summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-cache-target.c
blob: 66120bd46d15639613cdeaf09b4474db48550845 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
/*
 * Copyright (C) 2012 Red Hat. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm.h"
#include "dm-bio-prison.h"
#include "dm-cache-metadata.h"

#include <linux/dm-io.h>
#include <linux/dm-kcopyd.h>
#include <linux/init.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>

#define DM_MSG_PREFIX "cache"

DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(cache_copy_throttle,
	"A percentage of time allocated for copying to and/or from cache");

/*----------------------------------------------------------------*/

/*
 * Glossary:
 *
 * oblock: index of an origin block
 * cblock: index of a cache block
 * promotion: movement of a block from origin to cache
 * demotion: movement of a block from cache to origin
 * migration: movement of a block between the origin and cache device,
 *	      either direction
 */

/*----------------------------------------------------------------*/

static size_t bitset_size_in_bytes(unsigned nr_entries)
{
	return sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG);
}

static unsigned long *alloc_bitset(unsigned nr_entries)
{
	size_t s = bitset_size_in_bytes(nr_entries);
	return vzalloc(s);
}

static void clear_bitset(void *bitset, unsigned nr_entries)
{
	size_t s = bitset_size_in_bytes(nr_entries);
	memset(bitset, 0, s);
}

static void free_bitset(unsigned long *bits)
{
	vfree(bits);
}

/*----------------------------------------------------------------*/

#define PRISON_CELLS 1024
#define MIGRATION_POOL_SIZE 128
#define COMMIT_PERIOD HZ
#define MIGRATION_COUNT_WINDOW 10

/*
 * The block size of the device holding cache data must be >= 32KB
 */
#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (32 * 1024 >> SECTOR_SHIFT)

/*
 * FIXME: the cache is read/write for the time being.
 */
enum cache_mode {
	CM_WRITE,		/* metadata may be changed */
	CM_READ_ONLY,		/* metadata may not be changed */
};

struct cache_features {
	enum cache_mode mode;
	bool write_through:1;
};

struct cache_stats {
	atomic_t read_hit;
	atomic_t read_miss;
	atomic_t write_hit;
	atomic_t write_miss;
	atomic_t demotion;
	atomic_t promotion;
	atomic_t copies_avoided;
	atomic_t cache_cell_clash;
	atomic_t commit_count;
	atomic_t discard_count;
};

struct cache {
	struct dm_target *ti;
	struct dm_target_callbacks callbacks;

	/*
	 * Metadata is written to this device.
	 */
	struct dm_dev *metadata_dev;

	/*
	 * The slower of the two data devices.  Typically a spindle.
	 */
	struct dm_dev *origin_dev;

	/*
	 * The faster of the two data devices.  Typically an SSD.
	 */
	struct dm_dev *cache_dev;

	/*
	 * Cache features such as write-through.
	 */
	struct cache_features features;

	/*
	 * Size of the origin device in _complete_ blocks and native sectors.
	 */
	dm_oblock_t origin_blocks;
	sector_t origin_sectors;

	/*
	 * Size of the cache device in blocks.
	 */
	dm_cblock_t cache_size;

	/*
	 * Fields for converting from sectors to blocks.
	 */
	uint32_t sectors_per_block;
	int sectors_per_block_shift;

	struct dm_cache_metadata *cmd;

	spinlock_t lock;
	struct bio_list deferred_bios;
	struct bio_list deferred_flush_bios;
	struct bio_list deferred_writethrough_bios;
	struct list_head quiesced_migrations;
	struct list_head completed_migrations;
	struct list_head need_commit_migrations;
	sector_t migration_threshold;
	atomic_t nr_migrations;
	wait_queue_head_t migration_wait;

	/*
	 * cache_size entries, dirty if set
	 */
	dm_cblock_t nr_dirty;
	unsigned long *dirty_bitset;

	/*
	 * origin_blocks entries, discarded if set.
	 */
	uint32_t discard_block_size; /* a power of 2 times sectors per block */
	dm_dblock_t discard_nr_blocks;
	unsigned long *discard_bitset;

	struct dm_kcopyd_client *copier;
	struct workqueue_struct *wq;
	struct work_struct worker;

	struct delayed_work waker;
	unsigned long last_commit_jiffies;

	struct dm_bio_prison *prison;
	struct dm_deferred_set *all_io_ds;

	mempool_t *migration_pool;
	struct dm_cache_migration *next_migration;

	struct dm_cache_policy *policy;
	unsigned policy_nr_args;

	bool need_tick_bio:1;
	bool sized:1;
	bool quiescing:1;
	bool commit_requested:1;
	bool loaded_mappings:1;
	bool loaded_discards:1;

	struct cache_stats stats;

	/*
	 * Rather than reconstructing the table line for the status we just
	 * save it and regurgitate.
	 */
	unsigned nr_ctr_args;
	const char **ctr_args;
};

struct per_bio_data {
	bool tick:1;
	unsigned req_nr:2;
	struct dm_deferred_entry *all_io_entry;

	/* writethrough fields */
	struct cache *cache;
	dm_cblock_t cblock;
	bio_end_io_t *saved_bi_end_io;
};

struct dm_cache_migration {
	struct list_head list;
	struct cache *cache;

	unsigned long start_jiffies;
	dm_oblock_t old_oblock;
	dm_oblock_t new_oblock;
	dm_cblock_t cblock;

	bool err:1;
	bool writeback:1;
	bool demote:1;
	bool promote:1;

	struct dm_bio_prison_cell *old_ocell;
	struct dm_bio_prison_cell *new_ocell;
};

/*
 * Processing a bio in the worker thread may require these memory
 * allocations.  We prealloc to avoid deadlocks (the same worker thread
 * frees them back to the mempool).
 */
struct prealloc {
	struct dm_cache_migration *mg;
	struct dm_bio_prison_cell *cell1;
	struct dm_bio_prison_cell *cell2;
};

static void wake_worker(struct cache *cache)
{
	queue_work(cache->wq, &cache->worker);
}

/*----------------------------------------------------------------*/

static struct dm_bio_prison_cell *alloc_prison_cell(struct cache *cache)
{
	/* FIXME: change to use a local slab. */
	return dm_bio_prison_alloc_cell(cache->prison, GFP_NOWAIT);
}

static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cell)
{
	dm_bio_prison_free_cell(cache->prison, cell);
}

static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
{
	if (!p->mg) {
		p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
		if (!p->mg)
			return -ENOMEM;
	}

	if (!p->cell1) {
		p->cell1 = alloc_prison_cell(cache);
		if (!p->cell1)
			return -ENOMEM;
	}

	if (!p->cell2) {
		p->cell2 = alloc_prison_cell(cache);
		if (!p->cell2)
			return -ENOMEM;
	}

	return 0;
}

static void prealloc_free_structs(struct cache *cache, struct prealloc *p)
{
	if (p->cell2)
		free_prison_cell(cache, p->cell2);

	if (p->cell1)
		free_prison_cell(cache, p->cell1);

	if (p->mg)
		mempool_free(p->mg, cache->migration_pool);
}

static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p)
{
	struct dm_cache_migration *mg = p->mg;

	BUG_ON(!mg);
	p->mg = NULL;

	return mg;
}

/*
 * You must have a cell within the prealloc struct to return.  If not this
 * function will BUG() rather than returning NULL.
 */
static struct dm_bio_prison_cell *prealloc_get_cell(struct prealloc *p)
{
	struct dm_bio_prison_cell *r = NULL;

	if (p->cell1) {
		r = p->cell1;
		p->cell1 = NULL;

	} else if (p->cell2) {
		r = p->cell2;
		p->cell2 = NULL;
	} else
		BUG();

	return r;
}

/*
 * You can't have more than two cells in a prealloc struct.  BUG() will be
 * called if you try and overfill.
 */
static void prealloc_put_cell(struct prealloc *p, struct dm_bio_prison_cell *cell)
{
	if (!p->cell2)
		p->cell2 = cell;

	else if (!p->cell1)
		p->cell1 = cell;

	else
		BUG();
}

/*----------------------------------------------------------------*/

static void build_key(dm_oblock_t oblock, struct dm_cell_key *key)
{
	key->virtual = 0;
	key->dev = 0;
	key->block = from_oblock(oblock);
}

