webhooker/internal/middleware/logbound_test.go

package middleware_test

// This file covers the log lines OUTSIDE the access log that carry a
// client-chosen value. accesslog_test.go bounds the one INFO line the
// Logging middleware writes; these are the separate slog calls that
// were never in that sweep and so never got the budget:
//
//   - MaxBodySize's 413 rejection, at WARN, registered ahead of
//     RequireAuth and therefore reachable unauthenticated at a URL of
//     the client's choosing.
//   - CSRF's 403 rejection, at WARN, also registered ahead of
//     RequireAuth.
//   - The rate limiters' 429 rejection, at WARN, on the
//     unauthenticated receiver among others.
//   - RequireAuth's own unauthenticated-request line, at DEBUG.
//
// Every case here holds the ENCODED line to
// middleware.MaxAccessLogLineBytes, under both handlers
// internal/logger can install, against 8 KB of client-chosen text
// built out of the characters those handlers escape. A budget spent
// in raw bytes passes the plain-ASCII cases and fails the rest.

import (
	"bytes"
	"context"
	"io"
	"log/slog"
	"net/http"
	"net/http/httptest"
	"net/url"
	"strings"
	"testing"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/webhooker/internal/config"
	"sneak.berlin/go/webhooker/internal/middleware"
)

// bodyLimitBytes is the MaxBodySize cap these tests install. Any
// declared Content-Length above it takes the 413 branch.
const bodyLimitBytes = 1024

// declaredBodyBytes is the Content-Length an oversize request
// declares. Nothing is actually sent: the 413 branch fires off the
// declaration alone, which is what makes the attack free.
const declaredBodyBytes = bodyLimitBytes * 2

// receiverLimitPerMinute is the per-entrypoint receiver limit these
// tests install. The aggregate limiter sits at ten times this, so a
// flood stays under it and the rejections come from the
// per-entrypoint limiter, which is the one that logs the path.
const receiverLimitPerMinute = 8

// escapeFills are the characters a client can put in a request that
// the log handlers then escape, coming out wider than they went in.
// A budget counted in raw bytes lets any of them buy a field several
// times its nominal size.
//
// U+1000C is the case the JSON handler alone does not reach: it is
// unassigned, so it is non-printable, and strconv.Quote spells a
// non-printable rune at or above U+10000 as a ten-byte \UXXXXXXXX
// while the JSON handler passes its four UTF-8 bytes through. Only
// the text-handler shape of these tests holds that charge honest.
func escapeFills() map[string]string {
	return map[string]string{
		"plain":     "x",
		"quote":     `"`,
		"backslash": `\`,
		"tab":       "\t",
		"newline":   "\n",
		// A C0 control neither handler has a short escape for, so
		// each one costs six bytes on the line against the single
		// byte it cost to send. This is the widest multiplier a
		// client can drive, and the case a raw-byte budget breaks
		// on first.
		//
		// This fill is load-bearing, not decoration. Budgeting raw
		// bytes instead of encoded is caught by this fill alone,
		// and only under the JSON handler, at 3,072 bytes against
		// the 2,560 ceiling. Drop it and that mutation passes.
		"control": "\x01",
		"astral":  "\U0001000C",
	}
}

// logHandlers are the two handlers internal/logger can install: the
// JSON one, and the text one it selects when stderr is a tty. They do
// not escape alike, and MaxAccessLogLineBytes is quoted unqualified,
// so every case runs through both.
func logHandlers() map[string]func(
	io.Writer, *slog.HandlerOptions,
) slog.Handler {
	return map[string]func(
		io.Writer, *slog.HandlerOptions,
	) slog.Handler{
		"json": func(
			w io.Writer, o *slog.HandlerOptions,
		) slog.Handler {
			return slog.NewJSONHandler(w, o)
		},
		"text": func(
			w io.Writer, o *slog.HandlerOptions,
		) slog.Handler {
			return slog.NewTextHandler(w, o)
		},
	}
}

// oversizedPathSegment builds an 8 KB client-chosen path segment out
// of repetitions of ch, percent-encoded so it survives URL parsing
// into r.URL.Path the way it would arriving off a socket.
//
// Both markers sit at the END, past every budget, so their absence
// from the log is what proves the value was cut rather than merely
// being short. The leading 'x' keeps the segment non-empty for fills
// that a parser might otherwise fold away.
func oversizedPathSegment(ch string) string {
	return url.PathEscape(
		"x" + strings.Repeat(ch, oversizedSegmentBytes) +
			attackerMarker + tailMarker,
	)
}

