aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox/mlx4/main.c
blob: d498f049c74ecfa6578f02f1257e1063291bbe0d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2006, 2007 Cisco Systems, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     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
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/io-mapping.h>
#include <linux/delay.h>

#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>

#include "mlx4.h"
#include "fw.h"
#include "icm.h"

MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("Mellanox ConnectX HCA low-level driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);

struct workqueue_struct *mlx4_wq;

#ifdef CONFIG_MLX4_DEBUG

int mlx4_debug_level = 0;
module_param_named(debug_level, mlx4_debug_level, int, 0644);
MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0");

#endif /* CONFIG_MLX4_DEBUG */

#ifdef CONFIG_PCI_MSI

static int msi_x = 1;
module_param(msi_x, int, 0444);
MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");

#else /* CONFIG_PCI_MSI */

#define msi_x (0)

#endif /* CONFIG_PCI_MSI */

static int num_vfs;
module_param(num_vfs, int, 0444);
MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0");

static int probe_vf;
module_param(probe_vf, int, 0644);
MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");

int mlx4_log_num_mgm_entry_size = 10;
module_param_named(log_num_mgm_entry_size,
			mlx4_log_num_mgm_entry_size, int, 0444);
MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
					 " of qp per mcg, for example:"
					 " 10 gives 248.range: 9<="
					 " log_num_mgm_entry_size <= 12");

#define MLX4_VF                                        (1 << 0)

#define HCA_GLOBAL_CAP_MASK            0
#define PF_CONTEXT_BEHAVIOUR_MASK      0

static char mlx4_version[] __devinitdata =
	DRV_NAME ": Mellanox ConnectX core driver v"
	DRV_VERSION " (" DRV_RELDATE ")\n";

static struct mlx4_profile default_profile = {
	.num_qp		= 1 << 18,
	.num_srq	= 1 << 16,
	.rdmarc_per_qp	= 1 << 4,
	.num_cq		= 1 << 16,
	.num_mcg	= 1 << 13,
	.num_mpt	= 1 << 19,
	.num_mtt	= 1 << 20, /* It is really num mtt segements */
};

static int log_num_mac = 7;
module_param_named(log_num_mac, log_num_mac, int, 0444);
MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");

static int log_num_vlan;
module_param_named(log_num_vlan, log_num_vlan, int, 0444);
MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
/* Log2 max number of VLANs per ETH port (0-7) */
#define MLX4_LOG_NUM_VLANS 7

static bool use_prio;
module_param_named(use_prio, use_prio, bool, 0444);
MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
		  "(0/1, default 0)");

int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");

static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
static int arr_argc = 2;
module_param_array(port_type_array, int, &arr_argc, 0444);
MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
				"1 for IB, 2 for Ethernet");

struct mlx4_port_config {
	struct list_head list;
	enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
	struct pci_dev *pdev;
};

static inline int mlx4_master_get_num_eqs(struct mlx4_dev *dev)
{
	return dev->caps.reserved_eqs +
		MLX4_MFUNC_EQ_NUM * (dev->num_slaves + 1);
}

int mlx4_check_port_params(struct mlx4_dev *dev,
			   enum mlx4_port_type *port_type)
{
	int i;

	for (i = 0; i < dev->caps.num_ports - 1; i++) {
		if (port_type[i] != port_type[i + 1]) {
			if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) {
				mlx4_err(dev, "Only same port types supported "
					 "on this HCA, aborting.\n");
				return -EINVAL;
			}
			if (port_type[i] == MLX4_PORT_TYPE_ETH &&
			    port_type[i + 1] == MLX4_PORT_TYPE_IB)
				return -EINVAL;
		}
	}

	for (i = 0; i < dev->caps.num_ports; i++) {
		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
			mlx4_err(dev, "Requested port type for port %d is not "
				      "supported on this HCA\n", i + 1);
			return -EINVAL;
		}
	}
	return 0;
}

static void mlx4_set_port_mask(struct mlx4_dev *dev)
{
	int i;

	for (i = 1; i <= dev->caps.num_ports; ++i)
		dev->caps.port_mask[i] = dev->caps.port_type[i];
}

static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
	int err;
	int i;

	err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
	if (err) {
		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
		return err;
	}

	if (dev_cap->min_page_sz > PAGE_SIZE) {
		mlx4_err(dev, "HCA minimum page size of %d bigger than "
			 "kernel PAGE_SIZE of %ld, aborting.\n",
			 dev_cap->min_page_sz, PAGE_SIZE);
		return -ENODEV;
	}
	if (dev_cap->num_ports > MLX4_MAX_PORTS) {
		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
			 "aborting.\n",
			 dev_cap->num_ports, MLX4_MAX_PORTS);
		return -ENODEV;
	}

	if (dev_cap->uar_size > pci_resource_len(dev->pdev, 2)) {
		mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than "
			 "PCI resource 2 size of 0x%llx, aborting.\n",
			 dev_cap->uar_size,
			 (unsigned long long) pci_resource_len(dev->pdev, 2));
		return -ENODEV;
	}

	dev->caps.num_ports	     = dev_cap->num_ports;
	for (i = 1; i <= dev->caps.num_ports; ++i) {
		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
		dev->caps.gid_table_len[i]  = dev_cap->max_gids[i];
		dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
		dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
		dev->caps.eth_mtu_cap[i]    = dev_cap->eth_mtu[i];
		dev->caps.def_mac[i]        = dev_cap->def_mac[i];
		dev->caps.supported_type[i] = dev_cap->supported_port_types[i];
		dev->caps.suggested_type[i] = dev_cap->suggested_type[i];
		dev->caps.default_sense[i] = dev_cap->default_sense[i];
		dev->caps.trans_type[i]	    = dev_cap->trans_type[i];
		dev->caps.vendor_oui[i]     = dev_cap->vendor_oui[i];
		dev->caps.wavelength[i]     = dev_cap->wavelength[i];
		dev->caps.trans_code[i]     = dev_cap->trans_code[i];
	}

	dev->caps.uar_page_size	     = PAGE_SIZE;
	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
	dev->caps.bf_reg_size	     = dev_cap->bf_reg_size;
	dev->caps.bf_regs_per_page   = dev_cap->bf_regs_per_page;
	dev->caps.max_sq_sg	     = dev_cap->max_sq_sg;
	dev->caps.max_rq_sg	     = dev_cap->max_rq_sg;
	dev->caps.max_wqes	     = dev_cap->max_qp_sz;
	dev->caps.max_qp_init_rdma   = dev_cap->max_requester_per_qp;
	dev->caps.max_srq_wqes	     = dev_cap->max_srq_sz;
	dev->caps.max_srq_sge	     = dev_cap->max_rq_sg - 1;
	dev->caps.reserved_srqs	     = dev_cap->reserved_srqs;
	dev->caps.max_sq_desc_sz     = dev_cap->max_sq_desc_sz;
	dev->caps.max_rq_desc_sz     = dev_cap->max_rq_desc_sz;
	dev->caps.num_qp_per_mgm     = mlx4_get_qp_per_mgm(dev);
	/*
	 * Subtract 1 from the limit because we need to allocate a
	 * spare CQE so the HCA HW can tell the difference between an
	 * empty CQ and a full CQ.
	 */
	dev->caps.max_cqes	     = dev_cap->max_cq_sz - 1;
	dev->caps.reserved_cqs	     = dev_cap->reserved_cqs;
	dev->caps.reserved_eqs	     = dev_cap->reserved_eqs;
	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;

