summaryrefslogtreecommitdiffstats
path: root/sys/vm/vm_mmap.c
blob: 03365293ebffc01d5466221e157a853a6e78c3fa (plain)
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
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
/*
 * 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	8.4 (Berkeley) 1/12/94
 * $FreeBSD$
 */

/*
 * Mapped file (mmap) interface to VM
 */

#include "opt_bleed.h"
#include "opt_compat.h"
#include "opt_rlimit.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/sysproto.h>
#include <sys/filedesc.h>
#include <sys/proc.h>
#include <sys/vnode.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/mman.h>
#include <sys/conf.h>
#include <sys/stat.h>
#include <sys/vmmeter.h>
#include <sys/sysctl.h>

#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_pager.h>
#include <vm/vm_pageout.h>
#include <vm/vm_extern.h>
#include <vm/vm_page.h>
#include <vm/vm_kern.h>

#ifndef _SYS_SYSPROTO_H_
struct sbrk_args {
	int incr;
};
#endif

static int max_proc_mmap;
SYSCTL_INT(_vm, OID_AUTO, max_proc_mmap, CTLFLAG_RW, &max_proc_mmap, 0, "");

/*
 * Set the maximum number of vm_map_entry structures per process.  Roughly
 * speaking vm_map_entry structures are tiny, so allowing them to eat 1/100
 * of our KVM malloc space still results in generous limits.  We want a 
 * default that is good enough to prevent the kernel running out of resources
 * if attacked from compromised user account but generous enough such that
 * multi-threaded processes are not unduly inconvenienced.
 */

static void vmmapentry_rsrc_init __P((void *));
SYSINIT(vmmersrc, SI_SUB_KVM_RSRC, SI_ORDER_FIRST, vmmapentry_rsrc_init, NULL)

static void
vmmapentry_rsrc_init(dummy)
        void *dummy;
{
    max_proc_mmap = vm_kmem_size / sizeof(struct vm_map_entry);
    max_proc_mmap /= 100;
}

/*
 * MPSAFE
 */
/* ARGSUSED */
int
sbrk(td, uap)
	struct thread *td;
	struct sbrk_args *uap;
{
	/* Not yet implemented */
	/* mtx_lock(&Giant); */
	/* mtx_unlock(&Giant); */
	return (EOPNOTSUPP);
}

#ifndef _SYS_SYSPROTO_H_
struct sstk_args {
	int incr;
};
#endif

/*
 * MPSAFE
 */
/* ARGSUSED */
int
sstk(td, uap)
	struct thread *td;
	struct sstk_args *uap;
{
	/* Not yet implemented */
	/* mtx_lock(&Giant); */
	/* mtx_unlock(&Giant); */
	return (EOPNOTSUPP);
}

#if defined(COMPAT_43) || defined(COMPAT_SUNOS)
#ifndef _SYS_SYSPROTO_H_
struct getpagesize_args {
	int dummy;
};
#endif

/* ARGSUSED */
int
ogetpagesize(td, uap)
	struct thread *td;
	struct getpagesize_args *uap;
{
	/* MP SAFE */
	td->td_retval[0] = PAGE_SIZE;
	return (0);
}
#endif				/* COMPAT_43 || COMPAT_SUNOS */


/* 
 * Memory Map (mmap) system call.  Note that the file offset
 * and address are allowed to be NOT page aligned, though if
 * the MAP_FIXED flag it set, both must have the same remainder
 * modulo the PAGE_SIZE (POSIX 1003.1b).  If the address is not
 * page-aligned, the actual mapping starts at trunc_page(addr)
 * and the return value is adjusted up by the page offset.
 *
 * Generally speaking, only character devices which are themselves
 * memory-based, such as a video framebuffer, can be mmap'd.  Otherwise
 * there would be no cache coherency between a descriptor and a VM mapping
 * both to the same character device.
 *
 * Block devices can be mmap'd no matter what they represent.  Cache coherency
 * is maintained as long as you do not write directly to the underlying
 * character device.
 */
#ifndef _SYS_SYSPROTO_H_
struct mmap_args {
	void *addr;
	size_t len;
	int prot;
	int flags;
	int fd;
	long pad;
	off_t pos;
};
#endif

