Free Electrons

Embedded Linux Experts

   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
/*
 * iSCSI Initiator over TCP/IP Data-Path
 *
 * Copyright (C) 2004 Dmitry Yusupov
 * Copyright (C) 2004 Alex Aizman
 * Copyright (C) 2005 - 2006 Mike Christie
 * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
 * maintained by open-iscsi@googlegroups.com
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that 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.
 *
 * See the file COPYING included with this distribution for more details.
 *
 * Credits:
 *	Christoph Hellwig
 *	FUJITA Tomonori
 *	Arne Redlich
 *	Zhenyu Wang
 */

#include <linux/types.h>
#include <linux/list.h>
#include <linux/inet.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/crypto.h>
#include <linux/delay.h>
#include <linux/kfifo.h>
#include <linux/scatterlist.h>
#include <net/tcp.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi.h>
#include <scsi/scsi_transport_iscsi.h>

#include "iscsi_tcp.h"

MODULE_AUTHOR("Dmitry Yusupov <dmitry_yus@yahoo.com>, "
	      "Alex Aizman <itn780@yahoo.com>");
MODULE_DESCRIPTION("iSCSI/TCP data-path");
MODULE_LICENSE("GPL");
#undef DEBUG_TCP
#define DEBUG_ASSERT

#ifdef DEBUG_TCP
#define debug_tcp(fmt...) printk(KERN_INFO "tcp: " fmt)
#else
#define debug_tcp(fmt...)
#endif

#ifndef DEBUG_ASSERT
#ifdef BUG_ON
#undef BUG_ON
#endif
#define BUG_ON(expr)
#endif

static struct scsi_transport_template *iscsi_tcp_scsi_transport;
static struct scsi_host_template iscsi_sht;
static struct iscsi_transport iscsi_tcp_transport;

static unsigned int iscsi_max_lun = 512;
module_param_named(max_lun, iscsi_max_lun, uint, S_IRUGO);

static int iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn,
				   struct iscsi_segment *segment);

/*
 * Scatterlist handling: inside the iscsi_segment, we
 * remember an index into the scatterlist, and set data/size
 * to the current scatterlist entry. For highmem pages, we
 * kmap as needed.
 *
 * Note that the page is unmapped when we return from
 * TCP's data_ready handler, so we may end up mapping and
 * unmapping the same page repeatedly. The whole reason
 * for this is that we shouldn't keep the page mapped
 * outside the softirq.
 */

/**
 * iscsi_tcp_segment_init_sg - init indicated scatterlist entry
 * @segment: the buffer object
 * @sg: scatterlist
 * @offset: byte offset into that sg entry
 *
 * This function sets up the segment so that subsequent
 * data is copied to the indicated sg entry, at the given
 * offset.
 */
static inline void
iscsi_tcp_segment_init_sg(struct iscsi_segment *segment,
			  struct scatterlist *sg, unsigned int offset)
{
	segment->sg = sg;
	segment->sg_offset = offset;
	segment->size = min(sg->length - offset,
			    segment->total_size - segment->total_copied);
	segment->data = NULL;
}

/**
 * iscsi_tcp_segment_map - map the current S/G page
 * @segment: iscsi_segment
 * @recv: 1 if called from recv path
 *
 * We only need to possibly kmap data if scatter lists are being used,
 * because the iscsi passthrough and internal IO paths will never use high
 * mem pages.
 */
static inline void
iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv)
{
	struct scatterlist *sg;

	if (segment->data != NULL || !segment->sg)
		return;

	sg = segment->sg;
	BUG_ON(segment->sg_mapped);
	BUG_ON(sg->length == 0);

	/*
	 * If the page count is greater than one it is ok to send
	 * to the network layer's zero copy send path. If not we
	 * have to go the slow sendmsg path. We always map for the
	 * recv path.
	 */
	if (page_count(sg_page(sg)) >= 1 && !recv)
		return;

	debug_tcp("iscsi_tcp_segment_map %s %p\n", recv ? "recv" : "xmit",
		  segment);
	segment->sg_mapped = kmap_atomic(sg_page(sg), KM_SOFTIRQ0);
	segment->data = segment->sg_mapped + sg->offset + segment->sg_offset;
}

static inline void
iscsi_tcp_segment_unmap(struct iscsi_segment *segment)
{
	debug_tcp("iscsi_tcp_segment_unmap %p\n", segment);

	if (segment->sg_mapped) {
		debug_tcp("iscsi_tcp_segment_unmap valid\n");
		kunmap_atomic(segment->sg_mapped, KM_SOFTIRQ0);
		segment->sg_mapped = NULL;
		segment->data = NULL;
	}
}

/*
 * Splice the digest buffer into the buffer
 */
static inline void
iscsi_tcp_segment_splice_digest(struct iscsi_segment *segment, void *digest)
{
	segment->data = digest;
	segment->digest_len = ISCSI_DIGEST_SIZE;
	segment->total_size += ISCSI_DIGEST_SIZE;
	segment->size = ISCSI_DIGEST_SIZE;
	segment->copied = 0;
	segment->sg = NULL;
	segment->hash = NULL;
}

/**
 * iscsi_tcp_segment_done - check whether the segment is complete
 * @segment: iscsi segment to check
 * @recv: set to one of this is called from the recv path
 * @copied: number of bytes copied
 *
 * Check if we're done receiving this segment. If the receive
 * buffer is full but we expect more data, move on to the
 * next entry in the scatterlist.
 *
 * If the amount of data we received isn't a multiple of 4,
 * we will transparently receive the pad bytes, too.
 *
 * This function must be re-entrant.
 */
static inline int
iscsi_tcp_segment_done(struct iscsi_segment *segment, int recv, unsigned copied)
{
	static unsigned char padbuf[ISCSI_PAD_LEN];
	struct scatterlist sg;
	unsigned int pad;

	debug_tcp("copied %u %u size %u %s\n", segment->copied, copied,
		  segment->size, recv ? "recv" : "xmit");
	if (segment->hash && copied) {
		/*
		 * If a segment is kmapd we must unmap it before sending
		 * to the crypto layer since that will try to kmap it again.
		 */
		iscsi_tcp_segment_unmap(segment);

		if (!segment->data) {
			sg_init_table(&sg, 1);
			sg_set_page(&sg, sg_page(segment->sg), copied,
				    segment->copied + segment->sg_offset +
							segment->sg->offset);
		} else
			sg_init_one(&sg, segment->data + segment->copied,
				    copied);
		crypto_hash_update(segment->hash, &sg, copied);
	}

	segment->copied += copied;
	if (segment->copied < segment->size) {
		iscsi_tcp_segment_map(segment, recv);
		return 0;
	}

	segment->total_copied += segment->copied;
	segment->copied = 0;
	segment->size = 0;

	/* Unmap the current scatterlist page, if there is one. */
	iscsi_tcp_segment_unmap(segment);

	/* Do we have more scatterlist entries? */
	debug_tcp("total copied %u total size %u\n", segment->total_copied,
		   segment->total_size);
	if (segment->total_copied < segment->total_size) {
		/* Proceed to the next entry in the scatterlist. */
		iscsi_tcp_segment_init_sg(segment, sg_next(segment->sg),
					  0);
		iscsi_tcp_segment_map(segment, recv);
		BUG_ON(segment->size == 0);
		return 0;
	}

	/* Do we need to handle padding? */
	pad = iscsi_padding(segment->total_copied);
	if (pad != 0) {
		debug_tcp("consume %d pad bytes\n", pad);
		segment->total_size += pad;
		segment->size = pad;
		segment->data = padbuf;
		return 0;
	}

