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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
|
/*-
* Copyright (c) 2000 Marcel Moolenaar
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer
* in this position and unchanged.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/file.h>
#include <sys/fcntl.h>
#include <sys/imgact.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mman.h>
#include <sys/mutex.h>
#include <sys/sx.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/queue.h>
#include <sys/resource.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/syscallsubr.h>
#include <sys/sysproto.h>
#include <sys/unistd.h>
#include <sys/wait.h>
#include <sys/sched.h>
#include <machine/frame.h>
#include <machine/psl.h>
#include <machine/segments.h>
#include <machine/sysarch.h>
#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <i386/linux/linux.h>
#include <i386/linux/linux_proto.h>
#include <compat/linux/linux_ipc.h>
#include <compat/linux/linux_misc.h>
#include <compat/linux/linux_signal.h>
#include <compat/linux/linux_util.h>
#include <compat/linux/linux_emul.h>
#include <i386/include/pcb.h> /* needed for pcb definition in linux_set_thread_area */
#include "opt_posix.h"
extern struct sysentvec elf32_freebsd_sysvec; /* defined in i386/i386/elf_machdep.c */
struct l_descriptor {
l_uint entry_number;
l_ulong base_addr;
l_uint limit;
l_uint seg_32bit:1;
l_uint contents:2;
l_uint read_exec_only:1;
l_uint limit_in_pages:1;
l_uint seg_not_present:1;
l_uint useable:1;
};
struct l_old_select_argv {
l_int nfds;
l_fd_set *readfds;
l_fd_set *writefds;
l_fd_set *exceptfds;
struct l_timeval *timeout;
};
static int linux_mmap_common(struct thread *td, l_uintptr_t addr,
l_size_t len, l_int prot, l_int flags, l_int fd,
l_loff_t pos);
int
linux_to_bsd_sigaltstack(int lsa)
{
int bsa = 0;
if (lsa & LINUX_SS_DISABLE)
bsa |= SS_DISABLE;
if (lsa & LINUX_SS_ONSTACK)
bsa |= SS_ONSTACK;
return (bsa);
}
int
bsd_to_linux_sigaltstack(int bsa)
{
int lsa = 0;
if (bsa & SS_DISABLE)
lsa |= LINUX_SS_DISABLE;
if (bsa & SS_ONSTACK)
lsa |= LINUX_SS_ONSTACK;
return (lsa);
}
int
linux_execve(struct thread *td, struct linux_execve_args *args)
{
int error;
char *newpath;
struct image_args eargs;
LCONVPATHEXIST(td, args->path, &newpath);
#ifdef DEBUG
if (ldebug(execve))
printf(ARGS(execve, "%s"), newpath);
#endif
error = exec_copyin_args(&eargs, newpath, UIO_SYSSPACE,
args->argp, args->envp);
free(newpath, M_TEMP);
if (error == 0)
error = kern_execve(td, &eargs, NULL);
if (error == 0)
/* linux process can exec fbsd one, dont attempt
* to create emuldata for such process using
* linux_proc_init, this leads to a panic on KASSERT
* because such process has p->p_emuldata == NULL
*/
if (SV_PROC_ABI(td->td_proc) == SV_ABI_LINUX)
error = linux_proc_init(td, 0, 0);
return (error);
}
struct l_ipc_kludge {
struct l_msgbuf *msgp;
l_long msgtyp;
};
int
linux_ipc(struct thread *td, struct linux_ipc_args *args)
{
switch (args->what & 0xFFFF) {
