summaryrefslogtreecommitdiff
path: root/drivers/nvme/target/tcp.c
blob: c8655fc5aa5b8aac838cb4c2e4c0a76c8ebbc174 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe over Fabrics TCP target.
 * Copyright (c) 2018 Lightbits Labs. All rights reserved.
 */
#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/key.h>
#include <linux/nvme-tcp.h>
#include <linux/nvme-keyring.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <net/tls.h>
#include <net/tls_prot.h>
#include <net/handshake.h>
#include <linux/inet.h>
#include <linux/llist.h>
#include <crypto/hash.h>
#include <trace/events/sock.h>

#include "nvmet.h"

#define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
#define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
#define NVMET_TCP_BACKLOG 128

static int param_store_val(const char *str, int *val, int min, int max)
{
	int ret, new_val;

	ret = kstrtoint(str, 10, &new_val);
	if (ret)
		return -EINVAL;

	if (new_val < min || new_val > max)
		return -EINVAL;

	*val = new_val;
	return 0;
}

static int set_params(const char *str, const struct kernel_param *kp)
{
	return param_store_val(str, kp->arg, 0, INT_MAX);
}

static const struct kernel_param_ops set_param_ops = {
	.set	= set_params,
	.get	= param_get_int,
};

/* Define the socket priority to use for connections were it is desirable
 * that the NIC consider performing optimized packet processing or filtering.
 * A non-zero value being sufficient to indicate general consideration of any
 * possible optimization.  Making it a module param allows for alternative
 * values that may be unique for some NIC implementations.
 */
static int so_priority;
device_param_cb(so_priority, &set_param_ops, &so_priority, 0644);
MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority: Default 0");

/* Define a time period (in usecs) that io_work() shall sample an activated
 * queue before determining it to be idle.  This optional module behavior
 * can enable NIC solutions that support socket optimized packet processing
 * using advanced interrupt moderation techniques.
 */
static int idle_poll_period_usecs;
device_param_cb(idle_poll_period_usecs, &set_param_ops,
		&idle_poll_period_usecs, 0644);
MODULE_PARM_DESC(idle_poll_period_usecs,
		"nvmet tcp io_work poll till idle time period in usecs: Default 0");

#ifdef CONFIG_NVME_TARGET_TCP_TLS
/*
 * TLS handshake timeout
 */
static int tls_handshake_timeout = 10;
module_param(tls_handshake_timeout, int, 0644);
MODULE_PARM_DESC(tls_handshake_timeout,
		 "nvme TLS handshake timeout in seconds (default 10)");
#endif

#define NVMET_TCP_RECV_BUDGET		8
#define NVMET_TCP_SEND_BUDGET		8
#define NVMET_TCP_IO_WORK_BUDGET	64

enum nvmet_tcp_send_state {
	NVMET_TCP_SEND_DATA_PDU,
	NVMET_TCP_SEND_DATA,
	NVMET_TCP_SEND_R2T,
	NVMET_TCP_SEND_DDGST,
	NVMET_TCP_SEND_RESPONSE
};

enum nvmet_tcp_recv_state {
	NVMET_TCP_RECV_PDU,
	NVMET_TCP_RECV_DATA,
	NVMET_TCP_RECV_DDGST,
	NVMET_TCP_RECV_ERR,
};

enum {
	NVMET_TCP_F_INIT_FAILED = (1 << 0),
};

struct nvmet_tcp_cmd {
	struct nvmet_tcp_queue		*queue;
	struct nvmet_req		req;

	struct nvme_tcp_cmd_pdu		*cmd_pdu;
	struct nvme_tcp_rsp_pdu		*rsp_pdu;
	struct nvme_tcp_data_pdu	*data_pdu;
	struct nvme_tcp_r2t_pdu		*r2t_pdu;

	u32				rbytes_done;
	u32				wbytes_done;

	u32				pdu_len;
	u32				pdu_recv;
	int				sg_idx;
	char				recv_cbuf[CMSG_LEN(sizeof(char))];
	struct msghdr			recv_msg;
	struct bio_vec			*iov;
	u32				flags;

	struct list_head		entry;
	struct llist_node		lentry;

	/* send state */
	u32				offset;
	struct scatterlist		*cur_sg;
	enum nvmet_tcp_send_state	state;

	__le32				exp_ddgst;
	__le32				recv_ddgst;
};

enum nvmet_tcp_queue_state {
	NVMET_TCP_Q_CONNECTING,
	NVMET_TCP_Q_TLS_HANDSHAKE,
	NVMET_TCP_Q_LIVE,
	NVMET_TCP_Q_DISCONNECTING,
	NVMET_TCP_Q_FAILED,
};

struct nvmet_tcp_queue {
	struct socket		*sock;
	struct nvmet_tcp_port	*port;
	struct work_struct	io_work;
	struct nvmet_cq		nvme_cq;
	struct nvmet_sq		nvme_sq;
	struct kref		kref;

	/* send state */
	struct nvmet_tcp_cmd	*cmds;
	unsigned int		nr_cmds;
	struct list_head	free_list;
	struct llist_head	resp_list;
	struct list_head	resp_send_list;
	int			send_list_len;
	struct nvmet_tcp_cmd	*snd_cmd;

	/* recv state */
	int			offset;
	int			left;
	enum nvmet_tcp_recv_state rcv_state;
	struct nvmet_tcp_cmd	*cmd;
	union nvme_tcp_pdu	pdu;

	/* digest state */
	bool			hdr_digest;
	bool			data_digest;
	struct ahash_request	*snd_hash;
	struct ahash_request	*rcv_hash;

	/* TLS state */
	key_serial_t		tls_pskid;
	struct delayed_work	tls_handshake_tmo_work;

	unsigned long           poll_end;

	spinlock_t		state_lock;
	enum nvmet_tcp_queue_state state;

	struct sockaddr_storage	sockaddr;
	struct sockaddr_storage	sockaddr_peer;
	struct work_struct	release_work;

	int			idx;
	struct list_head	queue_list;

	struct nvmet_tcp_cmd	connect;

	struct page_frag_cache	pf_cache;

	void (*data_ready)(struct sock *);
	void (*state_change)(struct sock *);
	void (*write_space)(struct sock *);
};

struct nvmet_tcp_port {
	struct socket		*sock;
	struct work_struct	accept_work;
	struct nvmet_port	*nport;
	struct sockaddr_storage addr;
	void (*data_ready)(struct sock *);
};

static DEFINE_IDA(nvmet_tcp_queue_ida);
static LIST_HEAD(nvmet_tcp_queue_list);
static DEFINE_MUTEX(nvmet_tcp_queue_mutex);

static struct workqueue_struct *nvmet_tcp_wq;
static const struct nvmet_fabrics_ops nvmet_tcp_ops;
static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c);
static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd);

static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
		struct nvmet_tcp_cmd *cmd)
{
	if (unlikely(!queue->nr_cmds)) {
		/* We didn't allocate cmds yet, send 0xffff */
		return USHRT_MAX;
	}

	return cmd - queue->cmds;
}

static inline bool nvmet_tcp_has_data_in(struct nvmet_tcp_cmd *cmd)
{
	return nvme_is_write(cmd->req.cmd) &&
		cmd->rbytes_done < cmd->req.transfer_len;
}

static inline bool nvmet_tcp_need_data_in(struct nvmet_tcp_cmd *cmd)
{
	return nvmet_tcp_has_data_in(cmd) && !cmd->req.cqe->status;
}

static inline bool nvmet_tcp_need_data_out(struct nvmet_tcp_cmd *cmd)
{
	return !nvme_is_write(cmd->req.cmd) &&
		cmd->req.transfer_len > 0 &&
		!cmd->req.cqe->status;
}

static inline bool nvmet_tcp_has_inline_data(struct nvmet_tcp_cmd *cmd)
{
	return nvme_is_write(cmd->req.cmd) && cmd->pdu_len &&
		!cmd->rbytes_done;
}

static inline struct nvmet_tcp_cmd *
nvmet_tcp_get_cmd(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmd;

	cmd = list_first_entry_or_null(&queue->free_list,
				struct nvmet_tcp_cmd, entry);
	if (!cmd)
		return NULL;
	list_del_init(&cmd->entry);

	cmd->rbytes_done = cmd->wbytes_done = 0;
	cmd->pdu_len = 0;
	cmd->pdu_recv = 0;
	cmd->iov = NULL;
	cmd->flags = 0;
	return cmd;
}

static inline void nvmet_tcp_put_cmd(struct nvmet_tcp_cmd *cmd)
{
	if (unlikely(cmd == &cmd->queue->connect))
		return;

