aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md/dm.c
blob: 530c0fe1422910ed7df052f44f8a97f4139b5872 (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
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
/*
 * Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
 * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm-core.h"
#include "dm-rq.h"
#include "dm-uevent.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/mempool.h>
#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/uio.h>
#include <linux/hdreg.h>
#include <linux/delay.h>
#include <linux/wait.h>
#include <linux/pr.h>
#include <linux/refcount.h>

#define DM_MSG_PREFIX "core"

/*
 * Cookies are numeric values sent with CHANGE and REMOVE
 * uevents while resuming, removing or renaming the device.
 */
#define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE"
#define DM_COOKIE_LENGTH 24

static const char *_name = DM_NAME;

static unsigned int major = 0;
static unsigned int _major = 0;

static DEFINE_IDR(_minor_idr);

static DEFINE_SPINLOCK(_minor_lock);

static void do_deferred_remove(struct work_struct *w);

static DECLARE_WORK(deferred_remove_work, do_deferred_remove);

static struct workqueue_struct *deferred_remove_workqueue;

atomic_t dm_global_event_nr = ATOMIC_INIT(0);
DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq);

void dm_issue_global_event(void)
{
	atomic_inc(&dm_global_event_nr);
	wake_up(&dm_global_eventq);
}

/*
 * One of these is allocated (on-stack) per original bio.
 */
struct clone_info {
	struct dm_table *map;
	struct bio *bio;
	struct dm_io *io;
	sector_t sector;
	unsigned sector_count;
};

/*
 * One of these is allocated per clone bio.
 */
#define DM_TIO_MAGIC 7282014
struct dm_target_io {
	unsigned magic;
	struct dm_io *io;
	struct dm_target *ti;
	unsigned target_bio_nr;
	unsigned *len_ptr;
	bool inside_dm_io;
	struct bio clone;
};

/*
 * One of these is allocated per original bio.
 * It contains the first clone used for that original.
 */
#define DM_IO_MAGIC 5191977
struct dm_io {
	unsigned magic;
	struct mapped_device *md;
	blk_status_t status;
	atomic_t io_count;
	struct bio *orig_bio;
	unsigned long start_time;
	spinlock_t endio_lock;
	struct dm_stats_aux stats_aux;
	/* last member of dm_target_io is 'struct bio' */
	struct dm_target_io tio;
};

void *dm_per_bio_data(struct bio *bio, size_t data_size)
{
	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
	if (!tio->inside_dm_io)
		return (char *)bio - offsetof(struct dm_target_io, clone) - data_size;
	return (char *)bio - offsetof(struct dm_target_io, clone) - offsetof(struct dm_io, tio) - data_size;
}
EXPORT_SYMBOL_GPL(dm_per_bio_data);

struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
{
	struct dm_io *io = (struct dm_io *)((char *)data + data_size);
	if (io->magic == DM_IO_MAGIC)
		return (struct bio *)((char *)io + offsetof(struct dm_io, tio) + offsetof(struct dm_target_io, clone));
	BUG_ON(io->magic != DM_TIO_MAGIC);
	return (struct bio *)((char *)io + offsetof(struct dm_target_io, clone));
}
EXPORT_SYMBOL_GPL(dm_bio_from_per_bio_data);

unsigned dm_bio_get_target_bio_nr(const struct bio *bio)
{
	return container_of(bio, struct dm_target_io, clone)->target_bio_nr;
}
EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);

#define MINOR_ALLOCED ((void *)-1)

/*
 * Bits for the md->flags field.
 */
#define DMF_BLOCK_IO_FOR_SUSPEND 0
#define DMF_SUSPENDED 1
#define DMF_FROZEN 2
#define DMF_FREEING 3
#define DMF_DELETING 4
#define DMF_NOFLUSH_SUSPENDING 5
#define DMF_DEFERRED_REMOVE 6
#define DMF_SUSPENDED_INTERNALLY 7
#define DMF_POST_SUSPENDING 8

#define DM_NUMA_NODE NUMA_NO_NODE
static int dm_numa_node = DM_NUMA_NODE;

#define DEFAULT_SWAP_BIOS	(8 * 1048576 / PAGE_SIZE)
static int swap_bios = DEFAULT_SWAP_BIOS;
static int get_swap_bios(void)
{
	int latch = READ_ONCE(swap_bios);
	if (unlikely(latch <= 0))
		latch = DEFAULT_SWAP_BIOS;
	return latch;
}

/*
 * For mempools pre-allocation at the table loading time.
 */
struct dm_md_mempools {
	struct bio_set bs;
	struct bio_set io_bs;
};

struct table_device {
	struct list_head list;
	refcount_t count;
	struct dm_dev dm_dev;
};

/*
 * Bio-based DM's mempools' reserved IOs set by the user.
 */
#define RESERVED_BIO_BASED_IOS		16
static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;

static int __dm_get_module_param_int(int *module_param, int min, int max)
{
	int param = READ_ONCE(*module_param);
	int modified_param = 0;
	bool modified = true;

	if (param < min)
		modified_param = min;
	else if (param > max)
		modified_param = max;
	else
		modified = false;

	if (modified) {
		(void)cmpxchg(module_param, param, modified_param);
		param = modified_param;
	}

	return param;
}

unsigned __dm_get_module_param(unsigned *module_param,
			       unsigned def, unsigned max)
{
	unsigned param = READ_ONCE(*module_param);
	unsigned modified_param = 0;

	if (!param)
		modified_param = def;
	else if (param > max)
		modified_param = max;

	if (modified_param) {
		(void)cmpxchg(module_param, param, modified_param);
		param = modified_param;
	}

	return param;
}

unsigned dm_get_reserved_bio_based_ios(void)
{
	return __dm_get_module_param(&reserved_bio_based_ios,
				     RESERVED_BIO_BASED_IOS, DM_RESERVED_MAX_IOS);
}
EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);

static unsigned dm_get_numa_node(void)
{
	return __dm_get_module_param_int(&dm_numa_node,
					 DM_NUMA_NODE, num_online_nodes() - 1);
}

static int __init local_init(void)
{
	int r;

	r = dm_uevent_init();
	if (r)
		return r;

	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
	if (!deferred_remove_workqueue) {
		r = -ENOMEM;
		goto out_uevent_exit;
	}

	_major = major;
	r = register_blkdev(_major, _name);
	if (r < 0)
		goto out_free_workqueue;

	if (!_major)
		_major = r;

	return 0;

out_free_workqueue:
	destroy_workqueue(deferred_remove_workqueue);
out_uevent_exit:
	dm_uevent_exit();

	return r;
}

static void local_exit(void)
{
	flush_scheduled_work();
	destroy_workqueue(deferred_remove_workqueue);

	unregister_blkdev(_major, _name);
	dm_uevent_exit();

	_major = 0;

	DMINFO("cleaned up");
}

static int (*_inits[])(void) __initdata = {
	local_init,
	dm_target_init,
	dm_linear_init,
	dm_stripe_init,
	dm_io_init,
	dm_kcopyd_init,
	dm_interface_init,
	dm_statistics_init,
};

static void (*_exits[])(void) = {
	local_exit,
	dm_target_exit,
	dm_linear_exit,
	dm_stripe_exit,
	dm_io_exit,
	dm_kcopyd_exit,
	dm_interface_exit,
	dm_statistics_exit,
};

static int __init dm_init(void)
{
	const int count = ARRAY_SIZE(_inits);

	int r, i;

	for (i = 0; i < count; i++) {
		r = _inits[i]();
		if (r)
			goto bad;
	}

	return 0;

      bad:
	while (i--)
		_exits[i]();

	return r;
}

static void __exit dm_exit(void)
{
	int i = ARRAY_SIZE(_exits);

	while (i--)
		_exits[i]();

	/*
	 * Should be empty by this point.
	 */
	idr_destroy(&_minor_idr);
}

/*
 * Block device functions
 */
int dm_deleting_md(struct mapped_device *md)
{
	return test_bit(DMF_DELETING, &md->flags);
}

static int dm_blk_open(struct block_device *bdev, fmode_t mode)
{
	struct mapped_device *md;

	spin_lock(&_minor_lock);

	md = bdev->bd_disk->private_data;
	if (!md)
		goto out;

	if (test_bit(DMF_FREEING, &md->flags) ||
	    dm_deleting_md(md)) {
		md = NULL;
		goto out;
	}

	dm_get(md);
	atomic_inc(&md->open_count);
out:
	spin_unlock(&_minor_lock);

	return md ? 0 : -ENXIO;
}

static void dm_blk_close(struct gendisk *disk, fmode_t mode)
{
	struct mapped_device *md;

	spin_lock(&_minor_lock);

	md = disk->private_data;
	if (WARN_ON(!md))
		goto out;

	if (atomic_dec_and_test(&md->open_count) &&
	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
		queue_work(deferred_remove_workqueue, &deferred_remove_work);

	dm_put(md);
out:
	spin_unlock(&_minor_lock);
}

int dm_open_count(struct mapped_device *md)
{
	return atomic_read(&md->open_count);
}

/*
 * Guarantees nothing is using the device before it's deleted.
 */
int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred)
{
	int r = 0;

	spin_lock(&_minor_lock);

	if (dm_open_count(md)) {
		r = -EBUSY;
		if (mark_deferred)
			set_bit(DMF_DEFERRED_REMOVE, &md->flags);
	} else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags))
		r = -EEXIST;
	else
		set_bit(DMF_DELETING, &md->flags);

	spin_unlock(&_minor_lock);

	return r;
}

int dm_cancel_deferred_remove(struct mapped_device *md)
{
	int r = 0;

	spin_lock(&_minor_lock);

	if (test_bit(DMF_DELETING, &md->flags))
		r = -EBUSY;
	else
		clear_bit(DMF_DEFERRED_REMOVE, &md->flags);

	spin_unlock(&_minor_lock);

	return r;
}

static void do_deferred_remove(struct work_struct *w)
{
	dm_deferred_remove();
}

sector_t dm_get_size(struct mapped_device *md)
{
	return get_capacity(md->disk);
}

struct request_queue *dm_get_md_queue(struct mapped_device *md)
{
	return md->queue;
}

struct dm_stats *dm_get_stats(struct mapped_device *md)
{
	return &md->stats;
}

static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	struct mapped_device *md = bdev->bd_disk->private_data;

	return dm_get_geometry(md, geo);
}

static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
			       struct blk_zone *zones, unsigned int *nr_zones)
{
#ifdef CONFIG_BLK_DEV_ZONED
	struct mapped_device *md = disk->private_data;
	struct dm_target *tgt;
	struct dm_table *map;
	int srcu_idx, ret;

	if (dm_suspended_md(md))
		return -EAGAIN;

	map = dm_get_live_table(md, &srcu_idx);
	if (!map) {
		ret = -EIO;
		goto out;
	}

	tgt = dm_table_find_target(map, sector);
	if (!tgt) {
		ret = -EIO;
		goto out;
	}

