-
Notifications
You must be signed in to change notification settings - Fork 43
/
Copy pathsyscall.c
13811 lines (12687 loc) · 436 KB
/
syscall.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 syscalls
*
* Copyright (c) 2003 Fabrice Bellard
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#define _ATFILE_SOURCE
#include "qemu/osdep.h"
#include "qemu/cutils.h"
#include "qemu/path.h"
#include "qemu/memfd.h"
#include "qemu/queue.h"
#include "qemu/plugin.h"
#include "tcg/startup.h"
#include "target_mman.h"
#include "exec/page-protection.h"
#include <elf.h>
#include <endian.h>
#include <grp.h>
#include <sys/ipc.h>
#include <sys/msg.h>
#include <sys/wait.h>
#include <sys/mount.h>
#include <sys/file.h>
#include <sys/fsuid.h>
#include <sys/personality.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/swap.h>
#include <linux/capability.h>
#include <sched.h>
#include <sys/timex.h>
#include <sys/socket.h>
#include <linux/sockios.h>
#include <sys/un.h>
#include <sys/uio.h>
#include <poll.h>
#include <sys/times.h>
#include <sys/shm.h>
#include <sys/sem.h>
#include <sys/statfs.h>
#include <utime.h>
#include <sys/sysinfo.h>
#include <sys/signalfd.h>
//#include <sys/user.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/tcp.h>
#include <netinet/udp.h>
#include <linux/wireless.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/if_tun.h>
#include <linux/in6.h>
#include <linux/errqueue.h>
#include <linux/random.h>
#ifdef CONFIG_TIMERFD
#include <sys/timerfd.h>
#endif
#ifdef CONFIG_EVENTFD
#include <sys/eventfd.h>
#endif
#ifdef CONFIG_EPOLL
#include <sys/epoll.h>
#endif
#ifdef CONFIG_ATTR
#include "qemu/xattr.h"
#endif
#ifdef CONFIG_SENDFILE
#include <sys/sendfile.h>
#endif
#ifdef HAVE_SYS_KCOV_H
#include <sys/kcov.h>
#endif
#define termios host_termios
#define winsize host_winsize
#define termio host_termio
#define sgttyb host_sgttyb /* same as target */
#define tchars host_tchars /* same as target */
#define ltchars host_ltchars /* same as target */
#include <linux/termios.h>
#include <linux/unistd.h>
#include <linux/cdrom.h>
#include <linux/hdreg.h>
#include <linux/soundcard.h>
#include <linux/kd.h>
#include <linux/mtio.h>
#include <linux/fs.h>
#include <linux/fd.h>
#if defined(CONFIG_FIEMAP)
#include <linux/fiemap.h>
#endif
#include <linux/fb.h>
#if defined(CONFIG_USBFS)
#include <linux/usbdevice_fs.h>
#include <linux/usb/ch9.h>
#endif
#include <linux/vt.h>
#include <linux/dm-ioctl.h>
#include <linux/reboot.h>
#include <linux/route.h>
#include <linux/filter.h>
#include <linux/blkpg.h>
#include <netpacket/packet.h>
#include <linux/netlink.h>
#include <linux/if_alg.h>
#include <linux/rtc.h>
#include <sound/asound.h>
#ifdef HAVE_BTRFS_H
#include <linux/btrfs.h>
#endif
#ifdef HAVE_DRM_H
#include <libdrm/drm.h>
#include <libdrm/i915_drm.h>
#endif
#include "linux_loop.h"
#include "uname.h"
#include "qemu.h"
#include "user-internals.h"
#include "strace.h"
#include "signal-common.h"
#include "loader.h"
#include "user-mmap.h"
#include "user/safe-syscall.h"
#include "qemu/guest-random.h"
#include "qemu/selfmap.h"
#include "user/syscall-trace.h"
#include "special-errno.h"
#include "qapi/error.h"
#include "fd-trans.h"
#include "cpu_loop-common.h"
#ifndef CLONE_IO
#define CLONE_IO 0x80000000 /* Clone io context */
#endif
/* We can't directly call the host clone syscall, because this will
* badly confuse libc (breaking mutexes, for example). So we must
* divide clone flags into:
* * flag combinations that look like pthread_create()
* * flag combinations that look like fork()
* * flags we can implement within QEMU itself
* * flags we can't support and will return an error for
*/
/* For thread creation, all these flags must be present; for
* fork, none must be present.
