Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: a7d493366a65b31b547ef25d34b94f2417895372 (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
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
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
/*
 *  linux/mm/vmstat.c
 *
 *  Manages VM statistics
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  zoned VM statistics
 *  Copyright (C) 2006 Silicon Graphics, Inc.,
 *		Christoph Lameter <christoph@lameter.com>
 *  Copyright (C) 2008-2014 Christoph Lameter
 */
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/vmstat.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/sched.h>
#include <linux/math64.h>
#include <linux/writeback.h>
#include <linux/compaction.h>
#include <linux/mm_inline.h>
#include <linux/page_ext.h>
#include <linux/page_owner.h>

#include "internal.h"

#define NUMA_STATS_THRESHOLD (U16_MAX - 2)

#ifdef CONFIG_NUMA
int sysctl_vm_numa_stat = ENABLE_NUMA_STAT;

/* zero numa counters within a zone */
static void zero_zone_numa_counters(struct zone *zone)
{
	int item, cpu;

	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) {
		atomic_long_set(&zone->vm_numa_stat[item], 0);
		for_each_online_cpu(cpu)
			per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]
						= 0;
	}
}

/* zero numa counters of all the populated zones */
static void zero_zones_numa_counters(void)
{
	struct zone *zone;

	for_each_populated_zone(zone)
		zero_zone_numa_counters(zone);
}

/* zero global numa counters */
static void zero_global_numa_counters(void)
{
	int item;

	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++)
		atomic_long_set(&vm_numa_stat[item], 0);
}

static void invalid_numa_statistics(void)
{
	zero_zones_numa_counters();
	zero_global_numa_counters();
}

static DEFINE_MUTEX(vm_numa_stat_lock);

int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *length, loff_t *ppos)
{
	int ret, oldval;

	mutex_lock(&vm_numa_stat_lock);
	if (write)
		oldval = sysctl_vm_numa_stat;
	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (ret || !write)
		goto out;

	if (oldval == sysctl_vm_numa_stat)
		goto out;
	else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) {
		static_branch_enable(&vm_numa_stat_key);
		pr_info("enable numa statistics\n");
	} else {
		static_branch_disable(&vm_numa_stat_key);
		invalid_numa_statistics();
		pr_info("disable numa statistics, and clear numa counters\n");
	}

out:
	mutex_unlock(&vm_numa_stat_lock);
	return ret;
}
#endif

#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

static void sum_vm_events(unsigned long *ret)
{
	int cpu;
	int i;

	memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));

	for_each_online_cpu(cpu) {
		struct vm_event_state *this = &per_cpu(vm_event_states, cpu);

		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
			ret[i] += this->event[i];
	}
}

/*
 * Accumulate the vm event counters across all CPUs.
 * The result is unavoidably approximate - it can change
 * during and after execution of this function.
*/
void all_vm_events(unsigned long *ret)
{
	get_online_cpus();
	sum_vm_events(ret);
	put_online_cpus();
}
EXPORT_SYMBOL_GPL(all_vm_events);

/*
 * Fold the foreign cpu events into our own.
 *
 * This is adding to the events on one processor
 * but keeps the global counts constant.
 */
void vm_events_fold_cpu(int cpu)
{
	struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu);
	int i;

	for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
		count_vm_events(i, fold_state->event[i]);
		fold_state->event[i] = 0;
	}
}

#endif /* CONFIG_VM_EVENT_COUNTERS */

/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp;
atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
EXPORT_SYMBOL(vm_zone_stat);
EXPORT_SYMBOL(vm_numa_stat);
EXPORT_SYMBOL(vm_node_stat);

#ifdef CONFIG_SMP

int calculate_pressure_threshold(struct zone *zone)
{
	int threshold;
	int watermark_distance;

	/*
	 * As vmstats are not up to date, there is drift between the estimated
	 * and real values. For high thresholds and a high number of CPUs, it
	 * is possible for the min watermark to be breached while the estimated
	 * value looks fine. The pressure threshold is a reduced value such
	 * that even the maximum amount of drift will not accidentally breach
	 * the min watermark
	 */
	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
	threshold = max(1, (int)(watermark_distance / num_online_cpus()));

	/*
	 * Maximum threshold is 125
	 */
	threshold = min(125, threshold);

	return threshold;
}

int calculate_normal_threshold(struct zone *zone)
{
	int threshold;
	int mem;	/* memory in 128 MB units */

	/*
	 * The threshold scales with the number of processors and the amount
	 * of memory per zone. More memory means that we can defer updates for
	 * longer, more processors could lead to more contention.
 	 * fls() is used to have a cheap way of logarithmic scaling.
	 *
	 * Some sample thresholds:
	 *
	 * Threshold	Processors	(fls)	Zonesize	fls(mem+1)
	 * ------------------------------------------------------------------
	 * 8		1		1	0.9-1 GB	4
	 * 16		2		2	0.9-1 GB	4
	 * 20 		2		2	1-2 GB		5
	 * 24		2		2	2-4 GB		6
	 * 28		2		2	4-8 GB		7
	 * 32		2		2	8-16 GB		8
	 * 4		2		2	<128M		1
	 * 30		4		3	2-4 GB		5
	 * 48		4		3	8-16 GB		8
	 * 32		8		4	1-2 GB		4
	 * 32		8		4	0.9-1GB		4
	 * 10		16		5	<128M		1
	 * 40		16		5	900M		4
	 * 70		64		7	2-4 GB		5
	 * 84		64		7	4-8 GB		6
	 * 108		512		9	4-8 GB		6
	 * 125		1024		10	8-16 GB		8
	 * 125		1024		10	16-32 GB	9
	 */

	mem = zone_managed_pages(zone) >> (27 - PAGE_SHIFT);

	threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem));

	/*
	 * Maximum threshold is 125
	 */
	threshold = min(125, threshold);

	return threshold;
}

/*
 * Refresh the thresholds for each zone.
 */
void refresh_zone_stat_thresholds(void)
{
	struct pglist_data *pgdat;
	struct zone *zone;
	int cpu;
	int threshold;

