aboutsummaryrefslogtreecommitdiff
path: root/drivers/staging/zcache/zcache-main.c
blob: 4272ab9c29ff5c621f604251e3b60a3f41e73ff2 (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
/*
 * zcache.c
 *
 * Copyright (c) 2010-2012, Dan Magenheimer, Oracle Corp.
 * Copyright (c) 2010,2011, Nitin Gupta
 *
 * Zcache provides an in-kernel "host implementation" for transcendent memory
 * ("tmem") and, thus indirectly, for cleancache and frontswap.  Zcache uses
 * lzo1x compression to improve density and an embedded allocator called
 * "zbud" which "buddies" two compressed pages semi-optimally in each physical
 * pageframe.  Zbud is integrally tied into tmem to allow pageframes to
 * be "reclaimed" efficiently.
 */

#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/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>

#include <linux/cleancache.h>
#include <linux/frontswap.h>
#include "tmem.h"
#include "zcache.h"
#include "zbud.h"
#include "ramster.h"
#ifdef CONFIG_RAMSTER
static bool ramster_enabled __read_mostly;
#else
#define ramster_enabled false
#endif

#ifndef __PG_WAS_ACTIVE
static inline bool PageWasActive(struct page *page)
{
	return true;
}

static inline void SetPageWasActive(struct page *page)
{
}
#endif

#ifdef FRONTSWAP_HAS_EXCLUSIVE_GETS
static bool frontswap_has_exclusive_gets __read_mostly = true;
#else
static bool frontswap_has_exclusive_gets __read_mostly;
static inline void frontswap_tmem_exclusive_gets(bool b)
{
}
#endif

/* enable (or fix code) when Seth's patches are accepted upstream */
#define zcache_writeback_enabled 0

static bool zcache_enabled __read_mostly;
static bool disable_cleancache __read_mostly;
static bool disable_frontswap __read_mostly;
static bool disable_frontswap_ignore_nonactive __read_mostly;
static bool disable_cleancache_ignore_nonactive __read_mostly;
static char *namestr __read_mostly = "zcache";

#define ZCACHE_GFP_MASK \
	(__GFP_FS | __GFP_NORETRY | __GFP_NOWARN | __GFP_NOMEMALLOC)

MODULE_LICENSE("GPL");

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

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 = -1;

	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;
	default:
		ret = -EINVAL;
	}
	put_cpu();
	return ret;
}

/*
 * policy parameters
 */

/*
 * byte count defining poor compression; pages with greater zsize will be
 * rejected
 */
static unsigned int zbud_max_zsize __read_mostly = (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 zbud_max_mean_zsize __read_mostly = (PAGE_SIZE / 8) * 5;

/*
 * 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 DEFINE_PER_CPU(struct zcache_preload, zcache_preloads) = { 0, };

/* we try to keep these statistics SMP-consistent */
static ssize_t zcache_obj_count;
static atomic_t zcache_obj_atomic = ATOMIC_INIT(0);
static ssize_t zcache_obj_count_max;
static ssize_t zcache_objnode_count;
static inline void inc_zcache_obj_count(void)
{
	zcache_obj_count = atomic_inc_return(&zcache_obj_atomic);
	if (zcache_obj_count > zcache_obj_count_max)
		zcache_obj_count_max = zcache_obj_count;
}
static inline void dec_zcache_obj_count(void)
{
	zcache_obj_count = atomic_dec_return(&zcache_obj_atomic);
	BUG_ON(zcache_obj_count < 0);
};
static atomic_t zcache_objnode_atomic = ATOMIC_INIT(0);
static ssize_t zcache_objnode_count_max;
static inline void inc_zcache_objnode_count(void)
{
	zcache_objnode_count = atomic_inc_return(&zcache_objnode_atomic);
	if (zcache_objnode_count > zcache_objnode_count_max)
		zcache_objnode_count_max = zcache_objnode_count;
};
static inline void dec_zcache_objnode_count(void)
{
	zcache_objnode_count = atomic_dec_return(&zcache_objnode_atomic);
	BUG_ON(zcache_objnode_count < 0);
};
static u64 zcache_eph_zbytes;
static atomic_long_t zcache_eph_zbytes_atomic = ATOMIC_INIT(0);
static u64 zcache_eph_zbytes_max;
static inline void inc_zcache_eph_zbytes(unsigned clen)
{
	zcache_eph_zbytes = atomic_long_add_return(clen, &zcache_eph_zbytes_atomic);
	if (zcache_eph_zbytes > zcache_eph_zbytes_max)
		zcache_eph_zbytes_max = zcache_eph_zbytes;
};
static inline void dec_zcache_eph_zbytes(unsigned zsize)
{
	zcache_eph_zbytes = atomic_long_sub_return(zsize, &zcache_eph_zbytes_atomic);
};
static u64 zcache_pers_zbytes;
static atomic_long_t zcache_pers_zbytes_atomic = ATOMIC_INIT(0);
static u64 zcache_pers_zbytes_max;
static ssize_t zcache_eph_pageframes;
static inline void inc_zcache_pers_zbytes(unsigned clen)
{
	zcache_pers_zbytes = atomic_long_add_return(clen, &zcache_pers_zbytes_atomic);
	if (zcache_pers_zbytes > zcache_pers_zbytes_max)
		zcache_pers_zbytes_max = zcache_pers_zbytes;
}
static inline void dec_zcache_pers_zbytes(unsigned zsize)
{
	zcache_pers_zbytes = atomic_long_sub_return(zsize, &zcache_pers_zbytes_atomic);
}
static atomic_t zcache_eph_pageframes_atomic = ATOMIC_INIT(0);
static ssize_t zcache_eph_pageframes_max;
static ssize_t zcache_pers_pageframes;
static inline void inc_zcache_eph_pageframes(void)
{
	zcache_eph_pageframes = atomic_inc_return(&zcache_eph_pageframes_atomic);
	if (zcache_eph_pageframes > zcache_eph_pageframes_max)
		zcache_eph_pageframes_max = zcache_eph_pageframes;
};
static inline void dec_zcache_eph_pageframes(void)
{
	zcache_eph_pageframes = atomic_dec_return(&zcache_eph_pageframes_atomic);
};
static atomic_t zcache_pers_pageframes_atomic = ATOMIC_INIT(0);
static ssize_t zcache_pers_pageframes_max;
static ssize_t zcache_pageframes_alloced;
static inline void inc_zcache_pers_pageframes(void)
{
	zcache_pers_pageframes = atomic_inc_return(&zcache_pers_pageframes_atomic);
	if (zcache_pers_pageframes > zcache_pers_pageframes_max)
		zcache_pers_pageframes_max = zcache_pers_pageframes;
}
static inline void dec_zcache_pers_pageframes(void)
{
	zcache_pers_pageframes = atomic_dec_return(&zcache_pers_pageframes_atomic);
}
static atomic_t zcache_pageframes_alloced_atomic = ATOMIC_INIT(0);
static ssize_t zcache_pageframes_freed;
static inline void inc_zcache_pageframes_alloced(void)
{
	zcache_pageframes_alloced = atomic_inc_return(&zcache_pageframes_alloced_atomic);
};
static atomic_t zcache_pageframes_freed_atomic = ATOMIC_INIT(0);
static ssize_t zcache_eph_zpages;
static inline void inc_zcache_pageframes_freed(void)
{
	zcache_pageframes_freed = atomic_inc_return(&zcache_pageframes_freed_atomic);
}
static atomic_t zcache_eph_zpages_atomic = ATOMIC_INIT(0);
static ssize_t zcache_eph_zpages_max;
static ssize_t zcache_pers_zpages;
static inline void inc_zcache_eph_zpages(void)
{
	zcache_eph_zpages = atomic_inc_return(&zcache_eph_zpages_atomic);
	if (zcache_eph_zpages > zcache_eph_zpages_max)
		zcache_eph_zpages_max = zcache_eph_zpages;
}
static inline void dec_zcache_eph_zpages(unsigned zpages)
{
	zcache_eph_zpages = atomic_sub_return(zpages, &zcache_eph_zpages_atomic);
}
static atomic_t zcache_pers_zpages_atomic = ATOMIC_INIT(0);
static ssize_t zcache_pers_zpages_max;
static inline void inc_zcache_pers_zpages(void)
{
	zcache_pers_zpages = atomic_inc_return(&zcache_pers_zpages_atomic);
	if (zcache_pers_zpages > zcache_pers_zpages_max)
		zcache_pers_zpages_max = zcache_pers_zpages;
}
static inline void dec_zcache_pers_zpages(unsigned zpages)
{
	zcache_pers_zpages = atomic_sub_return(zpages, &zcache_pers_zpages_atomic);
}
/* but for the rest of these, counting races are ok */
static ssize_t zcache_flush_total;
static ssize_t zcache_flush_found;
static ssize_t zcache_flobj_total;
static ssize_t zcache_flobj_found;
static ssize_t zcache_failed_eph_puts;
static ssize_t zcache_failed_pers_puts;
static ssize_t zcache_failed_getfreepages;
static ssize_t zcache_failed_alloc;
static ssize_t zcache_put_to_flush;
static ssize_t zcache_compress_poor;
static ssize_t zcache_mean_compress_poor;
static ssize_t zcache_eph_ate_tail;
static ssize_t zcache_eph_ate_tail_failed;
static ssize_t zcache_pers_ate_eph;
static ssize_t zcache_pers_ate_eph_failed;
static ssize_t zcache_evicted_eph_zpages;
static ssize_t zcache_evicted_eph_pageframes;
static ssize_t zcache_last_active_file_pageframes;
static ssize_t zcache_last_inactive_file_pageframes;
static ssize_t zcache_last_active_anon_pageframes;
static ssize_t zcache_last_inactive_anon_pageframes;
static ssize_t zcache_eph_nonactive_puts_ignored;
static ssize_t zcache_pers_nonactive_puts_ignored;
static ssize_t zcache_writtenback_pages;
static ssize_t zcache_outstanding_writeback_pages;

