summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/rdma.c
blob: 6d4119dfbdaacf5df18c41bf92d0711c2e074bbf (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
/*
 * NVMe over Fabrics RDMA host code.
 * Copyright (c) 2015-2016 HGST, a Western Digital Company.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/string.h>
#include <linux/atomic.h>
#include <linux/blk-mq.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/nvme.h>
#include <asm/unaligned.h>

#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <linux/nvme-rdma.h>

#include "nvme.h"
#include "fabrics.h"


#define NVME_RDMA_CONNECT_TIMEOUT_MS	3000		/* 3 second */

#define NVME_RDMA_MAX_SEGMENT_SIZE	0xffffff	/* 24-bit SGL field */

#define NVME_RDMA_MAX_SEGMENTS		256

#define NVME_RDMA_MAX_INLINE_SEGMENTS	1

/*
 * We handle AEN commands ourselves and don't even let the
 * block layer know about them.
 */
#define NVME_RDMA_NR_AEN_COMMANDS      1
#define NVME_RDMA_AQ_BLKMQ_DEPTH       \
	(NVME_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS)

struct nvme_rdma_device {
	struct ib_device       *dev;
	struct ib_pd	       *pd;
	struct kref		ref;
	struct list_head	entry;
};

struct nvme_rdma_qe {
	struct ib_cqe		cqe;
	void			*data;
	u64			dma;
};

struct nvme_rdma_queue;
struct nvme_rdma_request {
	struct nvme_request	req;
	struct ib_mr		*mr;
	struct nvme_rdma_qe	sqe;
	struct ib_sge		sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
	u32			num_sge;
	int			nents;
	bool			inline_data;
	struct ib_reg_wr	reg_wr;
	struct ib_cqe		reg_cqe;
	struct nvme_rdma_queue  *queue;
	struct sg_table		sg_table;
	struct scatterlist	first_sgl[];
};

enum nvme_rdma_queue_flags {
	NVME_RDMA_Q_LIVE		= 0,
	NVME_RDMA_Q_DELETING		= 1,
};

struct nvme_rdma_queue {
	struct nvme_rdma_qe	*rsp_ring;
	u8			sig_count;
	int			queue_size;
	size_t			cmnd_capsule_len;
	struct nvme_rdma_ctrl	*ctrl;
	struct nvme_rdma_device	*device;
	struct ib_cq		*ib_cq;
	struct ib_qp		*qp;

	unsigned long		flags;
	struct rdma_cm_id	*cm_id;
	int			cm_error;
	struct completion	cm_done;
};

struct nvme_rdma_ctrl {
	/* read only in the hot path */
	struct nvme_rdma_queue	*queues;
	u32			queue_count;

	/* other member variables */
	struct blk_mq_tag_set	tag_set;
	struct work_struct	delete_work;
	struct work_struct	err_work;

	struct nvme_rdma_qe	async_event_sqe;

	struct delayed_work	reconnect_work;

	struct list_head	list;

	struct blk_mq_tag_set	admin_tag_set;
	struct nvme_rdma_device	*device;

	u64			cap;
	u32			max_fr_pages;

	struct sockaddr_storage addr;
	struct sockaddr_storage src_addr;

	struct nvme_ctrl	ctrl;
};

static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
{
	return container_of(ctrl, struct nvme_rdma_ctrl, ctrl);
}

static LIST_HEAD(device_list);
static DEFINE_MUTEX(device_list_mutex);

static LIST_HEAD(nvme_rdma_ctrl_list);
static DEFINE_MUTEX(nvme_rdma_ctrl_mutex);

/*
 * Disabling this option makes small I/O goes faster, but is fundamentally
 * unsafe.  With it turned off we will have to register a global rkey that
 * allows read and write access to all physical memory.
 */
static bool register_always = true;
module_param(register_always, bool, 0444);
MODULE_PARM_DESC(register_always,
	 "Use memory registration even for contiguous memory regions");

static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
		struct rdma_cm_event *event);
static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);

/* XXX: really should move to a generic header sooner or later.. */
static inline void put_unaligned_le24(u32 val, u8 *p)
{
	*p++ = val;
	*p++ = val >> 8;
	*p++ = val >> 16;
}

static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
{
	return queue - queue->ctrl->queues;
}

static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue)
{
	return queue->cmnd_capsule_len - sizeof(struct nvme_command);
}

static void nvme_rdma_free_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
		size_t capsule_size, enum dma_data_direction dir)
{
	ib_dma_unmap_single(ibdev, qe->dma, capsule_size, dir);
	kfree(qe->data);
}

static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
		size_t capsule_size, enum dma_data_direction dir)
{
	qe->data = kzalloc(capsule_size, GFP_KERNEL);
	if (!qe->data)
		return -ENOMEM;

	qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir);
	if (ib_dma_mapping_error(ibdev, qe->dma)) {
		kfree(qe->data);
		return -ENOMEM;
	}

	return 0;
}

static void nvme_rdma_free_ring(struct ib_device *ibdev,
		struct nvme_rdma_qe *ring, size_t ib_queue_size,
		size_t capsule_size, enum dma_data_direction dir)
{
	int i;

	for (i = 0; i < ib_queue_size; i++)
		nvme_rdma_free_qe(ibdev, &ring[i], capsule_size, dir);
	kfree(ring);
}

static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
		size_t ib_queue_size, size_t capsule_size,
		enum dma_data_direction dir)
{
	struct nvme_rdma_qe *ring;
	int i;

	ring = kcalloc(ib_queue_size, sizeof(struct nvme_rdma_qe), GFP_KERNEL);
	if (!ring)
		return NULL;

	for (i = 0; i < ib_queue_size; i++) {
		if (nvme_rdma_alloc_qe(ibdev, &ring[i], capsule_size, dir))
			goto out_free_ring;
	}

	return ring;

out_free_ring:
	nvme_rdma_free_ring(ibdev, ring, i, capsule_size, dir);
	return NULL;
}

static void nvme_rdma_qp_event(struct ib_event *event, void *context)
{
	pr_debug("QP event %s (%d)\n",
		 ib_event_msg(event->event), event->event);

}

static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue)
{
	wait_for_completion_interruptible_timeout(&queue->cm_done,
			msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1);
	return queue->cm_error;
}

static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
{
	struct nvme_rdma_device *dev = queue->device;
	struct ib_qp_init_attr init_attr;
	int ret;

	memset(&init_attr, 0, sizeof(init_attr));
	init_attr.event_handler = nvme_rdma_qp_event;
	/* +1 for drain */
	init_attr.cap.max_send_wr = factor * queue->queue_size + 1;
	/* +1 for drain */
	init_attr.cap.max_recv_wr = queue->queue_size + 1;
	init_attr.cap.max_recv_sge = 1;
	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
	init_attr.qp_type = IB_QPT_RC;
	init_attr.send_cq = queue->ib_cq;
	init_attr.recv_cq = queue->ib_cq;

	ret = rdma_create_qp(queue->cm_id, dev->pd, &init_attr);

	queue->qp = queue->cm_id->qp;
	return ret;
}

static int nvme_rdma_reinit_request(void *data, struct request *rq)
{
	struct nvme_rdma_ctrl *ctrl = data;
	struct nvme_rdma_device *dev = ctrl->device;
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	int ret = 0;

	if (!req->mr->need_inval)
		goto out;

	ib_dereg_mr(req->mr);

