aboutsummaryrefslogtreecommitdiff
path: root/sys/vm/vm_page.c
blob: 05123473f7645634ff11dd84316d1ac165cbaca8 (plain) (blame)
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
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
/*-
 * Copyright (c) 1991 Regents of the University of California.
 * All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * The Mach Operating System project at Carnegie-Mellon University.
 *
 * 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.
 * 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: @(#)vm_page.c	7.4 (Berkeley) 5/7/91
 */

/*-
 * Copyright (c) 1987, 1990 Carnegie-Mellon University.
 * All rights reserved.
 *
 * Authors: Avadis Tevanian, Jr., Michael Wayne Young
 *
 * Permission to use, copy, modify and distribute this software and
 * its documentation is hereby granted, provided that both the copyright
 * notice and this permission notice appear in all copies of the
 * software, derivative works or modified versions, and any portions
 * thereof, and that both notices appear in supporting documentation.
 *
 * CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
 * CONDITION.  CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND
 * FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
 *
 * Carnegie Mellon requests users of this software to return to
 *
 *  Software Distribution Coordinator  or  Software.Distribution@CS.CMU.EDU
 *  School of Computer Science
 *  Carnegie Mellon University
 *  Pittsburgh PA 15213-3890
 *
 * any improvements or extensions that they make and grant Carnegie the
 * rights to redistribute these changes.
 */

/*
 *			GENERAL RULES ON VM_PAGE MANIPULATION
 *
 *	- a pageq mutex is required when adding or removing a page from a
 *	  page queue (vm_page_queue[]), regardless of other mutexes or the
 *	  busy state of a page.
 *
 *	- a hash chain mutex is required when associating or disassociating
 *	  a page from the VM PAGE CACHE hash table (vm_page_buckets),
 *	  regardless of other mutexes or the busy state of a page.
 *
 *	- either a hash chain mutex OR a busied page is required in order
 *	  to modify the page flags.  A hash chain mutex must be obtained in
 *	  order to busy a page.  A page's flags cannot be modified by a
 *	  hash chain mutex if the page is marked busy.
 *
 *	- The object memq mutex is held when inserting or removing
 *	  pages from an object (vm_page_insert() or vm_page_remove()).  This
 *	  is different from the object's main mutex.
 *
 *	Generally speaking, you have to be aware of side effects when running
 *	vm_page ops.  A vm_page_lookup() will return with the hash chain
 *	locked, whether it was able to lookup the page or not.  vm_page_free(),
 *	vm_page_cache(), vm_page_activate(), and a number of other routines
 *	will release the hash chain mutex for you.  Intermediate manipulation
 *	routines such as vm_page_flag_set() expect the hash chain to be held
 *	on entry and the hash chain will remain held on return.
 *
 *	pageq scanning can only occur with the pageq in question locked.
 *	We have a known bottleneck with the active queue, but the cache
 *	and free queues are actually arrays already. 
 */

/*
 *	Resident memory management module.
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/lock.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/sysctl.h>
#include <sys/vmmeter.h>
#include <sys/vnode.h>

#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_kern.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_pageout.h>
#include <vm/vm_pager.h>
#include <vm/vm_extern.h>
#include <vm/uma.h>
#include <vm/uma_int.h>

#include <machine/md_var.h>

/*
 *	Associated with page of user-allocatable memory is a
 *	page structure.
 */

struct mtx vm_page_queue_mtx;
struct mtx vm_page_queue_free_mtx;

vm_page_t vm_page_array = 0;
int vm_page_array_size = 0;
long first_page = 0;
int vm_page_zero_count = 0;

static int boot_pages = UMA_BOOT_PAGES;
TUNABLE_INT("vm.boot_pages", &boot_pages);
SYSCTL_INT(_vm, OID_AUTO, boot_pages, CTLFLAG_RD, &boot_pages, 0,
	"number of pages allocated for bootstrapping the VM system");

/*
 *	vm_set_page_size:
 *
 *	Sets the page size, perhaps based upon the memory
 *	size.  Must be called before any use of page-size
 *	dependent functions.
 */
void
vm_set_page_size(void)
{
	if (cnt.v_page_size == 0)
		cnt.v_page_size = PAGE_SIZE;
	if (((cnt.v_page_size - 1) & cnt.v_page_size) != 0)
		panic("vm_set_page_size: page size not a power of two");
}

/*
 *	vm_page_startup:
 *
 *	Initializes the resident memory module.
 *
 *	Allocates memory for the page cells, and
 *	for the object/offset-to-page hash table headers.
 *	Each page cell is initialized and placed on the free list.
 */
vm_offset_t
vm_page_startup(vm_offset_t vaddr)
{
	vm_offset_t mapped;
	vm_size_t npages;
	vm_paddr_t page_range;
	vm_paddr_t new_end;
	int i;
	vm_paddr_t pa;
	int nblocks;
	vm_paddr_t last_pa;

	/* the biggest memory array is the second group of pages */
	vm_paddr_t end;
	vm_paddr_t biggestsize;
	int biggestone;

	vm_paddr_t total;

	total = 0;
	biggestsize = 0;
	biggestone = 0;
	nblocks = 0;
	vaddr = round_page(vaddr);

	for (i = 0; phys_avail[i + 1]; i += 2) {
		phys_avail[i] = round_page(phys_avail[i]);
		phys_avail[i + 1] = trunc_page(phys_avail[i + 1]);
	}

	for (i = 0; phys_avail[i + 1]; i += 2) {
		vm_paddr_t size = phys_avail[i + 1] - phys_avail[i];

		if (size > biggestsize) {
			biggestone = i;
			biggestsize = size;
		}
		++nblocks;
		total += size;
	}

	end = phys_avail[biggestone+1];

	/*
	 * Initialize the locks.
	 */
	mtx_init(&vm_page_queue_mtx, "vm page queue mutex", NULL, MTX_DEF |
	    MTX_RECURSE);
	mtx_init(&vm_page_queue_free_mtx, "vm page queue free mutex", NULL,
	    MTX_SPIN);

	/*
	 * Initialize the queue headers for the free queue, the active queue
	 * and the inactive queue.
	 */
	vm_pageq_init();

	/*
	 * Allocate memory for use when boot strapping the kernel memory
	 * allocator.
	 */
	new_end = end - (boot_pages * UMA_SLAB_SIZE);
	new_end = trunc_page(new_end);
	mapped = pmap_map(&vaddr, new_end, end,
	    VM_PROT_READ | VM_PROT_WRITE);
	bzero((void *)mapped, end - new_end);
	uma_startup((void *)mapped, boot_pages);

