Merge pull request #357 from crosbymichael/api

Flatten config structures and remove namespace package

.gitignore

@@ -0,0 +1 @@
+nsinit/nsinit

cgroups/cgroups.go

@@ -3,7 +3,7 @@ package cgroups
 import (
 	"fmt"
 
-	"github.com/docker/libcontainer/devices"
+	"github.com/docker/libcontainer/configs"
 )
 
 type Manager interface {
@@ -17,7 +17,7 @@ type Manager interface {
 	GetStats() (*Stats, error)
 
 	// Toggles the freezer cgroup according with specified state
-	Freeze(state FreezerState) error
+	Freeze(state configs.FreezerState) error
 
 	// Destroys the cgroup set
 	Destroy() error
@@ -33,14 +33,6 @@ type Manager interface {
 	GetPaths() map[string]string
 }
 
-type FreezerState string
-
-const (
-	Undefined FreezerState = ""
-	Frozen    FreezerState = "FROZEN"
-	Thawed    FreezerState = "THAWED"
-)
-
 type NotFoundError struct {
 	Subsystem string
 }
@@ -59,26 +51,6 @@ func IsNotFound(err error) bool {
 	if err == nil {
 		return false
 	}
-
 	_, ok := err.(*NotFoundError)
 	return ok
 }
-
-type Cgroup struct {
-	Name   string `json:"name,omitempty"`
-	Parent string `json:"parent,omitempty"` // name of parent cgroup or slice
-
-	AllowAllDevices   bool              `json:"allow_all_devices,omitempty"` // If this is true allow access to any kind of device within the container.  If false, allow access only to devices explicitly listed in the allowed_devices list.
-	AllowedDevices    []*devices.Device `json:"allowed_devices,omitempty"`
-	Memory            int64             `json:"memory,omitempty"`             // Memory limit (in bytes)
-	MemoryReservation int64             `json:"memory_reservation,omitempty"` // Memory reservation or soft_limit (in bytes)
-	MemorySwap        int64             `json:"memory_swap,omitempty"`        // Total memory usage (memory + swap); set `-1' to disable swap
-	CpuShares         int64             `json:"cpu_shares,omitempty"`         // CPU shares (relative weight vs. other containers)
-	CpuQuota          int64             `json:"cpu_quota,omitempty"`          // CPU hardcap limit (in usecs). Allowed cpu time in a given period.
-	CpuPeriod         int64             `json:"cpu_period,omitempty"`         // CPU period to be used for hardcapping (in usecs). 0 to use system default.
-	CpusetCpus        string            `json:"cpuset_cpus,omitempty"`        // CPU to use
-	CpusetMems        string            `json:"cpuset_mems,omitempty"`        // MEM to use
-	BlkioWeight       int64             `json:"blkio_weight,omitempty"`       // Specifies per cgroup weight, range is from 10 to 1000.
-	Freezer           FreezerState      `json:"freezer,omitempty"`            // set the freeze value for the process
-	Slice             string            `json:"slice,omitempty"`              // Parent slice to use for systemd
-}

cgroups/fs/apply_raw.go

@@ -8,6 +8,7 @@ import (
 	"strconv"
 
 	"github.com/docker/libcontainer/cgroups"
+	"github.com/docker/libcontainer/configs"
 )
 
 var (
@@ -24,8 +25,17 @@ var (
 	CgroupProcesses = "cgroup.procs"
 )
 
+type subsystem interface {
+	// Returns the stats, as 'stats', corresponding to the cgroup under 'path'.
+	GetStats(path string, stats *cgroups.Stats) error
+	// Removes the cgroup represented by 'data'.
+	Remove(*data) error
+	// Creates and joins the cgroup represented by data.
+	Set(*data) error
+}
+
 type Manager struct {
-	Cgroups *cgroups.Cgroup
+	Cgroups *configs.Cgroup
 	Paths   map[string]string
 }
 
@@ -46,19 +56,10 @@ func init() {
 	}
 }
 
-type subsystem interface {
-	// Returns the stats, as 'stats', corresponding to the cgroup under 'path'.
-	GetStats(path string, stats *cgroups.Stats) error
-	// Removes the cgroup represented by 'data'.
-	Remove(*data) error
-	// Creates and joins the cgroup represented by data.
-	Set(*data) error
-}
-
 type data struct {
 	root   string
 	cgroup string
-	c      *cgroups.Cgroup
+	c      *configs.Cgroup
 	pid    int
 }
 
@@ -109,7 +110,7 @@ func (m *Manager) GetPaths() map[string]string {
 
 // Symmetrical public function to update device based cgroups.  Also available
 // in the systemd implementation.
-func ApplyDevices(c *cgroups.Cgroup, pid int) error {
+func ApplyDevices(c *configs.Cgroup, pid int) error {
 	d, err := getCgroupData(c, pid)
 	if err != nil {
 		return err
@@ -137,7 +138,7 @@ func (m *Manager) GetStats() (*cgroups.Stats, error) {
 
 // Freeze toggles the container's freezer cgroup depending on the state
 // provided
-func (m *Manager) Freeze(state cgroups.FreezerState) error {
+func (m *Manager) Freeze(state configs.FreezerState) error {
 	d, err := getCgroupData(m.Cgroups, 0)
 	if err != nil {
 		return err
@@ -170,7 +171,7 @@ func (m *Manager) GetPids() ([]int, error) {
 	return cgroups.ReadProcsFile(dir)
 }
 
-func getCgroupData(c *cgroups.Cgroup, pid int) (*data, error) {
+func getCgroupData(c *configs.Cgroup, pid int) (*data, error) {
 	if cgroupRoot == "" {
 		return nil, fmt.Errorf("failed to find the cgroup root")
 	}

cgroups/fs/devices.go

@@ -17,7 +17,7 @@ func (s *DevicesGroup) Set(d *data) error {
 		}
 
 		for _, dev := range d.c.AllowedDevices {
-			if err := writeFile(dir, "devices.allow", dev.GetCgroupAllowString()); err != nil {
+			if err := writeFile(dir, "devices.allow", dev.CgroupString()); err != nil {
 				return err
 			}
 		}

cgroups/fs/freezer.go

@@ -5,6 +5,7 @@ import (
 	"time"
 
 	"github.com/docker/libcontainer/cgroups"
+	"github.com/docker/libcontainer/configs"
 )
 
 type FreezerGroup struct {
@@ -12,7 +13,7 @@ type FreezerGroup struct {
 
 func (s *FreezerGroup) Set(d *data) error {
 	switch d.c.Freezer {
-	case cgroups.Frozen, cgroups.Thawed:
+	case configs.Frozen, configs.Thawed:
 		dir, err := d.path("freezer")
 		if err != nil {
 			return err

cgroups/manager/manager.go

@@ -4,13 +4,14 @@ import (
 	"github.com/docker/libcontainer/cgroups"
 	"github.com/docker/libcontainer/cgroups/fs"
 	"github.com/docker/libcontainer/cgroups/systemd"
+	"github.com/docker/libcontainer/configs"
 )
 
 // Create a new cgroup manager with specified configuration
 // TODO this object is not really initialized until Apply() is called.
 // Maybe make this to the equivalent of Apply() at some point?
 // @vmarmol
-func NewCgroupManager(cgroups *cgroups.Cgroup) cgroups.Manager {
+func NewCgroupManager(cgroups *configs.Cgroup) cgroups.Manager {
 	if systemd.UseSystemd() {
 		return &systemd.Manager{
 			Cgroups: cgroups,
@@ -23,7 +24,7 @@ func NewCgroupManager(cgroups *cgroups.Cgroup) cgroups.Manager {
 }
 
 // Restore a cgroup manager with specified configuration and state
-func LoadCgroupManager(cgroups *cgroups.Cgroup, paths map[string]string) cgroups.Manager {
+func LoadCgroupManager(cgroups *configs.Cgroup, paths map[string]string) cgroups.Manager {
 	if systemd.UseSystemd() {
 		return &systemd.Manager{
 			Cgroups: cgroups,

cgroups/systemd/apply_nosystemd.go

@@ -6,10 +6,11 @@ import (
 	"fmt"
 
 	"github.com/docker/libcontainer/cgroups"
+	"github.com/docker/libcontainer/configs"
 )
 
 type Manager struct {
-	Cgroups *cgroups.Cgroup
+	Cgroups *configs.Cgroup
 	Paths   map[string]string
 }
 
@@ -37,14 +38,14 @@ func (m *Manager) GetStats() (*cgroups.Stats, error) {
 	return nil, fmt.Errorf("Systemd not supported")
 }
 
-func (m *Manager) Freeze(state cgroups.FreezerState) error {
+func (m *Manager) Freeze(state configs.FreezerState) error {
 	return fmt.Errorf("Systemd not supported")
 }
 
-func ApplyDevices(c *cgroups.Cgroup, pid int) error {
+func ApplyDevices(c *configs.Cgroup, pid int) error {
 	return fmt.Errorf("Systemd not supported")
 }
 
-func Freeze(c *cgroups.Cgroup, state cgroups.FreezerState) error {
+func Freeze(c *configs.Cgroup, state configs.FreezerState) error {
 	return fmt.Errorf("Systemd not supported")
 }

cgroups/systemd/apply_systemd.go

@@ -16,11 +16,12 @@ import (
 	systemd "github.com/coreos/go-systemd/dbus"
 	"github.com/docker/libcontainer/cgroups"
 	"github.com/docker/libcontainer/cgroups/fs"
+	"github.com/docker/libcontainer/configs"
 	"github.com/godbus/dbus"
 )
 
 type Manager struct {
-	Cgroups *cgroups.Cgroup
+	Cgroups *configs.Cgroup
 	Paths   map[string]string
 }
 
@@ -190,7 +191,7 @@ func writeFile(dir, file, data string) error {
 	return ioutil.WriteFile(filepath.Join(dir, file), []byte(data), 0700)
 }
 
-func joinFreezer(c *cgroups.Cgroup, pid int) error {
+func joinFreezer(c *configs.Cgroup, pid int) error {
 	path, err := getSubsystemPath(c, "freezer")
 	if err != nil {
 		return err
@@ -203,7 +204,7 @@ func joinFreezer(c *cgroups.Cgroup, pid int) error {
 	return ioutil.WriteFile(filepath.Join(path, "cgroup.procs"), []byte(strconv.Itoa(pid)), 0700)
 }
 
-func getSubsystemPath(c *cgroups.Cgroup, subsystem string) (string, error) {
+func getSubsystemPath(c *configs.Cgroup, subsystem string) (string, error) {
 	mountpoint, err := cgroups.FindCgroupMountpoint(subsystem)
 	if err != nil {
 		return "", err
@@ -222,7 +223,7 @@ func getSubsystemPath(c *cgroups.Cgroup, subsystem string) (string, error) {
 	return filepath.Join(mountpoint, initPath, slice, getUnitName(c)), nil
 }
 
-func (m *Manager) Freeze(state cgroups.FreezerState) error {
+func (m *Manager) Freeze(state configs.FreezerState) error {
 	path, err := getSubsystemPath(m.Cgroups, "freezer")
 	if err != nil {
 		return err
@@ -260,7 +261,7 @@ func (m *Manager) GetStats() (*cgroups.Stats, error) {
 	panic("not implemented")
 }
 
-func getUnitName(c *cgroups.Cgroup) string {
+func getUnitName(c *configs.Cgroup) string {
 	return fmt.Sprintf("%s-%s.scope", c.Parent, c.Name)
 }
 
@@ -275,7 +276,7 @@ func getUnitName(c *cgroups.Cgroup) string {
 // Note: we can't use systemd to set up the initial limits, and then change the cgroup
 // because systemd will re-write the device settings if it needs to re-apply the cgroup context.
 // This happens at least for v208 when any sibling unit is started.
-func joinDevices(c *cgroups.Cgroup, pid int) error {
+func joinDevices(c *configs.Cgroup, pid int) error {
 	path, err := getSubsystemPath(c, "devices")
 	if err != nil {
 		return err
@@ -294,7 +295,7 @@ func joinDevices(c *cgroups.Cgroup, pid int) error {
 	}
 
 	for _, dev := range c.AllowedDevices {
-		if err := writeFile(path, "devices.allow", dev.GetCgroupAllowString()); err != nil {
+		if err := writeFile(path, "devices.allow", dev.CgroupString()); err != nil {
 			return err
 		}
 	}
@@ -304,11 +305,11 @@ func joinDevices(c *cgroups.Cgroup, pid int) error {
 
 // Symmetrical public function to update device based cgroups.  Also available
 // in the fs implementation.
-func ApplyDevices(c *cgroups.Cgroup, pid int) error {
+func ApplyDevices(c *configs.Cgroup, pid int) error {
 	return joinDevices(c, pid)
 }
 
-func joinMemory(c *cgroups.Cgroup, pid int) error {
+func joinMemory(c *configs.Cgroup, pid int) error {
 	memorySwap := c.MemorySwap
 
 	if memorySwap == 0 {
@@ -327,7 +328,7 @@ func joinMemory(c *cgroups.Cgroup, pid int) error {
 // systemd does not atm set up the cpuset controller, so we must manually
 // join it. Additionally that is a very finicky controller where each
 // level must have a full setup as the default for a new directory is "no cpus"
-func joinCpuset(c *cgroups.Cgroup, pid int) error {
+func joinCpuset(c *configs.Cgroup, pid int) error {
 	path, err := getSubsystemPath(c, "cpuset")
 	if err != nil {
 		return err

configs/cgroup.go

@@ -0,0 +1,54 @@
+package configs
+
+type FreezerState string
+
+const (
+	Undefined FreezerState = ""
+	Frozen    FreezerState = "FROZEN"
+	Thawed    FreezerState = "THAWED"
+)
+
+type Cgroup struct {
+	Name string `json:"name,omitempty"`
+
+	// name of parent cgroup or slice
+	Parent string `json:"parent,omitempty"`
+
+	// If this is true allow access to any kind of device within the container.  If false, allow access only to devices explicitly listed in the allowed_devices list.
+	AllowAllDevices bool `json:"allow_all_devices,omitempty"`
+
+	AllowedDevices []*Device `json:"allowed_devices,omitempty"`
+
+	// Memory limit (in bytes)
+	Memory int64 `json:"memory,omitempty"`
+
+	// Memory reservation or soft_limit (in bytes)
+	MemoryReservation int64 `json:"memory_reservation,omitempty"`
+
+	// Total memory usage (memory + swap); set `-1' to disable swap
+	MemorySwap int64 `json:"memory_swap,omitempty"`
+
+	// CPU shares (relative weight vs. other containers)
+	CpuShares int64 `json:"cpu_shares,omitempty"`
+
+	// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
+	CpuQuota int64 `json:"cpu_quota,omitempty"`
+
+	// CPU period to be used for hardcapping (in usecs). 0 to use system default.
+	CpuPeriod int64 `json:"cpu_period,omitempty"`
+
+	// CPU to use
+	CpusetCpus string `json:"cpuset_cpus,omitempty"`
+
+	// MEM to use
+	CpusetMems string `json:"cpuset_mems,omitempty"`
+
+	// Specifies per cgroup weight, range is from 10 to 1000.
+	BlkioWeight int64 `json:"blkio_weight,omitempty"`
+
+	// set the freeze value for the process
+	Freezer FreezerState `json:"freezer,omitempty"`
+
+	// Parent slice to use for systemd TODO: remove in favor or parent
+	Slice string `json:"slice,omitempty"`
+}

configs/config.go

@@ -1,70 +1,43 @@
 package configs
 
-import (
-	"github.com/docker/libcontainer/cgroups"
-	"github.com/docker/libcontainer/mount"
-	"github.com/docker/libcontainer/network"
-)
+import "fmt"
 
-type MountConfig mount.MountConfig
-
-type Network network.Network
-
-type NamespaceType string
-
-const (
-	NEWNET  NamespaceType = "NEWNET"
-	NEWPID  NamespaceType = "NEWPID"
-	NEWNS   NamespaceType = "NEWNS"
-	NEWUTS  NamespaceType = "NEWUTS"
-	NEWIPC  NamespaceType = "NEWIPC"
-	NEWUSER NamespaceType = "NEWUSER"
-)
-
-// Namespace defines configuration for each namespace.  It specifies an
-// alternate path that is able to be joined via setns.
-type Namespace struct {
-	Type NamespaceType `json:"type"`
-	Path string        `json:"path,omitempty"`
+type Rlimit struct {
+	Type int    `json:"type,omitempty"`
+	Hard uint64 `json:"hard,omitempty"`
+	Soft uint64 `json:"soft,omitempty"`
 }
 
-type Namespaces []Namespace
-
-func (n *Namespaces) Remove(t NamespaceType) bool {
-	i := n.index(t)
-	if i == -1 {
-		return false
-	}
-	*n = append((*n)[:i], (*n)[i+1:]...)
-	return true
-}
-
-func (n *Namespaces) Add(t NamespaceType, path string) {
-	i := n.index(t)
-	if i == -1 {
-		*n = append(*n, Namespace{Type: t, Path: path})
-		return
-	}
-	(*n)[i].Path = path
-}
-
-func (n *Namespaces) index(t NamespaceType) int {
-	for i, ns := range *n {
-		if ns.Type == t {
-			return i
-		}
-	}
-	return -1
-}
-
-func (n *Namespaces) Contains(t NamespaceType) bool {
-	return n.index(t) != -1
+// IDMap represents UID/GID Mappings for User Namespaces.
+type IDMap struct {
+	ContainerID int `json:"container_id,omitempty"`
+	HostID      int `json:"host_id,omitempty"`
+	Size        int `json:"size,omitempty"`
 }
 
 // Config defines configuration options for executing a process inside a contained environment.
 type Config struct {
-	// Mount specific options.
-	MountConfig *MountConfig `json:"mount_config,omitempty"`
+	// NoPivotRoot will use MS_MOVE and a chroot to jail the process into the container's rootfs
+	// This is a common option when the container is running in ramdisk
+	NoPivotRoot bool `json:"no_pivot_root,omitempty"`
+
+	// PivotDir allows a custom directory inside the container's root filesystem to be used as pivot, when NoPivotRoot is not set.
+	// When a custom PivotDir not set, a temporary dir inside the root filesystem will be used. The pivot dir needs to be writeable.
+	// This is required when using read only root filesystems. In these cases, a read/writeable path can be (bind) mounted somewhere inside the root filesystem to act as pivot.
+	PivotDir string `json:"pivot_dir,omitempty"`
+
+	// ReadonlyFs will remount the container's rootfs as readonly where only externally mounted
+	// bind mounts are writtable
+	ReadonlyFs bool `json:"readonly_fs,omitempty"`
+
+	// Mounts specify additional source and destination paths that will be mounted inside the container's
+	// rootfs and mount namespace if specified
+	Mounts []*Mount `json:"mounts,omitempty"`
+
+	// The device nodes that should be automatically created within the container upon container start.  Note, make sure that the node is marked as allowed in the cgroup as well!
+	DeviceNodes []*Device `json:"device_nodes,omitempty"`
+
+	MountLabel string `json:"mount_label,omitempty"`
 
 	// Pathname to container's root filesystem
 	RootFs string `json:"root_fs,omitempty"`
@@ -83,9 +56,8 @@ type Config struct {
 	// provided in Env are provided to the process
 	Env []string `json:"environment,omitempty"`
 
-	// Tty when true will allocate a pty slave on the host for access by the container's process
-	// and ensure that it is mounted inside the container's rootfs
-	Tty bool `json:"tty,omitempty"`
+	// Console is the path to the console allocated to the container.
+	Console string `json:"console,omitempty"`
 
 	// Namespaces specifies the container's namespaces that it should setup when cloning the init process
 	// If a namespace is not provided that namespace is shared from the container's parent process
@@ -103,7 +75,7 @@ type Config struct {
 
 	// Cgroups specifies specific cgroup settings for the various subsystems that the container is
 	// placed into to limit the resources the container has available
-	Cgroups *cgroups.Cgroup `json:"cgroups,omitempty"`
+	Cgroups *Cgroup `json:"cgroups,omitempty"`
 
 	// AppArmorProfile specifies the profile to apply to the process running in the container and is
 	// change at the time the process is execed
@@ -124,6 +96,7 @@ type Config struct {
 	// AdditionalGroups specifies the gids that should be added to supplementary groups
 	// in addition to those that the user belongs to.
 	AdditionalGroups []int `json:"additional_groups,omitempty"`
+
 	// UidMappings is an array of User ID mappings for User Namespaces
 	UidMappings []IDMap `json:"uid_mappings,omitempty"`
 
@@ -131,36 +104,48 @@ type Config struct {
 	GidMappings []IDMap `json:"gid_mappings,omitempty"`
 }
 
-// Routes can be specified to create entries in the route table as the container is started
-//
-// All of destination, source, and gateway should be either IPv4 or IPv6.
-// One of the three options must be present, and ommitted entries will use their
-// IP family default for the route table.  For IPv4 for example, setting the
-// gateway to 1.2.3.4 and the interface to eth0 will set up a standard
-// destination of 0.0.0.0(or *) when viewed in the route table.
-type Route struct {
-	// Sets the destination and mask, should be a CIDR.  Accepts IPv4 and IPv6
-	Destination string `json:"destination,omitempty"`
-
-	// Sets the source and mask, should be a CIDR.  Accepts IPv4 and IPv6
-	Source string `json:"source,omitempty"`
-
-	// Sets the gateway.  Accepts IPv4 and IPv6
-	Gateway string `json:"gateway,omitempty"`
-
-	// The device to set this route up for, for example: eth0
-	InterfaceName string `json:"interface_name,omitempty"`
+// Gets the root uid for the process on host which could be non-zero
+// when user namespaces are enabled.
+func (c *Config) HostUID() (int, error) {
+	if c.Namespaces.Contains(NEWUSER) {
+		if c.UidMappings == nil {
+			return -1, fmt.Errorf("User namespaces enabled, but no user mappings found.")
+		}
+		id, found := c.hostIDFromMapping(0, c.UidMappings)
+		if !found {
+			return -1, fmt.Errorf("User namespaces enabled, but no root user mapping found.")
+		}
+		return id, nil
+	}
+	// Return default root uid 0
+	return 0, nil
 }
 