*/
#define CLONE_THREAD_FLAGS \
(CLONE_VM | CLONE_FS | CLONE_FILES | \
CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM)
/* These flags are ignored:
* CLONE_DETACHED is now ignored by the kernel;
* CLONE_IO is just an optimisation hint to the I/O scheduler
*/
#define CLONE_IGNORED_FLAGS \
(CLONE_DETACHED | CLONE_IO)
#ifndef CLONE_PIDFD
# define CLONE_PIDFD 0x00001000
#endif
/* Flags for fork which we can implement within QEMU itself */
#define CLONE_OPTIONAL_FORK_FLAGS \
(CLONE_SETTLS | CLONE_PARENT_SETTID | CLONE_PIDFD | \
CLONE_CHILD_CLEARTID | CLONE_CHILD_SETTID)
/* Flags for thread creation which we can implement within QEMU itself */
#define CLONE_OPTIONAL_THREAD_FLAGS \
(CLONE_SETTLS | CLONE_PARENT_SETTID | \
CLONE_CHILD_CLEARTID | CLONE_CHILD_SETTID | CLONE_PARENT)
#define CLONE_INVALID_FORK_FLAGS \
(~(CSIGNAL | CLONE_OPTIONAL_FORK_FLAGS | CLONE_IGNORED_FLAGS))
#define CLONE_INVALID_THREAD_FLAGS \
(~(CSIGNAL | CLONE_THREAD_FLAGS | CLONE_OPTIONAL_THREAD_FLAGS | \
CLONE_IGNORED_FLAGS))
/* CLONE_VFORK is special cased early in do_fork(). The other flag bits
* have almost all been allocated. We cannot support any of
* CLONE_NEWNS, CLONE_NEWCGROUP, CLONE_NEWUTS, CLONE_NEWIPC,
* CLONE_NEWUSER, CLONE_NEWPID, CLONE_NEWNET, CLONE_PTRACE, CLONE_UNTRACED.
* The checks against the invalid thread masks above will catch these.
* (The one remaining unallocated bit is 0x1000 which used to be CLONE_PID.)
*/
/* Define DEBUG_ERESTARTSYS to force every syscall to be restarted
* once. This exercises the codepaths for restart.
*/
//#define DEBUG_ERESTARTSYS
//#include <linux/msdos_fs.h>
#define VFAT_IOCTL_READDIR_BOTH \
_IOC(_IOC_READ, 'r', 1, (sizeof(struct linux_dirent) + 256) * 2)
#define VFAT_IOCTL_READDIR_SHORT \
_IOC(_IOC_READ, 'r', 2, (sizeof(struct linux_dirent) + 256) * 2)
#undef _syscall0
#undef _syscall1
#undef _syscall2
#undef _syscall3
#undef _syscall4
#undef _syscall5
#undef _syscall6
#define _syscall0(type,name) \
static type name (void) \
{ \
return syscall(__NR_##name); \
}
#define _syscall1(type,name,type1,arg1) \
static type name (type1 arg1) \
{ \
return syscall(__NR_##name, arg1); \
}
#define _syscall2(type,name,type1,arg1,type2,arg2) \
static type name (type1 arg1,type2 arg2) \
{ \
return syscall(__NR_##name, arg1, arg2); \
}
#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3) \
static type name (type1 arg1,type2 arg2,type3 arg3) \
{ \
return syscall(__NR_##name, arg1, arg2, arg3); \
}
#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4) \
{ \
return syscall(__NR_##name, arg1, arg2, arg3, arg4); \
}
#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
type5,arg5) \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
{ \
return syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5); \
}
#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4, \
type5,arg5,type6,arg6) \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5, \
type6 arg6) \
{ \
return syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5, arg6); \
}
#define __NR_sys_uname __NR_uname
#define __NR_sys_getcwd1 __NR_getcwd
#define __NR_sys_getdents __NR_getdents
#define __NR_sys_getdents64 __NR_getdents64
#define __NR_sys_getpriority __NR_getpriority
#define __NR_sys_rt_sigqueueinfo __NR_rt_sigqueueinfo
#define __NR_sys_rt_tgsigqueueinfo __NR_rt_tgsigqueueinfo
#define __NR_sys_syslog __NR_syslog
#if defined(__NR_futex)
# define __NR_sys_futex __NR_futex
#endif
#if defined(__NR_futex_time64)
# define __NR_sys_futex_time64 __NR_futex_time64
#endif
#define __NR_sys_statx __NR_statx
#if defined(__alpha__) || defined(__x86_64__) || defined(__s390x__)
#define __NR__llseek __NR_lseek
#endif
/* Newer kernel ports have llseek() instead of _llseek() */
#if defined(TARGET_NR_llseek) && !defined(TARGET_NR__llseek)
#define TARGET_NR__llseek TARGET_NR_llseek
#endif
/* some platforms need to mask more bits than just TARGET_O_NONBLOCK */
#ifndef TARGET_O_NONBLOCK_MASK
#define TARGET_O_NONBLOCK_MASK TARGET_O_NONBLOCK
#endif
#define __NR_sys_gettid __NR_gettid
_syscall0(int, sys_gettid)
/* For the 64-bit guest on 32-bit host case we must emulate
* getdents using getdents64, because otherwise the host
* might hand us back more dirent records than we can fit
* into the guest buffer after structure format conversion.
