Updated vendor for exported BuildArgs

vendor/github.com/opencontainers/runc/libcontainer/cgroups/cgroups.go

@@ -0,0 +1,64 @@
+// +build linux
+
+package cgroups
+
+import (
+	"fmt"
+
+	"github.com/opencontainers/runc/libcontainer/configs"
+)
+
+type Manager interface {
+	// Applies cgroup configuration to the process with the specified pid
+	Apply(pid int) error
+
+	// Returns the PIDs inside the cgroup set
+	GetPids() ([]int, error)
+
+	// Returns the PIDs inside the cgroup set & all sub-cgroups
+	GetAllPids() ([]int, error)
+
+	// Returns statistics for the cgroup set
+	GetStats() (*Stats, error)
+
+	// Toggles the freezer cgroup according with specified state
+	Freeze(state configs.FreezerState) error
+
+	// Destroys the cgroup set
+	Destroy() error
+
+	// The option func SystemdCgroups() and Cgroupfs() require following attributes:
+	// 	Paths   map[string]string
+	// 	Cgroups *configs.Cgroup
+	// Paths maps cgroup subsystem to path at which it is mounted.
+	// Cgroups specifies specific cgroup settings for the various subsystems
+
+	// Returns cgroup paths to save in a state file and to be able to
+	// restore the object later.
+	GetPaths() map[string]string
+
+	// Sets the cgroup as configured.
+	Set(container *configs.Config) error
+}
+
+type NotFoundError struct {
+	Subsystem string
+}
+
+func (e *NotFoundError) Error() string {
+	return fmt.Sprintf("mountpoint for %s not found", e.Subsystem)
+}
+
+func NewNotFoundError(sub string) error {
+	return &NotFoundError{
+		Subsystem: sub,
+	}
+}
+
+func IsNotFound(err error) bool {
+	if err == nil {
+		return false
+	}
+	_, ok := err.(*NotFoundError)
+	return ok
+}

vendor/github.com/opencontainers/runc/libcontainer/cgroups/cgroups_unsupported.go

@@ -0,0 +1,3 @@
+// +build !linux
+
+package cgroups

vendor/github.com/opencontainers/runc/libcontainer/cgroups/stats.go

@@ -0,0 +1,108 @@
+// +build linux
+
+package cgroups
+
+type ThrottlingData struct {
+	// Number of periods with throttling active
+	Periods uint64 `json:"periods,omitempty"`
+	// Number of periods when the container hit its throttling limit.
+	ThrottledPeriods uint64 `json:"throttled_periods,omitempty"`
+	// Aggregate time the container was throttled for in nanoseconds.
+	ThrottledTime uint64 `json:"throttled_time,omitempty"`
+}
+
+// CpuUsage denotes the usage of a CPU.
+// All CPU stats are aggregate since container inception.
+type CpuUsage struct {
+	// Total CPU time consumed.
+	// Units: nanoseconds.
+	TotalUsage uint64 `json:"total_usage,omitempty"`
+	// Total CPU time consumed per core.
+	// Units: nanoseconds.
+	PercpuUsage []uint64 `json:"percpu_usage,omitempty"`
+	// Time spent by tasks of the cgroup in kernel mode.
+	// Units: nanoseconds.
+	UsageInKernelmode uint64 `json:"usage_in_kernelmode"`
+	// Time spent by tasks of the cgroup in user mode.
+	// Units: nanoseconds.
+	UsageInUsermode uint64 `json:"usage_in_usermode"`
+}
+
+type CpuStats struct {
+	CpuUsage       CpuUsage       `json:"cpu_usage,omitempty"`
+	ThrottlingData ThrottlingData `json:"throttling_data,omitempty"`
+}
+
+type MemoryData struct {
+	Usage    uint64 `json:"usage,omitempty"`
+	MaxUsage uint64 `json:"max_usage,omitempty"`
+	Failcnt  uint64 `json:"failcnt"`
+	Limit    uint64 `json:"limit"`
+}
+
+type MemoryStats struct {
+	// memory used for cache
+	Cache uint64 `json:"cache,omitempty"`
+	// usage of memory
+	Usage MemoryData `json:"usage,omitempty"`
+	// usage of memory + swap
+	SwapUsage MemoryData `json:"swap_usage,omitempty"`
+	// usage of kernel memory
+	KernelUsage MemoryData `json:"kernel_usage,omitempty"`
+	// usage of kernel TCP memory
+	KernelTCPUsage MemoryData `json:"kernel_tcp_usage,omitempty"`
+	// if true, memory usage is accounted for throughout a hierarchy of cgroups.
+	UseHierarchy bool `json:"use_hierarchy"`
+
+	Stats map[string]uint64 `json:"stats,omitempty"`
+}
+
+type PidsStats struct {
+	// number of pids in the cgroup
+	Current uint64 `json:"current,omitempty"`
+	// active pids hard limit
+	Limit uint64 `json:"limit,omitempty"`
+}
+
+type BlkioStatEntry struct {
+	Major uint64 `json:"major,omitempty"`
+	Minor uint64 `json:"minor,omitempty"`
+	Op    string `json:"op,omitempty"`
+	Value uint64 `json:"value,omitempty"`
+}
+
+type BlkioStats struct {
+	// number of bytes tranferred to and from the block device
+	IoServiceBytesRecursive []BlkioStatEntry `json:"io_service_bytes_recursive,omitempty"`
+	IoServicedRecursive     []BlkioStatEntry `json:"io_serviced_recursive,omitempty"`
+	IoQueuedRecursive       []BlkioStatEntry `json:"io_queue_recursive,omitempty"`
+	IoServiceTimeRecursive  []BlkioStatEntry `json:"io_service_time_recursive,omitempty"`
+	IoWaitTimeRecursive     []BlkioStatEntry `json:"io_wait_time_recursive,omitempty"`
+	IoMergedRecursive       []BlkioStatEntry `json:"io_merged_recursive,omitempty"`
+	IoTimeRecursive         []BlkioStatEntry `json:"io_time_recursive,omitempty"`
+	SectorsRecursive        []BlkioStatEntry `json:"sectors_recursive,omitempty"`
+}
+
+type HugetlbStats struct {
+	// current res_counter usage for hugetlb
+	Usage uint64 `json:"usage,omitempty"`
+	// maximum usage ever recorded.
+	MaxUsage uint64 `json:"max_usage,omitempty"`
+	// number of times hugetlb usage allocation failure.
+	Failcnt uint64 `json:"failcnt"`
+}
+
+type Stats struct {
+	CpuStats    CpuStats    `json:"cpu_stats,omitempty"`
+	MemoryStats MemoryStats `json:"memory_stats,omitempty"`
+	PidsStats   PidsStats   `json:"pids_stats,omitempty"`
+	BlkioStats  BlkioStats  `json:"blkio_stats,omitempty"`
+	// the map is in the format "size of hugepage: stats of the hugepage"
+	HugetlbStats map[string]HugetlbStats `json:"hugetlb_stats,omitempty"`
+}
+
+func NewStats() *Stats {
+	memoryStats := MemoryStats{Stats: make(map[string]uint64)}
+	hugetlbStats := make(map[string]HugetlbStats)
+	return &Stats{MemoryStats: memoryStats, HugetlbStats: hugetlbStats}
+}

vendor/github.com/opencontainers/runc/libcontainer/cgroups/utils.go

@@ -0,0 +1,462 @@
+// +build linux
+
+package cgroups
+
+import (
+	"bufio"
+	"fmt"
+	"io"
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/docker/go-units"
+)
+
+const (
+	cgroupNamePrefix = "name="
+	CgroupProcesses  = "cgroup.procs"
+)
+
+// https://www.kernel.org/doc/Documentation/cgroup-v1/cgroups.txt
+func FindCgroupMountpoint(subsystem string) (string, error) {
+	mnt, _, err := FindCgroupMountpointAndRoot(subsystem)
+	return mnt, err
+}
+
+func FindCgroupMountpointAndRoot(subsystem string) (string, string, error) {
+	// We are not using mount.GetMounts() because it's super-inefficient,
+	// parsing it directly sped up x10 times because of not using Sscanf.
+	// It was one of two major performance drawbacks in container start.
+	if !isSubsystemAvailable(subsystem) {
+		return "", "", NewNotFoundError(subsystem)
+	}
+	f, err := os.Open("/proc/self/mountinfo")
+	if err != nil {
+		return "", "", err
+	}
+	defer f.Close()
+
+	scanner := bufio.NewScanner(f)
+	for scanner.Scan() {
+		txt := scanner.Text()
+		fields := strings.Split(txt, " ")
+		for _, opt := range strings.Split(fields[len(fields)-1], ",") {
+			if opt == subsystem {
+				return fields[4], fields[3], nil
+			}
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		return "", "", err
+	}
+
+	return "", "", NewNotFoundError(subsystem)
+}
+
+func isSubsystemAvailable(subsystem string) bool {
+	cgroups, err := ParseCgroupFile("/proc/self/cgroup")
+	if err != nil {
+		return false
+	}
+	_, avail := cgroups[subsystem]
+	return avail
+}
+
+func GetClosestMountpointAncestor(dir, mountinfo string) string {
+	deepestMountPoint := ""
+	for _, mountInfoEntry := range strings.Split(mountinfo, "\n") {
+		mountInfoParts := strings.Fields(mountInfoEntry)
+		if len(mountInfoParts) < 5 {
+			continue
+		}
+		mountPoint := mountInfoParts[4]
+		if strings.HasPrefix(mountPoint, deepestMountPoint) && strings.HasPrefix(dir, mountPoint) {
+			deepestMountPoint = mountPoint
+		}
+	}
+	return deepestMountPoint
+}
+
+func FindCgroupMountpointDir() (string, error) {
+	f, err := os.Open("/proc/self/mountinfo")
+	if err != nil {
+		return "", err
+	}
+	defer f.Close()
+
+	scanner := bufio.NewScanner(f)
+	for scanner.Scan() {
+		text := scanner.Text()
+		fields := strings.Split(text, " ")
+		// Safe as mountinfo encodes mountpoints with spaces as \040.
+		index := strings.Index(text, " - ")
+		postSeparatorFields := strings.Fields(text[index+3:])
+		numPostFields := len(postSeparatorFields)
+
+		// This is an error as we can't detect if the mount is for "cgroup"
+		if numPostFields == 0 {
+			return "", fmt.Errorf("Found no fields post '-' in %q", text)
+		}
+
+		if postSeparatorFields[0] == "cgroup" {
+			// Check that the mount is properly formated.
+			if numPostFields < 3 {
+				return "", fmt.Errorf("Error found less than 3 fields post '-' in %q", text)
+			}
+
+			return filepath.Dir(fields[4]), nil
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		return "", err
+	}
+
+	return "", NewNotFoundError("cgroup")
+}
+
+type Mount struct {
+	Mountpoint string
+	Root       string
+	Subsystems []string
+}
+
+func (m Mount) GetOwnCgroup(cgroups map[string]string) (string, error) {
+	if len(m.Subsystems) == 0 {
+		return "", fmt.Errorf("no subsystem for mount")
+	}
+
+	return getControllerPath(m.Subsystems[0], cgroups)
+}
+
+func getCgroupMountsHelper(ss map[string]bool, mi io.Reader, all bool) ([]Mount, error) {
+	res := make([]Mount, 0, len(ss))
+	scanner := bufio.NewScanner(mi)
+	numFound := 0
+	for scanner.Scan() && numFound < len(ss) {
+		txt := scanner.Text()
+		sepIdx := strings.Index(txt, " - ")
+		if sepIdx == -1 {
+			return nil, fmt.Errorf("invalid mountinfo format")
+		}
+		if txt[sepIdx+3:sepIdx+10] == "cgroup2" || txt[sepIdx+3:sepIdx+9] != "cgroup" {
+			continue
+		}
+		fields := strings.Split(txt, " ")
+		m := Mount{
+			Mountpoint: fields[4],
+			Root:       fields[3],
+		}
+		for _, opt := range strings.Split(fields[len(fields)-1], ",") {
+			if !ss[opt] {
+				continue
+			}
+			if strings.HasPrefix(opt, cgroupNamePrefix) {
+				m.Subsystems = append(m.Subsystems, opt[len(cgroupNamePrefix):])
+			} else {
+				m.Subsystems = append(m.Subsystems, opt)
+			}
+			if !all {
+				numFound++
+			}
+		}
+		res = append(res, m)
+	}
+	if err := scanner.Err(); err != nil {
+		return nil, err
+	}
+	return res, nil
+}
+
+// GetCgroupMounts returns the mounts for the cgroup subsystems.
+// all indicates whether to return just the first instance or all the mounts.
+func GetCgroupMounts(all bool) ([]Mount, error) {
+	f, err := os.Open("/proc/self/mountinfo")
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	allSubsystems, err := ParseCgroupFile("/proc/self/cgroup")
+	if err != nil {
+		return nil, err
+	}
+
+	allMap := make(map[string]bool)
+	for s := range allSubsystems {
+		allMap[s] = true
+	}
+	return getCgroupMountsHelper(allMap, f, all)
+}
+
+// GetAllSubsystems returns all the cgroup subsystems supported by the kernel
+func GetAllSubsystems() ([]string, error) {
+	f, err := os.Open("/proc/cgroups")
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	subsystems := []string{}
+
+	s := bufio.NewScanner(f)
+	for s.Scan() {
+		text := s.Text()
+		if text[0] != '#' {
+			parts := strings.Fields(text)
+			if len(parts) >= 4 && parts[3] != "0" {
+				subsystems = append(subsystems, parts[0])
+			}
+		}
+	}
+	if err := s.Err(); err != nil {
+		return nil, err
+	}
+	return subsystems, nil
+}
+
+// GetOwnCgroup returns the relative path to the cgroup docker is running in.
+func GetOwnCgroup(subsystem string) (string, error) {
+	cgroups, err := ParseCgroupFile("/proc/self/cgroup")
+	if err != nil {
+		return "", err
+	}
+
+	return getControllerPath(subsystem, cgroups)
+}
+
+func GetOwnCgroupPath(subsystem string) (string, error) {
+	cgroup, err := GetOwnCgroup(subsystem)
+	if err != nil {
+		return "", err
+	}
+
+	return getCgroupPathHelper(subsystem, cgroup)
+}
+
+func GetInitCgroup(subsystem string) (string, error) {
+	cgroups, err := ParseCgroupFile("/proc/1/cgroup")
+	if err != nil {
+		return "", err
+	}
+
+	return getControllerPath(subsystem, cgroups)
+}
+
+func GetInitCgroupPath(subsystem string) (string, error) {
+	cgroup, err := GetInitCgroup(subsystem)
+	if err != nil {
+		return "", err
+	}
+
+	return getCgroupPathHelper(subsystem, cgroup)
+}
+
+func getCgroupPathHelper(subsystem, cgroup string) (string, error) {
+	mnt, root, err := FindCgroupMountpointAndRoot(subsystem)
+	if err != nil {
+		return "", err
+	}
+
+	// This is needed for nested containers, because in /proc/self/cgroup we
+	// see pathes from host, which don't exist in container.
+	relCgroup, err := filepath.Rel(root, cgroup)
+	if err != nil {
+		return "", err
+	}
+
+	return filepath.Join(mnt, relCgroup), nil
+}
+
+func readProcsFile(dir string) ([]int, error) {
+	f, err := os.Open(filepath.Join(dir, CgroupProcesses))
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	var (
+		s   = bufio.NewScanner(f)
+		out = []int{}
+	)
+
+	for s.Scan() {
+		if t := s.Text(); t != "" {
+			pid, err := strconv.Atoi(t)
+			if err != nil {
+				return nil, err
+			}
+			out = append(out, pid)
+		}
+	}
+	return out, nil
+}
+
+// ParseCgroupFile parses the given cgroup file, typically from
+// /proc/<pid>/cgroup, into a map of subgroups to cgroup names.
+func ParseCgroupFile(path string) (map[string]string, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	return parseCgroupFromReader(f)
+}
+
+// helper function for ParseCgroupFile to make testing easier
+func parseCgroupFromReader(r io.Reader) (map[string]string, error) {
+	s := bufio.NewScanner(r)
+	cgroups := make(map[string]string)
+
+	for s.Scan() {
+		text := s.Text()
+		// from cgroups(7):
+		// /proc/[pid]/cgroup
+		// ...
+		// For each cgroup hierarchy ... there is one entry
+		// containing three colon-separated fields of the form:
+		//     hierarchy-ID:subsystem-list:cgroup-path
+		parts := strings.SplitN(text, ":", 3)
+		if len(parts) < 3 {
+			return nil, fmt.Errorf("invalid cgroup entry: must contain at least two colons: %v", text)
+		}
+
+		for _, subs := range strings.Split(parts[1], ",") {
+			cgroups[subs] = parts[2]
+		}
+	}
+	if err := s.Err(); err != nil {
+		return nil, err
+	}
+
+	return cgroups, nil
+}
+
+func getControllerPath(subsystem string, cgroups map[string]string) (string, error) {
+
+	if p, ok := cgroups[subsystem]; ok {
+		return p, nil
+	}
+
+	if p, ok := cgroups[cgroupNamePrefix+subsystem]; ok {
+		return p, nil
+	}
+
+	return "", NewNotFoundError(subsystem)
+}
+
+func PathExists(path string) bool {
+	if _, err := os.Stat(path); err != nil {
+		return false
+	}
+	return true
+}
+
+func EnterPid(cgroupPaths map[string]string, pid int) error {
+	for _, path := range cgroupPaths {
+		if PathExists(path) {
+			if err := WriteCgroupProc(path, pid); err != nil {
+				return err
+			}
+		}
+	}
+	return nil
+}
+
+// RemovePaths iterates over the provided paths removing them.
+// We trying to remove all paths five times with increasing delay between tries.
+// If after all there are not removed cgroups - appropriate error will be
+// returned.
+func RemovePaths(paths map[string]string) (err error) {
+	delay := 10 * time.Millisecond
+	for i := 0; i < 5; i++ {
+		if i != 0 {
+			time.Sleep(delay)
+			delay *= 2
+		}
+		for s, p := range paths {
+			os.RemoveAll(p)
+			// TODO: here probably should be logging
+			_, err := os.Stat(p)
+			// We need this strange way of checking cgroups existence because
+			// RemoveAll almost always returns error, even on already removed
+			// cgroups
+			if os.IsNotExist(err) {
+				delete(paths, s)
+			}
+		}
+		if len(paths) == 0 {
+			return nil
+		}
+	}
+	return fmt.Errorf("Failed to remove paths: %v", paths)
+}
+
+func GetHugePageSize() ([]string, error) {
+	var pageSizes []string
+	sizeList := []string{"B", "kB", "MB", "GB", "TB", "PB"}
+	files, err := ioutil.ReadDir("/sys/kernel/mm/hugepages")
+	if err != nil {
+		return pageSizes, err
+	}
+	for _, st := range files {
+		nameArray := strings.Split(st.Name(), "-")
+		pageSize, err := units.RAMInBytes(nameArray[1])
+		if err != nil {
+			return []string{}, err
+		}
+		sizeString := units.CustomSize("%g%s", float64(pageSize), 1024.0, sizeList)
+		pageSizes = append(pageSizes, sizeString)
+	}
+
+	return pageSizes, nil
+}
+
+// GetPids returns all pids, that were added to cgroup at path.
+func GetPids(path string) ([]int, error) {
+	return readProcsFile(path)
+}
+
+// GetAllPids returns all pids, that were added to cgroup at path and to all its
+// subcgroups.
+func GetAllPids(path string) ([]int, error) {
+	var pids []int
+	// collect pids from all sub-cgroups
+	err := filepath.Walk(path, func(p string, info os.FileInfo, iErr error) error {
+		dir, file := filepath.Split(p)
+		if file != CgroupProcesses {
+			return nil
+		}
+		if iErr != nil {
+			return iErr
+		}
+		cPids, err := readProcsFile(dir)
+		if err != nil {
+			return err
+		}
+		pids = append(pids, cPids...)
+		return nil
+	})
+	return pids, err
+}
+
+// WriteCgroupProc writes the specified pid into the cgroup's cgroup.procs file
+func WriteCgroupProc(dir string, pid int) error {
+	// Normally dir should not be empty, one case is that cgroup subsystem
+	// is not mounted, we will get empty dir, and we want it fail here.
+	if dir == "" {
+		return fmt.Errorf("no such directory for %s", CgroupProcesses)
+	}
+
+	// Dont attach any pid to the cgroup if -1 is specified as a pid
+	if pid != -1 {
+		if err := ioutil.WriteFile(filepath.Join(dir, CgroupProcesses), []byte(strconv.Itoa(pid)), 0700); err != nil {
+			return fmt.Errorf("failed to write %v to %v: %v", pid, CgroupProcesses, err)
+		}
+	}
+	return nil
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/blkio_device.go

