This repository has been archived by the owner on Feb 24, 2020. It is now read-only.
/
init.go
936 lines (797 loc) · 31.5 KB
/
init.go
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
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
// Copyright 2014 The rkt Authors
//
// 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.
//+build linux
package main
// this implements /init of stage1/nspawn+systemd
import (
"errors"
"flag"
"fmt"
"io"
"io/ioutil"
"net"
"os"
"os/exec"
"path/filepath"
"runtime"
"strings"
"syscall"
"github.com/appc/goaci/proj2aci"
"github.com/appc/spec/schema/types"
"github.com/coreos/go-systemd/util"
"github.com/coreos/pkg/dlopen"
"github.com/godbus/dbus"
"github.com/godbus/dbus/introspect"
"github.com/hashicorp/errwrap"
stage1common "github.com/rkt/rkt/stage1/common"
stage1commontypes "github.com/rkt/rkt/stage1/common/types"
stage1initcommon "github.com/rkt/rkt/stage1/init/common"
"github.com/rkt/rkt/common"
"github.com/rkt/rkt/common/cgroup"
"github.com/rkt/rkt/common/cgroup/v1"
"github.com/rkt/rkt/common/cgroup/v2"
commonnet "github.com/rkt/rkt/common/networking"
"github.com/rkt/rkt/networking"
pkgflag "github.com/rkt/rkt/pkg/flag"
"github.com/rkt/rkt/pkg/fs"
rktlog "github.com/rkt/rkt/pkg/log"
"github.com/rkt/rkt/pkg/sys"
"github.com/rkt/rkt/pkg/user"
"github.com/rkt/rkt/stage1/init/kvm"
"github.com/rkt/rkt/stage1/init/kvm/hypervisor/hvlkvm"
"github.com/rkt/rkt/stage1/init/kvm/hypervisor/hvqemu"
)
const (
// Path to systemd-nspawn binary within the stage1 rootfs
nspawnBin = "/usr/bin/systemd-nspawn"
// Path to the localtime file/symlink in host
localtimePath = "/etc/localtime"
)
// mirrorLocalZoneInfo tries to reproduce the /etc/localtime target in stage1/ to satisfy systemd-nspawn
func mirrorLocalZoneInfo(root string) {
zif, err := os.Readlink(localtimePath)
if err != nil {
return
}
// On some systems /etc/localtime is a relative symlink, make it absolute
if !filepath.IsAbs(zif) {
zif = filepath.Join(filepath.Dir(localtimePath), zif)
zif = filepath.Clean(zif)
}
src, err := os.Open(zif)
if err != nil {
return
}
defer src.Close()
destp := filepath.Join(common.Stage1RootfsPath(root), zif)
if err = os.MkdirAll(filepath.Dir(destp), 0755); err != nil {
return
}
dest, err := os.OpenFile(destp, os.O_CREATE|os.O_WRONLY, 0644)
if err != nil {
return
}
defer dest.Close()
_, _ = io.Copy(dest, src)
}
var (
debug bool
localhostIP net.IP
localConfig string
log *rktlog.Logger
diag *rktlog.Logger
interpBin string // Path to the interpreter within the stage1 rootfs, set by the linker
)
func parseFlags() *stage1commontypes.RuntimePod {
rp := stage1commontypes.RuntimePod{}
flag.BoolVar(&debug, "debug", false, "Run in debug mode")
flag.StringVar(&localConfig, "local-config", common.DefaultLocalConfigDir, "Local config path")
// These flags are persisted in the PodRuntime
flag.BoolVar(&rp.Interactive, "interactive", false, "The pod is interactive")
flag.BoolVar(&rp.Mutable, "mutable", false, "Enable mutable operations on this pod, including starting an empty one")
flag.Var(&rp.NetList, "net", "Setup networking")
flag.StringVar(&rp.PrivateUsers, "private-users", "", "Run within user namespace. Can be set to [=UIDBASE[:NUIDS]]")
flag.StringVar(&rp.MDSToken, "mds-token", "", "MDS auth token")
flag.StringVar(&rp.Hostname, "hostname", "", "Hostname of the pod")
flag.BoolVar(&rp.InsecureOptions.DisableCapabilities, "disable-capabilities-restriction", false, "Disable capability restrictions")
flag.BoolVar(&rp.InsecureOptions.DisablePaths, "disable-paths", false, "Disable paths restrictions")
flag.BoolVar(&rp.InsecureOptions.DisableSeccomp, "disable-seccomp", false, "Disable seccomp restrictions")
dnsConfMode := pkgflag.MustNewPairList(map[string][]string{
"resolv": {"host", "stage0", "none", "default"},
"hosts": {"host", "stage0", "default"},
}, map[string]string{
"resolv": "default",
"hosts": "default",
})
flag.Var(dnsConfMode, "dns-conf-mode", "DNS config file modes")
flag.StringVar(&rp.IPCMode, "ipc", "", "IPC mode --ipc=[auto|private|parent]")
flag.Parse()
rp.Debug = debug
rp.ResolvConfMode = dnsConfMode.Pairs["resolv"]
rp.EtcHostsMode = dnsConfMode.Pairs["hosts"]
return &rp
}
func init() {
// this ensures that main runs only on main thread (thread group leader).