case LINUX_SEMOP: {
struct linux_semop_args a;
a.semid = args->arg1;
a.tsops = args->ptr;
a.nsops = args->arg2;
return (linux_semop(td, &a));
}
case LINUX_SEMGET: {
struct linux_semget_args a;
a.key = args->arg1;
a.nsems = args->arg2;
a.semflg = args->arg3;
return (linux_semget(td, &a));
}
case LINUX_SEMCTL: {
struct linux_semctl_args a;
int error;
a.semid = args->arg1;
a.semnum = args->arg2;
a.cmd = args->arg3;
error = copyin(args->ptr, &a.arg, sizeof(a.arg));
if (error)
return (error);
return (linux_semctl(td, &a));
}
case LINUX_MSGSND: {
struct linux_msgsnd_args a;
a.msqid = args->arg1;
a.msgp = args->ptr;
a.msgsz = args->arg2;
a.msgflg = args->arg3;
return (linux_msgsnd(td, &a));
}
case LINUX_MSGRCV: {
struct linux_msgrcv_args a;
a.msqid = args->arg1;
a.msgsz = args->arg2;
a.msgflg = args->arg3;
if ((args->what >> 16) == 0) {
struct l_ipc_kludge tmp;
int error;
if (args->ptr == NULL)
return (EINVAL);
error = copyin(args->ptr, &tmp, sizeof(tmp));
if (error)
return (error);
a.msgp = tmp.msgp;
a.msgtyp = tmp.msgtyp;
} else {
a.msgp = args->ptr;
a.msgtyp = args->arg5;
}
return (linux_msgrcv(td, &a));
}
case LINUX_MSGGET: {
struct linux_msgget_args a;
a.key = args->arg1;
a.msgflg = args->arg2;
return (linux_msgget(td, &a));
}
case LINUX_MSGCTL: {
struct linux_msgctl_args a;
a.msqid = args->arg1;
a.cmd = args->arg2;
a.buf = args->ptr;
return (linux_msgctl(td, &a));
}
case LINUX_SHMAT: {
struct linux_shmat_args a;
a.shmid = args->arg1;
a.shmaddr = args->ptr;
a.shmflg = args->arg2;
a.raddr = (l_ulong *)args->arg3;
return (linux_shmat(td, &a));
}
case LINUX_SHMDT: {
struct linux_shmdt_args a;
a.shmaddr = args->ptr;
return (linux_shmdt(td, &a));
}
case LINUX_SHMGET: {
struct linux_shmget_args a;
a.key = args->arg1;
a.size = args->arg2;
a.shmflg = args->arg3;
return (linux_shmget(td, &a));
}
case LINUX_SHMCTL: {
struct linux_shmctl_args a;
a.shmid = args->arg1;
a.cmd = args->arg2;
a.buf = args->ptr;
return (linux_shmctl(td, &a));
}
default:
break;
}
return (EINVAL);
}
int
linux_old_select(struct thread *td, struct linux_old_select_args *args)
{
struct l_old_select_argv linux_args;
struct linux_select_args newsel;
int error;
#ifdef DEBUG
if (ldebug(old_select))
printf(ARGS(old_select, "%p"), args->ptr);
#endif
error = copyin(args->ptr, &linux_args, sizeof(linux_args));
if (error)
return (error);
newsel.nfds = linux_args.nfds;
newsel.readfds = linux_args.readfds;
newsel.writefds = linux_args.writefds;
newsel.exceptfds = linux_args.exceptfds;
newsel.timeout = linux_args.timeout;
return (linux_select(td, &newsel));
}
int
linux_set_cloned_tls(struct thread *td, void *desc)
{
struct segment_descriptor sd;
struct l_user_desc info;
int idx, error;
int a[2];
error = copyin(desc, &info, sizeof(struct l_user_desc));
if (error) {
printf(LMSG("copyin failed!"));
} else {
idx = info.entry_number;
/*
* looks like we're getting the idx we returned
* in the set_thread_area() syscall
*/
if (idx != 6 && idx != 3) {
printf(LMSG("resetting idx!"));
