integration: Add userns test with volumes

Signed-off-by: Rodrigo Campos <rodrigoca@microsoft.com>

integration/main_test.go

@@ -298,6 +298,21 @@ func WithVolumeMount(hostPath, containerPath string) ContainerOpts {
 	}
 }
 
+func WithIDMapVolumeMount(hostPath, containerPath string, uidMaps, gidMaps []*runtime.IDMapping) ContainerOpts {
+	return func(c *runtime.ContainerConfig) {
+		hostPath, _ = filepath.Abs(hostPath)
+		containerPath, _ = filepath.Abs(containerPath)
+		mount := &runtime.Mount{
+			HostPath:       hostPath,
+			ContainerPath:  containerPath,
+			SelinuxRelabel: selinux.GetEnabled(),
+			UidMappings:    uidMaps,
+			GidMappings:    gidMaps,
+		}
+		c.Mounts = append(c.Mounts, mount)
+	}
+}
+
 func WithWindowsUsername(username string) ContainerOpts {
 	return func(c *runtime.ContainerConfig) {
 		if c.Windows == nil {

integration/pod_userns_linux_test.go

@@ -19,7 +19,9 @@ package integration
 import (
 	"fmt"
 	"os"
+	"os/user"
 	"path/filepath"
+	"strings"
 	"syscall"
 	"testing"
 	"time"
@@ -28,17 +30,121 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	exec "golang.org/x/sys/execabs"
+	"golang.org/x/sys/unix"
 	runtime "k8s.io/cri-api/pkg/apis/runtime/v1"
 )
 