// since namespace ops (unshare, setns) are done for a single thread, we
// must ensure that the goroutine does not jump from OS thread to thread
runtime.LockOSThread()
// We'll need this later
localhostIP = net.ParseIP("127.0.0.1")
if localhostIP == nil {
panic("localhost IP failed to parse")
}
}
// machinedRegister checks if nspawn should register the pod to machined
func machinedRegister() bool {
// machined has a D-Bus interface following versioning guidelines, see:
// http://www.freedesktop.org/wiki/Software/systemd/machined/
// Therefore we can just check if the D-Bus method we need exists and we
// don't need to check the signature.
var found int
conn, err := dbus.SystemBus()
if err != nil {
return false
}
node, err := introspect.Call(conn.Object("org.freedesktop.machine1", "/org/freedesktop/machine1"))
if err != nil {
return false
}
for _, iface := range node.Interfaces {
if iface.Name != "org.freedesktop.machine1.Manager" {
continue
}
// machined v215 supports methods "RegisterMachine" and "CreateMachine" called by nspawn v215.
// machined v216+ (since commit 5aa4bb) additionally supports methods "CreateMachineWithNetwork"
// and "RegisterMachineWithNetwork", called by nspawn v216+.
for _, method := range iface.Methods {
if method.Name == "CreateMachineWithNetwork" || method.Name == "RegisterMachineWithNetwork" {
found++
}
}
break
}
return found == 2
}
func installAssets(systemdVersion int) error {
systemctlBin, err := common.LookupPath("systemctl", os.Getenv("PATH"))
if err != nil {
return err
}
systemdSysusersBin, err := common.LookupPath("systemd-sysusers", os.Getenv("PATH"))
if err != nil {
return err
}
systemdTmpfilesBin, err := common.LookupPath("systemd-tmpfiles", os.Getenv("PATH"))
if err != nil {
return err
}
bashBin, err := common.LookupPath("bash", os.Getenv("PATH"))
if err != nil {
return err
}
mountBin, err := common.LookupPath("mount", os.Getenv("PATH"))
if err != nil {
return err
}
umountBin, err := common.LookupPath("umount", os.Getenv("PATH"))
if err != nil {
return err
}
// More paths could be added in that list if some Linux distributions install it in a different path
// Note that we look in /usr/lib/... first because of the merge:
// http://www.freedesktop.org/wiki/Software/systemd/TheCaseForTheUsrMerge/
systemdShutdownBin, err := common.LookupPath("systemd-shutdown", "/usr/lib/systemd:/lib/systemd")
if err != nil {
return err
}
systemdBin, err := common.LookupPath("systemd", "/usr/lib/systemd:/lib/systemd")
if err != nil {
return err
}
systemdJournaldBin, err := common.LookupPath("systemd-journald", "/usr/lib/systemd:/lib/systemd")
if err != nil {
return err
}
systemdUnitsPath := "/lib/systemd/system"
assets := []string{
proj2aci.GetAssetString("/usr/lib/systemd/systemd", systemdBin),
proj2aci.GetAssetString("/usr/bin/systemctl", systemctlBin),
proj2aci.GetAssetString("/usr/bin/systemd-sysusers", systemdSysusersBin),
proj2aci.GetAssetString("/usr/bin/systemd-tmpfiles", systemdTmpfilesBin),
proj2aci.GetAssetString("/usr/lib/systemd/systemd-journald", systemdJournaldBin),
proj2aci.GetAssetString("/usr/bin/bash", bashBin),
proj2aci.GetAssetString("/bin/mount", mountBin),
proj2aci.GetAssetString("/bin/umount", umountBin),