-type Rlimit struct {
-	Type int    `json:"type,omitempty"`
-	Hard uint64 `json:"hard,omitempty"`
-	Soft uint64 `json:"soft,omitempty"`
+// Gets the root uid for the process on host which could be non-zero
+// when user namespaces are enabled.
+func (c *Config) HostGID() (int, error) {
+	if c.Namespaces.Contains(NEWUSER) {
+		if c.GidMappings == nil {
+			return -1, fmt.Errorf("User namespaces enabled, but no gid mappings found.")
+		}
+		id, found := c.hostIDFromMapping(0, c.GidMappings)
+		if !found {
+			return -1, fmt.Errorf("User namespaces enabled, but no root user mapping found.")
+		}
+		return id, nil
+	}
+	// Return default root uid 0
+	return 0, nil
 }
 
-// IDMap represents UID/GID Mappings for User Namespaces.
-type IDMap struct {
-	ContainerID int `json:"container_id,omitempty"`
-	HostID      int `json:"host_id,omitempty"`
-	Size        int `json:"size,omitempty"`
+// Utility function that gets a host ID for a container ID from user namespace map
+// if that ID is present in the map.
+func (c *Config) hostIDFromMapping(containerID int, uMap []IDMap) (int, bool) {
+	for _, m := range uMap {
+		if (containerID >= m.ContainerID) && (containerID <= (m.ContainerID + m.Size - 1)) {
+			hostID := m.HostID + (containerID - m.ContainerID)
+			return hostID, true
+		}
+	}
+	return -1, false
 }

configs/config_test.go

@@ -5,8 +5,6 @@ import (
 	"os"
 	"path/filepath"
 	"testing"
-
-	"github.com/docker/libcontainer/devices"
 )
 
 // Checks whether the expected capability is specified in the capabilities.
@@ -19,13 +17,13 @@ func contains(expected string, values []string) bool {
 	return false
 }
 
-func containsDevice(expected *devices.Device, values []*devices.Device) bool {
+func containsDevice(expected *Device, values []*Device) bool {
 	for _, d := range values {
 		if d.Path == expected.Path &&
-			d.CgroupPermissions == expected.CgroupPermissions &&
+			d.Permissions == expected.Permissions &&
 			d.FileMode == expected.FileMode &&
-			d.MajorNumber == expected.MajorNumber &&
-			d.MinorNumber == expected.MinorNumber &&
+			d.Major == expected.Major &&
+			d.Minor == expected.Minor &&
 			d.Type == expected.Type {
 			return true
 		}
@@ -59,11 +57,6 @@ func TestConfigJsonFormat(t *testing.T) {
 		t.Fail()
 	}
 
-	if !container.Tty {
-		t.Log("tty should be set to true")
-		t.Fail()
-	}
-
 	if !container.Namespaces.Contains(NEWNET) {
 		t.Log("namespaces should contain NEWNET")
 		t.Fail()
@@ -120,8 +113,8 @@ func TestConfigJsonFormat(t *testing.T) {
 		}
 	}
 
-	for _, d := range devices.DefaultSimpleDevices {
-		if !containsDevice(d, container.MountConfig.DeviceNodes) {
+	for _, d := range DefaultSimpleDevices {
+		if !containsDevice(d, container.DeviceNodes) {
 			t.Logf("expected device configuration for %s", d.Path)
 			t.Fail()
 		}
@@ -154,8 +147,8 @@ func TestSelinuxLabels(t *testing.T) {
 	if container.ProcessLabel != label {
 		t.Fatalf("expected process label %q but received %q", label, container.ProcessLabel)
 	}
-	if container.MountConfig.MountLabel != label {
-		t.Fatalf("expected mount label %q but received %q", label, container.MountConfig.MountLabel)
+	if container.MountLabel != label {
+		t.Fatalf("expected mount label %q but received %q", label, container.MountLabel)
 	}
 }
 

configs/device.go

@@ -0,0 +1,42 @@
+package configs
+
+import (
+	"fmt"
+	"os"
+)
+
+const (
+	Wildcard = -1
+)
+
+type Device struct {
+	Type rune `json:"type,omitempty"`
+	// It is fine if this is an empty string in the case that you are using Wildcards
+	Path string `json:"path,omitempty"`
+	// Use the wildcard constant for wildcards.
+	Major int64 `json:"major,omitempty"`
+	// Use the wildcard constant for wildcards.
+	Minor int64 `json:"minor,omitempty"`
+	// Typically just "rwm"
+	Permissions string `json:"permissions,omitempty"`
+	// The permission bits of the file's mode
+	FileMode os.FileMode `json:"file_mode,omitempty"`
+	Uid      uint32      `json:"uid,omitempty"`
+	Gid      uint32      `json:"gid,omitempty"`
+}
+
+func (d *Device) CgroupString() string {
+	return fmt.Sprintf("%c %s:%s %s", d.Type, deviceNumberString(d.Major), deviceNumberString(d.Minor), d.Permissions)
+}
+
+func (d *Device) Mkdev() int {
+	return int((d.Major << 8) | (d.Minor & 0xff) | ((d.Minor & 0xfff00) << 12))
+}
+
+// deviceNumberString converts the device number to a string return result.
+func deviceNumberString(number int64) string {
+	if number == Wildcard {
+		return "*"
+	}
+	return fmt.Sprint(number)
+}

configs/device_defaults.go

@@ -0,0 +1,137 @@
+package configs
+
+var (
+	// These are devices that are to be both allowed and created.
+	DefaultSimpleDevices = []*Device{
+		// /dev/null and zero
+		{
+			Path:        "/dev/null",
+			Type:        'c',
+			Major:       1,
+			Minor:       3,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+		{
+			Path:        "/dev/zero",
+			Type:        'c',
+			Major:       1,
+			Minor:       5,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+
+		{
+			Path:        "/dev/full",
+			Type:        'c',
+			Major:       1,
+			Minor:       7,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+
+		// consoles and ttys
+		{
+			Path:        "/dev/tty",
+			Type:        'c',
+			Major:       5,
+			Minor:       0,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+
+		// /dev/urandom,/dev/random
+		{
+			Path:        "/dev/urandom",
+			Type:        'c',
+			Major:       1,
+			Minor:       9,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+		{
+			Path:        "/dev/random",
+			Type:        'c',
+			Major:       1,
+			Minor:       8,
+			Permissions: "rwm",
+			FileMode:    0666,
+		},
+	}
+	DefaultAllowedDevices = append([]*Device{
+		// allow mknod for any device
+		{
+			Type:        'c',
+			Major:       Wildcard,
+			Minor:       Wildcard,
+			Permissions: "m",
+		},
+		{
+			Type:        'b',
+			Major:       Wildcard,
+			Minor:       Wildcard,
+			Permissions: "m",
+		},
+
+		{
+			Path:        "/dev/console",
+			Type:        'c',
+			Major:       5,
+			Minor:       1,
+			Permissions: "rwm",
+		},
+		{
+			Path:        "/dev/tty0",
+			Type:        'c',
+			Major:       4,
+			Minor:       0,
+			Permissions: "rwm",
+		},
+		{
+			Path:        "/dev/tty1",
+			Type:        'c',
+			Major:       4,
+			Minor:       1,
+			Permissions: "rwm",
+		},
+		// /dev/pts/ - pts namespaces are "coming soon"
+		{
+			Path:        "",
+			Type:        'c',
+			Major:       136,
+			Minor:       Wildcard,
+			Permissions: "rwm",
+		},
+		{
+			Path:        "",
+			Type:        'c',
+			Major:       5,
+			Minor:       2,
+			Permissions: "rwm",
+		},
+
+		// tuntap
+		{
+			Path:        "",
+			Type:        'c',
+			Major:       10,
+			Minor:       200,
+			Permissions: "rwm",
+		},
+	}, DefaultSimpleDevices...)
+	DefaultAutoCreatedDevices = append([]*Device{
+		{
+			// /dev/fuse is created but not allowed.
+			// This is to allow java to work.  Because java
+			// Insists on there being a /dev/fuse
+			// https://github.com/docker/docker/issues/514
+			// https://github.com/docker/docker/issues/2393
+			//
+			Path:        "/dev/fuse",
+			Type:        'c',
+			Major:       10,
+			Minor:       229,
+			Permissions: "rwm",
+		},
+	}, DefaultSimpleDevices...)
+)

configs/mount.go

@@ -1,4 +1,4 @@
-package mount
+package configs
 
 import (
 	"fmt"
@@ -10,6 +10,8 @@ import (
 	"github.com/docker/libcontainer/label"
 )
 
+const DefaultMountFlags = syscall.MS_NOEXEC | syscall.MS_NOSUID | syscall.MS_NODEV
+
 type Mount struct {
 	Type        string `json:"type,omitempty"`
 	Source      string `json:"source,omitempty"`      // Source path, in the host namespace
@@ -101,9 +103,31 @@ func (m *Mount) tmpfsMount(rootfs, mountLabel string) error {
 		return fmt.Errorf("creating new tmpfs mount target %s", err)
 	}
 
-	if err := syscall.Mount("tmpfs", dest, "tmpfs", uintptr(defaultMountFlags), l); err != nil {
+	if err := syscall.Mount("tmpfs", dest, "tmpfs", uintptr(DefaultMountFlags), l); err != nil {
 		return fmt.Errorf("%s mounting %s in tmpfs", err, dest)
 	}
 
 	return nil
 }
+
+func createIfNotExists(path string, isDir bool) error {
+	if _, err := os.Stat(path); err != nil {
+		if os.IsNotExist(err) {
+			if isDir {
+				if err := os.MkdirAll(path, 0755); err != nil {
+					return err
+				}
+			} else {
+				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
+}

configs/namespaces.go

@@ -0,0 +1,82 @@
+package configs
+
+import (
+	"syscall"
+)
+
+type NamespaceType string
+
+const (
+	NEWNET  NamespaceType = "NEWNET"
+	NEWPID  NamespaceType = "NEWPID"
+	NEWNS   NamespaceType = "NEWNS"
+	NEWUTS  NamespaceType = "NEWUTS"
+	NEWIPC  NamespaceType = "NEWIPC"
+	NEWUSER NamespaceType = "NEWUSER"
+)
+
+// Namespace defines configuration for each namespace.  It specifies an
+// alternate path that is able to be joined via setns.
+type Namespace struct {
+	Type NamespaceType `json:"type"`
+	Path string        `json:"path,omitempty"`
+}
+
+func (n *Namespace) Syscall() int {
+	return namespaceInfo[n.Type]
+}
+
+type Namespaces []Namespace
+
+func (n *Namespaces) Remove(t NamespaceType) bool {
+	i := n.index(t)
+	if i == -1 {
+		return false
+	}
+	*n = append((*n)[:i], (*n)[i+1:]...)
+	return true
+}
+
+func (n *Namespaces) Add(t NamespaceType, path string) {
+	i := n.index(t)
+	if i == -1 {
+		*n = append(*n, Namespace{Type: t, Path: path})
+		return
+	}
+	(*n)[i].Path = path
+}
+
+func (n *Namespaces) index(t NamespaceType) int {
+	for i, ns := range *n {
+		if ns.Type == t {
+			return i
+		}
+	}
+	return -1
+}
+
+func (n *Namespaces) Contains(t NamespaceType) bool {
+	return n.index(t) != -1
+}
+
+var namespaceInfo = map[NamespaceType]int{
+	NEWNET:  syscall.CLONE_NEWNET,
+	NEWNS:   syscall.CLONE_NEWNS,
+	NEWUSER: syscall.CLONE_NEWUSER,
+	NEWIPC:  syscall.CLONE_NEWIPC,
+	NEWUTS:  syscall.CLONE_NEWUTS,
+	NEWPID:  syscall.CLONE_NEWPID,
+}
+
+// CloneFlags parses the container's Namespaces options to set the correct
+// flags on clone, unshare. This functions returns flags only for new namespaces.
+func (n *Namespaces) CloneFlags() uintptr {
+	var flag int
+	for _, v := range *n {
+		if v.Path != "" {
+			continue
+		}
+		flag |= namespaceInfo[v.Type]
+	}
+	return uintptr(flag)
+}

configs/network.go

@@ -0,0 +1,62 @@
+package configs
+
+// Network defines configuration for a container's networking stack
+//
+// The network configuration can be omited from a container causing the
+// container to be setup with the host's networking stack
+type Network struct {
+	// Type sets the networks type, commonly veth and loopback
+	Type string `json:"type,omitempty"`
+
+	// The bridge to use.
+	Bridge string `json:"bridge,omitempty"`
+
+	// Prefix for the veth interfaces.
+	VethPrefix string `json:"veth_prefix,omitempty"`
+
+	// MacAddress contains the MAC address to set on the network interface
+	MacAddress string `json:"mac_address,omitempty"`
+
+	// Address contains the IPv4 and mask to set on the network interface
+	Address string `json:"address,omitempty"`
+
+	// IPv6Address contains the IPv6 and mask to set on the network interface
+	IPv6Address string `json:"ipv6_address,omitempty"`
+
+	// Gateway sets the gateway address that is used as the default for the interface
+	Gateway string `json:"gateway,omitempty"`
+
+	// IPv6Gateway sets the ipv6 gateway address that is used as the default for the interface
+	IPv6Gateway string `json:"ipv6_gateway,omitempty"`
+
+	// Mtu sets the mtu value for the interface and will be mirrored on both the host and
+	// container's interfaces if a pair is created, specifically in the case of type veth
+	// Note: This does not apply to loopback interfaces.
+	Mtu int `json:"mtu,omitempty"`
+
+	// TxQueueLen sets the tx_queuelen value for the interface and will be mirrored on both the host and
+	// container's interfaces if a pair is created, specifically in the case of type veth
+	// Note: This does not apply to loopback interfaces.
+	TxQueueLen int `json:"txqueuelen,omitempty"`
+}
+
+// Routes can be specified to create entries in the route table as the container is started
+//
+// All of destination, source, and gateway should be either IPv4 or IPv6.
+// One of the three options must be present, and ommitted entries will use their
+// IP family default for the route table.  For IPv4 for example, setting the
+// gateway to 1.2.3.4 and the interface to eth0 will set up a standard
+// destination of 0.0.0.0(or *) when viewed in the route table.
+type Route struct {
+	// Sets the destination and mask, should be a CIDR.  Accepts IPv4 and IPv6
+	Destination string `json:"destination,omitempty"`
+
+	// Sets the source and mask, should be a CIDR.  Accepts IPv4 and IPv6
+	Source string `json:"source,omitempty"`
+
+	// Sets the gateway.  Accepts IPv4 and IPv6
+	Gateway string `json:"gateway,omitempty"`
+
+	// The device to set this route up for, for example: eth0
+	InterfaceName string `json:"interface_name,omitempty"`
+}

configs/state.go

@@ -1,13 +1,5 @@
 package configs
 
-import (
-	"encoding/json"
-	"os"
-	"path/filepath"
-
-	"github.com/docker/libcontainer/network"
-)
-
 // State represents a running container's state
 type State struct {
 	// InitPid is the init process id in the parent namespace
@@ -17,21 +9,30 @@ type State struct {
 	InitStartTime string `json:"init_start_time,omitempty"`
 
 	// Network runtime state.
-	NetworkState network.NetworkState `json:"network_state,omitempty"`
+	NetworkState NetworkState `json:"network_state,omitempty"`
 
 	// Path to all the cgroups setup for a container. Key is cgroup subsystem name.
 	CgroupPaths map[string]string `json:"cgroup_paths,omitempty"`
+
+	Status Status `json:"status,omitempty"`
 }
 
-// The running state of the container.
-type RunState int
+// Struct describing the network specific runtime state that will be maintained by libcontainer for all running containers
+// Do not depend on it outside of libcontainer.
+// TODO: move veth names to config time
+type NetworkState struct {
+	// The name of the veth interface on the Host.
+	VethHost string `json:"veth_host,omitempty"`
+	// The name of the veth interface created inside the container for the child.
+	VethChild string `json:"veth_child,omitempty"`
+}
+
+// The status of a container.
+type Status int
 
 const (
-	// The name of the runtime state file
-	stateFile = "state.json"
-
 	// The container exists and is running.
-	Running RunState = iota + 1
+	Running Status = iota + 1
 
 	// The container exists, it is in the process of being paused.
 	Pausing
@@ -42,36 +43,3 @@ const (
 	// The container does not exist.
 	Destroyed
 )
-
-// SaveState writes the container's runtime state to a state.json file
-// in the specified path
-func SaveState(basePath string, state *State) error {
-	f, err := os.Create(filepath.Join(basePath, stateFile))
-	if err != nil {
-		return err
-	}
-	defer f.Close()
-
-	return json.NewEncoder(f).Encode(state)
-}
-
-// GetState reads the state.json file for a running container
-func GetState(basePath string) (*State, error) {
-	f, err := os.Open(filepath.Join(basePath, stateFile))
-	if err != nil {
-		return nil, err
-	}
-	defer f.Close()
-
-	var state *State
-	if err := json.NewDecoder(f).Decode(&state); err != nil {
-		return nil, err
-	}
-
-	return state, nil
-}
-
-// DeleteState deletes the state.json file
-func DeleteState(basePath string) error {
-	return os.Remove(filepath.Join(basePath, stateFile))
-}

container.go

@@ -4,9 +4,18 @@ NOTE: The API is in flux and mainly not implemented. Proceed with caution until
 package libcontainer
 
 import (
+	"os"
+
+	"github.com/docker/libcontainer/cgroups"
 	"github.com/docker/libcontainer/configs"
+	"github.com/docker/libcontainer/network"
 )
 
+type Stats struct {
+	NetworkStats *network.NetworkStats `json:"network_stats,omitempty"`
+	CgroupStats  *cgroups.Stats        `json:"cgroup_stats,omitempty"`
+}
+
 // A libcontainer container object.
 //
 // Each container is thread-safe within the same process. Since a container can
@@ -16,15 +25,14 @@ type Container interface {
 	// Returns the ID of the container
 	ID() string
 
-	// Returns the current run state of the container.
+	// Returns the current status of the container.
 	//
 	// errors:
-	// ContainerDestroyed - Container no longer exists,
 	// Systemerror - System error.
-	RunState() (configs.RunState, error)
+	Status() (configs.Status, error)
 
 	// Returns the current config of the container.
-	Config() *configs.Config
+	Config() configs.Config
 
 	// Returns the PIDs inside this container. The PIDs are in the namespace of the calling process.
 	//
@@ -41,7 +49,7 @@ type Container interface {
 	// errors:
 	// ContainerDestroyed - Container no longer exists,
 	// Systemerror - System error.
-	Stats() (*ContainerStats, error)
+	Stats() (*Stats, error)
 
 	// Start a process inside the container. Returns the PID of the new process (in the caller process's namespace) and a channel that will return the exit status of the process whenever it dies.
 	//
@@ -50,7 +58,7 @@ type Container interface {
 	// ConfigInvalid - config is invalid,
 	// ContainerPaused - Container is paused,
 	// Systemerror - System error.
-	StartProcess(config *ProcessConfig) (pid int, err error)
+	Start(process *Process) (pid int, err error)
 
 	// Destroys the container after killing all running processes.
 	//
@@ -80,25 +88,17 @@ type Container interface {
 	// Systemerror - System error.
 	Resume() error
 
-	// Signal sends the specified signal to a process owned by the container.
+	// Signal sends the specified signal to the init process of the container.
 	//
 	// errors:
 	// ContainerDestroyed - Container no longer exists,
 	// ContainerPaused - Container is paused,
 	// Systemerror - System error.
-	Signal(pid, signal int) error
+	Signal(signal os.Signal) error
 