/*
 * MPSAFE
 */
int
mmap(td, uap)
	struct thread *td;
	struct mmap_args *uap;
{
	struct filedesc *fdp = td->td_proc->p_fd;
	struct file *fp = NULL;
	struct vnode *vp;
	vm_offset_t addr;
	vm_size_t size, pageoff;
	vm_prot_t prot, maxprot;
	void *handle;
	int flags, error;
	int disablexworkaround;
	off_t pos;
	struct vmspace *vms = td->td_proc->p_vmspace;
	vm_object_t obj;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;
	prot = uap->prot & VM_PROT_ALL;
	flags = uap->flags;
	pos = uap->pos;

	/* make sure mapping fits into numeric range etc */
	if ((ssize_t) uap->len < 0 ||
	    ((flags & MAP_ANON) && uap->fd != -1))
		return (EINVAL);

	if (flags & MAP_STACK) {
		if ((uap->fd != -1) ||
		    ((prot & (PROT_READ | PROT_WRITE)) != (PROT_READ | PROT_WRITE)))
			return (EINVAL);
		flags |= MAP_ANON;
		pos = 0;
	}

	/*
	 * Align the file position to a page boundary,
	 * and save its page offset component.
	 */
	pageoff = (pos & PAGE_MASK);
	pos -= pageoff;

	/* Adjust size for rounding (on both ends). */
	size += pageoff;			/* low end... */
	size = (vm_size_t) round_page(size);	/* hi end */

	/*
	 * 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.
		 */
		addr -= pageoff;
		if (addr & PAGE_MASK)
			return (EINVAL);
		/* Address range must be all in user VM space. */
		if (VM_MAXUSER_ADDRESS > 0 && addr + size > VM_MAXUSER_ADDRESS)
			return (EINVAL);
#ifndef i386
		if (VM_MIN_ADDRESS > 0 && addr < VM_MIN_ADDRESS)
			return (EINVAL);
#endif
		if (addr + size < addr)
			return (EINVAL);
	}
	/*
	 * 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 == 0 ||
	    (addr >= round_page((vm_offset_t)vms->vm_taddr) &&
	     addr < round_page((vm_offset_t)vms->vm_daddr + MAXDSIZ)))
		addr = round_page((vm_offset_t)vms->vm_daddr + MAXDSIZ);

	mtx_lock(&Giant);	/* syscall marked mp-safe but isn't */
	if (flags & MAP_ANON) {
		/*
		 * Mapping blank space is trivial.
		 */
		handle = NULL;
		maxprot = VM_PROT_ALL;
		pos = 0;
	} else {
		/*
		 * Mapping file, get fp for validation. Obtain vnode and make
		 * sure it is of appropriate type.
		 */
		if (((unsigned) uap->fd) >= fdp->fd_nfiles ||
		    (fp = fdp->fd_ofiles[uap->fd]) == NULL) {
			error = EBADF;
			goto done2;
		}
		if (fp->f_type != DTYPE_VNODE) {
			error = EINVAL;
			goto done2;
		}

		/*
		 * don't let the descriptor disappear on us if we block
		 */
		fhold(fp);

