summaryrefslogtreecommitdiffstats
path: root/drivers/block/ublk_drv.c
blob: bea3d5cf8a83487909270d5f2398267250507a31 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Userspace block device - block device which IO is handled from userspace
 *
 * Take full use of io_uring passthrough command for communicating with
 * ublk userspace daemon(ublksrvd) for handling basic IO request.
 *
 * Copyright 2022 Ming Lei <ming.lei@redhat.com>
 *
 * (part of code stolen from loop.c)
 */
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/mutex.h>
#include <linux/writeback.h>
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/sysfs.h>
#include <linux/miscdevice.h>
#include <linux/falloc.h>
#include <linux/uio.h>
#include <linux/ioprio.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/cdev.h>
#include <linux/io_uring/cmd.h>
#include <linux/blk-mq.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <asm/page.h>
#include <linux/task_work.h>
#include <linux/namei.h>
#include <linux/kref.h>
#include <uapi/linux/ublk_cmd.h>

#define UBLK_MINORS		(1U << MINORBITS)

/* All UBLK_F_* have to be included into UBLK_F_ALL */
#define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \
		| UBLK_F_URING_CMD_COMP_IN_TASK \
		| UBLK_F_NEED_GET_DATA \
		| UBLK_F_USER_RECOVERY \
		| UBLK_F_USER_RECOVERY_REISSUE \
		| UBLK_F_UNPRIVILEGED_DEV \
		| UBLK_F_CMD_IOCTL_ENCODE \
		| UBLK_F_USER_COPY \
		| UBLK_F_ZONED)

/* All UBLK_PARAM_TYPE_* should be included here */
#define UBLK_PARAM_TYPE_ALL                                \
	(UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD | \
	 UBLK_PARAM_TYPE_DEVT | UBLK_PARAM_TYPE_ZONED)

struct ublk_rq_data {
	struct llist_node node;

	struct kref ref;
	__u64 sector;
	__u32 operation;
	__u32 nr_zones;
};

struct ublk_uring_cmd_pdu {
	struct ublk_queue *ubq;
	u16 tag;
};

/*
 * io command is active: sqe cmd is received, and its cqe isn't done
 *
 * If the flag is set, the io command is owned by ublk driver, and waited
 * for incoming blk-mq request from the ublk block device.
 *
 * If the flag is cleared, the io command will be completed, and owned by
 * ublk server.
 */
#define UBLK_IO_FLAG_ACTIVE	0x01

/*
 * IO command is completed via cqe, and it is being handled by ublksrv, and
 * not committed yet
 *
 * Basically exclusively with UBLK_IO_FLAG_ACTIVE, so can be served for
 * cross verification
 */
#define UBLK_IO_FLAG_OWNED_BY_SRV 0x02

/*
 * IO command is aborted, so this flag is set in case of
 * !UBLK_IO_FLAG_ACTIVE.
 *
 * After this flag is observed, any pending or new incoming request
 * associated with this io command will be failed immediately
 */
#define UBLK_IO_FLAG_ABORTED 0x04

/*
 * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires
 * get data buffer address from ublksrv.
 *
 * Then, bio data could be copied into this data buffer for a WRITE request
 * after the IO command is issued again and UBLK_IO_FLAG_NEED_GET_DATA is unset.
 */
#define UBLK_IO_FLAG_NEED_GET_DATA 0x08

/* atomic RW with ubq->cancel_lock */
#define UBLK_IO_FLAG_CANCELED	0x80000000

struct ublk_io {
	/* userspace buffer address from io cmd */
	__u64	addr;
	unsigned int flags;
	int res;

	struct io_uring_cmd *cmd;
};

struct ublk_queue {
	int q_id;
	int q_depth;

	unsigned long flags;
	struct task_struct	*ubq_daemon;
	char *io_cmd_buf;

	struct llist_head	io_cmds;

	unsigned long io_addr;	/* mapped vm address */
	unsigned int max_io_sz;
	bool force_abort;
	bool timeout;
	bool canceling;
	unsigned short nr_io_ready;	/* how many ios setup */
	spinlock_t		cancel_lock;
	struct ublk_device *dev;
	struct ublk_io ios[];
};

struct ublk_device {
	struct gendisk		*ub_disk;

	char	*__queues;

	unsigned int	queue_size;
	struct ublksrv_ctrl_dev_info	dev_info;

	struct blk_mq_tag_set	tag_set;

	struct cdev		cdev;
	struct device		cdev_dev;

#define UB_STATE_OPEN		0
#define UB_STATE_USED		1
#define UB_STATE_DELETED	2
	unsigned long		state;
	int			ub_number;

	struct mutex		mutex;

	spinlock_t		lock;
	struct mm_struct	*mm;

	struct ublk_params	params;

	struct completion	completion;
	unsigned int		nr_queues_ready;
	unsigned int		nr_privileged_daemon;

	struct work_struct	quiesce_work;
	struct work_struct	stop_work;
};

/* header of ublk_params */
struct ublk_params_header {
	__u32	len;
	__u32	types;
};

static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq);

static inline unsigned int ublk_req_build_flags(struct request *req);
static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
						   int tag);
static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
{
	return ub->dev_info.flags & UBLK_F_USER_COPY;
}

static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
{
	return ub->dev_info.flags & UBLK_F_ZONED;
}

static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq)
{
	return ubq->flags & UBLK_F_ZONED;
}

#ifdef CONFIG_BLK_DEV_ZONED

static int ublk_get_nr_zones(const struct ublk_device *ub)
{
	const struct ublk_param_basic *p = &ub->params.basic;

	/* Zone size is a power of 2 */
	return p->dev_sectors >> ilog2(p->chunk_sectors);
}

static int ublk_revalidate_disk_zones(struct ublk_device *ub)
{
	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
}

static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
{
	const struct ublk_param_zoned *p = &ub->params.zoned;
	int nr_zones;

	if (!ublk_dev_is_zoned(ub))
		return -EINVAL;

	if (!p->max_zone_append_sectors)
		return -EINVAL;

	nr_zones = ublk_get_nr_zones(ub);

	if (p->max_active_zones > nr_zones)
		return -EINVAL;

	if (p->max_open_zones > nr_zones)
		return -EINVAL;

	return 0;
}

static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
{
	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
	blk_queue_required_elevator_features(ub->ub_disk->queue,
					     ELEVATOR_F_ZBD_SEQ_WRITE);
	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
}

/* Based on virtblk_alloc_report_buffer */
static void *ublk_alloc_report_buffer(struct ublk_device *ublk,
				      unsigned int nr_zones, size_t *buflen)
{
	struct request_queue *q = ublk->ub_disk->queue;
	size_t bufsize;
	void *buf;

	nr_zones = min_t(unsigned int, nr_zones,
			 ublk->ub_disk->nr_zones);

	bufsize = nr_zones * sizeof(struct blk_zone);
	bufsize =
		min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT);

	while (bufsize >= sizeof(struct blk_zone)) {
		buf = kvmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
		if (buf) {
			*buflen = bufsize;
			return buf;
		}
		bufsize >>= 1;
	}

	*buflen = 0;
	return NULL;
}

static int ublk_report_zones(struct gendisk *disk, sector_t sector,
		      unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct ublk_device *ub = disk->private_data;
	unsigned int zone_size_sectors = disk->queue->limits.chunk_sectors;
	unsigned int first_zone = sector >> ilog2(zone_size_sectors);
	unsigned int done_zones = 0;
	unsigned int max_zones_per_request;
	int ret;
	struct blk_zone *buffer;
	size_t buffer_length;

	nr_zones = min_t(unsigned int, ub->ub_disk->nr_zones - first_zone,
			 nr_zones);

	buffer = ublk_alloc_report_buffer(ub, nr_zones, &buffer_length);
	if (!buffer)
		return -ENOMEM;

	max_zones_per_request = buffer_length / sizeof(struct blk_zone);

	while (done_zones < nr_zones) {
		unsigned int remaining_zones = nr_zones - done_zones;
		unsigned int zones_in_request =
			min_t(unsigned int, remaining_zones, max_zones_per_request);
		struct request *req;
		struct ublk_rq_data *pdu;
		blk_status_t status;

		memset(buffer, 0, buffer_length);

		req = blk_mq_alloc_request(disk->queue, REQ_OP_DRV_IN, 0);
		if (IS_ERR(req)) {
			ret = PTR_ERR(req);
			goto out;
		}

		pdu = blk_mq_rq_to_pdu(req);
		pdu->operation = UBLK_IO_OP_REPORT_ZONES;
		pdu->sector = sector;
		pdu->nr_zones = zones_in_request;

		ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length,
					GFP_KERNEL);
		if (ret) {
			blk_mq_free_request(req);
			goto out;
		}

		status = blk_execute_rq(req, 0);
		ret = blk_status_to_errno(status);
		blk_mq_free_request(req);
		if (ret)
			goto out;

		for (unsigned int i = 0; i < zones_in_request; i++) {
			struct blk_zone *zone = buffer + i;

			/* A zero length zone means no more zones in this response */
			if (!zone->len)
				break;

			ret = cb(zone, i, data);
			if (ret)
				goto out;

			done_zones++;
			sector += zone_size_sectors;

		}
	}

	ret = done_zones;

out:
	kvfree(buffer);
	return ret;
}

static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
					 struct request *req)
{
	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
	struct ublk_io *io = &ubq->ios[req->tag];
	struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req);
	u32 ublk_op;

	switch (req_op(req)) {
	case REQ_OP_ZONE_OPEN:
		ublk_op = UBLK_IO_OP_ZONE_OPEN;
		break;
	case REQ_OP_ZONE_CLOSE:
		ublk_op = UBLK_IO_OP_ZONE_CLOSE;
		break;
	case REQ_OP_ZONE_FINISH:
		ublk_op = UBLK_IO_OP_ZONE_FINISH;
		break;
	case REQ_OP_ZONE_RESET:
		ublk_op = UBLK_IO_OP_ZONE_RESET;
		break;
	case REQ_OP_ZONE_APPEND:
		ublk_op = UBLK_IO_OP_ZONE_APPEND;
		break;
	case REQ_OP_ZONE_RESET_ALL:
		ublk_op = UBLK_IO_OP_ZONE_RESET_ALL;
		break;
	case REQ_OP_DRV_IN:
		ublk_op = pdu->operation;
		switch (ublk_op) {
		case UBLK_IO_OP_REPORT_ZONES:
			iod->op_flags = ublk_op | ublk_req_build_flags(req);
			iod->nr_zones = pdu->nr_zones;
			iod->start_sector = pdu->sector;
			return BLK_STS_OK;
		default:
			return BLK_STS_IOERR;
		}
	case REQ_OP_DRV_OUT:
		/* We do not support drv_out */
		return BLK_STS_NOTSUPP;
	default:
		return BLK_STS_IOERR;
	}

	iod->op_flags = ublk_op | ublk_req_build_flags(req);
	iod->nr_sectors = blk_rq_sectors(req);
	iod->start_sector = blk_rq_pos(req);
	iod->addr = io->addr;

	return BLK_STS_OK;
}

#else

#define ublk_report_zones (NULL)

static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
{
	return -EOPNOTSUPP;
}

static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
{
}

static int ublk_revalidate_disk_zones(struct ublk_device *ub)
{
	return 0;
}

static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
					 struct request *req)
{
	return BLK_STS_NOTSUPP;
}

