chown cgroup to process uid in container namespace

Delegating cgroups to the container enables more complex workloads,
including systemd-based workloads.  The OCI runtime-spec was
recently updated to explicitly admit such delegation, through
specification of cgroup ownership semantics:

  https://github.com/opencontainers/runtime-spec/pull/1123

Pursuant to the updated OCI runtime-spec, change the ownership of
the container's cgroup directory and particular files therein, when
using cgroups v2 and when the cgroupfs is to be mounted read/write.

As a result of this change, systemd workloads can run in isolated
user namespaces on OpenShift when the sandbox's cgroupfs is mounted
read/write.

It might be possible to implement this feature in other cgroup
managers, but that work is deferred.

Signed-off-by: Fraser Tweedale <ftweedal@redhat.com>

libcontainer/cgroups/systemd/v2.go

@@ -1,8 +1,10 @@
 package systemd
 
 import (
+	"bufio"
 	"fmt"
 	"math"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
@@ -288,9 +290,46 @@ func (m *unifiedManager) Apply(pid int) error {
 	if err := fs2.CreateCgroupPath(m.path, m.cgroups); err != nil {
 		return err
 	}
+
+	if c.OwnerUID != nil {
+		filesToChown, err := cgroupFilesToChown()
+		if err != nil {
+			return err
+		}
+
+		for _, v := range filesToChown {
+			err := os.Chown(m.path+"/"+v, *c.OwnerUID, -1)
+			if err != nil {
+				return err
+			}
+		}
+	}
+
 	return nil
 }
 
+// The kernel exposes a list of files that should be chowned to the delegate
+// uid in /sys/kernel/cgroup/delegate.  If the file is not present
+// (Linux < 4.15), use the initial values mentioned in cgroups(7).
+func cgroupFilesToChown() ([]string, error) {
+	filesToChown := []string{"."} // the directory itself must be chowned
+	const cgroupDelegateFile = "/sys/kernel/cgroup/delegate"
+	f, err := os.Open(cgroupDelegateFile)
+	if err == nil {
+		defer f.Close()
+		scanner := bufio.NewScanner(f)
+		for scanner.Scan() {
+			filesToChown = append(filesToChown, scanner.Text())
+		}
+		if err := scanner.Err(); err != nil {
+			return nil, fmt.Errorf("error reading %s: %w", cgroupDelegateFile, err)
+		}
+	} else {
+		filesToChown = append(filesToChown, "cgroup.procs", "cgroup.subtree_control", "cgroup.threads")
+	}
+	return filesToChown, nil
+}
+
 func (m *unifiedManager) Destroy() error {
 	m.mu.Lock()
 	defer m.mu.Unlock()