Make separate nsinit pkg for a dockerinit like init
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This commit is contained in:
Michael Crosby
parent
6415e8becc
commit
c98df9e60a
|
|
@ -11,6 +11,8 @@ type Container struct {
|
|||
WorkingDir string `json:"working_dir,omitempty"`
|
||||
Namespaces Namespaces `json:"namespaces,omitempty"`
|
||||
Capabilities Capabilities `json:"capabilities,omitempty"`
|
||||
Master uintptr `json:"master"`
|
||||
Console string `json:"console"`
|
||||
}
|
||||
|
||||
type Command struct {
|
||||
|
|
|
|||
|
|
@ -12,19 +12,19 @@ const (
|
|||
TIOCSPTLCK = 0x40045431
|
||||
)
|
||||
|
||||
func chroot(dir string) error {
|
||||
func Chroot(dir string) error {
|
||||
return syscall.Chroot(dir)
|
||||
}
|
||||
|
||||
func chdir(dir string) error {
|
||||
func Chdir(dir string) error {
|
||||
return syscall.Chdir(dir)
|
||||
}
|
||||
|
||||
func exec(cmd string, args []string, env []string) error {
|
||||
func Exec(cmd string, args []string, env []string) error {
|
||||
return syscall.Exec(cmd, args, env)
|
||||
}
|
||||
|
||||
func fork() (int, error) {
|
||||
func Fork() (int, error) {
|
||||
syscall.ForkLock.Lock()
|
||||
pid, _, err := syscall.Syscall(syscall.SYS_FORK, 0, 0, 0)
|
||||
syscall.ForkLock.Unlock()
|
||||
|
|
@ -34,33 +34,23 @@ func fork() (int, error) {
|
|||
return int(pid), nil
|
||||
}
|
||||
|
||||
func vfork() (int, error) {
|
||||
syscall.ForkLock.Lock()
|
||||
pid, _, err := syscall.Syscall(syscall.SYS_VFORK, 0, 0, 0)
|
||||
syscall.ForkLock.Unlock()
|
||||
if err != 0 {
|
||||
return -1, err
|
||||
}
|
||||
return int(pid), nil
|
||||
}
|
||||
|
||||
func mount(source, target, fstype string, flags uintptr, data string) error {
|
||||
func Mount(source, target, fstype string, flags uintptr, data string) error {
|
||||
return syscall.Mount(source, target, fstype, flags, data)
|
||||
}
|
||||
|
||||
func unmount(target string, flags int) error {
|
||||
func Unmount(target string, flags int) error {
|
||||
return syscall.Unmount(target, flags)
|
||||
}
|
||||
|
||||
func pivotroot(newroot, putold string) error {
|
||||
func Pivotroot(newroot, putold string) error {
|
||||
return syscall.PivotRoot(newroot, putold)
|
||||
}
|
||||
|
||||
func unshare(flags int) error {
|
||||
func Unshare(flags int) error {
|
||||
return syscall.Unshare(flags)
|
||||
}
|
||||
|
||||
func clone(flags uintptr) (int, error) {
|
||||
func Clone(flags uintptr) (int, error) {
|
||||
syscall.ForkLock.Lock()
|
||||
pid, _, err := syscall.RawSyscall(syscall.SYS_CLONE, flags, 0, 0)
|
||||
syscall.ForkLock.Unlock()
|
||||
|
|
@ -70,7 +60,7 @@ func clone(flags uintptr) (int, error) {
|
|||
return int(pid), nil
|
||||
}
|
||||
|
||||
func setns(fd uintptr, flags uintptr) error {
|
||||
func Setns(fd uintptr, flags uintptr) error {
|
||||
_, _, err := syscall.RawSyscall(SYS_SETNS, fd, flags, 0)
|
||||
if err != 0 {
|
||||
return err
|
||||
|
|
@ -78,87 +68,87 @@ func setns(fd uintptr, flags uintptr) error {
|
|||
return nil
|
||||
}
|
||||
|
||||
func usetCloseOnExec(fd uintptr) error {
|
||||
func UsetCloseOnExec(fd uintptr) error {
|
||||
if _, _, err := syscall.Syscall(syscall.SYS_FCNTL, fd, syscall.F_SETFD, 0); err != 0 {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func setgroups(gids []int) error {
|
||||
func Setgroups(gids []int) error {
|
||||
return syscall.Setgroups(gids)
|
||||
}
|
||||
|
||||
func setresgid(rgid, egid, sgid int) error {
|
||||
func Setresgid(rgid, egid, sgid int) error {
|
||||
return syscall.Setresgid(rgid, egid, sgid)
|
||||
