-
Notifications
You must be signed in to change notification settings - Fork 115
/
Copy pathsys.c
2247 lines (1958 loc) · 52.3 KB
/
sys.c
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
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* linux/kernel/sys.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/kmod.h>
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.h>
#include <linux/device.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
#include <linux/dcookies.h>
#include <linux/suspend.h>
#include <linux/tty.h>
#include <linux/signal.h>
#include <linux/cn_proc.h>
#include <linux/getcpu.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/seccomp.h>
#include <linux/cpu.h>
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/fs_struct.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/gfp.h>
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>
#include <linux/binfmts.h>
#include <linux/kmsg_dump.h>
/* Move somewhere else to avoid recompiling? */
#include <generated/utsrelease.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/unistd.h>
#ifndef SET_UNALIGN_CTL
# define SET_UNALIGN_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_UNALIGN_CTL
# define GET_UNALIGN_CTL(a,b) (-EINVAL)
#endif
#ifndef SET_FPEMU_CTL
# define SET_FPEMU_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_FPEMU_CTL
# define GET_FPEMU_CTL(a,b) (-EINVAL)
#endif
#ifndef SET_FPEXC_CTL
# define SET_FPEXC_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_FPEXC_CTL
# define GET_FPEXC_CTL(a,b) (-EINVAL)
#endif
#ifndef GET_ENDIAN
# define GET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b) (-EINVAL)
#endif
#ifndef GET_TSC_CTL
# define GET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-EINVAL)
#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
* architectures that now have 32-bit UID/GID but didn't in the past
*/
int overflowuid = DEFAULT_OVERFLOWUID;
int overflowgid = DEFAULT_OVERFLOWGID;
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
/*
* the same as above, but for filesystems which can only store a 16-bit
* UID and GID. as such, this is needed on all architectures
*/
int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
/*
* this indicates whether you can reboot with ctrl-alt-del: the default is yes
*/
int C_A_D = 1;
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);
/*
* If set, this is used for preparing the system to power off.
*/
void (*pm_power_off_prepare)(void);
/*
* Returns true if current's euid is same as p's uid or euid,
* or has CAP_SYS_NICE to p's user_ns.
*
* Called with rcu_read_lock, creds are safe
*/
static bool set_one_prio_perm(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
if (uid_eq(pcred->uid, cred->euid) ||
uid_eq(pcred->euid, cred->euid))
return true;
if (ns_capable(pcred->user_ns, CAP_SYS_NICE))
return true;
return false;
}
/*
* set the priority of a task
* - the caller must hold the RCU read lock
*/
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
int no_nice;
if (!set_one_prio_perm(p)) {
error = -EPERM;
goto out;
}
if (niceval < task_nice(p) && !can_nice(p, niceval)) {
error = -EACCES;
goto out;
}
no_nice = security_task_setnice(p, niceval);
if (no_nice) {
error = no_nice;
goto out;
}
if (error == -ESRCH)
error = 0;
set_user_nice(p, niceval);
out:
return error;
}
SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
{
struct task_struct *g, *p;
struct user_struct *user;
const struct cred *cred = current_cred();
int error = -EINVAL;
struct pid *pgrp;
kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
goto out;
/* normalize: avoid signed division (rounding problems) */
error = -ESRCH;
if (niceval < -20)
niceval = -20;
if (niceval > 19)
niceval = 19;
rcu_read_lock();
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p)
error = set_one_prio(p, niceval, error);
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
user = cred->user;
if (!who)
uid = cred->uid;
else if (!uid_eq(uid, cred->uid) &&
!(user = find_user(uid)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p) {
if (uid_eq(task_uid(p), uid))
error = set_one_prio(p, niceval, error);
} while_each_thread(g, p);
if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
rcu_read_unlock();
out:
return error;
}
/*
* Ugh. To avoid negative return values, "getpriority()" will
* not return the normal nice-value, but a negated value that
* has been offset by 20 (ie it returns 40..1 instead of -20..19)
* to stay compatible.
*/
SYSCALL_DEFINE2(getpriority, int, which, int, who)
{
struct task_struct *g, *p;
struct user_struct *user;
const struct cred *cred = current_cred();
long niceval, retval = -ESRCH;
struct pid *pgrp;
kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
return -EINVAL;
rcu_read_lock();
read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
p = find_task_by_vpid(who);
else
p = current;
if (p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
break;
case PRIO_PGRP:
if (who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
user = cred->user;
if (!who)
uid = cred->uid;
else if (!uid_eq(uid, cred->uid) &&
!(user = find_user(uid)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p) {
if (uid_eq(task_uid(p), uid)) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
} while_each_thread(g, p);
if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
out_unlock:
read_unlock(&tasklist_lock);
rcu_read_unlock();
return retval;
}
/**
* emergency_restart - reboot the system
*
* Without shutting down any hardware or taking any locks
* reboot the system. This is called when we know we are in
* trouble so this is our best effort to reboot. This is
* safe to call in interrupt context.