/*
 * The caller hands in a preallocated cell, and a free function for it.
 * The cell will be freed if there's an error, or if it wasn't used because
 * a cell with that key already exists.
 */
typedef void (*cell_free_fn)(void *context, struct dm_bio_prison_cell *cell);

static int bio_detain(struct cache *cache, dm_oblock_t oblock,
		      struct bio *bio, struct dm_bio_prison_cell *cell_prealloc,
		      cell_free_fn free_fn, void *free_context,
		      struct dm_bio_prison_cell **cell_result)
{
	int r;
	struct dm_cell_key key;

	build_key(oblock, &key);
	r = dm_bio_detain(cache->prison, &key, bio, cell_prealloc, cell_result);
	if (r)
		free_fn(free_context, cell_prealloc);

	return r;
}

static int get_cell(struct cache *cache,
		    dm_oblock_t oblock,
		    struct prealloc *structs,
		    struct dm_bio_prison_cell **cell_result)
{
	int r;
	struct dm_cell_key key;
	struct dm_bio_prison_cell *cell_prealloc;

	cell_prealloc = prealloc_get_cell(structs);

	build_key(oblock, &key);
	r = dm_get_cell(cache->prison, &key, cell_prealloc, cell_result);
	if (r)
		prealloc_put_cell(structs, cell_prealloc);

	return r;
}

 /*----------------------------------------------------------------*/

static bool is_dirty(struct cache *cache, dm_cblock_t b)
{
	return test_bit(from_cblock(b), cache->dirty_bitset);
}

static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
{
	if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) {
		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1);
		policy_set_dirty(cache->policy, oblock);
	}
}

static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
{
	if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) {
		policy_clear_dirty(cache->policy, oblock);
		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1);
		if (!from_cblock(cache->nr_dirty))
			dm_table_event(cache->ti->table);
	}
}

/*----------------------------------------------------------------*/
static bool block_size_is_power_of_two(struct cache *cache)
{
	return cache->sectors_per_block_shift >= 0;
}

static dm_block_t block_div(dm_block_t b, uint32_t n)
{
	do_div(b, n);

	return b;
}

static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
{
	uint32_t discard_blocks = cache->discard_block_size;
	dm_block_t b = from_oblock(oblock);

	if (!block_size_is_power_of_two(cache))
		discard_blocks = discard_blocks / cache->sectors_per_block;
	else
		discard_blocks >>= cache->sectors_per_block_shift;

	b = block_div(b, discard_blocks);

	return to_dblock(b);
}

static void set_discard(struct cache *cache, dm_dblock_t b)
{
	unsigned long flags;

	atomic_inc(&cache->stats.discard_count);

	spin_lock_irqsave(&cache->lock, flags);
	set_bit(from_dblock(b), cache->discard_bitset);
	spin_unlock_irqrestore(&cache->lock, flags);
}

static void clear_discard(struct cache *cache, dm_dblock_t b)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	clear_bit(from_dblock(b), cache->discard_bitset);
	spin_unlock_irqrestore(&cache->lock, flags);
}

static bool is_discarded(struct cache *cache, dm_dblock_t b)
{
	int r;
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	r = test_bit(from_dblock(b), cache->discard_bitset);
	spin_unlock_irqrestore(&cache->lock, flags);

	return r;
}

static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
{
	int r;
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
		     cache->discard_bitset);
	spin_unlock_irqrestore(&cache->lock, flags);

	return r;
}

/*----------------------------------------------------------------*/

static void load_stats(struct cache *cache)
{
	struct dm_cache_statistics stats;

	dm_cache_metadata_get_stats(cache->cmd, &stats);
	atomic_set(&cache->stats.read_hit, stats.read_hits);
	atomic_set(&cache->stats.read_miss, stats.read_misses);
	atomic_set(&cache->stats.write_hit, stats.write_hits);
	atomic_set(&cache->stats.write_miss, stats.write_misses);
}

static void save_stats(struct cache *cache)
{
	struct dm_cache_statistics stats;

	stats.read_hits = atomic_read(&cache->stats.read_hit);
	stats.read_misses = atomic_read(&cache->stats.read_miss);
	stats.write_hits = atomic_read(&cache->stats.write_hit);
	stats.write_misses = atomic_read(&cache->stats.write_miss);

	dm_cache_metadata_set_stats(cache->cmd, &stats);
}

/*----------------------------------------------------------------
 * Per bio data
 *--------------------------------------------------------------*/
static struct per_bio_data *get_per_bio_data(struct bio *bio)
{
	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
	BUG_ON(!pb);
	return pb;
}

static struct per_bio_data *init_per_bio_data(struct bio *bio)
{
	struct per_bio_data *pb = get_per_bio_data(bio);

	pb->tick = false;
	pb->req_nr = dm_bio_get_target_bio_nr(bio);
	pb->all_io_entry = NULL;

	return pb;
}

/*----------------------------------------------------------------
 * Remapping
 *--------------------------------------------------------------*/
static void remap_to_origin(struct cache *cache, struct bio *bio)
{
	bio->bi_bdev = cache->origin_dev->bdev;
}

static void remap_to_cache(struct cache *cache, struct bio *bio,
			   dm_cblock_t cblock)
{
	sector_t bi_sector = bio->bi_sector;

	bio->bi_bdev = cache->cache_dev->bdev;
	if (!block_size_is_power_of_two(cache))
		bio->bi_sector = (from_cblock(cblock) * cache->sectors_per_block) +
				sector_div(bi_sector, cache->sectors_per_block);
	else
		bio->bi_sector = (from_cblock(cblock) << cache->sectors_per_block_shift) |
				(bi_sector & (cache->sectors_per_block - 1));
}

static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
{
	unsigned long flags;
	struct per_bio_data *pb = get_per_bio_data(bio);

	spin_lock_irqsave(&cache->lock, flags);
	if (cache->need_tick_bio &&
	    !(bio->bi_rw & (REQ_FUA | REQ_FLUSH | REQ_DISCARD))) {
		pb->tick = true;
		cache->need_tick_bio = false;
	}
	spin_unlock_irqrestore(&cache->lock, flags);
}

static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
				  dm_oblock_t oblock)
{
	check_if_tick_bio_needed(cache, bio);
	remap_to_origin(cache, bio);
	if (bio_data_dir(bio) == WRITE)
		clear_discard(cache, oblock_to_dblock(cache, oblock));
}

static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
				 dm_oblock_t oblock, dm_cblock_t cblock)
{
	remap_to_cache(cache, bio, cblock);
	if (bio_data_dir(bio) == WRITE) {
		set_dirty(cache, oblock, cblock);
		clear_discard(cache, oblock_to_dblock(cache, oblock));
	}
}

static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
{
	sector_t block_nr = bio->bi_sector;

	if (!block_size_is_power_of_two(cache))
		(void) sector_div(block_nr, cache->sectors_per_block);
	else
		block_nr >>= cache->sectors_per_block_shift;

	return to_oblock(block_nr);
}

static int bio_triggers_commit(struct cache *cache, struct bio *bio)
{
	return bio->bi_rw & (REQ_FLUSH | REQ_FUA);
}

static void issue(struct cache *cache, struct bio *bio)
{
	unsigned long flags;

	if (!bio_triggers_commit(cache, bio)) {
		generic_make_request(bio);
		return;
	}

	/*
	 * Batch together any bios that trigger commits and then issue a
	 * single commit for them in do_worker().
	 */
	spin_lock_irqsave(&cache->lock, flags);
	cache->commit_requested = true;
	bio_list_add(&cache->deferred_flush_bios, bio);
	spin_unlock_irqrestore(&cache->lock, flags);
}

static void defer_writethrough_bio(struct cache *cache, struct bio *bio)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_add(&cache->deferred_writethrough_bios, bio);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void writethrough_endio(struct bio *bio, int err)
{
	struct per_bio_data *pb = get_per_bio_data(bio);
	bio->bi_end_io = pb->saved_bi_end_io;

	if (err) {
		bio_endio(bio, err);
		return;
	}

	remap_to_cache(pb->cache, bio, pb->cblock);

	/*
	 * We can't issue this bio directly, since we're in interrupt
	 * context.  So it get's put on a bio list for processing by the
	 * worker thread.
	 */
	defer_writethrough_bio(pb->cache, bio);
}

/*
 * When running in writethrough mode we need to send writes to clean blocks
 * to both the cache and origin devices.  In future we'd like to clone the
 * bio and send them in parallel, but for now we're doing them in
 * series as this is easier.
 */
static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio,
				       dm_oblock_t oblock, dm_cblock_t cblock)
{
	struct per_bio_data *pb = get_per_bio_data(bio);

	pb->cache = cache;
	pb->cblock = cblock;
	pb->saved_bi_end_io = bio->bi_end_io;
	bio->bi_end_io = writethrough_endio;

	remap_to_origin_clear_discard(pb->cache, bio, oblock);
}

/*----------------------------------------------------------------
 * Migration processing
 *
 * Migration covers moving data from the origin device to the cache, or
 * vice versa.
 *--------------------------------------------------------------*/
static void free_migration(struct dm_cache_migration *mg)
{
	mempool_free(mg, mg->cache->migration_pool);
}

static void inc_nr_migrations(struct cache *cache)
{
	atomic_inc(&cache->nr_migrations);
}

static void dec_nr_migrations(struct cache *cache)
{
	atomic_dec(&cache->nr_migrations);

