smallwebwaf/internal/rproxy/question_test.go

package rproxy_test

import (
	"bytes"
	"crypto/rand"
	"io"
	"maps"
	"net/http"
	"net/http/httptest"
	"slices"
	"strconv"
	"strings"
	"testing"

	"sneak.berlin/go/smallwebwaf/internal/discriminator"
)

// questionBodyMaxBytes is the most of a body a question carries.
const questionBodyMaxBytes = discriminator.QuestionBodyMaxBytes

// chunked is the encoding of a body whose length the visitor did not announce.
const chunked = "chunked"

// pathGoReencodes is a path Go's client would decode and escape again, %2F turned
// into / and | into %7C, unless told to send it as it is. A test sets it as the
// visitor's URL.Opaque, so that the visitor sends it unchanged too.
const pathGoReencodes = "/some%2Fpath/with%20space|pipe"

func TestQuestionIsTheVisitorsRequestWithRProxysHeaders(t *testing.T) {
	t.Parallel()

	standIn := startDiscriminator(t, allow)
	app := startApp(t, greet)
	addr, _ := startRProxy(t, standIn.URL, app.URL, nil)

	const target = pathGoReencodes + "?b=2&a=1&bad=%zz;x"

	req := newRequest(t, http.MethodDelete, addr, target, http.NoBody)
	req.URL.Opaque = pathGoReencodes
	req.Host = site
	req.Header.Set("X-Test", "from the visitor")
	req.Header.Set(forwardedForHeader, "198.51.100.1")
	req.Header.Set(forwardedProtoHeader, "gopher")
	req.Header.Set(requestIDHeader, "the-visitor's")
	req.Header.Set(discriminator.ClientHeader, "198.51.100.2")
	req.Header.Set(discriminator.PeerHeader, "198.51.100.3")
	req.Header.Set(discriminator.ContentLengthHeader, "12345")
	// Go's client then sends no User-Agent, so that one in the question would be
	// Go's own.
	req.Header["User-Agent"] = nil

	wantGreeting(t, visit(t, req))

	asked := standIn.question(t)
	if asked.method != http.MethodDelete || asked.target != target ||
		asked.host != site {
		t.Errorf("asked about %s %s at %s", asked.method, asked.target, asked.host)
	}

	if asked.header.Get(requestIDHeader) == "the-visitor's" {
		t.Error("the question carries the visitor's id")
	}

	// Exactly these: visit's connection has the visitor send Connection: close.
	want := http.Header{}
	want.Set("Connection", "close")
	want.Set("X-Test", "from the visitor")
	want.Set(forwardedForHeader, "198.51.100.1")
	want.Set(forwardedProtoHeader, "http")
	want.Set(requestIDHeader, asked.header.Get(requestIDHeader))
	want.Set(discriminator.ClientHeader, localhost)
	want.Set(discriminator.PeerHeader, localhost)

	if !maps.EqualFunc(asked.header, want, slices.Equal) {
		t.Errorf("the question's headers are %v, want %v", asked.header, want)
	}
}

func TestQuestionNamesTheVisitorATrustedProxySpeaksFor(t *testing.T) {
	t.Parallel()

	const visitor = "203.0.113.9"

	for _, tc := range []struct {
		name, trusted, client, proto, forwarded string
	}{
		{
			"from a trusted proxy", localhost + "/32", visitor, "https",
			visitor + ", " + localhost,
		},
		{"from a peer not trusted", "10.0.0.0/8", localhost, "http", localhost},
	} {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			standIn := startDiscriminator(t, allow)
			forwarded := make(chan http.Header, 1)
			app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
				forwarded <- r.Header.Clone()

				greet(w, r)
			})
			addr, out := startRProxy(t, standIn.URL, app.URL, map[string]string{
				trustedProxies: tc.trusted,
			})

			req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
			req.Header.Set(forwardedForHeader, visitor)
			req.Header.Set(forwardedProtoHeader, "https")
			wantGreeting(t, visit(t, req))

			asked := standIn.question(t)
			if asked.header.Get(discriminator.ClientHeader) != tc.client ||
				asked.header.Get(discriminator.PeerHeader) != localhost ||
				asked.header.Get(forwardedForHeader) != visitor ||
				asked.header.Get(forwardedProtoHeader) != tc.proto {
				t.Errorf("the question's headers are %v", asked.header)
			}

			if line := out.requestLine(t); line["client_ip"] != tc.client {
				t.Errorf("line %v, want client_ip %s", line, tc.client)
			}

			if got := (<-forwarded).Get(forwardedForHeader); got != tc.forwarded {
				t.Errorf("the app saw %s %q, want %q", forwardedForHeader, got, tc.forwarded)
			}
		})
	}
}

