kata-monitor: update the hrefs in the debug/pprof index page

kata-monitor allows to get data profiles from the kata shim
instances running on the same node by acting as a proxy
(e.g., http://$NODE_ADDRESS:8090/debug/pprof/?sandbox=$MYSANDBOXID).
In order to proxy the requests and the responses to the right shim,
kata-monitor requires to pass the sandbox id via a query string in the
url.

The profiling index page proxied by kata-monitor contains the link to all
the data profiles available. All the links anyway do not contain the
sandbox id included in the request: the links result then broken when
accessed through kata-monitor.
This happens because the profiling index page comes from the kata shim,
which will not include the query string provided in the http request.

Let's add on-the-fly the sandbox id in each href tag returned by the kata
shim index page before providing the proxied page.

Fixes: #4054

Signed-off-by: Francesco Giudici <fgiudici@redhat.com>

src/runtime/pkg/kata-monitor/pprof.go

@@ -10,6 +10,8 @@ import (
 	"io"
 	"net"
 	"net/http"
+	"regexp"
+	"strings"
 
 	cdshim "github.com/containerd/containerd/runtime/v2/shim"
 
@@ -33,7 +35,13 @@ func (km *KataMonitor) composeSocketAddress(r *http.Request) (string, error) {
 	return shim.SocketAddress(sandbox), nil
 }
 
-func (km *KataMonitor) proxyRequest(w http.ResponseWriter, r *http.Request) {
+func (km *KataMonitor) proxyRequest(w http.ResponseWriter, r *http.Request,
+	proxyResponse func(req *http.Request, w io.Writer, r io.Reader) error) {
+
+	if proxyResponse == nil {
+		proxyResponse = copyResponse
+	}
+
 	w.Header().Set("X-Content-Type-Options", "nosniff")
 
 	socketAddress, err := km.composeSocketAddress(r)
@@ -73,38 +81,68 @@ func (km *KataMonitor) proxyRequest(w http.ResponseWriter, r *http.Request) {
 		w.Header().Set("Content-Disposition", contentDisposition)
 	}
 
-	io.Copy(w, output)
+	err = proxyResponse(r, w, output)
+	if err != nil {
+		monitorLog.WithError(err).Errorf("failed proxying %s from %s", uri, socketAddress)
+		serveError(w, http.StatusInternalServerError, "error retrieving resource")
+	}
 }
 
 // ExpvarHandler handles other `/debug/vars` requests
 func (km *KataMonitor) ExpvarHandler(w http.ResponseWriter, r *http.Request) {
-	km.proxyRequest(w, r)
+	km.proxyRequest(w, r, nil)
 }
 
 // PprofIndex handles other `/debug/pprof/` requests
 func (km *KataMonitor) PprofIndex(w http.ResponseWriter, r *http.Request) {
-	km.proxyRequest(w, r)
+	if len(strings.TrimPrefix(r.URL.Path, "/debug/pprof/")) == 0 {
+		km.proxyRequest(w, r, copyResponseAddingSandboxIdToHref)
+	} else {
+		km.proxyRequest(w, r, nil)
+	}
 }
 
 // PprofCmdline handles other `/debug/cmdline` requests
 func (km *KataMonitor) PprofCmdline(w http.ResponseWriter, r *http.Request) {
-	km.proxyRequest(w, r)
+	km.proxyRequest(w, r, nil)
 }
 
 // PprofProfile handles other `/debug/profile` requests
 func (km *KataMonitor) PprofProfile(w http.ResponseWriter, r *http.Request) {
-	km.proxyRequest(w, r)
+	km.proxyRequest(w, r, nil)
 }
 
 // PprofSymbol handles other `/debug/symbol` requests
 func (km *KataMonitor) PprofSymbol(w http.ResponseWriter, r *http.Request) {
 	w.Header().Set("Content-Type", "text/plain; charset=utf-8")
-	km.proxyRequest(w, r)
+	km.proxyRequest(w, r, nil)
 }
 
 // PprofTrace handles other `/debug/trace` requests
 func (km *KataMonitor) PprofTrace(w http.ResponseWriter, r *http.Request) {
 	w.Header().Set("Content-Type", "application/octet-stream")
 	w.Header().Set("Content-Disposition", `attachment; filename="trace"`)
-	km.proxyRequest(w, r)
+	km.proxyRequest(w, r, nil)
+}
+
+func copyResponse(req *http.Request, w io.Writer, r io.Reader) error {
+	_, err := io.Copy(w, r)
+	return err
+}
+
+func copyResponseAddingSandboxIdToHref(req *http.Request, w io.Writer, r io.Reader) error {
+	sb, err := getSandboxIDFromReq(req)
+	if err != nil {
+		monitorLog.WithError(err).Warning("missing sandbox query in pprof url")
+		return copyResponse(req, w, r)
+	}
+	buf, err := io.ReadAll(r)
+	if err != nil {
+		return err
+	}
+
+	re := regexp.MustCompile(`<a href=(['"])(\w+)\?(\w+=\w+)['"]>`)
+	outHtml := re.ReplaceAllString(string(buf), fmt.Sprintf("<a href=$1$2?sandbox=%s&$3$1>", sb))
+	w.Write([]byte(outHtml))
+	return nil
 }

