summaryrefslogtreecommitdiff
path: root/drivers/staging/zcache/zcache-main.c
blob: ed2c800b3a7eb6a3347d140dccb84034dd98400f (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
/*
 * zcache.c
 *
 * Copyright (c) 2010,2011, Dan Magenheimer, Oracle Corp.
 * Copyright (c) 2010,2011, Nitin Gupta
 *
 * Zcache provides an in-kernel "host implementation" for transcendent memory
 * and, thus indirectly, for cleancache and frontswap.  Zcache includes two
 * page-accessible memory [1] interfaces, both utilizing the crypto compression
 * API:
 * 1) "compression buddies" ("zbud") is used for ephemeral pages
 * 2) zsmalloc is used for persistent pages.
 * Xvmalloc (based on the TLSF allocator) has very low fragmentation
 * so maximizes space efficiency, while zbud allows pairs (and potentially,
 * in the future, more than a pair of) compressed pages to be closely linked
 * so that reclaiming can be done via the kernel's physical-page-oriented
 * "shrinker" interface.
 *
 * [1] For a definition of page-accessible memory (aka PAM), see:
 *   http://marc.info/?l=linux-mm&m=127811271605009
 */

#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/highmem.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/math64.h>
#include <linux/crypto.h>
#include <linux/string.h>
#include "tmem.h"

#include "../zsmalloc/zsmalloc.h"

#if (!defined(CONFIG_CLEANCACHE) && !defined(CONFIG_FRONTSWAP))
#error "zcache is useless without CONFIG_CLEANCACHE or CONFIG_FRONTSWAP"
#endif
#ifdef CONFIG_CLEANCACHE
#include <linux/cleancache.h>
#endif
#ifdef CONFIG_FRONTSWAP
#include <linux/frontswap.h>
#endif

#if 0
/* this is more aggressive but may cause other problems? */
#define ZCACHE_GFP_MASK	(GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN)
#else
#define ZCACHE_GFP_MASK \
	(__GFP_FS | __GFP_NORETRY | __GFP_NOWARN | __GFP_NOMEMALLOC)
#endif

#define MAX_POOLS_PER_CLIENT 16

#define MAX_CLIENTS 16
#define LOCAL_CLIENT ((uint16_t)-1)

MODULE_LICENSE("GPL");

struct zcache_client {
	struct tmem_pool *tmem_pools[MAX_POOLS_PER_CLIENT];
	struct zs_pool *zspool;
	bool allocated;
	atomic_t refcount;
};

static struct zcache_client zcache_host;
static struct zcache_client zcache_clients[MAX_CLIENTS];

static inline uint16_t get_client_id_from_client(struct zcache_client *cli)
{
	BUG_ON(cli == NULL);
	if (cli == &zcache_host)
		return LOCAL_CLIENT;
	return cli - &zcache_clients[0];
}

static inline bool is_local_client(struct zcache_client *cli)
{
	return cli == &zcache_host;
}

/* crypto API for zcache  */
#define ZCACHE_COMP_NAME_SZ CRYPTO_MAX_ALG_NAME
static char zcache_comp_name[ZCACHE_COMP_NAME_SZ];
static struct crypto_comp * __percpu *zcache_comp_pcpu_tfms;

enum comp_op {
	ZCACHE_COMPOP_COMPRESS,
	ZCACHE_COMPOP_DECOMPRESS
};

static inline int zcache_comp_op(enum comp_op op,
				const u8 *src, unsigned int slen,
				u8 *dst, unsigned int *dlen)
{
	struct crypto_comp *tfm;
	int ret;

	BUG_ON(!zcache_comp_pcpu_tfms);
	tfm = *per_cpu_ptr(zcache_comp_pcpu_tfms, get_cpu());
	BUG_ON(!tfm);
	switch (op) {
	case ZCACHE_COMPOP_COMPRESS:
		ret = crypto_comp_compress(tfm, src, slen, dst, dlen);
		break;
	case ZCACHE_COMPOP_DECOMPRESS:
		ret = crypto_comp_decompress(tfm, src, slen, dst, dlen);
		break;
	}
	put_cpu();
	return ret;
}

/**********
 * Compression buddies ("zbud") provides for packing two (or, possibly
 * in the future, more) compressed ephemeral pages into a single "raw"
 * (physical) page and tracking them with data structures so that
 * the raw pages can be easily reclaimed.
 *
 * A zbud page ("zbpg") is an aligned page containing a list_head,
 * a lock, and two "zbud headers".  The remainder of the physical
 * page is divided up into aligned 64-byte "chunks" which contain
 * the compressed data for zero, one, or two zbuds.  Each zbpg
 * resides on: (1) an "unused list" if it has no zbuds; (2) a
 * "buddied" list if it is fully populated  with two zbuds; or
 * (3) one of PAGE_SIZE/64 "unbuddied" lists indexed by how many chunks
 * the one unbuddied zbud uses.  The data inside a zbpg cannot be
 * read or written unless the zbpg's lock is held.
 */

#define ZBH_SENTINEL  0x43214321
#define ZBPG_SENTINEL  0xdeadbeef

#define ZBUD_MAX_BUDS 2

struct zbud_hdr {
	uint16_t client_id;
	uint16_t pool_id;
	struct tmem_oid oid;
	uint32_t index;
	uint16_t size; /* compressed size in bytes, zero means unused */
	DECL_SENTINEL
};

struct zbud_page {
	struct list_head bud_list;
	spinlock_t lock;
	struct zbud_hdr buddy[ZBUD_MAX_BUDS];
	DECL_SENTINEL
	/* followed by NUM_CHUNK aligned CHUNK_SIZE-byte chunks */
};

#define CHUNK_SHIFT	6
#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
#define CHUNK_MASK	(~(CHUNK_SIZE-1))
#define NCHUNKS		(((PAGE_SIZE - sizeof(struct zbud_page)) & \
				CHUNK_MASK) >> CHUNK_SHIFT)
#define MAX_CHUNK	(NCHUNKS-1)

static struct {
	struct list_head list;
	unsigned count;
} zbud_unbuddied[NCHUNKS];
/* list N contains pages with N chunks USED and NCHUNKS-N unused */
/* element 0 is never used but optimizing that isn't worth it */
static unsigned long zbud_cumul_chunk_counts[NCHUNKS];

struct list_head zbud_buddied_list;
static unsigned long zcache_zbud_buddied_count;

/* protects the buddied list and all unbuddied lists */
static DEFINE_SPINLOCK(zbud_budlists_spinlock);

static LIST_HEAD(zbpg_unused_list);
static unsigned long zcache_zbpg_unused_list_count;

/* protects the unused page list */
static DEFINE_SPINLOCK(zbpg_unused_list_spinlock);

static atomic_t zcache_zbud_curr_raw_pages;
static atomic_t zcache_zbud_curr_zpages;
static unsigned long zcache_zbud_curr_zbytes;
static unsigned long zcache_zbud_cumul_zpages;
static unsigned long zcache_zbud_cumul_zbytes;
static unsigned long zcache_compress_poor;
static unsigned long zcache_mean_compress_poor;

/* forward references */
static void *zcache_get_free_page(void);
static void zcache_free_page(void *p);

/*
 * zbud helper functions
 */

static inline unsigned zbud_max_buddy_size(void)
{
	return MAX_CHUNK << CHUNK_SHIFT;
}

static inline unsigned zbud_size_to_chunks(unsigned size)
{
	BUG_ON(size == 0 || size > zbud_max_buddy_size());
	return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT;
}

static inline int zbud_budnum(struct zbud_hdr *zh)
{
	unsigned offset = (unsigned long)zh & (PAGE_SIZE - 1);
	struct zbud_page *zbpg = NULL;
	unsigned budnum = -1U;
	int i;

	for (i = 0; i < ZBUD_MAX_BUDS; i++)
		if (offset == offsetof(typeof(*zbpg), buddy[i])) {
			budnum = i;
			break;
		}
	BUG_ON(budnum == -1U);
	return budnum;
}

static char *zbud_data(struct zbud_hdr *zh, unsigned size)
{
	struct zbud_page *zbpg;
	char *p;
	unsigned budnum;

	ASSERT_SENTINEL(zh, ZBH);
	budnum = zbud_budnum(zh);
	BUG_ON(size == 0 || size > zbud_max_buddy_size());
	zbpg = container_of(zh, struct zbud_page, buddy[budnum]);
	ASSERT_SPINLOCK(&zbpg->lock);
	p = (char *)zbpg;
	if (budnum == 0)
		p += ((sizeof(struct zbud_page) + CHUNK_SIZE - 1) &
							CHUNK_MASK);
	else if (budnum == 1)
		p += PAGE_SIZE - ((size + CHUNK_SIZE - 1) & CHUNK_MASK);
	return p;
}

/*
 * zbud raw page management
 */

static struct zbud_page *zbud_alloc_raw_page(void)
{
	struct zbud_page *zbpg = NULL;
	struct zbud_hdr *zh0, *zh1;
	bool recycled = 0;

