets", `{"netblock": "`+client+`/32"}`)
+}
+
 func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
 	t.Parallel()
 
@@ -38,7 +50,7 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
 				lookupTimeout:      "1h",
 				rateLimitPerMinute: "1",
 				denyNets:           denied,
-				deniedCountries:    "kp",
+				tagDeny:            denyKP,
 			}
 
 			if tc.setting != "" {
@@ -59,7 +71,7 @@ func TestObserveModeForwardsWhatEnforceModeRefuses(t *testing.T) {
 			for _, sent := range []struct{ from, refusal string }{
 				{denied, requestlog.ActionDenied},
 				{banned, requestlog.ActionBanned},
-				{fromKP, requestlog.ActionCountryDenied},
+				{fromKP, requestlog.ActionDenied},
 				{fromDE, requestlog.ActionRateLimited},
 			} {
 				if !tc.observe {

internal/discriminator/proxy.go

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

internal/discriminator/proxy_test.go

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

internal/discriminator/ratelimits.go

@@ -0,0 +1,65 @@
+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.ActionRateLimited, 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)
+}

internal/discriminator/ratelimits_test.go

@@ -72,6 +72,17 @@ 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.ActionRateLimited)
+	wantHeuristic(t, line, "rate_limits", `{"window": "minute", "count": 2, "limit": 1}`)
+}
+
 func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) {
 	t.Parallel()
 
@@ -125,7 +136,7 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 		rateLimitPerMinute:   "1",
 		rateLimitExemptPaths: "/assets/,/favicon.ico",
 		denyNets:             denied,
-		deniedCountries:      "kp",
+		tagDeny:              denyKP,
 	})
 
 	// The answers are kept before the requests, so that none waits for
@@ -156,7 +167,7 @@ func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 	s.request(client, "/assets/app.js", http.StatusForbidden, requestlog.ActionBanned)
 	s.request(denied, "/assets/app.js", http.StatusForbidden, requestlog.ActionDenied)
 	s.request(fromKP, "/assets/app.js",
-		http.StatusForbidden, requestlog.ActionCountryDenied)
+		http.StatusForbidden, requestlog.ActionDenied)
 }
 
 func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {

internal/discriminator/refusallimit.go

@@ -0,0 +1,54 @@
+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.ruleBlocked && !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.ActionRuleBlocked, requestlog.ActionWAFBlocked:
+		status = http.StatusForbidden
+	case requestlog.ActionBanned:
+		status = cfg.BanResponse
+	}
+
+	rq.banForLimit(now, hit, status)
+
+	return &verdict{action: requestlog.ActionBanned, figures: limitFigures(hit)}
+}

internal/discriminator/refusallimit_test.go

@@ -106,6 +106,25 @@ func TestErrorBurstBreaksAtOneOverTheThreshold(t *testing.T) {
 	}
 }
 
+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) {
 	t.Parallel()
 
@@ -172,7 +191,7 @@ func TestErrorBurstIsNotLoweredForAClientWithLowerLimits(t *testing.T) {
 		lookupTimeout:       "1h",
 		errorBurstThreshold: "2",
 		rulesDir:            writeRules(t, testRules),
-		countryLimitPercent: countryDEHalf,
+		tagLimitPercent:     countryTagDEHalf,
 	})
 
 	// Half of the threshold would be one, which the second refusal is over.

internal/discriminator/reputation.go

@@ -1,91 +1,17 @@
 package discriminator
 
-import (
+// What the reputation heuristics share: blocklists, crowdsec, dnsbl and
-	"context"
+// abuseipdb.
-	"time"
 
+import (
 	"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 SWW_BLOCKLIST_ACTION and the SWW_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 SWW_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 SWW_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
-// SWW_REPUTATION_ACTION, being deny, refuses the request, as dnsblDenied
-// 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. 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 SWW_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.

internal/discriminator/reputation_test.go

@@ -118,11 +118,61 @@ func TestEachBlocklistActionForAListedAddressAndAListedNetblock(t *testing.T) {
 	}
 }
 
+func TestReputationRefusalNamesItsHeuristicAndWhatListedTheClient(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.ActionDenied)
+			wantHeuristic(t, line, tc.heuristic, tc.figures)
+		})
+	}
+}
+
 func TestBlocklistsComeAfterTheCountryListsAndSkipAllowNets(t *testing.T) {
 	t.Parallel()
 
 	s, server, queue := startWithLookups(t, map[string]string{
-		blocklistURLs: dropURL, deniedCountries: "kp", allowNets: fromDE,
+		blocklistURLs: dropURL, allowedCountries: "de", allowNets: fromDE,
 	})
 	loadLists(t, server, map[string][]string{dropURL: {fromDE, fromKP}})
 