@@ -0,0 +1,61 @@
+package configs
+
+import "fmt"
+
+// blockIODevice holds major:minor format supported in blkio cgroup
+type blockIODevice struct {
+	// Major is the device's major number
+	Major int64 `json:"major"`
+	// Minor is the device's minor number
+	Minor int64 `json:"minor"`
+}
+
+// WeightDevice struct holds a `major:minor weight`|`major:minor leaf_weight` pair
+type WeightDevice struct {
+	blockIODevice
+	// Weight is the bandwidth rate for the device, range is from 10 to 1000
+	Weight uint16 `json:"weight"`
+	// LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, range is from 10 to 1000, cfq scheduler only
+	LeafWeight uint16 `json:"leafWeight"`
+}
+
+// NewWeightDevice returns a configured WeightDevice pointer
+func NewWeightDevice(major, minor int64, weight, leafWeight uint16) *WeightDevice {
+	wd := &WeightDevice{}
+	wd.Major = major
+	wd.Minor = minor
+	wd.Weight = weight
+	wd.LeafWeight = leafWeight
+	return wd
+}
+
+// WeightString formats the struct to be writable to the cgroup specific file
+func (wd *WeightDevice) WeightString() string {
+	return fmt.Sprintf("%d:%d %d", wd.Major, wd.Minor, wd.Weight)
+}
+
+// LeafWeightString formats the struct to be writable to the cgroup specific file
+func (wd *WeightDevice) LeafWeightString() string {
+	return fmt.Sprintf("%d:%d %d", wd.Major, wd.Minor, wd.LeafWeight)
+}
+
+// ThrottleDevice struct holds a `major:minor rate_per_second` pair
+type ThrottleDevice struct {
+	blockIODevice
+	// Rate is the IO rate limit per cgroup per device
+	Rate uint64 `json:"rate"`
+}
+
+// NewThrottleDevice returns a configured ThrottleDevice pointer
+func NewThrottleDevice(major, minor int64, rate uint64) *ThrottleDevice {
+	td := &ThrottleDevice{}
+	td.Major = major
+	td.Minor = minor
+	td.Rate = rate
+	return td
+}
+
+// String formats the struct to be writable to the cgroup specific file
+func (td *ThrottleDevice) String() string {
+	return fmt.Sprintf("%d:%d %d", td.Major, td.Minor, td.Rate)
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/cgroup_linux.go

@@ -0,0 +1,122 @@
+package configs
+
+type FreezerState string
+
+const (
+	Undefined FreezerState = ""
+	Frozen    FreezerState = "FROZEN"
+	Thawed    FreezerState = "THAWED"
+)
+
+type Cgroup struct {
+	// Deprecated, use Path instead
+	Name string `json:"name,omitempty"`
+
+	// name of parent of cgroup or slice
+	// Deprecated, use Path instead
+	Parent string `json:"parent,omitempty"`
+
+	// Path specifies the path to cgroups that are created and/or joined by the container.
+	// The path is assumed to be relative to the host system cgroup mountpoint.
+	Path string `json:"path"`
+
+	// ScopePrefix describes prefix for the scope name
+	ScopePrefix string `json:"scope_prefix"`
+
+	// Paths represent the absolute cgroups paths to join.
+	// This takes precedence over Path.
+	Paths map[string]string
+
+	// Resources contains various cgroups settings to apply
+	*Resources
+}
+
+type Resources struct {
+	// 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.
+	// Deprecated
+	AllowAllDevices *bool `json:"allow_all_devices,omitempty"`
+	// Deprecated
+	AllowedDevices []*Device `json:"allowed_devices,omitempty"`
+	// Deprecated
+	DeniedDevices []*Device `json:"denied_devices,omitempty"`
+
+	Devices []*Device `json:"devices"`
+
+	// Memory limit (in bytes)
+	Memory int64 `json:"memory"`
+
+	// Memory reservation or soft_limit (in bytes)
+	MemoryReservation int64 `json:"memory_reservation"`
+
+	// Total memory usage (memory + swap); set `-1` to enable unlimited swap
+	MemorySwap int64 `json:"memory_swap"`
+
+	// Kernel memory limit (in bytes)
+	KernelMemory int64 `json:"kernel_memory"`
+
+	// Kernel memory limit for TCP use (in bytes)
+	KernelMemoryTCP int64 `json:"kernel_memory_tcp"`
+
+	// CPU shares (relative weight vs. other containers)
+	CpuShares uint64 `json:"cpu_shares"`
+
+	// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
+	CpuQuota int64 `json:"cpu_quota"`
+
+	// CPU period to be used for hardcapping (in usecs). 0 to use system default.
+	CpuPeriod uint64 `json:"cpu_period"`
+
+	// How many time CPU will use in realtime scheduling (in usecs).
+	CpuRtRuntime int64 `json:"cpu_rt_quota"`
+
+	// CPU period to be used for realtime scheduling (in usecs).
+	CpuRtPeriod uint64 `json:"cpu_rt_period"`
+
+	// CPU to use
+	CpusetCpus string `json:"cpuset_cpus"`
+
+	// MEM to use
+	CpusetMems string `json:"cpuset_mems"`
+
+	// Process limit; set <= `0' to disable limit.
+	PidsLimit int64 `json:"pids_limit"`
+
+	// Specifies per cgroup weight, range is from 10 to 1000.
+	BlkioWeight uint16 `json:"blkio_weight"`
+
+	// Specifies tasks' weight in the given cgroup while competing with the cgroup's child cgroups, range is from 10 to 1000, cfq scheduler only
+	BlkioLeafWeight uint16 `json:"blkio_leaf_weight"`
+
+	// Weight per cgroup per device, can override BlkioWeight.
+	BlkioWeightDevice []*WeightDevice `json:"blkio_weight_device"`
+
+	// IO read rate limit per cgroup per device, bytes per second.
+	BlkioThrottleReadBpsDevice []*ThrottleDevice `json:"blkio_throttle_read_bps_device"`
+
+	// IO write rate limit per cgroup per device, bytes per second.
+	BlkioThrottleWriteBpsDevice []*ThrottleDevice `json:"blkio_throttle_write_bps_device"`
+
+	// IO read rate limit per cgroup per device, IO per second.
+	BlkioThrottleReadIOPSDevice []*ThrottleDevice `json:"blkio_throttle_read_iops_device"`
+
+	// IO write rate limit per cgroup per device, IO per second.
+	BlkioThrottleWriteIOPSDevice []*ThrottleDevice `json:"blkio_throttle_write_iops_device"`
+
+	// set the freeze value for the process
+	Freezer FreezerState `json:"freezer"`
+
+	// Hugetlb limit (in bytes)
+	HugetlbLimit []*HugepageLimit `json:"hugetlb_limit"`
+
+	// Whether to disable OOM Killer
+	OomKillDisable bool `json:"oom_kill_disable"`
+
+	// Tuning swappiness behaviour per cgroup
+	MemorySwappiness *uint64 `json:"memory_swappiness"`
+
+	// Set priority of network traffic for container
+	NetPrioIfpriomap []*IfPrioMap `json:"net_prio_ifpriomap"`
+
+	// Set class identifier for container's network packets
+	NetClsClassid uint32 `json:"net_cls_classid_u"`
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/cgroup_windows.go

@@ -0,0 +1,6 @@
+package configs
+
+// TODO Windows: This can ultimately be entirely factored out on Windows as
+// cgroups are a Unix-specific construct.
+type Cgroup struct {
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/config.go

