aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
blob: 18076c4178b4ff7762a117ef00595ab71173a10d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
/*
 * This file is part of UBIFS.
 *
 * Copyright (C) 2006-2008 Nokia Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 51
 * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
 *
 * Authors: Artem Bityutskiy (Битюцкий Артём)
 *          Adrian Hunter
 */

/*
 * This file implements UBIFS initialization and VFS superblock operations. Some
 * initialization stuff which is rather large and complex is placed at
 * corresponding subsystems, but most of it is here.
 */

#include <linux/init.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/math64.h>
#include <linux/writeback.h>
#include "ubifs.h"

/*
 * Maximum amount of memory we may 'kmalloc()' without worrying that we are
 * allocating too much.
 */
#define UBIFS_KMALLOC_OK (128*1024)

/* Slab cache for UBIFS inodes */
struct kmem_cache *ubifs_inode_slab;

/* UBIFS TNC shrinker description */
static struct shrinker ubifs_shrinker_info = {
	.scan_objects = ubifs_shrink_scan,
	.count_objects = ubifs_shrink_count,
	.seeks = DEFAULT_SEEKS,
};

/**
 * validate_inode - validate inode.
 * @c: UBIFS file-system description object
 * @inode: the inode to validate
 *
 * This is a helper function for 'ubifs_iget()' which validates various fields
 * of a newly built inode to make sure they contain sane values and prevent
 * possible vulnerabilities. Returns zero if the inode is all right and
 * a non-zero error code if not.
 */
static int validate_inode(struct ubifs_info *c, const struct inode *inode)
{
	int err;
	const struct ubifs_inode *ui = ubifs_inode(inode);

	if (inode->i_size > c->max_inode_sz) {
		ubifs_err(c, "inode is too large (%lld)",
			  (long long)inode->i_size);
		return 1;
	}

	if (ui->compr_type >= UBIFS_COMPR_TYPES_CNT) {
		ubifs_err(c, "unknown compression type %d", ui->compr_type);
		return 2;
	}

	if (ui->xattr_names + ui->xattr_cnt > XATTR_LIST_MAX)
		return 3;

	if (ui->data_len < 0 || ui->data_len > UBIFS_MAX_INO_DATA)
		return 4;

	if (ui->xattr && !S_ISREG(inode->i_mode))
		return 5;

	if (!ubifs_compr_present(ui->compr_type)) {
		ubifs_warn(c, "inode %lu uses '%s' compression, but it was not compiled in",
			   inode->i_ino, ubifs_compr_name(ui->compr_type));
	}

	err = dbg_check_dir(c, inode);
	return err;
}

struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
{
	int err;
	union ubifs_key key;
	struct ubifs_ino_node *ino;
	struct ubifs_info *c = sb->s_fs_info;
	struct inode *inode;
	struct ubifs_inode *ui;

	dbg_gen("inode %lu", inum);

	inode = iget_locked(sb, inum);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;
	ui = ubifs_inode(inode);

	ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS);
	if (!ino) {
		err = -ENOMEM;
		goto out;
	}

	ino_key_init(c, &key, inode->i_ino);

	err = ubifs_tnc_lookup(c, &key, ino);
	if (err)
		goto out_ino;

	inode->i_flags |= S_NOCMTIME;
#ifndef CONFIG_UBIFS_ATIME_SUPPORT
	inode->i_flags |= S_NOATIME;
#endif
	set_nlink(inode, le32_to_cpu(ino->nlink));
	i_uid_write(inode, le32_to_cpu(ino->uid));
	i_gid_write(inode, le32_to_cpu(ino->gid));
	inode->i_atime.tv_sec  = (int64_t)le64_to_cpu(ino->atime_sec);
	inode->i_atime.tv_nsec = le32_to_cpu(ino->atime_nsec);
	inode->i_mtime.tv_sec  = (int64_t)le64_to_cpu(ino->mtime_sec);
	inode->i_mtime.tv_nsec = le32_to_cpu(ino->mtime_nsec);
	inode->i_ctime.tv_sec  = (int64_t)le64_to_cpu(ino->ctime_sec);
	inode->i_ctime.tv_nsec = le32_to_cpu(ino->ctime_nsec);
	inode->i_mode = le32_to_cpu(ino->mode);
	inode->i_size = le64_to_cpu(ino->size);

	ui->data_len    = le32_to_cpu(ino->data_len);
	ui->flags       = le32_to_cpu(ino->flags);
	ui->compr_type  = le16_to_cpu(ino->compr_type);
	ui->creat_sqnum = le64_to_cpu(ino->creat_sqnum);
	ui->xattr_cnt   = le32_to_cpu(ino->xattr_cnt);
	ui->xattr_size  = le32_to_cpu(ino->xattr_size);
	ui->xattr_names = le32_to_cpu(ino->xattr_names);
	ui->synced_i_size = ui->ui_size = inode->i_size;

	ui->xattr = (ui->flags & UBIFS_XATTR_FL) ? 1 : 0;

	err = validate_inode(c, inode);
	if (err)
		goto out_invalid;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_mapping->a_ops = &ubifs_file_address_operations;
		inode->i_op = &ubifs_file_inode_operations;
		inode->i_fop = &ubifs_file_operations;
		if (ui->xattr) {
			ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
			if (!ui->data) {
				err = -ENOMEM;
				goto out_ino;
			}
			memcpy(ui->data, ino->data, ui->data_len);
			((char *)ui->data)[ui->data_len] = '\0';
		} else if (ui->data_len != 0) {
			err = 10;
			goto out_invalid;
		}
		break;
	case S_IFDIR:
		inode->i_op  = &ubifs_dir_inode_operations;
		inode->i_fop = &ubifs_dir_operations;
		if (ui->data_len != 0) {
			err = 11;
			goto out_invalid;
		}
		break;
	case S_IFLNK:
		inode->i_op = &ubifs_symlink_inode_operations;
		if (ui->data_len <= 0 || ui->data_len > UBIFS_MAX_INO_DATA) {
			err = 12;
			goto out_invalid;
		}
		ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
		if (!ui->data) {
			err = -ENOMEM;
			goto out_ino;
		}
		memcpy(ui->data, ino->data, ui->data_len);
		((char *)ui->data)[ui->data_len] = '\0';
		inode->i_link = ui->data;
		break;
	case S_IFBLK:
	case S_IFCHR:
	{
		dev_t rdev;
		union ubifs_dev_desc *dev;

		ui->data = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
		if (!ui->data) {
			err = -ENOMEM;
			goto out_ino;
		}

		dev = (union ubifs_dev_desc *)ino->data;
		if (ui->data_len == sizeof(dev->new))
			rdev = new_decode_dev(le32_to_cpu(dev->new));
		else if (ui->data_len == sizeof(dev->huge))
			rdev = huge_decode_dev(le64_to_cpu(dev->huge));
		else {
			err = 13;
			goto out_invalid;
		}
		memcpy(ui->data, ino->data, ui->data_len);
		inode->i_op = &ubifs_file_inode_operations;
		init_special_inode(inode, inode->i_mode, rdev);
		break;
	}
	case S_IFSOCK:
	case S_IFIFO:
		inode->i_op = &ubifs_file_inode_operations;
		init_special_inode(inode, inode->i_mode, 0);
		if (ui->data_len != 0) {
			err = 14;
			goto out_invalid;
		}
		break;
	default:
		err = 15;
		goto out_invalid;
	}

	kfree(ino);
	ubifs_set_inode_flags(inode);
	unlock_new_inode(inode);
	return inode;

out_invalid:
	ubifs_err(c, "inode %lu validation failed, error %d", inode->i_ino, err);
	ubifs_dump_node(c, ino);
	ubifs_dump_inode(c, inode);
	err = -EINVAL;
out_ino:
	kfree(ino);
out:
	ubifs_err(c, "failed to read inode %lu, error %d", inode->i_ino, err);
	iget_failed(inode);
	return ERR_PTR(err);
}

static struct inode *ubifs_alloc_inode(struct super_block *sb)
{
	struct ubifs_inode *ui;

	ui = kmem_cache_alloc(ubifs_inode_slab, GFP_NOFS);
	if (!ui)
		return NULL;

	memset((void *)ui + sizeof(struct inode), 0,
	       sizeof(struct ubifs_inode) - sizeof(struct inode));
	mutex_init(&ui->ui_mutex);
	spin_lock_init(&ui->ui_lock);
	return &ui->vfs_inode;
};

static void ubifs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct ubifs_inode *ui = ubifs_inode(inode);
	kmem_cache_free(ubifs_inode_slab, ui);
}

static void ubifs_destroy_inode(struct inode *inode)
{
	struct ubifs_inode *ui = ubifs_inode(inode);

	kfree(ui->data);
	call_rcu(&inode->i_rcu, ubifs_i_callback);
}

/*
 * Note, Linux write-back code calls this without 'i_mutex'.
 */
static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	int err = 0;
	struct ubifs_info *c = inode->i_sb->s_fs_info;
	struct ubifs_inode *ui = ubifs_inode(inode);

	ubifs_assert(!ui->xattr);
	if (is_bad_inode(inode))
		return 0;

	mutex_lock(&ui->ui_mutex);
	/*
	 * Due to races between write-back forced by budgeting
	 * (see 'sync_some_inodes()') and background write-back, the inode may
	 * have already been synchronized, do not do this again. This might
	 * also happen if it was synchronized in an VFS operation, e.g.
	 * 'ubifs_link()'.
	 */
	if (!ui->dirty) {
		mutex_unlock(&ui->ui_mutex);
		return 0;
	}

	/*
	 * As an optimization, do not write orphan inodes to the media just
	 * because this is not needed.
	 */
	dbg_gen("inode %lu, mode %#x, nlink %u",
		inode->i_ino, (int)inode->i_mode, inode->i_nlink);
	if (inode->i_nlink) {
		err = ubifs_jnl_write_inode(c, inode);
		if (err)
			ubifs_err(c, "can't write inode %lu, error %d",
				  inode->i_ino, err);
		else
			err = dbg_check_inode_size(c, inode, ui->ui_size);
	}

	ui->dirty = 0;
	mutex_unlock(&ui->ui_mutex);
	ubifs_release_dirty_inode_budget(c, ui);
	return err;
}

static void ubifs_evict_inode(struct inode *inode)
{
	int err;
	struct ubifs_info *c = inode->i_sb->s_fs_info;
	struct ubifs_inode *ui = ubifs_inode(inode);

	if (ui->xattr)
		/*
		 * Extended attribute inode deletions are fully handled in
		 * 'ubifs_removexattr()'. These inodes are special and have
		 * limited usage, so there is nothing to do here.
		 */
		goto out;

	dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
	ubifs_assert(!atomic_read(&inode->i_count));

	truncate_inode_pages_final(&inode->i_data);

	if (inode->i_nlink)
		goto done;

	if (is_bad_inode(inode))
		goto out;

	ui->ui_size = inode->i_size = 0;
	err = ubifs_jnl_delete_inode(c, inode);
	if (err)
		/*
		 * Worst case we have a lost orphan inode wasting space, so a
		 * simple error message is OK here.
		 */
		ubifs_err(c, "can't delete inode %lu, error %d",
			  inode->i_ino, err);

out:
	if (ui->dirty)
		ubifs_release_dirty_inode_budget(c, ui);
	else {
		/* We've deleted something - clean the "no space" flags */
		c->bi.nospace = c->bi.nospace_rp = 0;
		smp_wmb();
	}
done:
	clear_inode(inode);
}

