Merge pull request 'A route may say the largest body it carries' (#68) from feat/a-route-may-limit-the-body-it-carries into main

2026-09-26 14:01:56 +00:00
parent 557f419e71 a287812e14
commit e88d3bd485
2 changed files with 149 additions and 0 deletions
@@ -167,6 +167,16 @@ type rule struct {
 	// webmail front is the first of these — never for anything reached over plain http, where
 	// there is nothing to verify in the first place.
 	insecure bool
+	// maxRequestBody is the largest body, in bytes, this route carries. Zero is no limit, which is
+	// what every route gets by saying nothing: this proxy has never limited a body, and a default
+	// arriving with the field would change every route that never asked for one.
+	//
+	// **Configuration, not a policy** (novox/hq ADR 0108 closed that set at four). It belongs beside
+	// `insecure` for the same reason `insecure` is not a policy: both tune how this proxy carries a
+	// request to a backend, rather than deciding what the name admits or who may reach it. A
+	// registry is the case that needs it — image layers arrive as single requests of gigabytes, and
+	// a proxy's own default refuses them long before the workload is reached.
+	maxRequestBody int64
 }

 // table is what the proxy is currently serving, replaced whole whenever the file changes.
@@ -636,6 +646,18 @@ func handler(held *table) http.Handler {
 			return
 		}

+		if matched.maxRequestBody > 0 {
+			// Refused on the declared length where there is one, so an upload that cannot succeed
+			// is answered before it is carried; and capped while reading for a chunked body, which
+			// declares no length at all. Without the second, a limit is advice.
+			if r.ContentLength > matched.maxRequestBody {
+				http.Error(w, fmt.Sprintf("request body too large for this route: %d bytes is the most it carries",
+					matched.maxRequestBody), http.StatusRequestEntityTooLarge)
+				return
+			}
+			r.Body = http.MaxBytesReader(w, r.Body, matched.maxRequestBody)
+		}
+
 		matched.to.ServeHTTP(w, r)
 	})
 }
@@ -773,6 +795,18 @@ func routesFrom(path string) (map[string][]rule, map[string]bool, error) {
 				continue
 			}
 			made.insecure, _ = c.Values["insecure"].(bool)
+			// A limit this proxy cannot read is a route it does not serve, named like a port that
+			// is not a port. Serving it without the limit would carry exactly what the module said
+			// not to carry, and report success doing it.
+			if asked, said := c.Values["max-request-body"]; said {
+				bytes, whole := asWhole(asked)
+				if !whole || bytes <= 0 {
+					log.Printf("%s on %s asked for route %q with a max-request-body of %v, which is "+
+						"not a whole positive number of bytes; skipped", c.From, c.Node, name, asked)
+					continue
+				}
+				made.maxRequestBody = int64(bytes)
+			}
 			made.target = fmt.Sprintf("%s://%s:%d", scheme, at, port)
 		}

@@ -2,6 +2,8 @@ package main

 import (
 	"context"
+	"fmt"
+	"io"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -373,3 +375,116 @@ func TestWithdrawingARouteWithdrawsItsCertificate(t *testing.T) {
 			"once rather than what is served now")
 	}
 }
+
+// A route may say the largest body it carries, and the proxy holds requests to it.
+//
+// The registry is why: image layers arrive as single requests of gigabytes, and a proxy's own
+// default refuses them long before the workload is reached. It is configuration beside `insecure`,
+// not a fifth policy — novox/hq ADR 0108 closed that set at four.
+func TestARouteMayLimitTheBodyItCarries(t *testing.T) {
+	routes, _, err := routesFrom(write(t, `{"given":[
+	  {"from":"registry","node":"anchor","at":"anchor.internal",
+	   "values":{"name":"images.example","port":5000,"max-request-body":21474836480}}
+	]}`))
+	if err != nil {
+		t.Fatal(err)
+	}
+	rules := routes["images.example"]
+	if len(rules) != 1 {
+		t.Fatalf("the route is not served once: %v", routes)
+	}
+	if rules[0].maxRequestBody != 21474836480 {
+		t.Fatalf("the limit did not survive the contribution: %d", rules[0].maxRequestBody)
+	}
+}
+
+// Saying nothing leaves the route unlimited, which is what every route already got.
+func TestARouteThatSaysNothingCarriesAnySize(t *testing.T) {
+	routes, _, err := routesFrom(write(t, `{"given":[
+	  {"from":"app","node":"anchor","at":"anchor.internal","values":{"name":"app.example","port":8080}}
+	]}`))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := routes["app.example"][0].maxRequestBody; got != 0 {
+		t.Fatalf("a route that asked for no limit got one: %d", got)
+	}
+}
+
+// A limit that is not a whole positive number of bytes takes the route with it. Serving it without
+// the limit would carry exactly what the module said not to carry, and report success doing it.
+func TestARouteWithAnUnusableLimitIsSkipped(t *testing.T) {
+	for _, asked := range []string{`"lots"`, `-1`, `0`, `1.5`} {
+		routes, _, err := routesFrom(write(t, `{"given":[
+		  {"from":"registry","node":"anchor","at":"anchor.internal",
+		   "values":{"name":"images.example","port":5000,"max-request-body":`+asked+`}}
+		]}`))
+		if err != nil {
+			t.Fatal(err)
+		}
+		if len(routes["images.example"]) != 0 {
+			t.Errorf("a route asking for a max-request-body of %s was served anyway: %v", asked, routes)
+		}
+	}
+}
+
+// A request larger than the route carries is refused by the proxy, with the limit named, and the
+// workload never sees it. A request within it is proxied normally.
+func TestABodyOverTheLimitIsRefusedAndOneUnderItIsCarried(t *testing.T) {
+	var reached int
+	workload := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		body, _ := io.ReadAll(r.Body)
+		reached++
+		fmt.Fprintf(w, "carried %d bytes", len(body))
+	}))
+	defer workload.Close()
+
+	at := strings.TrimPrefix(workload.URL, "http://")
+	host, port, _ := strings.Cut(at, ":")
+	routes, _, err := routesFrom(write(t, `{"given":[
+	  {"from":"registry","node":"anchor","at":"`+host+`",
+	   "values":{"name":"images.example","port":`+port+`,"max-request-body":8}}
+	]}`))
+	if err != nil {
+		t.Fatal(err)
+	}
+	held := newTable()
+	held.set(routes, map[string]bool{})
+	proxy := httptest.NewServer(handler(held))
+	defer proxy.Close()
+
+	over, err := post(proxy.URL, "images.example", "123456789")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer over.Body.Close()
+	if over.StatusCode != http.StatusRequestEntityTooLarge {
+		t.Fatalf("a body over the limit answered %d, not 413", over.StatusCode)
+	}
+	if reached != 0 {
+		t.Fatalf("the workload was reached by a request the route said it would not carry")
+	}
+
+	under, err := post(proxy.URL, "images.example", "1234")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer under.Body.Close()
+	if under.StatusCode != http.StatusOK {
+		t.Fatalf("a body within the limit answered %d, not 200", under.StatusCode)
+	}
+	if reached != 1 {
+		t.Fatalf("the workload was not reached by a request within the limit")
+	}
+}
+
+// post sends a body to the proxy as the named route, since a route is found by the Host header.
+func post(url, host, body string) (*http.Response, error) {
+	asked, err := http.NewRequest(http.MethodPost, url, strings.NewReader(body))
+	if err != nil {
+		return nil, err
+	}
+	asked.Host = host
+	asked.Header.Set("Content-Type", "application/octet-stream")
+	return http.DefaultClient.Do(asked)
+}