proj2aci.GetAssetString(fmt.Sprintf("%s/systemd-journald.service", systemdUnitsPath), fmt.Sprintf("%s/systemd-journald.service", systemdUnitsPath)),
proj2aci.GetAssetString(fmt.Sprintf("%s/systemd-journald.socket", systemdUnitsPath), fmt.Sprintf("%s/systemd-journald.socket", systemdUnitsPath)),
proj2aci.GetAssetString(fmt.Sprintf("%s/systemd-journald-dev-log.socket", systemdUnitsPath), fmt.Sprintf("%s/systemd-journald-dev-log.socket", systemdUnitsPath)),
proj2aci.GetAssetString(fmt.Sprintf("%s/systemd-journald-audit.socket", systemdUnitsPath), fmt.Sprintf("%s/systemd-journald-audit.socket", systemdUnitsPath)),
// systemd-shutdown has to be installed at the same path as on the host
// because it depends on systemd build flag -DSYSTEMD_SHUTDOWN_BINARY_PATH=
proj2aci.GetAssetString(systemdShutdownBin, systemdShutdownBin),
}
// systemd-journal-flush.service was added in systemd-v233. Required to place
// the logs in /var/log/journal instead of /run/log/journal. See:
// https://github.com/systemd/systemd/commit/f78273c8dacf678cc8fd7387f678e6344a99405c
if systemdVersion >= 233 {
assets = append(assets, proj2aci.GetAssetString(fmt.Sprintf("%s/systemd-journal-flush.service", systemdUnitsPath), fmt.Sprintf("%s/systemd-journald.service", systemdUnitsPath)))
}
return proj2aci.PrepareAssets(assets, "./stage1/rootfs/", nil)
}
// getArgsEnv returns the nspawn or lkvm args and env according to the flavor
// as the first two return values respectively.
func getArgsEnv(p *stage1commontypes.Pod, flavor string, canMachinedRegister bool, debug bool, n *networking.Networking, parentIPC bool) ([]string, []string, error) {
var args []string
env := os.Environ()
// We store the pod's flavor so we can later garbage collect it correctly
if err := os.Symlink(flavor, filepath.Join(p.Root, stage1initcommon.FlavorFile)); err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to create flavor symlink"), err)
}
// systemd-nspawn needs /etc/machine-id to link the container's journal
// to the host. Since systemd-v230, /etc/machine-id is mandatory, see
// https://github.com/systemd/systemd/commit/e01ff70a77e781734e1e73a2238af2e9bf7967a8
mPath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc", "machine-id")
machineID := strings.Replace(p.UUID.String(), "-", "", -1)
switch flavor {
case "kvm":
if p.PrivateUsers != "" {
return nil, nil, fmt.Errorf("flag --private-users cannot be used with an lkvm stage1")
}
// kernel and hypervisor binaries are located relative to the working directory
// of init (/var/lib/rkt/..../uuid)
// TODO: move to path.go
kernelPath := filepath.Join(common.Stage1RootfsPath(p.Root), "kernel_image")
netDescriptions := kvm.GetNetworkDescriptions(n)
cpu, mem := kvm.GetAppsResources(p.Manifest.Apps)
// Parse hypervisor
hv, err := KvmCheckHypervisor(common.Stage1RootfsPath(p.Root))
if err != nil {
return nil, nil, err
}
// Set start command for hypervisor
StartCmd := hvlkvm.StartCmd
switch hv {
case "lkvm":
StartCmd = hvlkvm.StartCmd
case "qemu":
StartCmd = hvqemu.StartCmd
default:
return nil, nil, fmt.Errorf("unrecognized hypervisor")
}
hvStartCmd := StartCmd(
common.Stage1RootfsPath(p.Root),
p.UUID.String(),
kernelPath,
netDescriptions,
cpu,
mem,
debug,
)
if hvStartCmd == nil {
return nil, nil, fmt.Errorf("no hypervisor")
}
args = append(args, hvStartCmd...)