@@ -0,0 +1,348 @@
+package configs
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"os/exec"
+	"time"
+
+	"github.com/opencontainers/runtime-spec/specs-go"
+
+	"github.com/sirupsen/logrus"
+)
+
+type Rlimit struct {
+	Type int    `json:"type"`
+	Hard uint64 `json:"hard"`
+	Soft uint64 `json:"soft"`
+}
+
+// IDMap represents UID/GID Mappings for User Namespaces.
+type IDMap struct {
+	ContainerID int `json:"container_id"`
+	HostID      int `json:"host_id"`
+	Size        int `json:"size"`
+}
+
+// Seccomp represents syscall restrictions
+// By default, only the native architecture of the kernel is allowed to be used
+// for syscalls. Additional architectures can be added by specifying them in
+// Architectures.
+type Seccomp struct {
+	DefaultAction Action     `json:"default_action"`
+	Architectures []string   `json:"architectures"`
+	Syscalls      []*Syscall `json:"syscalls"`
+}
+
+// Action is taken upon rule match in Seccomp
+type Action int
+
+const (
+	Kill Action = iota + 1
+	Errno
+	Trap
+	Allow
+	Trace
+)
+
+// Operator is a comparison operator to be used when matching syscall arguments in Seccomp
+type Operator int
+
+const (
+	EqualTo Operator = iota + 1
+	NotEqualTo
+	GreaterThan
+	GreaterThanOrEqualTo
+	LessThan
+	LessThanOrEqualTo
+	MaskEqualTo
+)
+
+// Arg is a rule to match a specific syscall argument in Seccomp
+type Arg struct {
+	Index    uint     `json:"index"`
+	Value    uint64   `json:"value"`
+	ValueTwo uint64   `json:"value_two"`
+	Op       Operator `json:"op"`
+}
+
+// Syscall is a rule to match a syscall in Seccomp
+type Syscall struct {
+	Name   string `json:"name"`
+	Action Action `json:"action"`
+	Args   []*Arg `json:"args"`
+}
+
+// TODO Windows. Many of these fields should be factored out into those parts
+// which are common across platforms, and those which are platform specific.
+
+// Config defines configuration options for executing a process inside a contained environment.
+type Config 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"`
+
+	// ParentDeathSignal specifies the signal that is sent to the container's process in the case
+	// that the parent process dies.
+	ParentDeathSignal int `json:"parent_death_signal"`
+
+	// Path to a directory containing the container's root filesystem.
+	Rootfs string `json:"rootfs"`
+
+	// Readonlyfs will remount the container's rootfs as readonly where only externally mounted
+	// bind mounts are writtable.
+	Readonlyfs bool `json:"readonlyfs"`
+
+	// Specifies the mount propagation flags to be applied to /.
+	RootPropagation int `json:"rootPropagation"`
+
+	// 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"`
+
+	// 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!
+	Devices []*Device `json:"devices"`
+
+	MountLabel string `json:"mount_label"`
+
+	// Hostname optionally sets the container's hostname if provided
+	Hostname string `json:"hostname"`
+
+	// 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
+	Namespaces Namespaces `json:"namespaces"`
+
+	// Capabilities specify the capabilities to keep when executing the process inside the container
+	// All capabilities not specified will be dropped from the processes capability mask
+	Capabilities *Capabilities `json:"capabilities"`
+
+	// Networks specifies the container's network setup to be created
+	Networks []*Network `json:"networks"`
+
+	// Routes can be specified to create entries in the route table as the container is started
+	Routes []*Route `json:"routes"`
+
+	// Cgroups specifies specific cgroup settings for the various subsystems that the container is
+	// placed into to limit the resources the container has available
+	Cgroups *Cgroup `json:"cgroups"`
+
+	// AppArmorProfile specifies the profile to apply to the process running in the container and is
+	// change at the time the process is execed
+	AppArmorProfile string `json:"apparmor_profile,omitempty"`
+
+	// ProcessLabel specifies the label to apply to the process running in the container.  It is
+	// commonly used by selinux
+	ProcessLabel string `json:"process_label,omitempty"`
+
+	// Rlimits specifies the resource limits, such as max open files, to set in the container
+	// If Rlimits are not set, the container will inherit rlimits from the parent process
+	Rlimits []Rlimit `json:"rlimits,omitempty"`
+
+	// OomScoreAdj specifies the adjustment to be made by the kernel when calculating oom scores
+	// for a process. Valid values are between the range [-1000, '1000'], where processes with
+	// higher scores are preferred for being killed.
+	// More information about kernel oom score calculation here: https://lwn.net/Articles/317814/
+	OomScoreAdj int `json:"oom_score_adj"`
+
+	// UidMappings is an array of User ID mappings for User Namespaces
+	UidMappings []IDMap `json:"uid_mappings"`
+
+	// GidMappings is an array of Group ID mappings for User Namespaces
+	GidMappings []IDMap `json:"gid_mappings"`
+
+	// MaskPaths specifies paths within the container's rootfs to mask over with a bind
+	// mount pointing to /dev/null as to prevent reads of the file.
+	MaskPaths []string `json:"mask_paths"`
+
+	// ReadonlyPaths specifies paths within the container's rootfs to remount as read-only
+	// so that these files prevent any writes.
+	ReadonlyPaths []string `json:"readonly_paths"`
+
+	// Sysctl is a map of properties and their values. It is the equivalent of using
+	// sysctl -w my.property.name value in Linux.
+	Sysctl map[string]string `json:"sysctl"`
+
+	// Seccomp allows actions to be taken whenever a syscall is made within the container.
+	// A number of rules are given, each having an action to be taken if a syscall matches it.
+	// A default action to be taken if no rules match is also given.
+	Seccomp *Seccomp `json:"seccomp"`
+
+	// NoNewPrivileges controls whether processes in the container can gain additional privileges.
+	NoNewPrivileges bool `json:"no_new_privileges,omitempty"`
+
+	// Hooks are a collection of actions to perform at various container lifecycle events.
+	// CommandHooks are serialized to JSON, but other hooks are not.
+	Hooks *Hooks
+
+	// Version is the version of opencontainer specification that is supported.
+	Version string `json:"version"`
+
+	// Labels are user defined metadata that is stored in the config and populated on the state
+	Labels []string `json:"labels"`
+
+	// NoNewKeyring will not allocated a new session keyring for the container.  It will use the
+	// callers keyring in this case.
+	NoNewKeyring bool `json:"no_new_keyring"`
+
+	// Rootless specifies whether the container is a rootless container.
+	Rootless bool `json:"rootless"`
+
+	// IntelRdt specifies settings for Intel RDT/CAT group that the container is placed into
+	// to limit the resources (e.g., L3 cache) the container has available
+	IntelRdt *IntelRdt `json:"intel_rdt,omitempty"`
+}
+
+type Hooks struct {
+	// Prestart commands are executed after the container namespaces are created,
+	// but before the user supplied command is executed from init.
+	Prestart []Hook
+
+	// Poststart commands are executed after the container init process starts.
+	Poststart []Hook
+
+	// Poststop commands are executed after the container init process exits.
+	Poststop []Hook
+}
+
+type Capabilities struct {
+	// Bounding is the set of capabilities checked by the kernel.
+	Bounding []string
+	// Effective is the set of capabilities checked by the kernel.
+	Effective []string
+	// Inheritable is the capabilities preserved across execve.
+	Inheritable []string
+	// Permitted is the limiting superset for effective capabilities.
+	Permitted []string
+	// Ambient is the ambient set of capabilities that are kept.
+	Ambient []string
+}
+
+func (hooks *Hooks) UnmarshalJSON(b []byte) error {
+	var state struct {
+		Prestart  []CommandHook
+		Poststart []CommandHook
+		Poststop  []CommandHook
+	}
+
+	if err := json.Unmarshal(b, &state); err != nil {
+		return err
+	}
+
+	deserialize := func(shooks []CommandHook) (hooks []Hook) {
+		for _, shook := range shooks {
+			hooks = append(hooks, shook)
+		}
+
+		return hooks
+	}
+
+	hooks.Prestart = deserialize(state.Prestart)
+	hooks.Poststart = deserialize(state.Poststart)
+	hooks.Poststop = deserialize(state.Poststop)
+	return nil
+}
+
+func (hooks Hooks) MarshalJSON() ([]byte, error) {
+	serialize := func(hooks []Hook) (serializableHooks []CommandHook) {
+		for _, hook := range hooks {
+			switch chook := hook.(type) {
+			case CommandHook:
+				serializableHooks = append(serializableHooks, chook)
+			default:
+				logrus.Warnf("cannot serialize hook of type %T, skipping", hook)
+			}
+		}
+
+		return serializableHooks
+	}
+
+	return json.Marshal(map[string]interface{}{
+		"prestart":  serialize(hooks.Prestart),
+		"poststart": serialize(hooks.Poststart),
+		"poststop":  serialize(hooks.Poststop),
+	})
+}
+
+// HookState is the payload provided to a hook on execution.
+type HookState specs.State
+
+type Hook interface {
+	// Run executes the hook with the provided state.
+	Run(HookState) error
+}
+
+// NewFunctionHook will call the provided function when the hook is run.
+func NewFunctionHook(f func(HookState) error) FuncHook {
+	return FuncHook{
+		run: f,
+	}
+}
+
+type FuncHook struct {
+	run func(HookState) error
+}
+
+func (f FuncHook) Run(s HookState) error {
+	return f.run(s)
+}
+
+type Command struct {
+	Path    string         `json:"path"`
+	Args    []string       `json:"args"`
+	Env     []string       `json:"env"`
+	Dir     string         `json:"dir"`
+	Timeout *time.Duration `json:"timeout"`
+}
+
+// NewCommandHook will execute the provided command when the hook is run.
+func NewCommandHook(cmd Command) CommandHook {
+	return CommandHook{
+		Command: cmd,
+	}
+}
+
+type CommandHook struct {
+	Command
+}
+
+func (c Command) Run(s HookState) error {
+	b, err := json.Marshal(s)
+	if err != nil {
+		return err
+	}
+	var stdout, stderr bytes.Buffer
+	cmd := exec.Cmd{
+		Path:   c.Path,
+		Args:   c.Args,
+		Env:    c.Env,
+		Stdin:  bytes.NewReader(b),
+		Stdout: &stdout,
+		Stderr: &stderr,
+	}
+	if err := cmd.Start(); err != nil {
+		return err
+	}
+	errC := make(chan error, 1)
+	go func() {
+		err := cmd.Wait()
+		if err != nil {
+			err = fmt.Errorf("error running hook: %v, stdout: %s, stderr: %s", err, stdout.String(), stderr.String())
+		}
+		errC <- err
+	}()
+	var timerCh <-chan time.Time
+	if c.Timeout != nil {
+		timer := time.NewTimer(*c.Timeout)
+		defer timer.Stop()
+		timerCh = timer.C
+	}
+	select {
+	case err := <-errC:
+		return err
+	case <-timerCh:
+		cmd.Process.Kill()
+		cmd.Wait()
+		return fmt.Errorf("hook ran past specified timeout of %.1fs", c.Timeout.Seconds())
+	}
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/config_linux.go

@@ -0,0 +1,61 @@
+package configs
+
+import "fmt"
+
+// HostUID gets the translated uid for the process on host which could be
+// different when user namespaces are enabled.
+func (c Config) HostUID(containerId int) (int, error) {
+	if c.Namespaces.Contains(NEWUSER) {
+		if c.UidMappings == nil {
+			return -1, fmt.Errorf("User namespaces enabled, but no uid mappings found.")
+		}
+		id, found := c.hostIDFromMapping(containerId, c.UidMappings)
+		if !found {
+			return -1, fmt.Errorf("User namespaces enabled, but no user mapping found.")
+		}
+		return id, nil
+	}
+	// Return unchanged id.
+	return containerId, nil
+}
+
+// HostRootUID gets the root uid for the process on host which could be non-zero
+// when user namespaces are enabled.
+func (c Config) HostRootUID() (int, error) {
+	return c.HostUID(0)
+}
+
+// HostGID gets the translated gid for the process on host which could be
+// different when user namespaces are enabled.
+func (c Config) HostGID(containerId int) (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(containerId, c.GidMappings)
+		if !found {
+			return -1, fmt.Errorf("User namespaces enabled, but no group mapping found.")
+		}
+		return id, nil
+	}
+	// Return unchanged id.
+	return containerId, nil
+}
+
+// HostRootGID gets the root gid for the process on host which could be non-zero
+// when user namespaces are enabled.
+func (c Config) HostRootGID() (int, error) {
+	return c.HostGID(0)
+}
+
+// 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
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/device.go

@@ -0,0 +1,57 @@
+package configs
+
+import (
+	"fmt"
+	"os"
+)
+
+const (
+	Wildcard = -1
+)
+
+// TODO Windows: This can be factored out in the future
+
+type Device struct {
+	// Device type, block, char, etc.
+	Type rune `json:"type"`
+
+	// Path to the device.
+	Path string `json:"path"`
+
+	// Major is the device's major number.
+	Major int64 `json:"major"`
+
+	// Minor is the device's minor number.
+	Minor int64 `json:"minor"`
+
+	// Cgroup permissions format, rwm.
+	Permissions string `json:"permissions"`
+
+	// FileMode permission bits for the device.
+	FileMode os.FileMode `json:"file_mode"`
+
+	// Uid of the device.
+	Uid uint32 `json:"uid"`
+
+	// Gid of the device.
+	Gid uint32 `json:"gid"`
+
+	// Write the file to the allowed list
+	Allow bool `json:"allow"`
+}
+
+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)
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/device_defaults.go

@@ -0,0 +1,111 @@
+// +build linux
+
+package configs
+
+var (
+	// DefaultSimpleDevices 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",
+		},
+		// /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{}, DefaultSimpleDevices...)
+)

vendor/github.com/opencontainers/runc/libcontainer/configs/hugepage_limit.go

@@ -0,0 +1,9 @@
+package configs
+
+type HugepageLimit struct {
+	// which type of hugepage to limit.
+	Pagesize string `json:"page_size"`
+
+	// usage limit for hugepage.
+	Limit uint64 `json:"limit"`
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/intelrdt.go

@@ -0,0 +1,7 @@
+package configs
+
+type IntelRdt struct {
+	// The schema for L3 cache id and capacity bitmask (CBM)
+	// Format: "L3:<cache_id0>=<cbm0>;<cache_id1>=<cbm1>;..."
+	L3CacheSchema string `json:"l3_cache_schema,omitempty"`
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/interface_priority_map.go

@@ -0,0 +1,14 @@
+package configs
+
+import (
+	"fmt"
+)
+
+type IfPrioMap struct {
+	Interface string `json:"interface"`
+	Priority  int64  `json:"priority"`
+}
+
+func (i *IfPrioMap) CgroupString() string {
+	return fmt.Sprintf("%s %d", i.Interface, i.Priority)
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/mount.go

@@ -0,0 +1,39 @@
+package configs
+
+const (
+	// EXT_COPYUP is a directive to copy up the contents of a directory when
+	// a tmpfs is mounted over it.
+	EXT_COPYUP = 1 << iota
+)
+
+type Mount struct {
+	// Source path for the mount.
+	Source string `json:"source"`
+
+	// Destination path for the mount inside the container.
+	Destination string `json:"destination"`
+
+	// Device the mount is for.
+	Device string `json:"device"`
+
+	// Mount flags.
+	Flags int `json:"flags"`
+
+	// Propagation Flags
+	PropagationFlags []int `json:"propagation_flags"`
+
+	// Mount data applied to the mount.
+	Data string `json:"data"`
+
+	// Relabel source if set, "z" indicates shared, "Z" indicates unshared.
+	Relabel string `json:"relabel"`
+
+	// Extensions are additional flags that are specific to runc.
+	Extensions int `json:"extensions"`
+
+	// Optional Command to be run before Source is mounted.
+	PremountCmds []Command `json:"premount_cmds"`
+
+	// Optional Command to be run after Source is mounted.
+	PostmountCmds []Command `json:"postmount_cmds"`
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces.go

@@ -0,0 +1,5 @@
+package configs
+
+type NamespaceType string
+
+type Namespaces []Namespace

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces_linux.go

@@ -0,0 +1,122 @@
+package configs
+
+import (
+	"fmt"
+	"os"
+	"sync"
+)
+
+const (
+	NEWNET  NamespaceType = "NEWNET"
+	NEWPID  NamespaceType = "NEWPID"
+	NEWNS   NamespaceType = "NEWNS"
+	NEWUTS  NamespaceType = "NEWUTS"
+	NEWIPC  NamespaceType = "NEWIPC"
+	NEWUSER NamespaceType = "NEWUSER"
+)
+
+var (
+	nsLock              sync.Mutex
+	supportedNamespaces = make(map[NamespaceType]bool)
+)
+
+// NsName converts the namespace type to its filename
+func NsName(ns NamespaceType) string {
+	switch ns {
+	case NEWNET:
+		return "net"
+	case NEWNS:
+		return "mnt"
+	case NEWPID:
+		return "pid"
+	case NEWIPC:
+		return "ipc"
+	case NEWUSER:
+		return "user"
+	case NEWUTS:
+		return "uts"
+	}
+	return ""
+}
+
+// IsNamespaceSupported returns whether a namespace is available or
+// not
+func IsNamespaceSupported(ns NamespaceType) bool {
+	nsLock.Lock()
+	defer nsLock.Unlock()
+	supported, ok := supportedNamespaces[ns]
+	if ok {
+		return supported
+	}
+	nsFile := NsName(ns)
+	// if the namespace type is unknown, just return false
+	if nsFile == "" {
+		return false
+	}
+	_, err := os.Stat(fmt.Sprintf("/proc/self/ns/%s", nsFile))
+	// a namespace is supported if it exists and we have permissions to read it
+	supported = err == nil
+	supportedNamespaces[ns] = supported
+	return supported
+}
+
+func NamespaceTypes() []NamespaceType {
+	return []NamespaceType{
+		NEWUSER, // Keep user NS always first, don't move it.
+		NEWIPC,
+		NEWUTS,
+		NEWNET,
+		NEWPID,
+		NEWNS,
+	}
+}
+
+// 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"`
+}
+
+func (n *Namespace) GetPath(pid int) string {
+	return fmt.Sprintf("/proc/%d/ns/%s", pid, NsName(n.Type))
+}
+
+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
+}
+
+func (n *Namespaces) PathOf(t NamespaceType) string {
+	i := n.index(t)
+	if i == -1 {
+		return ""
+	}
+	return (*n)[i].Path
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces_syscall.go

@@ -0,0 +1,31 @@
+// +build linux
+
+package configs
+
+import "golang.org/x/sys/unix"
+
+func (n *Namespace) Syscall() int {
+	return namespaceInfo[n.Type]
+}
+
+var namespaceInfo = map[NamespaceType]int{
+	NEWNET:  unix.CLONE_NEWNET,
+	NEWNS:   unix.CLONE_NEWNS,
+	NEWUSER: unix.CLONE_NEWUSER,
+	NEWIPC:  unix.CLONE_NEWIPC,
+	NEWUTS:  unix.CLONE_NEWUTS,
+	NEWPID:  unix.CLONE_NEWPID,
+}
+
+// CloneFlags parses the container's Namespaces options to set the correct
+// flags on clone, unshare. This function 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)
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces_syscall_unsupported.go

@@ -0,0 +1,13 @@
+// +build !linux,!windows
+
+package configs
+
+func (n *Namespace) Syscall() int {
+	panic("No namespace syscall support")
+}
+
+// CloneFlags parses the container's Namespaces options to set the correct
+// flags on clone, unshare. This function returns flags only for new namespaces.
+func (n *Namespaces) CloneFlags() uintptr {
+	panic("No namespace syscall support")
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces_unsupported.go