	/*
	 * Set us up for transferring the data digest. hdr digest
	 * is completely handled in hdr done function.
	 */
	if (segment->hash) {
		crypto_hash_final(segment->hash, segment->digest);
		iscsi_tcp_segment_splice_digest(segment,
				 recv ? segment->recv_digest : segment->digest);
		return 0;
	}

	return 1;
}

/**
 * iscsi_tcp_xmit_segment - transmit segment
 * @tcp_conn: the iSCSI TCP connection
 * @segment: the buffer to transmnit
 *
 * This function transmits as much of the buffer as
 * the network layer will accept, and returns the number of
 * bytes transmitted.
 *
 * If CRC hashing is enabled, the function will compute the
 * hash as it goes. When the entire segment has been transmitted,
 * it will retrieve the hash value and send it as well.
 */
static int
iscsi_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn,
		       struct iscsi_segment *segment)
{
	struct socket *sk = tcp_conn->sock;
	unsigned int copied = 0;
	int r = 0;

	while (!iscsi_tcp_segment_done(segment, 0, r)) {
		struct scatterlist *sg;
		unsigned int offset, copy;
		int flags = 0;

		r = 0;
		offset = segment->copied;
		copy = segment->size - offset;

		if (segment->total_copied + segment->size < segment->total_size)
			flags |= MSG_MORE;

		/* Use sendpage if we can; else fall back to sendmsg */
		if (!segment->data) {
			sg = segment->sg;
			offset += segment->sg_offset + sg->offset;
			r = tcp_conn->sendpage(sk, sg_page(sg), offset, copy,
					       flags);
		} else {
			struct msghdr msg = { .msg_flags = flags };
			struct kvec iov = {
				.iov_base = segment->data + offset,
				.iov_len = copy
			};

			r = kernel_sendmsg(sk, &msg, &iov, 1, copy);
		}

		if (r < 0) {
			iscsi_tcp_segment_unmap(segment);
			if (copied || r == -EAGAIN)
				break;
			return r;
		}
		copied += r;
	}
	return copied;
}

/**
 * iscsi_tcp_segment_recv - copy data to segment
 * @tcp_conn: the iSCSI TCP connection
 * @segment: the buffer to copy to
 * @ptr: data pointer
 * @len: amount of data available
 *
 * This function copies up to @len bytes to the
 * given buffer, and returns the number of bytes
 * consumed, which can actually be less than @len.
 *
 * If hash digest is enabled, the function will update the
 * hash while copying.
 * Combining these two operations doesn't buy us a lot (yet),
 * but in the future we could implement combined copy+crc,
 * just way we do for network layer checksums.
 */
static int
iscsi_tcp_segment_recv(struct iscsi_tcp_conn *tcp_conn,
		       struct iscsi_segment *segment, const void *ptr,
		       unsigned int len)
{
	unsigned int copy = 0, copied = 0;

	while (!iscsi_tcp_segment_done(segment, 1, copy)) {
		if (copied == len) {
			debug_tcp("iscsi_tcp_segment_recv copied %d bytes\n",
				  len);
			break;
		}

		copy = min(len - copied, segment->size - segment->copied);
		debug_tcp("iscsi_tcp_segment_recv copying %d\n", copy);
		memcpy(segment->data + segment->copied, ptr + copied, copy);
		copied += copy;
	}
	return copied;
}

static inline void
iscsi_tcp_dgst_header(struct hash_desc *hash, const void *hdr, size_t hdrlen,
		      unsigned char digest[ISCSI_DIGEST_SIZE])
{
	struct scatterlist sg;

	sg_init_one(&sg, hdr, hdrlen);
	crypto_hash_digest(hash, &sg, hdrlen, digest);
}

static inline int
iscsi_tcp_dgst_verify(struct iscsi_tcp_conn *tcp_conn,
		      struct iscsi_segment *segment)
{
	if (!segment->digest_len)
		return 1;

	if (memcmp(segment->recv_digest, segment->digest,
		   segment->digest_len)) {
		debug_scsi("digest mismatch\n");
		return 0;
	}

	return 1;
}

/*
 * Helper function to set up segment buffer
 */
static inline void
__iscsi_segment_init(struct iscsi_segment *segment, size_t size,
		     iscsi_segment_done_fn_t *done, struct hash_desc *hash)
{
	memset(segment, 0, sizeof(*segment));
	segment->total_size = size;
	segment->done = done;

	if (hash) {
		segment->hash = hash;
		crypto_hash_init(hash);
	}
}

static inline void
iscsi_segment_init_linear(struct iscsi_segment *segment, void *data,
			  size_t size, iscsi_segment_done_fn_t *done,
			  struct hash_desc *hash)
{
	__iscsi_segment_init(segment, size, done, hash);
	segment->data = data;
	segment->size = size;
}

static inline int
iscsi_segment_seek_sg(struct iscsi_segment *segment,
		      struct scatterlist *sg_list, unsigned int sg_count,
		      unsigned int offset, size_t size,
		      iscsi_segment_done_fn_t *done, struct hash_desc *hash)
{
	struct scatterlist *sg;
	unsigned int i;

	debug_scsi("iscsi_segment_seek_sg offset %u size %llu\n",
		  offset, size);
	__iscsi_segment_init(segment, size, done, hash);
	for_each_sg(sg_list, sg, sg_count, i) {
		debug_scsi("sg %d, len %u offset %u\n", i, sg->length,
			   sg->offset);
		if (offset < sg->length) {
			iscsi_tcp_segment_init_sg(segment, sg, offset);
			return 0;
		}
		offset -= sg->length;
	}

	return ISCSI_ERR_DATA_OFFSET;
}

/**
 * iscsi_tcp_hdr_recv_prep - prep segment for hdr reception
 * @tcp_conn: iscsi connection to prep for
 *
 * This function always passes NULL for the hash argument, because when this
 * function is called we do not yet know the final size of the header and want
 * to delay the digest processing until we know that.
 */
static void
iscsi_tcp_hdr_recv_prep(struct iscsi_tcp_conn *tcp_conn)
{
	debug_tcp("iscsi_tcp_hdr_recv_prep(%p%s)\n", tcp_conn,
		  tcp_conn->iscsi_conn->hdrdgst_en ? ", digest enabled" : "");
	iscsi_segment_init_linear(&tcp_conn->in.segment,
				tcp_conn->in.hdr_buf, sizeof(struct iscsi_hdr),
				iscsi_tcp_hdr_recv_done, NULL);
}

/*
 * Handle incoming reply to any other type of command
 */
static int
iscsi_tcp_data_recv_done(struct iscsi_tcp_conn *tcp_conn,
			 struct iscsi_segment *segment)
{
	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
	int rc = 0;

	if (!iscsi_tcp_dgst_verify(tcp_conn, segment))
		return ISCSI_ERR_DATA_DGST;

	rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr,
			conn->data, tcp_conn->in.datalen);
	if (rc)
		return rc;

	iscsi_tcp_hdr_recv_prep(tcp_conn);
	return 0;
}

static void
iscsi_tcp_data_recv_prep(struct iscsi_tcp_conn *tcp_conn)
{
	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
	struct hash_desc *rx_hash = NULL;

	if (conn->datadgst_en)
		rx_hash = &tcp_conn->rx_hash;

	iscsi_segment_init_linear(&tcp_conn->in.segment,
				conn->data, tcp_conn->in.datalen,
				iscsi_tcp_data_recv_done, rx_hash);
}

/*
 * must be called with session lock
 */
static void
iscsi_tcp_cleanup_task(struct iscsi_conn *conn, struct iscsi_task *task)
{
	struct iscsi_tcp_task *tcp_task = task->dd_data;
	struct iscsi_r2t_info *r2t;

	/* nothing to do for mgmt tasks */
	if (!task->sc)
		return;

	/* flush task's r2t queues */
	while (__kfifo_get(tcp_task->r2tqueue, (void*)&r2t, sizeof(void*))) {
		__kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		debug_scsi("iscsi_tcp_cleanup_task pending r2t dropped\n");
	}

	r2t = tcp_task->r2t;
	if (r2t != NULL) {
		__kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		tcp_task->r2t = NULL;
	}
}

