This repository was archived by the owner on May 22, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Expand file tree
/
Copy pathkern_mman.c
More file actions
1277 lines (1130 loc) · 33.3 KB
/
kern_mman.c
File metadata and controls
1277 lines (1130 loc) · 33.3 KB
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
/*
* Copyright (c) 2007 Apple Inc. All Rights Reserved.
*
* @APPLE_OSREFERENCE_LICENSE_HEADER_START@
*
* This file contains Original Code and/or Modifications of Original Code
* as defined in and that are subject to the Apple Public Source License
* Version 2.0 (the 'License'). You may not use this file except in
* compliance with the License. The rights granted to you under the License
* may not be used to create, or enable the creation or redistribution of,
* unlawful or unlicensed copies of an Apple operating system, or to
* circumvent, violate, or enable the circumvention or violation of, any
* terms of an Apple operating system software license agreement.
*
* Please obtain a copy of the License at
* http://www.opensource.apple.com/apsl/ and read it before using this file.
*
* The Original Code and all software distributed under the License are
* distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
* EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
* INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
* Please see the License for the specific language governing rights and
* limitations under the License.
*
* @APPLE_OSREFERENCE_LICENSE_HEADER_END@
*/
/*
* Copyright (c) 1988 University of Utah.
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* the Systems Programming Group of the University of Utah Computer
* Science Department.
*
* 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.
* 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. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``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 REGENTS OR CONTRIBUTORS 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.
*
* from: Utah $Hdr: vm_mmap.c 1.6 91/10/21$
*
* @(#)vm_mmap.c 8.10 (Berkeley) 2/19/95
*/
/*
* NOTICE: This file was modified by SPARTA, Inc. in 2005 to introduce
* support for mandatory and extensible security protections. This notice
* is included in support of clause 2.2 (b) of the Apple Public License,
* Version 2.0.
*/
/*
* Mapped file (mmap) interface to VM
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/filedesc.h>
#include <sys/proc_internal.h>
#include <sys/kauth.h>
#include <sys/resourcevar.h>
#include <sys/vnode_internal.h>
#include <sys/acct.h>
#include <sys/wait.h>
#include <sys/file_internal.h>
#include <sys/vadvise.h>
#include <sys/trace.h>
#include <sys/mman.h>
#include <sys/conf.h>
#include <sys/stat.h>
#include <sys/ubc.h>
#include <sys/ubc_internal.h>
#include <sys/sysproto.h>
#include <sys/syscall.h>
#include <sys/kdebug.h>
#include <sys/bsdtask_info.h>
#include <security/audit/audit.h>
#include <bsm/audit_kevents.h>
#include <mach/mach_types.h>
#include <mach/mach_traps.h>
#include <mach/vm_sync.h>
#include <mach/vm_behavior.h>
#include <mach/vm_inherit.h>
#include <mach/vm_statistics.h>
#include <mach/mach_vm.h>
#include <mach/vm_map.h>
#include <mach/host_priv.h>
#include <mach/sdt.h>
#include <machine/machine_routines.h>
#include <kern/cpu_number.h>
#include <kern/host.h>
#include <kern/task.h>
#include <kern/page_decrypt.h>
#include <IOKit/IOReturn.h>
#include <vm/vm_map.h>
#include <vm/vm_kern.h>
#include <vm/vm_pager.h>
#include <vm/vm_protos.h>
/*
* XXX Internally, we use VM_PROT_* somewhat interchangeably, but the correct
* XXX usage is PROT_* from an interface perspective. Thus the values of
* XXX VM_PROT_* and PROT_* need to correspond.
*/
int
mmap(proc_t p, struct mmap_args *uap, user_addr_t *retval)
{
/*
* Map in special device (must be SHARED) or file
*/
struct fileproc *fp;
struct vnode *vp;
int flags;
int prot;
int err=0;
vm_map_t user_map;
kern_return_t result;
vm_map_offset_t user_addr;
vm_map_size_t user_size;
vm_object_offset_t pageoff;
vm_object_offset_t file_pos;
int alloc_flags=0;
boolean_t docow;
vm_prot_t maxprot;
void *handle;
memory_object_t pager = MEMORY_OBJECT_NULL;
memory_object_control_t control;
int mapanon=0;
int fpref=0;
int error =0;
int fd = uap->fd;
int num_retries = 0;
/*
* Note that for UNIX03 conformance, there is additional parameter checking for
* mmap() system call in libsyscall prior to entering the kernel. The sanity
* checks and argument validation done in this function are not the only places
* one can get returned errnos.