#endif

static inline void __ublk_complete_rq(struct request *req);
static void ublk_complete_rq(struct kref *ref);

static dev_t ublk_chr_devt;
static const struct class ublk_chr_class = {
	.name = "ublk-char",
};

static DEFINE_IDR(ublk_index_idr);
static DEFINE_SPINLOCK(ublk_idr_lock);
static wait_queue_head_t ublk_idr_wq;	/* wait until one idr is freed */

static DEFINE_MUTEX(ublk_ctl_mutex);

/*
 * Max ublk devices allowed to add
 *
 * It can be extended to one per-user limit in future or even controlled
 * by cgroup.
 */
#define UBLK_MAX_UBLKS UBLK_MINORS
static unsigned int ublks_max = 64;
static unsigned int ublks_added;	/* protected by ublk_ctl_mutex */

static struct miscdevice ublk_misc;

static inline unsigned ublk_pos_to_hwq(loff_t pos)
{
	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) &
		UBLK_QID_BITS_MASK;
}

static inline unsigned ublk_pos_to_buf_off(loff_t pos)
{
	return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK;
}

static inline unsigned ublk_pos_to_tag(loff_t pos)
{
	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) &
		UBLK_TAG_BITS_MASK;
}

static void ublk_dev_param_basic_apply(struct ublk_device *ub)
{
	struct request_queue *q = ub->ub_disk->queue;
	const struct ublk_param_basic *p = &ub->params.basic;

	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
			p->attrs & UBLK_ATTR_FUA);
	if (p->attrs & UBLK_ATTR_ROTATIONAL)
		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
	else
		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);

	if (p->attrs & UBLK_ATTR_READ_ONLY)
		set_disk_ro(ub->ub_disk, true);

	set_capacity(ub->ub_disk, p->dev_sectors);
}

static int ublk_validate_params(const struct ublk_device *ub)
{
	/* basic param is the only one which must be set */
	if (ub->params.types & UBLK_PARAM_TYPE_BASIC) {
		const struct ublk_param_basic *p = &ub->params.basic;

		if (p->logical_bs_shift > PAGE_SHIFT || p->logical_bs_shift < 9)
			return -EINVAL;

		if (p->logical_bs_shift > p->physical_bs_shift)
			return -EINVAL;

		if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9))
			return -EINVAL;

		if (ublk_dev_is_zoned(ub) && !p->chunk_sectors)
			return -EINVAL;
	} else
		return -EINVAL;

	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
		const struct ublk_param_discard *p = &ub->params.discard;

		/* So far, only support single segment discard */
		if (p->max_discard_sectors && p->max_discard_segments != 1)
			return -EINVAL;

		if (!p->discard_granularity)
			return -EINVAL;
	}

	/* dev_t is read-only */
	if (ub->params.types & UBLK_PARAM_TYPE_DEVT)
		return -EINVAL;

	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
		return ublk_dev_param_zoned_validate(ub);
	else if (ublk_dev_is_zoned(ub))
		return -EINVAL;

	return 0;
}

static void ublk_apply_params(struct ublk_device *ub)
{
	ublk_dev_param_basic_apply(ub);

	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
		ublk_dev_param_zoned_apply(ub);
}

static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
{
	return ubq->flags & UBLK_F_USER_COPY;
}

static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
{
	/*
	 * read()/write() is involved in user copy, so request reference
	 * has to be grabbed
	 */
	return ublk_support_user_copy(ubq);
}

static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
		struct request *req)
{
	if (ublk_need_req_ref(ubq)) {
		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);

		kref_init(&data->ref);
	}
}

static inline bool ublk_get_req_ref(const struct ublk_queue *ubq,
		struct request *req)
{
	if (ublk_need_req_ref(ubq)) {
		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);

		return kref_get_unless_zero(&data->ref);
	}

	return true;
}

static inline void ublk_put_req_ref(const struct ublk_queue *ubq,
		struct request *req)
{
	if (ublk_need_req_ref(ubq)) {
		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);

		kref_put(&data->ref, ublk_complete_rq);
	} else {
		__ublk_complete_rq(req);
	}
}

static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
{
	return ubq->flags & UBLK_F_NEED_GET_DATA;
}

/* Called in slow path only, keep it noinline for trace purpose */
static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub)
{
	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
		return ub;
	return NULL;
}

/* Called in slow path only, keep it noinline for trace purpose */
static noinline void ublk_put_device(struct ublk_device *ub)
{
	put_device(&ub->cdev_dev);
}

static inline struct ublk_queue *ublk_get_queue(struct ublk_device *dev,
		int qid)
{
       return (struct ublk_queue *)&(dev->__queues[qid * dev->queue_size]);
}

static inline bool ublk_rq_has_data(const struct request *rq)
{
	return bio_has_data(rq->bio);
}

static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
		int tag)
{
	return (struct ublksrv_io_desc *)
		&(ubq->io_cmd_buf[tag * sizeof(struct ublksrv_io_desc)]);
}

static inline char *ublk_queue_cmd_buf(struct ublk_device *ub, int q_id)
{
	return ublk_get_queue(ub, q_id)->io_cmd_buf;
}

static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
{
	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);

	return round_up(ubq->q_depth * sizeof(struct ublksrv_io_desc),
			PAGE_SIZE);
}

static inline bool ublk_queue_can_use_recovery_reissue(
		struct ublk_queue *ubq)
{
	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
}

static inline bool ublk_queue_can_use_recovery(
		struct ublk_queue *ubq)
{
	return ubq->flags & UBLK_F_USER_RECOVERY;
}

static inline bool ublk_can_use_recovery(struct ublk_device *ub)
{
	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
}

static void ublk_free_disk(struct gendisk *disk)
{
	struct ublk_device *ub = disk->private_data;

	clear_bit(UB_STATE_USED, &ub->state);
	ublk_put_device(ub);
}

static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
		unsigned int *owner_gid)
{
	kuid_t uid;
	kgid_t gid;

	current_uid_gid(&uid, &gid);

	*owner_uid = from_kuid(&init_user_ns, uid);
	*owner_gid = from_kgid(&init_user_ns, gid);
}

static int ublk_open(struct gendisk *disk, blk_mode_t mode)
{
	struct ublk_device *ub = disk->private_data;

	if (capable(CAP_SYS_ADMIN))
		return 0;

	/*
	 * If it is one unprivileged device, only owner can open
	 * the disk. Otherwise it could be one trap made by one
	 * evil user who grants this disk's privileges to other
	 * users deliberately.
	 *
	 * This way is reasonable too given anyone can create
	 * unprivileged device, and no need other's grant.
	 */
	if (ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV) {
		unsigned int curr_uid, curr_gid;

		ublk_store_owner_uid_gid(&curr_uid, &curr_gid);

		if (curr_uid != ub->dev_info.owner_uid || curr_gid !=
				ub->dev_info.owner_gid)
			return -EPERM;
	}

	return 0;
}

static const struct block_device_operations ub_fops = {
	.owner =	THIS_MODULE,
	.open =		ublk_open,
	.free_disk =	ublk_free_disk,
	.report_zones =	ublk_report_zones,
};

#define UBLK_MAX_PIN_PAGES	32

struct ublk_io_iter {
	struct page *pages[UBLK_MAX_PIN_PAGES];
	struct bio *bio;
	struct bvec_iter iter;
};

/* return how many pages are copied */
static void ublk_copy_io_pages(struct ublk_io_iter *data,
		size_t total, size_t pg_off, int dir)
{
	unsigned done = 0;
	unsigned pg_idx = 0;

	while (done < total) {
		struct bio_vec bv = bio_iter_iovec(data->bio, data->iter);
		unsigned int bytes = min3(bv.bv_len, (unsigned)total - done,
				(unsigned)(PAGE_SIZE - pg_off));
		void *bv_buf = bvec_kmap_local(&bv);
		void *pg_buf = kmap_local_page(data->pages[pg_idx]);

		if (dir == ITER_DEST)
			memcpy(pg_buf + pg_off, bv_buf, bytes);
		else
			memcpy(bv_buf, pg_buf + pg_off, bytes);

		kunmap_local(pg_buf);
		kunmap_local(bv_buf);

		/* advance page array */
		pg_off += bytes;
		if (pg_off == PAGE_SIZE) {
			pg_idx += 1;
			pg_off = 0;
		}

		done += bytes;

		/* advance bio */
		bio_advance_iter_single(data->bio, &data->iter, bytes);
		if (!data->iter.bi_size) {
			data->bio = data->bio->bi_next;
			if (data->bio == NULL)
				break;
			data->iter = data->bio->bi_iter;
		}
	}
}

static bool ublk_advance_io_iter(const struct request *req,
		struct ublk_io_iter *iter, unsigned int offset)
{
	struct bio *bio = req->bio;

	for_each_bio(bio) {
		if (bio->bi_iter.bi_size > offset) {
			iter->bio = bio;
			iter->iter = bio->bi_iter;
			bio_advance_iter(iter->bio, &iter->iter, offset);
			return true;
		}
		offset -= bio->bi_iter.bi_size;
	}
	return false;
}

/*
 * Copy data between request pages and io_iter, and 'offset'
 * is the start point of linear offset of request.
 */
static size_t ublk_copy_user_pages(const struct request *req,
		unsigned offset, struct iov_iter *uiter, int dir)
{
	struct ublk_io_iter iter;
	size_t done = 0;

	if (!ublk_advance_io_iter(req, &iter, offset))
		return 0;

	while (iov_iter_count(uiter) && iter.bio) {
		unsigned nr_pages;
		ssize_t len;
		size_t off;
		int i;

		len = iov_iter_get_pages2(uiter, iter.pages,
				iov_iter_count(uiter),
				UBLK_MAX_PIN_PAGES, &off);
		if (len <= 0)
			return done;

		ublk_copy_io_pages(&iter, len, off, dir);
		nr_pages = DIV_ROUND_UP(len + off, PAGE_SIZE);
		for (i = 0; i < nr_pages; i++) {
			if (dir == ITER_DEST)
				set_page_dirty(iter.pages[i]);
			put_page(iter.pages[i]);
		}
		done += len;
	}

	return done;
}

static inline bool ublk_need_map_req(const struct request *req)
{
	return ublk_rq_has_data(req) && req_op(req) == REQ_OP_WRITE;
}

static inline bool ublk_need_unmap_req(const struct request *req)
{
	return ublk_rq_has_data(req) &&
	       (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN);
}

static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
		struct ublk_io *io)
{
	const unsigned int rq_bytes = blk_rq_bytes(req);

	if (ublk_support_user_copy(ubq))
		return rq_bytes;