	/* Zero current pgdat thresholds */
	for_each_online_pgdat(pgdat) {
		for_each_online_cpu(cpu) {
			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0;
		}
	}

	for_each_populated_zone(zone) {
		struct pglist_data *pgdat = zone->zone_pgdat;
		unsigned long max_drift, tolerate_drift;

		threshold = calculate_normal_threshold(zone);

		for_each_online_cpu(cpu) {
			int pgdat_threshold;

			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;

			/* Base nodestat threshold on the largest populated zone. */
			pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
				= max(threshold, pgdat_threshold);
		}

		/*
		 * Only set percpu_drift_mark if there is a danger that
		 * NR_FREE_PAGES reports the low watermark is ok when in fact
		 * the min watermark could be breached by an allocation
		 */
		tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone);
		max_drift = num_online_cpus() * threshold;
		if (max_drift > tolerate_drift)
			zone->percpu_drift_mark = high_wmark_pages(zone) +
					max_drift;
	}
}

void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *))
{
	struct zone *zone;
	int cpu;
	int threshold;
	int i;

	for (i = 0; i < pgdat->nr_zones; i++) {
		zone = &pgdat->node_zones[i];
		if (!zone->percpu_drift_mark)
			continue;

		threshold = (*calculate_pressure)(zone);
		for_each_online_cpu(cpu)
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
}

/*
 * For use when we know that interrupts are disabled,
 * or when we know that preemption is disabled and that
 * particular counter cannot be updated from interrupt context.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
			   long delta)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	long x;
	long t;

	x = delta + __this_cpu_read(*p);

	t = __this_cpu_read(pcp->stat_threshold);

	if (unlikely(x > t || x < -t)) {
		zone_page_state_add(x, zone, item);
		x = 0;
	}
	__this_cpu_write(*p, x);
}
EXPORT_SYMBOL(__mod_zone_page_state);

void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
				long delta)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	long x;
	long t;

	x = delta + __this_cpu_read(*p);

	t = __this_cpu_read(pcp->stat_threshold);

	if (unlikely(x > t || x < -t)) {
		node_page_state_add(x, pgdat, item);
		x = 0;
	}
	__this_cpu_write(*p, x);
}
EXPORT_SYMBOL(__mod_node_page_state);

/*
 * Optimized increment and decrement functions.
 *
 * These are only for a single page and therefore can take a struct page *
 * argument instead of struct zone *. This allows the inclusion of the code
 * generated for page_zone(page) into the optimized functions.
 *
 * No overflow check is necessary and therefore the differential can be
 * incremented or decremented in place which may allow the compilers to
 * generate better code.
 * The increment or decrement is known and therefore one boundary check can
 * be omitted.
 *
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
 * Some processors have inc/dec instructions that are atomic vs an interrupt.
 * However, the code must first determine the differential location in a zone
 * based on the processor number and then inc/dec the counter. There is no
 * guarantee without disabling preemption that the processor will not change
 * in between and therefore the atomicity vs. interrupt cannot be exploited
 * in a useful way here.
 */
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;

	v = __this_cpu_inc_return(*p);
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;

		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
	}
}

void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	s8 v, t;

	v = __this_cpu_inc_return(*p);
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;

		node_page_state_add(v + overstep, pgdat, item);
		__this_cpu_write(*p, -overstep);
	}
}

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
EXPORT_SYMBOL(__inc_zone_page_state);

void __inc_node_page_state(struct page *page, enum node_stat_item item)
{
	__inc_node_state(page_pgdat(page), item);
}
EXPORT_SYMBOL(__inc_node_page_state);

void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;

	v = __this_cpu_dec_return(*p);
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;

		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
	}
}

void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	s8 v, t;

	v = __this_cpu_dec_return(*p);
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;

		node_page_state_add(v - overstep, pgdat, item);
		__this_cpu_write(*p, overstep);
	}
}

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
EXPORT_SYMBOL(__dec_zone_page_state);

void __dec_node_page_state(struct page *page, enum node_stat_item item)
{
	__dec_node_state(page_pgdat(page), item);
}
EXPORT_SYMBOL(__dec_node_page_state);

#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
/*
 * If we have cmpxchg_local support then we do not need to incur the overhead
 * that comes with local_irq_save/restore if we use this_cpu_cmpxchg.
 *
 * mod_state() modifies the zone counter state through atomic per cpu
 * operations.
 *
 * Overstep mode specifies how overstep should handled:
 *     0       No overstepping
 *     1       Overstepping half of threshold
 *     -1      Overstepping minus half of threshold
*/
static inline void mod_zone_state(struct zone *zone,
       enum zone_stat_item item, long delta, int overstep_mode)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	long o, n, t, z;

	do {
		z = 0;  /* overflow to zone counters */

		/*
		 * The fetching of the stat_threshold is racy. We may apply
		 * a counter threshold to the wrong the cpu if we get
		 * rescheduled while executing here. However, the next
		 * counter update will apply the threshold again and
		 * therefore bring the counter under the threshold again.
		 *
		 * Most of the time the thresholds are the same anyways
		 * for all cpus in a zone.
		 */
		t = this_cpu_read(pcp->stat_threshold);

		o = this_cpu_read(*p);
		n = delta + o;

		if (n > t || n < -t) {
			int os = overstep_mode * (t >> 1) ;