		/*
		 * POSIX shared-memory objects are defined to have
		 * kernel persistence, and are not defined to support
		 * read(2)/write(2) -- or even open(2).  Thus, we can
		 * use MAP_ASYNC to trade on-disk coherence for speed.
		 * The shm_open(3) library routine turns on the FPOSIXSHM
		 * flag to request this behavior.
		 */
		if (fp->f_flag & FPOSIXSHM)
			flags |= MAP_NOSYNC;
		vp = (struct vnode *) fp->f_data;
		if (vp->v_type != VREG && vp->v_type != VCHR) {
			error = EINVAL;
			goto done;
		}
		if (vp->v_type == VREG) {
			/*
			 * Get the proper underlying object
			 */
			if (VOP_GETVOBJECT(vp, &obj) != 0) {
				error = EINVAL;
				goto done;
			}
			vp = (struct vnode*)obj->handle;
		}
		/*
		 * XXX hack to handle use of /dev/zero to map anon memory (ala
		 * SunOS).
		 */
		if ((vp->v_type == VCHR) && 
		    (vp->v_rdev->si_devsw->d_flags & D_MMAP_ANON)) {
			handle = NULL;
			maxprot = VM_PROT_ALL;
			flags |= MAP_ANON;
			pos = 0;
		} else {
			/*
			 * cdevs does not provide private mappings of any kind.
			 */
			/*
			 * However, for XIG X server to continue to work,
			 * we should allow the superuser to do it anyway.
			 * We only allow it at securelevel < 1.
			 * (Because the XIG X server writes directly to video
			 * memory via /dev/mem, it should never work at any
			 * other securelevel.
			 * XXX this will have to go
			 */
			if (securelevel >= 1)
				disablexworkaround = 1;
			else
				disablexworkaround = suser_td(td);
			if (vp->v_type == VCHR && disablexworkaround &&
			    (flags & (MAP_PRIVATE|MAP_COPY))) {
				error = EINVAL;
				goto done;
			}
			/*
			 * 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_flag & FREAD) {
				maxprot |= VM_PROT_READ;
			} else if (prot & PROT_READ) {
				error = EACCES;
				goto done;
			}
			/*
			 * 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.  Check for superuser, only if
			 * we're at securelevel < 1, to allow the XIG X server
			 * to continue to work.
			 */

			if ((flags & MAP_SHARED) != 0 ||
			    (vp->v_type == VCHR && disablexworkaround)) {
				if ((fp->f_flag & FWRITE) != 0) {
					struct vattr va;
					if ((error =
					    VOP_GETATTR(vp, &va,
						        td->td_proc->p_ucred, td))) {
						goto done;
					}
					if ((va.va_flags &
					   (SF_SNAPSHOT|IMMUTABLE|APPEND)) == 0) {
						maxprot |= VM_PROT_WRITE;
					} else if (prot & PROT_WRITE) {
						error = EPERM;
						goto done;
					}
				} else if ((prot & PROT_WRITE) != 0) {
					error = EACCES;
					goto done;
				}
			} else {
				maxprot |= VM_PROT_WRITE;
			}

			handle = (void *)vp;
		}
	}

	/*
	 * Do not allow more then a certain number of vm_map_entry structures
	 * per process.  Scale with the number of rforks sharing the map
	 * to make the limit reasonable for threads.
	 */
	if (max_proc_mmap && 
	    vms->vm_map.nentries >= max_proc_mmap * vms->vm_refcnt) {
		error = ENOMEM;
		goto done;
	}

	mtx_unlock(&Giant);
	error = vm_mmap(&vms->vm_map, &addr, size, prot, maxprot,
	    flags, handle, pos);
	if (error == 0)
		td->td_retval[0] = (register_t) (addr + pageoff);
	mtx_lock(&Giant);
done:
	if (fp)
		fdrop(fp, td);
done2:
	mtx_unlock(&Giant);
	return (error);
}

#ifdef COMPAT_43
#ifndef _SYS_SYSPROTO_H_
struct ommap_args {
	caddr_t addr;
	int len;
	int prot;
	int flags;
	int fd;
	long pos;
};
#endif
int
ommap(td, uap)
	struct thread *td;
	struct ommap_args *uap;
{
	struct mmap_args nargs;
	static const char cvtbsdprot[8] = {
		0,
		PROT_EXEC,
		PROT_WRITE,
		PROT_EXEC | PROT_WRITE,
		PROT_READ,
		PROT_EXEC | PROT_READ,
		PROT_WRITE | PROT_READ,
		PROT_EXEC | PROT_WRITE | PROT_READ,
	};