	/*
	 * no zero copy, we delay copy WRITE request data into ublksrv
	 * context and the big benefit is that pinning pages in current
	 * context is pretty fast, see ublk_pin_user_pages
	 */
	if (ublk_need_map_req(req)) {
		struct iov_iter iter;
		const int dir = ITER_DEST;

		import_ubuf(dir, u64_to_user_ptr(io->addr), rq_bytes, &iter);
		return ublk_copy_user_pages(req, 0, &iter, dir);
	}
	return rq_bytes;
}

static int ublk_unmap_io(const struct ublk_queue *ubq,
		const struct request *req,
		struct ublk_io *io)
{
	const unsigned int rq_bytes = blk_rq_bytes(req);

	if (ublk_support_user_copy(ubq))
		return rq_bytes;

	if (ublk_need_unmap_req(req)) {
		struct iov_iter iter;
		const int dir = ITER_SOURCE;

		WARN_ON_ONCE(io->res > rq_bytes);

		import_ubuf(dir, u64_to_user_ptr(io->addr), io->res, &iter);
		return ublk_copy_user_pages(req, 0, &iter, dir);
	}
	return rq_bytes;
}

static inline unsigned int ublk_req_build_flags(struct request *req)
{
	unsigned flags = 0;

	if (req->cmd_flags & REQ_FAILFAST_DEV)
		flags |= UBLK_IO_F_FAILFAST_DEV;

	if (req->cmd_flags & REQ_FAILFAST_TRANSPORT)
		flags |= UBLK_IO_F_FAILFAST_TRANSPORT;

	if (req->cmd_flags & REQ_FAILFAST_DRIVER)
		flags |= UBLK_IO_F_FAILFAST_DRIVER;

	if (req->cmd_flags & REQ_META)
		flags |= UBLK_IO_F_META;

	if (req->cmd_flags & REQ_FUA)
		flags |= UBLK_IO_F_FUA;

	if (req->cmd_flags & REQ_NOUNMAP)
		flags |= UBLK_IO_F_NOUNMAP;

	if (req->cmd_flags & REQ_SWAP)
		flags |= UBLK_IO_F_SWAP;

	return flags;
}

static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req)
{
	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
	struct ublk_io *io = &ubq->ios[req->tag];
	enum req_op op = req_op(req);
	u32 ublk_op;

	if (!ublk_queue_is_zoned(ubq) &&
	    (op_is_zone_mgmt(op) || op == REQ_OP_ZONE_APPEND))
		return BLK_STS_IOERR;

	switch (req_op(req)) {
	case REQ_OP_READ:
		ublk_op = UBLK_IO_OP_READ;
		break;
	case REQ_OP_WRITE:
		ublk_op = UBLK_IO_OP_WRITE;
		break;
	case REQ_OP_FLUSH:
		ublk_op = UBLK_IO_OP_FLUSH;
		break;
	case REQ_OP_DISCARD:
		ublk_op = UBLK_IO_OP_DISCARD;
		break;
	case REQ_OP_WRITE_ZEROES:
		ublk_op = UBLK_IO_OP_WRITE_ZEROES;
		break;
	default:
		if (ublk_queue_is_zoned(ubq))
			return ublk_setup_iod_zoned(ubq, req);
		return BLK_STS_IOERR;
	}

	/* need to translate since kernel may change */
	iod->op_flags = ublk_op | ublk_req_build_flags(req);
	iod->nr_sectors = blk_rq_sectors(req);
	iod->start_sector = blk_rq_pos(req);
	iod->addr = io->addr;

	return BLK_STS_OK;
}

static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
		struct io_uring_cmd *ioucmd)
{
	return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu;
}

static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
{
	return ubq->ubq_daemon->flags & PF_EXITING;
}

/* todo: handle partial completion */
static inline void __ublk_complete_rq(struct request *req)
{
	struct ublk_queue *ubq = req->mq_hctx->driver_data;
	struct ublk_io *io = &ubq->ios[req->tag];
	unsigned int unmapped_bytes;
	blk_status_t res = BLK_STS_OK;

	/* called from ublk_abort_queue() code path */
	if (io->flags & UBLK_IO_FLAG_ABORTED) {
		res = BLK_STS_IOERR;
		goto exit;
	}

	/* failed read IO if nothing is read */
	if (!io->res && req_op(req) == REQ_OP_READ)
		io->res = -EIO;

	if (io->res < 0) {
		res = errno_to_blk_status(io->res);
		goto exit;
	}

	/*
	 * FLUSH, DISCARD or WRITE_ZEROES usually won't return bytes returned, so end them
	 * directly.
	 *
	 * Both the two needn't unmap.
	 */
	if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE &&
	    req_op(req) != REQ_OP_DRV_IN)
		goto exit;

	/* for READ request, writing data in iod->addr to rq buffers */
	unmapped_bytes = ublk_unmap_io(ubq, req, io);

	/*
	 * Extremely impossible since we got data filled in just before
	 *
	 * Re-read simply for this unlikely case.
	 */
	if (unlikely(unmapped_bytes < io->res))
		io->res = unmapped_bytes;

	if (blk_update_request(req, BLK_STS_OK, io->res))
		blk_mq_requeue_request(req, true);
	else
		__blk_mq_end_request(req, BLK_STS_OK);

	return;
exit:
	blk_mq_end_request(req, res);
}

static void ublk_complete_rq(struct kref *ref)
{
	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
			ref);
	struct request *req = blk_mq_rq_from_pdu(data);

	__ublk_complete_rq(req);
}

/*
 * Since __ublk_rq_task_work always fails requests immediately during
 * exiting, __ublk_fail_req() is only called from abort context during
 * exiting. So lock is unnecessary.
 *
 * Also aborting may not be started yet, keep in mind that one failed
 * request may be issued by block layer again.
 */
static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
		struct request *req)
{
	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);

	if (ublk_queue_can_use_recovery_reissue(ubq))
		blk_mq_requeue_request(req, false);
	else
		ublk_put_req_ref(ubq, req);
}

static void ubq_complete_io_cmd(struct ublk_io *io, int res,
				unsigned issue_flags)
{
	/* mark this cmd owned by ublksrv */
	io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV;

	/*
	 * clear ACTIVE since we are done with this sqe/cmd slot
	 * We can only accept io cmd in case of being not active.
	 */
	io->flags &= ~UBLK_IO_FLAG_ACTIVE;

	/* tell ublksrv one io request is coming */
	io_uring_cmd_done(io->cmd, res, 0, issue_flags);
}

#define UBLK_REQUEUE_DELAY_MS	3

static inline void __ublk_abort_rq(struct ublk_queue *ubq,
		struct request *rq)
{
	/* We cannot process this rq so just requeue it. */
	if (ublk_queue_can_use_recovery(ubq))
		blk_mq_requeue_request(rq, false);
	else
		blk_mq_end_request(rq, BLK_STS_IOERR);
}

static inline void __ublk_rq_task_work(struct request *req,
				       unsigned issue_flags)
{
	struct ublk_queue *ubq = req->mq_hctx->driver_data;
	int tag = req->tag;
	struct ublk_io *io = &ubq->ios[tag];
	unsigned int mapped_bytes;

	pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n",
			__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
			ublk_get_iod(ubq, req->tag)->addr);

	/*
	 * Task is exiting if either:
	 *
	 * (1) current != ubq_daemon.
	 * io_uring_cmd_complete_in_task() tries to run task_work
	 * in a workqueue if ubq_daemon(cmd's task) is PF_EXITING.
	 *
	 * (2) current->flags & PF_EXITING.
	 */
	if (unlikely(current != ubq->ubq_daemon || current->flags & PF_EXITING)) {
		__ublk_abort_rq(ubq, req);
		return;
	}

	if (ublk_need_get_data(ubq) && ublk_need_map_req(req)) {
		/*
		 * We have not handled UBLK_IO_NEED_GET_DATA command yet,
		 * so immepdately pass UBLK_IO_RES_NEED_GET_DATA to ublksrv
		 * and notify it.
		 */
		if (!(io->flags & UBLK_IO_FLAG_NEED_GET_DATA)) {
			io->flags |= UBLK_IO_FLAG_NEED_GET_DATA;
			pr_devel("%s: need get data. op %d, qid %d tag %d io_flags %x\n",
					__func__, io->cmd->cmd_op, ubq->q_id,
					req->tag, io->flags);
			ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA, issue_flags);
			return;
		}
		/*
		 * We have handled UBLK_IO_NEED_GET_DATA command,
		 * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just
		 * do the copy work.
		 */
		io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA;
		/* update iod->addr because ublksrv may have passed a new io buffer */
		ublk_get_iod(ubq, req->tag)->addr = io->addr;
		pr_devel("%s: update iod->addr: op %d, qid %d tag %d io_flags %x addr %llx\n",
				__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
				ublk_get_iod(ubq, req->tag)->addr);
	}

	mapped_bytes = ublk_map_io(ubq, req, io);