	/* The first 128 UARs are used for EQ doorbells */
	dev->caps.reserved_uars	     = max_t(int, 128, dev_cap->reserved_uars);
	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
					dev_cap->reserved_xrcds : 0;
	dev->caps.max_xrcds          = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
					dev_cap->max_xrcds : 0;
	dev->caps.mtt_entry_sz       = dev_cap->mtt_entry_sz;

	dev->caps.max_msg_sz         = dev_cap->max_msg_sz;
	dev->caps.page_size_cap	     = ~(u32) (dev_cap->min_page_sz - 1);
	dev->caps.flags		     = dev_cap->flags;
	dev->caps.bmme_flags	     = dev_cap->bmme_flags;
	dev->caps.reserved_lkey	     = dev_cap->reserved_lkey;
	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;

	/* Sense port always allowed on supported devices for ConnectX1 and 2 */
	if (dev->pdev->device != 0x1003)
		dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;

	dev->caps.log_num_macs  = log_num_mac;
	dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
	dev->caps.log_num_prios = use_prio ? 3 : 0;

	for (i = 1; i <= dev->caps.num_ports; ++i) {
		dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
		if (dev->caps.supported_type[i]) {
			/* if only ETH is supported - assign ETH */
			if (dev->caps.supported_type[i] == MLX4_PORT_TYPE_ETH)
				dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
			/* if only IB is supported,
			 * assign IB only if SRIOV is off*/
			else if (dev->caps.supported_type[i] ==
				 MLX4_PORT_TYPE_IB) {
				if (dev->flags & MLX4_FLAG_SRIOV)
					dev->caps.port_type[i] =
						MLX4_PORT_TYPE_NONE;
				else
					dev->caps.port_type[i] =
						MLX4_PORT_TYPE_IB;
			/* if IB and ETH are supported,
			 * first of all check if SRIOV is on */
			} else if (dev->flags & MLX4_FLAG_SRIOV)
				dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
			else {
				/* In non-SRIOV mode, we set the port type
				 * according to user selection of port type,
				 * if usere selected none, take the FW hint */
				if (port_type_array[i-1] == MLX4_PORT_TYPE_NONE)
					dev->caps.port_type[i] = dev->caps.suggested_type[i] ?
						MLX4_PORT_TYPE_ETH : MLX4_PORT_TYPE_IB;
				else
					dev->caps.port_type[i] = port_type_array[i-1];
			}
		}
		/*
		 * Link sensing is allowed on the port if 3 conditions are true:
		 * 1. Both protocols are supported on the port.
		 * 2. Different types are supported on the port
		 * 3. FW declared that it supports link sensing
		 */
		mlx4_priv(dev)->sense.sense_allowed[i] =
			((dev->caps.supported_type[i] == MLX4_PORT_TYPE_AUTO) &&
			 (dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
			 (dev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT));

		/*
		 * If "default_sense" bit is set, we move the port to "AUTO" mode
		 * and perform sense_port FW command to try and set the correct
		 * port type from beginning
		 */
		if (mlx4_priv(dev)->sense.sense_allowed[i] && dev->caps.default_sense[i]) {
			enum mlx4_port_type sensed_port = MLX4_PORT_TYPE_NONE;
			dev->caps.possible_type[i] = MLX4_PORT_TYPE_AUTO;
			mlx4_SENSE_PORT(dev, i, &sensed_port);
			if (sensed_port != MLX4_PORT_TYPE_NONE)
				dev->caps.port_type[i] = sensed_port;
		} else {
			dev->caps.possible_type[i] = dev->caps.port_type[i];
		}

		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
			mlx4_warn(dev, "Requested number of MACs is too much "
				  "for port %d, reducing to %d.\n",
				  i, 1 << dev->caps.log_num_macs);
		}
		if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
			dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
			mlx4_warn(dev, "Requested number of VLANs is too much "
				  "for port %d, reducing to %d.\n",
				  i, 1 << dev->caps.log_num_vlans);
		}
	}

	dev->caps.max_counters = 1 << ilog2(dev_cap->max_counters);

	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
		(1 << dev->caps.log_num_macs) *
		(1 << dev->caps.log_num_vlans) *
		(1 << dev->caps.log_num_prios) *
		dev->caps.num_ports;
	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;

	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] +
		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH];

	return 0;
}
/*The function checks if there are live vf, return the num of them*/
static int mlx4_how_many_lives_vf(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_slave_state *s_state;
	int i;
	int ret = 0;

	for (i = 1/*the ppf is 0*/; i < dev->num_slaves; ++i) {
		s_state = &priv->mfunc.master.slave_state[i];
		if (s_state->active && s_state->last_cmd !=
		    MLX4_COMM_CMD_RESET) {
			mlx4_warn(dev, "%s: slave: %d is still active\n",
				  __func__, i);
			ret++;
		}
	}
	return ret;
}

static int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_slave_state *s_slave;

	if (!mlx4_is_master(dev))
		return 0;

	s_slave = &priv->mfunc.master.slave_state[slave];
	return !!s_slave->active;
}
EXPORT_SYMBOL(mlx4_is_slave_active);

static int mlx4_slave_cap(struct mlx4_dev *dev)
{
	int			   err;
	u32			   page_size;
	struct mlx4_dev_cap	   dev_cap;
	struct mlx4_func_cap	   func_cap;
	struct mlx4_init_hca_param hca_param;
	int			   i;

	memset(&hca_param, 0, sizeof(hca_param));
	err = mlx4_QUERY_HCA(dev, &hca_param);
	if (err) {
		mlx4_err(dev, "QUERY_HCA command failed, aborting.\n");
		return err;
	}

	/*fail if the hca has an unknown capability */
	if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) !=
	    HCA_GLOBAL_CAP_MASK) {
		mlx4_err(dev, "Unknown hca global capabilities\n");
		return -ENOSYS;
	}

	mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;

	memset(&dev_cap, 0, sizeof(dev_cap));
	err = mlx4_dev_cap(dev, &dev_cap);
	if (err) {
		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
		return err;
	}

	page_size = ~dev->caps.page_size_cap + 1;
	mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
	if (page_size > PAGE_SIZE) {
		mlx4_err(dev, "HCA minimum page size of %d bigger than "
			 "kernel PAGE_SIZE of %ld, aborting.\n",
			 page_size, PAGE_SIZE);
		return -ENODEV;
	}

	/* slave gets uar page size from QUERY_HCA fw command */
	dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);

	/* TODO: relax this assumption */
	if (dev->caps.uar_page_size != PAGE_SIZE) {
		mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
			 dev->caps.uar_page_size, PAGE_SIZE);
		return -ENODEV;
	}

	memset(&func_cap, 0, sizeof(func_cap));
	err = mlx4_QUERY_FUNC_CAP(dev, &func_cap);
	if (err) {
		mlx4_err(dev, "QUERY_FUNC_CAP command failed, aborting.\n");
		return err;
	}

	if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
	    PF_CONTEXT_BEHAVIOUR_MASK) {
		mlx4_err(dev, "Unknown pf context behaviour\n");
		return -ENOSYS;
	}

	dev->caps.num_ports		= func_cap.num_ports;
	dev->caps.num_qps		= func_cap.qp_quota;
	dev->caps.num_srqs		= func_cap.srq_quota;
	dev->caps.num_cqs		= func_cap.cq_quota;
	dev->caps.num_eqs               = func_cap.max_eq;
	dev->caps.reserved_eqs          = func_cap.reserved_eq;
	dev->caps.num_mpts		= func_cap.mpt_quota;
	dev->caps.num_mtts		= func_cap.mtt_quota;
	dev->caps.num_pds               = MLX4_NUM_PDS;
	dev->caps.num_mgms              = 0;
	dev->caps.num_amgms             = 0;

	for (i = 1; i <= dev->caps.num_ports; ++i)
		dev->caps.port_mask[i] = dev->caps.port_type[i];

	if (dev->caps.num_ports > MLX4_MAX_PORTS) {
		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
			 "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS);
		return -ENODEV;
	}

	if (dev->caps.uar_page_size * (dev->caps.num_uars -
				       dev->caps.reserved_uars) >
				       pci_resource_len(dev->pdev, 2)) {
		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than "
			 "PCI resource 2 size of 0x%llx, aborting.\n",
			 dev->caps.uar_page_size * dev->caps.num_uars,
			 (unsigned long long) pci_resource_len(dev->pdev, 2));
		return -ENODEV;
	}