#define	OMAP_ANON	0x0002
#define	OMAP_COPY	0x0020
#define	OMAP_SHARED	0x0010
#define	OMAP_FIXED	0x0100

	nargs.addr = uap->addr;
	nargs.len = uap->len;
	nargs.prot = cvtbsdprot[uap->prot & 0x7];
	nargs.flags = 0;
	if (uap->flags & OMAP_ANON)
		nargs.flags |= MAP_ANON;
	if (uap->flags & OMAP_COPY)
		nargs.flags |= MAP_COPY;
	if (uap->flags & OMAP_SHARED)
		nargs.flags |= MAP_SHARED;
	else
		nargs.flags |= MAP_PRIVATE;
	if (uap->flags & OMAP_FIXED)
		nargs.flags |= MAP_FIXED;
	nargs.fd = uap->fd;
	nargs.pos = uap->pos;
	return (mmap(td, &nargs));
}
#endif				/* COMPAT_43 */


#ifndef _SYS_SYSPROTO_H_
struct msync_args {
	void *addr;
	int len;
	int flags;
};
#endif
/*
 * MPSAFE
 */
int
msync(td, uap)
	struct thread *td;
	struct msync_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	int flags;
	vm_map_t map;
	int rv;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;
	flags = uap->flags;

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);
	if (addr + size < addr)
		return(EINVAL);

	if ((flags & (MS_ASYNC|MS_INVALIDATE)) == (MS_ASYNC|MS_INVALIDATE))
		return (EINVAL);

	mtx_lock(&Giant);

	map = &td->td_proc->p_vmspace->vm_map;

	/*
	 * XXX Gak!  If size is zero we are supposed to sync "all modified
	 * pages with the region containing addr".  Unfortunately, we don't
	 * really keep track of individual mmaps so we approximate by flushing
	 * the range of the map entry containing addr. This can be incorrect
	 * if the region splits or is coalesced with a neighbor.
	 */
	if (size == 0) {
		vm_map_entry_t entry;

		vm_map_lock_read(map);
		rv = vm_map_lookup_entry(map, addr, &entry);
		vm_map_unlock_read(map);
		if (rv == FALSE) {
			rv = -1;
			goto done2;
		}
		addr = entry->start;
		size = entry->end - entry->start;
	}

	/*
	 * Clean the pages and interpret the return value.
	 */
	rv = vm_map_clean(map, addr, addr + size, (flags & MS_ASYNC) == 0,
	    (flags & MS_INVALIDATE) != 0);

done2:
	mtx_unlock(&Giant);

	switch (rv) {
	case KERN_SUCCESS:
		return(0);
	case KERN_INVALID_ADDRESS:
		return (EINVAL);	/* Sun returns ENOMEM? */
	case KERN_FAILURE:
		return (EIO);
	default:
		return (EINVAL);
	}
}

#ifndef _SYS_SYSPROTO_H_
struct munmap_args {
	void *addr;
	size_t len;
};
#endif
/*
 * MPSAFE
 */
int
munmap(td, uap)
	struct thread *td;
	struct munmap_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	vm_map_t map;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);
	if (addr + size < addr)
		return(EINVAL);

	if (size == 0)
		return (0);

	/*
	 * Check for illegal addresses.  Watch out for address wrap... Note
	 * that VM_*_ADDRESS are not constants due to casts (argh).
	 */
	if (VM_MAXUSER_ADDRESS > 0 && addr + size > VM_MAXUSER_ADDRESS)
		return (EINVAL);
#ifndef i386
	if (VM_MIN_ADDRESS > 0 && addr < VM_MIN_ADDRESS)
		return (EINVAL);
#endif
	mtx_lock(&Giant);
	map = &td->td_proc->p_vmspace->vm_map;
	/*
	 * Make sure entire range is allocated.
	 */
	if (!vm_map_check_protection(map, addr, addr + size, VM_PROT_NONE)) {
		mtx_unlock(&Giant);
		return (EINVAL);
	}
	/* returns nothing but KERN_SUCCESS anyway */
	(void) vm_map_remove(map, addr, addr + size);
	mtx_unlock(&Giant);
	return (0);
}

#if 0
void
munmapfd(td, fd)
	struct thread *td;
	int fd;
{
	/*
	 * XXX should unmap any regions mapped to this file
	 */
	td->td_proc->p_fd->fd_ofileflags[fd] &= ~UF_MAPPED;
}
#endif