	/* partially mapped, update io descriptor */
	if (unlikely(mapped_bytes != blk_rq_bytes(req))) {
		/*
		 * Nothing mapped, retry until we succeed.
		 *
		 * We may never succeed in mapping any bytes here because
		 * of OOM. TODO: reserve one buffer with single page pinned
		 * for providing forward progress guarantee.
		 */
		if (unlikely(!mapped_bytes)) {
			blk_mq_requeue_request(req, false);
			blk_mq_delay_kick_requeue_list(req->q,
					UBLK_REQUEUE_DELAY_MS);
			return;
		}

		ublk_get_iod(ubq, req->tag)->nr_sectors =
			mapped_bytes >> 9;
	}

	ublk_init_req_ref(ubq, req);
	ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags);
}

static inline void ublk_forward_io_cmds(struct ublk_queue *ubq,
					unsigned issue_flags)
{
	struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds);
	struct ublk_rq_data *data, *tmp;

	io_cmds = llist_reverse_order(io_cmds);
	llist_for_each_entry_safe(data, tmp, io_cmds, node)
		__ublk_rq_task_work(blk_mq_rq_from_pdu(data), issue_flags);
}

static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags)
{
	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
	struct ublk_queue *ubq = pdu->ubq;

	ublk_forward_io_cmds(ubq, issue_flags);
}

static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
{
	struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);

	if (llist_add(&data->node, &ubq->io_cmds)) {
		struct ublk_io *io = &ubq->ios[rq->tag];

		io_uring_cmd_complete_in_task(io->cmd, ublk_rq_task_work_cb);
	}
}

static enum blk_eh_timer_return ublk_timeout(struct request *rq)
{
	struct ublk_queue *ubq = rq->mq_hctx->driver_data;
	unsigned int nr_inflight = 0;
	int i;

	if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) {
		if (!ubq->timeout) {
			send_sig(SIGKILL, ubq->ubq_daemon, 0);
			ubq->timeout = true;
		}

		return BLK_EH_DONE;
	}

	if (!ubq_daemon_is_dying(ubq))
		return BLK_EH_RESET_TIMER;

	for (i = 0; i < ubq->q_depth; i++) {
		struct ublk_io *io = &ubq->ios[i];

		if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
			nr_inflight++;
	}

	/* cancelable uring_cmd can't help us if all commands are in-flight */
	if (nr_inflight == ubq->q_depth) {
		struct ublk_device *ub = ubq->dev;

		if (ublk_abort_requests(ub, ubq)) {
			if (ublk_can_use_recovery(ub))
				schedule_work(&ub->quiesce_work);
			else
				schedule_work(&ub->stop_work);
		}
		return BLK_EH_DONE;
	}

	return BLK_EH_RESET_TIMER;
}

static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
		const struct blk_mq_queue_data *bd)
{
	struct ublk_queue *ubq = hctx->driver_data;
	struct request *rq = bd->rq;
	blk_status_t res;

	/* fill iod to slot in io cmd buffer */
	res = ublk_setup_iod(ubq, rq);
	if (unlikely(res != BLK_STS_OK))
		return BLK_STS_IOERR;

	/* With recovery feature enabled, force_abort is set in
	 * ublk_stop_dev() before calling del_gendisk(). We have to
	 * abort all requeued and new rqs here to let del_gendisk()
	 * move on. Besides, we cannot not call io_uring_cmd_complete_in_task()
	 * to avoid UAF on io_uring ctx.
	 *
	 * Note: force_abort is guaranteed to be seen because it is set
	 * before request queue is unqiuesced.
	 */
	if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort))
		return BLK_STS_IOERR;

	if (unlikely(ubq->canceling)) {
		__ublk_abort_rq(ubq, rq);
		return BLK_STS_OK;
	}

	blk_mq_start_request(bd->rq);
	ublk_queue_cmd(ubq, rq);

	return BLK_STS_OK;
}

static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
		unsigned int hctx_idx)
{
	struct ublk_device *ub = driver_data;
	struct ublk_queue *ubq = ublk_get_queue(ub, hctx->queue_num);

	hctx->driver_data = ubq;
	return 0;
}

static const struct blk_mq_ops ublk_mq_ops = {
	.queue_rq       = ublk_queue_rq,
	.init_hctx	= ublk_init_hctx,
	.timeout	= ublk_timeout,
};

static int ublk_ch_open(struct inode *inode, struct file *filp)
{
	struct ublk_device *ub = container_of(inode->i_cdev,
			struct ublk_device, cdev);

	if (test_and_set_bit(UB_STATE_OPEN, &ub->state))
		return -EBUSY;
	filp->private_data = ub;
	return 0;
}

static int ublk_ch_release(struct inode *inode, struct file *filp)
{
	struct ublk_device *ub = filp->private_data;

	clear_bit(UB_STATE_OPEN, &ub->state);
	return 0;
}

/* map pre-allocated per-queue cmd buffer to ublksrv daemon */
static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma)
{
	struct ublk_device *ub = filp->private_data;
	size_t sz = vma->vm_end - vma->vm_start;
	unsigned max_sz = UBLK_MAX_QUEUE_DEPTH * sizeof(struct ublksrv_io_desc);
	unsigned long pfn, end, phys_off = vma->vm_pgoff << PAGE_SHIFT;
	int q_id, ret = 0;

	spin_lock(&ub->lock);
	if (!ub->mm)
		ub->mm = current->mm;
	if (current->mm != ub->mm)
		ret = -EINVAL;
	spin_unlock(&ub->lock);

	if (ret)
		return ret;

	if (vma->vm_flags & VM_WRITE)
		return -EPERM;

	end = UBLKSRV_CMD_BUF_OFFSET + ub->dev_info.nr_hw_queues * max_sz;
	if (phys_off < UBLKSRV_CMD_BUF_OFFSET || phys_off >= end)
		return -EINVAL;

	q_id = (phys_off - UBLKSRV_CMD_BUF_OFFSET) / max_sz;
	pr_devel("%s: qid %d, pid %d, addr %lx pg_off %lx sz %lu\n",
			__func__, q_id, current->pid, vma->vm_start,
			phys_off, (unsigned long)sz);

	if (sz != ublk_queue_cmd_buf_size(ub, q_id))
		return -EINVAL;

	pfn = virt_to_phys(ublk_queue_cmd_buf(ub, q_id)) >> PAGE_SHIFT;
	return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
}

static void ublk_commit_completion(struct ublk_device *ub,
		const struct ublksrv_io_cmd *ub_cmd)
{
	u32 qid = ub_cmd->q_id, tag = ub_cmd->tag;
	struct ublk_queue *ubq = ublk_get_queue(ub, qid);
	struct ublk_io *io = &ubq->ios[tag];
	struct request *req;

	/* now this cmd slot is owned by nbd driver */
	io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV;
	io->res = ub_cmd->result;

	/* find the io request and complete */
	req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag);
	if (WARN_ON_ONCE(unlikely(!req)))
		return;

	if (req_op(req) == REQ_OP_ZONE_APPEND)
		req->__sector = ub_cmd->zone_append_lba;

	if (likely(!blk_should_fake_timeout(req->q)))
		ublk_put_req_ref(ubq, req);
}

/*
 * Called from ubq_daemon context via cancel fn, meantime quiesce ublk
 * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon
 * context, so everything is serialized.
 */
static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
{
	int i;

	for (i = 0; i < ubq->q_depth; i++) {
		struct ublk_io *io = &ubq->ios[i];

		if (!(io->flags & UBLK_IO_FLAG_ACTIVE)) {
			struct request *rq;

			/*
			 * Either we fail the request or ublk_rq_task_work_fn
			 * will do it
			 */
			rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
			if (rq && blk_mq_request_started(rq)) {
				io->flags |= UBLK_IO_FLAG_ABORTED;
				__ublk_fail_req(ubq, io, rq);
			}
		}
	}
}

static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
{
	struct gendisk *disk;

	spin_lock(&ubq->cancel_lock);
	if (ubq->canceling) {
		spin_unlock(&ubq->cancel_lock);
		return false;
	}
	ubq->canceling = true;
	spin_unlock(&ubq->cancel_lock);

	spin_lock(&ub->lock);
	disk = ub->ub_disk;
	if (disk)
		get_device(disk_to_dev(disk));
	spin_unlock(&ub->lock);

	/* Our disk has been dead */
	if (!disk)
		return false;

	/* Now we are serialized with ublk_queue_rq() */
	blk_mq_quiesce_queue(disk->queue);
	/* abort queue is for making forward progress */
	ublk_abort_queue(ub, ubq);
	blk_mq_unquiesce_queue(disk->queue);
	put_device(disk_to_dev(disk));

	return true;
}

static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
		unsigned int issue_flags)
{
	bool done;

	if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
		return;

	spin_lock(&ubq->cancel_lock);
	done = !!(io->flags & UBLK_IO_FLAG_CANCELED);
	if (!done)
		io->flags |= UBLK_IO_FLAG_CANCELED;
	spin_unlock(&ubq->cancel_lock);

	if (!done)
		io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, issue_flags);
}

/*
 * The ublk char device won't be closed when calling cancel fn, so both
 * ublk device and queue are guaranteed to be live
 */
static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
		unsigned int issue_flags)
{
	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
	struct ublk_queue *ubq = pdu->ubq;
	struct task_struct *task;
	struct ublk_device *ub;
	bool need_schedule;
	struct ublk_io *io;

	if (WARN_ON_ONCE(!ubq))
		return;

	if (WARN_ON_ONCE(pdu->tag >= ubq->q_depth))
		return;

	task = io_uring_cmd_get_task(cmd);
	if (WARN_ON_ONCE(task && task != ubq->ubq_daemon))
		return;

	ub = ubq->dev;
	need_schedule = ublk_abort_requests(ub, ubq);

	io = &ubq->ios[pdu->tag];
	WARN_ON_ONCE(io->cmd != cmd);
	ublk_cancel_cmd(ubq, io, issue_flags);

	if (need_schedule) {
		if (ublk_can_use_recovery(ub))
			schedule_work(&ub->quiesce_work);
		else
			schedule_work(&ub->stop_work);
	}
}

static inline bool ublk_queue_ready(struct ublk_queue *ubq)
{
	return ubq->nr_io_ready == ubq->q_depth;
}

static void ublk_cancel_queue(struct ublk_queue *ubq)
{
	int i;

	for (i = 0; i < ubq->q_depth; i++)
		ublk_cancel_cmd(ubq, &ubq->ios[i], IO_URING_F_UNLOCKED);
}

/* Cancel all pending commands, must be called after del_gendisk() returns */
static void ublk_cancel_dev(struct ublk_device *ub)
{
	int i;

	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
		ublk_cancel_queue(ublk_get_queue(ub, i));
}

static bool ublk_check_inflight_rq(struct request *rq, void *data)
{
	bool *idle = data;

	if (blk_mq_request_started(rq)) {
		*idle = false;
		return false;
	}
	return true;
}

static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub)
{
	bool idle;