-	// Wait waits for the init process of the conatiner to die and returns it's exit status.
+	// OOM returns a read-only channel signaling when the container receives an OOM notification.
 	//
 	// errors:
-	// ContainerDestroyed - Container no longer exists,
 	// Systemerror - System error.
-	Wait() (exitStatus int, err error)
-
-	// WaitProcess waits on a process owned by the container.
-	//
-	// errors:
-	// ContainerDestroyed - Container no longer exists,
-	// Systemerror - System error.
-	WaitProcess(pid int) (exitStatus int, err error)
+	OOM() (<-chan struct{}, error)
 }

devices/defaults.go

@@ -1,159 +0,0 @@
-package devices
-
-var (
-	// These are devices that are to be both allowed and created.
-
-	DefaultSimpleDevices = []*Device{
-		// /dev/null and zero
-		{
-			Path:              "/dev/null",
-			Type:              'c',
-			MajorNumber:       1,
-			MinorNumber:       3,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-		{
-			Path:              "/dev/zero",
-			Type:              'c',
-			MajorNumber:       1,
-			MinorNumber:       5,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-
-		{
-			Path:              "/dev/full",
-			Type:              'c',
-			MajorNumber:       1,
-			MinorNumber:       7,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-
-		// consoles and ttys
-		{
-			Path:              "/dev/tty",
-			Type:              'c',
-			MajorNumber:       5,
-			MinorNumber:       0,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-
-		// /dev/urandom,/dev/random
-		{
-			Path:              "/dev/urandom",
-			Type:              'c',
-			MajorNumber:       1,
-			MinorNumber:       9,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-		{
-			Path:              "/dev/random",
-			Type:              'c',
-			MajorNumber:       1,
-			MinorNumber:       8,
-			CgroupPermissions: "rwm",
-			FileMode:          0666,
-		},
-	}
-
-	DefaultAllowedDevices = append([]*Device{
-		// allow mknod for any device
-		{
-			Type:              'c',
-			MajorNumber:       Wildcard,
-			MinorNumber:       Wildcard,
-			CgroupPermissions: "m",
-		},
-		{
-			Type:              'b',
-			MajorNumber:       Wildcard,
-			MinorNumber:       Wildcard,
-			CgroupPermissions: "m",
-		},
-
-		{
-			Path:              "/dev/console",
-			Type:              'c',
-			MajorNumber:       5,
-			MinorNumber:       1,
-			CgroupPermissions: "rwm",
-		},
-		{
-			Path:              "/dev/tty0",
-			Type:              'c',
-			MajorNumber:       4,
-			MinorNumber:       0,
-			CgroupPermissions: "rwm",
-		},
-		{
-			Path:              "/dev/tty1",
-			Type:              'c',
-			MajorNumber:       4,
-			MinorNumber:       1,
-			CgroupPermissions: "rwm",
-		},
-		// /dev/pts/ - pts namespaces are "coming soon"
-		{
-			Path:              "",
-			Type:              'c',
-			MajorNumber:       136,
-			MinorNumber:       Wildcard,
-			CgroupPermissions: "rwm",
-		},
-		{
-			Path:              "",
-			Type:              'c',
-			MajorNumber:       5,
-			MinorNumber:       2,
-			CgroupPermissions: "rwm",
-		},
-
-		// tuntap
-		{
-			Path:              "",
-			Type:              'c',
-			MajorNumber:       10,
-			MinorNumber:       200,
-			CgroupPermissions: "rwm",
-		},
-
-		/*// fuse
-		   {
-		    Path: "",
-		    Type: 'c',
-		    MajorNumber: 10,
-		    MinorNumber: 229,
-		    CgroupPermissions: "rwm",
-		   },
-
-		// rtc
-		   {
-		    Path: "",
-		    Type: 'c',
-		    MajorNumber: 254,
-		    MinorNumber: 0,
-		    CgroupPermissions: "rwm",
-		   },
-		*/
-	}, DefaultSimpleDevices...)
-
-	DefaultAutoCreatedDevices = append([]*Device{
-		{
-			// /dev/fuse is created but not allowed.
-			// This is to allow java to work.  Because java
-			// Insists on there being a /dev/fuse
-			// https://github.com/docker/docker/issues/514
-			// https://github.com/docker/docker/issues/2393
-			//
-			Path:              "/dev/fuse",
-			Type:              'c',
-			MajorNumber:       10,
-			MinorNumber:       229,
-			CgroupPermissions: "rwm",
-		},
-	}, DefaultSimpleDevices...)
-)

devices/devices.go

@@ -7,14 +7,12 @@ import (
 	"os"
 	"path/filepath"
 	"syscall"
-)
 
-const (
-	Wildcard = -1
+	"github.com/docker/libcontainer/configs"
 )
 
 var (
-	ErrNotADeviceNode = errors.New("not a device node")
+	ErrNotADevice = errors.New("not a device node")
 )
 
 // Testing dependencies
@@ -23,45 +21,20 @@ var (
 	ioutilReadDir = ioutil.ReadDir
 )
 
-type Device struct {
-	Type              rune        `json:"type,omitempty"`
-	Path              string      `json:"path,omitempty"`               // It is fine if this is an empty string in the case that you are using Wildcards
-	MajorNumber       int64       `json:"major_number,omitempty"`       // Use the wildcard constant for wildcards.
-	MinorNumber       int64       `json:"minor_number,omitempty"`       // Use the wildcard constant for wildcards.
-	CgroupPermissions string      `json:"cgroup_permissions,omitempty"` // Typically just "rwm"
-	FileMode          os.FileMode `json:"file_mode,omitempty"`          // The permission bits of the file's mode
-	Uid               uint32      `json:"uid,omitempty"`
-	Gid               uint32      `json:"gid,omitempty"`
-}
-
-func GetDeviceNumberString(deviceNumber int64) string {
-	if deviceNumber == Wildcard {
-		return "*"
-	} else {
-		return fmt.Sprintf("%d", deviceNumber)
-	}
-}
-
-func (device *Device) GetCgroupAllowString() string {
-	return fmt.Sprintf("%c %s:%s %s", device.Type, GetDeviceNumberString(device.MajorNumber), GetDeviceNumberString(device.MinorNumber), device.CgroupPermissions)
-}
-
 // Given the path to a device and it's cgroup_permissions(which cannot be easilly queried) look up the information about a linux device and return that information as a Device struct.
-func GetDevice(path, cgroupPermissions string) (*Device, error) {
+func DeviceFromPath(path, permissions string) (*configs.Device, error) {
 	fileInfo, err := osLstat(path)
 	if err != nil {
 		return nil, err
 	}
-
 	var (
 		devType                rune
 		mode                   = fileInfo.Mode()
 		fileModePermissionBits = os.FileMode.Perm(mode)
 	)
-
 	switch {
 	case mode&os.ModeDevice == 0:
-		return nil, ErrNotADeviceNode
+		return nil, ErrNotADevice
 	case mode&os.ModeCharDevice != 0:
 		fileModePermissionBits |= syscall.S_IFCHR
 		devType = 'c'
@@ -69,36 +42,33 @@ func GetDevice(path, cgroupPermissions string) (*Device, error) {
 		fileModePermissionBits |= syscall.S_IFBLK
 		devType = 'b'
 	}
-
 	stat_t, ok := fileInfo.Sys().(*syscall.Stat_t)
 	if !ok {
 		return nil, fmt.Errorf("cannot determine the device number for device %s", path)
 	}
 	devNumber := int(stat_t.Rdev)
-
-	return &Device{
-		Type:              devType,
-		Path:              path,
-		MajorNumber:       Major(devNumber),
-		MinorNumber:       Minor(devNumber),
-		CgroupPermissions: cgroupPermissions,
-		FileMode:          fileModePermissionBits,
-		Uid:               stat_t.Uid,
-		Gid:               stat_t.Gid,
+	return &configs.Device{
+		Type:        devType,
+		Path:        path,
+		Major:       Major(devNumber),
+		Minor:       Minor(devNumber),
+		Permissions: permissions,
+		FileMode:    fileModePermissionBits,
+		Uid:         stat_t.Uid,
+		Gid:         stat_t.Gid,
 	}, nil
 }
 
-func GetHostDeviceNodes() ([]*Device, error) {
+func HostDevices() ([]*configs.Device, error) {
 	return getDeviceNodes("/dev")
 }
 
-func getDeviceNodes(path string) ([]*Device, error) {
+func getDeviceNodes(path string) ([]*configs.Device, error) {
 	files, err := ioutilReadDir(path)
 	if err != nil {
 		return nil, err
 	}
-
-	out := []*Device{}
+	out := []*configs.Device{}
 	for _, f := range files {
 		switch {
 		case f.IsDir():
@@ -117,16 +87,14 @@ func getDeviceNodes(path string) ([]*Device, error) {
 		case f.Name() == "console":
 			continue
 		}
-
-		device, err := GetDevice(filepath.Join(path, f.Name()), "rwm")
+		device, err := DeviceFromPath(filepath.Join(path, f.Name()), "rwm")
 		if err != nil {
-			if err == ErrNotADeviceNode {
+			if err == ErrNotADevice {
 				continue
 			}
 			return nil, err
 		}
 		out = append(out, device)
 	}
-
 	return out, nil
 }

devices/devices_test.go

@@ -6,7 +6,7 @@ import (
 	"testing"
 )
 
-func TestGetDeviceLstatFailure(t *testing.T) {
+func TestDeviceFromPathLstatFailure(t *testing.T) {
 	testError := errors.New("test error")
 
 	// Override os.Lstat to inject error.
@@ -14,13 +14,13 @@ func TestGetDeviceLstatFailure(t *testing.T) {
 		return nil, testError
 	}
 
-	_, err := GetDevice("", "")
+	_, err := DeviceFromPath("", "")
 	if err != testError {
 		t.Fatalf("Unexpected error %v, expected %v", err, testError)
 	}
 }
 
-func TestGetHostDeviceNodesIoutilReadDirFailure(t *testing.T) {
+func TestHostDevicesIoutilReadDirFailure(t *testing.T) {
 	testError := errors.New("test error")
 
 	// Override ioutil.ReadDir to inject error.
@@ -28,13 +28,13 @@ func TestGetHostDeviceNodesIoutilReadDirFailure(t *testing.T) {
 		return nil, testError
 	}
 
-	_, err := GetHostDeviceNodes()
+	_, err := HostDevices()
 	if err != testError {
 		t.Fatalf("Unexpected error %v, expected %v", err, testError)
 	}
 }
 
-func TestGetHostDeviceNodesIoutilReadDirDeepFailure(t *testing.T) {
+func TestHostDevicesIoutilReadDirDeepFailure(t *testing.T) {
 	testError := errors.New("test error")
 	called := false
 
@@ -54,7 +54,7 @@ func TestGetHostDeviceNodesIoutilReadDirDeepFailure(t *testing.T) {
 		return []os.FileInfo{fi}, nil
 	}
 
-	_, err := GetHostDeviceNodes()
+	_, err := HostDevices()
 	if err != testError {
 		t.Fatalf("Unexpected error %v, expected %v", err, testError)
 	}

devices/number.go

@@ -20,7 +20,3 @@ func Major(devNumber int) int64 {
 func Minor(devNumber int) int64 {
 	return int64((devNumber & 0xff) | ((devNumber >> 12) & 0xfff00))
 }
-
-func Mkdev(majorNumber int64, minorNumber int64) int {
-	return int((majorNumber << 8) | (minorNumber & 0xff) | ((minorNumber & 0xfff00) << 12))
-}

integration/exec_test.go

@@ -5,7 +5,6 @@ import (
 	"io/ioutil"
 	"os"
 	"strings"
-	"syscall"
 	"testing"
 
 	"github.com/docker/libcontainer"
@@ -192,6 +191,20 @@ func newTestRoot() (string, error) {
 	return dir, nil
 }
 
+func waitProcess(pid int, t *testing.T) {
+	p, err := os.FindProcess(pid)
+	if err != nil {
+		t.Fatal(err)
+	}
+	status, err := p.Wait()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !status.Success() {
+		t.Fatal(status)
+	}
+}
+
 func TestEnter(t *testing.T) {
 	if testing.Short() {
 		return
@@ -229,12 +242,12 @@ func TestEnter(t *testing.T) {
 
 	var stdout, stdout2 bytes.Buffer
 
-	pconfig := libcontainer.ProcessConfig{
+	pconfig := libcontainer.Process{
 		Args:   []string{"sh", "-c", "cat && readlink /proc/self/ns/pid"},
 		Stdin:  stdinR,
 		Stdout: &stdout,
 	}
-	pid, err := container.StartProcess(&pconfig)
+	pid, err := container.Start(&pconfig)
 	stdinR.Close()
 	defer stdinW.Close()
 	if err != nil {
@@ -250,7 +263,7 @@ func TestEnter(t *testing.T) {
 	pconfig.Stdin = stdinR2
 	pconfig.Stdout = &stdout2
 
-	pid2, err := container.StartProcess(&pconfig)
+	pid2, err := container.Start(&pconfig)
 	stdinR2.Close()
 	defer stdinW2.Close()
 	if err != nil {
@@ -273,27 +286,11 @@ func TestEnter(t *testing.T) {
 	}
 
 	// Wait processes
-	var status syscall.WaitStatus
-
 	stdinW2.Close()
-	exitCode, err := container.WaitProcess(pid2)
-	if err != nil {
-		t.Fatal(err)
-	}
-	status = syscall.WaitStatus(exitCode)
-	if status.ExitStatus() != 0 {
-		t.Fatal(exitCode)
-	}
+	waitProcess(pid2, t)
 
 	stdinW.Close()
-	exitCode, err = container.WaitProcess(pid)
-	if err != nil {
-		t.Fatal(err)
-	}
-	status = syscall.WaitStatus(exitCode)
-	if status.ExitStatus() != 0 {
-		t.Fatal(exitCode)
-	}
+	waitProcess(pid, t)
 
 	// Check that both processes live in the same pidns
 	pidns := string(stdout.Bytes())
@@ -345,11 +342,11 @@ func TestFreeze(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	pconfig := libcontainer.ProcessConfig{
+	pconfig := libcontainer.Process{
 		Args:  []string{"cat"},
 		Stdin: stdinR,
 	}
-	pid, err := container.StartProcess(&pconfig)
+	pid, err := container.Start(&pconfig)
 	stdinR.Close()
 	defer stdinW.Close()
 	if err != nil {
@@ -364,7 +361,7 @@ func TestFreeze(t *testing.T) {
 	if err := container.Pause(); err != nil {
 		t.Fatal(err)
 	}
-	state, err := container.RunState()
+	state, err := container.Status()
 	if err != nil {
 		t.Fatal(err)
 	}

integration/init_test.go

@@ -6,7 +6,7 @@ import (
 	"runtime"
 
 	"github.com/docker/libcontainer"
-	_ "github.com/docker/libcontainer/namespaces/nsenter"
+	_ "github.com/docker/libcontainer/nsenter"
 )
 
 // init runs the libcontainer initialization code because of the busybox style needs

integration/template_test.go

@@ -3,9 +3,7 @@ package integration
 import (
 	"syscall"
 
-	"github.com/docker/libcontainer/cgroups"
 	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/devices"
 )
 
 // newTemplateConfig returns a base template for running a container
@@ -15,7 +13,6 @@ import (
 func newTemplateConfig(rootfs string) *configs.Config {
 	return &configs.Config{
 		RootFs: rootfs,
-		Tty:    false,
 		Capabilities: []string{
 			"CHOWN",
 			"DAC_OVERRIDE",
@@ -39,17 +36,15 @@ func newTemplateConfig(rootfs string) *configs.Config {
 			{Type: configs.NEWPID},
 			{Type: configs.NEWNET},
 		}),
-		Cgroups: &cgroups.Cgroup{
+		Cgroups: &configs.Cgroup{
 			Name:            "test",
 			Parent:          "integration",
 			AllowAllDevices: false,
-			AllowedDevices:  devices.DefaultAllowedDevices,
+			AllowedDevices:  configs.DefaultAllowedDevices,
 		},
 
-		MountConfig: &configs.MountConfig{
-			DeviceNodes: devices.DefaultAutoCreatedDevices,
-		},
-		Hostname: "integration",
+		DeviceNodes: configs.DefaultAutoCreatedDevices,
+		Hostname:    "integration",
 		Env: []string{
 			"HOME=/root",
 			"PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

integration/utils_test.go

@@ -91,9 +91,8 @@ func runContainer(config *configs.Config, console string, args ...string) (buffe
 
 	buffers = newStdBuffers()
 
-	process := &libcontainer.ProcessConfig{
+	process := &libcontainer.Process{
 		Args:   args,
-		Env:    make([]string, 0),
 		Stdin:  buffers.Stdin,
 		Stdout: buffers.Stdout,
 		Stderr: buffers.Stderr,
@@ -110,7 +109,7 @@ func runContainer(config *configs.Config, console string, args ...string) (buffe
 	}
 	defer container.Destroy()
 
-	pid, err := container.StartProcess(process)
+	pid, err := container.Start(process)
 	if err != nil {
 		return nil, -1, err
 	}

linux_container.go

@@ -5,18 +5,35 @@ package libcontainer
 import (
 	"encoding/json"
 	"fmt"
+	"io"
+	"io/ioutil"
 	"os"
 	"os/exec"
 	"path/filepath"
 	"syscall"
 
+	"github.com/docker/libcontainer/apparmor"
 	"github.com/docker/libcontainer/cgroups"
 	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/namespaces"
+	"github.com/docker/libcontainer/label"
+	"github.com/docker/libcontainer/mount"
 	"github.com/docker/libcontainer/network"
+	"github.com/docker/libcontainer/system"
 	"github.com/golang/glog"
 )
 
+const (
+	EXIT_SIGNAL_OFFSET = 128
+)
+
+type initError struct {
+	Message string `json:"message,omitempty"`
+}
+
+func (i initError) Error() string {
+	return i.Message
+}
+
 type linuxContainer struct {
 	id            string
 	root          string
@@ -26,19 +43,20 @@ type linuxContainer struct {
 	initArgs      []string
 }
 
+// ID returns the container's unique ID
 func (c *linuxContainer) ID() string {
 	return c.id
 }
 
-func (c *linuxContainer) Config() *configs.Config {
-	return c.config
+// Config returns the container's configuration
+func (c *linuxContainer) Config() configs.Config {
+	return *c.config
 }
 
-func (c *linuxContainer) RunState() (configs.RunState, error) {
+func (c *linuxContainer) Status() (configs.Status, error) {
 	if c.state.InitPid <= 0 {
 		return configs.Destroyed, nil
 	}
-
 	// return Running if the init process is alive
 	err := syscall.Kill(c.state.InitPid, 0)
 	if err != nil {
@@ -47,14 +65,10 @@ func (c *linuxContainer) RunState() (configs.RunState, error) {
 		}
 		return 0, err
 	}
-
 	if c.config.Cgroups != nil &&
-		c.config.Cgroups.Freezer == cgroups.Frozen {
+		c.config.Cgroups.Freezer == configs.Frozen {
 		return configs.Paused, nil
 	}
-
-	//FIXME get a cgroup state to check other states
-
 	return configs.Running, nil
 }
 
@@ -67,13 +81,12 @@ func (c *linuxContainer) Processes() ([]int, error) {
 	return pids, nil
 }
 
-func (c *linuxContainer) Stats() (*ContainerStats, error) {
+func (c *linuxContainer) Stats() (*Stats, error) {
 	glog.Info("fetch container stats")
 	var (
 		err   error
-		stats = &ContainerStats{}
+		stats = &Stats{}
 	)
-
 	if stats.CgroupStats, err = c.cgroupManager.GetStats(); err != nil {
 		return stats, newGenericError(err, SystemError)
 	}
@@ -83,114 +96,484 @@ func (c *linuxContainer) Stats() (*ContainerStats, error) {
 	return stats, nil
 }
 
-func (c *linuxContainer) StartProcess(config *ProcessConfig) (int, error) {
-	state, err := c.RunState()
+func (c *linuxContainer) Start(process *Process) (int, error) {
+	status, err := c.Status()
 	if err != nil {
 		return -1, err
 	}
-
 	cmd := exec.Command(c.initArgs[0], c.initArgs[1:]...)
-	cmd.Stdin = config.Stdin
-	cmd.Stdout = config.Stdout
-	cmd.Stderr = config.Stderr
-
-	cmd.Env = config.Env
+	cmd.Stdin = process.Stdin
+	cmd.Stdout = process.Stdout
+	cmd.Stderr = process.Stderr
+	cmd.Env = c.config.Env
 	cmd.Dir = c.config.RootFs
-
 	if cmd.SysProcAttr == nil {
 		cmd.SysProcAttr = &syscall.SysProcAttr{}
 	}
-
+	// TODO: add pdeath to config for a container
 	cmd.SysProcAttr.Pdeathsig = syscall.SIGKILL
-
-	if state != configs.Destroyed {
+	if status != configs.Destroyed {
 		glog.Info("start new container process")
-		return namespaces.ExecIn(config.Args, config.Env, config.Console, cmd, c.config, c.state)
+		// TODO: (crosbymichael) check out console use for execin
+		//return namespaces.ExecIn(process.Args, c.config.Env, "", cmd, c.config, c.state)
+		return c.startNewProcess(cmd, process.Args)
 	}
-
-	if err := c.startInitProcess(cmd, config); err != nil {
+	if err := c.startInitProcess(cmd, process.Args); err != nil {
 		return -1, err
 	}
-
 	return c.state.InitPid, nil
 }
 