idx = 3;
}
/* this doesnt happen in practice */
if (idx == 6) {
/* we might copy out the entry_number as 3 */
info.entry_number = 3;
error = copyout(&info, desc, sizeof(struct l_user_desc));
if (error)
printf(LMSG("copyout failed!"));
}
a[0] = LINUX_LDT_entry_a(&info);
a[1] = LINUX_LDT_entry_b(&info);
memcpy(&sd, &a, sizeof(a));
#ifdef DEBUG
if (ldebug(clone))
printf("Segment created in clone with "
"CLONE_SETTLS: lobase: %x, hibase: %x, "
"lolimit: %x, hilimit: %x, type: %i, "
"dpl: %i, p: %i, xx: %i, def32: %i, "
"gran: %i\n", sd.sd_lobase, sd.sd_hibase,
sd.sd_lolimit, sd.sd_hilimit, sd.sd_type,
sd.sd_dpl, sd.sd_p, sd.sd_xx,
sd.sd_def32, sd.sd_gran);
#endif
/* set %gs */
td->td_pcb->pcb_gsd = sd;
td->td_pcb->pcb_gs = GSEL(GUGS_SEL, SEL_UPL);
}
return (error);
}
int
linux_set_upcall_kse(struct thread *td, register_t stack)
{
td->td_frame->tf_esp = stack;
return (0);
}
#define STACK_SIZE (2 * 1024 * 1024)
#define GUARD_SIZE (4 * PAGE_SIZE)
int
linux_mmap2(struct thread *td, struct linux_mmap2_args *args)
{
#ifdef DEBUG
if (ldebug(mmap2))
printf(ARGS(mmap2, "%p, %d, %d, 0x%08x, %d, %d"),
(void *)args->addr, args->len, args->prot,
args->flags, args->fd, args->pgoff);
#endif
return (linux_mmap_common(td, args->addr, args->len, args->prot,
args->flags, args->fd, (uint64_t)(uint32_t)args->pgoff *
PAGE_SIZE));
}
int
linux_mmap(struct thread *td, struct linux_mmap_args *args)
{
int error;
struct l_mmap_argv linux_args;
error = copyin(args->ptr, &linux_args, sizeof(linux_args));
if (error)
return (error);
#ifdef DEBUG
if (ldebug(mmap))
printf(ARGS(mmap, "%p, %d, %d, 0x%08x, %d, %d"),
(void *)linux_args.addr, linux_args.len, linux_args.prot,
linux_args.flags, linux_args.fd, linux_args.pgoff);
#endif
return (linux_mmap_common(td, linux_args.addr, linux_args.len,
linux_args.prot, linux_args.flags, linux_args.fd,
(uint32_t)linux_args.pgoff));
}
static int
linux_mmap_common(struct thread *td, l_uintptr_t addr, l_size_t len, l_int prot,
l_int flags, l_int fd, l_loff_t pos)
{
struct proc *p = td->td_proc;
struct mmap_args /* {
caddr_t addr;
size_t len;
int prot;
int flags;
int fd;
long pad;
off_t pos;
} */ bsd_args;
int error;
struct file *fp;
error = 0;
bsd_args.flags = 0;
fp = NULL;
/*
* Linux mmap(2):
* You must specify exactly one of MAP_SHARED and MAP_PRIVATE
*/
if (!((flags & LINUX_MAP_SHARED) ^ (flags & LINUX_MAP_PRIVATE)))
return (EINVAL);
if (flags & LINUX_MAP_SHARED)
bsd_args.flags |= MAP_SHARED;
if (flags & LINUX_MAP_PRIVATE)
bsd_args.flags |= MAP_PRIVATE;
if (flags & LINUX_MAP_FIXED)
bsd_args.flags |= MAP_FIXED;
if (flags & LINUX_MAP_ANON) {
/* Enforce pos to be on page boundary, then ignore. */
if ((pos & PAGE_MASK) != 0)
return (EINVAL);
pos = 0;
bsd_args.flags |= MAP_ANON;
} else
bsd_args.flags |= MAP_NOSYNC;
if (flags & LINUX_MAP_GROWSDOWN)
bsd_args.flags |= MAP_STACK;
/*
* PROT_READ, PROT_WRITE, or PROT_EXEC implies PROT_READ and PROT_EXEC
* on Linux/i386. We do this to ensure maximum compatibility.