/**
 * iscsi_data_rsp - SCSI Data-In Response processing
 * @conn: iscsi connection
 * @task: scsi command task
 **/
static int
iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_task *task)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_tcp_task *tcp_task = task->dd_data;
	struct iscsi_data_rsp *rhdr = (struct iscsi_data_rsp *)tcp_conn->in.hdr;
	struct iscsi_session *session = conn->session;
	struct scsi_cmnd *sc = task->sc;
	int datasn = be32_to_cpu(rhdr->datasn);
	unsigned total_in_length = scsi_in(sc)->length;

	iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr);
	if (tcp_conn->in.datalen == 0)
		return 0;

	if (tcp_task->exp_datasn != datasn) {
		debug_tcp("%s: task->exp_datasn(%d) != rhdr->datasn(%d)\n",
		          __func__, tcp_task->exp_datasn, datasn);
		return ISCSI_ERR_DATASN;
	}

	tcp_task->exp_datasn++;

	tcp_task->data_offset = be32_to_cpu(rhdr->offset);
	if (tcp_task->data_offset + tcp_conn->in.datalen > total_in_length) {
		debug_tcp("%s: data_offset(%d) + data_len(%d) > total_length_in(%d)\n",
		          __func__, tcp_task->data_offset,
		          tcp_conn->in.datalen, total_in_length);
		return ISCSI_ERR_DATA_OFFSET;
	}

	if (rhdr->flags & ISCSI_FLAG_DATA_STATUS) {
		sc->result = (DID_OK << 16) | rhdr->cmd_status;
		conn->exp_statsn = be32_to_cpu(rhdr->statsn) + 1;
		if (rhdr->flags & (ISCSI_FLAG_DATA_UNDERFLOW |
		                   ISCSI_FLAG_DATA_OVERFLOW)) {
			int res_count = be32_to_cpu(rhdr->residual_count);

			if (res_count > 0 &&
			    (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW ||
			     res_count <= total_in_length))
				scsi_in(sc)->resid = res_count;
			else
				sc->result = (DID_BAD_TARGET << 16) |
					rhdr->cmd_status;
		}
	}

	conn->datain_pdus_cnt++;
	return 0;
}

/**
 * iscsi_solicit_data_init - initialize first Data-Out
 * @conn: iscsi connection
 * @task: scsi command task
 * @r2t: R2T info
 *
 * Notes:
 *	Initialize first Data-Out within this R2T sequence and finds
 *	proper data_offset within this SCSI command.
 *
 *	This function is called with connection lock taken.
 **/
static void
iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_task *task,
			struct iscsi_r2t_info *r2t)
{
	struct iscsi_data *hdr;

	hdr = &r2t->dtask.hdr;
	memset(hdr, 0, sizeof(struct iscsi_data));
	hdr->ttt = r2t->ttt;
	hdr->datasn = cpu_to_be32(r2t->solicit_datasn);
	r2t->solicit_datasn++;
	hdr->opcode = ISCSI_OP_SCSI_DATA_OUT;
	memcpy(hdr->lun, task->hdr->lun, sizeof(hdr->lun));
	hdr->itt = task->hdr->itt;
	hdr->exp_statsn = r2t->exp_statsn;
	hdr->offset = cpu_to_be32(r2t->data_offset);
	if (r2t->data_length > conn->max_xmit_dlength) {
		hton24(hdr->dlength, conn->max_xmit_dlength);
		r2t->data_count = conn->max_xmit_dlength;
		hdr->flags = 0;
	} else {
		hton24(hdr->dlength, r2t->data_length);
		r2t->data_count = r2t->data_length;
		hdr->flags = ISCSI_FLAG_CMD_FINAL;
	}
	conn->dataout_pdus_cnt++;

	r2t->sent = 0;
}

/**
 * iscsi_r2t_rsp - iSCSI R2T Response processing
 * @conn: iscsi connection
 * @task: scsi command task
 **/
static int
iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task)
{
	struct iscsi_r2t_info *r2t;
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_task *tcp_task = task->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_r2t_rsp *rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr;
	int r2tsn = be32_to_cpu(rhdr->r2tsn);
	int rc;

	if (tcp_conn->in.datalen) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "invalid R2t with datalen %d\n",
				  tcp_conn->in.datalen);
		return ISCSI_ERR_DATALEN;
	}

	if (tcp_task->exp_datasn != r2tsn){
		debug_tcp("%s: task->exp_datasn(%d) != rhdr->r2tsn(%d)\n",
		          __func__, tcp_task->exp_datasn, r2tsn);
		return ISCSI_ERR_R2TSN;
	}

	/* fill-in new R2T associated with the task */
	iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr);

	if (!task->sc || session->state != ISCSI_STATE_LOGGED_IN) {
		iscsi_conn_printk(KERN_INFO, conn,
				  "dropping R2T itt %d in recovery.\n",
				  task->itt);
		return 0;
	}

	rc = __kfifo_get(tcp_task->r2tpool.queue, (void*)&r2t, sizeof(void*));
	BUG_ON(!rc);

	r2t->exp_statsn = rhdr->statsn;
	r2t->data_length = be32_to_cpu(rhdr->data_length);
	if (r2t->data_length == 0) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "invalid R2T with zero data len\n");
		__kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		return ISCSI_ERR_DATALEN;
	}

	if (r2t->data_length > session->max_burst)
		debug_scsi("invalid R2T with data len %u and max burst %u."
			   "Attempting to execute request.\n",
			    r2t->data_length, session->max_burst);

	r2t->data_offset = be32_to_cpu(rhdr->data_offset);
	if (r2t->data_offset + r2t->data_length > scsi_out(task->sc)->length) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "invalid R2T with data len %u at offset %u "
				  "and total length %d\n", r2t->data_length,
				  r2t->data_offset, scsi_out(task->sc)->length);
		__kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		return ISCSI_ERR_DATALEN;
	}

	r2t->ttt = rhdr->ttt; /* no flip */
	r2t->solicit_datasn = 0;

	iscsi_solicit_data_init(conn, task, r2t);

	tcp_task->exp_datasn = r2tsn + 1;
	__kfifo_put(tcp_task->r2tqueue, (void*)&r2t, sizeof(void*));
	conn->r2t_pdus_cnt++;

	iscsi_requeue_task(task);
	return 0;
}

/*
 * Handle incoming reply to DataIn command
 */
static int
iscsi_tcp_process_data_in(struct iscsi_tcp_conn *tcp_conn,
			  struct iscsi_segment *segment)
{
	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
	struct iscsi_hdr *hdr = tcp_conn->in.hdr;
	int rc;

	if (!iscsi_tcp_dgst_verify(tcp_conn, segment))
		return ISCSI_ERR_DATA_DGST;

	/* check for non-exceptional status */
	if (hdr->flags & ISCSI_FLAG_DATA_STATUS) {
		rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, NULL, 0);
		if (rc)
			return rc;
	}

	iscsi_tcp_hdr_recv_prep(tcp_conn);
	return 0;
}

/**
 * iscsi_tcp_hdr_dissect - process PDU header
 * @conn: iSCSI connection
 * @hdr: PDU header
 *
 * This function analyzes the header of the PDU received,
 * and performs several sanity checks. If the PDU is accompanied
 * by data, the receive buffer is set up to copy the incoming data
 * to the correct location.
 */
static int
iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
{
	int rc = 0, opcode, ahslen;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_task *task;

	/* verify PDU length */
	tcp_conn->in.datalen = ntoh24(hdr->dlength);
	if (tcp_conn->in.datalen > conn->max_recv_dlength) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "iscsi_tcp: datalen %d > %d\n",
				  tcp_conn->in.datalen, conn->max_recv_dlength);
		return ISCSI_ERR_DATALEN;
	}

	/* Additional header segments. So far, we don't
	 * process additional headers.
	 */
	ahslen = hdr->hlength << 2;

	opcode = hdr->opcode & ISCSI_OPCODE_MASK;
	/* verify itt (itt encoding: age+cid+itt) */
	rc = iscsi_verify_itt(conn, hdr->itt);
	if (rc)
		return rc;

	debug_tcp("opcode 0x%x ahslen %d datalen %d\n",
		  opcode, ahslen, tcp_conn->in.datalen);

	switch(opcode) {
	case ISCSI_OP_SCSI_DATA_IN:
		spin_lock(&conn->session->lock);
		task = iscsi_itt_to_ctask(conn, hdr->itt);
		if (!task)
			rc = ISCSI_ERR_BAD_ITT;
		else
			rc = iscsi_data_rsp(conn, task);
		if (rc) {
			spin_unlock(&conn->session->lock);
			break;
		}

		if (tcp_conn->in.datalen) {
			struct iscsi_tcp_task *tcp_task = task->dd_data;
			struct hash_desc *rx_hash = NULL;
			struct scsi_data_buffer *sdb = scsi_in(task->sc);