#if 0
	mlx4_warn(dev, "sqp_demux:%d\n", dev->caps.sqp_demux);
	mlx4_warn(dev, "num_uars:%d reserved_uars:%d uar region:0x%x bar2:0x%llx\n",
		  dev->caps.num_uars, dev->caps.reserved_uars,
		  dev->caps.uar_page_size * dev->caps.num_uars,
		  pci_resource_len(dev->pdev, 2));
	mlx4_warn(dev, "num_eqs:%d reserved_eqs:%d\n", dev->caps.num_eqs,
		  dev->caps.reserved_eqs);
	mlx4_warn(dev, "num_pds:%d reserved_pds:%d slave_pd_shift:%d pd_base:%d\n",
		  dev->caps.num_pds, dev->caps.reserved_pds,
		  dev->caps.slave_pd_shift, dev->caps.pd_base);
#endif
	return 0;
}

/*
 * Change the port configuration of the device.
 * Every user of this function must hold the port mutex.
 */
int mlx4_change_port_types(struct mlx4_dev *dev,
			   enum mlx4_port_type *port_types)
{
	int err = 0;
	int change = 0;
	int port;

	for (port = 0; port <  dev->caps.num_ports; port++) {
		/* Change the port type only if the new type is different
		 * from the current, and not set to Auto */
		if (port_types[port] != dev->caps.port_type[port + 1])
			change = 1;
	}
	if (change) {
		mlx4_unregister_device(dev);
		for (port = 1; port <= dev->caps.num_ports; port++) {
			mlx4_CLOSE_PORT(dev, port);
			dev->caps.port_type[port] = port_types[port - 1];
			err = mlx4_SET_PORT(dev, port);
			if (err) {
				mlx4_err(dev, "Failed to set port %d, "
					      "aborting\n", port);
				goto out;
			}
		}
		mlx4_set_port_mask(dev);
		err = mlx4_register_device(dev);
	}

out:
	return err;
}

static ssize_t show_port_type(struct device *dev,
			      struct device_attribute *attr,
			      char *buf)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_attr);
	struct mlx4_dev *mdev = info->dev;
	char type[8];

	sprintf(type, "%s",
		(mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_IB) ?
		"ib" : "eth");
	if (mdev->caps.possible_type[info->port] == MLX4_PORT_TYPE_AUTO)
		sprintf(buf, "auto (%s)\n", type);
	else
		sprintf(buf, "%s\n", type);

	return strlen(buf);
}

static ssize_t set_port_type(struct device *dev,
			     struct device_attribute *attr,
			     const char *buf, size_t count)
{
	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
						   port_attr);
	struct mlx4_dev *mdev = info->dev;
	struct mlx4_priv *priv = mlx4_priv(mdev);
	enum mlx4_port_type types[MLX4_MAX_PORTS];
	enum mlx4_port_type new_types[MLX4_MAX_PORTS];
	int i;
	int err = 0;

	if (!strcmp(buf, "ib\n"))
		info->tmp_type = MLX4_PORT_TYPE_IB;
	else if (!strcmp(buf, "eth\n"))
		info->tmp_type = MLX4_PORT_TYPE_ETH;
	else if (!strcmp(buf, "auto\n"))
		info->tmp_type = MLX4_PORT_TYPE_AUTO;
	else {
		mlx4_err(mdev, "%s is not supported port type\n", buf);
		return -EINVAL;
	}

	mlx4_stop_sense(mdev);
	mutex_lock(&priv->port_mutex);
	/* Possible type is always the one that was delivered */
	mdev->caps.possible_type[info->port] = info->tmp_type;

	for (i = 0; i < mdev->caps.num_ports; i++) {
		types[i] = priv->port[i+1].tmp_type ? priv->port[i+1].tmp_type :
					mdev->caps.possible_type[i+1];
		if (types[i] == MLX4_PORT_TYPE_AUTO)
			types[i] = mdev->caps.port_type[i+1];
	}

	if (!(mdev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
	    !(mdev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT)) {
		for (i = 1; i <= mdev->caps.num_ports; i++) {
			if (mdev->caps.possible_type[i] == MLX4_PORT_TYPE_AUTO) {
				mdev->caps.possible_type[i] = mdev->caps.port_type[i];
				err = -EINVAL;
			}
		}
	}
	if (err) {
		mlx4_err(mdev, "Auto sensing is not supported on this HCA. "
			       "Set only 'eth' or 'ib' for both ports "
			       "(should be the same)\n");
		goto out;
	}

	mlx4_do_sense_ports(mdev, new_types, types);

	err = mlx4_check_port_params(mdev, new_types);
	if (err)
		goto out;

	/* We are about to apply the changes after the configuration
	 * was verified, no need to remember the temporary types
	 * any more */
	for (i = 0; i < mdev->caps.num_ports; i++)
		priv->port[i + 1].tmp_type = 0;

	err = mlx4_change_port_types(mdev, new_types);

out:
	mlx4_start_sense(mdev);
	mutex_unlock(&priv->port_mutex);
	return err ? err : count;
}

static int mlx4_load_fw(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;

	priv->fw.fw_icm = mlx4_alloc_icm(dev, priv->fw.fw_pages,
					 GFP_HIGHUSER | __GFP_NOWARN, 0);
	if (!priv->fw.fw_icm) {
		mlx4_err(dev, "Couldn't allocate FW area, aborting.\n");
		return -ENOMEM;
	}

	err = mlx4_MAP_FA(dev, priv->fw.fw_icm);
	if (err) {
		mlx4_err(dev, "MAP_FA command failed, aborting.\n");
		goto err_free;
	}

	err = mlx4_RUN_FW(dev);
	if (err) {
		mlx4_err(dev, "RUN_FW command failed, aborting.\n");
		goto err_unmap_fa;
	}

	return 0;

err_unmap_fa:
	mlx4_UNMAP_FA(dev);

err_free:
	mlx4_free_icm(dev, priv->fw.fw_icm, 0);
	return err;
}

static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
				int cmpt_entry_sz)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;
	int num_eqs;

	err = mlx4_init_icm_table(dev, &priv->qp_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_QP *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err)
		goto err;

	err = mlx4_init_icm_table(dev, &priv->srq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_SRQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_srqs,
				  dev->caps.reserved_srqs, 0, 0);
	if (err)
		goto err_qp;

	err = mlx4_init_icm_table(dev, &priv->cq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_CQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, dev->caps.num_cqs,
				  dev->caps.reserved_cqs, 0, 0);
	if (err)
		goto err_srq;

	num_eqs = (mlx4_is_master(dev)) ?
		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
		dev->caps.num_eqs;
	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
				  cmpt_base +
				  ((u64) (MLX4_CMPT_TYPE_EQ *
					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
				  cmpt_entry_sz, num_eqs, num_eqs, 0, 0);
	if (err)
		goto err_cq;

	return 0;

err_cq:
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);

err_srq:
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);

err_qp:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

err:
	return err;
}

static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
			 struct mlx4_init_hca_param *init_hca, u64 icm_size)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	u64 aux_pages;
	int num_eqs;
	int err;

	err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages);
	if (err) {
		mlx4_err(dev, "SET_ICM_SIZE command failed, aborting.\n");
		return err;
	}

	mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory.\n",
		 (unsigned long long) icm_size >> 10,
		 (unsigned long long) aux_pages << 2);

	priv->fw.aux_icm = mlx4_alloc_icm(dev, aux_pages,
					  GFP_HIGHUSER | __GFP_NOWARN, 0);
	if (!priv->fw.aux_icm) {
		mlx4_err(dev, "Couldn't allocate aux memory, aborting.\n");
		return -ENOMEM;
	}

	err = mlx4_MAP_ICM_AUX(dev, priv->fw.aux_icm);
	if (err) {
		mlx4_err(dev, "MAP_ICM_AUX command failed, aborting.\n");
		goto err_free_aux;
	}

	err = mlx4_init_cmpt_table(dev, init_hca->cmpt_base, dev_cap->cmpt_entry_sz);
	if (err) {
		mlx4_err(dev, "Failed to map cMPT context memory, aborting.\n");
		goto err_unmap_aux;
	}


	num_eqs = (mlx4_is_master(dev)) ?
		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
		dev->caps.num_eqs;
	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
				  num_eqs, num_eqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map EQ context memory, aborting.\n");
		goto err_unmap_cmpt;
	}