	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
			ctrl->max_fr_pages);
	if (IS_ERR(req->mr)) {
		ret = PTR_ERR(req->mr);
		req->mr = NULL;
		goto out;
	}

	req->mr->need_inval = false;

out:
	return ret;
}

static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
		struct request *rq, unsigned int hctx_idx)
{
	struct nvme_rdma_ctrl *ctrl = set->driver_data;
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
	struct nvme_rdma_device *dev = queue->device;

	if (req->mr)
		ib_dereg_mr(req->mr);

	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
			DMA_TO_DEVICE);
}

static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
		struct request *rq, unsigned int hctx_idx,
		unsigned int numa_node)
{
	struct nvme_rdma_ctrl *ctrl = set->driver_data;
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
	struct nvme_rdma_device *dev = queue->device;
	struct ib_device *ibdev = dev->dev;
	int ret;

	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
			DMA_TO_DEVICE);
	if (ret)
		return ret;

	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
			ctrl->max_fr_pages);
	if (IS_ERR(req->mr)) {
		ret = PTR_ERR(req->mr);
		goto out_free_qe;
	}

	req->queue = queue;

	return 0;

out_free_qe:
	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
			DMA_TO_DEVICE);
	return -ENOMEM;
}

static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
		unsigned int hctx_idx)
{
	struct nvme_rdma_ctrl *ctrl = data;
	struct nvme_rdma_queue *queue = &ctrl->queues[hctx_idx + 1];

	BUG_ON(hctx_idx >= ctrl->queue_count);

	hctx->driver_data = queue;
	return 0;
}

static int nvme_rdma_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
		unsigned int hctx_idx)
{
	struct nvme_rdma_ctrl *ctrl = data;
	struct nvme_rdma_queue *queue = &ctrl->queues[0];

	BUG_ON(hctx_idx != 0);

	hctx->driver_data = queue;
	return 0;
}

static void nvme_rdma_free_dev(struct kref *ref)
{
	struct nvme_rdma_device *ndev =
		container_of(ref, struct nvme_rdma_device, ref);

	mutex_lock(&device_list_mutex);
	list_del(&ndev->entry);
	mutex_unlock(&device_list_mutex);

	ib_dealloc_pd(ndev->pd);
	kfree(ndev);
}

static void nvme_rdma_dev_put(struct nvme_rdma_device *dev)
{
	kref_put(&dev->ref, nvme_rdma_free_dev);
}

static int nvme_rdma_dev_get(struct nvme_rdma_device *dev)
{
	return kref_get_unless_zero(&dev->ref);
}

static struct nvme_rdma_device *
nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
{
	struct nvme_rdma_device *ndev;

	mutex_lock(&device_list_mutex);
	list_for_each_entry(ndev, &device_list, entry) {
		if (ndev->dev->node_guid == cm_id->device->node_guid &&
		    nvme_rdma_dev_get(ndev))
			goto out_unlock;
	}

	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
	if (!ndev)
		goto out_err;

	ndev->dev = cm_id->device;
	kref_init(&ndev->ref);

	ndev->pd = ib_alloc_pd(ndev->dev,
		register_always ? 0 : IB_PD_UNSAFE_GLOBAL_RKEY);
	if (IS_ERR(ndev->pd))
		goto out_free_dev;

	if (!(ndev->dev->attrs.device_cap_flags &
	      IB_DEVICE_MEM_MGT_EXTENSIONS)) {
		dev_err(&ndev->dev->dev,
			"Memory registrations not supported.\n");
		goto out_free_pd;
	}

	list_add(&ndev->entry, &device_list);
out_unlock:
	mutex_unlock(&device_list_mutex);
	return ndev;

out_free_pd:
	ib_dealloc_pd(ndev->pd);
out_free_dev:
	kfree(ndev);
out_err:
	mutex_unlock(&device_list_mutex);
	return NULL;
}

static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
{
	struct nvme_rdma_device *dev;
	struct ib_device *ibdev;

	dev = queue->device;
	ibdev = dev->dev;
	rdma_destroy_qp(queue->cm_id);
	ib_free_cq(queue->ib_cq);

	nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
			sizeof(struct nvme_completion), DMA_FROM_DEVICE);

	nvme_rdma_dev_put(dev);
}

static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
{
	struct ib_device *ibdev;
	const int send_wr_factor = 3;			/* MR, SEND, INV */
	const int cq_factor = send_wr_factor + 1;	/* + RECV */
	int comp_vector, idx = nvme_rdma_queue_idx(queue);
	int ret;

	queue->device = nvme_rdma_find_get_device(queue->cm_id);
	if (!queue->device) {
		dev_err(queue->cm_id->device->dev.parent,
			"no client data found!\n");
		return -ECONNREFUSED;
	}
	ibdev = queue->device->dev;

	/*
	 * The admin queue is barely used once the controller is live, so don't
	 * bother to spread it out.
	 */
	if (idx == 0)
		comp_vector = 0;
	else
		comp_vector = idx % ibdev->num_comp_vectors;


	/* +1 for ib_stop_cq */
	queue->ib_cq = ib_alloc_cq(ibdev, queue,
				cq_factor * queue->queue_size + 1,
				comp_vector, IB_POLL_SOFTIRQ);
	if (IS_ERR(queue->ib_cq)) {
		ret = PTR_ERR(queue->ib_cq);
		goto out_put_dev;
	}

	ret = nvme_rdma_create_qp(queue, send_wr_factor);
	if (ret)
		goto out_destroy_ib_cq;

	queue->rsp_ring = nvme_rdma_alloc_ring(ibdev, queue->queue_size,
			sizeof(struct nvme_completion), DMA_FROM_DEVICE);
	if (!queue->rsp_ring) {
		ret = -ENOMEM;
		goto out_destroy_qp;
	}

	return 0;

out_destroy_qp:
	ib_destroy_qp(queue->qp);
out_destroy_ib_cq:
	ib_free_cq(queue->ib_cq);
out_put_dev:
	nvme_rdma_dev_put(queue->device);
	return ret;
}

static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
		int idx, size_t queue_size)
{
	struct nvme_rdma_queue *queue;
	struct sockaddr *src_addr = NULL;
	int ret;

	queue = &ctrl->queues[idx];
	queue->ctrl = ctrl;
	init_completion(&queue->cm_done);

	if (idx > 0)
		queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16;
	else
		queue->cmnd_capsule_len = sizeof(struct nvme_command);

	queue->queue_size = queue_size;

	queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
			RDMA_PS_TCP, IB_QPT_RC);
	if (IS_ERR(queue->cm_id)) {
		dev_info(ctrl->ctrl.device,
			"failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id));
		return PTR_ERR(queue->cm_id);
	}

	if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
		src_addr = (struct sockaddr *)&ctrl->src_addr;

	queue->cm_error = -ETIMEDOUT;
	ret = rdma_resolve_addr(queue->cm_id, src_addr,
			(struct sockaddr *)&ctrl->addr,
			NVME_RDMA_CONNECT_TIMEOUT_MS);
	if (ret) {
		dev_info(ctrl->ctrl.device,
			"rdma_resolve_addr failed (%d).\n", ret);
		goto out_destroy_cm_id;
	}

	ret = nvme_rdma_wait_for_cm(queue);
	if (ret) {
		dev_info(ctrl->ctrl.device,
			"rdma_resolve_addr wait failed (%d).\n", ret);
		goto out_destroy_cm_id;
	}

	clear_bit(NVME_RDMA_Q_DELETING, &queue->flags);

	return 0;

out_destroy_cm_id:
	rdma_destroy_id(queue->cm_id);
	return ret;
}

static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
{
	rdma_disconnect(queue->cm_id);
	ib_drain_qp(queue->qp);
}

static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
{
	nvme_rdma_destroy_queue_ib(queue);
	rdma_destroy_id(queue->cm_id);
}

static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
{
	if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
		return;
	nvme_rdma_stop_queue(queue);
	nvme_rdma_free_queue(queue);
}

static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl)
{
	int i;

	for (i = 1; i < ctrl->queue_count; i++)
		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
}

static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
{
	int i, ret = 0;

	for (i = 1; i < ctrl->queue_count; i++) {
		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
		if (ret) {
			dev_info(ctrl->ctrl.device,
				"failed to connect i/o queue: %d\n", ret);
			goto out_free_queues;
		}
		set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags);
	}

	return 0;

out_free_queues:
	nvme_rdma_free_io_queues(ctrl);
	return ret;
}

static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
{
	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
	unsigned int nr_io_queues;
	int i, ret;

	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
	if (ret)
		return ret;

	ctrl->queue_count = nr_io_queues + 1;
	if (ctrl->queue_count < 2)
		return 0;

	dev_info(ctrl->ctrl.device,
		"creating %d I/O queues.\n", nr_io_queues);

	for (i = 1; i < ctrl->queue_count; i++) {
		ret = nvme_rdma_init_queue(ctrl, i,
					   ctrl->ctrl.opts->queue_size);
		if (ret) {
			dev_info(ctrl->ctrl.device,
				"failed to initialize i/o queue: %d\n", ret);
			goto out_free_queues;
		}
	}

	return 0;

out_free_queues:
	for (i--; i >= 1; i--)
		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);

	return ret;
}

static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl)
{
	nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
			sizeof(struct nvme_command), DMA_TO_DEVICE);
	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
	blk_cleanup_queue(ctrl->ctrl.admin_q);
	blk_mq_free_tag_set(&ctrl->admin_tag_set);
	nvme_rdma_dev_put(ctrl->device);
}

static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
{
	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);

	if (list_empty(&ctrl->list))
		goto free_ctrl;

	mutex_lock(&nvme_rdma_ctrl_mutex);
	list_del(&ctrl->list);
	mutex_unlock(&nvme_rdma_ctrl_mutex);

	kfree(ctrl->queues);
	nvmf_free_options(nctrl->opts);
free_ctrl:
	kfree(ctrl);
}

static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
{
	/* If we are resetting/deleting then do nothing */
	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
			ctrl->ctrl.state == NVME_CTRL_LIVE);
		return;
	}

	if (nvmf_should_reconnect(&ctrl->ctrl)) {
		dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
			ctrl->ctrl.opts->reconnect_delay);
		queue_delayed_work(nvme_wq, &ctrl->reconnect_work,
				ctrl->ctrl.opts->reconnect_delay * HZ);
	} else {
		dev_info(ctrl->ctrl.device, "Removing controller...\n");
		queue_work(nvme_wq, &ctrl->delete_work);
	}
}

static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
{
	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
			struct nvme_rdma_ctrl, reconnect_work);
	bool changed;
	int ret;

	++ctrl->ctrl.nr_reconnects;

	if (ctrl->queue_count > 1) {
		nvme_rdma_free_io_queues(ctrl);

		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
		if (ret)
			goto requeue;
	}

	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);

	ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set);
	if (ret)
		goto requeue;

	ret = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH);
	if (ret)
		goto requeue;

	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
	if (ret)
		goto requeue;

	set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);

	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
	if (ret)
		goto requeue;

	nvme_start_keep_alive(&ctrl->ctrl);

	if (ctrl->queue_count > 1) {
		ret = nvme_rdma_init_io_queues(ctrl);
		if (ret)
			goto requeue;

		ret = nvme_rdma_connect_io_queues(ctrl);
		if (ret)
			goto requeue;
	}

	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
	WARN_ON_ONCE(!changed);
	ctrl->ctrl.nr_reconnects = 0;

	if (ctrl->queue_count > 1) {
		nvme_queue_scan(&ctrl->ctrl);
		nvme_queue_async_events(&ctrl->ctrl);
	}

	dev_info(ctrl->ctrl.device, "Successfully reconnected\n");

	return;

requeue:
	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
			ctrl->ctrl.nr_reconnects);
	nvme_rdma_reconnect_or_remove(ctrl);
}

static void nvme_rdma_error_recovery_work(struct work_struct *work)
{
	struct nvme_rdma_ctrl *ctrl = container_of(work,
			struct nvme_rdma_ctrl, err_work);
	int i;

	nvme_stop_keep_alive(&ctrl->ctrl);

	for (i = 0; i < ctrl->queue_count; i++)
		clear_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags);

	if (ctrl->queue_count > 1)
		nvme_stop_queues(&ctrl->ctrl);
	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);

	/* We must take care of fastfail/requeue all our inflight requests */
	if (ctrl->queue_count > 1)
		blk_mq_tagset_busy_iter(&ctrl->tag_set,
					nvme_cancel_request, &ctrl->ctrl);
	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
				nvme_cancel_request, &ctrl->ctrl);

	/*
	 * queues are not a live anymore, so restart the queues to fail fast
	 * new IO
	 */
	blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
	nvme_start_queues(&ctrl->ctrl);

	nvme_rdma_reconnect_or_remove(ctrl);
}

static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
{
	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING))
		return;

	queue_work(nvme_wq, &ctrl->err_work);
}

static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
		const char *op)
{
	struct nvme_rdma_queue *queue = cq->cq_context;
	struct nvme_rdma_ctrl *ctrl = queue->ctrl;