	/*
	 * If we are executing this, we already know that the block device
	 * is a zoned device and so each target should have support for that
	 * type of drive. A missing report_zones method means that the target
	 * driver has a problem.
	 */
	if (WARN_ON(!tgt->type->report_zones)) {
		ret = -EIO;
		goto out;
	}

	/*
	 * blkdev_report_zones() will loop and call this again to cover all the
	 * zones of the target, eventually moving on to the next target.
	 * So there is no need to loop here trying to fill the entire array
	 * of zones.
	 */
	ret = tgt->type->report_zones(tgt, sector, zones, nr_zones);

out:
	dm_put_live_table(md, srcu_idx);
	return ret;
#else
	return -ENOTSUPP;
#endif
}

static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
			    struct block_device **bdev)
{
	struct dm_target *tgt;
	struct dm_table *map;
	int r;

retry:
	r = -ENOTTY;
	map = dm_get_live_table(md, srcu_idx);
	if (!map || !dm_table_get_size(map))
		return r;

	/* We only support devices that have a single target */
	if (dm_table_get_num_targets(map) != 1)
		return r;

	tgt = dm_table_get_target(map, 0);
	if (!tgt->type->prepare_ioctl)
		return r;

	if (dm_suspended_md(md))
		return -EAGAIN;

	r = tgt->type->prepare_ioctl(tgt, bdev);
	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
		dm_put_live_table(md, *srcu_idx);
		msleep(10);
		goto retry;
	}

	return r;
}

static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx)
{
	dm_put_live_table(md, srcu_idx);
}

static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
			unsigned int cmd, unsigned long arg)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	int r, srcu_idx;

	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
	if (r < 0)
		goto out;

	if (r > 0) {
		/*
		 * Target determined this ioctl is being issued against a
		 * subset of the parent bdev; require extra privileges.
		 */
		if (!capable(CAP_SYS_RAWIO)) {
			DMDEBUG_LIMIT(
	"%s: sending ioctl %x to DM device without required privilege.",
				current->comm, cmd);
			r = -ENOIOCTLCMD;
			goto out;
		}
	}

	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
out:
	dm_unprepare_ioctl(md, srcu_idx);
	return r;
}

static void start_io_acct(struct dm_io *io);

static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
{
	struct dm_io *io;
	struct dm_target_io *tio;
	struct bio *clone;

	clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs);
	if (!clone)
		return NULL;

	tio = container_of(clone, struct dm_target_io, clone);
	tio->inside_dm_io = true;
	tio->io = NULL;

	io = container_of(tio, struct dm_io, tio);
	io->magic = DM_IO_MAGIC;
	io->status = 0;
	atomic_set(&io->io_count, 1);
	io->orig_bio = bio;
	io->md = md;
	spin_lock_init(&io->endio_lock);

	start_io_acct(io);

	return io;
}

static void free_io(struct mapped_device *md, struct dm_io *io)
{
	bio_put(&io->tio.clone);
}

static struct dm_target_io *alloc_tio(struct clone_info *ci, struct dm_target *ti,
				      unsigned target_bio_nr, gfp_t gfp_mask)
{
	struct dm_target_io *tio;

	if (!ci->io->tio.io) {
		/* the dm_target_io embedded in ci->io is available */
		tio = &ci->io->tio;
	} else {
		struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs);
		if (!clone)
			return NULL;

		tio = container_of(clone, struct dm_target_io, clone);
		tio->inside_dm_io = false;
	}

	tio->magic = DM_TIO_MAGIC;
	tio->io = ci->io;
	tio->ti = ti;
	tio->target_bio_nr = target_bio_nr;

	return tio;
}

static void free_tio(struct dm_target_io *tio)
{
	if (tio->inside_dm_io)
		return;
	bio_put(&tio->clone);
}

static bool md_in_flight_bios(struct mapped_device *md)
{
	int cpu;
	struct hd_struct *part = &dm_disk(md)->part0;
	long sum = 0;

	for_each_possible_cpu(cpu) {
		sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
		sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
	}

	return sum != 0;
}

static bool md_in_flight(struct mapped_device *md)
{
	if (queue_is_mq(md->queue))
		return blk_mq_queue_inflight(md->queue);
	else
		return md_in_flight_bios(md);
}

static void start_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;
	struct bio *bio = io->orig_bio;

	io->start_time = jiffies;

	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
			      &dm_disk(md)->part0);

	if (unlikely(dm_stats_used(&md->stats)))
		dm_stats_account_io(&md->stats, bio_data_dir(bio),
				    bio->bi_iter.bi_sector, bio_sectors(bio),
				    false, 0, &io->stats_aux);
}

static void end_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;
	struct bio *bio = io->orig_bio;
	unsigned long duration = jiffies - io->start_time;

	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
			    io->start_time);

	if (unlikely(dm_stats_used(&md->stats)))
		dm_stats_account_io(&md->stats, bio_data_dir(bio),
				    bio->bi_iter.bi_sector, bio_sectors(bio),
				    true, duration, &io->stats_aux);

	/* nudge anyone waiting on suspend queue */
	if (unlikely(wq_has_sleeper(&md->wait)))
		wake_up(&md->wait);
}

/*
 * Add the bio to the list of deferred io.
 */
static void queue_io(struct mapped_device *md, struct bio *bio)
{
	unsigned long flags;

	spin_lock_irqsave(&md->deferred_lock, flags);
	bio_list_add(&md->deferred, bio);
	spin_unlock_irqrestore(&md->deferred_lock, flags);
	queue_work(md->wq, &md->work);
}

/*
 * Everyone (including functions in this file), should use this
 * function to access the md->map field, and make sure they call
 * dm_put_live_table() when finished.
 */
struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx) __acquires(md->io_barrier)
{
	*srcu_idx = srcu_read_lock(&md->io_barrier);

	return srcu_dereference(md->map, &md->io_barrier);
}

void dm_put_live_table(struct mapped_device *md, int srcu_idx) __releases(md->io_barrier)
{
	srcu_read_unlock(&md->io_barrier, srcu_idx);
}

void dm_sync_table(struct mapped_device *md)
{
	synchronize_srcu(&md->io_barrier);
	synchronize_rcu_expedited();
}

/*
 * A fast alternative to dm_get_live_table/dm_put_live_table.
 * The caller must not block between these two functions.
 */
static struct dm_table *dm_get_live_table_fast(struct mapped_device *md) __acquires(RCU)
{
	rcu_read_lock();
	return rcu_dereference(md->map);
}

static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
{
	rcu_read_unlock();
}

static char *_dm_claim_ptr = "I belong to device-mapper";

/*
 * Open a table device so we can use it as a map destination.
 */
static int open_table_device(struct table_device *td, dev_t dev,
			     struct mapped_device *md)
{
	struct block_device *bdev;

	int r;

	BUG_ON(td->dm_dev.bdev);

	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);

	r = bd_link_disk_holder(bdev, dm_disk(md));
	if (r) {
		blkdev_put(bdev, td->dm_dev.mode | FMODE_EXCL);
		return r;
	}

	td->dm_dev.bdev = bdev;
	td->dm_dev.dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
	return 0;
}

/*
 * Close a table device that we've been using.
 */
static void close_table_device(struct table_device *td, struct mapped_device *md)
{
	if (!td->dm_dev.bdev)
		return;

	bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md));
	blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
	put_dax(td->dm_dev.dax_dev);
	td->dm_dev.bdev = NULL;
	td->dm_dev.dax_dev = NULL;
}

static struct table_device *find_table_device(struct list_head *l, dev_t dev,
					      fmode_t mode)
{
	struct table_device *td;

	list_for_each_entry(td, l, list)
		if (td->dm_dev.bdev->bd_dev == dev && td->dm_dev.mode == mode)
			return td;

	return NULL;
}

int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
			struct dm_dev **result)
{
	int r;
	struct table_device *td;

	mutex_lock(&md->table_devices_lock);
	td = find_table_device(&md->table_devices, dev, mode);
	if (!td) {
		td = kmalloc_node(sizeof(*td), GFP_KERNEL, md->numa_node_id);
		if (!td) {
			mutex_unlock(&md->table_devices_lock);
			return -ENOMEM;
		}

		td->dm_dev.mode = mode;
		td->dm_dev.bdev = NULL;

		if ((r = open_table_device(td, dev, md))) {
			mutex_unlock(&md->table_devices_lock);
			kfree(td);
			return r;
		}

		format_dev_t(td->dm_dev.name, dev);

		refcount_set(&td->count, 1);
		list_add(&td->list, &md->table_devices);
	} else {
		refcount_inc(&td->count);
	}
	mutex_unlock(&md->table_devices_lock);

	*result = &td->dm_dev;
	return 0;
}
EXPORT_SYMBOL_GPL(dm_get_table_device);

void dm_put_table_device(struct mapped_device *md, struct dm_dev *d)
{
	struct table_device *td = container_of(d, struct table_device, dm_dev);

	mutex_lock(&md->table_devices_lock);
	if (refcount_dec_and_test(&td->count)) {
		close_table_device(td, md);
		list_del(&td->list);
		kfree(td);
	}
	mutex_unlock(&md->table_devices_lock);
}
EXPORT_SYMBOL(dm_put_table_device);

static void free_table_devices(struct list_head *devices)
{
	struct list_head *tmp, *next;

	list_for_each_safe(tmp, next, devices) {
		struct table_device *td = list_entry(tmp, struct table_device, list);

		DMWARN("dm_destroy: %s still exists with %d references",
		       td->dm_dev.name, refcount_read(&td->count));
		kfree(td);
	}
}

/*
 * Get the geometry associated with a dm device
 */
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	*geo = md->geometry;

	return 0;
}

/*
 * Set the geometry of a device.
 */
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	sector_t sz = (sector_t)geo->cylinders * geo->heads * geo->sectors;

	if (geo->start > sz) {
		DMWARN("Start sector is beyond the geometry limits.");
		return -EINVAL;
	}

	md->geometry = *geo;

	return 0;
}

static int __noflush_suspending(struct mapped_device *md)
{
	return test_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
}

/*
 * Decrements the number of outstanding ios that a bio has been
 * cloned into, completing the original io if necc.
 */
static void dec_pending(struct dm_io *io, blk_status_t error)
{
	unsigned long flags;
	blk_status_t io_error;
	struct bio *bio;
	struct mapped_device *md = io->md;