+func (c *linuxContainer) startNewProcess(cmd *exec.Cmd, args []string) (int, error) {
+	var err error
+	parent, child, err := newInitPipe()
+	if err != nil {
+		return -1, err
+	}
+	defer parent.Close()
+	cmd.ExtraFiles = []*os.File{child}
+	cmd.Env = append(cmd.Env, fmt.Sprintf("_LIBCONTAINER_INITPID=%d", c.state.InitPid))
+	if err := cmd.Start(); err != nil {
+		child.Close()
+		return -1, err
+	}
+	child.Close()
+	s, err := cmd.Process.Wait()
+	if err != nil {
+		return -1, err
+	}
+	if !s.Success() {
+		return -1, &exec.ExitError{s}
+	}
+	decoder := json.NewDecoder(parent)
+	var pid *pid
+	if err := decoder.Decode(&pid); err != nil {
+		return -1, err
+	}
+	p, err := os.FindProcess(pid.Pid)
+	if err != nil {
+		return -1, err
+	}
+	terminate := func(terr error) (int, error) {
+		// TODO: log the errors for kill and wait
+		p.Kill()
+		p.Wait()
+		return -1, terr
+	}
+	// Enter cgroups.
+	if err := enterCgroups(c.state, pid.Pid); err != nil {
+		return terminate(err)
+	}
+	encoder := json.NewEncoder(parent)
+	if err := encoder.Encode(c.config); err != nil {
+		return terminate(err)
+	}
+	process := processArgs{
+		Config: c.config,
+		Args:   args,
+	}
+	if err := encoder.Encode(process); err != nil {
+		return terminate(err)
+	}
+	return pid.Pid, nil
+}
+
+func (c *linuxContainer) startInitProcess(cmd *exec.Cmd, args []string) error {
+	// create a pipe so that we can syncronize with the namespaced process and
+	// pass the state and configuration to the child process
+	parent, child, err := newInitPipe()
+	if err != nil {
+		return err
+	}
+	defer parent.Close()
+	cmd.ExtraFiles = []*os.File{child}
+	cmd.SysProcAttr.Cloneflags = c.config.Namespaces.CloneFlags()
+	if c.config.Namespaces.Contains(configs.NEWUSER) {
+		addUidGidMappings(cmd.SysProcAttr, c.config)
+		// Default to root user when user namespaces are enabled.
+		if cmd.SysProcAttr.Credential == nil {
+			cmd.SysProcAttr.Credential = &syscall.Credential{}
+		}
+	}
+	glog.Info("starting container init process")
+	err = cmd.Start()
+	child.Close()
+	if err != nil {
+		return newGenericError(err, SystemError)
+	}
+	wait := func() (*os.ProcessState, error) {
+		ps, err := cmd.Process.Wait()
+		// we should kill all processes in cgroup when init is died if we use
+		// host PID namespace
+		if !c.config.Namespaces.Contains(configs.NEWPID) {
+			c.killAllPids()
+		}
+		return ps, newGenericError(err, SystemError)
+	}
+	terminate := func(terr error) error {
+		// TODO: log the errors for kill and wait
+		cmd.Process.Kill()
+		wait()
+		return terr
+	}
+	started, err := system.GetProcessStartTime(cmd.Process.Pid)
+	if err != nil {
+		return terminate(err)
+	}
+	// Do this before syncing with child so that no children
+	// can escape the cgroup
+	if err := c.cgroupManager.Apply(cmd.Process.Pid); err != nil {
+		return terminate(err)
+	}
+	defer func() {
+		if err != nil {
+			c.cgroupManager.Destroy()
+		}
+	}()
+	var networkState configs.NetworkState
+	if err := c.initializeNetworking(cmd.Process.Pid, &networkState); err != nil {
+		return terminate(err)
+	}
+	process := processArgs{
+		Args:         args,
+		Config:       c.config,
+		NetworkState: &networkState,
+	}
+	// Start the setup process to setup the init process
+	if c.config.Namespaces.Contains(configs.NEWUSER) {
+		if err = executeSetupCmd(cmd.Args, cmd.Process.Pid, c.config, &process, &networkState); err != nil {
+			return terminate(err)
+		}
+	}
+	// send the state to the container's init process then shutdown writes for the parent
+	if err := json.NewEncoder(parent).Encode(process); err != nil {
+		return terminate(err)
+	}
+	// shutdown writes for the parent side of the pipe
+	if err := syscall.Shutdown(int(parent.Fd()), syscall.SHUT_WR); err != nil {
+		return terminate(err)
+	}
+	// wait for the child process to fully complete and receive an error message
+	// if one was encoutered
+	var ierr *initError
+	if err := json.NewDecoder(parent).Decode(&ierr); err != nil && err != io.EOF {
+		return terminate(err)
+	}
+	if ierr != nil {
+		return terminate(ierr)
+	}
+
+	c.state.InitPid = cmd.Process.Pid
+	c.state.InitStartTime = started
+	c.state.NetworkState = networkState
+	c.state.CgroupPaths = c.cgroupManager.GetPaths()
+
+	return nil
+}
+
+func (c *linuxContainer) Destroy() error {
+	status, err := c.Status()
+	if err != nil {
+		return err
+	}
+	if status != configs.Destroyed {
+		return newGenericError(nil, ContainerNotStopped)
+	}
+	return os.RemoveAll(c.root)
+}
+
+func (c *linuxContainer) Pause() error {
+	return c.cgroupManager.Freeze(configs.Frozen)
+}
+
+func (c *linuxContainer) Resume() error {
+	return c.cgroupManager.Freeze(configs.Thawed)
+}
+
+func (c *linuxContainer) Signal(signal os.Signal) error {
+	glog.Infof("sending signal %d to pid %d", signal, c.state.InitPid)
+	panic("not implemented")
+}
+
+func (c *linuxContainer) OOM() (<-chan struct{}, error) {
+	return NotifyOnOOM(c.state)
+}
+
 func (c *linuxContainer) updateStateFile() error {
 	fnew := filepath.Join(c.root, fmt.Sprintf("%s.new", stateFilename))
 	f, err := os.Create(fnew)
 	if err != nil {
 		return newGenericError(err, SystemError)
 	}
+	defer f.Close()
 
-	err = json.NewEncoder(f).Encode(c.state)
-	if err != nil {
+	if err := json.NewEncoder(f).Encode(c.state); err != nil {
 		f.Close()
 		os.Remove(fnew)
 		return newGenericError(err, SystemError)
 	}
-	f.Close()
-
 	fname := filepath.Join(c.root, stateFilename)
 	if err := os.Rename(fnew, fname); err != nil {
 		return newGenericError(err, SystemError)
 	}
-
 	return nil
 }
 
-func (c *linuxContainer) startInitProcess(cmd *exec.Cmd, config *ProcessConfig) error {
-	err := namespaces.Exec(config.Args, config.Env, config.Console, cmd, c.config, c.cgroupManager, c.state)
+// New returns a newly initialized Pipe for communication between processes
+func newInitPipe() (parent *os.File, child *os.File, err error) {
+	fds, err := syscall.Socketpair(syscall.AF_LOCAL, syscall.SOCK_STREAM|syscall.SOCK_CLOEXEC, 0)
+	if err != nil {
+		return nil, nil, err
+	}
+	return os.NewFile(uintptr(fds[1]), "parent"), os.NewFile(uintptr(fds[0]), "child"), nil
+}
+
+// Converts IDMap to SysProcIDMap array and adds it to SysProcAttr.
+func addUidGidMappings(sys *syscall.SysProcAttr, container *configs.Config) {
+	if container.UidMappings != nil {
+		sys.UidMappings = make([]syscall.SysProcIDMap, len(container.UidMappings))
+		for i, um := range container.UidMappings {
+			sys.UidMappings[i].ContainerID = um.ContainerID
+			sys.UidMappings[i].HostID = um.HostID
+			sys.UidMappings[i].Size = um.Size
+		}
+	}
+
+	if container.GidMappings != nil {
+		sys.GidMappings = make([]syscall.SysProcIDMap, len(container.GidMappings))
+		for i, gm := range container.GidMappings {
+			sys.GidMappings[i].ContainerID = gm.ContainerID
+			sys.GidMappings[i].HostID = gm.HostID
+			sys.GidMappings[i].Size = gm.Size
+		}
+	}
+}
+
+// killAllPids iterates over all of the container's processes
+// sending a SIGKILL to each process.
+func (c *linuxContainer) killAllPids() error {
+	glog.Info("killing all processes in container")
+	var procs []*os.Process
+	c.cgroupManager.Freeze(configs.Frozen)
+	pids, err := c.cgroupManager.GetPids()
 	if err != nil {
 		return err
 	}
+	for _, pid := range pids {
+		// TODO: log err without aborting if we are unable to find
+		// a single PID
+		if p, err := os.FindProcess(pid); err == nil {
+			procs = append(procs, p)
+			p.Kill()
+		}
+	}
+	c.cgroupManager.Freeze(configs.Thawed)
+	for _, p := range procs {
+		p.Wait()
+	}
+	return err
+}
 
-	err = c.updateStateFile()
+// initializeNetworking creates the container's network stack outside of the namespace and moves
+// interfaces into the container's net namespaces if necessary
+func (c *linuxContainer) initializeNetworking(nspid int, networkState *configs.NetworkState) error {
+	glog.Info("initailzing container's network stack")
+	for _, config := range c.config.Networks {
+		strategy, err := network.GetStrategy(config.Type)
+		if err != nil {
+			return err
+		}
+		if err := strategy.Create(config, nspid, networkState); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func executeSetupCmd(args []string, ppid int, container *configs.Config, process *processArgs, networkState *configs.NetworkState) error {
+	command := exec.Command(args[0], args[1:]...)
+	parent, child, err := newInitPipe()
 	if err != nil {
-		// FIXME c.Kill()
 		return err
 	}
+	defer parent.Close()
+	command.ExtraFiles = []*os.File{child}
+	command.Dir = container.RootFs
+	command.Env = append(command.Env,
+		fmt.Sprintf("_LIBCONTAINER_INITPID=%d", ppid),
+		fmt.Sprintf("_LIBCONTAINER_USERNS=1"))
+	err = command.Start()
+	child.Close()
+	if err != nil {
+		return err
+	}
+	s, err := command.Process.Wait()
+	if err != nil {
+		return err
+	}
+	if !s.Success() {
+		return &exec.ExitError{s}
+	}
+	decoder := json.NewDecoder(parent)
+	var pid *pid
+	if err := decoder.Decode(&pid); err != nil {
+		return err
+	}
+	p, err := os.FindProcess(pid.Pid)
+	if err != nil {
+		return err
+	}
+	terminate := func(terr error) error {
+		// TODO: log the errors for kill and wait
+		p.Kill()
+		p.Wait()
+		return terr
+	}
+	// send the state to the container's init process then shutdown writes for the parent
+	if err := json.NewEncoder(parent).Encode(process); err != nil {
+		return terminate(err)
+	}
+	// shutdown writes for the parent side of the pipe
+	if err := syscall.Shutdown(int(parent.Fd()), syscall.SHUT_WR); err != nil {
+		return terminate(err)
+	}
+	// wait for the child process to fully complete and receive an error message
+	// if one was encoutered
+	var ierr *initError
+	if err := decoder.Decode(&ierr); err != nil && err != io.EOF {
+		return terminate(err)
+	}
+	if ierr != nil {
+		return ierr
+	}
+	s, err = p.Wait()
+	if err != nil {
+		return err
+	}
+	if !s.Success() {
+		return &exec.ExitError{s}
+	}
+	return nil
+}
+
+type pid struct {
+	Pid int `json:"Pid"`
+}
+
+// Finalize entering into a container and execute a specified command
+func InitIn(pipe *os.File) (err error) {
+	defer func() {
+		// if we have an error during the initialization of the container's init then send it back to the
+		// parent process in the form of an initError.
+		if err != nil {
+			// ensure that any data sent from the parent is consumed so it doesn't
+			// receive ECONNRESET when the child writes to the pipe.
+			ioutil.ReadAll(pipe)
+			if err := json.NewEncoder(pipe).Encode(initError{
+				Message: err.Error(),
+			}); err != nil {
+				panic(err)
+			}
+		}
+		// ensure that this pipe is always closed
+		pipe.Close()
+	}()
+	decoder := json.NewDecoder(pipe)
+	var config *configs.Config
+	if err := decoder.Decode(&config); err != nil {
+		return err
+	}
+	var process *processArgs
+	if err := decoder.Decode(&process); err != nil {
+		return err
+	}
+	if err := finalizeSetns(config); err != nil {
+		return err
+	}
+	if err := system.Execv(process.Args[0], process.Args[0:], config.Env); err != nil {
+		return err
+	}
+	panic("unreachable")
+}
+
+// finalize expects that the setns calls have been setup and that is has joined an
+// existing namespace
+func finalizeSetns(container *configs.Config) error {
+	// clear the current processes env and replace it with the environment defined on the container
+	if err := loadContainerEnvironment(container); err != nil {
+		return err
+	}
+
+	if err := setupRlimits(container); err != nil {
+		return fmt.Errorf("setup rlimits %s", err)
+	}
+
+	if err := finalizeNamespace(container); err != nil {
+		return err
+	}
+
+	if err := apparmor.ApplyProfile(container.AppArmorProfile); err != nil {
+		return fmt.Errorf("set apparmor profile %s: %s", container.AppArmorProfile, err)
+	}
+
+	if container.ProcessLabel != "" {
+		if err := label.SetProcessLabel(container.ProcessLabel); err != nil {
+			return err
+		}
+	}
 
 	return nil
 }
 
-func (c *linuxContainer) Destroy() error {
-	state, err := c.RunState()
-	if err != nil {
+// SetupContainer is run to setup mounts and networking related operations
+// for a user namespace enabled process as a user namespace root doesn't
+// have permissions to perform these operations.
+// The setup process joins all the namespaces of user namespace enabled init
+// except the user namespace, so it run as root in the root user namespace
+// to perform these operations.
+func SetupContainer(process *processArgs) error {
+	container := process.Config
+	networkState := process.NetworkState
+
+	// TODO : move to validation
+	/*
+		rootfs, err := utils.ResolveRootfs(container.RootFs)
+		if err != nil {
+			return err
+		}
+	*/
+
+	// clear the current processes env and replace it with the environment
+	// defined on the container
+	if err := loadContainerEnvironment(container); err != nil {
 		return err
 	}
 
-	if state != configs.Destroyed {
-		return newGenericError(nil, ContainerNotStopped)
+	cloneFlags := container.Namespaces.CloneFlags()
+	if (cloneFlags & syscall.CLONE_NEWNET) == 0 {
+		if len(container.Networks) != 0 || len(container.Routes) != 0 {
+			return fmt.Errorf("unable to apply network parameters without network namespace")
+		}
+	} else {
+		if err := setupNetwork(container, networkState); err != nil {
+			return fmt.Errorf("setup networking %s", err)
+		}
+		if err := setupRoute(container); err != nil {
+			return fmt.Errorf("setup route %s", err)
+		}
 	}
 
-	os.RemoveAll(c.root)
+	label.Init()
+
+	// InitializeMountNamespace() can be executed only for a new mount namespace
+	if (cloneFlags & syscall.CLONE_NEWNS) != 0 {
+		if err := mount.InitializeMountNamespace(container); err != nil {
+			return fmt.Errorf("setup mount namespace %s", err)
+		}
+	}
 	return nil
 }
 
-func (c *linuxContainer) Pause() error {
-	return c.cgroupManager.Freeze(cgroups.Frozen)
-}
-
-func (c *linuxContainer) Resume() error {
-	return c.cgroupManager.Freeze(cgroups.Thawed)
-}
-
-func (c *linuxContainer) Signal(pid, signal int) error {
-	glog.Infof("sending signal %d to pid %d", signal, pid)
-	panic("not implemented")
-}
-
-func (c *linuxContainer) Wait() (int, error) {
-	return c.WaitProcess(c.state.InitPid)
-}
-
-func (c *linuxContainer) WaitProcess(pid int) (int, error) {
-	var status syscall.WaitStatus
-
-	_, err := syscall.Wait4(pid, &status, 0, nil)
-	if err != nil {
-		return -1, newGenericError(err, SystemError)
-	}
-
-	return int(status), err
+func enterCgroups(state *configs.State, pid int) error {
+	return cgroups.EnterPid(state.CgroupPaths, pid)
 }

linux_container_test.go

@@ -34,7 +34,7 @@ func (m *mockCgroupManager) GetPaths() map[string]string {
 	return nil
 }
 
-func (m *mockCgroupManager) Freeze(state cgroups.FreezerState) error {
+func (m *mockCgroupManager) Freeze(state configs.FreezerState) error {
 	return nil
 }
 

linux_factory.go

@@ -5,15 +5,28 @@ package libcontainer
 import (
 	"encoding/json"
 	"fmt"
+	"io/ioutil"
 	"os"
 	"path/filepath"
 	"regexp"
+	"strings"
+	"syscall"
 
 	"github.com/golang/glog"
 
+	"github.com/docker/libcontainer/apparmor"
 	cgroups "github.com/docker/libcontainer/cgroups/manager"
 	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/namespaces"
+	"github.com/docker/libcontainer/console"
+	"github.com/docker/libcontainer/label"
+	"github.com/docker/libcontainer/mount"
+	"github.com/docker/libcontainer/netlink"
+	"github.com/docker/libcontainer/network"
+	"github.com/docker/libcontainer/security/capabilities"
+	"github.com/docker/libcontainer/security/restrict"
+	"github.com/docker/libcontainer/system"
+	"github.com/docker/libcontainer/user"
+	"github.com/docker/libcontainer/utils"
 )
 
 const (
@@ -26,6 +39,13 @@ var (
 	maxIdLen = 1024
 )
 
+// Process is used for transferring parameters from Exec() to Init()
+type processArgs struct {
+	Args         []string              `json:"args,omitempty"`
+	Config       *configs.Config       `json:"config,omitempty"`
+	NetworkState *configs.NetworkState `json:"network_state,omitempty"`
+}
+
 // New returns a linux based container factory based in the root directory.
 func New(root string, initArgs []string) (Factory, error) {
 	if root != "" {
@@ -33,7 +53,6 @@ func New(root string, initArgs []string) (Factory, error) {
 			return nil, newGenericError(err, SystemError)
 		}
 	}
-
 	return &linuxFactory{
 		root:     root,
 		initArgs: initArgs,
@@ -51,44 +70,32 @@ func (l *linuxFactory) Create(id string, config *configs.Config) (Container, err
 	if l.root == "" {
 		return nil, newGenericError(fmt.Errorf("invalid root"), ConfigInvalid)
 	}
-	if !idRegex.MatchString(id) {
-		return nil, newGenericError(fmt.Errorf("Invalid id format: %v", id), InvalidIdFormat)
+	if err := l.validateID(id); err != nil {
+		return nil, err
 	}
-
-	if len(id) > maxIdLen {
-		return nil, newGenericError(fmt.Errorf("Invalid id format: %v", id), InvalidIdFormat)
-	}
-
 	containerRoot := filepath.Join(l.root, id)
-	_, err := os.Stat(containerRoot)
-	if err == nil {
+	if _, err := os.Stat(containerRoot); err == nil {
 		return nil, newGenericError(fmt.Errorf("Container with id exists: %v", id), IdInUse)
 	} else if !os.IsNotExist(err) {
 		return nil, newGenericError(err, SystemError)
 	}
-
 	data, err := json.MarshalIndent(config, "", "\t")
 	if err != nil {
 		return nil, newGenericError(err, SystemError)
 	}
-
 	if err := os.MkdirAll(containerRoot, 0700); err != nil {
 		return nil, newGenericError(err, SystemError)
 	}
-
 	f, err := os.Create(filepath.Join(containerRoot, configFilename))
 	if err != nil {
 		os.RemoveAll(containerRoot)
 		return nil, newGenericError(err, SystemError)
 	}
 	defer f.Close()
-
-	_, err = f.Write(data)
-	if err != nil {
+	if _, err := f.Write(data); err != nil {
 		os.RemoveAll(containerRoot)
 		return nil, newGenericError(err, SystemError)
 	}
-
 	cgroupManager := cgroups.NewCgroupManager(config.Cgroups)
 	return &linuxContainer{
 		id:            id,
@@ -110,13 +117,11 @@ func (l *linuxFactory) Load(id string) (Container, error) {
 	if err != nil {
 		return nil, err
 	}
-
 	glog.Infof("loading container state from %s", containerRoot)
 	state, err := l.loadContainerState(containerRoot)
 	if err != nil {
 		return nil, err
 	}
-
 	cgroupManager := cgroups.LoadCgroupManager(config.Cgroups, state.CgroupPaths)
 	glog.Infof("using %s as cgroup manager", cgroupManager)
 	return &linuxContainer{
@@ -129,6 +134,54 @@ func (l *linuxFactory) Load(id string) (Container, error) {
 	}, nil
 }
 
+// StartInitialization loads a container by opening the pipe fd from the parent to read the configuration and state
+// This is a low level implementation detail of the reexec and should not be consumed externally
+func (l *linuxFactory) StartInitialization(pipefd uintptr) (err error) {
+	pipe := os.NewFile(uintptr(pipefd), "pipe")
+	setupUserns := os.Getenv("_LIBCONTAINER_USERNS") != ""
+	pid := os.Getenv("_LIBCONTAINER_INITPID")
+	if pid != "" && !setupUserns {
+		return InitIn(pipe)
+	}
+	defer func() {
+		// if we have an error during the initialization of the container's init then send it back to the
+		// parent process in the form of an initError.
+		if err != nil {
+			// ensure that any data sent from the parent is consumed so it doesn't
+			// receive ECONNRESET when the child writes to the pipe.
+			ioutil.ReadAll(pipe)
+			if err := json.NewEncoder(pipe).Encode(initError{
+				Message: err.Error(),
+			}); err != nil {
+				panic(err)
+			}
+		}
+		// ensure that this pipe is always closed
+		pipe.Close()
+	}()
+	uncleanRootfs, err := os.Getwd()
+	if err != nil {
+		return err
+	}
+	var process *processArgs
+	// We always read this as it is a way to sync with the parent as well
+	if err := json.NewDecoder(pipe).Decode(&process); err != nil {
+		return err
+	}
+	if setupUserns {
+		err = SetupContainer(process)
+		if err == nil {
+			os.Exit(0)
+		} else {
+			os.Exit(1)
+		}
+	}
+	if process.Config.Namespaces.Contains(configs.NEWUSER) {
+		return l.initUserNs(uncleanRootfs, process)
+	}
+	return l.initDefault(uncleanRootfs, process)
+}
+
 func (l *linuxFactory) loadContainerConfig(root string) (*configs.Config, error) {
 	f, err := os.Open(filepath.Join(root, configFilename))
 	if err != nil {
@@ -138,7 +191,6 @@ func (l *linuxFactory) loadContainerConfig(root string) (*configs.Config, error)
 		return nil, newGenericError(err, SystemError)
 	}
 	defer f.Close()
-
 	var config *configs.Config
 	if err := json.NewDecoder(f).Decode(&config); err != nil {
 		return nil, newGenericError(err, ConfigInvalid)
@@ -155,7 +207,6 @@ func (l *linuxFactory) loadContainerState(root string) (*configs.State, error) {
 		return nil, newGenericError(err, SystemError)
 	}
 	defer f.Close()
-
 	var state *configs.State
 	if err := json.NewDecoder(f).Decode(&state); err != nil {
 		return nil, newGenericError(err, SystemError)
@@ -163,16 +214,346 @@ func (l *linuxFactory) loadContainerState(root string) (*configs.State, error) {
 	return state, nil
 }
 