// lkvm requires $HOME to be defined,
// see https://github.com/rkt/rkt/issues/1393
if os.Getenv("HOME") == "" {
env = append(env, "HOME=/root")
}
if err := linkJournal(common.Stage1RootfsPath(p.Root), machineID); err != nil {
return nil, nil, errwrap.Wrap(errors.New("error linking pod's journal"), err)
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
return args, env, nil
case "coreos":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), interpBin))
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, "--notify-ready=yes") // From systemd v231
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if canMachinedRegister {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
kubernetesLogDir, ok := p.Manifest.Annotations.Get("coreos.com/rkt/experiment/kubernetes-log-dir")
if ok {
args = append(args, fmt.Sprintf("--bind=%s:/rkt/kubernetes/log", kubernetesLogDir))
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib")+":"+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
case "src":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), interpBin))
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, "--notify-ready=yes") // From systemd v231
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if canMachinedRegister {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
kubernetesLogDir, ok := p.Manifest.Annotations.Get("coreos.com/rkt/experiment/kubernetes-log-dir")
if ok {
args = append(args, fmt.Sprintf("--bind=%s:/rkt/kubernetes/log", kubernetesLogDir))
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib")+":"+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
case "host":
hostNspawnBin, err := common.LookupPath("systemd-nspawn", os.Getenv("PATH"))
if err != nil {
return nil, nil, err
}
// Check dynamically which version is installed on the host
// Support version >= 220
versionBytes, err := exec.Command(hostNspawnBin, "--version").CombinedOutput()
if err != nil {
return nil, nil, errwrap.Wrap(fmt.Errorf("unable to probe %s version", hostNspawnBin), err)
}
versionStr := strings.SplitN(string(versionBytes), "\n", 2)[0]
var version int
n, err := fmt.Sscanf(versionStr, "systemd %d", &version)
if err != nil {
return nil, nil, fmt.Errorf("cannot parse version: %q", versionStr)
}
if n != 1 || version < 220 {
return nil, nil, fmt.Errorf("rkt needs systemd-nspawn >= 220. %s version not supported: %v", hostNspawnBin, versionStr)
}
// Copy systemd, bash, etc. in stage1 at run-time
if err := installAssets(version); err != nil {
return nil, nil, errwrap.Wrap(errors.New("cannot install assets from the host"), err)
}
args = append(args, hostNspawnBin)
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, fmt.Sprintf("--register=true"))
if version >= 231 {
args = append(args, "--notify-ready=yes") // From systemd v231
}
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
kubernetesLogDir, ok := p.Manifest.Annotations.Get("coreos.com/rkt/experiment/kubernetes-log-dir")
if ok {
args = append(args, fmt.Sprintf("--bind=%s:/rkt/kubernetes/log", kubernetesLogDir))
}
default:
return nil, nil, fmt.Errorf("unrecognized stage1 flavor: %q", flavor)
}
machineIDBytes := append([]byte(machineID), '\n')
if err := ioutil.WriteFile(mPath, machineIDBytes, 0644); err != nil {
return nil, nil, errwrap.Wrap(errors.New("error writing /etc/machine-id"), err)
}
if err := user.ShiftFiles([]string{mPath}, &p.UidRange); err != nil {
return nil, nil, errwrap.Wrap(errors.New("error shifting /etc/machine-id"), err)
}
// link journal only if the host is running systemd
if util.IsRunningSystemd() {
args = append(args, "--link-journal=try-guest")
keepUnit, err := util.RunningFromSystemService()
if err != nil {
if err == dlopen.ErrSoNotFound {
log.Print("warning: libsystemd not found even though systemd is running. Cgroup limits set by the environment (e.g. a systemd service) won't be enforced.")