	WARN_ON_ONCE(!blk_queue_quiesced(ub->ub_disk->queue));
	while (true) {
		idle = true;
		blk_mq_tagset_busy_iter(&ub->tag_set,
				ublk_check_inflight_rq, &idle);
		if (idle)
			break;
		msleep(UBLK_REQUEUE_DELAY_MS);
	}
}

static void __ublk_quiesce_dev(struct ublk_device *ub)
{
	pr_devel("%s: quiesce ub: dev_id %d state %s\n",
			__func__, ub->dev_info.dev_id,
			ub->dev_info.state == UBLK_S_DEV_LIVE ?
			"LIVE" : "QUIESCED");
	blk_mq_quiesce_queue(ub->ub_disk->queue);
	ublk_wait_tagset_rqs_idle(ub);
	ub->dev_info.state = UBLK_S_DEV_QUIESCED;
}

static void ublk_quiesce_work_fn(struct work_struct *work)
{
	struct ublk_device *ub =
		container_of(work, struct ublk_device, quiesce_work);

	mutex_lock(&ub->mutex);
	if (ub->dev_info.state != UBLK_S_DEV_LIVE)
		goto unlock;
	__ublk_quiesce_dev(ub);
 unlock:
	mutex_unlock(&ub->mutex);
	ublk_cancel_dev(ub);
}

static void ublk_unquiesce_dev(struct ublk_device *ub)
{
	int i;

	pr_devel("%s: unquiesce ub: dev_id %d state %s\n",
			__func__, ub->dev_info.dev_id,
			ub->dev_info.state == UBLK_S_DEV_LIVE ?
			"LIVE" : "QUIESCED");
	/* quiesce_work has run. We let requeued rqs be aborted
	 * before running fallback_wq. "force_abort" must be seen
	 * after request queue is unqiuesced. Then del_gendisk()
	 * can move on.
	 */
	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
		ublk_get_queue(ub, i)->force_abort = true;

	blk_mq_unquiesce_queue(ub->ub_disk->queue);
	/* We may have requeued some rqs in ublk_quiesce_queue() */
	blk_mq_kick_requeue_list(ub->ub_disk->queue);
}

static void ublk_stop_dev(struct ublk_device *ub)
{
	struct gendisk *disk;

	mutex_lock(&ub->mutex);
	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
		goto unlock;
	if (ublk_can_use_recovery(ub)) {
		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
			__ublk_quiesce_dev(ub);
		ublk_unquiesce_dev(ub);
	}
	del_gendisk(ub->ub_disk);

	/* Sync with ublk_abort_queue() by holding the lock */
	spin_lock(&ub->lock);
	disk = ub->ub_disk;
	ub->dev_info.state = UBLK_S_DEV_DEAD;
	ub->dev_info.ublksrv_pid = -1;
	ub->ub_disk = NULL;
	spin_unlock(&ub->lock);
	put_disk(disk);
 unlock:
	mutex_unlock(&ub->mutex);
	ublk_cancel_dev(ub);
}

/* device can only be started after all IOs are ready */
static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
{
	mutex_lock(&ub->mutex);
	ubq->nr_io_ready++;
	if (ublk_queue_ready(ubq)) {
		ubq->ubq_daemon = current;
		get_task_struct(ubq->ubq_daemon);
		ub->nr_queues_ready++;

		if (capable(CAP_SYS_ADMIN))
			ub->nr_privileged_daemon++;
	}
	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
		complete_all(&ub->completion);
	mutex_unlock(&ub->mutex);
}

static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
		int tag)
{
	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
	struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);

	ublk_queue_cmd(ubq, req);
}

static inline int ublk_check_cmd_op(u32 cmd_op)
{
	u32 ioc_type = _IOC_TYPE(cmd_op);

	if (!IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u')
		return -EOPNOTSUPP;

	if (ioc_type != 'u' && ioc_type != 0)
		return -EOPNOTSUPP;

	return 0;
}

static inline void ublk_fill_io_cmd(struct ublk_io *io,
		struct io_uring_cmd *cmd, unsigned long buf_addr)
{
	io->cmd = cmd;
	io->flags |= UBLK_IO_FLAG_ACTIVE;
	io->addr = buf_addr;
}

static inline void ublk_prep_cancel(struct io_uring_cmd *cmd,
				    unsigned int issue_flags,
				    struct ublk_queue *ubq, unsigned int tag)
{
	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);

	/*
	 * Safe to refer to @ubq since ublk_queue won't be died until its
	 * commands are completed
	 */
	pdu->ubq = ubq;
	pdu->tag = tag;
	io_uring_cmd_mark_cancelable(cmd, issue_flags);
}

static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
			       unsigned int issue_flags,
			       const struct ublksrv_io_cmd *ub_cmd)
{
	struct ublk_device *ub = cmd->file->private_data;
	struct ublk_queue *ubq;
	struct ublk_io *io;
	u32 cmd_op = cmd->cmd_op;
	unsigned tag = ub_cmd->tag;
	int ret = -EINVAL;
	struct request *req;

	pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n",
			__func__, cmd->cmd_op, ub_cmd->q_id, tag,
			ub_cmd->result);

	if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues)
		goto out;

	ubq = ublk_get_queue(ub, ub_cmd->q_id);
	if (!ubq || ub_cmd->q_id != ubq->q_id)
		goto out;

	if (ubq->ubq_daemon && ubq->ubq_daemon != current)
		goto out;

	if (tag >= ubq->q_depth)
		goto out;

	io = &ubq->ios[tag];

	/* there is pending io cmd, something must be wrong */
	if (io->flags & UBLK_IO_FLAG_ACTIVE) {
		ret = -EBUSY;
		goto out;
	}

	/*
	 * ensure that the user issues UBLK_IO_NEED_GET_DATA
	 * iff the driver have set the UBLK_IO_FLAG_NEED_GET_DATA.
	 */
	if ((!!(io->flags & UBLK_IO_FLAG_NEED_GET_DATA))
			^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
		goto out;

	ret = ublk_check_cmd_op(cmd_op);
	if (ret)
		goto out;

	ret = -EINVAL;
	switch (_IOC_NR(cmd_op)) {
	case UBLK_IO_FETCH_REQ:
		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
		if (ublk_queue_ready(ubq)) {
			ret = -EBUSY;
			goto out;
		}
		/*
		 * The io is being handled by server, so COMMIT_RQ is expected
		 * instead of FETCH_REQ
		 */
		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
			goto out;

		if (!ublk_support_user_copy(ubq)) {
			/*
			 * FETCH_RQ has to provide IO buffer if NEED GET
			 * DATA is not enabled
			 */
			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
				goto out;
		} else if (ub_cmd->addr) {
			/* User copy requires addr to be unset */
			ret = -EINVAL;
			goto out;
		}

		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
		ublk_mark_io_ready(ub, ubq);
		break;
	case UBLK_IO_COMMIT_AND_FETCH_REQ:
		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);

		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
			goto out;

		if (!ublk_support_user_copy(ubq)) {
			/*
			 * COMMIT_AND_FETCH_REQ has to provide IO buffer if
			 * NEED GET DATA is not enabled or it is Read IO.
			 */
			if (!ub_cmd->addr && (!ublk_need_get_data(ubq) ||
						req_op(req) == REQ_OP_READ))
				goto out;
		} else if (req_op(req) != REQ_OP_ZONE_APPEND && ub_cmd->addr) {
			/*
			 * User copy requires addr to be unset when command is
			 * not zone append
			 */
			ret = -EINVAL;
			goto out;
		}

		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
		ublk_commit_completion(ub, ub_cmd);
		break;
	case UBLK_IO_NEED_GET_DATA:
		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
			goto out;
		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
		ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
		break;
	default:
		goto out;
	}
	ublk_prep_cancel(cmd, issue_flags, ubq, tag);
	return -EIOCBQUEUED;

 out:
	io_uring_cmd_done(cmd, ret, 0, issue_flags);
	pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n",
			__func__, cmd_op, tag, ret, io->flags);
	return -EIOCBQUEUED;
}

static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
		struct ublk_queue *ubq, int tag, size_t offset)
{
	struct request *req;

	if (!ublk_need_req_ref(ubq))
		return NULL;

	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
	if (!req)
		return NULL;

	if (!ublk_get_req_ref(ubq, req))
		return NULL;

	if (unlikely(!blk_mq_request_started(req) || req->tag != tag))
		goto fail_put;

	if (!ublk_rq_has_data(req))
		goto fail_put;

	if (offset > blk_rq_bytes(req))
		goto fail_put;

	return req;
fail_put:
	ublk_put_req_ref(ubq, req);
	return NULL;
}

static inline int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
		unsigned int issue_flags)
{
	/*
	 * Not necessary for async retry, but let's keep it simple and always
	 * copy the values to avoid any potential reuse.
	 */
	const struct ublksrv_io_cmd *ub_src = io_uring_sqe_cmd(cmd->sqe);
	const struct ublksrv_io_cmd ub_cmd = {
		.q_id = READ_ONCE(ub_src->q_id),
		.tag = READ_ONCE(ub_src->tag),
		.result = READ_ONCE(ub_src->result),
		.addr = READ_ONCE(ub_src->addr)
	};

	WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED);

	return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd);
}

static void ublk_ch_uring_cmd_cb(struct io_uring_cmd *cmd,
		unsigned int issue_flags)
{
	ublk_ch_uring_cmd_local(cmd, issue_flags);
}

static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
{
	if (unlikely(issue_flags & IO_URING_F_CANCEL)) {
		ublk_uring_cmd_cancel_fn(cmd, issue_flags);
		return 0;
	}

	/* well-implemented server won't run into unlocked */
	if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) {
		io_uring_cmd_complete_in_task(cmd, ublk_ch_uring_cmd_cb);
		return -EIOCBQUEUED;
	}

	return ublk_ch_uring_cmd_local(cmd, issue_flags);
}

static inline bool ublk_check_ubuf_dir(const struct request *req,
		int ubuf_dir)
{
	/* copy ubuf to request pages */
	if ((req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN) &&
	    ubuf_dir == ITER_SOURCE)
		return true;

	/* copy request pages to ubuf */
	if ((req_op(req) == REQ_OP_WRITE ||
	     req_op(req) == REQ_OP_ZONE_APPEND) &&
	    ubuf_dir == ITER_DEST)
		return true;

	return false;
}

static struct request *ublk_check_and_get_req(struct kiocb *iocb,
		struct iov_iter *iter, size_t *off, int dir)
{
	struct ublk_device *ub = iocb->ki_filp->private_data;
	struct ublk_queue *ubq;
	struct request *req;
	size_t buf_off;
	u16 tag, q_id;

	if (!ub)
		return ERR_PTR(-EACCES);

	if (!user_backed_iter(iter))
		return ERR_PTR(-EACCES);