			/* Overflow must be added to zone counters */
			z = n + os;
			n = -os;
		}
	} while (this_cpu_cmpxchg(*p, o, n) != o);

	if (z)
		zone_page_state_add(z, zone, item);
}

void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
			 long delta)
{
	mod_zone_state(zone, item, delta, 0);
}
EXPORT_SYMBOL(mod_zone_page_state);

void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	mod_zone_state(page_zone(page), item, 1, 1);
}
EXPORT_SYMBOL(inc_zone_page_state);

void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	mod_zone_state(page_zone(page), item, -1, -1);
}
EXPORT_SYMBOL(dec_zone_page_state);

static inline void mod_node_state(struct pglist_data *pgdat,
       enum node_stat_item item, int delta, int overstep_mode)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	long o, n, t, z;

	do {
		z = 0;  /* overflow to node counters */

		/*
		 * The fetching of the stat_threshold is racy. We may apply
		 * a counter threshold to the wrong the cpu if we get
		 * rescheduled while executing here. However, the next
		 * counter update will apply the threshold again and
		 * therefore bring the counter under the threshold again.
		 *
		 * Most of the time the thresholds are the same anyways
		 * for all cpus in a node.
		 */
		t = this_cpu_read(pcp->stat_threshold);

		o = this_cpu_read(*p);
		n = delta + o;

		if (n > t || n < -t) {
			int os = overstep_mode * (t >> 1) ;

			/* Overflow must be added to node counters */
			z = n + os;
			n = -os;
		}
	} while (this_cpu_cmpxchg(*p, o, n) != o);

	if (z)
		node_page_state_add(z, pgdat, item);
}

void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
					long delta)
{
	mod_node_state(pgdat, item, delta, 0);
}
EXPORT_SYMBOL(mod_node_page_state);

void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	mod_node_state(pgdat, item, 1, 1);
}

void inc_node_page_state(struct page *page, enum node_stat_item item)
{
	mod_node_state(page_pgdat(page), item, 1, 1);
}
EXPORT_SYMBOL(inc_node_page_state);

void dec_node_page_state(struct page *page, enum node_stat_item item)
{
	mod_node_state(page_pgdat(page), item, -1, -1);
}
EXPORT_SYMBOL(dec_node_page_state);
#else
/*
 * Use interrupt disable to serialize counter updates
 */
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
			 long delta)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_zone_page_state(zone, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_zone_page_state);

void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	unsigned long flags;
	struct zone *zone;

	zone = page_zone(page);
	local_irq_save(flags);
	__inc_zone_state(zone, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_zone_page_state);

void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
	__dec_zone_page_state(page, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);

void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
	__inc_node_state(pgdat, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_node_state);

void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
					long delta)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_node_page_state(pgdat, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_node_page_state);

void inc_node_page_state(struct page *page, enum node_stat_item item)
{
	unsigned long flags;
	struct pglist_data *pgdat;

	pgdat = page_pgdat(page);
	local_irq_save(flags);
	__inc_node_state(pgdat, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_node_page_state);

void dec_node_page_state(struct page *page, enum node_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
	__dec_node_page_state(page, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_node_page_state);
#endif

/*
 * Fold a differential into the global counters.
 * Returns the number of counters updated.
 */
#ifdef CONFIG_NUMA
static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
{
	int i;
	int changes = 0;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (zone_diff[i]) {
			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		if (numa_diff[i]) {
			atomic_long_add(numa_diff[i], &vm_numa_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
		if (node_diff[i]) {
			atomic_long_add(node_diff[i], &vm_node_stat[i]);
			changes++;
	}
	return changes;
}
#else
static int fold_diff(int *zone_diff, int *node_diff)
{
	int i;
	int changes = 0;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (zone_diff[i]) {
			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
		if (node_diff[i]) {
			atomic_long_add(node_diff[i], &vm_node_stat[i]);
			changes++;
	}
	return changes;
}
#endif /* CONFIG_NUMA */

/*
 * Update the zone counters for the current cpu.
 *
 * Note that refresh_cpu_vm_stats strives to only access
 * node local memory. The per cpu pagesets on remote zones are placed
 * in the memory local to the processor using that pageset. So the
 * loop over all zones will access a series of cachelines local to
 * the processor.
 *
 * The call to zone_page_state_add updates the cachelines with the
 * statistics in the remote zone struct as well as the global cachelines
 * with the global counters. These could cause remote node cache line
 * bouncing and will have to be only done when necessary.
 *
 * The function returns the number of global counters updated.
 */
static int refresh_cpu_vm_stats(bool do_pagesets)
{
	struct pglist_data *pgdat;
	struct zone *zone;
	int i;
	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
#ifdef CONFIG_NUMA
	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
#endif
	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
	int changes = 0;

	for_each_populated_zone(zone) {
		struct per_cpu_pageset __percpu *p = zone->pageset;

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
			int v;

			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
			if (v) {

				atomic_long_add(v, &zone->vm_stat[i]);
				global_zone_diff[i] += v;
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
				__this_cpu_write(p->expire, 3);
#endif
			}
		}
#ifdef CONFIG_NUMA
		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
			int v;

			v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0);
			if (v) {

				atomic_long_add(v, &zone->vm_numa_stat[i]);
				global_numa_diff[i] += v;
				__this_cpu_write(p->expire, 3);
			}
		}

		if (do_pagesets) {
			cond_resched();
			/*
			 * Deal with draining the remote pageset of this
			 * processor
			 *
			 * Check if there are pages remaining in this pageset
			 * if not then there is nothing to expire.
			 */
			if (!__this_cpu_read(p->expire) ||
			       !__this_cpu_read(p->pcp.count))
				continue;

			/*
			 * We never drain zones local to this processor.
			 */
			if (zone_to_nid(zone) == numa_node_id()) {
				__this_cpu_write(p->expire, 0);
				continue;
			}

			if (__this_cpu_dec_return(p->expire))
				continue;

			if (__this_cpu_read(p->pcp.count)) {
				drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
				changes++;
			}
		}
#endif
	}

	for_each_online_pgdat(pgdat) {
		struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats;

		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
			int v;

			v = this_cpu_xchg(p->vm_node_stat_diff[i], 0);
			if (v) {
				atomic_long_add(v, &pgdat->vm_stat[i]);
				global_node_diff[i] += v;
			}
		}
	}

#ifdef CONFIG_NUMA
	changes += fold_diff(global_zone_diff, global_numa_diff,
			     global_node_diff);
#else
	changes += fold_diff(global_zone_diff, global_node_diff);
#endif
	return changes;
}