	/* Push-back supersedes any I/O errors */
	if (unlikely(error)) {
		spin_lock_irqsave(&io->endio_lock, flags);
		if (!(io->status == BLK_STS_DM_REQUEUE && __noflush_suspending(md)))
			io->status = error;
		spin_unlock_irqrestore(&io->endio_lock, flags);
	}

	if (atomic_dec_and_test(&io->io_count)) {
		if (io->status == BLK_STS_DM_REQUEUE) {
			/*
			 * Target requested pushing back the I/O.
			 */
			spin_lock_irqsave(&md->deferred_lock, flags);
			if (__noflush_suspending(md))
				/* NOTE early return due to BLK_STS_DM_REQUEUE below */
				bio_list_add_head(&md->deferred, io->orig_bio);
			else
				/* noflush suspend was interrupted. */
				io->status = BLK_STS_IOERR;
			spin_unlock_irqrestore(&md->deferred_lock, flags);
		}

		io_error = io->status;
		bio = io->orig_bio;
		end_io_acct(io);
		free_io(md, io);

		if (io_error == BLK_STS_DM_REQUEUE)
			return;

		if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) {
			/*
			 * Preflush done for flush with data, reissue
			 * without REQ_PREFLUSH.
			 */
			bio->bi_opf &= ~REQ_PREFLUSH;
			queue_io(md, bio);
		} else {
			/* done with normal IO or empty flush */
			if (io_error)
				bio->bi_status = io_error;
			bio_endio(bio);
		}
	}
}

void disable_discard(struct mapped_device *md)
{
	struct queue_limits *limits = dm_get_queue_limits(md);

	/* device doesn't really support DISCARD, disable it */
	limits->max_discard_sectors = 0;
	blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue);
}

void disable_write_same(struct mapped_device *md)
{
	struct queue_limits *limits = dm_get_queue_limits(md);

	/* device doesn't really support WRITE SAME, disable it */
	limits->max_write_same_sectors = 0;
}

void disable_write_zeroes(struct mapped_device *md)
{
	struct queue_limits *limits = dm_get_queue_limits(md);

	/* device doesn't really support WRITE ZEROES, disable it */
	limits->max_write_zeroes_sectors = 0;
}

static bool swap_bios_limit(struct dm_target *ti, struct bio *bio)
{
	return unlikely((bio->bi_opf & REQ_SWAP) != 0) && unlikely(ti->limit_swap_bios);
}

static void clone_endio(struct bio *bio)
{
	blk_status_t error = bio->bi_status;
	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
	struct dm_io *io = tio->io;
	struct mapped_device *md = tio->io->md;
	dm_endio_fn endio = tio->ti->type->end_io;

	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
		if (bio_op(bio) == REQ_OP_DISCARD &&
		    !bio->bi_disk->queue->limits.max_discard_sectors)
			disable_discard(md);
		else if (bio_op(bio) == REQ_OP_WRITE_SAME &&
			 !bio->bi_disk->queue->limits.max_write_same_sectors)
			disable_write_same(md);
		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
			 !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
			disable_write_zeroes(md);
	}

	if (endio) {
		int r = endio(tio->ti, bio, &error);
		switch (r) {
		case DM_ENDIO_REQUEUE:
			error = BLK_STS_DM_REQUEUE;
			/*FALLTHRU*/
		case DM_ENDIO_DONE:
			break;
		case DM_ENDIO_INCOMPLETE:
			/* The target will handle the io */
			return;
		default:
			DMWARN("unimplemented target endio return value: %d", r);
			BUG();
		}
	}

	if (unlikely(swap_bios_limit(tio->ti, bio))) {
		struct mapped_device *md = io->md;
		up(&md->swap_bios_semaphore);
	}

	free_tio(tio);
	dec_pending(io, error);
}

/*
 * Return maximum size of I/O possible at the supplied sector up to the current
 * target boundary.
 */
static sector_t max_io_len_target_boundary(sector_t sector, struct dm_target *ti)
{
	sector_t target_offset = dm_target_offset(ti, sector);

	return ti->len - target_offset;
}

static sector_t max_io_len(sector_t sector, struct dm_target *ti)
{
	sector_t len = max_io_len_target_boundary(sector, ti);
	sector_t offset, max_len;

	/*
	 * Does the target need to split even further?
	 */
	if (ti->max_io_len) {
		offset = dm_target_offset(ti, sector);
		if (unlikely(ti->max_io_len & (ti->max_io_len - 1)))
			max_len = sector_div(offset, ti->max_io_len);
		else
			max_len = offset & (ti->max_io_len - 1);
		max_len = ti->max_io_len - max_len;

		if (len > max_len)
			len = max_len;
	}

	return len;
}

int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
{
	if (len > UINT_MAX) {
		DMERR("Specified maximum size of target IO (%llu) exceeds limit (%u)",
		      (unsigned long long)len, UINT_MAX);
		ti->error = "Maximum size of target IO is too large";
		return -EINVAL;
	}

	ti->max_io_len = (uint32_t) len;

	return 0;
}
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);

static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
						sector_t sector, int *srcu_idx)
	__acquires(md->io_barrier)
{
	struct dm_table *map;
	struct dm_target *ti;

	map = dm_get_live_table(md, srcu_idx);
	if (!map)
		return NULL;

	ti = dm_table_find_target(map, sector);
	if (!ti)
		return NULL;

	return ti;
}

static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
				 long nr_pages, void **kaddr, pfn_t *pfn)
{
	struct mapped_device *md = dax_get_private(dax_dev);
	sector_t sector = pgoff * PAGE_SECTORS;
	struct dm_target *ti;
	long len, ret = -EIO;
	int srcu_idx;

	ti = dm_dax_get_live_target(md, sector, &srcu_idx);

	if (!ti)
		goto out;
	if (!ti->type->direct_access)
		goto out;
	len = max_io_len(sector, ti) / PAGE_SECTORS;
	if (len < 1)
		goto out;
	nr_pages = min(len, nr_pages);
	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);

 out:
	dm_put_live_table(md, srcu_idx);

	return ret;
}

static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
		int blocksize, sector_t start, sector_t len)
{
	struct mapped_device *md = dax_get_private(dax_dev);
	struct dm_table *map;
	bool ret = false;
	int srcu_idx;

	map = dm_get_live_table(md, &srcu_idx);
	if (!map)
		goto out;

	ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize);

out:
	dm_put_live_table(md, srcu_idx);

	return ret;
}

static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
				    void *addr, size_t bytes, struct iov_iter *i)
{
	struct mapped_device *md = dax_get_private(dax_dev);
	sector_t sector = pgoff * PAGE_SECTORS;
	struct dm_target *ti;
	long ret = 0;
	int srcu_idx;

	ti = dm_dax_get_live_target(md, sector, &srcu_idx);

	if (!ti)
		goto out;
	if (!ti->type->dax_copy_from_iter) {
		ret = copy_from_iter(addr, bytes, i);
		goto out;
	}
	ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
 out:
	dm_put_live_table(md, srcu_idx);

	return ret;
}

static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
		void *addr, size_t bytes, struct iov_iter *i)
{
	struct mapped_device *md = dax_get_private(dax_dev);
	sector_t sector = pgoff * PAGE_SECTORS;
	struct dm_target *ti;
	long ret = 0;
	int srcu_idx;

	ti = dm_dax_get_live_target(md, sector, &srcu_idx);

	if (!ti)
		goto out;
	if (!ti->type->dax_copy_to_iter) {
		ret = copy_to_iter(addr, bytes, i);
		goto out;
	}
	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
 out:
	dm_put_live_table(md, srcu_idx);

	return ret;
}

/*
 * A target may call dm_accept_partial_bio only from the map routine.  It is
 * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
 *
 * dm_accept_partial_bio informs the dm that the target only wants to process
 * additional n_sectors sectors of the bio and the rest of the data should be
 * sent in a next bio.
 *
 * A diagram that explains the arithmetics:
 * +--------------------+---------------+-------+
 * |         1          |       2       |   3   |
 * +--------------------+---------------+-------+
 *
 * <-------------- *tio->len_ptr --------------->
 *                      <------- bi_size ------->
 *                      <-- n_sectors -->
 *
 * Region 1 was already iterated over with bio_advance or similar function.
 *	(it may be empty if the target doesn't use bio_advance)
 * Region 2 is the remaining bio size that the target wants to process.
 *	(it may be empty if region 1 is non-empty, although there is no reason
 *	 to make it empty)
 * The target requires that region 3 is to be sent in the next bio.
 *
 * If the target wants to receive multiple copies of the bio (via num_*bios, etc),
 * the partially processed part (the sum of regions 1+2) must be the same for all
 * copies of the bio.
 */
void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
{
	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
	unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
	BUG_ON(bio->bi_opf & REQ_PREFLUSH);
	BUG_ON(bi_size > *tio->len_ptr);
	BUG_ON(n_sectors > bi_size);
	*tio->len_ptr -= bi_size - n_sectors;
	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;
}
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);

/*
 * The zone descriptors obtained with a zone report indicate
 * zone positions within the underlying device of the target. The zone
 * descriptors must be remapped to match their position within the dm device.
 * The caller target should obtain the zones information using
 * blkdev_report_zones() to ensure that remapping for partition offset is
 * already handled.
 */
void dm_remap_zone_report(struct dm_target *ti, sector_t start,
			  struct blk_zone *zones, unsigned int *nr_zones)
{
#ifdef CONFIG_BLK_DEV_ZONED
	struct blk_zone *zone;
	unsigned int nrz = *nr_zones;
	int i;

	/*
	 * Remap the start sector and write pointer position of the zones in
	 * the array. Since we may have obtained from the target underlying
	 * device more zones that the target size, also adjust the number
	 * of zones.
	 */
	for (i = 0; i < nrz; i++) {
		zone = zones + i;
		if (zone->start >= start + ti->len) {
			memset(zone, 0, sizeof(struct blk_zone) * (nrz - i));
			break;
		}

		zone->start = zone->start + ti->begin - start;
		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
			continue;

		if (zone->cond == BLK_ZONE_COND_FULL)
			zone->wp = zone->start + zone->len;
		else if (zone->cond == BLK_ZONE_COND_EMPTY)
			zone->wp = zone->start;
		else
			zone->wp = zone->wp + ti->begin - start;
	}

	*nr_zones = i;
#else /* !CONFIG_BLK_DEV_ZONED */
	*nr_zones = 0;
#endif
}
EXPORT_SYMBOL_GPL(dm_remap_zone_report);

static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch)
{
	mutex_lock(&md->swap_bios_lock);
	while (latch < md->swap_bios) {
		cond_resched();
		down(&md->swap_bios_semaphore);
		md->swap_bios--;
	}
	while (latch > md->swap_bios) {
		cond_resched();
		up(&md->swap_bios_semaphore);
		md->swap_bios++;
	}
	mutex_unlock(&md->swap_bios_lock);
}

static blk_qc_t __map_bio(struct dm_target_io *tio)
{
	int r;
	sector_t sector;
	struct bio *clone = &tio->clone;
	struct dm_io *io = tio->io;
	struct mapped_device *md = io->md;
	struct dm_target *ti = tio->ti;
	blk_qc_t ret = BLK_QC_T_NONE;

	clone->bi_end_io = clone_endio;

