runc/linux_rootfs.go

355 lines
9.7 KiB
Go

// +build linux
package libcontainer
import (
"fmt"
"io/ioutil"
"os"
"path/filepath"
"syscall"
"time"
"github.com/docker/libcontainer/configs"
"github.com/docker/libcontainer/label"
)
const defaultMountFlags = syscall.MS_NOEXEC | syscall.MS_NOSUID | syscall.MS_NODEV
var baseMounts = []*configs.Mount{
{
Source: "proc",
Destination: "/proc",
Device: "proc",
Flags: defaultMountFlags,
},
{
Source: "tmpfs",
Destination: "/dev",
Device: "tmpfs",
Flags: syscall.MS_NOSUID | syscall.MS_STRICTATIME,
Data: "mode=755",
},
{
Source: "devpts",
Destination: "/dev/pts",
Device: "devpts",
Flags: syscall.MS_NOSUID | syscall.MS_NOEXEC,
Data: "newinstance,ptmxmode=0666,mode=620,gid=5",
},
}
// setupRootfs sets up the devices, mount points, and filesystems for use inside a
// new mount namespace.
func setupRootfs(config *configs.Config) (err error) {
if err := prepareRoot(config); err != nil {
return err
}
for _, m := range append(baseMounts, config.Mounts...) {
if err := mount(m, config.Rootfs, config.MountLabel); err != nil {
return err
}
}
if err := createDevices(config); err != nil {
return err
}
if err := setupPtmx(config); err != nil {
return err
}
// stdin, stdout and stderr could be pointing to /dev/null from parent namespace.
// Re-open them inside this namespace.
// FIXME: Need to fix this for user namespaces.
if !config.Namespaces.Contains(configs.NEWUSER) {
if err := reOpenDevNull(config.Rootfs); err != nil {
return err
}
}
if err := setupDevSymlinks(config.Rootfs); err != nil {
return err
}
if err := syscall.Chdir(config.Rootfs); err != nil {
return err
}
if config.NoPivotRoot {
err = msMoveRoot(config.Rootfs)
} else {
err = pivotRoot(config.Rootfs, config.PivotDir)
}
if err != nil {
return err
}
if config.Readonlyfs {
if err := setReadonly(); err != nil {
return err
}
}
syscall.Umask(0022)
return nil
}
func mount(m *configs.Mount, rootfs, mountLabel string) error {
var (
dest = filepath.Join(rootfs, m.Destination)
data = label.FormatMountLabel(m.Data, mountLabel)
)
switch m.Device {
case "proc":
if err := os.MkdirAll(dest, 0755); err != nil && !os.IsExist(err) {
return err
}
return syscall.Mount(m.Source, dest, m.Device, uintptr(m.Flags), "")
case "tmpfs", "mqueue", "devpts", "sysfs":
if err := os.MkdirAll(dest, 0755); err != nil && !os.IsExist(err) {
return err
}
return syscall.Mount(m.Source, dest, m.Device, uintptr(m.Flags), data)
case "bind":
stat, err := os.Stat(m.Source)
if err != nil {
// error out if the source of a bind mount does not exist as we will be
// unable to bind anything to it.
return err
}
if err := createIfNotExists(dest, stat.IsDir()); err != nil {
return err
}
if err := syscall.Mount(m.Source, dest, m.Device, uintptr(m.Flags), data); err != nil {
return err
}
if m.Flags&syscall.MS_RDONLY != 0 {
if err := syscall.Mount(m.Source, dest, m.Device, uintptr(m.Flags|syscall.MS_REMOUNT), ""); err != nil {
return err
}
}
if m.Relabel != "" {
if err := label.Relabel(m.Source, mountLabel, m.Relabel); err != nil {
return err
}
}
if m.Flags&syscall.MS_PRIVATE != 0 {
if err := syscall.Mount("", dest, "none", uintptr(syscall.MS_PRIVATE), ""); err != nil {
return err
}
}
default:
return fmt.Errorf("unknown mount device %q to %q", m.Device, m.Destination)
}
return nil
}
func setupDevSymlinks(rootfs string) error {
var links = [][2]string{
{"/proc/self/fd", "/dev/fd"},
{"/proc/self/fd/0", "/dev/stdin"},
{"/proc/self/fd/1", "/dev/stdout"},
{"/proc/self/fd/2", "/dev/stderr"},
}
// kcore support can be toggled with CONFIG_PROC_KCORE; only create a symlink
// in /dev if it exists in /proc.
if _, err := os.Stat("/proc/kcore"); err == nil {
links = append(links, [2]string{"/proc/kcore", "/dev/kcore"})
}
for _, link := range links {
var (
src = link[0]
dst = filepath.Join(rootfs, link[1])
)
if err := os.Symlink(src, dst); err != nil && !os.IsExist(err) {
return fmt.Errorf("symlink %s %s %s", src, dst, err)
}
}
return nil
}
// Is stdin, stdout or stderr were to be pointing to '/dev/null',
// this method will make them point to '/dev/null' from within this namespace.
func reOpenDevNull(rootfs string) error {
var stat, devNullStat syscall.Stat_t
file, err := os.Open(filepath.Join(rootfs, "/dev/null"))
if err != nil {
return fmt.Errorf("Failed to open /dev/null - %s", err)
}
defer file.Close()
if err := syscall.Fstat(int(file.Fd()), &devNullStat); err != nil {
return err
}
for fd := 0; fd < 3; fd++ {
if err := syscall.Fstat(fd, &stat); err != nil {
return err
}
if stat.Rdev == devNullStat.Rdev {
// Close and re-open the fd.
if err := syscall.Dup2(int(file.Fd()), fd); err != nil {
return err
}
}
}
return nil
}
// Create the device nodes in the container.