	/*
	 * Reserved MTT entries must be aligned up to a cacheline
	 * boundary, since the FW will write to them, while the driver
	 * writes to all other MTT entries. (The variable
	 * dev->caps.mtt_entry_sz below is really the MTT segment
	 * size, not the raw entry size)
	 */
	dev->caps.reserved_mtts =
		ALIGN(dev->caps.reserved_mtts * dev->caps.mtt_entry_sz,
		      dma_get_cache_alignment()) / dev->caps.mtt_entry_sz;

	err = mlx4_init_icm_table(dev, &priv->mr_table.mtt_table,
				  init_hca->mtt_base,
				  dev->caps.mtt_entry_sz,
				  dev->caps.num_mtts,
				  dev->caps.reserved_mtts, 1, 0);
	if (err) {
		mlx4_err(dev, "Failed to map MTT context memory, aborting.\n");
		goto err_unmap_eq;
	}

	err = mlx4_init_icm_table(dev, &priv->mr_table.dmpt_table,
				  init_hca->dmpt_base,
				  dev_cap->dmpt_entry_sz,
				  dev->caps.num_mpts,
				  dev->caps.reserved_mrws, 1, 1);
	if (err) {
		mlx4_err(dev, "Failed to map dMPT context memory, aborting.\n");
		goto err_unmap_mtt;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.qp_table,
				  init_hca->qpc_base,
				  dev_cap->qpc_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map QP context memory, aborting.\n");
		goto err_unmap_dmpt;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.auxc_table,
				  init_hca->auxc_base,
				  dev_cap->aux_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n");
		goto err_unmap_qp;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.altc_table,
				  init_hca->altc_base,
				  dev_cap->altc_entry_sz,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n");
		goto err_unmap_auxc;
	}

	err = mlx4_init_icm_table(dev, &priv->qp_table.rdmarc_table,
				  init_hca->rdmarc_base,
				  dev_cap->rdmarc_entry_sz << priv->qp_table.rdmarc_shift,
				  dev->caps.num_qps,
				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map RDMARC context memory, aborting\n");
		goto err_unmap_altc;
	}

	err = mlx4_init_icm_table(dev, &priv->cq_table.table,
				  init_hca->cqc_base,
				  dev_cap->cqc_entry_sz,
				  dev->caps.num_cqs,
				  dev->caps.reserved_cqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map CQ context memory, aborting.\n");
		goto err_unmap_rdmarc;
	}

	err = mlx4_init_icm_table(dev, &priv->srq_table.table,
				  init_hca->srqc_base,
				  dev_cap->srq_entry_sz,
				  dev->caps.num_srqs,
				  dev->caps.reserved_srqs, 0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map SRQ context memory, aborting.\n");
		goto err_unmap_cq;
	}

	/*
	 * It's not strictly required, but for simplicity just map the
	 * whole multicast group table now.  The table isn't very big
	 * and it's a lot easier than trying to track ref counts.
	 */
	err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
				  init_hca->mc_base,
				  mlx4_get_mgm_entry_size(dev),
				  dev->caps.num_mgms + dev->caps.num_amgms,
				  dev->caps.num_mgms + dev->caps.num_amgms,
				  0, 0);
	if (err) {
		mlx4_err(dev, "Failed to map MCG context memory, aborting.\n");
		goto err_unmap_srq;
	}

	return 0;

err_unmap_srq:
	mlx4_cleanup_icm_table(dev, &priv->srq_table.table);

err_unmap_cq:
	mlx4_cleanup_icm_table(dev, &priv->cq_table.table);

err_unmap_rdmarc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.rdmarc_table);

err_unmap_altc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.altc_table);

err_unmap_auxc:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.auxc_table);

err_unmap_qp:
	mlx4_cleanup_icm_table(dev, &priv->qp_table.qp_table);

err_unmap_dmpt:
	mlx4_cleanup_icm_table(dev, &priv->mr_table.dmpt_table);

err_unmap_mtt:
	mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table);

err_unmap_eq:
	mlx4_cleanup_icm_table(dev, &priv->eq_table.table);

err_unmap_cmpt:
	mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

err_unmap_aux:
	mlx4_UNMAP_ICM_AUX(dev);

err_free_aux:
	mlx4_free_icm(dev, priv->fw.aux_icm, 0);

	return err;
}

static void mlx4_free_icms(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	mlx4_cleanup_icm_table(dev, &priv->mcg_table.table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.rdmarc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.altc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.auxc_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.qp_table);
	mlx4_cleanup_icm_table(dev, &priv->mr_table.dmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->mr_table.mtt_table);
	mlx4_cleanup_icm_table(dev, &priv->eq_table.table);
	mlx4_cleanup_icm_table(dev, &priv->eq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->cq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->srq_table.cmpt_table);
	mlx4_cleanup_icm_table(dev, &priv->qp_table.cmpt_table);

	mlx4_UNMAP_ICM_AUX(dev);
	mlx4_free_icm(dev, priv->fw.aux_icm, 0);
}

static void mlx4_slave_exit(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	down(&priv->cmd.slave_sem);
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME))
		mlx4_warn(dev, "Failed to close slave function.\n");
	up(&priv->cmd.slave_sem);
}

static int map_bf_area(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	resource_size_t bf_start;
	resource_size_t bf_len;
	int err = 0;

	if (!dev->caps.bf_reg_size)
		return -ENXIO;

	bf_start = pci_resource_start(dev->pdev, 2) +
			(dev->caps.num_uars << PAGE_SHIFT);
	bf_len = pci_resource_len(dev->pdev, 2) -
			(dev->caps.num_uars << PAGE_SHIFT);
	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
	if (!priv->bf_mapping)
		err = -ENOMEM;

	return err;
}

static void unmap_bf_area(struct mlx4_dev *dev)
{
	if (mlx4_priv(dev)->bf_mapping)
		io_mapping_free(mlx4_priv(dev)->bf_mapping);
}

static void mlx4_close_hca(struct mlx4_dev *dev)
{
	unmap_bf_area(dev);
	if (mlx4_is_slave(dev))
		mlx4_slave_exit(dev);
	else {
		mlx4_CLOSE_HCA(dev, 0);
		mlx4_free_icms(dev);
		mlx4_UNMAP_FA(dev);
		mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
	}
}

static int mlx4_init_slave(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	u64 dma = (u64) priv->mfunc.vhcr_dma;
	int num_of_reset_retries = NUM_OF_RESET_RETRIES;
	int ret_from_reset = 0;
	u32 slave_read;
	u32 cmd_channel_ver;

	down(&priv->cmd.slave_sem);
	priv->cmd.max_cmds = 1;
	mlx4_warn(dev, "Sending reset\n");
	ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0,
				       MLX4_COMM_TIME);
	/* if we are in the middle of flr the slave will try
	 * NUM_OF_RESET_RETRIES times before leaving.*/
	if (ret_from_reset) {
		if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) {
			msleep(SLEEP_TIME_IN_RESET);
			while (ret_from_reset && num_of_reset_retries) {
				mlx4_warn(dev, "slave is currently in the"
					  "middle of FLR. retrying..."
					  "(try num:%d)\n",
					  (NUM_OF_RESET_RETRIES -
					   num_of_reset_retries  + 1));
				ret_from_reset =
					mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET,
						      0, MLX4_COMM_TIME);
				num_of_reset_retries = num_of_reset_retries - 1;
			}
		} else
			goto err;
	}

