summaryrefslogtreecommitdiff
path: root/mm/zsmalloc.c
blob: 84beadc088b833fd40fc79b72d4692ea14427ecd (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
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
/*
 * zsmalloc memory allocator
 *
 * Copyright (C) 2011  Nitin Gupta
 * Copyright (C) 2012, 2013 Minchan Kim
 *
 * This code is released using a dual license strategy: BSD/GPL
 * You can choose the license that better fits your requirements.
 *
 * Released under the terms of 3-clause BSD License
 * Released under the terms of GNU General Public License Version 2.0
 */

/*
 * Following is how we use various fields and flags of underlying
 * struct page(s) to form a zspage.
 *
 * Usage of struct page fields:
 *	page->private: points to zspage
 *	page->index: links together all component pages of a zspage
 *		For the huge page, this is always 0, so we use this field
 *		to store handle.
 *	page->page_type: first object offset in a subpage of zspage
 *
 * Usage of struct page flags:
 *	PG_private: identifies the first component page
 *	PG_owner_priv_1: identifies the huge component page
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

/*
 * lock ordering:
 *	page_lock
 *	pool->lock
 *	zspage->lock
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/highmem.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/cpumask.h>
#include <linux/cpu.h>
#include <linux/vmalloc.h>
#include <linux/preempt.h>
#include <linux/spinlock.h>
#include <linux/shrinker.h>
#include <linux/types.h>
#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
#include <linux/migrate.h>
#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
#include <linux/local_lock.h>

#define ZSPAGE_MAGIC	0x58

/*
 * This must be power of 2 and greater than or equal to sizeof(link_free).
 * These two conditions ensure that any 'struct link_free' itself doesn't
 * span more than 1 page which avoids complex case of mapping 2 pages simply
 * to restore link_free pointer values.
 */
#define ZS_ALIGN		8

#define ZS_HANDLE_SIZE (sizeof(unsigned long))

/*
 * Object location (<PFN>, <obj_idx>) is encoded as
 * a single (unsigned long) handle value.
 *
 * Note that object index <obj_idx> starts from 0.
 *
 * This is made more complicated by various memory models and PAE.
 */

#ifndef MAX_POSSIBLE_PHYSMEM_BITS
#ifdef MAX_PHYSMEM_BITS
#define MAX_POSSIBLE_PHYSMEM_BITS MAX_PHYSMEM_BITS
#else
/*
 * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
 * be PAGE_SHIFT
 */
#define MAX_POSSIBLE_PHYSMEM_BITS BITS_PER_LONG
#endif
#endif

#define _PFN_BITS		(MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT)

/*
 * Head in allocated object should have OBJ_ALLOCATED_TAG
 * to identify the object was allocated or not.
 * It's okay to add the status bit in the least bit because
 * header keeps handle which is 4byte-aligned address so we
 * have room for two bit at least.
 */
#define OBJ_ALLOCATED_TAG 1

#define OBJ_TAG_BITS	1
#define OBJ_TAG_MASK	OBJ_ALLOCATED_TAG

#define OBJ_INDEX_BITS	(BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
#define OBJ_INDEX_MASK	((_AC(1, UL) << OBJ_INDEX_BITS) - 1)

#define HUGE_BITS	1
#define FULLNESS_BITS	4
#define CLASS_BITS	8
#define ISOLATED_BITS	5
#define MAGIC_VAL_BITS	8

#define MAX(a, b) ((a) >= (b) ? (a) : (b))

#define ZS_MAX_PAGES_PER_ZSPAGE	(_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL))

/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
#define ZS_MIN_ALLOC_SIZE \
	MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
/* each chunk includes extra space to keep handle */
#define ZS_MAX_ALLOC_SIZE	PAGE_SIZE

/*
 * On systems with 4K page size, this gives 255 size classes! There is a
 * trader-off here:
 *  - Large number of size classes is potentially wasteful as free page are
 *    spread across these classes
 *  - Small number of size classes causes large internal fragmentation
 *  - Probably its better to use specific size classes (empirically
 *    determined). NOTE: all those class sizes must be set as multiple of
 *    ZS_ALIGN to make sure link_free itself never has to span 2 pages.
 *
 *  ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
 *  (reason above)
 */
#define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> CLASS_BITS)
#define ZS_SIZE_CLASSES	(DIV_ROUND_UP(ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE, \
				      ZS_SIZE_CLASS_DELTA) + 1)

/*
 * Pages are distinguished by the ratio of used memory (that is the ratio
 * of ->inuse objects to all objects that page can store). For example,
 * INUSE_RATIO_10 means that the ratio of used objects is > 0% and <= 10%.
 *
 * The number of fullness groups is not random. It allows us to keep
 * difference between the least busy page in the group (minimum permitted
 * number of ->inuse objects) and the most busy page (maximum permitted
 * number of ->inuse objects) at a reasonable value.
 */
enum fullness_group {
	ZS_INUSE_RATIO_0,
	ZS_INUSE_RATIO_10,
	/* NOTE: 8 more fullness groups here */
	ZS_INUSE_RATIO_99       = 10,
	ZS_INUSE_RATIO_100,
	NR_FULLNESS_GROUPS,
};

enum class_stat_type {
	/* NOTE: stats for 12 fullness groups here: from inuse 0 to 100 */
	ZS_OBJS_ALLOCATED       = NR_FULLNESS_GROUPS,
	ZS_OBJS_INUSE,
	NR_CLASS_STAT_TYPES,
};

struct zs_size_stat {
	unsigned long objs[NR_CLASS_STAT_TYPES];
};

#ifdef CONFIG_ZSMALLOC_STAT
static struct dentry *zs_stat_root;
#endif

static size_t huge_class_size;

struct size_class {
	struct list_head fullness_list[NR_FULLNESS_GROUPS];
	/*
	 * Size of objects stored in this class. Must be multiple
	 * of ZS_ALIGN.
	 */
	int size;
	int objs_per_zspage;
	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
	int pages_per_zspage;

	unsigned int index;
	struct zs_size_stat stats;
};

/*
 * Placed within free objects to form a singly linked list.
 * For every zspage, zspage->freeobj gives head of this list.
 *
 * This must be power of 2 and less than or equal to ZS_ALIGN
 */
struct link_free {
	union {
		/*
		 * Free object index;
		 * It's valid for non-allocated object
		 */
		unsigned long next;
		/*
		 * Handle of allocated object.
		 */
		unsigned long handle;
	};
};

struct zs_pool {
	const char *name;

	struct size_class *size_class[ZS_SIZE_CLASSES];
	struct kmem_cache *handle_cachep;
	struct kmem_cache *zspage_cachep;

	atomic_long_t pages_allocated;

	struct zs_pool_stats stats;

	/* Compact classes */
	struct shrinker shrinker;

#ifdef CONFIG_ZSMALLOC_STAT
	struct dentry *stat_dentry;
#endif
#ifdef CONFIG_COMPACTION
	struct work_struct free_work;
#endif
	spinlock_t lock;
	atomic_t compaction_in_progress;
};

struct zspage {
	struct {
		unsigned int huge:HUGE_BITS;
		unsigned int fullness:FULLNESS_BITS;
		unsigned int class:CLASS_BITS + 1;
		unsigned int isolated:ISOLATED_BITS;
		unsigned int magic:MAGIC_VAL_BITS;
	};
	unsigned int inuse;
	unsigned int freeobj;
	struct page *first_page;
	struct list_head list; /* fullness list */
	struct zs_pool *pool;
	rwlock_t lock;
};

struct mapping_area {
	local_lock_t lock;
	char *vm_buf; /* copy buffer for objects that span pages */
	char *vm_addr; /* address of kmap_atomic()'ed pages */
	enum zs_mapmode vm_mm; /* mapping mode */
};

/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
static void SetZsHugePage(struct zspage *zspage)
{
	zspage->huge = 1;
}

static bool ZsHugePage(struct zspage *zspage)
{
	return zspage->huge;
}

static void migrate_lock_init(struct zspage *zspage);
static void migrate_read_lock(struct zspage *zspage);
static void migrate_read_unlock(struct zspage *zspage);

