OSSInnovation
/
runc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Refactor device handling code 

We now have one place that keeps track of (most) devices that are allowed and created within the container.  That place is pkg/libcontainer/devices/devices.go

This fixes several inconsistencies between which devices were created in the lxc backend and the native backend.  It also fixes inconsistencies between wich devices were created and which were allowed.  For example, /dev/full was being created but it was not allowed within the cgroup.  It also declares the file modes and permissions of the default devices, rather than copying them from the host.  This is in line with docker's philosphy of not being host dependent.

Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
This commit is contained in:
Timothy Hobbs 2014-02-17 15:14:30 -08:00 committed by Timothy
parent 5db18f2d5d
commit 18f6a5aaf4
11 changed files with 377 additions and 144 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
cgroups/cgroups.go
View File

@ -2,6 +2,8 @@ package cgroups
import (
"errors"
"github.com/dotcloud/docker/pkg/libcontainer/devices"
)
var (
@ -10,17 +12,18 @@ var (
type Cgroup struct {
Name string `json:"name,omitempty"`
Parent string `json:"parent,omitempty"`
Parent string `json:"parent,omitempty"` // name of parent cgroup or slice
DeviceAccess bool `json:"device_access,omitempty"` // name of parent cgroup or slice
Memory int64 `json:"memory,omitempty"` // Memory limit (in bytes)
MemoryReservation int64 `json:"memory_reservation,omitempty"` // Memory reservation or soft_limit (in bytes)
MemorySwap int64 `json:"memory_swap,omitempty"` // Total memory usage (memory + swap); set `-1' to disable swap
CpuShares int64 `json:"cpu_shares,omitempty"` // CPU shares (relative weight vs. other containers)
CpuQuota int64 `json:"cpu_quota,omitempty"` // CPU hardcap limit (in usecs). Allowed cpu time in a given period.
CpuPeriod int64 `json:"cpu_period,omitempty"` // CPU period to be used for hardcapping (in usecs). 0 to use system default.
CpusetCpus string `json:"cpuset_cpus,omitempty"` // CPU to use
Freezer string `json:"freezer,omitempty"` // set the freeze value for the process
AllowAllDevices bool `json:"allow_all_devices,omitempty"` // If this is true allow access to any kind of device within the container. If false, allow access only to devices explicitly listed in the allowed_devices list.
AllowedDevices []devices.Device `json:"allowed_devices,omitempty"`
Memory int64 `json:"memory,omitempty"` // Memory limit (in bytes)
MemoryReservation int64 `json:"memory_reservation,omitempty"` // Memory reservation or soft_limit (in bytes)
MemorySwap int64 `json:"memory_swap,omitempty"` // Total memory usage (memory + swap); set `-1' to disable swap
CpuShares int64 `json:"cpu_shares,omitempty"` // CPU shares (relative weight vs. other containers)
CpuQuota int64 `json:"cpu_quota,omitempty"` // CPU hardcap limit (in usecs). Allowed cpu time in a given period.
CpuPeriod int64 `json:"cpu_period,omitempty"` // CPU period to be used for hardcapping (in usecs). 0 to use system default.
CpusetCpus string `json:"cpuset_cpus,omitempty"` // CPU to use
Freezer string `json:"freezer,omitempty"` // set the freeze value for the process
Slice string `json:"slice,omitempty"` // Parent slice to use for systemd
}

34
cgroups/fs/devices.go
View File

@ -9,41 +9,13 @@ func (s *devicesGroup) Set(d *data) error {
return err
}
if !d.c.DeviceAccess {
if !d.c.AllowAllDevices {
if err := writeFile(dir, "devices.deny", "a"); err != nil {
return err
}
allow := []string{
// allow mknod for any device
"c *:* m",
"b *:* m",
// /dev/null, zero, full
"c 1:3 rwm",
"c 1:5 rwm",
"c 1:7 rwm",
// consoles
"c 5:1 rwm",
"c 5:0 rwm",
"c 4:0 rwm",
"c 4:1 rwm",
// /dev/urandom,/dev/random
"c 1:9 rwm",
"c 1:8 rwm",
// /dev/pts/ - pts namespaces are "coming soon"
"c 136:* rwm",
"c 5:2 rwm",
// tuntap
"c 10:200 rwm",
}
for _, val := range allow {
if err := writeFile(dir, "devices.allow", val); err != nil {
for _, dev := range d.c.AllowedDevices {
if err := writeFile(dir, "devices.allow", dev.GetCgroupAllowString()); err != nil {
return err
}
}