	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
		return ERR_PTR(-EACCES);

	tag = ublk_pos_to_tag(iocb->ki_pos);
	q_id = ublk_pos_to_hwq(iocb->ki_pos);
	buf_off = ublk_pos_to_buf_off(iocb->ki_pos);

	if (q_id >= ub->dev_info.nr_hw_queues)
		return ERR_PTR(-EINVAL);

	ubq = ublk_get_queue(ub, q_id);
	if (!ubq)
		return ERR_PTR(-EINVAL);

	if (tag >= ubq->q_depth)
		return ERR_PTR(-EINVAL);

	req = __ublk_check_and_get_req(ub, ubq, tag, buf_off);
	if (!req)
		return ERR_PTR(-EINVAL);

	if (!req->mq_hctx || !req->mq_hctx->driver_data)
		goto fail;

	if (!ublk_check_ubuf_dir(req, dir))
		goto fail;

	*off = buf_off;
	return req;
fail:
	ublk_put_req_ref(ubq, req);
	return ERR_PTR(-EACCES);
}

static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct ublk_queue *ubq;
	struct request *req;
	size_t buf_off;
	size_t ret;

	req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST);
	if (IS_ERR(req))
		return PTR_ERR(req);

	ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST);
	ubq = req->mq_hctx->driver_data;
	ublk_put_req_ref(ubq, req);

	return ret;
}

static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct ublk_queue *ubq;
	struct request *req;
	size_t buf_off;
	size_t ret;

	req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE);
	if (IS_ERR(req))
		return PTR_ERR(req);

	ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE);
	ubq = req->mq_hctx->driver_data;
	ublk_put_req_ref(ubq, req);

	return ret;
}

static const struct file_operations ublk_ch_fops = {
	.owner = THIS_MODULE,
	.open = ublk_ch_open,
	.release = ublk_ch_release,
	.llseek = no_llseek,
	.read_iter = ublk_ch_read_iter,
	.write_iter = ublk_ch_write_iter,
	.uring_cmd = ublk_ch_uring_cmd,
	.mmap = ublk_ch_mmap,
};

static void ublk_deinit_queue(struct ublk_device *ub, int q_id)
{
	int size = ublk_queue_cmd_buf_size(ub, q_id);
	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);

	if (ubq->ubq_daemon)
		put_task_struct(ubq->ubq_daemon);
	if (ubq->io_cmd_buf)
		free_pages((unsigned long)ubq->io_cmd_buf, get_order(size));
}

static int ublk_init_queue(struct ublk_device *ub, int q_id)
{
	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO;
	void *ptr;
	int size;

	spin_lock_init(&ubq->cancel_lock);
	ubq->flags = ub->dev_info.flags;
	ubq->q_id = q_id;
	ubq->q_depth = ub->dev_info.queue_depth;
	size = ublk_queue_cmd_buf_size(ub, q_id);

	ptr = (void *) __get_free_pages(gfp_flags, get_order(size));
	if (!ptr)
		return -ENOMEM;

	ubq->io_cmd_buf = ptr;
	ubq->dev = ub;
	return 0;
}

static void ublk_deinit_queues(struct ublk_device *ub)
{
	int nr_queues = ub->dev_info.nr_hw_queues;
	int i;

	if (!ub->__queues)
		return;

	for (i = 0; i < nr_queues; i++)
		ublk_deinit_queue(ub, i);
	kfree(ub->__queues);
}

static int ublk_init_queues(struct ublk_device *ub)
{
	int nr_queues = ub->dev_info.nr_hw_queues;
	int depth = ub->dev_info.queue_depth;
	int ubq_size = sizeof(struct ublk_queue) + depth * sizeof(struct ublk_io);
	int i, ret = -ENOMEM;

	ub->queue_size = ubq_size;
	ub->__queues = kcalloc(nr_queues, ubq_size, GFP_KERNEL);
	if (!ub->__queues)
		return ret;

	for (i = 0; i < nr_queues; i++) {
		if (ublk_init_queue(ub, i))
			goto fail;
	}

	init_completion(&ub->completion);
	return 0;

 fail:
	ublk_deinit_queues(ub);
	return ret;
}

static int ublk_alloc_dev_number(struct ublk_device *ub, int idx)
{
	int i = idx;
	int err;

	spin_lock(&ublk_idr_lock);
	/* allocate id, if @id >= 0, we're requesting that specific id */
	if (i >= 0) {
		err = idr_alloc(&ublk_index_idr, ub, i, i + 1, GFP_NOWAIT);
		if (err == -ENOSPC)
			err = -EEXIST;
	} else {
		err = idr_alloc(&ublk_index_idr, ub, 0, UBLK_MAX_UBLKS,
				GFP_NOWAIT);
	}
	spin_unlock(&ublk_idr_lock);

	if (err >= 0)
		ub->ub_number = err;

	return err;
}

static void ublk_free_dev_number(struct ublk_device *ub)
{
	spin_lock(&ublk_idr_lock);
	idr_remove(&ublk_index_idr, ub->ub_number);
	wake_up_all(&ublk_idr_wq);
	spin_unlock(&ublk_idr_lock);
}

static void ublk_cdev_rel(struct device *dev)
{
	struct ublk_device *ub = container_of(dev, struct ublk_device, cdev_dev);

	blk_mq_free_tag_set(&ub->tag_set);
	ublk_deinit_queues(ub);
	ublk_free_dev_number(ub);
	mutex_destroy(&ub->mutex);
	kfree(ub);
}

static int ublk_add_chdev(struct ublk_device *ub)
{
	struct device *dev = &ub->cdev_dev;
	int minor = ub->ub_number;
	int ret;

	dev->parent = ublk_misc.this_device;
	dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor);
	dev->class = &ublk_chr_class;
	dev->release = ublk_cdev_rel;
	device_initialize(dev);

	ret = dev_set_name(dev, "ublkc%d", minor);
	if (ret)
		goto fail;

	cdev_init(&ub->cdev, &ublk_ch_fops);
	ret = cdev_device_add(&ub->cdev, dev);
	if (ret)
		goto fail;

	ublks_added++;
	return 0;
 fail:
	put_device(dev);
	return ret;
}

static void ublk_stop_work_fn(struct work_struct *work)
{
	struct ublk_device *ub =
		container_of(work, struct ublk_device, stop_work);

	ublk_stop_dev(ub);
}

/* align max io buffer size with PAGE_SIZE */
static void ublk_align_max_io_size(struct ublk_device *ub)
{
	unsigned int max_io_bytes = ub->dev_info.max_io_buf_bytes;

	ub->dev_info.max_io_buf_bytes =
		round_down(max_io_bytes, PAGE_SIZE);
}

static int ublk_add_tag_set(struct ublk_device *ub)
{
	ub->tag_set.ops = &ublk_mq_ops;
	ub->tag_set.nr_hw_queues = ub->dev_info.nr_hw_queues;
	ub->tag_set.queue_depth = ub->dev_info.queue_depth;
	ub->tag_set.numa_node = NUMA_NO_NODE;
	ub->tag_set.cmd_size = sizeof(struct ublk_rq_data);
	ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
	ub->tag_set.driver_data = ub;
	return blk_mq_alloc_tag_set(&ub->tag_set);
}

static void ublk_remove(struct ublk_device *ub)
{
	ublk_stop_dev(ub);
	cancel_work_sync(&ub->stop_work);
	cancel_work_sync(&ub->quiesce_work);
	cdev_device_del(&ub->cdev, &ub->cdev_dev);
	ublk_put_device(ub);
	ublks_added--;
}

static struct ublk_device *ublk_get_device_from_id(int idx)
{
	struct ublk_device *ub = NULL;

	if (idx < 0)
		return NULL;

	spin_lock(&ublk_idr_lock);
	ub = idr_find(&ublk_index_idr, idx);
	if (ub)
		ub = ublk_get_device(ub);
	spin_unlock(&ublk_idr_lock);

	return ub;
}

static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	const struct ublk_param_basic *p = &ub->params.basic;
	int ublksrv_pid = (int)header->data[0];
	struct queue_limits lim = {
		.logical_block_size	= 1 << p->logical_bs_shift,
		.physical_block_size	= 1 << p->physical_bs_shift,
		.io_min			= 1 << p->io_min_shift,
		.io_opt			= 1 << p->io_opt_shift,
		.max_hw_sectors		= p->max_sectors,
		.chunk_sectors		= p->chunk_sectors,
		.virt_boundary_mask	= p->virt_boundary_mask,

	};
	struct gendisk *disk;
	int ret = -EINVAL;

	if (ublksrv_pid <= 0)
		return -EINVAL;
	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
		return -EINVAL;

	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
		const struct ublk_param_discard *pd = &ub->params.discard;

		lim.discard_alignment = pd->discard_alignment;
		lim.discard_granularity = pd->discard_granularity;
		lim.max_hw_discard_sectors = pd->max_discard_sectors;
		lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors;
		lim.max_discard_segments = pd->max_discard_segments;
	}

	if (ub->params.types & UBLK_PARAM_TYPE_ZONED) {
		const struct ublk_param_zoned *p = &ub->params.zoned;

		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
			return -EOPNOTSUPP;

		lim.zoned = true;
		lim.max_active_zones = p->max_active_zones;
		lim.max_open_zones =  p->max_open_zones;
		lim.max_zone_append_sectors = p->max_zone_append_sectors;
	}

	if (wait_for_completion_interruptible(&ub->completion) != 0)
		return -EINTR;

	mutex_lock(&ub->mutex);
	if (ub->dev_info.state == UBLK_S_DEV_LIVE ||
	    test_bit(UB_STATE_USED, &ub->state)) {
		ret = -EEXIST;
		goto out_unlock;
	}

	disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL);
	if (IS_ERR(disk)) {
		ret = PTR_ERR(disk);
		goto out_unlock;
	}
	sprintf(disk->disk_name, "ublkb%d", ub->ub_number);
	disk->fops = &ub_fops;
	disk->private_data = ub;

	ub->dev_info.ublksrv_pid = ublksrv_pid;
	ub->ub_disk = disk;

	ublk_apply_params(ub);