/*
 * Fold the data for an offline cpu into the global array.
 * There cannot be any access by the offline cpu and therefore
 * synchronization is simplified.
 */
void cpu_vm_stats_fold(int cpu)
{
	struct pglist_data *pgdat;
	struct zone *zone;
	int i;
	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
#ifdef CONFIG_NUMA
	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
#endif
	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *p;

		p = per_cpu_ptr(zone->pageset, cpu);

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
			if (p->vm_stat_diff[i]) {
				int v;

				v = p->vm_stat_diff[i];
				p->vm_stat_diff[i] = 0;
				atomic_long_add(v, &zone->vm_stat[i]);
				global_zone_diff[i] += v;
			}

#ifdef CONFIG_NUMA
		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
			if (p->vm_numa_stat_diff[i]) {
				int v;

				v = p->vm_numa_stat_diff[i];
				p->vm_numa_stat_diff[i] = 0;
				atomic_long_add(v, &zone->vm_numa_stat[i]);
				global_numa_diff[i] += v;
			}
#endif
	}

	for_each_online_pgdat(pgdat) {
		struct per_cpu_nodestat *p;

		p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);

		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
			if (p->vm_node_stat_diff[i]) {
				int v;

				v = p->vm_node_stat_diff[i];
				p->vm_node_stat_diff[i] = 0;
				atomic_long_add(v, &pgdat->vm_stat[i]);
				global_node_diff[i] += v;
			}
	}

#ifdef CONFIG_NUMA
	fold_diff(global_zone_diff, global_numa_diff, global_node_diff);
#else
	fold_diff(global_zone_diff, global_node_diff);
#endif
}

/*
 * this is only called if !populated_zone(zone), which implies no other users of
 * pset->vm_stat_diff[] exsist.
 */
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
{
	int i;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (pset->vm_stat_diff[i]) {
			int v = pset->vm_stat_diff[i];
			pset->vm_stat_diff[i] = 0;
			atomic_long_add(v, &zone->vm_stat[i]);
			atomic_long_add(v, &vm_zone_stat[i]);
		}

#ifdef CONFIG_NUMA
	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		if (pset->vm_numa_stat_diff[i]) {
			int v = pset->vm_numa_stat_diff[i];

			pset->vm_numa_stat_diff[i] = 0;
			atomic_long_add(v, &zone->vm_numa_stat[i]);
			atomic_long_add(v, &vm_numa_stat[i]);
		}
#endif
}
#endif

#ifdef CONFIG_NUMA
void __inc_numa_state(struct zone *zone,
				 enum numa_stat_item item)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	u16 __percpu *p = pcp->vm_numa_stat_diff + item;
	u16 v;

	v = __this_cpu_inc_return(*p);

	if (unlikely(v > NUMA_STATS_THRESHOLD)) {
		zone_numa_state_add(v, zone, item);
		__this_cpu_write(*p, 0);
	}
}

/*
 * Determine the per node value of a stat item. This function
 * is called frequently in a NUMA machine, so try to be as
 * frugal as possible.
 */
unsigned long sum_zone_node_page_state(int node,
				 enum zone_stat_item item)
{
	struct zone *zones = NODE_DATA(node)->node_zones;
	int i;
	unsigned long count = 0;

	for (i = 0; i < MAX_NR_ZONES; i++)
		count += zone_page_state(zones + i, item);

	return count;
}

/*
 * Determine the per node value of a numa stat item. To avoid deviation,
 * the per cpu stat number in vm_numa_stat_diff[] is also included.
 */
unsigned long sum_zone_numa_state(int node,
				 enum numa_stat_item item)
{
	struct zone *zones = NODE_DATA(node)->node_zones;
	int i;
	unsigned long count = 0;

	for (i = 0; i < MAX_NR_ZONES; i++)
		count += zone_numa_state_snapshot(zones + i, item);

	return count;
}

/*
 * Determine the per node value of a stat item.
 */
unsigned long node_page_state(struct pglist_data *pgdat,
				enum node_stat_item item)
{
	long x = atomic_long_read(&pgdat->vm_stat[item]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}
#endif

#ifdef CONFIG_COMPACTION

struct contig_page_info {
	unsigned long free_pages;
	unsigned long free_blocks_total;
	unsigned long free_blocks_suitable;
};

/*
 * Calculate the number of free pages in a zone, how many contiguous
 * pages are free and how many are large enough to satisfy an allocation of
 * the target size. Note that this function makes no attempt to estimate
 * how many suitable free blocks there *might* be if MOVABLE pages were
 * migrated. Calculating that is possible, but expensive and can be
 * figured out from userspace
 */
static void fill_contig_page_info(struct zone *zone,
				unsigned int suitable_order,
				struct contig_page_info *info)
{
	unsigned int order;

	info->free_pages = 0;
	info->free_blocks_total = 0;
	info->free_blocks_suitable = 0;

	for (order = 0; order < MAX_ORDER; order++) {
		unsigned long blocks;

		/* Count number of free blocks */
		blocks = zone->free_area[order].nr_free;
		info->free_blocks_total += blocks;

		/* Count free base pages */
		info->free_pages += blocks << order;

		/* Count the suitable free blocks */
		if (order >= suitable_order)
			info->free_blocks_suitable += blocks <<
						(order - suitable_order);
	}
}

/*
 * A fragmentation index only makes sense if an allocation of a requested
 * size would fail. If that is true, the fragmentation index indicates
 * whether external fragmentation or a lack of memory was the problem.
 * The value can be used to determine if page reclaim or compaction
 * should be used
 */
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
{
	unsigned long requested = 1UL << order;

	if (WARN_ON_ONCE(order >= MAX_ORDER))
		return 0;

	if (!info->free_blocks_total)
		return 0;

	/* Fragmentation index only makes sense when a request would fail */
	if (info->free_blocks_suitable)
		return -1000;

	/*
	 * Index is between 0 and 1 so return within 3 decimal places
	 *
	 * 0 => allocation would fail due to lack of memory
	 * 1 => allocation would fail due to fragmentation
	 */
	return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
}