	list_add_tail(&cmd->entry, &cmd->queue->free_list);
}

static inline int queue_cpu(struct nvmet_tcp_queue *queue)
{
	return queue->sock->sk->sk_incoming_cpu;
}

static inline u8 nvmet_tcp_hdgst_len(struct nvmet_tcp_queue *queue)
{
	return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0;
}

static inline u8 nvmet_tcp_ddgst_len(struct nvmet_tcp_queue *queue)
{
	return queue->data_digest ? NVME_TCP_DIGEST_LENGTH : 0;
}

static inline void nvmet_tcp_hdgst(struct ahash_request *hash,
		void *pdu, size_t len)
{
	struct scatterlist sg;

	sg_init_one(&sg, pdu, len);
	ahash_request_set_crypt(hash, &sg, pdu + len, len);
	crypto_ahash_digest(hash);
}

static int nvmet_tcp_verify_hdgst(struct nvmet_tcp_queue *queue,
	void *pdu, size_t len)
{
	struct nvme_tcp_hdr *hdr = pdu;
	__le32 recv_digest;
	__le32 exp_digest;

	if (unlikely(!(hdr->flags & NVME_TCP_F_HDGST))) {
		pr_err("queue %d: header digest enabled but no header digest\n",
			queue->idx);
		return -EPROTO;
	}

	recv_digest = *(__le32 *)(pdu + hdr->hlen);
	nvmet_tcp_hdgst(queue->rcv_hash, pdu, len);
	exp_digest = *(__le32 *)(pdu + hdr->hlen);
	if (recv_digest != exp_digest) {
		pr_err("queue %d: header digest error: recv %#x expected %#x\n",
			queue->idx, le32_to_cpu(recv_digest),
			le32_to_cpu(exp_digest));
		return -EPROTO;
	}

	return 0;
}

static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu)
{
	struct nvme_tcp_hdr *hdr = pdu;
	u8 digest_len = nvmet_tcp_hdgst_len(queue);
	u32 len;

	len = le32_to_cpu(hdr->plen) - hdr->hlen -
		(hdr->flags & NVME_TCP_F_HDGST ? digest_len : 0);

	if (unlikely(len && !(hdr->flags & NVME_TCP_F_DDGST))) {
		pr_err("queue %d: data digest flag is cleared\n", queue->idx);
		return -EPROTO;
	}

	return 0;
}

static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd)
{
	kfree(cmd->iov);
	sgl_free(cmd->req.sg);
	cmd->iov = NULL;
	cmd->req.sg = NULL;
}

static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd)
{
	struct bio_vec *iov = cmd->iov;
	struct scatterlist *sg;
	u32 length, offset, sg_offset;
	int nr_pages;

	length = cmd->pdu_len;
	nr_pages = DIV_ROUND_UP(length, PAGE_SIZE);
	offset = cmd->rbytes_done;
	cmd->sg_idx = offset / PAGE_SIZE;
	sg_offset = offset % PAGE_SIZE;
	sg = &cmd->req.sg[cmd->sg_idx];

	while (length) {
		u32 iov_len = min_t(u32, length, sg->length - sg_offset);

		bvec_set_page(iov, sg_page(sg), iov_len,
				sg->offset + sg_offset);

		length -= iov_len;
		sg = sg_next(sg);
		iov++;
		sg_offset = 0;
	}

	iov_iter_bvec(&cmd->recv_msg.msg_iter, ITER_DEST, cmd->iov,
		      nr_pages, cmd->pdu_len);
}

static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue)
{
	queue->rcv_state = NVMET_TCP_RECV_ERR;
	if (queue->nvme_sq.ctrl)
		nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl);
	else
		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
}

static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status)
{
	queue->rcv_state = NVMET_TCP_RECV_ERR;
	if (status == -EPIPE || status == -ECONNRESET)
		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
	else
		nvmet_tcp_fatal_error(queue);
}

static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
{
	struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl;
	u32 len = le32_to_cpu(sgl->length);

	if (!len)
		return 0;

	if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) |
			  NVME_SGL_FMT_OFFSET)) {
		if (!nvme_is_write(cmd->req.cmd))
			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;

		if (len > cmd->req.port->inline_data_size)
			return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
		cmd->pdu_len = len;
	}
	cmd->req.transfer_len += len;

	cmd->req.sg = sgl_alloc(len, GFP_KERNEL, &cmd->req.sg_cnt);
	if (!cmd->req.sg)
		return NVME_SC_INTERNAL;
	cmd->cur_sg = cmd->req.sg;

	if (nvmet_tcp_has_data_in(cmd)) {
		cmd->iov = kmalloc_array(cmd->req.sg_cnt,
				sizeof(*cmd->iov), GFP_KERNEL);
		if (!cmd->iov)
			goto err;
	}

	return 0;
err:
	nvmet_tcp_free_cmd_buffers(cmd);
	return NVME_SC_INTERNAL;
}

static void nvmet_tcp_calc_ddgst(struct ahash_request *hash,
		struct nvmet_tcp_cmd *cmd)
{
	ahash_request_set_crypt(hash, cmd->req.sg,
		(void *)&cmd->exp_ddgst, cmd->req.transfer_len);
	crypto_ahash_digest(hash);
}

static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd)
{
	struct nvme_tcp_data_pdu *pdu = cmd->data_pdu;
	struct nvmet_tcp_queue *queue = cmd->queue;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
	u8 ddgst = nvmet_tcp_ddgst_len(cmd->queue);

	cmd->offset = 0;
	cmd->state = NVMET_TCP_SEND_DATA_PDU;

	pdu->hdr.type = nvme_tcp_c2h_data;
	pdu->hdr.flags = NVME_TCP_F_DATA_LAST | (queue->nvme_sq.sqhd_disabled ?
						NVME_TCP_F_DATA_SUCCESS : 0);
	pdu->hdr.hlen = sizeof(*pdu);
	pdu->hdr.pdo = pdu->hdr.hlen + hdgst;
	pdu->hdr.plen =
		cpu_to_le32(pdu->hdr.hlen + hdgst +
				cmd->req.transfer_len + ddgst);
	pdu->command_id = cmd->req.cqe->command_id;
	pdu->data_length = cpu_to_le32(cmd->req.transfer_len);
	pdu->data_offset = cpu_to_le32(cmd->wbytes_done);

	if (queue->data_digest) {
		pdu->hdr.flags |= NVME_TCP_F_DDGST;
		nvmet_tcp_calc_ddgst(queue->snd_hash, cmd);
	}

	if (cmd->queue->hdr_digest) {
		pdu->hdr.flags |= NVME_TCP_F_HDGST;
		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
	}
}

static void nvmet_setup_r2t_pdu(struct nvmet_tcp_cmd *cmd)
{
	struct nvme_tcp_r2t_pdu *pdu = cmd->r2t_pdu;
	struct nvmet_tcp_queue *queue = cmd->queue;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);

	cmd->offset = 0;
	cmd->state = NVMET_TCP_SEND_R2T;

	pdu->hdr.type = nvme_tcp_r2t;
	pdu->hdr.flags = 0;
	pdu->hdr.hlen = sizeof(*pdu);
	pdu->hdr.pdo = 0;
	pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst);

	pdu->command_id = cmd->req.cmd->common.command_id;
	pdu->ttag = nvmet_tcp_cmd_tag(cmd->queue, cmd);
	pdu->r2t_length = cpu_to_le32(cmd->req.transfer_len - cmd->rbytes_done);
	pdu->r2t_offset = cpu_to_le32(cmd->rbytes_done);
	if (cmd->queue->hdr_digest) {
		pdu->hdr.flags |= NVME_TCP_F_HDGST;
		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
	}
}

static void nvmet_setup_response_pdu(struct nvmet_tcp_cmd *cmd)
{
	struct nvme_tcp_rsp_pdu *pdu = cmd->rsp_pdu;
	struct nvmet_tcp_queue *queue = cmd->queue;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);

	cmd->offset = 0;
	cmd->state = NVMET_TCP_SEND_RESPONSE;

	pdu->hdr.type = nvme_tcp_rsp;
	pdu->hdr.flags = 0;
	pdu->hdr.hlen = sizeof(*pdu);
	pdu->hdr.pdo = 0;
	pdu->hdr.plen = cpu_to_le32(pdu->hdr.hlen + hdgst);
	if (cmd->queue->hdr_digest) {
		pdu->hdr.flags |= NVME_TCP_F_HDGST;
		nvmet_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
	}
}

static void nvmet_tcp_process_resp_list(struct nvmet_tcp_queue *queue)
{
	struct llist_node *node;
	struct nvmet_tcp_cmd *cmd;