static void ubifs_dirty_inode(struct inode *inode, int flags)
{
	struct ubifs_inode *ui = ubifs_inode(inode);

	ubifs_assert(mutex_is_locked(&ui->ui_mutex));
	if (!ui->dirty) {
		ui->dirty = 1;
		dbg_gen("inode %lu",  inode->i_ino);
	}
}

static int ubifs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct ubifs_info *c = dentry->d_sb->s_fs_info;
	unsigned long long free;
	__le32 *uuid = (__le32 *)c->uuid;

	free = ubifs_get_free_space(c);
	dbg_gen("free space %lld bytes (%lld blocks)",
		free, free >> UBIFS_BLOCK_SHIFT);

	buf->f_type = UBIFS_SUPER_MAGIC;
	buf->f_bsize = UBIFS_BLOCK_SIZE;
	buf->f_blocks = c->block_cnt;
	buf->f_bfree = free >> UBIFS_BLOCK_SHIFT;
	if (free > c->report_rp_size)
		buf->f_bavail = (free - c->report_rp_size) >> UBIFS_BLOCK_SHIFT;
	else
		buf->f_bavail = 0;
	buf->f_files = 0;
	buf->f_ffree = 0;
	buf->f_namelen = UBIFS_MAX_NLEN;
	buf->f_fsid.val[0] = le32_to_cpu(uuid[0]) ^ le32_to_cpu(uuid[2]);
	buf->f_fsid.val[1] = le32_to_cpu(uuid[1]) ^ le32_to_cpu(uuid[3]);
	ubifs_assert(buf->f_bfree <= c->block_cnt);
	return 0;
}

static int ubifs_show_options(struct seq_file *s, struct dentry *root)
{
	struct ubifs_info *c = root->d_sb->s_fs_info;

	if (c->mount_opts.unmount_mode == 2)
		seq_puts(s, ",fast_unmount");
	else if (c->mount_opts.unmount_mode == 1)
		seq_puts(s, ",norm_unmount");

	if (c->mount_opts.bulk_read == 2)
		seq_puts(s, ",bulk_read");
	else if (c->mount_opts.bulk_read == 1)
		seq_puts(s, ",no_bulk_read");

	if (c->mount_opts.chk_data_crc == 2)
		seq_puts(s, ",chk_data_crc");
	else if (c->mount_opts.chk_data_crc == 1)
		seq_puts(s, ",no_chk_data_crc");

	if (c->mount_opts.override_compr) {
		seq_printf(s, ",compr=%s",
			   ubifs_compr_name(c->mount_opts.compr_type));
	}

	return 0;
}

static int ubifs_sync_fs(struct super_block *sb, int wait)
{
	int i, err;
	struct ubifs_info *c = sb->s_fs_info;

	/*
	 * Zero @wait is just an advisory thing to help the file system shove
	 * lots of data into the queues, and there will be the second
	 * '->sync_fs()' call, with non-zero @wait.
	 */
	if (!wait)
		return 0;

	/*
	 * Synchronize write buffers, because 'ubifs_run_commit()' does not
	 * do this if it waits for an already running commit.
	 */
	for (i = 0; i < c->jhead_cnt; i++) {
		err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
		if (err)
			return err;
	}

	/*
	 * Strictly speaking, it is not necessary to commit the journal here,
	 * synchronizing write-buffers would be enough. But committing makes
	 * UBIFS free space predictions much more accurate, so we want to let
	 * the user be able to get more accurate results of 'statfs()' after
	 * they synchronize the file system.
	 */
	err = ubifs_run_commit(c);
	if (err)
		return err;

	return ubi_sync(c->vi.ubi_num);
}

/**
 * init_constants_early - initialize UBIFS constants.
 * @c: UBIFS file-system description object
 *
 * This function initialize UBIFS constants which do not need the superblock to
 * be read. It also checks that the UBI volume satisfies basic UBIFS
 * requirements. Returns zero in case of success and a negative error code in
 * case of failure.
 */
static int init_constants_early(struct ubifs_info *c)
{
	if (c->vi.corrupted) {
		ubifs_warn(c, "UBI volume is corrupted - read-only mode");
		c->ro_media = 1;
	}

	if (c->di.ro_mode) {
		ubifs_msg(c, "read-only UBI device");
		c->ro_media = 1;
	}

	if (c->vi.vol_type == UBI_STATIC_VOLUME) {
		ubifs_msg(c, "static UBI volume - read-only mode");
		c->ro_media = 1;
	}

	c->leb_cnt = c->vi.size;
	c->leb_size = c->vi.usable_leb_size;
	c->leb_start = c->di.leb_start;
	c->half_leb_size = c->leb_size / 2;
	c->min_io_size = c->di.min_io_size;
	c->min_io_shift = fls(c->min_io_size) - 1;
	c->max_write_size = c->di.max_write_size;
	c->max_write_shift = fls(c->max_write_size) - 1;

	if (c->leb_size < UBIFS_MIN_LEB_SZ) {
		ubifs_err(c, "too small LEBs (%d bytes), min. is %d bytes",
			  c->leb_size, UBIFS_MIN_LEB_SZ);
		return -EINVAL;
	}

	if (c->leb_cnt < UBIFS_MIN_LEB_CNT) {
		ubifs_err(c, "too few LEBs (%d), min. is %d",
			  c->leb_cnt, UBIFS_MIN_LEB_CNT);
		return -EINVAL;
	}

	if (!is_power_of_2(c->min_io_size)) {
		ubifs_err(c, "bad min. I/O size %d", c->min_io_size);
		return -EINVAL;
	}

	/*
	 * Maximum write size has to be greater or equivalent to min. I/O
	 * size, and be multiple of min. I/O size.
	 */
	if (c->max_write_size < c->min_io_size ||
	    c->max_write_size % c->min_io_size ||
	    !is_power_of_2(c->max_write_size)) {
		ubifs_err(c, "bad write buffer size %d for %d min. I/O unit",
			  c->max_write_size, c->min_io_size);
		return -EINVAL;
	}

	/*
	 * UBIFS aligns all node to 8-byte boundary, so to make function in
	 * io.c simpler, assume minimum I/O unit size to be 8 bytes if it is
	 * less than 8.
	 */
	if (c->min_io_size < 8) {
		c->min_io_size = 8;
		c->min_io_shift = 3;
		if (c->max_write_size < c->min_io_size) {
			c->max_write_size = c->min_io_size;
			c->max_write_shift = c->min_io_shift;
		}
	}

	c->ref_node_alsz = ALIGN(UBIFS_REF_NODE_SZ, c->min_io_size);
	c->mst_node_alsz = ALIGN(UBIFS_MST_NODE_SZ, c->min_io_size);

	/*
	 * Initialize node length ranges which are mostly needed for node
	 * length validation.
	 */
	c->ranges[UBIFS_PAD_NODE].len  = UBIFS_PAD_NODE_SZ;
	c->ranges[UBIFS_SB_NODE].len   = UBIFS_SB_NODE_SZ;
	c->ranges[UBIFS_MST_NODE].len  = UBIFS_MST_NODE_SZ;
	c->ranges[UBIFS_REF_NODE].len  = UBIFS_REF_NODE_SZ;
	c->ranges[UBIFS_TRUN_NODE].len = UBIFS_TRUN_NODE_SZ;
	c->ranges[UBIFS_CS_NODE].len   = UBIFS_CS_NODE_SZ;

	c->ranges[UBIFS_INO_NODE].min_len  = UBIFS_INO_NODE_SZ;
	c->ranges[UBIFS_INO_NODE].max_len  = UBIFS_MAX_INO_NODE_SZ;
	c->ranges[UBIFS_ORPH_NODE].min_len =
				UBIFS_ORPH_NODE_SZ + sizeof(__le64);
	c->ranges[UBIFS_ORPH_NODE].max_len = c->leb_size;
	c->ranges[UBIFS_DENT_NODE].min_len = UBIFS_DENT_NODE_SZ;
	c->ranges[UBIFS_DENT_NODE].max_len = UBIFS_MAX_DENT_NODE_SZ;
	c->ranges[UBIFS_XENT_NODE].min_len = UBIFS_XENT_NODE_SZ;
	c->ranges[UBIFS_XENT_NODE].max_len = UBIFS_MAX_XENT_NODE_SZ;
	c->ranges[UBIFS_DATA_NODE].min_len = UBIFS_DATA_NODE_SZ;
	c->ranges[UBIFS_DATA_NODE].max_len = UBIFS_MAX_DATA_NODE_SZ;
	/*
	 * Minimum indexing node size is amended later when superblock is
	 * read and the key length is known.
	 */
	c->ranges[UBIFS_IDX_NODE].min_len = UBIFS_IDX_NODE_SZ + UBIFS_BRANCH_SZ;
	/*
	 * Maximum indexing node size is amended later when superblock is
	 * read and the fanout is known.
	 */
	c->ranges[UBIFS_IDX_NODE].max_len = INT_MAX;

	/*
	 * Initialize dead and dark LEB space watermarks. See gc.c for comments
	 * about these values.
	 */
	c->dead_wm = ALIGN(MIN_WRITE_SZ, c->min_io_size);
	c->dark_wm = ALIGN(UBIFS_MAX_NODE_SZ, c->min_io_size);

	/*
	 * Calculate how many bytes would be wasted at the end of LEB if it was
	 * fully filled with data nodes of maximum size. This is used in
	 * calculations when reporting free space.
	 */
	c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ;

	/* Buffer size for bulk-reads */
	c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
	if (c->max_bu_buf_len > c->leb_size)
		c->max_bu_buf_len = c->leb_size;
	return 0;
}

/**
 * bud_wbuf_callback - bud LEB write-buffer synchronization call-back.
 * @c: UBIFS file-system description object
 * @lnum: LEB the write-buffer was synchronized to
 * @free: how many free bytes left in this LEB
 * @pad: how many bytes were padded
 *
 * This is a callback function which is called by the I/O unit when the
 * write-buffer is synchronized. We need this to correctly maintain space
 * accounting in bud logical eraseblocks. This function returns zero in case of
 * success and a negative error code in case of failure.
 *
 * This function actually belongs to the journal, but we keep it here because
 * we want to keep it static.
 */
static int bud_wbuf_callback(struct ubifs_info *c, int lnum, int free, int pad)
{
	return ubifs_update_one_lp(c, lnum, free, pad, 0, 0);
}

/*
 * init_constants_sb - initialize UBIFS constants.
 * @c: UBIFS file-system description object
 *
 * This is a helper function which initializes various UBIFS constants after
 * the superblock has been read. It also checks various UBIFS parameters and
 * makes sure they are all right. Returns zero in case of success and a
 * negative error code in case of failure.
 */
static int init_constants_sb(struct ubifs_info *c)
{
	int tmp, err;
	long long tmp64;

	c->main_bytes = (long long)c->main_lebs * c->leb_size;
	c->max_znode_sz = sizeof(struct ubifs_znode) +
				c->fanout * sizeof(struct ubifs_zbranch);

	tmp = ubifs_idx_node_sz(c, 1);
	c->ranges[UBIFS_IDX_NODE].min_len = tmp;
	c->min_idx_node_sz = ALIGN(tmp, 8);

	tmp = ubifs_idx_node_sz(c, c->fanout);
	c->ranges[UBIFS_IDX_NODE].max_len = tmp;
	c->max_idx_node_sz = ALIGN(tmp, 8);

