summaryrefslogtreecommitdiffstats
path: root/uClinux-2.4.20-uc1/mmnommu/mmap.c
blob: 72fb61411014294646074931057d5abd3b7149e6 (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
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
/*
 *	linux/mm/mmap.c
 *
 * Written by obz.
 *
 * NO_MM
 *  Copyright (c) 2001 Lineo, Inc. David McCullough <davidm@lineo.com>
 *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org> ref uClinux 2.0
 */
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>

#include <asm/uaccess.h>
#include <asm/pgalloc.h>

#ifndef NO_MM
/*
 * WARNING: the debugging will use recursive algorithms so never enable this
 * unless you know what you are doing.
 */
#undef DEBUG_MM_RB

/* description of effects of mapping type and prot in current implementation.
 * this is due to the limited x86 page protection hardware.  The expected
 * behavior is in parens:
 *
 * map_type	prot
 *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
 * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *		
 * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 */
pgprot_t protection_map[16] = {
	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};

int sysctl_overcommit_memory;
int max_map_count = DEFAULT_MAX_MAP_COUNT;

/* Check that a process has enough memory to allocate a
 * new virtual mapping.
 */
int vm_enough_memory(long pages)
{
	/* Stupid algorithm to decide if we have enough memory: while
	 * simple, it hopefully works in most obvious cases.. Easy to
	 * fool it, but this should catch most mistakes.
	 */
	/* 23/11/98 NJC: Somewhat less stupid version of algorithm,
	 * which tries to do "TheRightThing".  Instead of using half of
	 * (buffers+cache), use the minimum values.  Allow an extra 2%
	 * of num_physpages for safety margin.
	 */

	unsigned long free;
	
        /* Sometimes we want to use more memory than we have. */
	if (sysctl_overcommit_memory)
	    return 1;

	/* The page cache contains buffer pages these days.. */
	free = atomic_read(&page_cache_size);
	free += nr_free_pages();
	free += nr_swap_pages;

	/*
	 * This double-counts: the nrpages are both in the page-cache
	 * and in the swapper space. At the same time, this compensates
	 * for the swap-space over-allocation (ie "nr_swap_pages" being
	 * too small.
	 */
	free += swapper_space.nrpages;

	/*
	 * The code below doesn't account for free space in the inode
	 * and dentry slab cache, slab cache fragmentation, inodes and
	 * dentries which will become freeable under VM load, etc.
	 * Lets just hope all these (complex) factors balance out...
	 */
	free += (dentry_stat.nr_unused * sizeof(struct dentry)) >> PAGE_SHIFT;
	free += (inodes_stat.nr_unused * sizeof(struct inode)) >> PAGE_SHIFT;

	return free > pages;
}

/* Remove one vm structure from the inode's i_mapping address space. */
static inline void __remove_shared_vm_struct(struct vm_area_struct *vma)
{
	struct file * file = vma->vm_file;

	if (file) {
		struct inode *inode = file->f_dentry->d_inode;
		if (vma->vm_flags & VM_DENYWRITE)
			atomic_inc(&inode->i_writecount);
		if(vma->vm_next_share)
			vma->vm_next_share->vm_pprev_share = vma->vm_pprev_share;
		*vma->vm_pprev_share = vma->vm_next_share;
	}
}

static inline void remove_shared_vm_struct(struct vm_area_struct *vma)
{
	lock_vma_mappings(vma);
	__remove_shared_vm_struct(vma);
	unlock_vma_mappings(vma);
}

void lock_vma_mappings(struct vm_area_struct *vma)
{
	struct address_space *mapping;

	mapping = NULL;
	if (vma->vm_file)
		mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
	if (mapping)
		spin_lock(&mapping->i_shared_lock);
}

void unlock_vma_mappings(struct vm_area_struct *vma)
{
	struct address_space *mapping;

	mapping = NULL;
	if (vma->vm_file)
		mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
	if (mapping)
		spin_unlock(&mapping->i_shared_lock);
}

#endif /* NO_MM */

/*
 *  sys_brk() for the most part doesn't need the global kernel
 *  lock, except when an application is doing something nasty
 *  like trying to un-brk an area that has already been mapped
 *  to a regular file.  in this case, the unmapping will need
 *  to invoke file system routines that need the global lock.
 */
asmlinkage unsigned long sys_brk(unsigned long brk)
{
#ifndef NO_MM
	unsigned long rlim, retval;
	unsigned long newbrk, oldbrk;
	struct mm_struct *mm = current->mm;

	down_write(&mm->mmap_sem);

	if (brk < mm->end_code)
		goto out;
	newbrk = PAGE_ALIGN(brk);
	oldbrk = PAGE_ALIGN(mm->brk);
	if (oldbrk == newbrk)
		goto set_brk;

	/* Always allow shrinking brk. */
	if (brk <= mm->brk) {
		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
			goto set_brk;
		goto out;
	}

	/* Check against rlimit.. */
	rlim = current->rlim[RLIMIT_DATA].rlim_cur;
	if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
		goto out;

	/* Check against existing mmap mappings. */
	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
		goto out;

	/* Check if we have enough memory.. */
	if (!vm_enough_memory((newbrk-oldbrk) >> PAGE_SHIFT))
		goto out;

	/* Ok, looks good - let it rip. */
	if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
		goto out;
set_brk:
	mm->brk = brk;
out:
	retval = mm->brk;
	up_write(&mm->mmap_sem);
	return retval;
#else
	struct mm_struct *mm = current->mm;

	if (brk < mm->end_code || brk < mm->start_brk || brk > mm->end_brk)
		return mm->brk;

	if (mm->brk == brk)
		return mm->brk;