	/* if any pages on the zbpg list, use one */
	spin_lock(&zbpg_unused_list_spinlock);
	if (!list_empty(&zbpg_unused_list)) {
		zbpg = list_first_entry(&zbpg_unused_list,
				struct zbud_page, bud_list);
		list_del_init(&zbpg->bud_list);
		zcache_zbpg_unused_list_count--;
		recycled = 1;
	}
	spin_unlock(&zbpg_unused_list_spinlock);
	if (zbpg == NULL)
		/* none on zbpg list, try to get a kernel page */
		zbpg = zcache_get_free_page();
	if (likely(zbpg != NULL)) {
		INIT_LIST_HEAD(&zbpg->bud_list);
		zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1];
		spin_lock_init(&zbpg->lock);
		if (recycled) {
			ASSERT_INVERTED_SENTINEL(zbpg, ZBPG);
			SET_SENTINEL(zbpg, ZBPG);
			BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid));
			BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid));
		} else {
			atomic_inc(&zcache_zbud_curr_raw_pages);
			INIT_LIST_HEAD(&zbpg->bud_list);
			SET_SENTINEL(zbpg, ZBPG);
			zh0->size = 0; zh1->size = 0;
			tmem_oid_set_invalid(&zh0->oid);
			tmem_oid_set_invalid(&zh1->oid);
		}
	}
	return zbpg;
}

static void zbud_free_raw_page(struct zbud_page *zbpg)
{
	struct zbud_hdr *zh0 = &zbpg->buddy[0], *zh1 = &zbpg->buddy[1];

	ASSERT_SENTINEL(zbpg, ZBPG);
	BUG_ON(!list_empty(&zbpg->bud_list));
	ASSERT_SPINLOCK(&zbpg->lock);
	BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid));
	BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid));
	INVERT_SENTINEL(zbpg, ZBPG);
	spin_unlock(&zbpg->lock);
	spin_lock(&zbpg_unused_list_spinlock);
	list_add(&zbpg->bud_list, &zbpg_unused_list);
	zcache_zbpg_unused_list_count++;
	spin_unlock(&zbpg_unused_list_spinlock);
}

/*
 * core zbud handling routines
 */

static unsigned zbud_free(struct zbud_hdr *zh)
{
	unsigned size;

	ASSERT_SENTINEL(zh, ZBH);
	BUG_ON(!tmem_oid_valid(&zh->oid));
	size = zh->size;
	BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size());
	zh->size = 0;
	tmem_oid_set_invalid(&zh->oid);
	INVERT_SENTINEL(zh, ZBH);
	zcache_zbud_curr_zbytes -= size;
	atomic_dec(&zcache_zbud_curr_zpages);
	return size;
}

static void zbud_free_and_delist(struct zbud_hdr *zh)
{
	unsigned chunks;
	struct zbud_hdr *zh_other;
	unsigned budnum = zbud_budnum(zh), size;
	struct zbud_page *zbpg =
		container_of(zh, struct zbud_page, buddy[budnum]);

	spin_lock(&zbud_budlists_spinlock);
	spin_lock(&zbpg->lock);
	if (list_empty(&zbpg->bud_list)) {
		/* ignore zombie page... see zbud_evict_pages() */
		spin_unlock(&zbpg->lock);
		spin_unlock(&zbud_budlists_spinlock);
		return;
	}
	size = zbud_free(zh);
	ASSERT_SPINLOCK(&zbpg->lock);
	zh_other = &zbpg->buddy[(budnum == 0) ? 1 : 0];
	if (zh_other->size == 0) { /* was unbuddied: unlist and free */
		chunks = zbud_size_to_chunks(size) ;
		BUG_ON(list_empty(&zbud_unbuddied[chunks].list));
		list_del_init(&zbpg->bud_list);
		zbud_unbuddied[chunks].count--;
		spin_unlock(&zbud_budlists_spinlock);
		zbud_free_raw_page(zbpg);
	} else { /* was buddied: move remaining buddy to unbuddied list */
		chunks = zbud_size_to_chunks(zh_other->size) ;
		list_del_init(&zbpg->bud_list);
		zcache_zbud_buddied_count--;
		list_add_tail(&zbpg->bud_list, &zbud_unbuddied[chunks].list);
		zbud_unbuddied[chunks].count++;
		spin_unlock(&zbud_budlists_spinlock);
		spin_unlock(&zbpg->lock);
	}
}

static struct zbud_hdr *zbud_create(uint16_t client_id, uint16_t pool_id,
					struct tmem_oid *oid,
					uint32_t index, struct page *page,
					void *cdata, unsigned size)
{
	struct zbud_hdr *zh0, *zh1, *zh = NULL;
	struct zbud_page *zbpg = NULL, *ztmp;
	unsigned nchunks;
	char *to;
	int i, found_good_buddy = 0;

	nchunks = zbud_size_to_chunks(size) ;
	for (i = MAX_CHUNK - nchunks + 1; i > 0; i--) {
		spin_lock(&zbud_budlists_spinlock);
		if (!list_empty(&zbud_unbuddied[i].list)) {
			list_for_each_entry_safe(zbpg, ztmp,
				    &zbud_unbuddied[i].list, bud_list) {
				if (spin_trylock(&zbpg->lock)) {
					found_good_buddy = i;
					goto found_unbuddied;
				}
			}
		}
		spin_unlock(&zbud_budlists_spinlock);
	}
	/* didn't find a good buddy, try allocating a new page */
	zbpg = zbud_alloc_raw_page();
	if (unlikely(zbpg == NULL))
		goto out;
	/* ok, have a page, now compress the data before taking locks */
	spin_lock(&zbud_budlists_spinlock);
	spin_lock(&zbpg->lock);
	list_add_tail(&zbpg->bud_list, &zbud_unbuddied[nchunks].list);
	zbud_unbuddied[nchunks].count++;
	zh = &zbpg->buddy[0];
	goto init_zh;

found_unbuddied:
	ASSERT_SPINLOCK(&zbpg->lock);
	zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1];
	BUG_ON(!((zh0->size == 0) ^ (zh1->size == 0)));
	if (zh0->size != 0) { /* buddy0 in use, buddy1 is vacant */
		ASSERT_SENTINEL(zh0, ZBH);
		zh = zh1;
	} else if (zh1->size != 0) { /* buddy1 in use, buddy0 is vacant */
		ASSERT_SENTINEL(zh1, ZBH);
		zh = zh0;
	} else
		BUG();
	list_del_init(&zbpg->bud_list);
	zbud_unbuddied[found_good_buddy].count--;
	list_add_tail(&zbpg->bud_list, &zbud_buddied_list);
	zcache_zbud_buddied_count++;

init_zh:
	SET_SENTINEL(zh, ZBH);
	zh->size = size;
	zh->index = index;
	zh->oid = *oid;
	zh->pool_id = pool_id;
	zh->client_id = client_id;
	to = zbud_data(zh, size);
	memcpy(to, cdata, size);
	spin_unlock(&zbpg->lock);
	spin_unlock(&zbud_budlists_spinlock);

	zbud_cumul_chunk_counts[nchunks]++;
	atomic_inc(&zcache_zbud_curr_zpages);
	zcache_zbud_cumul_zpages++;
	zcache_zbud_curr_zbytes += size;
	zcache_zbud_cumul_zbytes += size;
out:
	return zh;
}

static int zbud_decompress(struct page *page, struct zbud_hdr *zh)
{
	struct zbud_page *zbpg;
	unsigned budnum = zbud_budnum(zh);
	unsigned int out_len = PAGE_SIZE;
	char *to_va, *from_va;
	unsigned size;
	int ret = 0;

	zbpg = container_of(zh, struct zbud_page, buddy[budnum]);
	spin_lock(&zbpg->lock);
	if (list_empty(&zbpg->bud_list)) {
		/* ignore zombie page... see zbud_evict_pages() */
		ret = -EINVAL;
		goto out;
	}
	ASSERT_SENTINEL(zh, ZBH);
	BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size());
	to_va = kmap_atomic(page);
	size = zh->size;
	from_va = zbud_data(zh, size);
	ret = zcache_comp_op(ZCACHE_COMPOP_DECOMPRESS, from_va, size,
				to_va, &out_len);
	BUG_ON(ret);
	BUG_ON(out_len != PAGE_SIZE);
	kunmap_atomic(to_va);
out:
	spin_unlock(&zbpg->lock);
	return ret;
}

/*
 * The following routines handle shrinking of ephemeral pages by evicting
 * pages "least valuable" first.
 */

static unsigned long zcache_evicted_raw_pages;
static unsigned long zcache_evicted_buddied_pages;
static unsigned long zcache_evicted_unbuddied_pages;

static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id,
						uint16_t poolid);
static void zcache_put_pool(struct tmem_pool *pool);

/*
 * Flush and free all zbuds in a zbpg, then free the pageframe
 */
static void zbud_evict_zbpg(struct zbud_page *zbpg)
{
	struct zbud_hdr *zh;
	int i, j;
	uint32_t pool_id[ZBUD_MAX_BUDS], client_id[ZBUD_MAX_BUDS];
	uint32_t index[ZBUD_MAX_BUDS];
	struct tmem_oid oid[ZBUD_MAX_BUDS];
	struct tmem_pool *pool;