@@ -161,18 +211,18 @@ func TestBlocklistLimitTakesPartInTheLowestPercentageOfEveryLimit(t *testing.T)
 		// percentText gives them, and limitHit its limit_hit.
 		want, limitHit string
 	}{
-		{limitHalf, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
+		{limitHalf, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes},
-		{limitQuarter, asnDEHalf, "25 from " + blocklistAction, minuteBytes},
+		{limitQuarter, asnTagDEHalf, "25 from " + blocklistAction, minuteBytes},
 		// The AS number's, the first of two alike.
-		{limitQuarter, asnDEQuarter, "25 from " + asnLimitPercent, minuteBytes},
+		{limitQuarter, asnTagDEQuarter, "25 from " + tagLimitPercent, minuteBytes},
-		{actionLog, asnDE + ":100", none, ""},
+		{actionLog, "asn=64511:25", none, ""},
 	} {
 		t.Run(tc.action+" "+tc.asnPercent, func(t *testing.T) {
 			t.Parallel()
 
 			s, server, _ := startWithLookups(t, map[string]string{
 				bytesLimitPerMinute: twoUploads, blocklistURLs: dropURL,
-				blocklistAction: tc.action, asnLimitPercent: tc.asnPercent,
+				blocklistAction: tc.action, tagLimitPercent: tc.asnPercent,
 			})
 			loadLists(t, server, map[string][]string{dropURL: {fromDE}})
 
@@ -196,7 +246,7 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
 
 	const (
 		fromURL     = "25 from " + asnLimitPercentURL
-		fromSetting = "25 from " + asnLimitPercent
+		fromSetting = "25 from " + tagLimitPercent
 	)
 
 	for _, tc := range []struct {
@@ -210,16 +260,16 @@ func TestASNLimitPercentFileCountsAsTheSettingDoesTheLowerWinning(t *testing.T)
 		{"the file's alone", nil, asnDEQuarter, fromURL, fromURL},
 		{
 			"the file's, lower than the setting's",
-			map[string]string{asnLimitPercent: asnDEHalf}, asnDEQuarter, fromURL, fromURL,
+			map[string]string{tagLimitPercent: asnTagDEHalf}, asnDEQuarter, fromURL, fromURL,
 		},
 		{
 			"the setting's, lower than the file's",
-			map[string]string{asnLimitPercent: asnDEQuarter}, asnDEHalf,
+			map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEHalf,
 			fromSetting, fromSetting,
 		},
 		{
 			"the setting's, the first of two alike",
-			map[string]string{asnLimitPercent: asnDEQuarter}, asnDEQuarter,
+			map[string]string{tagLimitPercent: asnTagDEQuarter}, asnDEQuarter,
 			fromSetting, fromSetting,
 		},
 		{"none, for an AS number the file does not list", nil, asnKP + ":25", none, none},
@@ -432,6 +482,46 @@ func TestDNSBLZonesComeAfterTheBlocklistsAndSkipAllowNets(t *testing.T) {
 	}
 }
 
+func TestReputationSourcesTagTheRequestWhateverTheirAction(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name string
+		env  map[string]string
+		load func(*discriminator.Server)
+		want []string
+	}{
+		{
+			"dnsbl",
+			map[string]string{
+				dnsblZones: dnsblZone, dnsblResolver: noResolver, reputationAction: actionLog,
+			},
+			func(server *discriminator.Server) {
+				loadVerdicts(server, map[string][]string{fromDE: {dnsblZone}})
+			},
+			[]string{"asn=64496", "country=de", "dnsbl=" + dnsblZone},
+		},
+		{
+			abuseipdb,
+			map[string]string{abuseIPDBKey: accountKey, reputationAction: actionLog},
+			func(server *discriminator.Server) {
+				loadScores(server, map[string]int64{fromDE: 80})
+			},
+			[]string{abuseipdb, "asn=64496", "country=de"},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s, server, _ := startWithLookups(t, tc.env)
+			tc.load(server)
+
+			wantTags(t, s.get(fromDE, http.StatusOK, requestlog.ActionForward),
+				tc.want...)
+		})
+	}
+}
+
 func TestObserveModeForwardsAClientADNSBLZoneDeniesAndAlertsIt(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/request.go