}
|
||||
|
||||
func setresuid(ruid, euid, suid int) error {
|
||||
func Setresuid(ruid, euid, suid int) error {
|
||||
return syscall.Setresuid(ruid, euid, suid)
|
||||
}
|
||||
|
||||
func sethostname(name string) error {
|
||||
func Sethostname(name string) error {
|
||||
return syscall.Sethostname([]byte(name))
|
||||
}
|
||||
|
||||
func setsid() (int, error) {
|
||||
func Setsid() (int, error) {
|
||||
return syscall.Setsid()
|
||||
}
|
||||
|
||||
func ioctl(fd uintptr, flag, data uintptr) error {
|
||||
func Unlockpt(f *os.File) error {
|
||||
var u int
|
||||
return Ioctl(f.Fd(), TIOCSPTLCK, uintptr(unsafe.Pointer(&u)))
|
||||
}
|
||||
|
||||
func Ioctl(fd uintptr, flag, data uintptr) error {
|
||||
if _, _, err := syscall.Syscall(syscall.SYS_IOCTL, fd, flag, data); err != 0 {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func openpmtx() (*os.File, error) {
|
||||
return os.OpenFile("/dev/ptmx", syscall.O_RDONLY|syscall.O_NOCTTY|syscall.O_CLOEXEC, 0)
|
||||
}
|
||||
|
||||
func unlockpt(f *os.File) error {
|
||||
var u int
|
||||
return ioctl(f.Fd(), TIOCSPTLCK, uintptr(unsafe.Pointer(&u)))
|
||||
}
|
||||
|
||||
func ptsname(f *os.File) (string, error) {
|
||||
func Ptsname(f *os.File) (string, error) {
|
||||
var n int
|
||||
if err := ioctl(f.Fd(), TIOCGPTN, uintptr(unsafe.Pointer(&n))); err != nil {
|
||||
if err := Ioctl(f.Fd(), TIOCGPTN, uintptr(unsafe.Pointer(&n))); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return fmt.Sprintf("/dev/pts/%d", n), nil
|
||||
}
|
||||
|
||||
func closefd(fd uintptr) error {
|
||||
func Openpmtx() (*os.File, error) {
|
||||
return os.OpenFile("/dev/ptmx", syscall.O_RDONLY|syscall.O_NOCTTY|syscall.O_CLOEXEC, 0)
|
||||
}
|
||||
|
||||
func Closefd(fd uintptr) error {
|
||||
return syscall.Close(int(fd))
|
||||
}
|
||||
|
||||
func dup2(fd1, fd2 uintptr) error {
|
||||
func Dup2(fd1, fd2 uintptr) error {
|
||||
return syscall.Dup2(int(fd1), int(fd2))
|
||||
}
|
||||
|
||||
func mknod(path string, mode uint32, dev int) error {
|
||||
func Mknod(path string, mode uint32, dev int) error {
|
||||
return syscall.Mknod(path, mode, dev)
|
||||
}
|
||||
|
||||
func parentDeathSignal() error {
|
||||
func ParentDeathSignal() error {
|
||||
if _, _, err := syscall.RawSyscall6(syscall.SYS_PRCTL, syscall.PR_SET_PDEATHSIG, uintptr(syscall.SIGKILL), 0, 0, 0, 0); err != 0 {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func setctty() error {
|
||||
func Setctty() error {
|
||||
if _, _, err := syscall.RawSyscall(syscall.SYS_IOCTL, 0, uintptr(syscall.TIOCSCTTY), 0); err != 0 {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func mkfifo(name string, mode uint32) error {
|
||||
func Mkfifo(name string, mode uint32) error {
|
||||
return syscall.Mkfifo(name, mode)
|
||||
}
|
||||
|
||||
func umask(mask int) int {
|
||||
func Umask(mask int) int {
|
||||
return syscall.Umask(mask)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -8,12 +8,10 @@ import (
|
|||
"errors"
|
||||
"fmt"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer/capabilities"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer/utils"
|
||||
"io"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"os/exec"
|
||||
"syscall"
|
||||
)
|
||||
|
||||
|
|
@ -29,89 +27,31 @@ var (
|
|||
// the container will be spawned with a new network namespace with no configuration. Omiting an
|
||||
// existing network namespace and the CLONE_NEWNET option in the container configuration will allow
|
||||
// the container to the the host's networking options and configuration.
