File: utils_linux.go

package info (click to toggle)
runc 1.0.0~rc6+dfsg1-3
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 1,972 kB
  • sloc: sh: 1,386; ansic: 946; makefile: 117
file content (439 lines) | stat: -rw-r--r-- 11,766 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
// +build linux

package main

import (
	"errors"
	"fmt"
	"net"
	"os"
	"os/exec"
	"path/filepath"
	"strconv"

	"github.com/opencontainers/runc/libcontainer"
	"github.com/opencontainers/runc/libcontainer/cgroups/systemd"
	"github.com/opencontainers/runc/libcontainer/configs"
	"github.com/opencontainers/runc/libcontainer/intelrdt"
	"github.com/opencontainers/runc/libcontainer/specconv"
	"github.com/opencontainers/runc/libcontainer/utils"
	"github.com/opencontainers/runtime-spec/specs-go"

	"github.com/coreos/go-systemd/activation"
	"github.com/sirupsen/logrus"
	"github.com/urfave/cli"
	"golang.org/x/sys/unix"
)

var errEmptyID = errors.New("container id cannot be empty")

// loadFactory returns the configured factory instance for execing containers.
func loadFactory(context *cli.Context) (libcontainer.Factory, error) {
	root := context.GlobalString("root")
	abs, err := filepath.Abs(root)
	if err != nil {
		return nil, err
	}

	// We default to cgroupfs, and can only use systemd if the system is a
	// systemd box.
	cgroupManager := libcontainer.Cgroupfs
	rootlessCg, err := shouldUseRootlessCgroupManager(context)
	if err != nil {
		return nil, err
	}
	if rootlessCg {
		cgroupManager = libcontainer.RootlessCgroupfs
	}
	if context.GlobalBool("systemd-cgroup") {
		if systemd.UseSystemd() {
			cgroupManager = libcontainer.SystemdCgroups
		} else {
			return nil, fmt.Errorf("systemd cgroup flag passed, but systemd support for managing cgroups is not available")
		}
	}

	intelRdtManager := libcontainer.IntelRdtFs
	if !intelrdt.IsCatEnabled() && !intelrdt.IsMbaEnabled() {
		intelRdtManager = nil
	}

	// We resolve the paths for {newuidmap,newgidmap} from the context of runc,
	// to avoid doing a path lookup in the nsexec context. TODO: The binary
	// names are not currently configurable.
	newuidmap, err := exec.LookPath("newuidmap")
	if err != nil {
		newuidmap = ""
	}
	newgidmap, err := exec.LookPath("newgidmap")
	if err != nil {
		newgidmap = ""
	}

	return libcontainer.New(abs, cgroupManager, intelRdtManager,
		libcontainer.CriuPath(context.GlobalString("criu")),
		libcontainer.NewuidmapPath(newuidmap),
		libcontainer.NewgidmapPath(newgidmap))
}

// getContainer returns the specified container instance by loading it from state
// with the default factory.
func getContainer(context *cli.Context) (libcontainer.Container, error) {
	id := context.Args().First()
	if id == "" {
		return nil, errEmptyID
	}
	factory, err := loadFactory(context)
	if err != nil {
		return nil, err
	}
	return factory.Load(id)
}

func fatalf(t string, v ...interface{}) {
	fatal(fmt.Errorf(t, v...))
}

func getDefaultImagePath(context *cli.Context) string {
	cwd, err := os.Getwd()
	if err != nil {
		panic(err)
	}
	return filepath.Join(cwd, "checkpoint")
}

// newProcess returns a new libcontainer Process with the arguments from the
// spec and stdio from the current process.
func newProcess(p specs.Process, init bool) (*libcontainer.Process, error) {
	lp := &libcontainer.Process{
		Args: p.Args,
		Env:  p.Env,
		// TODO: fix libcontainer's API to better support uid/gid in a typesafe way.
		User:            fmt.Sprintf("%d:%d", p.User.UID, p.User.GID),
		Cwd:             p.Cwd,
		Label:           p.SelinuxLabel,
		NoNewPrivileges: &p.NoNewPrivileges,
		AppArmorProfile: p.ApparmorProfile,
		Init:            init,
	}

	if p.ConsoleSize != nil {
		lp.ConsoleWidth = uint16(p.ConsoleSize.Width)
		lp.ConsoleHeight = uint16(p.ConsoleSize.Height)
	}

	if p.Capabilities != nil {
		lp.Capabilities = &configs.Capabilities{}
		lp.Capabilities.Bounding = p.Capabilities.Bounding
		lp.Capabilities.Effective = p.Capabilities.Effective
		lp.Capabilities.Inheritable = p.Capabilities.Inheritable
		lp.Capabilities.Permitted = p.Capabilities.Permitted
		lp.Capabilities.Ambient = p.Capabilities.Ambient
	}
	for _, gid := range p.User.AdditionalGids {
		lp.AdditionalGroups = append(lp.AdditionalGroups, strconv.FormatUint(uint64(gid), 10))
	}
	for _, rlimit := range p.Rlimits {
		rl, err := createLibContainerRlimit(rlimit)
		if err != nil {
			return nil, err
		}
		lp.Rlimits = append(lp.Rlimits, rl)
	}
	return lp, nil
}

func destroy(container libcontainer.Container) {
	if err := container.Destroy(); err != nil {
		logrus.Error(err)
	}
}