	/*
	 * Map the clone.  If r == 0 we don't need to do
	 * anything, the target has assumed ownership of
	 * this io.
	 */
	atomic_inc(&io->io_count);
	sector = clone->bi_iter.bi_sector;

	if (unlikely(swap_bios_limit(ti, clone))) {
		struct mapped_device *md = io->md;
		int latch = get_swap_bios();
		if (unlikely(latch != md->swap_bios))
			__set_swap_bios_limit(md, latch);
		down(&md->swap_bios_semaphore);
	}

	r = ti->type->map(ti, clone);
	switch (r) {
	case DM_MAPIO_SUBMITTED:
		break;
	case DM_MAPIO_REMAPPED:
		/* the bio has been remapped so dispatch it */
		trace_block_bio_remap(clone->bi_disk->queue, clone,
				      bio_dev(io->orig_bio), sector);
		if (md->type == DM_TYPE_NVME_BIO_BASED)
			ret = direct_make_request(clone);
		else
			ret = generic_make_request(clone);
		break;
	case DM_MAPIO_KILL:
		if (unlikely(swap_bios_limit(ti, clone))) {
			struct mapped_device *md = io->md;
			up(&md->swap_bios_semaphore);
		}
		free_tio(tio);
		dec_pending(io, BLK_STS_IOERR);
		break;
	case DM_MAPIO_REQUEUE:
		if (unlikely(swap_bios_limit(ti, clone))) {
			struct mapped_device *md = io->md;
			up(&md->swap_bios_semaphore);
		}
		free_tio(tio);
		dec_pending(io, BLK_STS_DM_REQUEUE);
		break;
	default:
		DMWARN("unimplemented target map return value: %d", r);
		BUG();
	}

	return ret;
}

static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
{
	bio->bi_iter.bi_sector = sector;
	bio->bi_iter.bi_size = to_bytes(len);
}

/*
 * Creates a bio that consists of range of complete bvecs.
 */
static int clone_bio(struct dm_target_io *tio, struct bio *bio,
		     sector_t sector, unsigned len)
{
	struct bio *clone = &tio->clone;

	__bio_clone_fast(clone, bio);

	if (bio_integrity(bio)) {
		int r;

		if (unlikely(!dm_target_has_integrity(tio->ti->type) &&
			     !dm_target_passes_integrity(tio->ti->type))) {
			DMWARN("%s: the target %s doesn't support integrity data.",
				dm_device_name(tio->io->md),
				tio->ti->type->name);
			return -EIO;
		}

		r = bio_integrity_clone(clone, bio, GFP_NOIO);
		if (r < 0)
			return r;
	}

	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
	clone->bi_iter.bi_size = to_bytes(len);

	if (bio_integrity(bio))
		bio_integrity_trim(clone);

	return 0;
}

static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
				struct dm_target *ti, unsigned num_bios)
{
	struct dm_target_io *tio;
	int try;

	if (!num_bios)
		return;

	if (num_bios == 1) {
		tio = alloc_tio(ci, ti, 0, GFP_NOIO);
		bio_list_add(blist, &tio->clone);
		return;
	}

	for (try = 0; try < 2; try++) {
		int bio_nr;
		struct bio *bio;

		if (try)
			mutex_lock(&ci->io->md->table_devices_lock);
		for (bio_nr = 0; bio_nr < num_bios; bio_nr++) {
			tio = alloc_tio(ci, ti, bio_nr, try ? GFP_NOIO : GFP_NOWAIT);
			if (!tio)
				break;

			bio_list_add(blist, &tio->clone);
		}
		if (try)
			mutex_unlock(&ci->io->md->table_devices_lock);
		if (bio_nr == num_bios)
			return;

		while ((bio = bio_list_pop(blist))) {
			tio = container_of(bio, struct dm_target_io, clone);
			free_tio(tio);
		}
	}
}

static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci,
					   struct dm_target_io *tio, unsigned *len)
{
	struct bio *clone = &tio->clone;

	tio->len_ptr = len;

	__bio_clone_fast(clone, ci->bio);
	if (len)
		bio_setup_sector(clone, ci->sector, *len);

	return __map_bio(tio);
}

static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
				  unsigned num_bios, unsigned *len)
{
	struct bio_list blist = BIO_EMPTY_LIST;
	struct bio *bio;
	struct dm_target_io *tio;

	alloc_multiple_bios(&blist, ci, ti, num_bios);

	while ((bio = bio_list_pop(&blist))) {
		tio = container_of(bio, struct dm_target_io, clone);
		(void) __clone_and_map_simple_bio(ci, tio, len);
	}
}

static int __send_empty_flush(struct clone_info *ci)
{
	unsigned target_nr = 0;
	struct dm_target *ti;

	/*
	 * Empty flush uses a statically initialized bio, as the base for
	 * cloning.  However, blkg association requires that a bdev is
	 * associated with a gendisk, which doesn't happen until the bdev is
	 * opened.  So, blkg association is done at issue time of the flush
	 * rather than when the device is created in alloc_dev().
	 */
	bio_set_dev(ci->bio, ci->io->md->bdev);

	BUG_ON(bio_has_data(ci->bio));
	while ((ti = dm_table_get_target(ci->map, target_nr++)))
		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
	return 0;
}

static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
				    sector_t sector, unsigned *len)
{
	struct bio *bio = ci->bio;
	struct dm_target_io *tio;
	int r;

	tio = alloc_tio(ci, ti, 0, GFP_NOIO);
	tio->len_ptr = len;
	r = clone_bio(tio, bio, sector, *len);
	if (r < 0) {
		free_tio(tio);
		return r;
	}
	(void) __map_bio(tio);

	return 0;
}

typedef unsigned (*get_num_bios_fn)(struct dm_target *ti);

static unsigned get_num_discard_bios(struct dm_target *ti)
{
	return ti->num_discard_bios;
}

static unsigned get_num_secure_erase_bios(struct dm_target *ti)
{
	return ti->num_secure_erase_bios;
}

static unsigned get_num_write_same_bios(struct dm_target *ti)
{
	return ti->num_write_same_bios;
}

static unsigned get_num_write_zeroes_bios(struct dm_target *ti)
{
	return ti->num_write_zeroes_bios;
}

static int __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti,
				       unsigned num_bios)
{
	unsigned len;

	/*
	 * Even though the device advertised support for this type of
	 * request, that does not mean every target supports it, and
	 * reconfiguration might also have changed that since the
	 * check was performed.
	 */
	if (!num_bios)
		return -EOPNOTSUPP;

	len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti));

	__send_duplicate_bios(ci, ti, num_bios, &len);

	ci->sector += len;
	ci->sector_count -= len;

	return 0;
}

static int __send_discard(struct clone_info *ci, struct dm_target *ti)
{
	return __send_changing_extent_only(ci, ti, get_num_discard_bios(ti));
}

static int __send_secure_erase(struct clone_info *ci, struct dm_target *ti)
{
	return __send_changing_extent_only(ci, ti, get_num_secure_erase_bios(ti));
}

static int __send_write_same(struct clone_info *ci, struct dm_target *ti)
{
	return __send_changing_extent_only(ci, ti, get_num_write_same_bios(ti));
}

static int __send_write_zeroes(struct clone_info *ci, struct dm_target *ti)
{
	return __send_changing_extent_only(ci, ti, get_num_write_zeroes_bios(ti));
}

static bool is_abnormal_io(struct bio *bio)
{
	bool r = false;

	switch (bio_op(bio)) {
	case REQ_OP_DISCARD:
	case REQ_OP_SECURE_ERASE:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE_ZEROES:
		r = true;
		break;
	}

	return r;
}

static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti,
				  int *result)
{
	struct bio *bio = ci->bio;

	if (bio_op(bio) == REQ_OP_DISCARD)
		*result = __send_discard(ci, ti);
	else if (bio_op(bio) == REQ_OP_SECURE_ERASE)
		*result = __send_secure_erase(ci, ti);
	else if (bio_op(bio) == REQ_OP_WRITE_SAME)
		*result = __send_write_same(ci, ti);
	else if (bio_op(bio) == REQ_OP_WRITE_ZEROES)
		*result = __send_write_zeroes(ci, ti);
	else
		return false;

	return true;
}

/*
 * Select the correct strategy for processing a non-flush bio.
 */
static int __split_and_process_non_flush(struct clone_info *ci)
{
	struct dm_target *ti;
	unsigned len;
	int r;

	ti = dm_table_find_target(ci->map, ci->sector);
	if (!ti)
		return -EIO;

	if (__process_abnormal_io(ci, ti, &r))
		return r;

	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);

	r = __clone_and_map_data_bio(ci, ti, ci->sector, &len);
	if (r < 0)
		return r;

	ci->sector += len;
	ci->sector_count -= len;

	return 0;
}

static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
			    struct dm_table *map, struct bio *bio)
{
	ci->map = map;
	ci->io = alloc_io(md, bio);
	ci->sector = bio->bi_iter.bi_sector;
}

#define __dm_part_stat_sub(part, field, subnd)	\
	(part_stat_get(part, field) -= (subnd))

/*
 * Entry point to split a bio into clones and submit them to the targets.
 */
static blk_qc_t __split_and_process_bio(struct mapped_device *md,
					struct dm_table *map, struct bio *bio)
{
	struct clone_info ci;
	blk_qc_t ret = BLK_QC_T_NONE;
	int error = 0;

	init_clone_info(&ci, md, map, bio);

	if (bio->bi_opf & REQ_PREFLUSH) {
		struct bio flush_bio;

		/*
		 * Use an on-stack bio for this, it's safe since we don't
		 * need to reference it after submit. It's just used as
		 * the basis for the clone(s).
		 */
		bio_init(&flush_bio, NULL, 0);
		flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
		ci.bio = &flush_bio;
		ci.sector_count = 0;
		error = __send_empty_flush(&ci);
		bio_uninit(ci.bio);
		/* dec_pending submits any data associated with flush */
	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
		ci.bio = bio;
		ci.sector_count = 0;
		error = __split_and_process_non_flush(&ci);
	} else {
		ci.bio = bio;
		ci.sector_count = bio_sectors(bio);
		while (ci.sector_count && !error) {
			error = __split_and_process_non_flush(&ci);
			if (current->bio_list && ci.sector_count && !error) {
				/*
				 * Remainder must be passed to generic_make_request()
				 * so that it gets handled *after* bios already submitted
				 * have been completely processed.
				 * We take a clone of the original to store in
				 * ci.io->orig_bio to be used by end_io_acct() and
				 * for dec_pending to use for completion handling.
				 */
				struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
							  GFP_NOIO, &md->queue->bio_split);
				ci.io->orig_bio = b;