*/
user_map = current_map();
user_addr = (vm_map_offset_t)uap->addr;
user_size = (vm_map_size_t) uap->len;
AUDIT_ARG(addr, user_addr);
AUDIT_ARG(len, user_size);
AUDIT_ARG(fd, uap->fd);
prot = (uap->prot & VM_PROT_ALL);
#if 3777787
/*
* Since the hardware currently does not support writing without
* read-before-write, or execution-without-read, if the request is
* for write or execute access, we must imply read access as well;
* otherwise programs expecting this to work will fail to operate.
*/
if (prot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
prot |= VM_PROT_READ;
#endif /* radar 3777787 */
flags = uap->flags;
vp = NULLVP;
/*
* The vm code does not have prototypes & compiler doesn't do the'
* the right thing when you cast 64bit value and pass it in function
* call. So here it is.
*/
file_pos = (vm_object_offset_t)uap->pos;
/* make sure mapping fits into numeric range etc */
if (file_pos + user_size > (vm_object_offset_t)-PAGE_SIZE_64)
return (EINVAL);
/*
* Align the file position to a page boundary,
* and save its page offset component.
*/
pageoff = (file_pos & vm_map_page_mask(user_map));
file_pos -= (vm_object_offset_t)pageoff;
/* Adjust size for rounding (on both ends). */
user_size += pageoff; /* low end... */
user_size = vm_map_round_page(user_size,
vm_map_page_mask(user_map)); /* hi end */
if (flags & MAP_JIT) {
if ((flags & MAP_FIXED) ||
(flags & MAP_SHARED) ||
!(flags & MAP_ANON) ||
(flags & MAP_RESILIENT_CODESIGN) ||
(flags & MAP_RESILIENT_MEDIA)) {
return EINVAL;
}
}
if ((flags & MAP_RESILIENT_CODESIGN) ||
(flags & MAP_RESILIENT_MEDIA)) {
if ((flags & MAP_ANON) ||
(flags & MAP_JIT)) {
return EINVAL;
}
if (prot & (VM_PROT_WRITE | VM_PROT_EXECUTE)) {
return EPERM;
}
}
/*
* Check for illegal addresses. Watch out for address wrap... Note
* that VM_*_ADDRESS are not constants due to casts (argh).
*/
if (flags & MAP_FIXED) {
/*
* The specified address must have the same remainder
* as the file offset taken modulo PAGE_SIZE, so it
* should be aligned after adjustment by pageoff.
*/
user_addr -= pageoff;
if (user_addr & vm_map_page_mask(user_map))
return (EINVAL);
}
#ifdef notyet
/* DO not have apis to get this info, need to wait till then*/
/*
* XXX for non-fixed mappings where no hint is provided or
* the hint would fall in the potential heap space,
* place it after the end of the largest possible heap.
*
* There should really be a pmap call to determine a reasonable
* location.
*/
else if (addr < vm_map_round_page(p->p_vmspace->vm_daddr + MAXDSIZ,
vm_map_page_mask(user_map)))
addr = vm_map_round_page(p->p_vmspace->vm_daddr + MAXDSIZ,
vm_map_page_mask(user_map));
#endif
alloc_flags = 0;
if (flags & MAP_ANON) {
maxprot = VM_PROT_ALL;
#if CONFIG_MACF
/*
* Entitlement check.
*/
error = mac_proc_check_map_anon(p, user_addr, user_size, prot, flags, &maxprot);
if (error) {
return EINVAL;
}
#endif /* MAC */
/*
* Mapping blank space is trivial. Use positive fds as the alias
* value for memory tracking.
*/
if (fd != -1) {
/*
* Use "fd" to pass (some) Mach VM allocation flags,
* (see the VM_FLAGS_* definitions).