* Linux/ia64 does the same in i386 emulation mode.
*/
bsd_args.prot = prot;
if (bsd_args.prot & (PROT_READ | PROT_WRITE | PROT_EXEC))
bsd_args.prot |= PROT_READ | PROT_EXEC;
/* Linux does not check file descriptor when MAP_ANONYMOUS is set. */
bsd_args.fd = (bsd_args.flags & MAP_ANON) ? -1 : fd;
if (bsd_args.fd != -1) {
/*
* Linux follows Solaris mmap(2) description:
* The file descriptor fildes is opened with
* read permission, regardless of the
* protection options specified.
*/
if ((error = fget(td, bsd_args.fd, &fp)) != 0)
return (error);
if (fp->f_type != DTYPE_VNODE) {
fdrop(fp, td);
return (EINVAL);
}
/* Linux mmap() just fails for O_WRONLY files */
if (!(fp->f_flag & FREAD)) {
fdrop(fp, td);
return (EACCES);
}
fdrop(fp, td);
}
if (flags & LINUX_MAP_GROWSDOWN) {
/*
* The Linux MAP_GROWSDOWN option does not limit auto
* growth of the region. Linux mmap with this option
* takes as addr the inital BOS, and as len, the initial
* region size. It can then grow down from addr without
* limit. However, linux threads has an implicit internal
* limit to stack size of STACK_SIZE. Its just not
* enforced explicitly in linux. But, here we impose
* a limit of (STACK_SIZE - GUARD_SIZE) on the stack
* region, since we can do this with our mmap.
*
* Our mmap with MAP_STACK takes addr as the maximum
* downsize limit on BOS, and as len the max size of
* the region. It them maps the top SGROWSIZ bytes,
* and auto grows the region down, up to the limit
* in addr.
*
* If we don't use the MAP_STACK option, the effect
* of this code is to allocate a stack region of a
* fixed size of (STACK_SIZE - GUARD_SIZE).
*/
if ((caddr_t)PTRIN(addr) + len > p->p_vmspace->vm_maxsaddr) {
/*
* Some linux apps will attempt to mmap
* thread stacks near the top of their
* address space. If their TOS is greater
* than vm_maxsaddr, vm_map_growstack()
* will confuse the thread stack with the
* process stack and deliver a SEGV if they
* attempt to grow the thread stack past their
* current stacksize rlimit. To avoid this,
* adjust vm_maxsaddr upwards to reflect
* the current stacksize rlimit rather
* than the maximum possible stacksize.
* It would be better to adjust the
* mmap'ed region, but some apps do not check
* mmap's return value.
*/
PROC_LOCK(p);
p->p_vmspace->vm_maxsaddr = (char *)USRSTACK -
lim_cur(p, RLIMIT_STACK);
PROC_UNLOCK(p);
}
/*
* This gives us our maximum stack size and a new BOS.
* If we're using VM_STACK, then mmap will just map
* the top SGROWSIZ bytes, and let the stack grow down
* to the limit at BOS. If we're not using VM_STACK
* we map the full stack, since we don't have a way
* to autogrow it.