	/*
	 * Always allow shrinking brk
	 */
	if (brk <= mm->brk) {
		mm->brk = brk;
		return brk;
	}

	/*
	 * Ok, looks good - let it rip.
	 */
	return mm->brk = brk;
#endif
}


/* Combine the mmap "prot" and "flags" argument into one "vm_flags" used
 * internally. Essentially, translate the "PROT_xxx" and "MAP_xxx" bits
 * into "VM_xxx".
 */
static inline unsigned long calc_vm_flags(unsigned long prot, unsigned long flags)
{
#define _trans(x,bit1,bit2) \
((bit1==bit2)?(x&bit1):(x&bit1)?bit2:0)

	unsigned long prot_bits, flag_bits;
	prot_bits =
		_trans(prot, PROT_READ, VM_READ) |
		_trans(prot, PROT_WRITE, VM_WRITE) |
		_trans(prot, PROT_EXEC, VM_EXEC);
	flag_bits =
		_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN) |
		_trans(flags, MAP_DENYWRITE, VM_DENYWRITE) |
		_trans(flags, MAP_EXECUTABLE, VM_EXECUTABLE);
	return prot_bits | flag_bits;
#undef _trans
}

#ifndef NO_MM

#ifdef DEBUG_MM_RB
static int browse_rb(rb_node_t * rb_node) {
	int i = 0;
	if (rb_node) {
		i++;
		i += browse_rb(rb_node->rb_left);
		i += browse_rb(rb_node->rb_right);
	}
	return i;
}

static void validate_mm(struct mm_struct * mm) {
	int bug = 0;
	int i = 0;
	struct vm_area_struct * tmp = mm->mmap;
	while (tmp) {
		tmp = tmp->vm_next;
		i++;
	}
	if (i != mm->map_count)
		printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1;
	i = browse_rb(mm->mm_rb.rb_node);
	if (i != mm->map_count)
		printk("map_count %d rb %d\n", mm->map_count, i), bug = 1;
	if (bug)
		BUG();
}
#else
#define validate_mm(mm) do { } while (0)
#endif

static struct vm_area_struct * find_vma_prepare(struct mm_struct * mm, unsigned long addr,
						struct vm_area_struct ** pprev,
						rb_node_t *** rb_link, rb_node_t ** rb_parent)
{
	struct vm_area_struct * vma;
	rb_node_t ** __rb_link, * __rb_parent, * rb_prev;

	__rb_link = &mm->mm_rb.rb_node;
	rb_prev = __rb_parent = NULL;
	vma = NULL;

	while (*__rb_link) {
		struct vm_area_struct *vma_tmp;

		__rb_parent = *__rb_link;
		vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);

		if (vma_tmp->vm_end > addr) {
			vma = vma_tmp;
			if (vma_tmp->vm_start <= addr)
				return vma;
			__rb_link = &__rb_parent->rb_left;
		} else {
			rb_prev = __rb_parent;
			__rb_link = &__rb_parent->rb_right;
		}
	}

	*pprev = NULL;
	if (rb_prev)
		*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
	*rb_link = __rb_link;
	*rb_parent = __rb_parent;
	return vma;
}

static inline void __vma_link_list(struct mm_struct * mm, struct vm_area_struct * vma, struct vm_area_struct * prev,
				   rb_node_t * rb_parent)
{
	if (prev) {
		vma->vm_next = prev->vm_next;
		prev->vm_next = vma;
	} else {
		mm->mmap = vma;
		if (rb_parent)
			vma->vm_next = rb_entry(rb_parent, struct vm_area_struct, vm_rb);
		else
			vma->vm_next = NULL;
	}
}

static inline void __vma_link_rb(struct mm_struct * mm, struct vm_area_struct * vma,
				 rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
}

static inline void __vma_link_file(struct vm_area_struct * vma)
{
	struct file * file;

	file = vma->vm_file;
	if (file) {
		struct inode * inode = file->f_dentry->d_inode;
		struct address_space *mapping = inode->i_mapping;
		struct vm_area_struct **head;

		if (vma->vm_flags & VM_DENYWRITE)
			atomic_dec(&inode->i_writecount);

		head = &mapping->i_mmap;
		if (vma->vm_flags & VM_SHARED)
			head = &mapping->i_mmap_shared;
      
		/* insert vma into inode's share list */
		if((vma->vm_next_share = *head) != NULL)
			(*head)->vm_pprev_share = &vma->vm_next_share;
		*head = vma;
		vma->vm_pprev_share = head;
	}
}

static void __vma_link(struct mm_struct * mm, struct vm_area_struct * vma,  struct vm_area_struct * prev,
		       rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	__vma_link_list(mm, vma, prev, rb_parent);
	__vma_link_rb(mm, vma, rb_link, rb_parent);
	__vma_link_file(vma);
}

static inline void vma_link(struct mm_struct * mm, struct vm_area_struct * vma, struct vm_area_struct * prev,
			    rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	lock_vma_mappings(vma);
	spin_lock(&mm->page_table_lock);
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	spin_unlock(&mm->page_table_lock);
	unlock_vma_mappings(vma);

