rproxy, the proxy in front of each app, asks servewaf and fails open (closes #171)

`smallwebwaf rproxy` reads the first 64 KiB of each body, asks servewaf over
HTTP/1.1, and passes what servewaf allows to the app within its own size and
time limits. It reports each request servewaf answered. SWRP_DEFAULT_DISPOSITION
decides when servewaf gives no answer. A request it cannot put to servewaf as
sent, it refuses itself.

Duplication: internal/rproxy copies passing-on code from internal/proxy until
#172 removes the originals.
Rule suppressed: gosec G704 on servewaf's URL, a setting.
Rule suppressed: gosec G705 on the answer written to the visitor.
Judgement call: the SWRP_ size and time limits take off; SWRP_TIMEOUT_MS does not.
Judgement call: every target not starting with / gets 400, not only x:admin.

Model: opus-5-5

internal/rproxy/servewaf.go

@@ -0,0 +1,218 @@
+package rproxy
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"maps"
+	"net/http"
+
+	"sneak.berlin/go/smallwebwaf/internal/proxy"
+)
+
+// answerBodyMaxBytes is the most of the body of servewaf's answer that is read.
+// It is far above any answer's.
+const answerBodyMaxBytes = 1 << 20
+
+// reportAnswerMaxBytes is the most of the answer to a report that is read,
+// which has no body when servewaf takes the report.
+const reportAnswerMaxBytes = 4 << 10
+
+var (
+	errNoDisposition = errors.New("the answer has no valid " + proxy.DispositionHeader)
+	errAnswerTooLong = errors.New("the answer's body is over 1 MiB")
+	errReportRefused = errors.New("the report was answered")
+)
+
+// servewafAnswer is what servewaf answered to a question.
+type servewafAnswer struct {
+	status int
+	header http.Header
+	body   []byte
+}
+
+// askServeWAF asks servewaf about the request, and notes what is to be done
+// with it. It returns servewaf's answer, or nil when servewaf gave none, and
+// SWRP_DEFAULT_DISPOSITION decides. When the visitor went away while servewaf
+// was being asked, servewaf has not failed, and nothing is noted. ctx is the
+// request's own context.
+func (rq *request) askServeWAF(ctx context.Context) *servewafAnswer {
+	answer, err := rq.ask(ctx)
+	if err != nil {
+		if ctx.Err() != nil {
+			return nil
+		}
+
+		rq.h.processLog.Warn("servewaf gave no answer", "error", err.Error())
+
+		rq.disposition = rq.h.config.DefaultDisposition
+		rq.byDefault = true
+
+		return nil
+	}
+
+	rq.disposition = answer.header.Get(proxy.DispositionHeader)
+	rq.answered = true
+	rq.asn = answer.header.Get(asnHeader)
+	rq.country = answer.header.Get(countryHeader)
+
+	return answer
+}
+
+// ask sends servewaf the question, and returns its answer, which must have come
+// whole within SWRP_TIMEOUT_MS, with a valid disposition. It ends when ctx does,
+// as when the visitor goes away.
+func (rq *request) ask(ctx context.Context) (*servewafAnswer, error) {
+	ctx, cancel := context.WithTimeout(ctx, rq.h.config.Timeout)
+	defer cancel()
+
+	question, err := rq.newQuestion(ctx)
+	if err != nil {
+		return nil, err
+	}
+
+	res, err := rq.h.serveWAFTransport.RoundTrip(question)
+	if err != nil {
+		return nil, fmt.Errorf("send the question: %w", err)
+	}
+
+	defer func() {
+		_ = res.Body.Close()
+	}()
+
+	body, err := io.ReadAll(io.LimitReader(res.Body, answerBodyMaxBytes+1))
+	if err != nil {
+		return nil, fmt.Errorf("read the answer: %w", err)
+	}
+
+	if len(body) > answerBodyMaxBytes {
+		return nil, errAnswerTooLong
+	}
+
+	switch res.Header.Get(proxy.DispositionHeader) {
+	case proxy.DispositionAllow, proxy.DispositionDeny, proxy.DispositionClose:
+		return &servewafAnswer{res.StatusCode, res.Header, body}, nil
+	default:
+		return nil, fmt.Errorf("%w, and status %d", errNoDisposition, res.StatusCode)