+const (
+	defaultRoot = "/var/lib/containerd-test"
+)
+
+func supportsUserNS() bool {
+	if _, err := os.Stat("/proc/self/ns/user"); os.IsNotExist(err) {
+		return false
+	}
+	return true
+}
+
+func supportsIDMap(path string) bool {
+	treeFD, err := unix.OpenTree(-1, path, uint(unix.OPEN_TREE_CLONE|unix.OPEN_TREE_CLOEXEC))
+	if err != nil {
+		return false
+	}
+	defer unix.Close(treeFD)
+
+	// We want to test if idmap mounts are supported.
+	// So we use just some random mapping, it doesn't really matter which one.
+	// For the helper command, we just need something that is alive while we
+	// test this, a sleep 5 will do it.
+	cmd := exec.Command("sleep", "5")
+	cmd.SysProcAttr = &syscall.SysProcAttr{
+		Cloneflags:  syscall.CLONE_NEWUSER,
+		UidMappings: []syscall.SysProcIDMap{{ContainerID: 0, HostID: 65536, Size: 65536}},
+		GidMappings: []syscall.SysProcIDMap{{ContainerID: 0, HostID: 65536, Size: 65536}},
+	}
+	if err := cmd.Start(); err != nil {
+		return false
+	}
+	defer func() {
+		_ = cmd.Process.Kill()
+		_ = cmd.Wait()
+	}()
+
+	usernsFD := fmt.Sprintf("/proc/%d/ns/user", cmd.Process.Pid)
+	var usernsFile *os.File
+	if usernsFile, err = os.Open(usernsFD); err != nil {
+		return false
+	}
+	defer usernsFile.Close()
+
+	attr := unix.MountAttr{
+		Attr_set:  unix.MOUNT_ATTR_IDMAP,
+		Userns_fd: uint64(usernsFile.Fd()),
+	}
+	if err := unix.MountSetattr(treeFD, "", unix.AT_EMPTY_PATH, &attr); err != nil {
+		return false
+	}
+
+	return true
+}
+
+// traversePath gives 755 permissions for all elements in tPath below
+// os.TempDir() and errors out if elements above it don't have read+exec
+// permissions for others.  tPath MUST be a descendant of os.TempDir(). The path
+// returned by testing.TempDir() usually is.
+func traversePath(tPath string) error {
+	// Check the assumption that the argument is under os.TempDir().
+	tempBase := os.TempDir()
+	if !strings.HasPrefix(tPath, tempBase) {
+		return fmt.Errorf("traversePath: %q is not a descendant of %q", tPath, tempBase)
+	}
+
+	var path string
+	for _, p := range strings.SplitAfter(tPath, "/") {
+		path = path + p
+		stats, err := os.Stat(path)
+		if err != nil {
+			return err
+		}
+
+		perm := stats.Mode().Perm()
+		if perm&0o5 == 0o5 {
+			continue
+		}
+		if strings.HasPrefix(tempBase, path) {
+			return fmt.Errorf("traversePath: directory %q MUST have read+exec permissions for others", path)
+		}
+
+		if err := os.Chmod(path, perm|0o755); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
 func TestPodUserNS(t *testing.T) {
 	containerID := uint32(0)
 	hostID := uint32(65536)
 	size := uint32(65536)
+	idmap := []*runtime.IDMapping{
+		{
+			ContainerId: containerID,
+			HostId:      hostID,
+			Length:      size,
+		},
+	}
+
+	volumeHostPath := t.TempDir()
+	if err := traversePath(volumeHostPath); err != nil {
+		t.Fatalf("failed to setup volume host path: %v", err)
+	}
+
 	for name, test := range map[string]struct {
 		sandboxOpts   []PodSandboxOpts
 		containerOpts []ContainerOpts
 		checkOutput   func(t *testing.T, output string)
+		hostVolumes   bool // whether to config uses host Volumes
 		expectErr     bool
 	}{
 		"userns uid mapping": {
@@ -85,6 +191,31 @@ func TestPodUserNS(t *testing.T) {
 				assert.Contains(t, output, "=0=0=")
 			},
 		},
+		"volumes permissions": {
+			sandboxOpts: []PodSandboxOpts{
+				WithPodUserNs(containerID, hostID, size),
+			},
+			hostVolumes: true,
+			containerOpts: []ContainerOpts{
+				WithUserNamespace(containerID, hostID, size),
+				WithIDMapVolumeMount(volumeHostPath, "/mnt", idmap, idmap),
+				// Prints numeric UID and GID for path.
+				// For example, if UID and GID is 0 it will print: =0=0=
+				// We add the "=" signs so we use can assert.Contains() and be sure
+				// the UID/GID is 0 and not things like 100 (that contain 0).
+				// We can't use assert.Equal() easily as it contains timestamp, etc.
+				WithCommand("stat", "-c", "'=%u=%g='", "/mnt/"),
+			},
+			checkOutput: func(t *testing.T, output string) {
+				// The UID and GID should be the current user if chown/remap is done correctly.
+				uid := "0"
+				user, err := user.Current()
+				if user != nil && err == nil {
+					uid = user.Uid
+				}
+				assert.Contains(t, output, "="+uid+"="+uid+"=")
+			},
+		},
 		"fails with several mappings": {
 			sandboxOpts: []PodSandboxOpts{
 				WithPodUserNs(containerID, hostID, size),
@@ -94,12 +225,14 @@ func TestPodUserNS(t *testing.T) {
 		},
 	} {
 		t.Run(name, func(t *testing.T) {
-			cmd := exec.Command("true")
-			cmd.SysProcAttr = &syscall.SysProcAttr{
-				Cloneflags: syscall.CLONE_NEWUSER,
+			if !supportsUserNS() {
+				t.Skip("User namespaces are not supported")
 			}
-			if err := cmd.Run(); err != nil {
-				t.Skip("skipping test: user namespaces are unavailable")
+			if !supportsIDMap(defaultRoot) {
+				t.Skipf("ID mappings are not supported on: %v", defaultRoot)
+			}
+			if test.hostVolumes && !supportsIDMap(volumeHostPath) {
+				t.Skipf("ID mappings are not supported host volume filesystem: %v", volumeHostPath)
 			}
 
 			testPodLogDir := t.TempDir()