	ASSERT_SPINLOCK(&zbpg->lock);
	BUG_ON(!list_empty(&zbpg->bud_list));
	for (i = 0, j = 0; i < ZBUD_MAX_BUDS; i++) {
		zh = &zbpg->buddy[i];
		if (zh->size) {
			client_id[j] = zh->client_id;
			pool_id[j] = zh->pool_id;
			oid[j] = zh->oid;
			index[j] = zh->index;
			j++;
			zbud_free(zh);
		}
	}
	spin_unlock(&zbpg->lock);
	for (i = 0; i < j; i++) {
		pool = zcache_get_pool_by_id(client_id[i], pool_id[i]);
		if (pool != NULL) {
			tmem_flush_page(pool, &oid[i], index[i]);
			zcache_put_pool(pool);
		}
	}
	ASSERT_SENTINEL(zbpg, ZBPG);
	spin_lock(&zbpg->lock);
	zbud_free_raw_page(zbpg);
}

/*
 * Free nr pages.  This code is funky because we want to hold the locks
 * protecting various lists for as short a time as possible, and in some
 * circumstances the list may change asynchronously when the list lock is
 * not held.  In some cases we also trylock not only to avoid waiting on a
 * page in use by another cpu, but also to avoid potential deadlock due to
 * lock inversion.
 */
static void zbud_evict_pages(int nr)
{
	struct zbud_page *zbpg;
	int i;

	/* first try freeing any pages on unused list */
retry_unused_list:
	spin_lock_bh(&zbpg_unused_list_spinlock);
	if (!list_empty(&zbpg_unused_list)) {
		/* can't walk list here, since it may change when unlocked */
		zbpg = list_first_entry(&zbpg_unused_list,
				struct zbud_page, bud_list);
		list_del_init(&zbpg->bud_list);
		zcache_zbpg_unused_list_count--;
		atomic_dec(&zcache_zbud_curr_raw_pages);
		spin_unlock_bh(&zbpg_unused_list_spinlock);
		zcache_free_page(zbpg);
		zcache_evicted_raw_pages++;
		if (--nr <= 0)
			goto out;
		goto retry_unused_list;
	}
	spin_unlock_bh(&zbpg_unused_list_spinlock);

	/* now try freeing unbuddied pages, starting with least space avail */
	for (i = 0; i < MAX_CHUNK; i++) {
retry_unbud_list_i:
		spin_lock_bh(&zbud_budlists_spinlock);
		if (list_empty(&zbud_unbuddied[i].list)) {
			spin_unlock_bh(&zbud_budlists_spinlock);
			continue;
		}
		list_for_each_entry(zbpg, &zbud_unbuddied[i].list, bud_list) {
			if (unlikely(!spin_trylock(&zbpg->lock)))
				continue;
			list_del_init(&zbpg->bud_list);
			zbud_unbuddied[i].count--;
			spin_unlock(&zbud_budlists_spinlock);
			zcache_evicted_unbuddied_pages++;
			/* want budlists unlocked when doing zbpg eviction */
			zbud_evict_zbpg(zbpg);
			local_bh_enable();
			if (--nr <= 0)
				goto out;
			goto retry_unbud_list_i;
		}
		spin_unlock_bh(&zbud_budlists_spinlock);
	}

	/* as a last resort, free buddied pages */
retry_bud_list:
	spin_lock_bh(&zbud_budlists_spinlock);
	if (list_empty(&zbud_buddied_list)) {
		spin_unlock_bh(&zbud_budlists_spinlock);
		goto out;
	}
	list_for_each_entry(zbpg, &zbud_buddied_list, bud_list) {
		if (unlikely(!spin_trylock(&zbpg->lock)))
			continue;
		list_del_init(&zbpg->bud_list);
		zcache_zbud_buddied_count--;
		spin_unlock(&zbud_budlists_spinlock);
		zcache_evicted_buddied_pages++;
		/* want budlists unlocked when doing zbpg eviction */
		zbud_evict_zbpg(zbpg);
		local_bh_enable();
		if (--nr <= 0)
			goto out;
		goto retry_bud_list;
	}
	spin_unlock_bh(&zbud_budlists_spinlock);
out:
	return;
}

static void zbud_init(void)
{
	int i;

	INIT_LIST_HEAD(&zbud_buddied_list);
	zcache_zbud_buddied_count = 0;
	for (i = 0; i < NCHUNKS; i++) {
		INIT_LIST_HEAD(&zbud_unbuddied[i].list);
		zbud_unbuddied[i].count = 0;
	}
}

#ifdef CONFIG_SYSFS
/*
 * These sysfs routines show a nice distribution of how many zbpg's are
 * currently (and have ever been placed) in each unbuddied list.  It's fun
 * to watch but can probably go away before final merge.
 */
static int zbud_show_unbuddied_list_counts(char *buf)
{
	int i;
	char *p = buf;

	for (i = 0; i < NCHUNKS; i++)
		p += sprintf(p, "%u ", zbud_unbuddied[i].count);
	return p - buf;
}

static int zbud_show_cumul_chunk_counts(char *buf)
{
	unsigned long i, chunks = 0, total_chunks = 0, sum_total_chunks = 0;
	unsigned long total_chunks_lte_21 = 0, total_chunks_lte_32 = 0;
	unsigned long total_chunks_lte_42 = 0;
	char *p = buf;

	for (i = 0; i < NCHUNKS; i++) {
		p += sprintf(p, "%lu ", zbud_cumul_chunk_counts[i]);
		chunks += zbud_cumul_chunk_counts[i];
		total_chunks += zbud_cumul_chunk_counts[i];
		sum_total_chunks += i * zbud_cumul_chunk_counts[i];
		if (i == 21)
			total_chunks_lte_21 = total_chunks;
		if (i == 32)
			total_chunks_lte_32 = total_chunks;
		if (i == 42)
			total_chunks_lte_42 = total_chunks;
	}
	p += sprintf(p, "<=21:%lu <=32:%lu <=42:%lu, mean:%lu\n",
		total_chunks_lte_21, total_chunks_lte_32, total_chunks_lte_42,
		chunks == 0 ? 0 : sum_total_chunks / chunks);
	return p - buf;
}
#endif

/**********
 * This "zv" PAM implementation combines the slab-based zsmalloc
 * with the crypto compression API to maximize the amount of data that can
 * be packed into a physical page.
 *
 * Zv represents a PAM page with the index and object (plus a "size" value
 * necessary for decompression) immediately preceding the compressed data.
 */

#define ZVH_SENTINEL  0x43214321

struct zv_hdr {
	uint32_t pool_id;
	struct tmem_oid oid;
	uint32_t index;
	size_t size;
	DECL_SENTINEL
};

/* rudimentary policy limits */
/* total number of persistent pages may not exceed this percentage */
static unsigned int zv_page_count_policy_percent = 75;
/*
 * byte count defining poor compression; pages with greater zsize will be
 * rejected
 */
static unsigned int zv_max_zsize = (PAGE_SIZE / 8) * 7;
/*
 * byte count defining poor *mean* compression; pages with greater zsize
 * will be rejected until sufficient better-compressed pages are accepted
 * driving the mean below this threshold
 */
static unsigned int zv_max_mean_zsize = (PAGE_SIZE / 8) * 5;

static atomic_t zv_curr_dist_counts[NCHUNKS];
static atomic_t zv_cumul_dist_counts[NCHUNKS];

static struct zv_hdr *zv_create(struct zs_pool *pool, uint32_t pool_id,
				struct tmem_oid *oid, uint32_t index,
				void *cdata, unsigned clen)
{
	struct zv_hdr *zv;
	u32 size = clen + sizeof(struct zv_hdr);
	int chunks = (size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT;
	void *handle = NULL;

	BUG_ON(!irqs_disabled());
	BUG_ON(chunks >= NCHUNKS);
	handle = zs_malloc(pool, size);
	if (!handle)
		goto out;
	atomic_inc(&zv_curr_dist_counts[chunks]);
	atomic_inc(&zv_cumul_dist_counts[chunks]);
	zv = zs_map_object(pool, handle);
	zv->index = index;
	zv->oid = *oid;
	zv->pool_id = pool_id;
	zv->size = clen;
	SET_SENTINEL(zv, ZVH);
	memcpy((char *)zv + sizeof(struct zv_hdr), cdata, clen);
	zs_unmap_object(pool, handle);
out:
	return handle;
}

static void zv_free(struct zs_pool *pool, void *handle)
{
	unsigned long flags;
	struct zv_hdr *zv;
	uint16_t size;
	int chunks;

	zv = zs_map_object(pool, handle);
	ASSERT_SENTINEL(zv, ZVH);
	size = zv->size + sizeof(struct zv_hdr);
	INVERT_SENTINEL(zv, ZVH);
	zs_unmap_object(pool, handle);

	chunks = (size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT;
	BUG_ON(chunks >= NCHUNKS);
	atomic_dec(&zv_curr_dist_counts[chunks]);

	local_irq_save(flags);
	zs_free(pool, handle);
	local_irq_restore(flags);
}

static void zv_decompress(struct page *page, void *handle)
{
	unsigned int clen = PAGE_SIZE;
	char *to_va;
	int ret;
	struct zv_hdr *zv;

	zv = zs_map_object(zcache_host.zspool, handle);
	BUG_ON(zv->size == 0);
	ASSERT_SENTINEL(zv, ZVH);
	to_va = kmap_atomic(page);
	ret = zcache_comp_op(ZCACHE_COMPOP_DECOMPRESS, (char *)zv + sizeof(*zv),
				zv->size, to_va, &clen);
	kunmap_atomic(to_va);
	zs_unmap_object(zcache_host.zspool, handle);
	BUG_ON(ret);
	BUG_ON(clen != PAGE_SIZE);
}