#ifdef CONFIG_COMPACTION
static void migrate_write_lock(struct zspage *zspage);
static void migrate_write_lock_nested(struct zspage *zspage);
static void migrate_write_unlock(struct zspage *zspage);
static void kick_deferred_free(struct zs_pool *pool);
static void init_deferred_free(struct zs_pool *pool);
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage);
#else
static void migrate_write_lock(struct zspage *zspage) {}
static void migrate_write_lock_nested(struct zspage *zspage) {}
static void migrate_write_unlock(struct zspage *zspage) {}
static void kick_deferred_free(struct zs_pool *pool) {}
static void init_deferred_free(struct zs_pool *pool) {}
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {}
#endif

static int create_cache(struct zs_pool *pool)
{
	pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
					0, 0, NULL);
	if (!pool->handle_cachep)
		return 1;

	pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage),
					0, 0, NULL);
	if (!pool->zspage_cachep) {
		kmem_cache_destroy(pool->handle_cachep);
		pool->handle_cachep = NULL;
		return 1;
	}

	return 0;
}

static void destroy_cache(struct zs_pool *pool)
{
	kmem_cache_destroy(pool->handle_cachep);
	kmem_cache_destroy(pool->zspage_cachep);
}

static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
{
	return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
			gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
}

static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
{
	kmem_cache_free(pool->handle_cachep, (void *)handle);
}

static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags)
{
	return kmem_cache_zalloc(pool->zspage_cachep,
			flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
}

static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
{
	kmem_cache_free(pool->zspage_cachep, zspage);
}

/* pool->lock(which owns the handle) synchronizes races */
static void record_obj(unsigned long handle, unsigned long obj)
{
	*(unsigned long *)handle = obj;
}

/* zpool driver */

#ifdef CONFIG_ZPOOL

static void *zs_zpool_create(const char *name, gfp_t gfp)
{
	/*
	 * Ignore global gfp flags: zs_malloc() may be invoked from
	 * different contexts and its caller must provide a valid
	 * gfp mask.
	 */
	return zs_create_pool(name);
}

static void zs_zpool_destroy(void *pool)
{
	zs_destroy_pool(pool);
}

static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	*handle = zs_malloc(pool, size, gfp);

	if (IS_ERR_VALUE(*handle))
		return PTR_ERR((void *)*handle);
	return 0;
}
static void zs_zpool_free(void *pool, unsigned long handle)
{
	zs_free(pool, handle);
}

static void *zs_zpool_map(void *pool, unsigned long handle,
			enum zpool_mapmode mm)
{
	enum zs_mapmode zs_mm;

	switch (mm) {
	case ZPOOL_MM_RO:
		zs_mm = ZS_MM_RO;
		break;
	case ZPOOL_MM_WO:
		zs_mm = ZS_MM_WO;
		break;
	case ZPOOL_MM_RW:
	default:
		zs_mm = ZS_MM_RW;
		break;
	}

	return zs_map_object(pool, handle, zs_mm);
}
static void zs_zpool_unmap(void *pool, unsigned long handle)
{
	zs_unmap_object(pool, handle);
}

static u64 zs_zpool_total_size(void *pool)
{
	return zs_get_total_pages(pool) << PAGE_SHIFT;
}

static struct zpool_driver zs_zpool_driver = {
	.type =			  "zsmalloc",
	.owner =		  THIS_MODULE,
	.create =		  zs_zpool_create,
	.destroy =		  zs_zpool_destroy,
	.malloc_support_movable = true,
	.malloc =		  zs_zpool_malloc,
	.free =			  zs_zpool_free,
	.map =			  zs_zpool_map,
	.unmap =		  zs_zpool_unmap,
	.total_size =		  zs_zpool_total_size,
};

MODULE_ALIAS("zpool-zsmalloc");
#endif /* CONFIG_ZPOOL */

/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = {
	.lock	= INIT_LOCAL_LOCK(lock),
};

static __maybe_unused int is_first_page(struct page *page)
{
	return PagePrivate(page);
}

/* Protected by pool->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
	return zspage->inuse;
}


static inline void mod_zspage_inuse(struct zspage *zspage, int val)
{
	zspage->inuse += val;
}

static inline struct page *get_first_page(struct zspage *zspage)
{
	struct page *first_page = zspage->first_page;

	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
	return first_page;
}

static inline unsigned int get_first_obj_offset(struct page *page)
{
	return page->page_type;
}

static inline void set_first_obj_offset(struct page *page, unsigned int offset)
{
	page->page_type = offset;
}

static inline unsigned int get_freeobj(struct zspage *zspage)
{
	return zspage->freeobj;
}

static inline void set_freeobj(struct zspage *zspage, unsigned int obj)
{
	zspage->freeobj = obj;
}

static void get_zspage_mapping(struct zspage *zspage,
			       unsigned int *class_idx,
			       int *fullness)
{
	BUG_ON(zspage->magic != ZSPAGE_MAGIC);

	*fullness = zspage->fullness;
	*class_idx = zspage->class;
}

static struct size_class *zspage_class(struct zs_pool *pool,
				       struct zspage *zspage)
{
	return pool->size_class[zspage->class];
}

static void set_zspage_mapping(struct zspage *zspage,
			       unsigned int class_idx,
			       int fullness)
{
	zspage->class = class_idx;
	zspage->fullness = fullness;
}

/*
 * zsmalloc divides the pool into various size classes where each
 * class maintains a list of zspages where each zspage is divided
 * into equal sized chunks. Each allocation falls into one of these
 * classes depending on its size. This function returns index of the
 * size class which has chunk size big enough to hold the given size.
 */
static int get_size_class_index(int size)
{
	int idx = 0;

	if (likely(size > ZS_MIN_ALLOC_SIZE))
		idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
				ZS_SIZE_CLASS_DELTA);

	return min_t(int, ZS_SIZE_CLASSES - 1, idx);
}

static inline void class_stat_inc(struct size_class *class,
				int type, unsigned long cnt)
{
	class->stats.objs[type] += cnt;
}

static inline void class_stat_dec(struct size_class *class,
				int type, unsigned long cnt)
{
	class->stats.objs[type] -= cnt;
}

static inline unsigned long zs_stat_get(struct size_class *class, int type)
{
	return class->stats.objs[type];
}

#ifdef CONFIG_ZSMALLOC_STAT

static void __init zs_stat_init(void)
{
	if (!debugfs_initialized()) {
		pr_warn("debugfs not available, stat dir not created\n");
		return;
	}

	zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
}

static void __exit zs_stat_exit(void)
{
	debugfs_remove_recursive(zs_stat_root);
}

static unsigned long zs_can_compact(struct size_class *class);

static int zs_stats_size_show(struct seq_file *s, void *v)
{
	int i, fg;
	struct zs_pool *pool = s->private;
	struct size_class *class;
	int objs_per_zspage;
	unsigned long obj_allocated, obj_used, pages_used, freeable;
	unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
	unsigned long total_freeable = 0;
	unsigned long inuse_totals[NR_FULLNESS_GROUPS] = {0, };

	seq_printf(s, " %5s %5s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %13s %10s %10s %16s %8s\n",
			"class", "size", "10%", "20%", "30%", "40%",
			"50%", "60%", "70%", "80%", "90%", "99%", "100%",
			"obj_allocated", "obj_used", "pages_used",
			"pages_per_zspage", "freeable");

	for (i = 0; i < ZS_SIZE_CLASSES; i++) {

		class = pool->size_class[i];

		if (class->index != i)
			continue;

		spin_lock(&pool->lock);

		seq_printf(s, " %5u %5u ", i, class->size);
		for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++) {
			inuse_totals[fg] += zs_stat_get(class, fg);
			seq_printf(s, "%9lu ", zs_stat_get(class, fg));
		}

		obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED);
		obj_used = zs_stat_get(class, ZS_OBJS_INUSE);
		freeable = zs_can_compact(class);
		spin_unlock(&pool->lock);