*/
void emergency_restart(void)
{
kmsg_dump(KMSG_DUMP_EMERG);
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
void kernel_restart_prepare(char *cmd)
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
usermodehelper_disable();
device_shutdown();
}
/**
* register_reboot_notifier - Register function to be called at reboot time
* @nb: Info about notifier function to be called
*
* Registers a function with the list of functions
* to be called at reboot time.
*
* Currently always returns zero, as blocking_notifier_chain_register()
* always returns zero.
*/
int register_reboot_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(register_reboot_notifier);
/**
* unregister_reboot_notifier - Unregister previously registered reboot notifier
* @nb: Hook to be unregistered
*
* Unregisters a previously registered reboot
* notifier function.
*
* Returns zero on success, or %-ENOENT on failure.
*/
int unregister_reboot_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
}
EXPORT_SYMBOL(unregister_reboot_notifier);
/**
* kernel_restart - reboot the system
* @cmd: pointer to buffer containing command to execute for restart
* or %NULL
*
* Shutdown everything and perform a clean reboot.
* This is not safe to call in interrupt context.
*/
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
disable_nonboot_cpus();
syscore_shutdown();
if (!cmd)
printk(KERN_EMERG "Restarting system.\n");
else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
kmsg_dump(KMSG_DUMP_RESTART);
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
static void kernel_shutdown_prepare(enum system_states state)
{
blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
system_state = state;
usermodehelper_disable();
device_shutdown();
}
/**
* kernel_halt - halt the system
*
* Shutdown everything and perform a clean system halt.
*/
void kernel_halt(void)
{
kernel_shutdown_prepare(SYSTEM_HALT);
disable_nonboot_cpus();
syscore_shutdown();
printk(KERN_EMERG "System halted.\n");
kmsg_dump(KMSG_DUMP_HALT);
machine_halt();
}
EXPORT_SYMBOL_GPL(kernel_halt);
/**
* kernel_power_off - power_off the system
*
* Shutdown everything and perform a clean system power_off.
*/
void kernel_power_off(void)
{
kernel_shutdown_prepare(SYSTEM_POWER_OFF);
if (pm_power_off_prepare)
pm_power_off_prepare();
disable_nonboot_cpus();
syscore_shutdown();
printk(KERN_EMERG "Power down.\n");
kmsg_dump(KMSG_DUMP_POWEROFF);
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
static DEFINE_MUTEX(reboot_mutex);
/*
* Reboot system call: for obvious reasons only root may call it,
* and even root needs to set up some magic numbers in the registers
* so that some mistake won't make this reboot the whole machine.
* You can also set the meaning of the ctrl-alt-del-key here.
*
* reboot doesn't sync: do that yourself before calling this.
*/
SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
void __user *, arg)
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
char buffer[256];
int ret = 0;
/* We only trust the superuser with rebooting the system. */
if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT))
return -EPERM;
/* For safety, we require "magic" arguments. */
if (magic1 != LINUX_REBOOT_MAGIC1 ||
(magic2 != LINUX_REBOOT_MAGIC2 &&
magic2 != LINUX_REBOOT_MAGIC2A &&
magic2 != LINUX_REBOOT_MAGIC2B &&
magic2 != LINUX_REBOOT_MAGIC2C))
return -EINVAL;
/*
* If pid namespaces are enabled and the current task is in a child
* pid_namespace, the command is handled by reboot_pid_ns() which will
* call do_exit().
*/
ret = reboot_pid_ns(pid_ns, cmd);
if (ret)
return ret;
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
mutex_lock(&reboot_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
break;
case LINUX_REBOOT_CMD_CAD_ON:
C_A_D = 1;
break;
case LINUX_REBOOT_CMD_CAD_OFF:
C_A_D = 0;
break;
case LINUX_REBOOT_CMD_HALT:
kernel_halt();
do_exit(0);
panic("cannot halt");
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_power_off();
do_exit(0);
break;
case LINUX_REBOOT_CMD_RESTART2:
if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
ret = -EFAULT;
break;
}
buffer[sizeof(buffer) - 1] = '\0';
kernel_restart(buffer);
break;
#ifdef CONFIG_KEXEC
case LINUX_REBOOT_CMD_KEXEC:
ret = kernel_kexec();
break;
#endif
#ifdef CONFIG_HIBERNATION
case LINUX_REBOOT_CMD_SW_SUSPEND:
ret = hibernate();
break;
#endif
default:
ret = -EINVAL;
break;
}
mutex_unlock(&reboot_mutex);
return ret;
}
static void deferred_cad(struct work_struct *dummy)
{
kernel_restart(NULL);
}
/*
* This function gets called by ctrl-alt-del - ie the keyboard interrupt.