/* Same as __fragmentation index but allocs contig_page_info on stack */
int fragmentation_index(struct zone *zone, unsigned int order)
{
	struct contig_page_info info;

	fill_contig_page_info(zone, order, &info);
	return __fragmentation_index(order, &info);
}
#endif

#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
#define TEXT_FOR_DMA(xx)
#endif

#ifdef CONFIG_ZONE_DMA32
#define TEXT_FOR_DMA32(xx) xx "_dma32",
#else
#define TEXT_FOR_DMA32(xx)
#endif

#ifdef CONFIG_HIGHMEM
#define TEXT_FOR_HIGHMEM(xx) xx "_high",
#else
#define TEXT_FOR_HIGHMEM(xx)
#endif

#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
					TEXT_FOR_HIGHMEM(xx) xx "_movable",

const char * const vmstat_text[] = {
	/* enum zone_stat_item countes */
	"nr_free_pages",
	"nr_zone_inactive_anon",
	"nr_zone_active_anon",
	"nr_zone_inactive_file",
	"nr_zone_active_file",
	"nr_zone_unevictable",
	"nr_zone_write_pending",
	"nr_mlock",
	"nr_page_table_pages",
	"nr_kernel_stack",
	"nr_bounce",
#if IS_ENABLED(CONFIG_ZSMALLOC)
	"nr_zspages",
#endif
	"nr_free_cma",

	/* enum numa_stat_item counters */
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif

	/* Node-based counters */
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
	"nr_unevictable",
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
	"nr_isolated_anon",
	"nr_isolated_file",
	"workingset_nodes",
	"workingset_refault",
	"workingset_activate",
	"workingset_restore",
	"workingset_nodereclaim",
	"nr_anon_pages",
	"nr_mapped",
	"nr_file_pages",
	"nr_dirty",
	"nr_writeback",
	"nr_writeback_temp",
	"nr_shmem",
	"nr_shmem_hugepages",
	"nr_shmem_pmdmapped",
	"nr_anon_transparent_hugepages",
	"nr_unstable",
	"nr_vmscan_write",
	"nr_vmscan_immediate_reclaim",
	"nr_dirtied",
	"nr_written",
	"nr_kernel_misc_reclaimable",

	/* enum writeback_stat_item counters */
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",

#ifdef CONFIG_VM_EVENT_COUNTERS
	/* enum vm_event_item counters */
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	TEXTS_FOR_ZONES("pgalloc")
	TEXTS_FOR_ZONES("allocstall")
	TEXTS_FOR_ZONES("pgskip")

	"pgfree",
	"pgactivate",
	"pgdeactivate",
	"pglazyfree",

	"pgfault",
	"pgmajfault",
	"pglazyfreed",

	"pgrefill",
	"pgsteal_kswapd",
	"pgsteal_direct",
	"pgscan_kswapd",
	"pgscan_direct",
	"pgscan_direct_throttle",

#ifdef CONFIG_NUMA
	"zone_reclaim_failed",
#endif
	"pginodesteal",
	"slabs_scanned",
	"kswapd_inodesteal",
	"kswapd_low_wmark_hit_quickly",
	"kswapd_high_wmark_hit_quickly",
	"pageoutrun",

	"pgrotated",

	"drop_pagecache",
	"drop_slab",
	"oom_kill",

#ifdef CONFIG_NUMA_BALANCING
	"numa_pte_updates",
	"numa_huge_pte_updates",
	"numa_hint_faults",
	"numa_hint_faults_local",
	"numa_pages_migrated",
#endif
#ifdef CONFIG_MIGRATION
	"pgmigrate_success",
	"pgmigrate_fail",
#endif
#ifdef CONFIG_COMPACTION
	"compact_migrate_scanned",
	"compact_free_scanned",
	"compact_isolated",
	"compact_stall",
	"compact_fail",
	"compact_success",
	"compact_daemon_wake",
	"compact_daemon_migrate_scanned",
	"compact_daemon_free_scanned",
#endif

#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	"thp_fault_alloc",
	"thp_fault_fallback",
	"thp_collapse_alloc",
	"thp_collapse_alloc_failed",
	"thp_file_alloc",
	"thp_file_mapped",
	"thp_split_page",
	"thp_split_page_failed",
	"thp_deferred_split_page",
	"thp_split_pmd",
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
	"thp_split_pud",
#endif
	"thp_zero_page_alloc",
	"thp_zero_page_alloc_failed",
	"thp_swpout",
	"thp_swpout_fallback",
#endif
#ifdef CONFIG_MEMORY_BALLOON
	"balloon_inflate",
	"balloon_deflate",
#ifdef CONFIG_BALLOON_COMPACTION
	"balloon_migrate",
#endif
#endif /* CONFIG_MEMORY_BALLOON */
#ifdef CONFIG_DEBUG_TLBFLUSH
	"nr_tlb_remote_flush",
	"nr_tlb_remote_flush_received",
	"nr_tlb_local_flush_all",
	"nr_tlb_local_flush_one",
#endif /* CONFIG_DEBUG_TLBFLUSH */

#ifdef CONFIG_DEBUG_VM_VMACACHE
	"vmacache_find_calls",
	"vmacache_find_hits",
#endif
#ifdef CONFIG_SWAP
	"swap_ra",
	"swap_ra_hit",
#endif
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */

#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \
     defined(CONFIG_PROC_FS)
static void *frag_start(struct seq_file *m, loff_t *pos)
{
	pg_data_t *pgdat;
	loff_t node = *pos;

	for (pgdat = first_online_pgdat();
	     pgdat && node;
	     pgdat = next_online_pgdat(pgdat))
		--node;

	return pgdat;
}

static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	(*pos)++;
	return next_online_pgdat(pgdat);
}

static void frag_stop(struct seq_file *m, void *arg)
{
}

/*
 * Walk zones in a node and print using a callback.
 * If @assert_populated is true, only use callback for zones that are populated.
 */
static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
		bool assert_populated, bool nolock,
		void (*print)(struct seq_file *m, pg_data_t *, struct zone *))
{
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (assert_populated && !populated_zone(zone))
			continue;

		if (!nolock)
			spin_lock_irqsave(&zone->lock, flags);
		print(m, pgdat, zone);
		if (!nolock)
			spin_unlock_irqrestore(&zone->lock, flags);
	}
}
#endif