		objs_per_zspage = class->objs_per_zspage;
		pages_used = obj_allocated / objs_per_zspage *
				class->pages_per_zspage;

		seq_printf(s, "%13lu %10lu %10lu %16d %8lu\n",
			   obj_allocated, obj_used, pages_used,
			   class->pages_per_zspage, freeable);

		total_objs += obj_allocated;
		total_used_objs += obj_used;
		total_pages += pages_used;
		total_freeable += freeable;
	}

	seq_puts(s, "\n");
	seq_printf(s, " %5s %5s ", "Total", "");

	for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++)
		seq_printf(s, "%9lu ", inuse_totals[fg]);

	seq_printf(s, "%13lu %10lu %10lu %16s %8lu\n",
		   total_objs, total_used_objs, total_pages, "",
		   total_freeable);

	return 0;
}
DEFINE_SHOW_ATTRIBUTE(zs_stats_size);

static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
	if (!zs_stat_root) {
		pr_warn("no root stat dir, not creating <%s> stat dir\n", name);
		return;
	}

	pool->stat_dentry = debugfs_create_dir(name, zs_stat_root);

	debugfs_create_file("classes", S_IFREG | 0444, pool->stat_dentry, pool,
			    &zs_stats_size_fops);
}

static void zs_pool_stat_destroy(struct zs_pool *pool)
{
	debugfs_remove_recursive(pool->stat_dentry);
}

#else /* CONFIG_ZSMALLOC_STAT */
static void __init zs_stat_init(void)
{
}

static void __exit zs_stat_exit(void)
{
}

static inline void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
}

static inline void zs_pool_stat_destroy(struct zs_pool *pool)
{
}
#endif


/*
 * For each size class, zspages are divided into different groups
 * depending on their usage ratio. This function returns fullness
 * status of the given page.
 */
static int get_fullness_group(struct size_class *class, struct zspage *zspage)
{
	int inuse, objs_per_zspage, ratio;

	inuse = get_zspage_inuse(zspage);
	objs_per_zspage = class->objs_per_zspage;

	if (inuse == 0)
		return ZS_INUSE_RATIO_0;
	if (inuse == objs_per_zspage)
		return ZS_INUSE_RATIO_100;

	ratio = 100 * inuse / objs_per_zspage;
	/*
	 * Take integer division into consideration: a page with one inuse
	 * object out of 127 possible, will end up having 0 usage ratio,
	 * which is wrong as it belongs in ZS_INUSE_RATIO_10 fullness group.
	 */
	return ratio / 10 + 1;
}

/*
 * Each size class maintains various freelists and zspages are assigned
 * to one of these freelists based on the number of live objects they
 * have. This functions inserts the given zspage into the freelist
 * identified by <class, fullness_group>.
 */
static void insert_zspage(struct size_class *class,
				struct zspage *zspage,
				int fullness)
{
	class_stat_inc(class, fullness, 1);
	list_add(&zspage->list, &class->fullness_list[fullness]);
}

/*
 * This function removes the given zspage from the freelist identified
 * by <class, fullness_group>.
 */
static void remove_zspage(struct size_class *class,
				struct zspage *zspage,
				int fullness)
{
	VM_BUG_ON(list_empty(&class->fullness_list[fullness]));

	list_del_init(&zspage->list);
	class_stat_dec(class, fullness, 1);
}

/*
 * Each size class maintains zspages in different fullness groups depending
 * on the number of live objects they contain. When allocating or freeing
 * objects, the fullness status of the page can change, for instance, from
 * INUSE_RATIO_80 to INUSE_RATIO_70 when freeing an object. This function
 * checks if such a status change has occurred for the given page and
 * accordingly moves the page from the list of the old fullness group to that
 * of the new fullness group.
 */
static int fix_fullness_group(struct size_class *class, struct zspage *zspage)
{
	int class_idx;
	int currfg, newfg;

	get_zspage_mapping(zspage, &class_idx, &currfg);
	newfg = get_fullness_group(class, zspage);
	if (newfg == currfg)
		goto out;

	remove_zspage(class, zspage, currfg);
	insert_zspage(class, zspage, newfg);
	set_zspage_mapping(zspage, class_idx, newfg);
out:
	return newfg;
}

static struct zspage *get_zspage(struct page *page)
{
	struct zspage *zspage = (struct zspage *)page_private(page);

	BUG_ON(zspage->magic != ZSPAGE_MAGIC);
	return zspage;
}

static struct page *get_next_page(struct page *page)
{
	struct zspage *zspage = get_zspage(page);

	if (unlikely(ZsHugePage(zspage)))
		return NULL;

	return (struct page *)page->index;
}

/**
 * obj_to_location - get (<page>, <obj_idx>) from encoded object value
 * @obj: the encoded object value
 * @page: page object resides in zspage
 * @obj_idx: object index
 */
static void obj_to_location(unsigned long obj, struct page **page,
				unsigned int *obj_idx)
{
	obj >>= OBJ_TAG_BITS;
	*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
	*obj_idx = (obj & OBJ_INDEX_MASK);
}

static void obj_to_page(unsigned long obj, struct page **page)
{
	obj >>= OBJ_TAG_BITS;
	*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
}

/**
 * location_to_obj - get obj value encoded from (<page>, <obj_idx>)
 * @page: page object resides in zspage
 * @obj_idx: object index
 */
static unsigned long location_to_obj(struct page *page, unsigned int obj_idx)
{
	unsigned long obj;

	obj = page_to_pfn(page) << OBJ_INDEX_BITS;
	obj |= obj_idx & OBJ_INDEX_MASK;
	obj <<= OBJ_TAG_BITS;

	return obj;
}

static unsigned long handle_to_obj(unsigned long handle)
{
	return *(unsigned long *)handle;
}

static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle,
		int tag)
{
	unsigned long handle;
	struct zspage *zspage = get_zspage(page);

	if (unlikely(ZsHugePage(zspage))) {
		VM_BUG_ON_PAGE(!is_first_page(page), page);
		handle = page->index;
	} else
		handle = *(unsigned long *)obj;

	if (!(handle & tag))
		return false;

	/* Clear all tags before returning the handle */
	*phandle = handle & ~OBJ_TAG_MASK;
	return true;
}

static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
{
	return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG);
}

static void reset_page(struct page *page)
{
	__ClearPageMovable(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);
	page_mapcount_reset(page);
	page->index = 0;
}

static int trylock_zspage(struct zspage *zspage)
{
	struct page *cursor, *fail;

	for (cursor = get_first_page(zspage); cursor != NULL; cursor =
					get_next_page(cursor)) {
		if (!trylock_page(cursor)) {
			fail = cursor;
			goto unlock;
		}
	}

	return 1;
unlock:
	for (cursor = get_first_page(zspage); cursor != fail; cursor =
					get_next_page(cursor))
		unlock_page(cursor);

	return 0;
}

static void __free_zspage(struct zs_pool *pool, struct size_class *class,
				struct zspage *zspage)
{
	struct page *page, *next;
	int fg;
	unsigned int class_idx;

	get_zspage_mapping(zspage, &class_idx, &fg);

	assert_spin_locked(&pool->lock);

	VM_BUG_ON(get_zspage_inuse(zspage));
	VM_BUG_ON(fg != ZS_INUSE_RATIO_0);

	next = page = get_first_page(zspage);
	do {
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		next = get_next_page(page);
		reset_page(page);
		unlock_page(page);
		dec_zone_page_state(page, NR_ZSPAGES);
		put_page(page);
		page = next;
	} while (page != NULL);

	cache_free_zspage(pool, zspage);

	class_stat_dec(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
	atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated);
}

static void free_zspage(struct zs_pool *pool, struct size_class *class,
				struct zspage *zspage)
{
	VM_BUG_ON(get_zspage_inuse(zspage));
	VM_BUG_ON(list_empty(&zspage->list));