	mm->map_count++;
	validate_mm(mm);
}

static int vma_merge(struct mm_struct * mm, struct vm_area_struct * prev,
		     rb_node_t * rb_parent, unsigned long addr, unsigned long end, unsigned long vm_flags)
{
	spinlock_t * lock = &mm->page_table_lock;
	if (!prev) {
		prev = rb_entry(rb_parent, struct vm_area_struct, vm_rb);
		goto merge_next;
	}
	if (prev->vm_end == addr && can_vma_merge(prev, vm_flags)) {
		struct vm_area_struct * next;

		spin_lock(lock);
		prev->vm_end = end;
		next = prev->vm_next;
		if (next && prev->vm_end == next->vm_start && can_vma_merge(next, vm_flags)) {
			prev->vm_end = next->vm_end;
			__vma_unlink(mm, next, prev);
			spin_unlock(lock);

			mm->map_count--;
			kmem_cache_free(vm_area_cachep, next);
			return 1;
		}
		spin_unlock(lock);
		return 1;
	}

	prev = prev->vm_next;
	if (prev) {
 merge_next:
		if (!can_vma_merge(prev, vm_flags))
			return 0;
		if (end == prev->vm_start) {
			spin_lock(lock);
			prev->vm_start = addr;
			spin_unlock(lock);
			return 1;
		}
	}

	return 0;
}

unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, unsigned long len,
	unsigned long prot, unsigned long flags, unsigned long pgoff)
{
	struct mm_struct * mm = current->mm;
	struct vm_area_struct * vma, * prev;
	unsigned int vm_flags;
	int correct_wcount = 0;
	int error;
	rb_node_t ** rb_link, * rb_parent;

	if (file && (!file->f_op || !file->f_op->mmap))
		return -ENODEV;

	if ((len = PAGE_ALIGN(len)) == 0)
		return addr;

	if (len > TASK_SIZE)
		return -EINVAL;

	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
		return -EINVAL;

	/* Too many mappings? */
	if (mm->map_count > max_map_count)
		return -ENOMEM;

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	if (addr & ~PAGE_MASK)
		return addr;

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	vm_flags = calc_vm_flags(prot,flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

	/* mlock MCL_FUTURE? */
	if (vm_flags & VM_LOCKED) {
		unsigned long locked = mm->locked_vm << PAGE_SHIFT;
		locked += len;
		if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
			return -EAGAIN;
	}

	if (file) {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if ((prot & PROT_WRITE) && !(file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* Make sure we don't allow writing to an append-only file.. */
			if (IS_APPEND(file->f_dentry->d_inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* make sure there are no mandatory locks on the file. */
			if (locks_verify_locked(file->f_dentry->d_inode))
				return -EAGAIN;

			vm_flags |= VM_SHARED | VM_MAYSHARE;
			if (!(file->f_mode & FMODE_WRITE))
				vm_flags &= ~(VM_MAYWRITE | VM_SHARED);

			/* fall through */
		case MAP_PRIVATE:
			if (!(file->f_mode & FMODE_READ))
				return -EACCES;
			break;

		default:
			return -EINVAL;
		}
	} else {
		vm_flags |= VM_SHARED | VM_MAYSHARE;
		switch (flags & MAP_TYPE) {
		default:
			return -EINVAL;
		case MAP_PRIVATE:
			vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
			/* fall through */
		case MAP_SHARED:
			break;
		}
	}

	/* Clear old maps */
munmap_back:
	vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	if (vma && vma->vm_start < addr + len) {
		if (do_munmap(mm, addr, len))
			return -ENOMEM;
		goto munmap_back;
	}

	/* Check against address space limit. */
	if ((mm->total_vm << PAGE_SHIFT) + len
	    > current->rlim[RLIMIT_AS].rlim_cur)
		return -ENOMEM;

	/* Private writable mapping? Check memory availability.. */
	if ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
	    !(flags & MAP_NORESERVE)				 &&
	    !vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	/* Can we just expand an old anonymous mapping? */
	if (!file && !(vm_flags & VM_SHARED) && rb_parent)
		if (vma_merge(mm, prev, rb_parent, addr, addr + len, vm_flags))
			goto out;

	/* Determine the object being mapped and call the appropriate
	 * specific mapper. the address has already been validated, but
	 * not unmapped, but the maps are removed from the list.
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!vma)
		return -ENOMEM;

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = vm_flags;
	vma->vm_page_prot = protection_map[vm_flags & 0x0f];
	vma->vm_ops = NULL;
	vma->vm_pgoff = pgoff;
	vma->vm_file = NULL;
	vma->vm_private_data = NULL;
	vma->vm_raend = 0;

	if (file) {
		error = -EINVAL;
		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
			goto free_vma;
		if (vm_flags & VM_DENYWRITE) {
			error = deny_write_access(file);
			if (error)
				goto free_vma;
			correct_wcount = 1;
		}
		vma->vm_file = file;
		get_file(file);
		error = file->f_op->mmap(file, vma);
		if (error)
			goto unmap_and_free_vma;
	} else if (flags & MAP_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