	/* check the driver version - the slave I/F revision
	 * must match the master's */
	slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
	cmd_channel_ver = mlx4_comm_get_version();

	if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) !=
		MLX4_COMM_GET_IF_REV(slave_read)) {
		mlx4_err(dev, "slave driver version is not supported"
			 " by the master\n");
		goto err;
	}

	mlx4_warn(dev, "Sending vhcr0\n");
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR0, dma >> 48,
						    MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR1, dma >> 32,
						    MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR2, dma >> 16,
						    MLX4_COMM_TIME))
		goto err;
	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_EN, dma, MLX4_COMM_TIME))
		goto err;
	up(&priv->cmd.slave_sem);
	return 0;

err:
	mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, 0);
	up(&priv->cmd.slave_sem);
	return -EIO;
}

static int mlx4_init_hca(struct mlx4_dev *dev)
{
	struct mlx4_priv	  *priv = mlx4_priv(dev);
	struct mlx4_adapter	   adapter;
	struct mlx4_dev_cap	   dev_cap;
	struct mlx4_mod_stat_cfg   mlx4_cfg;
	struct mlx4_profile	   profile;
	struct mlx4_init_hca_param init_hca;
	u64 icm_size;
	int err;

	if (!mlx4_is_slave(dev)) {
		err = mlx4_QUERY_FW(dev);
		if (err) {
			if (err == -EACCES)
				mlx4_info(dev, "non-primary physical function, skipping.\n");
			else
				mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
			goto unmap_bf;
		}

		err = mlx4_load_fw(dev);
		if (err) {
			mlx4_err(dev, "Failed to start FW, aborting.\n");
			goto unmap_bf;
		}

		mlx4_cfg.log_pg_sz_m = 1;
		mlx4_cfg.log_pg_sz = 0;
		err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
		if (err)
			mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");

		err = mlx4_dev_cap(dev, &dev_cap);
		if (err) {
			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
			goto err_stop_fw;
		}

		profile = default_profile;

		icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
					     &init_hca);
		if ((long long) icm_size < 0) {
			err = icm_size;
			goto err_stop_fw;
		}

		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
		init_hca.uar_page_sz = PAGE_SHIFT - 12;

		err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
		if (err)
			goto err_stop_fw;

		err = mlx4_INIT_HCA(dev, &init_hca);
		if (err) {
			mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
			goto err_free_icm;
		}
	} else {
		err = mlx4_init_slave(dev);
		if (err) {
			mlx4_err(dev, "Failed to initialize slave\n");
			goto unmap_bf;
		}

		err = mlx4_slave_cap(dev);
		if (err) {
			mlx4_err(dev, "Failed to obtain slave caps\n");
			goto err_close;
		}
	}

	if (map_bf_area(dev))
		mlx4_dbg(dev, "Failed to map blue flame area\n");

	/*Only the master set the ports, all the rest got it from it.*/
	if (!mlx4_is_slave(dev))
		mlx4_set_port_mask(dev);

	err = mlx4_QUERY_ADAPTER(dev, &adapter);
	if (err) {
		mlx4_err(dev, "QUERY_ADAPTER command failed, aborting.\n");
		goto err_close;
	}

	priv->eq_table.inta_pin = adapter.inta_pin;
	memcpy(dev->board_id, adapter.board_id, sizeof dev->board_id);

	return 0;

err_close:
	mlx4_close_hca(dev);

err_free_icm:
	if (!mlx4_is_slave(dev))
		mlx4_free_icms(dev);

err_stop_fw:
	if (!mlx4_is_slave(dev)) {
		mlx4_UNMAP_FA(dev);
		mlx4_free_icm(dev, priv->fw.fw_icm, 0);
	}
unmap_bf:
	unmap_bf_area(dev);
	return err;
}

static int mlx4_init_counters_table(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int nent;

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return -ENOENT;

	nent = dev->caps.max_counters;
	return mlx4_bitmap_init(&priv->counters_bitmap, nent, nent - 1, 0, 0);
}

static void mlx4_cleanup_counters_table(struct mlx4_dev *dev)
{
	mlx4_bitmap_cleanup(&mlx4_priv(dev)->counters_bitmap);
}

int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
{
	struct mlx4_priv *priv = mlx4_priv(dev);

	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
		return -ENOENT;

	*idx = mlx4_bitmap_alloc(&priv->counters_bitmap);
	if (*idx == -1)
		return -ENOMEM;

	return 0;
}
EXPORT_SYMBOL_GPL(mlx4_counter_alloc);

void mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
{
	mlx4_bitmap_free(&mlx4_priv(dev)->counters_bitmap, idx);
	return;
}
EXPORT_SYMBOL_GPL(mlx4_counter_free);

static int mlx4_setup_hca(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int err;
	int port;
	__be32 ib_port_default_caps;

	err = mlx4_init_uar_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "user access region table, aborting.\n");
		return err;
	}

	err = mlx4_uar_alloc(dev, &priv->driver_uar);
	if (err) {
		mlx4_err(dev, "Failed to allocate driver access region, "
			 "aborting.\n");
		goto err_uar_table_free;
	}

	priv->kar = ioremap((phys_addr_t) priv->driver_uar.pfn << PAGE_SHIFT, PAGE_SIZE);
	if (!priv->kar) {
		mlx4_err(dev, "Couldn't map kernel access region, "
			 "aborting.\n");
		err = -ENOMEM;
		goto err_uar_free;
	}

	err = mlx4_init_pd_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "protection domain table, aborting.\n");
		goto err_kar_unmap;
	}

	err = mlx4_init_xrcd_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "reliable connection domain table, aborting.\n");
		goto err_pd_table_free;
	}

	err = mlx4_init_mr_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "memory region table, aborting.\n");
		goto err_xrcd_table_free;
	}

	err = mlx4_init_eq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "event queue table, aborting.\n");
		goto err_mr_table_free;
	}

	err = mlx4_cmd_use_events(dev);
	if (err) {
		mlx4_err(dev, "Failed to switch to event-driven "
			 "firmware commands, aborting.\n");
		goto err_eq_table_free;
	}

	err = mlx4_NOP(dev);
	if (err) {
		if (dev->flags & MLX4_FLAG_MSI_X) {
			mlx4_warn(dev, "NOP command failed to generate MSI-X "
				  "interrupt IRQ %d).\n",
				  priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
			mlx4_warn(dev, "Trying again without MSI-X.\n");
		} else {
			mlx4_err(dev, "NOP command failed to generate interrupt "
				 "(IRQ %d), aborting.\n",
				 priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
			mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n");
		}

		goto err_cmd_poll;
	}

	mlx4_dbg(dev, "NOP command IRQ test passed\n");

	err = mlx4_init_cq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "completion queue table, aborting.\n");
		goto err_cmd_poll;
	}

	err = mlx4_init_srq_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "shared receive queue table, aborting.\n");
		goto err_cq_table_free;
	}

	err = mlx4_init_qp_table(dev);
	if (err) {
		mlx4_err(dev, "Failed to initialize "
			 "queue pair table, aborting.\n");
		goto err_srq_table_free;
	}