func TestQuestionNamesTheClientAsTheForwardedAddressesSay(t *testing.T) {
	t.Parallel()

	for _, tc := range []struct {
		name   string
		header []string
		client string
	}{
		{
			"the first address outside the trusted proxies, from the right",
			[]string{"198.51.100.7, 203.0.113.9, 10.0.0.2"}, "203.0.113.9",
		},
		{
			"the leftmost, when every address is a trusted proxy",
			[]string{"10.0.0.5, 10.0.0.2"}, "10.0.0.5",
		},
		{"the peer, with no header", nil, localhost},
		{
			"the last address read, before an entry that is not an address",
			[]string{"203.0.113.9, unknown, 10.0.0.2"}, "10.0.0.2",
		},
		{
			"read as one list, with several header lines",
			[]string{"2001:db8::7", "10.0.0.2"}, "2001:db8::7",
		},
	} {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			standIn := startDiscriminator(t, allow)
			app := startApp(t, greet)
			addr, _ := startRProxy(t, standIn.URL, app.URL, map[string]string{
				trustedProxies: localhost + "/32,10.0.0.0/8",
			})

			req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
			req.Header[forwardedForHeader] = tc.header
			wantGreeting(t, visit(t, req))

			if got := standIn.question(t).header.Get(discriminator.ClientHeader); got !=
				tc.client {
				t.Errorf("the question names %s, want %s", got, tc.client)
			}
		})
	}
}

// randomBytes returns n random bytes.
func randomBytes(n int) []byte {
	body := make([]byte, n)
	_, _ = rand.Read(body) // it never returns an error

	return body
}

func TestFirst64KiBReachDiscriminatorAndTheWholeBodyTheApp(t *testing.T) {
	t.Parallel()

	for _, size := range []int{
		1, questionBodyMaxBytes - 1, questionBodyMaxBytes, questionBodyMaxBytes + 1,
		5 * questionBodyMaxBytes,
	} {
		for _, announced := range []bool{true, false} {
			name := strconv.Itoa(size) + " bytes, length announced: " +
				strconv.FormatBool(announced)

			t.Run(name, func(t *testing.T) {
				t.Parallel()

				body := randomBytes(size)
				standIn := startDiscriminator(t, allow)
				received := make(chan []byte, 1)
				app := startApp(t, func(w http.ResponseWriter, r *http.Request) {
					whole, _ := io.ReadAll(r.Body)
					received <- whole

					greet(w, r)
				})
				addr, _ := startRProxy(t, standIn.URL, app.URL, nil)

				req := newRequest(t, http.MethodPost, addr, "/", bytes.NewReader(body))
				if !announced {
					// Go's client sends a body of unknown length in chunks.
					req.ContentLength = -1
				}

				wantGreeting(t, visit(t, req))

				asked := standIn.question(t)
				want := body[:min(size, questionBodyMaxBytes)]
				wantQuestionBody(t, asked, want, size, announced)

				if !bytes.Equal(<-received, body) {
					t.Error("the app did not get the whole body")
				}

				if report := standIn.report(t); report.RequestBytes != int64(size) {
					t.Errorf("report %+v, of %d bytes", report, size)
				}
			})
		}
	}
}

// wantQuestionBody checks the body a question carries, want, and how it gives
// the length of the visitor's body, of size bytes.
func wantQuestionBody(
	t *testing.T, asked question, want []byte, size int, announced bool,
) {
	t.Helper()

	if !bytes.Equal(asked.body, want) {
		t.Errorf("the question carries %d bytes, want the first %d", len(asked.body),
			len(want))
	}

	values := asked.header.Values(discriminator.ContentLengthHeader)

	if announced {
		if !slices.Equal(values, []string{strconv.Itoa(size)}) ||
			asked.contentLength != int64(len(want)) {
			t.Errorf("announced %v and length %d, want %d and %d", values,
				asked.contentLength, size, len(want))
		}

		return
	}

	if len(values) != 0 || !slices.Equal(asked.transferEncoding, []string{chunked}) {
		t.Errorf("announced %v and encoded %v, want none and chunked", values,
			asked.transferEncoding)
	}
}

func TestDenyNeedsOnlyTheFirstPartOfALargeBody(t *testing.T) {
	t.Parallel()

	standIn := startDiscriminator(t, deny)
	app := startApp(t, greet)
	addr, _ := startRProxy(t, standIn.URL, app.URL, nil)