	for (node = llist_del_all(&queue->resp_list); node; node = node->next) {
		cmd = llist_entry(node, struct nvmet_tcp_cmd, lentry);
		list_add(&cmd->entry, &queue->resp_send_list);
		queue->send_list_len++;
	}
}

static struct nvmet_tcp_cmd *nvmet_tcp_fetch_cmd(struct nvmet_tcp_queue *queue)
{
	queue->snd_cmd = list_first_entry_or_null(&queue->resp_send_list,
				struct nvmet_tcp_cmd, entry);
	if (!queue->snd_cmd) {
		nvmet_tcp_process_resp_list(queue);
		queue->snd_cmd =
			list_first_entry_or_null(&queue->resp_send_list,
					struct nvmet_tcp_cmd, entry);
		if (unlikely(!queue->snd_cmd))
			return NULL;
	}

	list_del_init(&queue->snd_cmd->entry);
	queue->send_list_len--;

	if (nvmet_tcp_need_data_out(queue->snd_cmd))
		nvmet_setup_c2h_data_pdu(queue->snd_cmd);
	else if (nvmet_tcp_need_data_in(queue->snd_cmd))
		nvmet_setup_r2t_pdu(queue->snd_cmd);
	else
		nvmet_setup_response_pdu(queue->snd_cmd);

	return queue->snd_cmd;
}

static void nvmet_tcp_queue_response(struct nvmet_req *req)
{
	struct nvmet_tcp_cmd *cmd =
		container_of(req, struct nvmet_tcp_cmd, req);
	struct nvmet_tcp_queue	*queue = cmd->queue;
	struct nvme_sgl_desc *sgl;
	u32 len;

	if (unlikely(cmd == queue->cmd)) {
		sgl = &cmd->req.cmd->common.dptr.sgl;
		len = le32_to_cpu(sgl->length);

		/*
		 * Wait for inline data before processing the response.
		 * Avoid using helpers, this might happen before
		 * nvmet_req_init is completed.
		 */
		if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
		    len && len <= cmd->req.port->inline_data_size &&
		    nvme_is_write(cmd->req.cmd))
			return;
	}

	llist_add(&cmd->lentry, &queue->resp_list);
	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &cmd->queue->io_work);
}

static void nvmet_tcp_execute_request(struct nvmet_tcp_cmd *cmd)
{
	if (unlikely(cmd->flags & NVMET_TCP_F_INIT_FAILED))
		nvmet_tcp_queue_response(&cmd->req);
	else
		cmd->req.execute(&cmd->req);
}

static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
{
	struct msghdr msg = {
		.msg_flags = MSG_DONTWAIT | MSG_MORE | MSG_SPLICE_PAGES,
	};
	struct bio_vec bvec;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
	int left = sizeof(*cmd->data_pdu) - cmd->offset + hdgst;
	int ret;

	bvec_set_virt(&bvec, (void *)cmd->data_pdu + cmd->offset, left);
	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
	ret = sock_sendmsg(cmd->queue->sock, &msg);
	if (ret <= 0)
		return ret;

	cmd->offset += ret;
	left -= ret;

	if (left)
		return -EAGAIN;

	cmd->state = NVMET_TCP_SEND_DATA;
	cmd->offset  = 0;
	return 1;
}

static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
	struct nvmet_tcp_queue *queue = cmd->queue;
	int ret;

	while (cmd->cur_sg) {
		struct msghdr msg = {
			.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
		};
		struct page *page = sg_page(cmd->cur_sg);
		struct bio_vec bvec;
		u32 left = cmd->cur_sg->length - cmd->offset;

		if ((!last_in_batch && cmd->queue->send_list_len) ||
		    cmd->wbytes_done + left < cmd->req.transfer_len ||
		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
			msg.msg_flags |= MSG_MORE;

		bvec_set_page(&bvec, page, left, cmd->offset);
		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
		ret = sock_sendmsg(cmd->queue->sock, &msg);
		if (ret <= 0)
			return ret;

		cmd->offset += ret;
		cmd->wbytes_done += ret;

		/* Done with sg?*/
		if (cmd->offset == cmd->cur_sg->length) {
			cmd->cur_sg = sg_next(cmd->cur_sg);
			cmd->offset = 0;
		}
	}

	if (queue->data_digest) {
		cmd->state = NVMET_TCP_SEND_DDGST;
		cmd->offset = 0;
	} else {
		if (queue->nvme_sq.sqhd_disabled) {
			cmd->queue->snd_cmd = NULL;
			nvmet_tcp_put_cmd(cmd);
		} else {
			nvmet_setup_response_pdu(cmd);
		}
	}

	if (queue->nvme_sq.sqhd_disabled)
		nvmet_tcp_free_cmd_buffers(cmd);

	return 1;

}

static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
		bool last_in_batch)
{
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
	struct bio_vec bvec;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
	int left = sizeof(*cmd->rsp_pdu) - cmd->offset + hdgst;
	int ret;

	if (!last_in_batch && cmd->queue->send_list_len)
		msg.msg_flags |= MSG_MORE;
	else
		msg.msg_flags |= MSG_EOR;

	bvec_set_virt(&bvec, (void *)cmd->rsp_pdu + cmd->offset, left);
	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
	ret = sock_sendmsg(cmd->queue->sock, &msg);
	if (ret <= 0)
		return ret;
	cmd->offset += ret;
	left -= ret;

	if (left)
		return -EAGAIN;

	nvmet_tcp_free_cmd_buffers(cmd);
	cmd->queue->snd_cmd = NULL;
	nvmet_tcp_put_cmd(cmd);
	return 1;
}

static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
	struct bio_vec bvec;
	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
	int left = sizeof(*cmd->r2t_pdu) - cmd->offset + hdgst;
	int ret;

	if (!last_in_batch && cmd->queue->send_list_len)
		msg.msg_flags |= MSG_MORE;
	else
		msg.msg_flags |= MSG_EOR;

	bvec_set_virt(&bvec, (void *)cmd->r2t_pdu + cmd->offset, left);
	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
	ret = sock_sendmsg(cmd->queue->sock, &msg);
	if (ret <= 0)
		return ret;
	cmd->offset += ret;
	left -= ret;

	if (left)
		return -EAGAIN;

	cmd->queue->snd_cmd = NULL;
	return 1;
}

static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
	struct nvmet_tcp_queue *queue = cmd->queue;
	int left = NVME_TCP_DIGEST_LENGTH - cmd->offset;
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
	struct kvec iov = {
		.iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
		.iov_len = left
	};
	int ret;

	if (!last_in_batch && cmd->queue->send_list_len)
		msg.msg_flags |= MSG_MORE;
	else
		msg.msg_flags |= MSG_EOR;

	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
	if (unlikely(ret <= 0))
		return ret;

	cmd->offset += ret;
	left -= ret;

	if (left)
		return -EAGAIN;

	if (queue->nvme_sq.sqhd_disabled) {
		cmd->queue->snd_cmd = NULL;
		nvmet_tcp_put_cmd(cmd);
	} else {
		nvmet_setup_response_pdu(cmd);
	}
	return 1;
}

static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
		bool last_in_batch)
{
	struct nvmet_tcp_cmd *cmd = queue->snd_cmd;
	int ret = 0;

	if (!cmd || queue->state == NVMET_TCP_Q_DISCONNECTING) {
		cmd = nvmet_tcp_fetch_cmd(queue);
		if (unlikely(!cmd))
			return 0;
	}

	if (cmd->state == NVMET_TCP_SEND_DATA_PDU) {
		ret = nvmet_try_send_data_pdu(cmd);
		if (ret <= 0)
			goto done_send;
	}

	if (cmd->state == NVMET_TCP_SEND_DATA) {
		ret = nvmet_try_send_data(cmd, last_in_batch);
		if (ret <= 0)
			goto done_send;
	}

	if (cmd->state == NVMET_TCP_SEND_DDGST) {
		ret = nvmet_try_send_ddgst(cmd, last_in_batch);
		if (ret <= 0)
			goto done_send;
	}

	if (cmd->state == NVMET_TCP_SEND_R2T) {
		ret = nvmet_try_send_r2t(cmd, last_in_batch);
		if (ret <= 0)
			goto done_send;
	}

	if (cmd->state == NVMET_TCP_SEND_RESPONSE)
		ret = nvmet_try_send_response(cmd, last_in_batch);

done_send:
	if (ret < 0) {
		if (ret == -EAGAIN)
			return 0;
		return ret;
	}

	return 1;
}

static int nvmet_tcp_try_send(struct nvmet_tcp_queue *queue,
		int budget, int *sends)
{
	int i, ret = 0;