// setupIO modifies the given process config according to the options.
func setupIO(process *libcontainer.Process, rootuid, rootgid int, createTTY, detach bool, sockpath string) (*tty, error) {
	if createTTY {
		process.Stdin = nil
		process.Stdout = nil
		process.Stderr = nil
		t := &tty{}
		if !detach {
			parent, child, err := utils.NewSockPair("console")
			if err != nil {
				return nil, err
			}
			process.ConsoleSocket = child
			t.postStart = append(t.postStart, parent, child)
			t.consoleC = make(chan error, 1)
			go func() {
				if err := t.recvtty(process, parent); err != nil {
					t.consoleC <- err
				}
				t.consoleC <- nil
			}()
		} else {
			// the caller of runc will handle receiving the console master
			conn, err := net.Dial("unix", sockpath)
			if err != nil {
				return nil, err
			}
			uc, ok := conn.(*net.UnixConn)
			if !ok {
				return nil, fmt.Errorf("casting to UnixConn failed")
			}
			t.postStart = append(t.postStart, uc)
			socket, err := uc.File()
			if err != nil {
				return nil, err
			}
			t.postStart = append(t.postStart, socket)
			process.ConsoleSocket = socket
		}
		return t, nil
	}
	// when runc will detach the caller provides the stdio to runc via runc's 0,1,2
	// and the container's process inherits runc's stdio.
	if detach {
		if err := inheritStdio(process); err != nil {
			return nil, err
		}
		return &tty{}, nil
	}
	return setupProcessPipes(process, rootuid, rootgid)
}

// createPidFile creates a file with the processes pid inside it atomically
// it creates a temp file with the paths filename + '.' infront of it
// then renames the file
func createPidFile(path string, process *libcontainer.Process) error {
	pid, err := process.Pid()
	if err != nil {
		return err
	}
	var (
		tmpDir  = filepath.Dir(path)
		tmpName = filepath.Join(tmpDir, fmt.Sprintf(".%s", filepath.Base(path)))
	)
	f, err := os.OpenFile(tmpName, os.O_RDWR|os.O_CREATE|os.O_EXCL|os.O_SYNC, 0666)
	if err != nil {
		return err
	}
	_, err = fmt.Fprintf(f, "%d", pid)
	f.Close()
	if err != nil {
		return err
	}
	return os.Rename(tmpName, path)
}

func createContainer(context *cli.Context, id string, spec *specs.Spec) (libcontainer.Container, error) {
	rootlessCg, err := shouldUseRootlessCgroupManager(context)
	if err != nil {
		return nil, err
	}
	config, err := specconv.CreateLibcontainerConfig(&specconv.CreateOpts{
		CgroupName:       id,
		UseSystemdCgroup: context.GlobalBool("systemd-cgroup"),
		NoPivotRoot:      context.Bool("no-pivot"),
		NoNewKeyring:     context.Bool("no-new-keyring"),
		Spec:             spec,
		RootlessEUID:     os.Geteuid() != 0,
		RootlessCgroups:  rootlessCg,
	})
	if err != nil {
		return nil, err
	}

	factory, err := loadFactory(context)
	if err != nil {
		return nil, err
	}
	return factory.Create(id, config)
}

type runner struct {
	init            bool
	enableSubreaper bool
	shouldDestroy   bool
	detach          bool
	listenFDs       []*os.File
	preserveFDs     int
	pidFile         string
	consoleSocket   string
	container       libcontainer.Container
	action          CtAct
	notifySocket    *notifySocket
	criuOpts        *libcontainer.CriuOpts
}