|
||||
func Exec(container *libcontainer.Container) (pid int, err error) {
|
||||
func ExecContainer(container *libcontainer.Container) (pid int, err error) {
|
||||
// a user cannot pass CLONE_NEWNET and an existing net namespace fd to join
|
||||
if container.NetNsFd > 0 && container.Namespaces.Contains(libcontainer.CLONE_NEWNET) {
|
||||
return -1, ErrExistingNetworkNamespace
|
||||
}
|
||||
|
||||
rootfs, err := resolveRootfs(container)
|
||||
if err != nil {
|
||||
return -1, err
|
||||
}
|
||||
|
||||
master, console, err := createMasterAndConsole()
|
||||
if err != nil {
|
||||
return -1, err
|
||||
}
|
||||
|
||||
logger, err := os.OpenFile("/root/logs", os.O_RDWR|os.O_CREATE|os.O_APPEND, 0755)
|
||||
if err != nil {
|
||||
return -1, err
|
||||
}
|
||||
log.SetOutput(logger)
|
||||
container.Console = console
|
||||
container.Master = master.Fd()
|
||||
|
||||
// we need CLONE_VFORK so we can wait on the child
|
||||
flag := getNamespaceFlags(container.Namespaces) | CLONE_VFORK
|
||||
flag := uintptr(getNamespaceFlags(container.Namespaces) | CLONE_VFORK)
|
||||
|
||||
if pid, err = clone(uintptr(flag | SIGCHLD)); err != nil {
|
||||
return -1, fmt.Errorf("error cloning process: %s", err)
|
||||
}
|
||||
|
||||
if pid == 0 {
|
||||
// welcome to your new namespace ;)
|
||||
//
|
||||
// any errors encoutered inside the namespace we should write
|
||||
// out to a log or a pipe to our parent and exit(1)
|
||||
// because writing to stderr will not work after we close
|
||||
if err := closeMasterAndStd(master); err != nil {
|
||||
writeError("close master and std %s", err)
|
||||
}
|
||||
slave, err := openTerminal(console, syscall.O_RDWR)
|
||||
if err != nil {
|
||||
writeError("open terminal %s", err)
|
||||
}
|
||||
if err := dupSlave(slave); err != nil {
|
||||
writeError("dup2 slave %s", err)
|
||||
}
|
||||
|
||||
if container.NetNsFd > 0 {
|
||||
if err := JoinExistingNamespace(container.NetNsFd, libcontainer.CLONE_NEWNET); err != nil {
|
||||
writeError("join existing net namespace %s", err)
|
||||
}
|
||||
}
|
||||
|
||||
if _, err := setsid(); err != nil {
|
||||
writeError("setsid %s", err)
|
||||
}
|
||||
if err := setctty(); err != nil {
|
||||
writeError("setctty %s", err)
|
||||
}
|
||||
if err := parentDeathSignal(); err != nil {
|
||||
writeError("parent deth signal %s", err)
|
||||
}
|
||||
if err := SetupNewMountNamespace(rootfs, console, container.ReadonlyFs); err != nil {
|
||||
writeError("setup mount namespace %s", err)
|
||||
}
|
||||
if err := sethostname(container.ID); err != nil {
|
||||
writeError("sethostname %s", err)
|
||||
}
|
||||
if err := capabilities.DropCapabilities(container); err != nil {
|
||||
writeError("drop capabilities %s", err)
|
||||
}
|
||||
if err := setupUser(container); err != nil {
|
||||
writeError("setup user %s", err)
|
||||
}
|
||||
if container.WorkingDir != "" {
|
||||
if err := chdir(container.WorkingDir); err != nil {
|
||||
writeError("chdir to %s %s", container.WorkingDir, err)
|
||||
}
|
||||
}
|
||||
if err := exec(container.Command.Args[0], container.Command.Args[0:], container.Command.Env); err != nil {
|
||||
writeError("exec %s", err)
|
||||
}
|
||||
panic("unreachable")
|
||||
command := exec.Command("/.nsinit")
|
||||
command.SysProcAttr = &syscall.SysProcAttr{}
|
||||
command.SysProcAttr.Cloneflags = flag
|
||||
command.SysProcAttr.Setctty = true
|
||||
|
||||
if err := command.Start(); err != nil {
|
||||
return -1, err
|
||||
}
|
||||
pid = command.Process.Pid
|
||||
|
||||
go func() {
|
||||
if _, err := io.Copy(os.Stdout, master); err != nil {
|
||||
|
|
@ -130,91 +70,86 @@ func Exec(container *libcontainer.Container) (pid int, err error) {
|
|||
// pid and namespace configuration is needed along with the specific capabilities that should
|
||||
// be dropped once inside the namespace.