-// StartInitialization loads a container by opening the pipe fd from the parent to read the configuration and state
-// This is a low level implementation detail of the reexec and should not be consumed externally
-func (f *linuxFactory) StartInitialization(pipefd uintptr) (err error) {
-	pipe := os.NewFile(uintptr(pipefd), "pipe")
+func (l *linuxFactory) validateID(id string) error {
+	if !idRegex.MatchString(id) {
+		return newGenericError(fmt.Errorf("Invalid id format: %v", id), InvalidIdFormat)
+	}
+	if len(id) > maxIdLen {
+		return newGenericError(fmt.Errorf("Invalid id format: %v", id), InvalidIdFormat)
+	}
+	return nil
+}
 
-	setupUserns := os.Getenv("_LIBCONTAINER_USERNS")
-	pid := os.Getenv("_LIBCONTAINER_INITPID")
-	if pid != "" && setupUserns == "" {
-		return namespaces.InitIn(pipe)
+func (l *linuxFactory) initDefault(uncleanRootfs string, process *processArgs) (err error) {
+	config := process.Config
+	networkState := process.NetworkState
+
+	// TODO: move to validation
+	/*
+		rootfs, err := utils.ResolveRootfs(uncleanRootfs)
+		if err != nil {
+			return err
+		}
+	*/
+
+	// clear the current processes env and replace it with the environment
+	// defined on the container
+	if err := loadContainerEnvironment(config); err != nil {
+		return err
+	}
+	// join any namespaces via a path to the namespace fd if provided
+	if err := joinExistingNamespaces(config.Namespaces); err != nil {
+		return err
+	}
+	if config.Console != "" {
+		if err := console.OpenAndDup(config.Console); err != nil {
+			return err
+		}
+	}
+	if _, err := syscall.Setsid(); err != nil {
+		return fmt.Errorf("setsid %s", err)
+	}
+	if config.Console != "" {
+		if err := system.Setctty(); err != nil {
+			return fmt.Errorf("setctty %s", err)
+		}
 	}
 
-	return namespaces.Init(pipe, setupUserns != "")
+	cloneFlags := config.Namespaces.CloneFlags()
+	if (cloneFlags & syscall.CLONE_NEWNET) == 0 {
+		if len(config.Networks) != 0 || len(config.Routes) != 0 {
+			return fmt.Errorf("unable to apply network parameters without network namespace")
+		}
+	} else {
+		if err := setupNetwork(config, networkState); err != nil {
+			return fmt.Errorf("setup networking %s", err)
+		}
+		if err := setupRoute(config); err != nil {
+			return fmt.Errorf("setup route %s", err)
+		}
+	}
+	if err := setupRlimits(config); err != nil {
+		return fmt.Errorf("setup rlimits %s", err)
+	}
+	label.Init()
+	// InitializeMountNamespace() can be executed only for a new mount namespace
+	if (cloneFlags & syscall.CLONE_NEWNS) != 0 {
+		if err := mount.InitializeMountNamespace(config); err != nil {
+			return err
+		}
+	}
+	if config.Hostname != "" {
+		// TODO: (crosbymichael) move this to pre spawn validation
+		if (cloneFlags & syscall.CLONE_NEWUTS) == 0 {
+			return fmt.Errorf("unable to set the hostname without UTS namespace")
+		}
+		if err := syscall.Sethostname([]byte(config.Hostname)); err != nil {
+			return fmt.Errorf("unable to sethostname %q: %s", config.Hostname, err)
+		}
+	}
+	if err := apparmor.ApplyProfile(config.AppArmorProfile); err != nil {
+		return fmt.Errorf("set apparmor profile %s: %s", config.AppArmorProfile, err)
+	}
+	if err := label.SetProcessLabel(config.ProcessLabel); err != nil {
+		return fmt.Errorf("set process label %s", err)
+	}
+	// TODO: (crosbymichael) make this configurable at the Config level
+	if config.RestrictSys {
+		if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
+			return fmt.Errorf("unable to restrict access to kernel files without mount namespace")
+		}
+		if err := restrict.Restrict("proc/sys", "proc/sysrq-trigger", "proc/irq", "proc/bus"); err != nil {
+			return err
+		}
+	}
+	pdeathSignal, err := system.GetParentDeathSignal()
+	if err != nil {
+		return fmt.Errorf("get parent death signal %s", err)
+	}
+	if err := finalizeNamespace(config); err != nil {
+		return fmt.Errorf("finalize namespace %s", err)
+	}
+	// finalizeNamespace can change user/group which clears the parent death
+	// signal, so we restore it here.
+	if err := restoreParentDeathSignal(pdeathSignal); err != nil {
+		return fmt.Errorf("restore parent death signal %s", err)
+	}
+	return system.Execv(process.Args[0], process.Args[0:], config.Env)
+}
+
+func (l *linuxFactory) initUserNs(uncleanRootfs string, process *processArgs) (err error) {
+	config := process.Config
+	// clear the current processes env and replace it with the environment
+	// defined on the config
+	if err := loadContainerEnvironment(config); err != nil {
+		return err
+	}
+	// join any namespaces via a path to the namespace fd if provided
+	if err := joinExistingNamespaces(config.Namespaces); err != nil {
+		return err
+	}
+	if config.Console != "" {
+		if err := console.OpenAndDup("/dev/console"); err != nil {
+			return err
+		}
+	}
+	if _, err := syscall.Setsid(); err != nil {
+		return fmt.Errorf("setsid %s", err)
+	}
+	if config.Console != "" {
+		if err := system.Setctty(); err != nil {
+			return fmt.Errorf("setctty %s", err)
+		}
+	}
+	if config.WorkingDir == "" {
+		config.WorkingDir = "/"
+	}
+
+	if err := setupRlimits(config); err != nil {
+		return fmt.Errorf("setup rlimits %s", err)
+	}
+	cloneFlags := config.Namespaces.CloneFlags()
+	if config.Hostname != "" {
+		// TODO: move validation
+		if (cloneFlags & syscall.CLONE_NEWUTS) == 0 {
+			return fmt.Errorf("unable to set the hostname without UTS namespace")
+		}
+		if err := syscall.Sethostname([]byte(config.Hostname)); err != nil {
+			return fmt.Errorf("unable to sethostname %q: %s", config.Hostname, err)
+		}
+	}
+	if err := apparmor.ApplyProfile(config.AppArmorProfile); err != nil {
+		return fmt.Errorf("set apparmor profile %s: %s", config.AppArmorProfile, err)
+	}
+	if err := label.SetProcessLabel(config.ProcessLabel); err != nil {
+		return fmt.Errorf("set process label %s", err)
+	}
+	if config.RestrictSys {
+		if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
+			return fmt.Errorf("unable to restrict access to kernel files without mount namespace")
+		}
+		if err := restrict.Restrict("proc/sys", "proc/sysrq-trigger", "proc/irq", "proc/bus"); err != nil {
+			return err
+		}
+	}
+	pdeathSignal, err := system.GetParentDeathSignal()
+	if err != nil {
+		return fmt.Errorf("get parent death signal %s", err)
+	}
+	if err := finalizeNamespace(config); err != nil {
+		return fmt.Errorf("finalize namespace %s", err)
+	}
+	// finalizeNamespace can change user/group which clears the parent death
+	// signal, so we restore it here.
+	if err := restoreParentDeathSignal(pdeathSignal); err != nil {
+		return fmt.Errorf("restore parent death signal %s", err)
+	}
+	return system.Execv(process.Args[0], process.Args[0:], config.Env)
+}
+
+// restoreParentDeathSignal sets the parent death signal to old.
+func restoreParentDeathSignal(old int) error {
+	if old == 0 {
+		return nil
+	}
+	current, err := system.GetParentDeathSignal()
+	if err != nil {
+		return fmt.Errorf("get parent death signal %s", err)
+	}
+	if old == current {
+		return nil
+	}
+	if err := system.ParentDeathSignal(uintptr(old)); err != nil {
+		return fmt.Errorf("set parent death signal %s", err)
+	}
+	// Signal self if parent is already dead. Does nothing if running in a new
+	// PID namespace, as Getppid will always return 0.
+	if syscall.Getppid() == 1 {
+		return syscall.Kill(syscall.Getpid(), syscall.SIGKILL)
+	}
+	return nil
+}
+
+// setupUser changes the groups, gid, and uid for the user inside the container
+func setupUser(config *configs.Config) error {
+	// Set up defaults.
+	defaultExecUser := user.ExecUser{
+		Uid:  syscall.Getuid(),
+		Gid:  syscall.Getgid(),
+		Home: "/",
+	}
+	passwdPath, err := user.GetPasswdPath()
+	if err != nil {
+		return err
+	}
+	groupPath, err := user.GetGroupPath()
+	if err != nil {
+		return err
+	}
+	execUser, err := user.GetExecUserPath(config.User, &defaultExecUser, passwdPath, groupPath)
+	if err != nil {
+		return fmt.Errorf("get supplementary groups %s", err)
+	}
+	suppGroups := append(execUser.Sgids, config.AdditionalGroups...)
+	if err := syscall.Setgroups(suppGroups); err != nil {
+		return fmt.Errorf("setgroups %s", err)
+	}
+	if err := system.Setgid(execUser.Gid); err != nil {
+		return fmt.Errorf("setgid %s", err)
+	}
+	if err := system.Setuid(execUser.Uid); err != nil {
+		return fmt.Errorf("setuid %s", err)
+	}
+	// if we didn't get HOME already, set it based on the user's HOME
+	if envHome := os.Getenv("HOME"); envHome == "" {
+		if err := os.Setenv("HOME", execUser.Home); err != nil {
+			return fmt.Errorf("set HOME %s", err)
+		}
+	}
+	return nil
+}
+
+// setupVethNetwork uses the Network config if it is not nil to initialize
+// the new veth interface inside the container for use by changing the name to eth0
+// setting the MTU and IP address along with the default gateway
+func setupNetwork(config *configs.Config, networkState *configs.NetworkState) error {
+	for _, config := range config.Networks {
+		strategy, err := network.GetStrategy(config.Type)
+		if err != nil {
+			return err
+		}
+		err1 := strategy.Initialize(config, networkState)
+		if err1 != nil {
+			return err1
+		}
+	}
+	return nil
+}
+
+func setupRoute(config *configs.Config) error {
+	for _, config := range config.Routes {
+		if err := netlink.AddRoute(config.Destination, config.Source, config.Gateway, config.InterfaceName); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func setupRlimits(config *configs.Config) error {
+	for _, rlimit := range config.Rlimits {
+		l := &syscall.Rlimit{Max: rlimit.Hard, Cur: rlimit.Soft}
+		if err := syscall.Setrlimit(rlimit.Type, l); err != nil {
+			return fmt.Errorf("error setting rlimit type %v: %v", rlimit.Type, err)
+		}
+	}
+	return nil
+}
+
+// finalizeNamespace drops the caps, sets the correct user
+// and working dir, and closes any leaky file descriptors
+// before execing the command inside the namespace
+func finalizeNamespace(config *configs.Config) error {
+	// Ensure that all non-standard fds we may have accidentally
+	// inherited are marked close-on-exec so they stay out of the
+	// container
+	if err := utils.CloseExecFrom(3); err != nil {
+		return fmt.Errorf("close open file descriptors %s", err)
+	}
+	// drop capabilities in bounding set before changing user
+	if err := capabilities.DropBoundingSet(config.Capabilities); err != nil {
+		return fmt.Errorf("drop bounding set %s", err)
+	}
+	// preserve existing capabilities while we change users
+	if err := system.SetKeepCaps(); err != nil {
+		return fmt.Errorf("set keep caps %s", err)
+	}
+	if err := setupUser(config); err != nil {
+		return fmt.Errorf("setup user %s", err)
+	}
+	if err := system.ClearKeepCaps(); err != nil {
+		return fmt.Errorf("clear keep caps %s", err)
+	}
+	// drop all other capabilities
+	if err := capabilities.DropCapabilities(config.Capabilities); err != nil {
+		return fmt.Errorf("drop capabilities %s", err)
+	}
+	if config.WorkingDir != "" {
+		if err := syscall.Chdir(config.WorkingDir); err != nil {
+			return fmt.Errorf("chdir to %s %s", config.WorkingDir, err)
+		}
+	}
+	return nil
+}
+
+func loadContainerEnvironment(config *configs.Config) error {
+	os.Clearenv()
+	for _, pair := range config.Env {
+		p := strings.SplitN(pair, "=", 2)
+		if len(p) < 2 {
+			return fmt.Errorf("invalid environment '%v'", pair)
+		}
+		if err := os.Setenv(p[0], p[1]); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// joinExistingNamespaces gets all the namespace paths specified for the container and
+// does a setns on the namespace fd so that the current process joins the namespace.
+func joinExistingNamespaces(namespaces []configs.Namespace) error {
+	for _, ns := range namespaces {
+		if ns.Path != "" {
+			f, err := os.OpenFile(ns.Path, os.O_RDONLY, 0)
+			if err != nil {
+				return err
+			}
+			err = system.Setns(f.Fd(), uintptr(ns.Syscall()))
+			f.Close()
+			if err != nil {
+				return err
+			}
+		}
+	}
+	return nil
 }

linux_factory_test.go

@@ -118,9 +118,6 @@ func TestFactoryLoadContainer(t *testing.T) {
 	}
 
 	config := container.Config()
-	if config == nil {
-		t.Fatal("expected non nil container config")
-	}
 
 	if config.RootFs != expectedConfig.RootFs {
 		t.Fatalf("expected rootfs %q but received %q", expectedConfig.RootFs, config.RootFs)

mount/init.go

@@ -8,11 +8,10 @@ import (
 	"path/filepath"
 	"syscall"
 
+	"github.com/docker/libcontainer/configs"
 	"github.com/docker/libcontainer/label"
-	"github.com/docker/libcontainer/mount/nodes"
 )
 
-// default mount point flags
 const defaultMountFlags = syscall.MS_NOEXEC | syscall.MS_NOSUID | syscall.MS_NODEV
 
 type mount struct {
@@ -25,85 +24,60 @@ type mount struct {
 
 // InitializeMountNamespace sets up the devices, mount points, and filesystems for use inside a
 // new mount namespace.
-func InitializeMountNamespace(rootfs, console string, sysReadonly bool, hostRootUid, hostRootGid int, mountConfig *MountConfig) error {
-	var (
-		err  error
-		flag = syscall.MS_PRIVATE
-	)
-
-	if mountConfig.NoPivotRoot {
-		flag = syscall.MS_SLAVE
+func InitializeMountNamespace(config *configs.Config) (err error) {
+	if err := prepareRoot(config); err != nil {
+		return err
 	}
-
-	if err := syscall.Mount("", "/", "", uintptr(flag|syscall.MS_REC), ""); err != nil {
-		return fmt.Errorf("mounting / with flags %X %s", (flag | syscall.MS_REC), err)
+	if err := mountSystem(config); err != nil {
+		return err
 	}
-
-	if err := syscall.Mount(rootfs, rootfs, "bind", syscall.MS_BIND|syscall.MS_REC, ""); err != nil {
-		return fmt.Errorf("mouting %s as bind %s", rootfs, err)
-	}
-
-	if err := mountSystem(rootfs, sysReadonly, mountConfig); err != nil {
-		return fmt.Errorf("mount system %s", err)
-	}
-
 	// apply any user specified mounts within the new mount namespace
-	for _, m := range mountConfig.Mounts {
-		if err := m.Mount(rootfs, mountConfig.MountLabel); err != nil {
+	for _, m := range config.Mounts {
+		if err := m.Mount(config.RootFs, config.MountLabel); err != nil {
 			return err
 		}
 	}
-
-	if err := nodes.CreateDeviceNodes(rootfs, mountConfig.DeviceNodes); err != nil {
-		return fmt.Errorf("create device nodes %s", err)
-	}
-
-	if err := SetupPtmx(rootfs, console, mountConfig.MountLabel, hostRootUid, hostRootGid); err != nil {
+	if err := createDeviceNodes(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 hostRootUid == 0 {
-		if err := reOpenDevNull(rootfs); err != nil {
-			return fmt.Errorf("Failed to reopen /dev/null %s", err)
+	if 0 == 0 {
+		if err := reOpenDevNull(config.RootFs); err != nil {
+			return err
 		}
 	}
-
-	if err := setupDevSymlinks(rootfs); err != nil {
-		return fmt.Errorf("dev symlinks %s", err)
+	if err := setupDevSymlinks(config.RootFs); err != nil {
+		return err
 	}
-
-	if err := syscall.Chdir(rootfs); err != nil {
-		return fmt.Errorf("chdir into %s %s", rootfs, err)
+	if err := syscall.Chdir(config.RootFs); err != nil {
+		return err
 	}
-
-	if mountConfig.NoPivotRoot {
-		err = MsMoveRoot(rootfs)
+	if config.NoPivotRoot {
+		err = msMoveRoot(config.RootFs)
 	} else {
-		err = PivotRoot(rootfs, mountConfig.PivotDir)
+		err = pivotRoot(config.RootFs, config.PivotDir)
 	}
-
 	if err != nil {
 		return err
 	}
-
-	if mountConfig.ReadonlyFs {
-		if err := SetReadonly(); err != nil {
+	if config.ReadonlyFs {
+		if err := setReadonly(); err != nil {
 			return fmt.Errorf("set readonly %s", err)
 		}
 	}
-
 	syscall.Umask(0022)
-
 	return nil
 }
 
 // mountSystem sets up linux specific system mounts like mqueue, sys, proc, shm, and devpts
 // inside the mount namespace
-func mountSystem(rootfs string, sysReadonly bool, mountConfig *MountConfig) error {
-	for _, m := range newSystemMounts(rootfs, mountConfig.MountLabel, sysReadonly) {
+func mountSystem(config *configs.Config) error {
+	for _, m := range newSystemMounts(config.RootFs, config.MountLabel, config.RestrictSys) {
 		if err := os.MkdirAll(m.path, 0755); err != nil && !os.IsExist(err) {
 			return fmt.Errorf("mkdirall %s %s", m.path, err)
 		}
@@ -114,28 +88,6 @@ func mountSystem(rootfs string, sysReadonly bool, mountConfig *MountConfig) erro
 	return nil
 }
 
-func createIfNotExists(path string, isDir bool) error {
-	if _, err := os.Stat(path); err != nil {
-		if os.IsNotExist(err) {
-			if isDir {
-				if err := os.MkdirAll(path, 0755); err != nil {
-					return err
-				}
-			} else {
-				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
-}
-
 func setupDevSymlinks(rootfs string) error {
 	var links = [][2]string{
 		{"/proc/self/fd", "/dev/fd"},
@@ -210,3 +162,54 @@ func reOpenDevNull(rootfs string) error {
 	}
 	return nil
 }
+
+// Create the device nodes in the container.
+func createDeviceNodes(config *configs.Config) error {
+	oldMask := syscall.Umask(0000)
+	for _, node := range config.DeviceNodes {
+		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, "")
+}

mount/mount_config.go

@@ -1,33 +0,0 @@
-package mount
-
-import (
-	"errors"
-
-	"github.com/docker/libcontainer/devices"
-)
-
-var ErrUnsupported = errors.New("Unsupported method")
-
-type MountConfig struct {
-	// NoPivotRoot will use MS_MOVE and a chroot to jail the process into the container's rootfs
-	// This is a common option when the container is running in ramdisk
-	NoPivotRoot bool `json:"no_pivot_root,omitempty"`
-
-	// PivotDir allows a custom directory inside the container's root filesystem to be used as pivot, when NoPivotRoot is not set.
-	// When a custom PivotDir not set, a temporary dir inside the root filesystem will be used. The pivot dir needs to be writeable.
-	// This is required when using read only root filesystems. In these cases, a read/writeable path can be (bind) mounted somewhere inside the root filesystem to act as pivot.
-	PivotDir string `json:"pivot_dir,omitempty"`
-
-	// ReadonlyFs will remount the container's rootfs as readonly where only externally mounted
-	// bind mounts are writtable
-	ReadonlyFs bool `json:"readonly_fs,omitempty"`
-
-	// Mounts specify additional source and destination paths that will be mounted inside the container's
-	// rootfs and mount namespace if specified
-	Mounts []*Mount `json:"mounts,omitempty"`
-
-	// The device nodes that should be automatically created within the container upon container start.  Note, make sure that the node is marked as allowed in the cgroup as well!
-	DeviceNodes []*devices.Device `json:"device_nodes,omitempty"`
-
-	MountLabel string `json:"mount_label,omitempty"`
-}

mount/msmoveroot.go

@@ -2,19 +2,14 @@
 
 package mount
 
-import (
-	"fmt"
-	"syscall"
-)
+import "syscall"
 
-func MsMoveRoot(rootfs string) error {
+func msMoveRoot(rootfs string) error {
 	if err := syscall.Mount(rootfs, "/", "", syscall.MS_MOVE, ""); err != nil {
-		return fmt.Errorf("mount move %s into / %s", rootfs, err)
+		return err
 	}
-
 	if err := syscall.Chroot("."); err != nil {
-		return fmt.Errorf("chroot . %s", err)
+		return err
 	}
-
 	return syscall.Chdir("/")
 }

mount/nodes/nodes.go

@@ -1,57 +0,0 @@
-// +build linux
-
-package nodes
-
-import (
-	"fmt"
-	"os"
-	"path/filepath"
-	"syscall"
-
-	"github.com/docker/libcontainer/devices"
-)
-
-// Create the device nodes in the container.
-func CreateDeviceNodes(rootfs string, nodesToCreate []*devices.Device) error {
-	oldMask := syscall.Umask(0000)
-	defer syscall.Umask(oldMask)
-
-	for _, node := range nodesToCreate {
-		if err := CreateDeviceNode(rootfs, node); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-// Creates the device node in the rootfs of the container.
-func CreateDeviceNode(rootfs string, node *devices.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), devices.Mkdev(node.MajorNumber, node.MinorNumber)); 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
-}

mount/nodes/nodes_unsupported.go

@@ -1,13 +0,0 @@
-// +build !linux
-
-package nodes
-
-import (
-	"errors"
-
-	"github.com/docker/libcontainer/devices"
-)
-
-func CreateDeviceNodes(rootfs string, nodesToCreate []*devices.Device) error {
-	return errors.New("Unsupported method")
-}

mount/pivotroot.go

@@ -10,7 +10,7 @@ import (
 	"syscall"
 )
 