#ifndef _SYS_SYSPROTO_H_
struct mprotect_args {
	const void *addr;
	size_t len;
	int prot;
};
#endif
/*
 * MPSAFE
 */
int
mprotect(td, uap)
	struct thread *td;
	struct mprotect_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	vm_prot_t prot;
	int ret;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;
	prot = uap->prot & VM_PROT_ALL;
#if defined(VM_PROT_READ_IS_EXEC)
	if (prot & VM_PROT_READ)
		prot |= VM_PROT_EXECUTE;
#endif

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);
	if (addr + size < addr)
		return(EINVAL);

	mtx_lock(&Giant);
	ret = vm_map_protect(&td->td_proc->p_vmspace->vm_map, addr,
		     addr + size, prot, FALSE);
	mtx_unlock(&Giant);
	switch (ret) {
	case KERN_SUCCESS:
		return (0);
	case KERN_PROTECTION_FAILURE:
		return (EACCES);
	}
	return (EINVAL);
}

#ifndef _SYS_SYSPROTO_H_
struct minherit_args {
	void *addr;
	size_t len;
	int inherit;
};
#endif
/*
 * MPSAFE
 */
int
minherit(td, uap)
	struct thread *td;
	struct minherit_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	vm_inherit_t inherit;
	int ret;

	addr = (vm_offset_t)uap->addr;
	size = uap->len;
	inherit = uap->inherit;

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);
	if (addr + size < addr)
		return(EINVAL);

	mtx_lock(&Giant);
	ret = vm_map_inherit(&td->td_proc->p_vmspace->vm_map, addr, addr+size,
		    inherit);
	mtx_unlock(&Giant);

	switch (ret) {
	case KERN_SUCCESS:
		return (0);
	case KERN_PROTECTION_FAILURE:
		return (EACCES);
	}
	return (EINVAL);
}

#ifndef _SYS_SYSPROTO_H_
struct madvise_args {
	void *addr;
	size_t len;
	int behav;
};
#endif

/*
 * MPSAFE
 */
/* ARGSUSED */
int
madvise(td, uap)
	struct thread *td;
	struct madvise_args *uap;
{
	vm_offset_t start, end;
	int ret;

	/*
	 * Check for illegal behavior
	 */
	if (uap->behav < 0 || uap->behav > MADV_CORE)
		return (EINVAL);
	/*
	 * Check for illegal addresses.  Watch out for address wrap... Note
	 * that VM_*_ADDRESS are not constants due to casts (argh).
	 */
	if (VM_MAXUSER_ADDRESS > 0 &&
		((vm_offset_t) uap->addr + uap->len) > VM_MAXUSER_ADDRESS)
		return (EINVAL);
#ifndef i386
	if (VM_MIN_ADDRESS > 0 && uap->addr < VM_MIN_ADDRESS)
		return (EINVAL);
#endif
	if (((vm_offset_t) uap->addr + uap->len) < (vm_offset_t) uap->addr)
		return (EINVAL);

	/*
	 * Since this routine is only advisory, we default to conservative
	 * behavior.
	 */
	start = trunc_page((vm_offset_t) uap->addr);
	end = round_page((vm_offset_t) uap->addr + uap->len);
	
	mtx_lock(&Giant);
	ret = vm_map_madvise(&td->td_proc->p_vmspace->vm_map, start, end, uap->behav);
	mtx_unlock(&Giant);
	return (ret ? EINVAL : 0);
}

#ifndef _SYS_SYSPROTO_H_
struct mincore_args {
	const void *addr;
	size_t len;
	char *vec;
};
#endif

/*
 * MPSAFE
 */
/* ARGSUSED */
int
mincore(td, uap)
	struct thread *td;
	struct mincore_args *uap;
{
	vm_offset_t addr, first_addr;
	vm_offset_t end, cend;
	pmap_t pmap;
	vm_map_t map;
	char *vec;
	int error = 0;
	int vecindex, lastvecindex;
	vm_map_entry_t current;
	vm_map_entry_t entry;
	int mincoreinfo;
	unsigned int timestamp;