	/*
	 * Wake the worker in case we're suspending the target.
	 */
	wake_up(&cache->migration_wait);
}

static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
			 bool holder)
{
	(holder ? dm_cell_release : dm_cell_release_no_holder)
		(cache->prison, cell, &cache->deferred_bios);
	free_prison_cell(cache, cell);
}

static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
		       bool holder)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	__cell_defer(cache, cell, holder);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void cleanup_migration(struct dm_cache_migration *mg)
{
	dec_nr_migrations(mg->cache);
	free_migration(mg);
}

static void migration_failure(struct dm_cache_migration *mg)
{
	struct cache *cache = mg->cache;

	if (mg->writeback) {
		DMWARN_LIMIT("writeback failed; couldn't copy block");
		set_dirty(cache, mg->old_oblock, mg->cblock);
		cell_defer(cache, mg->old_ocell, false);

	} else if (mg->demote) {
		DMWARN_LIMIT("demotion failed; couldn't copy block");
		policy_force_mapping(cache->policy, mg->new_oblock, mg->old_oblock);

		cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1);
		if (mg->promote)
			cell_defer(cache, mg->new_ocell, 1);
	} else {
		DMWARN_LIMIT("promotion failed; couldn't copy block");
		policy_remove_mapping(cache->policy, mg->new_oblock);
		cell_defer(cache, mg->new_ocell, 1);
	}

	cleanup_migration(mg);
}

static void migration_success_pre_commit(struct dm_cache_migration *mg)
{
	unsigned long flags;
	struct cache *cache = mg->cache;

	if (mg->writeback) {
		cell_defer(cache, mg->old_ocell, false);
		clear_dirty(cache, mg->old_oblock, mg->cblock);
		cleanup_migration(mg);
		return;

	} else if (mg->demote) {
		if (dm_cache_remove_mapping(cache->cmd, mg->cblock)) {
			DMWARN_LIMIT("demotion failed; couldn't update on disk metadata");
			policy_force_mapping(cache->policy, mg->new_oblock,
					     mg->old_oblock);
			if (mg->promote)
				cell_defer(cache, mg->new_ocell, true);
			cleanup_migration(mg);
			return;
		}
	} else {
		if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) {
			DMWARN_LIMIT("promotion failed; couldn't update on disk metadata");
			policy_remove_mapping(cache->policy, mg->new_oblock);
			cleanup_migration(mg);
			return;
		}
	}

	spin_lock_irqsave(&cache->lock, flags);
	list_add_tail(&mg->list, &cache->need_commit_migrations);
	cache->commit_requested = true;
	spin_unlock_irqrestore(&cache->lock, flags);
}

static void migration_success_post_commit(struct dm_cache_migration *mg)
{
	unsigned long flags;
	struct cache *cache = mg->cache;

	if (mg->writeback) {
		DMWARN("writeback unexpectedly triggered commit");
		return;

	} else if (mg->demote) {
		cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1);

		if (mg->promote) {
			mg->demote = false;

			spin_lock_irqsave(&cache->lock, flags);
			list_add_tail(&mg->list, &cache->quiesced_migrations);
			spin_unlock_irqrestore(&cache->lock, flags);

		} else
			cleanup_migration(mg);

	} else {
		cell_defer(cache, mg->new_ocell, true);
		clear_dirty(cache, mg->new_oblock, mg->cblock);
		cleanup_migration(mg);
	}
}

static void copy_complete(int read_err, unsigned long write_err, void *context)
{
	unsigned long flags;
	struct dm_cache_migration *mg = (struct dm_cache_migration *) context;
	struct cache *cache = mg->cache;

	if (read_err || write_err)
		mg->err = true;

	spin_lock_irqsave(&cache->lock, flags);
	list_add_tail(&mg->list, &cache->completed_migrations);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void issue_copy_real(struct dm_cache_migration *mg)
{
	int r;
	struct dm_io_region o_region, c_region;
	struct cache *cache = mg->cache;

	o_region.bdev = cache->origin_dev->bdev;
	o_region.count = cache->sectors_per_block;

	c_region.bdev = cache->cache_dev->bdev;
	c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
	c_region.count = cache->sectors_per_block;

	if (mg->writeback || mg->demote) {
		/* demote */
		o_region.sector = from_oblock(mg->old_oblock) * cache->sectors_per_block;
		r = dm_kcopyd_copy(cache->copier, &c_region, 1, &o_region, 0, copy_complete, mg);
	} else {
		/* promote */
		o_region.sector = from_oblock(mg->new_oblock) * cache->sectors_per_block;
		r = dm_kcopyd_copy(cache->copier, &o_region, 1, &c_region, 0, copy_complete, mg);
	}

	if (r < 0)
		migration_failure(mg);
}

static void avoid_copy(struct dm_cache_migration *mg)
{
	atomic_inc(&mg->cache->stats.copies_avoided);
	migration_success_pre_commit(mg);
}

static void issue_copy(struct dm_cache_migration *mg)
{
	bool avoid;
	struct cache *cache = mg->cache;

	if (mg->writeback || mg->demote)
		avoid = !is_dirty(cache, mg->cblock) ||
			is_discarded_oblock(cache, mg->old_oblock);
	else
		avoid = is_discarded_oblock(cache, mg->new_oblock);

	avoid ? avoid_copy(mg) : issue_copy_real(mg);
}

static void complete_migration(struct dm_cache_migration *mg)
{
	if (mg->err)
		migration_failure(mg);
	else
		migration_success_pre_commit(mg);
}

static void process_migrations(struct cache *cache, struct list_head *head,
			       void (*fn)(struct dm_cache_migration *))
{
	unsigned long flags;
	struct list_head list;
	struct dm_cache_migration *mg, *tmp;

	INIT_LIST_HEAD(&list);
	spin_lock_irqsave(&cache->lock, flags);
	list_splice_init(head, &list);
	spin_unlock_irqrestore(&cache->lock, flags);

	list_for_each_entry_safe(mg, tmp, &list, list)
		fn(mg);
}

static void __queue_quiesced_migration(struct dm_cache_migration *mg)
{
	list_add_tail(&mg->list, &mg->cache->quiesced_migrations);
}

static void queue_quiesced_migration(struct dm_cache_migration *mg)
{
	unsigned long flags;
	struct cache *cache = mg->cache;

	spin_lock_irqsave(&cache->lock, flags);
	__queue_quiesced_migration(mg);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void queue_quiesced_migrations(struct cache *cache, struct list_head *work)
{
	unsigned long flags;
	struct dm_cache_migration *mg, *tmp;

	spin_lock_irqsave(&cache->lock, flags);
	list_for_each_entry_safe(mg, tmp, work, list)
		__queue_quiesced_migration(mg);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void check_for_quiesced_migrations(struct cache *cache,
					  struct per_bio_data *pb)
{
	struct list_head work;

	if (!pb->all_io_entry)
		return;

	INIT_LIST_HEAD(&work);
	if (pb->all_io_entry)
		dm_deferred_entry_dec(pb->all_io_entry, &work);

	if (!list_empty(&work))
		queue_quiesced_migrations(cache, &work);
}

static void quiesce_migration(struct dm_cache_migration *mg)
{
	if (!dm_deferred_set_add_work(mg->cache->all_io_ds, &mg->list))
		queue_quiesced_migration(mg);
}

static void promote(struct cache *cache, struct prealloc *structs,
		    dm_oblock_t oblock, dm_cblock_t cblock,
		    struct dm_bio_prison_cell *cell)
{
	struct dm_cache_migration *mg = prealloc_get_migration(structs);

	mg->err = false;
	mg->writeback = false;
	mg->demote = false;
	mg->promote = true;
	mg->cache = cache;
	mg->new_oblock = oblock;
	mg->cblock = cblock;
	mg->old_ocell = NULL;
	mg->new_ocell = cell;
	mg->start_jiffies = jiffies;

	inc_nr_migrations(cache);
	quiesce_migration(mg);
}

static void writeback(struct cache *cache, struct prealloc *structs,
		      dm_oblock_t oblock, dm_cblock_t cblock,
		      struct dm_bio_prison_cell *cell)
{
	struct dm_cache_migration *mg = prealloc_get_migration(structs);

	mg->err = false;
	mg->writeback = true;
	mg->demote = false;
	mg->promote = false;
	mg->cache = cache;
	mg->old_oblock = oblock;
	mg->cblock = cblock;
	mg->old_ocell = cell;
	mg->new_ocell = NULL;
	mg->start_jiffies = jiffies;

	inc_nr_migrations(cache);
	quiesce_migration(mg);
}

static void demote_then_promote(struct cache *cache, struct prealloc *structs,
				dm_oblock_t old_oblock, dm_oblock_t new_oblock,
				dm_cblock_t cblock,
				struct dm_bio_prison_cell *old_ocell,
				struct dm_bio_prison_cell *new_ocell)
{
	struct dm_cache_migration *mg = prealloc_get_migration(structs);

	mg->err = false;
	mg->writeback = false;
	mg->demote = true;
	mg->promote = true;
	mg->cache = cache;
	mg->old_oblock = old_oblock;
	mg->new_oblock = new_oblock;
	mg->cblock = cblock;
	mg->old_ocell = old_ocell;
	mg->new_ocell = new_ocell;
	mg->start_jiffies = jiffies;

	inc_nr_migrations(cache);
	quiesce_migration(mg);
}

/*----------------------------------------------------------------
 * bio processing
 *--------------------------------------------------------------*/
static void defer_bio(struct cache *cache, struct bio *bio)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_add(&cache->deferred_bios, bio);
	spin_unlock_irqrestore(&cache->lock, flags);

	wake_worker(cache);
}

static void process_flush_bio(struct cache *cache, struct bio *bio)
{
	struct per_bio_data *pb = get_per_bio_data(bio);