* As it's called within an interrupt, it may NOT sync: the only choice
* is whether to reboot at once, or just ignore the ctrl-alt-del.
*/
void ctrl_alt_del(void)
{
static DECLARE_WORK(cad_work, deferred_cad);
if (C_A_D)
schedule_work(&cad_work);
else
kill_cad_pid(SIGINT, 1);
}
/*
* Unprivileged users may change the real gid to the effective gid
* or vice versa. (BSD-style)
*
* If you set the real gid at all, or set the effective gid to a value not
* equal to the real gid, then the saved gid is set to the new effective gid.
*
* This makes it possible for a setgid program to completely drop its
* privileges, which is often a useful assertion to make when you are doing
* a security audit over a program.
*
* The general idea is that a program which uses just setregid() will be
* 100% compatible with BSD. A program which uses just setgid() will be
* 100% compatible with POSIX with saved IDs.
*
* SMP: There are not races, the GIDs are checked only by filesystem
* operations (as far as semantic preservation is concerned).
*/
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kgid_t krgid, kegid;
krgid = make_kgid(ns, rgid);
kegid = make_kgid(ns, egid);
if ((rgid != (gid_t) -1) && !gid_valid(krgid))
return -EINVAL;
if ((egid != (gid_t) -1) && !gid_valid(kegid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (rgid != (gid_t) -1) {
if (gid_eq(old->gid, krgid) ||
gid_eq(old->egid, krgid) ||
nsown_capable(CAP_SETGID))
new->gid = krgid;
else
goto error;
}
if (egid != (gid_t) -1) {
if (gid_eq(old->gid, kegid) ||
gid_eq(old->egid, kegid) ||
gid_eq(old->sgid, kegid) ||
nsown_capable(CAP_SETGID))
new->egid = kegid;
else
goto error;
}
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && !gid_eq(kegid, old->gid)))
new->sgid = new->egid;
new->fsgid = new->egid;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* setgid() is implemented like SysV w/ SAVED_IDS
*
* SMP: Same implicit races as above.
*/
SYSCALL_DEFINE1(setgid, gid_t, gid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kgid_t kgid;
kgid = make_kgid(ns, gid);
if (!gid_valid(kgid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (nsown_capable(CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = kgid;
else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
new->egid = new->fsgid = kgid;
else
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* change the user struct in a credentials set to match the new UID
*/
static int set_user(struct cred *new)
{
struct user_struct *new_user;
new_user = alloc_uid(new->uid);
if (!new_user)
return -EAGAIN;
/*
* We don't fail in case of NPROC limit excess here because too many
* poorly written programs don't check set*uid() return code, assuming
* it never fails if called by root. We may still enforce NPROC limit
* for programs doing set*uid()+execve() by harmlessly deferring the
* failure to the execve() stage.
*/
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
new_user != INIT_USER)
current->flags |= PF_NPROC_EXCEEDED;
else
current->flags &= ~PF_NPROC_EXCEEDED;
free_uid(new->user);
new->user = new_user;
return 0;
}
/*
* Unprivileged users may change the real uid to the effective uid
* or vice versa. (BSD-style)
*
* If you set the real uid at all, or set the effective uid to a value not
* equal to the real uid, then the saved uid is set to the new effective uid.
*
* This makes it possible for a setuid program to completely drop its
* privileges, which is often a useful assertion to make when you are doing
* a security audit over a program.
*
* The general idea is that a program which uses just setreuid() will be
* 100% compatible with BSD. A program which uses just setuid() will be
* 100% compatible with POSIX with saved IDs.
*/
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kruid, keuid;
kruid = make_kuid(ns, ruid);
keuid = make_kuid(ns, euid);
if ((ruid != (uid_t) -1) && !uid_valid(kruid))
return -EINVAL;
if ((euid != (uid_t) -1) && !uid_valid(keuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (ruid != (uid_t) -1) {
new->uid = kruid;
if (!uid_eq(old->uid, kruid) &&
!uid_eq(old->euid, kruid) &&
!nsown_capable(CAP_SETUID))
goto error;
}
if (euid != (uid_t) -1) {
new->euid = keuid;
if (!uid_eq(old->uid, keuid) &&
!uid_eq(old->euid, keuid) &&
!uid_eq(old->suid, keuid) &&
!nsown_capable(CAP_SETUID))
goto error;
}
if (!uid_eq(new->uid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
new->suid = new->euid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* setuid() is implemented like SysV with SAVED_IDS
*
* Note that SAVED_ID's is deficient in that a setuid root program
* like sendmail, for example, cannot set its uid to be a normal
* user and then switch back, because if you're root, setuid() sets
* the saved uid too. If you don't like this, blame the bright people
* in the POSIX committee and/or USG. Note that the BSD-style setreuid()
* will allow a root program to temporarily drop privileges and be able to
* regain them by swapping the real and effective uid.