	/*
	 * Since zs_free couldn't be sleepable, this function cannot call
	 * lock_page. The page locks trylock_zspage got will be released
	 * by __free_zspage.
	 */
	if (!trylock_zspage(zspage)) {
		kick_deferred_free(pool);
		return;
	}

	remove_zspage(class, zspage, ZS_INUSE_RATIO_0);
	__free_zspage(pool, class, zspage);
}

/* Initialize a newly allocated zspage */
static void init_zspage(struct size_class *class, struct zspage *zspage)
{
	unsigned int freeobj = 1;
	unsigned long off = 0;
	struct page *page = get_first_page(zspage);

	while (page) {
		struct page *next_page;
		struct link_free *link;
		void *vaddr;

		set_first_obj_offset(page, off);

		vaddr = kmap_atomic(page);
		link = (struct link_free *)vaddr + off / sizeof(*link);

		while ((off += class->size) < PAGE_SIZE) {
			link->next = freeobj++ << OBJ_TAG_BITS;
			link += class->size / sizeof(*link);
		}

		/*
		 * We now come to the last (full or partial) object on this
		 * page, which must point to the first object on the next
		 * page (if present)
		 */
		next_page = get_next_page(page);
		if (next_page) {
			link->next = freeobj++ << OBJ_TAG_BITS;
		} else {
			/*
			 * Reset OBJ_TAG_BITS bit to last link to tell
			 * whether it's allocated object or not.
			 */
			link->next = -1UL << OBJ_TAG_BITS;
		}
		kunmap_atomic(vaddr);
		page = next_page;
		off %= PAGE_SIZE;
	}

	set_freeobj(zspage, 0);
}

static void create_page_chain(struct size_class *class, struct zspage *zspage,
				struct page *pages[])
{
	int i;
	struct page *page;
	struct page *prev_page = NULL;
	int nr_pages = class->pages_per_zspage;

	/*
	 * Allocate individual pages and link them together as:
	 * 1. all pages are linked together using page->index
	 * 2. each sub-page point to zspage using page->private
	 *
	 * we set PG_private to identify the first page (i.e. no other sub-page
	 * has this flag set).
	 */
	for (i = 0; i < nr_pages; i++) {
		page = pages[i];
		set_page_private(page, (unsigned long)zspage);
		page->index = 0;
		if (i == 0) {
			zspage->first_page = page;
			SetPagePrivate(page);
			if (unlikely(class->objs_per_zspage == 1 &&
					class->pages_per_zspage == 1))
				SetZsHugePage(zspage);
		} else {
			prev_page->index = (unsigned long)page;
		}
		prev_page = page;
	}
}

/*
 * Allocate a zspage for the given size class
 */
static struct zspage *alloc_zspage(struct zs_pool *pool,
					struct size_class *class,
					gfp_t gfp)
{
	int i;
	struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE];
	struct zspage *zspage = cache_alloc_zspage(pool, gfp);

	if (!zspage)
		return NULL;

	zspage->magic = ZSPAGE_MAGIC;
	migrate_lock_init(zspage);

	for (i = 0; i < class->pages_per_zspage; i++) {
		struct page *page;

		page = alloc_page(gfp);
		if (!page) {
			while (--i >= 0) {
				dec_zone_page_state(pages[i], NR_ZSPAGES);
				__free_page(pages[i]);
			}
			cache_free_zspage(pool, zspage);
			return NULL;
		}

		inc_zone_page_state(page, NR_ZSPAGES);
		pages[i] = page;
	}

	create_page_chain(class, zspage, pages);
	init_zspage(class, zspage);
	zspage->pool = pool;

	return zspage;
}

static struct zspage *find_get_zspage(struct size_class *class)
{
	int i;
	struct zspage *zspage;

	for (i = ZS_INUSE_RATIO_99; i >= ZS_INUSE_RATIO_0; i--) {
		zspage = list_first_entry_or_null(&class->fullness_list[i],
						  struct zspage, list);
		if (zspage)
			break;
	}

	return zspage;
}

static inline int __zs_cpu_up(struct mapping_area *area)
{
	/*
	 * Make sure we don't leak memory if a cpu UP notification
	 * and zs_init() race and both call zs_cpu_up() on the same cpu
	 */
	if (area->vm_buf)
		return 0;
	area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL);
	if (!area->vm_buf)
		return -ENOMEM;
	return 0;
}

static inline void __zs_cpu_down(struct mapping_area *area)
{
	kfree(area->vm_buf);
	area->vm_buf = NULL;
}

static void *__zs_map_object(struct mapping_area *area,
			struct page *pages[2], int off, int size)
{
	int sizes[2];
	void *addr;
	char *buf = area->vm_buf;

	/* disable page faults to match kmap_atomic() return conditions */
	pagefault_disable();

	/* no read fastpath */
	if (area->vm_mm == ZS_MM_WO)
		goto out;

	sizes[0] = PAGE_SIZE - off;
	sizes[1] = size - sizes[0];

	/* copy object to per-cpu buffer */
	addr = kmap_atomic(pages[0]);
	memcpy(buf, addr + off, sizes[0]);
	kunmap_atomic(addr);
	addr = kmap_atomic(pages[1]);
	memcpy(buf + sizes[0], addr, sizes[1]);
	kunmap_atomic(addr);
out:
	return area->vm_buf;
}

static void __zs_unmap_object(struct mapping_area *area,
			struct page *pages[2], int off, int size)
{
	int sizes[2];
	void *addr;
	char *buf;

	/* no write fastpath */
	if (area->vm_mm == ZS_MM_RO)
		goto out;

	buf = area->vm_buf;
	buf = buf + ZS_HANDLE_SIZE;
	size -= ZS_HANDLE_SIZE;
	off += ZS_HANDLE_SIZE;

	sizes[0] = PAGE_SIZE - off;
	sizes[1] = size - sizes[0];

	/* copy per-cpu buffer to object */
	addr = kmap_atomic(pages[0]);
	memcpy(addr + off, buf, sizes[0]);
	kunmap_atomic(addr);
	addr = kmap_atomic(pages[1]);
	memcpy(addr, buf + sizes[0], sizes[1]);
	kunmap_atomic(addr);

out:
	/* enable page faults to match kunmap_atomic() return conditions */
	pagefault_enable();
}

static int zs_cpu_prepare(unsigned int cpu)
{
	struct mapping_area *area;

	area = &per_cpu(zs_map_area, cpu);
	return __zs_cpu_up(area);
}

static int zs_cpu_dead(unsigned int cpu)
{
	struct mapping_area *area;

	area = &per_cpu(zs_map_area, cpu);
	__zs_cpu_down(area);
	return 0;
}

static bool can_merge(struct size_class *prev, int pages_per_zspage,
					int objs_per_zspage)
{
	if (prev->pages_per_zspage == pages_per_zspage &&
		prev->objs_per_zspage == objs_per_zspage)
		return true;

	return false;
}

static bool zspage_full(struct size_class *class, struct zspage *zspage)
{
	return get_zspage_inuse(zspage) == class->objs_per_zspage;
}

static bool zspage_empty(struct zspage *zspage)
{
	return get_zspage_inuse(zspage) == 0;
}

/**
 * zs_lookup_class_index() - Returns index of the zsmalloc &size_class
 * that hold objects of the provided size.
 * @pool: zsmalloc pool to use
 * @size: object size
 *
 * Context: Any context.
 *
 * Return: the index of the zsmalloc &size_class that hold objects of the
 * provided size.
 */
unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size)
{
	struct size_class *class;

	class = pool->size_class[get_size_class_index(size)];

	return class->index;
}
EXPORT_SYMBOL_GPL(zs_lookup_class_index);

unsigned long zs_get_total_pages(struct zs_pool *pool)
{
	return atomic_long_read(&pool->pages_allocated);
}
EXPORT_SYMBOL_GPL(zs_get_total_pages);

