Settings code: one file per daemon (closes #227)

internal/config now keeps waf's settings in waf.go and rproxy's in
rproxy.go. config.go keeps what both read: the package doc,
SWW_COMMAND, the environment reader, listen addresses, sizes and
netblock lists. The app URL reader and the default trusted proxies,
which only rproxy uses, move to rproxy.go. config_test.go becomes
waf_test.go, beside rproxy_test.go. Code is moved, not changed.

Model: opus-5-5

SPEC.md

@@ -828,10 +828,23 @@ The changes hold in front of every app, and no setting undoes them:
         - branches and tags;
         - packages, on its pages and in its API.
 
-        A user's or an organisation's page is any path of one segment, so on
+        A user's or an organisation's page has a path of one segment, such as
-        every such path, on any app, `q` skips these rules, for example on
+        `/alice`. So on any app, `q` skips these rules on every path of one
-        `/search`. A path that ends in `.php`, such as `/index.php`, keeps
+        segment, such as `/search`. But it skips 932250 only on a path made of
-        932250, so `ls -la` is refused there.
+        the characters a name may hold: letters, digits, `-`, `_` and dots, the
+        first a letter or digit. So `ls -la` is refused on
+        `/login.jsp;jsessionid=abc`. `q` also keeps 932250 on a path that ends
+        in a server-side script's extension, such as `/index.php`. The
+        extensions are these, in upper or lower case:
+        - `.php`;
+        - `.phtml`;
+        - `.php5`;
+        - `.cgi`;
+        - `.pl`;
+        - `.py`;
+        - `.asp`;
+        - `.aspx`;
+        - `.jsp`.
 
         Some of these searches also skip the rule for Java class names (944130),
         which refused `org.apache.commons.logging`.

internal/config/rproxy.go

@@ -48,7 +48,17 @@ type RProxy struct {
 	settings []slog.Attr
 }
 
+// defaultUpstreamURL is the default of SWRP_UPSTREAM_URL.
+const defaultUpstreamURL = "http://127.0.0.1:8081"
+
+// privateRanges are the private address ranges, the default trusted
+// proxies.
+const privateRanges = "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"
+
 var (
+	errNotUpstreamURL = errors.New(
+		"is not a URL with only a scheme, a host and an optional port, " +
+			"such as http://127.0.0.1:8081")
 	errNeedsWAFBackend = errors.New(
 		"is required: it is waf's URL, such as http://waf:8080")
 	errNotDisposition  = errors.New("is not allow or deny")
@@ -124,6 +134,14 @@ func (c *RProxy) LogValue() slog.Value {
 	return slog.GroupValue(c.settings...)
 }
 
+// appURL reads a setting that is the app's URL.
+func (e *environment) appURL(name, defaultValue string) *url.URL {
+	upstream, err := parseUpstreamURL(e.value(name, defaultValue))
+	e.check(name, err)
+
+	return upstream
+}
+
 // wafBackend reads the setting that is waf's URL, which must be set.
 func (e *environment) wafBackend(name string) *url.URL {
 	value := e.value(name, "")
@@ -190,3 +208,32 @@ func parseMilliseconds(value string) (time.Duration, bool) {
 
 	return time.Duration(n) * time.Millisecond, true
 }
+
+// parseUpstreamURL reads the app's URL: http or https, a host and an
+// optional port from 1 to 65535, and nothing else, since the request's
+// own path and query go to the app unchanged.
+func parseUpstreamURL(value string) (*url.URL, error) {
+	upstream, err := url.Parse(value)
+	if err != nil {
+		return nil, fmt.Errorf("%q %w", value, errNotUpstreamURL)
+	}
+
+	onlySchemeAndHost := (upstream.Scheme == "http" || upstream.Scheme == "https") &&
+		upstream.Hostname() != "" && upstream.User == nil &&
+		upstream.Opaque == "" &&
+		(upstream.Path == "" || upstream.Path == "/") &&
+		upstream.RawQuery == "" &&
+		upstream.Fragment == ""
+	if !onlySchemeAndHost {
+		return nil, fmt.Errorf("%q %w", value, errNotUpstreamURL)
+	}
+
+	if upstream.Port() != "" {
+		port, err := strconv.ParseUint(upstream.Port(), 10, 16)
+		if err != nil || port == 0 {
+			return nil, fmt.Errorf("%q %w", value, errNotUpstreamURL)
+		}
+	}
+
+	return upstream, nil
+}

internal/coreruleset/coreruleset_test.go

@@ -1077,24 +1077,33 @@ func TestGiteaSearchOnAUsersOrAnOrganisationsPageLetsLsThrough(t *testing.T) {
 		wantResult(t, crs, get(target), coreruleset.Result{})
 	}
 
-	// A path that ends in .php, another field, and a path of two segments
+	// 932250 still applies on a path that ends in a server-side script's
-	// keep 932250.
+	// extension or holds a character no name holds, to another field, and on
+	// a path of two segments.
 	for _, target := range []string{
 		"/index.php?q=ls%20-la",
 		"/INDEX.PHP?q=ls%20-la",
 		"/index%2Ephp?q=ls%20-la",
+		"/search.cgi?q=ls%20-la",
+		"/login.jsp;jsessionid=abc?q=ls%20-la",
 		"/alice?tab=ls%20-la",
 		"/alice/tools?q=ls%20-la",
 	} {
 		wantResult(t, crs, get(target), matched(932250))
 	}
 