	/* Make sure LEB size is large enough to fit full commit */
	tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt;
	tmp = ALIGN(tmp, c->min_io_size);
	if (tmp > c->leb_size) {
		ubifs_err(c, "too small LEB size %d, at least %d needed",
			  c->leb_size, tmp);
		return -EINVAL;
	}

	/*
	 * Make sure that the log is large enough to fit reference nodes for
	 * all buds plus one reserved LEB.
	 */
	tmp64 = c->max_bud_bytes + c->leb_size - 1;
	c->max_bud_cnt = div_u64(tmp64, c->leb_size);
	tmp = (c->ref_node_alsz * c->max_bud_cnt + c->leb_size - 1);
	tmp /= c->leb_size;
	tmp += 1;
	if (c->log_lebs < tmp) {
		ubifs_err(c, "too small log %d LEBs, required min. %d LEBs",
			  c->log_lebs, tmp);
		return -EINVAL;
	}

	/*
	 * When budgeting we assume worst-case scenarios when the pages are not
	 * be compressed and direntries are of the maximum size.
	 *
	 * Note, data, which may be stored in inodes is budgeted separately, so
	 * it is not included into 'c->bi.inode_budget'.
	 */
	c->bi.page_budget = UBIFS_MAX_DATA_NODE_SZ * UBIFS_BLOCKS_PER_PAGE;
	c->bi.inode_budget = UBIFS_INO_NODE_SZ;
	c->bi.dent_budget = UBIFS_MAX_DENT_NODE_SZ;

	/*
	 * When the amount of flash space used by buds becomes
	 * 'c->max_bud_bytes', UBIFS just blocks all writers and starts commit.
	 * The writers are unblocked when the commit is finished. To avoid
	 * writers to be blocked UBIFS initiates background commit in advance,
	 * when number of bud bytes becomes above the limit defined below.
	 */
	c->bg_bud_bytes = (c->max_bud_bytes * 13) >> 4;

	/*
	 * Ensure minimum journal size. All the bytes in the journal heads are
	 * considered to be used, when calculating the current journal usage.
	 * Consequently, if the journal is too small, UBIFS will treat it as
	 * always full.
	 */
	tmp64 = (long long)(c->jhead_cnt + 1) * c->leb_size + 1;
	if (c->bg_bud_bytes < tmp64)
		c->bg_bud_bytes = tmp64;
	if (c->max_bud_bytes < tmp64 + c->leb_size)
		c->max_bud_bytes = tmp64 + c->leb_size;

	err = ubifs_calc_lpt_geom(c);
	if (err)
		return err;

	/* Initialize effective LEB size used in budgeting calculations */
	c->idx_leb_size = c->leb_size - c->max_idx_node_sz;
	return 0;
}

/*
 * init_constants_master - initialize UBIFS constants.
 * @c: UBIFS file-system description object
 *
 * This is a helper function which initializes various UBIFS constants after
 * the master node has been read. It also checks various UBIFS parameters and
 * makes sure they are all right.
 */
static void init_constants_master(struct ubifs_info *c)
{
	long long tmp64;

	c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c);
	c->report_rp_size = ubifs_reported_space(c, c->rp_size);

	/*
	 * Calculate total amount of FS blocks. This number is not used
	 * internally because it does not make much sense for UBIFS, but it is
	 * necessary to report something for the 'statfs()' call.
	 *
	 * Subtract the LEB reserved for GC, the LEB which is reserved for
	 * deletions, minimum LEBs for the index, and assume only one journal
	 * head is available.
	 */
	tmp64 = c->main_lebs - 1 - 1 - MIN_INDEX_LEBS - c->jhead_cnt + 1;
	tmp64 *= (long long)c->leb_size - c->leb_overhead;
	tmp64 = ubifs_reported_space(c, tmp64);
	c->block_cnt = tmp64 >> UBIFS_BLOCK_SHIFT;
}

/**
 * take_gc_lnum - reserve GC LEB.
 * @c: UBIFS file-system description object
 *
 * This function ensures that the LEB reserved for garbage collection is marked
 * as "taken" in lprops. We also have to set free space to LEB size and dirty
 * space to zero, because lprops may contain out-of-date information if the
 * file-system was un-mounted before it has been committed. This function
 * returns zero in case of success and a negative error code in case of
 * failure.
 */
static int take_gc_lnum(struct ubifs_info *c)
{
	int err;

	if (c->gc_lnum == -1) {
		ubifs_err(c, "no LEB for GC");
		return -EINVAL;
	}

	/* And we have to tell lprops that this LEB is taken */
	err = ubifs_change_one_lp(c, c->gc_lnum, c->leb_size, 0,
				  LPROPS_TAKEN, 0, 0);
	return err;
}

/**
 * alloc_wbufs - allocate write-buffers.
 * @c: UBIFS file-system description object
 *
 * This helper function allocates and initializes UBIFS write-buffers. Returns
 * zero in case of success and %-ENOMEM in case of failure.
 */
static int alloc_wbufs(struct ubifs_info *c)
{
	int i, err;

	c->jheads = kcalloc(c->jhead_cnt, sizeof(struct ubifs_jhead),
			    GFP_KERNEL);
	if (!c->jheads)
		return -ENOMEM;

	/* Initialize journal heads */
	for (i = 0; i < c->jhead_cnt; i++) {
		INIT_LIST_HEAD(&c->jheads[i].buds_list);
		err = ubifs_wbuf_init(c, &c->jheads[i].wbuf);
		if (err)
			return err;

		c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
		c->jheads[i].wbuf.jhead = i;
		c->jheads[i].grouped = 1;
	}

	/*
	 * Garbage Collector head does not need to be synchronized by timer.
	 * Also GC head nodes are not grouped.
	 */
	c->jheads[GCHD].wbuf.no_timer = 1;
	c->jheads[GCHD].grouped = 0;

	return 0;
}

/**
 * free_wbufs - free write-buffers.
 * @c: UBIFS file-system description object
 */
static void free_wbufs(struct ubifs_info *c)
{
	int i;

	if (c->jheads) {
		for (i = 0; i < c->jhead_cnt; i++) {
			kfree(c->jheads[i].wbuf.buf);
			kfree(c->jheads[i].wbuf.inodes);
		}
		kfree(c->jheads);
		c->jheads = NULL;
	}
}

/**
 * free_orphans - free orphans.
 * @c: UBIFS file-system description object
 */
static void free_orphans(struct ubifs_info *c)
{
	struct ubifs_orphan *orph;

	while (c->orph_dnext) {
		orph = c->orph_dnext;
		c->orph_dnext = orph->dnext;
		list_del(&orph->list);
		kfree(orph);
	}

	while (!list_empty(&c->orph_list)) {
		orph = list_entry(c->orph_list.next, struct ubifs_orphan, list);
		list_del(&orph->list);
		kfree(orph);
		ubifs_err(c, "orphan list not empty at unmount");
	}

	vfree(c->orph_buf);
	c->orph_buf = NULL;
}

/**
 * free_buds - free per-bud objects.
 * @c: UBIFS file-system description object
 */
static void free_buds(struct ubifs_info *c)
{
	struct ubifs_bud *bud, *n;

	rbtree_postorder_for_each_entry_safe(bud, n, &c->buds, rb)
		kfree(bud);
}

/**
 * check_volume_empty - check if the UBI volume is empty.
 * @c: UBIFS file-system description object
 *
 * This function checks if the UBIFS volume is empty by looking if its LEBs are
 * mapped or not. The result of checking is stored in the @c->empty variable.
 * Returns zero in case of success and a negative error code in case of
 * failure.
 */
static int check_volume_empty(struct ubifs_info *c)
{
	int lnum, err;

	c->empty = 1;
	for (lnum = 0; lnum < c->leb_cnt; lnum++) {
		err = ubifs_is_mapped(c, lnum);
		if (unlikely(err < 0))
			return err;
		if (err == 1) {
			c->empty = 0;
			break;
		}

		cond_resched();
	}

	return 0;
}

/*
 * UBIFS mount options.
 *
 * Opt_fast_unmount: do not run a journal commit before un-mounting
 * Opt_norm_unmount: run a journal commit before un-mounting
 * Opt_bulk_read: enable bulk-reads
 * Opt_no_bulk_read: disable bulk-reads
 * Opt_chk_data_crc: check CRCs when reading data nodes
 * Opt_no_chk_data_crc: do not check CRCs when reading data nodes
 * Opt_override_compr: override default compressor
 * Opt_err: just end of array marker
 */
enum {
	Opt_fast_unmount,
	Opt_norm_unmount,
	Opt_bulk_read,
	Opt_no_bulk_read,
	Opt_chk_data_crc,
	Opt_no_chk_data_crc,
	Opt_override_compr,
	Opt_err,
};

static const match_table_t tokens = {
	{Opt_fast_unmount, "fast_unmount"},
	{Opt_norm_unmount, "norm_unmount"},
	{Opt_bulk_read, "bulk_read"},
	{Opt_no_bulk_read, "no_bulk_read"},
	{Opt_chk_data_crc, "chk_data_crc"},
	{Opt_no_chk_data_crc, "no_chk_data_crc"},
	{Opt_override_compr, "compr=%s"},
	{Opt_err, NULL},
};

/**
 * parse_standard_option - parse a standard mount option.
 * @option: the option to parse
 *
 * Normally, standard mount options like "sync" are passed to file-systems as
 * flags. However, when a "rootflags=" kernel boot parameter is used, they may
 * be present in the options string. This function tries to deal with this
 * situation and parse standard options. Returns 0 if the option was not
 * recognized, and the corresponding integer flag if it was.
 *
 * UBIFS is only interested in the "sync" option, so do not check for anything
 * else.
 */
static int parse_standard_option(const char *option)
{

	pr_notice("UBIFS: parse %s\n", option);
	if (!strcmp(option, "sync"))
		return MS_SYNCHRONOUS;
	return 0;
}

/**
 * ubifs_parse_options - parse mount parameters.
 * @c: UBIFS file-system description object
 * @options: parameters to parse
 * @is_remount: non-zero if this is FS re-mount
 *
 * This function parses UBIFS mount options and returns zero in case success
 * and a negative error code in case of failure.
 */
static int ubifs_parse_options(struct ubifs_info *c, char *options,
			       int is_remount)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];

	if (!options)
		return 0;

	while ((p = strsep(&options, ","))) {
		int token;