* Otherwise we emulate getdents with getdents if the host has it.
*/
#if defined(__NR_getdents) && HOST_LONG_BITS >= TARGET_ABI_BITS
#define EMULATE_GETDENTS_WITH_GETDENTS
#endif
#if defined(TARGET_NR_getdents) && defined(EMULATE_GETDENTS_WITH_GETDENTS)
_syscall3(int, sys_getdents, unsigned int, fd, struct linux_dirent *, dirp, unsigned int, count);
#endif
#if (defined(TARGET_NR_getdents) && \
!defined(EMULATE_GETDENTS_WITH_GETDENTS)) || \
(defined(TARGET_NR_getdents64) && defined(__NR_getdents64))
_syscall3(int, sys_getdents64, unsigned int, fd, struct linux_dirent64 *, dirp, unsigned int, count);
#endif
#if defined(TARGET_NR__llseek) && defined(__NR_llseek)
_syscall5(int, _llseek, unsigned int, fd, unsigned long, hi, unsigned long, lo,
loff_t *, res, unsigned int, wh);
#endif
_syscall3(int, sys_rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t *, uinfo)
_syscall4(int, sys_rt_tgsigqueueinfo, pid_t, pid, pid_t, tid, int, sig,
siginfo_t *, uinfo)
_syscall3(int,sys_syslog,int,type,char*,bufp,int,len)
#ifdef __NR_exit_group
_syscall1(int,exit_group,int,error_code)
#endif
#if defined(__NR_close_range) && defined(TARGET_NR_close_range)
#define __NR_sys_close_range __NR_close_range
_syscall3(int,sys_close_range,int,first,int,last,int,flags)
#ifndef CLOSE_RANGE_CLOEXEC
#define CLOSE_RANGE_CLOEXEC (1U << 2)
#endif
#endif
#if defined(__NR_futex)
_syscall6(int,sys_futex,int *,uaddr,int,op,int,val,
const struct timespec *,timeout,int *,uaddr2,int,val3)
#endif
#if defined(__NR_futex_time64)
_syscall6(int,sys_futex_time64,int *,uaddr,int,op,int,val,
const struct timespec *,timeout,int *,uaddr2,int,val3)
#endif
#if defined(__NR_pidfd_open) && defined(TARGET_NR_pidfd_open)
_syscall2(int, pidfd_open, pid_t, pid, unsigned int, flags);
#endif
#if defined(__NR_pidfd_send_signal) && defined(TARGET_NR_pidfd_send_signal)
_syscall4(int, pidfd_send_signal, int, pidfd, int, sig, siginfo_t *, info,
unsigned int, flags);
#endif
#if defined(__NR_pidfd_getfd) && defined(TARGET_NR_pidfd_getfd)
_syscall3(int, pidfd_getfd, int, pidfd, int, targetfd, unsigned int, flags);
#endif
#define __NR_sys_sched_getaffinity __NR_sched_getaffinity
_syscall3(int, sys_sched_getaffinity, pid_t, pid, unsigned int, len,
unsigned long *, user_mask_ptr);
#define __NR_sys_sched_setaffinity __NR_sched_setaffinity
_syscall3(int, sys_sched_setaffinity, pid_t, pid, unsigned int, len,
unsigned long *, user_mask_ptr);
/* sched_attr is not defined in glibc */
struct sched_attr {
uint32_t size;
uint32_t sched_policy;
uint64_t sched_flags;
int32_t sched_nice;
uint32_t sched_priority;
uint64_t sched_runtime;
uint64_t sched_deadline;
uint64_t sched_period;
uint32_t sched_util_min;
uint32_t sched_util_max;
};
#define __NR_sys_sched_getattr __NR_sched_getattr
_syscall4(int, sys_sched_getattr, pid_t, pid, struct sched_attr *, attr,
unsigned int, size, unsigned int, flags);
#define __NR_sys_sched_setattr __NR_sched_setattr
_syscall3(int, sys_sched_setattr, pid_t, pid, struct sched_attr *, attr,
unsigned int, flags);
#define __NR_sys_sched_getscheduler __NR_sched_getscheduler
_syscall1(int, sys_sched_getscheduler, pid_t, pid);
#define __NR_sys_sched_setscheduler __NR_sched_setscheduler
_syscall3(int, sys_sched_setscheduler, pid_t, pid, int, policy,
const struct sched_param *, param);
#define __NR_sys_sched_getparam __NR_sched_getparam
_syscall2(int, sys_sched_getparam, pid_t, pid,
struct sched_param *, param);
#define __NR_sys_sched_setparam __NR_sched_setparam
_syscall2(int, sys_sched_setparam, pid_t, pid,
const struct sched_param *, param);
#define __NR_sys_getcpu __NR_getcpu
_syscall3(int, sys_getcpu, unsigned *, cpu, unsigned *, node, void *, tcache);
_syscall4(int, reboot, int, magic1, int, magic2, unsigned int, cmd,
void *, arg);
_syscall2(int, capget, struct __user_cap_header_struct *, header,
struct __user_cap_data_struct *, data);
_syscall2(int, capset, struct __user_cap_header_struct *, header,
struct __user_cap_data_struct *, data);
#if defined(TARGET_NR_ioprio_get) && defined(__NR_ioprio_get)
_syscall2(int, ioprio_get, int, which, int, who)
#endif
#if defined(TARGET_NR_ioprio_set) && defined(__NR_ioprio_set)
_syscall3(int, ioprio_set, int, which, int, who, int, ioprio)
#endif
#if defined(TARGET_NR_getrandom) && defined(__NR_getrandom)
_syscall3(int, getrandom, void *, buf, size_t, buflen, unsigned int, flags)
#endif
#if defined(TARGET_NR_kcmp) && defined(__NR_kcmp)
_syscall5(int, kcmp, pid_t, pid1, pid_t, pid2, int, type,
unsigned long, idx1, unsigned long, idx2)
#endif
/*
* It is assumed that struct statx is architecture independent.