#if defined(__amd64__) || defined(__i386__)
	/*
	 * Allocate a bitmap to indicate that a random physical page
	 * needs to be included in a minidump.
	 *
	 * The amd64 port needs this to indicate which direct map pages
	 * need to be dumped, via calls to dump_add_page()/dump_drop_page().
	 *
	 * However, i386 still needs this workspace internally within the
	 * minidump code.  In theory, they are not needed on i386, but are
	 * included should the sf_buf code decide to use them.
	 */
	page_range = phys_avail[(nblocks - 1) * 2 + 1] / PAGE_SIZE;
	vm_page_dump_size = round_page(roundup2(page_range, NBBY) / NBBY);
	new_end -= vm_page_dump_size;
	vm_page_dump = (void *)(uintptr_t)pmap_map(&vaddr, new_end,
	    new_end + vm_page_dump_size, VM_PROT_READ | VM_PROT_WRITE);
	bzero((void *)vm_page_dump, vm_page_dump_size);
#endif
	/*
	 * Compute the number of pages of memory that will be available for
	 * use (taking into account the overhead of a page structure per
	 * page).
	 */
	first_page = phys_avail[0] / PAGE_SIZE;
	page_range = phys_avail[(nblocks - 1) * 2 + 1] / PAGE_SIZE - first_page;
	npages = (total - (page_range * sizeof(struct vm_page)) -
	    (end - new_end)) / PAGE_SIZE;
	end = new_end;

	/*
	 * Reserve an unmapped guard page to trap access to vm_page_array[-1].
	 */
	vaddr += PAGE_SIZE;

	/*
	 * Initialize the mem entry structures now, and put them in the free
	 * queue.
	 */
	new_end = trunc_page(end - page_range * sizeof(struct vm_page));
	mapped = pmap_map(&vaddr, new_end, end,
	    VM_PROT_READ | VM_PROT_WRITE);
	vm_page_array = (vm_page_t) mapped;
	phys_avail[biggestone + 1] = new_end;

	/*
	 * Clear all of the page structures
	 */
	bzero((caddr_t) vm_page_array, page_range * sizeof(struct vm_page));
	vm_page_array_size = page_range;

	/*
	 * Construct the free queue(s) in descending order (by physical
	 * address) so that the first 16MB of physical memory is allocated
	 * last rather than first.  On large-memory machines, this avoids
	 * the exhaustion of low physical memory before isa_dma_init has run.
	 */
	cnt.v_page_count = 0;
	cnt.v_free_count = 0;
	for (i = 0; phys_avail[i + 1] && npages > 0; i += 2) {
		pa = phys_avail[i];
		last_pa = phys_avail[i + 1];
		while (pa < last_pa && npages-- > 0) {
			vm_pageq_add_new_page(pa);
			pa += PAGE_SIZE;
		}
	}
	return (vaddr);
}

void
vm_page_flag_set(vm_page_t m, unsigned short bits)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	m->flags |= bits;
} 

void
vm_page_flag_clear(vm_page_t m, unsigned short bits)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	m->flags &= ~bits;
}

void
vm_page_busy(vm_page_t m)
{

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	KASSERT((m->flags & PG_BUSY) == 0,
	    ("vm_page_busy: page already busy!!!"));
	vm_page_flag_set(m, PG_BUSY);
}

/*
 *      vm_page_flash:
 *
 *      wakeup anyone waiting for the page.
 */
void
vm_page_flash(vm_page_t m)
{

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if (m->flags & PG_WANTED) {
		vm_page_flag_clear(m, PG_WANTED);
		wakeup(m);
	}
}

/*
 *      vm_page_wakeup:
 *
 *      clear the PG_BUSY flag and wakeup anyone waiting for the
 *      page.
 *
 */
void
vm_page_wakeup(vm_page_t m)
{

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	KASSERT(m->flags & PG_BUSY, ("vm_page_wakeup: page not busy!!!"));
	vm_page_flag_clear(m, PG_BUSY);
	vm_page_flash(m);
}

void
vm_page_io_start(vm_page_t m)
{

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	m->busy++;
}

void
vm_page_io_finish(vm_page_t m)
{

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	m->busy--;
	if (m->busy == 0)
		vm_page_flash(m);
}

/*
 * Keep page from being freed by the page daemon
 * much of the same effect as wiring, except much lower
 * overhead and should be used only for *very* temporary
 * holding ("wiring").
 */
void
vm_page_hold(vm_page_t mem)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
        mem->hold_count++;
}

void
vm_page_unhold(vm_page_t mem)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	--mem->hold_count;
	KASSERT(mem->hold_count >= 0, ("vm_page_unhold: hold count < 0!!!"));
	if (mem->hold_count == 0 && VM_PAGE_INQUEUE2(mem, PQ_HOLD))
		vm_page_free_toq(mem);
}

/*
 *	vm_page_free:
 *
 *	Free a page
 *
 *	The clearing of PG_ZERO is a temporary safety until the code can be
 *	reviewed to determine that PG_ZERO is being properly cleared on
 *	write faults or maps.  PG_ZERO was previously cleared in
 *	vm_page_alloc().
 */
void
vm_page_free(vm_page_t m)
{
	vm_page_flag_clear(m, PG_ZERO);
	vm_page_free_toq(m);
	vm_page_zero_idle_wakeup();
}

/*
 *	vm_page_free_zero:
 *
 *	Free a page to the zerod-pages queue
 */
void
vm_page_free_zero(vm_page_t m)
{
	vm_page_flag_set(m, PG_ZERO);
	vm_page_free_toq(m);
}

/*
 *	vm_page_sleep_if_busy:
 *
 *	Sleep and release the page queues lock if PG_BUSY is set or,
 *	if also_m_busy is TRUE, busy is non-zero.  Returns TRUE if the
 *	thread slept and the page queues lock was released.
 *	Otherwise, retains the page queues lock and returns FALSE.
 */
int
vm_page_sleep_if_busy(vm_page_t m, int also_m_busy, const char *msg)
{
	vm_object_t object;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if ((m->flags & PG_BUSY) || (also_m_busy && m->busy)) {
		vm_page_flag_set(m, PG_WANTED | PG_REFERENCED);
		/*
		 * It's possible that while we sleep, the page will get
		 * unbusied and freed.  If we are holding the object
		 * lock, we will assume we hold a reference to the object
		 * such that even if m->object changes, we can re-lock
		 * it.
		 */
		object = m->object;
		VM_OBJECT_UNLOCK(object);
		msleep(m, &vm_page_queue_mtx, PDROP | PVM, msg, 0);
		VM_OBJECT_LOCK(object);
		return (TRUE);
	}
	return (FALSE);
}