	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
		dev_info(ctrl->ctrl.device,
			     "%s for CQE 0x%p failed with status %s (%d)\n",
			     op, wc->wr_cqe,
			     ib_wc_status_msg(wc->status), wc->status);
	nvme_rdma_error_recovery(ctrl);
}

static void nvme_rdma_memreg_done(struct ib_cq *cq, struct ib_wc *wc)
{
	if (unlikely(wc->status != IB_WC_SUCCESS))
		nvme_rdma_wr_error(cq, wc, "MEMREG");
}

static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
{
	if (unlikely(wc->status != IB_WC_SUCCESS))
		nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
}

static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
		struct nvme_rdma_request *req)
{
	struct ib_send_wr *bad_wr;
	struct ib_send_wr wr = {
		.opcode		    = IB_WR_LOCAL_INV,
		.next		    = NULL,
		.num_sge	    = 0,
		.send_flags	    = 0,
		.ex.invalidate_rkey = req->mr->rkey,
	};

	req->reg_cqe.done = nvme_rdma_inv_rkey_done;
	wr.wr_cqe = &req->reg_cqe;

	return ib_post_send(queue->qp, &wr, &bad_wr);
}

static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
		struct request *rq)
{
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
	struct nvme_rdma_device *dev = queue->device;
	struct ib_device *ibdev = dev->dev;
	int res;

	if (!blk_rq_bytes(rq))
		return;

	if (req->mr->need_inval) {
		res = nvme_rdma_inv_rkey(queue, req);
		if (res < 0) {
			dev_err(ctrl->ctrl.device,
				"Queueing INV WR for rkey %#x failed (%d)\n",
				req->mr->rkey, res);
			nvme_rdma_error_recovery(queue->ctrl);
		}
	}

	ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
			req->nents, rq_data_dir(rq) ==
				    WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);

	nvme_cleanup_cmd(rq);
	sg_free_table_chained(&req->sg_table, true);
}

static int nvme_rdma_set_sg_null(struct nvme_command *c)
{
	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;

	sg->addr = 0;
	put_unaligned_le24(0, sg->length);
	put_unaligned_le32(0, sg->key);
	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
	return 0;
}

static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
		struct nvme_rdma_request *req, struct nvme_command *c)
{
	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;

	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
	req->sge[1].lkey = queue->device->pd->local_dma_lkey;

	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;

	req->inline_data = true;
	req->num_sge++;
	return 0;
}

static int nvme_rdma_map_sg_single(struct nvme_rdma_queue *queue,
		struct nvme_rdma_request *req, struct nvme_command *c)
{
	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;

	sg->addr = cpu_to_le64(sg_dma_address(req->sg_table.sgl));
	put_unaligned_le24(sg_dma_len(req->sg_table.sgl), sg->length);
	put_unaligned_le32(queue->device->pd->unsafe_global_rkey, sg->key);
	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
	return 0;
}

static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
		struct nvme_rdma_request *req, struct nvme_command *c,
		int count)
{
	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
	int nr;

	nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE);
	if (nr < count) {
		if (nr < 0)
			return nr;
		return -EINVAL;
	}

	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));

	req->reg_cqe.done = nvme_rdma_memreg_done;
	memset(&req->reg_wr, 0, sizeof(req->reg_wr));
	req->reg_wr.wr.opcode = IB_WR_REG_MR;
	req->reg_wr.wr.wr_cqe = &req->reg_cqe;
	req->reg_wr.wr.num_sge = 0;
	req->reg_wr.mr = req->mr;
	req->reg_wr.key = req->mr->rkey;
	req->reg_wr.access = IB_ACCESS_LOCAL_WRITE |
			     IB_ACCESS_REMOTE_READ |
			     IB_ACCESS_REMOTE_WRITE;

	req->mr->need_inval = true;

	sg->addr = cpu_to_le64(req->mr->iova);
	put_unaligned_le24(req->mr->length, sg->length);
	put_unaligned_le32(req->mr->rkey, sg->key);
	sg->type = (NVME_KEY_SGL_FMT_DATA_DESC << 4) |
			NVME_SGL_FMT_INVALIDATE;

	return 0;
}

static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
		struct request *rq, struct nvme_command *c)
{
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	struct nvme_rdma_device *dev = queue->device;
	struct ib_device *ibdev = dev->dev;
	int count, ret;

	req->num_sge = 1;
	req->inline_data = false;
	req->mr->need_inval = false;

	c->common.flags |= NVME_CMD_SGL_METABUF;

	if (!blk_rq_bytes(rq))
		return nvme_rdma_set_sg_null(c);

	req->sg_table.sgl = req->first_sgl;
	ret = sg_alloc_table_chained(&req->sg_table,
			blk_rq_nr_phys_segments(rq), req->sg_table.sgl);
	if (ret)
		return -ENOMEM;

	req->nents = blk_rq_map_sg(rq->q, rq, req->sg_table.sgl);

	count = ib_dma_map_sg(ibdev, req->sg_table.sgl, req->nents,
		    rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
	if (unlikely(count <= 0)) {
		sg_free_table_chained(&req->sg_table, true);
		return -EIO;
	}

	if (count == 1) {
		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
		    blk_rq_payload_bytes(rq) <=
				nvme_rdma_inline_data_size(queue))
			return nvme_rdma_map_sg_inline(queue, req, c);

		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
			return nvme_rdma_map_sg_single(queue, req, c);
	}

	return nvme_rdma_map_sg_fr(queue, req, c, count);
}

static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
{
	if (unlikely(wc->status != IB_WC_SUCCESS))
		nvme_rdma_wr_error(cq, wc, "SEND");
}

static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
{
	int sig_limit;

	/*
	 * We signal completion every queue depth/2 and also handle the
	 * degenerated case of a  device with queue_depth=1, where we
	 * would need to signal every message.
	 */
	sig_limit = max(queue->queue_size / 2, 1);
	return (++queue->sig_count % sig_limit) == 0;
}

static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
		struct ib_send_wr *first, bool flush)
{
	struct ib_send_wr wr, *bad_wr;
	int ret;

	sge->addr   = qe->dma;
	sge->length = sizeof(struct nvme_command),
	sge->lkey   = queue->device->pd->local_dma_lkey;

	qe->cqe.done = nvme_rdma_send_done;

	wr.next       = NULL;
	wr.wr_cqe     = &qe->cqe;
	wr.sg_list    = sge;
	wr.num_sge    = num_sge;
	wr.opcode     = IB_WR_SEND;
	wr.send_flags = 0;