/**
 * zs_map_object - get address of allocated object from handle.
 * @pool: pool from which the object was allocated
 * @handle: handle returned from zs_malloc
 * @mm: mapping mode to use
 *
 * Before using an object allocated from zs_malloc, it must be mapped using
 * this function. When done with the object, it must be unmapped using
 * zs_unmap_object.
 *
 * Only one object can be mapped per cpu at a time. There is no protection
 * against nested mappings.
 *
 * This function returns with preemption and page faults disabled.
 */
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
			enum zs_mapmode mm)
{
	struct zspage *zspage;
	struct page *page;
	unsigned long obj, off;
	unsigned int obj_idx;

	struct size_class *class;
	struct mapping_area *area;
	struct page *pages[2];
	void *ret;

	/*
	 * Because we use per-cpu mapping areas shared among the
	 * pools/users, we can't allow mapping in interrupt context
	 * because it can corrupt another users mappings.
	 */
	BUG_ON(in_interrupt());

	/* It guarantees it can get zspage from handle safely */
	spin_lock(&pool->lock);
	obj = handle_to_obj(handle);
	obj_to_location(obj, &page, &obj_idx);
	zspage = get_zspage(page);

	/*
	 * migration cannot move any zpages in this zspage. Here, pool->lock
	 * is too heavy since callers would take some time until they calls
	 * zs_unmap_object API so delegate the locking from class to zspage
	 * which is smaller granularity.
	 */
	migrate_read_lock(zspage);
	spin_unlock(&pool->lock);

	class = zspage_class(pool, zspage);
	off = offset_in_page(class->size * obj_idx);

	local_lock(&zs_map_area.lock);
	area = this_cpu_ptr(&zs_map_area);
	area->vm_mm = mm;
	if (off + class->size <= PAGE_SIZE) {
		/* this object is contained entirely within a page */
		area->vm_addr = kmap_atomic(page);
		ret = area->vm_addr + off;
		goto out;
	}

	/* this object spans two pages */
	pages[0] = page;
	pages[1] = get_next_page(page);
	BUG_ON(!pages[1]);

	ret = __zs_map_object(area, pages, off, class->size);
out:
	if (likely(!ZsHugePage(zspage)))
		ret += ZS_HANDLE_SIZE;

	return ret;
}
EXPORT_SYMBOL_GPL(zs_map_object);

void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
{
	struct zspage *zspage;
	struct page *page;
	unsigned long obj, off;
	unsigned int obj_idx;

	struct size_class *class;
	struct mapping_area *area;

	obj = handle_to_obj(handle);
	obj_to_location(obj, &page, &obj_idx);
	zspage = get_zspage(page);
	class = zspage_class(pool, zspage);
	off = offset_in_page(class->size * obj_idx);

	area = this_cpu_ptr(&zs_map_area);
	if (off + class->size <= PAGE_SIZE)
		kunmap_atomic(area->vm_addr);
	else {
		struct page *pages[2];

		pages[0] = page;
		pages[1] = get_next_page(page);
		BUG_ON(!pages[1]);

		__zs_unmap_object(area, pages, off, class->size);
	}
	local_unlock(&zs_map_area.lock);

	migrate_read_unlock(zspage);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);

/**
 * zs_huge_class_size() - Returns the size (in bytes) of the first huge
 *                        zsmalloc &size_class.
 * @pool: zsmalloc pool to use
 *
 * The function returns the size of the first huge class - any object of equal
 * or bigger size will be stored in zspage consisting of a single physical
 * page.
 *
 * Context: Any context.
 *
 * Return: the size (in bytes) of the first huge zsmalloc &size_class.
 */
size_t zs_huge_class_size(struct zs_pool *pool)
{
	return huge_class_size;
}
EXPORT_SYMBOL_GPL(zs_huge_class_size);

static unsigned long obj_malloc(struct zs_pool *pool,
				struct zspage *zspage, unsigned long handle)
{
	int i, nr_page, offset;
	unsigned long obj;
	struct link_free *link;
	struct size_class *class;

	struct page *m_page;
	unsigned long m_offset;
	void *vaddr;

	class = pool->size_class[zspage->class];
	handle |= OBJ_ALLOCATED_TAG;
	obj = get_freeobj(zspage);

	offset = obj * class->size;
	nr_page = offset >> PAGE_SHIFT;
	m_offset = offset_in_page(offset);
	m_page = get_first_page(zspage);

	for (i = 0; i < nr_page; i++)
		m_page = get_next_page(m_page);

	vaddr = kmap_atomic(m_page);
	link = (struct link_free *)vaddr + m_offset / sizeof(*link);
	set_freeobj(zspage, link->next >> OBJ_TAG_BITS);
	if (likely(!ZsHugePage(zspage)))
		/* record handle in the header of allocated chunk */
		link->handle = handle;
	else
		/* record handle to page->index */
		zspage->first_page->index = handle;

	kunmap_atomic(vaddr);
	mod_zspage_inuse(zspage, 1);

	obj = location_to_obj(m_page, obj);

	return obj;
}


/**
 * zs_malloc - Allocate block of given size from pool.
 * @pool: pool to allocate from
 * @size: size of block to allocate
 * @gfp: gfp flags when allocating object
 *
 * On success, handle to the allocated object is returned,
 * otherwise an ERR_PTR().
 * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
 */
unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
{
	unsigned long handle, obj;
	struct size_class *class;
	int newfg;
	struct zspage *zspage;

	if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
		return (unsigned long)ERR_PTR(-EINVAL);

	handle = cache_alloc_handle(pool, gfp);
	if (!handle)
		return (unsigned long)ERR_PTR(-ENOMEM);

	/* extra space in chunk to keep the handle */
	size += ZS_HANDLE_SIZE;
	class = pool->size_class[get_size_class_index(size)];

	/* pool->lock effectively protects the zpage migration */
	spin_lock(&pool->lock);
	zspage = find_get_zspage(class);
	if (likely(zspage)) {
		obj = obj_malloc(pool, zspage, handle);
		/* Now move the zspage to another fullness group, if required */
		fix_fullness_group(class, zspage);
		record_obj(handle, obj);
		class_stat_inc(class, ZS_OBJS_INUSE, 1);

		goto out;
	}

	spin_unlock(&pool->lock);

	zspage = alloc_zspage(pool, class, gfp);
	if (!zspage) {
		cache_free_handle(pool, handle);
		return (unsigned long)ERR_PTR(-ENOMEM);
	}

	spin_lock(&pool->lock);
	obj = obj_malloc(pool, zspage, handle);
	newfg = get_fullness_group(class, zspage);
	insert_zspage(class, zspage, newfg);
	set_zspage_mapping(zspage, class->index, newfg);
	record_obj(handle, obj);
	atomic_long_add(class->pages_per_zspage, &pool->pages_allocated);
	class_stat_inc(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
	class_stat_inc(class, ZS_OBJS_INUSE, 1);

	/* We completely set up zspage so mark them as movable */
	SetZsPageMovable(pool, zspage);
out:
	spin_unlock(&pool->lock);

	return handle;
}
EXPORT_SYMBOL_GPL(zs_malloc);

static void obj_free(int class_size, unsigned long obj)
{
	struct link_free *link;
	struct zspage *zspage;
	struct page *f_page;
	unsigned long f_offset;
	unsigned int f_objidx;
	void *vaddr;

	obj_to_location(obj, &f_page, &f_objidx);
	f_offset = offset_in_page(class_size * f_objidx);
	zspage = get_zspage(f_page);

	vaddr = kmap_atomic(f_page);
	link = (struct link_free *)(vaddr + f_offset);

	/* Insert this object in containing zspage's freelist */
	if (likely(!ZsHugePage(zspage)))
		link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
	else
		f_page->index = 0;
	set_freeobj(zspage, f_objidx);

	kunmap_atomic(vaddr);
	mod_zspage_inuse(zspage, -1);
}

void zs_free(struct zs_pool *pool, unsigned long handle)
{
	struct zspage *zspage;
	struct page *f_page;
	unsigned long obj;
	struct size_class *class;
	int fullness;

	if (IS_ERR_OR_NULL((void *)handle))
		return;