|
||||
func ExecIn(container *libcontainer.Container, cmd *libcontainer.Command) (int, error) {
|
||||
if container.NsPid <= 0 {
|
||||
return -1, libcontainer.ErrInvalidPid
|
||||
}
|
||||
|
||||
fds, err := getNsFds(container)
|
||||
if err != nil {
|
||||
return -1, err
|
||||
}
|
||||
|
||||
if container.NetNsFd > 0 {
|
||||
fds = append(fds, container.NetNsFd)
|
||||
}
|
||||
|
||||
pid, err := fork()
|
||||
if err != nil {
|
||||
for _, fd := range fds {
|
||||
syscall.Close(int(fd))
|
||||
return -1, fmt.Errorf("not implemented")
|
||||
/*
|
||||
if container.NsPid <= 0 {
|
||||
return -1, libcontainer.ErrInvalidPid
|
||||
}
|
||||
return -1, err
|
||||
}
|
||||
|
||||
if pid == 0 {
|
||||
for _, fd := range fds {
|
||||
if fd > 0 {
|
||||
if err := JoinExistingNamespace(fd, ""); err != nil {
|
||||
for _, fd := range fds {
|
||||
syscall.Close(int(fd))
|
||||
fds, err := getNsFds(container)
|
||||
if err != nil {
|
||||
return -1, err
|
||||
}
|
||||
|
||||
if container.NetNsFd > 0 {
|
||||
fds = append(fds, container.NetNsFd)
|
||||
}
|
||||
|
||||
pid, err := fork()
|
||||
if err != nil {
|
||||
for _, fd := range fds {
|
||||
syscall.Close(int(fd))
|
||||
}
|
||||
return -1, err
|
||||
}
|
||||
|
||||
if pid == 0 {
|
||||
for _, fd := range fds {
|
||||
if fd > 0 {
|
||||
if err := JoinExistingNamespace(fd, ""); err != nil {
|
||||
for _, fd := range fds {
|
||||
syscall.Close(int(fd))
|
||||
}
|
||||
writeError("join existing namespace for %d %s", fd, err)
|
||||
}
|
||||
writeError("join existing namespace for %d %s", fd, err)
|
||||
}
|
||||
}
|
||||
syscall.Close(int(fd))
|
||||
}
|
||||
|
||||
if container.Namespaces.Contains(libcontainer.CLONE_NEWNS) &&
|
||||
container.Namespaces.Contains(libcontainer.CLONE_NEWPID) {
|
||||
// important:
|
||||
//
|
||||
// we need to fork and unshare so that re can remount proc and sys within
|
||||
// the namespace so the CLONE_NEWPID namespace will take effect
|
||||
// if we don't fork we would end up unmounting proc and sys for the entire
|
||||
// namespace
|
||||
child, err := fork()
|
||||
if err != nil {
|
||||
writeError("fork child %s", err)
|
||||
syscall.Close(int(fd))
|
||||
}
|
||||
|
||||
if child == 0 {
|
||||
if err := unshare(CLONE_NEWNS); err != nil {
|
||||
writeError("unshare newns %s", err)
|
||||
if container.Namespaces.Contains(libcontainer.CLONE_NEWNS) &&
|
||||
container.Namespaces.Contains(libcontainer.CLONE_NEWPID) {
|
||||
// important:
|
||||
//
|
||||
// we need to fork and unshare so that re can remount proc and sys within
|
||||
// the namespace so the CLONE_NEWPID namespace will take effect
|
||||
// if we don't fork we would end up unmounting proc and sys for the entire
|
||||
// namespace
|
||||
child, err := fork()
|
||||
if err != nil {
|
||||
writeError("fork child %s", err)
|
||||
}
|
||||
if err := remountProc(); err != nil {
|
||||
writeError("remount proc %s", err)
|
||||
}
|
||||
if err := remountSys(); err != nil {
|
||||
writeError("remount sys %s", err)
|
||||
}
|
||||
if err := capabilities.DropCapabilities(container); err != nil {
|
||||
writeError("drop caps %s", err)
|
||||
}
|
||||
if err := exec(cmd.Args[0], cmd.Args[0:], cmd.Env); err != nil {
|
||||
writeError("exec %s", err)
|
||||
}
|
||||
panic("unreachable")
|
||||
}
|
||||
exit, err := utils.WaitOnPid(child)
|
||||
if err != nil {
|
||||
writeError("wait on child %s", err)
|
||||
}
|
||||
os.Exit(exit)
|
||||
}
|
||||
if err := exec(cmd.Args[0], cmd.Args[0:], cmd.Env); err != nil {
|
||||
writeError("exec %s", err)
|
||||
}
|
||||
panic("unreachable")
|
||||
}
|
||||
return pid, err
|
||||
}
|
||||
|
||||