	/* Can addr have changed??
	 *
	 * Answer: Yes, several device drivers can do it in their
	 *         f_op->mmap method. -DaveM
	 */
	if (addr != vma->vm_start) {
		/*
		 * It is a bit too late to pretend changing the virtual
		 * area of the mapping, we just corrupted userspace
		 * in the do_munmap, so FIXME (not in 2.4 to avoid breaking
		 * the driver API).
		 */
		struct vm_area_struct * stale_vma;
		/* Since addr changed, we rely on the mmap op to prevent 
		 * collisions with existing vmas and just use find_vma_prepare 
		 * to update the tree pointers.
		 */
		addr = vma->vm_start;
		stale_vma = find_vma_prepare(mm, addr, &prev,
						&rb_link, &rb_parent);
		/*
		 * Make sure the lowlevel driver did its job right.
		 */
		if (unlikely(stale_vma && stale_vma->vm_start < vma->vm_end)) {
			printk(KERN_ERR "buggy mmap operation: [<%p>]\n",
				file ? file->f_op->mmap : NULL);
			BUG();
		}
	}

	vma_link(mm, vma, prev, rb_link, rb_parent);
	if (correct_wcount)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);

out:	
	mm->total_vm += len >> PAGE_SHIFT;
	if (vm_flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	return addr;

unmap_and_free_vma:
	if (correct_wcount)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);
	vma->vm_file = NULL;
	fput(file);

	/* Undo any partial mapping done by a device driver. */
	zap_page_range(mm, vma->vm_start, vma->vm_end - vma->vm_start);
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
	return error;
}

/* Get an address range which is currently unmapped.
 * For shmat() with addr=0.
 *
 * Ugly calling convention alert:
 * Return value with the low bits set means error value,
 * ie
 *	if (ret & ~PAGE_MASK)
 *		error = ret;
 *
 * This function "knows" that -ENOMEM has the bits set.
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA
static inline unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct vm_area_struct *vma;

	if (len > TASK_SIZE)
		return -ENOMEM;

	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(current->mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}
	addr = PAGE_ALIGN(TASK_UNMAPPED_BASE);

	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr)
			return -ENOMEM;
		if (!vma || addr + len <= vma->vm_start)
			return addr;
		addr = vma->vm_end;
	}
}
#else
extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
#endif	

unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
	if (flags & MAP_FIXED) {
		if (addr > TASK_SIZE - len)
			return -ENOMEM;
		if (addr & ~PAGE_MASK)
			return -EINVAL;
		return addr;
	}

	if (file && file->f_op && file->f_op->get_unmapped_area)
		return file->f_op->get_unmapped_area(file, addr, len, pgoff, flags);

	return arch_get_unmapped_area(file, addr, len, pgoff, flags);
}

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct *vma = NULL;

	if (mm) {
		/* Check the cache first. */
		/* (Cache hit rate is typically around 35%.) */
		vma = mm->mmap_cache;
		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
			rb_node_t * rb_node;

			rb_node = mm->mm_rb.rb_node;
			vma = NULL;

			while (rb_node) {
				struct vm_area_struct * vma_tmp;

				vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);

				if (vma_tmp->vm_end > addr) {
					vma = vma_tmp;
					if (vma_tmp->vm_start <= addr)
						break;
					rb_node = rb_node->rb_left;
				} else
					rb_node = rb_node->rb_right;
			}
			if (vma)
				mm->mmap_cache = vma;
		}
	}
	return vma;
}

/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */
struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
				      struct vm_area_struct **pprev)
{
	if (mm) {
		/* Go through the RB tree quickly. */
		struct vm_area_struct * vma;
		rb_node_t * rb_node, * rb_last_right, * rb_prev;
		
		rb_node = mm->mm_rb.rb_node;
		rb_last_right = rb_prev = NULL;
		vma = NULL;

		while (rb_node) {
			struct vm_area_struct * vma_tmp;

			vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);

			if (vma_tmp->vm_end > addr) {
				vma = vma_tmp;
				rb_prev = rb_last_right;
				if (vma_tmp->vm_start <= addr)
					break;
				rb_node = rb_node->rb_left;
			} else {
				rb_last_right = rb_node;
				rb_node = rb_node->rb_right;
			}
		}
		if (vma) {
			if (vma->vm_rb.rb_left) {
				rb_prev = vma->vm_rb.rb_left;
				while (rb_prev->rb_right)
					rb_prev = rb_prev->rb_right;
			}
			*pprev = NULL;
			if (rb_prev)
				*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
			if ((rb_prev ? (*pprev)->vm_next : mm->mmap) != vma)
				BUG();
			return vma;
		}
	}
	*pprev = NULL;
	return NULL;
}

struct vm_area_struct * find_extend_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct * vma;
	unsigned long start;

	addr &= PAGE_MASK;
	vma = find_vma(mm,addr);
	if (!vma)
		return NULL;
	if (vma->vm_start <= addr)
		return vma;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		return NULL;
	start = vma->vm_start;
	if (expand_stack(vma, addr))
		return NULL;
	if (vma->vm_flags & VM_LOCKED) {
		make_pages_present(addr, start);
	}
	return vma;
}

/* Normal function to fix up a mapping
 * This function is the default for when an area has no specific
 * function.  This may be used as part of a more specific routine.
 * This function works out what part of an area is affected and
 * adjusts the mapping information.  Since the actual page
 * manipulation is done in do_mmap(), none need be done here,
 * though it would probably be more appropriate.
 *
 * By the time this function is called, the area struct has been
 * removed from the process mapping list, so it needs to be
 * reinserted if necessary.
 *
 * The 4 main cases are:
 *    Unmapping the whole area
 *    Unmapping from the start of the segment to a point in it
 *    Unmapping from an intermediate point to the end
 *    Unmapping between to intermediate points, making a hole.
 *
 * Case 4 involves the creation of 2 new areas, for each side of
 * the hole.  If possible, we reuse the existing area rather than
 * allocate a new one, and the return indicates whether the old
 * area was reused.
 */
static struct vm_area_struct * unmap_fixup(struct mm_struct *mm, 
	struct vm_area_struct *area, unsigned long addr, size_t len, 
	struct vm_area_struct *extra)
{
	struct vm_area_struct *mpnt;
	unsigned long end = addr + len;

	area->vm_mm->total_vm -= len >> PAGE_SHIFT;
	if (area->vm_flags & VM_LOCKED)
		area->vm_mm->locked_vm -= len >> PAGE_SHIFT;