@@ -0,0 +1,8 @@
+// +build !linux
+
+package configs
+
+// Namespace defines configuration for each namespace.  It specifies an
+// alternate path that is able to be joined via setns.
+type Namespace struct {
+}

vendor/github.com/opencontainers/runc/libcontainer/configs/network.go

@@ -0,0 +1,72 @@
+package configs
+
+// Network defines configuration for a container's networking stack
+//
+// The network configuration can be omitted 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"`
+
+	// Name of the network interface
+	Name string `json:"name"`
+
+	// The bridge to use.
+	Bridge string `json:"bridge"`
+
+	// MacAddress contains the MAC address to set on the network interface
+	MacAddress string `json:"mac_address"`
+
+	// Address contains the IPv4 and mask to set on the network interface
+	Address string `json:"address"`
+
+	// Gateway sets the gateway address that is used as the default for the interface
+	Gateway string `json:"gateway"`
+
+	// IPv6Address contains the IPv6 and mask to set on the network interface
+	IPv6Address string `json:"ipv6_address"`
+
+	// IPv6Gateway sets the ipv6 gateway address that is used as the default for the interface
+	IPv6Gateway string `json:"ipv6_gateway"`
+
+	// 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"`
+
+	// 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"`
+
+	// HostInterfaceName is a unique name of a veth pair that resides on in the host interface of the
+	// container.
+	HostInterfaceName string `json:"host_interface_name"`
+
+	// HairpinMode specifies if hairpin NAT should be enabled on the virtual interface
+	// bridge port in the case of type veth
+	// Note: This is unsupported on some systems.
+	// Note: This does not apply to loopback interfaces.
+	HairpinMode bool `json:"hairpin_mode"`
+}
+
+// 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 omitted 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"`
+
+	// Sets the source and mask, should be a CIDR.  Accepts IPv4 and IPv6
+	Source string `json:"source"`
+
+	// Sets the gateway.  Accepts IPv4 and IPv6
+	Gateway string `json:"gateway"`
+
+	// The device to set this route up for, for example: eth0
+	InterfaceName string `json:"interface_name"`
+}

vendor/github.com/opencontainers/runc/libcontainer/devices/devices.go

@@ -0,0 +1,104 @@
+package devices
+
+import (
+	"errors"
+	"io/ioutil"
+	"os"
+	"path/filepath"
+
+	"github.com/opencontainers/runc/libcontainer/configs"
+
+	"golang.org/x/sys/unix"
+)
+
+var (
+	ErrNotADevice = errors.New("not a device node")
+)
+
+// Testing dependencies
+var (
+	unixLstat     = unix.Lstat
+	ioutilReadDir = ioutil.ReadDir
+)
+
+// Given the path to a device and its cgroup_permissions(which cannot be easily queried) look up the information about a linux device and return that information as a Device struct.
+func DeviceFromPath(path, permissions string) (*configs.Device, error) {
+	var stat unix.Stat_t
+	err := unixLstat(path, &stat)
+	if err != nil {
+		return nil, err
+	}
+
+	var (
+		devNumber = stat.Rdev
+		major     = unix.Major(devNumber)
+	)
+	if major == 0 {
+		return nil, ErrNotADevice
+	}
+
+	var (
+		devType rune
+		mode    = stat.Mode
+	)
+	switch {
+	case mode&unix.S_IFBLK == unix.S_IFBLK:
+		devType = 'b'
+	case mode&unix.S_IFCHR == unix.S_IFCHR:
+		devType = 'c'
+	}
+	return &configs.Device{
+		Type:        devType,
+		Path:        path,
+		Major:       int64(major),
+		Minor:       int64(unix.Minor(devNumber)),
+		Permissions: permissions,
+		FileMode:    os.FileMode(mode),
+		Uid:         stat.Uid,
+		Gid:         stat.Gid,
+	}, nil
+}
+
+func HostDevices() ([]*configs.Device, error) {
+	return getDevices("/dev")
+}
+
+func getDevices(path string) ([]*configs.Device, error) {
+	files, err := ioutilReadDir(path)
+	if err != nil {
+		return nil, err
+	}
+	out := []*configs.Device{}
+	for _, f := range files {
+		switch {
+		case f.IsDir():
+			switch f.Name() {
+			// ".lxc" & ".lxd-mounts" added to address https://github.com/lxc/lxd/issues/2825
+			case "pts", "shm", "fd", "mqueue", ".lxc", ".lxd-mounts":
+				continue
+			default:
+				sub, err := getDevices(filepath.Join(path, f.Name()))
+				if err != nil {
+					return nil, err
+				}
+
+				out = append(out, sub...)
+				continue
+			}
+		case f.Name() == "console":
+			continue
+		}
+		device, err := DeviceFromPath(filepath.Join(path, f.Name()), "rwm")
+		if err != nil {
+			if err == ErrNotADevice {
+				continue
+			}
+			if os.IsNotExist(err) {
+				continue
+			}
+			return nil, err
+		}
+		out = append(out, device)
+	}
+	return out, nil
+}

vendor/github.com/opencontainers/runc/libcontainer/system/linux.go

@@ -7,8 +7,10 @@ import (
 	"fmt"
 	"os"
 	"os/exec"
-	"syscall"
+	"syscall" // only for exec
 	"unsafe"
+
+	"golang.org/x/sys/unix"
 )
 
 // If arg2 is nonzero, set the "child subreaper" attribute of the
@@ -53,8 +55,8 @@ func Execv(cmd string, args []string, env []string) error {
 	return syscall.Exec(name, args, env)
 }
 
-func Prlimit(pid, resource int, limit syscall.Rlimit) error {
-	_, _, err := syscall.RawSyscall6(syscall.SYS_PRLIMIT64, uintptr(pid), uintptr(resource), uintptr(unsafe.Pointer(&limit)), uintptr(unsafe.Pointer(&limit)), 0, 0)
+func Prlimit(pid, resource int, limit unix.Rlimit) error {
+	_, _, err := unix.RawSyscall6(unix.SYS_PRLIMIT64, uintptr(pid), uintptr(resource), uintptr(unsafe.Pointer(&limit)), uintptr(unsafe.Pointer(&limit)), 0, 0)
 	if err != 0 {
 		return err
 	}
@@ -62,7 +64,7 @@ func Prlimit(pid, resource int, limit syscall.Rlimit) error {
 }
 
 func SetParentDeathSignal(sig uintptr) error {
-	if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_PDEATHSIG, sig, 0); err != 0 {
+	if err := unix.Prctl(unix.PR_SET_PDEATHSIG, sig, 0, 0, 0); err != nil {
 		return err
 	}
 	return nil
@@ -70,15 +72,14 @@ func SetParentDeathSignal(sig uintptr) error {
 
 func GetParentDeathSignal() (ParentDeathSignal, error) {
 	var sig int
-	_, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_GET_PDEATHSIG, uintptr(unsafe.Pointer(&sig)), 0)
-	if err != 0 {
+	if err := unix.Prctl(unix.PR_GET_PDEATHSIG, uintptr(unsafe.Pointer(&sig)), 0, 0, 0); err != nil {
 		return -1, err
 	}
 	return ParentDeathSignal(sig), nil
 }
 
 func SetKeepCaps() error {
-	if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_KEEPCAPS, 1, 0); err != 0 {
+	if err := unix.Prctl(unix.PR_SET_KEEPCAPS, 1, 0, 0, 0); err != nil {
 		return err
 	}
 
@@ -86,7 +87,7 @@ func SetKeepCaps() error {
 }
 
 func ClearKeepCaps() error {
-	if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_KEEPCAPS, 0, 0); err != 0 {
+	if err := unix.Prctl(unix.PR_SET_KEEPCAPS, 0, 0, 0, 0); err != nil {
 		return err
 	}
 
@@ -94,23 +95,18 @@ func ClearKeepCaps() error {
 }
 
 func Setctty() error {
-	if _, _, err := syscall.RawSyscall(syscall.SYS_IOCTL, 0, uintptr(syscall.TIOCSCTTY), 0); err != 0 {
+	if err := unix.IoctlSetInt(0, unix.TIOCSCTTY, 0); err != nil {
 		return err
 	}
 	return nil
 }
 
-/*
- * Detect whether we are currently running in a user namespace.
- * Copied from github.com/lxc/lxd/shared/util.go
- */
+// RunningInUserNS detects whether we are currently running in a user namespace.
+// Copied from github.com/lxc/lxd/shared/util.go
 func RunningInUserNS() bool {
 	file, err := os.Open("/proc/self/uid_map")
 	if err != nil {
-		/*
-		 * This kernel-provided file only exists if user namespaces are
-		 * supported
-		 */
+		// This kernel-provided file only exists if user namespaces are supported
 		return false
 	}
 	defer file.Close()
@@ -136,13 +132,16 @@ func RunningInUserNS() bool {
 
 // SetSubreaper sets the value i as the subreaper setting for the calling process
 func SetSubreaper(i int) error {
-	return Prctl(PR_SET_CHILD_SUBREAPER, uintptr(i), 0, 0, 0)
+	return unix.Prctl(PR_SET_CHILD_SUBREAPER, uintptr(i), 0, 0, 0)
 }
 
-func Prctl(option int, arg2, arg3, arg4, arg5 uintptr) (err error) {
-	_, _, e1 := syscall.Syscall6(syscall.SYS_PRCTL, uintptr(option), arg2, arg3, arg4, arg5, 0)
-	if e1 != 0 {
-		err = e1
+// GetSubreaper returns the subreaper setting for the calling process
+func GetSubreaper() (int, error) {
+	var i uintptr
+
+	if err := unix.Prctl(unix.PR_GET_CHILD_SUBREAPER, uintptr(unsafe.Pointer(&i)), 0, 0, 0); err != nil {
+		return -1, err
 	}
-	return
+
+	return int(i), nil
 }

vendor/github.com/opencontainers/runc/libcontainer/system/proc.go

@@ -1,27 +1,113 @@
 package system
 
 import (
+	"fmt"
 	"io/ioutil"
 	"path/filepath"
 	"strconv"
 	"strings"
 )
 
-// look in /proc to find the process start time so that we can verify
-// that this pid has started after ourself
+// State is the status of a process.
+type State rune
+
+const ( // Only values for Linux 3.14 and later are listed here
+	Dead        State = 'X'
+	DiskSleep   State = 'D'
+	Running     State = 'R'
+	Sleeping    State = 'S'
+	Stopped     State = 'T'
+	TracingStop State = 't'
+	Zombie      State = 'Z'
+)
+
+// String forms of the state from proc(5)'s documentation for
+// /proc/[pid]/status' "State" field.
+func (s State) String() string {
+	switch s {
+	case Dead:
+		return "dead"
+	case DiskSleep:
+		return "disk sleep"
+	case Running:
+		return "running"
+	case Sleeping:
+		return "sleeping"
+	case Stopped:
+		return "stopped"
+	case TracingStop:
+		return "tracing stop"
+	case Zombie:
+		return "zombie"
+	default:
+		return fmt.Sprintf("unknown (%c)", s)
+	}
+}
+
+// Stat_t represents the information from /proc/[pid]/stat, as
+// described in proc(5) with names based on the /proc/[pid]/status
+// fields.
+type Stat_t struct {
+	// PID is the process ID.
+	PID uint
+
+	// Name is the command run by the process.
+	Name string
+
+	// State is the state of the process.
+	State State
+
+	// StartTime is the number of clock ticks after system boot (since
+	// Linux 2.6).
+	StartTime uint64
+}
+
+// Stat returns a Stat_t instance for the specified process.
+func Stat(pid int) (stat Stat_t, err error) {
+	bytes, err := ioutil.ReadFile(filepath.Join("/proc", strconv.Itoa(pid), "stat"))
+	if err != nil {
+		return stat, err
+	}
+	return parseStat(string(bytes))
+}
+
+// GetProcessStartTime is deprecated.  Use Stat(pid) and
+// Stat_t.StartTime instead.
 func GetProcessStartTime(pid int) (string, error) {
-	data, err := ioutil.ReadFile(filepath.Join("/proc", strconv.Itoa(pid), "stat"))
+	stat, err := Stat(pid)
 	if err != nil {
 		return "", err
 	}
+	return fmt.Sprintf("%d", stat.StartTime), nil
+}
 
-	parts := strings.Split(string(data), " ")
-	// the starttime is located at pos 22
-	// from the man page
-	//
-	// starttime %llu (was %lu before Linux 2.6)
-	// (22)  The  time the process started after system boot.  In kernels before Linux 2.6, this
-	// value was expressed in jiffies.  Since Linux 2.6, the value is expressed in  clock  ticks
-	// (divide by sysconf(_SC_CLK_TCK)).
-	return parts[22-1], nil // starts at 1
+func parseStat(data string) (stat Stat_t, err error) {
+	// From proc(5), field 2 could contain space and is inside `(` and `)`.
+	// The following is an example:
+	// 89653 (gunicorn: maste) S 89630 89653 89653 0 -1 4194560 29689 28896 0 3 146 32 76 19 20 0 1 0 2971844 52965376 3920 18446744073709551615 1 1 0 0 0 0 0 16781312 137447943 0 0 0 17 1 0 0 0 0 0 0 0 0 0 0 0 0 0
+	i := strings.LastIndex(data, ")")
+	if i <= 2 || i >= len(data)-1 {
+		return stat, fmt.Errorf("invalid stat data: %q", data)
+	}
+
+	parts := strings.SplitN(data[:i], "(", 2)
+	if len(parts) != 2 {
+		return stat, fmt.Errorf("invalid stat data: %q", data)
+	}
+
+	stat.Name = parts[1]
+	_, err = fmt.Sscanf(parts[0], "%d", &stat.PID)
+	if err != nil {
+		return stat, err
+	}
+
+	// parts indexes should be offset by 3 from the field number given
+	// proc(5), because parts is zero-indexed and we've removed fields
+	// one (PID) and two (Name) in the paren-split.
+	parts = strings.Split(data[i+2:], " ")
+	var state int
+	fmt.Sscanf(parts[3-3], "%c", &state)
+	stat.State = State(state)
+	fmt.Sscanf(parts[22-3], "%d", &stat.StartTime)
+	return stat, nil
 }

vendor/github.com/opencontainers/runc/libcontainer/system/syscall_linux_32.go

@@ -0,0 +1,26 @@
+// +build linux
+// +build 386 arm
+
+package system
+
+import (
+	"golang.org/x/sys/unix"
+)
+
+// Setuid sets the uid of the calling thread to the specified uid.
+func Setuid(uid int) (err error) {
+	_, _, e1 := unix.RawSyscall(unix.SYS_SETUID32, uintptr(uid), 0, 0)
+	if e1 != 0 {
+		err = e1
+	}
+	return
+}
+
+// Setgid sets the gid of the calling thread to the specified gid.
+func Setgid(gid int) (err error) {
+	_, _, e1 := unix.RawSyscall(unix.SYS_SETGID32, uintptr(gid), 0, 0)
+	if e1 != 0 {
+		err = e1
+	}
+	return
+}

vendor/github.com/opencontainers/runc/libcontainer/system/syscall_linux_64.go

@@ -1,14 +1,15 @@
-// +build linux,arm64 linux,amd64 linux,ppc linux,ppc64 linux,ppc64le linux,s390x
+// +build linux
+// +build arm64 amd64 mips mipsle mips64 mips64le ppc ppc64 ppc64le s390x
 
 package system
 
 import (
-	"syscall"
+	"golang.org/x/sys/unix"
 )
 
 // Setuid sets the uid of the calling thread to the specified uid.
 func Setuid(uid int) (err error) {
-	_, _, e1 := syscall.RawSyscall(syscall.SYS_SETUID, uintptr(uid), 0, 0)
+	_, _, e1 := unix.RawSyscall(unix.SYS_SETUID, uintptr(uid), 0, 0)
 	if e1 != 0 {
 		err = e1
 	}
@@ -17,7 +18,7 @@ func Setuid(uid int) (err error) {
 
 // Setgid sets the gid of the calling thread to the specified gid.
 func Setgid(gid int) (err error) {
-	_, _, e1 := syscall.RawSyscall(syscall.SYS_SETGID, uintptr(gid), 0, 0)
+	_, _, e1 := unix.RawSyscall(unix.SYS_SETGID, uintptr(gid), 0, 0)
 	if e1 != 0 {
 		err = e1
 	}

vendor/github.com/opencontainers/runc/libcontainer/system/sysconfig.go

@@ -1,4 +1,4 @@
-// +build cgo,linux cgo,freebsd
+// +build cgo,linux
 
 package system
 

vendor/github.com/opencontainers/runc/libcontainer/system/xattrs_linux.go

@@ -1,99 +1,35 @@
 package system
 
-import (
-	"syscall"
-	"unsafe"
-)
-
-var _zero uintptr
-
-// Returns the size of xattrs and nil error
-// Requires path, takes allocated []byte or nil as last argument
-func Llistxattr(path string, dest []byte) (size int, err error) {
-	pathBytes, err := syscall.BytePtrFromString(path)
-	if err != nil {
-		return -1, err
-	}
-	var newpathBytes unsafe.Pointer
-	if len(dest) > 0 {
-		newpathBytes = unsafe.Pointer(&dest[0])
-	} else {
-		newpathBytes = unsafe.Pointer(&_zero)
-	}
-
-	_size, _, errno := syscall.Syscall6(syscall.SYS_LLISTXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(newpathBytes), uintptr(len(dest)), 0, 0, 0)
-	size = int(_size)
-	if errno != 0 {
-		return -1, errno
-	}
-
-	return size, nil
-}
+import "golang.org/x/sys/unix"
 