func resolveRootfs(container *libcontainer.Container) (string, error) {
|
||||
rootfs, err := filepath.Abs(container.RootFs)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return filepath.EvalSymlinks(rootfs)
|
||||
if child == 0 {
|
||||
if err := unshare(CLONE_NEWNS); err != nil {
|
||||
writeError("unshare newns %s", err)
|
||||
}
|
||||
if err := remountProc(); err != nil {
|
||||
writeError("remount proc %s", err)
|
||||
}
|
||||
if err := remountSys(); err != nil {
|
||||
writeError("remount sys %s", err)
|
||||
}
|
||||
if err := capabilities.DropCapabilities(container); err != nil {
|
||||
writeError("drop caps %s", err)
|
||||
}
|
||||
if err := exec(cmd.Args[0], cmd.Args[0:], cmd.Env); err != nil {
|
||||
writeError("exec %s", err)
|
||||
}
|
||||
panic("unreachable")
|
||||
}
|
||||
exit, err := utils.WaitOnPid(child)
|
||||
if err != nil {
|
||||
writeError("wait on child %s", err)
|
||||
}
|
||||
os.Exit(exit)
|
||||
}
|
||||
if err := exec(cmd.Args[0], cmd.Args[0:], cmd.Env); err != nil {
|
||||
writeError("exec %s", err)
|
||||
}
|
||||
panic("unreachable")
|
||||
}
|
||||
return pid, err
|
||||
*/
|
||||
}
|
||||
|
||||
func createMasterAndConsole() (*os.File, string, error) {
|
||||
|
|
@ -223,44 +158,13 @@ func createMasterAndConsole() (*os.File, string, error) {
|
|||
return nil, "", err
|
||||
}
|
||||
|
||||
console, err := ptsname(master)
|
||||
console, err := Ptsname(master)
|
||||
if err != nil {
|
||||
return nil, "", err
|
||||
}
|
||||
|
||||
if err := unlockpt(master); err != nil {
|
||||
if err := Unlockpt(master); err != nil {
|
||||
return nil, "", err
|
||||
}
|
||||
return master, console, nil
|
||||
}
|
||||
|
||||
func closeMasterAndStd(master *os.File) error {
|
||||
closefd(master.Fd())
|
||||
closefd(0)
|
||||
closefd(1)
|
||||
closefd(2)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func dupSlave(slave *os.File) error {
|
||||
// we close Stdin,etc so our pty slave should have fd 0
|
||||
if slave.Fd() != 0 {
|
||||
return fmt.Errorf("slave fd not 0 %d", slave.Fd())
|
||||
}
|
||||
if err := dup2(slave.Fd(), 1); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := dup2(slave.Fd(), 2); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func openTerminal(name string, flag int) (*os.File, error) {
|
||||
r, e := syscall.Open(name, flag, 0)
|
||||
if e != nil {
|
||||
return nil, &os.PathError{"open", name, e}
|
||||
}
|
||||
return os.NewFile(uintptr(r), name), nil
|
||||
}
|
||||
|
|
|
|||
|
|
@ -14,16 +14,16 @@ var (
|
|||
)
|
||||
|
||||
func SetupNewMountNamespace(rootfs, console string, readonly bool) error {
|
||||
if err := mount("", "/", "", syscall.MS_SLAVE|syscall.MS_REC, ""); err != nil {
|
||||
if err := Mount("", "/", "", syscall.MS_SLAVE|syscall.MS_REC, ""); err != nil {
|
||||
return fmt.Errorf("mounting / as slave %s", err)
|
||||
}
|
||||
|
||||
if err := mount(rootfs, rootfs, "bind", syscall.MS_BIND|syscall.MS_REC, ""); err != nil {
|
||||
if err := Mount(rootfs, rootfs, "bind", syscall.MS_BIND|syscall.MS_REC, ""); err != nil {
|
||||
return fmt.Errorf("mouting %s as bind %s", rootfs, err)
|
||||
}
|
||||
|
||||
if readonly {
|
||||
if err := mount(rootfs, rootfs, "bind", syscall.MS_BIND|syscall.MS_REMOUNT|syscall.MS_RDONLY|syscall.MS_REC, ""); err != nil {
|
||||
if err := Mount(rootfs, rootfs, "bind", syscall.MS_BIND|syscall.MS_REMOUNT|syscall.MS_RDONLY|syscall.MS_REC, ""); err != nil {
|
||||
return fmt.Errorf("mounting %s as readonly %s", rootfs, err)
|
||||
}
|
||||
}
|
||||
|
|
@ -52,29 +52,29 @@ func SetupNewMountNamespace(rootfs, console string, readonly bool) error {
|
|||
return err
|
||||