/*
 *	vm_page_dirty:
 *
 *	make page all dirty
 */
void
vm_page_dirty(vm_page_t m)
{
	KASSERT(VM_PAGE_GETKNOWNQUEUE1(m) != PQ_CACHE,
	    ("vm_page_dirty: page in cache!"));
	KASSERT(VM_PAGE_GETKNOWNQUEUE1(m) != PQ_FREE,
	    ("vm_page_dirty: page is free!"));
	m->dirty = VM_PAGE_BITS_ALL;
}

/*
 *	vm_page_splay:
 *
 *	Implements Sleator and Tarjan's top-down splay algorithm.  Returns
 *	the vm_page containing the given pindex.  If, however, that
 *	pindex is not found in the vm_object, returns a vm_page that is
 *	adjacent to the pindex, coming before or after it.
 */
vm_page_t
vm_page_splay(vm_pindex_t pindex, vm_page_t root)
{
	struct vm_page dummy;
	vm_page_t lefttreemax, righttreemin, y;

	if (root == NULL)
		return (root);
	lefttreemax = righttreemin = &dummy;
	for (;; root = y) {
		if (pindex < root->pindex) {
			if ((y = root->left) == NULL)
				break;
			if (pindex < y->pindex) {
				/* Rotate right. */
				root->left = y->right;
				y->right = root;
				root = y;
				if ((y = root->left) == NULL)
					break;
			}
			/* Link into the new root's right tree. */
			righttreemin->left = root;
			righttreemin = root;
		} else if (pindex > root->pindex) {
			if ((y = root->right) == NULL)
				break;
			if (pindex > y->pindex) {
				/* Rotate left. */
				root->right = y->left;
				y->left = root;
				root = y;
				if ((y = root->right) == NULL)
					break;
			}
			/* Link into the new root's left tree. */
			lefttreemax->right = root;
			lefttreemax = root;
		} else
			break;
	}
	/* Assemble the new root. */
	lefttreemax->right = root->left;
	righttreemin->left = root->right;
	root->left = dummy.right;
	root->right = dummy.left;
	return (root);
}

/*
 *	vm_page_insert:		[ internal use only ]
 *
 *	Inserts the given mem entry into the object and object list.
 *
 *	The pagetables are not updated but will presumably fault the page
 *	in if necessary, or if a kernel page the caller will at some point
 *	enter the page into the kernel's pmap.  We are not allowed to block
 *	here so we *can't* do this anyway.
 *
 *	The object and page must be locked.
 *	This routine may not block.
 */
void
vm_page_insert(vm_page_t m, vm_object_t object, vm_pindex_t pindex)
{
	vm_page_t root;

	VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
	if (m->object != NULL)
		panic("vm_page_insert: page already inserted");

	/*
	 * Record the object/offset pair in this page
	 */
	m->object = object;
	m->pindex = pindex;

	/*
	 * Now link into the object's ordered list of backed pages.
	 */
	root = object->root;
	if (root == NULL) {
		m->left = NULL;
		m->right = NULL;
		TAILQ_INSERT_TAIL(&object->memq, m, listq);
	} else {
		root = vm_page_splay(pindex, root);
		if (pindex < root->pindex) {
			m->left = root->left;
			m->right = root;
			root->left = NULL;
			TAILQ_INSERT_BEFORE(root, m, listq);
		} else if (pindex == root->pindex)
			panic("vm_page_insert: offset already allocated");
		else {
			m->right = root->right;
			m->left = root;
			root->right = NULL;
			TAILQ_INSERT_AFTER(&object->memq, root, m, listq);
		}
	}
	object->root = m;
	object->generation++;

	/*
	 * show that the object has one more resident page.
	 */
	object->resident_page_count++;
	/*
	 * Hold the vnode until the last page is released.
	 */
	if (object->resident_page_count == 1 && object->type == OBJT_VNODE)
		vhold((struct vnode *)object->handle);

	/*
	 * Since we are inserting a new and possibly dirty page,
	 * update the object's OBJ_WRITEABLE and OBJ_MIGHTBEDIRTY flags.
	 */
	if (m->flags & PG_WRITEABLE)
		vm_object_set_writeable_dirty(object);
}

/*
 *	vm_page_remove:
 *				NOTE: used by device pager as well -wfj
 *
 *	Removes the given mem entry from the object/offset-page
 *	table and the object page list, but do not invalidate/terminate
 *	the backing store.
 *
 *	The object and page must be locked.
 *	The underlying pmap entry (if any) is NOT removed here.
 *	This routine may not block.
 */
void
vm_page_remove(vm_page_t m)
{
	vm_object_t object;
	vm_page_t root;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if ((object = m->object) == NULL)
		return;
	VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
	if (m->flags & PG_BUSY) {
		vm_page_flag_clear(m, PG_BUSY);
		vm_page_flash(m);
	}

	/*
	 * Now remove from the object's list of backed pages.
	 */
	if (m != object->root)
		vm_page_splay(m->pindex, object->root);
	if (m->left == NULL)
		root = m->right;
	else {
		root = vm_page_splay(m->pindex, m->left);
		root->right = m->right;
	}
	object->root = root;
	TAILQ_REMOVE(&object->memq, m, listq);

	/*
	 * And show that the object has one fewer resident page.
	 */
	object->resident_page_count--;
	object->generation++;
	/*
	 * The vnode may now be recycled.
	 */
	if (object->resident_page_count == 0 && object->type == OBJT_VNODE)
		vdrop((struct vnode *)object->handle);

	m->object = NULL;
}

/*
 *	vm_page_lookup:
 *
 *	Returns the page associated with the object/offset
 *	pair specified; if none is found, NULL is returned.
 *
 *	The object must be locked.
 *	This routine may not block.
 *	This is a critical path routine
 */
vm_page_t
vm_page_lookup(vm_object_t object, vm_pindex_t pindex)
{
	vm_page_t m;

	VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
	if ((m = object->root) != NULL && m->pindex != pindex) {
		m = vm_page_splay(pindex, m);
		if ((object->root = m)->pindex != pindex)
			m = NULL;
	}
	return (m);
}

/*
 *	vm_page_rename:
 *
 *	Move the given memory entry from its
 *	current object to the specified target object/offset.
 *
 *	The object must be locked.
 *	This routine may not block.
 *
 *	Note: swap associated with the page must be invalidated by the move.  We
 *	      have to do this for several reasons:  (1) we aren't freeing the
 *	      page, (2) we are dirtying the page, (3) the VM system is probably
 *	      moving the page from object A to B, and will then later move
 *	      the backing store from A to B and we can't have a conflict.
 *
 *	Note: we *always* dirty the page.  It is necessary both for the
 *	      fact that we moved it, and because we may be invalidating
 *	      swap.  If the page is on the cache, we have to deactivate it
 *	      or vm_page_dirty() will panic.  Dirty pages are not allowed
 *	      on the cache.
 */
void
vm_page_rename(vm_page_t m, vm_object_t new_object, vm_pindex_t new_pindex)
{

	vm_page_remove(m);
	vm_page_insert(m, new_object, new_pindex);
	if (VM_PAGE_INQUEUE1(m, PQ_CACHE))
		vm_page_deactivate(m);
	vm_page_dirty(m);
}