func (r *runner) run(config *specs.Process) (int, error) {
	if err := r.checkTerminal(config); err != nil {
		r.destroy()
		return -1, err
	}
	process, err := newProcess(*config, r.init)
	if err != nil {
		r.destroy()
		return -1, err
	}
	if len(r.listenFDs) > 0 {
		process.Env = append(process.Env, fmt.Sprintf("LISTEN_FDS=%d", len(r.listenFDs)), "LISTEN_PID=1")
		process.ExtraFiles = append(process.ExtraFiles, r.listenFDs...)
	}
	baseFd := 3 + len(process.ExtraFiles)
	for i := baseFd; i < baseFd+r.preserveFDs; i++ {
		process.ExtraFiles = append(process.ExtraFiles, os.NewFile(uintptr(i), "PreserveFD:"+strconv.Itoa(i)))
	}
	rootuid, err := r.container.Config().HostRootUID()
	if err != nil {
		r.destroy()
		return -1, err
	}
	rootgid, err := r.container.Config().HostRootGID()
	if err != nil {
		r.destroy()
		return -1, err
	}
	var (
		detach = r.detach || (r.action == CT_ACT_CREATE)
	)
	// Setting up IO is a two stage process. We need to modify process to deal
	// with detaching containers, and then we get a tty after the container has
	// started.
	handler := newSignalHandler(r.enableSubreaper, r.notifySocket)
	tty, err := setupIO(process, rootuid, rootgid, config.Terminal, detach, r.consoleSocket)
	if err != nil {
		r.destroy()
		return -1, err
	}
	defer tty.Close()

	switch r.action {
	case CT_ACT_CREATE:
		err = r.container.Start(process)
	case CT_ACT_RESTORE:
		err = r.container.Restore(process, r.criuOpts)
	case CT_ACT_RUN:
		err = r.container.Run(process)
	default:
		panic("Unknown action")
	}
	if err != nil {
		r.destroy()
		return -1, err
	}
	if err := tty.waitConsole(); err != nil {
		r.terminate(process)
		r.destroy()
		return -1, err
	}
	if err = tty.ClosePostStart(); err != nil {
		r.terminate(process)
		r.destroy()
		return -1, err
	}
	if r.pidFile != "" {
		if err = createPidFile(r.pidFile, process); err != nil {
			r.terminate(process)
			r.destroy()
			return -1, err
		}
	}
	status, err := handler.forward(process, tty, detach)
	if err != nil {
		r.terminate(process)
	}
	if detach {
		return 0, nil
	}
	r.destroy()
	return status, err
}

func (r *runner) destroy() {
	if r.shouldDestroy {
		destroy(r.container)
	}
}

func (r *runner) terminate(p *libcontainer.Process) {
	_ = p.Signal(unix.SIGKILL)
	_, _ = p.Wait()
}

func (r *runner) checkTerminal(config *specs.Process) error {
	detach := r.detach || (r.action == CT_ACT_CREATE)
	// Check command-line for sanity.
	if detach && config.Terminal && r.consoleSocket == "" {
		return fmt.Errorf("cannot allocate tty if runc will detach without setting console socket")
	}
	if (!detach || !config.Terminal) && r.consoleSocket != "" {
		return fmt.Errorf("cannot use console socket if runc will not detach or allocate tty")
	}
	return nil
}

func validateProcessSpec(spec *specs.Process) error {
	if spec.Cwd == "" {
		return fmt.Errorf("Cwd property must not be empty")
	}
	if !filepath.IsAbs(spec.Cwd) {
		return fmt.Errorf("Cwd must be an absolute path")
	}
	if len(spec.Args) == 0 {
		return fmt.Errorf("args must not be empty")
	}
	return nil
}

type CtAct uint8

const (
	CT_ACT_CREATE CtAct = iota + 1
	CT_ACT_RUN
	CT_ACT_RESTORE
)

func startContainer(context *cli.Context, spec *specs.Spec, action CtAct, criuOpts *libcontainer.CriuOpts) (int, error) {
	id := context.Args().First()
	if id == "" {
		return -1, errEmptyID
	}

	notifySocket := newNotifySocket(context, os.Getenv("NOTIFY_SOCKET"), id)
	if notifySocket != nil {
		notifySocket.setupSpec(context, spec)
	}

	container, err := createContainer(context, id, spec)
	if err != nil {
		return -1, err
	}

	if notifySocket != nil {
		err := notifySocket.setupSocket()
		if err != nil {
			return -1, err
		}
	}

	// Support on-demand socket activation by passing file descriptors into the container init process.
	listenFDs := []*os.File{}
	if os.Getenv("LISTEN_FDS") != "" {
		listenFDs = activation.Files(false)
	}
	r := &runner{
		enableSubreaper: !context.Bool("no-subreaper"),
		shouldDestroy:   true,
		container:       container,
		listenFDs:       listenFDs,
		notifySocket:    notifySocket,
		consoleSocket:   context.String("console-socket"),
		detach:          context.Bool("detach"),
		pidFile:         context.String("pid-file"),
		preserveFDs:     context.Int("preserve-fds"),
		action:          action,
		criuOpts:        criuOpts,
		init:            true,
	}
	return r.run(spec.Process)
}