*/
alloc_flags = fd & (VM_FLAGS_ALIAS_MASK | VM_FLAGS_SUPERPAGE_MASK |
VM_FLAGS_PURGABLE);
if (alloc_flags != fd) {
/* reject if there are any extra flags */
return EINVAL;
}
}
handle = NULL;
file_pos = 0;
mapanon = 1;
} else {
struct vnode_attr va;
vfs_context_t ctx = vfs_context_current();
if (flags & MAP_JIT)
return EINVAL;
/*
* Mapping file, get fp for validation. Obtain vnode and make
* sure it is of appropriate type.
*/
err = fp_lookup(p, fd, &fp, 0);
if (err)
return(err);
fpref = 1;
switch (FILEGLOB_DTYPE(fp->f_fglob)) {
case DTYPE_PSXSHM:
uap->addr = (user_addr_t)user_addr;
uap->len = (user_size_t)user_size;
uap->prot = prot;
uap->flags = flags;
uap->pos = file_pos;
error = pshm_mmap(p, uap, retval, fp, (off_t)pageoff);
goto bad;
case DTYPE_VNODE:
break;
default:
error = EINVAL;
goto bad;
}
vp = (struct vnode *)fp->f_fglob->fg_data;
error = vnode_getwithref(vp);
if(error != 0)
goto bad;
if (vp->v_type != VREG && vp->v_type != VCHR) {
(void)vnode_put(vp);
error = EINVAL;
goto bad;
}
AUDIT_ARG(vnpath, vp, ARG_VNODE1);
/*
* POSIX: mmap needs to update access time for mapped files
*/
if ((vnode_vfsvisflags(vp) & MNT_NOATIME) == 0) {
VATTR_INIT(&va);
nanotime(&va.va_access_time);
VATTR_SET_ACTIVE(&va, va_access_time);
vnode_setattr(vp, &va, ctx);
}
/*
* XXX hack to handle use of /dev/zero to map anon memory (ala
* SunOS).
*/
if (vp->v_type == VCHR || vp->v_type == VSTR) {
(void)vnode_put(vp);
error = ENODEV;
goto bad;
} else {
/*
* Ensure that file and memory protections are
* compatible. Note that we only worry about
* writability if mapping is shared; in this case,
* current and max prot are dictated by the open file.
* XXX use the vnode instead? Problem is: what
* credentials do we use for determination? What if
* proc does a setuid?
*/
maxprot = VM_PROT_EXECUTE; /* ??? */
if (fp->f_fglob->fg_flag & FREAD)
maxprot |= VM_PROT_READ;
else if (prot & PROT_READ) {
(void)vnode_put(vp);
error = EACCES;
goto bad;
}
/*
* If we are sharing potential changes (either via
* MAP_SHARED or via the implicit sharing of character
* device mappings), and we are trying to get write
* permission although we opened it without asking
* for it, bail out.
*/
if ((flags & MAP_SHARED) != 0) {
if ((fp->f_fglob->fg_flag & FWRITE) != 0 &&
/*
* Do not allow writable mappings of
* swap files (see vm_swapfile_pager.c).
*/
!vnode_isswap(vp)) {
/*
* check for write access
*
* Note that we already made this check when granting FWRITE
* against the file, so it seems redundant here.
*/
error = vnode_authorize(vp, NULL, KAUTH_VNODE_CHECKIMMUTABLE, ctx);
/* if not granted for any reason, but we wanted it, bad */
if ((prot & PROT_WRITE) && (error != 0)) {
vnode_put(vp);
goto bad;
}
/* if writable, remember */
if (error == 0)
maxprot |= VM_PROT_WRITE;
} else if ((prot & PROT_WRITE) != 0) {
(void)vnode_put(vp);
error = EACCES;
goto bad;
}
} else
maxprot |= VM_PROT_WRITE;
handle = (void *)vp;
#if CONFIG_MACF
error = mac_file_check_mmap(vfs_context_ucred(ctx),
fp->f_fglob, prot, flags, file_pos, &maxprot);
if (error) {
(void)vnode_put(vp);
goto bad;
}
#endif /* MAC */
}
}
if (user_size == 0) {
if (!mapanon)
(void)vnode_put(vp);
error = 0;
goto bad;
}
/*
* We bend a little - round the start and end addresses
* to the nearest page boundary.