50
cgroups/systemd/apply_systemd.go
View File

@ -21,11 +21,6 @@ type systemdCgroup struct {
cleanupDirs []string
}
type DeviceAllow struct {
Node string
Permissions string
}
var (
connLock sync.Mutex
theConn *systemd1.Conn
@ -116,24 +111,9 @@ func Apply(c *cgroups.Cgroup, pid int) (cgroups.ActiveCgroup, error) {
systemd1.Property{"PIDs", dbus.MakeVariant([]uint32{uint32(pid)})},
)
if !c.DeviceAccess {
if !c.AllowAllDevices {
properties = append(properties,
systemd1.Property{"DevicePolicy", dbus.MakeVariant("strict")},
systemd1.Property{"DeviceAllow", dbus.MakeVariant([]DeviceAllow{
{"/dev/null", "rwm"},
{"/dev/zero", "rwm"},
{"/dev/full", "rwm"},
{"/dev/random", "rwm"},
{"/dev/urandom", "rwm"},
{"/dev/tty", "rwm"},
{"/dev/console", "rwm"},
{"/dev/tty0", "rwm"},
{"/dev/tty1", "rwm"},
{"/dev/pts/ptmx", "rwm"},
// There is no way to add /dev/pts/* here atm, so we hack this manually below
// /dev/pts/* (how to add this?)
// Same with tuntap, which doesn't exist as a node most of the time
})})
systemd1.Property{"DevicePolicy", dbus.MakeVariant("strict")})
}
// Always enable accounting, this gets us the same behaviour as the fs implementation,
@ -167,28 +147,16 @@ func Apply(c *cgroups.Cgroup, pid int) (cgroups.ActiveCgroup, error) {
cgroup := props["ControlGroup"].(string)
if !c.DeviceAccess {
if !c.AllowAllDevices {
mountpoint, err := cgroups.FindCgroupMountpoint("devices")
if err != nil {
return nil, err
}
path := filepath.Join(mountpoint, cgroup)
allow := []string{
// allow mknod for any device
"c *:* m",
"b *:* m",
// /dev/pts/ - pts namespaces are "coming soon"
"c 136:* rwm",
// tuntap
"c 10:200 rwm",
}
for _, val := range allow {
if err := ioutil.WriteFile(filepath.Join(path, "devices.allow"), []byte(val), 0700); err != nil {
dir := filepath.Join(mountpoint, cgroup)
// We use the same method of allowing devices as in the fs backend. This needs to be changed to use DBUS as soon as possible. However, that change has to wait untill http://cgit.freedesktop.org/systemd/systemd/commit/?id=90060676c442604780634c0a993e3f9c3733f8e6 has been applied in most commonly used systemd versions.
for _, dev := range c.AllowedDevices {
if err := writeFile(dir, "devices.allow", dev.GetCgroupAllowString()); err != nil {
return nil, err
}
}
@ -295,6 +263,10 @@ func Apply(c *cgroups.Cgroup, pid int) (cgroups.ActiveCgroup, error) {
return &res, nil
}
func writeFile(dir, file, data string) error {
return ioutil.WriteFile(filepath.Join(dir, file), []byte(data), 0700)
}
func (c *systemdCgroup) Cleanup() error {
// systemd cleans up, we don't need to do much

10
container.go
View File

@ -2,6 +2,7 @@ package libcontainer
import (
"github.com/dotcloud/docker/pkg/libcontainer/cgroups"
"github.com/dotcloud/docker/pkg/libcontainer/devices"
)
// Context is a generic key value pair that allows arbatrary data to be sent
@ -60,13 +61,8 @@ type Container struct {
// rootfs and mount namespace if specified
Mounts Mounts `json:"mounts,omitempty"`
// RequiredDeviceNodes are a list of device nodes that will be mknod into the container's rootfs at /dev
// If the host system does not support the device that the container requests an error is returned
RequiredDeviceNodes []string `json:"required_device_nodes,omitempty"`
// OptionalDeviceNodes are a list of device nodes that will be mknod into the container's rootfs at /dev
// If the host system does not support the device that the container requests the error is ignored
OptionalDeviceNodes []string `json:"optional_device_nodes,omitempty"`
// The device nodes that should be automatically created within the container upon container start. Note, make sure that the node is marked as allowed in the cgroup as well!
DeviceNodes []devices.Device `json:"device_nodes,omitempty"`
}
// Network defines configuration for a container's networking stack