}
|
||||
|
||||
if err := chdir(rootfs); err != nil {
|
||||
if err := Chdir(rootfs); err != nil {
|
||||
return fmt.Errorf("chdir into %s %s", rootfs, err)
|
||||
}
|
||||
|
||||
if err := mount(rootfs, "/", "", syscall.MS_MOVE, ""); err != nil {
|
||||
if err := Mount(rootfs, "/", "", syscall.MS_MOVE, ""); err != nil {
|
||||
return fmt.Errorf("mount move %s into / %s", rootfs, err)
|
||||
}
|
||||
|
||||
if err := chroot("."); err != nil {
|
||||
if err := Chroot("."); err != nil {
|
||||
return fmt.Errorf("chroot . %s", err)
|
||||
}
|
||||
|
||||
if err := chdir("/"); err != nil {
|
||||
if err := Chdir("/"); err != nil {
|
||||
return fmt.Errorf("chdir / %s", err)
|
||||
}
|
||||
|
||||
umask(0022)
|
||||
Umask(0022)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func copyDevNodes(rootfs string) error {
|
||||
umask(0000)
|
||||
Umask(0000)
|
||||
|
||||
for _, node := range []string{
|
||||
"null",
|
||||
|
|
@ -95,7 +95,7 @@ func copyDevNodes(rootfs string) error {
|
|||
)
|
||||
|
||||
log.Printf("copy %s to %s %d\n", node, dest, st.Rdev)
|
||||
if err := mknod(dest, st.Mode, int(st.Rdev)); err != nil && !os.IsExist(err) {
|
||||
if err := Mknod(dest, st.Mode, int(st.Rdev)); err != nil && !os.IsExist(err) {
|
||||
return fmt.Errorf("copy %s %s", node, err)
|
||||
}
|
||||
}
|
||||
|
|
@ -125,7 +125,7 @@ func setupDev(rootfs string) error {
|
|||
}
|
||||
|
||||
func setupConsole(rootfs, console string) error {
|
||||
umask(0000)
|
||||
Umask(0000)
|
||||
|
||||
stat, err := os.Stat(console)
|
||||
if err != nil {
|
||||
|
|
@ -145,11 +145,11 @@ func setupConsole(rootfs, console string) error {
|
|||
return err
|
||||
}
|
||||
|
||||
if err := mknod(dest, (st.Mode&^07777)|0600, int(st.Rdev)); err != nil {
|
||||
if err := Mknod(dest, (st.Mode&^07777)|0600, int(st.Rdev)); err != nil {
|
||||
return fmt.Errorf("mknod %s %s", dest, err)
|
||||
}
|
||||
|
||||
if err := mount(console, dest, "bind", syscall.MS_BIND, ""); err != nil {
|
||||
if err := Mount(console, dest, "bind", syscall.MS_BIND, ""); err != nil {
|
||||
return fmt.Errorf("bind %s to %s %s", console, dest, err)
|
||||
}
|
||||
return nil
|
||||
|
|
@ -176,7 +176,7 @@ func mountSystem(rootfs string) error {
|
|||
if err := os.MkdirAll(m.path, 0755); err != nil && !os.IsExist(err) {
|
||||
return fmt.Errorf("mkdirall %s %s", m.path, err)
|
||||
}
|
||||
if err := mount(m.source, m.path, m.device, uintptr(m.flags), m.data); err != nil {
|
||||
if err := Mount(m.source, m.path, m.device, uintptr(m.flags), m.data); err != nil {
|
||||
return fmt.Errorf("mounting %s into %s %s", m.source, m.path, err)
|
||||
}
|
||||
}
|
||||
|
|
@ -184,22 +184,22 @@ func mountSystem(rootfs string) error {
|
|||
}
|
||||
|
||||
func remountProc() error {
|
||||
if err := unmount("/proc", syscall.MNT_DETACH); err != nil {
|
||||
if err := Unmount("/proc", syscall.MNT_DETACH); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := mount("proc", "/proc", "proc", uintptr(defaults), ""); err != nil {
|
||||
if err := Mount("proc", "/proc", "proc", uintptr(defaults), ""); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func remountSys() error {
|
||||
if err := unmount("/sys", syscall.MNT_DETACH); err != nil {
|
||||
if err := Unmount("/sys", syscall.MNT_DETACH); err != nil {
|
||||
if err != syscall.EINVAL {
|
||||
return err
|
||||
}
|
||||
} else {
|
||||
if err := mount("sysfs", "/sys", "sysfs", uintptr(defaults), ""); err != nil {
|
||||
if err := Mount("sysfs", "/sys", "sysfs", uintptr(defaults), ""); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -9,52 +9,14 @@
|
|||
package namespaces