*/
user_size = vm_map_round_page(user_size,
vm_map_page_mask(user_map));
if (file_pos & vm_map_page_mask(user_map)) {
if (!mapanon)
(void)vnode_put(vp);
error = EINVAL;
goto bad;
}
if ((flags & MAP_FIXED) == 0) {
alloc_flags |= VM_FLAGS_ANYWHERE;
user_addr = vm_map_round_page(user_addr,
vm_map_page_mask(user_map));
} else {
if (user_addr != vm_map_trunc_page(user_addr,
vm_map_page_mask(user_map))) {
if (!mapanon)
(void)vnode_put(vp);
error = EINVAL;
goto bad;
}
/*
* mmap(MAP_FIXED) will replace any existing mappings in the
* specified range, if the new mapping is successful.
* If we just deallocate the specified address range here,
* another thread might jump in and allocate memory in that
* range before we get a chance to establish the new mapping,
* and we won't have a chance to restore the old mappings.
* So we use VM_FLAGS_OVERWRITE to let Mach VM know that it
* has to deallocate the existing mappings and establish the
* new ones atomically.
*/
alloc_flags |= VM_FLAGS_FIXED | VM_FLAGS_OVERWRITE;
}
if (flags & MAP_NOCACHE)
alloc_flags |= VM_FLAGS_NO_CACHE;
if (flags & MAP_JIT) {
alloc_flags |= VM_FLAGS_MAP_JIT;
}
if (flags & MAP_RESILIENT_CODESIGN) {
alloc_flags |= VM_FLAGS_RESILIENT_CODESIGN;
}
/*
* Lookup/allocate object.
*/
if (handle == NULL) {
control = NULL;
#ifdef notyet
/* Hmm .. */
#if defined(VM_PROT_READ_IS_EXEC)
if (prot & VM_PROT_READ)
prot |= VM_PROT_EXECUTE;
if (maxprot & VM_PROT_READ)
maxprot |= VM_PROT_EXECUTE;
#endif
#endif
#if 3777787
if (prot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
prot |= VM_PROT_READ;
if (maxprot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
maxprot |= VM_PROT_READ;
#endif /* radar 3777787 */
map_anon_retry:
result = vm_map_enter_mem_object(user_map,
&user_addr, user_size,
0, alloc_flags,
IPC_PORT_NULL, 0, FALSE,
prot, maxprot,
(flags & MAP_SHARED) ?
VM_INHERIT_SHARE :
VM_INHERIT_DEFAULT);
/* If a non-binding address was specified for this anonymous
* mapping, retry the mapping with a zero base
* in the event the mapping operation failed due to
* lack of space between the address and the map's maximum.
*/
if ((result == KERN_NO_SPACE) && ((flags & MAP_FIXED) == 0) && user_addr && (num_retries++ == 0)) {
user_addr = vm_map_page_size(user_map);
goto map_anon_retry;
}
} else {
if (vnode_isswap(vp)) {
/*
* Map swap files with a special pager
* that returns obfuscated contents.
*/
control = NULL;
pager = swapfile_pager_setup(vp);
if (pager != MEMORY_OBJECT_NULL) {
control = swapfile_pager_control(pager);
}
} else {
control = ubc_getobject(vp, UBC_FLAGS_NONE);
}
if (control == NULL) {
(void)vnode_put(vp);
error = ENOMEM;
goto bad;
}
/*
* Set credentials:
* FIXME: if we're writing the file we need a way to
* ensure that someone doesn't replace our R/W creds
* with ones that only work for read.
*/
ubc_setthreadcred(vp, p, current_thread());
docow = FALSE;
if ((flags & (MAP_ANON|MAP_SHARED)) == 0) {
docow = TRUE;
}
#ifdef notyet
/* Hmm .. */
#if defined(VM_PROT_READ_IS_EXEC)
if (prot & VM_PROT_READ)
prot |= VM_PROT_EXECUTE;
if (maxprot & VM_PROT_READ)
maxprot |= VM_PROT_EXECUTE;
#endif
#endif /* notyet */
#if 3777787
if (prot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
prot |= VM_PROT_READ;
if (maxprot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
maxprot |= VM_PROT_READ;
#endif /* radar 3777787 */
map_file_retry:
if ((flags & MAP_RESILIENT_CODESIGN) ||
(flags & MAP_RESILIENT_MEDIA)) {
if (prot & (VM_PROT_WRITE | VM_PROT_EXECUTE)) {
assert(!mapanon);
vnode_put(vp);
error = EPERM;
goto bad;
}
/* strictly limit access to "prot" */
maxprot &= prot;
}
result = vm_map_enter_mem_object_control(user_map,
&user_addr, user_size,
0, alloc_flags,
control, file_pos,
docow, prot, maxprot,
(flags & MAP_SHARED) ?