/*
 *	vm_page_select_cache:
 *
 *	Move a page of the given color from the cache queue to the free
 *	queue.  As pages might be found, but are not applicable, they are
 *	deactivated.
 *
 *	This routine may not block.
 */
vm_page_t
vm_page_select_cache(int color)
{
	vm_object_t object;
	vm_page_t m;
	boolean_t was_trylocked;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	while ((m = vm_pageq_find(PQ_CACHE, color, FALSE)) != NULL) {
		KASSERT(m->dirty == 0, ("Found dirty cache page %p", m));
		KASSERT(!pmap_page_is_mapped(m),
		    ("Found mapped cache page %p", m));
		KASSERT((m->flags & PG_UNMANAGED) == 0,
		    ("Found unmanaged cache page %p", m));
		KASSERT(m->wire_count == 0, ("Found wired cache page %p", m));
		if (m->hold_count == 0 && (object = m->object,
		    (was_trylocked = VM_OBJECT_TRYLOCK(object)) ||
		    VM_OBJECT_LOCKED(object))) {
			KASSERT((m->flags & PG_BUSY) == 0 && m->busy == 0,
			    ("Found busy cache page %p", m));
			vm_page_free(m);
			if (was_trylocked)
				VM_OBJECT_UNLOCK(object);
			break;
		}
		vm_page_deactivate(m);
	}
	return (m);
}

/*
 *	vm_page_alloc:
 *
 *	Allocate and return a memory cell associated
 *	with this VM object/offset pair.
 *
 *	page_req classes:
 *	VM_ALLOC_NORMAL		normal process request
 *	VM_ALLOC_SYSTEM		system *really* needs a page
 *	VM_ALLOC_INTERRUPT	interrupt time request
 *	VM_ALLOC_ZERO		zero page
 *
 *	This routine may not block.
 *
 *	Additional special handling is required when called from an
 *	interrupt (VM_ALLOC_INTERRUPT).  We are not allowed to mess with
 *	the page cache in this case.
 */
vm_page_t
vm_page_alloc(vm_object_t object, vm_pindex_t pindex, int req)
{
	vm_page_t m = NULL;
	int color, flags, page_req;

	page_req = req & VM_ALLOC_CLASS_MASK;
	KASSERT(curthread->td_intr_nesting_level == 0 ||
	    page_req == VM_ALLOC_INTERRUPT,
	    ("vm_page_alloc(NORMAL|SYSTEM) in interrupt context"));

	if ((req & VM_ALLOC_NOOBJ) == 0) {
		KASSERT(object != NULL,
		    ("vm_page_alloc: NULL object."));
		VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
		color = (pindex + object->pg_color) & PQ_COLORMASK;
	} else
		color = pindex & PQ_COLORMASK;

	/*
	 * The pager is allowed to eat deeper into the free page list.
	 */
	if ((curproc == pageproc) && (page_req != VM_ALLOC_INTERRUPT)) {
		page_req = VM_ALLOC_SYSTEM;
	};

loop:
	mtx_lock_spin(&vm_page_queue_free_mtx);
	if (cnt.v_free_count > cnt.v_free_reserved ||
	    (page_req == VM_ALLOC_SYSTEM && 
	     cnt.v_cache_count == 0 && 
	     cnt.v_free_count > cnt.v_interrupt_free_min) ||
	    (page_req == VM_ALLOC_INTERRUPT && cnt.v_free_count > 0)) {
		/*
		 * Allocate from the free queue if the number of free pages
		 * exceeds the minimum for the request class.
		 */
		m = vm_pageq_find(PQ_FREE, color, (req & VM_ALLOC_ZERO) != 0);
	} else if (page_req != VM_ALLOC_INTERRUPT) {
		mtx_unlock_spin(&vm_page_queue_free_mtx);
		/*
		 * Allocatable from cache (non-interrupt only).  On success,
		 * we must free the page and try again, thus ensuring that
		 * cnt.v_*_free_min counters are replenished.
		 */
		vm_page_lock_queues();
		if ((m = vm_page_select_cache(color)) == NULL) {
			KASSERT(cnt.v_cache_count == 0,
			    ("vm_page_alloc: cache queue is missing %d pages",
			    cnt.v_cache_count));
			vm_page_unlock_queues();
			atomic_add_int(&vm_pageout_deficit, 1);
			pagedaemon_wakeup();

			if (page_req != VM_ALLOC_SYSTEM) 
				return NULL;

			mtx_lock_spin(&vm_page_queue_free_mtx);
			if (cnt.v_free_count <=  cnt.v_interrupt_free_min) {
				mtx_unlock_spin(&vm_page_queue_free_mtx);
				return (NULL);
			}
			m = vm_pageq_find(PQ_FREE, color, (req & VM_ALLOC_ZERO) != 0);
		} else {
			vm_page_unlock_queues();
			goto loop;
		}
	} else {
		/*
		 * Not allocatable from cache from interrupt, give up.
		 */
		mtx_unlock_spin(&vm_page_queue_free_mtx);
		atomic_add_int(&vm_pageout_deficit, 1);
		pagedaemon_wakeup();
		return (NULL);
	}

	/*
	 *  At this point we had better have found a good page.
	 */

	KASSERT(
	    m != NULL,
	    ("vm_page_alloc(): missing page on free queue")
	);

	/*
	 * Remove from free queue
	 */
	vm_pageq_remove_nowakeup(m);

	/*
	 * Initialize structure.  Only the PG_ZERO flag is inherited.
	 */
	flags = PG_BUSY;
	if (m->flags & PG_ZERO) {
		vm_page_zero_count--;
		if (req & VM_ALLOC_ZERO)
			flags = PG_ZERO | PG_BUSY;
	}
	if (req & (VM_ALLOC_NOBUSY | VM_ALLOC_NOOBJ))
		flags &= ~PG_BUSY;
	m->flags = flags;
	if (req & VM_ALLOC_WIRED) {
		atomic_add_int(&cnt.v_wire_count, 1);
		m->wire_count = 1;
	} else
		m->wire_count = 0;
	m->hold_count = 0;
	m->act_count = 0;
	m->busy = 0;
	m->valid = 0;
	KASSERT(m->dirty == 0, ("vm_page_alloc: free/cache page %p was dirty", m));
	mtx_unlock_spin(&vm_page_queue_free_mtx);

	if ((req & VM_ALLOC_NOOBJ) == 0)
		vm_page_insert(m, object, pindex);
	else
		m->pindex = pindex;