				/*
				 * Adjust IO stats for each split, otherwise upon queue
				 * reentry there will be redundant IO accounting.
				 * NOTE: this is a stop-gap fix, a proper fix involves
				 * significant refactoring of DM core's bio splitting
				 * (by eliminating DM's splitting and just using bio_split)
				 */
				part_stat_lock();
				__dm_part_stat_sub(&dm_disk(md)->part0,
						   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
				part_stat_unlock();

				bio_chain(b, bio);
				trace_block_split(md->queue, b, bio->bi_iter.bi_sector);
				ret = generic_make_request(bio);
				break;
			}
		}
	}

	/* drop the extra reference count */
	dec_pending(ci.io, errno_to_blk_status(error));
	return ret;
}

/*
 * Optimized variant of __split_and_process_bio that leverages the
 * fact that targets that use it do _not_ have a need to split bios.
 */
static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
			      struct bio *bio, struct dm_target *ti)
{
	struct clone_info ci;
	blk_qc_t ret = BLK_QC_T_NONE;
	int error = 0;

	init_clone_info(&ci, md, map, bio);

	if (bio->bi_opf & REQ_PREFLUSH) {
		struct bio flush_bio;

		/*
		 * Use an on-stack bio for this, it's safe since we don't
		 * need to reference it after submit. It's just used as
		 * the basis for the clone(s).
		 */
		bio_init(&flush_bio, NULL, 0);
		flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
		ci.bio = &flush_bio;
		ci.sector_count = 0;
		error = __send_empty_flush(&ci);
		bio_uninit(ci.bio);
		/* dec_pending submits any data associated with flush */
	} else {
		struct dm_target_io *tio;

		ci.bio = bio;
		ci.sector_count = bio_sectors(bio);
		if (__process_abnormal_io(&ci, ti, &error))
			goto out;

		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
		ret = __clone_and_map_simple_bio(&ci, tio, NULL);
	}
out:
	/* drop the extra reference count */
	dec_pending(ci.io, errno_to_blk_status(error));
	return ret;
}

static blk_qc_t dm_process_bio(struct mapped_device *md,
			       struct dm_table *map, struct bio *bio)
{
	blk_qc_t ret = BLK_QC_T_NONE;
	struct dm_target *ti = md->immutable_target;

	if (unlikely(!map)) {
		bio_io_error(bio);
		return ret;
	}

	if (!ti) {
		ti = dm_table_find_target(map, bio->bi_iter.bi_sector);
		if (unlikely(!ti)) {
			bio_io_error(bio);
			return ret;
		}
	}

	/*
	 * If in ->make_request_fn we need to use blk_queue_split(), otherwise
	 * queue_limits for abnormal requests (e.g. discard, writesame, etc)
	 * won't be imposed.
	 */
	if (current->bio_list) {
		if (is_abnormal_io(bio))
			blk_queue_split(md->queue, &bio);
		/* regular IO is split by __split_and_process_bio */
	}

	if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
		return __process_bio(md, map, bio, ti);
	return __split_and_process_bio(md, map, bio);
}

static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
{
	struct mapped_device *md = q->queuedata;
	blk_qc_t ret = BLK_QC_T_NONE;
	int srcu_idx;
	struct dm_table *map;

	map = dm_get_live_table(md, &srcu_idx);

	/* if we're suspended, we have to queue this io for later */
	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
		dm_put_live_table(md, srcu_idx);

		if (!(bio->bi_opf & REQ_RAHEAD))
			queue_io(md, bio);
		else
			bio_io_error(bio);
		return ret;
	}

	ret = dm_process_bio(md, map, bio);

	dm_put_live_table(md, srcu_idx);
	return ret;
}

static int dm_any_congested(void *congested_data, int bdi_bits)
{
	int r = bdi_bits;
	struct mapped_device *md = congested_data;
	struct dm_table *map;

	if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
		if (dm_request_based(md)) {
			/*
			 * With request-based DM we only need to check the
			 * top-level queue for congestion.
			 */
			struct backing_dev_info *bdi = md->queue->backing_dev_info;
			r = bdi->wb.congested->state & bdi_bits;
		} else {
			map = dm_get_live_table_fast(md);
			if (map)
				r = dm_table_any_congested(map, bdi_bits);
			dm_put_live_table_fast(md);
		}
	}

	return r;
}

/*-----------------------------------------------------------------
 * An IDR is used to keep track of allocated minor numbers.
 *---------------------------------------------------------------*/
static void free_minor(int minor)
{
	spin_lock(&_minor_lock);
	idr_remove(&_minor_idr, minor);
	spin_unlock(&_minor_lock);
}

/*
 * See if the device with a specific minor # is free.
 */
static int specific_minor(int minor)
{
	int r;

	if (minor >= (1 << MINORBITS))
		return -EINVAL;

	idr_preload(GFP_KERNEL);
	spin_lock(&_minor_lock);

	r = idr_alloc(&_minor_idr, MINOR_ALLOCED, minor, minor + 1, GFP_NOWAIT);

	spin_unlock(&_minor_lock);
	idr_preload_end();
	if (r < 0)
		return r == -ENOSPC ? -EBUSY : r;
	return 0;
}

static int next_free_minor(int *minor)
{
	int r;

	idr_preload(GFP_KERNEL);
	spin_lock(&_minor_lock);

	r = idr_alloc(&_minor_idr, MINOR_ALLOCED, 0, 1 << MINORBITS, GFP_NOWAIT);

	spin_unlock(&_minor_lock);
	idr_preload_end();
	if (r < 0)
		return r;
	*minor = r;
	return 0;
}

static const struct block_device_operations dm_blk_dops;
static const struct dax_operations dm_dax_ops;

static void dm_wq_work(struct work_struct *work);

static void cleanup_mapped_device(struct mapped_device *md)
{
	if (md->wq)
		destroy_workqueue(md->wq);
	bioset_exit(&md->bs);
	bioset_exit(&md->io_bs);

	if (md->dax_dev) {
		kill_dax(md->dax_dev);
		put_dax(md->dax_dev);
		md->dax_dev = NULL;
	}

	if (md->disk) {
		spin_lock(&_minor_lock);
		md->disk->private_data = NULL;
		spin_unlock(&_minor_lock);
		del_gendisk(md->disk);
		put_disk(md->disk);
	}

	if (md->queue)
		blk_cleanup_queue(md->queue);

	cleanup_srcu_struct(&md->io_barrier);

	if (md->bdev) {
		bdput(md->bdev);
		md->bdev = NULL;
	}

	mutex_destroy(&md->suspend_lock);
	mutex_destroy(&md->type_lock);
	mutex_destroy(&md->table_devices_lock);
	mutex_destroy(&md->swap_bios_lock);

	dm_mq_cleanup_mapped_device(md);
}

/*
 * Allocate and initialise a blank device with a given minor.
 */
static struct mapped_device *alloc_dev(int minor)
{
	int r, numa_node_id = dm_get_numa_node();
	struct mapped_device *md;
	void *old_md;

	md = kvzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id);
	if (!md) {
		DMWARN("unable to allocate device, out of memory.");
		return NULL;
	}

	if (!try_module_get(THIS_MODULE))
		goto bad_module_get;

	/* get a minor number for the dev */
	if (minor == DM_ANY_MINOR)
		r = next_free_minor(&minor);
	else
		r = specific_minor(minor);
	if (r < 0)
		goto bad_minor;

	r = init_srcu_struct(&md->io_barrier);
	if (r < 0)
		goto bad_io_barrier;

	md->numa_node_id = numa_node_id;
	md->init_tio_pdu = false;
	md->type = DM_TYPE_NONE;
	mutex_init(&md->suspend_lock);
	mutex_init(&md->type_lock);
	mutex_init(&md->table_devices_lock);
	spin_lock_init(&md->deferred_lock);
	atomic_set(&md->holders, 1);
	atomic_set(&md->open_count, 0);
	atomic_set(&md->event_nr, 0);
	atomic_set(&md->uevent_seq, 0);
	INIT_LIST_HEAD(&md->uevent_list);
	INIT_LIST_HEAD(&md->table_devices);
	spin_lock_init(&md->uevent_lock);

	md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id);
	if (!md->queue)
		goto bad;
	md->queue->queuedata = md;
	/*
	 * default to bio-based required ->make_request_fn until DM
	 * table is loaded and md->type established. If request-based
	 * table is loaded: blk-mq will override accordingly.
	 */
	blk_queue_make_request(md->queue, dm_make_request);

	md->disk = alloc_disk_node(1, md->numa_node_id);
	if (!md->disk)
		goto bad;

	init_waitqueue_head(&md->wait);
	INIT_WORK(&md->work, dm_wq_work);
	init_waitqueue_head(&md->eventq);
	init_completion(&md->kobj_holder.completion);

	md->swap_bios = get_swap_bios();
	sema_init(&md->swap_bios_semaphore, md->swap_bios);
	mutex_init(&md->swap_bios_lock);

	md->disk->major = _major;
	md->disk->first_minor = minor;
	md->disk->fops = &dm_blk_dops;
	md->disk->queue = md->queue;
	md->disk->private_data = md;
	sprintf(md->disk->disk_name, "dm-%d", minor);

	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
		md->dax_dev = alloc_dax(md, md->disk->disk_name,
					&dm_dax_ops, 0);
		if (!md->dax_dev)
			goto bad;
	}

	add_disk_no_queue_reg(md->disk);
	format_dev_t(md->name, MKDEV(_major, minor));

	md->wq = alloc_workqueue("kdmflush", WQ_MEM_RECLAIM, 0);
	if (!md->wq)
		goto bad;

	md->bdev = bdget_disk(md->disk, 0);
	if (!md->bdev)
		goto bad;

	dm_stats_init(&md->stats);

	/* Populate the mapping, nobody knows we exist yet */
	spin_lock(&_minor_lock);
	old_md = idr_replace(&_minor_idr, md, minor);
	spin_unlock(&_minor_lock);