	BUG_ON(bio->bi_size);
	if (!pb->req_nr)
		remap_to_origin(cache, bio);
	else
		remap_to_cache(cache, bio, 0);

	issue(cache, bio);
}

/*
 * People generally discard large parts of a device, eg, the whole device
 * when formatting.  Splitting these large discards up into cache block
 * sized ios and then quiescing (always neccessary for discard) takes too
 * long.
 *
 * We keep it simple, and allow any size of discard to come in, and just
 * mark off blocks on the discard bitset.  No passdown occurs!
 *
 * To implement passdown we need to change the bio_prison such that a cell
 * can have a key that spans many blocks.
 */
static void process_discard_bio(struct cache *cache, struct bio *bio)
{
	dm_block_t start_block = dm_sector_div_up(bio->bi_sector,
						  cache->discard_block_size);
	dm_block_t end_block = bio->bi_sector + bio_sectors(bio);
	dm_block_t b;

	end_block = block_div(end_block, cache->discard_block_size);

	for (b = start_block; b < end_block; b++)
		set_discard(cache, to_dblock(b));

	bio_endio(bio, 0);
}

static bool spare_migration_bandwidth(struct cache *cache)
{
	sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) *
		cache->sectors_per_block;
	return current_volume < cache->migration_threshold;
}

static bool is_writethrough_io(struct cache *cache, struct bio *bio,
			       dm_cblock_t cblock)
{
	return bio_data_dir(bio) == WRITE &&
		cache->features.write_through && !is_dirty(cache, cblock);
}

static void inc_hit_counter(struct cache *cache, struct bio *bio)
{
	atomic_inc(bio_data_dir(bio) == READ ?
		   &cache->stats.read_hit : &cache->stats.write_hit);
}

static void inc_miss_counter(struct cache *cache, struct bio *bio)
{
	atomic_inc(bio_data_dir(bio) == READ ?
		   &cache->stats.read_miss : &cache->stats.write_miss);
}

static void process_bio(struct cache *cache, struct prealloc *structs,
			struct bio *bio)
{
	int r;
	bool release_cell = true;
	dm_oblock_t block = get_bio_block(cache, bio);
	struct dm_bio_prison_cell *cell_prealloc, *old_ocell, *new_ocell;
	struct policy_result lookup_result;
	struct per_bio_data *pb = get_per_bio_data(bio);
	bool discarded_block = is_discarded_oblock(cache, block);
	bool can_migrate = discarded_block || spare_migration_bandwidth(cache);

	/*
	 * Check to see if that block is currently migrating.
	 */
	cell_prealloc = prealloc_get_cell(structs);
	r = bio_detain(cache, block, bio, cell_prealloc,
		       (cell_free_fn) prealloc_put_cell,
		       structs, &new_ocell);
	if (r > 0)
		return;

	r = policy_map(cache->policy, block, true, can_migrate, discarded_block,
		       bio, &lookup_result);

	if (r == -EWOULDBLOCK)
		/* migration has been denied */
		lookup_result.op = POLICY_MISS;

	switch (lookup_result.op) {
	case POLICY_HIT:
		inc_hit_counter(cache, bio);
		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);

		if (is_writethrough_io(cache, bio, lookup_result.cblock))
			remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock);
		else
			remap_to_cache_dirty(cache, bio, block, lookup_result.cblock);

		issue(cache, bio);
		break;

	case POLICY_MISS:
		inc_miss_counter(cache, bio);
		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
		remap_to_origin_clear_discard(cache, bio, block);
		issue(cache, bio);
		break;

	case POLICY_NEW:
		atomic_inc(&cache->stats.promotion);
		promote(cache, structs, block, lookup_result.cblock, new_ocell);
		release_cell = false;
		break;

	case POLICY_REPLACE:
		cell_prealloc = prealloc_get_cell(structs);
		r = bio_detain(cache, lookup_result.old_oblock, bio, cell_prealloc,
			       (cell_free_fn) prealloc_put_cell,
			       structs, &old_ocell);
		if (r > 0) {
			/*
			 * We have to be careful to avoid lock inversion of
			 * the cells.  So we back off, and wait for the
			 * old_ocell to become free.
			 */
			policy_force_mapping(cache->policy, block,
					     lookup_result.old_oblock);
			atomic_inc(&cache->stats.cache_cell_clash);
			break;
		}
		atomic_inc(&cache->stats.demotion);
		atomic_inc(&cache->stats.promotion);

		demote_then_promote(cache, structs, lookup_result.old_oblock,
				    block, lookup_result.cblock,
				    old_ocell, new_ocell);
		release_cell = false;
		break;

	default:
		DMERR_LIMIT("%s: erroring bio, unknown policy op: %u", __func__,
			    (unsigned) lookup_result.op);
		bio_io_error(bio);
	}

	if (release_cell)
		cell_defer(cache, new_ocell, false);
}

static int need_commit_due_to_time(struct cache *cache)
{
	return jiffies < cache->last_commit_jiffies ||
	       jiffies > cache->last_commit_jiffies + COMMIT_PERIOD;
}

static int commit_if_needed(struct cache *cache)
{
	if (dm_cache_changed_this_transaction(cache->cmd) &&
	    (cache->commit_requested || need_commit_due_to_time(cache))) {
		atomic_inc(&cache->stats.commit_count);
		cache->last_commit_jiffies = jiffies;
		cache->commit_requested = false;
		return dm_cache_commit(cache->cmd, false);
	}

	return 0;
}

static void process_deferred_bios(struct cache *cache)
{
	unsigned long flags;
	struct bio_list bios;
	struct bio *bio;
	struct prealloc structs;

	memset(&structs, 0, sizeof(structs));
	bio_list_init(&bios);

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_merge(&bios, &cache->deferred_bios);
	bio_list_init(&cache->deferred_bios);
	spin_unlock_irqrestore(&cache->lock, flags);

	while (!bio_list_empty(&bios)) {
		/*
		 * If we've got no free migration structs, and processing
		 * this bio might require one, we pause until there are some
		 * prepared mappings to process.
		 */
		if (prealloc_data_structs(cache, &structs)) {
			spin_lock_irqsave(&cache->lock, flags);
			bio_list_merge(&cache->deferred_bios, &bios);
			spin_unlock_irqrestore(&cache->lock, flags);
			break;
		}

		bio = bio_list_pop(&bios);

		if (bio->bi_rw & REQ_FLUSH)
			process_flush_bio(cache, bio);
		else if (bio->bi_rw & REQ_DISCARD)
			process_discard_bio(cache, bio);
		else
			process_bio(cache, &structs, bio);
	}

	prealloc_free_structs(cache, &structs);
}

static void process_deferred_flush_bios(struct cache *cache, bool submit_bios)
{
	unsigned long flags;
	struct bio_list bios;
	struct bio *bio;

	bio_list_init(&bios);