#ifdef CONFIG_PROC_FS
static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
						struct zone *zone)
{
	int order;

	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
	for (order = 0; order < MAX_ORDER; ++order)
		seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
	seq_putc(m, '\n');
}

/*
 * This walks the free areas for each zone.
 */
static int frag_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;
	walk_zones_in_node(m, pgdat, true, false, frag_show_print);
	return 0;
}

static void pagetypeinfo_showfree_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	int order, mtype;

	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) {
		seq_printf(m, "Node %4d, zone %8s, type %12s ",
					pgdat->node_id,
					zone->name,
					migratetype_names[mtype]);
		for (order = 0; order < MAX_ORDER; ++order) {
			unsigned long freecount = 0;
			struct free_area *area;
			struct list_head *curr;

			area = &(zone->free_area[order]);

			list_for_each(curr, &area->free_list[mtype])
				freecount++;
			seq_printf(m, "%6lu ", freecount);
		}
		seq_putc(m, '\n');
	}
}

/* Print out the free pages at each order for each migatetype */
static int pagetypeinfo_showfree(struct seq_file *m, void *arg)
{
	int order;
	pg_data_t *pgdat = (pg_data_t *)arg;

	/* Print header */
	seq_printf(m, "%-43s ", "Free pages count per migrate type at order");
	for (order = 0; order < MAX_ORDER; ++order)
		seq_printf(m, "%6d ", order);
	seq_putc(m, '\n');

	walk_zones_in_node(m, pgdat, true, false, pagetypeinfo_showfree_print);

	return 0;
}

static void pagetypeinfo_showblockcount_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	int mtype;
	unsigned long pfn;
	unsigned long start_pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	unsigned long count[MIGRATE_TYPES] = { 0, };

	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		struct page *page;

		page = pfn_to_online_page(pfn);
		if (!page)
			continue;

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
			continue;

		if (page_zone(page) != zone)
			continue;

		mtype = get_pageblock_migratetype(page);

		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
	}

	/* Print counts */
	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
		seq_printf(m, "%12lu ", count[mtype]);
	seq_putc(m, '\n');
}

/* Print out the number of pageblocks for each migratetype */
static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
{
	int mtype;
	pg_data_t *pgdat = (pg_data_t *)arg;

	seq_printf(m, "\n%-23s", "Number of blocks type ");
	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
		seq_printf(m, "%12s ", migratetype_names[mtype]);
	seq_putc(m, '\n');
	walk_zones_in_node(m, pgdat, true, false,
		pagetypeinfo_showblockcount_print);

	return 0;
}

/*
 * Print out the number of pageblocks for each migratetype that contain pages
 * of other types. This gives an indication of how well fallbacks are being
 * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
 * to determine what is going on
 */
static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
{
#ifdef CONFIG_PAGE_OWNER
	int mtype;

	if (!static_branch_unlikely(&page_owner_inited))
		return;

	drain_all_pages(NULL);

	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
		seq_printf(m, "%12s ", migratetype_names[mtype]);
	seq_putc(m, '\n');

	walk_zones_in_node(m, pgdat, true, true,
		pagetypeinfo_showmixedcount_print);
#endif /* CONFIG_PAGE_OWNER */
}

/*
 * This prints out statistics in relation to grouping pages by mobility.
 * It is expensive to collect so do not constantly read the file.
 */
static int pagetypeinfo_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_MEMORY))
		return 0;

	seq_printf(m, "Page block order: %d\n", pageblock_order);
	seq_printf(m, "Pages per block:  %lu\n", pageblock_nr_pages);
	seq_putc(m, '\n');
	pagetypeinfo_showfree(m, pgdat);
	pagetypeinfo_showblockcount(m, pgdat);
	pagetypeinfo_showmixedcount(m, pgdat);

	return 0;
}

static const struct seq_operations fragmentation_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

static const struct seq_operations pagetypeinfo_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
{
	int zid;

	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		struct zone *compare = &pgdat->node_zones[zid];

		if (populated_zone(compare))
			return zone == compare;
	}

	return false;
}

static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
{
	int i;
	seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
	if (is_zone_first_populated(pgdat, zone)) {
		seq_printf(m, "\n  per-node stats");
		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
			seq_printf(m, "\n      %-12s %lu",
				vmstat_text[i + NR_VM_ZONE_STAT_ITEMS +
				NR_VM_NUMA_STAT_ITEMS],
				node_page_state(pgdat, i));
		}
	}
	seq_printf(m,
		   "\n  pages free     %lu"
		   "\n        min      %lu"
		   "\n        low      %lu"
		   "\n        high     %lu"
		   "\n        spanned  %lu"
		   "\n        present  %lu"
		   "\n        managed  %lu",
		   zone_page_state(zone, NR_FREE_PAGES),
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
		   zone->spanned_pages,
		   zone->present_pages,
		   zone_managed_pages(zone));

	seq_printf(m,
		   "\n        protection: (%ld",
		   zone->lowmem_reserve[0]);
	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
		seq_printf(m, ", %ld", zone->lowmem_reserve[i]);
	seq_putc(m, ')');

	/* If unpopulated, no other information is useful */
	if (!populated_zone(zone)) {
		seq_putc(m, '\n');
		return;
	}

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		seq_printf(m, "\n      %-12s %lu", vmstat_text[i],
				zone_page_state(zone, i));