@@ -138,6 +138,17 @@ func (h *handler) startRequest(
 	return rq
 }
 
+// addTag adds tag, in lower case, to the request's tags, which stay sorted and
+// hold each tag once.
+func (rq *request) addTag(tag string) {
+	tag = strings.ToLower(tag)
+
+	at, found := slices.BinarySearch(rq.line.Tags, tag)
+	if !found {
+		rq.line.Tags = slices.Insert(rq.line.Tags, at, tag)
+	}
+}
+
 // requestHeaders returns the headers of r that names lists, by name in
 // lower case, each with its values joined by ", ". Authorization, Cookie
 // and Set-Cookie are never among them, whatever names says.
@@ -160,16 +171,20 @@ func requestHeaders(r *http.Request, names []string) map[string]string {
 }
 
 // check is the one place where a request can be refused. It returns nil to let
-// the request through. The checks of checkClient decide: a request they refuse
+// the request through. The heuristics of checkClient decide: a request they
-// is answered with SWW_BAN_RESPONSE, 403 for a block rule or the Core Rule Set,
+// refuse is answered with SWW_BAN_RESPONSE, 403 for a block rule or the Core
-// or 431 for the header limits. In observe mode nothing is refused, and the log
+// Rule Set, or 431 for the header limits. In observe mode nothing is refused,
-// line names what enforce mode would have done. ctx is the request's own context.
+// 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 {
-	action := rq.checkClient(ctx)
+	v := rq.checkClient(ctx)
+	if v == nil {
+		return nil
+	}
+
+	action := v.action
 
 	switch {
-	case action == "":
-		return nil
 	case rq.h.config.Observe:
 		rq.line.WouldAction = action
 
@@ -183,35 +198,21 @@ func (rq *request) check(ctx context.Context) *refusal {
 	}
 }
 
-// checkClient runs the checks on the request's client, and returns the
+// checkClient runs the heuristics of beforeLookup on the request, then looks
-// action of the first that refuses the request, or "" when none does. A
+// up the client's AS number and country, then runs those of afterLookup. It
-// client in SWW_ALLOW_NETS skips them, and is not looked up. For any
+// returns the first verdict, or nil when none gives one. A client in
-// other client, SWW_DENY_NETS comes first, then a ban on its netblock,
+// SWW_ALLOW_NETS skips them all, and is not looked up. ctx is the request's
-// so that a client either refuses is not looked up, then the lookup of
+// own context.
-// its AS number and country, then the country lists, then the blocklists,
+func (rq *request) checkClient(ctx context.Context) *verdict {
-// then the CrowdSec decision list, which bans the client it lists, then
+	if isInside(rq.client, rq.h.config.AllowNets) {
-// the DNSBL zones' verdicts, and then AbuseIPDB's score; a request any of
+		return nil
-// them refuses is not counted for the rate limits. Then come the
-// rate limits, unless the client is in SWW_RATE_LIMIT_EXEMPT_NETS or the
-// request's path is exempt under SWW_RATE_LIMIT_EXEMPT_PATHS, so that
-// every other request is counted, each of them by the client's limit
-// percentages, then SWW_TRAP_PATHS, then the rule files, then the header
-// limits, 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) {
+	v := rq.runHeuristics(ctx, beforeLookup(), now)
-		return requestlog.ActionDenied
+	if v != nil {
-	}
+		return v
-
-	if rq.banned(now) {
-		return requestlog.ActionBanned
 	}
 
 	rq.lookUp(ctx, now)
@@ -220,59 +221,7 @@ func (rq *request) checkClient(ctx context.Context) string {
 	// 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()
+	return rq.runHeuristics(ctx, afterLookup(), 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 = rq.countedByRateLimits()
-	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
-	}
-
-	if rq.overHeaderLimits() {
-		return requestlog.ActionTooLarge
-	}
-
-	return rq.checkCoreRuleSet()
-}
-
-// 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)
 }
 
 // pathExempt reports whether r is exempt under prefixes,

internal/discriminator/requestlog_test.go

@@ -1,6 +1,7 @@
 package discriminator_test
 
 import (
+	"encoding/json"
 	"io"
 	"math"
 	"net/http"
@@ -272,6 +273,48 @@ 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.
 func microseconds(milliseconds float64) int64 {
 	return int64(math.Round(milliseconds * 1000))

internal/discriminator/rulefiles.go

@@ -0,0 +1,59 @@
+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 ActionRuleBlocked for a block
+// rule, and ActionBanned for a ban rule. A ban rule bans the client's netblock
+// for a clear sign of attack, or in observe mode raises the alert for the ban
+// 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.ruleBlocked = true
+
+		return &verdict{action: requestlog.ActionRuleBlocked, figures: figures}
+	case rules.ActionBan:
+		rq.attack = true
+		rq.banForAttack(now, bans.Notes{RuleID: last.ID, Target: last.Target})
+
+		return &verdict{action: requestlog.ActionBanned, figures: figures}
+	default:
+		return nil
+	}
+}

internal/discriminator/rulefiles_test.go

@@ -93,6 +93,35 @@ func TestEachRuleAction(t *testing.T) {
 	s.get(client, http.StatusTooManyRequests, requestlog.ActionBanned)
 }
 