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_merge(&bios, &cache->deferred_flush_bios);
	bio_list_init(&cache->deferred_flush_bios);
	spin_unlock_irqrestore(&cache->lock, flags);

	while ((bio = bio_list_pop(&bios)))
		submit_bios ? generic_make_request(bio) : bio_io_error(bio);
}

static void process_deferred_writethrough_bios(struct cache *cache)
{
	unsigned long flags;
	struct bio_list bios;
	struct bio *bio;

	bio_list_init(&bios);

	spin_lock_irqsave(&cache->lock, flags);
	bio_list_merge(&bios, &cache->deferred_writethrough_bios);
	bio_list_init(&cache->deferred_writethrough_bios);
	spin_unlock_irqrestore(&cache->lock, flags);

	while ((bio = bio_list_pop(&bios)))
		generic_make_request(bio);
}

static void writeback_some_dirty_blocks(struct cache *cache)
{
	int r = 0;
	dm_oblock_t oblock;
	dm_cblock_t cblock;
	struct prealloc structs;
	struct dm_bio_prison_cell *old_ocell;

	memset(&structs, 0, sizeof(structs));

	while (spare_migration_bandwidth(cache)) {
		if (prealloc_data_structs(cache, &structs))
			break;

		r = policy_writeback_work(cache->policy, &oblock, &cblock);
		if (r)
			break;

		r = get_cell(cache, oblock, &structs, &old_ocell);
		if (r) {
			policy_set_dirty(cache->policy, oblock);
			break;
		}

		writeback(cache, &structs, oblock, cblock, old_ocell);
	}

	prealloc_free_structs(cache, &structs);
}

/*----------------------------------------------------------------
 * Main worker loop
 *--------------------------------------------------------------*/
static void start_quiescing(struct cache *cache)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	cache->quiescing = 1;
	spin_unlock_irqrestore(&cache->lock, flags);
}

static void stop_quiescing(struct cache *cache)
{
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	cache->quiescing = 0;
	spin_unlock_irqrestore(&cache->lock, flags);
}

static bool is_quiescing(struct cache *cache)
{
	int r;
	unsigned long flags;

	spin_lock_irqsave(&cache->lock, flags);
	r = cache->quiescing;
	spin_unlock_irqrestore(&cache->lock, flags);

	return r;
}

static void wait_for_migrations(struct cache *cache)
{
	wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations));
}

static void stop_worker(struct cache *cache)
{
	cancel_delayed_work(&cache->waker);
	flush_workqueue(cache->wq);
}

static void requeue_deferred_io(struct cache *cache)
{
	struct bio *bio;
	struct bio_list bios;

	bio_list_init(&bios);
	bio_list_merge(&bios, &cache->deferred_bios);
	bio_list_init(&cache->deferred_bios);

	while ((bio = bio_list_pop(&bios)))
		bio_endio(bio, DM_ENDIO_REQUEUE);
}

static int more_work(struct cache *cache)
{
	if (is_quiescing(cache))
		return !list_empty(&cache->quiesced_migrations) ||
			!list_empty(&cache->completed_migrations) ||
			!list_empty(&cache->need_commit_migrations);
	else
		return !bio_list_empty(&cache->deferred_bios) ||
			!bio_list_empty(&cache->deferred_flush_bios) ||
			!bio_list_empty(&cache->deferred_writethrough_bios) ||
			!list_empty(&cache->quiesced_migrations) ||
			!list_empty(&cache->completed_migrations) ||
			!list_empty(&cache->need_commit_migrations);
}

static void do_worker(struct work_struct *ws)
{
	struct cache *cache = container_of(ws, struct cache, worker);

	do {
		if (!is_quiescing(cache))
			process_deferred_bios(cache);

		process_migrations(cache, &cache->quiesced_migrations, issue_copy);
		process_migrations(cache, &cache->completed_migrations, complete_migration);

		writeback_some_dirty_blocks(cache);

		process_deferred_writethrough_bios(cache);

		if (commit_if_needed(cache)) {
			process_deferred_flush_bios(cache, false);

			/*
			 * FIXME: rollback metadata or just go into a
			 * failure mode and error everything
			 */
		} else {
			process_deferred_flush_bios(cache, true);
			process_migrations(cache, &cache->need_commit_migrations,
					   migration_success_post_commit);
		}
	} while (more_work(cache));
}

/*
 * We want to commit periodically so that not too much
 * unwritten metadata builds up.
 */
static void do_waker(struct work_struct *ws)
{
	struct cache *cache = container_of(to_delayed_work(ws), struct cache, waker);
	wake_worker(cache);
	queue_delayed_work(cache->wq, &cache->waker, COMMIT_PERIOD);
}

/*----------------------------------------------------------------*/

static int is_congested(struct dm_dev *dev, int bdi_bits)
{
	struct request_queue *q = bdev_get_queue(dev->bdev);
	return bdi_congested(&q->backing_dev_info, bdi_bits);
}

static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
{
	struct cache *cache = container_of(cb, struct cache, callbacks);

	return is_congested(cache->origin_dev, bdi_bits) ||
		is_congested(cache->cache_dev, bdi_bits);
}

/*----------------------------------------------------------------
 * Target methods
 *--------------------------------------------------------------*/

/*
 * This function gets called on the error paths of the constructor, so we
 * have to cope with a partially initialised struct.
 */
static void destroy(struct cache *cache)
{
	unsigned i;

	if (cache->next_migration)
		mempool_free(cache->next_migration, cache->migration_pool);

	if (cache->migration_pool)
		mempool_destroy(cache->migration_pool);

	if (cache->all_io_ds)
		dm_deferred_set_destroy(cache->all_io_ds);

	if (cache->prison)
		dm_bio_prison_destroy(cache->prison);

	if (cache->wq)
		destroy_workqueue(cache->wq);

	if (cache->dirty_bitset)
		free_bitset(cache->dirty_bitset);

	if (cache->discard_bitset)
		free_bitset(cache->discard_bitset);

	if (cache->copier)
		dm_kcopyd_client_destroy(cache->copier);

	if (cache->cmd)
		dm_cache_metadata_close(cache->cmd);

	if (cache->metadata_dev)
		dm_put_device(cache->ti, cache->metadata_dev);

	if (cache->origin_dev)
		dm_put_device(cache->ti, cache->origin_dev);

	if (cache->cache_dev)
		dm_put_device(cache->ti, cache->cache_dev);

	if (cache->policy)
		dm_cache_policy_destroy(cache->policy);

	for (i = 0; i < cache->nr_ctr_args ; i++)
		kfree(cache->ctr_args[i]);
	kfree(cache->ctr_args);

	kfree(cache);
}

static void cache_dtr(struct dm_target *ti)
{
	struct cache *cache = ti->private;

	destroy(cache);
}

static sector_t get_dev_size(struct dm_dev *dev)
{
	return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
}

/*----------------------------------------------------------------*/

/*
 * Construct a cache device mapping.
 *
 * cache <metadata dev> <cache dev> <origin dev> <block size>
 *       <#feature args> [<feature arg>]*
 *       <policy> <#policy args> [<policy arg>]*
 *
 * metadata dev    : fast device holding the persistent metadata
 * cache dev	   : fast device holding cached data blocks
 * origin dev	   : slow device holding original data blocks
 * block size	   : cache unit size in sectors
 *
 * #feature args   : number of feature arguments passed
 * feature args    : writethrough.  (The default is writeback.)
 *
 * policy	   : the replacement policy to use
 * #policy args    : an even number of policy arguments corresponding
 *		     to key/value pairs passed to the policy
 * policy args	   : key/value pairs passed to the policy
 *		     E.g. 'sequential_threshold 1024'
 *		     See cache-policies.txt for details.
 *
 * Optional feature arguments are:
 *   writethrough  : write through caching that prohibits cache block
 *		     content from being different from origin block content.
 *		     Without this argument, the default behaviour is to write
 *		     back cache block contents later for performance reasons,
 *		     so they may differ from the corresponding origin blocks.
 */
struct cache_args {
	struct dm_target *ti;

	struct dm_dev *metadata_dev;

	struct dm_dev *cache_dev;
	sector_t cache_sectors;

	struct dm_dev *origin_dev;
	sector_t origin_sectors;

	uint32_t block_size;

	const char *policy_name;
	int policy_argc;
	const char **policy_argv;

	struct cache_features features;
};

static void destroy_cache_args(struct cache_args *ca)
{
	if (ca->metadata_dev)
		dm_put_device(ca->ti, ca->metadata_dev);

	if (ca->cache_dev)
		dm_put_device(ca->ti, ca->cache_dev);

	if (ca->origin_dev)
		dm_put_device(ca->ti, ca->origin_dev);

	kfree(ca);
}

static bool at_least_one_arg(struct dm_arg_set *as, char **error)
{
	if (!as->argc) {
		*error = "Insufficient args";
		return false;
	}

	return true;
}

static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as,
			      char **error)
{
	int r;
	sector_t metadata_dev_size;
	char b[BDEVNAME_SIZE];

	if (!at_least_one_arg(as, error))
		return -EINVAL;

	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
			  &ca->metadata_dev);
	if (r) {
		*error = "Error opening metadata device";
		return r;
	}

	metadata_dev_size = get_dev_size(ca->metadata_dev);
	if (metadata_dev_size > DM_CACHE_METADATA_MAX_SECTORS_WARNING)
		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
		       bdevname(ca->metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS);

	return 0;
}

static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as,
			   char **error)
{
	int r;

	if (!at_least_one_arg(as, error))
		return -EINVAL;

	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
			  &ca->cache_dev);
	if (r) {
		*error = "Error opening cache device";
		return r;
	}
	ca->cache_sectors = get_dev_size(ca->cache_dev);

	return 0;
}

static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as,
			    char **error)
{
	int r;

	if (!at_least_one_arg(as, error))
		return -EINVAL;