#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#define	zdfs	debugfs_create_size_t
#define	zdfs64	debugfs_create_u64
static int zcache_debugfs_init(void)
{
	struct dentry *root = debugfs_create_dir("zcache", NULL);
	if (root == NULL)
		return -ENXIO;

	zdfs("obj_count", S_IRUGO, root, &zcache_obj_count);
	zdfs("obj_count_max", S_IRUGO, root, &zcache_obj_count_max);
	zdfs("objnode_count", S_IRUGO, root, &zcache_objnode_count);
	zdfs("objnode_count_max", S_IRUGO, root, &zcache_objnode_count_max);
	zdfs("flush_total", S_IRUGO, root, &zcache_flush_total);
	zdfs("flush_found", S_IRUGO, root, &zcache_flush_found);
	zdfs("flobj_total", S_IRUGO, root, &zcache_flobj_total);
	zdfs("flobj_found", S_IRUGO, root, &zcache_flobj_found);
	zdfs("failed_eph_puts", S_IRUGO, root, &zcache_failed_eph_puts);
	zdfs("failed_pers_puts", S_IRUGO, root, &zcache_failed_pers_puts);
	zdfs("failed_get_free_pages", S_IRUGO, root,
				&zcache_failed_getfreepages);
	zdfs("failed_alloc", S_IRUGO, root, &zcache_failed_alloc);
	zdfs("put_to_flush", S_IRUGO, root, &zcache_put_to_flush);
	zdfs("compress_poor", S_IRUGO, root, &zcache_compress_poor);
	zdfs("mean_compress_poor", S_IRUGO, root, &zcache_mean_compress_poor);
	zdfs("eph_ate_tail", S_IRUGO, root, &zcache_eph_ate_tail);
	zdfs("eph_ate_tail_failed", S_IRUGO, root, &zcache_eph_ate_tail_failed);
	zdfs("pers_ate_eph", S_IRUGO, root, &zcache_pers_ate_eph);
	zdfs("pers_ate_eph_failed", S_IRUGO, root, &zcache_pers_ate_eph_failed);
	zdfs("evicted_eph_zpages", S_IRUGO, root, &zcache_evicted_eph_zpages);
	zdfs("evicted_eph_pageframes", S_IRUGO, root,
				&zcache_evicted_eph_pageframes);
	zdfs("eph_pageframes", S_IRUGO, root, &zcache_eph_pageframes);
	zdfs("eph_pageframes_max", S_IRUGO, root, &zcache_eph_pageframes_max);
	zdfs("pers_pageframes", S_IRUGO, root, &zcache_pers_pageframes);
	zdfs("pers_pageframes_max", S_IRUGO, root, &zcache_pers_pageframes_max);
	zdfs("eph_zpages", S_IRUGO, root, &zcache_eph_zpages);
	zdfs("eph_zpages_max", S_IRUGO, root, &zcache_eph_zpages_max);
	zdfs("pers_zpages", S_IRUGO, root, &zcache_pers_zpages);
	zdfs("pers_zpages_max", S_IRUGO, root, &zcache_pers_zpages_max);
	zdfs("last_active_file_pageframes", S_IRUGO, root,
				&zcache_last_active_file_pageframes);
	zdfs("last_inactive_file_pageframes", S_IRUGO, root,
				&zcache_last_inactive_file_pageframes);
	zdfs("last_active_anon_pageframes", S_IRUGO, root,
				&zcache_last_active_anon_pageframes);
	zdfs("last_inactive_anon_pageframes", S_IRUGO, root,
				&zcache_last_inactive_anon_pageframes);
	zdfs("eph_nonactive_puts_ignored", S_IRUGO, root,
				&zcache_eph_nonactive_puts_ignored);
	zdfs("pers_nonactive_puts_ignored", S_IRUGO, root,
				&zcache_pers_nonactive_puts_ignored);
	zdfs64("eph_zbytes", S_IRUGO, root, &zcache_eph_zbytes);
	zdfs64("eph_zbytes_max", S_IRUGO, root, &zcache_eph_zbytes_max);
	zdfs64("pers_zbytes", S_IRUGO, root, &zcache_pers_zbytes);
	zdfs64("pers_zbytes_max", S_IRUGO, root, &zcache_pers_zbytes_max);
	zdfs("outstanding_writeback_pages", S_IRUGO, root,
				&zcache_outstanding_writeback_pages);
	zdfs("writtenback_pages", S_IRUGO, root, &zcache_writtenback_pages);
	return 0;
}
#undef	zdebugfs
#undef	zdfs64
#endif