	/* Unmapping the whole area. */
	if (addr == area->vm_start && end == area->vm_end) {
		if (area->vm_ops && area->vm_ops->close)
			area->vm_ops->close(area);
		if (area->vm_file)
			fput(area->vm_file);
		kmem_cache_free(vm_area_cachep, area);
		return extra;
	}

	/* Work out to one of the ends. */
	if (end == area->vm_end) {
		/*
		 * here area isn't visible to the semaphore-less readers
		 * so we don't need to update it under the spinlock.
		 */
		area->vm_end = addr;
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
	} else if (addr == area->vm_start) {
		area->vm_pgoff += (end - area->vm_start) >> PAGE_SHIFT;
		/* same locking considerations of the above case */
		area->vm_start = end;
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
	} else {
	/* Unmapping a hole: area->vm_start < addr <= end < area->vm_end */
		/* Add end mapping -- leave beginning for below */
		mpnt = extra;
		extra = NULL;

		mpnt->vm_mm = area->vm_mm;
		mpnt->vm_start = end;
		mpnt->vm_end = area->vm_end;
		mpnt->vm_page_prot = area->vm_page_prot;
		mpnt->vm_flags = area->vm_flags;
		mpnt->vm_raend = 0;
		mpnt->vm_ops = area->vm_ops;
		mpnt->vm_pgoff = area->vm_pgoff + ((end - area->vm_start) >> PAGE_SHIFT);
		mpnt->vm_file = area->vm_file;
		mpnt->vm_private_data = area->vm_private_data;
		if (mpnt->vm_file)
			get_file(mpnt->vm_file);
		if (mpnt->vm_ops && mpnt->vm_ops->open)
			mpnt->vm_ops->open(mpnt);
		area->vm_end = addr;	/* Truncate area */

		/* Because mpnt->vm_file == area->vm_file this locks
		 * things correctly.
		 */
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
		__insert_vm_struct(mm, mpnt);
	}

	__insert_vm_struct(mm, area);
	spin_unlock(&mm->page_table_lock);
	unlock_vma_mappings(area);
	return extra;
}

/*
 * Try to free as many page directory entries as we can,
 * without having to work very hard at actually scanning
 * the page tables themselves.
 *
 * Right now we try to free page tables if we have a nice
 * PGDIR-aligned area that got free'd up. We could be more
 * granular if we want to, but this is fast and simple,
 * and covers the bad cases.
 *
 * "prev", if it exists, points to a vma before the one
 * we just free'd - but there's no telling how much before.
 */
static void free_pgtables(struct mm_struct * mm, struct vm_area_struct *prev,
	unsigned long start, unsigned long end)
{
	unsigned long first = start & PGDIR_MASK;
	unsigned long last = end + PGDIR_SIZE - 1;
	unsigned long start_index, end_index;

	if (!prev) {
		prev = mm->mmap;
		if (!prev)
			goto no_mmaps;
		if (prev->vm_end > start) {
			if (last > prev->vm_start)
				last = prev->vm_start;
			goto no_mmaps;
		}
	}
	for (;;) {
		struct vm_area_struct *next = prev->vm_next;

		if (next) {
			if (next->vm_start < start) {
				prev = next;
				continue;
			}
			if (last > next->vm_start)
				last = next->vm_start;
		}
		if (prev->vm_end > first)
			first = prev->vm_end + PGDIR_SIZE - 1;
		break;
	}
no_mmaps:
	/*
	 * If the PGD bits are not consecutive in the virtual address, the
	 * old method of shifting the VA >> by PGDIR_SHIFT doesn't work.
	 */
	start_index = pgd_index(first);
	end_index = pgd_index(last);
	if (end_index > start_index) {
		clear_page_tables(mm, start_index, end_index - start_index);
		flush_tlb_pgtables(mm, first & PGDIR_MASK, last & PGDIR_MASK);
	}
}

/* Munmap is split into 2 main parts -- this part which finds
 * what needs doing, and the areas themselves, which do the
 * work.  This now handles partial unmappings.
 * Jeremy Fitzhardine <jeremy@sw.oz.au>
 */
int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
{
	struct vm_area_struct *mpnt, *prev, **npp, *free, *extra;

	if ((addr & ~PAGE_MASK) || addr > TASK_SIZE || len > TASK_SIZE-addr)
		return -EINVAL;

	if ((len = PAGE_ALIGN(len)) == 0)
		return -EINVAL;

	/* Check if this memory area is ok - put it on the temporary
	 * list if so..  The checks here are pretty simple --
	 * every area affected in some way (by any overlap) is put
	 * on the list.  If nothing is put on, nothing is affected.
	 */
	mpnt = find_vma_prev(mm, addr, &prev);
	if (!mpnt)
		return 0;
	/* we have  addr < mpnt->vm_end  */

	if (mpnt->vm_start >= addr+len)
		return 0;

	/* If we'll make "hole", check the vm areas limit */
	if ((mpnt->vm_start < addr && mpnt->vm_end > addr+len)
	    && mm->map_count >= max_map_count)
		return -ENOMEM;