// capturingLogger returns a logger at DEBUG writing into the returned
// buffer through the named handler.
func capturingLogger(
	newHandler func(io.Writer, *slog.HandlerOptions) slog.Handler,
) (*slog.Logger, *bytes.Buffer) {
	buf := new(bytes.Buffer)
	opts := &slog.HandlerOptions{Level: slog.LevelDebug}

	return slog.New(newHandler(buf, opts)), buf
}

// capturingBoundMiddleware builds a Middleware with a real session
// manager (CSRF needs its key, RequireAuth needs its store) whose log
// is captured at DEBUG.
func capturingBoundMiddleware(
	t *testing.T,
	newHandler func(io.Writer, *slog.HandlerOptions) slog.Handler,
) (*middleware.Middleware, *bytes.Buffer) {
	t.Helper()

	log, buf := capturingLogger(newHandler)

	cfg := &config.Config{
		Environment:       config.EnvironmentDev,
		ReceiverRateLimit: receiverLimitPerMinute,
	}

	sess := newTestSessionManager(cfg, log, nil)

	return middleware.NewForTest(log, cfg, sess), buf
}

// unreachable is a next-handler that fails the test if the middleware
// under test let the request through. Every site here rejects.
func unreachable(t *testing.T) http.Handler {
	t.Helper()

	return http.HandlerFunc(func(http.ResponseWriter, *http.Request) {
		assert.Fail(t, "rejected request reached the next handler")
	})
}

// logSite is one non-access-log call site that logs a client-chosen
// path. drive sends requests at it that all take the rejecting
// branch; linesPerRequest is how many log lines one such request
// produces there.
type logSite struct {
	// build wraps the site's middleware around a handler that must
	// not be reached.
	build func(
		t *testing.T, m *middleware.Middleware,
	) http.Handler
	// send issues one request for the given client-chosen path and
	// returns the status. Some sites need a warm-up request before
	// they reject, which send performs itself.
	send func(h http.Handler, path string) int
	// wantStatus is the status the rejecting branch answers with.
	wantStatus int
}

// postOversize sends a POST whose declared Content-Length exceeds the
// body limit without sending a body, which is the whole cost of the
// attack on the MaxBodySize branch.
func postOversize(h http.Handler, path string) int {
	req := httptest.NewRequestWithContext(
		context.Background(), http.MethodPost, path, nil,
	)
	req.ContentLength = declaredBodyBytes
	req.Header.Set(
		"Content-Type", "application/x-www-form-urlencoded",
	)

	w := httptest.NewRecorder()
	h.ServeHTTP(w, req)

	return w.Code
}

// postNoToken sends a POST carrying no CSRF token and no session
// cookie, which is what an unauthenticated client sends.
func postNoToken(h http.Handler, path string) int {
	req := httptest.NewRequestWithContext(
		context.Background(), http.MethodPost, path,
		strings.NewReader(""),
	)
	req.Header.Set(
		"Content-Type", "application/x-www-form-urlencoded",
	)

	w := httptest.NewRecorder()
	h.ServeHTTP(w, req)

	return w.Code
}

// getNoSession sends a GET with no session cookie.
func getNoSession(h http.Handler, path string) int {
	req := httptest.NewRequestWithContext(
		context.Background(), http.MethodGet, path, nil,
	)

	w := httptest.NewRecorder()
	h.ServeHTTP(w, req)

	return w.Code
}

// logSites enumerates the call sites under test.
func logSites() map[string]logSite {
	return map[string]logSite{
		// The site this file exists for: WARN, on by default, and
		// registered ahead of RequireAuth.
		"maxbodysize 413": {
			build: func(
				t *testing.T, m *middleware.Middleware,
			) http.Handler {
				t.Helper()

				return m.MaxBodySize(bodyLimitBytes)(
					unreachable(t),
				)
			},
			send:       postOversize,
			wantStatus: http.StatusRequestEntityTooLarge,
		},
		// Also ahead of RequireAuth, also WARN.
		"csrf 403": {
			build: func(
				t *testing.T, m *middleware.Middleware,
			) http.Handler {
				t.Helper()

				return m.CSRF()(unreachable(t))
			},
			send:       postNoToken,
			wantStatus: http.StatusForbidden,
		},
		// The per-entrypoint receiver limiter, unauthenticated. Its
		// bucket is keyed on the path, so the first request through a
		// fresh path is served and only the ones after it are
		// rejected; sendUntilLimited absorbs that.
		"receiver rate limit 429": {
			build: func(
				t *testing.T, m *middleware.Middleware,
			) http.Handler {
				t.Helper()

				return m.ReceiverRateLimit()(okHandler())
			},
			send:       sendUntilLimited,
			wantStatus: http.StatusTooManyRequests,
		},
		// RequireAuth's own line. DEBUG is off in production by
		// default, but turning it on to diagnose a flood must not
		// restore an unbounded write.
		"requireauth redirect": {
			build: func(
				t *testing.T, m *middleware.Middleware,
			) http.Handler {
				t.Helper()

				return m.RequireAuth()(unreachable(t))
			},
			send:       getNoSession,
			wantStatus: http.StatusSeeOther,
		},
	}
}