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer/utils"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
)
|
||||
|
||||
// CreateNewNamespace creates a new namespace and binds it's fd to the specified path
|
||||
func CreateNewNamespace(namespace libcontainer.Namespace, bindTo string) error {
|
||||
var (
|
||||
flag = namespaceMap[namespace]
|
||||
name = namespaceFileMap[namespace]
|
||||
nspath = filepath.Join("/proc/self/ns", name)
|
||||
)
|
||||
// TODO: perform validation on name and flag
|
||||
|
||||
pid, err := fork()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if pid == 0 {
|
||||
if err := unshare(flag); err != nil {
|
||||
writeError("unshare %s", err)
|
||||
}
|
||||
if err := mount(nspath, bindTo, "none", syscall.MS_BIND, ""); err != nil {
|
||||
writeError("bind mount %s", err)
|
||||
}
|
||||
os.Exit(0)
|
||||
}
|
||||
exit, err := utils.WaitOnPid(pid)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if exit != 0 {
|
||||
return fmt.Errorf("exit status %d", exit)
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
// JoinExistingNamespace uses the fd of an existing linux namespace and
|
||||
// has the current process join that namespace or the spacespace specified by ns
|
||||
func JoinExistingNamespace(fd uintptr, ns libcontainer.Namespace) error {
|
||||
flag := namespaceMap[ns]
|
||||
if err := setns(fd, uintptr(flag)); err != nil {
|
||||
if err := Setns(fd, uintptr(flag)); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
|
|
|
|||
|
|
@ -0,0 +1,140 @@
|
|||
package nsinit
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer/capabilities"
|
||||
"github.com/dotcloud/docker/pkg/libcontainer/namespaces"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
)
|
||||
|
||||
// InitNamespace should be run inside an existing namespace to setup
|
||||
// common mounts, drop capabilities, and setup network interfaces
|
||||
func InitNamespace(container *libcontainer.Container) error {
|
||||
rootfs, err := resolveRootfs(container)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// any errors encoutered inside the namespace we should write
|
||||
// out to a log or a pipe to our parent and exit(1)
|
||||
// because writing to stderr will not work after we close
|
||||
if err := closeMasterAndStd(container.Master); err != nil {
|
||||
log.Fatalf("close master and std %s", err)
|
||||
return err
|
||||
}
|
||||
|
||||
slave, err := openTerminal(container.Console, syscall.O_RDWR)
|
||||
if err != nil {
|
||||
log.Fatalf("open terminal %s", err)
|
||||
return err
|
||||
}
|
||||
if err := dupSlave(slave); err != nil {
|
||||
log.Fatalf("dup2 slave %s", err)
|
||||
return err
|
||||
}
|
||||
|
||||
/*
|
||||
if container.NetNsFd > 0 {
|
||||
if err := joinExistingNamespace(container.NetNsFd, libcontainer.CLONE_NEWNET); err != nil {
|
||||
log.Fatalf("join existing net namespace %s", err)
|
||||
}
|
||||
}
|
||||
*/
|
||||
|
||||
if _, err := namespaces.Setsid(); err != nil {
|
||||
log.Fatalf("setsid %s", err)
|
||||
return err
|
||||
}
|
||||
if err := namespaces.Setctty(); err != nil {
|
||||
log.Fatalf("setctty %s", err)
|
||||
return err
|
||||
}
|
||||
if err := namespaces.ParentDeathSignal(); err != nil {
|
||||
log.Fatalf("parent deth signal %s", err)
|
||||
return err
|
||||
}
|
||||
if err := namespaces.SetupNewMountNamespace(rootfs, container.Console, container.ReadonlyFs); err != nil {
|
||||
log.Fatalf("setup mount namespace %s", err)
|
||||
return err
|
||||
}
|
||||
if err := namespaces.Sethostname(container.ID); err != nil {
|
||||
log.Fatalf("sethostname %s", err)
|
||||
return err
|
||||
}
|
||||