VM_INHERIT_SHARE :
VM_INHERIT_DEFAULT);
/* If a non-binding address was specified for this file backed
* mapping, retry the mapping with a zero base
* in the event the mapping operation failed due to
* lack of space between the address and the map's maximum.
*/
if ((result == KERN_NO_SPACE) && ((flags & MAP_FIXED) == 0) && user_addr && (num_retries++ == 0)) {
user_addr = vm_map_page_size(user_map);
goto map_file_retry;
}
}
if (!mapanon) {
(void)vnode_put(vp);
}
switch (result) {
case KERN_SUCCESS:
*retval = user_addr + pageoff;
error = 0;
break;
case KERN_INVALID_ADDRESS:
case KERN_NO_SPACE:
error = ENOMEM;
break;
case KERN_PROTECTION_FAILURE:
error = EACCES;
break;
default:
error = EINVAL;
break;
}
bad:
if (pager != MEMORY_OBJECT_NULL) {
/*
* Release the reference on the pager.
* If the mapping was successful, it now holds
* an extra reference.
*/
memory_object_deallocate(pager);
}
if (fpref)
fp_drop(p, fd, fp, 0);
KERNEL_DEBUG_CONSTANT((BSDDBG_CODE(DBG_BSD_SC_EXTENDED_INFO, SYS_mmap) | DBG_FUNC_NONE), fd, (uint32_t)(*retval), (uint32_t)user_size, error, 0);
KERNEL_DEBUG_CONSTANT((BSDDBG_CODE(DBG_BSD_SC_EXTENDED_INFO2, SYS_mmap) | DBG_FUNC_NONE), (uint32_t)(*retval >> 32), (uint32_t)(user_size >> 32),
(uint32_t)(file_pos >> 32), (uint32_t)file_pos, 0);
return(error);
}
int
msync(__unused proc_t p, struct msync_args *uap, int32_t *retval)
{
__pthread_testcancel(1);
return(msync_nocancel(p, (struct msync_nocancel_args *)uap, retval));
}
int
msync_nocancel(__unused proc_t p, struct msync_nocancel_args *uap, __unused int32_t *retval)
{
mach_vm_offset_t addr;
mach_vm_size_t size;
int flags;
vm_map_t user_map;
int rv;
vm_sync_t sync_flags=0;
user_map = current_map();
addr = (mach_vm_offset_t) uap->addr;
size = (mach_vm_size_t)uap->len;
KERNEL_DEBUG_CONSTANT((BSDDBG_CODE(DBG_BSD_SC_EXTENDED_INFO, SYS_msync) | DBG_FUNC_NONE), (uint32_t)(addr >> 32), (uint32_t)(size >> 32), 0, 0, 0);
if (addr & vm_map_page_mask(user_map)) {
/* UNIX SPEC: user address is not page-aligned, return EINVAL */
return EINVAL;
}
if (size == 0) {
/*
* We cannot support this properly without maintaining
* list all mmaps done. Cannot use vm_map_entry as they could be
* split or coalesced by indepenedant actions. So instead of
* inaccurate results, lets just return error as invalid size
* specified
*/
return (EINVAL); /* XXX breaks posix apps */
}
flags = uap->flags;
/* disallow contradictory flags */
if ((flags & (MS_SYNC|MS_ASYNC)) == (MS_SYNC|MS_ASYNC))
return (EINVAL);
if (flags & MS_KILLPAGES)
sync_flags |= VM_SYNC_KILLPAGES;
if (flags & MS_DEACTIVATE)
sync_flags |= VM_SYNC_DEACTIVATE;
if (flags & MS_INVALIDATE)
sync_flags |= VM_SYNC_INVALIDATE;
if ( !(flags & (MS_KILLPAGES | MS_DEACTIVATE))) {
if (flags & MS_ASYNC)