56
container.json
View File

@ -44,12 +44,54 @@
"type": "devtmpfs"
}
],
"required_device_nodes": [
"/dev/null",
"/dev/zero",
"/dev/full",
"/dev/random",
"/dev/urandom",
"/dev/tty"
"device_nodes": [
{
"path": "/dev/null",
"type": 99,
"major_number": 1,
"minor_number": 3,
"cgroup_permissions": "rwm",
"file_mode": 438
},
{
"path": "/dev/zero",
"type": 99,
"major_number": 1,
"minor_number": 5,
"cgroup_permissions": "rwm",
"file_mode": 438
},
{
"path": "/dev/full",
"type": 99,
"major_number": 1,
"minor_number": 7,
"cgroup_permissions": "rwm",
"file_mode": 438
},
{
"path": "/dev/tty",
"type": 99,
"major_number": 5,
"minor_number": 0,
"cgroup_permissions": "rwm",
"file_mode": 438
},
{
"path": "/dev/urandom",
"type": 99,
"major_number": 1,
"minor_number": 9,
"cgroup_permissions": "rwm",
"file_mode": 438
},
{
"path": "/dev/random",
"type": 99,
"major_number": 1,
"minor_number": 8,
"cgroup_permissions": "rwm",
"file_mode": 438
}
]
}

9
container_test.go
View File

@ -4,8 +4,6 @@ import (
"encoding/json"
"os"
"testing"
"github.com/dotcloud/docker/pkg/libcontainer/mount/nodes"
)
// Checks whether the expected capability is specified in the capabilities.
@ -63,11 +61,4 @@ func TestContainerJsonFormat(t *testing.T) {
t.Log("capabilities mask should not contain SYS_CHROOT")
t.Fail()
}
for _, n := range nodes.DefaultNodes {
if !contains(n, container.RequiredDeviceNodes) {
t.Logf("devices should contain %s", n)
t.Fail()
}
}
}