} else {
return nil, nil, errwrap.Wrap(errors.New("error determining if we're running from a system service"), err)
}
}
if keepUnit {
args = append(args, "--keep-unit")
}
} else {
args = append(args, "--link-journal=no")
}
if !debug {
args = append(args, "--quiet") // silence most nspawn output (log_warning is currently not covered by this)
env = append(env, "SYSTEMD_LOG_LEVEL=err") // silence log_warning too
}
if parentIPC {
env = append(env, "SYSTEMD_NSPAWN_SHARE_NS_IPC=true")
}
env = append(env, "SYSTEMD_NSPAWN_CONTAINER_SERVICE=rkt")
// TODO (alepuccetti) remove this line when rkt will use cgroup namespace
// If the kernel has the cgroup namespace enabled, systemd v232 will use it by default.
// This was introduced by https://github.com/systemd/systemd/pull/3809 and it will cause
// problems in rkt when cgns is enabled and cgroup-v1 is used. For more information see
// https://github.com/systemd/systemd/pull/3589#discussion_r70277625.
// The following line tells systemd-nspawn not to use cgroup namespace using the environment variable
// introduced by https://github.com/systemd/systemd/pull/3809.
env = append(env, "SYSTEMD_NSPAWN_USE_CGNS=no")
if p.InsecureOptions.DisablePaths {
env = append(env, "SYSTEMD_NSPAWN_API_VFS_WRITABLE=yes")
}
if len(p.PrivateUsers) > 0 {
args = append(args, "--private-users="+p.PrivateUsers)
}
nsargs, err := stage1initcommon.PodToNspawnArgs(p)
if err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to generate nspawn args"), err)
}
args = append(args, nsargs...)
// Arguments to systemd
args = append(args, "--")
args = append(args, "--default-standard-output=tty") // redirect all service logs straight to tty
if !debug {
args = append(args, "--log-target=null") // silence systemd output inside pod
args = append(args, "--show-status=0") // silence systemd initialization status output
}
return args, env, nil
}
func stage1(rp *stage1commontypes.RuntimePod) int {
uuid, err := types.NewUUID(flag.Arg(0))
if err != nil {
log.FatalE("UUID is missing or malformed", err)
}
root := "."
p, err := stage1commontypes.LoadPod(root, uuid, rp)
if err != nil {
log.FatalE("failed to load pod", err)
}
if err := p.SaveRuntime(); err != nil {
log.FatalE("failed to save runtime parameters", err)
}
// set close-on-exec flag on RKT_LOCK_FD so it gets correctly closed when invoking
// network plugins
lfd, err := common.GetRktLockFD()
if err != nil {
log.FatalE("failed to get rkt lock fd", err)
}
if err := sys.CloseOnExec(lfd, true); err != nil {
log.FatalE("failed to set FD_CLOEXEC on rkt lock", err)
}
mirrorLocalZoneInfo(p.Root)
flavor, _, err := stage1initcommon.GetFlavor(p)
if err != nil {
log.FatalE("failed to get stage1 flavor", err)
}
var n *networking.Networking
if p.NetList.Contained() {
fps, err := commonnet.ForwardedPorts(p.Manifest)
if err != nil {
log.FatalE("error initializing forwarding ports", err)
}
noDNS := p.ResolvConfMode != "default" // force ignore CNI DNS results
n, err = networking.Setup(root, p.UUID, fps, p.NetList, localConfig, flavor, noDNS, debug)
if err != nil {
log.FatalE("failed to setup network", err)
}
if err = n.Save(); err != nil {
log.PrintE("failed to save networking state", err)
n.Teardown(flavor, debug)
return 254
}
if len(p.MDSToken) > 0 {
hostIP, err := n.GetForwardableNetHostIP()
if err != nil {
log.FatalE("failed to get default Host IP", err)
}
p.MetadataServiceURL = common.MetadataServicePublicURL(hostIP, p.MDSToken)
}
} else {
if flavor == "kvm" {
log.Fatal("flavor kvm requires private network configuration (try --net)")
}
if len(p.MDSToken) > 0 {
p.MetadataServiceURL = common.MetadataServicePublicURL(localhostIP, p.MDSToken)
}
}
mnt := fs.NewLoggingMounter(
fs.MounterFunc(syscall.Mount),
fs.UnmounterFunc(syscall.Unmount),
diag.Printf,
)
// set hostname inside pod
// According to systemd manual (https://www.freedesktop.org/software/systemd/man/hostname.html) :
// "The /etc/hostname file configures the name of the local system that is set
// during boot using the sethostname system call"
if p.Hostname == "" {
p.Hostname = stage1initcommon.GetMachineID(p)
}
hostnamePath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc/hostname")
if err := ioutil.WriteFile(hostnamePath, []byte(p.Hostname), 0644); err != nil {
log.PrintE("error writing "+hostnamePath, err)
return 254
}
if err := user.ShiftFiles([]string{hostnamePath}, &p.UidRange); err != nil {
log.PrintE("error shifting "+hostnamePath, err)
}
if p.ResolvConfMode == "host" {
stage1initcommon.UseHostResolv(mnt, root)
}
// Set up the hosts file.