	BUG_ON(old_md != MINOR_ALLOCED);

	return md;

bad:
	cleanup_mapped_device(md);
bad_io_barrier:
	free_minor(minor);
bad_minor:
	module_put(THIS_MODULE);
bad_module_get:
	kvfree(md);
	return NULL;
}

static void unlock_fs(struct mapped_device *md);

static void free_dev(struct mapped_device *md)
{
	int minor = MINOR(disk_devt(md->disk));

	unlock_fs(md);

	cleanup_mapped_device(md);

	free_table_devices(&md->table_devices);
	dm_stats_cleanup(&md->stats);
	free_minor(minor);

	module_put(THIS_MODULE);
	kvfree(md);
}

static int __bind_mempools(struct mapped_device *md, struct dm_table *t)
{
	struct dm_md_mempools *p = dm_table_get_md_mempools(t);
	int ret = 0;

	if (dm_table_bio_based(t)) {
		/*
		 * The md may already have mempools that need changing.
		 * If so, reload bioset because front_pad may have changed
		 * because a different table was loaded.
		 */
		bioset_exit(&md->bs);
		bioset_exit(&md->io_bs);

	} else if (bioset_initialized(&md->bs)) {
		/*
		 * There's no need to reload with request-based dm
		 * because the size of front_pad doesn't change.
		 * Note for future: If you are to reload bioset,
		 * prep-ed requests in the queue may refer
		 * to bio from the old bioset, so you must walk
		 * through the queue to unprep.
		 */
		goto out;
	}

	BUG_ON(!p ||
	       bioset_initialized(&md->bs) ||
	       bioset_initialized(&md->io_bs));

	ret = bioset_init_from_src(&md->bs, &p->bs);
	if (ret)
		goto out;
	ret = bioset_init_from_src(&md->io_bs, &p->io_bs);
	if (ret)
		bioset_exit(&md->bs);
out:
	/* mempool bind completed, no longer need any mempools in the table */
	dm_table_free_md_mempools(t);
	return ret;
}

/*
 * Bind a table to the device.
 */
static void event_callback(void *context)
{
	unsigned long flags;
	LIST_HEAD(uevents);
	struct mapped_device *md = (struct mapped_device *) context;

	spin_lock_irqsave(&md->uevent_lock, flags);
	list_splice_init(&md->uevent_list, &uevents);
	spin_unlock_irqrestore(&md->uevent_lock, flags);

	dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj);

	atomic_inc(&md->event_nr);
	wake_up(&md->eventq);
	dm_issue_global_event();
}

/*
 * Protected by md->suspend_lock obtained by dm_swap_table().
 */
static void __set_size(struct mapped_device *md, sector_t size)
{
	lockdep_assert_held(&md->suspend_lock);

	set_capacity(md->disk, size);

	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
}

/*
 * Returns old map, which caller must destroy.
 */
static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
			       struct queue_limits *limits)
{
	struct dm_table *old_map;
	struct request_queue *q = md->queue;
	bool request_based = dm_table_request_based(t);
	sector_t size;
	int ret;

	lockdep_assert_held(&md->suspend_lock);

	size = dm_table_get_size(t);

	/*
	 * Wipe any geometry if the size of the table changed.
	 */
	if (size != dm_get_size(md))
		memset(&md->geometry, 0, sizeof(md->geometry));

	__set_size(md, size);

	dm_table_event_callback(t, event_callback, md);

	/*
	 * The queue hasn't been stopped yet, if the old table type wasn't
	 * for request-based during suspension.  So stop it to prevent
	 * I/O mapping before resume.
	 * This must be done before setting the queue restrictions,
	 * because request-based dm may be run just after the setting.
	 */
	if (request_based)
		dm_stop_queue(q);

	if (request_based || md->type == DM_TYPE_NVME_BIO_BASED) {
		/*
		 * Leverage the fact that request-based DM targets and
		 * NVMe bio based targets are immutable singletons
		 * - used to optimize both dm_request_fn and dm_mq_queue_rq;
		 *   and __process_bio.
		 */
		md->immutable_target = dm_table_get_immutable_target(t);
	}

	ret = __bind_mempools(md, t);
	if (ret) {
		old_map = ERR_PTR(ret);
		goto out;
	}

	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
	rcu_assign_pointer(md->map, (void *)t);
	md->immutable_target_type = dm_table_get_immutable_target_type(t);

	dm_table_set_restrictions(t, q, limits);
	if (old_map)
		dm_sync_table(md);

out:
	return old_map;
}

/*
 * Returns unbound table for the caller to free.
 */
static struct dm_table *__unbind(struct mapped_device *md)
{
	struct dm_table *map = rcu_dereference_protected(md->map, 1);

	if (!map)
		return NULL;

	dm_table_event_callback(map, NULL, NULL);
	RCU_INIT_POINTER(md->map, NULL);
	dm_sync_table(md);

	return map;
}

/*
 * Constructor for a new device.
 */
int dm_create(int minor, struct mapped_device **result)
{
	int r;
	struct mapped_device *md;

	md = alloc_dev(minor);
	if (!md)
		return -ENXIO;

	r = dm_sysfs_init(md);
	if (r) {
		free_dev(md);
		return r;
	}

	*result = md;
	return 0;
}

/*
 * Functions to manage md->type.
 * All are required to hold md->type_lock.
 */
void dm_lock_md_type(struct mapped_device *md)
{
	mutex_lock(&md->type_lock);
}

void dm_unlock_md_type(struct mapped_device *md)
{
	mutex_unlock(&md->type_lock);
}

void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type)
{
	BUG_ON(!mutex_is_locked(&md->type_lock));
	md->type = type;
}

enum dm_queue_mode dm_get_md_type(struct mapped_device *md)
{
	return md->type;
}

struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
{
	return md->immutable_target_type;
}

/*
 * The queue_limits are only valid as long as you have a reference
 * count on 'md'.
 */
struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
{
	BUG_ON(!atomic_read(&md->holders));
	return &md->queue->limits;
}
EXPORT_SYMBOL_GPL(dm_get_queue_limits);

static void dm_init_congested_fn(struct mapped_device *md)
{
	md->queue->backing_dev_info->congested_data = md;
	md->queue->backing_dev_info->congested_fn = dm_any_congested;
}

/*
 * Setup the DM device's queue based on md's type
 */
int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
{
	int r;
	struct queue_limits limits;
	enum dm_queue_mode type = dm_get_md_type(md);

	switch (type) {
	case DM_TYPE_REQUEST_BASED:
		r = dm_mq_init_request_queue(md, t);
		if (r) {
			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
			return r;
		}
		dm_init_congested_fn(md);
		break;
	case DM_TYPE_BIO_BASED:
	case DM_TYPE_DAX_BIO_BASED:
	case DM_TYPE_NVME_BIO_BASED:
		dm_init_congested_fn(md);
		break;
	case DM_TYPE_NONE:
		WARN_ON_ONCE(true);
		break;
	}

	r = dm_calculate_queue_limits(t, &limits);
	if (r) {
		DMERR("Cannot calculate initial queue limits");
		return r;
	}
	dm_table_set_restrictions(t, md->queue, &limits);
	blk_register_queue(md->disk);

	return 0;
}

struct mapped_device *dm_get_md(dev_t dev)
{
	struct mapped_device *md;
	unsigned minor = MINOR(dev);

	if (MAJOR(dev) != _major || minor >= (1 << MINORBITS))
		return NULL;

	spin_lock(&_minor_lock);

	md = idr_find(&_minor_idr, minor);
	if (!md || md == MINOR_ALLOCED || (MINOR(disk_devt(dm_disk(md))) != minor) ||
	    test_bit(DMF_FREEING, &md->flags) || dm_deleting_md(md)) {
		md = NULL;
		goto out;
	}
	dm_get(md);
out:
	spin_unlock(&_minor_lock);

	return md;
}
EXPORT_SYMBOL_GPL(dm_get_md);

void *dm_get_mdptr(struct mapped_device *md)
{
	return md->interface_ptr;
}

void dm_set_mdptr(struct mapped_device *md, void *ptr)
{
	md->interface_ptr = ptr;
}

void dm_get(struct mapped_device *md)
{
	atomic_inc(&md->holders);
	BUG_ON(test_bit(DMF_FREEING, &md->flags));
}

int dm_hold(struct mapped_device *md)
{
	spin_lock(&_minor_lock);
	if (test_bit(DMF_FREEING, &md->flags)) {
		spin_unlock(&_minor_lock);
		return -EBUSY;
	}
	dm_get(md);
	spin_unlock(&_minor_lock);
	return 0;
}
EXPORT_SYMBOL_GPL(dm_hold);

const char *dm_device_name(struct mapped_device *md)
{
	return md->name;
}
EXPORT_SYMBOL_GPL(dm_device_name);

static void __dm_destroy(struct mapped_device *md, bool wait)
{
	struct dm_table *map;
	int srcu_idx;

	might_sleep();

	spin_lock(&_minor_lock);
	idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
	set_bit(DMF_FREEING, &md->flags);
	spin_unlock(&_minor_lock);

	blk_set_queue_dying(md->queue);

	/*
	 * Take suspend_lock so that presuspend and postsuspend methods
	 * do not race with internal suspend.
	 */
	mutex_lock(&md->suspend_lock);
	map = dm_get_live_table(md, &srcu_idx);
	if (!dm_suspended_md(md)) {
		dm_table_presuspend_targets(map);
		set_bit(DMF_SUSPENDED, &md->flags);
		set_bit(DMF_POST_SUSPENDING, &md->flags);
		dm_table_postsuspend_targets(map);
	}
	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
	dm_put_live_table(md, srcu_idx);
	mutex_unlock(&md->suspend_lock);

	/*
	 * Rare, but there may be I/O requests still going to complete,
	 * for example.  Wait for all references to disappear.
	 * No one should increment the reference count of the mapped_device,
	 * after the mapped_device state becomes DMF_FREEING.
	 */
	if (wait)
		while (atomic_read(&md->holders))
			msleep(1);
	else if (atomic_read(&md->holders))
		DMWARN("%s: Forcibly removing mapped_device still in use! (%d users)",
		       dm_device_name(md), atomic_read(&md->holders));

	dm_sysfs_exit(md);
	dm_table_destroy(__unbind(md));
	free_dev(md);
}

void dm_destroy(struct mapped_device *md)
{
	__dm_destroy(md, true);
}

void dm_destroy_immediate(struct mapped_device *md)
{
	__dm_destroy(md, false);
}

void dm_put(struct mapped_device *md)
{
	atomic_dec(&md->holders);
}
EXPORT_SYMBOL_GPL(dm_put);

static int dm_wait_for_completion(struct mapped_device *md, long task_state)
{
	int r = 0;
	DEFINE_WAIT(wait);

	while (1) {
		prepare_to_wait(&md->wait, &wait, task_state);

		if (!md_in_flight(md))
			break;

		if (signal_pending_state(task_state, current)) {
			r = -EINTR;
			break;
		}

		io_schedule();
	}
	finish_wait(&md->wait, &wait);

	return r;
}

/*
 * Process the deferred bios
 */
static void dm_wq_work(struct work_struct *work)
{
	struct mapped_device *md = container_of(work, struct mapped_device,
						work);
	struct bio *c;
	int srcu_idx;
	struct dm_table *map;

	map = dm_get_live_table(md, &srcu_idx);

	while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
		spin_lock_irq(&md->deferred_lock);
		c = bio_list_pop(&md->deferred);
		spin_unlock_irq(&md->deferred_lock);

		if (!c)
			break;

		if (dm_request_based(md))
			(void) generic_make_request(c);
		else
			(void) dm_process_bio(md, map, c);
	}

	dm_put_live_table(md, srcu_idx);
}

static void dm_queue_flush(struct mapped_device *md)
{
	clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
	smp_mb__after_atomic();
	queue_work(md->wq, &md->work);
}