			/*
			 * Setup copy of Data-In into the Scsi_Cmnd
			 * Scatterlist case:
			 * We set up the iscsi_segment to point to the next
			 * scatterlist entry to copy to. As we go along,
			 * we move on to the next scatterlist entry and
			 * update the digest per-entry.
			 */
			if (conn->datadgst_en)
				rx_hash = &tcp_conn->rx_hash;

			debug_tcp("iscsi_tcp_begin_data_in(%p, offset=%d, "
				  "datalen=%d)\n", tcp_conn,
				  tcp_task->data_offset,
				  tcp_conn->in.datalen);
			rc = iscsi_segment_seek_sg(&tcp_conn->in.segment,
						   sdb->table.sgl,
						   sdb->table.nents,
						   tcp_task->data_offset,
						   tcp_conn->in.datalen,
						   iscsi_tcp_process_data_in,
						   rx_hash);
			spin_unlock(&conn->session->lock);
			return rc;
		}
		rc = __iscsi_complete_pdu(conn, hdr, NULL, 0);
		spin_unlock(&conn->session->lock);
		break;
	case ISCSI_OP_SCSI_CMD_RSP:
		if (tcp_conn->in.datalen) {
			iscsi_tcp_data_recv_prep(tcp_conn);
			return 0;
		}
		rc = iscsi_complete_pdu(conn, hdr, NULL, 0);
		break;
	case ISCSI_OP_R2T:
		spin_lock(&conn->session->lock);
		task = iscsi_itt_to_ctask(conn, hdr->itt);
		if (!task)
			rc = ISCSI_ERR_BAD_ITT;
		else if (ahslen)
			rc = ISCSI_ERR_AHSLEN;
		else if (task->sc->sc_data_direction == DMA_TO_DEVICE)
			rc = iscsi_r2t_rsp(conn, task);
		else
			rc = ISCSI_ERR_PROTO;
		spin_unlock(&conn->session->lock);
		break;
	case ISCSI_OP_LOGIN_RSP:
	case ISCSI_OP_TEXT_RSP:
	case ISCSI_OP_REJECT:
	case ISCSI_OP_ASYNC_EVENT:
		/*
		 * It is possible that we could get a PDU with a buffer larger
		 * than 8K, but there are no targets that currently do this.
		 * For now we fail until we find a vendor that needs it
		 */
		if (ISCSI_DEF_MAX_RECV_SEG_LEN < tcp_conn->in.datalen) {
			iscsi_conn_printk(KERN_ERR, conn,
					  "iscsi_tcp: received buffer of "
					  "len %u but conn buffer is only %u "
					  "(opcode %0x)\n",
					  tcp_conn->in.datalen,
					  ISCSI_DEF_MAX_RECV_SEG_LEN, opcode);
			rc = ISCSI_ERR_PROTO;
			break;
		}

		/* If there's data coming in with the response,
		 * receive it to the connection's buffer.
		 */
		if (tcp_conn->in.datalen) {
			iscsi_tcp_data_recv_prep(tcp_conn);
			return 0;
		}
	/* fall through */
	case ISCSI_OP_LOGOUT_RSP:
	case ISCSI_OP_NOOP_IN:
	case ISCSI_OP_SCSI_TMFUNC_RSP:
		rc = iscsi_complete_pdu(conn, hdr, NULL, 0);
		break;
	default:
		rc = ISCSI_ERR_BAD_OPCODE;
		break;
	}

	if (rc == 0) {
		/* Anything that comes with data should have
		 * been handled above. */
		if (tcp_conn->in.datalen)
			return ISCSI_ERR_PROTO;
		iscsi_tcp_hdr_recv_prep(tcp_conn);
	}

	return rc;
}

/**
 * iscsi_tcp_hdr_recv_done - process PDU header
 *
 * This is the callback invoked when the PDU header has
 * been received. If the header is followed by additional
 * header segments, we go back for more data.
 */
static int
iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn,
			struct iscsi_segment *segment)
{
	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
	struct iscsi_hdr *hdr;

	/* Check if there are additional header segments
	 * *prior* to computing the digest, because we
	 * may need to go back to the caller for more.
	 */
	hdr = (struct iscsi_hdr *) tcp_conn->in.hdr_buf;
	if (segment->copied == sizeof(struct iscsi_hdr) && hdr->hlength) {
		/* Bump the header length - the caller will
		 * just loop around and get the AHS for us, and
		 * call again. */
		unsigned int ahslen = hdr->hlength << 2;

		/* Make sure we don't overflow */
		if (sizeof(*hdr) + ahslen > sizeof(tcp_conn->in.hdr_buf))
			return ISCSI_ERR_AHSLEN;

		segment->total_size += ahslen;
		segment->size += ahslen;
		return 0;
	}

	/* We're done processing the header. See if we're doing
	 * header digests; if so, set up the recv_digest buffer
	 * and go back for more. */
	if (conn->hdrdgst_en) {
		if (segment->digest_len == 0) {
			iscsi_tcp_segment_splice_digest(segment,
							segment->recv_digest);
			return 0;
		}
		iscsi_tcp_dgst_header(&tcp_conn->rx_hash, hdr,
				      segment->total_copied - ISCSI_DIGEST_SIZE,
				      segment->digest);

		if (!iscsi_tcp_dgst_verify(tcp_conn, segment))
			return ISCSI_ERR_HDR_DGST;
	}

	tcp_conn->in.hdr = hdr;
	return iscsi_tcp_hdr_dissect(conn, hdr);
}

/**
 * iscsi_tcp_recv - TCP receive in sendfile fashion
 * @rd_desc: read descriptor
 * @skb: socket buffer
 * @offset: offset in skb
 * @len: skb->len - offset
 **/
static int
iscsi_tcp_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
	       unsigned int offset, size_t len)
{
	struct iscsi_conn *conn = rd_desc->arg.data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_segment *segment = &tcp_conn->in.segment;
	struct skb_seq_state seq;
	unsigned int consumed = 0;
	int rc = 0;

	debug_tcp("in %d bytes\n", skb->len - offset);

	if (unlikely(conn->suspend_rx)) {
		debug_tcp("conn %d Rx suspended!\n", conn->id);
		return 0;
	}

	skb_prepare_seq_read(skb, offset, skb->len, &seq);
	while (1) {
		unsigned int avail;
		const u8 *ptr;

		avail = skb_seq_read(consumed, &ptr, &seq);
		if (avail == 0) {
			debug_tcp("no more data avail. Consumed %d\n",
				  consumed);
			break;
		}
		BUG_ON(segment->copied >= segment->size);

		debug_tcp("skb %p ptr=%p avail=%u\n", skb, ptr, avail);
		rc = iscsi_tcp_segment_recv(tcp_conn, segment, ptr, avail);
		BUG_ON(rc == 0);
		consumed += rc;

		if (segment->total_copied >= segment->total_size) {
			debug_tcp("segment done\n");
			rc = segment->done(tcp_conn, segment);
			if (rc != 0) {
				skb_abort_seq_read(&seq);
				goto error;
			}

			/* The done() functions sets up the
			 * next segment. */
		}
	}
	skb_abort_seq_read(&seq);
	conn->rxdata_octets += consumed;
	return consumed;

error:
	debug_tcp("Error receiving PDU, errno=%d\n", rc);
	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	return 0;
}

static void
iscsi_tcp_data_ready(struct sock *sk, int flag)
{
	struct iscsi_conn *conn = sk->sk_user_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	read_descriptor_t rd_desc;

	read_lock(&sk->sk_callback_lock);

	/*
	 * Use rd_desc to pass 'conn' to iscsi_tcp_recv.
	 * We set count to 1 because we want the network layer to
	 * hand us all the skbs that are available. iscsi_tcp_recv
	 * handled pdus that cross buffers or pdus that still need data.
	 */
	rd_desc.arg.data = conn;
	rd_desc.count = 1;
	tcp_read_sock(sk, &rd_desc, iscsi_tcp_recv);

	read_unlock(&sk->sk_callback_lock);