*/
if (len > STACK_SIZE - GUARD_SIZE) {
bsd_args.addr = (caddr_t)PTRIN(addr);
bsd_args.len = len;
} else {
bsd_args.addr = (caddr_t)PTRIN(addr) -
(STACK_SIZE - GUARD_SIZE - len);
bsd_args.len = STACK_SIZE - GUARD_SIZE;
}
} else {
bsd_args.addr = (caddr_t)PTRIN(addr);
bsd_args.len = len;
}
bsd_args.pos = pos;
#ifdef DEBUG
if (ldebug(mmap))
printf("-> %s(%p, %d, %d, 0x%08x, %d, 0x%x)\n",
__func__,
(void *)bsd_args.addr, bsd_args.len, bsd_args.prot,
bsd_args.flags, bsd_args.fd, (int)bsd_args.pos);
#endif
error = mmap(td, &bsd_args);
#ifdef DEBUG
if (ldebug(mmap))
printf("-> %s() return: 0x%x (0x%08x)\n",
__func__, error, (u_int)td->td_retval[0]);
#endif
return (error);
}
int
linux_mprotect(struct thread *td, struct linux_mprotect_args *uap)
{
struct mprotect_args bsd_args;
bsd_args.addr = uap->addr;
bsd_args.len = uap->len;
bsd_args.prot = uap->prot;
if (bsd_args.prot & (PROT_READ | PROT_WRITE | PROT_EXEC))
bsd_args.prot |= PROT_READ | PROT_EXEC;
return (mprotect(td, &bsd_args));
}
int
linux_pipe(struct thread *td, struct linux_pipe_args *args)
{
int error;
int fildes[2];
#ifdef DEBUG
if (ldebug(pipe))
printf(ARGS(pipe, "*"));
#endif
error = kern_pipe(td, fildes);
if (error)
return (error);
/* XXX: Close descriptors on error. */
return (copyout(fildes, args->pipefds, sizeof fildes));
}
int
linux_ioperm(struct thread *td, struct linux_ioperm_args *args)
{
int error;
struct i386_ioperm_args iia;
iia.start = args->start;
iia.length = args->length;
iia.enable = args->enable;
error = i386_set_ioperm(td, &iia);
return (error);
}
int
linux_iopl(struct thread *td, struct linux_iopl_args *args)
{
int error;
if (args->level < 0 || args->level > 3)
return (EINVAL);
if ((error = priv_check(td, PRIV_IO)) != 0)
return (error);
if ((error = securelevel_gt(td->td_ucred, 0)) != 0)
return (error);
td->td_frame->tf_eflags = (td->td_frame->tf_eflags & ~PSL_IOPL) |
(args->level * (PSL_IOPL / 3));
return (0);
}
int
linux_modify_ldt(struct thread *td, struct linux_modify_ldt_args *uap)
{
int error;
struct i386_ldt_args ldt;
struct l_descriptor ld;
union descriptor desc;
int size, written;
switch (uap->func) {
case 0x00: /* read_ldt */
ldt.start = 0;
ldt.descs = uap->ptr;
ldt.num = uap->bytecount / sizeof(union descriptor);
error = i386_get_ldt(td, &ldt);
td->td_retval[0] *= sizeof(union descriptor);
break;
case 0x02: /* read_default_ldt = 0 */
size = 5*sizeof(struct l_desc_struct);
if (size > uap->bytecount)
size = uap->bytecount;
for (written = error = 0; written < size && error == 0; written++)
error = subyte((char *)uap->ptr + written, 0);
td->td_retval[0] = written;
break;
case 0x01: /* write_ldt */
case 0x11: /* write_ldt */
if (uap->bytecount != sizeof(ld))
return (EINVAL);
error = copyin(uap->ptr, &ld, sizeof(ld));
if (error)
return (error);
ldt.start = ld.entry_number;
ldt.descs = &desc;
ldt.num = 1;
desc.sd.sd_lolimit = (ld.limit & 0x0000ffff);
desc.sd.sd_hilimit = (ld.limit & 0x000f0000) >> 16;
desc.sd.sd_lobase = (ld.base_addr & 0x00ffffff);
desc.sd.sd_hibase = (ld.base_addr & 0xff000000) >> 24;
desc.sd.sd_type = SDT_MEMRO | ((ld.read_exec_only ^ 1) << 1) |
(ld.contents << 2);
desc.sd.sd_dpl = 3;
desc.sd.sd_p = (ld.seg_not_present ^ 1);
desc.sd.sd_xx = 0;
desc.sd.sd_def32 = ld.seg_32bit;
desc.sd.sd_gran = ld.limit_in_pages;