	/*
	 * Don't wakeup too often - wakeup the pageout daemon when
	 * we would be nearly out of memory.
	 */
	if (vm_paging_needed())
		pagedaemon_wakeup();

	return (m);
}

/*
 *	vm_wait:	(also see VM_WAIT macro)
 *
 *	Block until free pages are available for allocation
 *	- Called in various places before memory allocations.
 */
void
vm_wait(void)
{

	vm_page_lock_queues();
	if (curproc == pageproc) {
		vm_pageout_pages_needed = 1;
		msleep(&vm_pageout_pages_needed, &vm_page_queue_mtx,
		    PDROP | PSWP, "VMWait", 0);
	} else {
		if (!vm_pages_needed) {
			vm_pages_needed = 1;
			wakeup(&vm_pages_needed);
		}
		msleep(&cnt.v_free_count, &vm_page_queue_mtx, PDROP | PVM,
		    "vmwait", 0);
	}
}

/*
 *	vm_waitpfault:	(also see VM_WAITPFAULT macro)
 *
 *	Block until free pages are available for allocation
 *	- Called only in vm_fault so that processes page faulting
 *	  can be easily tracked.
 *	- Sleeps at a lower priority than vm_wait() so that vm_wait()ing
 *	  processes will be able to grab memory first.  Do not change
 *	  this balance without careful testing first.
 */
void
vm_waitpfault(void)
{

	vm_page_lock_queues();
	if (!vm_pages_needed) {
		vm_pages_needed = 1;
		wakeup(&vm_pages_needed);
	}
	msleep(&cnt.v_free_count, &vm_page_queue_mtx, PDROP | PUSER,
	    "pfault", 0);
}

/*
 *	vm_page_activate:
 *
 *	Put the specified page on the active list (if appropriate).
 *	Ensure that act_count is at least ACT_INIT but do not otherwise
 *	mess with it.
 *
 *	The page queues must be locked.
 *	This routine may not block.
 */
void
vm_page_activate(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (VM_PAGE_GETKNOWNQUEUE2(m) != PQ_ACTIVE) {
		if (VM_PAGE_INQUEUE1(m, PQ_CACHE))
			cnt.v_reactivated++;
		vm_pageq_remove(m);
		if (m->wire_count == 0 && (m->flags & PG_UNMANAGED) == 0) {
			if (m->act_count < ACT_INIT)
				m->act_count = ACT_INIT;
			vm_pageq_enqueue(PQ_ACTIVE, m);
		}
	} else {
		if (m->act_count < ACT_INIT)
			m->act_count = ACT_INIT;
	}
}

/*
 *	vm_page_free_wakeup:
 *
 *	Helper routine for vm_page_free_toq() and vm_page_cache().  This
 *	routine is called when a page has been added to the cache or free
 *	queues.
 *
 *	The page queues must be locked.
 *	This routine may not block.
 */
static inline void
vm_page_free_wakeup(void)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	/*
	 * if pageout daemon needs pages, then tell it that there are
	 * some free.
	 */
	if (vm_pageout_pages_needed &&
	    cnt.v_cache_count + cnt.v_free_count >= cnt.v_pageout_free_min) {
		wakeup(&vm_pageout_pages_needed);
		vm_pageout_pages_needed = 0;
	}
	/*
	 * wakeup processes that are waiting on memory if we hit a
	 * high water mark. And wakeup scheduler process if we have
	 * lots of memory. this process will swapin processes.
	 */
	if (vm_pages_needed && !vm_page_count_min()) {
		vm_pages_needed = 0;
		wakeup(&cnt.v_free_count);
	}
}

/*
 *	vm_page_free_toq:
 *
 *	Returns the given page to the PQ_FREE list,
 *	disassociating it with any VM object.
 *
 *	Object and page must be locked prior to entry.
 *	This routine may not block.
 */

void
vm_page_free_toq(vm_page_t m)
{
	struct vpgqueues *pq;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	KASSERT(!pmap_page_is_mapped(m),
	    ("vm_page_free_toq: freeing mapped page %p", m));
	cnt.v_tfree++;

	if (m->busy || VM_PAGE_INQUEUE1(m, PQ_FREE)) {
		printf(
		"vm_page_free: pindex(%lu), busy(%d), PG_BUSY(%d), hold(%d)\n",
		    (u_long)m->pindex, m->busy, (m->flags & PG_BUSY) ? 1 : 0,
		    m->hold_count);
		if (VM_PAGE_INQUEUE1(m, PQ_FREE))
			panic("vm_page_free: freeing free page");
		else
			panic("vm_page_free: freeing busy page");
	}

	/*
	 * unqueue, then remove page.  Note that we cannot destroy
	 * the page here because we do not want to call the pager's
	 * callback routine until after we've put the page on the
	 * appropriate free queue.
	 */
	vm_pageq_remove_nowakeup(m);
	vm_page_remove(m);

	/*
	 * If fictitious remove object association and
	 * return, otherwise delay object association removal.
	 */
	if ((m->flags & PG_FICTITIOUS) != 0) {
		return;
	}

	m->valid = 0;
	vm_page_undirty(m);

	if (m->wire_count != 0) {
		if (m->wire_count > 1) {
			panic("vm_page_free: invalid wire count (%d), pindex: 0x%lx",
				m->wire_count, (long)m->pindex);
		}
		panic("vm_page_free: freeing wired page");
	}

	/*
	 * Clear the UNMANAGED flag when freeing an unmanaged page.
	 */
	if (m->flags & PG_UNMANAGED) {
		m->flags &= ~PG_UNMANAGED;
	}

	if (m->hold_count != 0) {
		m->flags &= ~PG_ZERO;
		VM_PAGE_SETQUEUE2(m, PQ_HOLD);
	} else
		VM_PAGE_SETQUEUE1(m, PQ_FREE);
	pq = &vm_page_queues[VM_PAGE_GETQUEUE(m)];
	mtx_lock_spin(&vm_page_queue_free_mtx);
	pq->lcnt++;
	++(*pq->cnt);

	/*
	 * Put zero'd pages on the end ( where we look for zero'd pages
	 * first ) and non-zerod pages at the head.
	 */
	if (m->flags & PG_ZERO) {
		TAILQ_INSERT_TAIL(&pq->pl, m, pageq);
		++vm_page_zero_count;
	} else {
		TAILQ_INSERT_HEAD(&pq->pl, m, pageq);
	}
	mtx_unlock_spin(&vm_page_queue_free_mtx);
	vm_page_free_wakeup();
}