	for (i = 0; i < budget; i++) {
		ret = nvmet_tcp_try_send_one(queue, i == budget - 1);
		if (unlikely(ret < 0)) {
			nvmet_tcp_socket_error(queue, ret);
			goto done;
		} else if (ret == 0) {
			break;
		}
		(*sends)++;
	}
done:
	return ret;
}

static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
{
	queue->offset = 0;
	queue->left = sizeof(struct nvme_tcp_hdr);
	queue->cmd = NULL;
	queue->rcv_state = NVMET_TCP_RECV_PDU;
}

static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)
{
	struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash);

	ahash_request_free(queue->rcv_hash);
	ahash_request_free(queue->snd_hash);
	crypto_free_ahash(tfm);
}

static int nvmet_tcp_alloc_crypto(struct nvmet_tcp_queue *queue)
{
	struct crypto_ahash *tfm;

	tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC);
	if (IS_ERR(tfm))
		return PTR_ERR(tfm);

	queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL);
	if (!queue->snd_hash)
		goto free_tfm;
	ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL);

	queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL);
	if (!queue->rcv_hash)
		goto free_snd_hash;
	ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL);

	return 0;
free_snd_hash:
	ahash_request_free(queue->snd_hash);
free_tfm:
	crypto_free_ahash(tfm);
	return -ENOMEM;
}


static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
{
	struct nvme_tcp_icreq_pdu *icreq = &queue->pdu.icreq;
	struct nvme_tcp_icresp_pdu *icresp = &queue->pdu.icresp;
	struct msghdr msg = {};
	struct kvec iov;
	int ret;

	if (le32_to_cpu(icreq->hdr.plen) != sizeof(struct nvme_tcp_icreq_pdu)) {
		pr_err("bad nvme-tcp pdu length (%d)\n",
			le32_to_cpu(icreq->hdr.plen));
		nvmet_tcp_fatal_error(queue);
	}

	if (icreq->pfv != NVME_TCP_PFV_1_0) {
		pr_err("queue %d: bad pfv %d\n", queue->idx, icreq->pfv);
		return -EPROTO;
	}

	if (icreq->hpda != 0) {
		pr_err("queue %d: unsupported hpda %d\n", queue->idx,
			icreq->hpda);
		return -EPROTO;
	}

	queue->hdr_digest = !!(icreq->digest & NVME_TCP_HDR_DIGEST_ENABLE);
	queue->data_digest = !!(icreq->digest & NVME_TCP_DATA_DIGEST_ENABLE);
	if (queue->hdr_digest || queue->data_digest) {
		ret = nvmet_tcp_alloc_crypto(queue);
		if (ret)
			return ret;
	}

	memset(icresp, 0, sizeof(*icresp));
	icresp->hdr.type = nvme_tcp_icresp;
	icresp->hdr.hlen = sizeof(*icresp);
	icresp->hdr.pdo = 0;
	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
	icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA);
	icresp->cpda = 0;
	if (queue->hdr_digest)
		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
	if (queue->data_digest)
		icresp->digest |= NVME_TCP_DATA_DIGEST_ENABLE;

	iov.iov_base = icresp;
	iov.iov_len = sizeof(*icresp);
	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
	if (ret < 0) {
		queue->state = NVMET_TCP_Q_FAILED;
		return ret; /* queue removal will cleanup */
	}

	queue->state = NVMET_TCP_Q_LIVE;
	nvmet_prepare_receive_pdu(queue);
	return 0;
}

static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
		struct nvmet_tcp_cmd *cmd, struct nvmet_req *req)
{
	size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
	int ret;

	/*
	 * This command has not been processed yet, hence we are trying to
	 * figure out if there is still pending data left to receive. If
	 * we don't, we can simply prepare for the next pdu and bail out,
	 * otherwise we will need to prepare a buffer and receive the
	 * stale data before continuing forward.
	 */
	if (!nvme_is_write(cmd->req.cmd) || !data_len ||
	    data_len > cmd->req.port->inline_data_size) {
		nvmet_prepare_receive_pdu(queue);
		return;
	}

	ret = nvmet_tcp_map_data(cmd);
	if (unlikely(ret)) {
		pr_err("queue %d: failed to map data\n", queue->idx);
		nvmet_tcp_fatal_error(queue);
		return;
	}

	queue->rcv_state = NVMET_TCP_RECV_DATA;
	nvmet_tcp_build_pdu_iovec(cmd);
	cmd->flags |= NVMET_TCP_F_INIT_FAILED;
}

static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
{
	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
	struct nvmet_tcp_cmd *cmd;
	unsigned int exp_data_len;

	if (likely(queue->nr_cmds)) {
		if (unlikely(data->ttag >= queue->nr_cmds)) {
			pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n",
				queue->idx, data->ttag, queue->nr_cmds);
			goto err_proto;
		}
		cmd = &queue->cmds[data->ttag];
	} else {
		cmd = &queue->connect;
	}

	if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) {
		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
			data->ttag, le32_to_cpu(data->data_offset),
			cmd->rbytes_done);
		goto err_proto;
	}

	exp_data_len = le32_to_cpu(data->hdr.plen) -
			nvmet_tcp_hdgst_len(queue) -
			nvmet_tcp_ddgst_len(queue) -
			sizeof(*data);

	cmd->pdu_len = le32_to_cpu(data->data_length);
	if (unlikely(cmd->pdu_len != exp_data_len ||
		     cmd->pdu_len == 0 ||
		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
		goto err_proto;
	}
	cmd->pdu_recv = 0;
	nvmet_tcp_build_pdu_iovec(cmd);
	queue->cmd = cmd;
	queue->rcv_state = NVMET_TCP_RECV_DATA;

	return 0;

err_proto:
	/* FIXME: use proper transport errors */
	nvmet_tcp_fatal_error(queue);
	return -EPROTO;
}

static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue)
{
	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
	struct nvme_command *nvme_cmd = &queue->pdu.cmd.cmd;
	struct nvmet_req *req;
	int ret;

	if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) {
		if (hdr->type != nvme_tcp_icreq) {
			pr_err("unexpected pdu type (%d) before icreq\n",
				hdr->type);
			nvmet_tcp_fatal_error(queue);
			return -EPROTO;
		}
		return nvmet_tcp_handle_icreq(queue);
	}

	if (unlikely(hdr->type == nvme_tcp_icreq)) {
		pr_err("queue %d: received icreq pdu in state %d\n",
			queue->idx, queue->state);
		nvmet_tcp_fatal_error(queue);
		return -EPROTO;
	}

	if (hdr->type == nvme_tcp_h2c_data) {
		ret = nvmet_tcp_handle_h2c_data_pdu(queue);
		if (unlikely(ret))
			return ret;
		return 0;
	}

	queue->cmd = nvmet_tcp_get_cmd(queue);
	if (unlikely(!queue->cmd)) {
		/* This should never happen */
		pr_err("queue %d: out of commands (%d) send_list_len: %d, opcode: %d",
			queue->idx, queue->nr_cmds, queue->send_list_len,
			nvme_cmd->common.opcode);
		nvmet_tcp_fatal_error(queue);
		return -ENOMEM;
	}

	req = &queue->cmd->req;
	memcpy(req->cmd, nvme_cmd, sizeof(*nvme_cmd));

	if (unlikely(!nvmet_req_init(req, &queue->nvme_cq,
			&queue->nvme_sq, &nvmet_tcp_ops))) {
		pr_err("failed cmd %p id %d opcode %d, data_len: %d\n",
			req->cmd, req->cmd->common.command_id,
			req->cmd->common.opcode,
			le32_to_cpu(req->cmd->common.dptr.sgl.length));

		nvmet_tcp_handle_req_failure(queue, queue->cmd, req);
		return 0;
	}

	ret = nvmet_tcp_map_data(queue->cmd);
	if (unlikely(ret)) {
		pr_err("queue %d: failed to map data\n", queue->idx);
		if (nvmet_tcp_has_inline_data(queue->cmd))
			nvmet_tcp_fatal_error(queue);
		else
			nvmet_req_complete(req, ret);
		ret = -EAGAIN;
		goto out;
	}

	if (nvmet_tcp_need_data_in(queue->cmd)) {
		if (nvmet_tcp_has_inline_data(queue->cmd)) {
			queue->rcv_state = NVMET_TCP_RECV_DATA;
			nvmet_tcp_build_pdu_iovec(queue->cmd);
			return 0;
		}
		/* send back R2T */
		nvmet_tcp_queue_response(&queue->cmd->req);
		goto out;
	}