	/*
	 * The pool->lock protects the race with zpage's migration
	 * so it's safe to get the page from handle.
	 */
	spin_lock(&pool->lock);
	obj = handle_to_obj(handle);
	obj_to_page(obj, &f_page);
	zspage = get_zspage(f_page);
	class = zspage_class(pool, zspage);

	class_stat_dec(class, ZS_OBJS_INUSE, 1);
	obj_free(class->size, obj);

	fullness = fix_fullness_group(class, zspage);
	if (fullness == ZS_INUSE_RATIO_0)
		free_zspage(pool, class, zspage);

	spin_unlock(&pool->lock);
	cache_free_handle(pool, handle);
}
EXPORT_SYMBOL_GPL(zs_free);

static void zs_object_copy(struct size_class *class, unsigned long dst,
				unsigned long src)
{
	struct page *s_page, *d_page;
	unsigned int s_objidx, d_objidx;
	unsigned long s_off, d_off;
	void *s_addr, *d_addr;
	int s_size, d_size, size;
	int written = 0;

	s_size = d_size = class->size;

	obj_to_location(src, &s_page, &s_objidx);
	obj_to_location(dst, &d_page, &d_objidx);

	s_off = offset_in_page(class->size * s_objidx);
	d_off = offset_in_page(class->size * d_objidx);

	if (s_off + class->size > PAGE_SIZE)
		s_size = PAGE_SIZE - s_off;

	if (d_off + class->size > PAGE_SIZE)
		d_size = PAGE_SIZE - d_off;

	s_addr = kmap_atomic(s_page);
	d_addr = kmap_atomic(d_page);

	while (1) {
		size = min(s_size, d_size);
		memcpy(d_addr + d_off, s_addr + s_off, size);
		written += size;

		if (written == class->size)
			break;

		s_off += size;
		s_size -= size;
		d_off += size;
		d_size -= size;

		/*
		 * Calling kunmap_atomic(d_addr) is necessary. kunmap_atomic()
		 * calls must occurs in reverse order of calls to kmap_atomic().
		 * So, to call kunmap_atomic(s_addr) we should first call
		 * kunmap_atomic(d_addr). For more details see
		 * Documentation/mm/highmem.rst.
		 */
		if (s_off >= PAGE_SIZE) {
			kunmap_atomic(d_addr);
			kunmap_atomic(s_addr);
			s_page = get_next_page(s_page);
			s_addr = kmap_atomic(s_page);
			d_addr = kmap_atomic(d_page);
			s_size = class->size - written;
			s_off = 0;
		}

		if (d_off >= PAGE_SIZE) {
			kunmap_atomic(d_addr);
			d_page = get_next_page(d_page);
			d_addr = kmap_atomic(d_page);
			d_size = class->size - written;
			d_off = 0;
		}
	}

	kunmap_atomic(d_addr);
	kunmap_atomic(s_addr);
}

/*
 * Find object with a certain tag in zspage from index object and
 * return handle.
 */
static unsigned long find_tagged_obj(struct size_class *class,
					struct page *page, int *obj_idx, int tag)
{
	unsigned int offset;
	int index = *obj_idx;
	unsigned long handle = 0;
	void *addr = kmap_atomic(page);

	offset = get_first_obj_offset(page);
	offset += class->size * index;

	while (offset < PAGE_SIZE) {
		if (obj_tagged(page, addr + offset, &handle, tag))
			break;

		offset += class->size;
		index++;
	}

	kunmap_atomic(addr);

	*obj_idx = index;

	return handle;
}

/*
 * Find alloced object in zspage from index object and
 * return handle.
 */
static unsigned long find_alloced_obj(struct size_class *class,
					struct page *page, int *obj_idx)
{
	return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG);
}

static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage,
			   struct zspage *dst_zspage)
{
	unsigned long used_obj, free_obj;
	unsigned long handle;
	int obj_idx = 0;
	struct page *s_page = get_first_page(src_zspage);
	struct size_class *class = pool->size_class[src_zspage->class];

	while (1) {
		handle = find_alloced_obj(class, s_page, &obj_idx);
		if (!handle) {
			s_page = get_next_page(s_page);
			if (!s_page)
				break;
			obj_idx = 0;
			continue;
		}

		used_obj = handle_to_obj(handle);
		free_obj = obj_malloc(pool, dst_zspage, handle);
		zs_object_copy(class, free_obj, used_obj);
		obj_idx++;
		record_obj(handle, free_obj);
		obj_free(class->size, used_obj);

		/* Stop if there is no more space */
		if (zspage_full(class, dst_zspage))
			break;

		/* Stop if there are no more objects to migrate */
		if (zspage_empty(src_zspage))
			break;
	}
}

static struct zspage *isolate_src_zspage(struct size_class *class)
{
	struct zspage *zspage;
	int fg;

	for (fg = ZS_INUSE_RATIO_10; fg <= ZS_INUSE_RATIO_99; fg++) {
		zspage = list_first_entry_or_null(&class->fullness_list[fg],
						  struct zspage, list);
		if (zspage) {
			remove_zspage(class, zspage, fg);
			return zspage;
		}
	}

	return zspage;
}

static struct zspage *isolate_dst_zspage(struct size_class *class)
{
	struct zspage *zspage;
	int fg;

	for (fg = ZS_INUSE_RATIO_99; fg >= ZS_INUSE_RATIO_10; fg--) {
		zspage = list_first_entry_or_null(&class->fullness_list[fg],
						  struct zspage, list);
		if (zspage) {
			remove_zspage(class, zspage, fg);
			return zspage;
		}
	}

	return zspage;
}

/*
 * putback_zspage - add @zspage into right class's fullness list
 * @class: destination class
 * @zspage: target page
 *
 * Return @zspage's fullness status
 */
static int putback_zspage(struct size_class *class, struct zspage *zspage)
{
	int fullness;

	fullness = get_fullness_group(class, zspage);
	insert_zspage(class, zspage, fullness);
	set_zspage_mapping(zspage, class->index, fullness);

	return fullness;
}

#ifdef CONFIG_COMPACTION
/*
 * To prevent zspage destroy during migration, zspage freeing should
 * hold locks of all pages in the zspage.
 */
static void lock_zspage(struct zspage *zspage)
{
	struct page *curr_page, *page;

	/*
	 * Pages we haven't locked yet can be migrated off the list while we're
	 * trying to lock them, so we need to be careful and only attempt to
	 * lock each page under migrate_read_lock(). Otherwise, the page we lock
	 * may no longer belong to the zspage. This means that we may wait for
	 * the wrong page to unlock, so we must take a reference to the page
	 * prior to waiting for it to unlock outside migrate_read_lock().
	 */
	while (1) {
		migrate_read_lock(zspage);
		page = get_first_page(zspage);
		if (trylock_page(page))
			break;
		get_page(page);
		migrate_read_unlock(zspage);
		wait_on_page_locked(page);
		put_page(page);
	}

	curr_page = page;
	while ((page = get_next_page(curr_page))) {
		if (trylock_page(page)) {
			curr_page = page;
		} else {
			get_page(page);
			migrate_read_unlock(zspage);
			wait_on_page_locked(page);
			put_page(page);
			migrate_read_lock(zspage);
		}
	}
	migrate_read_unlock(zspage);
}
#endif /* CONFIG_COMPACTION */

static void migrate_lock_init(struct zspage *zspage)
{
	rwlock_init(&zspage->lock);
}

static void migrate_read_lock(struct zspage *zspage) __acquires(&zspage->lock)
{
	read_lock(&zspage->lock);
}

static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock)
{
	read_unlock(&zspage->lock);
}

#ifdef CONFIG_COMPACTION
static void migrate_write_lock(struct zspage *zspage)
{
	write_lock(&zspage->lock);
}

static void migrate_write_lock_nested(struct zspage *zspage)
{
	write_lock_nested(&zspage->lock, SINGLE_DEPTH_NESTING);
}

static void migrate_write_unlock(struct zspage *zspage)
{
	write_unlock(&zspage->lock);
}