	/*
	 * Make sure that the addresses presented are valid for user
	 * mode.
	 */
	first_addr = addr = trunc_page((vm_offset_t) uap->addr);
	end = addr + (vm_size_t)round_page(uap->len);
	if (VM_MAXUSER_ADDRESS > 0 && end > VM_MAXUSER_ADDRESS)
		return (EINVAL);
	if (end < addr)
		return (EINVAL);

	/*
	 * Address of byte vector
	 */
	vec = uap->vec;

	mtx_lock(&Giant);
	map = &td->td_proc->p_vmspace->vm_map;
	pmap = vmspace_pmap(td->td_proc->p_vmspace);

	vm_map_lock_read(map);
RestartScan:
	timestamp = map->timestamp;

	if (!vm_map_lookup_entry(map, addr, &entry))
		entry = entry->next;

	/*
	 * Do this on a map entry basis so that if the pages are not
	 * in the current processes address space, we can easily look
	 * up the pages elsewhere.
	 */
	lastvecindex = -1;
	for (current = entry;
	    (current != &map->header) && (current->start < end);
	    current = current->next) {

		/*
		 * ignore submaps (for now) or null objects
		 */
		if ((current->eflags & MAP_ENTRY_IS_SUB_MAP) ||
			current->object.vm_object == NULL)
			continue;
		
		/*
		 * limit this scan to the current map entry and the
		 * limits for the mincore call
		 */
		if (addr < current->start)
			addr = current->start;
		cend = current->end;
		if (cend > end)
			cend = end;

		/*
		 * scan this entry one page at a time
		 */
		while (addr < cend) {
			/*
			 * Check pmap first, it is likely faster, also
			 * it can provide info as to whether we are the
			 * one referencing or modifying the page.
			 */
			mincoreinfo = pmap_mincore(pmap, addr);
			if (!mincoreinfo) {
				vm_pindex_t pindex;
				vm_ooffset_t offset;
				vm_page_t m;
				/*
				 * calculate the page index into the object
				 */
				offset = current->offset + (addr - current->start);
				pindex = OFF_TO_IDX(offset);
				m = vm_page_lookup(current->object.vm_object,
					pindex);
				/*
				 * if the page is resident, then gather information about
				 * it.
				 */
				if (m) {
					mincoreinfo = MINCORE_INCORE;
					if (m->dirty ||
						pmap_is_modified(m))
						mincoreinfo |= MINCORE_MODIFIED_OTHER;
					if ((m->flags & PG_REFERENCED) ||
						pmap_ts_referenced(m)) {
						vm_page_flag_set(m, PG_REFERENCED);
						mincoreinfo |= MINCORE_REFERENCED_OTHER;
					}
				}
			}

			/*
			 * subyte may page fault.  In case it needs to modify
			 * the map, we release the lock.
			 */
			vm_map_unlock_read(map);

			/*
			 * calculate index into user supplied byte vector
			 */
			vecindex = OFF_TO_IDX(addr - first_addr);

			/*
			 * If we have skipped map entries, we need to make sure that
			 * the byte vector is zeroed for those skipped entries.
			 */
			while ((lastvecindex + 1) < vecindex) {
				error = subyte( vec + lastvecindex, 0);
				if (error) {
					error = EFAULT;
					goto done2;
				}
				++lastvecindex;
			}

			/*
			 * Pass the page information to the user
			 */
			error = subyte( vec + vecindex, mincoreinfo);
			if (error) {
				error = EFAULT;
				goto done2;
			}

			/*
			 * If the map has changed, due to the subyte, the previous
			 * output may be invalid.
			 */
			vm_map_lock_read(map);
			if (timestamp != map->timestamp)
				goto RestartScan;

			lastvecindex = vecindex;
			addr += PAGE_SIZE;
		}
	}

	/*
	 * subyte may page fault.  In case it needs to modify
	 * the map, we release the lock.
	 */
	vm_map_unlock_read(map);