#define ZCACHE_DEBUG
#ifdef ZCACHE_DEBUG
/* developers can call this in case of ooms, e.g. to find memory leaks */
void zcache_dump(void)
{
	pr_info("zcache: obj_count=%zd\n", zcache_obj_count);
	pr_info("zcache: obj_count_max=%zd\n", zcache_obj_count_max);
	pr_info("zcache: objnode_count=%zd\n", zcache_objnode_count);
	pr_info("zcache: objnode_count_max=%zd\n", zcache_objnode_count_max);
	pr_info("zcache: flush_total=%zd\n", zcache_flush_total);
	pr_info("zcache: flush_found=%zd\n", zcache_flush_found);
	pr_info("zcache: flobj_total=%zd\n", zcache_flobj_total);
	pr_info("zcache: flobj_found=%zd\n", zcache_flobj_found);
	pr_info("zcache: failed_eph_puts=%zd\n", zcache_failed_eph_puts);
	pr_info("zcache: failed_pers_puts=%zd\n", zcache_failed_pers_puts);
	pr_info("zcache: failed_get_free_pages=%zd\n",
				zcache_failed_getfreepages);
	pr_info("zcache: failed_alloc=%zd\n", zcache_failed_alloc);
	pr_info("zcache: put_to_flush=%zd\n", zcache_put_to_flush);
	pr_info("zcache: compress_poor=%zd\n", zcache_compress_poor);
	pr_info("zcache: mean_compress_poor=%zd\n",
				zcache_mean_compress_poor);
	pr_info("zcache: eph_ate_tail=%zd\n", zcache_eph_ate_tail);
	pr_info("zcache: eph_ate_tail_failed=%zd\n",
				zcache_eph_ate_tail_failed);
	pr_info("zcache: pers_ate_eph=%zd\n", zcache_pers_ate_eph);
	pr_info("zcache: pers_ate_eph_failed=%zd\n",
				zcache_pers_ate_eph_failed);
	pr_info("zcache: evicted_eph_zpages=%zd\n", zcache_evicted_eph_zpages);
	pr_info("zcache: evicted_eph_pageframes=%zd\n",
				zcache_evicted_eph_pageframes);
	pr_info("zcache: eph_pageframes=%zd\n", zcache_eph_pageframes);
	pr_info("zcache: eph_pageframes_max=%zd\n", zcache_eph_pageframes_max);
	pr_info("zcache: pers_pageframes=%zd\n", zcache_pers_pageframes);
	pr_info("zcache: pers_pageframes_max=%zd\n",
				zcache_pers_pageframes_max);
	pr_info("zcache: eph_zpages=%zd\n", zcache_eph_zpages);
	pr_info("zcache: eph_zpages_max=%zd\n", zcache_eph_zpages_max);
	pr_info("zcache: pers_zpages=%zd\n", zcache_pers_zpages);
	pr_info("zcache: pers_zpages_max=%zd\n", zcache_pers_zpages_max);
	pr_info("zcache: last_active_file_pageframes=%zd\n",
				zcache_last_active_file_pageframes);
	pr_info("zcache: last_inactive_file_pageframes=%zd\n",
				zcache_last_inactive_file_pageframes);
	pr_info("zcache: last_active_anon_pageframes=%zd\n",
				zcache_last_active_anon_pageframes);
	pr_info("zcache: last_inactive_anon_pageframes=%zd\n",
				zcache_last_inactive_anon_pageframes);
	pr_info("zcache: eph_nonactive_puts_ignored=%zd\n",
				zcache_eph_nonactive_puts_ignored);
	pr_info("zcache: pers_nonactive_puts_ignored=%zd\n",
				zcache_pers_nonactive_puts_ignored);
	pr_info("zcache: eph_zbytes=%llu\n",
				zcache_eph_zbytes);
	pr_info("zcache: eph_zbytes_max=%llu\n",
				zcache_eph_zbytes_max);
	pr_info("zcache: pers_zbytes=%llu\n",
				zcache_pers_zbytes);
	pr_info("zcache: pers_zbytes_max=%llu\n",
				zcache_pers_zbytes_max);
	pr_info("zcache: outstanding_writeback_pages=%zd\n",
				zcache_outstanding_writeback_pages);
	pr_info("zcache: writtenback_pages=%zd\n", zcache_writtenback_pages);
}
#endif

/*
 * zcache core code starts here
 */

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

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

static struct zcache_client *zcache_get_client_by_id(uint16_t cli_id)
{
	struct zcache_client *cli = &zcache_host;

	if (cli_id != LOCAL_CLIENT) {
		if (cli_id >= MAX_CLIENTS)
			goto out;
		cli = &zcache_clients[cli_id];
	}
out:
	return cli;
}

/*
 * 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.
 */
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;

	cli = zcache_get_client_by_id(cli_id);
	if (cli == NULL)
		goto out;
	if (!is_local_client(cli))
		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;
}

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

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

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

	cli = zcache_get_client_by_id(cli_id);
	if (cli == NULL)
		goto out;
	if (cli->allocated)
		goto out;
	cli->allocated = 1;
	ret = 0;
out:
	return ret;
}

/*
 * zcache implementation for tmem host ops
 */

static struct tmem_objnode *zcache_objnode_alloc(struct tmem_pool *pool)
{
	struct tmem_objnode *objnode = NULL;
	struct zcache_preload *kp;
	int i;

	kp = &__get_cpu_var(zcache_preloads);
	for (i = 0; i < ARRAY_SIZE(kp->objnodes); i++) {
		objnode = kp->objnodes[i];
		if (objnode != NULL) {
			kp->objnodes[i] = NULL;
			break;
		}
	}
	BUG_ON(objnode == NULL);
	inc_zcache_objnode_count();
	return objnode;
}

static void zcache_objnode_free(struct tmem_objnode *objnode,
					struct tmem_pool *pool)
{
	dec_zcache_objnode_count();
	kmem_cache_free(zcache_objnode_cache, objnode);
}

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

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

static void zcache_obj_free(struct tmem_obj *obj, struct tmem_pool *pool)
{
	dec_zcache_obj_count();
	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,
};

static struct page *zcache_alloc_page(void)
{
	struct page *page = alloc_page(ZCACHE_GFP_MASK);

	if (page != NULL)
		inc_zcache_pageframes_alloced();
	return page;
}

static void zcache_free_page(struct page *page)
{
	long curr_pageframes;
	static long max_pageframes, min_pageframes;

	if (page == NULL)
		BUG();
	__free_page(page);
	inc_zcache_pageframes_freed();
	curr_pageframes = zcache_pageframes_alloced -
			atomic_read(&zcache_pageframes_freed_atomic) -
			atomic_read(&zcache_eph_pageframes_atomic) -
			atomic_read(&zcache_pers_pageframes_atomic);
	if (curr_pageframes > max_pageframes)
		max_pageframes = curr_pageframes;
	if (curr_pageframes < min_pageframes)
		min_pageframes = curr_pageframes;
#ifdef ZCACHE_DEBUG
	if (curr_pageframes > 2L || curr_pageframes < -2L) {
		/* pr_info here */
	}
#endif
}