	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
			  &ca->origin_dev);
	if (r) {
		*error = "Error opening origin device";
		return r;
	}

	ca->origin_sectors = get_dev_size(ca->origin_dev);
	if (ca->ti->len > ca->origin_sectors) {
		*error = "Device size larger than cached device";
		return -EINVAL;
	}

	return 0;
}

static int parse_block_size(struct cache_args *ca, struct dm_arg_set *as,
			    char **error)
{
	unsigned long tmp;

	if (!at_least_one_arg(as, error))
		return -EINVAL;

	if (kstrtoul(dm_shift_arg(as), 10, &tmp) || !tmp ||
	    tmp < DATA_DEV_BLOCK_SIZE_MIN_SECTORS ||
	    tmp & (DATA_DEV_BLOCK_SIZE_MIN_SECTORS - 1)) {
		*error = "Invalid data block size";
		return -EINVAL;
	}

	if (tmp > ca->cache_sectors) {
		*error = "Data block size is larger than the cache device";
		return -EINVAL;
	}

	ca->block_size = tmp;

	return 0;
}

static void init_features(struct cache_features *cf)
{
	cf->mode = CM_WRITE;
	cf->write_through = false;
}

static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
			  char **error)
{
	static struct dm_arg _args[] = {
		{0, 1, "Invalid number of cache feature arguments"},
	};

	int r;
	unsigned argc;
	const char *arg;
	struct cache_features *cf = &ca->features;

	init_features(cf);

	r = dm_read_arg_group(_args, as, &argc, error);
	if (r)
		return -EINVAL;

	while (argc--) {
		arg = dm_shift_arg(as);

		if (!strcasecmp(arg, "writeback"))
			cf->write_through = false;

		else if (!strcasecmp(arg, "writethrough"))
			cf->write_through = true;

		else {
			*error = "Unrecognised cache feature requested";
			return -EINVAL;
		}
	}

	return 0;
}

static int parse_policy(struct cache_args *ca, struct dm_arg_set *as,
			char **error)
{
	static struct dm_arg _args[] = {
		{0, 1024, "Invalid number of policy arguments"},
	};

	int r;

	if (!at_least_one_arg(as, error))
		return -EINVAL;

	ca->policy_name = dm_shift_arg(as);

	r = dm_read_arg_group(_args, as, &ca->policy_argc, error);
	if (r)
		return -EINVAL;

	ca->policy_argv = (const char **)as->argv;
	dm_consume_args(as, ca->policy_argc);

	return 0;
}

static int parse_cache_args(struct cache_args *ca, int argc, char **argv,
			    char **error)
{
	int r;
	struct dm_arg_set as;

	as.argc = argc;
	as.argv = argv;

	r = parse_metadata_dev(ca, &as, error);
	if (r)
		return r;

	r = parse_cache_dev(ca, &as, error);
	if (r)
		return r;

	r = parse_origin_dev(ca, &as, error);
	if (r)
		return r;

	r = parse_block_size(ca, &as, error);
	if (r)
		return r;

	r = parse_features(ca, &as, error);
	if (r)
		return r;

	r = parse_policy(ca, &as, error);
	if (r)
		return r;

	return 0;
}

/*----------------------------------------------------------------*/

static struct kmem_cache *migration_cache;

static int set_config_values(struct dm_cache_policy *p, int argc, const char **argv)
{
	int r = 0;

	if (argc & 1) {
		DMWARN("Odd number of policy arguments given but they should be <key> <value> pairs.");
		return -EINVAL;
	}

	while (argc) {
		r = policy_set_config_value(p, argv[0], argv[1]);
		if (r) {
			DMWARN("policy_set_config_value failed: key = '%s', value = '%s'",
			       argv[0], argv[1]);
			return r;
		}

		argc -= 2;
		argv += 2;
	}

	return r;
}

static int create_cache_policy(struct cache *cache, struct cache_args *ca,
			       char **error)
{
	int r;

	cache->policy =	dm_cache_policy_create(ca->policy_name,
					       cache->cache_size,
					       cache->origin_sectors,
					       cache->sectors_per_block);
	if (!cache->policy) {
		*error = "Error creating cache's policy";
		return -ENOMEM;
	}

	r = set_config_values(cache->policy, ca->policy_argc, ca->policy_argv);
	if (r) {
		*error = "Error setting cache policy's config values";
		dm_cache_policy_destroy(cache->policy);
		cache->policy = NULL;
	}

	return r;
}

/*
 * We want the discard block size to be a power of two, at least the size
 * of the cache block size, and have no more than 2^14 discard blocks
 * across the origin.
 */
#define MAX_DISCARD_BLOCKS (1 << 14)

static bool too_many_discard_blocks(sector_t discard_block_size,
				    sector_t origin_size)
{
	(void) sector_div(origin_size, discard_block_size);

	return origin_size > MAX_DISCARD_BLOCKS;
}

static sector_t calculate_discard_block_size(sector_t cache_block_size,
					     sector_t origin_size)
{
	sector_t discard_block_size;

	discard_block_size = roundup_pow_of_two(cache_block_size);

	if (origin_size)
		while (too_many_discard_blocks(discard_block_size, origin_size))
			discard_block_size *= 2;

	return discard_block_size;
}

#define DEFAULT_MIGRATION_THRESHOLD (2048 * 100)

static int cache_create(struct cache_args *ca, struct cache **result)
{
	int r = 0;
	char **error = &ca->ti->error;
	struct cache *cache;
	struct dm_target *ti = ca->ti;
	dm_block_t origin_blocks;
	struct dm_cache_metadata *cmd;
	bool may_format = ca->features.mode == CM_WRITE;

	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
	if (!cache)
		return -ENOMEM;

	cache->ti = ca->ti;
	ti->private = cache;
	ti->per_bio_data_size = sizeof(struct per_bio_data);
	ti->num_flush_bios = 2;
	ti->flush_supported = true;

	ti->num_discard_bios = 1;
	ti->discards_supported = true;
	ti->discard_zeroes_data_unsupported = true;

	memcpy(&cache->features, &ca->features, sizeof(cache->features));

	cache->callbacks.congested_fn = cache_is_congested;
	dm_table_add_target_callbacks(ti->table, &cache->callbacks);

	cache->metadata_dev = ca->metadata_dev;
	cache->origin_dev = ca->origin_dev;
	cache->cache_dev = ca->cache_dev;

	ca->metadata_dev = ca->origin_dev = ca->cache_dev = NULL;

	/* FIXME: factor out this whole section */
	origin_blocks = cache->origin_sectors = ca->origin_sectors;
	origin_blocks = block_div(origin_blocks, ca->block_size);
	cache->origin_blocks = to_oblock(origin_blocks);

	cache->sectors_per_block = ca->block_size;
	if (dm_set_target_max_io_len(ti, cache->sectors_per_block)) {
		r = -EINVAL;
		goto bad;
	}

	if (ca->block_size & (ca->block_size - 1)) {
		dm_block_t cache_size = ca->cache_sectors;

		cache->sectors_per_block_shift = -1;
		cache_size = block_div(cache_size, ca->block_size);
		cache->cache_size = to_cblock(cache_size);
	} else {
		cache->sectors_per_block_shift = __ffs(ca->block_size);
		cache->cache_size = to_cblock(ca->cache_sectors >> cache->sectors_per_block_shift);
	}

	r = create_cache_policy(cache, ca, error);
	if (r)
		goto bad;
	cache->policy_nr_args = ca->policy_argc;

	cmd = dm_cache_metadata_open(cache->metadata_dev->bdev,
				     ca->block_size, may_format,
				     dm_cache_policy_get_hint_size(cache->policy));
	if (IS_ERR(cmd)) {
		*error = "Error creating metadata object";
		r = PTR_ERR(cmd);
		goto bad;
	}
	cache->cmd = cmd;

	spin_lock_init(&cache->lock);
	bio_list_init(&cache->deferred_bios);
	bio_list_init(&cache->deferred_flush_bios);
	bio_list_init(&cache->deferred_writethrough_bios);
	INIT_LIST_HEAD(&cache->quiesced_migrations);
	INIT_LIST_HEAD(&cache->completed_migrations);
	INIT_LIST_HEAD(&cache->need_commit_migrations);
	cache->migration_threshold = DEFAULT_MIGRATION_THRESHOLD;
	atomic_set(&cache->nr_migrations, 0);
	init_waitqueue_head(&cache->migration_wait);

	cache->nr_dirty = 0;
	cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
	if (!cache->dirty_bitset) {
		*error = "could not allocate dirty bitset";
		goto bad;
	}
	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));

	cache->discard_block_size =
		calculate_discard_block_size(cache->sectors_per_block,
					     cache->origin_sectors);
	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
	if (!cache->discard_bitset) {
		*error = "could not allocate discard bitset";
		goto bad;
	}
	clear_bitset(cache->discard_bitset, from_dblock(cache->discard_nr_blocks));