/* Number of isolated subpage for *page migration* in this zspage */
static void inc_zspage_isolation(struct zspage *zspage)
{
	zspage->isolated++;
}

static void dec_zspage_isolation(struct zspage *zspage)
{
	VM_BUG_ON(zspage->isolated == 0);
	zspage->isolated--;
}

static const struct movable_operations zsmalloc_mops;

static void replace_sub_page(struct size_class *class, struct zspage *zspage,
				struct page *newpage, struct page *oldpage)
{
	struct page *page;
	struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, };
	int idx = 0;

	page = get_first_page(zspage);
	do {
		if (page == oldpage)
			pages[idx] = newpage;
		else
			pages[idx] = page;
		idx++;
	} while ((page = get_next_page(page)) != NULL);

	create_page_chain(class, zspage, pages);
	set_first_obj_offset(newpage, get_first_obj_offset(oldpage));
	if (unlikely(ZsHugePage(zspage)))
		newpage->index = oldpage->index;
	__SetPageMovable(newpage, &zsmalloc_mops);
}

static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
{
	struct zspage *zspage;

	/*
	 * Page is locked so zspage couldn't be destroyed. For detail, look at
	 * lock_zspage in free_zspage.
	 */
	VM_BUG_ON_PAGE(PageIsolated(page), page);

	zspage = get_zspage(page);
	migrate_write_lock(zspage);
	inc_zspage_isolation(zspage);
	migrate_write_unlock(zspage);

	return true;
}

static int zs_page_migrate(struct page *newpage, struct page *page,
		enum migrate_mode mode)
{
	struct zs_pool *pool;
	struct size_class *class;
	struct zspage *zspage;
	struct page *dummy;
	void *s_addr, *d_addr, *addr;
	unsigned int offset;
	unsigned long handle;
	unsigned long old_obj, new_obj;
	unsigned int obj_idx;

	/*
	 * We cannot support the _NO_COPY case here, because copy needs to
	 * happen under the zs lock, which does not work with
	 * MIGRATE_SYNC_NO_COPY workflow.
	 */
	if (mode == MIGRATE_SYNC_NO_COPY)
		return -EINVAL;

	VM_BUG_ON_PAGE(!PageIsolated(page), page);

	/* The page is locked, so this pointer must remain valid */
	zspage = get_zspage(page);
	pool = zspage->pool;

	/*
	 * The pool's lock protects the race between zpage migration
	 * and zs_free.
	 */
	spin_lock(&pool->lock);
	class = zspage_class(pool, zspage);

	/* the migrate_write_lock protects zpage access via zs_map_object */
	migrate_write_lock(zspage);

	offset = get_first_obj_offset(page);
	s_addr = kmap_atomic(page);

	/*
	 * Here, any user cannot access all objects in the zspage so let's move.
	 */
	d_addr = kmap_atomic(newpage);
	memcpy(d_addr, s_addr, PAGE_SIZE);
	kunmap_atomic(d_addr);

	for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE;
					addr += class->size) {
		if (obj_allocated(page, addr, &handle)) {

			old_obj = handle_to_obj(handle);
			obj_to_location(old_obj, &dummy, &obj_idx);
			new_obj = (unsigned long)location_to_obj(newpage,
								obj_idx);
			record_obj(handle, new_obj);
		}
	}
	kunmap_atomic(s_addr);

	replace_sub_page(class, zspage, newpage, page);
	/*
	 * Since we complete the data copy and set up new zspage structure,
	 * it's okay to release the pool's lock.
	 */
	spin_unlock(&pool->lock);
	dec_zspage_isolation(zspage);
	migrate_write_unlock(zspage);

	get_page(newpage);
	if (page_zone(newpage) != page_zone(page)) {
		dec_zone_page_state(page, NR_ZSPAGES);
		inc_zone_page_state(newpage, NR_ZSPAGES);
	}

	reset_page(page);
	put_page(page);

	return MIGRATEPAGE_SUCCESS;
}

static void zs_page_putback(struct page *page)
{
	struct zspage *zspage;

	VM_BUG_ON_PAGE(!PageIsolated(page), page);

	zspage = get_zspage(page);
	migrate_write_lock(zspage);
	dec_zspage_isolation(zspage);
	migrate_write_unlock(zspage);
}

static const struct movable_operations zsmalloc_mops = {
	.isolate_page = zs_page_isolate,
	.migrate_page = zs_page_migrate,
	.putback_page = zs_page_putback,
};

/*
 * Caller should hold page_lock of all pages in the zspage
 * In here, we cannot use zspage meta data.
 */
static void async_free_zspage(struct work_struct *work)
{
	int i;
	struct size_class *class;
	unsigned int class_idx;
	int fullness;
	struct zspage *zspage, *tmp;
	LIST_HEAD(free_pages);
	struct zs_pool *pool = container_of(work, struct zs_pool,
					free_work);

	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
		class = pool->size_class[i];
		if (class->index != i)
			continue;

		spin_lock(&pool->lock);
		list_splice_init(&class->fullness_list[ZS_INUSE_RATIO_0],
				 &free_pages);
		spin_unlock(&pool->lock);
	}

	list_for_each_entry_safe(zspage, tmp, &free_pages, list) {
		list_del(&zspage->list);
		lock_zspage(zspage);

		get_zspage_mapping(zspage, &class_idx, &fullness);
		VM_BUG_ON(fullness != ZS_INUSE_RATIO_0);
		class = pool->size_class[class_idx];
		spin_lock(&pool->lock);
		__free_zspage(pool, class, zspage);
		spin_unlock(&pool->lock);
	}
};

static void kick_deferred_free(struct zs_pool *pool)
{
	schedule_work(&pool->free_work);
}

static void zs_flush_migration(struct zs_pool *pool)
{
	flush_work(&pool->free_work);
}

static void init_deferred_free(struct zs_pool *pool)
{
	INIT_WORK(&pool->free_work, async_free_zspage);
}

static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
{
	struct page *page = get_first_page(zspage);

	do {
		WARN_ON(!trylock_page(page));
		__SetPageMovable(page, &zsmalloc_mops);
		unlock_page(page);
	} while ((page = get_next_page(page)) != NULL);
}
#else
static inline void zs_flush_migration(struct zs_pool *pool) { }
#endif

/*
 *
 * Based on the number of unused allocated objects calculate
 * and return the number of pages that we can free.
 */
static unsigned long zs_can_compact(struct size_class *class)
{
	unsigned long obj_wasted;
	unsigned long obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED);
	unsigned long obj_used = zs_stat_get(class, ZS_OBJS_INUSE);

	if (obj_allocated <= obj_used)
		return 0;

	obj_wasted = obj_allocated - obj_used;
	obj_wasted /= class->objs_per_zspage;

	return obj_wasted * class->pages_per_zspage;
}

static unsigned long __zs_compact(struct zs_pool *pool,
				  struct size_class *class)
{
	struct zspage *src_zspage = NULL;
	struct zspage *dst_zspage = NULL;
	unsigned long pages_freed = 0;

	/*
	 * protect the race between zpage migration and zs_free
	 * as well as zpage allocation/free
	 */
	spin_lock(&pool->lock);
	while (zs_can_compact(class)) {
		int fg;

		if (!dst_zspage) {
			dst_zspage = isolate_dst_zspage(class);
			if (!dst_zspage)
				break;
			migrate_write_lock(dst_zspage);
		}

		src_zspage = isolate_src_zspage(class);
		if (!src_zspage)
			break;

		migrate_write_lock_nested(src_zspage);

		migrate_zspage(pool, src_zspage, dst_zspage);
		fg = putback_zspage(class, src_zspage);
		migrate_write_unlock(src_zspage);

		if (fg == ZS_INUSE_RATIO_0) {
			free_zspage(pool, class, src_zspage);
			pages_freed += class->pages_per_zspage;
		}
		src_zspage = NULL;

		if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100
		    || spin_is_contended(&pool->lock)) {
			putback_zspage(class, dst_zspage);
			migrate_write_unlock(dst_zspage);
			dst_zspage = NULL;

			spin_unlock(&pool->lock);
			cond_resched();
			spin_lock(&pool->lock);
		}
	}

	if (src_zspage) {
		putback_zspage(class, src_zspage);
		migrate_write_unlock(src_zspage);
	}

	if (dst_zspage) {
		putback_zspage(class, dst_zspage);
		migrate_write_unlock(dst_zspage);
	}
	spin_unlock(&pool->lock);

	return pages_freed;
}

unsigned long zs_compact(struct zs_pool *pool)
{
	int i;
	struct size_class *class;
	unsigned long pages_freed = 0;