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		/*
		 * %Opt_fast_unmount and %Opt_norm_unmount options are ignored.
		 * We accept them in order to be backward-compatible. But this
		 * should be removed at some point.
		 */
		case Opt_fast_unmount:
			c->mount_opts.unmount_mode = 2;
			break;
		case Opt_norm_unmount:
			c->mount_opts.unmount_mode = 1;
			break;
		case Opt_bulk_read:
			c->mount_opts.bulk_read = 2;
			c->bulk_read = 1;
			break;
		case Opt_no_bulk_read:
			c->mount_opts.bulk_read = 1;
			c->bulk_read = 0;
			break;
		case Opt_chk_data_crc:
			c->mount_opts.chk_data_crc = 2;
			c->no_chk_data_crc = 0;
			break;
		case Opt_no_chk_data_crc:
			c->mount_opts.chk_data_crc = 1;
			c->no_chk_data_crc = 1;
			break;
		case Opt_override_compr:
		{
			char *name = match_strdup(&args[0]);

			if (!name)
				return -ENOMEM;
			if (!strcmp(name, "none"))
				c->mount_opts.compr_type = UBIFS_COMPR_NONE;
			else if (!strcmp(name, "lzo"))
				c->mount_opts.compr_type = UBIFS_COMPR_LZO;
			else if (!strcmp(name, "zlib"))
				c->mount_opts.compr_type = UBIFS_COMPR_ZLIB;
			else {
				ubifs_err(c, "unknown compressor \"%s\"", name); //FIXME: is c ready?
				kfree(name);
				return -EINVAL;
			}
			kfree(name);
			c->mount_opts.override_compr = 1;
			c->default_compr = c->mount_opts.compr_type;
			break;
		}
		default:
		{
			unsigned long flag;
			struct super_block *sb = c->vfs_sb;

			flag = parse_standard_option(p);
			if (!flag) {
				ubifs_err(c, "unrecognized mount option \"%s\" or missing value",
					  p);
				return -EINVAL;
			}
			sb->s_flags |= flag;
			break;
		}
		}
	}

	return 0;
}

/**
 * destroy_journal - destroy journal data structures.
 * @c: UBIFS file-system description object
 *
 * This function destroys journal data structures including those that may have
 * been created by recovery functions.
 */
static void destroy_journal(struct ubifs_info *c)
{
	while (!list_empty(&c->unclean_leb_list)) {
		struct ubifs_unclean_leb *ucleb;

		ucleb = list_entry(c->unclean_leb_list.next,
				   struct ubifs_unclean_leb, list);
		list_del(&ucleb->list);
		kfree(ucleb);
	}
	while (!list_empty(&c->old_buds)) {
		struct ubifs_bud *bud;

		bud = list_entry(c->old_buds.next, struct ubifs_bud, list);
		list_del(&bud->list);
		kfree(bud);
	}
	ubifs_destroy_idx_gc(c);
	ubifs_destroy_size_tree(c);
	ubifs_tnc_close(c);
	free_buds(c);
}

/**
 * bu_init - initialize bulk-read information.
 * @c: UBIFS file-system description object
 */
static void bu_init(struct ubifs_info *c)
{
	ubifs_assert(c->bulk_read == 1);

	if (c->bu.buf)
		return; /* Already initialized */

again:
	c->bu.buf = kmalloc(c->max_bu_buf_len, GFP_KERNEL | __GFP_NOWARN);
	if (!c->bu.buf) {
		if (c->max_bu_buf_len > UBIFS_KMALLOC_OK) {
			c->max_bu_buf_len = UBIFS_KMALLOC_OK;
			goto again;
		}

		/* Just disable bulk-read */
		ubifs_warn(c, "cannot allocate %d bytes of memory for bulk-read, disabling it",
			   c->max_bu_buf_len);
		c->mount_opts.bulk_read = 1;
		c->bulk_read = 0;
		return;
	}
}

/**
 * check_free_space - check if there is enough free space to mount.
 * @c: UBIFS file-system description object
 *
 * This function makes sure UBIFS has enough free space to be mounted in
 * read/write mode. UBIFS must always have some free space to allow deletions.
 */
static int check_free_space(struct ubifs_info *c)
{
	ubifs_assert(c->dark_wm > 0);
	if (c->lst.total_free + c->lst.total_dirty < c->dark_wm) {
		ubifs_err(c, "insufficient free space to mount in R/W mode");
		ubifs_dump_budg(c, &c->bi);
		ubifs_dump_lprops(c);
		return -ENOSPC;
	}
	return 0;
}

/**
 * mount_ubifs - mount UBIFS file-system.
 * @c: UBIFS file-system description object
 *
 * This function mounts UBIFS file system. Returns zero in case of success and
 * a negative error code in case of failure.
 */
static int mount_ubifs(struct ubifs_info *c)
{
	int err;
	long long x, y;
	size_t sz;

	c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY);
	/* Suppress error messages while probing if MS_SILENT is set */
	c->probing = !!(c->vfs_sb->s_flags & MS_SILENT);

	err = init_constants_early(c);
	if (err)
		return err;

	err = ubifs_debugging_init(c);
	if (err)
		return err;

	err = check_volume_empty(c);
	if (err)
		goto out_free;

	if (c->empty && (c->ro_mount || c->ro_media)) {
		/*
		 * This UBI volume is empty, and read-only, or the file system
		 * is mounted read-only - we cannot format it.
		 */
		ubifs_err(c, "can't format empty UBI volume: read-only %s",
			  c->ro_media ? "UBI volume" : "mount");
		err = -EROFS;
		goto out_free;
	}

	if (c->ro_media && !c->ro_mount) {
		ubifs_err(c, "cannot mount read-write - read-only media");
		err = -EROFS;
		goto out_free;
	}

	/*
	 * The requirement for the buffer is that it should fit indexing B-tree
	 * height amount of integers. We assume the height if the TNC tree will
	 * never exceed 64.
	 */
	err = -ENOMEM;
	c->bottom_up_buf = kmalloc(BOTTOM_UP_HEIGHT * sizeof(int), GFP_KERNEL);
	if (!c->bottom_up_buf)
		goto out_free;

	c->sbuf = vmalloc(c->leb_size);
	if (!c->sbuf)
		goto out_free;

	if (!c->ro_mount) {
		c->ileb_buf = vmalloc(c->leb_size);
		if (!c->ileb_buf)
			goto out_free;
	}

	if (c->bulk_read == 1)
		bu_init(c);

	if (!c->ro_mount) {
		c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ,
					       GFP_KERNEL);
		if (!c->write_reserve_buf)
			goto out_free;
	}

	c->mounting = 1;

	err = ubifs_read_superblock(c);
	if (err)
		goto out_free;

	c->probing = 0;

	/*
	 * Make sure the compressor which is set as default in the superblock
	 * or overridden by mount options is actually compiled in.
	 */
	if (!ubifs_compr_present(c->default_compr)) {
		ubifs_err(c, "'compressor \"%s\" is not compiled in",
			  ubifs_compr_name(c->default_compr));
		err = -ENOTSUPP;
		goto out_free;
	}

	err = init_constants_sb(c);
	if (err)
		goto out_free;

	sz = ALIGN(c->max_idx_node_sz, c->min_io_size);
	sz = ALIGN(sz + c->max_idx_node_sz, c->min_io_size);
	c->cbuf = kmalloc(sz, GFP_NOFS);
	if (!c->cbuf) {
		err = -ENOMEM;
		goto out_free;
	}

	err = alloc_wbufs(c);
	if (err)
		goto out_cbuf;

	sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
	if (!c->ro_mount) {
		/* Create background thread */
		c->bgt = kthread_create(ubifs_bg_thread, c, "%s", c->bgt_name);
		if (IS_ERR(c->bgt)) {
			err = PTR_ERR(c->bgt);
			c->bgt = NULL;
			ubifs_err(c, "cannot spawn \"%s\", error %d",
				  c->bgt_name, err);
			goto out_wbufs;
		}
		wake_up_process(c->bgt);
	}

	err = ubifs_read_master(c);
	if (err)
		goto out_master;

	init_constants_master(c);

	if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
		ubifs_msg(c, "recovery needed");
		c->need_recovery = 1;
	}

	if (c->need_recovery && !c->ro_mount) {
		err = ubifs_recover_inl_heads(c, c->sbuf);
		if (err)
			goto out_master;
	}

	err = ubifs_lpt_init(c, 1, !c->ro_mount);
	if (err)
		goto out_master;

	if (!c->ro_mount && c->space_fixup) {
		err = ubifs_fixup_free_space(c);
		if (err)
			goto out_lpt;
	}

	if (!c->ro_mount && !c->need_recovery) {
		/*
		 * Set the "dirty" flag so that if we reboot uncleanly we
		 * will notice this immediately on the next mount.
		 */
		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
		err = ubifs_write_master(c);
		if (err)
			goto out_lpt;
	}

	err = dbg_check_idx_size(c, c->bi.old_idx_sz);
	if (err)
		goto out_lpt;

	err = ubifs_replay_journal(c);
	if (err)
		goto out_journal;

	/* Calculate 'min_idx_lebs' after journal replay */
	c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c);

	err = ubifs_mount_orphans(c, c->need_recovery, c->ro_mount);
	if (err)
		goto out_orphans;

	if (!c->ro_mount) {
		int lnum;

		err = check_free_space(c);
		if (err)
			goto out_orphans;

		/* Check for enough log space */
		lnum = c->lhead_lnum + 1;
		if (lnum >= UBIFS_LOG_LNUM + c->log_lebs)
			lnum = UBIFS_LOG_LNUM;
		if (lnum == c->ltail_lnum) {
			err = ubifs_consolidate_log(c);
			if (err)
				goto out_orphans;
		}

		if (c->need_recovery) {
			err = ubifs_recover_size(c);
			if (err)
				goto out_orphans;
			err = ubifs_rcvry_gc_commit(c);
			if (err)
				goto out_orphans;
		} else {
			err = take_gc_lnum(c);
			if (err)
				goto out_orphans;

			/*
			 * GC LEB may contain garbage if there was an unclean
			 * reboot, and it should be un-mapped.
			 */
			err = ubifs_leb_unmap(c, c->gc_lnum);
			if (err)
				goto out_orphans;
		}

		err = dbg_check_lprops(c);
		if (err)
			goto out_orphans;
	} else if (c->need_recovery) {
		err = ubifs_recover_size(c);
		if (err)
			goto out_orphans;
	} else {
		/*
		 * Even if we mount read-only, we have to set space in GC LEB
		 * to proper value because this affects UBIFS free space
		 * reporting. We do not want to have a situation when
		 * re-mounting from R/O to R/W changes amount of free space.
		 */
		err = take_gc_lnum(c);
		if (err)
			goto out_orphans;
	}

	spin_lock(&ubifs_infos_lock);
	list_add_tail(&c->infos_list, &ubifs_infos);
	spin_unlock(&ubifs_infos_lock);

	if (c->need_recovery) {
		if (c->ro_mount)
			ubifs_msg(c, "recovery deferred");
		else {
			c->need_recovery = 0;
			ubifs_msg(c, "recovery completed");
			/*
			 * GC LEB has to be empty and taken at this point. But
			 * the journal head LEBs may also be accounted as
			 * "empty taken" if they are empty.
			 */
			ubifs_assert(c->lst.taken_empty_lebs > 0);
		}
	} else
		ubifs_assert(c->lst.taken_empty_lebs > 0);

	err = dbg_check_filesystem(c);
	if (err)
		goto out_infos;

	err = dbg_debugfs_init_fs(c);
	if (err)
		goto out_infos;

	c->mounting = 0;

	ubifs_msg(c, "UBIFS: mounted UBI device %d, volume %d, name \"%s\"%s",
		  c->vi.ubi_num, c->vi.vol_id, c->vi.name,
		  c->ro_mount ? ", R/O mode" : "");
	x = (long long)c->main_lebs * c->leb_size;
	y = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes;
	ubifs_msg(c, "LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes",
		  c->leb_size, c->leb_size >> 10, c->min_io_size,
		  c->max_write_size);
	ubifs_msg(c, "FS size: %lld bytes (%lld MiB, %d LEBs), journal size %lld bytes (%lld MiB, %d LEBs)",
		  x, x >> 20, c->main_lebs,
		  y, y >> 20, c->log_lebs + c->max_bud_cnt);
	ubifs_msg(c, "reserved for root: %llu bytes (%llu KiB)",
		  c->report_rp_size, c->report_rp_size >> 10);
	ubifs_msg(c, "media format: w%d/r%d (latest is w%d/r%d), UUID %pUB%s",
		  c->fmt_version, c->ro_compat_version,
		  UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION, c->uuid,
		  c->big_lpt ? ", big LPT model" : ", small LPT model");