	/*
	 * Unsignalled send completions are another giant desaster in the
	 * IB Verbs spec:  If we don't regularly post signalled sends
	 * the send queue will fill up and only a QP reset will rescue us.
	 * Would have been way to obvious to handle this in hardware or
	 * at least the RDMA stack..
	 *
	 * Always signal the flushes. The magic request used for the flush
	 * sequencer is not allocated in our driver's tagset and it's
	 * triggered to be freed by blk_cleanup_queue(). So we need to
	 * always mark it as signaled to ensure that the "wr_cqe", which is
	 * embedded in request's payload, is not freed when __ib_process_cq()
	 * calls wr_cqe->done().
	 */
	if (nvme_rdma_queue_sig_limit(queue) || flush)
		wr.send_flags |= IB_SEND_SIGNALED;

	if (first)
		first->next = &wr;
	else
		first = &wr;

	ret = ib_post_send(queue->qp, first, &bad_wr);
	if (ret) {
		dev_err(queue->ctrl->ctrl.device,
			     "%s failed with error code %d\n", __func__, ret);
	}
	return ret;
}

static int nvme_rdma_post_recv(struct nvme_rdma_queue *queue,
		struct nvme_rdma_qe *qe)
{
	struct ib_recv_wr wr, *bad_wr;
	struct ib_sge list;
	int ret;

	list.addr   = qe->dma;
	list.length = sizeof(struct nvme_completion);
	list.lkey   = queue->device->pd->local_dma_lkey;

	qe->cqe.done = nvme_rdma_recv_done;

	wr.next     = NULL;
	wr.wr_cqe   = &qe->cqe;
	wr.sg_list  = &list;
	wr.num_sge  = 1;

	ret = ib_post_recv(queue->qp, &wr, &bad_wr);
	if (ret) {
		dev_err(queue->ctrl->ctrl.device,
			"%s failed with error code %d\n", __func__, ret);
	}
	return ret;
}

static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue)
{
	u32 queue_idx = nvme_rdma_queue_idx(queue);

	if (queue_idx == 0)
		return queue->ctrl->admin_tag_set.tags[queue_idx];
	return queue->ctrl->tag_set.tags[queue_idx - 1];
}

static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
{
	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
	struct nvme_rdma_queue *queue = &ctrl->queues[0];
	struct ib_device *dev = queue->device->dev;
	struct nvme_rdma_qe *sqe = &ctrl->async_event_sqe;
	struct nvme_command *cmd = sqe->data;
	struct ib_sge sge;
	int ret;

	if (WARN_ON_ONCE(aer_idx != 0))
		return;

	ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(*cmd), DMA_TO_DEVICE);

	memset(cmd, 0, sizeof(*cmd));
	cmd->common.opcode = nvme_admin_async_event;
	cmd->common.command_id = NVME_RDMA_AQ_BLKMQ_DEPTH;
	cmd->common.flags |= NVME_CMD_SGL_METABUF;
	nvme_rdma_set_sg_null(cmd);

	ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
			DMA_TO_DEVICE);

	ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
	WARN_ON_ONCE(ret);
}

static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
		struct nvme_completion *cqe, struct ib_wc *wc, int tag)
{
	struct request *rq;
	struct nvme_rdma_request *req;
	int ret = 0;

	rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id);
	if (!rq) {
		dev_err(queue->ctrl->ctrl.device,
			"tag 0x%x on QP %#x not found\n",
			cqe->command_id, queue->qp->qp_num);
		nvme_rdma_error_recovery(queue->ctrl);
		return ret;
	}
	req = blk_mq_rq_to_pdu(rq);

	if (rq->tag == tag)
		ret = 1;

	if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
	    wc->ex.invalidate_rkey == req->mr->rkey)
		req->mr->need_inval = false;

	nvme_end_request(rq, cqe->status, cqe->result);
	return ret;
}

static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag)
{
	struct nvme_rdma_qe *qe =
		container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
	struct nvme_rdma_queue *queue = cq->cq_context;
	struct ib_device *ibdev = queue->device->dev;
	struct nvme_completion *cqe = qe->data;
	const size_t len = sizeof(struct nvme_completion);
	int ret = 0;

	if (unlikely(wc->status != IB_WC_SUCCESS)) {
		nvme_rdma_wr_error(cq, wc, "RECV");
		return 0;
	}

	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
	/*
	 * AEN requests are special as they don't time out and can
	 * survive any kind of queue freeze and often don't respond to
	 * aborts.  We don't even bother to allocate a struct request
	 * for them but rather special case them here.
	 */
	if (unlikely(nvme_rdma_queue_idx(queue) == 0 &&
			cqe->command_id >= NVME_RDMA_AQ_BLKMQ_DEPTH))
		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
				&cqe->result);
	else
		ret = nvme_rdma_process_nvme_rsp(queue, cqe, wc, tag);
	ib_dma_sync_single_for_device(ibdev, qe->dma, len, DMA_FROM_DEVICE);

	nvme_rdma_post_recv(queue, qe);
	return ret;
}

static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
{
	__nvme_rdma_recv_done(cq, wc, -1);
}

static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue)
{
	int ret, i;

	for (i = 0; i < queue->queue_size; i++) {
		ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]);
		if (ret)
			goto out_destroy_queue_ib;
	}

	return 0;

out_destroy_queue_ib:
	nvme_rdma_destroy_queue_ib(queue);
	return ret;
}

static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue,
		struct rdma_cm_event *ev)
{
	struct rdma_cm_id *cm_id = queue->cm_id;
	int status = ev->status;
	const char *rej_msg;
	const struct nvme_rdma_cm_rej *rej_data;
	u8 rej_data_len;

	rej_msg = rdma_reject_msg(cm_id, status);
	rej_data = rdma_consumer_reject_data(cm_id, ev, &rej_data_len);

	if (rej_data && rej_data_len >= sizeof(u16)) {
		u16 sts = le16_to_cpu(rej_data->sts);

		dev_err(queue->ctrl->ctrl.device,
		      "Connect rejected: status %d (%s) nvme status %d (%s).\n",
		      status, rej_msg, sts, nvme_rdma_cm_msg(sts));
	} else {
		dev_err(queue->ctrl->ctrl.device,
			"Connect rejected: status %d (%s).\n", status, rej_msg);
	}

	return -ECONNRESET;
}

static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue)
{
	int ret;

	ret = nvme_rdma_create_queue_ib(queue);
	if (ret)
		return ret;

	ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS);
	if (ret) {
		dev_err(queue->ctrl->ctrl.device,
			"rdma_resolve_route failed (%d).\n",
			queue->cm_error);
		goto out_destroy_queue;
	}

	return 0;

out_destroy_queue:
	nvme_rdma_destroy_queue_ib(queue);
	return ret;
}

static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
{
	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
	struct rdma_conn_param param = { };
	struct nvme_rdma_cm_req priv = { };
	int ret;

	param.qp_num = queue->qp->qp_num;
	param.flow_control = 1;

	param.responder_resources = queue->device->dev->attrs.max_qp_rd_atom;
	/* maximum retry count */
	param.retry_count = 7;
	param.rnr_retry_count = 7;
	param.private_data = &priv;
	param.private_data_len = sizeof(priv);

	priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
	priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue));
	/*
	 * set the admin queue depth to the minimum size
	 * specified by the Fabrics standard.
	 */
	if (priv.qid == 0) {
		priv.hrqsize = cpu_to_le16(NVME_AQ_DEPTH);
		priv.hsqsize = cpu_to_le16(NVME_AQ_DEPTH - 1);
	} else {
		/*
		 * current interpretation of the fabrics spec
		 * is at minimum you make hrqsize sqsize+1, or a
		 * 1's based representation of sqsize.
		 */
		priv.hrqsize = cpu_to_le16(queue->queue_size);
		priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
	}

