Files
runc/restore.go
T
Akihiro Suda 06f789cf26 Disable rootless mode except RootlessCgMgr when executed as the root in userns
This PR decomposes `libcontainer/configs.Config.Rootless bool` into `RootlessEUID bool` and
`RootlessCgroups bool`, so as to make "runc-in-userns" to be more compatible with "rootful" runc.

`RootlessEUID` denotes that runc is being executed as a non-root user (euid != 0) in
the current user namespace. `RootlessEUID` is almost identical to the former `Rootless`
except cgroups stuff.

`RootlessCgroups` denotes that runc is unlikely to have the full access to cgroups.
`RootlessCgroups` is set to false if runc is executed as the root (euid == 0) in the initial namespace.
Otherwise `RootlessCgroups` is set to true.
(Hint: if `RootlessEUID` is true, `RootlessCgroups` becomes true as well)

When runc is executed as the root (euid == 0) in an user namespace (e.g. by Docker-in-LXD, Podman, Usernetes),
`RootlessEUID` is set to false but `RootlessCgroups` is set to true.
So, "runc-in-userns" behaves almost same as "rootful" runc except that cgroups errors are ignored.

This PR does not have any impact on CLI flags and `state.json`.

Note about CLI:
* Now `runc --rootless=(auto|true|false)` CLI flag is only used for setting `RootlessCgroups`.
* Now `runc spec --rootless` is only required when `RootlessEUID` is set to true.
  For runc-in-userns, `runc spec`  without `--rootless` should work, when sufficient numbers of
  UID/GID are mapped.

Note about `$XDG_RUNTIME_DIR` (e.g. `/run/user/1000`):
* `$XDG_RUNTIME_DIR` is ignored if runc is being executed as the root (euid == 0) in the initial namespace, for backward compatibility.
  (`/run/runc` is used)
* If runc is executed as the root (euid == 0) in an user namespace, `$XDG_RUNTIME_DIR` is honored if `$USER != "" && $USER != "root"`.
  This allows unprivileged users to allow execute runc as the root in userns, without mounting writable `/run/runc`.

Note about `state.json`:
* `rootless` is set to true when `RootlessEUID == true && RootlessCgroups == true`.

Signed-off-by: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
2018-09-07 15:05:03 +09:00

143 lines
4.0 KiB
Go

// +build linux
package main
import (
"os"
"github.com/opencontainers/runc/libcontainer"
"github.com/opencontainers/runc/libcontainer/system"
"github.com/sirupsen/logrus"
"github.com/urfave/cli"
)
var restoreCommand = cli.Command{
Name: "restore",
Usage: "restore a container from a previous checkpoint",
ArgsUsage: `<container-id>
Where "<container-id>" is the name for the instance of the container to be
restored.`,
Description: `Restores the saved state of the container instance that was previously saved
using the runc checkpoint command.`,
Flags: []cli.Flag{
cli.StringFlag{
Name: "console-socket",
Value: "",
Usage: "path to an AF_UNIX socket which will receive a file descriptor referencing the master end of the console's pseudoterminal",
},
cli.StringFlag{
Name: "image-path",
Value: "",
Usage: "path to criu image files for restoring",
},
cli.StringFlag{
Name: "work-path",
Value: "",
Usage: "path for saving work files and logs",
},
cli.BoolFlag{
Name: "tcp-established",
Usage: "allow open tcp connections",
},
cli.BoolFlag{
Name: "ext-unix-sk",
Usage: "allow external unix sockets",
},
cli.BoolFlag{
Name: "shell-job",
Usage: "allow shell jobs",
},
cli.BoolFlag{
Name: "file-locks",
Usage: "handle file locks, for safety",
},
cli.StringFlag{
Name: "manage-cgroups-mode",
Value: "",
Usage: "cgroups mode: 'soft' (default), 'full' and 'strict'",
},
cli.StringFlag{
Name: "bundle, b",
Value: "",
Usage: "path to the root of the bundle directory",
},
cli.BoolFlag{
Name: "detach,d",
Usage: "detach from the container's process",
},
cli.StringFlag{
Name: "pid-file",
Value: "",
Usage: "specify the file to write the process id to",
},
cli.BoolFlag{
Name: "no-subreaper",
Usage: "disable the use of the subreaper used to reap reparented processes",
},
cli.BoolFlag{
Name: "no-pivot",
Usage: "do not use pivot root to jail process inside rootfs. This should be used whenever the rootfs is on top of a ramdisk",
},
cli.StringSliceFlag{
Name: "empty-ns",
Usage: "create a namespace, but don't restore its properties",
},
cli.BoolFlag{
Name: "auto-dedup",
Usage: "enable auto deduplication of memory images",
},
cli.BoolFlag{
Name: "lazy-pages",
Usage: "use userfaultfd to lazily restore memory pages",
},
},
Action: func(context *cli.Context) error {
if err := checkArgs(context, 1, exactArgs); err != nil {
return err
}
// XXX: Currently this is untested with rootless containers.
if os.Geteuid() != 0 || system.RunningInUserNS() {
logrus.Warn("runc checkpoint is untested with rootless containers")
}
spec, err := setupSpec(context)
if err != nil {
return err
}
options := criuOptions(context)
if err := setEmptyNsMask(context, options); err != nil {
return err
}
status, err := startContainer(context, spec, CT_ACT_RESTORE, options)
if err != nil {
return err
}
// exit with the container's exit status so any external supervisor is
// notified of the exit with the correct exit status.
os.Exit(status)
return nil
},
}
func criuOptions(context *cli.Context) *libcontainer.CriuOpts {
imagePath := getCheckpointImagePath(context)
if err := os.MkdirAll(imagePath, 0655); err != nil {
fatal(err)
}
return &libcontainer.CriuOpts{
ImagesDirectory: imagePath,
WorkDirectory: context.String("work-path"),
ParentImage: context.String("parent-path"),
LeaveRunning: context.Bool("leave-running"),
TcpEstablished: context.Bool("tcp-established"),
ExternalUnixConnections: context.Bool("ext-unix-sk"),
ShellJob: context.Bool("shell-job"),
FileLocks: context.Bool("file-locks"),
PreDump: context.Bool("pre-dump"),
AutoDedup: context.Bool("auto-dedup"),
LazyPages: context.Bool("lazy-pages"),
StatusFd: context.String("status-fd"),
}
}