	/*
	 * Pool compaction is performed under pool->lock so it is basically
	 * single-threaded. Having more than one thread in __zs_compact()
	 * will increase pool->lock contention, which will impact other
	 * zsmalloc operations that need pool->lock.
	 */
	if (atomic_xchg(&pool->compaction_in_progress, 1))
		return 0;

	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
		class = pool->size_class[i];
		if (class->index != i)
			continue;
		pages_freed += __zs_compact(pool, class);
	}
	atomic_long_add(pages_freed, &pool->stats.pages_compacted);
	atomic_set(&pool->compaction_in_progress, 0);

	return pages_freed;
}
EXPORT_SYMBOL_GPL(zs_compact);

void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats)
{
	memcpy(stats, &pool->stats, sizeof(struct zs_pool_stats));
}
EXPORT_SYMBOL_GPL(zs_pool_stats);

static unsigned long zs_shrinker_scan(struct shrinker *shrinker,
		struct shrink_control *sc)
{
	unsigned long pages_freed;
	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
			shrinker);

	/*
	 * Compact classes and calculate compaction delta.
	 * Can run concurrently with a manually triggered
	 * (by user) compaction.
	 */
	pages_freed = zs_compact(pool);

	return pages_freed ? pages_freed : SHRINK_STOP;
}

static unsigned long zs_shrinker_count(struct shrinker *shrinker,
		struct shrink_control *sc)
{
	int i;
	struct size_class *class;
	unsigned long pages_to_free = 0;
	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
			shrinker);

	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
		class = pool->size_class[i];
		if (class->index != i)
			continue;

		pages_to_free += zs_can_compact(class);
	}

	return pages_to_free;
}

static void zs_unregister_shrinker(struct zs_pool *pool)
{
	unregister_shrinker(&pool->shrinker);
}

static int zs_register_shrinker(struct zs_pool *pool)
{
	pool->shrinker.scan_objects = zs_shrinker_scan;
	pool->shrinker.count_objects = zs_shrinker_count;
	pool->shrinker.batch = 0;
	pool->shrinker.seeks = DEFAULT_SEEKS;

	return register_shrinker(&pool->shrinker, "mm-zspool:%s",
				 pool->name);
}

static int calculate_zspage_chain_size(int class_size)
{
	int i, min_waste = INT_MAX;
	int chain_size = 1;

	if (is_power_of_2(class_size))
		return chain_size;

	for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
		int waste;

		waste = (i * PAGE_SIZE) % class_size;
		if (waste < min_waste) {
			min_waste = waste;
			chain_size = i;
		}
	}

	return chain_size;
}

/**
 * zs_create_pool - Creates an allocation pool to work from.
 * @name: pool name to be created
 *
 * This function must be called before anything when using
 * the zsmalloc allocator.
 *
 * On success, a pointer to the newly created pool is returned,
 * otherwise NULL.
 */
struct zs_pool *zs_create_pool(const char *name)
{
	int i;
	struct zs_pool *pool;
	struct size_class *prev_class = NULL;

	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
	if (!pool)
		return NULL;

	init_deferred_free(pool);
	spin_lock_init(&pool->lock);
	atomic_set(&pool->compaction_in_progress, 0);

	pool->name = kstrdup(name, GFP_KERNEL);
	if (!pool->name)
		goto err;

	if (create_cache(pool))
		goto err;

	/*
	 * Iterate reversely, because, size of size_class that we want to use
	 * for merging should be larger or equal to current size.
	 */
	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
		int size;
		int pages_per_zspage;
		int objs_per_zspage;
		struct size_class *class;
		int fullness;

		size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
		if (size > ZS_MAX_ALLOC_SIZE)
			size = ZS_MAX_ALLOC_SIZE;
		pages_per_zspage = calculate_zspage_chain_size(size);
		objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;

		/*
		 * We iterate from biggest down to smallest classes,
		 * so huge_class_size holds the size of the first huge
		 * class. Any object bigger than or equal to that will
		 * endup in the huge class.
		 */
		if (pages_per_zspage != 1 && objs_per_zspage != 1 &&
				!huge_class_size) {
			huge_class_size = size;
			/*
			 * The object uses ZS_HANDLE_SIZE bytes to store the
			 * handle. We need to subtract it, because zs_malloc()
			 * unconditionally adds handle size before it performs
			 * size class search - so object may be smaller than
			 * huge class size, yet it still can end up in the huge
			 * class because it grows by ZS_HANDLE_SIZE extra bytes
			 * right before class lookup.
			 */
			huge_class_size -= (ZS_HANDLE_SIZE - 1);
		}

		/*
		 * size_class is used for normal zsmalloc operation such
		 * as alloc/free for that size. Although it is natural that we
		 * have one size_class for each size, there is a chance that we
		 * can get more memory utilization if we use one size_class for
		 * many different sizes whose size_class have same
		 * characteristics. So, we makes size_class point to
		 * previous size_class if possible.
		 */
		if (prev_class) {
			if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) {
				pool->size_class[i] = prev_class;
				continue;
			}
		}

		class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
		if (!class)
			goto err;

		class->size = size;
		class->index = i;
		class->pages_per_zspage = pages_per_zspage;
		class->objs_per_zspage = objs_per_zspage;
		pool->size_class[i] = class;

		fullness = ZS_INUSE_RATIO_0;
		while (fullness < NR_FULLNESS_GROUPS) {
			INIT_LIST_HEAD(&class->fullness_list[fullness]);
			fullness++;
		}

		prev_class = class;
	}

	/* debug only, don't abort if it fails */
	zs_pool_stat_create(pool, name);

	/*
	 * Not critical since shrinker is only used to trigger internal
	 * defragmentation of the pool which is pretty optional thing.  If
	 * registration fails we still can use the pool normally and user can
	 * trigger compaction manually. Thus, ignore return code.
	 */
	zs_register_shrinker(pool);

	return pool;

err:
	zs_destroy_pool(pool);
	return NULL;
}
EXPORT_SYMBOL_GPL(zs_create_pool);

void zs_destroy_pool(struct zs_pool *pool)
{
	int i;

	zs_unregister_shrinker(pool);
	zs_flush_migration(pool);
	zs_pool_stat_destroy(pool);

	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
		int fg;
		struct size_class *class = pool->size_class[i];

		if (!class)
			continue;

		if (class->index != i)
			continue;

		for (fg = ZS_INUSE_RATIO_0; fg < NR_FULLNESS_GROUPS; fg++) {
			if (list_empty(&class->fullness_list[fg]))
				continue;

			pr_err("Class-%d fullness group %d is not empty\n",
			       class->size, fg);
		}
		kfree(class);
	}

	destroy_cache(pool);
	kfree(pool->name);
	kfree(pool);
}
EXPORT_SYMBOL_GPL(zs_destroy_pool);

static int __init zs_init(void)
{
	int ret;

	ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
				zs_cpu_prepare, zs_cpu_dead);
	if (ret)
		goto out;

#ifdef CONFIG_ZPOOL
	zpool_register_driver(&zs_zpool_driver);
#endif

	zs_stat_init();

	return 0;

out:
	return ret;
}

static void __exit zs_exit(void)
{
#ifdef CONFIG_ZPOOL
	zpool_unregister_driver(&zs_zpool_driver);
#endif
	cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);

	zs_stat_exit();
}

module_init(zs_init);
module_exit(zs_exit);

MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");