	cache->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle);
	if (IS_ERR(cache->copier)) {
		*error = "could not create kcopyd client";
		r = PTR_ERR(cache->copier);
		goto bad;
	}

	cache->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM);
	if (!cache->wq) {
		*error = "could not create workqueue for metadata object";
		goto bad;
	}
	INIT_WORK(&cache->worker, do_worker);
	INIT_DELAYED_WORK(&cache->waker, do_waker);
	cache->last_commit_jiffies = jiffies;

	cache->prison = dm_bio_prison_create(PRISON_CELLS);
	if (!cache->prison) {
		*error = "could not create bio prison";
		goto bad;
	}

	cache->all_io_ds = dm_deferred_set_create();
	if (!cache->all_io_ds) {
		*error = "could not create all_io deferred set";
		goto bad;
	}

	cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE,
							 migration_cache);
	if (!cache->migration_pool) {
		*error = "Error creating cache's migration mempool";
		goto bad;
	}

	cache->next_migration = NULL;

	cache->need_tick_bio = true;
	cache->sized = false;
	cache->quiescing = false;
	cache->commit_requested = false;
	cache->loaded_mappings = false;
	cache->loaded_discards = false;

	load_stats(cache);

	atomic_set(&cache->stats.demotion, 0);
	atomic_set(&cache->stats.promotion, 0);
	atomic_set(&cache->stats.copies_avoided, 0);
	atomic_set(&cache->stats.cache_cell_clash, 0);
	atomic_set(&cache->stats.commit_count, 0);
	atomic_set(&cache->stats.discard_count, 0);

	*result = cache;
	return 0;

bad:
	destroy(cache);
	return r;
}

static int copy_ctr_args(struct cache *cache, int argc, const char **argv)
{
	unsigned i;
	const char **copy;

	copy = kcalloc(argc, sizeof(*copy), GFP_KERNEL);
	if (!copy)
		return -ENOMEM;
	for (i = 0; i < argc; i++) {
		copy[i] = kstrdup(argv[i], GFP_KERNEL);
		if (!copy[i]) {
			while (i--)
				kfree(copy[i]);
			kfree(copy);
			return -ENOMEM;
		}
	}

	cache->nr_ctr_args = argc;
	cache->ctr_args = copy;

	return 0;
}

static int cache_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
	int r = -EINVAL;
	struct cache_args *ca;
	struct cache *cache = NULL;

	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
	if (!ca) {
		ti->error = "Error allocating memory for cache";
		return -ENOMEM;
	}
	ca->ti = ti;

	r = parse_cache_args(ca, argc, argv, &ti->error);
	if (r)
		goto out;

	r = cache_create(ca, &cache);
	if (r)
		goto out;

	r = copy_ctr_args(cache, argc - 3, (const char **)argv + 3);
	if (r) {
		destroy(cache);
		goto out;
	}

	ti->private = cache;

out:
	destroy_cache_args(ca);
	return r;
}

static int cache_map(struct dm_target *ti, struct bio *bio)
{
	struct cache *cache = ti->private;

	int r;
	dm_oblock_t block = get_bio_block(cache, bio);
	bool can_migrate = false;
	bool discarded_block;
	struct dm_bio_prison_cell *cell;
	struct policy_result lookup_result;
	struct per_bio_data *pb;

	if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
		/*
		 * This can only occur if the io goes to a partial block at
		 * the end of the origin device.  We don't cache these.
		 * Just remap to the origin and carry on.
		 */
		remap_to_origin_clear_discard(cache, bio, block);
		return DM_MAPIO_REMAPPED;
	}

	pb = init_per_bio_data(bio);

	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
		defer_bio(cache, bio);
		return DM_MAPIO_SUBMITTED;
	}

	/*
	 * Check to see if that block is currently migrating.
	 */
	cell = alloc_prison_cell(cache);
	if (!cell) {
		defer_bio(cache, bio);
		return DM_MAPIO_SUBMITTED;
	}

	r = bio_detain(cache, block, bio, cell,
		       (cell_free_fn) free_prison_cell,
		       cache, &cell);
	if (r) {
		if (r < 0)
			defer_bio(cache, bio);

		return DM_MAPIO_SUBMITTED;
	}

	discarded_block = is_discarded_oblock(cache, block);

	r = policy_map(cache->policy, block, false, can_migrate, discarded_block,
		       bio, &lookup_result);
	if (r == -EWOULDBLOCK) {
		cell_defer(cache, cell, true);
		return DM_MAPIO_SUBMITTED;

	} else if (r) {
		DMERR_LIMIT("Unexpected return from cache replacement policy: %d", r);
		bio_io_error(bio);
		return DM_MAPIO_SUBMITTED;
	}

	switch (lookup_result.op) {
	case POLICY_HIT:
		inc_hit_counter(cache, bio);
		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);

		if (is_writethrough_io(cache, bio, lookup_result.cblock))
			remap_to_origin_then_cache(cache, bio, block, lookup_result.cblock);
		else
			remap_to_cache_dirty(cache, bio, block, lookup_result.cblock);

		cell_defer(cache, cell, false);
		break;

	case POLICY_MISS:
		inc_miss_counter(cache, bio);
		pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);

		if (pb->req_nr != 0) {
			/*
			 * This is a duplicate writethrough io that is no
			 * longer needed because the block has been demoted.
			 */
			bio_endio(bio, 0);
			cell_defer(cache, cell, false);
			return DM_MAPIO_SUBMITTED;
		} else {
			remap_to_origin_clear_discard(cache, bio, block);
			cell_defer(cache, cell, false);
		}
		break;

	default:
		DMERR_LIMIT("%s: erroring bio: unknown policy op: %u", __func__,
			    (unsigned) lookup_result.op);
		bio_io_error(bio);
		return DM_MAPIO_SUBMITTED;
	}

	return DM_MAPIO_REMAPPED;
}

static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
{
	struct cache *cache = ti->private;
	unsigned long flags;
	struct per_bio_data *pb = get_per_bio_data(bio);

	if (pb->tick) {
		policy_tick(cache->policy);

		spin_lock_irqsave(&cache->lock, flags);
		cache->need_tick_bio = true;
		spin_unlock_irqrestore(&cache->lock, flags);
	}

	check_for_quiesced_migrations(cache, pb);

	return 0;
}

static int write_dirty_bitset(struct cache *cache)
{
	unsigned i, r;

	for (i = 0; i < from_cblock(cache->cache_size); i++) {
		r = dm_cache_set_dirty(cache->cmd, to_cblock(i),
				       is_dirty(cache, to_cblock(i)));
		if (r)
			return r;
	}

	return 0;
}

static int write_discard_bitset(struct cache *cache)
{
	unsigned i, r;

	r = dm_cache_discard_bitset_resize(cache->cmd, cache->discard_block_size,
					   cache->discard_nr_blocks);
	if (r) {
		DMERR("could not resize on-disk discard bitset");
		return r;
	}

	for (i = 0; i < from_dblock(cache->discard_nr_blocks); i++) {
		r = dm_cache_set_discard(cache->cmd, to_dblock(i),
					 is_discarded(cache, to_dblock(i)));
		if (r)
			return r;
	}

	return 0;
}

static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock,
		     uint32_t hint)
{
	struct cache *cache = context;
	return dm_cache_save_hint(cache->cmd, cblock, hint);
}

static int write_hints(struct cache *cache)
{
	int r;

	r = dm_cache_begin_hints(cache->cmd, cache->policy);
	if (r) {
		DMERR("dm_cache_begin_hints failed");
		return r;
	}

	r = policy_walk_mappings(cache->policy, save_hint, cache);
	if (r)
		DMERR("policy_walk_mappings failed");

	return r;
}

/*
 * returns true on success
 */
static bool sync_metadata(struct cache *cache)
{
	int r1, r2, r3, r4;

	r1 = write_dirty_bitset(cache);
	if (r1)
		DMERR("could not write dirty bitset");

	r2 = write_discard_bitset(cache);
	if (r2)
		DMERR("could not write discard bitset");

	save_stats(cache);

	r3 = write_hints(cache);
	if (r3)
		DMERR("could not write hints");

	/*
	 * If writing the above metadata failed, we still commit, but don't
	 * set the clean shutdown flag.  This will effectively force every
	 * dirty bit to be set on reload.
	 */
	r4 = dm_cache_commit(cache->cmd, !r1 && !r2 && !r3);
	if (r4)
		DMERR("could not write cache metadata.  Data loss may occur.");

	return !r1 && !r2 && !r3 && !r4;
}

static void cache_postsuspend(struct dm_target *ti)
{
	struct cache *cache = ti->private;

	start_quiescing(cache);
	wait_for_migrations(cache);
	stop_worker(cache);
	requeue_deferred_io(cache);
	stop_quiescing(cache);