	/*
	 * Zero the last entries in the byte vector.
	 */
	vecindex = OFF_TO_IDX(end - first_addr);
	while ((lastvecindex + 1) < vecindex) {
		error = subyte( vec + lastvecindex, 0);
		if (error) {
			error = EFAULT;
			goto done2;
		}
		++lastvecindex;
	}
	
	/*
	 * If the map has changed, due to the subyte, the previous
	 * output may be invalid.
	 */
	vm_map_lock_read(map);
	if (timestamp != map->timestamp)
		goto RestartScan;
	vm_map_unlock_read(map);
done2:
	mtx_unlock(&Giant);
	return (error);
}

#ifndef _SYS_SYSPROTO_H_
struct mlock_args {
	const void *addr;
	size_t len;
};
#endif
/*
 * MPSAFE
 */
int
mlock(td, uap)
	struct thread *td;
	struct mlock_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	int error;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);

	/* disable wrap around */
	if (addr + size < addr)
		return (EINVAL);

	if (atop(size) + cnt.v_wire_count > vm_page_max_wired)
		return (EAGAIN);

#ifdef pmap_wired_count
	if (size + ptoa(pmap_wired_count(vm_map_pmap(&td->td_proc->p_vmspace->vm_map))) >
	    td->td_proc->p_rlimit[RLIMIT_MEMLOCK].rlim_cur)
		return (ENOMEM);
#else
	error = suser_td(td);
	if (error)
		return (error);
#endif

	mtx_lock(&Giant);
	error = vm_map_user_pageable(&td->td_proc->p_vmspace->vm_map, addr,
		     addr + size, FALSE);
	mtx_unlock(&Giant);
	return (error == KERN_SUCCESS ? 0 : ENOMEM);
}

#ifndef _SYS_SYSPROTO_H_
struct mlockall_args {
	int	how;
};
#endif

/*
 * MPSAFE
 */
int
mlockall(td, uap)
	struct thread *td;
	struct mlockall_args *uap;
{
	/* mtx_lock(&Giant); */
	/* mtx_unlock(&Giant); */
	return 0;
}

#ifndef _SYS_SYSPROTO_H_
struct mlockall_args {
	int	how;
};
#endif

/*
 * MPSAFE
 */
int
munlockall(td, uap)
	struct thread *td;
	struct munlockall_args *uap;
{
	/* mtx_lock(&Giant); */
	/* mtx_unlock(&Giant); */
	return 0;
}

#ifndef _SYS_SYSPROTO_H_
struct munlock_args {
	const void *addr;
	size_t len;
};
#endif
/*
 * MPSAFE
 */
int
munlock(td, uap)
	struct thread *td;
	struct munlock_args *uap;
{
	vm_offset_t addr;
	vm_size_t size, pageoff;
	int error;

	addr = (vm_offset_t) uap->addr;
	size = uap->len;

	pageoff = (addr & PAGE_MASK);
	addr -= pageoff;
	size += pageoff;
	size = (vm_size_t) round_page(size);

	/* disable wrap around */
	if (addr + size < addr)
		return (EINVAL);

#ifndef pmap_wired_count
	error = suser_td(td);
	if (error)
		return (error);
#endif

	mtx_lock(&Giant);
	error = vm_map_user_pageable(&td->td_proc->p_vmspace->vm_map, addr,
		     addr + size, TRUE);
	mtx_unlock(&Giant);
	return (error == KERN_SUCCESS ? 0 : ENOMEM);
}

/*
 * vm_mmap()
 *
 * MPSAFE
 *
 * Internal version of mmap.  Currently used by mmap, exec, and sys5
 * shared memory.  Handle is either a vnode pointer or NULL for MAP_ANON.
 */
int
vm_mmap(vm_map_t map, vm_offset_t *addr, vm_size_t size, vm_prot_t prot,
	vm_prot_t maxprot, int flags,
	void *handle,
	vm_ooffset_t foff)
{
	boolean_t fitit;
	vm_object_t object;
	struct vnode *vp = NULL;
	objtype_t type;
	int rv = KERN_SUCCESS;
	vm_ooffset_t objsize;
	int docow;
	struct thread *td = curthread;

	if (size == 0)
		return (0);

	objsize = size = round_page(size);