	/*
	 * We may need one additional vma to fix up the mappings ... 
	 * and this is the last chance for an easy error exit.
	 */
	extra = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!extra)
		return -ENOMEM;

	npp = (prev ? &prev->vm_next : &mm->mmap);
	free = NULL;
	spin_lock(&mm->page_table_lock);
	for ( ; mpnt && mpnt->vm_start < addr+len; mpnt = *npp) {
		*npp = mpnt->vm_next;
		mpnt->vm_next = free;
		free = mpnt;
		rb_erase(&mpnt->vm_rb, &mm->mm_rb);
	}
	mm->mmap_cache = NULL;	/* Kill the cache. */
	spin_unlock(&mm->page_table_lock);

	/* Ok - we have the memory areas we should free on the 'free' list,
	 * so release them, and unmap the page range..
	 * If the one of the segments is only being partially unmapped,
	 * it will put new vm_area_struct(s) into the address space.
	 * In that case we have to be careful with VM_DENYWRITE.
	 */
	while ((mpnt = free) != NULL) {
		unsigned long st, end, size;
		struct file *file = NULL;

		free = free->vm_next;

		st = addr < mpnt->vm_start ? mpnt->vm_start : addr;
		end = addr+len;
		end = end > mpnt->vm_end ? mpnt->vm_end : end;
		size = end - st;

		if (mpnt->vm_flags & VM_DENYWRITE &&
		    (st != mpnt->vm_start || end != mpnt->vm_end) &&
		    (file = mpnt->vm_file) != NULL) {
			atomic_dec(&file->f_dentry->d_inode->i_writecount);
		}
		remove_shared_vm_struct(mpnt);
		mm->map_count--;

		zap_page_range(mm, st, size);

		/*
		 * Fix the mapping, and free the old area if it wasn't reused.
		 */
		extra = unmap_fixup(mm, mpnt, st, size, extra);
		if (file)
			atomic_inc(&file->f_dentry->d_inode->i_writecount);
	}
	validate_mm(mm);

	/* Release the extra vma struct if it wasn't used */
	if (extra)
		kmem_cache_free(vm_area_cachep, extra);

	free_pgtables(mm, prev, addr, addr+len);

	return 0;
}

asmlinkage long sys_munmap(unsigned long addr, size_t len)
{
	int ret;
	struct mm_struct *mm = current->mm;

	down_write(&mm->mmap_sem);
	ret = do_munmap(mm, addr, len);
	up_write(&mm->mmap_sem);
	return ret;
}

/*
 *  this is really a simplified "do_mmap".  it only handles
 *  anonymous maps.  eventually we may be able to do some
 *  brk-specific accounting here.
 */
unsigned long do_brk(unsigned long addr, unsigned long len)
{
	struct mm_struct * mm = current->mm;
	struct vm_area_struct * vma, * prev;
	unsigned long flags;
	rb_node_t ** rb_link, * rb_parent;

	len = PAGE_ALIGN(len);
	if (!len)
		return addr;

	/*
	 * mlock MCL_FUTURE?
	 */
	if (mm->def_flags & VM_LOCKED) {
		unsigned long locked = mm->locked_vm << PAGE_SHIFT;
		locked += len;
		if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
			return -EAGAIN;
	}

	/*
	 * Clear old maps.  this also does some error checking for us
	 */
 munmap_back:
	vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	if (vma && vma->vm_start < addr + len) {
		if (do_munmap(mm, addr, len))
			return -ENOMEM;
		goto munmap_back;
	}

	/* Check against address space limits *after* clearing old maps... */
	if ((mm->total_vm << PAGE_SHIFT) + len
	    > current->rlim[RLIMIT_AS].rlim_cur)
		return -ENOMEM;

	if (mm->map_count > max_map_count)
		return -ENOMEM;

	if (!vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	flags = VM_DATA_DEFAULT_FLAGS | mm->def_flags;

	/* Can we just expand an old anonymous mapping? */
	if (rb_parent && vma_merge(mm, prev, rb_parent, addr, addr + len, flags))
		goto out;

	/*
	 * create a vma struct for an anonymous mapping
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!vma)
		return -ENOMEM;

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = flags;
	vma->vm_page_prot = protection_map[flags & 0x0f];
	vma->vm_ops = NULL;
	vma->vm_pgoff = 0;
	vma->vm_file = NULL;
	vma->vm_private_data = NULL;

	vma_link(mm, vma, prev, rb_link, rb_parent);

out:
	mm->total_vm += len >> PAGE_SHIFT;
	if (flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	return addr;
}

/* Build the RB tree corresponding to the VMA list. */
void build_mmap_rb(struct mm_struct * mm)
{
	struct vm_area_struct * vma;
	rb_node_t ** rb_link, * rb_parent;

	mm->mm_rb = RB_ROOT;
	rb_link = &mm->mm_rb.rb_node;
	rb_parent = NULL;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		__vma_link_rb(mm, vma, rb_link, rb_parent);
		rb_parent = &vma->vm_rb;
		rb_link = &rb_parent->rb_right;
	}
}