// We write <stage1>/etc/rkt-hosts if we want to override each app's hosts,
// and <stage1>/etc/hosts-fallback if we want to let the app "win"
// Either way, we should add our hostname to it, unless the hosts's
// /etc/hosts is bind-mounted in.
if p.EtcHostsMode == "host" { // We should bind-mount the hosts's /etc/hosts
stage1initcommon.UseHostHosts(mnt, root)
} else if p.EtcHostsMode == "default" { // Create hosts-fallback
hostsFile := filepath.Join(common.Stage1RootfsPath(p.Root), "etc", "hosts-fallback")
if err := stage1initcommon.AddHostsEntry(hostsFile, "127.0.0.1", p.Hostname); err != nil {
log.PrintE("Failed to write hostname to "+hostsFile, err)
return 254
}
} else if p.EtcHostsMode == "stage0" { // The stage0 has created rkt-hosts
hostsFile := filepath.Join(common.Stage1RootfsPath(p.Root), "etc", "rkt-hosts")
if err := stage1initcommon.AddHostsEntry(hostsFile, "127.0.0.1", p.Hostname); err != nil {
log.PrintE("Failed to write hostname to "+hostsFile, err)
return 254
}
}
if p.Mutable {
if err = stage1initcommon.MutableEnv(p); err != nil {
log.FatalE("cannot initialize mutable environment", err)
}
} else {
if err = stage1initcommon.ImmutableEnv(p); err != nil {
log.FatalE("cannot initialize immutable environment", err)
}
}
if err := stage1initcommon.SetJournalPermissions(p); err != nil {
log.PrintE("warning: error setting journal ACLs, you'll need root to read the pod journal", err)
}
if flavor == "kvm" {
kvm.InitDebug(debug)
if err := KvmNetworkingToSystemd(p, n); err != nil {
log.FatalE("failed to configure systemd for kvm", err)
}
}
canMachinedRegister := false
if flavor != "kvm" {
// kvm doesn't register with systemd right now, see #2664.