	/*
	 * We currently can only deal with page aligned file offsets.
	 * The check is here rather than in the syscall because the
	 * kernel calls this function internally for other mmaping
	 * operations (such as in exec) and non-aligned offsets will
	 * cause pmap inconsistencies...so we want to be sure to
	 * disallow this in all cases.
	 */
	if (foff & PAGE_MASK)
		return (EINVAL);

	if ((flags & MAP_FIXED) == 0) {
		fitit = TRUE;
		*addr = round_page(*addr);
		mtx_lock(&Giant);
	} else {
		if (*addr != trunc_page(*addr))
			return (EINVAL);
		fitit = FALSE;
		mtx_lock(&Giant);
		(void) vm_map_remove(map, *addr, *addr + size);
	}

	/*
	 * Lookup/allocate object.
	 */
	if (flags & MAP_ANON) {
		type = OBJT_DEFAULT;
		/*
		 * Unnamed anonymous regions always start at 0.
		 */
		if (handle == 0)
			foff = 0;
	} else {
		vp = (struct vnode *) handle;
		if (vp->v_type == VCHR) {
			type = OBJT_DEVICE;
			handle = (void *)(intptr_t)vp->v_rdev;
		} else {
			struct vattr vat;
			int error;

			error = VOP_GETATTR(vp, &vat, td->td_proc->p_ucred, td);
			if (error) {
				mtx_unlock(&Giant);
				return (error);
			}
			objsize = round_page(vat.va_size);
			type = OBJT_VNODE;
			/*
			 * if it is a regular file without any references
			 * we do not need to sync it.
			 */
			if (vp->v_type == VREG && vat.va_nlink == 0) {
				flags |= MAP_NOSYNC;
			}
		}
	}

	if (handle == NULL) {
		object = NULL;
		docow = 0;
	} else {
		object = vm_pager_allocate(type,
			handle, objsize, prot, foff);
		if (object == NULL) {
			mtx_unlock(&Giant);
			return (type == OBJT_DEVICE ? EINVAL : ENOMEM);
		}
		docow = MAP_PREFAULT_PARTIAL;
	}

	/*
	 * Force device mappings to be shared.
	 */
	if (type == OBJT_DEVICE || type == OBJT_PHYS) {
		flags &= ~(MAP_PRIVATE|MAP_COPY);
		flags |= MAP_SHARED;
	}

	if ((flags & (MAP_ANON|MAP_SHARED)) == 0)
		docow |= MAP_COPY_ON_WRITE;
	if (flags & MAP_NOSYNC)
		docow |= MAP_DISABLE_SYNCER;
	if (flags & MAP_NOCORE)
		docow |= MAP_DISABLE_COREDUMP;

#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

	if (fitit)
		*addr = pmap_addr_hint(object, *addr, size);

	if (flags & MAP_STACK)
		rv = vm_map_stack (map, *addr, size, prot,
				   maxprot, docow);
	else
		rv = vm_map_find(map, object, foff, addr, size, fitit,
				 prot, maxprot, docow);

	if (rv != KERN_SUCCESS) {
		/*
		 * Lose the object reference. Will destroy the
		 * object if it's an unnamed anonymous mapping
		 * or named anonymous without other references.
		 */
		vm_object_deallocate(object);
	} else if (flags & MAP_SHARED) {
		/*
		 * Shared memory is also shared with children.
		 */
		rv = vm_map_inherit(map, *addr, *addr + size, VM_INHERIT_SHARE);
		if (rv != KERN_SUCCESS)
			(void) vm_map_remove(map, *addr, *addr + size);
	}
	mtx_unlock(&Giant);
	switch (rv) {
	case KERN_SUCCESS:
		return (0);
	case KERN_INVALID_ADDRESS:
	case KERN_NO_SPACE:
		return (ENOMEM);
	case KERN_PROTECTION_FAILURE:
		return (EACCES);
	default:
		return (EINVAL);
	}
}
OpenPOWER on IntegriCloud