*/
SYSCALL_DEFINE1(setuid, uid_t, uid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kuid;
kuid = make_kuid(ns, uid);
if (!uid_valid(kuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (nsown_capable(CAP_SETUID)) {
new->suid = new->uid = kuid;
if (!uid_eq(kuid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
goto error;
}
new->fsuid = new->euid = kuid;
retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
/*
* This function implements a generic ability to update ruid, euid,
* and suid. This allows you to implement the 4.4 compatible seteuid().
*/
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kuid_t kruid, keuid, ksuid;
kruid = make_kuid(ns, ruid);
keuid = make_kuid(ns, euid);
ksuid = make_kuid(ns, suid);
if ((ruid != (uid_t) -1) && !uid_valid(kruid))
return -EINVAL;
if ((euid != (uid_t) -1) && !uid_valid(keuid))
return -EINVAL;
if ((suid != (uid_t) -1) && !uid_valid(ksuid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (!nsown_capable(CAP_SETUID)) {
if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) &&
!uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
goto error;
if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) &&
!uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
goto error;
if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) &&
!uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
goto error;
}
if (ruid != (uid_t) -1) {
new->uid = kruid;
if (!uid_eq(kruid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
}
if (euid != (uid_t) -1)
new->euid = keuid;
if (suid != (uid_t) -1)
new->suid = ksuid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
if (retval < 0)
goto error;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
{
const struct cred *cred = current_cred();
int retval;
uid_t ruid, euid, suid;
ruid = from_kuid_munged(cred->user_ns, cred->uid);
euid = from_kuid_munged(cred->user_ns, cred->euid);
suid = from_kuid_munged(cred->user_ns, cred->suid);
if (!(retval = put_user(ruid, ruidp)) &&
!(retval = put_user(euid, euidp)))
retval = put_user(suid, suidp);
return retval;
}
/*
* Same as above, but for rgid, egid, sgid.
*/
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
{
struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
kgid_t krgid, kegid, ksgid;
krgid = make_kgid(ns, rgid);
kegid = make_kgid(ns, egid);
ksgid = make_kgid(ns, sgid);
if ((rgid != (gid_t) -1) && !gid_valid(krgid))
return -EINVAL;
if ((egid != (gid_t) -1) && !gid_valid(kegid))
return -EINVAL;
if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
old = current_cred();
retval = -EPERM;
if (!nsown_capable(CAP_SETGID)) {
if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) &&
!gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
goto error;
if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) &&
!gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
goto error;
if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) &&
!gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
goto error;
}
if (rgid != (gid_t) -1)
new->gid = krgid;
if (egid != (gid_t) -1)
new->egid = kegid;
if (sgid != (gid_t) -1)
new->sgid = ksgid;
new->fsgid = new->egid;
return commit_creds(new);
error:
abort_creds(new);
return retval;
}
SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
{
const struct cred *cred = current_cred();
int retval;
gid_t rgid, egid, sgid;
rgid = from_kgid_munged(cred->user_ns, cred->gid);
egid = from_kgid_munged(cred->user_ns, cred->egid);
sgid = from_kgid_munged(cred->user_ns, cred->sgid);
if (!(retval = put_user(rgid, rgidp)) &&
!(retval = put_user(egid, egidp)))
retval = put_user(sgid, sgidp);
return retval;
}
/*
* "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
* is used for "access()" and for the NFS daemon (letting nfsd stay at
* whatever uid it wants to). It normally shadows "euid", except when
* explicitly set by setfsuid() or for access..
*/
SYSCALL_DEFINE1(setfsuid, uid_t, uid)
{
const struct cred *old;
struct cred *new;
uid_t old_fsuid;
kuid_t kuid;
old = current_cred();
old_fsuid = from_kuid_munged(old->user_ns, old->fsuid);
kuid = make_kuid(old->user_ns, uid);
if (!uid_valid(kuid))
return old_fsuid;
new = prepare_creds();
if (!new)
return old_fsuid;
if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) ||
uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
nsown_capable(CAP_SETUID)) {
if (!uid_eq(kuid, old->fsuid)) {
new->fsuid = kuid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
goto change_okay;
}
}