/*
 * Swap in a new table, returning the old one for the caller to destroy.
 */
struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
{
	struct dm_table *live_map = NULL, *map = ERR_PTR(-EINVAL);
	struct queue_limits limits;
	int r;

	mutex_lock(&md->suspend_lock);

	/* device must be suspended */
	if (!dm_suspended_md(md))
		goto out;

	/*
	 * If the new table has no data devices, retain the existing limits.
	 * This helps multipath with queue_if_no_path if all paths disappear,
	 * then new I/O is queued based on these limits, and then some paths
	 * reappear.
	 */
	if (dm_table_has_no_data_devices(table)) {
		live_map = dm_get_live_table_fast(md);
		if (live_map)
			limits = md->queue->limits;
		dm_put_live_table_fast(md);
	}

	if (!live_map) {
		r = dm_calculate_queue_limits(table, &limits);
		if (r) {
			map = ERR_PTR(r);
			goto out;
		}
	}

	map = __bind(md, table, &limits);
	dm_issue_global_event();

out:
	mutex_unlock(&md->suspend_lock);
	return map;
}

/*
 * Functions to lock and unlock any filesystem running on the
 * device.
 */
static int lock_fs(struct mapped_device *md)
{
	int r;

	WARN_ON(md->frozen_sb);

	md->frozen_sb = freeze_bdev(md->bdev);
	if (IS_ERR(md->frozen_sb)) {
		r = PTR_ERR(md->frozen_sb);
		md->frozen_sb = NULL;
		return r;
	}

	set_bit(DMF_FROZEN, &md->flags);

	return 0;
}

static void unlock_fs(struct mapped_device *md)
{
	if (!test_bit(DMF_FROZEN, &md->flags))
		return;

	thaw_bdev(md->bdev, md->frozen_sb);
	md->frozen_sb = NULL;
	clear_bit(DMF_FROZEN, &md->flags);
}

/*
 * @suspend_flags: DM_SUSPEND_LOCKFS_FLAG and/or DM_SUSPEND_NOFLUSH_FLAG
 * @task_state: e.g. TASK_INTERRUPTIBLE or TASK_UNINTERRUPTIBLE
 * @dmf_suspended_flag: DMF_SUSPENDED or DMF_SUSPENDED_INTERNALLY
 *
 * If __dm_suspend returns 0, the device is completely quiescent
 * now. There is no request-processing activity. All new requests
 * are being added to md->deferred list.
 */
static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
			unsigned suspend_flags, long task_state,
			int dmf_suspended_flag)
{
	bool do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG;
	bool noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG;
	int r;

	lockdep_assert_held(&md->suspend_lock);

	/*
	 * DMF_NOFLUSH_SUSPENDING must be set before presuspend.
	 * This flag is cleared before dm_suspend returns.
	 */
	if (noflush)
		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
	else
		pr_debug("%s: suspending with flush\n", dm_device_name(md));

	/*
	 * This gets reverted if there's an error later and the targets
	 * provide the .presuspend_undo hook.
	 */
	dm_table_presuspend_targets(map);

	/*
	 * Flush I/O to the device.
	 * Any I/O submitted after lock_fs() may not be flushed.
	 * noflush takes precedence over do_lockfs.
	 * (lock_fs() flushes I/Os and waits for them to complete.)
	 */
	if (!noflush && do_lockfs) {
		r = lock_fs(md);
		if (r) {
			dm_table_presuspend_undo_targets(map);
			return r;
		}
	}

	/*
	 * Here we must make sure that no processes are submitting requests
	 * to target drivers i.e. no one may be executing
	 * __split_and_process_bio. This is called from dm_request and
	 * dm_wq_work.
	 *
	 * To get all processes out of __split_and_process_bio in dm_request,
	 * we take the write lock. To prevent any process from reentering
	 * __split_and_process_bio from dm_request and quiesce the thread
	 * (dm_wq_work), we set BMF_BLOCK_IO_FOR_SUSPEND and call
	 * flush_workqueue(md->wq).
	 */
	set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
	if (map)
		synchronize_srcu(&md->io_barrier);

	/*
	 * Stop md->queue before flushing md->wq in case request-based
	 * dm defers requests to md->wq from md->queue.
	 */
	if (dm_request_based(md))
		dm_stop_queue(md->queue);

	flush_workqueue(md->wq);

	/*
	 * At this point no more requests are entering target request routines.
	 * We call dm_wait_for_completion to wait for all existing requests
	 * to finish.
	 */
	r = dm_wait_for_completion(md, task_state);
	if (!r)
		set_bit(dmf_suspended_flag, &md->flags);

	if (noflush)
		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
	if (map)
		synchronize_srcu(&md->io_barrier);

	/* were we interrupted ? */
	if (r < 0) {
		dm_queue_flush(md);

		if (dm_request_based(md))
			dm_start_queue(md->queue);

		unlock_fs(md);
		dm_table_presuspend_undo_targets(map);
		/* pushback list is already flushed, so skip flush */
	}

	return r;
}

/*
 * We need to be able to change a mapping table under a mounted
 * filesystem.  For example we might want to move some data in
 * the background.  Before the table can be swapped with
 * dm_bind_table, dm_suspend must be called to flush any in
 * flight bios and ensure that any further io gets deferred.
 */
/*
 * Suspend mechanism in request-based dm.
 *
 * 1. Flush all I/Os by lock_fs() if needed.
 * 2. Stop dispatching any I/O by stopping the request_queue.
 * 3. Wait for all in-flight I/Os to be completed or requeued.
 *
 * To abort suspend, start the request_queue.
 */
int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
{
	struct dm_table *map = NULL;
	int r = 0;

retry:
	mutex_lock_nested(&md->suspend_lock, SINGLE_DEPTH_NESTING);

	if (dm_suspended_md(md)) {
		r = -EINVAL;
		goto out_unlock;
	}

	if (dm_suspended_internally_md(md)) {
		/* already internally suspended, wait for internal resume */
		mutex_unlock(&md->suspend_lock);
		r = wait_on_bit(&md->flags, DMF_SUSPENDED_INTERNALLY, TASK_INTERRUPTIBLE);
		if (r)
			return r;
		goto retry;
	}

	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));

	r = __dm_suspend(md, map, suspend_flags, TASK_INTERRUPTIBLE, DMF_SUSPENDED);
	if (r)
		goto out_unlock;

	set_bit(DMF_POST_SUSPENDING, &md->flags);
	dm_table_postsuspend_targets(map);
	clear_bit(DMF_POST_SUSPENDING, &md->flags);

out_unlock:
	mutex_unlock(&md->suspend_lock);
	return r;
}

static int __dm_resume(struct mapped_device *md, struct dm_table *map)
{
	if (map) {
		int r = dm_table_resume_targets(map);
		if (r)
			return r;
	}

	dm_queue_flush(md);

	/*
	 * Flushing deferred I/Os must be done after targets are resumed
	 * so that mapping of targets can work correctly.
	 * Request-based dm is queueing the deferred I/Os in its request_queue.
	 */
	if (dm_request_based(md))
		dm_start_queue(md->queue);

	unlock_fs(md);

	return 0;
}

int dm_resume(struct mapped_device *md)
{
	int r;
	struct dm_table *map = NULL;

retry:
	r = -EINVAL;
	mutex_lock_nested(&md->suspend_lock, SINGLE_DEPTH_NESTING);

	if (!dm_suspended_md(md))
		goto out;

	if (dm_suspended_internally_md(md)) {
		/* already internally suspended, wait for internal resume */
		mutex_unlock(&md->suspend_lock);
		r = wait_on_bit(&md->flags, DMF_SUSPENDED_INTERNALLY, TASK_INTERRUPTIBLE);
		if (r)
			return r;
		goto retry;
	}

	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
	if (!map || !dm_table_get_size(map))
		goto out;

	r = __dm_resume(md, map);
	if (r)
		goto out;

	clear_bit(DMF_SUSPENDED, &md->flags);
out:
	mutex_unlock(&md->suspend_lock);

	return r;
}

/*
 * Internal suspend/resume works like userspace-driven suspend. It waits
 * until all bios finish and prevents issuing new bios to the target drivers.
 * It may be used only from the kernel.
 */

static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_flags)
{
	struct dm_table *map = NULL;

	lockdep_assert_held(&md->suspend_lock);

	if (md->internal_suspend_count++)
		return; /* nested internal suspend */

	if (dm_suspended_md(md)) {
		set_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
		return; /* nest suspend */
	}

	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));

	/*
	 * Using TASK_UNINTERRUPTIBLE because only NOFLUSH internal suspend is
	 * supported.  Properly supporting a TASK_INTERRUPTIBLE internal suspend
	 * would require changing .presuspend to return an error -- avoid this
	 * until there is a need for more elaborate variants of internal suspend.
	 */
	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
			    DMF_SUSPENDED_INTERNALLY);

	set_bit(DMF_POST_SUSPENDING, &md->flags);
	dm_table_postsuspend_targets(map);
	clear_bit(DMF_POST_SUSPENDING, &md->flags);
}

static void __dm_internal_resume(struct mapped_device *md)
{
	BUG_ON(!md->internal_suspend_count);

	if (--md->internal_suspend_count)
		return; /* resume from nested internal suspend */

	if (dm_suspended_md(md))
		goto done; /* resume from nested suspend */

	/*
	 * NOTE: existing callers don't need to call dm_table_resume_targets
	 * (which may fail -- so best to avoid it for now by passing NULL map)
	 */
	(void) __dm_resume(md, NULL);

done:
	clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
	smp_mb__after_atomic();
	wake_up_bit(&md->flags, DMF_SUSPENDED_INTERNALLY);
}

void dm_internal_suspend_noflush(struct mapped_device *md)
{
	mutex_lock(&md->suspend_lock);
	__dm_internal_suspend(md, DM_SUSPEND_NOFLUSH_FLAG);
	mutex_unlock(&md->suspend_lock);
}
EXPORT_SYMBOL_GPL(dm_internal_suspend_noflush);

void dm_internal_resume(struct mapped_device *md)
{
	mutex_lock(&md->suspend_lock);
	__dm_internal_resume(md);
	mutex_unlock(&md->suspend_lock);
}
EXPORT_SYMBOL_GPL(dm_internal_resume);

