Do not create devices when in user namespace

When we launch a container in a new user namespace, we cannot create
devices, so we bind mount the host's devices into place instead.

If we are running in a user namespace (i.e. nested in a container),
then we need to do the same thing.  Add a function to detect that
and check for it before doing mknod.

Signed-off-by: Serge Hallyn <[email protected]>
---
 Changelog - add a comment clarifying what's going on with the
	     uidmap file.

Author: hallyn

libcontainer/rootfs_linux.go

@@ -18,6 +18,7 @@ import (
 	"github.com/opencontainers/runc/libcontainer/cgroups"
 	"github.com/opencontainers/runc/libcontainer/configs"
 	"github.com/opencontainers/runc/libcontainer/label"
+	"github.com/opencontainers/runc/libcontainer/system"
 )
 
 const defaultMountFlags = syscall.MS_NOEXEC | syscall.MS_NOSUID | syscall.MS_NODEV
@@ -383,11 +384,12 @@ func reOpenDevNull() error {
 
 // Create the device nodes in the container.
 func createDevices(config *configs.Config) error {
+	useBindMount := system.RunningInUserNS() || config.Namespaces.Contains(configs.NEWUSER)
 	oldMask := syscall.Umask(0000)
 	for _, node := range config.Devices {
 		// containers running in a user namespace are not allowed to mknod
 		// devices so we can just bind mount it from the host.
-		if err := createDeviceNode(config.Rootfs, node, config.Namespaces.Contains(configs.NEWUSER)); err != nil {
+		if err := createDeviceNode(config.Rootfs, node, useBindMount); err != nil {
 			syscall.Umask(oldMask)
 			return err
 		}

libcontainer/system/linux.go

@@ -3,6 +3,9 @@
 package system
 
 import (
+	"bufio"
+	"fmt"
+	"os"
 	"os/exec"
 	"syscall"
 	"unsafe"
@@ -75,3 +78,37 @@ func Setctty() error {
 	}
 	return nil
 }
+
+/*
+ * Detect whether we are currently running in a user namespace.
+ * Copied from github.com/lxc/lxd/shared/util.go
+ */
+func RunningInUserNS() bool {
+	file, err := os.Open("/proc/self/uid_map")
+	if err != nil {
+		/*
+		 * This kernel-provided file only exists if user namespaces are
+		 * supported
+		 */
+		return false
+	}
+	defer file.Close()
+
+	buf := bufio.NewReader(file)
+	l, _, err := buf.ReadLine()
+	if err != nil {
+		return false
+	}
+
+	line := string(l)
+	var a, b, c int64
+	fmt.Sscanf(line, "%d %d %d", &a, &b, &c)
+	/*
+	 * We assume we are in the initial user namespace if we have a full
+	 * range - 4294967295 uids starting at uid 0.
+	 */
+	if a == 0 && b == 0 && c == 4294967295 {
+		return false
+	}
+	return true
+}