	dbg_gen("default compressor:  %s", ubifs_compr_name(c->default_compr));
	dbg_gen("data journal heads:  %d",
		c->jhead_cnt - NONDATA_JHEADS_CNT);
	dbg_gen("log LEBs:            %d (%d - %d)",
		c->log_lebs, UBIFS_LOG_LNUM, c->log_last);
	dbg_gen("LPT area LEBs:       %d (%d - %d)",
		c->lpt_lebs, c->lpt_first, c->lpt_last);
	dbg_gen("orphan area LEBs:    %d (%d - %d)",
		c->orph_lebs, c->orph_first, c->orph_last);
	dbg_gen("main area LEBs:      %d (%d - %d)",
		c->main_lebs, c->main_first, c->leb_cnt - 1);
	dbg_gen("index LEBs:          %d", c->lst.idx_lebs);
	dbg_gen("total index bytes:   %lld (%lld KiB, %lld MiB)",
		c->bi.old_idx_sz, c->bi.old_idx_sz >> 10,
		c->bi.old_idx_sz >> 20);
	dbg_gen("key hash type:       %d", c->key_hash_type);
	dbg_gen("tree fanout:         %d", c->fanout);
	dbg_gen("reserved GC LEB:     %d", c->gc_lnum);
	dbg_gen("max. znode size      %d", c->max_znode_sz);
	dbg_gen("max. index node size %d", c->max_idx_node_sz);
	dbg_gen("node sizes:          data %zu, inode %zu, dentry %zu",
		UBIFS_DATA_NODE_SZ, UBIFS_INO_NODE_SZ, UBIFS_DENT_NODE_SZ);
	dbg_gen("node sizes:          trun %zu, sb %zu, master %zu",
		UBIFS_TRUN_NODE_SZ, UBIFS_SB_NODE_SZ, UBIFS_MST_NODE_SZ);
	dbg_gen("node sizes:          ref %zu, cmt. start %zu, orph %zu",
		UBIFS_REF_NODE_SZ, UBIFS_CS_NODE_SZ, UBIFS_ORPH_NODE_SZ);
	dbg_gen("max. node sizes:     data %zu, inode %zu dentry %zu, idx %d",
		UBIFS_MAX_DATA_NODE_SZ, UBIFS_MAX_INO_NODE_SZ,
		UBIFS_MAX_DENT_NODE_SZ, ubifs_idx_node_sz(c, c->fanout));
	dbg_gen("dead watermark:      %d", c->dead_wm);
	dbg_gen("dark watermark:      %d", c->dark_wm);
	dbg_gen("LEB overhead:        %d", c->leb_overhead);
	x = (long long)c->main_lebs * c->dark_wm;
	dbg_gen("max. dark space:     %lld (%lld KiB, %lld MiB)",
		x, x >> 10, x >> 20);
	dbg_gen("maximum bud bytes:   %lld (%lld KiB, %lld MiB)",
		c->max_bud_bytes, c->max_bud_bytes >> 10,
		c->max_bud_bytes >> 20);
	dbg_gen("BG commit bud bytes: %lld (%lld KiB, %lld MiB)",
		c->bg_bud_bytes, c->bg_bud_bytes >> 10,
		c->bg_bud_bytes >> 20);
	dbg_gen("current bud bytes    %lld (%lld KiB, %lld MiB)",
		c->bud_bytes, c->bud_bytes >> 10, c->bud_bytes >> 20);
	dbg_gen("max. seq. number:    %llu", c->max_sqnum);
	dbg_gen("commit number:       %llu", c->cmt_no);

	return 0;

out_infos:
	spin_lock(&ubifs_infos_lock);
	list_del(&c->infos_list);
	spin_unlock(&ubifs_infos_lock);
out_orphans:
	free_orphans(c);
out_journal:
	destroy_journal(c);
out_lpt:
	ubifs_lpt_free(c, 0);
out_master:
	kfree(c->mst_node);
	kfree(c->rcvrd_mst_node);
	if (c->bgt)
		kthread_stop(c->bgt);
out_wbufs:
	free_wbufs(c);
out_cbuf:
	kfree(c->cbuf);
out_free:
	kfree(c->write_reserve_buf);
	kfree(c->bu.buf);
	vfree(c->ileb_buf);
	vfree(c->sbuf);
	kfree(c->bottom_up_buf);
	ubifs_debugging_exit(c);
	return err;
}

/**
 * ubifs_umount - un-mount UBIFS file-system.
 * @c: UBIFS file-system description object
 *
 * Note, this function is called to free allocated resourced when un-mounting,
 * as well as free resources when an error occurred while we were half way
 * through mounting (error path cleanup function). So it has to make sure the
 * resource was actually allocated before freeing it.
 */
static void ubifs_umount(struct ubifs_info *c)
{
	dbg_gen("un-mounting UBI device %d, volume %d", c->vi.ubi_num,
		c->vi.vol_id);

	dbg_debugfs_exit_fs(c);
	spin_lock(&ubifs_infos_lock);
	list_del(&c->infos_list);
	spin_unlock(&ubifs_infos_lock);

	if (c->bgt)
		kthread_stop(c->bgt);

	destroy_journal(c);
	free_wbufs(c);
	free_orphans(c);
	ubifs_lpt_free(c, 0);

	kfree(c->cbuf);
	kfree(c->rcvrd_mst_node);
	kfree(c->mst_node);
	kfree(c->write_reserve_buf);
	kfree(c->bu.buf);
	vfree(c->ileb_buf);
	vfree(c->sbuf);
	kfree(c->bottom_up_buf);
	ubifs_debugging_exit(c);
}

/**
 * ubifs_remount_rw - re-mount in read-write mode.
 * @c: UBIFS file-system description object
 *
 * UBIFS avoids allocating many unnecessary resources when mounted in read-only
 * mode. This function allocates the needed resources and re-mounts UBIFS in
 * read-write mode.
 */
static int ubifs_remount_rw(struct ubifs_info *c)
{
	int err, lnum;

	if (c->rw_incompat) {
		ubifs_err(c, "the file-system is not R/W-compatible");
		ubifs_msg(c, "on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d",
			  c->fmt_version, c->ro_compat_version,
			  UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION);
		return -EROFS;
	}

	mutex_lock(&c->umount_mutex);
	dbg_save_space_info(c);
	c->remounting_rw = 1;
	c->ro_mount = 0;

	if (c->space_fixup) {
		err = ubifs_fixup_free_space(c);
		if (err)
			goto out;
	}

	err = check_free_space(c);
	if (err)
		goto out;

	if (c->old_leb_cnt != c->leb_cnt) {
		struct ubifs_sb_node *sup;

		sup = ubifs_read_sb_node(c);
		if (IS_ERR(sup)) {
			err = PTR_ERR(sup);
			goto out;
		}
		sup->leb_cnt = cpu_to_le32(c->leb_cnt);
		err = ubifs_write_sb_node(c, sup);
		kfree(sup);
		if (err)
			goto out;
	}

	if (c->need_recovery) {
		ubifs_msg(c, "completing deferred recovery");
		err = ubifs_write_rcvrd_mst_node(c);
		if (err)
			goto out;
		err = ubifs_recover_size(c);
		if (err)
			goto out;
		err = ubifs_clean_lebs(c, c->sbuf);
		if (err)
			goto out;
		err = ubifs_recover_inl_heads(c, c->sbuf);
		if (err)
			goto out;
	} else {
		/* A readonly mount is not allowed to have orphans */
		ubifs_assert(c->tot_orphans == 0);
		err = ubifs_clear_orphans(c);
		if (err)
			goto out;
	}

	if (!(c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY))) {
		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
		err = ubifs_write_master(c);
		if (err)
			goto out;
	}

	c->ileb_buf = vmalloc(c->leb_size);
	if (!c->ileb_buf) {
		err = -ENOMEM;
		goto out;
	}

	c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ, GFP_KERNEL);
	if (!c->write_reserve_buf) {
		err = -ENOMEM;
		goto out;
	}

	err = ubifs_lpt_init(c, 0, 1);
	if (err)
		goto out;

	/* Create background thread */
	c->bgt = kthread_create(ubifs_bg_thread, c, "%s", c->bgt_name);
	if (IS_ERR(c->bgt)) {
		err = PTR_ERR(c->bgt);
		c->bgt = NULL;
		ubifs_err(c, "cannot spawn \"%s\", error %d",
			  c->bgt_name, err);
		goto out;
	}
	wake_up_process(c->bgt);

	c->orph_buf = vmalloc(c->leb_size);
	if (!c->orph_buf) {
		err = -ENOMEM;
		goto out;
	}

	/* Check for enough log space */
	lnum = c->lhead_lnum + 1;
	if (lnum >= UBIFS_LOG_LNUM + c->log_lebs)
		lnum = UBIFS_LOG_LNUM;
	if (lnum == c->ltail_lnum) {
		err = ubifs_consolidate_log(c);
		if (err)
			goto out;
	}

	if (c->need_recovery)
		err = ubifs_rcvry_gc_commit(c);
	else
		err = ubifs_leb_unmap(c, c->gc_lnum);
	if (err)
		goto out;

	dbg_gen("re-mounted read-write");
	c->remounting_rw = 0;

	if (c->need_recovery) {
		c->need_recovery = 0;
		ubifs_msg(c, "deferred recovery completed");
	} else {
		/*
		 * Do not run the debugging space check if the were doing
		 * recovery, because when we saved the information we had the
		 * file-system in a state where the TNC and lprops has been
		 * modified in memory, but all the I/O operations (including a
		 * commit) were deferred. So the file-system was in
		 * "non-committed" state. Now the file-system is in committed
		 * state, and of course the amount of free space will change
		 * because, for example, the old index size was imprecise.
		 */
		err = dbg_check_space_info(c);
	}

	mutex_unlock(&c->umount_mutex);
	return err;

out:
	c->ro_mount = 1;
	vfree(c->orph_buf);
	c->orph_buf = NULL;
	if (c->bgt) {
		kthread_stop(c->bgt);
		c->bgt = NULL;
	}
	free_wbufs(c);
	kfree(c->write_reserve_buf);
	c->write_reserve_buf = NULL;
	vfree(c->ileb_buf);
	c->ileb_buf = NULL;
	ubifs_lpt_free(c, 1);
	c->remounting_rw = 0;
	mutex_unlock(&c->umount_mutex<
/*******************************************************************************

  Intel 10 Gigabit PCI Express Linux driver
  Copyright(c) 1999 - 2013 Intel Corporation.

  This program is free software; you can redistribute it and/or modify it
  under the terms and conditions of the GNU General Public License,
  version 2, as published by the Free Software Foundation.

  This program is distributed in the hope it will be useful, but WITHOUT
  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  more details.

  You should have received a copy of the GNU General Public License along with
  this program; if not, write to the Free Software Foundation, Inc.,
  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.

  The full GNU General Public License is included in this distribution in
  the file called "COPYING".