 // Returns a []byte slice if the xattr is set and nil otherwise
 // Requires path and its attribute as arguments
 func Lgetxattr(path string, attr string) ([]byte, error) {
 	var sz int
-	pathBytes, err := syscall.BytePtrFromString(path)
-	if err != nil {
-		return nil, err
-	}
-	attrBytes, err := syscall.BytePtrFromString(attr)
-	if err != nil {
-		return nil, err
-	}
-
 	// Start with a 128 length byte array
-	sz = 128
-	dest := make([]byte, sz)
-	destBytes := unsafe.Pointer(&dest[0])
-	_sz, _, errno := syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(destBytes), uintptr(len(dest)), 0, 0)
+	dest := make([]byte, 128)
+	sz, errno := unix.Lgetxattr(path, attr, dest)
 
 	switch {
-	case errno == syscall.ENODATA:
+	case errno == unix.ENODATA:
 		return nil, errno
-	case errno == syscall.ENOTSUP:
+	case errno == unix.ENOTSUP:
 		return nil, errno
-	case errno == syscall.ERANGE:
+	case errno == unix.ERANGE:
 		// 128 byte array might just not be good enough,
-		// A dummy buffer is used ``uintptr(0)`` to get real size
+		// A dummy buffer is used to get the real size
 		// of the xattrs on disk
-		_sz, _, errno = syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(unsafe.Pointer(nil)), uintptr(0), 0, 0)
-		sz = int(_sz)
-		if sz < 0 {
+		sz, errno = unix.Lgetxattr(path, attr, []byte{})
+		if errno != nil {
 			return nil, errno
 		}
 		dest = make([]byte, sz)
-		destBytes := unsafe.Pointer(&dest[0])
-		_sz, _, errno = syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(destBytes), uintptr(len(dest)), 0, 0)
-		if errno != 0 {
+		sz, errno = unix.Lgetxattr(path, attr, dest)
+		if errno != nil {
 			return nil, errno
 		}
-	case errno != 0:
+	case errno != nil:
 		return nil, errno
 	}
-	sz = int(_sz)
 	return dest[:sz], nil
 }
-
-func Lsetxattr(path string, attr string, data []byte, flags int) error {
-	pathBytes, err := syscall.BytePtrFromString(path)
-	if err != nil {
-		return err
-	}
-	attrBytes, err := syscall.BytePtrFromString(attr)
-	if err != nil {
-		return err
-	}
-	var dataBytes unsafe.Pointer
-	if len(data) > 0 {
-		dataBytes = unsafe.Pointer(&data[0])
-	} else {
-		dataBytes = unsafe.Pointer(&_zero)
-	}
-	_, _, errno := syscall.Syscall6(syscall.SYS_LSETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(dataBytes), uintptr(len(data)), uintptr(flags), 0)
-	if errno != 0 {
-		return errno
-	}
-	return nil
-}

vendor/github.com/opencontainers/runc/libcontainer/user/lookup.go

@@ -2,7 +2,6 @@ package user
 
 import (
 	"errors"
-	"syscall"
 )
 
 var (
@@ -36,13 +35,6 @@ func lookupUser(filter func(u User) bool) (User, error) {
 	return users[0], nil
 }
 
-// CurrentUser looks up the current user by their user id in /etc/passwd. If the
-// user cannot be found (or there is no /etc/passwd file on the filesystem),
-// then CurrentUser returns an error.
-func CurrentUser() (User, error) {
-	return LookupUid(syscall.Getuid())
-}
-
 // LookupUser looks up a user by their username in /etc/passwd. If the user
 // cannot be found (or there is no /etc/passwd file on the filesystem), then
 // LookupUser returns an error.
@@ -84,13 +76,6 @@ func lookupGroup(filter func(g Group) bool) (Group, error) {
 	return groups[0], nil
 }
 
-// CurrentGroup looks up the current user's group by their primary group id's
-// entry in /etc/passwd. If the group cannot be found (or there is no
-// /etc/group file on the filesystem), then CurrentGroup returns an error.
-func CurrentGroup() (Group, error) {
-	return LookupGid(syscall.Getgid())
-}
-
 // LookupGroup looks up a group by its name in /etc/group. If the group cannot
 // be found (or there is no /etc/group file on the filesystem), then LookupGroup
 // returns an error.

vendor/github.com/opencontainers/runc/libcontainer/user/lookup_unix.go

@@ -5,6 +5,8 @@ package user
 import (
 	"io"
 	"os"
+
+	"golang.org/x/sys/unix"
 )
 
 // Unix-specific path to the passwd and group formatted files.
@@ -28,3 +30,17 @@ func GetGroupPath() (string, error) {
 func GetGroup() (io.ReadCloser, error) {
 	return os.Open(unixGroupPath)
 }
+
+// CurrentUser looks up the current user by their user id in /etc/passwd. If the
+// user cannot be found (or there is no /etc/passwd file on the filesystem),
+// then CurrentUser returns an error.
+func CurrentUser() (User, error) {
+	return LookupUid(unix.Getuid())
+}
+
+// CurrentGroup looks up the current user's group by their primary group id's
+// entry in /etc/passwd. If the group cannot be found (or there is no
+// /etc/group file on the filesystem), then CurrentGroup returns an error.
+func CurrentGroup() (Group, error) {
+	return LookupGid(unix.Getgid())
+}

vendor/github.com/opencontainers/runc/libcontainer/user/user.go

@@ -199,18 +199,16 @@ type ExecUser struct {
 // files cannot be opened for any reason, the error is ignored and a nil
 // io.Reader is passed instead.
 func GetExecUserPath(userSpec string, defaults *ExecUser, passwdPath, groupPath string) (*ExecUser, error) {
-	passwd, err := os.Open(passwdPath)
-	if err != nil {
-		passwd = nil
-	} else {
-		defer passwd.Close()
+	var passwd, group io.Reader
+
+	if passwdFile, err := os.Open(passwdPath); err == nil {
+		passwd = passwdFile
+		defer passwdFile.Close()
 	}
 
-	group, err := os.Open(groupPath)
-	if err != nil {
-		group = nil
-	} else {
-		defer group.Close()
+	if groupFile, err := os.Open(groupPath); err == nil {
+		group = groupFile
+		defer groupFile.Close()
 	}
 
 	return GetExecUser(userSpec, defaults, passwd, group)
@@ -343,7 +341,7 @@ func GetExecUser(userSpec string, defaults *ExecUser, passwd, group io.Reader) (
 			if len(groups) > 0 {
 				// First match wins, even if there's more than one matching entry.
 				user.Gid = groups[0].Gid
-			} else if groupArg != "" {
+			} else {
 				// If we can't find a group with the given name, the only other valid
 				// option is if it's a numeric group name with no associated entry in group.
 
@@ -433,9 +431,11 @@ func GetAdditionalGroups(additionalGroups []string, group io.Reader) ([]int, err
 // that opens the groupPath given and gives it as an argument to
 // GetAdditionalGroups.
 func GetAdditionalGroupsPath(additionalGroups []string, groupPath string) ([]int, error) {
-	group, err := os.Open(groupPath)
-	if err == nil {
-		defer group.Close()
+	var group io.Reader
+
+	if groupFile, err := os.Open(groupPath); err == nil {
+		group = groupFile
+		defer groupFile.Close()
 	}
 	return GetAdditionalGroups(additionalGroups, group)
 }

vendor/github.com/opencontainers/runtime-spec/LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2015 The Linux Foundation.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