/*
 *	vm_page_unmanage:
 *
 * 	Prevent PV management from being done on the page.  The page is
 *	removed from the paging queues as if it were wired, and as a 
 *	consequence of no longer being managed the pageout daemon will not
 *	touch it (since there is no way to locate the pte mappings for the
 *	page).  madvise() calls that mess with the pmap will also no longer
 *	operate on the page.
 *
 *	Beyond that the page is still reasonably 'normal'.  Freeing the page
 *	will clear the flag.
 *
 *	This routine is used by OBJT_PHYS objects - objects using unswappable
 *	physical memory as backing store rather then swap-backed memory and
 *	will eventually be extended to support 4MB unmanaged physical 
 *	mappings.
 */
void
vm_page_unmanage(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if ((m->flags & PG_UNMANAGED) == 0) {
		if (m->wire_count == 0)
			vm_pageq_remove(m);
	}
	vm_page_flag_set(m, PG_UNMANAGED);
}

/*
 *	vm_page_wire:
 *
 *	Mark this page as wired down by yet
 *	another map, removing it from paging queues
 *	as necessary.
 *
 *	The page queues must be locked.
 *	This routine may not block.
 */
void
vm_page_wire(vm_page_t m)
{

	/*
	 * Only bump the wire statistics if the page is not already wired,
	 * and only unqueue the page if it is on some queue (if it is unmanaged
	 * it is already off the queues).
	 */
	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (m->flags & PG_FICTITIOUS)
		return;
	if (m->wire_count == 0) {
		if ((m->flags & PG_UNMANAGED) == 0)
			vm_pageq_remove(m);
		atomic_add_int(&cnt.v_wire_count, 1);
	}
	m->wire_count++;
	KASSERT(m->wire_count != 0, ("vm_page_wire: wire_count overflow m=%p", m));
}

/*
 *	vm_page_unwire:
 *
 *	Release one wiring of this page, potentially
 *	enabling it to be paged again.
 *
 *	Many pages placed on the inactive queue should actually go
 *	into the cache, but it is difficult to figure out which.  What
 *	we do instead, if the inactive target is well met, is to put
 *	clean pages at the head of the inactive queue instead of the tail.
 *	This will cause them to be moved to the cache more quickly and
 *	if not actively re-referenced, freed more quickly.  If we just
 *	stick these pages at the end of the inactive queue, heavy filesystem
 *	meta-data accesses can cause an unnecessary paging load on memory bound 
 *	processes.  This optimization causes one-time-use metadata to be
 *	reused more quickly.
 *
 *	BUT, if we are in a low-memory situation we have no choice but to
 *	put clean pages on the cache queue.
 *
 *	A number of routines use vm_page_unwire() to guarantee that the page
 *	will go into either the inactive or active queues, and will NEVER
 *	be placed in the cache - for example, just after dirtying a page.
 *	dirty pages in the cache are not allowed.
 *
 *	The page queues must be locked.
 *	This routine may not block.
 */
void
vm_page_unwire(vm_page_t m, int activate)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (m->flags & PG_FICTITIOUS)
		return;
	if (m->wire_count > 0) {
		m->wire_count--;
		if (m->wire_count == 0) {
			atomic_subtract_int(&cnt.v_wire_count, 1);
			if (m->flags & PG_UNMANAGED) {
				;
			} else if (activate)
				vm_pageq_enqueue(PQ_ACTIVE, m);
			else {
				vm_page_flag_clear(m, PG_WINATCFLS);
				vm_pageq_enqueue(PQ_INACTIVE, m);
			}
		}
	} else {
		panic("vm_page_unwire: invalid wire count: %d", m->wire_count);
	}
}


/*
 * Move the specified page to the inactive queue.  If the page has
 * any associated swap, the swap is deallocated.
 *
 * Normally athead is 0 resulting in LRU operation.  athead is set
 * to 1 if we want this page to be 'as if it were placed in the cache',
 * except without unmapping it from the process address space.
 *
 * This routine may not block.
 */
static inline void
_vm_page_deactivate(vm_page_t m, int athead)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);

	/*
	 * Ignore if already inactive.
	 */
	if (VM_PAGE_INQUEUE2(m, PQ_INACTIVE))
		return;
	if (m->wire_count == 0 && (m->flags & PG_UNMANAGED) == 0) {
		if (VM_PAGE_INQUEUE1(m, PQ_CACHE))
			cnt.v_reactivated++;
		vm_page_flag_clear(m, PG_WINATCFLS);
		vm_pageq_remove(m);
		if (athead)
			TAILQ_INSERT_HEAD(&vm_page_queues[PQ_INACTIVE].pl, m, pageq);
		else
			TAILQ_INSERT_TAIL(&vm_page_queues[PQ_INACTIVE].pl, m, pageq);
		VM_PAGE_SETQUEUE2(m, PQ_INACTIVE);
		vm_page_queues[PQ_INACTIVE].lcnt++;
		cnt.v_inactive_count++;
	}
}

void
vm_page_deactivate(vm_page_t m)
{
    _vm_page_deactivate(m, 0);
}

/*
 * vm_page_try_to_cache:
 *
 * Returns 0 on failure, 1 on success
 */
int
vm_page_try_to_cache(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if (m->dirty || m->hold_count || m->busy || m->wire_count ||
	    (m->flags & (PG_BUSY|PG_UNMANAGED))) {
		return (0);
	}
	pmap_remove_all(m);
	if (m->dirty)
		return (0);
	vm_page_cache(m);
	return (1);
}

/*
 * vm_page_try_to_free()
 *
 *	Attempt to free the page.  If we cannot free it, we do nothing.
 *	1 is returned on success, 0 on failure.
 */
int
vm_page_try_to_free(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (m->object != NULL)
		VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if (m->dirty || m->hold_count || m->busy || m->wire_count ||
	    (m->flags & (PG_BUSY|PG_UNMANAGED))) {
		return (0);
	}
	pmap_remove_all(m);
	if (m->dirty)
		return (0);
	vm_page_free(m);
	return (1);
}

/*
 * vm_page_cache
 *
 * Put the specified page onto the page cache queue (if appropriate).
 *
 * This routine may not block.
 */
void
vm_page_cache(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if ((m->flags & (PG_BUSY|PG_UNMANAGED)) || m->busy ||
	    m->hold_count || m->wire_count) {
		printf("vm_page_cache: attempting to cache busy page\n");
		return;
	}
	if (VM_PAGE_INQUEUE1(m, PQ_CACHE))
		return;

	/*
	 * Remove all pmaps and indicate that the page is not
	 * writeable or mapped.
	 */
	pmap_remove_all(m);
	if (m->dirty != 0) {
		panic("vm_page_cache: caching a dirty page, pindex: %ld",
			(long)m->pindex);
	}
	vm_pageq_remove_nowakeup(m);
	vm_pageq_enqueue(PQ_CACHE + m->pc, m);
	vm_page_free_wakeup();
}