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

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

static struct page *zcache_evict_eph_pageframe(void);

static void *zcache_pampd_eph_create(char *data, size_t size, bool raw,
					struct tmem_handle *th)
{
	void *pampd = NULL, *cdata = data;
	unsigned clen = size;
	struct page *page = (struct page *)(data), *newpage;

	if (!raw) {
		zcache_compress(page, &cdata, &clen);
		if (clen > zbud_max_buddy_size()) {
			zcache_compress_poor++;
			goto out;
		}
	} else {
		BUG_ON(clen > zbud_max_buddy_size());
	}

	/* look for space via an existing match first */
	pampd = (void *)zbud_match_prep(th, true, cdata, clen);
	if (pampd != NULL)
		goto got_pampd;

	/* no match, now we need to find (or free up) a full page */
	newpage = zcache_alloc_page();
	if (newpage != NULL)
		goto create_in_new_page;

	zcache_failed_getfreepages++;
	/* can't allocate a page, evict an ephemeral page via LRU */
	newpage = zcache_evict_eph_pageframe();
	if (newpage == NULL) {
		zcache_eph_ate_tail_failed++;
		goto out;
	}
	zcache_eph_ate_tail++;

create_in_new_page:
	pampd = (void *)zbud_create_prep(th, true, cdata, clen, newpage);
	BUG_ON(pampd == NULL);
	inc_zcache_eph_pageframes();

got_pampd:
	inc_zcache_eph_zbytes(clen);
	inc_zcache_eph_zpages();
	if (ramster_enabled && raw)
		ramster_count_foreign_pages(true, 1);
out:
	return pampd;
}

static void *zcache_pampd_pers_create(char *data, size_t size, bool raw,
					struct tmem_handle *th)
{
	void *pampd = NULL, *cdata = data;
	unsigned clen = size;
	struct page *page = (struct page *)(data), *newpage;
	unsigned long zbud_mean_zsize;
	unsigned long curr_pers_zpages, total_zsize;

	if (data == NULL) {
		BUG_ON(!ramster_enabled);
		goto create_pampd;
	}
	curr_pers_zpages = zcache_pers_zpages;
/* FIXME CONFIG_RAMSTER... subtract atomic remote_pers_pages here? */
	if (!raw)
		zcache_compress(page, &cdata, &clen);
	/* reject if compression is too poor */
	if (clen > zbud_max_zsize) {
		zcache_compress_poor++;
		goto out;
	}
	/* reject if mean compression is too poor */
	if ((clen > zbud_max_mean_zsize) && (curr_pers_zpages > 0)) {
		total_zsize = zcache_pers_zbytes;
		if ((long)total_zsize < 0)
			total_zsize = 0;
		zbud_mean_zsize = div_u64(total_zsize,
					curr_pers_zpages);
		if (zbud_mean_zsize > zbud_max_mean_zsize) {
			zcache_mean_compress_poor++;
			goto out;
		}
	}

create_pampd:
	/* look for space via an existing match first */
	pampd = (void *)zbud_match_prep(th, false, cdata, clen);
	if (pampd != NULL)
		goto got_pampd;

	/* no match, now we need to find (or free up) a full page */
	newpage = zcache_alloc_page();
	if (newpage != NULL)
		goto create_in_new_page;
	/*
	 * FIXME do the following only if eph is oversized?
	 * if (zcache_eph_pageframes >
	 * (global_page_state(NR_LRU_BASE + LRU_ACTIVE_FILE) +
	 * global_page_state(NR_LRU_BASE + LRU_INACTIVE_FILE)))
	 */
	zcache_failed_getfreepages++;
	/* can't allocate a page, evict an ephemeral page via LRU */
	newpage = zcache_evict_eph_pageframe();
	if (newpage == NULL) {
		zcache_pers_ate_eph_failed++;
		goto out;
	}
	zcache_pers_ate_eph++;

create_in_new_page:
	pampd = (void *)zbud_create_prep(th, false, cdata, clen, newpage);
	BUG_ON(pampd == NULL);
	inc_zcache_pers_pageframes();

got_pampd:
	inc_zcache_pers_zpages();
	inc_zcache_pers_zbytes(clen);
	if (ramster_enabled && raw)
		ramster_count_foreign_pages(false, 1);
out:
	return pampd;
}

/*
 * This is called directly from zcache_put_page to pre-allocate space
 * to store a zpage.
 */
void *zcache_pampd_create(char *data, unsigned int size, bool raw,
					int eph, struct tmem_handle *th)
{
	void *pampd = NULL;
	struct zcache_preload *kp;
	struct tmem_objnode *objnode;
	struct tmem_obj *obj;
	int i;

	BUG_ON(!irqs_disabled());
	/* pre-allocate per-cpu metadata */
	BUG_ON(zcache_objnode_cache == NULL);
	BUG_ON(zcache_obj_cache == NULL);
	kp = &__get_cpu_var(zcache_preloads);
	for (i = 0; i < ARRAY_SIZE(kp->objnodes); i++) {
		objnode = kp->objnodes[i];
		if (objnode == NULL) {
			objnode = kmem_cache_alloc(zcache_objnode_cache,
							ZCACHE_GFP_MASK);
			if (unlikely(objnode == NULL)) {
				zcache_failed_alloc++;
				goto out;
			}
			kp->objnodes[i] = objnode;
		}
	}
	if (kp->obj == NULL) {
		obj = kmem_cache_alloc(zcache_obj_cache, ZCACHE_GFP_MASK);
		kp->obj = obj;
	}
	if (unlikely(kp->obj == NULL)) {
		zcache_failed_alloc++;
		goto out;
	}
	/*
	 * ok, have all the metadata pre-allocated, now do the data
	 * but since how we allocate the data is dependent on ephemeral
	 * or persistent, we split the call here to different sub-functions
	 */
	if (eph)
		pampd = zcache_pampd_eph_create(data, size, raw, th);
	else
		pampd = zcache_pampd_pers_create(data, size, raw, th);
out:
	return pampd;
}

/*
 * This is a pamops called via tmem_put and is necessary to "finish"
 * a pampd creation.
 */
void zcache_pampd_create_finish(void *pampd, bool eph)
{
	zbud_create_finish((struct zbudref *)pampd, eph);
}

/*
 * This is passed as a function parameter to zbud_decompress so that
 * zbud need not be familiar with the details of crypto. It assumes that
 * the bytes from_va and to_va through from_va+size-1 and to_va+size-1 are
 * kmapped.  It must be successful, else there is a logic bug somewhere.
 */
static void zcache_decompress(char *from_va, unsigned int size, char *to_va)
{
	int ret;
	unsigned int outlen = PAGE_SIZE;

	ret = zcache_comp_op(ZCACHE_COMPOP_DECOMPRESS, from_va, size,
				to_va, &outlen);
	BUG_ON(ret);
	BUG_ON(outlen != PAGE_SIZE);
}