canMachinedRegister = machinedRegister()
}
diag.Printf("canMachinedRegister %t", canMachinedRegister)
// --ipc=[auto|private|parent]
// default to private
parentIPC := false
switch p.IPCMode {
case "parent":
parentIPC = true
case "private":
parentIPC = false
case "auto":
fallthrough
case "":
parentIPC = false
default:
log.Fatalf("unknown value for --ipc parameter: %v", p.IPCMode)
}
if parentIPC && flavor == "kvm" {
log.Fatal("flavor kvm requires private IPC namespace (try to remove --ipc)")
}
args, env, err := getArgsEnv(p, flavor, canMachinedRegister, debug, n, parentIPC)
if err != nil {
log.FatalE("cannot get environment", err)
}
diag.Printf("args %q", args)
diag.Printf("env %q", env)
// create a separate mount namespace so the cgroup filesystems
// are unmounted when exiting the pod
if err := syscall.Unshare(syscall.CLONE_NEWNS); err != nil {
log.FatalE("error unsharing", err)
}
// we recursively make / a "shared and slave" so mount events from the
// new namespace don't propagate to the host namespace but mount events
// from the host propagate to the new namespace and are forwarded to
// its peer group
// See https://www.kernel.org/doc/Documentation/filesystems/sharedsubtree.txt
if err := mnt.Mount("", "/", "none", syscall.MS_REC|syscall.MS_SLAVE, ""); err != nil {
log.FatalE("error making / a slave mount", err)
}
if err := mnt.Mount("", "/", "none", syscall.MS_REC|syscall.MS_SHARED, ""); err != nil {
log.FatalE("error making / a shared and slave mount", err)
}
unifiedCgroup, err := cgroup.IsCgroupUnified("/")
if err != nil {
log.FatalE("error determining cgroup version", err)
}
diag.Printf("unifiedCgroup %t", unifiedCgroup)
machineID := stage1initcommon.GetMachineID(p)
subcgroup, err := getContainerSubCgroup(machineID, canMachinedRegister, unifiedCgroup)
if err != nil {
log.FatalE("error getting container subcgroup", err)
}
diag.Printf("subcgroup %q", subcgroup)
if err := ioutil.WriteFile(filepath.Join(p.Root, "subcgroup"),
[]byte(fmt.Sprintf("%s", subcgroup)), 0644); err != nil {
log.FatalE("cannot write subcgroup file", err)
}
if !unifiedCgroup {
enabledCgroups, err := v1.GetEnabledCgroups()
if err != nil {
log.FatalE("error getting v1 cgroups", err)
}
diag.Printf("enabledCgroups %q", enabledCgroups)
if err := mountHostV1Cgroups(mnt, enabledCgroups); err != nil {
log.FatalE("couldn't mount the host v1 cgroups", err)
}
if !canMachinedRegister {
if err := v1.JoinSubcgroup("systemd", subcgroup); err != nil {
log.FatalE(fmt.Sprintf("error joining subcgroup %q", subcgroup), err)
}
}
var serviceNames []string
for _, app := range p.Manifest.Apps {
serviceNames = append(serviceNames, stage1initcommon.ServiceUnitName(app.Name))
}
diag.Printf("serviceNames %q", serviceNames)
if err := mountContainerV1Cgroups(mnt, p, enabledCgroups, subcgroup, serviceNames); err != nil {
log.FatalE("couldn't mount the container v1 cgroups", err)
}
}
// KVM flavor has a bit different logic in handling pid vs ppid, for details look into #2389
// it doesn't require the existence of a "ppid", instead it registers the current pid (which
// will be reused by lkvm binary) as a pod process pid used during entering
pid_filename := "ppid"
if flavor == "kvm" {
pid_filename = "pid"
}
if err = stage1common.WritePid(os.Getpid(), pid_filename); err != nil {
log.FatalE("error writing pid", err)
}
if flavor == "kvm" {
if err := KvmPrepareMounts(p); err != nil {
log.FatalE("error preparing mounts", err)
}
}
err = stage1common.WithClearedCloExec(lfd, func() error {
return syscall.Exec(args[0], args, env)
})
if err != nil {
log.FatalE(fmt.Sprintf("failed to execute %q", args[0]), err)
}
return 0
}
func areHostV1CgroupsMounted(enabledV1Cgroups map[int][]string) bool {
controllers := v1.GetControllerDirs(enabledV1Cgroups)
for _, c := range controllers {
if mounted, _ := v1.IsControllerMounted(c); !mounted {
return false
}
}
return true
}
// mountHostV1Cgroups mounts the host v1 cgroup hierarchy as required by
// systemd-nspawn. We need this because some distributions don't have the
// "name=systemd" cgroup or don't mount the cgroup controllers in
// "/sys/fs/cgroup", and systemd-nspawn needs this. Since this is mounted
// inside the rkt mount namespace, it doesn't affect the host.