	queue->cmd->req.execute(&queue->cmd->req);
out:
	nvmet_prepare_receive_pdu(queue);
	return ret;
}

static const u8 nvme_tcp_pdu_sizes[] = {
	[nvme_tcp_icreq]	= sizeof(struct nvme_tcp_icreq_pdu),
	[nvme_tcp_cmd]		= sizeof(struct nvme_tcp_cmd_pdu),
	[nvme_tcp_h2c_data]	= sizeof(struct nvme_tcp_data_pdu),
};

static inline u8 nvmet_tcp_pdu_size(u8 type)
{
	size_t idx = type;

	return (idx < ARRAY_SIZE(nvme_tcp_pdu_sizes) &&
		nvme_tcp_pdu_sizes[idx]) ?
			nvme_tcp_pdu_sizes[idx] : 0;
}

static inline bool nvmet_tcp_pdu_valid(u8 type)
{
	switch (type) {
	case nvme_tcp_icreq:
	case nvme_tcp_cmd:
	case nvme_tcp_h2c_data:
		/* fallthru */
		return true;
	}

	return false;
}

static int nvmet_tcp_tls_record_ok(struct nvmet_tcp_queue *queue,
		struct msghdr *msg, char *cbuf)
{
	struct cmsghdr *cmsg = (struct cmsghdr *)cbuf;
	u8 ctype, level, description;
	int ret = 0;

	ctype = tls_get_record_type(queue->sock->sk, cmsg);
	switch (ctype) {
	case 0:
		break;
	case TLS_RECORD_TYPE_DATA:
		break;
	case TLS_RECORD_TYPE_ALERT:
		tls_alert_recv(queue->sock->sk, msg, &level, &description);
		if (level == TLS_ALERT_LEVEL_FATAL) {
			pr_err("queue %d: TLS Alert desc %u\n",
			       queue->idx, description);
			ret = -ENOTCONN;
		} else {
			pr_warn("queue %d: TLS Alert desc %u\n",
			       queue->idx, description);
			ret = -EAGAIN;
		}
		break;
	default:
		/* discard this record type */
		pr_err("queue %d: TLS record %d unhandled\n",
		       queue->idx, ctype);
		ret = -EAGAIN;
		break;
	}
	return ret;
}

static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
{
	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
	int len, ret;
	struct kvec iov;
	char cbuf[CMSG_LEN(sizeof(char))] = {};
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };

recv:
	iov.iov_base = (void *)&queue->pdu + queue->offset;
	iov.iov_len = queue->left;
	if (queue->tls_pskid) {
		msg.msg_control = cbuf;
		msg.msg_controllen = sizeof(cbuf);
	}
	len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
			iov.iov_len, msg.msg_flags);
	if (unlikely(len < 0))
		return len;
	if (queue->tls_pskid) {
		ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
		if (ret < 0)
			return ret;
	}

	queue->offset += len;
	queue->left -= len;
	if (queue->left)
		return -EAGAIN;

	if (queue->offset == sizeof(struct nvme_tcp_hdr)) {
		u8 hdgst = nvmet_tcp_hdgst_len(queue);

		if (unlikely(!nvmet_tcp_pdu_valid(hdr->type))) {
			pr_err("unexpected pdu type %d\n", hdr->type);
			nvmet_tcp_fatal_error(queue);
			return -EIO;
		}

		if (unlikely(hdr->hlen != nvmet_tcp_pdu_size(hdr->type))) {
			pr_err("pdu %d bad hlen %d\n", hdr->type, hdr->hlen);
			return -EIO;
		}

		queue->left = hdr->hlen - queue->offset + hdgst;
		goto recv;
	}

	if (queue->hdr_digest &&
	    nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) {
		nvmet_tcp_fatal_error(queue); /* fatal */
		return -EPROTO;
	}

	if (queue->data_digest &&
	    nvmet_tcp_check_ddgst(queue, &queue->pdu)) {
		nvmet_tcp_fatal_error(queue); /* fatal */
		return -EPROTO;
	}

	return nvmet_tcp_done_recv_pdu(queue);
}

static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd)
{
	struct nvmet_tcp_queue *queue = cmd->queue;

	nvmet_tcp_calc_ddgst(queue->rcv_hash, cmd);
	queue->offset = 0;
	queue->left = NVME_TCP_DIGEST_LENGTH;
	queue->rcv_state = NVMET_TCP_RECV_DDGST;
}

static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd  *cmd = queue->cmd;
	int len, ret;

	while (msg_data_left(&cmd->recv_msg)) {
		len = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg,
			cmd->recv_msg.msg_flags);
		if (len <= 0)
			return len;
		if (queue->tls_pskid) {
			ret = nvmet_tcp_tls_record_ok(cmd->queue,
					&cmd->recv_msg, cmd->recv_cbuf);
			if (ret < 0)
				return ret;
		}

		cmd->pdu_recv += len;
		cmd->rbytes_done += len;
	}

	if (queue->data_digest) {
		nvmet_tcp_prep_recv_ddgst(cmd);
		return 0;
	}

	if (cmd->rbytes_done == cmd->req.transfer_len)
		nvmet_tcp_execute_request(cmd);

	nvmet_prepare_receive_pdu(queue);
	return 0;
}

static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmd = queue->cmd;
	int ret, len;
	char cbuf[CMSG_LEN(sizeof(char))] = {};
	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
	struct kvec iov = {
		.iov_base = (void *)&cmd->recv_ddgst + queue->offset,
		.iov_len = queue->left
	};

	if (queue->tls_pskid) {
		msg.msg_control = cbuf;
		msg.msg_controllen = sizeof(cbuf);
	}
	len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
			iov.iov_len, msg.msg_flags);
	if (unlikely(len < 0))
		return len;
	if (queue->tls_pskid) {
		ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
		if (ret < 0)
			return ret;
	}

	queue->offset += len;
	queue->left -= len;
	if (queue->left)
		return -EAGAIN;

	if (queue->data_digest && cmd->exp_ddgst != cmd->recv_ddgst) {
		pr_err("queue %d: cmd %d pdu (%d) data digest error: recv %#x expected %#x\n",
			queue->idx, cmd->req.cmd->common.command_id,
			queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst),
			le32_to_cpu(cmd->exp_ddgst));
		nvmet_req_uninit(&cmd->req);
		nvmet_tcp_free_cmd_buffers(cmd);
		nvmet_tcp_fatal_error(queue);
		ret = -EPROTO;
		goto out;
	}

	if (cmd->rbytes_done == cmd->req.transfer_len)
		nvmet_tcp_execute_request(cmd);

	ret = 0;
out:
	nvmet_prepare_receive_pdu(queue);
	return ret;
}

static int nvmet_tcp_try_recv_one(struct nvmet_tcp_queue *queue)
{
	int result = 0;

	if (unlikely(queue->rcv_state == NVMET_TCP_RECV_ERR))
		return 0;

	if (queue->rcv_state == NVMET_TCP_RECV_PDU) {
		result = nvmet_tcp_try_recv_pdu(queue);
		if (result != 0)
			goto done_recv;
	}

	if (queue->rcv_state == NVMET_TCP_RECV_DATA) {
		result = nvmet_tcp_try_recv_data(queue);
		if (result != 0)
			goto done_recv;
	}

	if (queue->rcv_state == NVMET_TCP_RECV_DDGST) {
		result = nvmet_tcp_try_recv_ddgst(queue);
		if (result != 0)
			goto done_recv;
	}

done_recv:
	if (result < 0) {
		if (result == -EAGAIN)
			return 0;
		return result;
	}
	return 1;
}

static int nvmet_tcp_try_recv(struct nvmet_tcp_queue *queue,
		int budget, int *recvs)
{
	int i, ret = 0;

	for (i = 0; i < budget; i++) {
		ret = nvmet_tcp_try_recv_one(queue);
		if (unlikely(ret < 0)) {
			nvmet_tcp_socket_error(queue, ret);
			goto done;
		} else if (ret == 0) {
			break;
		}
		(*recvs)++;
	}
done:
	return ret;
}

static void nvmet_tcp_release_queue(struct kref *kref)
{
	struct nvmet_tcp_queue *queue =
		container_of(kref, struct nvmet_tcp_queue, kref);