	/* If we had to (atomically) map a highmem page,
	 * unmap it now. */
	iscsi_tcp_segment_unmap(&tcp_conn->in.segment);
}

static void
iscsi_tcp_state_change(struct sock *sk)
{
	struct iscsi_tcp_conn *tcp_conn;
	struct iscsi_conn *conn;
	struct iscsi_session *session;
	void (*old_state_change)(struct sock *);

	read_lock(&sk->sk_callback_lock);

	conn = (struct iscsi_conn*)sk->sk_user_data;
	session = conn->session;

	if ((sk->sk_state == TCP_CLOSE_WAIT ||
	     sk->sk_state == TCP_CLOSE) &&
	    !atomic_read(&sk->sk_rmem_alloc)) {
		debug_tcp("iscsi_tcp_state_change: TCP_CLOSE|TCP_CLOSE_WAIT\n");
		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	}

	tcp_conn = conn->dd_data;
	old_state_change = tcp_conn->old_state_change;

	read_unlock(&sk->sk_callback_lock);

	old_state_change(sk);
}

/**
 * iscsi_write_space - Called when more output buffer space is available
 * @sk: socket space is available for
 **/
static void
iscsi_write_space(struct sock *sk)
{
	struct iscsi_conn *conn = (struct iscsi_conn*)sk->sk_user_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	tcp_conn->old_write_space(sk);
	debug_tcp("iscsi_write_space: cid %d\n", conn->id);
	scsi_queue_work(conn->session->host, &conn->xmitwork);
}

static void
iscsi_conn_set_callbacks(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct sock *sk = tcp_conn->sock->sk;

	/* assign new callbacks */
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_user_data = conn;
	tcp_conn->old_data_ready = sk->sk_data_ready;
	tcp_conn->old_state_change = sk->sk_state_change;
	tcp_conn->old_write_space = sk->sk_write_space;
	sk->sk_data_ready = iscsi_tcp_data_ready;
	sk->sk_state_change = iscsi_tcp_state_change;
	sk->sk_write_space = iscsi_write_space;
	write_unlock_bh(&sk->sk_callback_lock);
}

static void
iscsi_conn_restore_callbacks(struct iscsi_tcp_conn *tcp_conn)
{
	struct sock *sk = tcp_conn->sock->sk;

	/* restore socket callbacks, see also: iscsi_conn_set_callbacks() */
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_user_data    = NULL;
	sk->sk_data_ready   = tcp_conn->old_data_ready;
	sk->sk_state_change = tcp_conn->old_state_change;
	sk->sk_write_space  = tcp_conn->old_write_space;
	sk->sk_no_check	 = 0;
	write_unlock_bh(&sk->sk_callback_lock);
}

/**
 * iscsi_xmit - TCP transmit
 **/
static int
iscsi_xmit(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_segment *segment = &tcp_conn->out.segment;
	unsigned int consumed = 0;
	int rc = 0;

	while (1) {
		rc = iscsi_tcp_xmit_segment(tcp_conn, segment);
		if (rc < 0)
			goto error;
		if (rc == 0)
			break;

		consumed += rc;

		if (segment->total_copied >= segment->total_size) {
			if (segment->done != NULL) {
				rc = segment->done(tcp_conn, segment);
				if (rc < 0)
					goto error;
			}
		}
	}

	debug_tcp("xmit %d bytes\n", consumed);

	conn->txdata_octets += consumed;
	return consumed;

error:
	/* Transmit error. We could initiate error recovery
	 * here. */
	debug_tcp("Error sending PDU, errno=%d\n", rc);
	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
	return rc;
}

/**
 * iscsi_tcp_xmit_qlen - return the number of bytes queued for xmit
 */
static inline int
iscsi_tcp_xmit_qlen(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_segment *segment = &tcp_conn->out.segment;

	return segment->total_copied - segment->total_size;
}

static inline int
iscsi_tcp_flush(struct iscsi_conn *conn)
{
	int rc;

	while (iscsi_tcp_xmit_qlen(conn)) {
		rc = iscsi_xmit(conn);
		if (rc == 0)
			return -EAGAIN;
		if (rc < 0)
			return rc;
	}

	return 0;
}

/*
 * This is called when we're done sending the header.
 * Simply copy the data_segment to the send segment, and return.
 */
static int
iscsi_tcp_send_hdr_done(struct iscsi_tcp_conn *tcp_conn,
			struct iscsi_segment *segment)
{
	tcp_conn->out.segment = tcp_conn->out.data_segment;
	debug_tcp("Header done. Next segment size %u total_size %u\n",
		  tcp_conn->out.segment.size, tcp_conn->out.segment.total_size);
	return 0;
}

static void
iscsi_tcp_send_hdr_prep(struct iscsi_conn *conn, void *hdr, size_t hdrlen)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	debug_tcp("%s(%p%s)\n", __func__, tcp_conn,
			conn->hdrdgst_en? ", digest enabled" : "");

	/* Clear the data segment - needs to be filled in by the
	 * caller using iscsi_tcp_send_data_prep() */
	memset(&tcp_conn->out.data_segment, 0, sizeof(struct iscsi_segment));

	/* If header digest is enabled, compute the CRC and
	 * place the digest into the same buffer. We make
	 * sure that both iscsi_tcp_task and mtask have
	 * sufficient room.
	 */
	if (conn->hdrdgst_en) {
		iscsi_tcp_dgst_header(&tcp_conn->tx_hash, hdr, hdrlen,
				      hdr + hdrlen);
		hdrlen += ISCSI_DIGEST_SIZE;
	}

	/* Remember header pointer for later, when we need
	 * to decide whether there's a payload to go along
	 * with the header. */
	tcp_conn->out.hdr = hdr;

	iscsi_segment_init_linear(&tcp_conn->out.segment, hdr, hdrlen,
				iscsi_tcp_send_hdr_done, NULL);
}

/*
 * Prepare the send buffer for the payload data.
 * Padding and checksumming will all be taken care
 * of by the iscsi_segment routines.
 */
static int
iscsi_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg,
			 unsigned int count, unsigned int offset,
			 unsigned int len)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct hash_desc *tx_hash = NULL;
	unsigned int hdr_spec_len;

	debug_tcp("%s(%p, offset=%d, datalen=%d%s)\n", __func__,
			tcp_conn, offset, len,
			conn->datadgst_en? ", digest enabled" : "");

	/* Make sure the datalen matches what the caller
	   said he would send. */
	hdr_spec_len = ntoh24(tcp_conn->out.hdr->dlength);
	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));

	if (conn->datadgst_en)
		tx_hash = &tcp_conn->tx_hash;

	return iscsi_segment_seek_sg(&tcp_conn->out.data_segment,
				   sg, count, offset, len,
				   NULL, tx_hash);
}

static void
iscsi_tcp_send_linear_data_prepare(struct iscsi_conn *conn, void *data,
				   size_t len)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct hash_desc *tx_hash = NULL;
	unsigned int hdr_spec_len;

	debug_tcp("%s(%p, datalen=%d%s)\n", __func__, tcp_conn, len,
		  conn->datadgst_en? ", digest enabled" : "");

	/* Make sure the datalen matches what the caller
	   said he would send. */
	hdr_spec_len = ntoh24(tcp_conn->out.hdr->dlength);
	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));

	if (conn->datadgst_en)
		tx_hash = &tcp_conn->tx_hash;

	iscsi_segment_init_linear(&tcp_conn->out.data_segment,
				data, len, NULL, tx_hash);
}

/**
 * iscsi_solicit_data_cont - initialize next Data-Out
 * @conn: iscsi connection
 * @task: scsi command task
 * @r2t: R2T info
 * @left: bytes left to transfer
 *
 * Notes:
 *	Initialize next Data-Out within this R2T sequence and continue
 *	to process next Scatter-Gather element(if any) of this SCSI command.
 *
 *	Called under connection lock.
 **/
static int
iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_task *task,
			struct iscsi_r2t_info *r2t)
{
	struct iscsi_data *hdr;
	int new_offset, left;