	if (!mlx4_is_slave(dev)) {
		err = mlx4_init_mcg_table(dev);
		if (err) {
			mlx4_err(dev, "Failed to initialize "
				 "multicast group table, aborting.\n");
			goto err_qp_table_free;
		}
	}

	err = mlx4_init_counters_table(dev);
	if (err && err != -ENOENT) {
		mlx4_err(dev, "Failed to initialize counters table, aborting.\n");
		goto err_mcg_table_free;
	}

	if (!mlx4_is_slave(dev)) {
		for (port = 1; port <= dev->caps.num_ports; port++) {
			ib_port_default_caps = 0;
			err = mlx4_get_port_ib_caps(dev, port,
						    &ib_port_default_caps);
			if (err)
				mlx4_warn(dev, "failed to get port %d default "
					  "ib capabilities (%d). Continuing "
					  "with caps = 0\n", port, err);
			dev->caps.ib_port_def_cap[port] = ib_port_default_caps;

			err = mlx4_check_ext_port_caps(dev, port);
			if (err)
				mlx4_warn(dev, "failed to get port %d extended "
					  "port capabilities support info (%d)."
					  " Assuming not supported\n",
					  port, err);

			err = mlx4_SET_PORT(dev, port);
			if (err) {
				mlx4_err(dev, "Failed to set port %d, aborting\n",
					port);
				goto err_counters_table_free;
			}
		}
	}

	return 0;

err_counters_table_free:
	mlx4_cleanup_counters_table(dev);

err_mcg_table_free:
	mlx4_cleanup_mcg_table(dev);

err_qp_table_free:
	mlx4_cleanup_qp_table(dev);

err_srq_table_free:
	mlx4_cleanup_srq_table(dev);

err_cq_table_free:
	mlx4_cleanup_cq_table(dev);

err_cmd_poll:
	mlx4_cmd_use_polling(dev);

err_eq_table_free:
	mlx4_cleanup_eq_table(dev);

err_mr_table_free:
	mlx4_cleanup_mr_table(dev);

err_xrcd_table_free:
	mlx4_cleanup_xrcd_table(dev);

err_pd_table_free:
	mlx4_cleanup_pd_table(dev);

err_kar_unmap:
	iounmap(priv->kar);

err_uar_free:
	mlx4_uar_free(dev, &priv->driver_uar);

err_uar_table_free:
	mlx4_cleanup_uar_table(dev);
	return err;
}

static void mlx4_enable_msi_x(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct msix_entry *entries;
	int nreq = min_t(int, dev->caps.num_ports *
			 min_t(int, num_online_cpus() + 1, MAX_MSIX_P_PORT)
				+ MSIX_LEGACY_SZ, MAX_MSIX);
	int err;
	int i;

	if (msi_x) {
		/* In multifunction mode each function gets 2 msi-X vectors
		 * one for data path completions anf the other for asynch events
		 * or command completions */
		if (mlx4_is_mfunc(dev)) {
			nreq = 2;
		} else {
			nreq = min_t(int, dev->caps.num_eqs -
				     dev->caps.reserved_eqs, nreq);
		}

		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
		if (!entries)
			goto no_msi;

		for (i = 0; i < nreq; ++i)
			entries[i].entry = i;

	retry:
		err = pci_enable_msix(dev->pdev, entries, nreq);
		if (err) {
			/* Try again if at least 2 vectors are available */
			if (err > 1) {
				mlx4_info(dev, "Requested %d vectors, "
					  "but only %d MSI-X vectors available, "
					  "trying again\n", nreq, err);
				nreq = err;
				goto retry;
			}
			kfree(entries);
			goto no_msi;
		}

		if (nreq <
		    MSIX_LEGACY_SZ + dev->caps.num_ports * MIN_MSIX_P_PORT) {
			/*Working in legacy mode , all EQ's shared*/
			dev->caps.comp_pool           = 0;
			dev->caps.num_comp_vectors = nreq - 1;
		} else {
			dev->caps.comp_pool           = nreq - MSIX_LEGACY_SZ;
			dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1;
		}
		for (i = 0; i < nreq; ++i)
			priv->eq_table.eq[i].irq = entries[i].vector;

		dev->flags |= MLX4_FLAG_MSI_X;

		kfree(entries);
		return;
	}

no_msi:
	dev->caps.num_comp_vectors = 1;
	dev->caps.comp_pool	   = 0;

	for (i = 0; i < 2; ++i)
		priv->eq_table.eq[i].irq = dev->pdev->irq;
}

static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
{
	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
	int err = 0;

	info->dev = dev;
	info->port = port;
	if (!mlx4_is_slave(dev)) {
		INIT_RADIX_TREE(&info->mac_tree, GFP_KERNEL);
		mlx4_init_mac_table(dev, &info->mac_table);
		mlx4_init_vlan_table(dev, &info->vlan_table);
		info->base_qpn =
			dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
			(port - 1) * (1 << log_num_mac);
	}

	sprintf(info->dev_name, "mlx4_port%d", port);
	info->port_attr.attr.name = info->dev_name;
	if (mlx4_is_mfunc(dev))
		info->port_attr.attr.mode = S_IRUGO;
	else {
		info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
		info->port_attr.store     = set_port_type;
	}
	info->port_attr.show      = show_port_type;
	sysfs_attr_init(&info->port_attr.attr);

	err = device_create_file(&dev->pdev->dev, &info->port_attr);
	if (err) {
		mlx4_err(dev, "Failed to create file for port %d\n", port);
		info->port = -1;
	}

	return err;
}

static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
{
	if (info->port < 0)
		return;

	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
}

static int mlx4_init_steering(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	int num_entries = dev->caps.num_ports;
	int i, j;

	priv->steer = kzalloc(sizeof(struct mlx4_steer) * num_entries, GFP_KERNEL);
	if (!priv->steer)
		return -ENOMEM;

	for (i = 0; i < num_entries; i++) {
		for (j = 0; j < MLX4_NUM_STEERS; j++) {
			INIT_LIST_HEAD(&priv->steer[i].promisc_qps[j]);
			INIT_LIST_HEAD(&priv->steer[i].steer_entries[j]);
		}
		INIT_LIST_HEAD(&priv->steer[i].high_prios);
	}
	return 0;
}

static void mlx4_clear_steering(struct mlx4_dev *dev)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_steer_index *entry, *tmp_entry;
	struct mlx4_promisc_qp *pqp, *tmp_pqp;
	int num_entries = dev->caps.num_ports;
	int i, j;

	for (i = 0; i < num_entries; i++) {
		for (j = 0; j < MLX4_NUM_STEERS; j++) {
			list_for_each_entry_safe(pqp, tmp_pqp,
						 &priv->steer[i].promisc_qps[j],
						 list) {
				list_del(&pqp->list);
				kfree(pqp);
			}
			list_for_each_entry_safe(entry, tmp_entry,
						 &priv->steer[i].steer_entries[j],
						 list) {
				list_del(&entry->list);
				list_for_each_entry_safe(pqp, tmp_pqp,
							 &entry->duplicates,
							 list) {
					list_del(&pqp->list);
					kfree(pqp);
				}
				kfree(entry);
			}
		}
	}
	kfree(priv->steer);
}

static int extended_func_num(struct pci_dev *pdev)
{
	return PCI_SLOT(pdev->devfn) * 8 + PCI_FUNC(pdev->devfn);
}

#define MLX4_OWNER_BASE	0x8069c
#define MLX4_OWNER_SIZE	4

static int mlx4_get_ownership(struct mlx4_dev *dev)
{
	void __iomem *owner;
	u32 ret;

	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
			MLX4_OWNER_SIZE);
	if (!owner) {
		mlx4_err(dev, "Failed to obtain ownership bit\n");
		return -ENOMEM;
	}

	ret = readl(owner);
	iounmap(owner);
	return (int) !!ret;
}

static void mlx4_free_ownership(struct mlx4_dev *dev)
{
	void __iomem *owner;