	WARN_ON(queue->state != NVMET_TCP_Q_DISCONNECTING);
	queue_work(nvmet_wq, &queue->release_work);
}

static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue)
{
	spin_lock_bh(&queue->state_lock);
	if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
		/* Socket closed during handshake */
		tls_handshake_cancel(queue->sock->sk);
	}
	if (queue->state != NVMET_TCP_Q_DISCONNECTING) {
		queue->state = NVMET_TCP_Q_DISCONNECTING;
		kref_put(&queue->kref, nvmet_tcp_release_queue);
	}
	spin_unlock_bh(&queue->state_lock);
}

static inline void nvmet_tcp_arm_queue_deadline(struct nvmet_tcp_queue *queue)
{
	queue->poll_end = jiffies + usecs_to_jiffies(idle_poll_period_usecs);
}

static bool nvmet_tcp_check_queue_deadline(struct nvmet_tcp_queue *queue,
		int ops)
{
	if (!idle_poll_period_usecs)
		return false;

	if (ops)
		nvmet_tcp_arm_queue_deadline(queue);

	return !time_after(jiffies, queue->poll_end);
}

static void nvmet_tcp_io_work(struct work_struct *w)
{
	struct nvmet_tcp_queue *queue =
		container_of(w, struct nvmet_tcp_queue, io_work);
	bool pending;
	int ret, ops = 0;

	do {
		pending = false;

		ret = nvmet_tcp_try_recv(queue, NVMET_TCP_RECV_BUDGET, &ops);
		if (ret > 0)
			pending = true;
		else if (ret < 0)
			return;

		ret = nvmet_tcp_try_send(queue, NVMET_TCP_SEND_BUDGET, &ops);
		if (ret > 0)
			pending = true;
		else if (ret < 0)
			return;

	} while (pending && ops < NVMET_TCP_IO_WORK_BUDGET);

	/*
	 * Requeue the worker if idle deadline period is in progress or any
	 * ops activity was recorded during the do-while loop above.
	 */
	if (nvmet_tcp_check_queue_deadline(queue, ops) || pending)
		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
}

static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
		struct nvmet_tcp_cmd *c)
{
	u8 hdgst = nvmet_tcp_hdgst_len(queue);

	c->queue = queue;
	c->req.port = queue->port->nport;

	c->cmd_pdu = page_frag_alloc(&queue->pf_cache,
			sizeof(*c->cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
	if (!c->cmd_pdu)
		return -ENOMEM;
	c->req.cmd = &c->cmd_pdu->cmd;

	c->rsp_pdu = page_frag_alloc(&queue->pf_cache,
			sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
	if (!c->rsp_pdu)
		goto out_free_cmd;
	c->req.cqe = &c->rsp_pdu->cqe;

	c->data_pdu = page_frag_alloc(&queue->pf_cache,
			sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
	if (!c->data_pdu)
		goto out_free_rsp;

	c->r2t_pdu = page_frag_alloc(&queue->pf_cache,
			sizeof(*c->r2t_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
	if (!c->r2t_pdu)
		goto out_free_data;

	if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
		c->recv_msg.msg_control = c->recv_cbuf;
		c->recv_msg.msg_controllen = sizeof(c->recv_cbuf);
	}
	c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;

	list_add_tail(&c->entry, &queue->free_list);

	return 0;
out_free_data:
	page_frag_free(c->data_pdu);
out_free_rsp:
	page_frag_free(c->rsp_pdu);
out_free_cmd:
	page_frag_free(c->cmd_pdu);
	return -ENOMEM;
}

static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c)
{
	page_frag_free(c->r2t_pdu);
	page_frag_free(c->data_pdu);
	page_frag_free(c->rsp_pdu);
	page_frag_free(c->cmd_pdu);
}

static int nvmet_tcp_alloc_cmds(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmds;
	int i, ret = -EINVAL, nr_cmds = queue->nr_cmds;

	cmds = kcalloc(nr_cmds, sizeof(struct nvmet_tcp_cmd), GFP_KERNEL);
	if (!cmds)
		goto out;

	for (i = 0; i < nr_cmds; i++) {
		ret = nvmet_tcp_alloc_cmd(queue, cmds + i);
		if (ret)
			goto out_free;
	}

	queue->cmds = cmds;

	return 0;
out_free:
	while (--i >= 0)
		nvmet_tcp_free_cmd(cmds + i);
	kfree(cmds);
out:
	return ret;
}

static void nvmet_tcp_free_cmds(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmds = queue->cmds;
	int i;

	for (i = 0; i < queue->nr_cmds; i++)
		nvmet_tcp_free_cmd(cmds + i);

	nvmet_tcp_free_cmd(&queue->connect);
	kfree(cmds);
}

static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
{
	struct socket *sock = queue->sock;

	write_lock_bh(&sock->sk->sk_callback_lock);
	sock->sk->sk_data_ready =  queue->data_ready;
	sock->sk->sk_state_change = queue->state_change;
	sock->sk->sk_write_space = queue->write_space;
	sock->sk->sk_user_data = NULL;
	write_unlock_bh(&sock->sk->sk_callback_lock);
}

static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmd = queue->cmds;
	int i;

	for (i = 0; i < queue->nr_cmds; i++, cmd++) {
		if (nvmet_tcp_need_data_in(cmd))
			nvmet_req_uninit(&cmd->req);
	}

	if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) {
		/* failed in connect */
		nvmet_req_uninit(&queue->connect.req);
	}
}

static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue)
{
	struct nvmet_tcp_cmd *cmd = queue->cmds;
	int i;

	for (i = 0; i < queue->nr_cmds; i++, cmd++) {
		if (nvmet_tcp_need_data_in(cmd))
			nvmet_tcp_free_cmd_buffers(cmd);
	}

	if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect))
		nvmet_tcp_free_cmd_buffers(&queue->connect);
}

static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
	struct page *page;
	struct nvmet_tcp_queue *queue =
		container_of(w, struct nvmet_tcp_queue, release_work);

	mutex_lock(&nvmet_tcp_queue_mutex);
	list_del_init(&queue->queue_list);
	mutex_unlock(&nvmet_tcp_queue_mutex);

	nvmet_tcp_restore_socket_callbacks(queue);
	cancel_delayed_work_sync(&queue->tls_handshake_tmo_work);
	cancel_work_sync(&queue->io_work);
	/* stop accepting incoming data */
	queue->rcv_state = NVMET_TCP_RECV_ERR;

	nvmet_tcp_uninit_data_in_cmds(queue);
	nvmet_sq_destroy(&queue->nvme_sq);
	cancel_work_sync(&queue->io_work);
	nvmet_tcp_free_cmd_data_in_buffers(queue);
	/* ->sock will be released by fput() */
	fput(queue->sock->file);
	nvmet_tcp_free_cmds(queue);
	if (queue->hdr_digest || queue->data_digest)
		nvmet_tcp_free_crypto(queue);
	ida_free(&nvmet_tcp_queue_ida, queue->idx);
	page = virt_to_head_page(queue->pf_cache.va);
	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
	kfree(queue);
}

static void nvmet_tcp_data_ready(struct sock *sk)
{
	struct nvmet_tcp_queue *queue;

	trace_sk_data_ready(sk);

	read_lock_bh(&sk->sk_callback_lock);
	queue = sk->sk_user_data;
	if (likely(queue)) {
		if (queue->data_ready)
			queue->data_ready(sk);
		if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)
			queue_work_on(queue_cpu(queue), nvmet_tcp_wq,
				      &queue->io_work);
	}
	read_unlock_bh(&sk->sk_callback_lock);
}

static void nvmet_tcp_write_space(struct sock *sk)
{
	struct nvmet_tcp_queue *queue;

	read_lock_bh(&sk->sk_callback_lock);
	queue = sk->sk_user_data;
	if (unlikely(!queue))
		goto out;

	if (unlikely(queue->state == NVMET_TCP_Q_CONNECTING)) {
		queue->write_space(sk);
		goto out;
	}

	if (sk_stream_is_writeable(sk)) {
		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
	}
out:
	read_unlock_bh(&sk->sk_callback_lock);
}

static void nvmet_tcp_state_change(struct sock *sk)
{
	struct nvmet_tcp_queue *queue;

	read_lock_bh(&sk->sk_callback_lock);
	queue = sk->sk_user_data;
	if (!queue)
		goto done;

	switch (sk->sk_state) {
	case TCP_FIN_WAIT2:
	case TCP_LAST_ACK:
		break;
	case TCP_FIN_WAIT1:
	case TCP_CLOSE_WAIT:
	case TCP_CLOSE:
		/* FALLTHRU */
		nvmet_tcp_schedule_release_queue(queue);
		break;
	default:
		pr_warn("queue %d unhandled state %d\n",
			queue->idx, sk->sk_state);
	}
done:
	read_unlock_bh(&sk->sk_callback_lock);
}

static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
{
	struct socket *sock = queue->sock;
	struct inet_sock *inet = inet_sk(sock->sk);
	int ret;

	ret = kernel_getsockname(sock,
		(struct sockaddr *)&queue->sockaddr);
	if (ret < 0)
		return ret;

	ret = kernel_getpeername(sock,
		(struct sockaddr *)&queue->sockaddr_peer);
	if (ret < 0)
		return ret;