if err := capabilities.DropCapabilities(container); err != nil {
|
||||
log.Fatalf("drop capabilities %s", err)
|
||||
return err
|
||||
}
|
||||
if err := setupUser(container); err != nil {
|
||||
log.Fatalf("setup user %s", err)
|
||||
return err
|
||||
}
|
||||
if container.WorkingDir != "" {
|
||||
if err := namespaces.Chdir(container.WorkingDir); err != nil {
|
||||
log.Fatalf("chdir to %s %s", container.WorkingDir, err)
|
||||
return err
|
||||
}
|
||||
}
|
||||
if err := namespaces.Exec(container.Command.Args[0], container.Command.Args[0:], container.Command.Env); err != nil {
|
||||
log.Fatalf("exec %s", err)
|
||||
return err
|
||||
}
|
||||
panic("unreachable")
|
||||
}
|
||||
|
||||
func resolveRootfs(container *libcontainer.Container) (string, error) {
|
||||
rootfs, err := filepath.Abs(container.RootFs)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return filepath.EvalSymlinks(rootfs)
|
||||
}
|
||||
|
||||
func closeMasterAndStd(master uintptr) error {
|
||||
namespaces.Closefd(master)
|
||||
namespaces.Closefd(0)
|
||||
namespaces.Closefd(1)
|
||||
namespaces.Closefd(2)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func setupUser(container *libcontainer.Container) error {
|
||||
// TODO: honor user passed on container
|
||||
if err := namespaces.Setgroups(nil); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := namespaces.Setresgid(0, 0, 0); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := namespaces.Setresuid(0, 0, 0); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func dupSlave(slave *os.File) error {
|
||||
// we close Stdin,etc so our pty slave should have fd 0
|
||||
if slave.Fd() != 0 {
|
||||
return fmt.Errorf("slave fd not 0 %d", slave.Fd())
|
||||
}
|
||||
if err := namespaces.Dup2(slave.Fd(), 1); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := namespaces.Dup2(slave.Fd(), 2); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func openTerminal(name string, flag int) (*os.File, error) {
|
||||
r, e := syscall.Open(name, flag, 0)
|
||||
if e != nil {
|
||||
return nil, &os.PathError{"open", name, e}
|
||||
}
|
||||
return os.NewFile(uintptr(r), name), nil
|
||||
}
|
||||
|
|
@ -26,12 +26,6 @@ func addEnvIfNotSet(container *libcontainer.Container, key, value string) {
|
|||
container.Command.Env = append(container.Command.Env, jv)
|
||||
}
|
||||
|
||||
// print and error to stderr and exit(1)
|
||||
func writeError(format string, v ...interface{}) {
|
||||
fmt.Fprintf(os.Stderr, format, v...)
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
// getNsFds inspects the container's namespace configuration and opens the fds to
|
||||
// each of the namespaces.
|
||||
func getNsFds(container *libcontainer.Container) ([]uintptr, error) {
|
||||
|
|
@ -79,27 +73,13 @@ func setupEnvironment(container *libcontainer.Container) {
|
|||
addEnvIfNotSet(container, "LOGNAME", "root")
|
||||
}
|
||||
|
||||
func setupUser(container *libcontainer.Container) error {
|
||||
// TODO: honor user passed on container
|
||||
if err := setgroups(nil); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := setresgid(0, 0, 0); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := setresuid(0, 0, 0); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func getMasterAndConsole(container *libcontainer.Container) (string, *os.File, error) {
|
||||
master, err := openpmtx()
|
||||
master, err := Openpmtx()
|
||||
if err != nil {
|
||||
return "", nil, err
|
||||
}
|
||||
|
||||
console, err := ptsname(master)
|
||||
console, err := Ptsname(master)
|
||||
if err != nil {
|
||||
master.Close()
|
||||
return "", nil, err
|
||||
|
|
|
|||
Loading…
Reference in New Issue