	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
			MLX4_OWNER_SIZE);
	if (!owner) {
		mlx4_err(dev, "Failed to obtain ownership bit\n");
		return;
	}
	writel(0, owner);
	msleep(1000);
	iounmap(owner);
}

static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct mlx4_priv *priv;
	struct mlx4_dev *dev;
	int err;
	int port;

	pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));

	err = pci_enable_device(pdev);
	if (err) {
		dev_err(&pdev->dev, "Cannot enable PCI device, "
			"aborting.\n");
		return err;
	}
	if (num_vfs > MLX4_MAX_NUM_VF) {
		printk(KERN_ERR "There are more VF's (%d) than allowed(%d)\n",
		       num_vfs, MLX4_MAX_NUM_VF);
		return -EINVAL;
	}
	/*
	 * Check for BARs.
	 */
	if (((id == NULL) || !(id->driver_data & MLX4_VF)) &&
	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
		dev_err(&pdev->dev, "Missing DCS, aborting."
			"(id == 0X%p, id->driver_data: 0x%lx,"
			" pci_resource_flags(pdev, 0):0x%lx)\n", id,
			id ? id->driver_data : 0, pci_resource_flags(pdev, 0));
		err = -ENODEV;
		goto err_disable_pdev;
	}
	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
		dev_err(&pdev->dev, "Missing UAR, aborting.\n");
		err = -ENODEV;
		goto err_disable_pdev;
	}

	err = pci_request_regions(pdev, DRV_NAME);
	if (err) {
		dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n");
		goto err_disable_pdev;
	}

	pci_set_master(pdev);

	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
	if (err) {
		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask.\n");
		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting.\n");
			goto err_release_regions;
		}
	}
	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
	if (err) {
		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit "
			 "consistent PCI DMA mask.\n");
		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, "
				"aborting.\n");
			goto err_release_regions;
		}
	}

	/* Allow large DMA segments, up to the firmware limit of 1 GB */
	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);

	priv = kzalloc(sizeof *priv, GFP_KERNEL);
	if (!priv) {
		dev_err(&pdev->dev, "Device struct alloc failed, "
			"aborting.\n");
		err = -ENOMEM;
		goto err_release_regions;
	}

	dev       = &priv->dev;
	dev->pdev = pdev;
	INIT_LIST_HEAD(&priv->ctx_list);
	spin_lock_init(&priv->ctx_lock);

	mutex_init(&priv->port_mutex);

	INIT_LIST_HEAD(&priv->pgdir_list);
	mutex_init(&priv->pgdir_mutex);

	INIT_LIST_HEAD(&priv->bf_list);
	mutex_init(&priv->bf_mutex);

	dev->rev_id = pdev->revision;
	/* Detect if this device is a virtual function */
	if (id && id->driver_data & MLX4_VF) {
		/* When acting as pf, we normally skip vfs unless explicitly
		 * requested to probe them. */
		if (num_vfs && extended_func_num(pdev) > probe_vf) {
			mlx4_warn(dev, "Skipping virtual function:%d\n",
						extended_func_num(pdev));
			err = -ENODEV;
			goto err_free_dev;
		}
		mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
		dev->flags |= MLX4_FLAG_SLAVE;
	} else {
		/* We reset the device and enable SRIOV only for physical
		 * devices.  Try to claim ownership on the device;
		 * if already taken, skip -- do not allow multiple PFs */
		err = mlx4_get_ownership(dev);
		if (err) {
			if (err < 0)
				goto err_free_dev;
			else {
				mlx4_warn(dev, "Multiple PFs not yet supported."
					  " Skipping PF.\n");
				err = -EINVAL;
				goto err_free_dev;
			}
		}

		if (num_vfs) {
			mlx4_warn(dev, "Enabling sriov with:%d vfs\n", num_vfs);
			err = pci_enable_sriov(pdev, num_vfs);
			if (err) {
				mlx4_err(dev, "Failed to enable sriov,"
					 "continuing without sriov enabled"
					 " (err = %d).\n", err);
				num_vfs = 0;
				err = 0;
			} else {
				mlx4_warn(dev, "Running in master mode\n");
				dev->flags |= MLX4_FLAG_SRIOV |
					      MLX4_FLAG_MASTER;
				dev->num_vfs = num_vfs;
			}
		}

		/*
		 * Now reset the HCA before we touch the PCI capabilities or
		 * attempt a firmware command, since a boot ROM may have left
		 * the HCA in an undefined state.
		 */
		err = mlx4_reset(dev);
		if (err) {
			mlx4_err(dev, "Failed to reset HCA, aborting.\n");
			goto err_rel_own;
		}
	}

slave_start:
	if (mlx4_cmd_init(dev)) {
		mlx4_err(dev, "Failed to init command interface, aborting.\n");
		goto err_sriov;
	}

	/* In slave functions, the communication channel must be initialized
	 * before posting commands. Also, init num_slaves before calling
	 * mlx4_init_hca */
	if (mlx4_is_mfunc(dev)) {
		if (mlx4_is_master(dev))
			dev->num_slaves = MLX4_MAX_NUM_SLAVES;
		else {
			dev->num_slaves = 0;
			if (mlx4_multi_func_init(dev)) {
				mlx4_err(dev, "Failed to init slave mfunc"
					 " interface, aborting.\n");
				goto err_cmd;
			}
		}
	}

	err = mlx4_init_hca(dev);
	if (err) {
		if (err == -EACCES) {
			/* Not primary Physical function
			 * Running in slave mode */
			mlx4_cmd_cleanup(dev);
			dev->flags |= MLX4_FLAG_SLAVE;
			dev->flags &= ~MLX4_FLAG_MASTER;
			goto slave_start;
		} else
			goto err_mfunc;
	}

	/* In master functions, the communication channel must be initialized
	 * after obtaining its address from fw */
	if (mlx4_is_master(dev)) {
		if (mlx4_multi_func_init(dev)) {
			mlx4_err(dev, "Failed to init master mfunc"
				 "interface, aborting.\n");
			goto err_close;
		}
	}

	err = mlx4_alloc_eq_table(dev);
	if (err)
		goto err_master_mfunc;

	priv->msix_ctl.pool_bm = 0;
	mutex_init(&priv->msix_ctl.pool_lock);

	mlx4_enable_msi_x(dev);
	if ((mlx4_is_mfunc(dev)) &&
	    !(dev->flags & MLX4_FLAG_MSI_X)) {
		mlx4_err(dev, "INTx is not supported in multi-function mode."
			 " aborting.\n");
		goto err_free_eq;
	}

	if (!mlx4_is_slave(dev)) {
		err = mlx4_init_steering(dev);
		if (err)
			goto err_free_eq;
	}

	err = mlx4_setup_hca(dev);
	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X) &&
	    !mlx4_is_mfunc(dev)) {
		dev->flags &= ~MLX4_FLAG_MSI_X;
		pci_disable_msix(pdev);
		err = mlx4_setup_hca(dev);
	}

	if (err)
		goto err_steer;

	for (port = 1; port <= dev->caps.num_ports; port++) {
		err = mlx4_init_port_info(dev, port);
		if (err)
			goto err_port;
	}

	err = mlx4_register_device(dev);
	if (err)
		goto err_port;

	mlx4_sense_init(dev);
	mlx4_start_sense(dev);

	pci_set_drvdata(pdev, dev);

	return 0;

err_port:
	for (--port; port >= 1; --port)
		mlx4_cleanup_port_info(&priv->port[port]);