+func TestEachRuleActionAddsTheExploitSignatureTag(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		rulesDir: writeRules(t, "noted path log ^/noted$\n"+testRules),
+	})
+
+	wantTags(t, s.request(client, "/noted", http.StatusOK, requestlog.ActionForward),
+		"exploitsignature")
+	wantTags(t, s.request(client, "/blocked", http.StatusForbidden,
+		requestlog.ActionRuleBlocked), "exploitsignature")
+	wantTags(t, s.get(client, http.StatusOK, requestlog.ActionForward))
+}
+
+func TestRuleRefusalNamesItsHeuristicAndTheRule(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{
+		rulesDir: writeRules(t, "noted path log ^/\n"+testRules),
+	})
+
+	line := s.request(client, "/blocked", http.StatusForbidden,
+		requestlog.ActionRuleBlocked)
+	wantHeuristic(t, line, "rule_files", `{"rule_id": "blocked", "rule_action": "block"}`)
+
+	line = s.request(client, "/.env", http.StatusForbidden, requestlog.ActionBanned)
+	wantHeuristic(t, line, "rule_files", `{"rule_id": "probe", "rule_action": "ban"}`)
+}
+
 func TestNextClearSignOfAttackAfterABanBansPermanently(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/rules.go

@@ -1,64 +0,0 @@
-package discriminator
-
-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
-// 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.
-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 ""
-	}
-}

internal/discriminator/staticlists_test.go

@@ -32,7 +32,7 @@ func TestAllowNetsSkipEveryCheck(t *testing.T) {
 		trustedProxies:     trustLocalhost,
 		allowNets:          "198.51.100.0/24",
 		denyNets:           fromKP,
-		deniedCountries:    "kp",
+		tagDeny:            denyKP,
 		rateLimitPerMinute: "1",
 	})
 
@@ -85,7 +85,7 @@ func TestDenyNetsRefuseBeforeTheLookup(t *testing.T) {
 	addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
 		trustedProxies: trustLocalhost,
 		denyNets:       "203.0.113.0/24",
-		deniedCountries: "kp",
+		tagDeny:        denyKP,
 	})
 
 	req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
@@ -104,6 +104,15 @@ func TestDenyNetsRefuseBeforeTheLookup(t *testing.T) {
 	}
 }
 
+func TestDenyNetsRefusalNamesItsHeuristicAndNetblock(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{denyNets: clientsNet})
+
+	line := s.get(client, http.StatusForbidden, requestlog.ActionDenied)
+	wantHeuristic(t, line, "deny_nets", `{"netblock": "`+clientsNet+`"}`)
+}
+
 func TestRequestRefusedByDenyNetsIsNotCounted(t *testing.T) {
 	t.Parallel()
 
@@ -133,7 +142,7 @@ func TestRateLimitExemptNetsAreNeitherCountedNorRefused(t *testing.T) {
 		trustedProxies:      trustLocalhost,
 		lookupTimeout:       "1h",
 		rateLimitExemptNets: listedAddr + "," + fromKP,
-		deniedCountries:     "kp",
+		tagDeny:             denyKP,
 		rateLimitPerMinute:  "1",
 	})
 
@@ -145,7 +154,7 @@ func TestRateLimitExemptNetsAreNeitherCountedNorRefused(t *testing.T) {
 		{listedAddr, http.StatusOK, requestlog.ActionForward},
 		{unlistedAddr, http.StatusOK, requestlog.ActionForward},
 		{unlistedAddr, http.StatusForbidden, requestlog.ActionRateLimited},
-		{fromKP, http.StatusForbidden, requestlog.ActionCountryDenied},
+		{fromKP, http.StatusForbidden, requestlog.ActionDenied},
 	})
 }
 

internal/discriminator/tagdeny.go

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

internal/discriminator/tagdeny_test.go

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

internal/discriminator/taglists.go

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

internal/discriminator/taglists_test.go

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

internal/discriminator/trappaths.go

@@ -0,0 +1,39 @@
+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/requestlog"
+	"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
+	rq.banForAttack(now, bans.Notes{TrapPath: path})
+
+	return &verdict{
+		action:  requestlog.ActionBanned,
+		figures: map[string]any{"path": path},
+	}
+}