+	}
+}
+
+// newQuestion returns the question about the request, as "The question" in
+// SPEC.md gives it: the visitor's request as the visitor sent it, with the part
+// of the body it holds and rproxy's headers.
+func (rq *request) newQuestion(ctx context.Context) (*http.Request, error) {
+	in := rq.in
+
+	var held []byte
+	if rq.body != nil {
+		held = rq.body.held
+	}
+
+	question, err := http.NewRequestWithContext( //nolint:gosec // a setting's URL
+		ctx, in.Method, rq.h.config.WAFBackend.String(), bytes.NewReader(held))
+	if err != nil {
+		return nil, fmt.Errorf("make the question: %w", err)
+	}
+
+	backend := question.URL
+	target := *in.URL
+	target.Scheme = backend.Scheme
+	target.Host = backend.Host
+	setPathAsSent(&target, in)
+	question.URL = &target
+	question.Host = in.Host
+
+	// The length NewRequestWithContext set is that of what is held. A body whose
+	// length the visitor did not announce goes chunked. Named here, since Go's
+	// client would otherwise send a CONNECT's body with neither length nor chunks,
+	// which servewaf would read as further requests.
+	question.TransferEncoding = in.TransferEncoding
+
+	question.Header = in.Header.Clone()
+	question.Header.Set(proxy.ClientHeader, rq.client.String())
+	question.Header.Set(proxy.PeerHeader, rq.peer.String())
+	question.Header.Del(proxy.ContentLengthHeader)
+
+	announced := in.Header.Get("Content-Length")
+	if announced != "" {
+		question.Header.Set(proxy.ContentLengthHeader, announced)
+	}
+
+	question.Header.Set(requestIDHeader, rq.id)
+	question.Header.Set("X-Forwarded-Proto", scheme(in, rq.peerTrusted))
+
+	// Go's client adds a User-Agent of its own to a request without the key.
+	_, sent := question.Header["User-Agent"]
+	if !sent {
+		question.Header["User-Agent"] = nil
+	}
+
+	return question, nil
+}
+
+// answerWith gives the visitor servewaf's answer, less its disposition.
+func (rq *request) answerWith(answer *servewafAnswer) {
+	rq.prepareOwnAnswer(rq.requestDeadline())
+
+	header := rq.out.Header()
+	maps.Copy(header, answer.header)
+	header.Del(proxy.DispositionHeader)
+	rq.out.WriteHeader(answer.status)
+	_, _ = rq.out.Write(answer.body)
+}
+
+// sendReport sends servewaf report on a goroutine of its own, so that the
+// visitor does not wait for it. The report goes on after ctx, the request's own
+// context, has ended.
+func (h *handler) sendReport(ctx context.Context, report *proxy.Report) {
+	h.reportsMu.Lock()
+	defer h.reportsMu.Unlock()
+
+	if h.reportsStopped {
+		return
+	}
+
+	h.reports.Go(func() {
+		err := h.postReport(context.WithoutCancel(ctx), report)
+		if err != nil {
+			h.processLog.Warn("a report is dropped", "error", err.Error())
+		}
+	})
+}
+
+// postReport posts report to servewaf, and waits for its answer for up to
+// SWRP_TIMEOUT_MS.
+func (h *handler) postReport(ctx context.Context, report *proxy.Report) error {
+	body, err := json.Marshal(report)
+	if err != nil {
+		return fmt.Errorf("encode the report: %w", err)
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, h.config.Timeout)
+	defer cancel()
+
+	req, err := http.NewRequestWithContext( //nolint:gosec // a setting's URL
+		ctx, http.MethodPost, h.reportURL, bytes.NewReader(body))
+	if err != nil {
+		return fmt.Errorf("make the request: %w", err)
+	}
+
+	req.Header.Set("Content-Type", "application/json")
+
+	res, err := h.serveWAFTransport.RoundTrip(req)
+	if err != nil {
+		return fmt.Errorf("send the report: %w", err)
+	}
+
+	_, _ = io.Copy(io.Discard, io.LimitReader(res.Body, reportAnswerMaxBytes))
+	_ = res.Body.Close()
+
+	if res.StatusCode != http.StatusNoContent {
+		return fmt.Errorf("%w %s", errReportRefused, res.Status)
+	}
+
+	return nil
+}