*/
#if defined(TARGET_NR_statx) && defined(__NR_statx)
_syscall5(int, sys_statx, int, dirfd, const char *, pathname, int, flags,
unsigned int, mask, struct target_statx *, statxbuf)
#endif
#if defined(TARGET_NR_membarrier) && defined(__NR_membarrier)
_syscall2(int, membarrier, int, cmd, int, flags)
#endif
static const bitmask_transtbl fcntl_flags_tbl[] = {
{ TARGET_O_ACCMODE, TARGET_O_WRONLY, O_ACCMODE, O_WRONLY, },
{ TARGET_O_ACCMODE, TARGET_O_RDWR, O_ACCMODE, O_RDWR, },
{ TARGET_O_CREAT, TARGET_O_CREAT, O_CREAT, O_CREAT, },
{ TARGET_O_EXCL, TARGET_O_EXCL, O_EXCL, O_EXCL, },
{ TARGET_O_NOCTTY, TARGET_O_NOCTTY, O_NOCTTY, O_NOCTTY, },
{ TARGET_O_TRUNC, TARGET_O_TRUNC, O_TRUNC, O_TRUNC, },
{ TARGET_O_APPEND, TARGET_O_APPEND, O_APPEND, O_APPEND, },
{ TARGET_O_NONBLOCK, TARGET_O_NONBLOCK, O_NONBLOCK, O_NONBLOCK, },
{ TARGET_O_SYNC, TARGET_O_DSYNC, O_SYNC, O_DSYNC, },
{ TARGET_O_SYNC, TARGET_O_SYNC, O_SYNC, O_SYNC, },
{ TARGET_FASYNC, TARGET_FASYNC, FASYNC, FASYNC, },
{ TARGET_O_DIRECTORY, TARGET_O_DIRECTORY, O_DIRECTORY, O_DIRECTORY, },
{ TARGET_O_NOFOLLOW, TARGET_O_NOFOLLOW, O_NOFOLLOW, O_NOFOLLOW, },
#if defined(O_DIRECT)
{ TARGET_O_DIRECT, TARGET_O_DIRECT, O_DIRECT, O_DIRECT, },
#endif
#if defined(O_NOATIME)
{ TARGET_O_NOATIME, TARGET_O_NOATIME, O_NOATIME, O_NOATIME },
#endif
#if defined(O_CLOEXEC)
{ TARGET_O_CLOEXEC, TARGET_O_CLOEXEC, O_CLOEXEC, O_CLOEXEC },
#endif
#if defined(O_PATH)
{ TARGET_O_PATH, TARGET_O_PATH, O_PATH, O_PATH },
#endif
#if defined(O_TMPFILE)
{ TARGET_O_TMPFILE, TARGET_O_TMPFILE, O_TMPFILE, O_TMPFILE },
#endif
/* Don't terminate the list prematurely on 64-bit host+guest. */
#if TARGET_O_LARGEFILE != 0 || O_LARGEFILE != 0
{ TARGET_O_LARGEFILE, TARGET_O_LARGEFILE, O_LARGEFILE, O_LARGEFILE, },
#endif
};
_syscall2(int, sys_getcwd1, char *, buf, size_t, size)
#if defined(TARGET_NR_utimensat) || defined(TARGET_NR_utimensat_time64)
#if defined(__NR_utimensat)
#define __NR_sys_utimensat __NR_utimensat
_syscall4(int,sys_utimensat,int,dirfd,const char *,pathname,
const struct timespec *,tsp,int,flags)
#else
static int sys_utimensat(int dirfd, const char *pathname,
const struct timespec times[2], int flags)
{
errno = ENOSYS;
return -1;
}
#endif
#endif /* TARGET_NR_utimensat */
#ifdef TARGET_NR_renameat2
#if defined(__NR_renameat2)
#define __NR_sys_renameat2 __NR_renameat2
_syscall5(int, sys_renameat2, int, oldfd, const char *, old, int, newfd,
const char *, new, unsigned int, flags)
#else
static int sys_renameat2(int oldfd, const char *old,
int newfd, const char *new, int flags)
{
if (flags == 0) {
return renameat(oldfd, old, newfd, new);
}
errno = ENOSYS;
return -1;
}
#endif
#endif /* TARGET_NR_renameat2 */
#ifdef CONFIG_INOTIFY
#include <sys/inotify.h>
#else
/* Userspace can usually survive runtime without inotify */
#undef TARGET_NR_inotify_init
#undef TARGET_NR_inotify_init1
#undef TARGET_NR_inotify_add_watch
#undef TARGET_NR_inotify_rm_watch
#endif /* CONFIG_INOTIFY */
#if defined(TARGET_NR_prlimit64)
#ifndef __NR_prlimit64
# define __NR_prlimit64 -1
#endif
#define __NR_sys_prlimit64 __NR_prlimit64
/* The glibc rlimit structure may not be that used by the underlying syscall */
struct host_rlimit64 {
uint64_t rlim_cur;
uint64_t rlim_max;
};
_syscall4(int, sys_prlimit64, pid_t, pid, int, resource,
const struct host_rlimit64 *, new_limit,
struct host_rlimit64 *, old_limit)
#endif