	/* don't probe partitions if any one ubq daemon is un-trusted */
	if (ub->nr_privileged_daemon != ub->nr_queues_ready)
		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);

	ublk_get_device(ub);
	ub->dev_info.state = UBLK_S_DEV_LIVE;

	if (ublk_dev_is_zoned(ub)) {
		ret = ublk_revalidate_disk_zones(ub);
		if (ret)
			goto out_put_cdev;
	}

	ret = add_disk(disk);
	if (ret)
		goto out_put_cdev;

	set_bit(UB_STATE_USED, &ub->state);

out_put_cdev:
	if (ret) {
		ub->dev_info.state = UBLK_S_DEV_DEAD;
		ublk_put_device(ub);
	}
	if (ret)
		put_disk(disk);
out_unlock:
	mutex_unlock(&ub->mutex);
	return ret;
}

static int ublk_ctrl_get_queue_affinity(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;
	cpumask_var_t cpumask;
	unsigned long queue;
	unsigned int retlen;
	unsigned int i;
	int ret;

	if (header->len * BITS_PER_BYTE < nr_cpu_ids)
		return -EINVAL;
	if (header->len & (sizeof(unsigned long)-1))
		return -EINVAL;
	if (!header->addr)
		return -EINVAL;

	queue = header->data[0];
	if (queue >= ub->dev_info.nr_hw_queues)
		return -EINVAL;

	if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
		return -ENOMEM;

	for_each_possible_cpu(i) {
		if (ub->tag_set.map[HCTX_TYPE_DEFAULT].mq_map[i] == queue)
			cpumask_set_cpu(i, cpumask);
	}

	ret = -EFAULT;
	retlen = min_t(unsigned short, header->len, cpumask_size());
	if (copy_to_user(argp, cpumask, retlen))
		goto out_free_cpumask;
	if (retlen != header->len &&
	    clear_user(argp + retlen, header->len - retlen))
		goto out_free_cpumask;

	ret = 0;
out_free_cpumask:
	free_cpumask_var(cpumask);
	return ret;
}

static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info)
{
	pr_devel("%s: dev id %d flags %llx\n", __func__,
			info->dev_id, info->flags);
	pr_devel("\t nr_hw_queues %d queue_depth %d\n",
			info->nr_hw_queues, info->queue_depth);
}

static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;
	struct ublksrv_ctrl_dev_info info;
	struct ublk_device *ub;
	int ret = -EINVAL;

	if (header->len < sizeof(info) || !header->addr)
		return -EINVAL;
	if (header->queue_id != (u16)-1) {
		pr_warn("%s: queue_id is wrong %x\n",
			__func__, header->queue_id);
		return -EINVAL;
	}

	if (copy_from_user(&info, argp, sizeof(info)))
		return -EFAULT;

	if (capable(CAP_SYS_ADMIN))
		info.flags &= ~UBLK_F_UNPRIVILEGED_DEV;
	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
		return -EPERM;

	/*
	 * unprivileged device can't be trusted, but RECOVERY and
	 * RECOVERY_REISSUE still may hang error handling, so can't
	 * support recovery features for unprivileged ublk now
	 *
	 * TODO: provide forward progress for RECOVERY handler, so that
	 * unprivileged device can benefit from it
	 */
	if (info.flags & UBLK_F_UNPRIVILEGED_DEV)
		info.flags &= ~(UBLK_F_USER_RECOVERY_REISSUE |
				UBLK_F_USER_RECOVERY);

	/* the created device is always owned by current user */
	ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid);

	if (header->dev_id != info.dev_id) {
		pr_warn("%s: dev id not match %u %u\n",
			__func__, header->dev_id, info.dev_id);
		return -EINVAL;
	}

	if (header->dev_id != U32_MAX && header->dev_id >= UBLK_MAX_UBLKS) {
		pr_warn("%s: dev id is too large. Max supported is %d\n",
			__func__, UBLK_MAX_UBLKS - 1);
		return -EINVAL;
	}

	ublk_dump_dev_info(&info);

	ret = mutex_lock_killable(&ublk_ctl_mutex);
	if (ret)
		return ret;

	ret = -EACCES;
	if (ublks_added >= ublks_max)
		goto out_unlock;

	ret = -ENOMEM;
	ub = kzalloc(sizeof(*ub), GFP_KERNEL);
	if (!ub)
		goto out_unlock;
	mutex_init(&ub->mutex);
	spin_lock_init(&ub->lock);
	INIT_WORK(&ub->quiesce_work, ublk_quiesce_work_fn);
	INIT_WORK(&ub->stop_work, ublk_stop_work_fn);

	ret = ublk_alloc_dev_number(ub, header->dev_id);
	if (ret < 0)
		goto out_free_ub;

	memcpy(&ub->dev_info, &info, sizeof(info));

	/* update device id */
	ub->dev_info.dev_id = ub->ub_number;

	/*
	 * 64bit flags will be copied back to userspace as feature
	 * negotiation result, so have to clear flags which driver
	 * doesn't support yet, then userspace can get correct flags
	 * (features) to handle.
	 */
	ub->dev_info.flags &= UBLK_F_ALL;

	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
		UBLK_F_URING_CMD_COMP_IN_TASK;

	/* GET_DATA isn't needed any more with USER_COPY */
	if (ublk_dev_is_user_copy(ub))
		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;

	/* Zoned storage support requires user copy feature */
	if (ublk_dev_is_zoned(ub) &&
	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) {
		ret = -EINVAL;
		goto out_free_dev_number;
	}

	/* We are not ready to support zero copy */
	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;

	ub->dev_info.nr_hw_queues = min_t(unsigned int,
			ub->dev_info.nr_hw_queues, nr_cpu_ids);
	ublk_align_max_io_size(ub);

	ret = ublk_init_queues(ub);
	if (ret)
		goto out_free_dev_number;

	ret = ublk_add_tag_set(ub);
	if (ret)
		goto out_deinit_queues;

	ret = -EFAULT;
	if (copy_to_user(argp, &ub->dev_info, sizeof(info)))
		goto out_free_tag_set;

	/*
	 * Add the char dev so that ublksrv daemon can be setup.
	 * ublk_add_chdev() will cleanup everything if it fails.
	 */
	ret = ublk_add_chdev(ub);
	goto out_unlock;

out_free_tag_set:
	blk_mq_free_tag_set(&ub->tag_set);
out_deinit_queues:
	ublk_deinit_queues(ub);
out_free_dev_number:
	ublk_free_dev_number(ub);
out_free_ub:
	mutex_destroy(&ub->mutex);
	kfree(ub);
out_unlock:
	mutex_unlock(&ublk_ctl_mutex);
	return ret;
}

static inline bool ublk_idr_freed(int id)
{
	void *ptr;

	spin_lock(&ublk_idr_lock);
	ptr = idr_find(&ublk_index_idr, id);
	spin_unlock(&ublk_idr_lock);

	return ptr == NULL;
}

static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
{
	struct ublk_device *ub = *p_ub;
	int idx = ub->ub_number;
	int ret;

	ret = mutex_lock_killable(&ublk_ctl_mutex);
	if (ret)
		return ret;

	if (!test_bit(UB_STATE_DELETED, &ub->state)) {
		ublk_remove(ub);
		set_bit(UB_STATE_DELETED, &ub->state);
	}

	/* Mark the reference as consumed */
	*p_ub = NULL;
	ublk_put_device(ub);
	mutex_unlock(&ublk_ctl_mutex);

	/*
	 * Wait until the idr is removed, then it can be reused after
	 * DEL_DEV command is returned.
	 *
	 * If we returns because of user interrupt, future delete command
	 * may come:
	 *
	 * - the device number isn't freed, this device won't or needn't
	 *   be deleted again, since UB_STATE_DELETED is set, and device
	 *   will be released after the last reference is dropped
	 *
	 * - the device number is freed already, we will not find this
	 *   device via ublk_get_device_from_id()
	 */
	if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
		return -EINTR;
	return 0;
}

static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);

	pr_devel("%s: cmd_op %x, dev id %d qid %d data %llx buf %llx len %u\n",
			__func__, cmd->cmd_op, header->dev_id, header->queue_id,
			header->data[0], header->addr, header->len);
}

static int ublk_ctrl_stop_dev(struct ublk_device *ub)
{
	ublk_stop_dev(ub);
	cancel_work_sync(&ub->stop_work);
	cancel_work_sync(&ub->quiesce_work);

	return 0;
}

static int ublk_ctrl_get_dev_info(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;

	if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr)
		return -EINVAL;

	if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info)))
		return -EFAULT;

	return 0;
}

/* TYPE_DEVT is readonly, so fill it up before returning to userspace */
static void ublk_ctrl_fill_params_devt(struct ublk_device *ub)
{
	ub->params.devt.char_major = MAJOR(ub->cdev_dev.devt);
	ub->params.devt.char_minor = MINOR(ub->cdev_dev.devt);

	if (ub->ub_disk) {
		ub->params.devt.disk_major = MAJOR(disk_devt(ub->ub_disk));
		ub->params.devt.disk_minor = MINOR(disk_devt(ub->ub_disk));
	} else {
		ub->params.devt.disk_major = 0;
		ub->params.devt.disk_minor = 0;
	}
	ub->params.types |= UBLK_PARAM_TYPE_DEVT;
}

static int ublk_ctrl_get_params(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;
	struct ublk_params_header ph;
	int ret;

	if (header->len <= sizeof(ph) || !header->addr)
		return -EINVAL;

	if (copy_from_user(&ph, argp, sizeof(ph)))
		return -EFAULT;

	if (ph.len > header->len || !ph.len)
		return -EINVAL;

	if (ph.len > sizeof(struct ublk_params))
		ph.len = sizeof(struct ublk_params);

	mutex_lock(&ub->mutex);
	ublk_ctrl_fill_params_devt(ub);
	if (copy_to_user(argp, &ub->params, ph.len))
		ret = -EFAULT;
	else
		ret = 0;
	mutex_unlock(&ub->mutex);

	return ret;
}

static int ublk_ctrl_set_params(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;
	struct ublk_params_header ph;
	int ret = -EFAULT;

	if (header->len <= sizeof(ph) || !header->addr)
		return -EINVAL;

	if (copy_from_user(&ph, argp, sizeof(ph)))
		return -EFAULT;

	if (ph.len > header->len || !ph.len || !ph.types)
		return -EINVAL;

	if (ph.len > sizeof(struct ublk_params))
		ph.len = sizeof(struct ublk_params);

	/* parameters can only be changed when device isn't live */
	mutex_lock(&ub->mutex);
	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
		ret = -EACCES;
	} else if (copy_from_user(&ub->params, argp, ph.len)) {
		ret = -EFAULT;
	} else {
		/* clear all we don't support yet */
		ub->params.types &= UBLK_PARAM_TYPE_ALL;
		ret = ublk_validate_params(ub);
		if (ret)
			ub->params.types = 0;
	}
	mutex_unlock(&ub->mutex);

	return ret;
}

static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
{
	int i;

	WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq)));

	/* All old ioucmds have to be completed */
	ubq->nr_io_ready = 0;
	/* old daemon is PF_EXITING, put it now */
	put_task_struct(ubq->ubq_daemon);
	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
	ubq->ubq_daemon = NULL;
	ubq->timeout = false;
	ubq->canceling = false;

	for (i = 0; i < ubq->q_depth; i++) {
		struct ublk_io *io = &ubq->ios[i];