/*
 * vm_page_dontneed
 *
 *	Cache, deactivate, or do nothing as appropriate.  This routine
 *	is typically used by madvise() MADV_DONTNEED.
 *
 *	Generally speaking we want to move the page into the cache so
 *	it gets reused quickly.  However, this can result in a silly syndrome
 *	due to the page recycling too quickly.  Small objects will not be
 *	fully cached.  On the otherhand, if we move the page to the inactive
 *	queue we wind up with a problem whereby very large objects 
 *	unnecessarily blow away our inactive and cache queues.
 *
 *	The solution is to move the pages based on a fixed weighting.  We
 *	either leave them alone, deactivate them, or move them to the cache,
 *	where moving them to the cache has the highest weighting.
 *	By forcing some pages into other queues we eventually force the
 *	system to balance the queues, potentially recovering other unrelated
 *	space from active.  The idea is to not force this to happen too
 *	often.
 */
void
vm_page_dontneed(vm_page_t m)
{
	static int dnweight;
	int dnw;
	int head;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	dnw = ++dnweight;

	/*
	 * occassionally leave the page alone
	 */
	if ((dnw & 0x01F0) == 0 ||
	    VM_PAGE_INQUEUE2(m, PQ_INACTIVE) || 
	    VM_PAGE_INQUEUE1(m, PQ_CACHE)
	) {
		if (m->act_count >= ACT_INIT)
			--m->act_count;
		return;
	}

	if (m->dirty == 0 && pmap_is_modified(m))
		vm_page_dirty(m);

	if (m->dirty || (dnw & 0x0070) == 0) {
		/*
		 * Deactivate the page 3 times out of 32.
		 */
		head = 0;
	} else {
		/*
		 * Cache the page 28 times out of every 32.  Note that
		 * the page is deactivated instead of cached, but placed
		 * at the head of the queue instead of the tail.
		 */
		head = 1;
	}
	_vm_page_deactivate(m, head);
}

/*
 * Grab a page, waiting until we are waken up due to the page
 * changing state.  We keep on waiting, if the page continues
 * to be in the object.  If the page doesn't exist, first allocate it
 * and then conditionally zero it.
 *
 * This routine may block.
 */
vm_page_t
vm_page_grab(vm_object_t object, vm_pindex_t pindex, int allocflags)
{
	vm_page_t m;

	VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
retrylookup:
	if ((m = vm_page_lookup(object, pindex)) != NULL) {
		vm_page_lock_queues();
		if (m->busy || (m->flags & PG_BUSY)) {
			vm_page_flag_set(m, PG_WANTED | PG_REFERENCED);
			VM_OBJECT_UNLOCK(object);
			msleep(m, &vm_page_queue_mtx, PDROP | PVM, "pgrbwt", 0);
			VM_OBJECT_LOCK(object);
			if ((allocflags & VM_ALLOC_RETRY) == 0)
				return (NULL);
			goto retrylookup;
		} else {
			if (allocflags & VM_ALLOC_WIRED)
				vm_page_wire(m);
			if ((allocflags & VM_ALLOC_NOBUSY) == 0)
				vm_page_busy(m);
			vm_page_unlock_queues();
			return (m);
		}
	}
	m = vm_page_alloc(object, pindex, allocflags & ~VM_ALLOC_RETRY);
	if (m == NULL) {
		VM_OBJECT_UNLOCK(object);
		VM_WAIT;
		VM_OBJECT_LOCK(object);
		if ((allocflags & VM_ALLOC_RETRY) == 0)
			return (NULL);
		goto retrylookup;
	}
	if (allocflags & VM_ALLOC_ZERO && (m->flags & PG_ZERO) == 0)
		pmap_zero_page(m);
	return (m);
}

/*
 * Mapping function for valid bits or for dirty bits in
 * a page.  May not block.
 *
 * Inputs are required to range within a page.
 */
inline int
vm_page_bits(int base, int size)
{
	int first_bit;
	int last_bit;

	KASSERT(
	    base + size <= PAGE_SIZE,
	    ("vm_page_bits: illegal base/size %d/%d", base, size)
	);

	if (size == 0)		/* handle degenerate case */
		return (0);

	first_bit = base >> DEV_BSHIFT;
	last_bit = (base + size - 1) >> DEV_BSHIFT;

	return ((2 << last_bit) - (1 << first_bit));
}

/*
 *	vm_page_set_validclean:
 *
 *	Sets portions of a page valid and clean.  The arguments are expected
 *	to be DEV_BSIZE aligned but if they aren't the bitmap is inclusive
 *	of any partial chunks touched by the range.  The invalid portion of
 *	such chunks will be zero'd.
 *
 *	This routine may not block.
 *
 *	(base + size) must be less then or equal to PAGE_SIZE.
 */
void
vm_page_set_validclean(vm_page_t m, int base, int size)
{
	int pagebits;
	int frag;
	int endoff;

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if (size == 0)	/* handle degenerate case */
		return;

	/*
	 * If the base is not DEV_BSIZE aligned and the valid
	 * bit is clear, we have to zero out a portion of the
	 * first block.
	 */
	if ((frag = base & ~(DEV_BSIZE - 1)) != base &&
	    (m->valid & (1 << (base >> DEV_BSHIFT))) == 0)
		pmap_zero_page_area(m, frag, base - frag);

	/*
	 * If the ending offset is not DEV_BSIZE aligned and the 
	 * valid bit is clear, we have to zero out a portion of
	 * the last block.
	 */
	endoff = base + size;
	if ((frag = endoff & ~(DEV_BSIZE - 1)) != endoff &&
	    (m->valid & (1 << (endoff >> DEV_BSHIFT))) == 0)
		pmap_zero_page_area(m, endoff,
		    DEV_BSIZE - (endoff & (DEV_BSIZE - 1)));

	/*
	 * Set valid, clear dirty bits.  If validating the entire
	 * page we can safely clear the pmap modify bit.  We also
	 * use this opportunity to clear the PG_NOSYNC flag.  If a process
	 * takes a write fault on a MAP_NOSYNC memory area the flag will
	 * be set again.
	 *
	 * We set valid bits inclusive of any overlap, but we can only
	 * clear dirty bits for DEV_BSIZE chunks that are fully within
	 * the range.
	 */
	pagebits = vm_page_bits(base, size);
	m->valid |= pagebits;
#if 0	/* NOT YET */
	if ((frag = base & (DEV_BSIZE - 1)) != 0) {
		frag = DEV_BSIZE - frag;
		base += frag;
		size -= frag;
		if (size < 0)
			size = 0;
	}
	pagebits = vm_page_bits(base, size & (DEV_BSIZE - 1));
#endif
	m->dirty &= ~pagebits;
	if (base == 0 && size == PAGE_SIZE) {
		pmap_clear_modify(m);
		vm_page_flag_clear(m, PG_NOSYNC);
	}
}

void
vm_page_clear_dirty(vm_page_t m, int base, int size)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	m->dirty &= ~vm_page_bits(base, size);
}