-func PivotRoot(rootfs, pivotBaseDir string) error {
+func pivotRoot(rootfs, pivotBaseDir string) error {
 	if pivotBaseDir == "" {
 		pivotBaseDir = "/"
 	}
@@ -22,20 +22,16 @@ func PivotRoot(rootfs, pivotBaseDir string) error {
 	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)
 }

mount/ptmx.go

@@ -7,24 +7,28 @@ import (
 	"os"
 	"path/filepath"
 
+	"github.com/docker/libcontainer/configs"
 	"github.com/docker/libcontainer/console"
 )
 
-func SetupPtmx(rootfs, consolePath, mountLabel string, hostRootUid, hostRootGid int) error {
-	ptmx := filepath.Join(rootfs, "dev/ptmx")
+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 consolePath != "" {
-		if err := console.Setup(rootfs, consolePath, mountLabel, hostRootUid, hostRootGid); err != nil {
+	if config.Console != "" {
+		uid, err := config.HostUID()
+		if err != nil {
 			return err
 		}
+		gid, err := config.HostGID()
+		if err != nil {
+			return err
+		}
+		return console.Setup(config.RootFs, config.Console, config.MountLabel, uid, gid)
 	}
-
 	return nil
 }

mount/readonly.go

@@ -6,6 +6,6 @@ import (
 	"syscall"
 )
 
-func SetReadonly() error {
+func setReadonly() error {
 	return syscall.Mount("/", "/", "bind", syscall.MS_BIND|syscall.MS_REMOUNT|syscall.MS_RDONLY|syscall.MS_REC, "")
 }

mount/remount.go

@@ -1,31 +0,0 @@
-// +build linux
-
-package mount
-
-import "syscall"
-
-func RemountProc() error {
-	if err := syscall.Unmount("/proc", syscall.MNT_DETACH); err != nil {
-		return err
-	}
-
-	if err := syscall.Mount("proc", "/proc", "proc", uintptr(defaultMountFlags), ""); err != nil {
-		return err
-	}
-
-	return nil
-}
-
-func RemountSys() error {
-	if err := syscall.Unmount("/sys", syscall.MNT_DETACH); err != nil {
-		if err != syscall.EINVAL {
-			return err
-		}
-	} else {
-		if err := syscall.Mount("sysfs", "/sys", "sysfs", uintptr(defaultMountFlags), ""); err != nil {
-			return err
-		}
-	}
-
-	return nil
-}

namespaces/exec.go

@@ -1,323 +0,0 @@
-// +build linux
-
-package namespaces
-
-import (
-	"encoding/json"
-	"fmt"
-	"io"
-	"os"
-	"os/exec"
-	"syscall"
-
-	"github.com/docker/libcontainer/cgroups"
-	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/network"
-	"github.com/docker/libcontainer/system"
-)
-
-const (
-	EXIT_SIGNAL_OFFSET = 128
-)
-
-func executeSetupCmd(args []string, ppid int, container *configs.Config, process *processArgs, networkState *network.NetworkState) error {
-	command := exec.Command(args[0], args[1:]...)
-
-	parent, child, err := newInitPipe()
-	if err != nil {
-		return err
-	}
-	defer parent.Close()
-	command.ExtraFiles = []*os.File{child}
-
-	command.Dir = container.RootFs
-	command.Env = append(command.Env,
-		fmt.Sprintf("_LIBCONTAINER_INITPID=%d", ppid),
-		fmt.Sprintf("_LIBCONTAINER_USERNS=1"))
-
-	err = command.Start()
-	child.Close()
-	if err != nil {
-		return err
-	}
-
-	s, err := command.Process.Wait()
-	if err != nil {
-		return err
-	}
-	if !s.Success() {
-		return &exec.ExitError{s}
-	}
-
-	decoder := json.NewDecoder(parent)
-	var pid *pid
-
-	if err := decoder.Decode(&pid); err != nil {
-		return err
-	}
-
-	p, err := os.FindProcess(pid.Pid)
-	if err != nil {
-		return err
-	}
-
-	terminate := func(terr error) error {
-		// TODO: log the errors for kill and wait
-		p.Kill()
-		p.Wait()
-		return terr
-	}
-
-	// send the state to the container's init process then shutdown writes for the parent
-	if err := json.NewEncoder(parent).Encode(process); err != nil {
-		return terminate(err)
-	}
-
-	// shutdown writes for the parent side of the pipe
-	if err := syscall.Shutdown(int(parent.Fd()), syscall.SHUT_WR); err != nil {
-		return terminate(err)
-	}
-
-	// wait for the child process to fully complete and receive an error message
-	// if one was encoutered
-	var ierr *initError
-	if err := decoder.Decode(&ierr); err != nil && err != io.EOF {
-		return terminate(err)
-	}
-	if ierr != nil {
-		return ierr
-	}
-
-	s, err = p.Wait()
-	if err != nil {
-		return err
-	}
-	if !s.Success() {
-		return &exec.ExitError{s}
-	}
-
-	return nil
-}
-
-// TODO(vishh): This is part of the libcontainer API and it does much more than just namespaces related work.
-// Move this to libcontainer package.
-// Exec performs setup outside of a namespace so that a container can be
-// executed.  Exec is a high level function for working with container namespaces.
-func Exec(args []string, env []string, console string, command *exec.Cmd, container *configs.Config, cgroupManager cgroups.Manager, state *configs.State) (err error) {
-	// create a pipe so that we can syncronize with the namespaced process and
-	// pass the state and configuration to the child process
-	parent, child, err := newInitPipe()
-	if err != nil {
-		return err
-	}
-	defer parent.Close()
-	command.ExtraFiles = []*os.File{child}
-
-	command.Dir = container.RootFs
-	command.SysProcAttr.Cloneflags = uintptr(GetNamespaceFlags(container.Namespaces))
-
-	if container.Namespaces.Contains(configs.NEWUSER) {
-		AddUidGidMappings(command.SysProcAttr, container)
-
-		// Default to root user when user namespaces are enabled.
-		if command.SysProcAttr.Credential == nil {
-			command.SysProcAttr.Credential = &syscall.Credential{}
-		}
-	}
-
-	if err := command.Start(); err != nil {
-		child.Close()
-		return err
-	}
-	child.Close()
-
-	wait := func() (*os.ProcessState, error) {
-		ps, err := command.Process.Wait()
-		// we should kill all processes in cgroup when init is died if we use
-		// host PID namespace
-		if !container.Namespaces.Contains(configs.NEWPID) {
-			killAllPids(cgroupManager)
-		}
-		return ps, err
-	}
-
-	terminate := func(terr error) error {
-		// TODO: log the errors for kill and wait
-		command.Process.Kill()
-		wait()
-		return terr
-	}
-
-	started, err := system.GetProcessStartTime(command.Process.Pid)
-	if err != nil {
-		return terminate(err)
-	}
-
-	// Do this before syncing with child so that no children
-	// can escape the cgroup
-	err = cgroupManager.Apply(command.Process.Pid)
-	if err != nil {
-		return terminate(err)
-	}
-	defer func() {
-		if err != nil {
-			cgroupManager.Destroy()
-		}
-	}()
-
-	var networkState network.NetworkState
-	if err := InitializeNetworking(container, command.Process.Pid, &networkState); err != nil {
-		return terminate(err)
-	}
-
-	process := processArgs{
-		Env:          append(env[0:], container.Env...),
-		Args:         args,
-		ConsolePath:  console,
-		Config:       container,
-		NetworkState: &networkState,
-	}
-
-	// Start the setup process to setup the init process
-	if container.Namespaces.Contains(configs.NEWUSER) {
-		if err = executeSetupCmd(command.Args, command.Process.Pid, container, &process, &networkState); err != nil {
-			return terminate(err)
-		}
-	}
-
-	// send the state to the container's init process then shutdown writes for the parent
-	if err := json.NewEncoder(parent).Encode(process); err != nil {
-		return terminate(err)
-	}
-	// shutdown writes for the parent side of the pipe
-	if err := syscall.Shutdown(int(parent.Fd()), syscall.SHUT_WR); err != nil {
-		return terminate(err)
-	}
-
-	// wait for the child process to fully complete and receive an error message
-	// if one was encoutered
-	var ierr *initError
-	if err := json.NewDecoder(parent).Decode(&ierr); err != nil && err != io.EOF {
-		return terminate(err)
-	}
-	if ierr != nil {
-		return terminate(ierr)
-	}
-
-	state.InitPid = command.Process.Pid
-	state.InitStartTime = started
-	state.NetworkState = networkState
-	state.CgroupPaths = cgroupManager.GetPaths()
-
-	return nil
-}
-
-// killAllPids iterates over all of the container's processes
-// sending a SIGKILL to each process.
-func killAllPids(m cgroups.Manager) error {
-	var (
-		procs []*os.Process
-	)
-	m.Freeze(cgroups.Frozen)
-	pids, err := m.GetPids()
-	if err != nil {
-		return err
-	}
-	for _, pid := range pids {
-		// TODO: log err without aborting if we are unable to find
-		// a single PID
-		if p, err := os.FindProcess(pid); err == nil {
-			procs = append(procs, p)
-			p.Kill()
-		}
-	}
-	m.Freeze(cgroups.Thawed)
-	for _, p := range procs {
-		p.Wait()
-	}
-	return err
-}
-
-// Utility function that gets a host ID for a container ID from user namespace map
-// if that ID is present in the map.
-func hostIDFromMapping(containerID int, uMap []configs.IDMap) (int, bool) {
-	for _, m := range uMap {
-		if (containerID >= m.ContainerID) && (containerID <= (m.ContainerID + m.Size - 1)) {
-			hostID := m.HostID + (containerID - m.ContainerID)
-			return hostID, true
-		}
-	}
-	return -1, false
-}
-
-// Gets the root uid for the process on host which could be non-zero
-// when user namespaces are enabled.
-func GetHostRootGid(container *configs.Config) (int, error) {
-	if container.Namespaces.Contains(configs.NEWUSER) {
-		if container.GidMappings == nil {
-			return -1, fmt.Errorf("User namespaces enabled, but no gid mappings found.")
-		}
-		hostRootGid, found := hostIDFromMapping(0, container.GidMappings)
-		if !found {
-			return -1, fmt.Errorf("User namespaces enabled, but no root user mapping found.")
-		}
-		return hostRootGid, nil
-	}
-
-	// Return default root uid 0
-	return 0, nil
-}
-
-// Gets the root uid for the process on host which could be non-zero
-// when user namespaces are enabled.
-func GetHostRootUid(container *configs.Config) (int, error) {
-	if container.Namespaces.Contains(configs.NEWUSER) {
-		if container.UidMappings == nil {
-			return -1, fmt.Errorf("User namespaces enabled, but no user mappings found.")
-		}
-		hostRootUid, found := hostIDFromMapping(0, container.UidMappings)
-		if !found {
-			return -1, fmt.Errorf("User namespaces enabled, but no root user mapping found.")
-		}
-		return hostRootUid, nil
-	}
-
-	// Return default root uid 0
-	return 0, nil
-}
-
-// Converts IDMap to SysProcIDMap array and adds it to SysProcAttr.
-func AddUidGidMappings(sys *syscall.SysProcAttr, container *configs.Config) {
-	if container.UidMappings != nil {
-		sys.UidMappings = make([]syscall.SysProcIDMap, len(container.UidMappings))
-		for i, um := range container.UidMappings {
-			sys.UidMappings[i].ContainerID = um.ContainerID
-			sys.UidMappings[i].HostID = um.HostID
-			sys.UidMappings[i].Size = um.Size
-		}
-	}
-
-	if container.GidMappings != nil {
-		sys.GidMappings = make([]syscall.SysProcIDMap, len(container.GidMappings))
-		for i, gm := range container.GidMappings {
-			sys.GidMappings[i].ContainerID = gm.ContainerID
-			sys.GidMappings[i].HostID = gm.HostID
-			sys.GidMappings[i].Size = gm.Size
-		}
-	}
-}
-
-// InitializeNetworking creates the container's network stack outside of the namespace and moves
-// interfaces into the container's net namespaces if necessary
-func InitializeNetworking(container *configs.Config, nspid int, networkState *network.NetworkState) error {
-	for _, config := range container.Networks {
-		strategy, err := network.GetStrategy(config.Type)
-		if err != nil {
-			return err
-		}
-		if err := strategy.Create((*network.Network)(config), nspid, networkState); err != nil {
-			return err
-		}
-	}
-	return nil
-}

namespaces/execin.go

@@ -1,235 +0,0 @@
-// +build linux
-
-package namespaces
-
-import (
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"os/exec"
-	"syscall"
-
-	"github.com/docker/libcontainer/apparmor"
-	"github.com/docker/libcontainer/cgroups"
-	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/label"
-	"github.com/docker/libcontainer/mount"
-	"github.com/docker/libcontainer/system"
-	"github.com/docker/libcontainer/utils"
-)
-
-type pid struct {
-	Pid int `json:"Pid"`
-}
-
-// ExecIn reexec's cmd with _LIBCONTAINER_INITPID=PID so that it is able to run the
-// setns code in a single threaded environment joining the existing containers' namespaces.
-func ExecIn(args []string, env []string, console string, cmd *exec.Cmd, container *configs.Config, state *configs.State) (int, error) {
-	var err error
-
-	parent, child, err := newInitPipe()
-	if err != nil {
-		return -1, err
-	}
-	defer parent.Close()
-
-	cmd.ExtraFiles = []*os.File{child}
-	cmd.Env = append(cmd.Env, fmt.Sprintf("_LIBCONTAINER_INITPID=%d", state.InitPid))
-
-	if err := cmd.Start(); err != nil {
-		child.Close()
-		return -1, err
-	}
-	child.Close()
-
-	s, err := cmd.Process.Wait()
-	if err != nil {
-		return -1, err
-	}
-	if !s.Success() {
-		return -1, &exec.ExitError{s}
-	}
-
-	decoder := json.NewDecoder(parent)
-	var pid *pid
-
-	if err := decoder.Decode(&pid); err != nil {
-		return -1, err
-	}
-
-	p, err := os.FindProcess(pid.Pid)
-	if err != nil {
-		return -1, err
-	}
-
-	terminate := func(terr error) (int, error) {
-		// TODO: log the errors for kill and wait
-		p.Kill()
-		p.Wait()
-		return -1, terr
-	}
-
-	// Enter cgroups.
-	if err := EnterCgroups(state, pid.Pid); err != nil {
-		return terminate(err)
-	}
-
-	encoder := json.NewEncoder(parent)
-
-	if err := encoder.Encode(container); err != nil {
-		return terminate(err)
-	}
-
-	process := processArgs{
-		Env:         append(env[0:], container.Env...),
-		Args:        args,
-		ConsolePath: console,
-	}
-	if err := encoder.Encode(process); err != nil {
-		return terminate(err)
-	}
-
-	return pid.Pid, nil
-}
-
-// Finalize entering into a container and execute a specified command
-func InitIn(pipe *os.File) (err error) {
-	defer func() {
-		// if we have an error during the initialization of the container's init then send it back to the
-		// parent process in the form of an initError.
-		if err != nil {
-			// ensure that any data sent from the parent is consumed so it doesn't
-			// receive ECONNRESET when the child writes to the pipe.
-			ioutil.ReadAll(pipe)
-			if err := json.NewEncoder(pipe).Encode(initError{
-				Message: err.Error(),
-			}); err != nil {
-				panic(err)
-			}
-		}
-		// ensure that this pipe is always closed
-		pipe.Close()
-	}()
-
-	decoder := json.NewDecoder(pipe)
-
-	var container *configs.Config
-	if err := decoder.Decode(&container); err != nil {
-		return err
-	}
-
-	var process *processArgs
-	if err := decoder.Decode(&process); err != nil {
-		return err
-	}
-
-	if err := FinalizeSetns(container); err != nil {
-		return err
-	}
-
-	if err := system.Execv(process.Args[0], process.Args[0:], process.Env); err != nil {
-		return err
-	}
-
-	panic("unreachable")
-}
-
-// Finalize expects that the setns calls have been setup and that is has joined an
-// existing namespace
-func FinalizeSetns(container *configs.Config) error {
-	// clear the current processes env and replace it with the environment defined on the container
-	if err := LoadContainerEnvironment(container); err != nil {
-		return err
-	}
-
-	if err := setupRlimits(container); err != nil {
-		return fmt.Errorf("setup rlimits %s", err)
-	}
-
-	if err := FinalizeNamespace(container); err != nil {
-		return err
-	}
-
-	if err := apparmor.ApplyProfile(container.AppArmorProfile); err != nil {
-		return fmt.Errorf("set apparmor profile %s: %s", container.AppArmorProfile, err)
-	}
-
-	if container.ProcessLabel != "" {
-		if err := label.SetProcessLabel(container.ProcessLabel); err != nil {
-			return err
-		}
-	}
-
-	return nil
-}
-
-// SetupContainer is run to setup mounts and networking related operations
-// for a user namespace enabled process as a user namespace root doesn't
-// have permissions to perform these operations.
-// The setup process joins all the namespaces of user namespace enabled init
-// except the user namespace, so it run as root in the root user namespace
-// to perform these operations.
-func SetupContainer(process *processArgs) error {
-	container := process.Config
-	networkState := process.NetworkState
-	consolePath := process.ConsolePath
-
-	rootfs, err := utils.ResolveRootfs(container.RootFs)
-	if err != nil {
-		return err
-	}
-
-	// clear the current processes env and replace it with the environment
-	// defined on the container
-	if err := LoadContainerEnvironment(container); err != nil {
-		return err
-	}
-
-	cloneFlags := GetNamespaceFlags(container.Namespaces)
-
-	if (cloneFlags & syscall.CLONE_NEWNET) == 0 {
-		if len(container.Networks) != 0 || len(container.Routes) != 0 {
-			return fmt.Errorf("unable to apply network parameters without network namespace")
-		}
-	} else {
-		if err := setupNetwork(container, networkState); err != nil {
-			return fmt.Errorf("setup networking %s", err)
-		}
-		if err := setupRoute(container); err != nil {
-			return fmt.Errorf("setup route %s", err)
-		}
-	}
-
-	label.Init()
-
-	hostRootUid, err := GetHostRootUid(container)
-	if err != nil {
-		return fmt.Errorf("failed to get hostRootUid %s", err)
-	}
-
-	hostRootGid, err := GetHostRootGid(container)
-	if err != nil {
-		return fmt.Errorf("failed to get hostRootGid %s", err)
-	}
-
-	// InitializeMountNamespace() can be executed only for a new mount namespace
-	if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
-		if container.MountConfig != nil {
-			return fmt.Errorf("mount config is set without mount namespace")
-		}
-	} else if err := mount.InitializeMountNamespace(rootfs,
-		consolePath,
-		container.RestrictSys,
-		hostRootUid,
-		hostRootGid,
-		(*mount.MountConfig)(container.MountConfig)); err != nil {
-		return fmt.Errorf("setup mount namespace %s", err)
-	}
-
-	return nil
-}
-
-func EnterCgroups(state *configs.State, pid int) error {
-	return cgroups.EnterPid(state.CgroupPaths, pid)
-}