/* Release all mmaps. */
void exit_mmap(struct mm_struct * mm)
{
	struct vm_area_struct * mpnt;

	release_segments(mm);
	spin_lock(&mm->page_table_lock);
	mpnt = mm->mmap;
	mm->mmap = mm->mmap_cache = NULL;
	mm->mm_rb = RB_ROOT;
	mm->rss = 0;
	spin_unlock(&mm->page_table_lock);
	mm->total_vm = 0;
	mm->locked_vm = 0;

	flush_cache_mm(mm);
	while (mpnt) {
		struct vm_area_struct * next = mpnt->vm_next;
		unsigned long start = mpnt->vm_start;
		unsigned long end = mpnt->vm_end;
		unsigned long size = end - start;

		if (mpnt->vm_ops) {
			if (mpnt->vm_ops->close)
				mpnt->vm_ops->close(mpnt);
		}
		mm->map_count--;
		remove_shared_vm_struct(mpnt);
		zap_page_range(mm, start, size);
		if (mpnt->vm_file)
			fput(mpnt->vm_file);
		kmem_cache_free(vm_area_cachep, mpnt);
		mpnt = next;
	}

	/* This is just debugging */
	if (mm->map_count)
		BUG();

	clear_page_tables(mm, FIRST_USER_PGD_NR, USER_PTRS_PER_PGD);

	flush_tlb_mm(mm);
}

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap ring.  If vm_file is non-NULL
 * then the i_shared_lock must be held here.
 */
void __insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	rb_node_t ** rb_link, * rb_parent;

	__vma = find_vma_prepare(mm, vma->vm_start, &prev, &rb_link, &rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		BUG();
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	mm->map_count++;
	validate_mm(mm);
}

void insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	rb_node_t ** rb_link, * rb_parent;

	__vma = find_vma_prepare(mm, vma->vm_start, &prev, &rb_link, &rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		BUG();
	vma_link(mm, vma, prev, rb_link, rb_parent);
	validate_mm(mm);
}

#else /* NO_MM */

unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
	if (flags & MAP_FIXED) {
		if (addr > TASK_SIZE - len)
			return -EINVAL;
		if (addr & ~PAGE_MASK)
			return -EINVAL;
		return addr;
	}

	if (file && file->f_op && file->f_op->get_unmapped_area)
		return file->f_op->get_unmapped_area(file, addr, len, pgoff, flags);

	return 0;
}

#ifdef DEBUG
static void show_process_blocks(void)
{
	struct mm_tblock_struct * tblock, *tmp;
	
	printk("Process blocks %d:", current->pid);
	
	tmp = &current->mm->tblock;
	while (tmp) {
		printk(" %p: %p", tmp, tmp->rblock);
		if (tmp->rblock)
			printk(" (%d @%p #%d)", ksize(tmp->rblock->kblock), tmp->rblock->kblock, tmp->rblock->refcount);
		if (tmp->next)
			printk(" ->");
		else
			printk(".");
		tmp = tmp->next;
	}
	printk("\n");
}
#endif /* DEBUG */

extern unsigned long askedalloc, realalloc;

unsigned long do_mmap_pgoff(
	struct file * file,
	unsigned long addr,
	unsigned long len,
	unsigned long prot,
	unsigned long flags,
	unsigned long pgoff)
{
	void * result;
#if 0
	struct mm_struct * mm = current->mm;
#endif
	struct mm_tblock_struct * tblock;
	unsigned int vm_flags;

	/*
	 * Get the NO_MM specific checks done first
	 */
	if ((flags & MAP_SHARED) && (prot & PROT_WRITE) && (file)) {
		printk("MAP_SHARED not supported (cannot write mappings to disk)\n");
		return -EINVAL;
	}
	
	if ((prot & PROT_WRITE) && (flags & MAP_PRIVATE)) {
		printk("Private writable mappings not supported\n");
		return -EINVAL;
	}
	
	/*
	 *	now all the standard checks
	 */
	if (file && (!file->f_op || !file->f_op->mmap))
		return -ENODEV;

	if (PAGE_ALIGN(len) == 0)
		return addr;

	if (len > TASK_SIZE)
		return -EINVAL;

	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
		return -EINVAL;

#if 0
	/* Too many mappings? */
	if (mm->map_count > MAX_MAP_COUNT)
		return -ENOMEM;
#endif

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	if (addr & ~PAGE_MASK)
		return addr;

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	vm_flags = calc_vm_flags(prot,flags) /* | mm->def_flags */ | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

#if 0
	/* mlock MCL_FUTURE? */
	if (vm_flags & VM_LOCKED) {
		unsigned long locked = mm->locked_vm << PAGE_SHIFT;
		locked += len;
		if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
			return -EAGAIN;
	}
#endif

	/*
	 * determine the object being mapped and call the appropriate
	 * specific mapper. 
	 */

	if (file) {
		struct vm_area_struct vma;
		int error;
		
		
		if (!file->f_op)
			return -ENODEV;

		vma.vm_start = addr;
		vma.vm_end = addr + len;
		vma.vm_flags = vm_flags;
		vma.vm_offset = pgoff << PAGE_SHIFT;

#ifdef MAGIC_ROM_PTR
		/* First, try simpler routine designed to give us a ROM pointer. */

		if (file->f_op->romptr && !(prot & PROT_WRITE)) {
			error = file->f_op->romptr(file, &vma);
#ifdef DEBUG
			printk("romptr mmap returned %d, start 0x%.8x\n", error,
					vma.vm_start);
#endif
			if (!error)
				return vma.vm_start;
			else if (error != -ENOSYS)
				return error;
		} else
#endif /* MAGIC_ROM_PTR */
		/* Then try full mmap routine, which might return a RAM pointer,
		   or do something truly complicated. */
		   
		if (file->f_op->mmap) {
			error = file->f_op->mmap(file, &vma);
				   