-	// A command after a ";" is still refused on those pages.
+	// A command after a ";" in q is still refused on each of these paths.
 	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
 
-	target := "/alice?tab=repositories&q=" + commandInjection
+	for _, target := range []string{
-	if got := inspect(t, crs, get(target)); got.Score < threshold {
+		"/alice?tab=repositories&q=",
-		t.Errorf("%s let through: %+v", target, got)
+		"/index.php?q=",
+		"/wp-login.php?q=",
+		"/alice/tools?q=",
+	} {
+		if got := inspect(t, crs, get(target+commandInjection)); got.Score < threshold {
+			t.Errorf("%s%s let through: %+v", target, commandInjection, got)
+		}
 	}
 }
 

internal/coreruleset/gitea.conf

@@ -146,11 +146,14 @@ SecRule REQUEST_FILENAME "@rx ^/[^/]+$" \
     ctl:ruleRemoveTargetById=932120;ARGS:q,\
     ctl:ruleRemoveTargetById=932260;ARGS:q"
 
-# On those pages q skips 932250 too, which refused ls -la. A path that ends in
+# On those pages q skips 932250 too, which refused ls -la, but only on a path
-# .php, such as /index.php, keeps it.
+# made of the characters a user's or an organisation's name may hold. Those are
-SecRule REQUEST_FILENAME "@rx ^/[^/]+$" \
+# letters, digits, -, _ and dots, the first a letter or digit, so
-    "id:900605,phase:1,pass,nolog,chain"
+# /login.jsp;jsessionid=abc keeps 932250. A path that ends in a server-side
-    SecRule REQUEST_FILENAME "!@rx \.php$" \
+# script's extension keeps it too, such as /index.php or /search.cgi.
+SecRule REQUEST_FILENAME "@rx ^/[0-9A-Za-z][-.\w]*$" \
+    "id:900606,phase:1,pass,nolog,chain"
+    SecRule REQUEST_FILENAME "!@rx \.(?:php|phtml|php5|cgi|pl|py|asp|aspx|jsp)$" \
         "t:lowercase,ctl:ruleRemoveTargetById=932250;ARGS:q"
 
 # These requests name a file in the path, which skips these rules there:

internal/coreruleset/testdata/forgejo-requests.txt

@@ -4,9 +4,7 @@
 # the API and the generic package registry, and by crane on the container
 # registry. Each line is one request as JSON. Names, addresses and passwords
 # are invented. The browser's User-Agent is an ordinary Chrome's. A body or a
-# multipart part that is not text is written as base64. The searches for ls -la
+# multipart part that is not text is written as base64.
-# on a user's and an organisation's page are the recorded searches for python3
-# there, with q changed.
 {"method": "GET", "target": "/", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate"], "body": ""}
 {"method": "GET", "target": "/assets/js/webcomponents.js?v=17.0.1~gitea-1.22.0", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: */*", "Referer: http://example.com/", "Accept-Encoding: gzip, deflate"], "body": ""}
 {"method": "GET", "target": "/assets/css/index.css?v=17.0.1~gitea-1.22.0", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/css,*/*;q=0.1", "Referer: http://example.com/", "Accept-Encoding: gzip, deflate"], "body": ""}
@@ -104,7 +102,6 @@
 {"method": "GET", "target": "/explore/users?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/explore/organizations?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice?tab=repositories&q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/alice?tab=repositories&q=ls%20-la", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/avatars/53bce4f1dfa0fe8e7ca126f91b35d3a6?size=64", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice?tab=repositories&q=python3", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice/tools/commits/branch/main/search?q=python3&all=true", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice/-/packages?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
@@ -471,4 +468,7 @@
 {"method": "GET", "target": "/repo-avatars/f9e66d43eb4888aac5d9d93745661631a09b4c73969226a3e89b2911ece215ba", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/avatars/53bce4f1dfa0fe8e7ca126f91b35d3a6?size=64", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/acme?q=python3&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/acme?q=ls%20-la&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/alice?q=ls+-la&tab=repositories&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/alice?tab=repositories", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/acme?q=ls+-la&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/acme?q=powershell&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/acme?q=.htaccess&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}

internal/coreruleset/testdata/gitea-requests.txt

@@ -91,6 +91,17 @@
 /explore/organizations?q=docker-ci
 /api/v1/users/search?q=docker-ci
 
+# Searches of the repositories on a user's and an organisation's page, recorded
+# from gitea 1.27.3.
+/alice?tab=repositories&q=ls+-la&sort=recentupdate
+/alice?tab=repositories&q=python3&sort=recentupdate
+/alice?tab=repositories&q=powershell&sort=recentupdate
+/alice?tab=repositories&q=.htaccess&sort=recentupdate
+/acme?q=ls+-la&sort=recentupdate
+/acme?q=python3&sort=recentupdate
+/acme?q=powershell&sort=recentupdate
+/acme?q=.htaccess&sort=recentupdate
+
 # Pages, raw files and edit pages of files, and the API's call for their
 # contents.
 /owner/repo/src/branch/main/package.json