#ifdef CONFIG_NUMA
	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		seq_printf(m, "\n      %-12s %lu",
				vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
				zone_numa_state_snapshot(zone, i));
#endif

	seq_printf(m, "\n  pagesets");
	for_each_online_cpu(i) {
		struct per_cpu_pageset *pageset;

		pageset = per_cpu_ptr(zone->pageset, i);
		seq_printf(m,
			   "\n    cpu: %i"
			   "\n              count: %i"
			   "\n              high:  %i"
			   "\n              batch: %i",
			   i,
			   pageset->pcp.count,
			   pageset->pcp.high,
			   pageset->pcp.batch);
#ifdef CONFIG_SMP
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
#endif
	}
	seq_printf(m,
		   "\n  node_unreclaimable:  %u"
		   "\n  start_pfn:           %lu",
		   pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES,
		   zone->zone_start_pfn);
	seq_putc(m, '\n');
}

/*
 * Output information about zones in @pgdat.  All zones are printed regardless
 * of whether they are populated or not: lowmem_reserve_ratio operates on the
 * set of all zones and userspace would not be aware of such zones if they are
 * suppressed here (zoneinfo displays the effect of lowmem_reserve_ratio).
 */
static int zoneinfo_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;
	walk_zones_in_node(m, pgdat, false, false, zoneinfo_show_print);
	return 0;
}

static const struct seq_operations zoneinfo_op = {
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

enum writeback_stat_item {
	NR_DIRTY_THRESHOLD,
	NR_DIRTY_BG_THRESHOLD,
	NR_VM_WRITEBACK_STAT_ITEMS,
};

static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
	unsigned long *v;
	int i, stat_items_size;

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_NUMA_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);

#ifdef CONFIG_VM_EVENT_COUNTERS
	stat_items_size += sizeof(struct vm_event_state);
#endif

	BUILD_BUG_ON(stat_items_size !=
		     ARRAY_SIZE(vmstat_text) * sizeof(unsigned long));
	v = kmalloc(stat_items_size, GFP_KERNEL);
	m->private = v;
	if (!v)
		return ERR_PTR(-ENOMEM);
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_zone_page_state(i);
	v += NR_VM_ZONE_STAT_ITEMS;

#ifdef CONFIG_NUMA
	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		v[i] = global_numa_state(i);
	v += NR_VM_NUMA_STAT_ITEMS;
#endif

	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
		v[i] = global_node_page_state(i);
	v += NR_VM_NODE_STAT_ITEMS;

	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
			    v + NR_DIRTY_THRESHOLD);
	v += NR_VM_WRITEBACK_STAT_ITEMS;

#ifdef CONFIG_VM_EVENT_COUNTERS
	all_vm_events(v);
	v[PGPGIN] /= 2;		/* sectors -> kbytes */
	v[PGPGOUT] /= 2;
#endif
	return (unsigned long *)m->private + *pos;
}

static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
{
	(*pos)++;
	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	return (unsigned long *)m->private + *pos;
}

static int vmstat_show(struct seq_file *m, void *arg)
{
	unsigned long *l = arg;
	unsigned long off = l - (unsigned long *)m->private;

	seq_puts(m, vmstat_text[off]);
	seq_put_decimal_ull(m, " ", *l);
	seq_putc(m, '\n');
	return 0;
}

static void vmstat_stop(struct seq_file *m, void *arg)
{
	kfree(m->private);
	m->private = NULL;
}

static const struct seq_operations vmstat_op = {
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};
#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;

#ifdef CONFIG_PROC_FS
static void refresh_vm_stats(struct work_struct *work)
{
	refresh_cpu_vm_stats(true);
}

int vmstat_refresh(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos)
{
	long val;
	int err;
	int i;

	/*
	 * The regular update, every sysctl_stat_interval, may come later
	 * than expected: leaving a significant amount in per_cpu buckets.
	 * This is particularly misleading when checking a quantity of HUGE
	 * pages, immediately after running a test.  /proc/sys/vm/stat_refresh,
	 * which can equally be echo'ed to or cat'ted from (by root),
	 * can be used to update the stats just before reading them.
	 *
	 * Oh, and since global_zone_page_state() etc. are so careful to hide
	 * transiently negative values, report an error here if any of
	 * the stats is negative, so we know to go looking for imbalance.
	 */
	err = schedule_on_each_cpu(refresh_vm_stats);
	if (err)
		return err;
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
		val = atomic_long_read(&vm_zone_stat[i]);
		if (val < 0) {
			pr_warn("%s: %s %ld\n",
				__func__, vmstat_text[i], val);
			err = -EINVAL;
		}
	}
#ifdef CONFIG_NUMA
	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
		val = atomic_long_read(&vm_numa_stat[i]);
		if (val < 0) {
			pr_warn("%s: %s %ld\n",
				__func__, vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], val);
			err = -EINVAL;
		}
	}
#endif
	if (err)
		return err;
	if (write)
		*ppos += *lenp;
	else
		*lenp = 0;
	return 0;
}
#endif /* CONFIG_PROC_FS */

static void vmstat_update(struct work_struct *w)
{
	if (refresh_cpu_vm_stats(true)) {
		/*
		 * Counters were updated so we expect more updates
		 * to occur in the future. Keep on running the
		 * update worker thread.
		 */
		queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
				this_cpu_ptr(&vmstat_work),
				round_jiffies_relative(sysctl_stat_interval));
	}
}

/*
 * Switch off vmstat processing and then fold all the remaining differentials
 * until the diffs stay at zero. The function is used by NOHZ and can only be
 * invoked when tick processing is not active.
 */
/*
 * Check if the diffs for a certain cpu indicate that
 * an update is needed.
 */
static bool need_update(int cpu)
{
	struct zone *zone;

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);

		BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
#ifdef CONFIG_NUMA
		BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 2);
#endif

		/*
		 * The fast way of checking if there are any vmstat diffs.
		 */
		if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS *
			       sizeof(p->vm_stat_diff[0])))
			return true;
#ifdef CONFIG_NUMA
		if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS *
			       sizeof(p->vm_numa_stat_diff[0])))
			return true;
#endif
	}
	return false;
}