239
devices/devices.go Normal file
View File

@ -0,0 +1,239 @@
package devices
import (
"fmt"
"os"
"syscall"
)
const (
Wildcard = -1
)
type Device struct {
Type rune `json:"type,omitempty"`
Path string `json:"path,omitempty"` // It is fine if this is an empty string in the case that you are using Wildcards
MajorNumber int64 `json:"major_number,omitempty"` // Use the wildcard constant for wildcards.
MinorNumber int64 `json:"minor_number,omitempty"` // Use the wildcard constant for wildcards.
CgroupPermissions string `json:"cgroup_permissions,omitempty"` // Typically just "rwm"
FileMode os.FileMode `json:"file_mode,omitempty"` // The permission bits of the file's mode
}
func GetDeviceNumberString(deviceNumber int64) string {
if deviceNumber == Wildcard {
return "*"
} else {
return fmt.Sprintf("%d", deviceNumber)
}
}
func (device Device) GetCgroupAllowString() string {
return fmt.Sprintf("%c %s:%s %s", device.Type, GetDeviceNumberString(device.MajorNumber), GetDeviceNumberString(device.MinorNumber), device.CgroupPermissions)
}
// Given the path to a device and it's cgroup_permissions(which cannot be easilly queried) look up the information about a linux device and return that information as a Device struct.
func GetDevice(path string, cgroupPermissions string) (Device, error) {
var (
err error
fileInfo os.FileInfo
mode os.FileMode
fileModePermissionBits os.FileMode
devType rune
devNumber int
stat_t *syscall.Stat_t
ok bool
device Device
)
fileInfo, err = os.Stat(path)
if err != nil {
return Device{}, err
}
mode = fileInfo.Mode()
fileModePermissionBits = os.FileMode.Perm(mode)
switch {
case (mode & os.ModeDevice) == 0:
return Device{}, fmt.Errorf("%s is not a device", path)
case (mode & os.ModeCharDevice) != 0:
fileModePermissionBits |= syscall.S_IFCHR
devType = 'c'
default:
fileModePermissionBits |= syscall.S_IFBLK
devType = 'b'
}
stat_t, ok = fileInfo.Sys().(*syscall.Stat_t)
if !ok {
return Device{}, fmt.Errorf("cannot determine the device number for device %s", path)
}
devNumber = int(stat_t.Rdev)
device = Device{
Type: devType,
Path: path,
MajorNumber: Major(devNumber),
MinorNumber: Minor(devNumber),
CgroupPermissions: cgroupPermissions,
FileMode: fileModePermissionBits,
}
return device, nil
}
var (
// These are devices that are to be both allowed and created.
DefaultSimpleDevices = []Device{
// /dev/null and zero
{
Path: "/dev/null",
Type: 'c',
MajorNumber: 1,
MinorNumber: 3,
CgroupPermissions: "rwm",
FileMode: 0666,
},
{
Path: "/dev/zero",
Type: 'c',
MajorNumber: 1,
MinorNumber: 5,
CgroupPermissions: "rwm",
FileMode: 0666,
},
{
Path: "/dev/full",
Type: 'c',
MajorNumber: 1,
MinorNumber: 7,
CgroupPermissions: "rwm",
FileMode: 0666,
},
// consoles and ttys
{
Path: "/dev/tty",
Type: 'c',
MajorNumber: 5,
MinorNumber: 0,
CgroupPermissions: "rwm",
FileMode: 0666,
},
// /dev/urandom,/dev/random
{
Path: "/dev/urandom",
Type: 'c',
MajorNumber: 1,
MinorNumber: 9,
CgroupPermissions: "rwm",
FileMode: 0666,
},
{
Path: "/dev/random",
Type: 'c',
MajorNumber: 1,
MinorNumber: 8,
CgroupPermissions: "rwm",
FileMode: 0666,
},
}
DefaultAllowedDevices = append([]Device{
// allow mknod for any device
{
Type: 'c',
MajorNumber: Wildcard,
MinorNumber: Wildcard,
CgroupPermissions: "m",
},
{
Type: 'b',
MajorNumber: Wildcard,
MinorNumber: Wildcard,
CgroupPermissions: "m",
},
{
Path: "/dev/console",
Type: 'c',
MajorNumber: 5,
MinorNumber: 1,
CgroupPermissions: "rwm",
},
{
Path: "/dev/tty0",
Type: 'c',
MajorNumber: 4,
MinorNumber: 0,
CgroupPermissions: "rwm",
},
{
Path: "/dev/tty1",
Type: 'c',
MajorNumber: 4,
MinorNumber: 1,
CgroupPermissions: "rwm",
},
// /dev/pts/ - pts namespaces are "coming soon"
{
Path: "",
Type: 'c',
MajorNumber: 136,
MinorNumber: Wildcard,
CgroupPermissions: "rwm",
},
{
Path: "",
Type: 'c',
MajorNumber: 5,
MinorNumber: 2,
CgroupPermissions: "rwm",
},
// tuntap
{
Path: "",
Type: 'c',
MajorNumber: 10,
MinorNumber: 200,
CgroupPermissions: "rwm",
},
/*// fuse
{
Path: "",
Type: 'c',
MajorNumber: 10,
MinorNumber: 229,
CgroupPermissions: "rwm",
},
// rtc
{
Path: "",
Type: 'c',
MajorNumber: 254,
MinorNumber: 0,
CgroupPermissions: "rwm",
},
*/
}, DefaultSimpleDevices...)
DefaultAutoCreatedDevices = append([]Device{
{
// /dev/fuse is created but not allowed.
// This is to allow java to work. Because java
// Insists on there being a /dev/fuse
// https://github.com/dotcloud/docker/issues/514
// https://github.com/dotcloud/docker/issues/2393
//
Path: "/dev/fuse",
Type: 'c',
MajorNumber: 10,
MinorNumber: 229,
CgroupPermissions: "rwm",
},
}, DefaultSimpleDevices...)
)

26
devices/number.go Normal file
View File

@ -0,0 +1,26 @@
package devices
/*
This code provides support for manipulating linux device numbers. It should be replaced by normal syscall functions once http://code.google.com/p/go/issues/detail?id=8106 is solved.
You can read what they are here:
- http://www.makelinux.net/ldd3/chp-3-sect-2
- http://www.linux-tutorial.info/modules.php?name=MContent&pageid=94
Note! These are NOT the same as the MAJOR(dev_t device);, MINOR(dev_t device); and MKDEV(int major, int minor); functions as defined in <linux/kdev_t.h> as the representation of device numbers used by go is different than the one used internally to the kernel! - https://github.com/torvalds/linux/blob/master/include/linux/kdev_t.h#L9
*/
func Major(devNumber int) int64 {
return int64((devNumber >> 8) & 0xfff)
}
func Minor(devNumber int) int64 {
return int64((devNumber & 0xff) | ((devNumber >> 12) & 0xfff00))
}
func Mkdev(majorNumber int64, minorNumber int64) int {
return int((majorNumber << 8) | (minorNumber & 0xff) | ((minorNumber & 0xfff00) << 12))
}