  Contact Information:
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

*******************************************************************************/

#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
#include <linux/pkt_sched.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/if_macvlan.h>
#include <linux/if_bridge.h>
#include <linux/prefetch.h>
#include <scsi/fc/fc_fcoe.h>

#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
#include "ixgbe_sriov.h"

char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
			      "Intel(R) 10 Gigabit PCI Express Network Driver";
#ifdef IXGBE_FCOE
char ixgbe_default_device_descr[] =
			      "Intel(R) 10 Gigabit Network Connection";
#else
static char ixgbe_default_device_descr[] =
			      "Intel(R) 10 Gigabit Network Connection";
#endif
#define DRV_VERSION "3.19.1-k"
const char ixgbe_driver_version[] = DRV_VERSION;
static const char ixgbe_copyright[] =
				"Copyright (c) 1999-2013 Intel Corporation.";

static const struct ixgbe_info *ixgbe_info_tbl[] = {
	[board_82598] = &ixgbe_82598_info,
	[board_82599] = &ixgbe_82599_info,
	[board_X540] = &ixgbe_X540_info,
};

/* ixgbe_pci_tbl - PCI Device ID Table
 *
 * Wildcard entries (PCI_ANY_ID) should come last
 * Last entry must be all 0s
 *
 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
 *   Class, Class Mask, private data (not used) }
 */
static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 },
	/* required last entry */
	{0, }
};
MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl);

#ifdef CONFIG_IXGBE_DCA
static int ixgbe_notify_dca(struct notifier_block *, unsigned long event,
			    void *p);
static struct notifier_block dca_notifier = {
	.notifier_call = ixgbe_notify_dca,
	.next          = NULL,
	.priority      = 0
};
#endif

#ifdef CONFIG_PCI_IOV
static unsigned int max_vfs;
module_param(max_vfs, uint, 0);
MODULE_PARM_DESC(max_vfs,
		 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)");
#endif /* CONFIG_PCI_IOV */

static unsigned int allow_unsupported_sfp;
module_param(allow_unsupported_sfp, uint, 0);
MODULE_PARM_DESC(allow_unsupported_sfp,
		 "Allow unsupported and untested SFP+ modules on 82599-based adapters");

#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
static int debug = -1;
module_param(debug, int, 0);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
					  u32 reg, u16 *value)
{
	struct pci_dev *parent_dev;
	struct pci_bus *parent_bus;

	parent_bus = adapter->pdev->bus->parent;
	if (!parent_bus)
		return -1;

	parent_dev = parent_bus->self;
	if (!parent_dev)
		return -1;

	if (!pci_is_pcie(parent_dev))
		return -1;

	pcie_capability_read_word(parent_dev, reg, value);
	return 0;
}

static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u16 link_status = 0;
	int err;

	hw->bus.type = ixgbe_bus_type_pci_express;

	/* Get the negotiated link width and speed from PCI config space of the
	 * parent, as this device is behind a switch
	 */
	err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status);

	/* assume caller will handle error case */
	if (err)
		return err;

	hw->bus.width = ixgbe_convert_bus_width(link_status);
	hw->bus.speed = ixgbe_convert_bus_speed(link_status);

	return 0;
}

/**
 * ixgbe_check_from_parent - Determine whether PCIe info should come from parent
 * @hw: hw specific details
 *
 * This function is used by probe to determine whether a device's PCI-Express
 * bandwidth details should be gathered from the parent bus instead of from the
 * device. Used to ensure that various locations all have the correct device ID
 * checks.
 */
static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
{
	switch (hw->device_id) {
	case IXGBE_DEV_ID_82599_SFP_SF_QP:
	case IXGBE_DEV_ID_82599_QSFP_SF_QP:
		return true;
	default:
		return false;
	}
}

static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter,
				     int expected_gts)
{
	int max_gts = 0;
	enum pci_bus_speed speed = PCI_SPEED_UNKNOWN;
	enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN;
	struct pci_dev *pdev;

	/* determine whether to use the the parent device
	 */
	if (ixgbe_pcie_from_parent(&adapter->hw))
		pdev = adapter->pdev->bus->parent->self;
	else
		pdev = adapter->pdev;

	if (pcie_get_minimum_link(pdev, &speed, &width) ||
	    speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) {
		e_dev_warn("Unable to determine PCI Express bandwidth.\n");
		return;
	}

	switch (speed) {
	case PCIE_SPEED_2_5GT:
		/* 8b/10b encoding reduces max throughput by 20% */
		max_gts = 2 * width;
		break;
	case PCIE_SPEED_5_0GT:
		/* 8b/10b encoding reduces max throughput by 20% */
		max_gts = 4 * width;
		break;
	case PCIE_SPEED_8_0GT:
		/* 128b/130b encoding reduces throughput by less than 2% */
		max_gts = 8 * width;
		break;
	default:
		e_dev_warn("Unable to determine PCI Express bandwidth.\n");
		return;
	}

	e_dev_info("PCI Express bandwidth of %dGT/s available\n",
		   max_gts);
	e_dev_info("(Speed:%s, Width: x%d, Encoding Loss:%s)\n",
		   (speed == PCIE_SPEED_8_0GT ? "8.0GT/s" :
		    speed == PCIE_SPEED_5_0GT ? "5.0GT/s" :
		    speed == PCIE_SPEED_2_5GT ? "2.5GT/s" :
		    "Unknown"),
		   width,
		   (speed == PCIE_SPEED_2_5GT ? "20%" :
		    speed == PCIE_SPEED_5_0GT ? "20%" :
		    speed == PCIE_SPEED_8_0GT ? "<2%" :
		    "Unknown"));

	if (max_gts < expected_gts) {
		e_dev_warn("This is not sufficient for optimal performance of this card.\n");
		e_dev_warn("For optimal performance, at least %dGT/s of bandwidth is required.\n",
			expected_gts);
		e_dev_warn("A slot with more lanes and/or higher speed is suggested.\n");
	}
}

static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter)
{
	if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
	    !test_bit(__IXGBE_REMOVING, &adapter->state) &&
	    !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state))
		schedule_work(&adapter->service_task);
}

static void ixgbe_remove_adapter(struct ixgbe_hw *hw)
{
	struct ixgbe_adapter *adapter = hw->back;

	if (!hw->hw_addr)
		return;
	hw->hw_addr = NULL;
	e_dev_err("Adapter removed\n");
	ixgbe_service_event_schedule(adapter);
}

void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
{
	u32 value;

	/* The following check not only optimizes a bit by not
	 * performing a read on the status register when the
	 * register just read was a status register read that
	 * returned IXGBE_FAILED_READ_REG. It also blocks any
	 * potential recursion.
	 */
	if (reg == IXGBE_STATUS) {
		ixgbe_remove_adapter(hw);
		return;
	}
	value = ixgbe_read_reg(hw, IXGBE_STATUS);
	if (value == IXGBE_FAILED_READ_REG)
		ixgbe_remove_adapter(hw);
}

static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
{
	BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));

	/* flush memory to make sure state is correct before next watchdog */
	smp_mb__before_clear_bit();
	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
}

struct ixgbe_reg_info {
	u32 ofs;
	char *name;
};

static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {

	/* General Registers */
	{IXGBE_CTRL, "CTRL"},
	{IXGBE_STATUS, "STATUS"},
	{IXGBE_CTRL_EXT, "CTRL_EXT"},

	/* Interrupt Registers */
	{IXGBE_EICR, "EICR"},

	/* RX Registers */
	{IXGBE_SRRCTL(0), "SRRCTL"},
	{IXGBE_DCA_RXCTRL(0), "DRXCTL"},
	{IXGBE_RDLEN(0), "RDLEN"},
	{IXGBE_RDH(0), "RDH"},
	{IXGBE_RDT(0), "RDT"},
	{IXGBE_RXDCTL(0), "RXDCTL"},
	{IXGBE_RDBAL(0), "RDBAL"},
	{IXGBE_RDBAH(0), "RDBAH"},

	/* TX Registers */
	{IXGBE_TDBAL(0), "TDBAL"},
	{IXGBE_TDBAH(0), "TDBAH"},
	{IXGBE_TDLEN(0), "TDLEN"},
	{IXGBE_TDH(0), "TDH"},
	{IXGBE_TDT(0), "TDT"},
	{IXGBE_TXDCTL(0), "TXDCTL"},

	/* List Terminator */
	{}
};


/*
 * ixgbe_regdump - register printout routine
 */
static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
{
	int i = 0, j = 0;
	char rname[16];
	u32 regs[64];

	switch (reginfo->ofs) {
	case IXGBE_SRRCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i));
		break;
	case IXGBE_DCA_RXCTRL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
		break;
	case IXGBE_RDLEN(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i));
		break;
	case IXGBE_RDH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i));
		break;
	case IXGBE_RDT(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i));
		break;
	case IXGBE_RXDCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i));
		break;
	case IXGBE_RDBAL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i));
		break;
	case IXGBE_RDBAH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i));
		break;
	case IXGBE_TDBAL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i));
		break;
	case IXGBE_TDBAH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i));
		break;
	case IXGBE_TDLEN(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i));
		break;
	case IXGBE_TDH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i));
		break;
	case IXGBE_TDT(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i));
		break;
	case IXGBE_TXDCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
		break;
	default:
		pr_info("%-15s %08x\n", reginfo->name,
			IXGBE_READ_REG(hw, reginfo->ofs));
		return;
	}

	for (i = 0; i < 8; i++) {
		snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7);
		pr_err("%-15s", rname);
		for (j = 0; j < 8; j++)
			pr_cont(" %08x", regs[i*8+j]);
		pr_cont("\n");
	}

}

/*
 * ixgbe_dump - Print registers, tx-rings and rx-rings
 */
static void ixgbe_dump(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_reg_info *reginfo;
	int n = 0;
	struct ixgbe_ring *tx_ring;
	struct ixgbe_tx_buffer *tx_buffer;
	union ixgbe_adv_tx_desc *tx_desc;
	struct my_u0 { u64 a; u64 b; } *u0;
	struct ixgbe_ring *rx_ring;
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbe_rx_buffer *rx_buffer_info;
	u32 staterr;
	int i = 0;

	if (!netif_msg_hw(adapter))
		return;

	/* Print netdevice Info */
	if (netdev) {
		dev_info(&adapter->pdev->dev, "Net device Info\n");
		pr_info("Device Name     state            "
			"trans_start      last_rx\n");
		pr_info("%-15s %016lX %016lX %016lX\n",
			netdev->name,
			netdev->state,
			netdev->trans_start,
			netdev->last_rx);
	}

	/* Print Registers */
	dev_info(&adapter->pdev->dev, "Register Dump\n");
	pr_info(" Register Name   Value\n");
	for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl;
	     reginfo->name; reginfo++) {
		ixgbe_regdump(hw, reginfo);
	}

	/* Print TX Ring Summary */
	if (!netdev || !netif_running(netdev))
		goto exit;

	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
	pr_info(" %s     %s              %s        %s\n",
		"Queue [NTU] [NTC] [bi(ntc)->dma  ]",
		"leng", "ntw", "timestamp");
	for (n = 0; n < adapter->num_tx_queues; n++) {
		tx_ring = adapter->tx_ring[n];
		tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
		pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
			   n, tx_ring->next_to_use, tx_ring->next_to_clean,
			   (u64)dma_unmap_addr(tx_buffer, dma),
			   dma_unmap_len(tx_buffer, len),
			   tx_buffer->next_to_watch,
			   (u64)tx_buffer->time_stamp);
	}

	/* Print TX Rings */
	if (!netif_msg_tx_done(adapter))
		goto rx_ring_summary;

	dev_info(&adapter->pdev->dev, "TX Rings Dump\n");