#ifdef CONFIG_SYSFS
/*
 * show a distribution of compression stats for zv pages.
 */

static int zv_curr_dist_counts_show(char *buf)
{
	unsigned long i, n, chunks = 0, sum_total_chunks = 0;
	char *p = buf;

	for (i = 0; i < NCHUNKS; i++) {
		n = atomic_read(&zv_curr_dist_counts[i]);
		p += sprintf(p, "%lu ", n);
		chunks += n;
		sum_total_chunks += i * n;
	}
	p += sprintf(p, "mean:%lu\n",
		chunks == 0 ? 0 : sum_total_chunks / chunks);
	return p - buf;
}

static int zv_cumul_dist_counts_show(char *buf)
{
	unsigned long i, n, chunks = 0, sum_total_chunks = 0;
	char *p = buf;

	for (i = 0; i < NCHUNKS; i++) {
		n = atomic_read(&zv_cumul_dist_counts[i]);
		p += sprintf(p, "%lu ", n);
		chunks += n;
		sum_total_chunks += i * n;
	}
	p += sprintf(p, "mean:%lu\n",
		chunks == 0 ? 0 : sum_total_chunks / chunks);
	return p - buf;
}

/*
 * setting zv_max_zsize via sysfs causes all persistent (e.g. swap)
 * pages that don't compress to less than this value (including metadata
 * overhead) to be rejected.  We don't allow the value to get too close
 * to PAGE_SIZE.
 */
static ssize_t zv_max_zsize_show(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    char *buf)
{
	return sprintf(buf, "%u\n", zv_max_zsize);
}

static ssize_t zv_max_zsize_store(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    const char *buf, size_t count)
{
	unsigned long val;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	err = kstrtoul(buf, 10, &val);
	if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7))
		return -EINVAL;
	zv_max_zsize = val;
	return count;
}

/*
 * setting zv_max_mean_zsize via sysfs causes all persistent (e.g. swap)
 * pages that don't compress to less than this value (including metadata
 * overhead) to be rejected UNLESS the mean compression is also smaller
 * than this value.  In other words, we are load-balancing-by-zsize the
 * accepted pages.  Again, we don't allow the value to get too close
 * to PAGE_SIZE.
 */
static ssize_t zv_max_mean_zsize_show(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    char *buf)
{
	return sprintf(buf, "%u\n", zv_max_mean_zsize);
}

static ssize_t zv_max_mean_zsize_store(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    const char *buf, size_t count)
{
	unsigned long val;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	err = kstrtoul(buf, 10, &val);
	if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7))
		return -EINVAL;
	zv_max_mean_zsize = val;
	return count;
}

/*
 * setting zv_page_count_policy_percent via sysfs sets an upper bound of
 * persistent (e.g. swap) pages that will be retained according to:
 *     (zv_page_count_policy_percent * totalram_pages) / 100)
 * when that limit is reached, further puts will be rejected (until
 * some pages have been flushed).  Note that, due to compression,
 * this number may exceed 100; it defaults to 75 and we set an
 * arbitary limit of 150.  A poor choice will almost certainly result
 * in OOM's, so this value should only be changed prudently.
 */
static ssize_t zv_page_count_policy_percent_show(struct kobject *kobj,
						 struct kobj_attribute *attr,
						 char *buf)
{
	return sprintf(buf, "%u\n", zv_page_count_policy_percent);
}

static ssize_t zv_page_count_policy_percent_store(struct kobject *kobj,
						  struct kobj_attribute *attr,
						  const char *buf, size_t count)
{
	unsigned long val;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	err = kstrtoul(buf, 10, &val);
	if (err || (val == 0) || (val > 150))
		return -EINVAL;
	zv_page_count_policy_percent = val;
	return count;
}

static struct kobj_attribute zcache_zv_max_zsize_attr = {
		.attr = { .name = "zv_max_zsize", .mode = 0644 },
		.show = zv_max_zsize_show,
		.store = zv_max_zsize_store,
};

static struct kobj_attribute zcache_zv_max_mean_zsize_attr = {
		.attr = { .name = "zv_max_mean_zsize", .mode = 0644 },
		.show = zv_max_mean_zsize_show,
		.store = zv_max_mean_zsize_store,
};

static struct kobj_attribute zcache_zv_page_count_policy_percent_attr = {
		.attr = { .name = "zv_page_count_policy_percent",
			  .mode = 0644 },
		.show = zv_page_count_policy_percent_show,
		.store = zv_page_count_policy_percent_store,
};
#endif

/*
 * zcache core code starts here
 */

/* useful stats not collected by cleancache or frontswap */
static unsigned long zcache_flush_total;
static unsigned long zcache_flush_found;
static unsigned long zcache_flobj_total;
static unsigned long zcache_flobj_found;
static unsigned long zcache_failed_eph_puts;
static unsigned long zcache_failed_pers_puts;

/*
 * Tmem operations assume the poolid implies the invoking client.
 * Zcache only has one client (the kernel itself): LOCAL_CLIENT.
 * RAMster has each client numbered by cluster node, and a KVM version
 * of zcache would have one client per guest and each client might
 * have a poolid==N.
 */
static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id, uint16_t poolid)
{
	struct tmem_pool *pool = NULL;
	struct zcache_client *cli = NULL;

	if (cli_id == LOCAL_CLIENT)
		cli = &zcache_host;
	else {
		if (cli_id >= MAX_CLIENTS)
			goto out;
		cli = &zcache_clients[cli_id];
		if (cli == NULL)
			goto out;
		atomic_inc(&cli->refcount);
	}
	if (poolid < MAX_POOLS_PER_CLIENT) {
		pool = cli->tmem_pools[poolid];
		if (pool != NULL)
			atomic_inc(&pool->refcount);
	}
out:
	return pool;
}

static void zcache_put_pool(struct tmem_pool *pool)
{
	struct zcache_client *cli = NULL;

	if (pool == NULL)
		BUG();
	cli = pool->client;
	atomic_dec(&pool->refcount);
	atomic_dec(&cli->refcount);
}

int zcache_new_client(uint16_t cli_id)
{
	struct zcache_client *cli = NULL;
	int ret = -1;

	if (cli_id == LOCAL_CLIENT)
		cli = &zcache_host;
	else if ((unsigned int)cli_id < MAX_CLIENTS)
		cli = &zcache_clients[cli_id];
	if (cli == NULL)
		goto out;
	if (cli->allocated)
		goto out;
	cli->allocated = 1;
#ifdef CONFIG_FRONTSWAP
	cli->zspool = zs_create_pool("zcache", ZCACHE_GFP_MASK);
	if (cli->zspool == NULL)
		goto out;
#endif
	ret = 0;
out:
	return ret;
}

/* counters for debugging */
static unsigned long zcache_failed_get_free_pages;
static unsigned long zcache_failed_alloc;
static unsigned long zcache_put_to_flush;

/*
 * for now, used named slabs so can easily track usage; later can
 * either just use kmalloc, or perhaps add a slab-like allocator
 * to more carefully manage total memory utilization
 */
static struct kmem_cache *zcache_objnode_cache;
static struct kmem_cache *zcache_obj_cache;
static atomic_t zcache_curr_obj_count = ATOMIC_INIT(0);
static unsigned long zcache_curr_obj_count_max;
static atomic_t zcache_curr_objnode_count = ATOMIC_INIT(0);
static unsigned long zcache_curr_objnode_count_max;

/*
 * to avoid memory allocation recursion (e.g. due to direct reclaim), we
 * preload all necessary data structures so the hostops callbacks never
 * actually do a malloc
 */
struct zcache_preload {
	void *page;
	struct tmem_obj *obj;
	int nr;
	struct tmem_objnode *objnodes[OBJNODE_TREE_MAX_PATH];
};
static DEFINE_PER_CPU(struct zcache_preload, zcache_preloads) = { 0, };

static int zcache_do_preload(struct tmem_pool *pool)
{
	struct zcache_preload *kp;
	struct tmem_objnode *objnode;
	struct tmem_obj *obj;
	void *page;
	int ret = -ENOMEM;

	if (unlikely(zcache_objnode_cache == NULL))
		goto out;
	if (unlikely(zcache_obj_cache == NULL))
		goto out;
	preempt_disable();
	kp = &__get_cpu_var(zcache_preloads);
	while (kp->nr < ARRAY_SIZE(kp->objnodes)) {
		preempt_enable_no_resched();
		objnode = kmem_cache_alloc(zcache_objnode_cache,
				ZCACHE_GFP_MASK);
		if (unlikely(objnode == NULL)) {
			zcache_failed_alloc++;
			goto out;
		}
		preempt_disable();
		kp = &__get_cpu_var(zcache_preloads);
		if (kp->nr < ARRAY_SIZE(kp->objnodes))
			kp->objnodes[kp->nr++] = objnode;
		else
			kmem_cache_free(zcache_objnode_cache, objnode);
	}
	preempt_enable_no_resched();
	obj = kmem_cache_alloc(zcache_obj_cache, ZCACHE_GFP_MASK);
	if (unlikely(obj == NULL)) {
		zcache_failed_alloc++;
		goto out;
	}
	page = (void *)__get_free_page(ZCACHE_GFP_MASK);
	if (unlikely(page == NULL)) {
		zcache_failed_get_free_pages++;
		kmem_cache_free(zcache_obj_cache, obj);
		goto out;
	}
	preempt_disable();
	kp = &__get_cpu_var(zcache_preloads);
	if (kp->obj == NULL)
		kp->obj = obj;
	else
		kmem_cache_free(zcache_obj_cache, obj);
	if (kp->page == NULL)
		kp->page = page;
	else
		free_page((unsigned long)page);
	ret = 0;
out:
	return ret;
}

static void *zcache_get_free_page(void)
{
	struct zcache_preload *kp;
	void *page;

	kp = &__get_cpu_var(zcache_preloads);
	page = kp->page;
	BUG_ON(page == NULL);
	kp->page = NULL;
	return page;
}

static void zcache_free_page(void *p)
{
	free_page((unsigned long)p);
}

/*
 * zcache implementation for tmem host ops
 */

static struct tmem_objnode *zcache_objnode_alloc(struct tmem_pool *pool)
{
	struct tmem_objnode *objnode = NULL;
	unsigned long count;
	struct zcache_preload *kp;

	kp = &__get_cpu_var(zcache_preloads);
	if (kp->nr <= 0)
		goto out;
	objnode = kp->objnodes[kp->nr - 1];
	BUG_ON(objnode == NULL);
	kp->objnodes[kp->nr - 1] = NULL;
	kp->nr--;
	count = atomic_inc_return(&zcache_curr_objnode_count);
	if (count > zcache_curr_objnode_count_max)
		zcache_curr_objnode_count_max = count;
out:
	return objnode;
}

static void zcache_objnode_free(struct tmem_objnode *objnode,
					struct tmem_pool *pool)
{
	atomic_dec(&zcache_curr_objnode_count);
	BUG_ON(atomic_read(&zcache_curr_objnode_count) < 0);
	kmem_cache_free(zcache_objnode_cache, objnode);
}

static struct tmem_obj *zcache_obj_alloc(struct tmem_pool *pool)
{
	struct tmem_obj *obj = NULL;
	unsigned long count;
	struct zcache_preload *kp;

	kp = &__get_cpu_var(zcache_preloads);
	obj = kp->obj;
	BUG_ON(obj == NULL);
	kp->obj = NULL;
	count = atomic_inc_return(&zcache_curr_obj_count);
	if (count > zcache_curr_obj_count_max)
		zcache_curr_obj_count_max = count;
	return obj;
}

static void zcache_obj_free(struct tmem_obj *obj, struct tmem_pool *pool)
{
	atomic_dec(&zcache_curr_obj_count);
	BUG_ON(atomic_read(&zcache_curr_obj_count) < 0);
	kmem_cache_free(zcache_obj_cache, obj);
}

static struct tmem_hostops zcache_hostops = {
	.obj_alloc = zcache_obj_alloc,
	.obj_free = zcache_obj_free,
	.objnode_alloc = zcache_objnode_alloc,
	.objnode_free = zcache_objnode_free,
};

/*
 * zcache implementations for PAM page descriptor ops
 */

static atomic_t zcache_curr_eph_pampd_count = ATOMIC_INIT(0);
static unsigned long zcache_curr_eph_pampd_count_max;
static atomic_t zcache_curr_pers_pampd_count = ATOMIC_INIT(0);
static unsigned long zcache_curr_pers_pampd_count_max;

/* forward reference */
static int zcache_compress(struct page *from, void **out_va, unsigned *out_len);

static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph,
				struct tmem_pool *pool, struct tmem_oid *oid,
				 uint32_t index)
{
	void *pampd = NULL, *cdata;
	unsigned clen;
	int ret;
	unsigned long count;
	struct page *page = (struct page *)(data);
	struct zcache_client *cli = pool->client;
	uint16_t client_id = get_client_id_from_client(cli);
	unsigned long zv_mean_zsize;
	unsigned long curr_pers_pampd_count;
	u64 total_zsize;

	if (eph) {
		ret = zcache_compress(page, &cdata, &clen);
		if (ret == 0)
			goto out;
		if (clen == 0 || clen > zbud_max_buddy_size()) {
			zcache_compress_poor++;
			goto out;
		}
		pampd = (void *)zbud_create(client_id, pool->pool_id, oid,
						index, page, cdata, clen);
		if (pampd != NULL) {
			count = atomic_inc_return(&zcache_curr_eph_pampd_count);
			if (count > zcache_curr_eph_pampd_count_max)
				zcache_curr_eph_pampd_count_max = count;
		}
	} else {
		curr_pers_pampd_count =
			atomic_read(&zcache_curr_pers_pampd_count);
		if (curr_pers_pampd_count >
		    (zv_page_count_policy_percent * totalram_pages) / 100)
			goto out;
		ret = zcache_compress(page, &cdata, &clen);
		if (ret == 0)
			goto out;
		/* reject if compression is too poor */
		if (clen > zv_max_zsize) {
			zcache_compress_poor++;
			goto out;
		}
		/* reject if mean compression is too poor */
		if ((clen > zv_max_mean_zsize) && (curr_pers_pampd_count > 0)) {
			total_zsize = zs_get_total_size_bytes(cli->zspool);
			zv_mean_zsize = div_u64(total_zsize,
						curr_pers_pampd_count);
			if (zv_mean_zsize > zv_max_mean_zsize) {
				zcache_mean_compress_poor++;
				goto out;
			}
		}
		pampd = (void *)zv_create(cli->zspool, pool->pool_id,
						oid, index, cdata, clen);
		if (pampd == NULL)
			goto out;
		count = atomic_inc_return(&zcache_curr_pers_pampd_count);
		if (count > zcache_curr_pers_pampd_count_max)
			zcache_curr_pers_pampd_count_max = count;
	}
out:
	return pampd;
}

/*
 * fill the pageframe corresponding to the struct page with the data
 * from the passed pampd
 */
static int zcache_pampd_get_data(char *data, size_t *bufsize, bool raw,
					void *pampd, struct tmem_pool *pool,
					struct tmem_oid *oid, uint32_t index)
{
	int ret = 0;

	BUG_ON(is_ephemeral(pool));
	zv_decompress((struct page *)(data), pampd);
	return ret;
}

/*
 * fill the pageframe corresponding to the struct page with the data
 * from the passed pampd
 */
static int zcache_pampd_get_data_and_free(char *data, size_t *bufsize, bool raw,
					void *pampd, struct tmem_pool *pool,
					struct tmem_oid *oid, uint32_t index)
{
	int ret = 0;

	BUG_ON(!is_ephemeral(pool));
	zbud_decompress((struct page *)(data), pampd);
	zbud_free_and_delist((struct zbud_hdr *)pampd);
	atomic_dec(&zcache_curr_eph_pampd_count);
	return ret;
}

/*
 * free the pampd and remove it from any zcache lists
 * pampd must no longer be pointed to from any tmem data structures!
 */
static void zcache_pampd_free(void *pampd, struct tmem_pool *pool,
				struct tmem_oid *oid, uint32_t index)
{
	struct zcache_client *cli = pool->client;

	if (is_ephemeral(pool)) {
		zbud_free_and_delist((struct zbud_hdr *)pampd);
		atomic_dec(&zcache_curr_eph_pampd_count);
		BUG_ON(atomic_read(&zcache_curr_eph_pampd_count) < 0);
	} else {
		zv_free(cli->zspool, pampd);
		atomic_dec(&zcache_curr_pers_pampd_count);
		BUG_ON(atomic_read(&zcache_curr_pers_pampd_count) < 0);
	}
}

static void zcache_pampd_free_obj(struct tmem_pool *pool, struct tmem_obj *obj)
{
}

static void zcache_pampd_new_obj(struct tmem_obj *obj)
{
}

static int zcache_pampd_replace_in_obj(void *pampd, struct tmem_obj *obj)
{
	return -1;
}

static bool zcache_pampd_is_remote(void *pampd)
{
	return 0;
}

static struct tmem_pamops zcache_pamops = {
	.create = zcache_pampd_create,
	.get_data = zcache_pampd_get_data,
	.get_data_and_free = zcache_pampd_get_data_and_free,
	.free = zcache_pampd_free,
	.free_obj = zcache_pampd_free_obj,
	.new_obj = zcache_pampd_new_obj,
	.replace_in_obj = zcache_pampd_replace_in_obj,
	.is_remote = zcache_pampd_is_remote,
};

/*
 * zcache compression/decompression and related per-cpu stuff
 */

static DEFINE_PER_CPU(unsigned char *, zcache_dstmem);
#define ZCACHE_DSTMEM_ORDER 1

static int zcache_compress(struct page *from, void **out_va, unsigned *out_len)
{
	int ret = 0;
	unsigned char *dmem = __get_cpu_var(zcache_dstmem);
	char *from_va;

	BUG_ON(!irqs_disabled());
	if (unlikely(dmem == NULL))
		goto out;  /* no buffer or no compressor so can't compress */
	*out_len = PAGE_SIZE << ZCACHE_DSTMEM_ORDER;
	from_va = kmap_atomic(from);
	mb();
	ret = zcache_comp_op(ZCACHE_COMPOP_COMPRESS, from_va, PAGE_SIZE, dmem,
				out_len);
	BUG_ON(ret);
	*out_va = dmem;
	kunmap_atomic(from_va);
	ret = 1;
out:
	return ret;
}

static int zcache_comp_cpu_up(int cpu)
{
	struct crypto_comp *tfm;

	tfm = crypto_alloc_comp(zcache_comp_name, 0, 0);
	if (IS_ERR(tfm))
		return NOTIFY_BAD;
	*per_cpu_ptr(zcache_comp_pcpu_tfms, cpu) = tfm;
	return NOTIFY_OK;
}

static void zcache_comp_cpu_down(int cpu)
{
	struct crypto_comp *tfm;

	tfm = *per_cpu_ptr(zcache_comp_pcpu_tfms, cpu);
	crypto_free_comp(tfm);
	*per_cpu_ptr(zcache_comp_pcpu_tfms, cpu) = NULL;
}

static int zcache_cpu_notifier(struct notifier_block *nb,
				unsigned long action, void *pcpu)
{
	int ret, cpu = (long)pcpu;
	struct zcache_preload *kp;

	switch (action) {
	case CPU_UP_PREPARE:
		ret = zcache_comp_cpu_up(cpu);
		if (ret != NOTIFY_OK) {
			pr_err("zcache: can't allocate compressor transform\n");
			return ret;
		}
		per_cpu(zcache_dstmem, cpu) = (void *)__get_free_pages(
			GFP_KERNEL | __GFP_REPEAT, ZCACHE_DSTMEM_ORDER);
		break;
	case CPU_DEAD:
	case CPU_UP_CANCELED:
		zcache_comp_cpu_down(cpu);
		free_pages((unsigned long)per_cpu(zcache_dstmem, cpu),
			ZCACHE_DSTMEM_ORDER);
		per_cpu(zcache_dstmem, cpu) = NULL;
		kp = &per_cpu(zcache_preloads, cpu);
		while (kp->nr) {
			kmem_cache_free(zcache_objnode_cache,
					kp->objnodes[kp->nr - 1]);
			kp->objnodes[kp->nr - 1] = NULL;
			kp->nr--;
		}
		if (kp->obj) {
			kmem_cache_free(zcache_obj_cache, kp->obj);
			kp->obj = NULL;
		}
		if (kp->page) {
			free_page((unsigned long)kp->page);
			kp->page = NULL;
		}
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block zcache_cpu_notifier_block = {
	.notifier_call = zcache_cpu_notifier
};

#ifdef CONFIG_SYSFS
#define ZCACHE_SYSFS_RO(_name) \
	static ssize_t zcache_##_name##_show(struct kobject *kobj, \
				struct kobj_attribute *attr, char *buf) \
	{ \
		return sprintf(buf, "%lu\n", zcache_##_name); \
	} \
	static struct kobj_attribute zcache_##_name##_attr = { \
		.attr = { .name = __stringify(_name), .mode = 0444 }, \
		.show = zcache_##_name##_show, \
	}

#define ZCACHE_SYSFS_RO_ATOMIC(_name) \
	static ssize_t zcache_##_name##_show(struct kobject *kobj, \
				struct kobj_attribute *attr, char *buf) \
	{ \
	    return sprintf(buf, "%d\n", atomic_read(&zcache_##_name)); \
	} \
	static struct kobj_attribute zcache_##_name##_attr = { \
		.attr = { .name = __stringify(_name), .mode = 0444 }, \
		.show = zcache_##_name##_show, \
	}

#define ZCACHE_SYSFS_RO_CUSTOM(_name, _func) \
	static ssize_t zcache_##_name##_show(struct kobject *kobj, \
				struct kobj_attribute *attr, char *buf) \
	{ \
	    return _func(buf); \
	} \
	static struct kobj_attribute zcache_##_name##_attr = { \
		.attr = { .name = __stringify(_name), .mode = 0444 }, \
		.show = zcache_##_name##_show, \
	}

ZCACHE_SYSFS_RO(curr_obj_count_max);
ZCACHE_SYSFS_RO(curr_objnode_count_max);
ZCACHE_SYSFS_RO(flush_total);
ZCACHE_SYSFS_RO(flush_found);
ZCACHE_SYSFS_RO(flobj_total);
ZCACHE_SYSFS_RO(flobj_found);
ZCACHE_SYSFS_RO(failed_eph_puts);
ZCACHE_SYSFS_RO(failed_pers_puts);
ZCACHE_SYSFS_RO(zbud_curr_zbytes);
ZCACHE_SYSFS_RO(zbud_cumul_zpages);
ZCACHE_SYSFS_RO(zbud_cumul_zbytes);
ZCACHE_SYSFS_RO(zbud_buddied_count);
ZCACHE_SYSFS_RO(zbpg_unused_list_count);
ZCACHE_SYSFS_RO(evicted_raw_pages);
ZCACHE_SYSFS_RO(evicted_unbuddied_pages);
ZCACHE_SYSFS_RO(evicted_buddied_pages);
ZCACHE_SYSFS_RO(failed_get_free_pages);
ZCACHE_SYSFS_RO(failed_alloc);
ZCACHE_SYSFS_RO(put_to_flush);
ZCACHE_SYSFS_RO(compress_poor);
ZCACHE_SYSFS_RO(mean_compress_poor);
ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_raw_pages);
ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_zpages);
ZCACHE_SYSFS_RO_ATOMIC(curr_obj_count);
ZCACHE_SYSFS_RO_ATOMIC(curr_objnode_count);
ZCACHE_SYSFS_RO_CUSTOM(zbud_unbuddied_list_counts,
			zbud_show_unbuddied_list_counts);
ZCACHE_SYSFS_RO_CUSTOM(zbud_cumul_chunk_counts,
			zbud_show_cumul_chunk_counts);
ZCACHE_SYSFS_RO_CUSTOM(zv_curr_dist_counts,
			zv_curr_dist_counts_show);
ZCACHE_SYSFS_RO_CUSTOM(zv_cumul_dist_counts,
			zv_cumul_dist_counts_show);

static struct attribute *zcache_attrs[] = {
	&zcache_curr_obj_count_attr.attr,
	&zcache_curr_obj_count_max_attr.attr,
	&zcache_curr_objnode_count_attr.attr,
	&zcache_curr_objnode_count_max_attr.attr,
	&zcache_flush_total_attr.attr,
	&zcache_flobj_total_attr.attr,
	&zcache_flush_found_attr.attr,
	&zcache_flobj_found_attr.attr,
	&zcache_failed_eph_puts_attr.attr,
	&zcache_failed_pers_puts_attr.attr,
	&zcache_compress_poor_attr.attr,
	&zcache_mean_compress_poor_attr.attr,
	&zcache_zbud_curr_raw_pages_attr.attr,
	&zcache_zbud_curr_zpages_attr.attr,
	&zcache_zbud_curr_zbytes_attr.attr,
	&zcache_zbud_cumul_zpages_attr.attr,
	&zcache_zbud_cumul_zbytes_attr.attr,
	&zcache_zbud_buddied_count_attr.attr,
	&zcache_zbpg_unused_list_count_attr.attr,
	&zcache_evicted_raw_pages_attr.attr,
	&zcache_evicted_unbuddied_pages_attr.attr,
	&zcache_evicted_buddied_pages_attr.attr,
	&zcache_failed_get_free_pages_attr.attr,
	&zcache_failed_alloc_attr.attr,
	&zcache_put_to_flush_attr.attr,
	&zcache_zbud_unbuddied_list_counts_attr.attr,
	&zcache_zbud_cumul_chunk_counts_attr.attr,
	&zcache_zv_curr_dist_counts_attr.attr,
	&zcache_zv_cumul_dist_counts_attr.attr,
	&zcache_zv_max_zsize_attr.attr,
	&zcache_zv_max_mean_zsize_attr.attr,
	&zcache_zv_page_count_policy_percent_attr.attr,
	NULL,
};

static struct attribute_group zcache_attr_group = {
	.attrs = zcache_attrs,
	.name = "zcache",
};

#endif /* CONFIG_SYSFS */
/*
 * When zcache is disabled ("frozen"), pools can be created and destroyed,
 * but all puts (and thus all other operations that require memory allocation)
 * must fail.  If zcache is unfrozen, accepts puts, then frozen again,
 * data consistency requires all puts while frozen to be converted into
 * flushes.
 */
static bool zcache_freeze;

/*
 * zcache shrinker interface (only useful for ephemeral pages, so zbud only)
 */
static int shrink_zcache_memory(struct shrinker *shrink,
				struct shrink_control *sc)
{
	int ret = -1;
	int nr = sc->nr_to_scan;
	gfp_t gfp_mask = sc->gfp_mask;

	if (nr >= 0) {
		if (!(gfp_mask & __GFP_FS))
			/* does this case really need to be skipped? */
			goto out;
		zbud_evict_pages(nr);
	}
	ret = (int)atomic_read(&zcache_zbud_curr_raw_pages);
out:
	return ret;
}

static struct shrinker zcache_shrinker = {
	.shrink = shrink_zcache_memory,
	.seeks = DEFAULT_SEEKS,
};

/*
 * zcache shims between cleancache/frontswap ops and tmem
 */

static int zcache_put_page(int cli_id, int pool_id, struct tmem_oid *oidp,
				uint32_t index, struct page *page)
{
	struct tmem_pool *pool;
	int ret = -1;

	BUG_ON(!irqs_disabled());
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	if (unlikely(pool == NULL))
		goto out;
	if (!zcache_freeze && zcache_do_preload(pool) == 0) {
		/* preload does preempt_disable on success */
		ret = tmem_put(pool, oidp, index, (char *)(page),
				PAGE_SIZE, 0, is_ephemeral(pool));
		if (ret < 0) {
			if (is_ephemeral(pool))
				zcache_failed_eph_puts++;
			else
				zcache_failed_pers_puts++;
		}
		zcache_put_pool(pool);
		preempt_enable_no_resched();
	} else {
		zcache_put_to_flush++;
		if (atomic_read(&pool->obj_count) > 0)
			/* the put fails whether the flush succeeds or not */
			(void)tmem_flush_page(pool, oidp, index);
		zcache_put_pool(pool);
	}
out:
	return ret;
}

static int zcache_get_page(int cli_id, int pool_id, struct tmem_oid *oidp,
				uint32_t index, struct page *page)
{
	struct tmem_pool *pool;
	int ret = -1;
	unsigned long flags;
	size_t size = PAGE_SIZE;

	local_irq_save(flags);
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	if (likely(pool != NULL)) {
		if (atomic_read(&pool->obj_count) > 0)
			ret = tmem_get(pool, oidp, index, (char *)(page),
					&size, 0, is_ephemeral(pool));
		zcache_put_pool(pool);
	}
	local_irq_restore(flags);
	return ret;
}

static int zcache_flush_page(int cli_id, int pool_id,
				struct tmem_oid *oidp, uint32_t index)
{
	struct tmem_pool *pool;
	int ret = -1;
	unsigned long flags;

	local_irq_save(flags);
	zcache_flush_total++;
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	if (likely(pool != NULL)) {
		if (atomic_read(&pool->obj_count) > 0)
			ret = tmem_flush_page(pool, oidp, index);
		zcache_put_pool(pool);
	}
	if (ret >= 0)
		zcache_flush_found++;
	local_irq_restore(flags);
	return ret;
}

static int zcache_flush_object(int cli_id, int pool_id,
				struct tmem_oid *oidp)
{
	struct tmem_pool *pool;
	int ret = -1;
	unsigned long flags;

	local_irq_save(flags);
	zcache_flobj_total++;
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	if (likely(pool != NULL)) {
		if (atomic_read(&pool->obj_count) > 0)
			ret = tmem_flush_object(pool, oidp);
		zcache_put_pool(pool);
	}
	if (ret >= 0)
		zcache_flobj_found++;
	local_irq_restore(flags);
	return ret;
}

static int zcache_destroy_pool(int cli_id, int pool_id)
{
	struct tmem_pool *pool = NULL;
	struct zcache_client *cli = NULL;
	int ret = -1;

	if (pool_id < 0)
		goto out;
	if (cli_id == LOCAL_CLIENT)
		cli = &zcache_host;
	else if ((unsigned int)cli_id < MAX_CLIENTS)
		cli = &zcache_clients[cli_id];
	if (cli == NULL)
		goto out;
	atomic_inc(&cli->refcount);
	pool = cli->tmem_pools[pool_id];
	if (pool == NULL)
		goto out;
	cli->tmem_pools[pool_id] = NULL;
	/* wait for pool activity on other cpus to quiesce */
	while (atomic_read(&pool->refcount) != 0)
		;
	atomic_dec(&cli->refcount);
	local_bh_disable();
	ret = tmem_destroy_pool(pool);
	local_bh_enable();
	kfree(pool);
	pr_info("zcache: destroyed pool id=%d, cli_id=%d\n",
			pool_id, cli_id);
out:
	return ret;
}

static int zcache_new_pool(uint16_t cli_id, uint32_t flags)
{
	int poolid = -1;
	struct tmem_pool *pool;
	struct zcache_client *cli = NULL;

	if (cli_id == LOCAL_CLIENT)
		cli = &zcache_host;
	else if ((unsigned int)cli_id < MAX_CLIENTS)
		cli = &zcache_clients[cli_id];
	if (cli == NULL)
		goto out;
	atomic_inc(&cli->refcount);
	pool = kmalloc(sizeof(struct tmem_pool), GFP_ATOMIC);
	if (pool == NULL) {
		pr_info("zcache: pool creation failed: out of memory\n");
		goto out;
	}

	for (poolid = 0; poolid < MAX_POOLS_PER_CLIENT; poolid++)
		if (cli->tmem_pools[poolid] == NULL)
			break;
	if (poolid >= MAX_POOLS_PER_CLIENT) {
		pr_info("zcache: pool creation failed: max exceeded\n");
		kfree(pool);
		poolid = -1;
		goto out;
	}
	atomic_set(&pool->refcount, 0);
	pool->client = cli;
	pool->pool_id = poolid;
	tmem_new_pool(pool, flags);
	cli->tmem_pools[poolid] = pool;
	pr_info("zcache: created %s tmem pool, id=%d, client=%d\n",
		flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral",
		poolid, cli_id);
out:
	if (cli != NULL)
		atomic_dec(&cli->refcount);
	return poolid;
}

/**********
 * Two kernel functionalities currently can be layered on top of tmem.
 * These are "cleancache" which is used as a second-chance cache for clean
 * page cache pages; and "frontswap" which is used for swap pages
 * to avoid writes to disk.  A generic "shim" is provided here for each
 * to translate in-kernel semantics to zcache semantics.
 */

#ifdef CONFIG_CLEANCACHE
static void zcache_cleancache_put_page(int pool_id,
					struct cleancache_filekey key,
					pgoff_t index, struct page *page)
{
	u32 ind = (u32) index;
	struct tmem_oid oid = *(struct tmem_oid *)&key;

	if (likely(ind == index))
		(void)zcache_put_page(LOCAL_CLIENT, pool_id, &oid, index, page);
}

static int zcache_cleancache_get_page(int pool_id,
					struct cleancache_filekey key,
					pgoff_t index, struct page *page)
{
	u32 ind = (u32) index;
	struct tmem_oid oid = *(struct tmem_oid *)&key;
	int ret = -1;

	if (likely(ind == index))
		ret = zcache_get_page(LOCAL_CLIENT, pool_id, &oid, index, page);
	return ret;
}

static void zcache_cleancache_flush_page(int pool_id,
					struct cleancache_filekey key,
					pgoff_t index)
{
	u32 ind = (u32) index;
	struct tmem_oid oid = *(struct tmem_oid *)&key;

	if (likely(ind == index))
		(void)zcache_flush_page(LOCAL_CLIENT, pool_id, &oid, ind);
}

static void zcache_cleancache_flush_inode(int pool_id,
					struct cleancache_filekey key)
{
	struct tmem_oid oid = *(struct tmem_oid *)&key;