vendor/github.com/opencontainers/runtime-spec/specs-go/config.go

@@ -0,0 +1,570 @@
+package specs
+
+import "os"
+
+// Spec is the base configuration for the container.
+type Spec struct {
+	// Version of the Open Container Initiative Runtime Specification with which the bundle complies.
+	Version string `json:"ociVersion"`
+	// Process configures the container process.
+	Process *Process `json:"process,omitempty"`
+	// Root configures the container's root filesystem.
+	Root *Root `json:"root,omitempty"`
+	// Hostname configures the container's hostname.
+	Hostname string `json:"hostname,omitempty"`
+	// Mounts configures additional mounts (on top of Root).
+	Mounts []Mount `json:"mounts,omitempty"`
+	// Hooks configures callbacks for container lifecycle events.
+	Hooks *Hooks `json:"hooks,omitempty" platform:"linux,solaris"`
+	// Annotations contains arbitrary metadata for the container.
+	Annotations map[string]string `json:"annotations,omitempty"`
+
+	// Linux is platform-specific configuration for Linux based containers.
+	Linux *Linux `json:"linux,omitempty" platform:"linux"`
+	// Solaris is platform-specific configuration for Solaris based containers.
+	Solaris *Solaris `json:"solaris,omitempty" platform:"solaris"`
+	// Windows is platform-specific configuration for Windows based containers.
+	Windows *Windows `json:"windows,omitempty" platform:"windows"`
+}
+
+// Process contains information to start a specific application inside the container.
+type Process struct {
+	// Terminal creates an interactive terminal for the container.
+	Terminal bool `json:"terminal,omitempty"`
+	// ConsoleSize specifies the size of the console.
+	ConsoleSize *Box `json:"consoleSize,omitempty"`
+	// User specifies user information for the process.
+	User User `json:"user"`
+	// Args specifies the binary and arguments for the application to execute.
+	Args []string `json:"args"`
+	// Env populates the process environment for the process.
+	Env []string `json:"env,omitempty"`
+	// Cwd is the current working directory for the process and must be
+	// relative to the container's root.
+	Cwd string `json:"cwd"`
+	// Capabilities are Linux capabilities that are kept for the process.
+	Capabilities *LinuxCapabilities `json:"capabilities,omitempty" platform:"linux"`
+	// Rlimits specifies rlimit options to apply to the process.
+	Rlimits []POSIXRlimit `json:"rlimits,omitempty" platform:"linux,solaris"`
+	// NoNewPrivileges controls whether additional privileges could be gained by processes in the container.
+	NoNewPrivileges bool `json:"noNewPrivileges,omitempty" platform:"linux"`
+	// ApparmorProfile specifies the apparmor profile for the container.
+	ApparmorProfile string `json:"apparmorProfile,omitempty" platform:"linux"`
+	// Specify an oom_score_adj for the container.
+	OOMScoreAdj *int `json:"oomScoreAdj,omitempty" platform:"linux"`
+	// SelinuxLabel specifies the selinux context that the container process is run as.
+	SelinuxLabel string `json:"selinuxLabel,omitempty" platform:"linux"`
+}
+
+// LinuxCapabilities specifies the whitelist of capabilities that are kept for a process.
+// http://man7.org/linux/man-pages/man7/capabilities.7.html
+type LinuxCapabilities struct {
+	// Bounding is the set of capabilities checked by the kernel.
+	Bounding []string `json:"bounding,omitempty" platform:"linux"`
+	// Effective is the set of capabilities checked by the kernel.
+	Effective []string `json:"effective,omitempty" platform:"linux"`
+	// Inheritable is the capabilities preserved across execve.
+	Inheritable []string `json:"inheritable,omitempty" platform:"linux"`
+	// Permitted is the limiting superset for effective capabilities.
+	Permitted []string `json:"permitted,omitempty" platform:"linux"`
+	// Ambient is the ambient set of capabilities that are kept.
+	Ambient []string `json:"ambient,omitempty" platform:"linux"`
+}
+
+// Box specifies dimensions of a rectangle. Used for specifying the size of a console.
+type Box struct {
+	// Height is the vertical dimension of a box.
+	Height uint `json:"height"`
+	// Width is the horizontal dimension of a box.
+	Width uint `json:"width"`
+}
+
+// User specifies specific user (and group) information for the container process.
+type User struct {
+	// UID is the user id.
+	UID uint32 `json:"uid" platform:"linux,solaris"`
+	// GID is the group id.
+	GID uint32 `json:"gid" platform:"linux,solaris"`
+	// AdditionalGids are additional group ids set for the container's process.
+	AdditionalGids []uint32 `json:"additionalGids,omitempty" platform:"linux,solaris"`
+	// Username is the user name.
+	Username string `json:"username,omitempty" platform:"windows"`
+}
+
+// Root contains information about the container's root filesystem on the host.
+type Root struct {
+	// Path is the absolute path to the container's root filesystem.
+	Path string `json:"path"`
+	// Readonly makes the root filesystem for the container readonly before the process is executed.
+	Readonly bool `json:"readonly,omitempty"`
+}
+
+// Mount specifies a mount for a container.
+type Mount struct {
+	// Destination is the absolute path where the mount will be placed in the container.
+	Destination string `json:"destination"`
+	// Type specifies the mount kind.
+	Type string `json:"type,omitempty" platform:"linux,solaris"`
+	// Source specifies the source path of the mount.
+	Source string `json:"source,omitempty"`
+	// Options are fstab style mount options.
+	Options []string `json:"options,omitempty"`
+}
+
+// Hook specifies a command that is run at a particular event in the lifecycle of a container
+type Hook struct {
+	Path    string   `json:"path"`
+	Args    []string `json:"args,omitempty"`
+	Env     []string `json:"env,omitempty"`
+	Timeout *int     `json:"timeout,omitempty"`
+}
+
+// Hooks for container setup and teardown
+type Hooks struct {
+	// Prestart is a list of hooks to be run before the container process is executed.
+	Prestart []Hook `json:"prestart,omitempty"`
+	// Poststart is a list of hooks to be run after the container process is started.
+	Poststart []Hook `json:"poststart,omitempty"`
+	// Poststop is a list of hooks to be run after the container process exits.
+	Poststop []Hook `json:"poststop,omitempty"`
+}
+
+// Linux contains platform-specific configuration for Linux based containers.
+type Linux struct {
+	// UIDMapping specifies user mappings for supporting user namespaces.
+	UIDMappings []LinuxIDMapping `json:"uidMappings,omitempty"`
+	// GIDMapping specifies group mappings for supporting user namespaces.
+	GIDMappings []LinuxIDMapping `json:"gidMappings,omitempty"`
+	// Sysctl are a set of key value pairs that are set for the container on start
+	Sysctl map[string]string `json:"sysctl,omitempty"`
+	// Resources contain cgroup information for handling resource constraints
+	// for the container
+	Resources *LinuxResources `json:"resources,omitempty"`
+	// CgroupsPath specifies the path to cgroups that are created and/or joined by the container.
+	// The path is expected to be relative to the cgroups mountpoint.
+	// If resources are specified, the cgroups at CgroupsPath will be updated based on resources.
+	CgroupsPath string `json:"cgroupsPath,omitempty"`
+	// Namespaces contains the namespaces that are created and/or joined by the container
+	Namespaces []LinuxNamespace `json:"namespaces,omitempty"`
+	// Devices are a list of device nodes that are created for the container
+	Devices []LinuxDevice `json:"devices,omitempty"`
+	// Seccomp specifies the seccomp security settings for the container.
+	Seccomp *LinuxSeccomp `json:"seccomp,omitempty"`
+	// RootfsPropagation is the rootfs mount propagation mode for the container.
+	RootfsPropagation string `json:"rootfsPropagation,omitempty"`
+	// MaskedPaths masks over the provided paths inside the container.
+	MaskedPaths []string `json:"maskedPaths,omitempty"`
+	// ReadonlyPaths sets the provided paths as RO inside the container.
+	ReadonlyPaths []string `json:"readonlyPaths,omitempty"`
+	// MountLabel specifies the selinux context for the mounts in the container.
+	MountLabel string `json:"mountLabel,omitempty"`
+	// IntelRdt contains Intel Resource Director Technology (RDT) information
+	// for handling resource constraints (e.g., L3 cache) for the container
+	IntelRdt *LinuxIntelRdt `json:"intelRdt,omitempty"`
+}
+
+// LinuxNamespace is the configuration for a Linux namespace
+type LinuxNamespace struct {
+	// Type is the type of namespace
+	Type LinuxNamespaceType `json:"type"`
+	// Path is a path to an existing namespace persisted on disk that can be joined
+	// and is of the same type
+	Path string `json:"path,omitempty"`
+}
+
+// LinuxNamespaceType is one of the Linux namespaces
+type LinuxNamespaceType string
+
+const (
+	// PIDNamespace for isolating process IDs
+	PIDNamespace LinuxNamespaceType = "pid"
+	// NetworkNamespace for isolating network devices, stacks, ports, etc
+	NetworkNamespace = "network"
+	// MountNamespace for isolating mount points
+	MountNamespace = "mount"
+	// IPCNamespace for isolating System V IPC, POSIX message queues
+	IPCNamespace = "ipc"
+	// UTSNamespace for isolating hostname and NIS domain name
+	UTSNamespace = "uts"
+	// UserNamespace for isolating user and group IDs
+	UserNamespace = "user"
+	// CgroupNamespace for isolating cgroup hierarchies
+	CgroupNamespace = "cgroup"
+)
+
+// LinuxIDMapping specifies UID/GID mappings
+type LinuxIDMapping struct {
+	// HostID is the starting UID/GID on the host to be mapped to 'ContainerID'
+	HostID uint32 `json:"hostID"`
+	// ContainerID is the starting UID/GID in the container
+	ContainerID uint32 `json:"containerID"`
+	// Size is the number of IDs to be mapped
+	Size uint32 `json:"size"`
+}
+
+// POSIXRlimit type and restrictions
+type POSIXRlimit struct {
+	// Type of the rlimit to set
+	Type string `json:"type"`
+	// Hard is the hard limit for the specified type
+	Hard uint64 `json:"hard"`
+	// Soft is the soft limit for the specified type
+	Soft uint64 `json:"soft"`
+}
+
+// LinuxHugepageLimit structure corresponds to limiting kernel hugepages
+type LinuxHugepageLimit struct {
+	// Pagesize is the hugepage size
+	Pagesize string `json:"pageSize"`
+	// Limit is the limit of "hugepagesize" hugetlb usage
+	Limit uint64 `json:"limit"`
+}
+
+// LinuxInterfacePriority for network interfaces
+type LinuxInterfacePriority struct {
+	// Name is the name of the network interface
+	Name string `json:"name"`
+	// Priority for the interface
+	Priority uint32 `json:"priority"`
+}
+
+// linuxBlockIODevice holds major:minor format supported in blkio cgroup
+type linuxBlockIODevice struct {
+	// Major is the device's major number.
+	Major int64 `json:"major"`
+	// Minor is the device's minor number.
+	Minor int64 `json:"minor"`
+}
+
+// LinuxWeightDevice struct holds a `major:minor weight` pair for weightDevice
+type LinuxWeightDevice struct {
+	linuxBlockIODevice
+	// Weight is the bandwidth rate for the device.
+	Weight *uint16 `json:"weight,omitempty"`
+	// LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, CFQ scheduler only
+	LeafWeight *uint16 `json:"leafWeight,omitempty"`
+}
+
+// LinuxThrottleDevice struct holds a `major:minor rate_per_second` pair
+type LinuxThrottleDevice struct {
+	linuxBlockIODevice
+	// Rate is the IO rate limit per cgroup per device
+	Rate uint64 `json:"rate"`
+}
+
+// LinuxBlockIO for Linux cgroup 'blkio' resource management
+type LinuxBlockIO struct {
+	// Specifies per cgroup weight
+	Weight *uint16 `json:"weight,omitempty"`
+	// Specifies tasks' weight in the given cgroup while competing with the cgroup's child cgroups, CFQ scheduler only
+	LeafWeight *uint16 `json:"leafWeight,omitempty"`
+	// Weight per cgroup per device, can override BlkioWeight
+	WeightDevice []LinuxWeightDevice `json:"weightDevice,omitempty"`
+	// IO read rate limit per cgroup per device, bytes per second
+	ThrottleReadBpsDevice []LinuxThrottleDevice `json:"throttleReadBpsDevice,omitempty"`
+	// IO write rate limit per cgroup per device, bytes per second
+	ThrottleWriteBpsDevice []LinuxThrottleDevice `json:"throttleWriteBpsDevice,omitempty"`
+	// IO read rate limit per cgroup per device, IO per second
+	ThrottleReadIOPSDevice []LinuxThrottleDevice `json:"throttleReadIOPSDevice,omitempty"`
+	// IO write rate limit per cgroup per device, IO per second
+	ThrottleWriteIOPSDevice []LinuxThrottleDevice `json:"throttleWriteIOPSDevice,omitempty"`
+}
+
+// LinuxMemory for Linux cgroup 'memory' resource management
+type LinuxMemory struct {
+	// Memory limit (in bytes).
+	Limit *int64 `json:"limit,omitempty"`
+	// Memory reservation or soft_limit (in bytes).
+	Reservation *int64 `json:"reservation,omitempty"`
+	// Total memory limit (memory + swap).
+	Swap *int64 `json:"swap,omitempty"`
+	// Kernel memory limit (in bytes).
+	Kernel *int64 `json:"kernel,omitempty"`
+	// Kernel memory limit for tcp (in bytes)
+	KernelTCP *int64 `json:"kernelTCP,omitempty"`
+	// How aggressive the kernel will swap memory pages.
+	Swappiness *uint64 `json:"swappiness,omitempty"`
+	// DisableOOMKiller disables the OOM killer for out of memory conditions
+	DisableOOMKiller *bool `json:"disableOOMKiller,omitempty"`
+}
+
+// LinuxCPU for Linux cgroup 'cpu' resource management
+type LinuxCPU struct {
+	// CPU shares (relative weight (ratio) vs. other cgroups with cpu shares).
+	Shares *uint64 `json:"shares,omitempty"`
+	// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
+	Quota *int64 `json:"quota,omitempty"`
+	// CPU period to be used for hardcapping (in usecs).
+	Period *uint64 `json:"period,omitempty"`
+	// How much time realtime scheduling may use (in usecs).
+	RealtimeRuntime *int64 `json:"realtimeRuntime,omitempty"`
+	// CPU period to be used for realtime scheduling (in usecs).
+	RealtimePeriod *uint64 `json:"realtimePeriod,omitempty"`
+	// CPUs to use within the cpuset. Default is to use any CPU available.
+	Cpus string `json:"cpus,omitempty"`
+	// List of memory nodes in the cpuset. Default is to use any available memory node.
+	Mems string `json:"mems,omitempty"`
+}
+
+// LinuxPids for Linux cgroup 'pids' resource management (Linux 4.3)
+type LinuxPids struct {
+	// Maximum number of PIDs. Default is "no limit".
+	Limit int64 `json:"limit"`
+}
+
+// LinuxNetwork identification and priority configuration
+type LinuxNetwork struct {
+	// Set class identifier for container's network packets
+	ClassID *uint32 `json:"classID,omitempty"`
+	// Set priority of network traffic for container
+	Priorities []LinuxInterfacePriority `json:"priorities,omitempty"`
+}
+
+// LinuxResources has container runtime resource constraints
+type LinuxResources struct {
+	// Devices configures the device whitelist.
+	Devices []LinuxDeviceCgroup `json:"devices,omitempty"`
+	// Memory restriction configuration
+	Memory *LinuxMemory `json:"memory,omitempty"`
+	// CPU resource restriction configuration
+	CPU *LinuxCPU `json:"cpu,omitempty"`
+	// Task resource restriction configuration.
+	Pids *LinuxPids `json:"pids,omitempty"`
+	// BlockIO restriction configuration
+	BlockIO *LinuxBlockIO `json:"blockIO,omitempty"`
+	// Hugetlb limit (in bytes)
+	HugepageLimits []LinuxHugepageLimit `json:"hugepageLimits,omitempty"`
+	// Network restriction configuration
+	Network *LinuxNetwork `json:"network,omitempty"`
+}
+
+// LinuxDevice represents the mknod information for a Linux special device file
+type LinuxDevice struct {
+	// Path to the device.
+	Path string `json:"path"`
+	// Device type, block, char, etc.
+	Type string `json:"type"`
+	// Major is the device's major number.
+	Major int64 `json:"major"`
+	// Minor is the device's minor number.
+	Minor int64 `json:"minor"`
+	// FileMode permission bits for the device.
+	FileMode *os.FileMode `json:"fileMode,omitempty"`
+	// UID of the device.
+	UID *uint32 `json:"uid,omitempty"`
+	// Gid of the device.
+	GID *uint32 `json:"gid,omitempty"`
+}
+
+// LinuxDeviceCgroup represents a device rule for the whitelist controller
+type LinuxDeviceCgroup struct {
+	// Allow or deny
+	Allow bool `json:"allow"`
+	// Device type, block, char, etc.
+	Type string `json:"type,omitempty"`
+	// Major is the device's major number.
+	Major *int64 `json:"major,omitempty"`
+	// Minor is the device's minor number.
+	Minor *int64 `json:"minor,omitempty"`
+	// Cgroup access permissions format, rwm.
+	Access string `json:"access,omitempty"`
+}
+
+// Solaris contains platform-specific configuration for Solaris application containers.
+type Solaris struct {
+	// SMF FMRI which should go "online" before we start the container process.
+	Milestone string `json:"milestone,omitempty"`
+	// Maximum set of privileges any process in this container can obtain.
+	LimitPriv string `json:"limitpriv,omitempty"`
+	// The maximum amount of shared memory allowed for this container.
+	MaxShmMemory string `json:"maxShmMemory,omitempty"`
+	// Specification for automatic creation of network resources for this container.
+	Anet []SolarisAnet `json:"anet,omitempty"`
+	// Set limit on the amount of CPU time that can be used by container.
+	CappedCPU *SolarisCappedCPU `json:"cappedCPU,omitempty"`
+	// The physical and swap caps on the memory that can be used by this container.
+	CappedMemory *SolarisCappedMemory `json:"cappedMemory,omitempty"`
+}
+
+// SolarisCappedCPU allows users to set limit on the amount of CPU time that can be used by container.
+type SolarisCappedCPU struct {
+	Ncpus string `json:"ncpus,omitempty"`
+}
+
+// SolarisCappedMemory allows users to set the physical and swap caps on the memory that can be used by this container.
+type SolarisCappedMemory struct {
+	Physical string `json:"physical,omitempty"`
+	Swap     string `json:"swap,omitempty"`
+}
+
+// SolarisAnet provides the specification for automatic creation of network resources for this container.
+type SolarisAnet struct {
+	// Specify a name for the automatically created VNIC datalink.
+	Linkname string `json:"linkname,omitempty"`
+	// Specify the link over which the VNIC will be created.
+	Lowerlink string `json:"lowerLink,omitempty"`
+	// The set of IP addresses that the container can use.
+	Allowedaddr string `json:"allowedAddress,omitempty"`
+	// Specifies whether allowedAddress limitation is to be applied to the VNIC.
+	Configallowedaddr string `json:"configureAllowedAddress,omitempty"`
+	// The value of the optional default router.
+	Defrouter string `json:"defrouter,omitempty"`
+	// Enable one or more types of link protection.
+	Linkprotection string `json:"linkProtection,omitempty"`
+	// Set the VNIC's macAddress
+	Macaddress string `json:"macAddress,omitempty"`
+}
+
+// Windows defines the runtime configuration for Windows based containers, including Hyper-V containers.
+type Windows struct {
+	// LayerFolders contains a list of absolute paths to directories containing image layers.
+	LayerFolders []string `json:"layerFolders"`
+	// Resources contains information for handling resource constraints for the container.
+	Resources *WindowsResources `json:"resources,omitempty"`
+	// CredentialSpec contains a JSON object describing a group Managed Service Account (gMSA) specification.
+	CredentialSpec interface{} `json:"credentialSpec,omitempty"`
+	// Servicing indicates if the container is being started in a mode to apply a Windows Update servicing operation.
+	Servicing bool `json:"servicing,omitempty"`
+	// IgnoreFlushesDuringBoot indicates if the container is being started in a mode where disk writes are not flushed during its boot process.
+	IgnoreFlushesDuringBoot bool `json:"ignoreFlushesDuringBoot,omitempty"`
+	// HyperV contains information for running a container with Hyper-V isolation.
+	HyperV *WindowsHyperV `json:"hyperv,omitempty"`
+	// Network restriction configuration.
+	Network *WindowsNetwork `json:"network,omitempty"`
+}
+
+// WindowsResources has container runtime resource constraints for containers running on Windows.
+type WindowsResources struct {
+	// Memory restriction configuration.
+	Memory *WindowsMemoryResources `json:"memory,omitempty"`
+	// CPU resource restriction configuration.
+	CPU *WindowsCPUResources `json:"cpu,omitempty"`
+	// Storage restriction configuration.
+	Storage *WindowsStorageResources `json:"storage,omitempty"`
+}
+
+// WindowsMemoryResources contains memory resource management settings.
+type WindowsMemoryResources struct {
+	// Memory limit in bytes.
+	Limit *uint64 `json:"limit,omitempty"`
+}
+
+// WindowsCPUResources contains CPU resource management settings.
+type WindowsCPUResources struct {
+	// Number of CPUs available to the container.
+	Count *uint64 `json:"count,omitempty"`
+	// CPU shares (relative weight to other containers with cpu shares).
+	Shares *uint16 `json:"shares,omitempty"`
+	// Specifies the portion of processor cycles that this container can use as a percentage times 100.
+	Maximum *uint16 `json:"maximum,omitempty"`
+}
+
+// WindowsStorageResources contains storage resource management settings.
+type WindowsStorageResources struct {
+	// Specifies maximum Iops for the system drive.
+	Iops *uint64 `json:"iops,omitempty"`
+	// Specifies maximum bytes per second for the system drive.
+	Bps *uint64 `json:"bps,omitempty"`
+	// Sandbox size specifies the minimum size of the system drive in bytes.
+	SandboxSize *uint64 `json:"sandboxSize,omitempty"`
+}
+
+// WindowsNetwork contains network settings for Windows containers.
+type WindowsNetwork struct {
+	// List of HNS endpoints that the container should connect to.
+	EndpointList []string `json:"endpointList,omitempty"`
+	// Specifies if unqualified DNS name resolution is allowed.
+	AllowUnqualifiedDNSQuery bool `json:"allowUnqualifiedDNSQuery,omitempty"`
+	// Comma separated list of DNS suffixes to use for name resolution.
+	DNSSearchList []string `json:"DNSSearchList,omitempty"`
+	// Name (ID) of the container that we will share with the network stack.
+	NetworkSharedContainerName string `json:"networkSharedContainerName,omitempty"`
+}
+
+// WindowsHyperV contains information for configuring a container to run with Hyper-V isolation.
+type WindowsHyperV struct {
+	// UtilityVMPath is an optional path to the image used for the Utility VM.
+	UtilityVMPath string `json:"utilityVMPath,omitempty"`
+}
+
+// LinuxSeccomp represents syscall restrictions
+type LinuxSeccomp struct {
+	DefaultAction LinuxSeccompAction `json:"defaultAction"`
+	Architectures []Arch             `json:"architectures,omitempty"`
+	Syscalls      []LinuxSyscall     `json:"syscalls,omitempty"`
+}
+
+// Arch used for additional architectures
+type Arch string
+
+// Additional architectures permitted to be used for system calls
+// By default only the native architecture of the kernel is permitted
+const (
+	ArchX86         Arch = "SCMP_ARCH_X86"
+	ArchX86_64      Arch = "SCMP_ARCH_X86_64"
+	ArchX32         Arch = "SCMP_ARCH_X32"
+	ArchARM         Arch = "SCMP_ARCH_ARM"
+	ArchAARCH64     Arch = "SCMP_ARCH_AARCH64"
+	ArchMIPS        Arch = "SCMP_ARCH_MIPS"
+	ArchMIPS64      Arch = "SCMP_ARCH_MIPS64"
+	ArchMIPS64N32   Arch = "SCMP_ARCH_MIPS64N32"
+	ArchMIPSEL      Arch = "SCMP_ARCH_MIPSEL"
+	ArchMIPSEL64    Arch = "SCMP_ARCH_MIPSEL64"
+	ArchMIPSEL64N32 Arch = "SCMP_ARCH_MIPSEL64N32"
+	ArchPPC         Arch = "SCMP_ARCH_PPC"
+	ArchPPC64       Arch = "SCMP_ARCH_PPC64"
+	ArchPPC64LE     Arch = "SCMP_ARCH_PPC64LE"
+	ArchS390        Arch = "SCMP_ARCH_S390"
+	ArchS390X       Arch = "SCMP_ARCH_S390X"
+	ArchPARISC      Arch = "SCMP_ARCH_PARISC"
+	ArchPARISC64    Arch = "SCMP_ARCH_PARISC64"
+)
+
+// LinuxSeccompAction taken upon Seccomp rule match
+type LinuxSeccompAction string
+
+// Define actions for Seccomp rules
+const (
+	ActKill  LinuxSeccompAction = "SCMP_ACT_KILL"
+	ActTrap  LinuxSeccompAction = "SCMP_ACT_TRAP"
+	ActErrno LinuxSeccompAction = "SCMP_ACT_ERRNO"
+	ActTrace LinuxSeccompAction = "SCMP_ACT_TRACE"
+	ActAllow LinuxSeccompAction = "SCMP_ACT_ALLOW"
+)
+
+// LinuxSeccompOperator used to match syscall arguments in Seccomp
+type LinuxSeccompOperator string
+
+// Define operators for syscall arguments in Seccomp
+const (
+	OpNotEqual     LinuxSeccompOperator = "SCMP_CMP_NE"
+	OpLessThan     LinuxSeccompOperator = "SCMP_CMP_LT"
+	OpLessEqual    LinuxSeccompOperator = "SCMP_CMP_LE"
+	OpEqualTo      LinuxSeccompOperator = "SCMP_CMP_EQ"
+	OpGreaterEqual LinuxSeccompOperator = "SCMP_CMP_GE"
+	OpGreaterThan  LinuxSeccompOperator = "SCMP_CMP_GT"
+	OpMaskedEqual  LinuxSeccompOperator = "SCMP_CMP_MASKED_EQ"
+)
+
+// LinuxSeccompArg used for matching specific syscall arguments in Seccomp
+type LinuxSeccompArg struct {
+	Index    uint                 `json:"index"`
+	Value    uint64               `json:"value"`
+	ValueTwo uint64               `json:"valueTwo,omitempty"`
+	Op       LinuxSeccompOperator `json:"op"`
+}
+
+// LinuxSyscall is used to match a syscall in Seccomp
+type LinuxSyscall struct {
+	Names  []string           `json:"names"`
+	Action LinuxSeccompAction `json:"action"`
+	Args   []LinuxSeccompArg  `json:"args,omitempty"`
+}
+
+// LinuxIntelRdt has container runtime resource constraints
+// for Intel RDT/CAT which introduced in Linux 4.10 kernel
+type LinuxIntelRdt struct {
+	// The schema for L3 cache id and capacity bitmask (CBM)
+	// Format: "L3:<cache_id0>=<cbm0>;<cache_id1>=<cbm1>;..."
+	L3CacheSchema string `json:"l3CacheSchema,omitempty"`
+}