src/runtime/pkg/kata-monitor/pprof_test.go

@@ -0,0 +1,117 @@
+// Copyright (c) 2022 Red Hat Inc.
+//
+// SPDX-License-Identifier: Apache-2.0
+//
+
+package katamonitor
+
+import (
+	"bytes"
+	"net/http"
+	"net/url"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCopyResponseAddingSandboxIdToHref(t *testing.T) {
+	assert := assert.New(t)
+
+	htmlIn := strings.NewReader(`
+<html>
+<head>
+<title>/debug/pprof/</title>
+<style>
+.profile-name{
+	display:inline-block;
+	width:6rem;
+}
+</style>
+</head>
+<body>
+/debug/pprof/<br>
+<br>
+Types of profiles available:
+<table>
+<thead><td>Count</td><td>Profile</td></thead>
+<tr><td>27</td><td><a href='allocs?debug=1'>allocs</a></td></tr>
+<tr><td>0</td><td><a href='block?debug=1'>block</a></td></tr>
+<tr><td>0</td><td><a href='cmdline?debug=1'>cmdline</a></td></tr>
+<tr><td>39</td><td><a href='goroutine?debug=1'>goroutine</a></td></tr>
+<tr><td>27</td><td><a href='heap?debug=1'>heap</a></td></tr>
+<tr><td>0</td><td><a href='mutex?debug=1'>mutex</a></td></tr>
+<tr><td>0</td><td><a href='profile?debug=1'>profile</a></td></tr>
+<tr><td>10</td><td><a href='threadcreate?debug=1'>threadcreate</a></td></tr>
+<tr><td>0</td><td><a href='trace?debug=1'>trace</a></td></tr>
+</table>
+<a href="goroutine?debug=2">full goroutine stack dump</a>
+<br>
+<p>
+Profile Descriptions:
+<ul>
+<li><div class=profile-name>allocs: </div> A sampling of all past memory allocations</li>
+<li><div class=profile-name>block: </div> Stack traces that led to blocking on synchronization primitives</li>
+<li><div class=profile-name>cmdline: </div> The command line invocation of the current program</li>
+<li><div class=profile-name>goroutine: </div> Stack traces of all current goroutines</li>
+<li><div class=profile-name>heap: </div> A sampling of memory allocations of live objects. You can specify the gc GET parameter to run GC before taking the heap sample.</li>
+<li><div class=profile-name>mutex: </div> Stack traces of holders of contended mutexes</li>
+<li><div class=profile-name>profile: </div> CPU profile. You can specify the duration in the seconds GET parameter. After you get the profile file, use the go tool pprof command to investigate the profile.</li>
+<li><div class=profile-name>threadcreate: </div> Stack traces that led to the creation of new OS threads</li>
+<li><div class=profile-name>trace: </div> A trace of execution of the current program. You can specify the duration in the seconds GET parameter. After you get the trace file, use the go tool trace command to investigate the trace.</li>
+</ul>
+</p>
+</body>
+</html>`)
+
+	htmlExpected := bytes.NewBufferString(`
+<html>
+<head>
+<title>/debug/pprof/</title>
+<style>
+.profile-name{
+	display:inline-block;
+	width:6rem;
+}
+</style>
+</head>
+<body>
+/debug/pprof/<br>
+<br>
+Types of profiles available:
+<table>
+<thead><td>Count</td><td>Profile</td></thead>
+<tr><td>27</td><td><a href='allocs?sandbox=1234567890&debug=1'>allocs</a></td></tr>
+<tr><td>0</td><td><a href='block?sandbox=1234567890&debug=1'>block</a></td></tr>
+<tr><td>0</td><td><a href='cmdline?sandbox=1234567890&debug=1'>cmdline</a></td></tr>
+<tr><td>39</td><td><a href='goroutine?sandbox=1234567890&debug=1'>goroutine</a></td></tr>
+<tr><td>27</td><td><a href='heap?sandbox=1234567890&debug=1'>heap</a></td></tr>
+<tr><td>0</td><td><a href='mutex?sandbox=1234567890&debug=1'>mutex</a></td></tr>
+<tr><td>0</td><td><a href='profile?sandbox=1234567890&debug=1'>profile</a></td></tr>
+<tr><td>10</td><td><a href='threadcreate?sandbox=1234567890&debug=1'>threadcreate</a></td></tr>
+<tr><td>0</td><td><a href='trace?sandbox=1234567890&debug=1'>trace</a></td></tr>
+</table>
+<a href="goroutine?sandbox=1234567890&debug=2">full goroutine stack dump</a>
+<br>
+<p>
+Profile Descriptions:
+<ul>
+<li><div class=profile-name>allocs: </div> A sampling of all past memory allocations</li>
+<li><div class=profile-name>block: </div> Stack traces that led to blocking on synchronization primitives</li>
+<li><div class=profile-name>cmdline: </div> The command line invocation of the current program</li>
+<li><div class=profile-name>goroutine: </div> Stack traces of all current goroutines</li>
+<li><div class=profile-name>heap: </div> A sampling of memory allocations of live objects. You can specify the gc GET parameter to run GC before taking the heap sample.</li>
+<li><div class=profile-name>mutex: </div> Stack traces of holders of contended mutexes</li>
+<li><div class=profile-name>profile: </div> CPU profile. You can specify the duration in the seconds GET parameter. After you get the profile file, use the go tool pprof command to investigate the profile.</li>
+<li><div class=profile-name>threadcreate: </div> Stack traces that led to the creation of new OS threads</li>
+<li><div class=profile-name>trace: </div> A trace of execution of the current program. You can specify the duration in the seconds GET parameter. After you get the trace file, use the go tool trace command to investigate the trace.</li>
+</ul>
+</p>
+</body>
+</html>`)
+
+	req := &http.Request{URL: &url.URL{RawQuery: "sandbox=1234567890"}}
+	buf := bytes.NewBuffer(nil)
+	copyResponseAddingSandboxIdToHref(req, buf, htmlIn)
+	assert.Equal(htmlExpected, buf)
+}