func createDevices(config *configs.Config) error {
oldMask := syscall.Umask(0000)
for _, node := range config.Devices {
if err := createDeviceNode(config.Rootfs, node); err != nil {
syscall.Umask(oldMask)
return err
}
}
syscall.Umask(oldMask)
return nil
}
// Creates the device node in the rootfs of the container.
func createDeviceNode(rootfs string, node *configs.Device) error {
var (
dest = filepath.Join(rootfs, node.Path)
parent = filepath.Dir(dest)
)
if err := os.MkdirAll(parent, 0755); err != nil {
return err
}
fileMode := node.FileMode
switch node.Type {
case 'c':
fileMode |= syscall.S_IFCHR
case 'b':
fileMode |= syscall.S_IFBLK
default:
return fmt.Errorf("%c is not a valid device type for device %s", node.Type, node.Path)
}
if err := syscall.Mknod(dest, uint32(fileMode), node.Mkdev()); err != nil && !os.IsExist(err) {
return fmt.Errorf("mknod %s %s", node.Path, err)
}
if err := syscall.Chown(dest, int(node.Uid), int(node.Gid)); err != nil {
return fmt.Errorf("chown %s to %d:%d", node.Path, node.Uid, node.Gid)
}
return nil
}
func prepareRoot(config *configs.Config) error {
flag := syscall.MS_PRIVATE | syscall.MS_REC
if config.NoPivotRoot {
flag = syscall.MS_SLAVE | syscall.MS_REC
}
if err := syscall.Mount("", "/", "", uintptr(flag), ""); err != nil {
return err
}
return syscall.Mount(config.Rootfs, config.Rootfs, "bind", syscall.MS_BIND|syscall.MS_REC, "")
}
func setReadonly() error {
return syscall.Mount("/", "/", "bind", syscall.MS_BIND|syscall.MS_REMOUNT|syscall.MS_RDONLY|syscall.MS_REC, "")
}
func setupPtmx(config *configs.Config) error {
ptmx := filepath.Join(config.Rootfs, "dev/ptmx")
if err := os.Remove(ptmx); err != nil && !os.IsNotExist(err) {
return err
}
if err := os.Symlink("pts/ptmx", ptmx); err != nil {
return fmt.Errorf("symlink dev ptmx %s", err)
}
if config.Console != "" {
uid, err := config.HostUID()
if err != nil {
return err
}
gid, err := config.HostGID()
if err != nil {
return err
}
console := newConsoleFromPath(config.Console)
return console.mount(config.Rootfs, config.MountLabel, uid, gid)
}
return nil
}
func pivotRoot(rootfs, pivotBaseDir string) error {
if pivotBaseDir == "" {
pivotBaseDir = "/"
}
tmpDir := filepath.Join(rootfs, pivotBaseDir)
if err := os.MkdirAll(tmpDir, 0755); err != nil {
return fmt.Errorf("can't create tmp dir %s, error %v", tmpDir, err)
}
pivotDir, err := ioutil.TempDir(tmpDir, ".pivot_root")
if err != nil {
return fmt.Errorf("can't create pivot_root dir %s, error %v", pivotDir, err)
}
if err := syscall.PivotRoot(rootfs, pivotDir); err != nil {
return fmt.Errorf("pivot_root %s", err)
}
if err := syscall.Chdir("/"); err != nil {
return fmt.Errorf("chdir / %s", err)
}
// path to pivot dir now changed, update
pivotDir = filepath.Join(pivotBaseDir, filepath.Base(pivotDir))
if err := syscall.Unmount(pivotDir, syscall.MNT_DETACH); err != nil {
return fmt.Errorf("unmount pivot_root dir %s", err)
}
return os.Remove(pivotDir)
}
func msMoveRoot(rootfs string) error {
if err := syscall.Mount(rootfs, "/", "", syscall.MS_MOVE, ""); err != nil {
return err
}
if err := syscall.Chroot("."); err != nil {
return err
}
return syscall.Chdir("/")
}
// createIfNotExists creates a file or a directory only if it does not already exist.
func createIfNotExists(path string, isDir bool) error {
if _, err := os.Stat(path); err != nil {
if os.IsNotExist(err) {
if isDir {
return os.MkdirAll(path, 0755)
}
if err := os.MkdirAll(filepath.Dir(path), 0755); err != nil {
return err
}
f, err := os.OpenFile(path, os.O_CREATE, 0755)
if err != nil {
return err
}
f.Close()
}
}
return nil
}
// remountReadonly will bind over the top of an existing path and ensure that it is read-only.
func remountReadonly(path string) error {
for i := 0; i < 5; i++ {
if err := syscall.Mount("", path, "", syscall.MS_REMOUNT|syscall.MS_RDONLY, ""); err != nil && !os.IsNotExist(err) {
switch err {
case syscall.EINVAL:
// Probably not a mountpoint, use bind-mount
if err := syscall.Mount(path, path, "", syscall.MS_BIND, ""); err != nil {
return err
}
return syscall.Mount(path, path, "", syscall.MS_BIND|syscall.MS_REMOUNT|syscall.MS_RDONLY|syscall.MS_REC|defaultMountFlags, "")
case syscall.EBUSY:
time.Sleep(100 * time.Millisecond)
continue
default:
return err
}
}
return nil
}
return fmt.Errorf("unable to mount %s as readonly max retries reached", path)
}
// maskFile bind mounts /dev/null over the top of the specified path inside a container
// to avoid security issues from processes reading information from non-namespace aware mounts ( proc/kcore ).
func maskFile(path string) error {
if err := syscall.Mount("/dev/null", path, "", syscall.MS_BIND, ""); err != nil && !os.IsNotExist(err) {
return err
}
return nil
}