	BUG_ON(r2t->data_length - r2t->sent < 0);
	left = r2t->data_length - r2t->sent;
	if (left == 0)
		return 0;

	hdr = &r2t->dtask.hdr;
	memset(hdr, 0, sizeof(struct iscsi_data));
	hdr->ttt = r2t->ttt;
	hdr->datasn = cpu_to_be32(r2t->solicit_datasn);
	r2t->solicit_datasn++;
	hdr->opcode = ISCSI_OP_SCSI_DATA_OUT;
	memcpy(hdr->lun, task->hdr->lun, sizeof(hdr->lun));
	hdr->itt = task->hdr->itt;
	hdr->exp_statsn = r2t->exp_statsn;
	new_offset = r2t->data_offset + r2t->sent;
	hdr->offset = cpu_to_be32(new_offset);
	if (left > conn->max_xmit_dlength) {
		hton24(hdr->dlength, conn->max_xmit_dlength);
		r2t->data_count = conn->max_xmit_dlength;
	} else {
		hton24(hdr->dlength, left);
		r2t->data_count = left;
		hdr->flags = ISCSI_FLAG_CMD_FINAL;
	}

	conn->dataout_pdus_cnt++;
	return 1;
}

/**
 * iscsi_tcp_task - Initialize iSCSI SCSI_READ or SCSI_WRITE commands
 * @conn: iscsi connection
 * @task: scsi command task
 * @sc: scsi command
 **/
static int
iscsi_tcp_task_init(struct iscsi_task *task)
{
	struct iscsi_tcp_task *tcp_task = task->dd_data;
	struct iscsi_conn *conn = task->conn;
	struct scsi_cmnd *sc = task->sc;
	int err;

	if (!sc) {
		/*
		 * mgmt tasks do not have a scatterlist since they come
		 * in from the iscsi interface.
		 */
		debug_scsi("mtask deq [cid %d itt 0x%x]\n", conn->id,
			   task->itt);

		/* Prepare PDU, optionally w/ immediate data */
		iscsi_tcp_send_hdr_prep(conn, task->hdr, sizeof(*task->hdr));

		/* If we have immediate data, attach a payload */
		if (task->data_count)
			iscsi_tcp_send_linear_data_prepare(conn, task->data,
							   task->data_count);
		return 0;
	}

	BUG_ON(__kfifo_len(tcp_task->r2tqueue));
	tcp_task->sent = 0;
	tcp_task->exp_datasn = 0;

	/* Prepare PDU, optionally w/ immediate data */
	debug_scsi("task deq [cid %d itt 0x%x imm %d unsol %d]\n",
		    conn->id, task->itt, task->imm_count,
		    task->unsol_count);
	iscsi_tcp_send_hdr_prep(conn, task->hdr, task->hdr_len);

	if (!task->imm_count)
		return 0;

	/* If we have immediate data, attach a payload */
	err = iscsi_tcp_send_data_prep(conn, scsi_out(sc)->table.sgl,
				       scsi_out(sc)->table.nents,
				       0, task->imm_count);
	if (err)
		return err;
	tcp_task->sent += task->imm_count;
	task->imm_count = 0;
	return 0;
}

/*
 * iscsi_tcp_task_xmit - xmit normal PDU task
 * @task: iscsi command task
 *
 * We're expected to return 0 when everything was transmitted succesfully,
 * -EAGAIN if there's still data in the queue, or != 0 for any other kind
 * of error.
 */
static int
iscsi_tcp_task_xmit(struct iscsi_task *task)
{
	struct iscsi_conn *conn = task->conn;
	struct iscsi_tcp_task *tcp_task = task->dd_data;
	struct scsi_cmnd *sc = task->sc;
	struct scsi_data_buffer *sdb;
	int rc = 0;

flush:
	/* Flush any pending data first. */
	rc = iscsi_tcp_flush(conn);
	if (rc < 0)
		return rc;

	/* mgmt command */
	if (!sc) {
		if (task->hdr->itt == RESERVED_ITT)
			iscsi_put_task(task);
		return 0;
	}

	/* Are we done already? */
	if (sc->sc_data_direction != DMA_TO_DEVICE)
		return 0;

	sdb = scsi_out(sc);
	if (task->unsol_count != 0) {
		struct iscsi_data *hdr = &tcp_task->unsol_dtask.hdr;

		/* Prepare a header for the unsolicited PDU.
		 * The amount of data we want to send will be
		 * in task->data_count.
		 * FIXME: return the data count instead.
		 */
		iscsi_prep_unsolicit_data_pdu(task, hdr);

		debug_tcp("unsol dout [itt 0x%x doff %d dlen %d]\n",
				task->itt, tcp_task->sent, task->data_count);

		iscsi_tcp_send_hdr_prep(conn, hdr, sizeof(*hdr));
		rc = iscsi_tcp_send_data_prep(conn, sdb->table.sgl,
					      sdb->table.nents, tcp_task->sent,
					      task->data_count);
		if (rc)
			goto fail;
		tcp_task->sent += task->data_count;
		task->unsol_count -= task->data_count;
		goto flush;
	} else {
		struct iscsi_session *session = conn->session;
		struct iscsi_r2t_info *r2t;

		/* All unsolicited PDUs sent. Check for solicited PDUs.
		 */
		spin_lock_bh(&session->lock);
		r2t = tcp_task->r2t;
		if (r2t != NULL) {
			/* Continue with this R2T? */
			if (!iscsi_solicit_data_cont(conn, task, r2t)) {
				debug_scsi("  done with r2t %p\n", r2t);

				__kfifo_put(tcp_task->r2tpool.queue,
					    (void*)&r2t, sizeof(void*));
				tcp_task->r2t = r2t = NULL;
			}
		}

		if (r2t == NULL) {
			__kfifo_get(tcp_task->r2tqueue, (void*)&tcp_task->r2t,
				    sizeof(void*));
			r2t = tcp_task->r2t;
		}
		spin_unlock_bh(&session->lock);

		/* Waiting for more R2Ts to arrive. */
		if (r2t == NULL) {
			debug_tcp("no R2Ts yet\n");
			return 0;
		}

		debug_scsi("sol dout %p [dsn %d itt 0x%x doff %d dlen %d]\n",
			r2t, r2t->solicit_datasn - 1, task->itt,
			r2t->data_offset + r2t->sent, r2t->data_count);

		iscsi_tcp_send_hdr_prep(conn, &r2t->dtask.hdr,
					sizeof(struct iscsi_hdr));

		rc = iscsi_tcp_send_data_prep(conn, sdb->table.sgl,
					      sdb->table.nents,
					      r2t->data_offset + r2t->sent,
					      r2t->data_count);
		if (rc)
			goto fail;
		tcp_task->sent += r2t->data_count;
		r2t->sent += r2t->data_count;
		goto flush;
	}
	return 0;
fail:
	iscsi_conn_failure(conn, rc);
	return -EIO;
}

static struct iscsi_cls_conn *
iscsi_tcp_conn_create(struct iscsi_cls_session *cls_session, uint32_t conn_idx)
{
	struct iscsi_conn *conn;
	struct iscsi_cls_conn *cls_conn;
	struct iscsi_tcp_conn *tcp_conn;

	cls_conn = iscsi_conn_setup(cls_session, sizeof(*tcp_conn), conn_idx);
	if (!cls_conn)
		return NULL;
	conn = cls_conn->dd_data;
	/*
	 * due to strange issues with iser these are not set
	 * in iscsi_conn_setup
	 */
	conn->max_recv_dlength = ISCSI_DEF_MAX_RECV_SEG_LEN;

	tcp_conn = conn->dd_data;
	tcp_conn->iscsi_conn = conn;

	tcp_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						  CRYPTO_ALG_ASYNC);
	tcp_conn->tx_hash.flags = 0;
	if (IS_ERR(tcp_conn->tx_hash.tfm))
		goto free_conn;

	tcp_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
						  CRYPTO_ALG_ASYNC);
	tcp_conn->rx_hash.flags = 0;
	if (IS_ERR(tcp_conn->rx_hash.tfm))
		goto free_tx_tfm;

	return cls_conn;

free_tx_tfm:
	crypto_free_hash(tcp_conn->tx_hash.tfm);
free_conn:
	iscsi_conn_printk(KERN_ERR, conn,
			  "Could not create connection due to crc32c "
			  "loading error. Make sure the crc32c "
			  "module is built as a module or into the "
			  "kernel\n");
	iscsi_conn_teardown(cls_conn);
	return NULL;
}

static void
iscsi_tcp_release_conn(struct iscsi_conn *conn)
{
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct socket *sock = tcp_conn->sock;

	if (!sock)
		return;

	sock_hold(sock->sk);
	iscsi_conn_restore_callbacks(tcp_conn);
	sock_put(sock->sk);

	spin_lock_bh(&session->lock);
	tcp_conn->sock = NULL;
	spin_unlock_bh(&session->lock);
	sockfd_put(sock);
}

static void
iscsi_tcp_conn_destroy(struct iscsi_cls_conn *cls_conn)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	iscsi_tcp_release_conn(conn);

	if (tcp_conn->tx_hash.tfm)
		crypto_free_hash(tcp_conn->tx_hash.tfm);
	if (tcp_conn->rx_hash.tfm)
		crypto_free_hash(tcp_conn->rx_hash.tfm);

	iscsi_conn_teardown(cls_conn);
}

static void
iscsi_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	/* userspace may have goofed up and not bound us */
	if (!tcp_conn->sock)
		return;
	/*
	 * Make sure our recv side is stopped.
	 * Older tools called conn stop before ep_disconnect
	 * so IO could still be coming in.
	 */
	write_lock_bh(&tcp_conn->sock->sk->sk_callback_lock);
	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx);
	write_unlock_bh(&tcp_conn->sock->sk->sk_callback_lock);

	iscsi_conn_stop(cls_conn, flag);
	iscsi_tcp_release_conn(conn);
}

static int iscsi_tcp_get_addr(struct iscsi_conn *conn, struct socket *sock,
			      char *buf, int *port,
			      int (*getname)(struct socket *, struct sockaddr *,
					int *addrlen))
{
	struct sockaddr_storage *addr;
	struct sockaddr_in6 *sin6;
	struct sockaddr_in *sin;
	int rc = 0, len;

	addr = kmalloc(sizeof(*addr), GFP_KERNEL);
	if (!addr)
		return -ENOMEM;

	if (getname(sock, (struct sockaddr *) addr, &len)) {
		rc = -ENODEV;
		goto free_addr;
	}

	switch (addr->ss_family) {
	case AF_INET:
		sin = (struct sockaddr_in *)addr;
		spin_lock_bh(&conn->session->lock);
		sprintf(buf, NIPQUAD_FMT, NIPQUAD(sin->sin_addr.s_addr));
		*port = be16_to_cpu(sin->sin_port);
		spin_unlock_bh(&conn->session->lock);
		break;
	case AF_INET6:
		sin6 = (struct sockaddr_in6 *)addr;
		spin_lock_bh(&conn->session->lock);
		sprintf(buf, NIP6_FMT, NIP6(sin6->sin6_addr));
		*port = be16_to_cpu(sin6->sin6_port);
		spin_unlock_bh(&conn->session->lock);
		break;
	}
free_addr:
	kfree(addr);
	return rc;
}

static int
iscsi_tcp_conn_bind(struct iscsi_cls_session *cls_session,
		    struct iscsi_cls_conn *cls_conn, uint64_t transport_eph,
		    int is_leading)
{
	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
	struct iscsi_host *ihost = shost_priv(shost);
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct sock *sk;
	struct socket *sock;
	int err;

	/* lookup for existing socket */
	sock = sockfd_lookup((int)transport_eph, &err);
	if (!sock) {
		iscsi_conn_printk(KERN_ERR, conn,
				  "sockfd_lookup failed %d\n", err);
		return -EEXIST;
	}
	/*
	 * copy these values now because if we drop the session
	 * userspace may still want to query the values since we will
	 * be using them for the reconnect
	 */
	err = iscsi_tcp_get_addr(conn, sock, conn->portal_address,
				 &conn->portal_port, kernel_getpeername);
	if (err)
		goto free_socket;

	err = iscsi_tcp_get_addr(conn, sock, ihost->local_address,
				&ihost->local_port, kernel_getsockname);
	if (err)
		goto free_socket;

	err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
	if (err)
		goto free_socket;

	/* bind iSCSI connection and socket */
	tcp_conn->sock = sock;

	/* setup Socket parameters */
	sk = sock->sk;
	sk->sk_reuse = 1;
	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
	sk->sk_allocation = GFP_ATOMIC;

	iscsi_conn_set_callbacks(conn);
	tcp_conn->sendpage = tcp_conn->sock->ops->sendpage;
	/*
	 * set receive state machine into initial state
	 */
	iscsi_tcp_hdr_recv_prep(tcp_conn);
	return 0;

free_socket:
	sockfd_put(sock);
	return err;
}

static int
iscsi_r2tpool_alloc(struct iscsi_session *session)
{
	int i;
	int cmd_i;

	/*
	 * initialize per-task: R2T pool and xmit queue
	 */
	for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) {
	        struct iscsi_task *task = session->cmds[cmd_i];
		struct iscsi_tcp_task *tcp_task = task->dd_data;

		/*
		 * pre-allocated x4 as much r2ts to handle race when
		 * target acks DataOut faster than we data_xmit() queues
		 * could replenish r2tqueue.
		 */

		/* R2T pool */
		if (iscsi_pool_init(&tcp_task->r2tpool, session->max_r2t * 4, NULL,
				    sizeof(struct iscsi_r2t_info))) {
			goto r2t_alloc_fail;
		}

		/* R2T xmit queue */
		tcp_task->r2tqueue = kfifo_alloc(
		      session->max_r2t * 4 * sizeof(void*), GFP_KERNEL, NULL);
		if (tcp_task->r2tqueue == ERR_PTR(-ENOMEM)) {
			iscsi_pool_free(&tcp_task->r2tpool);
			goto r2t_alloc_fail;
		}
	}

	return 0;

r2t_alloc_fail:
	for (i = 0; i < cmd_i; i++) {
		struct iscsi_task *task = session->cmds[i];
		struct iscsi_tcp_task *tcp_task = task->dd_data;

		kfifo_free(tcp_task->r2tqueue);
		iscsi_pool_free(&tcp_task->r2tpool);
	}
	return -ENOMEM;
}

static void
iscsi_r2tpool_free(struct iscsi_session *session)
{
	int i;

	for (i = 0; i < session->cmds_max; i++) {
		struct iscsi_task *task = session->cmds[i];
		struct iscsi_tcp_task *tcp_task = task->dd_data;

		kfifo_free(tcp_task->r2tqueue);
		iscsi_pool_free(&tcp_task->r2tpool);
	}
}

static int
iscsi_conn_set_param(struct iscsi_cls_conn *cls_conn, enum iscsi_param param,
		     char *buf, int buflen)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int value;

	switch(param) {
	case ISCSI_PARAM_HDRDGST_EN:
		iscsi_set_param(cls_conn, param, buf, buflen);
		break;
	case ISCSI_PARAM_DATADGST_EN:
		iscsi_set_param(cls_conn, param, buf, buflen);
		tcp_conn->sendpage = conn->datadgst_en ?
			sock_no_sendpage : tcp_conn->sock->ops->sendpage;
		break;
	case ISCSI_PARAM_MAX_R2T:
		sscanf(buf, "%d", &value);
		if (value <= 0 || !is_power_of_2(value))
			return -EINVAL;
		if (session->max_r2t == value)
			break;
		iscsi_r2tpool_free(session);
		iscsi_set_param(cls_conn, param, buf, buflen);
		if (iscsi_r2tpool_alloc(session))
			return -ENOMEM;
		break;
	default:
		return iscsi_set_param(cls_conn, param, buf, buflen);
	}

	return 0;
}

static int
iscsi_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn,
			 enum iscsi_param param, char *buf)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	int len;

	switch(param) {
	case ISCSI_PARAM_CONN_PORT:
		spin_lock_bh(&conn->session->lock);
		len = sprintf(buf, "%hu\n", conn->portal_port);
		spin_unlock_bh(&conn->session->lock);
		break;
	case ISCSI_PARAM_CONN_ADDRESS:
		spin_lock_bh(&conn->session->lock);
		len = sprintf(buf, "%s\n", conn->portal_address);
		spin_unlock_bh(&conn->session->lock);
		break;
	default:
		return iscsi_conn_get_param(cls_conn, param, buf);
	}

	return len;
}

static void
iscsi_conn_get_stats(struct iscsi_cls_conn *cls_conn, struct iscsi_stats *stats)
{
	struct iscsi_conn *conn = cls_conn->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	stats->txdata_octets = conn->txdata_octets;
	stats->rxdata_octets = conn->rxdata_octets;
	stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
	stats->dataout_pdus = conn->dataout_pdus_cnt;
	stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
	stats->datain_pdus = conn->datain_pdus_cnt;
	stats->r2t_pdus = conn->r2t_pdus_cnt;
	stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
	stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
	stats->custom_length = 3;
	strcpy(stats->custom[0].desc, "tx_sendpage_failures");
	stats->custom[0].value = tcp_conn->sendpage_failures_cnt;
	strcpy(stats->custom[1].desc, "rx_discontiguous_hdr");
	stats->custom[1].value = tcp_conn->discontiguous_hdr_cnt;
	strcpy(stats->custom[2].desc, "eh_abort_cnt");
	stats->custom[2].value = conn->eh_abort_cnt;
}

static struct iscsi_cls_session *
iscsi_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max,
			 uint16_t qdepth, uint32_t initial_cmdsn,
			 uint32_t *hostno)
{
	struct iscsi_cls_session *cls_session;
	struct iscsi_session *session;
	struct Scsi_Host *shost;
	int cmd_i;

	if (ep) {
		printk(KERN_ERR "iscsi_tcp: invalid ep %p.\n", ep);
		return NULL;
	}

	shost = iscsi_host_alloc(&iscsi_sht, 0, qdepth);
	if (!shost)
		return NULL;
	shost->transportt = iscsi_tcp_scsi_transport;
	shost->max_lun = iscsi_max_lun;
	shost->max_id = 0;
	shost->max_channel = 0;
	shost->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE;

	if (iscsi_host_add(shost, NULL))
		goto free_host;
	*hostno = shost->host_no;

	cls_session = iscsi_session_setup(&iscsi_tcp_transport, shost, cmds_max,
					  sizeof(struct iscsi_tcp_task),
					  initial_cmdsn, 0);
	if (!cls_session)
		goto remove_host;
	session = cls_session->dd_data;

	shost->can_queue = session->scsi_cmds_max;
	for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) {
		struct iscsi_task *task = session->cmds[cmd_i];
		struct iscsi_tcp_task *tcp_task = task->dd_data;

		task->hdr = &tcp_task->hdr.cmd_hdr;
		task->hdr_max = sizeof(tcp_task->hdr) - ISCSI_DIGEST_SIZE;
	}

	if (iscsi_r2tpool_alloc(session))
		goto remove_session;
	return cls_session;

remove_session:
	iscsi_session_teardown(cls_session);
remove_host:
	iscsi_host_remove(shost);
free_host:
	iscsi_host_free(shost);
	return NULL;
}

static void iscsi_tcp_session_destroy(struct iscsi_cls_session *cls_session)
{
	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);

	iscsi_r2tpool_free(cls_session->dd_data);

	iscsi_host_remove(shost);
	iscsi_host_free(shost);
}

static int iscsi_tcp_slave_configure(struct scsi_device *sdev)
{
	blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_ANY);
	blk_queue_dma_alignment(sdev->request_queue, 0);
	return 0;
}

static struct scsi_host_template iscsi_sht = {
	.module			= THIS_MODULE,
	.name			= "iSCSI Initiator over TCP/IP",
	.queuecommand           = iscsi_queuecommand,
	.change_queue_depth	= iscsi_change_queue_depth,
	.can_queue		= ISCSI_DEF_XMIT_CMDS_MAX - 1,
	.sg_tablesize		= 4096,
	.max_sectors		= 0xFFFF,
	.cmd_per_lun		= ISCSI_DEF_CMD_PER_LUN,
	.eh_abort_handler       = iscsi_eh_abort,
	.eh_device_reset_handler= iscsi_eh_device_reset,
	.eh_host_reset_handler	= iscsi_eh_host_reset,
	.use_clustering         = DISABLE_CLUSTERING,
	.slave_configure        = iscsi_tcp_slave_configure,
	.proc_name		= "iscsi_tcp",
	.this_id		= -1,
};

static struct iscsi_transport iscsi_tcp_transport = {
	.owner			= THIS_MODULE,
	.name			= "tcp",
	.caps			= CAP_RECOVERY_L0 | CAP_MULTI_R2T | CAP_HDRDGST
				  | CAP_DATADGST,
	.param_mask		= ISCSI_MAX_RECV_DLENGTH |
				  ISCSI_MAX_XMIT_DLENGTH |
				  ISCSI_HDRDGST_EN |
				  ISCSI_DATADGST_EN |
				  ISCSI_INITIAL_R2T_EN |
				  ISCSI_MAX_R2T |
				  ISCSI_IMM_DATA_EN |
				  ISCSI_FIRST_BURST |
				  ISCSI_MAX_BURST |
				  ISCSI_PDU_INORDER_EN |
				  ISCSI_DATASEQ_INORDER_EN |
				  ISCSI_ERL |
				  ISCSI_CONN_PORT |
				  ISCSI_CONN_ADDRESS |
				  ISCSI_EXP_STATSN |
				  ISCSI_PERSISTENT_PORT |
				  ISCSI_PERSISTENT_ADDRESS |
				  ISCSI_TARGET_NAME | ISCSI_TPGT |
				  ISCSI_USERNAME | ISCSI_PASSWORD |
				  ISCSI_USERNAME_IN | ISCSI_PASSWORD_IN |
				  ISCSI_FAST_ABORT | ISCSI_ABORT_TMO |
				  ISCSI_LU_RESET_TMO |
				  ISCSI_PING_TMO | ISCSI_RECV_TMO |
				  ISCSI_IFACE_NAME | ISCSI_INITIATOR_NAME,
	.host_param_mask	= ISCSI_HOST_HWADDRESS | ISCSI_HOST_IPADDRESS |
				  ISCSI_HOST_INITIATOR_NAME |
				  ISCSI_HOST_NETDEV_NAME,
	/* session management */
	.create_session		= iscsi_tcp_session_create,
	.destroy_session	= iscsi_tcp_session_destroy,
	/* connection management */
	.create_conn		= iscsi_tcp_conn_create,
	.bind_conn		= iscsi_tcp_conn_bind,
	.destroy_conn		= iscsi_tcp_conn_destroy,
	.set_param		= iscsi_conn_set_param,
	.get_conn_param		= iscsi_tcp_conn_get_param,
	.get_session_param	= iscsi_session_get_param,
	.start_conn		= iscsi_conn_start,
	.stop_conn		= iscsi_tcp_conn_stop,
	/* iscsi host params */
	.get_host_param		= iscsi_host_get_param,
	.set_host_param		= iscsi_host_set_param,
	/* IO */
	.send_pdu		= iscsi_conn_send_pdu,
	.get_stats		= iscsi_conn_get_stats,
	.init_task		= iscsi_tcp_task_init,
	.xmit_task		= iscsi_tcp_task_xmit,
	.cleanup_task		= iscsi_tcp_cleanup_task,
	/* recovery */
	.session_recovery_timedout = iscsi_session_recovery_timedout,
};

static int __init
iscsi_tcp_init(void)
{
	if (iscsi_max_lun < 1) {
		printk(KERN_ERR "iscsi_tcp: Invalid max_lun value of %u\n",
		       iscsi_max_lun);
		return -EINVAL;
	}

	iscsi_tcp_scsi_transport = iscsi_register_transport(
							&iscsi_tcp_transport);
	if (!iscsi_tcp_scsi_transport)
		return -ENODEV;

	return 0;
}

static void __exit
iscsi_tcp_exit(void)
{
	iscsi_unregister_transport(&iscsi_tcp_transport);
}

module_init(iscsi_tcp_init);
module_exit(iscsi_tcp_exit);