	/* Transmit Descriptor Formats
	 *
	 * 82598 Advanced Transmit Descriptor
	 *   +--------------------------------------------------------------+
	 * 0 |         Buffer Address [63:0]                                |
	 *   +--------------------------------------------------------------+
	 * 8 |  PAYLEN  | POPTS  | IDX | STA | DCMD  |DTYP |  RSV |  DTALEN |
	 *   +--------------------------------------------------------------+
	 *   63       46 45    40 39 36 35 32 31   24 23 20 19              0
	 *
	 * 82598 Advanced Transmit Descriptor (Write-Back Format)
	 *   +--------------------------------------------------------------+
	 * 0 |                          RSV [63:0]                          |
	 *   +--------------------------------------------------------------+
	 * 8 |            RSV           |  STA  |          NXTSEQ           |
	 *   +--------------------------------------------------------------+
	 *   63                       36 35   32 31                         0
	 *
	 * 82599+ Advanced Transmit Descriptor
	 *   +--------------------------------------------------------------+
	 * 0 |         Buffer Address [63:0]                                |
	 *   +--------------------------------------------------------------+
	 * 8 |PAYLEN  |POPTS|CC|IDX  |STA  |DCMD  |DTYP |MAC  |RSV  |DTALEN |
	 *   +--------------------------------------------------------------+
	 *   63     46 45 40 39 38 36 35 32 31  24 23 20 19 18 17 16 15     0
	 *
	 * 82599+ Advanced Transmit Descriptor (Write-Back Format)
	 *   +--------------------------------------------------------------+
	 * 0 |                          RSV [63:0]                          |
	 *   +--------------------------------------------------------------+
	 * 8 |            RSV           |  STA  |           RSV             |
	 *   +--------------------------------------------------------------+
	 *   63                       36 35   32 31                         0
	 */

	for (n = 0; n < adapter->num_tx_queues; n++) {
		tx_ring = adapter->tx_ring[n];
		pr_info("------------------------------------\n");
		pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
		pr_info("------------------------------------\n");
		pr_info("%s%s    %s              %s        %s          %s\n",
			"T [desc]     [address 63:0  ] ",
			"[PlPOIdStDDt Ln] [bi->dma       ] ",
			"leng", "ntw", "timestamp", "bi->skb");

		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
			tx_desc = IXGBE_TX_DESC(tx_ring, i);
			tx_buffer = &tx_ring->tx_buffer_info[i];
			u0 = (struct my_u0 *)tx_desc;
			if (dma_unmap_len(tx_buffer, len) > 0) {
				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p",
					i,
					le64_to_cpu(u0->a),
					le64_to_cpu(u0->b),
					(u64)dma_unmap_addr(tx_buffer, dma),
					dma_unmap_len(tx_buffer, len),
					tx_buffer->next_to_watch,
					(u64)tx_buffer->time_stamp,
					tx_buffer->skb);
				if (i == tx_ring->next_to_use &&
					i == tx_ring->next_to_clean)
					pr_cont(" NTC/U\n");
				else if (i == tx_ring->next_to_use)
					pr_cont(" NTU\n");
				else if (i == tx_ring->next_to_clean)
					pr_cont(" NTC\n");
				else
					pr_cont("\n");

				if (netif_msg_pktdata(adapter) &&
				    tx_buffer->skb)
					print_hex_dump(KERN_INFO, "",
						DUMP_PREFIX_ADDRESS, 16, 1,
						tx_buffer->skb->data,
						dma_unmap_len(tx_buffer, len),
						true);
			}
		}
	}

	/* Print RX Rings Summary */
rx_ring_summary:
	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
	pr_info("Queue [NTU] [NTC]\n");
	for (n = 0; n < adapter->num_rx_queues; n++) {
		rx_ring = adapter->rx_ring[n];
		pr_info("%5d %5X %5X\n",
			n, rx_ring->next_to_use, rx_ring->next_to_clean);
	}

	/* Print RX Rings */
	if (!netif_msg_rx_status(adapter))
		goto exit;

	dev_info(&adapter->pdev->dev, "RX Rings Dump\n");

	/* Receive Descriptor Formats
	 *
	 * 82598 Advanced Receive Descriptor (Read) Format
	 *    63                                           1        0
	 *    +-----------------------------------------------------+
	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
	 *    +----------------------------------------------+------+
	 *  8 |       Header Buffer Address [63:1]           |  DD  |
	 *    +-----------------------------------------------------+
	 *
	 *
	 * 82598 Advanced Receive Descriptor (Write-Back) Format
	 *
	 *   63       48 47    32 31  30      21 20 16 15   4 3     0
	 *   +------------------------------------------------------+
	 * 0 |       RSS Hash /  |SPH| HDR_LEN  | RSV |Packet|  RSS |
	 *   | Packet   | IP     |   |          |     | Type | Type |
	 *   | Checksum | Ident  |   |          |     |      |      |
	 *   +------------------------------------------------------+
	 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
	 *   +------------------------------------------------------+
	 *   63       48 47    32 31            20 19               0
	 *
	 * 82599+ Advanced Receive Descriptor (Read) Format
	 *    63                                           1        0
	 *    +-----------------------------------------------------+
	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
	 *    +----------------------------------------------+------+
	 *  8 |       Header Buffer Address [63:1]           |  DD  |
	 *    +-----------------------------------------------------+
	 *
	 *
	 * 82599+ Advanced Receive Descriptor (Write-Back) Format
	 *
	 *   63       48 47    32 31  30      21 20 17 16   4 3     0
	 *   +------------------------------------------------------+
	 * 0 |RSS / Frag Checksum|SPH| HDR_LEN  |RSC- |Packet|  RSS |
	 *   |/ RTT / PCoE_PARAM |   |          | CNT | Type | Type |
	 *   |/ Flow Dir Flt ID  |   |          |     |      |      |
	 *   +------------------------------------------------------+
	 * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP |
	 *   +------------------------------------------------------+
	 *   63       48 47    32 31          20 19                 0
	 */

	for (n = 0; n < adapter->num_rx_queues; n++) {
		rx_ring = adapter->rx_ring[n];
		pr_info("------------------------------------\n");
		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
		pr_info("------------------------------------\n");
		pr_info("%s%s%s",
			"R  [desc]      [ PktBuf     A0] ",
			"[  HeadBuf   DD] [bi->dma       ] [bi->skb       ] ",
			"<-- Adv Rx Read format\n");
		pr_info("%s%s%s",
			"RWB[desc]      [PcsmIpSHl PtRs] ",
			"[vl er S cks ln] ---------------- [bi->skb       ] ",
			"<-- Adv Rx Write-Back format\n");

		for (i = 0; i < rx_ring->count; i++) {
			rx_buffer_info = &rx_ring->rx_buffer_info[i];
			rx_desc = IXGBE_RX_DESC(rx_ring, i);
			u0 = (struct my_u0 *)rx_desc;
			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
			if (staterr & IXGBE_RXD_STAT_DD) {
				/* Descriptor Done */
				pr_info("RWB[0x%03X]     %016llX "
					"%016llX ---------------- %p", i,
					le64_to_cpu(u0->a),
					le64_to_cpu(u0->b),
					rx_buffer_info->skb);
			} else {
				pr_info("R  [0x%03X]     %016llX "
					"%016llX %016llX %p", i,
					le64_to_cpu(u0->a),
					le64_to_cpu(u0->b),
					(u64)rx_buffer_info->dma,
					rx_buffer_info->skb);

				if (netif_msg_pktdata(adapter) &&
				    rx_buffer_info->dma) {
					print_hex_dump(KERN_INFO, "",
					   DUMP_PREFIX_ADDRESS, 16, 1,
					   page_address(rx_buffer_info->page) +
						    rx_buffer_info->page_offset,
					   ixgbe_rx_bufsz(rx_ring), true);
				}
			}

			if (i == rx_ring->next_to_use)
				pr_cont(" NTU\n");
			else if (i == rx_ring->next_to_clean)
				pr_cont(" NTC\n");
			else
				pr_cont("\n");

		}
	}

exit:
	return;
}

static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
{
	u32 ctrl_ext;

	/* Let firmware take over control of h/w */
	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
			ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD);
}

static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter)
{
	u32 ctrl_ext;

	/* Let firmware know the driver has taken over */
	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
			ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD);
}

/**
 * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
 * @adapter: pointer to adapter struct
 * @direction: 0 for Rx, 1 for Tx, -1 for other causes
 * @queue: queue to map the corresponding interrupt to
 * @msix_vector: the vector to map to the corresponding queue
 *
 */
static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
			   u8 queue, u8 msix_vector)
{
	u32 ivar, index;
	struct ixgbe_hw *hw = &adapter->hw;
	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
		if (direction == -1)
			direction = 0;
		index = (((direction * 64) + queue) >> 2) & 0x1F;
		ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
		ivar &= ~(0xFF << (8 * (queue & 0x3)));
		ivar |= (msix_vector << (8 * (queue & 0x3)));
		IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		if (direction == -1) {
			/* other causes */
			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
			index = ((queue & 1) * 8);
			ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC);
			ivar &= ~(0xFF << index);
			ivar |= (msix_vector << index);
			IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar);
			break;
		} else {
			/* tx or rx causes */
			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
			index = ((16 * (queue & 1)) + (8 * direction));
			ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1));
			ivar &= ~(0xFF << index);
			ivar |= (msix_vector << index);
			IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar);
			break;
		}
	default:
		break;
	}
}

static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
					  u64 qmask)
{
	u32 mask;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82598EB:
		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		mask = (qmask & 0xFFFFFFFF);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
		mask = (qmask >> 32);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
		break;
	default:
		break;
	}
}

void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring,
				      struct ixgbe_tx_buffer *tx_buffer)
{
	if (tx_buffer->skb) {
		dev_kfree_skb_any(tx_buffer->skb);
		if (dma_unmap_len(tx_buffer, len))
			dma_unmap_single(ring->dev,
					 dma_unmap_addr(tx_buffer, dma),
					 dma_unmap_len(tx_buffer, len),
					 DMA_TO_DEVICE);
	} else if (dma_unmap_len(tx_buffer, len)) {
		dma_unmap_page(ring->dev,
			       dma_unmap_addr(tx_buffer, dma),
			       dma_unmap_len(tx_buffer, len),
			       DMA_TO_DEVICE);
	}
	tx_buffer->next_to_watch = NULL;
	tx_buffer->skb = NULL;
	dma_unmap_len_set(tx_buffer, len, 0);
	/* tx_buffer must be completely set up in the transmit path */
}

static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_hw_stats *hwstats = &adapter->stats;
	int i;
	u32 data;

	if ((hw->fc.current_mode != ixgbe_fc_full) &&
	    (hw->fc.current_mode != ixgbe_fc_rx_pause))
		return;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
		break;
	default:
		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
	}
	hwstats->lxoffrxc += data;

	/* refill credits (no tx hang) if we received xoff */
	if (!data)
		return;

	for (i = 0; i < adapter->num_tx_queues; i++)
		clear_bit(__IXGBE_HANG_CHECK_ARMED,
			  &adapter->tx_ring[i]->state);
}

static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_hw_stats *hwstats = &adapter->stats;
	u32 xoff[8] = {0};
	u8 tc;
	int i;
	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;

	if (adapter->ixgbe_ieee_pfc)
		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);

	if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) {
		ixgbe_update_xoff_rx_lfc(adapter);
		return;
	}

	/* update stats for each tc, only valid with PFC enabled */
	for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
		u32 pxoffrxc;

		switch (hw->mac.type) {
		case ixgbe_mac_82598EB:
			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
			break;
		default:
			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
		}
		hwstats->pxoffrxc[i] += pxoffrxc;
		/* Get the TC for given UP */
		tc = netdev_get_prio_tc_map(adapter->netdev, i);
		xoff[tc] += pxoffrxc;
	}