	mlx4_cleanup_counters_table(dev);
	mlx4_cleanup_mcg_table(dev);
	mlx4_cleanup_qp_table(dev);
	mlx4_cleanup_srq_table(dev);
	mlx4_cleanup_cq_table(dev);
	mlx4_cmd_use_polling(dev);
	mlx4_cleanup_eq_table(dev);
	mlx4_cleanup_mr_table(dev);
	mlx4_cleanup_xrcd_table(dev);
	mlx4_cleanup_pd_table(dev);
	mlx4_cleanup_uar_table(dev);

err_steer:
	if (!mlx4_is_slave(dev))
		mlx4_clear_steering(dev);

err_free_eq:
	mlx4_free_eq_table(dev);

err_master_mfunc:
	if (mlx4_is_master(dev))
		mlx4_multi_func_cleanup(dev);

err_close:
	if (dev->flags & MLX4_FLAG_MSI_X)
		pci_disable_msix(pdev);

	mlx4_close_hca(dev);

err_mfunc:
	if (mlx4_is_slave(dev))
		mlx4_multi_func_cleanup(dev);

err_cmd:
	mlx4_cmd_cleanup(dev);

err_sriov:
	if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV))
		pci_disable_sriov(pdev);

err_rel_own:
	if (!mlx4_is_slave(dev))
		mlx4_free_ownership(dev);

err_free_dev:
	kfree(priv);

err_release_regions:
	pci_release_regions(pdev);

err_disable_pdev:
	pci_disable_device(pdev);
	pci_set_drvdata(pdev, NULL);
	return err;
}

static int __devinit mlx4_init_one(struct pci_dev *pdev,
				   const struct pci_device_id *id)
{
	printk_once(KERN_INFO "%s", mlx4_version);

	return __mlx4_init_one(pdev, id);
}

static void mlx4_remove_one(struct pci_dev *pdev)
{
	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
	struct mlx4_priv *priv = mlx4_priv(dev);
	int p;

	if (dev) {
		/* in SRIOV it is not allowed to unload the pf's
		 * driver while there are alive vf's */
		if (mlx4_is_master(dev)) {
			if (mlx4_how_many_lives_vf(dev))
				printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
		}
		mlx4_stop_sense(dev);
		mlx4_unregister_device(dev);

		for (p = 1; p <= dev->caps.num_ports; p++) {
			mlx4_cleanup_port_info(&priv->port[p]);
			mlx4_CLOSE_PORT(dev, p);
		}

		mlx4_cleanup_counters_table(dev);
		mlx4_cleanup_mcg_table(dev);
		mlx4_cleanup_qp_table(dev);
		mlx4_cleanup_srq_table(dev);
		mlx4_cleanup_cq_table(dev);
		mlx4_cmd_use_polling(dev);
		mlx4_cleanup_eq_table(dev);
		mlx4_cleanup_mr_table(dev);
		mlx4_cleanup_xrcd_table(dev);
		mlx4_cleanup_pd_table(dev);

		if (mlx4_is_master(dev))
			mlx4_free_resource_tracker(dev);

		iounmap(priv->kar);
		mlx4_uar_free(dev, &priv->driver_uar);
		mlx4_cleanup_uar_table(dev);
		if (!mlx4_is_slave(dev))
			mlx4_clear_steering(dev);
		mlx4_free_eq_table(dev);
		if (mlx4_is_master(dev))
			mlx4_multi_func_cleanup(dev);
		mlx4_close_hca(dev);
		if (mlx4_is_slave(dev))
			mlx4_multi_func_cleanup(dev);
		mlx4_cmd_cleanup(dev);

		if (dev->flags & MLX4_FLAG_MSI_X)
			pci_disable_msix(pdev);
		if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV)) {
			mlx4_warn(dev, "Disabling sriov\n");
			pci_disable_sriov(pdev);
		}

		if (!mlx4_is_slave(dev))
			mlx4_free_ownership(dev);
		kfree(priv);
		pci_release_regions(pdev);
		pci_disable_device(pdev);
		pci_set_drvdata(pdev, NULL);
	}
}

int mlx4_restart_one(struct pci_dev *pdev)
{
	mlx4_remove_one(pdev);
	return __mlx4_init_one(pdev, NULL);
}

static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = {
	/* MT25408 "Hermon" SDR */
	{ PCI_VDEVICE(MELLANOX, 0x6340), 0 },
	/* MT25408 "Hermon" DDR */
	{ PCI_VDEVICE(MELLANOX, 0x634a), 0 },
	/* MT25408 "Hermon" QDR */
	{ PCI_VDEVICE(MELLANOX, 0x6354), 0 },
	/* MT25408 "Hermon" DDR PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x6732), 0 },
	/* MT25408 "Hermon" QDR PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x673c), 0 },
	/* MT25408 "Hermon" EN 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x6368), 0 },
	/* MT25408 "Hermon" EN 10GigE PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x6750), 0 },
	/* MT25458 ConnectX EN 10GBASE-T 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x6372), 0 },
	/* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
	{ PCI_VDEVICE(MELLANOX, 0x675a), 0 },
	/* MT26468 ConnectX EN 10GigE PCIe gen2*/
	{ PCI_VDEVICE(MELLANOX, 0x6764), 0 },
	/* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
	{ PCI_VDEVICE(MELLANOX, 0x6746), 0 },
	/* MT26478 ConnectX2 40GigE PCIe gen2 */
	{ PCI_VDEVICE(MELLANOX, 0x676e), 0 },
	/* MT25400 Family [ConnectX-2 Virtual Function] */
	{ PCI_VDEVICE(MELLANOX, 0x1002), MLX4_VF },
	/* MT27500 Family [ConnectX-3] */
	{ PCI_VDEVICE(MELLANOX, 0x1003), 0 },
	/* MT27500 Family [ConnectX-3 Virtual Function] */
	{ PCI_VDEVICE(MELLANOX, 0x1004), MLX4_VF },
	{ PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1008), 0 }, /* MT27521 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1009), 0 }, /* MT27530 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100a), 0 }, /* MT27531 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100b), 0 }, /* MT27540 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100c), 0 }, /* MT27541 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100d), 0 }, /* MT27550 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100e), 0 }, /* MT27551 Family */
	{ PCI_VDEVICE(MELLANOX, 0x100f), 0 }, /* MT27560 Family */
	{ PCI_VDEVICE(MELLANOX, 0x1010), 0 }, /* MT27561 Family */
	{ 0, }
};

MODULE_DEVICE_TABLE(pci, mlx4_pci_table);

static struct pci_driver mlx4_driver = {
	.name		= DRV_NAME,
	.id_table	= mlx4_pci_table,
	.probe		= mlx4_init_one,
	.remove		= __devexit_p(mlx4_remove_one)
};

static int __init mlx4_verify_params(void)
{
	if ((log_num_mac < 0) || (log_num_mac > 7)) {
		pr_warning("mlx4_core: bad num_mac: %d\n", log_num_mac);
		return -1;
	}

	if (log_num_vlan != 0)
		pr_warning("mlx4_core: log_num_vlan - obsolete module param, using %d\n",
			   MLX4_LOG_NUM_VLANS);

	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
		pr_warning("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg);
		return -1;
	}

	/* Check if module param for ports type has legal combination */
	if (port_type_array[0] == false && port_type_array[1] == true) {
		printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
		port_type_array[0] = true;
	}

	return 0;
}

static int __init mlx4_init(void)
{
	int ret;

	if (mlx4_verify_params())
		return -EINVAL;

	mlx4_catas_init();

	mlx4_wq = create_singlethread_workqueue("mlx4");
	if (!mlx4_wq)
		return -ENOMEM;

	ret = pci_register_driver(&mlx4_driver);
	return ret < 0 ? ret : 0;
}

static void __exit mlx4_cleanup(void)
{
	pci_unregister_driver(&mlx4_driver);
	destroy_workqueue(mlx4_wq);
}

module_init(mlx4_init);
module_exit(mlx4_cleanup);