	// Far more announced than sent. Go's server does not wait for that much, so
	// the answer comes at once.
	conn := dial(t, addr)
	send(t, conn, post+announcedLength(100*questionBodyMaxBytes)+
		strings.Repeat("x", questionBodyMaxBytes))

	if status := readStatus(t, conn); status != http.StatusForbidden {
		t.Errorf("status %d, want discriminator's 403", status)
	}

	if report := standIn.report(t); report.RequestBytes != questionBodyMaxBytes {
		t.Errorf("report %+v, want the first part's bytes", report)
	}
}

func TestAQuestionCarriesItsBodyWhateverTheMethod(t *testing.T) {
	t.Parallel()

	for _, tc := range []struct {
		name, framing, body string
		encoding            []string
	}{
		{
			chunked, "Transfer-Encoding: chunked\r\n\r\n4\r\nbody\r\n0\r\n\r\n", "body",
			[]string{chunked},
		},
		{
			"chunked and empty", "Transfer-Encoding: chunked\r\n\r\n0\r\n\r\n", "",
			[]string{chunked},
		},
		{"with its length", announcedLength(4) + "body", "body", nil},
	} {
		for _, method := range []string{
			http.MethodGet, http.MethodDelete, http.MethodPost,
		} {
			t.Run(method+" "+tc.name, func(t *testing.T) {
				t.Parallel()

				standIn := startDiscriminator(t, deny)
				addr, _ := startRProxy(t, standIn.URL, nowhere, nil)

				conn := dial(t, addr)
				send(t, conn, method+" /x HTTP/1.1\r\nHost: site.example\r\n"+tc.framing)

				if status := readStatus(t, conn); status != http.StatusForbidden {
					t.Errorf("status %d, want discriminator's 403", status)
				}

				asked := standIn.question(t)
				if string(asked.body) != tc.body ||
					!slices.Equal(asked.transferEncoding, tc.encoding) {
					t.Errorf("the question carries %q, encoded %v, want %q, encoded %v",
						asked.body, asked.transferEncoding, tc.body, tc.encoding)
				}
			})
		}
	}
}

func TestAMethodNotPassedOnIsAnswered405(t *testing.T) {
	t.Parallel()

	for _, method := range []string{http.MethodTrace, "MKCALENDAR", "BREW"} {
		t.Run(method, func(t *testing.T) {
			t.Parallel()

			standIn := startDiscriminator(t, allow)
			app := startApp(t, func(http.ResponseWriter, *http.Request) {
				t.Error("the app was asked")
			})
			addr, out := startRProxy(t, standIn.URL, app.URL, nil)

			got := visit(t, newRequest(t, method, addr, "/", http.NoBody))
			if got.status != http.StatusMethodNotAllowed ||
				got.header.Get("Allow") != "GET, HEAD, POST, OPTIONS, PUT, DELETE, PATCH, QUERY, "+
					"PROPFIND, PROPPATCH, MKCOL, COPY, MOVE, REPORT, SEARCH, LOCK, UNLOCK" {
				t.Errorf("answered %+v, want 405 naming the methods passed on", got)
			}

			line := out.requestLine(t)
			if line["status"] != float64(http.StatusMethodNotAllowed) ||
				line["disposition"] != nil || line["default_disposition"] != nil {
				t.Errorf("line %v, want status 405 and no disposition", line)
			}

			if len(standIn.questions) != 0 {
				t.Error("discriminator was asked")
			}

			standIn.wantNoReport(t)
		})
	}
}

func TestEachMethodPassedOnReachesDiscriminatorAndTheApp(t *testing.T) {
	t.Parallel()

	for _, method := range []string{
		http.MethodGet, http.MethodHead, http.MethodPost, http.MethodOptions,
		http.MethodPut, http.MethodDelete, http.MethodPatch, "QUERY",
		"PROPFIND", "PROPPATCH", "MKCOL", "COPY", "MOVE", "REPORT", "SEARCH",
		"LOCK", "UNLOCK",
	} {
		t.Run(method, func(t *testing.T) {
			t.Parallel()

			reached := make(chan string, 1)
			standIn := startDiscriminator(t, allow)
			app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
				reached <- r.Method
			})
			addr, _ := startRProxy(t, standIn.URL, app.URL, nil)

			got := visit(t, newRequest(t, method, addr, "/", http.NoBody))
			if got.status != http.StatusOK {
				t.Errorf("answered %+v, want the app's 200", got)
			}

			if asked := standIn.question(t); asked.method != method {
				t.Errorf("discriminator was asked about %s", asked.method)
			}

			if atApp := <-reached; atApp != method {
				t.Errorf("the app was asked %s", atApp)
			}
		})
	}
}

func TestARequestThatCannotGoToDiscriminatorAsSentIsRefused(t *testing.T) {
	t.Parallel()