7
mount/init.go
View File

@ -48,11 +48,8 @@ func InitializeMountNamespace(rootfs, console string, container *libcontainer.Co
if err := setupBindmounts(rootfs, container.Mounts); err != nil {
return fmt.Errorf("bind mounts %s", err)
}
if err := nodes.CopyN(rootfs, container.RequiredDeviceNodes, true); err != nil {
return fmt.Errorf("copy required dev nodes %s", err)
}
if err := nodes.CopyN(rootfs, container.OptionalDeviceNodes, false); err != nil {
return fmt.Errorf("copy optional dev nodes %s", err)
if err := nodes.CreateDeviceNodes(rootfs, container.DeviceNodes); err != nil {
return fmt.Errorf("create device nodes %s", err)
}
if err := SetupPtmx(rootfs, console, container.Context["mount_label"]); err != nil {
return err

56
mount/nodes/nodes.go
View File

@ -9,47 +9,27 @@ import (
"path/filepath"
"syscall"
"github.com/dotcloud/docker/pkg/libcontainer/devices"
"github.com/dotcloud/docker/pkg/system"
)
// Default list of device nodes to copy
var DefaultNodes = []string{
"/dev/null",
"/dev/zero",
"/dev/full",
"/dev/random",
"/dev/urandom",
"/dev/tty",
}
// CopyN copies the device node from the host into the rootfs
func CopyN(rootfs string, nodesToCopy []string, shouldExist bool) error {
// Create the device nodes in the container.
func CreateDeviceNodes(rootfs string, nodesToCreate []devices.Device) error {
oldMask := system.Umask(0000)
defer system.Umask(oldMask)
for _, node := range nodesToCopy {
if err := Copy(rootfs, node, shouldExist); err != nil {
for _, node := range nodesToCreate {
if err := CreateDeviceNode(rootfs, node); err != nil {
return err
}
}
return nil
}
// Copy copies the device node into the rootfs. If the node
// on the host system does not exist and the boolean flag is passed
// an error will be returned
func Copy(rootfs, node string, shouldExist bool) error {
stat, err := os.Stat(node)
if err != nil {
if os.IsNotExist(err) && !shouldExist {
return nil
}
return err
}
// Creates the device node in the rootfs of the container.
func CreateDeviceNode(rootfs string, node devices.Device) error {
var (
dest = filepath.Join(rootfs, node)
st = stat.Sys().(*syscall.Stat_t)
dest = filepath.Join(rootfs, node.Path)
parent = filepath.Dir(dest)
)
@ -57,13 +37,23 @@ func Copy(rootfs, node string, shouldExist bool) error {
return err
}
if err := system.Mknod(dest, st.Mode, int(st.Rdev)); err != nil && !os.IsExist(err) {
return fmt.Errorf("mknod %s %s", node, err)
fileMode := node.FileMode
switch node.Type {
case 'c':
fileMode |= syscall.S_IFCHR
case 'b':
fileMode |= syscall.S_IFBLK
default:
return fmt.Errorf("%c is not a valid device type for device %s", node.Type, node.Path)
}
if err := system.Mknod(dest, uint32(fileMode), devices.Mkdev(node.MajorNumber, node.MinorNumber)); err != nil && !os.IsExist(err) {
return fmt.Errorf("mknod %s %s", node.Path, err)
}
return nil
}
func getNodes(path string) ([]string, error) {
func getDeviceNodes(path string) ([]string, error) {
out := []string{}
files, err := ioutil.ReadDir(path)
if err != nil {
@ -71,7 +61,7 @@ func getNodes(path string) ([]string, error) {
}
for _, f := range files {
if f.IsDir() && f.Name() != "pts" && f.Name() != "shm" {
sub, err := getNodes(filepath.Join(path, f.Name()))
sub, err := getDeviceNodes(filepath.Join(path, f.Name()))
if err != nil {
return nil, err
}
@ -84,5 +74,5 @@ func getNodes(path string) ([]string, error) {
}
func GetHostDeviceNodes() ([]string, error) {
return getNodes("/dev")
return getDeviceNodes("/dev")
}

11
mount/nodes/nodes_unsupported.go
View File

@ -2,10 +2,15 @@
package nodes
import "github.com/dotcloud/docker/pkg/libcontainer"
var DefaultNodes = []string{}
import (
"github.com/dotcloud/docker/pkg/libcontainer"
"github.com/dotcloud/docker/pkg/libcontainer/devices"
)
func GetHostDeviceNodes() ([]string, error) {
return nil, libcontainer.ErrUnsupported
}
func CreateDeviceNodes(rootfs string, nodesToCreate []devices.Device) error {
return libcontainer.ErrUnsupported
}