#ifdef DEBUG
			printk("mmap mmap returned %d /%x\n", error, vma.vm_start);
#endif
			if (!error)
				return vma.vm_start;
			else if (error != -ENOSYS)
				return error;
		} else
			return -ENODEV; /* No mapping operations defined */

		/* An ENOSYS error indicates that mmap isn't possible (as opposed to
		   tried but failed) so we'll fall through to the copy. */
	}

	tblock = (struct mm_tblock_struct *)
                        kmalloc(sizeof(struct mm_tblock_struct), GFP_KERNEL);
	if (!tblock) {
		printk("Allocation of tblock for %lu byte allocation from process %d failed\n", len, current->pid);
		show_buffers();
		show_free_areas();
		return -ENOMEM;
	}

	tblock->rblock = (struct mm_rblock_struct *)
			kmalloc(sizeof(struct mm_rblock_struct), GFP_KERNEL);

	if (!tblock->rblock) {
		printk("Allocation of rblock for %lu byte allocation from process %d failed\n", len, current->pid);
		show_buffers();
		show_free_areas();
		kfree(tblock);
		return -ENOMEM;
	}

	
	result = kmalloc(len, GFP_KERNEL);
	if (!result) {
		printk("Allocation of length %lu from process %d failed\n", len,
				current->pid);
		show_buffers();
		show_free_areas();
		kfree(tblock->rblock);
		kfree(tblock);
		return -ENOMEM;
	}

	tblock->rblock->refcount = 1;
	tblock->rblock->kblock = result;
	tblock->rblock->size = len;
	
	realalloc += ksize(result);
	askedalloc += len;

#ifdef WARN_ON_SLACK	
	if ((len+WARN_ON_SLACK) <= ksize(result))
		printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n", len, current->pid, ksize(result)-len);
#endif
	
	if (file) {
		int error;
		mm_segment_t old_fs = get_fs();
		set_fs(KERNEL_DS);
		error = file->f_op->read(file, (char *) result, len, &file->f_pos);
		set_fs(old_fs);
		if (error < 0) {
			kfree(result);
			kfree(tblock->rblock);
			kfree(tblock);
			return error;
		}
		if (error<len)
			memset(result+error, '\0', len-error);
	} else {
		memset(result, '\0', len);
	}

        
	realalloc += ksize(tblock);
	askedalloc += sizeof(struct mm_tblock_struct);

	realalloc += ksize(tblock->rblock);
	askedalloc += sizeof(struct mm_rblock_struct);

	tblock->next = current->mm->tblock.next;
	current->mm->tblock.next = tblock;

#ifdef DEBUG
	printk("do_mmap:\n");
	show_process_blocks();
#endif	  

	return (unsigned long)result;
}

int do_munmap(struct mm_struct * mm, unsigned long addr, size_t len)
{
	struct mm_tblock_struct * tblock, *tmp;

#ifdef MAGIC_ROM_PTR
	/* For efficiency's sake, if the pointer is obviously in ROM,
	   don't bother walking the lists to free it */
	if (is_in_rom(addr))
		return 0;
#endif

#ifdef DEBUG
	printk("do_munmap:\n");
#endif

	tmp = &mm->tblock; /* dummy head */
	while ((tblock=tmp->next) && tblock->rblock &&
			tblock->rblock->kblock != (void*)addr) 
		tmp = tblock;
		
	if (!tblock) {
		printk("munmap of non-mmaped memory by process %d (%s): %p\n",
				current->pid, current->comm, (void*)addr);
		return -EINVAL;
	}
	if (tblock->rblock) {
		if (!--tblock->rblock->refcount) {
			if (tblock->rblock->kblock) {
				realalloc -= ksize(tblock->rblock->kblock);
				askedalloc -= tblock->rblock->size;
				kfree(tblock->rblock->kblock);
			}
			
			realalloc -= ksize(tblock->rblock);
			askedalloc -= sizeof(struct mm_rblock_struct);
			kfree(tblock->rblock);
		}
	}
	tmp->next = tblock->next;
	realalloc -= ksize(tblock);
	askedalloc -= sizeof(struct mm_tblock_struct);
	kfree(tblock);

#ifdef DEBUG
	show_process_blocks();
#endif	  

	return 0;
}

/* Release all mmaps. */
void exit_mmap(struct mm_struct * mm)
{
	struct mm_tblock_struct *tmp;

	if (!mm)
		return;

#ifdef DEBUG
	printk("Exit_mmap:\n");
#endif

	while((tmp = mm->tblock.next)) {
		if (tmp->rblock) {
			if (!--tmp->rblock->refcount) {
				if (tmp->rblock->kblock) {
					realalloc -= ksize(tmp->rblock->kblock);
					askedalloc -= tmp->rblock->size;
					kfree(tmp->rblock->kblock);
				}
				realalloc -= ksize(tmp->rblock);
				askedalloc -= sizeof(struct mm_rblock_struct);
				kfree(tmp->rblock);
			}
			tmp->rblock = 0;
		}
		mm->tblock.next = tmp->next;
		realalloc -= ksize(tmp);
		askedalloc -= sizeof(struct mm_tblock_struct);
		kfree(tmp);
	}

#ifdef DEBUG
	show_process_blocks();
#endif	  
}

asmlinkage long sys_munmap(unsigned long addr, size_t len)
{
	int ret;
	struct mm_struct *mm = current->mm;

	down_write(&mm->mmap_sem);
	ret = do_munmap(mm, addr, len);
	up_write(&mm->mmap_sem);
	return ret;
}

#endif /* NO_MM */