sync_flags |= VM_SYNC_ASYNCHRONOUS;
else
sync_flags |= VM_SYNC_SYNCHRONOUS;
}
sync_flags |= VM_SYNC_CONTIGUOUS; /* complain if holes */
rv = mach_vm_msync(user_map, addr, size, sync_flags);
switch (rv) {
case KERN_SUCCESS:
break;
case KERN_INVALID_ADDRESS: /* hole in region being sync'ed */
return (ENOMEM);
case KERN_FAILURE:
return (EIO);
default:
return (EINVAL);
}
return (0);
}
int
munmap(__unused proc_t p, struct munmap_args *uap, __unused int32_t *retval)
{
mach_vm_offset_t user_addr;
mach_vm_size_t user_size;
kern_return_t result;
vm_map_t user_map;
user_map = current_map();
user_addr = (mach_vm_offset_t) uap->addr;
user_size = (mach_vm_size_t) uap->len;
AUDIT_ARG(addr, user_addr);
AUDIT_ARG(len, user_size);
if (user_addr & vm_map_page_mask(user_map)) {
/* UNIX SPEC: user address is not page-aligned, return EINVAL */
return EINVAL;
}
if (user_addr + user_size < user_addr)
return(EINVAL);
if (user_size == 0) {
/* UNIX SPEC: size is 0, return EINVAL */
return EINVAL;
}
result = mach_vm_deallocate(user_map, user_addr, user_size);
if (result != KERN_SUCCESS) {
return(EINVAL);
}
return(0);
}
int
mprotect(__unused proc_t p, struct mprotect_args *uap, __unused int32_t *retval)
{
vm_prot_t prot;
mach_vm_offset_t user_addr;
mach_vm_size_t user_size;
kern_return_t result;
vm_map_t user_map;
#if CONFIG_MACF
int error;
#endif
AUDIT_ARG(addr, uap->addr);
AUDIT_ARG(len, uap->len);
AUDIT_ARG(value32, uap->prot);
user_map = current_map();
user_addr = (mach_vm_offset_t) uap->addr;
user_size = (mach_vm_size_t) uap->len;
prot = (vm_prot_t)(uap->prot & (VM_PROT_ALL | VM_PROT_TRUSTED | VM_PROT_STRIP_READ));
if (user_addr & vm_map_page_mask(user_map)) {
/* UNIX SPEC: user address is not page-aligned, return EINVAL */
return EINVAL;
}
#ifdef notyet
/* Hmm .. */
#if defined(VM_PROT_READ_IS_EXEC)
if (prot & VM_PROT_READ)
prot |= VM_PROT_EXECUTE;
#endif
#endif /* notyet */
#if 3936456
if (prot & (VM_PROT_EXECUTE | VM_PROT_WRITE))
prot |= VM_PROT_READ;
#endif /* 3936456 */
#if CONFIG_MACF
/*
* The MAC check for mprotect is of limited use for 2 reasons:
* Without mmap revocation, the caller could have asked for the max
* protections initially instead of a reduced set, so a mprotect
* check would offer no new security.
* It is not possible to extract the vnode from the pager object(s)
* of the target memory range.
* However, the MAC check may be used to prevent a process from,
* e.g., making the stack executable.
*/
error = mac_proc_check_mprotect(p, user_addr,
user_size, prot);
if (error)
return (error);
#endif
if(prot & VM_PROT_TRUSTED) {
#if CONFIG_DYNAMIC_CODE_SIGNING
/* CODE SIGNING ENFORCEMENT - JIT support */
/* The special protection value VM_PROT_TRUSTED requests that we treat
* this page as if it had a valid code signature.