	ret = rdma_connect(queue->cm_id, &param);
	if (ret) {
		dev_err(ctrl->ctrl.device,
			"rdma_connect failed (%d).\n", ret);
		goto out_destroy_queue_ib;
	}

	return 0;

out_destroy_queue_ib:
	nvme_rdma_destroy_queue_ib(queue);
	return ret;
}

static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
		struct rdma_cm_event *ev)
{
	struct nvme_rdma_queue *queue = cm_id->context;
	int cm_error = 0;

	dev_dbg(queue->ctrl->ctrl.device, "%s (%d): status %d id %p\n",
		rdma_event_msg(ev->event), ev->event,
		ev->status, cm_id);

	switch (ev->event) {
	case RDMA_CM_EVENT_ADDR_RESOLVED:
		cm_error = nvme_rdma_addr_resolved(queue);
		break;
	case RDMA_CM_EVENT_ROUTE_RESOLVED:
		cm_error = nvme_rdma_route_resolved(queue);
		break;
	case RDMA_CM_EVENT_ESTABLISHED:
		queue->cm_error = nvme_rdma_conn_established(queue);
		/* complete cm_done regardless of success/failure */
		complete(&queue->cm_done);
		return 0;
	case RDMA_CM_EVENT_REJECTED:
		nvme_rdma_destroy_queue_ib(queue);
		cm_error = nvme_rdma_conn_rejected(queue, ev);
		break;
	case RDMA_CM_EVENT_ROUTE_ERROR:
	case RDMA_CM_EVENT_CONNECT_ERROR:
	case RDMA_CM_EVENT_UNREACHABLE:
		nvme_rdma_destroy_queue_ib(queue);
	case RDMA_CM_EVENT_ADDR_ERROR:
		dev_dbg(queue->ctrl->ctrl.device,
			"CM error event %d\n", ev->event);
		cm_error = -ECONNRESET;
		break;
	case RDMA_CM_EVENT_DISCONNECTED:
	case RDMA_CM_EVENT_ADDR_CHANGE:
	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
		dev_dbg(queue->ctrl->ctrl.device,
			"disconnect received - connection closed\n");
		nvme_rdma_error_recovery(queue->ctrl);
		break;
	case RDMA_CM_EVENT_DEVICE_REMOVAL:
		/* device removal is handled via the ib_client API */
		break;
	default:
		dev_err(queue->ctrl->ctrl.device,
			"Unexpected RDMA CM event (%d)\n", ev->event);
		nvme_rdma_error_recovery(queue->ctrl);
		break;
	}

	if (cm_error) {
		queue->cm_error = cm_error;
		complete(&queue->cm_done);
	}

	return 0;
}

static enum blk_eh_timer_return
nvme_rdma_timeout(struct request *rq, bool reserved)
{
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);

	/* queue error recovery */
	nvme_rdma_error_recovery(req->queue->ctrl);

	/* fail with DNR on cmd timeout */
	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;

	return BLK_EH_HANDLED;
}

/*
 * We cannot accept any other command until the Connect command has completed.
 */
static inline blk_status_t
nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
{
	if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
		struct nvme_command *cmd = nvme_req(rq)->cmd;

		if (!blk_rq_is_passthrough(rq) ||
		    cmd->common.opcode != nvme_fabrics_command ||
		    cmd->fabrics.fctype != nvme_fabrics_type_connect) {
			/*
			 * reconnecting state means transport disruption, which
			 * can take a long time and even might fail permanently,
			 * so we can't let incoming I/O be requeued forever.
			 * fail it fast to allow upper layers a chance to
			 * failover.
			 */
			if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING)
				return BLK_STS_IOERR;
			return BLK_STS_RESOURCE; /* try again later */
		}
	}

	return 0;
}

static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
		const struct blk_mq_queue_data *bd)
{
	struct nvme_ns *ns = hctx->queue->queuedata;
	struct nvme_rdma_queue *queue = hctx->driver_data;
	struct request *rq = bd->rq;
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
	struct nvme_rdma_qe *sqe = &req->sqe;
	struct nvme_command *c = sqe->data;
	bool flush = false;
	struct ib_device *dev;
	blk_status_t ret;
	int err;

	WARN_ON_ONCE(rq->tag < 0);

	ret = nvme_rdma_queue_is_ready(queue, rq);
	if (unlikely(ret))
		return ret;

	dev = queue->device->dev;
	ib_dma_sync_single_for_cpu(dev, sqe->dma,
			sizeof(struct nvme_command), DMA_TO_DEVICE);

	ret = nvme_setup_cmd(ns, rq, c);
	if (ret)
		return ret;

	blk_mq_start_request(rq);

	err = nvme_rdma_map_data(queue, rq, c);
	if (err < 0) {
		dev_err(queue->ctrl->ctrl.device,
			     "Failed to map data (%d)\n", err);
		nvme_cleanup_cmd(rq);
		goto err;
	}

	ib_dma_sync_single_for_device(dev, sqe->dma,
			sizeof(struct nvme_command), DMA_TO_DEVICE);

	if (req_op(rq) == REQ_OP_FLUSH)
		flush = true;
	err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
			req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
	if (err) {
		nvme_rdma_unmap_data(queue, rq);
		goto err;
	}

	return BLK_STS_OK;
err:
	if (err == -ENOMEM || err == -EAGAIN)
		return BLK_STS_RESOURCE;
	return BLK_STS_IOERR;
}

static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
{
	struct nvme_rdma_queue *queue = hctx->driver_data;
	struct ib_cq *cq = queue->ib_cq;
	struct ib_wc wc;
	int found = 0;

	while (ib_poll_cq(cq, 1, &wc) > 0) {
		struct ib_cqe *cqe = wc.wr_cqe;

		if (cqe) {
			if (cqe->done == nvme_rdma_recv_done)
				found |= __nvme_rdma_recv_done(cq, &wc, tag);
			else
				cqe->done(cq, &wc);
		}
	}

	return found;
}

static void nvme_rdma_complete_rq(struct request *rq)
{
	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);

	nvme_rdma_unmap_data(req->queue, rq);
	nvme_complete_rq(rq);
}

static const struct blk_mq_ops nvme_rdma_mq_ops = {
	.queue_rq	= nvme_rdma_queue_rq,
	.complete	= nvme_rdma_complete_rq,
	.init_request	= nvme_rdma_init_request,
	.exit_request	= nvme_rdma_exit_request,
	.reinit_request	= nvme_rdma_reinit_request,
	.init_hctx	= nvme_rdma_init_hctx,
	.poll		= nvme_rdma_poll,
	.timeout	= nvme_rdma_timeout,
};

static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
	.queue_rq	= nvme_rdma_queue_rq,
	.complete	= nvme_rdma_complete_rq,
	.init_request	= nvme_rdma_init_request,
	.exit_request	= nvme_rdma_exit_request,
	.reinit_request	= nvme_rdma_reinit_request,
	.init_hctx	= nvme_rdma_init_admin_hctx,
	.timeout	= nvme_rdma_timeout,
};

static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
{
	int error;

	error = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH);
	if (error)
		return error;

	ctrl->device = ctrl->queues[0].device;