#if defined(TARGET_NR_timer_create)
/* Maximum of 32 active POSIX timers allowed at any one time. */
#define GUEST_TIMER_MAX 32
static timer_t g_posix_timers[GUEST_TIMER_MAX];
static int g_posix_timer_allocated[GUEST_TIMER_MAX];
static inline int next_free_host_timer(void)
{
int k;
for (k = 0; k < ARRAY_SIZE(g_posix_timer_allocated); k++) {
if (qatomic_xchg(g_posix_timer_allocated + k, 1) == 0) {
return k;
}
}
return -1;
}
static inline void free_host_timer_slot(int id)
{
qatomic_store_release(g_posix_timer_allocated + id, 0);
}
#endif
static inline int host_to_target_errno(int host_errno)
{
switch (host_errno) {
#define E(X) case X: return TARGET_##X;
#include "errnos.c.inc"
#undef E
default:
return host_errno;
}
}
static inline int target_to_host_errno(int target_errno)
{
switch (target_errno) {
#define E(X) case TARGET_##X: return X;
#include "errnos.c.inc"
#undef E
default:
return target_errno;
}
}
abi_long get_errno(abi_long ret)
{
if (ret == -1)
return -host_to_target_errno(errno);
else
return ret;
}
const char *target_strerror(int err)
{
if (err == QEMU_ERESTARTSYS) {
return "To be restarted";
}
if (err == QEMU_ESIGRETURN) {
return "Successful exit from sigreturn";
}
return strerror(target_to_host_errno(err));
}
static int check_zeroed_user(abi_long addr, size_t ksize, size_t usize)
{
int i;
uint8_t b;
if (usize <= ksize) {
return 1;
}
for (i = ksize; i < usize; i++) {
if (get_user_u8(b, addr + i)) {
return -TARGET_EFAULT;
}
if (b != 0) {
return 0;
}
}
return 1;
}
#define safe_syscall0(type, name) \
static type safe_##name(void) \
{ \
return safe_syscall(__NR_##name); \
}
#define safe_syscall1(type, name, type1, arg1) \
static type safe_##name(type1 arg1) \
{ \
return safe_syscall(__NR_##name, arg1); \
}
#define safe_syscall2(type, name, type1, arg1, type2, arg2) \
static type safe_##name(type1 arg1, type2 arg2) \
{ \
return safe_syscall(__NR_##name, arg1, arg2); \
}
#define safe_syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3) \
{ \
return safe_syscall(__NR_##name, arg1, arg2, arg3); \
}
#define safe_syscall4(type, name, type1, arg1, type2, arg2, type3, arg3, \
type4, arg4) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
{ \
return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4); \
}
#define safe_syscall5(type, name, type1, arg1, type2, arg2, type3, arg3, \
type4, arg4, type5, arg5) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \
type5 arg5) \
{ \
return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5); \
}
#define safe_syscall6(type, name, type1, arg1, type2, arg2, type3, arg3, \
type4, arg4, type5, arg5, type6, arg6) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \
type5 arg5, type6 arg6) \
{ \
return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5, arg6); \
}
safe_syscall3(ssize_t, read, int, fd, void *, buff, size_t, count)
safe_syscall3(ssize_t, write, int, fd, const void *, buff, size_t, count)
safe_syscall4(int, openat, int, dirfd, const char *, pathname, \
int, flags, mode_t, mode)
#if defined(TARGET_NR_wait4) || defined(TARGET_NR_waitpid)
safe_syscall4(pid_t, wait4, pid_t, pid, int *, status, int, options, \
struct rusage *, rusage)
#endif
safe_syscall5(int, waitid, idtype_t, idtype, id_t, id, siginfo_t *, infop, \
int, options, struct rusage *, rusage)
safe_syscall3(int, execve, const char *, filename, char **, argv, char **, envp)
safe_syscall5(int, execveat, int, dirfd, const char *, filename,
char **, argv, char **, envp, int, flags)
#if defined(TARGET_NR_select) || defined(TARGET_NR__newselect) || \
defined(TARGET_NR_pselect6) || defined(TARGET_NR_pselect6_time64)
safe_syscall6(int, pselect6, int, nfds, fd_set *, readfds, fd_set *, writefds, \
fd_set *, exceptfds, struct timespec *, timeout, void *, sig)
#endif
#if defined(TARGET_NR_ppoll) || defined(TARGET_NR_ppoll_time64)
safe_syscall5(int, ppoll, struct pollfd *, ufds, unsigned int, nfds,
struct timespec *, tsp, const sigset_t *, sigmask,
size_t, sigsetsize)
#endif
safe_syscall6(int, epoll_pwait, int, epfd, struct epoll_event *, events,
int, maxevents, int, timeout, const sigset_t *, sigmask,
size_t, sigsetsize)
#if defined(__NR_futex)
safe_syscall6(int,futex,int *,uaddr,int,op,int,val, \
const struct timespec *,timeout,int *,uaddr2,int,val3)
#endif
#if defined(__NR_futex_time64)
safe_syscall6(int,futex_time64,int *,uaddr,int,op,int,val, \
const struct timespec *,timeout,int *,uaddr2,int,val3)
#endif
safe_syscall2(int, rt_sigsuspend, sigset_t *, newset, size_t, sigsetsize)
safe_syscall2(int, kill, pid_t, pid, int, sig)
safe_syscall2(int, tkill, int, tid, int, sig)
safe_syscall3(int, tgkill, int, tgid, int, pid, int, sig)
safe_syscall3(ssize_t, readv, int, fd, const struct iovec *, iov, int, iovcnt)
safe_syscall3(ssize_t, writev, int, fd, const struct iovec *, iov, int, iovcnt)
safe_syscall5(ssize_t, preadv, int, fd, const struct iovec *, iov, int, iovcnt,
unsigned long, pos_l, unsigned long, pos_h)
safe_syscall5(ssize_t, pwritev, int, fd, const struct iovec *, iov, int, iovcnt,
unsigned long, pos_l, unsigned long, pos_h)
safe_syscall3(int, connect, int, fd, const struct sockaddr *, addr,
socklen_t, addrlen)
safe_syscall6(ssize_t, sendto, int, fd, const void *, buf, size_t, len,
int, flags, const struct sockaddr *, addr, socklen_t, addrlen)
safe_syscall6(ssize_t, recvfrom, int, fd, void *, buf, size_t, len,
int, flags, struct sockaddr *, addr, socklen_t *, addrlen)
safe_syscall3(ssize_t, sendmsg, int, fd, const struct msghdr *, msg, int, flags)
safe_syscall3(ssize_t, recvmsg, int, fd, struct msghdr *, msg, int, flags)
safe_syscall2(int, flock, int, fd, int, operation)
#if defined(TARGET_NR_rt_sigtimedwait) || defined(TARGET_NR_rt_sigtimedwait_time64)
safe_syscall4(int, rt_sigtimedwait, const sigset_t *, these, siginfo_t *, uinfo,
const struct timespec *, uts, size_t, sigsetsize)
#endif
safe_syscall4(int, accept4, int, fd, struct sockaddr *, addr, socklen_t *, len,
int, flags)
#if defined(TARGET_NR_nanosleep)
safe_syscall2(int, nanosleep, const struct timespec *, req,
struct timespec *, rem)
#endif
#if defined(TARGET_NR_clock_nanosleep) || \
defined(TARGET_NR_clock_nanosleep_time64)
safe_syscall4(int, clock_nanosleep, const clockid_t, clock, int, flags,
const struct timespec *, req, struct timespec *, rem)
#endif
#ifdef __NR_ipc
#ifdef __s390x__
safe_syscall5(int, ipc, int, call, long, first, long, second, long, third,
void *, ptr)
#else
safe_syscall6(int, ipc, int, call, long, first, long, second, long, third,
void *, ptr, long, fifth)
#endif
#endif
#ifdef __NR_msgsnd
safe_syscall4(int, msgsnd, int, msgid, const void *, msgp, size_t, sz,
int, flags)
#endif
#ifdef __NR_msgrcv
safe_syscall5(int, msgrcv, int, msgid, void *, msgp, size_t, sz,
long, msgtype, int, flags)
#endif
#ifdef __NR_semtimedop
safe_syscall4(int, semtimedop, int, semid, struct sembuf *, tsops,
unsigned, nsops, const struct timespec *, timeout)
#endif
#if defined(TARGET_NR_mq_timedsend) || \
defined(TARGET_NR_mq_timedsend_time64)
safe_syscall5(int, mq_timedsend, int, mqdes, const char *, msg_ptr,
size_t, len, unsigned, prio, const struct timespec *, timeout)
#endif
#if defined(TARGET_NR_mq_timedreceive) || \
defined(TARGET_NR_mq_timedreceive_time64)
safe_syscall5(int, mq_timedreceive, int, mqdes, char *, msg_ptr,
size_t, len, unsigned *, prio, const struct timespec *, timeout)
#endif
#if defined(TARGET_NR_copy_file_range) && defined(__NR_copy_file_range)
safe_syscall6(ssize_t, copy_file_range, int, infd, loff_t *, pinoff,
int, outfd, loff_t *, poutoff, size_t, length,
unsigned int, flags)
#endif
/* We do ioctl like this rather than via safe_syscall3 to preserve the
* "third argument might be integer or pointer or not present" behaviour of
* the libc function.
*/
#define safe_ioctl(...) safe_syscall(__NR_ioctl, __VA_ARGS__)
/* Similarly for fcntl. Note that callers must always:
* pass the F_GETLK64 etc constants rather than the unsuffixed F_GETLK
* use the flock64 struct rather than unsuffixed flock
* This will then work and use a 64-bit offset for both 32-bit and 64-bit hosts.
*/
#ifdef __NR_fcntl64
#define safe_fcntl(...) safe_syscall(__NR_fcntl64, __VA_ARGS__)
#else
#define safe_fcntl(...) safe_syscall(__NR_fcntl, __VA_ARGS__)
#endif
static inline int host_to_target_sock_type(int host_type)
{
int target_type;
switch (host_type & 0xf /* SOCK_TYPE_MASK */) {
case SOCK_DGRAM:
target_type = TARGET_SOCK_DGRAM;
break;
case SOCK_STREAM:
target_type = TARGET_SOCK_STREAM;
break;
default:
target_type = host_type & 0xf /* SOCK_TYPE_MASK */;
break;
}
#if defined(SOCK_CLOEXEC)
if (host_type & SOCK_CLOEXEC) {
target_type |= TARGET_SOCK_CLOEXEC;
}
#endif
#if defined(SOCK_NONBLOCK)
if (host_type & SOCK_NONBLOCK) {
target_type |= TARGET_SOCK_NONBLOCK;
}
#endif
return target_type;
}
static abi_ulong target_brk, initial_target_brk;
void target_set_brk(abi_ulong new_brk)
{
target_brk = TARGET_PAGE_ALIGN(new_brk);
initial_target_brk = target_brk;
}
/* do_brk() must return target values and target errnos. */
abi_long do_brk(abi_ulong brk_val)
{
abi_long mapped_addr;
abi_ulong new_brk;
abi_ulong old_brk;
/* brk pointers are always untagged */
/* do not allow to shrink below initial brk value */
if (brk_val < initial_target_brk) {
return target_brk;
}
new_brk = TARGET_PAGE_ALIGN(brk_val);
old_brk = TARGET_PAGE_ALIGN(target_brk);
/* new and old target_brk might be on the same page */
if (new_brk == old_brk) {
target_brk = brk_val;
return target_brk;
}
/* Release heap if necessary */
if (new_brk < old_brk) {
target_munmap(new_brk, old_brk - new_brk);
target_brk = brk_val;
return target_brk;
}
mapped_addr = target_mmap(old_brk, new_brk - old_brk,
PROT_READ | PROT_WRITE,
MAP_FIXED_NOREPLACE | MAP_ANON | MAP_PRIVATE,
-1, 0);
if (mapped_addr == old_brk) {
target_brk = brk_val;
return target_brk;
}
#if defined(TARGET_ALPHA)
/* We (partially) emulate OSF/1 on Alpha, which requires we
return a proper errno, not an unchanged brk value. */
return -TARGET_ENOMEM;
#endif
/* For everything else, return the previous break. */
return target_brk;
}
#if defined(TARGET_NR_select) || defined(TARGET_NR__newselect) || \
defined(TARGET_NR_pselect6) || defined(TARGET_NR_pselect6_time64)
static inline abi_long copy_from_user_fdset(fd_set *fds,
abi_ulong target_fds_addr,
int n)
{
int i, nw, j, k;
abi_ulong b, *target_fds;
nw = DIV_ROUND_UP(n, TARGET_ABI_BITS);
if (!(target_fds = lock_user(VERIFY_READ,
target_fds_addr,
sizeof(abi_ulong) * nw,
1)))
return -TARGET_EFAULT;
FD_ZERO(fds);
k = 0;
for (i = 0; i < nw; i++) {
/* grab the abi_ulong */
__get_user(b, &target_fds[i]);
for (j = 0; j < TARGET_ABI_BITS; j++) {
/* check the bit inside the abi_ulong */
if ((b >> j) & 1)
FD_SET(k, fds);
k++;
}
}
unlock_user(target_fds, target_fds_addr, 0);
return 0;
}
static inline abi_ulong copy_from_user_fdset_ptr(fd_set *fds, fd_set **fds_ptr,
abi_ulong target_fds_addr,
int n)
{
if (target_fds_addr) {
if (copy_from_user_fdset(fds, target_fds_addr, n))
return -TARGET_EFAULT;
*fds_ptr = fds;
} else {
*fds_ptr = NULL;
}
return 0;
}
static inline abi_long copy_to_user_fdset(abi_ulong target_fds_addr,
const fd_set *fds,
int n)
{
int i, nw, j, k;
abi_long v;
abi_ulong *target_fds;
nw = DIV_ROUND_UP(n, TARGET_ABI_BITS);
if (!(target_fds = lock_user(VERIFY_WRITE,
target_fds_addr,
sizeof(abi_ulong) * nw,
0)))
return -TARGET_EFAULT;
k = 0;
for (i = 0; i < nw; i++) {
v = 0;
for (j = 0; j < TARGET_ABI_BITS; j++) {
v |= ((abi_ulong)(FD_ISSET(k, fds) != 0) << j);
k++;
}
__put_user(v, &target_fds[i]);
}
unlock_user(target_fds, target_fds_addr, sizeof(abi_ulong) * nw);
return 0;
}
#endif
#if defined(__alpha__)
#define HOST_HZ 1024
#else
#define HOST_HZ 100
#endif
static inline abi_long host_to_target_clock_t(long ticks)
{
#if HOST_HZ == TARGET_HZ
return ticks;
#else
return ((int64_t)ticks * TARGET_HZ) / HOST_HZ;
#endif
}
static inline abi_long host_to_target_rusage(abi_ulong target_addr,
const struct rusage *rusage)
{
struct target_rusage *target_rusage;
if (!lock_user_struct(VERIFY_WRITE, target_rusage, target_addr, 0))
return -TARGET_EFAULT;
target_rusage->ru_utime.tv_sec = tswapal(rusage->ru_utime.tv_sec);
target_rusage->ru_utime.tv_usec = tswapal(rusage->ru_utime.tv_usec);
target_rusage->ru_stime.tv_sec = tswapal(rusage->ru_stime.tv_sec);
target_rusage->ru_stime.tv_usec = tswapal(rusage->ru_stime.tv_usec);
target_rusage->ru_maxrss = tswapal(rusage->ru_maxrss);
target_rusage->ru_ixrss = tswapal(rusage->ru_ixrss);
target_rusage->ru_idrss = tswapal(rusage->ru_idrss);
target_rusage->ru_isrss = tswapal(rusage->ru_isrss);
target_rusage->ru_minflt = tswapal(rusage->ru_minflt);
target_rusage->ru_majflt = tswapal(rusage->ru_majflt);
target_rusage->ru_nswap = tswapal(rusage->ru_nswap);
target_rusage->ru_inblock = tswapal(rusage->ru_inblock);
target_rusage->ru_oublock = tswapal(rusage->ru_oublock);
target_rusage->ru_msgsnd = tswapal(rusage->ru_msgsnd);
target_rusage->ru_msgrcv = tswapal(rusage->ru_msgrcv);
target_rusage->ru_nsignals = tswapal(rusage->ru_nsignals);
target_rusage->ru_nvcsw = tswapal(rusage->ru_nvcsw);
target_rusage->ru_nivcsw = tswapal(rusage->ru_nivcsw);
unlock_user_struct(target_rusage, target_addr, 1);
return 0;
}
#ifdef TARGET_NR_setrlimit
static inline rlim_t target_to_host_rlim(abi_ulong target_rlim)
{
abi_ulong target_rlim_swap;
rlim_t result;
target_rlim_swap = tswapal(target_rlim);
if (target_rlim_swap == TARGET_RLIM_INFINITY)
return RLIM_INFINITY;
result = target_rlim_swap;
if (target_rlim_swap != (rlim_t)result)
return RLIM_INFINITY;
return result;