vendor/github.com/opencontainers/runtime-spec/specs-go/state.go

@@ -0,0 +1,17 @@
+package specs
+
+// State holds information about the runtime state of the container.
+type State struct {
+	// Version is the version of the specification that is supported.
+	Version string `json:"ociVersion"`
+	// ID is the container ID
+	ID string `json:"id"`
+	// Status is the runtime status of the container.
+	Status string `json:"status"`
+	// Pid is the process ID for the container process.
+	Pid int `json:"pid,omitempty"`
+	// Bundle is the path to the container's bundle directory.
+	Bundle string `json:"bundle"`
+	// Annotations are key values associated with the container.
+	Annotations map[string]string `json:"annotations,omitempty"`
+}

vendor/github.com/opencontainers/runtime-spec/specs-go/version.go

@@ -0,0 +1,18 @@
+package specs
+
+import "fmt"
+
+const (
+	// VersionMajor is for an API incompatible changes
+	VersionMajor = 1
+	// VersionMinor is for functionality in a backwards-compatible manner
+	VersionMinor = 0
+	// VersionPatch is for backwards-compatible bug fixes
+	VersionPatch = 1
+
+	// VersionDev indicates development branch. Releases will be empty string.
+	VersionDev = ""
+)
+
+// Version is the specification version that the package types support.
+var Version = fmt.Sprintf("%d.%d.%d%s", VersionMajor, VersionMinor, VersionPatch, VersionDev)

vendor/github.com/opencontainers/selinux/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright {yyyy} {name of copyright owner}
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

vendor/github.com/opencontainers/selinux/go-selinux/label/label.go

@@ -0,0 +1,84 @@
+// +build !selinux !linux
+
+package label
+
+// InitLabels returns the process label and file labels to be used within
+// the container.  A list of options can be passed into this function to alter
+// the labels.
+func InitLabels(options []string) (string, string, error) {
+	return "", "", nil
+}
+
+func GetROMountLabel() string {
+	return ""
+}
+
+func GenLabels(options string) (string, string, error) {
+	return "", "", nil
+}
+
+func FormatMountLabel(src string, mountLabel string) string {
+	return src
+}
+
+func SetProcessLabel(processLabel string) error {
+	return nil
+}
+
+func GetFileLabel(path string) (string, error) {
+	return "", nil
+}
+
+func SetFileLabel(path string, fileLabel string) error {
+	return nil
+}
+
+func SetFileCreateLabel(fileLabel string) error {
+	return nil
+}
+
+func Relabel(path string, fileLabel string, shared bool) error {
+	return nil
+}
+
+func GetPidLabel(pid int) (string, error) {
+	return "", nil
+}
+
+func Init() {
+}
+
+func ReserveLabel(label string) error {
+	return nil
+}
+
+func ReleaseLabel(label string) error {
+	return nil
+}
+
+// DupSecOpt takes a process label and returns security options that
+// can be used to set duplicate labels on future container processes
+func DupSecOpt(src string) []string {
+	return nil
+}
+
+// DisableSecOpt returns a security opt that can disable labeling
+// support for future container processes
+func DisableSecOpt() []string {
+	return nil
+}
+
+// Validate checks that the label does not include unexpected options
+func Validate(label string) error {
+	return nil
+}
+
+// RelabelNeeded checks whether the user requested a relabel
+func RelabelNeeded(label string) bool {
+	return false
+}
+
+// IsShared checks that the label includes a "shared" mark
+func IsShared(label string) bool {
+	return false
+}

vendor/github.com/opencontainers/selinux/go-selinux/label/label_selinux.go

@@ -0,0 +1,204 @@
+// +build selinux,linux
+
+package label
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/opencontainers/selinux/go-selinux"
+)
+
+// Valid Label Options
+var validOptions = map[string]bool{
+	"disable": true,
+	"type":    true,
+	"user":    true,
+	"role":    true,
+	"level":   true,
+}
+
+var ErrIncompatibleLabel = fmt.Errorf("Bad SELinux option z and Z can not be used together")
+
+// InitLabels returns the process label and file labels to be used within
+// the container.  A list of options can be passed into this function to alter
+// the labels.  The labels returned will include a random MCS String, that is
+// guaranteed to be unique.
+func InitLabels(options []string) (string, string, error) {
+	if !selinux.GetEnabled() {
+		return "", "", nil
+	}
+	processLabel, mountLabel := selinux.ContainerLabels()
+	if processLabel != "" {
+		pcon := selinux.NewContext(processLabel)
+		mcon := selinux.NewContext(mountLabel)
+		for _, opt := range options {
+			if opt == "disable" {
+				return "", "", nil
+			}
+			if i := strings.Index(opt, ":"); i == -1 {
+				return "", "", fmt.Errorf("Bad label option %q, valid options 'disable' or \n'user, role, level, type' followed by ':' and a value", opt)
+			}
+			con := strings.SplitN(opt, ":", 2)
+			if !validOptions[con[0]] {
+				return "", "", fmt.Errorf("Bad label option %q, valid options 'disable, user, role, level, type'", con[0])
+
+			}
+			pcon[con[0]] = con[1]
+			if con[0] == "level" || con[0] == "user" {
+				mcon[con[0]] = con[1]
+			}
+		}
+		processLabel = pcon.Get()
+		mountLabel = mcon.Get()
+	}
+	return processLabel, mountLabel, nil
+}
+
+func ROMountLabel() string {
+	return selinux.ROFileLabel()
+}
+
+// DEPRECATED: The GenLabels function is only to be used during the transition to the official API.
+func GenLabels(options string) (string, string, error) {
+	return InitLabels(strings.Fields(options))
+}
+
+// FormatMountLabel returns a string to be used by the mount command.
+// The format of this string will be used to alter the labeling of the mountpoint.
+// The string returned is suitable to be used as the options field of the mount command.
+// If you need to have additional mount point options, you can pass them in as
+// the first parameter.  Second parameter is the label that you wish to apply
+// to all content in the mount point.
+func FormatMountLabel(src, mountLabel string) string {
+	if mountLabel != "" {
+		switch src {
+		case "":
+			src = fmt.Sprintf("context=%q", mountLabel)
+		default:
+			src = fmt.Sprintf("%s,context=%q", src, mountLabel)
+		}
+	}
+	return src
+}
+
+// SetProcessLabel takes a process label and tells the kernel to assign the
+// label to the next program executed by the current process.
+func SetProcessLabel(processLabel string) error {
+	if processLabel == "" {
+		return nil
+	}
+	return selinux.SetExecLabel(processLabel)
+}
+
+// ProcessLabel returns the process label that the kernel will assign
+// to the next program executed by the current process.  If "" is returned
+// this indicates that the default labeling will happen for the process.
+func ProcessLabel() (string, error) {
+	return selinux.ExecLabel()
+}
+
+// GetFileLabel returns the label for specified path
+func FileLabel(path string) (string, error) {
+	return selinux.FileLabel(path)
+}
+
+// SetFileLabel modifies the "path" label to the specified file label
+func SetFileLabel(path string, fileLabel string) error {
+	if selinux.GetEnabled() && fileLabel != "" {
+		return selinux.SetFileLabel(path, fileLabel)
+	}
+	return nil
+}
+
+// SetFileCreateLabel tells the kernel the label for all files to be created
+func SetFileCreateLabel(fileLabel string) error {
+	if selinux.GetEnabled() {
+		return selinux.SetFSCreateLabel(fileLabel)
+	}
+	return nil
+}
+
+// Relabel changes the label of path to the filelabel string.
+// It changes the MCS label to s0 if shared is true.
+// This will allow all containers to share the content.
+func Relabel(path string, fileLabel string, shared bool) error {
+	if !selinux.GetEnabled() {
+		return nil
+	}
+
+	if fileLabel == "" {
+		return nil
+	}
+
+	exclude_paths := map[string]bool{"/": true, "/usr": true, "/etc": true}
+	if exclude_paths[path] {
+		return fmt.Errorf("SELinux relabeling of %s is not allowed", path)
+	}
+
+	if shared {
+		c := selinux.NewContext(fileLabel)
+		c["level"] = "s0"
+		fileLabel = c.Get()
+	}
+	if err := selinux.Chcon(path, fileLabel, true); err != nil {
+		return err
+	}
+	return nil
+}
+
+// PidLabel will return the label of the process running with the specified pid
+func PidLabel(pid int) (string, error) {
+	return selinux.PidLabel(pid)
+}
+
+// Init initialises the labeling system
+func Init() {
+	selinux.GetEnabled()
+}
+
+// ReserveLabel will record the fact that the MCS label has already been used.
+// This will prevent InitLabels from using the MCS label in a newly created
+// container
+func ReserveLabel(label string) error {
+	selinux.ReserveLabel(label)
+	return nil
+}
+
+// ReleaseLabel will remove the reservation of the MCS label.
+// This will allow InitLabels to use the MCS label in a newly created
+// containers
+func ReleaseLabel(label string) error {
+	selinux.ReleaseLabel(label)
+	return nil
+}
+
+// DupSecOpt takes a process label and returns security options that
+// can be used to set duplicate labels on future container processes
+func DupSecOpt(src string) []string {
+	return selinux.DupSecOpt(src)
+}
+
+// DisableSecOpt returns a security opt that can disable labeling
+// support for future container processes
+func DisableSecOpt() []string {
+	return selinux.DisableSecOpt()
+}
+
+// Validate checks that the label does not include unexpected options
+func Validate(label string) error {
+	if strings.Contains(label, "z") && strings.Contains(label, "Z") {
+		return ErrIncompatibleLabel
+	}
+	return nil
+}
+
+// RelabelNeeded checks whether the user requested a relabel
+func RelabelNeeded(label string) bool {
+	return strings.Contains(label, "z") || strings.Contains(label, "Z")
+}
+
+// IsShared checks that the label includes a "shared" mark
+func IsShared(label string) bool {
+	return strings.Contains(label, "z")
+}