internal/discriminator/trappaths_test.go

@@ -83,6 +83,16 @@ func TestTrapPathBansAsABanRuleDoes(t *testing.T) {
 	}
 }
 
+func TestTrapPathRefusalNamesItsHeuristicAndPath(t *testing.T) {
+	t.Parallel()
+
+	s, _, _ := startWithClock(t, "", map[string]string{trapPaths: trapPathList})
+
+	line := s.request(client, "/wp-login.php?redirect_to=x", http.StatusForbidden,
+		requestlog.ActionBanned)
+	wantHeuristic(t, line, "trap_paths", `{"path": "/wp-login.php"}`)
+}
+
 func TestTrapPathMatchesThePathDecodedOnce(t *testing.T) {
 	t.Parallel()
 

internal/metrics/busiest.go

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

internal/reputation/reputation.go

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

internal/requestlog/requestlog.go

@@ -38,9 +38,10 @@ const (
 	// ActionDenied is a request refused because its client is in
 	// SWW_DENY_NETS, in a blocklist while SWW_BLOCKLIST_ACTION is deny,
 	// or listed by a DNSBL zone, or scored a hit by AbuseIPDB, while
-	// SWW_REPUTATION_ACTION is deny.
+	// SWW_REPUTATION_ACTION is deny, or that carries a tag in SWW_TAG_DENY.
 	ActionDenied = "denied"
-	// ActionCountryDenied is a request refused for its client's country.
+	// ActionCountryDenied is a request refused because its client's country
+	// is not in SWW_EXCLUSIVELY_ALLOWED_COUNTRIES.
 	ActionCountryDenied = "country_denied"
 	// ActionAdmin is a request discriminator answered at one of its own
 	// endpoints, or a question about a path under /_sww/.
@@ -131,6 +132,16 @@ type Line struct {
 	// ActionRuleBlocked, ActionWAFBlocked, or, in discriminator, ActionTooLarge
 	// for the header limits.
 	WouldAction string `json:"would_action,omitempty"`
+	// Heuristic is the name of the heuristic that refused the request, in
+	// observe mode too, and HeuristicFigures are the figures it acted on, by
+	// name.
+	Heuristic        string         `json:"heuristic,omitempty"`
+	HeuristicFigures map[string]any `json:"heuristic_figures,omitempty"`
+	// AfterAnswerHeuristic and AfterAnswerHeuristicFigures are the same for
+	// the heuristic that banned the client after discriminator answered the
+	// request.
+	AfterAnswerHeuristic        string         `json:"after_answer_heuristic,omitempty"`
+	AfterAnswerHeuristicFigures map[string]any `json:"after_answer_heuristic_figures,omitempty"` //nolint:lll // a struct tag cannot be split
 	// LimitPercent and LimitPercentSetting are, for a request the rate
 	// limits counted whose client a biased threshold gives a percentage of
 	// the rate limits below 100, that percentage and the setting that gave
@@ -162,6 +173,8 @@ type Line struct {
 	// whose verdict lists it, their keys masked, then abuseipdb when its
 	// score is a hit.
 	Reputation []string `json:"reputation,omitempty"`
+	// Tags are the request's tags, sorted.
+	Tags []string `json:"tags,omitempty"`
 	// Offence is the offence the request was held as, OffenceLimit.
 	Offence string `json:"offence,omitempty"`
 	// BanExpires is when the ban the request made, or was refused under,

internal/sww/sww_test.go

@@ -618,7 +618,7 @@ func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 		instanceName:   instance,
 		lookupSource:   "file",
 		lookupDBPath:   path,
-		"SWW_DENIED_COUNTRIES": "kp",
+		"SWW_TAG_DENY": "country=kp",
 		// The requests sent until a replacement takes effect, and those
 		// for the metrics, must not break a rate limit, whose ban would
 		// refuse them too.
@@ -1280,7 +1280,7 @@ func wantStartingLine(t *testing.T, line map[string]any, dir string) {
 		"SWW_RATE_LIMIT_PER_HOUR":           "1500",
 		rateLimitPerDay:                     "6000",
 		"SWW_RATE_LIMIT_EXEMPT_PATHS":       "",
-		"SWW_DENIED_COUNTRIES":              "",
+		"SWW_TAG_DENY":                      "",
 		"SWW_EXCLUSIVELY_ALLOWED_COUNTRIES": "",
 		"SWW_BAN_RESPONSE":                  "403",
 		"SWW_LIMIT_BAN_DURATION":            "1h",