namespaces/init.go

@@ -1,468 +0,0 @@
-// +build linux
-
-package namespaces
-
-import (
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"strings"
-	"syscall"
-
-	"github.com/docker/libcontainer/apparmor"
-	"github.com/docker/libcontainer/configs"
-	"github.com/docker/libcontainer/console"
-	"github.com/docker/libcontainer/label"
-	"github.com/docker/libcontainer/mount"
-	"github.com/docker/libcontainer/netlink"
-	"github.com/docker/libcontainer/network"
-	"github.com/docker/libcontainer/security/capabilities"
-	"github.com/docker/libcontainer/security/restrict"
-	"github.com/docker/libcontainer/system"
-	"github.com/docker/libcontainer/user"
-	"github.com/docker/libcontainer/utils"
-)
-
-// Process is used for transferring parameters from Exec() to Init()
-type processArgs struct {
-	Args         []string              `json:"args,omitempty"`
-	Env          []string              `json:"environment,omitempty"`
-	ConsolePath  string                `json:"console_path,omitempty"`
-	Config       *configs.Config       `json:"config,omitempty"`
-	NetworkState *network.NetworkState `json:"network_state,omitempty"`
-}
-
-// TODO(vishh): This is part of the libcontainer API and it does much more than just namespaces related work.
-// Move this to libcontainer package.
-// Init is the init process that first runs inside a new namespace to setup mounts, users, networking,
-// and other options required for the new container.
-// The caller of Init function has to ensure that the go runtime is locked to an OS thread
-// (using runtime.LockOSThread) else system calls like setns called within Init may not work as intended.
-func Init(pipe *os.File, setupUserns bool) (err error) {
-	defer func() {
-		// if we have an error during the initialization of the container's init then send it back to the
-		// parent process in the form of an initError.
-		if err != nil {
-			// ensure that any data sent from the parent is consumed so it doesn't
-			// receive ECONNRESET when the child writes to the pipe.
-			ioutil.ReadAll(pipe)
-			if err := json.NewEncoder(pipe).Encode(initError{
-				Message: err.Error(),
-			}); err != nil {
-				panic(err)
-			}
-		}
-		// ensure that this pipe is always closed
-		pipe.Close()
-	}()
-
-	uncleanRootfs, err := os.Getwd()
-	if err != nil {
-		return err
-	}
-
-	var process *processArgs
-	// We always read this as it is a way to sync with the parent as well
-	if err := json.NewDecoder(pipe).Decode(&process); err != nil {
-		return err
-	}
-
-	if setupUserns {
-		err = SetupContainer(process)
-		if err == nil {
-			os.Exit(0)
-		} else {
-			os.Exit(1)
-		}
-	}
-
-	if process.Config.Namespaces.Contains(configs.NEWUSER) {
-		return initUserNs(uncleanRootfs, process)
-	} else {
-		return initDefault(uncleanRootfs, process)
-	}
-}
-
-func initDefault(uncleanRootfs string, process *processArgs) (err error) {
-	container := process.Config
-	networkState := process.NetworkState
-
-	rootfs, err := utils.ResolveRootfs(uncleanRootfs)
-	if err != nil {
-		return err
-	}
-
-	// clear the current processes env and replace it with the environment
-	// defined on the container
-	if err := LoadContainerEnvironment(container); err != nil {
-		return err
-	}
-
-	// join any namespaces via a path to the namespace fd if provided
-	if err := joinExistingNamespaces(container.Namespaces); err != nil {
-		return err
-	}
-	if process.ConsolePath != "" {
-		if err := console.OpenAndDup(process.ConsolePath); err != nil {
-			return err
-		}
-	}
-	if _, err := syscall.Setsid(); err != nil {
-		return fmt.Errorf("setsid %s", err)
-	}
-	if process.ConsolePath != "" {
-		if err := system.Setctty(); err != nil {
-			return fmt.Errorf("setctty %s", err)
-		}
-	}
-
-	cloneFlags := GetNamespaceFlags(container.Namespaces)
-
-	if (cloneFlags & syscall.CLONE_NEWNET) == 0 {
-		if len(container.Networks) != 0 || len(container.Routes) != 0 {
-			return fmt.Errorf("unable to apply network parameters without network namespace")
-		}
-	} else {
-		if err := setupNetwork(container, networkState); err != nil {
-			return fmt.Errorf("setup networking %s", err)
-		}
-		if err := setupRoute(container); err != nil {
-			return fmt.Errorf("setup route %s", err)
-		}
-	}
-
-	if err := setupRlimits(container); err != nil {
-		return fmt.Errorf("setup rlimits %s", err)
-	}
-
-	label.Init()
-
-	// InitializeMountNamespace() can be executed only for a new mount namespace
-	if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
-		if container.MountConfig != nil {
-			return fmt.Errorf("mount config is set without mount namespace")
-		}
-	} else if err := mount.InitializeMountNamespace(rootfs,
-		process.ConsolePath,
-		container.RestrictSys,
-		0, // Default Root Uid
-		0, // Default Root Gid
-		(*mount.MountConfig)(container.MountConfig)); err != nil {
-		return fmt.Errorf("setup mount namespace %s", err)
-	}
-
-	if container.Hostname != "" {
-		if (cloneFlags & syscall.CLONE_NEWUTS) == 0 {
-			return fmt.Errorf("unable to set the hostname without UTS namespace")
-		}
-		if err := syscall.Sethostname([]byte(container.Hostname)); err != nil {
-			return fmt.Errorf("unable to sethostname %q: %s", container.Hostname, err)
-		}
-	}
-
-	if err := apparmor.ApplyProfile(container.AppArmorProfile); err != nil {
-		return fmt.Errorf("set apparmor profile %s: %s", container.AppArmorProfile, err)
-	}
-
-	if err := label.SetProcessLabel(container.ProcessLabel); err != nil {
-		return fmt.Errorf("set process label %s", err)
-	}
-
-	// TODO: (crosbymichael) make this configurable at the Config level
-	if container.RestrictSys {
-		if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
-			return fmt.Errorf("unable to restrict access to kernel files without mount namespace")
-		}
-		if err := restrict.Restrict("proc/sys", "proc/sysrq-trigger", "proc/irq", "proc/bus"); err != nil {
-			return err
-		}
-	}
-
-	pdeathSignal, err := system.GetParentDeathSignal()
-	if err != nil {
-		return fmt.Errorf("get parent death signal %s", err)
-	}
-
-	if err := FinalizeNamespace(container); err != nil {
-		return fmt.Errorf("finalize namespace %s", err)
-	}
-
-	// FinalizeNamespace can change user/group which clears the parent death
-	// signal, so we restore it here.
-	if err := RestoreParentDeathSignal(pdeathSignal); err != nil {
-		return fmt.Errorf("restore parent death signal %s", err)
-	}
-
-	return system.Execv(process.Args[0], process.Args[0:], process.Env)
-}
-
-func initUserNs(uncleanRootfs string, process *processArgs) (err error) {
-	container := process.Config
-
-	// clear the current processes env and replace it with the environment
-	// defined on the container
-	if err := LoadContainerEnvironment(container); err != nil {
-		return err
-	}
-
-	// join any namespaces via a path to the namespace fd if provided
-	if err := joinExistingNamespaces(container.Namespaces); err != nil {
-		return err
-	}
-	if process.ConsolePath != "" {
-		if err := console.OpenAndDup("/dev/console"); err != nil {
-			return err
-		}
-	}
-	if _, err := syscall.Setsid(); err != nil {
-		return fmt.Errorf("setsid %s", err)
-	}
-	if process.ConsolePath != "" {
-		if err := system.Setctty(); err != nil {
-			return fmt.Errorf("setctty %s", err)
-		}
-	}
-
-	if container.WorkingDir == "" {
-		container.WorkingDir = "/"
-	}
-
-	if err := setupRlimits(container); err != nil {
-		return fmt.Errorf("setup rlimits %s", err)
-	}
-
-	cloneFlags := GetNamespaceFlags(container.Namespaces)
-
-	if container.Hostname != "" {
-		if (cloneFlags & syscall.CLONE_NEWUTS) == 0 {
-			return fmt.Errorf("unable to set the hostname without UTS namespace")
-		}
-		if err := syscall.Sethostname([]byte(container.Hostname)); err != nil {
-			return fmt.Errorf("unable to sethostname %q: %s", container.Hostname, err)
-		}
-	}
-
-	if err := apparmor.ApplyProfile(container.AppArmorProfile); err != nil {
-		return fmt.Errorf("set apparmor profile %s: %s", container.AppArmorProfile, err)
-	}
-
-	if err := label.SetProcessLabel(container.ProcessLabel); err != nil {
-		return fmt.Errorf("set process label %s", err)
-	}
-
-	if container.RestrictSys {
-		if (cloneFlags & syscall.CLONE_NEWNS) == 0 {
-			return fmt.Errorf("unable to restrict access to kernel files without mount namespace")
-		}
-		if err := restrict.Restrict("proc/sys", "proc/sysrq-trigger", "proc/irq", "proc/bus"); err != nil {
-			return err
-		}
-	}
-
-	pdeathSignal, err := system.GetParentDeathSignal()
-	if err != nil {
-		return fmt.Errorf("get parent death signal %s", err)
-	}
-
-	if err := FinalizeNamespace(container); err != nil {
-		return fmt.Errorf("finalize namespace %s", err)
-	}
-
-	// FinalizeNamespace can change user/group which clears the parent death
-	// signal, so we restore it here.
-	if err := RestoreParentDeathSignal(pdeathSignal); err != nil {
-		return fmt.Errorf("restore parent death signal %s", err)
-	}
-
-	return system.Execv(process.Args[0], process.Args[0:], process.Env)
-}
-
-// RestoreParentDeathSignal sets the parent death signal to old.
-func RestoreParentDeathSignal(old int) error {
-	if old == 0 {
-		return nil
-	}
-
-	current, err := system.GetParentDeathSignal()
-	if err != nil {
-		return fmt.Errorf("get parent death signal %s", err)
-	}
-
-	if old == current {
-		return nil
-	}
-
-	if err := system.ParentDeathSignal(uintptr(old)); err != nil {
-		return fmt.Errorf("set parent death signal %s", err)
-	}
-
-	// Signal self if parent is already dead. Does nothing if running in a new
-	// PID namespace, as Getppid will always return 0.
-	if syscall.Getppid() == 1 {
-		return syscall.Kill(syscall.Getpid(), syscall.SIGKILL)
-	}
-
-	return nil
-}
-
-// SetupUser changes the groups, gid, and uid for the user inside the container
-func SetupUser(container *configs.Config) error {
-	// Set up defaults.
-	defaultExecUser := user.ExecUser{
-		Uid:  syscall.Getuid(),
-		Gid:  syscall.Getgid(),
-		Home: "/",
-	}
-
-	passwdPath, err := user.GetPasswdPath()
-	if err != nil {
-		return err
-	}
-
-	groupPath, err := user.GetGroupPath()
-	if err != nil {
-		return err
-	}
-
-	execUser, err := user.GetExecUserPath(container.User, &defaultExecUser, passwdPath, groupPath)
-	if err != nil {
-		return fmt.Errorf("get supplementary groups %s", err)
-	}
-
-	suppGroups := append(execUser.Sgids, container.AdditionalGroups...)
-
-	if err := syscall.Setgroups(suppGroups); err != nil {
-		return fmt.Errorf("setgroups %s", err)
-	}
-
-	if err := system.Setgid(execUser.Gid); err != nil {
-		return fmt.Errorf("setgid %s", err)
-	}
-
-	if err := system.Setuid(execUser.Uid); err != nil {
-		return fmt.Errorf("setuid %s", err)
-	}
-
-	// if we didn't get HOME already, set it based on the user's HOME
-	if envHome := os.Getenv("HOME"); envHome == "" {
-		if err := os.Setenv("HOME", execUser.Home); err != nil {
-			return fmt.Errorf("set HOME %s", err)
-		}
-	}
-
-	return nil
-}
-
-// setupVethNetwork uses the Network config if it is not nil to initialize
-// the new veth interface inside the container for use by changing the name to eth0
-// setting the MTU and IP address along with the default gateway
-func setupNetwork(container *configs.Config, networkState *network.NetworkState) error {
-	for _, config := range container.Networks {
-		strategy, err := network.GetStrategy(config.Type)
-		if err != nil {
-			return err
-		}
-
-		err1 := strategy.Initialize((*network.Network)(config), networkState)
-		if err1 != nil {
-			return err1
-		}
-	}
-	return nil
-}
-
-func setupRoute(container *configs.Config) error {
-	for _, config := range container.Routes {
-		if err := netlink.AddRoute(config.Destination, config.Source, config.Gateway, config.InterfaceName); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func setupRlimits(container *configs.Config) error {
-	for _, rlimit := range container.Rlimits {
-		l := &syscall.Rlimit{Max: rlimit.Hard, Cur: rlimit.Soft}
-		if err := syscall.Setrlimit(rlimit.Type, l); err != nil {
-			return fmt.Errorf("error setting rlimit type %v: %v", rlimit.Type, err)
-		}
-	}
-	return nil
-}
-
-// FinalizeNamespace drops the caps, sets the correct user
-// and working dir, and closes any leaky file descriptors
-// before execing the command inside the namespace
-func FinalizeNamespace(container *configs.Config) error {
-	// Ensure that all non-standard fds we may have accidentally
-	// inherited are marked close-on-exec so they stay out of the
-	// container
-	if err := utils.CloseExecFrom(3); err != nil {
-		return fmt.Errorf("close open file descriptors %s", err)
-	}
-
-	// drop capabilities in bounding set before changing user
-	if err := capabilities.DropBoundingSet(container.Capabilities); err != nil {
-		return fmt.Errorf("drop bounding set %s", err)
-	}
-
-	// preserve existing capabilities while we change users
-	if err := system.SetKeepCaps(); err != nil {
-		return fmt.Errorf("set keep caps %s", err)
-	}
-
-	if err := SetupUser(container); err != nil {
-		return fmt.Errorf("setup user %s", err)
-	}
-
-	if err := system.ClearKeepCaps(); err != nil {
-		return fmt.Errorf("clear keep caps %s", err)
-	}
-
-	// drop all other capabilities
-	if err := capabilities.DropCapabilities(container.Capabilities); err != nil {
-		return fmt.Errorf("drop capabilities %s", err)
-	}
-
-	if container.WorkingDir != "" {
-		if err := syscall.Chdir(container.WorkingDir); err != nil {
-			return fmt.Errorf("chdir to %s %s", container.WorkingDir, err)
-		}
-	}
-
-	return nil
-}
-
-func LoadContainerEnvironment(container *configs.Config) error {
-	os.Clearenv()
-	for _, pair := range container.Env {
-		p := strings.SplitN(pair, "=", 2)
-		if len(p) < 2 {
-			return fmt.Errorf("invalid environment '%v'", pair)
-		}
-		if err := os.Setenv(p[0], p[1]); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-// joinExistingNamespaces gets all the namespace paths specified for the container and
-// does a setns on the namespace fd so that the current process joins the namespace.
-func joinExistingNamespaces(namespaces []configs.Namespace) error {
-	for _, ns := range namespaces {
-		if ns.Path != "" {
-			f, err := os.OpenFile(ns.Path, os.O_RDONLY, 0)
-			if err != nil {
-				return err
-			}
-			err = system.Setns(f.Fd(), uintptr(namespaceInfo[ns.Type]))
-			f.Close()
-			if err != nil {
-				return err
-			}
-		}
-	}
-	return nil
-}

namespaces/utils.go

@@ -1,48 +0,0 @@
-// +build linux
-
-package namespaces
-
-import (
-	"os"
-	"syscall"
-
-	"github.com/docker/libcontainer/configs"
-)
-
-type initError struct {
-	Message string `json:"message,omitempty"`
-}
-
-func (i initError) Error() string {
-	return i.Message
-}
-
-var namespaceInfo = map[configs.NamespaceType]int{
-	configs.NEWNET:  syscall.CLONE_NEWNET,
-	configs.NEWNS:   syscall.CLONE_NEWNS,
-	configs.NEWUSER: syscall.CLONE_NEWUSER,
-	configs.NEWIPC:  syscall.CLONE_NEWIPC,
-	configs.NEWUTS:  syscall.CLONE_NEWUTS,
-	configs.NEWPID:  syscall.CLONE_NEWPID,
-}
-
-// New returns a newly initialized Pipe for communication between processes
-func newInitPipe() (parent *os.File, child *os.File, err error) {
-	fds, err := syscall.Socketpair(syscall.AF_LOCAL, syscall.SOCK_STREAM|syscall.SOCK_CLOEXEC, 0)
-	if err != nil {
-		return nil, nil, err
-	}
-	return os.NewFile(uintptr(fds[1]), "parent"), os.NewFile(uintptr(fds[0]), "child"), nil
-}
-
-// GetNamespaceFlags parses the container's Namespaces options to set the correct
-// flags on clone, unshare. This functions returns flags only for new namespaces.
-func GetNamespaceFlags(namespaces configs.Namespaces) (flag int) {
-	for _, v := range namespaces {
-		if v.Path != "" {
-			continue
-		}
-		flag |= namespaceInfo[v.Type]
-	}
-	return flag
-}

network/loopback.go

@@ -4,17 +4,19 @@ package network
 
 import (
 	"fmt"
+
+	"github.com/docker/libcontainer/configs"
 )
 
 // Loopback is a network strategy that provides a basic loopback device
 type Loopback struct {
 }
 
-func (l *Loopback) Create(n *Network, nspid int, networkState *NetworkState) error {
+func (l *Loopback) Create(n *configs.Network, nspid int, networkState *configs.NetworkState) error {
 	return nil
 }
 
-func (l *Loopback) Initialize(config *Network, networkState *NetworkState) error {
+func (l *Loopback) Initialize(config *configs.Network, networkState *configs.NetworkState) error {
 	// Do not set the MTU on the loopback interface - use the default.
 	if err := InterfaceUp("lo"); err != nil {
 		return fmt.Errorf("lo up %s", err)

network/stats.go

@@ -5,6 +5,8 @@ import (
 	"path/filepath"
 	"strconv"
 	"strings"
+
+	"github.com/docker/libcontainer/configs"
 )
 
 type NetworkStats struct {
@@ -19,7 +21,7 @@ type NetworkStats struct {
 }
 
 // Returns the network statistics for the network interfaces represented by the NetworkRuntimeInfo.
-func GetStats(networkState *NetworkState) (*NetworkStats, error) {
+func GetStats(networkState *configs.NetworkState) (*NetworkStats, error) {
 	// This can happen if the network runtime information is missing - possible if the container was created by an old version of libcontainer.
 	if networkState.VethHost == "" {
 		return &NetworkStats{}, nil

network/strategy.go

@@ -4,6 +4,8 @@ package network
 
 import (
 	"errors"
+
+	"github.com/docker/libcontainer/configs"
 )
 
 var (
@@ -18,8 +20,8 @@ var strategies = map[string]NetworkStrategy{
 // NetworkStrategy represents a specific network configuration for
 // a container's networking stack
 type NetworkStrategy interface {
-	Create(*Network, int, *NetworkState) error
-	Initialize(*Network, *NetworkState) error
+	Create(*configs.Network, int, *configs.NetworkState) error
+	Initialize(*configs.Network, *configs.NetworkState) error
 }
 
 // GetStrategy returns the specific network strategy for the

network/types.go

@@ -1,50 +1 @@
 package network
-
-// Network defines configuration for a container's networking stack
-//
-// The network configuration can be omited from a container causing the
-// container to be setup with the host's networking stack
-type Network struct {
-	// Type sets the networks type, commonly veth and loopback
-	Type string `json:"type,omitempty"`
-
-	// The bridge to use.
-	Bridge string `json:"bridge,omitempty"`
-
-	// Prefix for the veth interfaces.
-	VethPrefix string `json:"veth_prefix,omitempty"`
-
-	// MacAddress contains the MAC address to set on the network interface
-	MacAddress string `json:"mac_address,omitempty"`
-
-	// Address contains the IPv4 and mask to set on the network interface
-	Address string `json:"address,omitempty"`
-
-	// IPv6Address contains the IPv6 and mask to set on the network interface
-	IPv6Address string `json:"ipv6_address,omitempty"`
-
-	// Gateway sets the gateway address that is used as the default for the interface
-	Gateway string `json:"gateway,omitempty"`
-
-	// IPv6Gateway sets the ipv6 gateway address that is used as the default for the interface
-	IPv6Gateway string `json:"ipv6_gateway,omitempty"`
-
-	// Mtu sets the mtu value for the interface and will be mirrored on both the host and
-	// container's interfaces if a pair is created, specifically in the case of type veth
-	// Note: This does not apply to loopback interfaces.
-	Mtu int `json:"mtu,omitempty"`
-
-	// TxQueueLen sets the tx_queuelen value for the interface and will be mirrored on both the host and
-	// container's interfaces if a pair is created, specifically in the case of type veth
-	// Note: This does not apply to loopback interfaces.
-	TxQueueLen int `json:"txqueuelen,omitempty"`
-}
-
-// Struct describing the network specific runtime state that will be maintained by libcontainer for all running containers
-// Do not depend on it outside of libcontainer.
-type NetworkState struct {
-	// The name of the veth interface on the Host.
-	VethHost string `json:"veth_host,omitempty"`
-	// The name of the veth interface created inside the container for the child.
-	VethChild string `json:"veth_child,omitempty"`
-}

network/veth.go

@@ -5,6 +5,7 @@ package network
 import (
 	"fmt"
 
+	"github.com/docker/libcontainer/configs"
 	"github.com/docker/libcontainer/netlink"
 	"github.com/docker/libcontainer/utils"
 )
@@ -17,7 +18,7 @@ type Veth struct {
 
 const defaultDevice = "eth0"
 
-func (v *Veth) Create(n *Network, nspid int, networkState *NetworkState) error {
+func (v *Veth) Create(n *configs.Network, nspid int, networkState *configs.NetworkState) error {
 	var (
 		bridge     = n.Bridge
 		prefix     = n.VethPrefix
@@ -51,7 +52,7 @@ func (v *Veth) Create(n *Network, nspid int, networkState *NetworkState) error {
 	return nil
 }
 
-func (v *Veth) Initialize(config *Network, networkState *NetworkState) error {
+func (v *Veth) Initialize(config *configs.Network, networkState *configs.NetworkState) error {
 	var vethChild = networkState.VethChild
 	if vethChild == "" {
 		return fmt.Errorf("vethChild is not specified")

nsinit/config.go

@@ -1,29 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"log"
-
-	"github.com/codegangsta/cli"
-)
-
-var configCommand = cli.Command{
-	Name:   "config",
-	Usage:  "display the container configuration",
-	Action: configAction,
-}
-
-func configAction(context *cli.Context) {
-	container, err := loadConfig()
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	data, err := json.MarshalIndent(container, "", "\t")
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	fmt.Printf("%s", data)
-}

nsinit/exec.go

@@ -1,11 +1,9 @@
 package main
 
 import (
-	"crypto/md5"
-	"fmt"
 	"io"
-	"log"
 	"os"
+	"os/signal"
 	"syscall"
 
 	"github.com/codegangsta/cli"
@@ -15,145 +13,148 @@ import (
 	consolepkg "github.com/docker/libcontainer/console"
 )
 
-var (
-	dataPath  = os.Getenv("data_path")
-	console   = os.Getenv("console")
-	rawPipeFd = os.Getenv("pipe")
-)
+type tty struct {
+	master  *os.File
+	console string
+	state   *term.State
+}
+
+func (t *tty) Close() error {
+	if t.master != nil {
+		t.master.Close()
+	}
+	if t.state != nil {
+		term.RestoreTerminal(os.Stdin.Fd(), t.state)
+	}
+	return nil
+}
+
+func (t *tty) set(config *configs.Config) {
+	config.Console = t.console
+}
+
+func (t *tty) attach(process *libcontainer.Process) {
+	if t.master != nil {
+		process.Stderr = nil
+		process.Stdout = nil
+		process.Stdin = nil
+	}
+}
+
+func (t *tty) resize() error {
+	if t.master == nil {
+		return nil
+	}
+	ws, err := term.GetWinsize(os.Stdin.Fd())
+	if err != nil {
+		return err
+	}
+	return term.SetWinsize(t.master.Fd(), ws)
+}
 
 var execCommand = cli.Command{
 	Name:   "exec",
 	Usage:  "execute a new command inside a container",
 	Action: execAction,
 	Flags: []cli.Flag{
-		cli.BoolFlag{Name: "list", Usage: "list all registered exec functions"},
-		cli.StringFlag{Name: "func", Value: "exec", Usage: "function name to exec inside a container"},
+		cli.BoolFlag{Name: "tty", Usage: "allocate a TTY to the container"},
+		cli.StringFlag{Name: "id", Value: "nsinit", Usage: "specify the ID for a container"},
+		cli.StringFlag{Name: "config", Value: "container.json", Usage: "path to the configuration file"},
 	},
 }
 