	/*
	 * Cleanup whatever is sitting in the TCP transmit queue on socket
	 * close. This is done to prevent stale data from being sent should
	 * the network connection be restored before TCP times out.
	 */
	sock_no_linger(sock->sk);

	if (so_priority > 0)
		sock_set_priority(sock->sk, so_priority);

	/* Set socket type of service */
	if (inet->rcv_tos > 0)
		ip_sock_set_tos(sock->sk, inet->rcv_tos);

	ret = 0;
	write_lock_bh(&sock->sk->sk_callback_lock);
	if (sock->sk->sk_state != TCP_ESTABLISHED) {
		/*
		 * If the socket is already closing, don't even start
		 * consuming it
		 */
		ret = -ENOTCONN;
	} else {
		sock->sk->sk_user_data = queue;
		queue->data_ready = sock->sk->sk_data_ready;
		sock->sk->sk_data_ready = nvmet_tcp_data_ready;
		queue->state_change = sock->sk->sk_state_change;
		sock->sk->sk_state_change = nvmet_tcp_state_change;
		queue->write_space = sock->sk->sk_write_space;
		sock->sk->sk_write_space = nvmet_tcp_write_space;
		if (idle_poll_period_usecs)
			nvmet_tcp_arm_queue_deadline(queue);
		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
	}
	write_unlock_bh(&sock->sk->sk_callback_lock);

	return ret;
}

#ifdef CONFIG_NVME_TARGET_TCP_TLS
static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue)
{
	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
	int len, ret;
	struct kvec iov = {
		.iov_base = (u8 *)&queue->pdu + queue->offset,
		.iov_len = sizeof(struct nvme_tcp_hdr),
	};
	char cbuf[CMSG_LEN(sizeof(char))] = {};
	struct msghdr msg = {
		.msg_control = cbuf,
		.msg_controllen = sizeof(cbuf),
		.msg_flags = MSG_PEEK,
	};

	if (nvmet_port_secure_channel_required(queue->port->nport))
		return 0;

	len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
			iov.iov_len, msg.msg_flags);
	if (unlikely(len < 0)) {
		pr_debug("queue %d: peek error %d\n",
			 queue->idx, len);
		return len;
	}

	ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
	if (ret < 0)
		return ret;

	if (len < sizeof(struct nvme_tcp_hdr)) {
		pr_debug("queue %d: short read, %d bytes missing\n",
			 queue->idx, (int)iov.iov_len - len);
		return -EAGAIN;
	}
	pr_debug("queue %d: hdr type %d hlen %d plen %d size %d\n",
		 queue->idx, hdr->type, hdr->hlen, hdr->plen,
		 (int)sizeof(struct nvme_tcp_icreq_pdu));
	if (hdr->type == nvme_tcp_icreq &&
	    hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) &&
	    hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) {
		pr_debug("queue %d: icreq detected\n",
			 queue->idx);
		return len;
	}
	return 0;
}

static void nvmet_tcp_tls_handshake_done(void *data, int status,
					 key_serial_t peerid)
{
	struct nvmet_tcp_queue *queue = data;

	pr_debug("queue %d: TLS handshake done, key %x, status %d\n",
		 queue->idx, peerid, status);
	spin_lock_bh(&queue->state_lock);
	if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) {
		spin_unlock_bh(&queue->state_lock);
		return;
	}
	if (!status) {
		queue->tls_pskid = peerid;
		queue->state = NVMET_TCP_Q_CONNECTING;
	} else
		queue->state = NVMET_TCP_Q_FAILED;
	spin_unlock_bh(&queue->state_lock);

	cancel_delayed_work_sync(&queue->tls_handshake_tmo_work);
	if (status)
		nvmet_tcp_schedule_release_queue(queue);
	else
		nvmet_tcp_set_queue_sock(queue);
	kref_put(&queue->kref, nvmet_tcp_release_queue);
}

static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w)
{
	struct nvmet_tcp_queue *queue = container_of(to_delayed_work(w),
			struct nvmet_tcp_queue, tls_handshake_tmo_work);

	pr_warn("queue %d: TLS handshake timeout\n", queue->idx);
	/*
	 * If tls_handshake_cancel() fails we've lost the race with
	 * nvmet_tcp_tls_handshake_done() */
	if (!tls_handshake_cancel(queue->sock->sk))
		return;
	spin_lock_bh(&queue->state_lock);
	if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) {
		spin_unlock_bh(&queue->state_lock);
		return;
	}
	queue->state = NVMET_TCP_Q_FAILED;
	spin_unlock_bh(&queue->state_lock);
	nvmet_tcp_schedule_release_queue(queue);
	kref_put(&queue->kref, nvmet_tcp_release_queue);
}

static int nvmet_tcp_tls_handshake(struct nvmet_tcp_queue *queue)
{
	int ret = -EOPNOTSUPP;
	struct tls_handshake_args args;

	if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE) {
		pr_warn("cannot start TLS in state %d\n", queue->state);
		return -EINVAL;
	}

	kref_get(&queue->kref);
	pr_debug("queue %d: TLS ServerHello\n", queue->idx);
	memset(&args, 0, sizeof(args));
	args.ta_sock = queue->sock;
	args.ta_done = nvmet_tcp_tls_handshake_done;
	args.ta_data = queue;
	args.ta_keyring = key_serial(queue->port->nport->keyring);
	args.ta_timeout_ms = tls_handshake_timeout * 1000;

	ret = tls_server_hello_psk(&args, GFP_KERNEL);
	if (ret) {
		kref_put(&queue->kref, nvmet_tcp_release_queue);
		pr_err("failed to start TLS, err=%d\n", ret);
	} else {
		queue_delayed_work(nvmet_wq, &queue->tls_handshake_tmo_work,
				   tls_handshake_timeout * HZ);
	}
	return ret;
}
#else
static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) {}
#endif

static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
		struct socket *newsock)
{
	struct nvmet_tcp_queue *queue;
	struct file *sock_file = NULL;
	int ret;

	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
	if (!queue) {
		ret = -ENOMEM;
		goto out_release;
	}

	INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work);
	INIT_WORK(&queue->io_work, nvmet_tcp_io_work);
	kref_init(&queue->kref);
	queue->sock = newsock;
	queue->port = port;
	queue->nr_cmds = 0;
	spin_lock_init(&queue->state_lock);
	if (queue->port->nport->disc_addr.tsas.tcp.sectype ==
	    NVMF_TCP_SECTYPE_TLS13)
		queue->state = NVMET_TCP_Q_TLS_HANDSHAKE;
	else
		queue->state = NVMET_TCP_Q_CONNECTING;
	INIT_LIST_HEAD(&queue->free_list);
	init_llist_head(&queue->resp_list);
	INIT_LIST_HEAD(&queue->resp_send_list);

	sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL);
	if (IS_ERR(sock_file)) {
		ret = PTR_ERR(sock_file);
		goto out_free_queue;
	}

	queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL);
	if (queue->idx < 0) {
		ret = queue->idx;
		goto out_sock;
	}

	ret = nvmet_tcp_alloc_cmd(queue, &queue->connect);
	if (ret)
		goto out_ida_remove;

	ret = nvmet_sq_init(&queue->nvme_sq);
	if (ret)
		goto out_free_connect;

	nvmet_prepare_receive_pdu(queue);

	mutex_lock(&nvmet_tcp_queue_mutex);
	list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list);
	mutex_unlock(&nvmet_tcp_queue_mutex);

	INIT_DELAYED_WORK(&queue->tls_handshake_tmo_work,
			  nvmet_tcp_tls_handshake_timeout);
#ifdef CONFIG_NVME_TARGET_TCP_TLS
	if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
		struct sock *sk = queue->sock->sk;