/*
 * Decompress from the kernel va to a pageframe
 */
void zcache_decompress_to_page(char *from_va, unsigned int size,
					struct page *to_page)
{
	char *to_va = kmap_atomic(to_page);
	zcache_decompress(from_va, size, to_va);
	kunmap_atomic(to_va);
}

/*
 * 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 *sizep, bool raw,
					void *pampd, struct tmem_pool *pool,
					struct tmem_oid *oid, uint32_t index)
{
	int ret;
	bool eph = !is_persistent(pool);

	BUG_ON(preemptible());
	BUG_ON(eph);	/* fix later if shared pools get implemented */
	BUG_ON(pampd_is_remote(pampd));
	if (raw)
		ret = zbud_copy_from_zbud(data, (struct zbudref *)pampd,
						sizep, eph);
	else {
		ret = zbud_decompress((struct page *)(data),
					(struct zbudref *)pampd, false,
					zcache_decompress);
		*sizep = PAGE_SIZE;
	}
	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 *sizep, bool raw,
					void *pampd, struct tmem_pool *pool,
					struct tmem_oid *oid, uint32_t index)
{
	int ret;
	bool eph = !is_persistent(pool);
	struct page *page = NULL;
	unsigned int zsize, zpages;

	BUG_ON(preemptible());
	BUG_ON(pampd_is_remote(pampd));
	if (raw)
		ret = zbud_copy_from_zbud(data, (struct zbudref *)pampd,
						sizep, eph);
	else {
		ret = zbud_decompress((struct page *)(data),
					(struct zbudref *)pampd, eph,
					zcache_decompress);
		*sizep = PAGE_SIZE;
	}
	page = zbud_free_and_delist((struct zbudref *)pampd, eph,
					&zsize, &zpages);
	if (eph) {
		if (page)
			dec_zcache_eph_pageframes();
		dec_zcache_eph_zpages(zpages);
		dec_zcache_eph_zbytes(zsize);
	} else {
		if (page)
			dec_zcache_pers_pageframes();
		dec_zcache_pers_zpages(zpages);
		dec_zcache_pers_zbytes(zsize);
	}
	if (!is_local_client(pool->client))
		ramster_count_foreign_pages(eph, -1);
	if (page)
		zcache_free_page(page);
	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, bool acct)
{
	struct page *page = NULL;
	unsigned int zsize, zpages;

	BUG_ON(preemptible());
	if (pampd_is_remote(pampd)) {
		BUG_ON(!ramster_enabled);
		pampd = ramster_pampd_free(pampd, pool, oid, index, acct);
		if (pampd == NULL)
			return;
	}
	if (is_ephemeral(pool)) {
		page = zbud_free_and_delist((struct zbudref *)pampd,
						true, &zsize, &zpages);
		if (page)
			dec_zcache_eph_pageframes();
		dec_zcache_eph_zpages(zpages);
		dec_zcache_eph_zbytes(zsize);
		/* FIXME CONFIG_RAMSTER... check acct parameter? */
	} else {
		page = zbud_free_and_delist((struct zbudref *)pampd,
						false, &zsize, &zpages);
		if (page)
			dec_zcache_pers_pageframes();
		dec_zcache_pers_zpages(zpages);
		dec_zcache_pers_zbytes(zsize);
	}
	if (!is_local_client(pool->client))
		ramster_count_foreign_pages(is_ephemeral(pool), -1);
	if (page)
		zcache_free_page(page);
}

static struct tmem_pamops zcache_pamops = {
	.create_finish = zcache_pampd_create_finish,
	.get_data = zcache_pampd_get_data,
	.get_data_and_free = zcache_pampd_get_data_and_free,
	.free = zcache_pampd_free,
};

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

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

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

	BUG_ON(!irqs_disabled());
	/* no buffer or no compressor so can't compress */
	BUG_ON(dmem == NULL);
	*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);
}

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, i, 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("%s: can't allocate compressor xform\n",
				namestr);
			return ret;
		}
		per_cpu(zcache_dstmem, cpu) = (void *)__get_free_pages(
			GFP_KERNEL | __GFP_REPEAT, ZCACHE_DSTMEM_ORDER);
		if (ramster_enabled)
			ramster_cpu_up(cpu);
		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);
		for (i = 0; i < ARRAY_SIZE(kp->objnodes); i++) {
			if (kp->objnodes[i])
				kmem_cache_free(zcache_objnode_cache,
						kp->objnodes[i]);
		}
		if (kp->obj) {
			kmem_cache_free(zcache_obj_cache, kp->obj);
			kp->obj = NULL;
		}
		if (ramster_enabled)
			ramster_cpu_down(cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

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

/*
 * The following code interacts with the zbud eviction and zbud
 * zombify code to access LRU pages
 */

static struct page *zcache_evict_eph_pageframe(void)
{
	struct page *page;
	unsigned int zsize = 0, zpages = 0;

	page = zbud_evict_pageframe_lru(&zsize, &zpages);
	if (page == NULL)
		goto out;
	dec_zcache_eph_zbytes(zsize);
	dec_zcache_eph_zpages(zpages);
	zcache_evicted_eph_zpages += zpages;
	dec_zcache_eph_pageframes();
	zcache_evicted_eph_pageframes++;
out:
	return page;
}

#ifdef CONFIG_ZCACHE_WRITEBACK

static atomic_t zcache_outstanding_writeback_pages_atomic = ATOMIC_INIT(0);

static inline void inc_zcache_outstanding_writeback_pages(void)
{
	zcache_outstanding_writeback_pages =
	    atomic_inc_return(&zcache_outstanding_writeback_pages_atomic);
}
static inline void dec_zcache_outstanding_writeback_pages(void)
{
	zcache_outstanding_writeback_pages =
	  atomic_dec_return(&zcache_outstanding_writeback_pages_atomic);
};
static void unswiz(struct tmem_oid oid, u32 index,
				unsigned *type, pgoff_t *offset);

/*
 *  Choose an LRU persistent pageframe and attempt to write it back to
 *  the backing swap disk by calling frontswap_writeback on both zpages.
 *
 *  This is work-in-progress.
 */

static void zcache_end_swap_write(struct bio *bio, int err)
{
	end_swap_bio_write(bio, err);
	dec_zcache_outstanding_writeback_pages();
	zcache_writtenback_pages++;
}

/*
 * zcache_get_swap_cache_page
 *
 * This is an adaption of read_swap_cache_async()
 *
 * If success, page is returned in retpage
 * Returns 0 if page was already in the swap cache, page is not locked
 * Returns 1 if the new page needs to be populated, page is locked
 */
static int zcache_get_swap_cache_page(int type, pgoff_t offset,
				struct page *new_page)
{
	struct page *found_page;
	swp_entry_t entry = swp_entry(type, offset);
	int err;

	BUG_ON(new_page == NULL);
	do {
		/*
		 * First check the swap cache.  Since this is normally
		 * called after lookup_swap_cache() failed, re-calling
		 * that would confuse statistics.
		 */
		found_page = find_get_page(&swapper_space, entry.val);
		if (found_page)
			return 0;

		/*
		 * call radix_tree_preload() while we can wait.
		 */
		err = radix_tree_preload(GFP_KERNEL);
		if (err)
			break;

		/*
		 * Swap entry may have been freed since our caller observed it.
		 */
		err = swapcache_prepare(entry);
		if (err == -EEXIST) { /* seems racy */
			radix_tree_preload_end();
			continue;
		}
		if (err) { /* swp entry is obsolete ? */
			radix_tree_preload_end();
			break;
		}

		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
		__set_page_locked(new_page);
		SetPageSwapBacked(new_page);
		err = __add_to_swap_cache(new_page, entry);
		if (likely(!err)) {
			radix_tree_preload_end();
			lru_cache_add_anon(new_page);
			return 1;
		}
		radix_tree_preload_end();
		ClearPageSwapBacked(new_page);
		__clear_page_locked(new_page);
		/*
		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
		 * clear SWAP_HAS_CACHE flag.
		 */
		swapcache_free(entry, NULL);
		/* FIXME: is it possible to get here without err==-ENOMEM?
		 * If not, we can dispense with the do loop, use goto retry */
	} while (err != -ENOMEM);

	return -ENOMEM;
}

/*
 * Given a frontswap zpage in zcache (identified by type/offset) and
 * an empty page, put the page into the swap cache, use frontswap
 * to get the page from zcache into the empty page, then give it
 * to the swap subsystem to send to disk (carefully avoiding the
 * possibility that frontswap might snatch it back).
 * Returns < 0 if error, 0 if successful, and 1 if successful but
 * the newpage passed in not needed and should be freed.
 */
static int zcache_frontswap_writeback_zpage(int type, pgoff_t offset,
					struct page *newpage)
{
	struct page *page = newpage;
	int ret;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_NONE,
	};

	ret = zcache_get_swap_cache_page(type, offset, page);
	if (ret < 0)
		return ret;
	else if (ret == 0) {
		/* more uptodate page is already in swapcache */
		__frontswap_invalidate_page(type, offset);
		return 1;
	}

	BUG_ON(!frontswap_has_exclusive_gets); /* load must also invalidate */
	/* FIXME: how is it possible to get here when page is unlocked? */
	__frontswap_load(page);
	SetPageUptodate(page);  /* above does SetPageDirty, is that enough? */

	/* start writeback */
	SetPageReclaim(page);
	/*
	 * Return value is ignored here because it doesn't change anything
	 * for us.  Page is returned unlocked.
	 */
	(void)__swap_writepage(page, &wbc, zcache_end_swap_write);
	page_cache_release(page);
	inc_zcache_outstanding_writeback_pages();

	return 0;
}

/*
 * The following is still a magic number... we want to allow forward progress
 * for writeback because it clears out needed RAM when under pressure, but
 * we don't want to allow writeback to absorb and queue too many GFP_KERNEL
 * pages if the swap device is very slow.
 */
#define ZCACHE_MAX_OUTSTANDING_WRITEBACK_PAGES 6400

/*
 * Try to allocate two free pages, first using a non-aggressive alloc,
 * then by evicting zcache ephemeral (clean pagecache) pages, and last
 * by aggressive GFP_KERNEL alloc.  We allow zbud to choose a pageframe
 * consisting of 1-2 zbuds/zpages, then call the writeback_zpage helper
 * function above for each.
 */
static int zcache_frontswap_writeback(void)
{
	struct tmem_handle th[2];
	int ret = 0;
	int nzbuds, writeback_ret;
	unsigned type;
	struct page *znewpage1 = NULL, *znewpage2 = NULL;
	struct page *evictpage1 = NULL, *evictpage2 = NULL;
	struct page *newpage1 = NULL, *newpage2 = NULL;
	struct page *page1 = NULL, *page2 = NULL;
	pgoff_t offset;

	znewpage1 = alloc_page(ZCACHE_GFP_MASK);
	znewpage2 = alloc_page(ZCACHE_GFP_MASK);
	if (znewpage1 == NULL)
		evictpage1 = zcache_evict_eph_pageframe();
	if (znewpage2 == NULL)
		evictpage2 = zcache_evict_eph_pageframe();

	if ((evictpage1 == NULL || evictpage2 == NULL) &&
	    atomic_read(&zcache_outstanding_writeback_pages_atomic) >
				ZCACHE_MAX_OUTSTANDING_WRITEBACK_PAGES) {
		goto free_and_out;
	}
	if (znewpage1 == NULL && evictpage1 == NULL)
		newpage1 = alloc_page(GFP_KERNEL);
	if (znewpage2 == NULL && evictpage2 == NULL)
		newpage2 = alloc_page(GFP_KERNEL);
	if (newpage1 == NULL || newpage2 == NULL)
			goto free_and_out;

	/* ok, we have two pageframes pre-allocated, get a pair of zbuds */
	nzbuds = zbud_make_zombie_lru(&th[0], NULL, NULL, false);
	if (nzbuds == 0) {
		ret = -ENOENT;
		goto free_and_out;
	}

	/* process the first zbud */
	unswiz(th[0].oid, th[0].index, &type, &offset);
	page1 = (znewpage1 != NULL) ? znewpage1 :
			((newpage1 != NULL) ? newpage1 : evictpage1);
	writeback_ret = zcache_frontswap_writeback_zpage(type, offset, page1);
	if (writeback_ret < 0) {
		ret = -ENOMEM;
		goto free_and_out;
	}
	if (evictpage1 != NULL)
		zcache_pageframes_freed =
			atomic_inc_return(&zcache_pageframes_freed_atomic);
	if (writeback_ret == 0) {
		/* zcache_get_swap_cache_page will free, don't double free */
		znewpage1 = NULL;
		newpage1 = NULL;
		evictpage1 = NULL;
	}
	if (nzbuds < 2)
		goto free_and_out;

	/* if there is a second zbud, process it */
	unswiz(th[1].oid, th[1].index, &type, &offset);
	page2 = (znewpage2 != NULL) ? znewpage2 :
			((newpage2 != NULL) ? newpage2 : evictpage2);
	writeback_ret = zcache_frontswap_writeback_zpage(type, offset, page2);
	if (writeback_ret < 0) {
		ret = -ENOMEM;
		goto free_and_out;
	}
	if (evictpage2 != NULL)
		zcache_pageframes_freed =
			atomic_inc_return(&zcache_pageframes_freed_atomic);
	if (writeback_ret == 0) {
		znewpage2 = NULL;
		newpage2 = NULL;
		evictpage2 = NULL;
	}

free_and_out:
	if (znewpage1 != NULL)
		page_cache_release(znewpage1);
	if (znewpage2 != NULL)
		page_cache_release(znewpage2);
	if (newpage1 != NULL)
		page_cache_release(newpage1);
	if (newpage2 != NULL)
		page_cache_release(newpage2);
	if (evictpage1 != NULL)
		zcache_free_page(evictpage1);
	if (evictpage2 != NULL)
		zcache_free_page(evictpage2);
	return ret;
}
#endif /* CONFIG_ZCACHE_WRITEBACK */

/*
 * 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;

/*
 * This zcache shrinker interface reduces the number of ephemeral pageframes
 * used by zcache to approximately the same as the total number of LRU_FILE
 * pageframes in use, and now also reduces the number of persistent pageframes
 * used by zcache to approximately the same as the total number of LRU_ANON
 * pageframes in use.  FIXME POLICY: Probably the writeback should only occur
 * if the eviction doesn't free enough pages.
 */
static int shrink_zcache_memory(struct shrinker *shrink,
				struct shrink_control *sc)
{
	static bool in_progress;
	int ret = -1;
	int nr = sc->nr_to_scan;
	int nr_evict = 0;
	int nr_writeback = 0;
	struct page *page;
	int  file_pageframes_inuse, anon_pageframes_inuse;

	if (nr <= 0)
		goto skip_evict;

	/* don't allow more than one eviction thread at a time */
	if (in_progress)
		goto skip_evict;

	in_progress = true;

	/* we are going to ignore nr, and target a different value */
	zcache_last_active_file_pageframes =
		global_page_state(NR_LRU_BASE + LRU_ACTIVE_FILE);
	zcache_last_inactive_file_pageframes =
		global_page_state(NR_LRU_BASE + LRU_INACTIVE_FILE);
	file_pageframes_inuse = zcache_last_active_file_pageframes +
				zcache_last_inactive_file_pageframes;
	if (zcache_eph_pageframes > file_pageframes_inuse)
		nr_evict = zcache_eph_pageframes - file_pageframes_inuse;
	else
		nr_evict = 0;
	while (nr_evict-- > 0) {
		page = zcache_evict_eph_pageframe();
		if (page == NULL)
			break;
		zcache_free_page(page);
	}

	zcache_last_active_anon_pageframes =
		global_page_state(NR_LRU_BASE + LRU_ACTIVE_ANON);
	zcache_last_inactive_anon_pageframes =
		global_page_state(NR_LRU_BASE + LRU_INACTIVE_ANON);
	anon_pageframes_inuse = zcache_last_active_anon_pageframes +
				zcache_last_inactive_anon_pageframes;
	if (zcache_pers_pageframes > anon_pageframes_inuse)
		nr_writeback = zcache_pers_pageframes - anon_pageframes_inuse;
	else
		nr_writeback = 0;
	while (nr_writeback-- > 0) {
#ifdef CONFIG_ZCACHE_WRITEBACK
		int writeback_ret;
		writeback_ret = zcache_frontswap_writeback();
		if (writeback_ret == -ENOMEM)
#endif
			break;
	}
	in_progress = false;

skip_evict:
	/* resample: has changed, but maybe not all the way yet */
	zcache_last_active_file_pageframes =
		global_page_state(NR_LRU_BASE + LRU_ACTIVE_FILE);
	zcache_last_inactive_file_pageframes =
		global_page_state(NR_LRU_BASE + LRU_INACTIVE_FILE);
	ret = zcache_eph_pageframes - zcache_last_active_file_pageframes +
		zcache_last_inactive_file_pageframes;
	if (ret < 0)
		ret = 0;
	return ret;
}

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

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

/* FIXME rename these core routines to zcache_tmemput etc? */
int zcache_put_page(int cli_id, int pool_id, struct tmem_oid *oidp,
				uint32_t index, void *page,
				unsigned int size, bool raw, int ephemeral)
{
	struct tmem_pool *pool;
	struct tmem_handle th;
	int ret = -1;
	void *pampd = NULL;

	BUG_ON(!irqs_disabled());
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	if (unlikely(pool == NULL))
		goto out;
	if (!zcache_freeze) {
		ret = 0;
		th.client_id = cli_id;
		th.pool_id = pool_id;
		th.oid = *oidp;
		th.index = index;
		pampd = zcache_pampd_create((char *)page, size, raw,
				ephemeral, &th);
		if (pampd == NULL) {
			ret = -ENOMEM;
			if (ephemeral)
				zcache_failed_eph_puts++;
			else
				zcache_failed_pers_puts++;
		} else {
			if (ramster_enabled)
				ramster_do_preload_flnode(pool);
			ret = tmem_put(pool, oidp, index, 0, pampd);
			if (ret < 0)
				BUG();
		}
		zcache_put_pool(pool);
	} else {
		zcache_put_to_flush++;
		if (ramster_enabled)
			ramster_do_preload_flnode(pool);
		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;
}

int zcache_get_page(int cli_id, int pool_id, struct tmem_oid *oidp,
				uint32_t index, void *page,
				size_t *sizep, bool raw, int get_and_free)
{
	struct tmem_pool *pool;
	int ret = -1;
	bool eph;

	if (!raw) {
		BUG_ON(irqs_disabled());
		BUG_ON(in_softirq());
	}
	pool = zcache_get_pool_by_id(cli_id, pool_id);
	eph = is_ephemeral(pool);
	if (likely(pool != NULL)) {
		if (atomic_read(&pool->obj_count) > 0)
			ret = tmem_get(pool, oidp, index, (char *)(page),
					sizep, raw, get_and_free);
		zcache_put_pool(pool);
	}
	WARN_ONCE((!is_ephemeral(pool) && (ret != 0)),
			"zcache_get fails on persistent pool, "
			"bad things are very likely to happen soon\n");
#ifdef RAMSTER_TESTING
	if (ret != 0 && ret != -1 && !(ret == -EINVAL && is_ephemeral(pool)))
		pr_err("TESTING zcache_get tmem_get returns ret=%d\n", ret);
#endif
	return ret;
}

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 (ramster_enabled)
		ramster_do_preload_flnode(pool);
	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;
}

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 (ramster_enabled)
		ramster_do_preload_flnode(pool);
	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_client_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);
	if (cli_id == LOCAL_CLIENT)
		pr_info("%s: destroyed local pool id=%d\n", namestr, pool_id);
	else
		pr_info("%s: destroyed pool id=%d, client=%d\n",
				namestr, pool_id, cli_id);
out:
	return ret;
}

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)
		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("%s: pool creation failed: max exceeded\n", namestr);
		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;
	if (cli_id == LOCAL_CLIENT)
		pr_info("%s: created %s local tmem pool, id=%d\n", namestr,
			flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral",
			poolid);
	else
		pr_info("%s: created %s tmem pool, id=%d, client=%d\n", namestr,
			flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral",
			poolid, cli_id);
out:
	if (cli != NULL)
		atomic_dec(&cli->refcount);
	return poolid;
}

static int zcache_local_new_pool(uint32_t flags)
{
	return zcache_new_pool(LOCAL_CLIENT, flags);
}

int zcache_autocreate_pool(unsigned int cli_id, unsigned int pool_id, bool eph)
{
	struct tmem_pool *pool;
	struct zcache_client *cli;
	uint32_t flags = eph ? 0 : TMEM_POOL_PERSIST;
	int ret = -1;

	BUG_ON(!ramster_enabled);
	if (cli_id == LOCAL_CLIENT)
		goto out;
	if (pool_id >= MAX_POOLS_PER_CLIENT)
		goto out;
	if (cli_id >= MAX_CLIENTS)
		goto out;

	cli = &zcache_clients[cli_id];
	if ((eph && disable_cleancache) || (!eph && disable_frontswap)) {
		pr_err("zcache_autocreate_pool: pool type disabled\n");
		goto out;
	}
	if (!cli->allocated) {
		if (zcache_new_client(cli_id)) {
			pr_err("zcache_autocreate_pool: can't create client\n");
			goto out;
		}
		cli = &zcache_clients[cli_id];
	}
	atomic_inc(&cli->refcount);
	pool = cli->tmem_pools[pool_id];
	if (pool != NULL) {
		if (pool->persistent && eph) {
			pr_err("zcache_autocreate_pool: type mismatch\n");
			goto out;
		}
		ret = 0;
		goto out;
	}
	pool = kmalloc(sizeof(struct tmem_pool), GFP_KERNEL);
	if (pool == NULL)
		goto out;

	atomic_set(&pool->refcount, 0);
	pool->client = cli;
	pool->pool_id = pool_id;
	tmem_new_pool(pool, flags);
	cli->tmem_pools[pool_id] = pool;
	pr_info("%s: AUTOcreated %s tmem poolid=%d, for remote client=%d\n",
		namestr, flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral",
		pool_id, cli_id);
	ret = 0;
out:
	if (cli != NULL)
		atomic_dec(&cli->refcount);
	return ret;
}

/**********
 * 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.
 */

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 (!disable_cleancache_ignore_nonactive && !PageWasActive(page)) {
		zcache_eph_nonactive_puts_ignored++;
		return;
	}
	if (likely(ind == index))
		(void)zcache_put_page(LOCAL_CLIENT, pool_id, &oid, index,
					page, PAGE_SIZE, false, 1);
}

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;
	size_t size;
	int ret = -1;

	if (likely(ind == index)) {
		ret = zcache_get_page(LOCAL_CLIENT, pool_id, &oid, index,
					page, &size, false, 0);
		BUG_ON(ret >= 0 && size != PAGE_SIZE);
		if (ret == 0)
			SetPageWasActive(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_client_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_local_new_pool(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_local_new_pool(0);
}

static struct cleancache_ops zcache_cleancache_ops = {
	.put_page = zcache_cleancache_put_page,
	.get_page = zcache_cleancache_get_page,
	.invalidate_page = zcache_cleancache_flush_page,
	.invalidate_inode = zcache_cleancache_flush_inode,
	.invalidate_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;
}

/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
static int zcache_frontswap_poolid __read_mostly = -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;
}

#ifdef CONFIG_ZCACHE_WRITEBACK
static void unswiz(struct tmem_oid oid, u32 index,
				unsigned *type, pgoff_t *offset)
{
	*type = (unsigned)(oid.oid[0] >> SWIZ_BITS);
	*offset = (pgoff_t)((index << SWIZ_BITS) |
			(oid.oid[0] & SWIZ_MASK));
}
#endif

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 (!disable_frontswap_ignore_nonactive && !PageWasActive(page)) {
		zcache_pers_nonactive_puts_ignored++;
		ret = -ERANGE;
		goto out;
	}
	if (likely(ind64 == ind)) {
		local_irq_save(flags);
		ret = zcache_put_page(LOCAL_CLIENT, zcache_frontswap_poolid,
					&oid, iswiz(ind),
					page, PAGE_SIZE, false, 0);
		local_irq_restore(flags);
	}
out:
	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);
	size_t size;
	int ret = -1, get_and_free;

	if (frontswap_has_exclusive_gets)
		get_and_free = 1;
	else
		get_and_free = -1;
	BUG_ON(!PageLocked(page));
	if (likely(ind64 == ind)) {
		ret = zcache_get_page(LOCAL_CLIENT, zcache_frontswap_poolid,
					&oid, iswiz(ind),
					page, &size, false, get_and_free);
		BUG_ON(ret >= 0 && size != PAGE_SIZE);
	}
	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_local_new_pool(TMEM_POOL_PERSIST);
}

static struct frontswap_ops zcache_frontswap_ops = {
	.store = zcache_frontswap_put_page,
	.load = zcache_frontswap_get_page,
	.invalidate_page = zcache_frontswap_flush_page,
	.invalidate_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;
}

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

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

static int __init enable_ramster(char *s)
{
	zcache_enabled = true;
#ifdef CONFIG_RAMSTER
	ramster_enabled = true;
#endif
	return 1;
}
__setup("ramster", enable_ramster);

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

static int __init no_cleancache(char *s)
{
	disable_cleancache = true;
	return 1;
}

__setup("nocleancache", no_cleancache);

static int __init no_frontswap(char *s)
{
	disable_frontswap = true;
	return 1;
}

__setup("nofrontswap", no_frontswap);

static int __init no_frontswap_exclusive_gets(char *s)
{
	frontswap_has_exclusive_gets = false;
	return 1;
}

__setup("nofrontswapexclusivegets", no_frontswap_exclusive_gets);

static int __init no_frontswap_ignore_nonactive(char *s)
{
	disable_frontswap_ignore_nonactive = true;
	return 1;
}

__setup("nofrontswapignorenonactive", no_frontswap_ignore_nonactive);

static int __init no_cleancache_ignore_nonactive(char *s)
{
	disable_cleancache_ignore_nonactive = true;
	return 1;
}

__setup("nocleancacheignorenonactive", no_cleancache_ignore_nonactive);

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


static int __init 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;

	if (ramster_enabled) {
		namestr = "ramster";
		ramster_register_pamops(&zcache_pamops);
	}
#ifdef CONFIG_DEBUG_FS
	zcache_debugfs_init();
#endif
	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("%s: can't register cpu notifier\n", namestr);
			goto out;
		}
		ret = zcache_comp_init();
		if (ret) {
			pr_err("%s: compressor initialization failed\n",
				namestr);
			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("%s: can't create client\n", namestr);
		goto out;
	}
	zbud_init();
	if (zcache_enabled && !disable_cleancache) {
		struct cleancache_ops old_ops;

		register_shrinker(&zcache_shrinker);
		old_ops = zcache_cleancache_register_ops();
		pr_info("%s: cleancache enabled using kernel transcendent "
			"memory and compression buddies\n", namestr);
#ifdef ZCACHE_DEBUG
		pr_info("%s: cleancache: ignorenonactive = %d\n",
			namestr, !disable_cleancache_ignore_nonactive);
#endif
		if (old_ops.init_fs != NULL)
			pr_warn("%s: cleancache_ops overridden\n", namestr);
	}
	if (zcache_enabled && !disable_frontswap) {
		struct frontswap_ops old_ops;

		old_ops = zcache_frontswap_register_ops();
		if (frontswap_has_exclusive_gets)
			frontswap_tmem_exclusive_gets(true);
		pr_info("%s: frontswap enabled using kernel transcendent "
			"memory and compression buddies\n", namestr);
#ifdef ZCACHE_DEBUG
		pr_info("%s: frontswap: excl gets = %d active only = %d\n",
			namestr, frontswap_has_exclusive_gets,
			!disable_frontswap_ignore_nonactive);
#endif
		if (old_ops.init != NULL)
			pr_warn("%s: frontswap_ops overridden\n", namestr);
	}
	if (ramster_enabled)
		ramster_init(!disable_cleancache, !disable_frontswap,
				frontswap_has_exclusive_gets);
out:
	return ret;
}

late_initcall(zcache_init);