	/*
	 * We need a reference on the device as long as the tag_set is alive,
	 * as the MRs in the request structures need a valid ib_device.
	 */
	error = -EINVAL;
	if (!nvme_rdma_dev_get(ctrl->device))
		goto out_free_queue;

	ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS,
		ctrl->device->dev->attrs.max_fast_reg_page_list_len);

	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
	ctrl->admin_tag_set.ops = &nvme_rdma_admin_mq_ops;
	ctrl->admin_tag_set.queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH;
	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
		SG_CHUNK_SIZE * sizeof(struct scatterlist);
	ctrl->admin_tag_set.driver_data = ctrl;
	ctrl->admin_tag_set.nr_hw_queues = 1;
	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;

	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
	if (error)
		goto out_put_dev;

	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
	if (IS_ERR(ctrl->ctrl.admin_q)) {
		error = PTR_ERR(ctrl->ctrl.admin_q);
		goto out_free_tagset;
	}

	error = nvmf_connect_admin_queue(&ctrl->ctrl);
	if (error)
		goto out_cleanup_queue;

	set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);

	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
	if (error) {
		dev_err(ctrl->ctrl.device,
			"prop_get NVME_REG_CAP failed\n");
		goto out_cleanup_queue;
	}

	ctrl->ctrl.sqsize =
		min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize);

	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
	if (error)
		goto out_cleanup_queue;

	ctrl->ctrl.max_hw_sectors =
		(ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9);

	error = nvme_init_identify(&ctrl->ctrl);
	if (error)
		goto out_cleanup_queue;

	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
			&ctrl->async_event_sqe, sizeof(struct nvme_command),
			DMA_TO_DEVICE);
	if (error)
		goto out_cleanup_queue;

	nvme_start_keep_alive(&ctrl->ctrl);

	return 0;

out_cleanup_queue:
	blk_cleanup_queue(ctrl->ctrl.admin_q);
out_free_tagset:
	/* disconnect and drain the queue before freeing the tagset */
	nvme_rdma_stop_queue(&ctrl->queues[0]);
	blk_mq_free_tag_set(&ctrl->admin_tag_set);
out_put_dev:
	nvme_rdma_dev_put(ctrl->device);
out_free_queue:
	nvme_rdma_free_queue(&ctrl->queues[0]);
	return error;
}

static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl)
{
	nvme_stop_keep_alive(&ctrl->ctrl);
	cancel_work_sync(&ctrl->err_work);
	cancel_delayed_work_sync(&ctrl->reconnect_work);

	if (ctrl->queue_count > 1) {
		nvme_stop_queues(&ctrl->ctrl);
		blk_mq_tagset_busy_iter(&ctrl->tag_set,
					nvme_cancel_request, &ctrl->ctrl);
		nvme_rdma_free_io_queues(ctrl);
	}

	if (test_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags))
		nvme_shutdown_ctrl(&ctrl->ctrl);

	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
				nvme_cancel_request, &ctrl->ctrl);
	nvme_rdma_destroy_admin_queue(ctrl);
}

static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
{
	nvme_uninit_ctrl(&ctrl->ctrl);
	if (shutdown)
		nvme_rdma_shutdown_ctrl(ctrl);

	if (ctrl->ctrl.tagset) {
		blk_cleanup_queue(ctrl->ctrl.connect_q);
		blk_mq_free_tag_set(&ctrl->tag_set);
		nvme_rdma_dev_put(ctrl->device);
	}

	nvme_put_ctrl(&ctrl->ctrl);
}

static void nvme_rdma_del_ctrl_work(struct work_struct *work)
{
	struct nvme_rdma_ctrl *ctrl = container_of(work,
				struct nvme_rdma_ctrl, delete_work);

	__nvme_rdma_remove_ctrl(ctrl, true);
}

static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl)
{
	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
		return -EBUSY;

	if (!queue_work(nvme_wq, &ctrl->delete_work))
		return -EBUSY;

	return 0;
}

static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
{
	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
	int ret = 0;

	/*
	 * Keep a reference until all work is flushed since
	 * __nvme_rdma_del_ctrl can free the ctrl mem
	 */
	if (!kref_get_unless_zero(&ctrl->ctrl.kref))
		return -EBUSY;
	ret = __nvme_rdma_del_ctrl(ctrl);
	if (!ret)
		flush_work(&ctrl->delete_work);
	nvme_put_ctrl(&ctrl->ctrl);
	return ret;
}

static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
{
	struct nvme_rdma_ctrl *ctrl = container_of(work,
				struct nvme_rdma_ctrl, delete_work);

	__nvme_rdma_remove_ctrl(ctrl, false);
}

static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
{
	struct nvme_rdma_ctrl *ctrl =
		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
	int ret;
	bool changed;

	nvme_rdma_shutdown_ctrl(ctrl);

	ret = nvme_rdma_configure_admin_queue(ctrl);
	if (ret) {
		/* ctrl is already shutdown, just remove the ctrl */
		INIT_WORK(&ctrl->delete_work, nvme_rdma_remove_ctrl_work);
		goto del_dead_ctrl;
	}

	if (ctrl->queue_count > 1) {
		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
		if (ret)
			goto del_dead_ctrl;

		ret = nvme_rdma_init_io_queues(ctrl);
		if (ret)
			goto del_dead_ctrl;

		ret = nvme_rdma_connect_io_queues(ctrl);
		if (ret)
			goto del_dead_ctrl;
	}

	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
	WARN_ON_ONCE(!changed);

	if (ctrl->queue_count > 1) {
		nvme_start_queues(&ctrl->ctrl);
		nvme_queue_scan(&ctrl->ctrl);
		nvme_queue_async_events(&ctrl->ctrl);
	}

	return;

del_dead_ctrl:
	/* Deleting this dead controller... */
	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
	WARN_ON(!queue_work(nvme_wq, &ctrl->delete_work));
}

static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
	.name			= "rdma",
	.module			= THIS_MODULE,
	.flags			= NVME_F_FABRICS,
	.reg_read32		= nvmf_reg_read32,
	.reg_read64		= nvmf_reg_read64,
	.reg_write32		= nvmf_reg_write32,
	.free_ctrl		= nvme_rdma_free_ctrl,
	.submit_async_event	= nvme_rdma_submit_async_event,
	.delete_ctrl		= nvme_rdma_del_ctrl,
	.get_address		= nvmf_get_address,
};

static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
{
	int ret;

	ret = nvme_rdma_init_io_queues(ctrl);
	if (ret)
		return ret;

	/*
	 * We need a reference on the device as long as the tag_set is alive,
	 * as the MRs in the request structures need a valid ib_device.
	 */
	ret = -EINVAL;
	if (!nvme_rdma_dev_get(ctrl->device))
		goto out_free_io_queues;