		/* Restore the default callbacks before starting upcall */
		read_lock_bh(&sk->sk_callback_lock);
		sk->sk_user_data = NULL;
		sk->sk_data_ready = port->data_ready;
		read_unlock_bh(&sk->sk_callback_lock);
		if (!nvmet_tcp_try_peek_pdu(queue)) {
			if (!nvmet_tcp_tls_handshake(queue))
				return;
			/* TLS handshake failed, terminate the connection */
			goto out_destroy_sq;
		}
		/* Not a TLS connection, continue with normal processing */
		queue->state = NVMET_TCP_Q_CONNECTING;
	}
#endif

	ret = nvmet_tcp_set_queue_sock(queue);
	if (ret)
		goto out_destroy_sq;

	return;
out_destroy_sq:
	mutex_lock(&nvmet_tcp_queue_mutex);
	list_del_init(&queue->queue_list);
	mutex_unlock(&nvmet_tcp_queue_mutex);
	nvmet_sq_destroy(&queue->nvme_sq);
out_free_connect:
	nvmet_tcp_free_cmd(&queue->connect);
out_ida_remove:
	ida_free(&nvmet_tcp_queue_ida, queue->idx);
out_sock:
	fput(queue->sock->file);
out_free_queue:
	kfree(queue);
out_release:
	pr_err("failed to allocate queue, error %d\n", ret);
	if (!sock_file)
		sock_release(newsock);
}

static void nvmet_tcp_accept_work(struct work_struct *w)
{
	struct nvmet_tcp_port *port =
		container_of(w, struct nvmet_tcp_port, accept_work);
	struct socket *newsock;
	int ret;

	while (true) {
		ret = kernel_accept(port->sock, &newsock, O_NONBLOCK);
		if (ret < 0) {
			if (ret != -EAGAIN)
				pr_warn("failed to accept err=%d\n", ret);
			return;
		}
		nvmet_tcp_alloc_queue(port, newsock);
	}
}

static void nvmet_tcp_listen_data_ready(struct sock *sk)
{
	struct nvmet_tcp_port *port;

	trace_sk_data_ready(sk);

	read_lock_bh(&sk->sk_callback_lock);
	port = sk->sk_user_data;
	if (!port)
		goto out;

	if (sk->sk_state == TCP_LISTEN)
		queue_work(nvmet_wq, &port->accept_work);
out:
	read_unlock_bh(&sk->sk_callback_lock);
}

static int nvmet_tcp_add_port(struct nvmet_port *nport)
{
	struct nvmet_tcp_port *port;
	__kernel_sa_family_t af;
	int ret;

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

	switch (nport->disc_addr.adrfam) {
	case NVMF_ADDR_FAMILY_IP4:
		af = AF_INET;
		break;
	case NVMF_ADDR_FAMILY_IP6:
		af = AF_INET6;
		break;
	default:
		pr_err("address family %d not supported\n",
				nport->disc_addr.adrfam);
		ret = -EINVAL;
		goto err_port;
	}

	ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
			nport->disc_addr.trsvcid, &port->addr);
	if (ret) {
		pr_err("malformed ip/port passed: %s:%s\n",
			nport->disc_addr.traddr, nport->disc_addr.trsvcid);
		goto err_port;
	}

	port->nport = nport;
	INIT_WORK(&port->accept_work, nvmet_tcp_accept_work);
	if (port->nport->inline_data_size < 0)
		port->nport->inline_data_size = NVMET_TCP_DEF_INLINE_DATA_SIZE;

	ret = sock_create(port->addr.ss_family, SOCK_STREAM,
				IPPROTO_TCP, &port->sock);
	if (ret) {
		pr_err("failed to create a socket\n");
		goto err_port;
	}

	port->sock->sk->sk_user_data = port;
	port->data_ready = port->sock->sk->sk_data_ready;
	port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;
	sock_set_reuseaddr(port->sock->sk);
	tcp_sock_set_nodelay(port->sock->sk);
	if (so_priority > 0)
		sock_set_priority(port->sock->sk, so_priority);

	ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
			sizeof(port->addr));
	if (ret) {
		pr_err("failed to bind port socket %d\n", ret);
		goto err_sock;
	}

	ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG);
	if (ret) {
		pr_err("failed to listen %d on port sock\n", ret);
		goto err_sock;
	}

	nport->priv = port;
	pr_info("enabling port %d (%pISpc)\n",
		le16_to_cpu(nport->disc_addr.portid), &port->addr);

	return 0;

err_sock:
	sock_release(port->sock);
err_port:
	kfree(port);
	return ret;
}

static void nvmet_tcp_destroy_port_queues(struct nvmet_tcp_port *port)
{
	struct nvmet_tcp_queue *queue;

	mutex_lock(&nvmet_tcp_queue_mutex);
	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
		if (queue->port == port)
			kernel_sock_shutdown(queue->sock, SHUT_RDWR);
	mutex_unlock(&nvmet_tcp_queue_mutex);
}

static void nvmet_tcp_remove_port(struct nvmet_port *nport)
{
	struct nvmet_tcp_port *port = nport->priv;

	write_lock_bh(&port->sock->sk->sk_callback_lock);
	port->sock->sk->sk_data_ready = port->data_ready;
	port->sock->sk->sk_user_data = NULL;
	write_unlock_bh(&port->sock->sk->sk_callback_lock);
	cancel_work_sync(&port->accept_work);
	/*
	 * Destroy the remaining queues, which are not belong to any
	 * controller yet.
	 */
	nvmet_tcp_destroy_port_queues(port);

	sock_release(port->sock);
	kfree(port);
}

static void nvmet_tcp_delete_ctrl(struct nvmet_ctrl *ctrl)
{
	struct nvmet_tcp_queue *queue;

	mutex_lock(&nvmet_tcp_queue_mutex);
	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
		if (queue->nvme_sq.ctrl == ctrl)
			kernel_sock_shutdown(queue->sock, SHUT_RDWR);
	mutex_unlock(&nvmet_tcp_queue_mutex);
}

static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
{
	struct nvmet_tcp_queue *queue =
		container_of(sq, struct nvmet_tcp_queue, nvme_sq);

	if (sq->qid == 0) {
		struct nvmet_tcp_queue *q;
		int pending = 0;

		/* Check for pending controller teardown */
		mutex_lock(&nvmet_tcp_queue_mutex);
		list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) {
			if (q->nvme_sq.ctrl == sq->ctrl &&
			    q->state == NVMET_TCP_Q_DISCONNECTING)
				pending++;
		}
		mutex_unlock(&nvmet_tcp_queue_mutex);
		if (pending > NVMET_TCP_BACKLOG)
			return NVME_SC_CONNECT_CTRL_BUSY;
	}

	queue->nr_cmds = sq->size * 2;
	if (nvmet_tcp_alloc_cmds(queue))
		return NVME_SC_INTERNAL;
	return 0;
}

static void nvmet_tcp_disc_port_addr(struct nvmet_req *req,
		struct nvmet_port *nport, char *traddr)
{
	struct nvmet_tcp_port *port = nport->priv;

	if (inet_addr_is_any((struct sockaddr *)&port->addr)) {
		struct nvmet_tcp_cmd *cmd =
			container_of(req, struct nvmet_tcp_cmd, req);
		struct nvmet_tcp_queue *queue = cmd->queue;

		sprintf(traddr, "%pISc", (struct sockaddr *)&queue->sockaddr);
	} else {
		memcpy(traddr, nport->disc_addr.traddr, NVMF_TRADDR_SIZE);
	}
}

static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
	.owner			= THIS_MODULE,
	.type			= NVMF_TRTYPE_TCP,
	.msdbd			= 1,
	.add_port		= nvmet_tcp_add_port,
	.remove_port		= nvmet_tcp_remove_port,
	.queue_response		= nvmet_tcp_queue_response,
	.delete_ctrl		= nvmet_tcp_delete_ctrl,
	.install_queue		= nvmet_tcp_install_queue,
	.disc_traddr		= nvmet_tcp_disc_port_addr,
};

static int __init nvmet_tcp_init(void)
{
	int ret;

	nvmet_tcp_wq = alloc_workqueue("nvmet_tcp_wq",
				WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
	if (!nvmet_tcp_wq)
		return -ENOMEM;

	ret = nvmet_register_transport(&nvmet_tcp_ops);
	if (ret)
		goto err;

	return 0;
err:
	destroy_workqueue(nvmet_tcp_wq);
	return ret;
}

static void __exit nvmet_tcp_exit(void)
{
	struct nvmet_tcp_queue *queue;

	nvmet_unregister_transport(&nvmet_tcp_ops);

	flush_workqueue(nvmet_wq);
	mutex_lock(&nvmet_tcp_queue_mutex);
	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
	mutex_unlock(&nvmet_tcp_queue_mutex);
	flush_workqueue(nvmet_wq);

	destroy_workqueue(nvmet_tcp_wq);
	ida_destroy(&nvmet_tcp_queue_ida);
}

module_init(nvmet_tcp_init);
module_exit(nvmet_tcp_exit);

MODULE_DESCRIPTION("NVMe target TCP transport driver");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */