summaryrefslogtreecommitdiffstats
path: root/drivers/ntb/ntb_transport.c
blob: 0f86b60a0c0eeba501d05983e8dbb1907d79e3d2 (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
/*
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 *   redistributing this file, you may do so under either license.
 *
 *   GPL LICENSE SUMMARY
 *
 *   Copyright(c) 2012 Intel Corporation. All rights reserved.
 *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
 *
 *   This program is free software; you can redistribute it and/or modify
 *   it under the terms of version 2 of the GNU General Public License as
 *   published by the Free Software Foundation.
 *
 *   BSD LICENSE
 *
 *   Copyright(c) 2012 Intel Corporation. All rights reserved.
 *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copy
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * PCIe NTB Transport Linux driver
 *
 * Contact Information:
 * Jon Mason <jon.mason@intel.com>
 */
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/types.h>
#include "linux/ntb.h"
#include "linux/ntb_transport.h"

#define NTB_TRANSPORT_VERSION	4
#define NTB_TRANSPORT_VER	"4"
#define NTB_TRANSPORT_NAME	"ntb_transport"
#define NTB_TRANSPORT_DESC	"Software Queue-Pair Transport over NTB"

MODULE_DESCRIPTION(NTB_TRANSPORT_DESC);
MODULE_VERSION(NTB_TRANSPORT_VER);
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Intel Corporation");

static unsigned long max_mw_size;
module_param(max_mw_size, ulong, 0644);
MODULE_PARM_DESC(max_mw_size, "Limit size of large memory windows");

static unsigned int transport_mtu = 0x401E;
module_param(transport_mtu, uint, 0644);
MODULE_PARM_DESC(transport_mtu, "Maximum size of NTB transport packets");

static unsigned char max_num_clients;
module_param(max_num_clients, byte, 0644);
MODULE_PARM_DESC(max_num_clients, "Maximum number of NTB transport clients");

static unsigned int copy_bytes = 1024;
module_param(copy_bytes, uint, 0644);
MODULE_PARM_DESC(copy_bytes, "Threshold under which NTB will use the CPU to copy instead of DMA");

static struct dentry *nt_debugfs_dir;

struct ntb_queue_entry {
	/* ntb_queue list reference */
	struct list_head entry;
	/* pointers to data to be transferred */
	void *cb_data;
	void *buf;
	unsigned int len;
	unsigned int flags;

	struct ntb_transport_qp *qp;
	union {
		struct ntb_payload_header __iomem *tx_hdr;
		struct ntb_payload_header *rx_hdr;
	};
	unsigned int index;
};

struct ntb_rx_info {
	unsigned int entry;
};

struct ntb_transport_qp {
	struct ntb_transport_ctx *transport;
	struct ntb_dev *ndev;
	void *cb_data;
	struct dma_chan *dma_chan;

	bool client_ready;
	bool link_is_up;

	u8 qp_num;	/* Only 64 QP's are allowed.  0-63 */
	u64 qp_bit;

	struct ntb_rx_info __iomem *rx_info;
	struct ntb_rx_info *remote_rx_info;

	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
			   void *data, int len);
	struct list_head tx_free_q;
	spinlock_t ntb_tx_free_q_lock;
	void __iomem *tx_mw;
	dma_addr_t tx_mw_phys;
	unsigned int tx_index;
	unsigned int tx_max_entry;
	unsigned int tx_max_frame;

	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
			   void *data, int len);
	struct list_head rx_pend_q;
	struct list_head rx_free_q;
	spinlock_t ntb_rx_pend_q_lock;
	spinlock_t ntb_rx_free_q_lock;
	void *rx_buff;
	unsigned int rx_index;
	unsigned int rx_max_entry;
	unsigned int rx_max_frame;
	dma_cookie_t last_cookie;
	struct tasklet_struct rxc_db_work;

	void (*event_handler)(void *data, int status);
	struct delayed_work link_work;
	struct work_struct link_cleanup;

	struct dentry *debugfs_dir;
	struct dentry *debugfs_stats;

	/* Stats */
	u64 rx_bytes;
	u64 rx_pkts;
	u64 rx_ring_empty;
	u64 rx_err_no_buf;
	u64 rx_err_oflow;
	u64 rx_err_ver;
	u64 rx_memcpy;
	u64 rx_async;
	u64 tx_bytes;
	u64 tx_pkts;
	u64 tx_ring_full;
	u64 tx_err_no_buf;
	u64 tx_memcpy;
	u64 tx_async;
};

struct ntb_transport_mw {
	phys_addr_t phys_addr;
	resource_size_t phys_size;
	resource_size_t xlat_align;
	resource_size_t xlat_align_size;
	void __iomem *vbase;
	size_t xlat_size;
	size_t buff_size;
	void *virt_addr;
	dma_addr_t dma_addr;
};

struct ntb_transport_client_dev {
	struct list_head entry;
	struct ntb_transport_ctx *nt;
	struct device dev;
};

struct ntb_transport_ctx {
	struct list_head entry;
	struct list_head client_devs;

	struct ntb_dev *ndev;

	struct ntb_transport_mw *mw_vec;
	struct ntb_transport_qp *qp_vec;
	unsigned int mw_count;
	unsigned int qp_count;
	u64 qp_bitmap;
	u64 qp_bitmap_free;

	bool link_is_up;
	struct delayed_work link_work;
	struct work_struct link_cleanup;
};

enum {
	DESC_DONE_FLAG = BIT(0),
	LINK_DOWN_FLAG = BIT(1),
};

struct ntb_payload_header {
	unsigned int ver;
	unsigned int len;
	unsigned int flags;
};

enum {
	VERSION = 0,
	QP_LINKS,
	NUM_QPS,
	NUM_MWS,
	MW0_SZ_HIGH,
	MW0_SZ_LOW,
	MW1_SZ_HIGH,
	MW1_SZ_LOW,
	MAX_SPAD,
};

#define dev_client_dev(__dev) \
	container_of((__dev), struct ntb_transport_client_dev, dev)

#define drv_client(__drv) \
	container_of((__drv), struct ntb_transport_client, driver)

#define QP_TO_MW(nt, qp)	((qp) % nt->mw_count)
#define NTB_QP_DEF_NUM_ENTRIES	100
#define NTB_LINK_DOWN_TIMEOUT	10

static void ntb_transport_rxc_db(unsigned long data);
static const struct ntb_ctx_ops ntb_transport_ops;
static struct ntb_client ntb_transport_client;

static int ntb_transport_bus_match(struct device *dev,
				   struct device_driver *drv)
{
	return !strncmp(dev_name(dev), drv->name, strlen(drv->name));
}

static int ntb_transport_bus_probe(struct device *dev)
{
	const struct ntb_transport_client *client;
	int rc = -EINVAL;

	get_device(dev);

	client = drv_client(dev->driver);
	rc = client->probe(dev);
	if (rc)
		put_device(dev);

	return rc;
}

static int ntb_transport_bus_remove(struct device *dev)
{
	const struct ntb_transport_client *client;

	client = drv_client(dev->driver);
	client->remove(dev);

	put_device(dev);

	return 0;
}

static struct bus_type ntb_transport_bus = {
	.name = "ntb_transport",
	.match = ntb_transport_bus_match,
	.probe = ntb_transport_bus_probe,
	.remove = ntb_transport_bus_remove,
};

static LIST_HEAD(ntb_transport_list);

static int ntb_bus_init(struct ntb_transport_ctx *nt)
{
	list_add(&nt->entry, &ntb_transport_list);
	return 0;
}

static void ntb_bus_remove(struct ntb_transport_ctx *nt)
{
	struct ntb_transport_client_dev *client_dev, *cd;

	list_for_each_entry_safe(client_dev, cd, &nt->client_devs, entry) {
		dev_err(client_dev->dev.parent, "%s still attached to bus, removing\n",
			dev_name(&client_dev->dev));
		list_del(&client_dev->entry);
		device_unregister(&client_dev->dev);
	}

	list_del(&nt->entry);
}

static void ntb_transport_client_release(struct device *dev)
{
	struct ntb_transport_client_dev *client_dev;

	client_dev = dev_client_dev(dev);
	kfree(client_dev);
}

/**
 * ntb_transport_unregister_client_dev - Unregister NTB client device
 * @device_name: Name of NTB client device
 *
 * Unregister an NTB client device with the NTB transport layer
 */
void ntb_transport_unregister_client_dev(char *device_name)
{
	struct ntb_transport_client_dev *client, *cd;
	struct ntb_transport_ctx *nt;

	list_for_each_entry(nt, &ntb_transport_list, entry)
		list_for_each_entry_safe(client, cd, &nt->client_devs, entry)
			if (!strncmp(dev_name(&client->dev), device_name,
				     strlen(device_name))) {
				list_del(&client->entry);
				device_unregister(&client->dev);
			}
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client_dev);

/**
 * ntb_transport_register_client_dev - Register NTB client device
 * @device_name: Name of NTB client device
 *
 * Register an NTB client device with the NTB transport layer
 */
int ntb_transport_register_client_dev(char *device_name)
{
	struct ntb_transport_client_dev *client_dev;
	struct ntb_transport_ctx *nt;
	int rc, i = 0;

	if (list_empty(&ntb_transport_list))
		return -ENODEV;

	list_for_each_entry(nt, &ntb_transport_list, entry) {
		struct device *dev;

		client_dev = kzalloc(sizeof(*client_dev),
				     GFP_KERNEL);
		if (!client_dev) {
			rc = -ENOMEM;
			goto err;
		}

		dev = &client_dev->dev;

		/* setup and register client devices */
		dev_set_name(dev, "%s%d", device_name, i);
		dev->bus = &ntb_transport_bus;
		dev->release = ntb_transport_client_release;
		dev->parent = &nt->ndev->dev;

		rc = device_register(dev);
		if (rc) {
			kfree(client_dev);
			goto err;
		}

		list_add_tail(&client_dev->entry, &nt->client_devs);
		i++;
	}

	return 0;

err:
	ntb_transport_unregister_client_dev(device_name);

	return rc;
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client_dev);

/**
 * ntb_transport_register_client - Register NTB client driver
 * @drv: NTB client driver to be registered
 *
 * Register an NTB client driver with the NTB transport layer
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
int ntb_transport_register_client(struct ntb_transport_client *drv)
{
	drv->driver.bus = &ntb_transport_bus;

	if (list_empty(&ntb_transport_list))
		return -ENODEV;

	return driver_register(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client);

/**
 * ntb_transport_unregister_client - Unregister NTB client driver
 * @drv: NTB client driver to be unregistered
 *
 * Unregister an NTB client driver with the NTB transport layer
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
void ntb_transport_unregister_client(struct ntb_transport_client *drv)
{
	driver_unregister(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client);

static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
			    loff_t *offp)
{
	struct ntb_transport_qp *qp;
	char *buf;
	ssize_t ret, out_offset, out_count;

	out_count = 1000;

	buf = kmalloc(out_count, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	qp = filp->private_data;
	out_offset = 0;
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "NTB QP stats\n");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_bytes - \t%llu\n", qp->rx_bytes);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_pkts - \t%llu\n", qp->rx_pkts);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_memcpy - \t%llu\n", qp->rx_memcpy);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_async - \t%llu\n", qp->rx_async);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_ring_empty - %llu\n", qp->rx_ring_empty);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_no_buf - %llu\n", qp->rx_err_no_buf);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_oflow - \t%llu\n", qp->rx_err_oflow);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_ver - \t%llu\n", qp->rx_err_ver);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_buff - \t%p\n", qp->rx_buff);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_index - \t%u\n", qp->rx_index);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_max_entry - \t%u\n", qp->rx_max_entry);

	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_bytes - \t%llu\n", qp->tx_bytes);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_pkts - \t%llu\n", qp->tx_pkts);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_memcpy - \t%llu\n", qp->tx_memcpy);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_async - \t%llu\n", qp->tx_async);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_ring_full - \t%llu\n", qp->tx_ring_full);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_err_no_buf - %llu\n", qp->tx_err_no_buf);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_mw - \t%p\n", qp->tx_mw);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_index - \t%u\n", qp->tx_index);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_max_entry - \t%u\n", qp->tx_max_entry);

	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "\nQP Link %s\n",
			       qp->link_is_up ? "Up" : "Down");
	if (out_offset > out_count)
		out_offset = out_count;

	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
	kfree(buf);
	return ret;
}

static const struct file_operations ntb_qp_debugfs_stats = {
	.owner = THIS_MODULE,
	.open = simple_open,
	.read = debugfs_read,
};

static void ntb_list_add(spinlock_t *lock, struct list_head *entry,
			 struct list_head *list)
{
	unsigned long flags;

	spin_lock_irqsave(lock, flags);
	list_add_tail(entry, list);
	spin_unlock_irqrestore(lock, flags);
}

static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock,
					   struct list_head *list)
{
	struct ntb_queue_entry *entry;
	unsigned long flags;

	spin_lock_irqsave(lock, flags);
	if (list_empty(list)) {
		entry = NULL;
		goto out;
	}
	entry = list_first_entry(list, struct ntb_queue_entry, entry);
	list_del(&entry->entry);
out:
	spin_unlock_irqrestore(lock, flags);

	return entry;
}

static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
				     unsigned int qp_num)
{
	struct ntb_transport_qp *qp = &nt->qp_vec[qp_num];
	struct ntb_transport_mw *mw;
	unsigned int rx_size, num_qps_mw;
	unsigned int mw_num, mw_count, qp_count;
	unsigned int i;

	mw_count = nt->mw_count;
	qp_count = nt->qp_count;

	mw_num = QP_TO_MW(nt, qp_num);
	mw = &nt->mw_vec[mw_num];

	if (!mw->virt_addr)
		return -ENOMEM;

	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
		num_qps_mw = qp_count / mw_count + 1;
	else
		num_qps_mw = qp_count / mw_count;

	rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
	qp->rx_buff = mw->virt_addr + rx_size * qp_num / mw_count;
	rx_size -= sizeof(struct ntb_rx_info);

	qp->remote_rx_info = qp->rx_buff + rx_size;

	/* Due to housekeeping, there must be atleast 2 buffs */
	qp->rx_max_frame = min(transport_mtu, rx_size / 2);
	qp->rx_max_entry = rx_size / qp->rx_max_frame;
	qp->rx_index = 0;

	qp->remote_rx_info->entry = qp->rx_max_entry - 1;

	/* setup the hdr offsets with 0's */
	for (i = 0; i < qp->rx_max_entry; i++) {
		void *offset = (qp->rx_buff + qp->rx_max_frame * (i + 1) -
				sizeof(struct ntb_payload_header));
		memset(offset, 0, sizeof(struct ntb_payload_header));
	}

	qp->rx_pkts = 0;
	qp->tx_pkts = 0;
	qp->tx_index = 0;

	return 0;
}

static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
{
	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
	struct pci_dev *pdev = nt->ndev->pdev;

	if (!mw->virt_addr)
		return;

	ntb_mw_clear_trans(nt->ndev, num_mw);
	dma_free_coherent(&pdev->dev, mw->buff_size,
			  mw->virt_addr, mw->dma_addr);
	mw->xlat_size = 0;
	mw->buff_size = 0;
	mw->virt_addr = NULL;
}

static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
		      unsigned int size)
{
	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
	struct pci_dev *pdev = nt->ndev->pdev;
	unsigned int xlat_size, buff_size;
	int rc;

	xlat_size = round_up(size, mw->xlat_align_size);
	buff_size = round_up(size, mw->xlat_align);

	/* No need to re-setup */
	if (mw->xlat_size == xlat_size)
		return 0;

	if (mw->buff_size)
		ntb_free_mw(nt, num_mw);

	/* Alloc memory for receiving data.  Must be aligned */
	mw->xlat_size = xlat_size;
	mw->buff_size = buff_size;

	mw->virt_addr = dma_alloc_coherent(&pdev->dev, buff_size,
					   &mw->dma_addr, GFP_KERNEL);
	if (!mw->virt_addr) {
		mw->xlat_size = 0;
		mw->buff_size = 0;
		dev_err(&pdev->dev, "Unable to alloc MW buff of size %d\n",
			buff_size);
		return -ENOMEM;
	}

	/*
	 * we must ensure that the memory address allocated is BAR size
	 * aligned in order for the XLAT register to take the value. This
	 * is a requirement of the hardware. It is recommended to setup CMA
	 * for BAR sizes equal or greater than 4MB.
	 */
	if (!IS_ALIGNED(mw->dma_addr, mw->xlat_align)) {
		dev_err(&pdev->dev, "DMA memory %pad is not aligned\n",
			&mw->dma_addr);
		ntb_free_mw(nt, num_mw);
		return -ENOMEM;
	}

	/* Notify HW the memory location of the receive buffer */
	rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size);
	if (rc) {
		dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw);
		ntb_free_mw(nt, num_mw);
		return -EIO;
	}

	return 0;
}

static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)
{
	struct ntb_transport_ctx *nt = qp->transport;
	struct pci_dev *pdev = nt->ndev->pdev;

	if (qp->link_is_up) {
		cancel_delayed_work_sync(&qp->link_work);
		return;
	}

	dev_info(&pdev->dev, "qp %d: Link Cleanup\n", qp->qp_num);
	qp->link_is_up = false;

	if (qp->event_handler)
		qp->event_handler(qp->cb_data, qp->link_is_up);
}

static void ntb_qp_link_cleanup_work(struct work_struct *work)
{
	struct ntb_transport_qp *qp = container_of(work,
						   struct ntb_transport_qp,
						   link_cleanup);
	struct ntb_transport_ctx *nt = qp->transport;

	ntb_qp_link_cleanup(qp);

	if (nt->link_is_up)
		schedule_delayed_work(&qp->link_work,
				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}

static void ntb_qp_link_down(struct ntb_transport_qp *qp)
{
	schedule_work(&qp->link_cleanup);
}

static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
{
	struct ntb_transport_qp *qp;
	u64 qp_bitmap_alloc;
	int i;

	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;

	/* Pass along the info to any clients */
	for (i = 0; i < nt->qp_count; i++)
		if (qp_bitmap_alloc & BIT_ULL(i)) {
			qp = &nt->qp_vec[i];
			ntb_qp_link_cleanup(qp);
			cancel_work_sync(&qp->link_cleanup);
			cancel_delayed_work_sync(&qp->link_work);
		}

	if (!nt->link_is_up)
		cancel_delayed_work_sync(&nt->link_work);

	/* The scratchpad registers keep the values if the remote side
	 * goes down, blast them now to give them a sane value the next
	 * time they are accessed
	 */
	for (i = 0; i < MAX_SPAD; i++)
		ntb_spad_write(nt->ndev, i, 0);
}

static void ntb_transport_link_cleanup_work(struct work_struct *work)
{
	struct ntb_transport_ctx *nt =
		container_of(work, struct ntb_transport_ctx, link_cleanup);

	ntb_transport_link_cleanup(nt);
}

static void ntb_transport_event_callback(void *data)
{
	struct ntb_transport_ctx *nt = data;

	if (ntb_link_is_up(nt->ndev, NULL, NULL) == 1)
		schedule_delayed_work(&nt->link_work, 0);
	else
		schedule_work(&nt->link_cleanup);
}

static void ntb_transport_link_work(struct work_struct *work)
{
	struct ntb_transport_ctx *nt =
		container_of(work, struct ntb_transport_ctx, link_work.work);
	struct ntb_dev *ndev = nt->ndev;
	struct pci_dev *pdev = ndev->pdev;
	resource_size_t size;
	u32 val;
	int rc, i, spad;

	/* send the local info, in the opposite order of the way we read it */
	for (i = 0; i < nt->mw_count; i++) {
		size = nt->mw_vec[i].phys_size;

		if (max_mw_size && size > max_mw_size)
			size = max_mw_size;

		spad = MW0_SZ_HIGH + (i * 2);
		ntb_peer_spad_write(ndev, spad, (u32)(size >> 32));

		spad = MW0_SZ_LOW + (i * 2);
		ntb_peer_spad_write(ndev, spad, (u32)size);
	}

	ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);

	ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count);

	ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION);

	/* Query the remote side for its info */
	val = ntb_spad_read(ndev, VERSION);
	dev_dbg(&pdev->dev, "Remote version = %d\n", val);
	if (val != NTB_TRANSPORT_VERSION)
		goto out;

	val = ntb_spad_read(ndev, NUM_QPS);
	dev_dbg(&pdev->dev, "Remote max number of qps = %d\n", val);
	if (val != nt->qp_count)
		goto out;

	val = ntb_spad_read(ndev, NUM_MWS);
	dev_dbg(&pdev->dev, "Remote number of mws = %d\n", val);
	if (val != nt->mw_count)
		goto out;

	for (i = 0; i < nt->mw_count; i++) {
		u64 val64;

		val = ntb_spad_read(ndev, MW0_SZ_HIGH + (i * 2));
		val64 = (u64)val << 32;

		val = ntb_spad_read(ndev, MW0_SZ_LOW + (i * 2));
		val64 |= val;

		dev_dbg(&pdev->dev, "Remote MW%d size = %#llx\n", i, val64);

		rc = ntb_set_mw(nt, i, val64);
		if (rc)
			goto out1;
	}

	nt->link_is_up = true;

	for (i = 0; i < nt->qp_count; i++) {
		struct ntb_transport_qp *qp = &nt->qp_vec[i];

		ntb_transport_setup_qp_mw(nt, i);

		if (qp->client_ready)
			schedule_delayed_work(&qp->link_work, 0);
	}

	return;

out1:
	for (i = 0; i < nt->mw_count; i++)
		ntb_free_mw(nt, i);
out:
	if (ntb_link_is_up(ndev, NULL, NULL) == 1)
		schedule_delayed_work(&nt->link_work,
				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}

static void ntb_qp_link_work(struct work_struct *work)
{
	struct ntb_transport_qp *qp = container_of(work,
						   struct ntb_transport_qp,
						   link_work.work);
	struct pci_dev *pdev = qp->ndev->pdev;
	struct ntb_transport_ctx *nt = qp->transport;
	int val;

	WARN_ON(!nt->link_is_up);

	val = ntb_spad_read(nt->ndev, QP_LINKS);

	ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num));

	/* query remote spad for qp ready bits */
	ntb_peer_spad_read(nt->ndev, QP_LINKS);
	dev_dbg(&pdev->dev, "Remote QP link status = %x\n", val);

	/* See if the remote side is up */
	if (val & BIT(qp->qp_num)) {
		dev_info(&pdev->dev, "qp %d: Link Up\n", qp->qp_num);
		qp->link_is_up = true;

		if (qp->event_handler)
			qp->event_handler(qp->cb_data, qp->link_is_up);
	} else if (nt->link_is_up)
		schedule_delayed_work(&qp->link_work,
				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}

static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
				    unsigned int qp_num)
{
	struct ntb_transport_qp *qp;
	struct ntb_transport_mw *mw;
	phys_addr_t mw_base;
	resource_size_t mw_size;
	unsigned int num_qps_mw, tx_size;
	unsigned int mw_num, mw_count, qp_count;
	u64 qp_offset;

	mw_count = nt->mw_count;
	qp_count = nt->qp_count;

	mw_num = QP_TO_MW(nt, qp_num);
	mw = &nt->mw_vec[mw_num];

	qp = &nt->qp_vec[qp_num];
	qp->qp_num = qp_num;
	qp->transport = nt;
	qp->ndev = nt->ndev;
	qp->link_is_up = false;
	qp->client_ready = false;
	qp->event_handler = NULL;

	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
		num_qps_mw = qp_count / mw_count + 1;
	else
		num_qps_mw = qp_count / mw_count;

	mw_base = nt->mw_vec[mw_num].phys_addr;
	mw_size = nt->mw_vec[mw_num].phys_size;

	tx_size = (unsigned int)mw_size / num_qps_mw;
	qp_offset = tx_size * qp_num / mw_count;

	qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
	if (!qp->tx_mw)
		return -EINVAL;

	qp->tx_mw_phys = mw_base + qp_offset;
	if (!qp->tx_mw_phys)
		return -EINVAL;

	tx_size -= sizeof(struct ntb_rx_info);
	qp->rx_info = qp->tx_mw + tx_size;

	/* Due to housekeeping, there must be atleast 2 buffs */
	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
	qp->tx_max_entry = tx_size / qp->tx_max_frame;

	if (nt_debugfs_dir) {
		char debugfs_name[4];

		snprintf(debugfs_name, 4, "qp%d", qp_num);
		qp->debugfs_dir = debugfs_create_dir(debugfs_name,
						     nt_debugfs_dir);

		qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
							qp->debugfs_dir, qp,
							&ntb_qp_debugfs_stats);
	} else {
		qp->debugfs_dir = NULL;
		qp->debugfs_stats = NULL;
	}

	INIT_DELAYED_WORK(&qp->link_work, ntb_qp_link_work);
	INIT_WORK(&qp->link_cleanup, ntb_qp_link_cleanup_work);

	spin_lock_init(&qp->ntb_rx_pend_q_lock);
	spin_lock_init(&qp->ntb_rx_free_q_lock);
	spin_lock_init(&qp->ntb_tx_free_q_lock);

	INIT_LIST_HEAD(&qp->rx_pend_q);
	INIT_LIST_HEAD(&qp->rx_free_q);
	INIT_LIST_HEAD(&qp->tx_free_q);

	tasklet_init(&qp->rxc_db_work, ntb_transport_rxc_db,
		     (unsigned long)qp);

	return 0;
}

static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
{
	struct ntb_transport_ctx *nt;
	struct ntb_transport_mw *mw;
	unsigned int mw_count, qp_count;
	u64 qp_bitmap;
	int rc, i;

	if (ntb_db_is_unsafe(ndev))
		dev_dbg(&ndev->dev,
			"doorbell is unsafe, proceed anyway...\n");
	if (ntb_spad_is_unsafe(ndev))
		dev_dbg(&ndev->dev,
			"scratchpad is unsafe, proceed anyway...\n");

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

	nt->ndev = ndev;

	mw_count = ntb_mw_count(ndev);

	nt->mw_count = mw_count;

	nt->mw_vec = kcalloc(mw_count, sizeof(*nt->mw_vec), GFP_KERNEL);
	if (!nt->mw_vec) {
		rc = -ENOMEM;
		goto err;
	}

	for (i = 0; i < mw_count; i++) {
		mw = &nt->mw_vec[i];

		rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size,
				      &mw->xlat_align, &mw->xlat_align_size);
		if (rc)
			goto err1;

		mw->vbase = ioremap(mw->phys_addr, mw->phys_size);
		if (!mw->vbase) {
			rc = -ENOMEM;
			goto err1;
		}

		mw->buff_size = 0;
		mw->xlat_size = 0;
		mw->virt_addr = NULL;
		mw->dma_addr = 0;
	}

	qp_bitmap = ntb_db_valid_mask(ndev);

	qp_count = ilog2(qp_bitmap);
	if (max_num_clients && max_num_clients < qp_count)
		qp_count = max_num_clients;
	else if (mw_count < qp_count)
		qp_count = mw_count;

	qp_bitmap &= BIT_ULL(qp_count) - 1;

	nt->qp_count = qp_count;
	nt->qp_bitmap = qp_bitmap;
	nt->qp_bitmap_free = qp_bitmap;

	nt->qp_vec = kcalloc(qp_count, sizeof(*nt->qp_vec), GFP_KERNEL);
	if (!nt->qp_vec) {
		rc = -ENOMEM;
		goto err2;
	}

	for (i = 0; i < qp_count; i++) {
		rc = ntb_transport_init_queue(nt, i);
		if (rc)
			goto err3;
	}

	INIT_DELAYED_WORK(&nt->link_work, ntb_transport_link_work);
	INIT_WORK(&nt->link_cleanup, ntb_transport_link_cleanup_work);

	rc = ntb_set_ctx(ndev, nt, &ntb_transport_ops);
	if (rc)
		goto err3;

	INIT_LIST_HEAD(&nt->client_devs);
	rc = ntb_bus_init(nt);
	if (rc)
		goto err4;

	nt->link_is_up = false;
	ntb_link_enable(ndev, NTB_SPEED_AUTO, NTB_WIDTH_AUTO);
	ntb_link_event(ndev);

	return 0;

err4:
	ntb_clear_ctx(ndev);
err3:
	kfree(nt->qp_vec);
err2:
	kfree(nt->mw_vec);
err1:
	while (i--) {
		mw = &nt->mw_vec[i];
		iounmap(mw->vbase);
	}
err:
	kfree(nt);
	return rc;
}

static void ntb_transport_free(struct ntb_client *self, struct ntb_dev *ndev)
{
	struct ntb_transport_ctx *nt = ndev->ctx;
	struct ntb_transport_qp *qp;
	u64 qp_bitmap_alloc;
	int i;

	ntb_transport_link_cleanup(nt);
	cancel_work_sync(&nt->link_cleanup);
	cancel_delayed_work_sync(&nt->link_work);

	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;

	/* verify that all the qp's are freed */
	for (i = 0; i < nt->qp_count; i++) {
		qp = &nt->qp_vec[i];
		if (qp_bitmap_alloc & BIT_ULL(i))
			ntb_transport_free_queue(qp);
		debugfs_remove_recursive(qp->debugfs_dir);
	}

	ntb_link_disable(ndev);
	ntb_clear_ctx(ndev);

	ntb_bus_remove(nt);

	for (i = nt->mw_count; i--; ) {
		ntb_free_mw(nt, i);
		iounmap(nt->mw_vec[i].vbase);
	}

	kfree(nt->qp_vec);
	kfree(nt->mw_vec);
	kfree(nt);
}

static void ntb_rx_copy_callback(void *data)
{
	struct ntb_queue_entry *entry = data;
	struct ntb_transport_qp *qp = entry->qp;
	void *cb_data = entry->cb_data;
	unsigned int len = entry->len;
	struct ntb_payload_header *hdr = entry->rx_hdr;

	hdr->flags = 0;

	iowrite32(entry->index, &qp->rx_info->entry);

	ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry, &qp->rx_free_q);

	if (qp->rx_handler && qp->client_ready)
		qp->rx_handler(qp, qp->cb_data, cb_data, len);
}

static void ntb_memcpy_rx(struct ntb_queue_entry *entry, void *offset)
{
	void *buf = entry->buf;
	size_t len = entry->len;

	memcpy(buf, offset, len);

	/* Ensure that the data is fully copied out before clearing the flag */
	wmb();

	ntb_rx_copy_callback(entry);
}

static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
			 size_t len)
{
	struct dma_async_tx_descriptor *txd;
	struct ntb_transport_qp *qp = entry->qp;
	struct dma_chan *chan = qp->dma_chan;
	struct dma_device *device;
	size_t pay_off, buff_off;
	struct dmaengine_unmap_data *unmap;
	dma_cookie_t cookie;
	void *buf = entry->buf;

	entry->len = len;

	if (!chan)
		goto err;

	if (len < copy_bytes)
		goto err_wait;

	device = chan->device;
	pay_off = (size_t)offset & ~PAGE_MASK;
	buff_off = (size_t)buf & ~PAGE_MASK;

	if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
		goto err_wait;

	unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
	if (!unmap)
		goto err_wait;

	unmap->len = len;
	unmap->addr[0] = dma_map_page(device->dev, virt_to_page(offset),
				      pay_off, len, DMA_TO_DEVICE);
	if (dma_mapping_error(device->dev, unmap->addr[0]))
		goto err_get_unmap;

	unmap->to_cnt = 1;

	unmap->addr[1] = dma_map_page(device->dev, virt_to_page(buf),
				      buff_off, len, DMA_FROM_DEVICE);
	if (dma_mapping_error(device->dev, unmap->addr[1]))
		goto err_get_unmap;

	unmap->from_cnt = 1;

	txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
					     unmap->addr[0], len,
					     DMA_PREP_INTERRUPT);
	if (!txd)
		goto err_get_unmap;

	txd->callback = ntb_rx_copy_callback;
	txd->callback_param = entry;
	dma_set_unmap(txd, unmap);

	cookie = dmaengine_submit(txd);
	if (dma_submit_error(cookie))
		goto err_set_unmap;

	dmaengine_unmap_put(unmap);

	qp->last_cookie = cookie;

	qp->rx_async++;

	return;

err_set_unmap:
	dmaengine_unmap_put(unmap);
err_get_unmap:
	dmaengine_unmap_put(unmap);
err_wait:
	/* If the callbacks come out of order, the writing of the index to the
	 * last completed will be out of order.  This may result in the
	 * receive stalling forever.
	 */
	dma_sync_wait(chan, qp->last_cookie);
err:
	ntb_memcpy_rx(entry, offset);
	qp->rx_memcpy++;
}

static int ntb_process_rxc(struct ntb_transport_qp *qp)
{
	struct ntb_payload_header *hdr;
	struct ntb_queue_entry *entry;
	void *offset;
	int rc;

	offset = qp->rx_buff + qp->rx_max_frame * qp->rx_index;
	hdr = offset + qp->rx_max_frame - sizeof(struct ntb_payload_header);

	dev_dbg(&qp->ndev->pdev->dev, "qp %d: RX ver %u len %d flags %x\n",
		qp->qp_num, hdr->ver, hdr->len, hdr->flags);

	if (!(hdr->flags & DESC_DONE_FLAG)) {
		dev_dbg(&qp->ndev->pdev->dev, "done flag not set\n");
		qp->rx_ring_empty++;
		return -EAGAIN;
	}

	if (hdr->flags & LINK_DOWN_FLAG) {
		dev_dbg(&qp->ndev->pdev->dev, "link down flag set\n");
		ntb_qp_link_down(qp);
		hdr->flags = 0;
		return -EAGAIN;
	}

	if (hdr->ver != (u32)qp->rx_pkts) {
		dev_dbg(&qp->ndev->pdev->dev,
			"version mismatch, expected %llu - got %u\n",
			qp->rx_pkts, hdr->ver);
		qp->rx_err_ver++;
		return -EIO;
	}

	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
	if (!entry) {
		dev_dbg(&qp->ndev->pdev->dev, "no receive buffer\n");
		qp->rx_err_no_buf++;

		rc = -ENOMEM;
		goto err;
	}

	if (hdr->len > entry->len) {
		dev_dbg(&qp->ndev->pdev->dev,
			"receive buffer overflow! Wanted %d got %d\n",
			hdr->len, entry->len);
		qp->rx_err_oflow++;

		rc = -EIO;
		goto err;
	}

	dev_dbg(&qp->ndev->pdev->dev,
		"RX OK index %u ver %u size %d into buf size %d\n",
		qp->rx_index, hdr->ver, hdr->len, entry->len);

	qp->rx_bytes += hdr->len;
	qp->rx_pkts++;

	entry->index = qp->rx_index;
	entry->rx_hdr = hdr;

	ntb_async_rx(entry, offset, hdr->len);

	qp->rx_index++;
	qp->rx_index %= qp->rx_max_entry;

	return 0;

err:
	/* FIXME: if this syncrhonous update of the rx_index gets ahead of
	 * asyncrhonous ntb_rx_copy_callback of previous entry, there are three
	 * scenarios:
	 *
	 * 1) The peer might miss this update, but observe the update
	 * from the memcpy completion callback.  In this case, the buffer will
	 * not be freed on the peer to be reused for a different packet.  The
	 * successful rx of a later packet would clear the condition, but the
	 * condition could persist if several rx fail in a row.
	 *
	 * 2) The peer may observe this update before the asyncrhonous copy of
	 * prior packets is completed.  The peer may overwrite the buffers of
	 * the prior packets before they are copied.
	 *
	 * 3) Both: the peer may observe the update, and then observe the index
	 * decrement by the asynchronous completion callback.  Who knows what
	 * badness that will cause.
	 */
	hdr->flags = 0;
	iowrite32(qp->rx_index, &qp->rx_info->entry);

	return rc;
}

static void ntb_transport_rxc_db(unsigned long data)
{
	struct ntb_transport_qp *qp = (void *)data;
	int rc, i;

	dev_dbg(&qp->ndev->pdev->dev, "%s: doorbell %d received\n",
		__func__, qp->qp_num);

	/* Limit the number of packets processed in a single interrupt to
	 * provide fairness to others
	 */
	for (i = 0; i < qp->rx_max_entry; i++) {
		rc = ntb_process_rxc(qp);
		if (rc)
			break;
	}

	if (qp->dma_chan)
		dma_async_issue_pending(qp->dma_chan);

	if (i == qp->rx_max_entry) {
		/* there is more work to do */
		tasklet_schedule(&qp->rxc_db_work);
	} else if (ntb_db_read(qp->ndev) & BIT_ULL(qp->qp_num)) {
		/* the doorbell bit is set: clear it */
		ntb_db_clear(qp->ndev, BIT_ULL(qp->qp_num));
		/* ntb_db_read ensures ntb_db_clear write is committed */
		ntb_db_read(qp->ndev);

		/* an interrupt may have arrived between finishing
		 * ntb_process_rxc and clearing the doorbell bit:
		 * there might be some more work to do.
		 */
		tasklet_schedule(&qp->rxc_db_work);
	}
}

static void ntb_tx_copy_callback(void *data)
{
	struct ntb_queue_entry *entry = data;
	struct ntb_transport_qp *qp = entry->qp;
	struct ntb_payload_header __iomem *hdr = entry->tx_hdr;

	iowrite32(entry->flags | DESC_DONE_FLAG, &hdr->flags);

	ntb_peer_db_set(qp->ndev, BIT_ULL(qp->qp_num));

	/* The entry length can only be zero if the packet is intended to be a
	 * "link down" or similar.  Since no payload is being sent in these
	 * cases, there is nothing to add to the completion queue.
	 */
	if (entry->len > 0) {
		qp->tx_bytes += entry->len;

		if (qp->tx_handler)
			qp->tx_handler(qp, qp->cb_data, entry->cb_data,
				       entry->len);
	}

	ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry, &qp->tx_free_q);
}

static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset)
{
	memcpy_toio(offset, entry->buf, entry->len);

	/* Ensure that the data is fully copied out before setting the flags */
	wmb();

	ntb_tx_copy_callback(entry);
}

static void ntb_async_tx(struct ntb_transport_qp *qp,
			 struct ntb_queue_entry *entry)
{
	struct ntb_payload_header __iomem *hdr;
	struct dma_async_tx_descriptor *txd;
	struct dma_chan *chan = qp->dma_chan;
	struct dma_device *device;
	size_t dest_off, buff_off;
	struct dmaengine_unmap_data *unmap;
	dma_addr_t dest;
	dma_cookie_t cookie;
	void __iomem *offset;
	size_t len = entry->len;
	void *buf = entry->buf;

	offset = qp->tx_mw + qp->tx_max_frame * qp->tx_index;
	hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
	entry->tx_hdr = hdr;

	iowrite32(entry->len, &hdr->len);
	iowrite32((u32)qp->tx_pkts, &hdr->ver);

	if (!chan)
		goto err;

	if (len < copy_bytes)
		goto err;

	device = chan->device;
	dest = qp->tx_mw_phys + qp->tx_max_frame * qp->tx_index;
	buff_off = (size_t)buf & ~PAGE_MASK;
	dest_off = (size_t)dest & ~PAGE_MASK;

	if (!is_dma_copy_aligned(device, buff_off, dest_off, len))
		goto err;

	unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
	if (!unmap)
		goto err;

	unmap->len = len;
	unmap->addr[0] = dma_map_page(device->dev, virt_to_page(buf),
				      buff_off, len, DMA_TO_DEVICE);
	if (dma_mapping_error(device->dev, unmap->addr[0]))
		goto err_get_unmap;

	unmap->to_cnt = 1;

	txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len,
					     DMA_PREP_INTERRUPT);
	if (!txd)
		goto err_get_unmap;

	txd->callback = ntb_tx_copy_callback;
	txd->callback_param = entry;
	dma_set_unmap(txd, unmap);

	cookie = dmaengine_submit(txd);
	if (dma_submit_error(cookie))
		goto err_set_unmap;

	dmaengine_unmap_put(unmap);

	dma_async_issue_pending(chan);
	qp->tx_async++;

	return;
err_set_unmap:
	dmaengine_unmap_put(unmap);
err_get_unmap:
	dmaengine_unmap_put(unmap);
err:
	ntb_memcpy_tx(entry, offset);
	qp->tx_memcpy++;
}

static int ntb_process_tx(struct ntb_transport_qp *qp,
			  struct ntb_queue_entry *entry)
{
	if (qp->tx_index == qp->remote_rx_info->entry) {
		qp->tx_ring_full++;
		return -EAGAIN;
	}

	if (entry->len > qp->tx_max_frame - sizeof(struct ntb_payload_header)) {
		if (qp->tx_handler)
			qp->tx_handler(qp->cb_data, qp, NULL, -EIO);

		ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry,
			     &qp->tx_free_q);
		return 0;
	}

	ntb_async_tx(qp, entry);

	qp->tx_index++;
	qp->tx_index %= qp->tx_max_entry;

	qp->tx_pkts++;

	return 0;
}

static void ntb_send_link_down(struct ntb_transport_qp *qp)
{
	struct pci_dev *pdev = qp->ndev->pdev;
	struct ntb_queue_entry *entry;
	int i, rc;

	if (!qp->link_is_up)
		return;

	qp->link_is_up = false;
	dev_info(&pdev->dev, "qp %d: Send Link Down\n", qp->qp_num);

	for (i = 0; i < NTB_LINK_DOWN_TIMEOUT; i++) {
		entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
		if (entry)
			break;
		msleep(100);
	}

	if (!entry)
		return;

	entry->cb_data = NULL;
	entry->buf = NULL;
	entry->len = 0;
	entry->flags = LINK_DOWN_FLAG;

	rc = ntb_process_tx(qp, entry);
	if (rc)
		dev_err(&pdev->dev, "ntb: QP%d unable to send linkdown msg\n",
			qp->qp_num);
}

/**
 * ntb_transport_create_queue - Create a new NTB transport layer queue
 * @rx_handler: receive callback function
 * @tx_handler: transmit callback function
 * @event_handler: event callback function
 *
 * Create a new NTB transport layer queue and provide the queue with a callback
 * routine for both transmit and receive.  The receive callback routine will be
 * used to pass up data when the transport has received it on the queue.   The
 * transmit callback routine will be called when the transport has completed the
 * transmission of the data on the queue and the data is ready to be freed.
 *
 * RETURNS: pointer to newly created ntb_queue, NULL on error.
 */
struct ntb_transport_qp *
ntb_transport_create_queue(void *data, struct device *client_dev,
			   const struct ntb_queue_handlers *handlers)
{
	struct ntb_dev *ndev;
	struct pci_dev *pdev;
	struct ntb_transport_ctx *nt;
	struct ntb_queue_entry *entry;
	struct ntb_transport_qp *qp;
	u64 qp_bit;
	unsigned int free_queue;
	int i;

	ndev = dev_ntb(client_dev->parent);
	pdev = ndev->pdev;
	nt = ndev->ctx;

	free_queue = ffs(nt->qp_bitmap);
	if (!free_queue)
		goto err;

	/* decrement free_queue to make it zero based */
	free_queue--;

	qp = &nt->qp_vec[free_queue];
	qp_bit = BIT_ULL(qp->qp_num);

	nt->qp_bitmap_free &= ~qp_bit;

	qp->cb_data = data;
	qp->rx_handler = handlers->rx_handler;
	qp->tx_handler = handlers->tx_handler;
	qp->event_handler = handlers->event_handler;

	dmaengine_get();
	qp->dma_chan = dma_find_channel(DMA_MEMCPY);
	if (!qp->dma_chan) {
		dmaengine_put();
		dev_info(&pdev->dev, "Unable to allocate DMA channel, using CPU instead\n");
	}

	for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
		entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
		if (!entry)
			goto err1;

		entry->qp = qp;
		ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry,
			     &qp->rx_free_q);
	}

	for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
		entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
		if (!entry)
			goto err2;

		entry->qp = qp;
		ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry,
			     &qp->tx_free_q);
	}

	ntb_db_clear(qp->ndev, qp_bit);
	ntb_db_clear_mask(qp->ndev, qp_bit);

	dev_info(&pdev->dev, "NTB Transport QP %d created\n", qp->qp_num);

	return qp;

err2:
	while ((entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q)))
		kfree(entry);
err1:
	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
		kfree(entry);
	if (qp->dma_chan)
		dmaengine_put();
	nt->qp_bitmap_free |= qp_bit;
err:
	return NULL;
}
EXPORT_SYMBOL_GPL(ntb_transport_create_queue);

/**
 * ntb_transport_free_queue - Frees NTB transport queue
 * @qp: NTB queue to be freed
 *
 * Frees NTB transport queue
 */
void ntb_transport_free_queue(struct ntb_transport_qp *qp)
{
	struct ntb_transport_ctx *nt = qp->transport;
	struct pci_dev *pdev;
	struct ntb_queue_entry *entry;
	u64 qp_bit;

	if (!qp)
		return;

	pdev = qp->ndev->pdev;

	if (qp->dma_chan) {
		struct dma_chan *chan = qp->dma_chan;
		/* Putting the dma_chan to NULL will force any new traffic to be
		 * processed by the CPU instead of the DAM engine
		 */
		qp->dma_chan = NULL;

		/* Try to be nice and wait for any queued DMA engine
		 * transactions to process before smashing it with a rock
		 */
		dma_sync_wait(chan, qp->last_cookie);
		dmaengine_terminate_all(chan);
		dmaengine_put();
	}

	qp_bit = BIT_ULL(qp->qp_num);

	ntb_db_set_mask(qp->ndev, qp_bit);
	tasklet_disable(&qp->rxc_db_work);

	cancel_delayed_work_sync(&qp->link_work);

	qp->cb_data = NULL;
	qp->rx_handler = NULL;
	qp->tx_handler = NULL;
	qp->event_handler = NULL;

	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
		kfree(entry);

	while ((entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q))) {
		dev_warn(&pdev->dev, "Freeing item from a non-empty queue\n");
		kfree(entry);
	}

	while ((entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q)))
		kfree(entry);

	nt->qp_bitmap_free |= qp_bit;

	dev_info(&pdev->dev, "NTB Transport QP %d freed\n", qp->qp_num);
}
EXPORT_SYMBOL_GPL(ntb_transport_free_queue);

/**
 * ntb_transport_rx_remove - Dequeues enqueued rx packet
 * @qp: NTB queue to be freed
 * @len: pointer to variable to write enqueued buffers length
 *
 * Dequeues unused buffers from receive queue.  Should only be used during
 * shutdown of qp.
 *
 * RETURNS: NULL error value on error, or void* for success.
 */
void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len)
{
	struct ntb_queue_entry *entry;
	void *buf;

	if (!qp || qp->client_ready)
		return NULL;

	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
	if (!entry)
		return NULL;

	buf = entry->cb_data;
	*len = entry->len;

	ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry, &qp->rx_free_q);

	return buf;
}
EXPORT_SYMBOL_GPL(ntb_transport_rx_remove);

/**
 * ntb_transport_rx_enqueue - Enqueue a new NTB queue entry
 * @qp: NTB transport layer queue the entry is to be enqueued on
 * @cb: per buffer pointer for callback function to use
 * @data: pointer to data buffer that incoming packets will be copied into
 * @len: length of the data buffer
 *
 * Enqueue a new receive buffer onto the transport queue into which a NTB
 * payload can be received into.
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
			     unsigned int len)
{
	struct ntb_queue_entry *entry;

	if (!qp)
		return -EINVAL;

	entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q);
	if (!entry)
		return -ENOMEM;

	entry->cb_data = cb;
	entry->buf = data;
	entry->len = len;

	ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry, &qp->rx_pend_q);

	return 0;
}
EXPORT_SYMBOL_GPL(ntb_transport_rx_enqueue);

/**
 * ntb_transport_tx_enqueue - Enqueue a new NTB queue entry
 * @qp: NTB transport layer queue the entry is to be enqueued on
 * @cb: per buffer pointer for callback function to use
 * @data: pointer to data buffer that will be sent
 * @len: length of the data buffer
 *
 * Enqueue a new transmit buffer onto the transport queue from which a NTB
 * payload will be transmitted.  This assumes that a lock is being held to
 * serialize access to the qp.
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
			     unsigned int len)
{
	struct ntb_queue_entry *entry;
	int rc;

	if (!qp || !qp->link_is_up || !len)
		return -EINVAL;

	entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
	if (!entry) {
		qp->tx_err_no_buf++;
		return -ENOMEM;
	}

	entry->cb_data = cb;
	entry->buf = data;
	entry->len = len;
	entry->flags = 0;

	rc = ntb_process_tx(qp, entry);
	if (rc)
		ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry,
			     &qp->tx_free_q);

	return rc;
}
EXPORT_SYMBOL_GPL(ntb_transport_tx_enqueue);

/**
 * ntb_transport_link_up - Notify NTB transport of client readiness to use queue
 * @qp: NTB transport layer queue to be enabled
 *
 * Notify NTB transport layer of client readiness to use queue
 */
void ntb_transport_link_up(struct ntb_transport_qp *qp)
{
	if (!qp)
		return;

	qp->client_ready = true;

	if (qp->transport->link_is_up)
		schedule_delayed_work(&qp->link_work, 0);
}
EXPORT_SYMBOL_GPL(ntb_transport_link_up);

/**
 * ntb_transport_link_down - Notify NTB transport to no longer enqueue data
 * @qp: NTB transport layer queue to be disabled
 *
 * Notify NTB transport layer of client's desire to no longer receive data on
 * transport queue specified.  It is the client's responsibility to ensure all
 * entries on queue are purged or otherwise handled appropriately.
 */
void ntb_transport_link_down(struct ntb_transport_qp *qp)
{
	struct pci_dev *pdev;
	int val;

	if (!qp)
		return;

	pdev = qp->ndev->pdev;
	qp->client_ready = false;

	val = ntb_spad_read(qp->ndev, QP_LINKS);

	ntb_peer_spad_write(qp->ndev, QP_LINKS,
			    val & ~BIT(qp->qp_num));

	if (qp->link_is_up)
		ntb_send_link_down(qp);
	else
		cancel_delayed_work_sync(&qp->link_work);
}
EXPORT_SYMBOL_GPL(ntb_transport_link_down);

/**
 * ntb_transport_link_query - Query transport link state
 * @qp: NTB transport layer queue to be queried
 *
 * Query connectivity to the remote system of the NTB transport queue
 *
 * RETURNS: true for link up or false for link down
 */
bool ntb_transport_link_query(struct ntb_transport_qp *qp)
{
	if (!qp)
		return false;

	return qp->link_is_up;
}
EXPORT_SYMBOL_GPL(ntb_transport_link_query);

/**
 * ntb_transport_qp_num - Query the qp number
 * @qp: NTB transport layer queue to be queried
 *
 * Query qp number of the NTB transport queue
 *
 * RETURNS: a zero based number specifying the qp number
 */
unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp)
{
	if (!qp)
		return 0;

	return qp->qp_num;
}
EXPORT_SYMBOL_GPL(ntb_transport_qp_num);

/**
 * ntb_transport_max_size - Query the max payload size of a qp
 * @qp: NTB transport layer queue to be queried
 *
 * Query the maximum payload size permissible on the given qp
 *
 * RETURNS: the max payload size of a qp
 */
unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp)
{
	unsigned int max;

	if (!qp)
		return 0;

	if (!qp->dma_chan)
		return qp->tx_max_frame - sizeof(struct ntb_payload_header);

	/* If DMA engine usage is possible, try to find the max size for that */
	max = qp->tx_max_frame - sizeof(struct ntb_payload_header);
	max -= max % (1 << qp->dma_chan->device->copy_align);

	return max;
}
EXPORT_SYMBOL_GPL(ntb_transport_max_size);

static void ntb_transport_doorbell_callback(void *data, int vector)
{
	struct ntb_transport_ctx *nt = data;
	struct ntb_transport_qp *qp;
	u64 db_bits;
	unsigned int qp_num;

	db_bits = (nt->qp_bitmap & ~nt->qp_bitmap_free &
		   ntb_db_vector_mask(nt->ndev, vector));

	while (db_bits) {
		qp_num = __ffs(db_bits);
		qp = &nt->qp_vec[qp_num];

		tasklet_schedule(&qp->rxc_db_work);

		db_bits &= ~BIT_ULL(qp_num);
	}
}

static const struct ntb_ctx_ops ntb_transport_ops = {
	.link_event = ntb_transport_event_callback,
	.db_event = ntb_transport_doorbell_callback,
};

static struct ntb_client ntb_transport_client = {
	.ops = {
		.probe = ntb_transport_probe,
		.remove = ntb_transport_free,
	},
};

static int __init ntb_transport_init(void)
{
	int rc;

	if (debugfs_initialized())
		nt_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);

	rc = bus_register(&ntb_transport_bus);
	if (rc)
		goto err_bus;

	rc = ntb_register_client(&ntb_transport_client);
	if (rc)
		goto err_client;

	return 0;

err_client:
	bus_unregister(&ntb_transport_bus);
err_bus:
	debugfs_remove_recursive(nt_debugfs_dir);
	return rc;
}
module_init(ntb_transport_init);

static void __exit ntb_transport_exit(void)
{
	debugfs_remove_recursive(nt_debugfs_dir);

	ntb_unregister_client(&ntb_transport_client);
	bus_unregister(&ntb_transport_bus);
}
module_exit(ntb_transport_exit);