error = i386_set_ldt(td, &ldt, &desc);
break;
default:
error = ENOSYS;
break;
}
if (error == EOPNOTSUPP) {
printf("linux: modify_ldt needs kernel option USER_LDT\n");
error = ENOSYS;
}
return (error);
}
int
linux_sigaction(struct thread *td, struct linux_sigaction_args *args)
{
l_osigaction_t osa;
l_sigaction_t act, oact;
int error;
#ifdef DEBUG
if (ldebug(sigaction))
printf(ARGS(sigaction, "%d, %p, %p"),
args->sig, (void *)args->nsa, (void *)args->osa);
#endif
if (args->nsa != NULL) {
error = copyin(args->nsa, &osa, sizeof(l_osigaction_t));
if (error)
return (error);
act.lsa_handler = osa.lsa_handler;
act.lsa_flags = osa.lsa_flags;
act.lsa_restorer = osa.lsa_restorer;
LINUX_SIGEMPTYSET(act.lsa_mask);
act.lsa_mask.__bits[0] = osa.lsa_mask;
}
error = linux_do_sigaction(td, args->sig, args->nsa ? &act : NULL,
args->osa ? &oact : NULL);
if (args->osa != NULL && !error) {
osa.lsa_handler = oact.lsa_handler;
osa.lsa_flags = oact.lsa_flags;
osa.lsa_restorer = oact.lsa_restorer;
osa.lsa_mask = oact.lsa_mask.__bits[0];
error = copyout(&osa, args->osa, sizeof(l_osigaction_t));
}
return (error);
}
/*
* Linux has two extra args, restart and oldmask. We dont use these,
* but it seems that "restart" is actually a context pointer that
* enables the signal to happen with a different register set.
*/
int
linux_sigsuspend(struct thread *td, struct linux_sigsuspend_args *args)
{
sigset_t sigmask;
l_sigset_t mask;
#ifdef DEBUG
if (ldebug(sigsuspend))
printf(ARGS(sigsuspend, "%08lx"), (unsigned long)args->mask);
#endif
LINUX_SIGEMPTYSET(mask);
mask.__bits[0] = args->mask;
linux_to_bsd_sigset(&mask, &sigmask);
return (kern_sigsuspend(td, sigmask));
}
int
linux_rt_sigsuspend(struct thread *td, struct linux_rt_sigsuspend_args *uap)
{
l_sigset_t lmask;
sigset_t sigmask;
int error;
#ifdef DEBUG
if (ldebug(rt_sigsuspend))
printf(ARGS(rt_sigsuspend, "%p, %d"),
(void *)uap->newset, uap->sigsetsize);
#endif
if (uap->sigsetsize != sizeof(l_sigset_t))
return (EINVAL);
error = copyin(uap->newset, &lmask, sizeof(l_sigset_t));
if (error)
return (error);
linux_to_bsd_sigset(&lmask, &sigmask);
return (kern_sigsuspend(td, sigmask));
}
int
linux_pause(struct thread *td, struct linux_pause_args *args)
{
struct proc *p = td->td_proc;
sigset_t sigmask;
#ifdef DEBUG
if (ldebug(pause))
printf(ARGS(pause, ""));
#endif
PROC_LOCK(p);
sigmask = td->td_sigmask;
PROC_UNLOCK(p);
return (kern_sigsuspend(td, sigmask));
}
int
linux_sigaltstack(struct thread *td, struct linux_sigaltstack_args *uap)
{
stack_t ss, oss;
l_stack_t lss;
int error;
#ifdef DEBUG
if (ldebug(sigaltstack))
printf(ARGS(sigaltstack, "%p, %p"), uap->uss, uap->uoss);
#endif
if (uap->uss != NULL) {
error = copyin(uap->uss, &lss, sizeof(l_stack_t));
if (error)
return (error);
ss.ss_sp = lss.ss_sp;
ss.ss_size = lss.ss_size;
ss.ss_flags = linux_to_bsd_sigaltstack(lss.ss_flags);
}
error = kern_sigaltstack(td, (uap->uss != NULL) ? &ss : NULL,
(uap->uoss != NULL) ? &oss : NULL);
if (!error && uap->uoss != NULL) {
lss.ss_sp = oss.ss_sp;
lss.ss_size = oss.ss_size;
lss.ss_flags = bsd_to_linux_sigaltstack(oss.ss_flags);
error = copyout(&lss, uap->uoss, sizeof(l_stack_t));
}
return (error);
}
int
linux_ftruncate64(struct thread *td, struct linux_ftruncate64_args *args)
{
struct ftruncate_args sa;
#ifdef DEBUG
if (ldebug(ftruncate64))
printf(ARGS(ftruncate64, "%u, %jd"), args->fd,
(intmax_t)args->length);
#endif
sa.fd = args->fd;
sa.length = args->length;
return ftruncate(td, &sa);
}
int
linux_set_thread_area(struct thread *td, struct linux_set_thread_area_args *args)
{
struct l_user_desc info;
int error;
int idx;
int a[2];
struct segment_descriptor sd;
error = copyin(args->desc, &info, sizeof(struct l_user_desc));
if (error)
return (error);
#ifdef DEBUG
if (ldebug(set_thread_area))
printf(ARGS(set_thread_area, "%i, %x, %x, %i, %i, %i, %i, %i, %i\n"),
info.entry_number,
info.base_addr,
info.limit,
info.seg_32bit,
info.contents,
info.read_exec_only,
info.limit_in_pages,
info.seg_not_present,
info.useable);
#endif
idx = info.entry_number;
/*
* Semantics of linux version: every thread in the system has array of
* 3 tls descriptors. 1st is GLIBC TLS, 2nd is WINE, 3rd unknown. This
* syscall loads one of the selected tls decriptors with a value and
* also loads GDT descriptors 6, 7 and 8 with the content of the
* per-thread descriptors.
*
* Semantics of fbsd version: I think we can ignore that linux has 3
* per-thread descriptors and use just the 1st one. The tls_array[]
* is used only in set/get-thread_area() syscalls and for loading the
* GDT descriptors. In fbsd we use just one GDT descriptor for TLS so
* we will load just one.
*
* XXX: this doesn't work when a user space process tries to use more
* than 1 TLS segment. Comment in the linux sources says wine might do
* this.
*/
/*
* we support just GLIBC TLS now
* we should let 3 proceed as well because we use this segment so
* if code does two subsequent calls it should succeed
*/
if (idx != 6 && idx != -1 && idx != 3)
return (EINVAL);
/*
* we have to copy out the GDT entry we use
* FreeBSD uses GDT entry #3 for storing %gs so load that
*
* XXX: what if a user space program doesn't check this value and tries
* to use 6, 7 or 8?
*/
idx = info.entry_number = 3;
error = copyout(&info, args->desc, sizeof(struct l_user_desc));
if (error)
return (error);
if (LINUX_LDT_empty(&info)) {
a[0] = 0;
a[1] = 0;
} else {
a[0] = LINUX_LDT_entry_a(&info);
a[1] = LINUX_LDT_entry_b(&info);
}
memcpy(&sd, &a, sizeof(a));
#ifdef DEBUG
if (ldebug(set_thread_area))
printf("Segment created in set_thread_area: lobase: %x, hibase: %x, lolimit: %x, hilimit: %x, type: %i, dpl: %i, p: %i, xx: %i, def32: %i, gran: %i\n", sd.sd_lobase,
sd.sd_hibase,
sd.sd_lolimit,
sd.sd_hilimit,
sd.sd_type,
sd.sd_dpl,
sd.sd_p,
sd.sd_xx,
sd.sd_def32,
sd.sd_gran);
#endif
/* this is taken from i386 version of cpu_set_user_tls() */
critical_enter();
/* set %gs */
td->td_pcb->pcb_gsd = sd;
PCPU_GET(fsgs_gdt)[1] = sd;
load_gs(GSEL(GUGS_SEL, SEL_UPL));
critical_exit();
return (0);
}
int
linux_get_thread_area(struct thread *td, struct linux_get_thread_area_args *args)
{
struct l_user_desc info;
int error;
int idx;
struct l_desc_struct desc;
struct segment_descriptor sd;
#ifdef DEBUG
if (ldebug(get_thread_area))
printf(ARGS(get_thread_area, "%p"), args->desc);
#endif
error = copyin(args->desc, &info, sizeof(struct l_user_desc));
if (error)
return (error);
idx = info.entry_number;
/* XXX: I am not sure if we want 3 to be allowed too. */
if (idx != 6 && idx != 3)
return (EINVAL);
idx = 3;
memset(&info, 0, sizeof(info));
sd = PCPU_GET(fsgs_gdt)[1];
memcpy(&desc, &sd, sizeof(desc));
info.entry_number = idx;
info.base_addr = LINUX_GET_BASE(&desc);
info.limit = LINUX_GET_LIMIT(&desc);
info.seg_32bit = LINUX_GET_32BIT(&desc);
info.contents = LINUX_GET_CONTENTS(&desc);
info.read_exec_only = !LINUX_GET_WRITABLE(&desc);
info.limit_in_pages = LINUX_GET_LIMIT_PAGES(&desc);
info.seg_not_present = !LINUX_GET_PRESENT(&desc);
info.useable = LINUX_GET_USEABLE(&desc);
error = copyout(&info, args->desc, sizeof(struct l_user_desc));
if (error)
return (EFAULT);
return (0);
}
/* copied from kern/kern_time.c */
int
linux_timer_create(struct thread *td, struct linux_timer_create_args *args)
{
return ktimer_create(td, (struct ktimer_create_args *) args);
}
int
linux_timer_settime(struct thread *td, struct linux_timer_settime_args *args)
{
return ktimer_settime(td, (struct ktimer_settime_args *) args);
}
int
linux_timer_gettime(struct thread *td, struct linux_timer_gettime_args *args)
{
return ktimer_gettime(td, (struct ktimer_gettime_args *) args);
}
int
linux_timer_getoverrun(struct thread *td, struct linux_timer_getoverrun_args *args)
{
return ktimer_getoverrun(td, (struct ktimer_getoverrun_args *) args);
}
int
linux_timer_delete(struct thread *td, struct linux_timer_delete_args *args)
{
return ktimer_delete(td, (struct ktimer_delete_args *) args);
}
/* XXX: this wont work with module - convert it */
int
linux_mq_open(struct thread *td, struct linux_mq_open_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_open(td, (struct kmq_open_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_mq_unlink(struct thread *td, struct linux_mq_unlink_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_unlink(td, (struct kmq_unlink_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_mq_timedsend(struct thread *td, struct linux_mq_timedsend_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_timedsend(td, (struct kmq_timedsend_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_mq_timedreceive(struct thread *td, struct linux_mq_timedreceive_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_timedreceive(td, (struct kmq_timedreceive_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_mq_notify(struct thread *td, struct linux_mq_notify_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_notify(td, (struct kmq_notify_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_mq_getsetattr(struct thread *td, struct linux_mq_getsetattr_args *args)
{
#ifdef P1003_1B_MQUEUE
return kmq_setattr(td, (struct kmq_setattr_args *) args);
#else
return (ENOSYS);
#endif
}
int
linux_wait4(struct thread *td, struct linux_wait4_args *args)
{
int error, options;
struct rusage ru, *rup;
#ifdef DEBUG
if (ldebug(wait4))
printf(ARGS(wait4, "%d, %p, %d, %p"),
args->pid, (void *)args->status, args->options,
(void *)args->rusage);
#endif
options = (args->options & (WNOHANG | WUNTRACED));
/* WLINUXCLONE should be equal to __WCLONE, but we make sure */
if (args->options & __WCLONE)
options |= WLINUXCLONE;
if (args->rusage != NULL)
rup = &ru;
else
rup = NULL;
error = linux_common_wait(td, args->pid, args->status, options, rup);
if (error)
return (error);
if (args->rusage != NULL)
error = copyout(&ru, args->rusage, sizeof(ru));
return (error);
}
|