* If this is enabled, there MUST be a MAC policy implementing the
* mac_proc_check_mprotect() hook above. Otherwise, Codesigning will be
* compromised because the check would always succeed and thusly any
* process could sign dynamically. */
result = vm_map_sign(
user_map,
vm_map_trunc_page(user_addr,
vm_map_page_mask(user_map)),
vm_map_round_page(user_addr+user_size,
vm_map_page_mask(user_map)));
switch (result) {
case KERN_SUCCESS:
break;
case KERN_INVALID_ADDRESS:
/* UNIX SPEC: for an invalid address range, return ENOMEM */
return ENOMEM;
default:
return EINVAL;
}
#else
return ENOTSUP;
#endif
}
prot &= ~VM_PROT_TRUSTED;
result = mach_vm_protect(user_map, user_addr, user_size,
FALSE, prot);
switch (result) {
case KERN_SUCCESS:
return (0);
case KERN_PROTECTION_FAILURE:
return (EACCES);
case KERN_INVALID_ADDRESS:
/* UNIX SPEC: for an invalid address range, return ENOMEM */
return ENOMEM;
}
return (EINVAL);
}
int
minherit(__unused proc_t p, struct minherit_args *uap, __unused int32_t *retval)
{
mach_vm_offset_t addr;
mach_vm_size_t size;
vm_inherit_t inherit;
vm_map_t user_map;
kern_return_t result;
AUDIT_ARG(addr, uap->addr);
AUDIT_ARG(len, uap->len);
AUDIT_ARG(value32, uap->inherit);
addr = (mach_vm_offset_t)uap->addr;
size = (mach_vm_size_t)uap->len;
inherit = uap->inherit;
user_map = current_map();
result = mach_vm_inherit(user_map, addr, size,
inherit);
switch (result) {
case KERN_SUCCESS:
return (0);
case KERN_PROTECTION_FAILURE:
return (EACCES);
}
return (EINVAL);
}
int
madvise(__unused proc_t p, struct madvise_args *uap, __unused int32_t *retval)
{
vm_map_t user_map;
mach_vm_offset_t start;
mach_vm_size_t size;
vm_behavior_t new_behavior;
kern_return_t result;
/*
* Since this routine is only advisory, we default to conservative
* behavior.
*/
switch (uap->behav) {
case MADV_RANDOM:
new_behavior = VM_BEHAVIOR_RANDOM;
break;
case MADV_SEQUENTIAL:
new_behavior = VM_BEHAVIOR_SEQUENTIAL;
break;
case MADV_NORMAL:
new_behavior = VM_BEHAVIOR_DEFAULT;
break;
case MADV_WILLNEED:
new_behavior = VM_BEHAVIOR_WILLNEED;
break;
case MADV_DONTNEED:
new_behavior = VM_BEHAVIOR_DONTNEED;
break;
case MADV_FREE:
new_behavior = VM_BEHAVIOR_FREE;
break;
case MADV_ZERO_WIRED_PAGES:
new_behavior = VM_BEHAVIOR_ZERO_WIRED_PAGES;
break;
case MADV_FREE_REUSABLE:
new_behavior = VM_BEHAVIOR_REUSABLE;
break;
case MADV_FREE_REUSE:
new_behavior = VM_BEHAVIOR_REUSE;
break;
case MADV_CAN_REUSE:
new_behavior = VM_BEHAVIOR_CAN_REUSE;
break;
case MADV_PAGEOUT:
#if MACH_ASSERT
new_behavior = VM_BEHAVIOR_PAGEOUT;
break;
#else /* MACH_ASSERT */
return ENOTSUP;
#endif /* MACH_ASSERT */
default:
return(EINVAL);
}
start = (mach_vm_offset_t) uap->addr;
size = (mach_vm_size_t) uap->len;
user_map = current_map();
result = mach_vm_behavior_set(user_map, start, size, new_behavior);
switch (result) {
case KERN_SUCCESS:
return 0;
case KERN_INVALID_ADDRESS:
return EINVAL;
case KERN_NO_SPACE:
return ENOMEM;
}
return EINVAL;
}
int
mincore(__unused proc_t p, struct mincore_args *uap, __unused int32_t *retval)
{
mach_vm_offset_t addr, first_addr, end;
vm_map_t map;
user_addr_t vec;
int error;
int vecindex, lastvecindex;
int mincoreinfo=0;
int pqueryinfo;
kern_return_t ret;
int numref;
char c;
map = current_map();
/*
* Make sure that the addresses presented are valid for user
* mode.
*/
first_addr = addr = vm_map_trunc_page(uap->addr,
vm_map_page_mask(map));
end = addr + vm_map_round_page(uap->len,
vm_map_page_mask(map));
if (end < addr)
return (EINVAL);
/*