/*
 *	vm_page_set_invalid:
 *
 *	Invalidates DEV_BSIZE'd chunks within a page.  Both the
 *	valid and dirty bits for the effected areas are cleared.
 *
 *	May not block.
 */
void
vm_page_set_invalid(vm_page_t m, int base, int size)
{
	int bits;

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	bits = vm_page_bits(base, size);
	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (m->valid == VM_PAGE_BITS_ALL && bits != 0)
		pmap_remove_all(m);
	m->valid &= ~bits;
	m->dirty &= ~bits;
	m->object->generation++;
}

/*
 * vm_page_zero_invalid()
 *
 *	The kernel assumes that the invalid portions of a page contain 
 *	garbage, but such pages can be mapped into memory by user code.
 *	When this occurs, we must zero out the non-valid portions of the
 *	page so user code sees what it expects.
 *
 *	Pages are most often semi-valid when the end of a file is mapped 
 *	into memory and the file's size is not page aligned.
 */
void
vm_page_zero_invalid(vm_page_t m, boolean_t setvalid)
{
	int b;
	int i;

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	/*
	 * Scan the valid bits looking for invalid sections that
	 * must be zerod.  Invalid sub-DEV_BSIZE'd areas ( where the
	 * valid bit may be set ) have already been zerod by
	 * vm_page_set_validclean().
	 */
	for (b = i = 0; i <= PAGE_SIZE / DEV_BSIZE; ++i) {
		if (i == (PAGE_SIZE / DEV_BSIZE) || 
		    (m->valid & (1 << i))
		) {
			if (i > b) {
				pmap_zero_page_area(m, 
				    b << DEV_BSHIFT, (i - b) << DEV_BSHIFT);
			}
			b = i + 1;
		}
	}

	/*
	 * setvalid is TRUE when we can safely set the zero'd areas
	 * as being valid.  We can do this if there are no cache consistancy
	 * issues.  e.g. it is ok to do with UFS, but not ok to do with NFS.
	 */
	if (setvalid)
		m->valid = VM_PAGE_BITS_ALL;
}

/*
 *	vm_page_is_valid:
 *
 *	Is (partial) page valid?  Note that the case where size == 0
 *	will return FALSE in the degenerate case where the page is
 *	entirely invalid, and TRUE otherwise.
 *
 *	May not block.
 */
int
vm_page_is_valid(vm_page_t m, int base, int size)
{
	int bits = vm_page_bits(base, size);

	VM_OBJECT_LOCK_ASSERT(m->object, MA_OWNED);
	if (m->valid && ((m->valid & bits) == bits))
		return 1;
	else
		return 0;
}

/*
 * update dirty bits from pmap/mmu.  May not block.
 */
void
vm_page_test_dirty(vm_page_t m)
{
	if ((m->dirty != VM_PAGE_BITS_ALL) && pmap_is_modified(m)) {
		vm_page_dirty(m);
	}
}

int so_zerocp_fullpage = 0;

void
vm_page_cowfault(vm_page_t m)
{
	vm_page_t mnew;
	vm_object_t object;
	vm_pindex_t pindex;

	object = m->object;
	pindex = m->pindex;

 retry_alloc:
	pmap_remove_all(m);
	vm_page_remove(m);
	mnew = vm_page_alloc(object, pindex, VM_ALLOC_NORMAL);
	if (mnew == NULL) {
		vm_page_insert(m, object, pindex);
		vm_page_unlock_queues();
		VM_OBJECT_UNLOCK(object);
		VM_WAIT;
		VM_OBJECT_LOCK(object);
		vm_page_lock_queues();
		goto retry_alloc;
	}

	if (m->cow == 0) {
		/* 
		 * check to see if we raced with an xmit complete when 
		 * waiting to allocate a page.  If so, put things back 
		 * the way they were 
		 */
		vm_page_free(mnew);
		vm_page_insert(m, object, pindex);
	} else { /* clear COW & copy page */
		if (!so_zerocp_fullpage)
			pmap_copy_page(m, mnew);
		mnew->valid = VM_PAGE_BITS_ALL;
		vm_page_dirty(mnew);
		vm_page_flag_clear(mnew, PG_BUSY);
		mnew->wire_count = m->wire_count - m->cow;
		m->wire_count = m->cow;
	}
}

void 
vm_page_cowclear(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	if (m->cow) {
		m->cow--;
		/* 
		 * let vm_fault add back write permission  lazily
		 */
	} 
	/*
	 *  sf_buf_free() will free the page, so we needn't do it here
	 */ 
}

void
vm_page_cowsetup(vm_page_t m)
{

	mtx_assert(&vm_page_queue_mtx, MA_OWNED);
	m->cow++;
	pmap_page_protect(m, VM_PROT_READ);
}

#include "opt_ddb.h"
#ifdef DDB
#include <sys/kernel.h>

#include <ddb/ddb.h>

DB_SHOW_COMMAND(page, vm_page_print_page_info)
{
	db_printf("cnt.v_free_count: %d\n", cnt.v_free_count);
	db_printf("cnt.v_cache_count: %d\n", cnt.v_cache_count);
	db_printf("cnt.v_inactive_count: %d\n", cnt.v_inactive_count);
	db_printf("cnt.v_active_count: %d\n", cnt.v_active_count);
	db_printf("cnt.v_wire_count: %d\n", cnt.v_wire_count);
	db_printf("cnt.v_free_reserved: %d\n", cnt.v_free_reserved);
	db_printf("cnt.v_free_min: %d\n", cnt.v_free_min);
	db_printf("cnt.v_free_target: %d\n", cnt.v_free_target);
	db_printf("cnt.v_cache_min: %d\n", cnt.v_cache_min);
	db_printf("cnt.v_inactive_target: %d\n", cnt.v_inactive_target);
}

DB_SHOW_COMMAND(pageq, vm_page_print_pageq_info)
{
	int i;
	db_printf("PQ_FREE:");
	for (i = 0; i < PQ_NUMCOLORS; i++) {
		db_printf(" %d", vm_page_queues[PQ_FREE + i].lcnt);
	}
	db_printf("\n");
		
	db_printf("PQ_CACHE:");
	for (i = 0; i < PQ_NUMCOLORS; i++) {
		db_printf(" %d", vm_page_queues[PQ_CACHE + i].lcnt);
	}
	db_printf("\n");

	db_printf("PQ_ACTIVE: %d, PQ_INACTIVE: %d\n",
		vm_page_queues[PQ_ACTIVE].lcnt,
		vm_page_queues[PQ_INACTIVE].lcnt);
}
#endif /* DDB */