/*
 * Fast variants of internal suspend/resume hold md->suspend_lock,
 * which prevents interaction with userspace-driven suspend.
 */

void dm_internal_suspend_fast(struct mapped_device *md)
{
	mutex_lock(&md->suspend_lock);
	if (dm_suspended_md(md) || dm_suspended_internally_md(md))
		return;

	set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
	synchronize_srcu(&md->io_barrier);
	flush_workqueue(md->wq);
	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL_GPL(dm_internal_suspend_fast);

void dm_internal_resume_fast(struct mapped_device *md)
{
	if (dm_suspended_md(md) || dm_suspended_internally_md(md))
		goto done;

	dm_queue_flush(md);

done:
	mutex_unlock(&md->suspend_lock);
}
EXPORT_SYMBOL_GPL(dm_internal_resume_fast);

/*-----------------------------------------------------------------
 * Event notification.
 *---------------------------------------------------------------*/
int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
		       unsigned cookie)
{
	int r;
	unsigned noio_flag;
	char udev_cookie[DM_COOKIE_LENGTH];
	char *envp[] = { udev_cookie, NULL };

	noio_flag = memalloc_noio_save();

	if (!cookie)
		r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
	else {
		snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
			 DM_COOKIE_ENV_VAR_NAME, cookie);
		r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
				       action, envp);
	}

	memalloc_noio_restore(noio_flag);

	return r;
}

uint32_t dm_next_uevent_seq(struct mapped_device *md)
{
	return atomic_add_return(1, &md->uevent_seq);
}

uint32_t dm_get_event_nr(struct mapped_device *md)
{
	return atomic_read(&md->event_nr);
}

int dm_wait_event(struct mapped_device *md, int event_nr)
{
	return wait_event_interruptible(md->eventq,
			(event_nr != atomic_read(&md->event_nr)));
}

void dm_uevent_add(struct mapped_device *md, struct list_head *elist)
{
	unsigned long flags;

	spin_lock_irqsave(&md->uevent_lock, flags);
	list_add(elist, &md->uevent_list);
	spin_unlock_irqrestore(&md->uevent_lock, flags);
}

/*
 * The gendisk is only valid as long as you have a reference
 * count on 'md'.
 */
struct gendisk *dm_disk(struct mapped_device *md)
{
	return md->disk;
}
EXPORT_SYMBOL_GPL(dm_disk);

struct kobject *dm_kobject(struct mapped_device *md)
{
	return &md->kobj_holder.kobj;
}

struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
{
	struct mapped_device *md;

	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);

	spin_lock(&_minor_lock);
	if (test_bit(DMF_FREEING, &md->flags) || dm_deleting_md(md)) {
		md = NULL;
		goto out;
	}
	dm_get(md);
out:
	spin_unlock(&_minor_lock);

	return md;
}

int dm_suspended_md(struct mapped_device *md)
{
	return test_bit(DMF_SUSPENDED, &md->flags);
}

static int dm_post_suspending_md(struct mapped_device *md)
{
	return test_bit(DMF_POST_SUSPENDING, &md->flags);
}

int dm_suspended_internally_md(struct mapped_device *md)
{
	return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
}

int dm_test_deferred_remove_flag(struct mapped_device *md)
{
	return test_bit(DMF_DEFERRED_REMOVE, &md->flags);
}

int dm_suspended(struct dm_target *ti)
{
	return dm_suspended_md(dm_table_get_md(ti->table));
}
EXPORT_SYMBOL_GPL(dm_suspended);

int dm_post_suspending(struct dm_target *ti)
{
	return dm_post_suspending_md(dm_table_get_md(ti->table));
}
EXPORT_SYMBOL_GPL(dm_post_suspending);

int dm_noflush_suspending(struct dm_target *ti)
{
	return __noflush_suspending(dm_table_get_md(ti->table));
}
EXPORT_SYMBOL_GPL(dm_noflush_suspending);

struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_queue_mode type,
					    unsigned integrity, unsigned per_io_data_size,
					    unsigned min_pool_size)
{
	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
	unsigned int pool_size = 0;
	unsigned int front_pad, io_front_pad;
	int ret;

	if (!pools)
		return NULL;

	switch (type) {
	case DM_TYPE_BIO_BASED:
	case DM_TYPE_DAX_BIO_BASED:
	case DM_TYPE_NVME_BIO_BASED:
		pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
		io_front_pad = roundup(front_pad,  __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
		ret = bioset_init(&pools->io_bs, pool_size, io_front_pad, 0);
		if (ret)
			goto out;
		if (integrity && bioset_integrity_create(&pools->io_bs, pool_size))
			goto out;
		break;
	case DM_TYPE_REQUEST_BASED:
		pool_size = max(dm_get_reserved_rq_based_ios(), min_pool_size);
		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
		/* per_io_data_size is used for blk-mq pdu at queue allocation */
		break;
	default:
		BUG();
	}

	ret = bioset_init(&pools->bs, pool_size, front_pad, 0);
	if (ret)
		goto out;

	if (integrity && bioset_integrity_create(&pools->bs, pool_size))
		goto out;

	return pools;

out:
	dm_free_md_mempools(pools);

	return NULL;
}

void dm_free_md_mempools(struct dm_md_mempools *pools)
{
	if (!pools)
		return;

	bioset_exit(&pools->bs);
	bioset_exit(&pools->io_bs);

	kfree(pools);
}

struct dm_pr {
	u64	old_key;
	u64	new_key;
	u32	flags;
	bool	fail_early;
};

static int dm_call_pr(struct block_device *bdev, iterate_devices_callout_fn fn,
		      void *data)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	struct dm_table *table;
	struct dm_target *ti;
	int ret = -ENOTTY, srcu_idx;

	table = dm_get_live_table(md, &srcu_idx);
	if (!table || !dm_table_get_size(table))
		goto out;

	/* We only support devices that have a single target */
	if (dm_table_get_num_targets(table) != 1)
		goto out;
	ti = dm_table_get_target(table, 0);

	ret = -EINVAL;
	if (!ti->type->iterate_devices)
		goto out;

	ret = ti->type->iterate_devices(ti, fn, data);
out:
	dm_put_live_table(md, srcu_idx);
	return ret;
}

/*
 * For register / unregister we need to manually call out to every path.
 */
static int __dm_pr_register(struct dm_target *ti, struct dm_dev *dev,
			    sector_t start, sector_t len, void *data)
{
	struct dm_pr *pr = data;
	const struct pr_ops *ops = dev->bdev->bd_disk->fops->pr_ops;

	if (!ops || !ops->pr_register)
		return -EOPNOTSUPP;
	return ops->pr_register(dev->bdev, pr->old_key, pr->new_key, pr->flags);
}

static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
			  u32 flags)
{
	struct dm_pr pr = {
		.old_key	= old_key,
		.new_key	= new_key,
		.flags		= flags,
		.fail_early	= true,
	};
	int ret;

	ret = dm_call_pr(bdev, __dm_pr_register, &pr);
	if (ret && new_key) {
		/* unregister all paths if we failed to register any path */
		pr.old_key = new_key;
		pr.new_key = 0;
		pr.flags = 0;
		pr.fail_early = false;
		dm_call_pr(bdev, __dm_pr_register, &pr);
	}

	return ret;
}

static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
			 u32 flags)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	const struct pr_ops *ops;
	int r, srcu_idx;

	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
	if (r < 0)
		goto out;

	ops = bdev->bd_disk->fops->pr_ops;
	if (ops && ops->pr_reserve)
		r = ops->pr_reserve(bdev, key, type, flags);
	else
		r = -EOPNOTSUPP;
out:
	dm_unprepare_ioctl(md, srcu_idx);
	return r;
}

static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	const struct pr_ops *ops;
	int r, srcu_idx;

	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
	if (r < 0)
		goto out;

	ops = bdev->bd_disk->fops->pr_ops;
	if (ops && ops->pr_release)
		r = ops->pr_release(bdev, key, type);
	else
		r = -EOPNOTSUPP;
out:
	dm_unprepare_ioctl(md, srcu_idx);
	return r;
}

static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
			 enum pr_type type, bool abort)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	const struct pr_ops *ops;
	int r, srcu_idx;

	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
	if (r < 0)
		goto out;

	ops = bdev->bd_disk->fops->pr_ops;
	if (ops && ops->pr_preempt)
		r = ops->pr_preempt(bdev, old_key, new_key, type, abort);
	else
		r = -EOPNOTSUPP;
out:
	dm_unprepare_ioctl(md, srcu_idx);
	return r;
}

static int dm_pr_clear(struct block_device *bdev, u64 key)
{
	struct mapped_device *md = bdev->bd_disk->private_data;
	const struct pr_ops *ops;
	int r, srcu_idx;

	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
	if (r < 0)
		goto out;

	ops = bdev->bd_disk->fops->pr_ops;
	if (ops && ops->pr_clear)
		r = ops->pr_clear(bdev, key);
	else
		r = -EOPNOTSUPP;
out:
	dm_unprepare_ioctl(md, srcu_idx);
	return r;
}

static const struct pr_ops dm_pr_ops = {
	.pr_register	= dm_pr_register,
	.pr_reserve	= dm_pr_reserve,
	.pr_release	= dm_pr_release,
	.pr_preempt	= dm_pr_preempt,
	.pr_clear	= dm_pr_clear,
};

static const struct block_device_operations dm_blk_dops = {
	.open = dm_blk_open,
	.release = dm_blk_close,
	.ioctl = dm_blk_ioctl,
	.getgeo = dm_blk_getgeo,
	.report_zones = dm_blk_report_zones,
	.pr_ops = &dm_pr_ops,
	.owner = THIS_MODULE
};

static const struct dax_operations dm_dax_ops = {
	.direct_access = dm_dax_direct_access,
	.dax_supported = dm_dax_supported,
	.copy_from_iter = dm_dax_copy_from_iter,
	.copy_to_iter = dm_dax_copy_to_iter,
};

/*
 * module hooks
 */
module_init(dm_init);
module_exit(dm_exit);

module_param(major, uint, 0);
MODULE_PARM_DESC(major, "The major number of the device mapper");

module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");

module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");

module_param(swap_bios, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(swap_bios, "Maximum allowed inflight swap IOs");

MODULE_DESCRIPTION(DM_NAME " driver");
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");