	(void)zcache_flush_object(LOCAL_CLIENT, pool_id, &oid);
}

static void zcache_cleancache_flush_fs(int pool_id)
{
	if (pool_id >= 0)
		(void)zcache_destroy_pool(LOCAL_CLIENT, pool_id);
}

static int zcache_cleancache_init_fs(size_t pagesize)
{
	BUG_ON(sizeof(struct cleancache_filekey) !=
				sizeof(struct tmem_oid));
	BUG_ON(pagesize != PAGE_SIZE);
	return zcache_new_pool(LOCAL_CLIENT, 0);
}

static int zcache_cleancache_init_shared_fs(char *uuid, size_t pagesize)
{
	/* shared pools are unsupported and map to private */
	BUG_ON(sizeof(struct cleancache_filekey) !=
				sizeof(struct tmem_oid));
	BUG_ON(pagesize != PAGE_SIZE);
	return zcache_new_pool(LOCAL_CLIENT, 0);
}

static struct cleancache_ops zcache_cleancache_ops = {
	.put_page = zcache_cleancache_put_page,
	.get_page = zcache_cleancache_get_page,
	.flush_page = zcache_cleancache_flush_page,
	.flush_inode = zcache_cleancache_flush_inode,
	.flush_fs = zcache_cleancache_flush_fs,
	.init_shared_fs = zcache_cleancache_init_shared_fs,
	.init_fs = zcache_cleancache_init_fs
};

struct cleancache_ops zcache_cleancache_register_ops(void)
{
	struct cleancache_ops old_ops =
		cleancache_register_ops(&zcache_cleancache_ops);

	return old_ops;
}
#endif

#ifdef CONFIG_FRONTSWAP
/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
static int zcache_frontswap_poolid = -1;

/*
 * Swizzling increases objects per swaptype, increasing tmem concurrency
 * for heavy swaploads.  Later, larger nr_cpus -> larger SWIZ_BITS
 * Setting SWIZ_BITS to 27 basically reconstructs the swap entry from
 * frontswap_get_page(), but has side-effects. Hence using 8.
 */
#define SWIZ_BITS		8
#define SWIZ_MASK		((1 << SWIZ_BITS) - 1)
#define _oswiz(_type, _ind)	((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
#define iswiz(_ind)		(_ind >> SWIZ_BITS)

static inline struct tmem_oid oswiz(unsigned type, u32 ind)
{
	struct tmem_oid oid = { .oid = { 0 } };
	oid.oid[0] = _oswiz(type, ind);
	return oid;
}

static int zcache_frontswap_put_page(unsigned type, pgoff_t offset,
				   struct page *page)
{
	u64 ind64 = (u64)offset;
	u32 ind = (u32)offset;
	struct tmem_oid oid = oswiz(type, ind);
	int ret = -1;
	unsigned long flags;

	BUG_ON(!PageLocked(page));
	if (likely(ind64 == ind)) {
		local_irq_save(flags);
		ret = zcache_put_page(LOCAL_CLIENT, zcache_frontswap_poolid,
					&oid, iswiz(ind), page);
		local_irq_restore(flags);
	}
	return ret;
}

/* returns 0 if the page was successfully gotten from frontswap, -1 if
 * was not present (should never happen!) */
static int zcache_frontswap_get_page(unsigned type, pgoff_t offset,
				   struct page *page)
{
	u64 ind64 = (u64)offset;
	u32 ind = (u32)offset;
	struct tmem_oid oid = oswiz(type, ind);
	int ret = -1;

	BUG_ON(!PageLocked(page));
	if (likely(ind64 == ind))
		ret = zcache_get_page(LOCAL_CLIENT, zcache_frontswap_poolid,
					&oid, iswiz(ind), page);
	return ret;
}

/* flush a single page from frontswap */
static void zcache_frontswap_flush_page(unsigned type, pgoff_t offset)
{
	u64 ind64 = (u64)offset;
	u32 ind = (u32)offset;
	struct tmem_oid oid = oswiz(type, ind);

	if (likely(ind64 == ind))
		(void)zcache_flush_page(LOCAL_CLIENT, zcache_frontswap_poolid,
					&oid, iswiz(ind));
}

/* flush all pages from the passed swaptype */
static void zcache_frontswap_flush_area(unsigned type)
{
	struct tmem_oid oid;
	int ind;

	for (ind = SWIZ_MASK; ind >= 0; ind--) {
		oid = oswiz(type, ind);
		(void)zcache_flush_object(LOCAL_CLIENT,
						zcache_frontswap_poolid, &oid);
	}
}

static void zcache_frontswap_init(unsigned ignored)
{
	/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
	if (zcache_frontswap_poolid < 0)
		zcache_frontswap_poolid =
			zcache_new_pool(LOCAL_CLIENT, TMEM_POOL_PERSIST);
}

static struct frontswap_ops zcache_frontswap_ops = {
	.put_page = zcache_frontswap_put_page,
	.get_page = zcache_frontswap_get_page,
	.flush_page = zcache_frontswap_flush_page,
	.flush_area = zcache_frontswap_flush_area,
	.init = zcache_frontswap_init
};

struct frontswap_ops zcache_frontswap_register_ops(void)
{
	struct frontswap_ops old_ops =
		frontswap_register_ops(&zcache_frontswap_ops);

	return old_ops;
}
#endif

/*
 * zcache initialization
 * NOTE FOR NOW zcache MUST BE PROVIDED AS A KERNEL BOOT PARAMETER OR
 * NOTHING HAPPENS!
 */

static int zcache_enabled;

static int __init enable_zcache(char *s)
{
	zcache_enabled = 1;
	return 1;
}
__setup("zcache", enable_zcache);

/* allow independent dynamic disabling of cleancache and frontswap */

static int use_cleancache = 1;

static int __init no_cleancache(char *s)
{
	use_cleancache = 0;
	return 1;
}

__setup("nocleancache", no_cleancache);

static int use_frontswap = 1;

static int __init no_frontswap(char *s)
{
	use_frontswap = 0;
	return 1;
}

__setup("nofrontswap", no_frontswap);

static int __init enable_zcache_compressor(char *s)
{
	strncpy(zcache_comp_name, s, ZCACHE_COMP_NAME_SZ);
	zcache_enabled = 1;
	return 1;
}
__setup("zcache=", enable_zcache_compressor);


static int zcache_comp_init(void)
{
	int ret = 0;

	/* check crypto algorithm */
	if (*zcache_comp_name != '\0') {
		ret = crypto_has_comp(zcache_comp_name, 0, 0);
		if (!ret)
			pr_info("zcache: %s not supported\n",
					zcache_comp_name);
	}
	if (!ret)
		strcpy(zcache_comp_name, "lzo");
	ret = crypto_has_comp(zcache_comp_name, 0, 0);
	if (!ret) {
		ret = 1;
		goto out;
	}
	pr_info("zcache: using %s compressor\n", zcache_comp_name);

	/* alloc percpu transforms */
	ret = 0;
	zcache_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *);
	if (!zcache_comp_pcpu_tfms)
		ret = 1;
out:
	return ret;
}

static int __init zcache_init(void)
{
	int ret = 0;

#ifdef CONFIG_SYSFS
	ret = sysfs_create_group(mm_kobj, &zcache_attr_group);
	if (ret) {
		pr_err("zcache: can't create sysfs\n");
		goto out;
	}
#endif /* CONFIG_SYSFS */
#if defined(CONFIG_CLEANCACHE) || defined(CONFIG_FRONTSWAP)
	if (zcache_enabled) {
		unsigned int cpu;

		tmem_register_hostops(&zcache_hostops);
		tmem_register_pamops(&zcache_pamops);
		ret = register_cpu_notifier(&zcache_cpu_notifier_block);
		if (ret) {
			pr_err("zcache: can't register cpu notifier\n");
			goto out;
		}
		ret = zcache_comp_init();
		if (ret) {
			pr_err("zcache: compressor initialization failed\n");
			goto out;
		}
		for_each_online_cpu(cpu) {
			void *pcpu = (void *)(long)cpu;
			zcache_cpu_notifier(&zcache_cpu_notifier_block,
				CPU_UP_PREPARE, pcpu);
		}
	}
	zcache_objnode_cache = kmem_cache_create("zcache_objnode",
				sizeof(struct tmem_objnode), 0, 0, NULL);
	zcache_obj_cache = kmem_cache_create("zcache_obj",
				sizeof(struct tmem_obj), 0, 0, NULL);
	ret = zcache_new_client(LOCAL_CLIENT);
	if (ret) {
		pr_err("zcache: can't create client\n");
		goto out;
	}
#endif
#ifdef CONFIG_CLEANCACHE
	if (zcache_enabled && use_cleancache) {
		struct cleancache_ops old_ops;

		zbud_init();
		register_shrinker(&zcache_shrinker);
		old_ops = zcache_cleancache_register_ops();
		pr_info("zcache: cleancache enabled using kernel "
			"transcendent memory and compression buddies\n");
		if (old_ops.init_fs != NULL)
			pr_warning("zcache: cleancache_ops overridden");
	}
#endif
#ifdef CONFIG_FRONTSWAP
	if (zcache_enabled && use_frontswap) {
		struct frontswap_ops old_ops;

		old_ops = zcache_frontswap_register_ops();
		pr_info("zcache: frontswap enabled using kernel "
			"transcendent memory and zsmalloc\n");
		if (old_ops.init != NULL)
			pr_warning("zcache: frontswap_ops overridden");
	}
#endif
out:
	return ret;
}

module_init(zcache_init)