// sendUntilLimited drives the per-entrypoint receiver limiter past
// its allowance on one path and returns the status of the rejected
// request. Every request before the last is served, and only the last
// one logs.
func sendUntilLimited(h http.Handler, path string) int {
	code := http.StatusOK

	for range receiverLimitPerMinute + 1 {
		req := httptest.NewRequestWithContext(
			context.Background(), http.MethodPost, path, nil,
		)
		req.RemoteAddr = "203.0.113.7:5555"

		w := httptest.NewRecorder()
		h.ServeHTTP(w, req)
		code = w.Code
	}

	return code
}

// logLines splits the captured buffer into non-empty lines, holding
// each to bound bytes.
func logLines(t *testing.T, buf *bytes.Buffer, bound int) []string {
	t.Helper()

	var lines []string

	for line := range strings.SplitSeq(
		strings.TrimSpace(buf.String()), "\n",
	) {
		if line == "" {
			continue
		}

		require.LessOrEqual(
			t, len(line), bound,
			"log line exceeded its bound: %s", line,
		)

		lines = append(lines, line)
	}

	return lines
}

// assertNoClientText fails if any marker from the far end of the
// client-chosen input survived into the log. Their absence is what
// distinguishes a real cut from a value that merely happened to be
// short.
func assertNoClientText(t *testing.T, buf *bytes.Buffer) {
	t.Helper()

	assert.NotContains(
		t, buf.String(), attackerMarker,
		"log carried attacker-chosen text",
	)
	assert.NotContains(
		t, buf.String(), tailMarker,
		"log carried the tail of the attacker-chosen text",
	)
}

// TestLogLines_ClientChosenPathDoesNotSizeTheLine points 8 KB of
// client-chosen path at each non-access-log call site that logs one,
// through both handlers and through every character those handlers
// escape, and holds the resulting line to MaxAccessLogLineBytes.
//
// Removing any one of the logfield.Truncate calls at those sites
// fails this test: the line grows to roughly the size of the input,
// or to several times it on the escaping fills.
func TestLogLines_ClientChosenPathDoesNotSizeTheLine(t *testing.T) {
	t.Parallel()

	for siteName, site := range logSites() {
		for handlerName, newHandler := range logHandlers() {
			for fillName, fill := range escapeFills() {
				name := siteName + "/" + handlerName + "/" + fillName

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

					m, buf := capturingBoundMiddleware(
						t, newHandler,
					)

					path := "/source/" +
						oversizedPathSegment(fill) + "/edit"

					assert.Equal(
						t,
						site.wantStatus,
						site.send(site.build(t, m), path),
					)

					lines := logLines(
						t, buf,
						middleware.MaxAccessLogLineBytes,
					)
					require.NotEmpty(
						t, lines,
						"the site under test logged nothing, "+
							"so the bound proves nothing",
					)
					assertNoClientText(t, buf)
				})
			}
		}
	}
}

// TestMaxBodySize_FloodOfOversizePathsDoesNotGrowTheLog is the
// flood shape from the issue: an unauthenticated client posting
// oversize declarations at invented 8 KB paths, as fast as it likes.
//
// It asserts the property directly rather than by proxy — the bytes
// the flood writes to the operator's log do not track the bytes the
// flood sent. The same flood at a one-character path is the control:
// 8 KB of extra input per request buys at most the field budget, not
// 8 KB of log.
func TestMaxBodySize_FloodOfOversizePathsDoesNotGrowTheLog(
	t *testing.T,
) {
	t.Parallel()

	for handlerName, newHandler := range logHandlers() {
		for fillName, fill := range escapeFills() {
			t.Run(handlerName+"/"+fillName, func(t *testing.T) {
				t.Parallel()

				flood := func(segment func(i int) string) int {
					m, buf := capturingBoundMiddleware(
						t, newHandler,
					)
					h := m.MaxBodySize(bodyLimitBytes)(
						unreachable(t),
					)

					for i := range floodRequests {
						assert.Equal(
							t,
							http.StatusRequestEntityTooLarge,
							postOversize(
								h,
								"/source/"+segment(i)+"/edit",
							),
						)
					}

					lines := logLines(
						t, buf,
						middleware.MaxAccessLogLineBytes,
					)
					require.Len(t, lines, floodRequests)
					assertNoClientText(t, buf)

					return buf.Len()
				}

				sent := oversizedSegmentBytes * floodRequests

				oversize := flood(func(i int) string {
					return oversizedPathSegment(fill) +
						strings.Repeat("y", i)
				})
				control := flood(func(i int) string {
					return "a" + strings.Repeat("y", i)
				})

				// The whole point: 8 KB per request of extra
				// client-chosen input bought a bounded amount of
				// log, not a proportional amount.
				assert.Less(
					t, oversize-control, sent/2,
					"log volume tracked the size of the flood's "+
						"input",
				)
				assert.LessOrEqual(
					t,
					oversize,
					floodRequests*
						middleware.MaxAccessLogLineBytes,
				)
			})
		}
	}
}