func mountHostV1Cgroups(m fs.Mounter, enabledCgroups map[int][]string) error {
systemdControllerPath := "/sys/fs/cgroup/systemd"
if !areHostV1CgroupsMounted(enabledCgroups) {
mountContext := os.Getenv(common.EnvSELinuxMountContext)
if err := v1.CreateCgroups(m, "/", enabledCgroups, mountContext); err != nil {
return errwrap.Wrap(errors.New("error creating host cgroups"), err)
}
}
mounted, err := v1.IsControllerMounted("systemd")
if err != nil {
return err
}
if !mounted {
if err := os.MkdirAll(systemdControllerPath, 0700); err != nil {
return err
}
if err := m.Mount("cgroup", systemdControllerPath, "cgroup", 0, "none,name=systemd"); err != nil {
return errwrap.Wrap(fmt.Errorf("error mounting name=systemd hierarchy on %q", systemdControllerPath), err)
}
}
return nil
}
// mountContainerV1Cgroups mounts the cgroup controllers hierarchy in the container's
// namespace read-only, leaving the needed knobs in the subcgroup for each-app
// read-write so systemd inside stage1 can apply isolators to them
func mountContainerV1Cgroups(m fs.Mounter, p *stage1commontypes.Pod, enabledCgroups map[int][]string, subcgroup string, serviceNames []string) error {
mountContext := os.Getenv(common.EnvSELinuxMountContext)
stage1Root := common.Stage1RootfsPath(p.Root)
if err := v1.CreateCgroups(m, stage1Root, enabledCgroups, mountContext); err != nil {
return errwrap.Wrap(errors.New("error creating container cgroups"), err)
}
if err := v1.RemountCgroups(m, stage1Root, enabledCgroups, subcgroup, p.InsecureOptions.DisablePaths); err != nil {
return errwrap.Wrap(errors.New("error restricting container cgroups"), err)
}
return nil
}
func getContainerSubCgroup(machineID string, canMachinedRegister, unified bool) (string, error) {
var fromUnit bool
if util.IsRunningSystemd() {
var err error
if fromUnit, err = util.RunningFromSystemService(); err != nil {
return "", errwrap.Wrap(errors.New("could not determine if we're running from a unit file"), err)
}
}
if fromUnit {
slice, err := util.GetRunningSlice()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get slice name"), err)
}
slicePath, err := common.SliceToPath(slice)
if err != nil {
return "", errwrap.Wrap(errors.New("could not convert slice name to path"), err)
}
unit, err := util.CurrentUnitName()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get unit name"), err)
}
subcgroup := filepath.Join(slicePath, unit)
if unified {
return filepath.Join(subcgroup, "payload"), nil
}
return subcgroup, nil
}
escapedmID := strings.Replace(machineID, "-", "\\x2d", -1)
machineDir := "machine-" + escapedmID + ".scope"
if canMachinedRegister {
// we are not in the final cgroup yet: systemd-nspawn will move us
// to the correct cgroup later during registration so we can't
// look it up in /proc/self/cgroup
return filepath.Join("machine.slice", machineDir), nil
}
if unified {
subcgroup, err := v2.GetOwnCgroupPath()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get own v2 cgroup path"), err)
}
return subcgroup, nil
}
// when registration is disabled the container will be directly
// under the current cgroup so we can look it up in /proc/self/cgroup
// Try the systemd slice first, falling back to cpu if that fails (e.g. on
// systems not running systemd). See issue #3502.
ownV1CgroupPath, err := v1.GetOwnCgroupPath("name=systemd")
if err != nil {
ownV1CgroupPath, err = v1.GetOwnCgroupPath("cpu")
if err != nil {
return "", errwrap.Wrap(errors.New("could not get own v1 cgroup path"), err)
}
}
// systemd-nspawn won't work if we are in the root cgroup. In addition,
// we want all rkt instances to be in distinct cgroups. Create a
// subcgroup and add ourselves to it.
return filepath.Join(ownV1CgroupPath, machineDir), nil
}
func main() {
rp := parseFlags()
stage1initcommon.InitDebug(debug)
log, diag, _ = rktlog.NewLogSet("stage1", debug)
if !debug {
diag.SetOutput(ioutil.Discard)
}
// move code into stage1() helper so deferred fns get run
os.Exit(stage1(rp))
}