	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
	ctrl->tag_set.ops = &nvme_rdma_mq_ops;
	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
	ctrl->tag_set.numa_node = NUMA_NO_NODE;
	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
	ctrl->tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
		SG_CHUNK_SIZE * sizeof(struct scatterlist);
	ctrl->tag_set.driver_data = ctrl;
	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;

	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
	if (ret)
		goto out_put_dev;
	ctrl->ctrl.tagset = &ctrl->tag_set;

	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
	if (IS_ERR(ctrl->ctrl.connect_q)) {
		ret = PTR_ERR(ctrl->ctrl.connect_q);
		goto out_free_tag_set;
	}

	ret = nvme_rdma_connect_io_queues(ctrl);
	if (ret)
		goto out_cleanup_connect_q;

	return 0;

out_cleanup_connect_q:
	blk_cleanup_queue(ctrl->ctrl.connect_q);
out_free_tag_set:
	blk_mq_free_tag_set(&ctrl->tag_set);
out_put_dev:
	nvme_rdma_dev_put(ctrl->device);
out_free_io_queues:
	nvme_rdma_free_io_queues(ctrl);
	return ret;
}

static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
		struct nvmf_ctrl_options *opts)
{
	struct nvme_rdma_ctrl *ctrl;
	int ret;
	bool changed;
	char *port;

	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
	if (!ctrl)
		return ERR_PTR(-ENOMEM);
	ctrl->ctrl.opts = opts;
	INIT_LIST_HEAD(&ctrl->list);

	if (opts->mask & NVMF_OPT_TRSVCID)
		port = opts->trsvcid;
	else
		port = __stringify(NVME_RDMA_IP_PORT);

	ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
			opts->traddr, port, &ctrl->addr);
	if (ret) {
		pr_err("malformed address passed: %s:%s\n", opts->traddr, port);
		goto out_free_ctrl;
	}

	if (opts->mask & NVMF_OPT_HOST_TRADDR) {
		ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
			opts->host_traddr, NULL, &ctrl->src_addr);
		if (ret) {
			pr_err("malformed src address passed: %s\n",
			       opts->host_traddr);
			goto out_free_ctrl;
		}
	}

	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
				0 /* no quirks, we're perfect! */);
	if (ret)
		goto out_free_ctrl;

	INIT_DELAYED_WORK(&ctrl->reconnect_work,
			nvme_rdma_reconnect_ctrl_work);
	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
	INIT_WORK(&ctrl->delete_work, nvme_rdma_del_ctrl_work);
	INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work);

	ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */
	ctrl->ctrl.sqsize = opts->queue_size - 1;
	ctrl->ctrl.kato = opts->kato;

	ret = -ENOMEM;
	ctrl->queues = kcalloc(ctrl->queue_count, sizeof(*ctrl->queues),
				GFP_KERNEL);
	if (!ctrl->queues)
		goto out_uninit_ctrl;

	ret = nvme_rdma_configure_admin_queue(ctrl);
	if (ret)
		goto out_kfree_queues;

	/* sanity check icdoff */
	if (ctrl->ctrl.icdoff) {
		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
		ret = -EINVAL;
		goto out_remove_admin_queue;
	}

	/* sanity check keyed sgls */
	if (!(ctrl->ctrl.sgls & (1 << 20))) {
		dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not support\n");
		ret = -EINVAL;
		goto out_remove_admin_queue;
	}

	if (opts->queue_size > ctrl->ctrl.maxcmd) {
		/* warn if maxcmd is lower than queue_size */
		dev_warn(ctrl->ctrl.device,
			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
			opts->queue_size, ctrl->ctrl.maxcmd);
		opts->queue_size = ctrl->ctrl.maxcmd;
	}

	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
		/* warn if sqsize is lower than queue_size */
		dev_warn(ctrl->ctrl.device,
			"queue_size %zu > ctrl sqsize %u, clamping down\n",
			opts->queue_size, ctrl->ctrl.sqsize + 1);
		opts->queue_size = ctrl->ctrl.sqsize + 1;
	}

	if (opts->nr_io_queues) {
		ret = nvme_rdma_create_io_queues(ctrl);
		if (ret)
			goto out_remove_admin_queue;
	}

	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
	WARN_ON_ONCE(!changed);

	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);

	kref_get(&ctrl->ctrl.kref);

	mutex_lock(&nvme_rdma_ctrl_mutex);
	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
	mutex_unlock(&nvme_rdma_ctrl_mutex);

	if (opts->nr_io_queues) {
		nvme_queue_scan(&ctrl->ctrl);
		nvme_queue_async_events(&ctrl->ctrl);
	}

	return &ctrl->ctrl;

out_remove_admin_queue:
	nvme_stop_keep_alive(&ctrl->ctrl);
	nvme_rdma_destroy_admin_queue(ctrl);
out_kfree_queues:
	kfree(ctrl->queues);
out_uninit_ctrl:
	nvme_uninit_ctrl(&ctrl->ctrl);
	nvme_put_ctrl(&ctrl->ctrl);
	if (ret > 0)
		ret = -EIO;
	return ERR_PTR(ret);
out_free_ctrl:
	kfree(ctrl);
	return ERR_PTR(ret);
}

static struct nvmf_transport_ops nvme_rdma_transport = {
	.name		= "rdma",
	.required_opts	= NVMF_OPT_TRADDR,
	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
	.create_ctrl	= nvme_rdma_create_ctrl,
};

static void nvme_rdma_add_one(struct ib_device *ib_device)
{
}

static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
{
	struct nvme_rdma_ctrl *ctrl;

	/* Delete all controllers using this device */
	mutex_lock(&nvme_rdma_ctrl_mutex);
	list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) {
		if (ctrl->device->dev != ib_device)
			continue;
		dev_info(ctrl->ctrl.device,
			"Removing ctrl: NQN \"%s\", addr %pISp\n",
			ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
		__nvme_rdma_del_ctrl(ctrl);
	}
	mutex_unlock(&nvme_rdma_ctrl_mutex);

	flush_workqueue(nvme_wq);
}

static struct ib_client nvme_rdma_ib_client = {
	.name   = "nvme_rdma",
	.add = nvme_rdma_add_one,
	.remove = nvme_rdma_remove_one
};

static int __init nvme_rdma_init_module(void)
{
	int ret;

	ret = ib_register_client(&nvme_rdma_ib_client);
	if (ret)
		return ret;

	ret = nvmf_register_transport(&nvme_rdma_transport);
	if (ret)
		goto err_unreg_client;

	return 0;

err_unreg_client:
	ib_unregister_client(&nvme_rdma_ib_client);
	return ret;
}

static void __exit nvme_rdma_cleanup_module(void)
{
	nvmf_unregister_transport(&nvme_rdma_transport);
	ib_unregister_client(&nvme_rdma_ib_client);
}

module_init(nvme_rdma_init_module);
module_exit(nvme_rdma_cleanup_module);

MODULE_LICENSE("GPL v2");