-func getContainer(context *cli.Context) (libcontainer.Container, error) {
-	factory, err := libcontainer.New(context.GlobalString("root"), []string{os.Args[0], "init", "--fd", "3", "--"})
+func execAction(context *cli.Context) {
+	factory, err := loadFactory(context)
 	if err != nil {
-		log.Fatal(err)
+		fatal(err)
 	}
-
-	id := fmt.Sprintf("%x", md5.Sum([]byte(dataPath)))
-	container, err := factory.Load(id)
-	if err != nil && !os.IsNotExist(err) {
-		var config *configs.Config
-
-		config, err = loadConfig()
-		if err != nil {
-			log.Fatal(err)
+	tty, err := newTty(context)
+	if err != nil {
+		fatal(err)
+	}
+	container, err := factory.Load(context.String("id"))
+	if err != nil {
+		if lerr, ok := err.(libcontainer.Error); !ok || lerr.Code() != libcontainer.ContainerNotExists {
+			fatal(err)
+		}
+		config, err := loadConfig(context)
+		if err != nil {
+			fatal(err)
+		}
+		tty.set(config)
+		if container, err = factory.Create(context.String("id"), config); err != nil {
+			fatal(err)
 		}
-		container, err = factory.Create(id, config)
 	}
-
-	return container, err
+	go handleSignals(container, tty)
+	process := &libcontainer.Process{
+		Args:   context.Args(),
+		Stdin:  os.Stdin,
+		Stdout: os.Stdout,
+		Stderr: os.Stderr,
+	}
+	tty.attach(process)
+	pid, err := container.Start(process)
+	if err != nil {
+		fatal(err)
+	}
+	proc, err := os.FindProcess(pid)
+	if err != nil {
+		fatal(err)
+	}
+	status, err := proc.Wait()
+	if err != nil {
+		fatal(err)
+	}
+	if err := container.Destroy(); err != nil {
+		fatal(err)
+	}
+	exit(status.Sys().(syscall.WaitStatus))
 }
 
-func execAction(context *cli.Context) {
-	var (
-		master  *os.File
-		console string
-		err     error
-
-		sigc = make(chan os.Signal, 10)
-
-		stdin  = os.Stdin
-		stdout = os.Stdout
-		stderr = os.Stderr
-
-		exitCode int
-	)
-
-	container, err := getContainer(context)
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	if container.Config().Tty {
-		stdin = nil
-		stdout = nil
-		stderr = nil
-
-		master, console, err = consolepkg.CreateMasterAndConsole()
-		if err != nil {
-			log.Fatal(err)
-		}
-
-		go io.Copy(master, os.Stdin)
-		go io.Copy(os.Stdout, master)
-
-		state, err := term.SetRawTerminal(os.Stdin.Fd())
-		if err != nil {
-			log.Fatal(err)
-		}
-
-		defer term.RestoreTerminal(os.Stdin.Fd(), state)
-	}
-
-	process := &libcontainer.ProcessConfig{
-		Args:    context.Args(),
-		Env:     context.StringSlice("env"),
-		Stdin:   stdin,
-		Stdout:  stdout,
-		Stderr:  stderr,
-		Console: console,
-	}
-
-	pid, err := container.StartProcess(process)
-	if err != nil {
-		log.Fatalf("failed to exec: %s", err)
-	}
-
-	p, err := os.FindProcess(pid)
-	if err != nil {
-		log.Fatalf("Unable to find the %d process: %s", pid, err)
-	}
-
-	go func() {
-		resizeTty(master)
-
-		for sig := range sigc {
-			switch sig {
-			case syscall.SIGWINCH:
-				resizeTty(master)
-			default:
-				p.Signal(sig)
-			}
-		}
-	}()
-
-	ps, err := p.Wait()
-	if err != nil {
-		log.Fatalf("Unable to wait the %d process: %s", pid, err)
-	}
-	container.Destroy()
-
-	status := ps.Sys().(syscall.WaitStatus)
+func exit(status syscall.WaitStatus) {
+	var exitCode int
 	if status.Exited() {
 		exitCode = status.ExitStatus()
 	} else if status.Signaled() {
 		exitCode = -int(status.Signal())
 	} else {
-		log.Fatalf("Unexpected status")
+		fatalf("Unexpected status")
 	}
-
 	os.Exit(exitCode)
 }
 
-func resizeTty(master *os.File) {
-	if master == nil {
-		return
-	}
-
-	ws, err := term.GetWinsize(os.Stdin.Fd())
-	if err != nil {
-		return
-	}
-
-	if err := term.SetWinsize(master.Fd(), ws); err != nil {
-		return
+func handleSignals(container libcontainer.Container, tty *tty) {
+	sigc := make(chan os.Signal, 10)
+	signal.Notify(sigc)
+	tty.resize()
+	for sig := range sigc {
+		switch sig {
+		case syscall.SIGWINCH:
+			tty.resize()
+		default:
+			container.Signal(sig)
+		}
 	}
 }
+
+func newTty(context *cli.Context) (*tty, error) {
+	if context.Bool("tty") {
+		master, console, err := consolepkg.CreateMasterAndConsole()
+		if err != nil {
+			return nil, err
+		}
+		go io.Copy(master, os.Stdin)
+		go io.Copy(os.Stdout, master)
+		state, err := term.SetRawTerminal(os.Stdin.Fd())
+		if err != nil {
+			return nil, err
+		}
+		return &tty{
+			master:  master,
+			console: console,
+			state:   state,
+		}, nil
+	}
+	return &tty{}, nil
+}

nsinit/init.go

@@ -5,35 +5,27 @@ import (
 
 	"github.com/codegangsta/cli"
 	"github.com/docker/libcontainer"
-	_ "github.com/docker/libcontainer/namespaces/nsenter"
+	_ "github.com/docker/libcontainer/nsenter"
 )
 
-var (
-	initCommand = cli.Command{
-		Name:   "init",
-		Usage:  "runs the init process inside the namespace",
-		Action: initAction,
-		Flags: []cli.Flag{
-			cli.IntFlag{"fd", 0, "internal pipe fd"},
-		},
-	}
-)
-
-func initAction(context *cli.Context) {
-	factory, err := libcontainer.New("", []string{})
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	if context.Int("fd") == 0 {
-		log.Fatal("--fd must be specified for init process")
-	}
-
-	fd := uintptr(context.Int("fd"))
-
-	if err := factory.StartInitialization(fd); err != nil {
-		log.Fatal(err)
-	}
-
-	panic("This line should never been executed")
+var initCommand = cli.Command{
+	Name:  "init",
+	Usage: "runs the init process inside the namespace",
+	Flags: []cli.Flag{
+		cli.IntFlag{Name: "fd", Value: 0, Usage: "internal pipe fd"},
+	},
+	Action: func(context *cli.Context) {
+		factory, err := libcontainer.New("", nil)
+		if err != nil {
+			log.Fatal(err)
+		}
+		if context.Int("fd") == 0 {
+			log.Fatal("--fd must be specified for init process")
+		}
+		fd := uintptr(context.Int("fd"))
+		if err := factory.StartInitialization(fd); err != nil {
+			log.Fatal(err)
+		}
+		panic("This line should never been executed")
+	},
 }

nsinit/main.go

@@ -7,26 +7,17 @@ import (
 	"github.com/codegangsta/cli"
 )
 
-var (
-	logPath = os.Getenv("log")
-)
-
 func main() {
 	app := cli.NewApp()
-
 	app.Name = "nsinit"
-	app.Version = "0.1"
+	app.Version = "1"
 	app.Author = "libcontainer maintainers"
 	app.Flags = []cli.Flag{
 		cli.StringFlag{Name: "nspid"},
 		cli.StringFlag{Name: "console"},
 		cli.StringFlag{Name: "root", Value: ".", Usage: "root directory for containers"},
 	}
-
-	app.Before = preload
-
 	app.Commands = []cli.Command{
-		configCommand,
 		execCommand,
 		initCommand,
 		oomCommand,
@@ -34,7 +25,6 @@ func main() {
 		statsCommand,
 		unpauseCommand,
 	}
-
 	if err := app.Run(os.Args); err != nil {
 		log.Fatal(err)
 	}

nsinit/oom.go

@@ -4,26 +4,25 @@ import (
 	"log"
 
 	"github.com/codegangsta/cli"
-	"github.com/docker/libcontainer"
-	"github.com/docker/libcontainer/configs"
 )
 
 var oomCommand = cli.Command{
-	Name:   "oom",
-	Usage:  "display oom notifications for a container",
-	Action: oomAction,
-}
-
-func oomAction(context *cli.Context) {
-	state, err := configs.GetState(dataPath)
-	if err != nil {
-		log.Fatal(err)
-	}
-	n, err := libcontainer.NotifyOnOOM(state)
-	if err != nil {
-		log.Fatal(err)
-	}
-	for range n {
-		log.Printf("OOM notification received")
-	}
+	Name:  "oom",
+	Usage: "display oom notifications for a container",
+	Flags: []cli.Flag{
+		cli.StringFlag{Name: "id", Value: "nsinit", Usage: "specify the ID for a container"},
+	},
+	Action: func(context *cli.Context) {
+		container, err := getContainer(context)
+		if err != nil {
+			log.Fatal(err)
+		}
+		n, err := container.OOM()
+		if err != nil {
+			log.Fatal(err)
+		}
+		for range n {
+			log.Printf("OOM notification received")
+		}
+	},
 }

nsinit/pause.go

@@ -7,35 +7,35 @@ import (
 )
 
 var pauseCommand = cli.Command{
-	Name:   "pause",
-	Usage:  "pause the container's processes",
-	Action: pauseAction,
+	Name:  "pause",
+	Usage: "pause the container's processes",
+	Flags: []cli.Flag{
+		cli.StringFlag{Name: "id", Value: "nsinit", Usage: "specify the ID for a container"},
+	},
+	Action: func(context *cli.Context) {
+		container, err := getContainer(context)
+		if err != nil {
+			log.Fatal(err)
+		}
+		if err = container.Pause(); err != nil {
+			log.Fatal(err)
+		}
+	},
 }
 
 var unpauseCommand = cli.Command{
-	Name:   "unpause",
-	Usage:  "unpause the container's processes",
-	Action: unpauseAction,
-}
-
-func pauseAction(context *cli.Context) {
-	container, err := getContainer(context)
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	if err = container.Pause(); err != nil {
-		log.Fatal(err)
-	}
-}
-
-func unpauseAction(context *cli.Context) {
-	container, err := getContainer(context)
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	if err = container.Resume(); err != nil {
-		log.Fatal(err)
-	}
+	Name:  "unpause",
+	Usage: "unpause the container's processes",
+	Flags: []cli.Flag{
+		cli.StringFlag{Name: "id", Value: "nsinit", Usage: "specify the ID for a container"},
+	},
+	Action: func(context *cli.Context) {
+		container, err := getContainer(context)
+		if err != nil {
+			log.Fatal(err)
+		}
+		if err = container.Resume(); err != nil {
+			log.Fatal(err)
+		}
+	},
 }

nsinit/stats.go

@@ -6,34 +6,27 @@ import (
 	"log"
 
 	"github.com/codegangsta/cli"
-	"github.com/docker/libcontainer"
 )
 
 var statsCommand = cli.Command{
-	Name:   "stats",
-	Usage:  "display statistics for the container",
-	Action: statsAction,
-}
-
-func statsAction(context *cli.Context) {
-	factory, err := libcontainer.New(context.GlobalString("root"), nil)
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	container, err := factory.Load(context.Args().First())
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	stats, err := container.Stats()
-	if err != nil {
-		log.Fatal(err)
-	}
-	data, jerr := json.MarshalIndent(stats, "", "\t")
-	if err != nil {
-		log.Fatal(jerr)
-	}
-
-	fmt.Printf("%s", data)
+	Name:  "stats",
+	Usage: "display statistics for the container",
+	Flags: []cli.Flag{
+		cli.StringFlag{Name: "id", Value: "nsinit", Usage: "specify the ID for a container"},
+	},
+	Action: func(context *cli.Context) {
+		container, err := getContainer(context)
+		if err != nil {
+			log.Fatal(err)
+		}
+		stats, err := container.Stats()
+		if err != nil {
+			log.Fatal(err)
+		}
+		data, jerr := json.MarshalIndent(stats, "", "\t")
+		if err != nil {
+			log.Fatal(jerr)
+		}
+		fmt.Printf("%s", data)
+	},
 }

nsinit/utils.go

@@ -2,89 +2,52 @@ package main
 
 import (
 	"encoding/json"
-	"log"
+	"fmt"
 	"os"
-	"path/filepath"
 
 	"github.com/codegangsta/cli"
+	"github.com/docker/libcontainer"
 	"github.com/docker/libcontainer/configs"
 )
 
-// rFunc is a function registration for calling after an execin
-type rFunc struct {
-	Usage  string
-	Action func(*configs.Config, []string)
-}
-
-func loadConfig() (*configs.Config, error) {
-	f, err := os.Open(filepath.Join(dataPath, "container.json"))
+func loadConfig(context *cli.Context) (*configs.Config, error) {
+	f, err := os.Open(context.String("config"))
 	if err != nil {
 		return nil, err
 	}
 	defer f.Close()
-
-	var container *configs.Config
-	if err := json.NewDecoder(f).Decode(&container); err != nil {
-		return nil, err
-	}
-
-	return container, nil
-}
-
-func openLog(name string) error {
-	f, err := os.OpenFile(name, os.O_CREATE|os.O_RDWR|os.O_APPEND, 0755)
-	if err != nil {
-		return err
-	}
-
-	log.SetOutput(f)
-
-	return nil
-}
-
-func findUserArgs() []string {
-	i := 0
-	for _, a := range os.Args {
-		i++
-
-		if a == "--" {
-			break
-		}
-	}
-
-	return os.Args[i:]
-}
-
-// loadConfigFromFd loads a container's config from the sync pipe that is provided by
-// fd 3 when running a process
-func loadConfigFromFd() (*configs.Config, error) {
-	pipe := os.NewFile(3, "pipe")
-	defer pipe.Close()
-
 	var config *configs.Config
-	if err := json.NewDecoder(pipe).Decode(&config); err != nil {
+	if err := json.NewDecoder(f).Decode(&config); err != nil {
 		return nil, err
 	}
 	return config, nil
 }
 
-func preload(context *cli.Context) error {
-	if logPath != "" {
-		if err := openLog(logPath); err != nil {
-			return err
-		}
-	}
-
-	return nil
+func loadFactory(context *cli.Context) (libcontainer.Factory, error) {
+	return libcontainer.New(context.GlobalString("root"), []string{os.Args[0], "init", "--fd", "3", "--"})
 }
 
-func runFunc(f *rFunc) {
-	userArgs := findUserArgs()
-
-	config, err := loadConfigFromFd()
+func getContainer(context *cli.Context) (libcontainer.Container, error) {
+	factory, err := loadFactory(context)
 	if err != nil {
-		log.Fatalf("unable to receive config from sync pipe: %s", err)
+		return nil, err
 	}
-
-	f.Action(config, userArgs)
+	container, err := factory.Load(context.String("id"))
+	if err != nil {
+		return nil, err
+	}
+	return container, nil
+}
+
+func fatal(err error) {
+	if lerr, ok := err.(libcontainer.Error); ok {
+		lerr.Detail(os.Stderr)
+		os.Exit(1)
+	}
+	fmt.Fprintln(os.Stderr, err)
+}
+
+func fatalf(t string, v ...interface{}) {
+	fmt.Fprintf(os.Stderr, t, v...)
+	os.Exit(1)
 }

process.go

@@ -3,13 +3,9 @@ package libcontainer
 import "io"
 
 // Configuration for a process to be run inside a container.
-type ProcessConfig struct {
+type Process struct {
 	// The command to be run followed by any arguments.
 	Args []string
-
-	// Map of environment variables to their values.
-	Env []string
-
 	// Stdin is a pointer to a reader which provides the standard input stream.
 	// Stdout is a pointer to a writer which receives the standard output stream.
 	// Stderr is a pointer to a writer which receives the standard error stream.
@@ -21,7 +17,4 @@ type ProcessConfig struct {
 	Stdin  io.Reader
 	Stdout io.Writer
 	Stderr io.Writer
-
-	// Console is the path to the pty slave for use by the master
-	Console string
 }

sample_configs/apparmor.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -118,57 +118,55 @@
     },
     "restrict_sys": true,
     "apparmor_profile": "docker-default",
-    "mount_config": {
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/attach_to_bridge.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -117,57 +117,55 @@
         "parent": "docker"
     },
     "restrict_sys": true,
-    "mount_config": {
-        "device_nodes": [
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
-                "path": "/dev/null",
-                "type": 99
-            },
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
-                "path": "/dev/zero",
-                "type": 99
-            },
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
-                "path": "/dev/full",
-                "type": 99
-            },
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 5,
-                "path": "/dev/tty",
-                "type": 99
-            },
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
-                "path": "/dev/urandom",
-                "type": 99
-            },
-            {
-                "cgroup_permissions": "rwm",
-                "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
-                "path": "/dev/random",
-                "type": 99
-            }
-        ]
-    },
+    "device_nodes": [
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 1,
+            "minor": 3,
+            "path": "/dev/null",
+            "type": 99
+        },
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 1,
+            "minor": 5,
+            "path": "/dev/zero",
+            "type": 99
+        },
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 1,
+            "minor": 7,
+            "path": "/dev/full",
+            "type": 99
+        },
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 5,
+            "path": "/dev/tty",
+            "type": 99
+        },
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 1,
+            "minor": 9,
+            "path": "/dev/urandom",
+            "type": 99
+        },
+        {
+            "permissions": "rwm",
+            "file_mode": 438,
+            "major": 1,
+            "minor": 8,
+            "path": "/dev/random",
+            "type": 99
+        }
+    ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/host-pid.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -117,52 +117,51 @@
         "parent": "docker"
     },
     "restrict_sys": true,
-    "mount_config": {
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -172,8 +171,7 @@
                 "type": "tmpfs",
                 "destination": "/tmp"
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/minimal.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -117,52 +117,51 @@
         "parent": "docker"
     },
     "restrict_sys": true,
-    "mount_config": {
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -172,8 +171,7 @@
                 "type": "tmpfs",
                 "destination": "/tmp"
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/route_source_address_selection.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -117,57 +117,55 @@
         "parent": "docker"
     },
     "restrict_sys": true,
-    "mount_config": {
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/selinux.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -118,58 +118,56 @@
     },
     "restrict_sys": true,
     "process_label": "system_u:system_r:svirt_lxc_net_t:s0:c164,c475",
-    "mount_config": {
         "mount_label": "system_u:system_r:svirt_lxc_net_t:s0:c164,c475",
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

sample_configs/userns.json

@@ -16,99 +16,99 @@
     "cgroups": {
         "allowed_devices": [
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "m",
-                "major_number": -1,
-                "minor_number": -1,
+                "permissions": "m",
+                "major": -1,
+                "minor": -1,
                 "type": 98
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 1,
                 "path": "/dev/console",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
+                "permissions": "rwm",
+                "major": 4,
                 "path": "/dev/tty0",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 4,
-                "minor_number": 1,
+                "permissions": "rwm",
+                "major": 4,
+                "minor": 1,
                 "path": "/dev/tty1",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 136,
-                "minor_number": -1,
+                "permissions": "rwm",
+                "major": 136,
+                "minor": -1,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 5,
-                "minor_number": 2,
+                "permissions": "rwm",
+                "major": 5,
+                "minor": 2,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
-                "major_number": 10,
-                "minor_number": 200,
+                "permissions": "rwm",
+                "major": 10,
+                "minor": 200,
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -117,52 +117,51 @@
         "parent": "docker"
     },
     "restrict_sys": true,
-    "mount_config": {
         "device_nodes": [
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 3,
+                "major": 1,
+                "minor": 3,
                 "path": "/dev/null",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 5,
+                "major": 1,
+                "minor": 5,
                 "path": "/dev/zero",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 7,
+                "major": 1,
+                "minor": 7,
                 "path": "/dev/full",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 5,
+                "major": 5,
                 "path": "/dev/tty",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 9,
+                "major": 1,
+                "minor": 9,
                 "path": "/dev/urandom",
                 "type": 99
             },
             {
-                "cgroup_permissions": "rwm",
+                "permissions": "rwm",
                 "file_mode": 438,
-                "major_number": 1,
-                "minor_number": 8,
+                "major": 1,
+                "minor": 8,
                 "path": "/dev/random",
                 "type": 99
             }
@@ -172,8 +171,7 @@
                 "type": "tmpfs",
                 "destination": "/tmp"
             }
-        ]
-    },
+        ],
     "environment": [
         "HOME=/",
         "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",

types.go

@@ -1,11 +0,0 @@
-package libcontainer
-
-import (
-	"github.com/docker/libcontainer/cgroups"
-	"github.com/docker/libcontainer/network"
-)
-
-type ContainerStats struct {
-	NetworkStats *network.NetworkStats `json:"network_stats,omitempty"`
-	CgroupStats  *cgroups.Stats        `json:"cgroup_stats,omitempty"`
-}