		/* forget everything now and be ready for new FETCH_REQ */
		io->flags = 0;
		io->cmd = NULL;
		io->addr = 0;
	}
}

static int ublk_ctrl_start_recovery(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	int ret = -EINVAL;
	int i;

	mutex_lock(&ub->mutex);
	if (!ublk_can_use_recovery(ub))
		goto out_unlock;
	/*
	 * START_RECOVERY is only allowd after:
	 *
	 * (1) UB_STATE_OPEN is not set, which means the dying process is exited
	 *     and related io_uring ctx is freed so file struct of /dev/ublkcX is
	 *     released.
	 *
	 * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
	 *     (a)has quiesced request queue
	 *     (b)has requeued every inflight rqs whose io_flags is ACTIVE
	 *     (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
	 *     (d)has completed/camceled all ioucmds owned by ther dying process
	 */
	if (test_bit(UB_STATE_OPEN, &ub->state) ||
			ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
		ret = -EBUSY;
		goto out_unlock;
	}
	pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id);
	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
	ub->mm = NULL;
	ub->nr_queues_ready = 0;
	ub->nr_privileged_daemon = 0;
	init_completion(&ub->completion);
	ret = 0;
 out_unlock:
	mutex_unlock(&ub->mutex);
	return ret;
}

static int ublk_ctrl_end_recovery(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	int ublksrv_pid = (int)header->data[0];
	int ret = -EINVAL;

	pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
	/* wait until new ubq_daemon sending all FETCH_REQ */
	if (wait_for_completion_interruptible(&ub->completion))
		return -EINTR;

	pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n",
			__func__, ub->dev_info.nr_hw_queues, header->dev_id);

	mutex_lock(&ub->mutex);
	if (!ublk_can_use_recovery(ub))
		goto out_unlock;

	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
		ret = -EBUSY;
		goto out_unlock;
	}
	ub->dev_info.ublksrv_pid = ublksrv_pid;
	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
			__func__, ublksrv_pid, header->dev_id);
	blk_mq_unquiesce_queue(ub->ub_disk->queue);
	pr_devel("%s: queue unquiesced, dev id %d.\n",
			__func__, header->dev_id);
	blk_mq_kick_requeue_list(ub->ub_disk->queue);
	ub->dev_info.state = UBLK_S_DEV_LIVE;
	ret = 0;
 out_unlock:
	mutex_unlock(&ub->mutex);
	return ret;
}

static int ublk_ctrl_get_features(struct io_uring_cmd *cmd)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	void __user *argp = (void __user *)(unsigned long)header->addr;
	u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY;

	if (header->len != UBLK_FEATURES_LEN || !header->addr)
		return -EINVAL;

	if (copy_to_user(argp, &features, UBLK_FEATURES_LEN))
		return -EFAULT;

	return 0;
}

/*
 * All control commands are sent via /dev/ublk-control, so we have to check
 * the destination device's permission
 */
static int ublk_char_dev_permission(struct ublk_device *ub,
		const char *dev_path, int mask)
{
	int err;
	struct path path;
	struct kstat stat;

	err = kern_path(dev_path, LOOKUP_FOLLOW, &path);
	if (err)
		return err;

	err = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT);
	if (err)
		goto exit;

	err = -EPERM;
	if (stat.rdev != ub->cdev_dev.devt || !S_ISCHR(stat.mode))
		goto exit;

	err = inode_permission(&nop_mnt_idmap,
			d_backing_inode(path.dentry), mask);
exit:
	path_put(&path);
	return err;
}

static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
		struct io_uring_cmd *cmd)
{
	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)io_uring_sqe_cmd(cmd->sqe);
	bool unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
	void __user *argp = (void __user *)(unsigned long)header->addr;
	char *dev_path = NULL;
	int ret = 0;
	int mask;

	if (!unprivileged) {
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;
		/*
		 * The new added command of UBLK_CMD_GET_DEV_INFO2 includes
		 * char_dev_path in payload too, since userspace may not
		 * know if the specified device is created as unprivileged
		 * mode.
		 */
		if (_IOC_NR(cmd->cmd_op) != UBLK_CMD_GET_DEV_INFO2)
			return 0;
	}

	/*
	 * User has to provide the char device path for unprivileged ublk
	 *
	 * header->addr always points to the dev path buffer, and
	 * header->dev_path_len records length of dev path buffer.
	 */
	if (!header->dev_path_len || header->dev_path_len > PATH_MAX)
		return -EINVAL;

	if (header->len < header->dev_path_len)
		return -EINVAL;

	dev_path = memdup_user_nul(argp, header->dev_path_len);
	if (IS_ERR(dev_path))
		return PTR_ERR(dev_path);

	ret = -EINVAL;
	switch (_IOC_NR(cmd->cmd_op)) {
	case UBLK_CMD_GET_DEV_INFO:
	case UBLK_CMD_GET_DEV_INFO2:
	case UBLK_CMD_GET_QUEUE_AFFINITY:
	case UBLK_CMD_GET_PARAMS:
	case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)):
		mask = MAY_READ;
		break;
	case UBLK_CMD_START_DEV:
	case UBLK_CMD_STOP_DEV:
	case UBLK_CMD_ADD_DEV:
	case UBLK_CMD_DEL_DEV:
	case UBLK_CMD_SET_PARAMS:
	case UBLK_CMD_START_USER_RECOVERY:
	case UBLK_CMD_END_USER_RECOVERY:
		mask = MAY_READ | MAY_WRITE;
		break;
	default:
		goto exit;
	}

	ret = ublk_char_dev_permission(ub, dev_path, mask);
	if (!ret) {
		header->len -= header->dev_path_len;
		header->addr += header->dev_path_len;
	}
	pr_devel("%s: dev id %d cmd_op %x uid %d gid %d path %s ret %d\n",
			__func__, ub->ub_number, cmd->cmd_op,
			ub->dev_info.owner_uid, ub->dev_info.owner_gid,
			dev_path, ret);
exit:
	kfree(dev_path);
	return ret;
}

static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
		unsigned int issue_flags)
{
	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
	struct ublk_device *ub = NULL;
	u32 cmd_op = cmd->cmd_op;
	int ret = -EINVAL;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ublk_ctrl_cmd_dump(cmd);

	if (!(issue_flags & IO_URING_F_SQE128))
		goto out;

	ret = ublk_check_cmd_op(cmd_op);
	if (ret)
		goto out;

	if (cmd_op == UBLK_U_CMD_GET_FEATURES) {
		ret = ublk_ctrl_get_features(cmd);
		goto out;
	}

	if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) {
		ret = -ENODEV;
		ub = ublk_get_device_from_id(header->dev_id);
		if (!ub)
			goto out;

		ret = ublk_ctrl_uring_cmd_permission(ub, cmd);
		if (ret)
			goto put_dev;
	}

	switch (_IOC_NR(cmd_op)) {
	case UBLK_CMD_START_DEV:
		ret = ublk_ctrl_start_dev(ub, cmd);
		break;
	case UBLK_CMD_STOP_DEV:
		ret = ublk_ctrl_stop_dev(ub);
		break;
	case UBLK_CMD_GET_DEV_INFO:
	case UBLK_CMD_GET_DEV_INFO2:
		ret = ublk_ctrl_get_dev_info(ub, cmd);
		break;
	case UBLK_CMD_ADD_DEV:
		ret = ublk_ctrl_add_dev(cmd);
		break;
	case UBLK_CMD_DEL_DEV:
		ret = ublk_ctrl_del_dev(&ub, true);
		break;
	case UBLK_U_CMD_DEL_DEV_ASYNC:
		ret = ublk_ctrl_del_dev(&ub, false);
		break;
	case UBLK_CMD_GET_QUEUE_AFFINITY:
		ret = ublk_ctrl_get_queue_affinity(ub, cmd);
		break;
	case UBLK_CMD_GET_PARAMS:
		ret = ublk_ctrl_get_params(ub, cmd);
		break;
	case UBLK_CMD_SET_PARAMS:
		ret = ublk_ctrl_set_params(ub, cmd);
		break;
	case UBLK_CMD_START_USER_RECOVERY:
		ret = ublk_ctrl_start_recovery(ub, cmd);
		break;
	case UBLK_CMD_END_USER_RECOVERY:
		ret = ublk_ctrl_end_recovery(ub, cmd);
		break;
	default:
		ret = -ENOTSUPP;
		break;
	}

 put_dev:
	if (ub)
		ublk_put_device(ub);
 out:
	io_uring_cmd_done(cmd, ret, 0, issue_flags);
	pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n",
			__func__, ret, cmd->cmd_op, header->dev_id, header->queue_id);
	return -EIOCBQUEUED;
}

static const struct file_operations ublk_ctl_fops = {
	.open		= nonseekable_open,
	.uring_cmd      = ublk_ctrl_uring_cmd,
	.owner		= THIS_MODULE,
	.llseek		= noop_llseek,
};

static struct miscdevice ublk_misc = {
	.minor		= MISC_DYNAMIC_MINOR,
	.name		= "ublk-control",
	.fops		= &ublk_ctl_fops,
};

static int __init ublk_init(void)
{
	int ret;

	BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET +
			UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET);

	init_waitqueue_head(&ublk_idr_wq);

	ret = misc_register(&ublk_misc);
	if (ret)
		return ret;

	ret = alloc_chrdev_region(&ublk_chr_devt, 0, UBLK_MINORS, "ublk-char");
	if (ret)
		goto unregister_mis;

	ret = class_register(&ublk_chr_class);
	if (ret)
		goto free_chrdev_region;

	return 0;

free_chrdev_region:
	unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
unregister_mis:
	misc_deregister(&ublk_misc);
	return ret;
}

static void __exit ublk_exit(void)
{
	struct ublk_device *ub;
	int id;

	idr_for_each_entry(&ublk_index_idr, ub, id)
		ublk_remove(ub);

	class_unregister(&ublk_chr_class);
	misc_deregister(&ublk_misc);

	idr_destroy(&ublk_index_idr);
	unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
}

module_init(ublk_init);
module_exit(ublk_exit);

static int ublk_set_max_ublks(const char *buf, const struct kernel_param *kp)
{
	return param_set_uint_minmax(buf, kp, 0, UBLK_MAX_UBLKS);
}

static int ublk_get_max_ublks(char *buf, const struct kernel_param *kp)
{
	return sysfs_emit(buf, "%u\n", ublks_max);
}

static const struct kernel_param_ops ublk_max_ublks_ops = {
	.set = ublk_set_max_ublks,
	.get = ublk_get_max_ublks,
};

module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644);
MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)");

MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>");
MODULE_LICENSE("GPL");