	const host = "Host: site.example\r\n\r\n"

	for name, request := range map[string]string{
		"a target of a scheme":    "GET x:admin HTTP/1.1\r\n" + host,
		"a target of a URL":       "GET http://site.example/ HTTP/1.1\r\n" + host,
		"a host Go will not send": "GET http://a<b/ HTTP/1.1\r\n" + host,
		"a target of a host":      "GET site.example:443 HTTP/1.1\r\n" + host,
		"a target of *":           "GET * HTTP/1.1\r\n" + host,
		"a target of //":          "GET //x/y HTTP/1.1\r\n" + host,
		"a target of // escaped":  "GET //x%2Fadmin| HTTP/1.1\r\n" + host,
		"an empty Host":           "GET / HTTP/1.1\r\nHost:\r\n\r\n",
		"HTTP/1.0 with no Host":   "GET / HTTP/1.0\r\n\r\n",
		"a Host with a zone":      "GET / HTTP/1.1\r\nHost: [fe80::1%25eth0]:80\r\n\r\n",
		"two User-Agents": "GET / HTTP/1.1\r\nUser-Agent: a\r\nUser-Agent: b\r\n" +
			host,
	} {
		t.Run(name, func(t *testing.T) {
			t.Parallel()

			standIn := startDiscriminator(t, allow)
			app := startApp(t, greet)
			addr, out := startRProxy(t, standIn.URL, app.URL, nil)

			conn := dial(t, addr)
			send(t, conn, request)

			if status := readStatus(t, conn); status != http.StatusBadRequest {
				t.Errorf("status %d, want 400", status)
			}

			line := out.requestLine(t)
			if line["status"] != float64(http.StatusBadRequest) ||
				line["disposition"] != nil || line["default_disposition"] != nil {
				t.Errorf("line %v, want status 400 and no disposition", line)
			}

			if len(standIn.questions) != 0 {
				t.Error("discriminator was asked")
			}

			standIn.wantNoReport(t)
		})
	}
}

func TestAHostWithAPercentSignButNoBracketGoesToDiscriminator(t *testing.T) {
	t.Parallel()

	const host = "a%b"

	standIn := startDiscriminator(t, allow)
	app := startApp(t, greet)
	addr, _ := startRProxy(t, standIn.URL, app.URL, nil)

	conn := dial(t, addr)
	send(t, conn, "GET / HTTP/1.1\r\nHost: "+host+"\r\n\r\n")

	if status := readStatus(t, conn); status != http.StatusOK {
		t.Errorf("status %d, want the app's 200", status)
	}

	if asked := standIn.question(t); asked.host != host {
		t.Errorf("asked about the host %q, want %q", asked.host, host)
	}
}

func TestATrustedPeerWithNoForwardedProtoIsAskedAboutAsHTTP(t *testing.T) {
	t.Parallel()

	const want = "http"

	standIn := startDiscriminator(t, allow)
	app := startApp(t, greet)
	addr, _ := startRProxy(t, standIn.URL, app.URL, map[string]string{
		trustedProxies: localhost + "/32",
	})

	wantGreeting(t, get(t, addr, "/"))

	asked := standIn.question(t)
	if got := asked.header.Get(forwardedProtoHeader); got != want {
		t.Errorf("the question's %s is %q, want %s", forwardedProtoHeader, got, want)
	}
}

func TestAQuestionNamesNoZone(t *testing.T) {
	t.Parallel()

	for _, tc := range []struct {
		name, remoteAddr, forwardedFor, client, peer string
	}{
		{"from a link-local peer", "[fe80::1%eth0]:1234", "", "fe80::1", "fe80::1"},
		{
			"from X-Forwarded-For through a trusted peer", localhost + ":1234",
			"2001:db8::1%eth0", "2001:db8::1", localhost,
		},
	} {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			standIn := startDiscriminator(t, deny)
			app := startApp(t, greet)
			_, out, server := startServer(t, standIn.URL, app.URL, map[string]string{
				trustedProxies: localhost + "/32",
			})

			req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", http.NoBody)
			req.RemoteAddr = tc.remoteAddr
			req.Header.Set(forwardedForHeader, tc.forwardedFor)

			server.Handler.ServeHTTP(httptest.NewRecorder(), req)

			asked := standIn.question(t)
			if asked.header.Get(discriminator.ClientHeader) != tc.client ||
				asked.header.Get(discriminator.PeerHeader) != tc.peer {
				t.Errorf("the question's headers are %v", asked.header)
			}

			if line := out.requestLine(t); line["client_ip"] != tc.client {
				t.Errorf("line %v, want client_ip %s", line, tc.client)
			}
		})
	}
}