	(void) sync_metadata(cache);
}

static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
			bool dirty, uint32_t hint, bool hint_valid)
{
	int r;
	struct cache *cache = context;

	r = policy_load_mapping(cache->policy, oblock, cblock, hint, hint_valid);
	if (r)
		return r;

	if (dirty)
		set_dirty(cache, oblock, cblock);
	else
		clear_dirty(cache, oblock, cblock);

	return 0;
}

static int load_discard(void *context, sector_t discard_block_size,
			dm_dblock_t dblock, bool discard)
{
	struct cache *cache = context;

	/* FIXME: handle mis-matched block size */

	if (discard)
		set_discard(cache, dblock);
	else
		clear_discard(cache, dblock);

	return 0;
}

static int cache_preresume(struct dm_target *ti)
{
	int r = 0;
	struct cache *cache = ti->private;
	sector_t actual_cache_size = get_dev_size(cache->cache_dev);
	(void) sector_div(actual_cache_size, cache->sectors_per_block);

	/*
	 * Check to see if the cache has resized.
	 */
	if (from_cblock(cache->cache_size) != actual_cache_size || !cache->sized) {
		cache->cache_size = to_cblock(actual_cache_size);

		r = dm_cache_resize(cache->cmd, cache->cache_size);
		if (r) {
			DMERR("could not resize cache metadata");
			return r;
		}

		cache->sized = true;
	}

	if (!cache->loaded_mappings) {
		r = dm_cache_load_mappings(cache->cmd, cache->policy,
					   load_mapping, cache);
		if (r) {
			DMERR("could not load cache mappings");
			return r;
		}

		cache->loaded_mappings = true;
	}

	if (!cache->loaded_discards) {
		r = dm_cache_load_discards(cache->cmd, load_discard, cache);
		if (r) {
			DMERR("could not load origin discards");
			return r;
		}

		cache->loaded_discards = true;
	}

	return r;
}

static void cache_resume(struct dm_target *ti)
{
	struct cache *cache = ti->private;

	cache->need_tick_bio = true;
	do_waker(&cache->waker.work);
}

/*
 * Status format:
 *
 * <#used metadata blocks>/<#total metadata blocks>
 * <#read hits> <#read misses> <#write hits> <#write misses>
 * <#demotions> <#promotions> <#blocks in cache> <#dirty>
 * <#features> <features>*
 * <#core args> <core args>
 * <#policy args> <policy args>*
 */
static void cache_status(struct dm_target *ti, status_type_t type,
			 unsigned status_flags, char *result, unsigned maxlen)
{
	int r = 0;
	unsigned i;
	ssize_t sz = 0;
	dm_block_t nr_free_blocks_metadata = 0;
	dm_block_t nr_blocks_metadata = 0;
	char buf[BDEVNAME_SIZE];
	struct cache *cache = ti->private;
	dm_cblock_t residency;

	switch (type) {
	case STATUSTYPE_INFO:
		/* Commit to ensure statistics aren't out-of-date */
		if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) {
			r = dm_cache_commit(cache->cmd, false);
			if (r)
				DMERR("could not commit metadata for accurate status");
		}

		r = dm_cache_get_free_metadata_block_count(cache->cmd,
							   &nr_free_blocks_metadata);
		if (r) {
			DMERR("could not get metadata free block count");
			goto err;
		}

		r = dm_cache_get_metadata_dev_size(cache->cmd, &nr_blocks_metadata);
		if (r) {
			DMERR("could not get metadata device size");
			goto err;
		}

		residency = policy_residency(cache->policy);

		DMEMIT("%llu/%llu %u %u %u %u %u %u %llu %u ",
		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
		       (unsigned long long)nr_blocks_metadata,
		       (unsigned) atomic_read(&cache->stats.read_hit),
		       (unsigned) atomic_read(&cache->stats.read_miss),
		       (unsigned) atomic_read(&cache->stats.write_hit),
		       (unsigned) atomic_read(&cache->stats.write_miss),
		       (unsigned) atomic_read(&cache->stats.demotion),
		       (unsigned) atomic_read(&cache->stats.promotion),
		       (unsigned long long) from_cblock(residency),
		       cache->nr_dirty);

		if (cache->features.write_through)
			DMEMIT("1 writethrough ");
		else
			DMEMIT("0 ");

		DMEMIT("2 migration_threshold %llu ", (unsigned long long) cache->migration_threshold);
		if (sz < maxlen) {
			r = policy_emit_config_values(cache->policy, result + sz, maxlen - sz);
			if (r)
				DMERR("policy_emit_config_values returned %d", r);
		}

		break;

	case STATUSTYPE_TABLE:
		format_dev_t(buf, cache->metadata_dev->bdev->bd_dev);
		DMEMIT("%s ", buf);
		format_dev_t(buf, cache->cache_dev->bdev->bd_dev);
		DMEMIT("%s ", buf);
		format_dev_t(buf, cache->origin_dev->bdev->bd_dev);
		DMEMIT("%s", buf);

		for (i = 0; i < cache->nr_ctr_args - 1; i++)
			DMEMIT(" %s", cache->ctr_args[i]);
		if (cache->nr_ctr_args)
			DMEMIT(" %s", cache->ctr_args[cache->nr_ctr_args - 1]);
	}

	return;

err:
	DMEMIT("Error");
}

#define NOT_CORE_OPTION 1

static int process_config_option(struct cache *cache, char **argv)
{
	unsigned long tmp;

	if (!strcasecmp(argv[0], "migration_threshold")) {
		if (kstrtoul(argv[1], 10, &tmp))
			return -EINVAL;

		cache->migration_threshold = tmp;
		return 0;
	}

	return NOT_CORE_OPTION;
}

/*
 * Supports <key> <value>.
 *
 * The key migration_threshold is supported by the cache target core.
 */
static int cache_message(struct dm_target *ti, unsigned argc, char **argv)
{
	int r;
	struct cache *cache = ti->private;

	if (argc != 2)
		return -EINVAL;

	r = process_config_option(cache, argv);
	if (r == NOT_CORE_OPTION)
		return policy_set_config_value(cache->policy, argv[0], argv[1]);

	return r;
}

static int cache_iterate_devices(struct dm_target *ti,
				 iterate_devices_callout_fn fn, void *data)
{
	int r = 0;
	struct cache *cache = ti->private;

	r = fn(ti, cache->cache_dev, 0, get_dev_size(cache->cache_dev), data);
	if (!r)
		r = fn(ti, cache->origin_dev, 0, ti->len, data);

	return r;
}

/*
 * We assume I/O is going to the origin (which is the volume
 * more likely to have restrictions e.g. by being striped).
 * (Looking up the exact location of the data would be expensive
 * and could always be out of date by the time the bio is submitted.)
 */
static int cache_bvec_merge(struct dm_target *ti,
			    struct bvec_merge_data *bvm,
			    struct bio_vec *biovec, int max_size)
{
	struct cache *cache = ti->private;
	struct request_queue *q = bdev_get_queue(cache->origin_dev->bdev);

	if (!q->merge_bvec_fn)
		return max_size;

	bvm->bi_bdev = cache->origin_dev->bdev;
	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
}

static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
{
	/*
	 * FIXME: these limits may be incompatible with the cache device
	 */
	limits->max_discard_sectors = cache->discard_block_size * 1024;
	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
}

static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
	struct cache *cache = ti->private;

	blk_limits_io_min(limits, 0);
	blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT);
	set_discard_limits(cache, limits);
}

/*----------------------------------------------------------------*/

static struct target_type cache_target = {
	.name = "cache",
	.version = {1, 1, 0},
	.module = THIS_MODULE,
	.ctr = cache_ctr,
	.dtr = cache_dtr,
	.map = cache_map,
	.end_io = cache_end_io,
	.postsuspend = cache_postsuspend,
	.preresume = cache_preresume,
	.resume = cache_resume,
	.status = cache_status,
	.message = cache_message,
	.iterate_devices = cache_iterate_devices,
	.merge = cache_bvec_merge,
	.io_hints = cache_io_hints,
};

static int __init dm_cache_init(void)
{
	int r;

	r = dm_register_target(&cache_target);
	if (r) {
		DMERR("cache target registration failed: %d", r);
		return r;
	}

	migration_cache = KMEM_CACHE(dm_cache_migration, 0);
	if (!migration_cache) {
		dm_unregister_target(&cache_target);
		return -ENOMEM;
	}

	return 0;
}

static void __exit dm_cache_exit(void)
{
	dm_unregister_target(&cache_target);
	kmem_cache_destroy(migration_cache);
}

module_init(dm_cache_init);
module_exit(dm_cache_exit);

MODULE_DESCRIPTION(DM_NAME " cache target");
MODULE_AUTHOR("Joe Thornber <ejt@redhat.com>");
MODULE_LICENSE("GPL");