/*
 * Switch off vmstat processing and then fold all the remaining differentials
 * until the diffs stay at zero. The function is used by NOHZ and can only be
 * invoked when tick processing is not active.
 */
void quiet_vmstat(void)
{
	if (system_state != SYSTEM_RUNNING)
		return;

	if (!delayed_work_pending(this_cpu_ptr(&vmstat_work)))
		return;

	if (!need_update(smp_processor_id()))
		return;

	/*
	 * Just refresh counters and do not care about the pending delayed
	 * vmstat_update. It doesn't fire that often to matter and canceling
	 * it would be too expensive from this path.
	 * vmstat_shepherd will take care about that for us.
	 */
	refresh_cpu_vm_stats(false);
}

/*
 * Shepherd worker thread that checks the
 * differentials of processors that have their worker
 * threads for vm statistics updates disabled because of
 * inactivity.
 */
static void vmstat_shepherd(struct work_struct *w);

static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd);

static void vmstat_shepherd(struct work_struct *w)
{
	int cpu;

	get_online_cpus();
	/* Check processors whose vmstat worker threads have been disabled */
	for_each_online_cpu(cpu) {
		struct delayed_work *dw = &per_cpu(vmstat_work, cpu);

		if (!delayed_work_pending(dw) && need_update(cpu))
			queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
	}
	put_online_cpus();

	schedule_delayed_work(&shepherd,
		round_jiffies_relative(sysctl_stat_interval));
}

static void __init start_shepherd_timer(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
			vmstat_update);

	schedule_delayed_work(&shepherd,
		round_jiffies_relative(sysctl_stat_interval));
}

static void __init init_cpu_node_state(void)
{
	int node;

	for_each_online_node(node) {
		if (cpumask_weight(cpumask_of_node(node)) > 0)
			node_set_state(node, N_CPU);
	}
}

static int vmstat_cpu_online(unsigned int cpu)
{
	refresh_zone_stat_thresholds();
	node_set_state(cpu_to_node(cpu), N_CPU);
	return 0;
}

static int vmstat_cpu_down_prep(unsigned int cpu)
{
	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
	return 0;
}

static int vmstat_cpu_dead(unsigned int cpu)
{
	const struct cpumask *node_cpus;
	int node;

	node = cpu_to_node(cpu);

	refresh_zone_stat_thresholds();
	node_cpus = cpumask_of_node(node);
	if (cpumask_weight(node_cpus) > 0)
		return 0;

	node_clear_state(node, N_CPU);
	return 0;
}

#endif

struct workqueue_struct *mm_percpu_wq;

void __init init_mm_internals(void)
{
	int ret __maybe_unused;

	mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0);

#ifdef CONFIG_SMP
	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
					NULL, vmstat_cpu_dead);
	if (ret < 0)
		pr_err("vmstat: failed to register 'dead' hotplug state\n");

	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
					vmstat_cpu_online,
					vmstat_cpu_down_prep);
	if (ret < 0)
		pr_err("vmstat: failed to register 'online' hotplug state\n");

	get_online_cpus();
	init_cpu_node_state();
	put_online_cpus();

	start_shepherd_timer();
#endif
#ifdef CONFIG_PROC_FS
	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
	proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
#endif
}

#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)

/*
 * Return an index indicating how much of the available free memory is
 * unusable for an allocation of the requested size.
 */
static int unusable_free_index(unsigned int order,
				struct contig_page_info *info)
{
	/* No free memory is interpreted as all free memory is unusable */
	if (info->free_pages == 0)
		return 1000;

	/*
	 * Index should be a value between 0 and 1. Return a value to 3
	 * decimal places.
	 *
	 * 0 => no fragmentation
	 * 1 => high fragmentation
	 */
	return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages);

}

static void unusable_show_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	unsigned int order;
	int index;
	struct contig_page_info info;

	seq_printf(m, "Node %d, zone %8s ",
				pgdat->node_id,
				zone->name);
	for (order = 0; order < MAX_ORDER; ++order) {
		fill_contig_page_info(zone, order, &info);
		index = unusable_free_index(order, &info);
		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
	}

	seq_putc(m, '\n');
}

/*
 * Display unusable free space index
 *
 * The unusable free space index measures how much of the available free
 * memory cannot be used to satisfy an allocation of a given size and is a
 * value between 0 and 1. The higher the value, the more of free memory is
 * unusable and by implication, the worse the external fragmentation is. This
 * can be expressed as a percentage by multiplying by 100.
 */
static int unusable_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_MEMORY))
		return 0;

	walk_zones_in_node(m, pgdat, true, false, unusable_show_print);

	return 0;
}

static const struct seq_operations unusable_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= unusable_show,
};

static int unusable_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &unusable_op);
}

static const struct file_operations unusable_file_ops = {
	.open		= unusable_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static void extfrag_show_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	unsigned int order;
	int index;

	/* Alloc on stack as interrupts are disabled for zone walk */
	struct contig_page_info info;

	seq_printf(m, "Node %d, zone %8s ",
				pgdat->node_id,
				zone->name);
	for (order = 0; order < MAX_ORDER; ++order) {
		fill_contig_page_info(zone, order, &info);
		index = __fragmentation_index(order, &info);
		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
	}

	seq_putc(m, '\n');
}

/*
 * Display fragmentation index for orders that allocations would fail for
 */
static int extfrag_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	walk_zones_in_node(m, pgdat, true, false, extfrag_show_print);

	return 0;
}

static const struct seq_operations extfrag_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= extfrag_show,
};

static int extfrag_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &extfrag_op);
}

static const struct file_operations extfrag_file_ops = {
	.open		= extfrag_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init extfrag_debug_init(void)
{
	struct dentry *extfrag_debug_root;

	extfrag_debug_root = debugfs_create_dir("extfrag", NULL);

	debugfs_create_file("unusable_index", 0444, extfrag_debug_root, NULL,
			    &unusable_file_ops);

	debugfs_create_file("extfrag_index", 0444, extfrag_debug_root, NULL,
			    &extfrag_file_ops);

	return 0;
}

module_init(extfrag_debug_init);
#endif