vendor/github.com/opencontainers/selinux/go-selinux/selinux.go

@@ -0,0 +1,593 @@
+// +build linux
+
+package selinux
+
+import (
+	"bufio"
+	"crypto/rand"
+	"encoding/binary"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strconv"
+	"strings"
+	"sync"
+	"syscall"
+)
+
+const (
+	// Enforcing constant indicate SELinux is in enforcing mode
+	Enforcing = 1
+	// Permissive constant to indicate SELinux is in permissive mode
+	Permissive = 0
+	// Disabled constant to indicate SELinux is disabled
+	Disabled         = -1
+	selinuxDir       = "/etc/selinux/"
+	selinuxConfig    = selinuxDir + "config"
+	selinuxTypeTag   = "SELINUXTYPE"
+	selinuxTag       = "SELINUX"
+	selinuxPath      = "/sys/fs/selinux"
+	xattrNameSelinux = "security.selinux"
+	stRdOnly         = 0x01
+)
+
+type selinuxState struct {
+	enabledSet   bool
+	enabled      bool
+	selinuxfsSet bool
+	selinuxfs    string
+	mcsList      map[string]bool
+	sync.Mutex
+}
+
+var (
+	assignRegex = regexp.MustCompile(`^([^=]+)=(.*)$`)
+	state       = selinuxState{
+		mcsList: make(map[string]bool),
+	}
+)
+
+// Context is a representation of the SELinux label broken into 4 parts
+type Context map[string]string
+
+func (s *selinuxState) setEnable(enabled bool) bool {
+	s.Lock()
+	defer s.Unlock()
+	s.enabledSet = true
+	s.enabled = enabled
+	return s.enabled
+}
+
+func (s *selinuxState) getEnabled() bool {
+	s.Lock()
+	enabled := s.enabled
+	enabledSet := s.enabledSet
+	s.Unlock()
+	if enabledSet {
+		return enabled
+	}
+
+	enabled = false
+	if fs := getSelinuxMountPoint(); fs != "" {
+		if con, _ := CurrentLabel(); con != "kernel" {
+			enabled = true
+		}
+	}
+	return s.setEnable(enabled)
+}
+
+// SetDisabled disables selinux support for the package
+func SetDisabled() {
+	state.setEnable(false)
+}
+
+func (s *selinuxState) setSELinuxfs(selinuxfs string) string {
+	s.Lock()
+	defer s.Unlock()
+	s.selinuxfsSet = true
+	s.selinuxfs = selinuxfs
+	return s.selinuxfs
+}
+
+func (s *selinuxState) getSELinuxfs() string {
+	s.Lock()
+	selinuxfs := s.selinuxfs
+	selinuxfsSet := s.selinuxfsSet
+	s.Unlock()
+	if selinuxfsSet {
+		return selinuxfs
+	}
+
+	selinuxfs = ""
+	f, err := os.Open("/proc/self/mountinfo")
+	if err != nil {
+		return selinuxfs
+	}
+	defer f.Close()
+
+	scanner := bufio.NewScanner(f)
+	for scanner.Scan() {
+		txt := scanner.Text()
+		// Safe as mountinfo encodes mountpoints with spaces as \040.
+		sepIdx := strings.Index(txt, " - ")
+		if sepIdx == -1 {
+			continue
+		}
+		if !strings.Contains(txt[sepIdx:], "selinuxfs") {
+			continue
+		}
+		fields := strings.Split(txt, " ")
+		if len(fields) < 5 {
+			continue
+		}
+		selinuxfs = fields[4]
+		break
+	}
+
+	if selinuxfs != "" {
+		var buf syscall.Statfs_t
+		syscall.Statfs(selinuxfs, &buf)
+		if (buf.Flags & stRdOnly) == 1 {
+			selinuxfs = ""
+		}
+	}
+	return s.setSELinuxfs(selinuxfs)
+}
+
+// getSelinuxMountPoint returns the path to the mountpoint of an selinuxfs
+// filesystem or an empty string if no mountpoint is found.  Selinuxfs is
+// a proc-like pseudo-filesystem that exposes the selinux policy API to
+// processes.  The existence of an selinuxfs mount is used to determine
+// whether selinux is currently enabled or not.
+func getSelinuxMountPoint() string {
+	return state.getSELinuxfs()
+}
+
+// GetEnabled returns whether selinux is currently enabled.
+func GetEnabled() bool {
+	return state.getEnabled()
+}
+
+func readConfig(target string) (value string) {
+	var (
+		val, key string
+		bufin    *bufio.Reader
+	)
+
+	in, err := os.Open(selinuxConfig)
+	if err != nil {
+		return ""
+	}
+	defer in.Close()
+
+	bufin = bufio.NewReader(in)
+
+	for done := false; !done; {
+		var line string
+		if line, err = bufin.ReadString('\n'); err != nil {
+			if err != io.EOF {
+				return ""
+			}
+			done = true
+		}
+		line = strings.TrimSpace(line)
+		if len(line) == 0 {
+			// Skip blank lines
+			continue
+		}
+		if line[0] == ';' || line[0] == '#' {
+			// Skip comments
+			continue
+		}
+		if groups := assignRegex.FindStringSubmatch(line); groups != nil {
+			key, val = strings.TrimSpace(groups[1]), strings.TrimSpace(groups[2])
+			if key == target {
+				return strings.Trim(val, "\"")
+			}
+		}
+	}
+	return ""
+}
+
+func getSELinuxPolicyRoot() string {
+	return selinuxDir + readConfig(selinuxTypeTag)
+}
+
+func readCon(name string) (string, error) {
+	var val string
+
+	in, err := os.Open(name)
+	if err != nil {
+		return "", err
+	}
+	defer in.Close()
+
+	_, err = fmt.Fscanf(in, "%s", &val)
+	return val, err
+}
+
+// SetFileLabel sets the SELinux label for this path or returns an error.
+func SetFileLabel(path string, label string) error {
+	return lsetxattr(path, xattrNameSelinux, []byte(label), 0)
+}
+
+// Filecon returns the SELinux label for this path or returns an error.
+func FileLabel(path string) (string, error) {
+	label, err := lgetxattr(path, xattrNameSelinux)
+	if err != nil {
+		return "", err
+	}
+	// Trim the NUL byte at the end of the byte buffer, if present.
+	if len(label) > 0 && label[len(label)-1] == '\x00' {
+		label = label[:len(label)-1]
+	}
+	return string(label), nil
+}
+
+/*
+SetFSCreateLabel tells kernel the label to create all file system objects
+created by this task. Setting label="" to return to default.
+*/
+func SetFSCreateLabel(label string) error {
+	return writeCon(fmt.Sprintf("/proc/self/task/%d/attr/fscreate", syscall.Gettid()), label)
+}
+
+/*
+FSCreateLabel returns the default label the kernel which the kernel is using
+for file system objects created by this task. "" indicates default.
+*/
+func FSCreateLabel() (string, error) {
+	return readCon(fmt.Sprintf("/proc/self/task/%d/attr/fscreate", syscall.Gettid()))
+}
+
+// CurrentLabel returns the SELinux label of the current process thread, or an error.
+func CurrentLabel() (string, error) {
+	return readCon(fmt.Sprintf("/proc/self/task/%d/attr/current", syscall.Gettid()))
+}
+
+// PidLabel returns the SELinux label of the given pid, or an error.
+func PidLabel(pid int) (string, error) {
+	return readCon(fmt.Sprintf("/proc/%d/attr/current", pid))
+}
+
+/*
+ExecLabel returns the SELinux label that the kernel will use for any programs
+that are executed by the current process thread, or an error.
+*/
+func ExecLabel() (string, error) {
+	return readCon(fmt.Sprintf("/proc/self/task/%d/attr/exec", syscall.Gettid()))
+}
+
+func writeCon(name string, val string) error {
+	out, err := os.OpenFile(name, os.O_WRONLY, 0)
+	if err != nil {
+		return err
+	}
+	defer out.Close()
+
+	if val != "" {
+		_, err = out.Write([]byte(val))
+	} else {
+		_, err = out.Write(nil)
+	}
+	return err
+}
+
+/*
+SetExecLabel sets the SELinux label that the kernel will use for any programs
+that are executed by the current process thread, or an error.
+*/
+func SetExecLabel(label string) error {
+	return writeCon(fmt.Sprintf("/proc/self/task/%d/attr/exec", syscall.Gettid()), label)
+}
+
+// Get returns the Context as a string
+func (c Context) Get() string {
+	return fmt.Sprintf("%s:%s:%s:%s", c["user"], c["role"], c["type"], c["level"])
+}
+
+// NewContext creates a new Context struct from the specified label
+func NewContext(label string) Context {
+	c := make(Context)
+
+	if len(label) != 0 {
+		con := strings.SplitN(label, ":", 4)
+		c["user"] = con[0]
+		c["role"] = con[1]
+		c["type"] = con[2]
+		c["level"] = con[3]
+	}
+	return c
+}
+
+// ReserveLabel reserves the MLS/MCS level component of the specified label
+func ReserveLabel(label string) {
+	if len(label) != 0 {
+		con := strings.SplitN(label, ":", 4)
+		mcsAdd(con[3])
+	}
+}
+
+func selinuxEnforcePath() string {
+	return fmt.Sprintf("%s/enforce", selinuxPath)
+}
+
+// EnforceMode returns the current SELinux mode Enforcing, Permissive, Disabled
+func EnforceMode() int {
+	var enforce int
+
+	enforceS, err := readCon(selinuxEnforcePath())
+	if err != nil {
+		return -1
+	}
+
+	enforce, err = strconv.Atoi(string(enforceS))
+	if err != nil {
+		return -1
+	}
+	return enforce
+}
+
+/*
+SetEnforce sets the current SELinux mode Enforcing, Permissive.
+Disabled is not valid, since this needs to be set at boot time.
+*/
+func SetEnforceMode(mode int) error {
+	return writeCon(selinuxEnforcePath(), fmt.Sprintf("%d", mode))
+}
+
+/*
+DefaultEnforceMode returns the systems default SELinux mode Enforcing,
+Permissive or Disabled. Note this is is just the default at boot time.
+EnforceMode tells you the systems current mode.
+*/
+func DefaultEnforceMode() int {
+	switch readConfig(selinuxTag) {
+	case "enforcing":
+		return Enforcing
+	case "permissive":
+		return Permissive
+	}
+	return Disabled
+}
+
+func mcsAdd(mcs string) error {
+	state.Lock()
+	defer state.Unlock()
+	if state.mcsList[mcs] {
+		return fmt.Errorf("MCS Label already exists")
+	}
+	state.mcsList[mcs] = true
+	return nil
+}
+
+func mcsDelete(mcs string) {
+	state.Lock()
+	defer state.Unlock()
+	state.mcsList[mcs] = false
+}
+
+func intToMcs(id int, catRange uint32) string {
+	var (
+		SETSIZE = int(catRange)
+		TIER    = SETSIZE
+		ORD     = id
+	)
+
+	if id < 1 || id > 523776 {
+		return ""
+	}
+
+	for ORD > TIER {
+		ORD = ORD - TIER
+		TIER--
+	}
+	TIER = SETSIZE - TIER
+	ORD = ORD + TIER
+	return fmt.Sprintf("s0:c%d,c%d", TIER, ORD)
+}
+
+func uniqMcs(catRange uint32) string {
+	var (
+		n      uint32
+		c1, c2 uint32
+		mcs    string
+	)
+
+	for {
+		binary.Read(rand.Reader, binary.LittleEndian, &n)
+		c1 = n % catRange
+		binary.Read(rand.Reader, binary.LittleEndian, &n)
+		c2 = n % catRange
+		if c1 == c2 {
+			continue
+		} else {
+			if c1 > c2 {
+				c1, c2 = c2, c1
+			}
+		}
+		mcs = fmt.Sprintf("s0:c%d,c%d", c1, c2)
+		if err := mcsAdd(mcs); err != nil {
+			continue
+		}
+		break
+	}
+	return mcs
+}
+
+/*
+ReleaseLabel will unreserve the MLS/MCS Level field of the specified label.
+Allowing it to be used by another process.
+*/
+func ReleaseLabel(label string) {
+	if len(label) != 0 {
+		con := strings.SplitN(label, ":", 4)
+		mcsDelete(con[3])
+	}
+}
+
+var roFileLabel string
+
+// ROFileLabel returns the specified SELinux readonly file label
+func ROFileLabel() (fileLabel string) {
+	return roFileLabel
+}
+
+/*
+ContainerLabels returns an allocated processLabel and fileLabel to be used for
+container labeling by the calling process.
+*/
+func ContainerLabels() (processLabel string, fileLabel string) {
+	var (
+		val, key string
+		bufin    *bufio.Reader
+	)
+
+	if !GetEnabled() {
+		return "", ""
+	}
+	lxcPath := fmt.Sprintf("%s/contexts/lxc_contexts", getSELinuxPolicyRoot())
+	in, err := os.Open(lxcPath)
+	if err != nil {
+		return "", ""
+	}
+	defer in.Close()
+
+	bufin = bufio.NewReader(in)
+
+	for done := false; !done; {
+		var line string
+		if line, err = bufin.ReadString('\n'); err != nil {
+			if err == io.EOF {
+				done = true
+			} else {
+				goto exit
+			}
+		}
+		line = strings.TrimSpace(line)
+		if len(line) == 0 {
+			// Skip blank lines
+			continue
+		}
+		if line[0] == ';' || line[0] == '#' {
+			// Skip comments
+			continue
+		}
+		if groups := assignRegex.FindStringSubmatch(line); groups != nil {
+			key, val = strings.TrimSpace(groups[1]), strings.TrimSpace(groups[2])
+			if key == "process" {
+				processLabel = strings.Trim(val, "\"")
+			}
+			if key == "file" {
+				fileLabel = strings.Trim(val, "\"")
+			}
+			if key == "ro_file" {
+				roFileLabel = strings.Trim(val, "\"")
+			}
+		}
+	}
+
+	if processLabel == "" || fileLabel == "" {
+		return "", ""
+	}
+
+	if roFileLabel == "" {
+		roFileLabel = fileLabel
+	}
+exit:
+	mcs := uniqMcs(1024)
+	scon := NewContext(processLabel)
+	scon["level"] = mcs
+	processLabel = scon.Get()
+	scon = NewContext(fileLabel)
+	scon["level"] = mcs
+	fileLabel = scon.Get()
+	return processLabel, fileLabel
+}
+
+// SecurityCheckContext validates that the SELinux label is understood by the kernel
+func SecurityCheckContext(val string) error {
+	return writeCon(fmt.Sprintf("%s.context", selinuxPath), val)
+}
+
+/*
+CopyLevel returns a label with the MLS/MCS level from src label replaces on
+the dest label.
+*/
+func CopyLevel(src, dest string) (string, error) {
+	if src == "" {
+		return "", nil
+	}
+	if err := SecurityCheckContext(src); err != nil {
+		return "", err
+	}
+	if err := SecurityCheckContext(dest); err != nil {
+		return "", err
+	}
+	scon := NewContext(src)
+	tcon := NewContext(dest)
+	mcsDelete(tcon["level"])
+	mcsAdd(scon["level"])
+	tcon["level"] = scon["level"]
+	return tcon.Get(), nil
+}
+
+// Prevent users from relabing system files
+func badPrefix(fpath string) error {
+	var badprefixes = []string{"/usr"}
+
+	for _, prefix := range badprefixes {
+		if fpath == prefix || strings.HasPrefix(fpath, fmt.Sprintf("%s/", prefix)) {
+			return fmt.Errorf("relabeling content in %s is not allowed", prefix)
+		}
+	}
+	return nil
+}
+
+// Chcon changes the fpath file object to the SELinux label label.
+// If the fpath is a directory and recurse is true Chcon will walk the
+// directory tree setting the label
+func Chcon(fpath string, label string, recurse bool) error {
+	if label == "" {
+		return nil
+	}
+	if err := badPrefix(fpath); err != nil {
+		return err
+	}
+	callback := func(p string, info os.FileInfo, err error) error {
+		return SetFileLabel(p, label)
+	}
+
+	if recurse {
+		return filepath.Walk(fpath, callback)
+	}
+
+	return SetFileLabel(fpath, label)
+}
+
+// DupSecOpt takes an SELinux process label and returns security options that
+// can will set the SELinux Type and Level for future container processes
+func DupSecOpt(src string) []string {
+	if src == "" {
+		return nil
+	}
+	con := NewContext(src)
+	if con["user"] == "" ||
+		con["role"] == "" ||
+		con["type"] == "" ||
+		con["level"] == "" {
+		return nil
+	}
+	return []string{"user:" + con["user"],
+		"role:" + con["role"],
+		"type:" + con["type"],
+		"level:" + con["level"]}
+}
+
+// DisableSecOpt returns a security opt that can be used to disabling SELinux
+// labeling support for future container processes
+func DisableSecOpt() []string {
+	return []string{"disable"}
+}

vendor/github.com/opencontainers/selinux/go-selinux/xattrs.go

@@ -0,0 +1,78 @@
+// +build linux
+
+package selinux
+
+import (
+	"syscall"
+	"unsafe"
+)
+
+var _zero uintptr
+
+// Returns a []byte slice if the xattr is set and nil otherwise
+// Requires path and its attribute as arguments
+func lgetxattr(path string, attr string) ([]byte, error) {
+	var sz int
+	pathBytes, err := syscall.BytePtrFromString(path)
+	if err != nil {
+		return nil, err
+	}
+	attrBytes, err := syscall.BytePtrFromString(attr)
+	if err != nil {
+		return nil, err
+	}
+
+	// Start with a 128 length byte array
+	sz = 128
+	dest := make([]byte, sz)
+	destBytes := unsafe.Pointer(&dest[0])
+	_sz, _, errno := syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(destBytes), uintptr(len(dest)), 0, 0)
+
+	switch {
+	case errno == syscall.ENODATA:
+		return nil, errno
+	case errno == syscall.ENOTSUP:
+		return nil, errno
+	case errno == syscall.ERANGE:
+		// 128 byte array might just not be good enough,
+		// A dummy buffer is used ``uintptr(0)`` to get real size
+		// of the xattrs on disk
+		_sz, _, errno = syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(unsafe.Pointer(nil)), uintptr(0), 0, 0)
+		sz = int(_sz)
+		if sz < 0 {
+			return nil, errno
+		}
+		dest = make([]byte, sz)
+		destBytes := unsafe.Pointer(&dest[0])
+		_sz, _, errno = syscall.Syscall6(syscall.SYS_LGETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(destBytes), uintptr(len(dest)), 0, 0)
+		if errno != 0 {
+			return nil, errno
+		}
+	case errno != 0:
+		return nil, errno
+	}
+	sz = int(_sz)
+	return dest[:sz], nil
+}
+
+func lsetxattr(path string, attr string, data []byte, flags int) error {
+	pathBytes, err := syscall.BytePtrFromString(path)
+	if err != nil {
+		return err
+	}
+	attrBytes, err := syscall.BytePtrFromString(attr)
+	if err != nil {
+		return err
+	}
+	var dataBytes unsafe.Pointer
+	if len(data) > 0 {
+		dataBytes = unsafe.Pointer(&data[0])
+	} else {
+		dataBytes = unsafe.Pointer(&_zero)
+	}
+	_, _, errno := syscall.Syscall6(syscall.SYS_LSETXATTR, uintptr(unsafe.Pointer(pathBytes)), uintptr(unsafe.Pointer(attrBytes)), uintptr(dataBytes), uintptr(len(data)), uintptr(flags), 0)
+	if errno != 0 {
+		return errno
+	}
+	return nil
+}