	/* disarm tx queues that have received xoff frames */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];

		tc = tx_ring->dcb_tc;
		if (xoff[tc])
			clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
	}
}

static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
{
	return ring->stats.packets;
}

static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
{
	struct ixgbe_adapter *adapter;
	struct ixgbe_hw *hw;
	u32 head, tail;

	if (ring->l2_accel_priv)
		adapter = ring->l2_accel_priv->real_adapter;
	else
		adapter = netdev_priv(ring->netdev);

	hw = &adapter->hw;
	head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
	tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));

	if (head != tail)
		return (head < tail) ?
			tail - head : (tail + ring->count - head);

	return 0;
}

static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
{
	u32 tx_done = ixgbe_get_tx_completed(tx_ring);
	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
	u32 tx_pending = ixgbe_get_tx_pending(tx_ring);
	bool ret = false;

	clear_check_for_tx_hang(tx_ring);

	/*
	 * Check for a hung queue, but be thorough. This verifies
	 * that a transmit has been completed since the previous
	 * check AND there is at least one packet pending. The
	 * ARMED bit is set to indicate a potential hang. The
	 * bit is cleared if a pause frame is received to remove
	 * false hang detection due to PFC or 802.3x frames. By
	 * requiring this to fail twice we avoid races with
	 * pfc clearing the ARMED bit and conditions where we
	 * run the check_tx_hang logic with a transmit completion
	 * pending but without time to complete it yet.
	 */
	if ((tx_done_old == tx_done) && tx_pending) {
		/* make sure it is true for two checks in a row */
		ret = test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
				       &tx_ring->state);
	} else {
		/* update completed stats and continue */
		tx_ring->tx_stats.tx_done_old = tx_done;
		/* reset the countdown */
		clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
	}

	return ret;
}

/**
 * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout
 * @adapter: driver private struct
 **/
static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
{

	/* Do the reset outside of interrupt context */
	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
		adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
		e_warn(drv, "initiating reset due to tx timeout\n");
		ixgbe_service_event_schedule(adapter);
	}
}

/**
 * ixgbe_clean_tx_irq - Reclaim resources after transmit completes
 * @q_vector: structure containing interrupt and ring information
 * @tx_ring: tx ring to clean
 **/
static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
			       struct ixgbe_ring *tx_ring)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_tx_buffer *tx_buffer;
	union ixgbe_adv_tx_desc *tx_desc;
	unsigned int total_bytes = 0, total_packets = 0;
	unsigned int budget = q_vector->tx.work_limit;
	unsigned int i = tx_ring->next_to_clean;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return true;

	tx_buffer = &tx_ring->tx_buffer_info[i];
	tx_desc = IXGBE_TX_DESC(tx_ring, i);
	i -= tx_ring->count;

	do {
		union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;

		/* if next_to_watch is not set then there is no work pending */
		if (!eop_desc)
			break;

		/* prevent any other reads prior to eop_desc */
		read_barrier_depends();

		/* if DD is not set pending work has not been completed */
		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
			break;

		/* clear next_to_watch to prevent false hangs */
		tx_buffer->next_to_watch = NULL;

		/* update the statistics for this packet */
		total_bytes += tx_buffer->bytecount;
		total_packets += tx_buffer->gso_segs;

		/* free the skb */
		dev_kfree_skb_any(tx_buffer->skb);

		/* unmap skb header data */
		dma_unmap_single(tx_ring->dev,
				 dma_unmap_addr(tx_buffer, dma),
				 dma_unmap_len(tx_buffer, len),
				 DMA_TO_DEVICE);

		/* clear tx_buffer data */
		tx_buffer->skb = NULL;
		dma_unmap_len_set(tx_buffer, len, 0);

		/* unmap remaining buffers */
		while (tx_desc != eop_desc) {
			tx_buffer++;
			tx_desc++;
			i++;
			if (unlikely(!i)) {
				i -= tx_ring->count;
				tx_buffer = tx_ring->tx_buffer_info;
				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
			}

			/* unmap any remaining paged data */
			if (dma_unmap_len(tx_buffer, len)) {
				dma_unmap_page(tx_ring->dev,
					       dma_unmap_addr(tx_buffer, dma),
					       dma_unmap_len(tx_buffer, len),
					       DMA_TO_DEVICE);
				dma_unmap_len_set(tx_buffer, len, 0);
			}
		}

		/* move us one more past the eop_desc for start of next pkt */
		tx_buffer++;
		tx_desc++;
		i++;
		if (unlikely(!i)) {
			i -= tx_ring->count;
			tx_buffer = tx_ring->tx_buffer_info;
			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
		}

		/* issue prefetch for next Tx descriptor */
		prefetch(tx_desc);

		/* update budget accounting */
		budget--;
	} while (likely(budget));

	i += tx_ring->count;
	tx_ring->next_to_clean = i;
	u64_stats_update_begin(&tx_ring->syncp);
	tx_ring->stats.bytes += total_bytes;
	tx_ring->stats.packets += total_packets;
	u64_stats_update_end(&tx_ring->syncp);
	q_vector->tx.total_bytes += total_bytes;
	q_vector->tx.total_packets += total_packets;

	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
		/* schedule immediate reset if we believe we hung */
		struct ixgbe_hw *hw = &adapter->hw;
		e_err(drv, "Detected Tx Unit Hang\n"
			"  Tx Queue             <%d>\n"
			"  TDH, TDT             <%x>, <%x>\n"
			"  next_to_use          <%x>\n"
			"  next_to_clean        <%x>\n"
			"tx_buffer_info[next_to_clean]\n"
			"  time_stamp           <%lx>\n"
			"  jiffies              <%lx>\n",
			tx_ring->queue_index,
			IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
			IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
			tx_ring->next_to_use, i,
			tx_ring->tx_buffer_info[i].time_stamp, jiffies);

		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);

		e_info(probe,
		       "tx hang %d detected on queue %d, resetting adapter\n",
			adapter->tx_timeout_count + 1, tx_ring->queue_index);

		/* schedule immediate reset if we believe we hung */
		ixgbe_tx_timeout_reset(adapter);

		/* the adapter is about to reset, no point in enabling stuff */
		return true;
	}

	netdev_tx_completed_queue(txring_txq(tx_ring),
				  total_packets, total_bytes);

#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
		     (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
		/* Make sure that anybody stopping the queue after this
		 * sees the new next_to_clean.
		 */
		smp_mb();
		if (__netif_subqueue_stopped(tx_ring->netdev,
					     tx_ring->queue_index)
		    && !test_bit(__IXGBE_DOWN, &adapter->state)) {
			netif_wake_subqueue(tx_ring->netdev,
					    tx_ring->queue_index);
			++tx_ring->tx_stats.restart_queue;
		}
	}

	return !!budget;
}

#ifdef CONFIG_IXGBE_DCA
static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
				struct ixgbe_ring *tx_ring,
				int cpu)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 txctrl = dca3_get_tag(tx_ring->dev, cpu);
	u16 reg_offset;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		reg_offset = IXGBE_DCA_TXCTRL_82599(tx_ring->reg_idx);
		txctrl <<= IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599;
		break;
	default:
		/* for unknown hardware do not write register */
		return;
	}

	/*
	 * We can enable relaxed ordering for reads, but not writes when
	 * DCA is enabled.  This is due to a known issue in some chipsets
	 * which will cause the DCA tag to be cleared.
	 */
	txctrl |= IXGBE_DCA_TXCTRL_DESC_RRO_EN |
		  IXGBE_DCA_TXCTRL_DATA_RRO_EN |
		  IXGBE_DCA_TXCTRL_DESC_DCA_EN;

	IXGBE_WRITE_REG(hw, reg_offset, txctrl);
}

static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
				struct ixgbe_ring *rx_ring,
				int cpu)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 rxctrl = dca3_get_tag(rx_ring->dev, cpu);
	u8 reg_idx = rx_ring->reg_idx;


	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		rxctrl <<= IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599;
		break;
	default:
		break;
	}

	/*
	 * We can enable relaxed ordering for reads, but not writes when
	 * DCA is enabled.  This is due to a known issue in some chipsets
	 * which will cause the DCA tag to be cleared.
	 */
	rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN |
		  IXGBE_DCA_RXCTRL_DESC_DCA_EN;

	IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl);
}

static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_ring *ring;
	int cpu = get_cpu();

	if (q_vector->cpu == cpu)
		goto out_no_update;

	ixgbe_for_each_ring(ring, q_vector->tx)
		ixgbe_update_tx_dca(adapter, ring, cpu);

	ixgbe_for_each_ring(ring, q_vector->rx)
		ixgbe_update_rx_dca(adapter, ring, cpu);

	q_vector->cpu = cpu;
out_no_update:
	put_cpu();
}

static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
{
	int i;

	if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED))
		return;

	/* always use CB2 mode, difference is masked in the CB driver */
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2);

	for (i = 0; i < adapter->num_q_vectors; i++) {
		adapter->q_vector[i]->cpu = -1;
		ixgbe_update_dca(adapter->q_vector[i]);
	}
}

static int __ixgbe_notify_dca(struct device *dev, void *data)
{
	struct ixgbe_adapter *adapter = dev_get_drvdata(dev);
	unsigned long event = *(unsigned long *)data;

	if (!(adapter->flags & IXGBE_FLAG_DCA_CAPABLE))
		return 0;

	switch (event) {
	case DCA_PROVIDER_ADD:
		/* if we're already enabled, don't do it again */
		if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
			break;
		if (dca_add_requester(dev) == 0) {
			adapter->flags |= IXGBE_FLAG_DCA_ENABLED;
			ixgbe_setup_dca(adapter);
			break;
		}
		/* Fall Through since DCA is disabled. */
	case DCA_PROVIDER_REMOVE:
		if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
			dca_remove_requester(dev);
			adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED;
			IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 1);
		}
		break;
	}

	return 0;
}

#endif /* CONFIG_IXGBE_DCA */
static inline void ixgbe_rx_hash(struct ixgbe_ring *ring,
				 union ixgbe_adv_rx_desc *rx_desc,
				 struct sk_buff *skb)
{
	if (ring->netdev->features & NETIF_F_RXHASH)
		skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
}

#ifdef IXGBE_FCOE
/**
 * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type
 * @ring: structure containing ring specific data
 * @rx_desc: advanced rx descriptor
 *
 * Returns : true if it is FCoE pkt
 */
static inline bool ixgbe_rx_is_fcoe(struct ixgbe_ring *ring,
				    union ixgbe_adv_rx_desc *rx_desc)
{
	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;

	return test_bit(__IXGBE_RX_FCOE, &ring->state) &&
	       ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) ==
		(cpu_to_le16(IXGBE_ETQF_FILTER_FCOE <<
			     IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT)));
}

#endif /* IXGBE_FCOE */
/**
 * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum
 * @ring: structure containing ring specific data
 * @rx_desc: current Rx descriptor being processed
 * @skb: skb currently being received and modified
 **/
static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
				     union ixgbe_adv_rx_desc *rx_desc,
				     struct sk_buff *skb)
{
	skb_checksum_none_assert(skb);

	/* Rx csum disabled */
	if (!(ring->netdev->features & NETIF_F_RXCSUM))
		return;

	/* if IP and error */
	if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) &&
	    ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) {
		ring->rx_stats.csum_err++;
		return;
	}

	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS))
		return;

	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) {
		__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;

		/*
		 * 82599 errata, UDP frames with a 0 checksum can be marked as
		 * checksum errors.
		 */
		if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_UDP)) &&
		    test_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state))
			return;

		ring->rx_stats.csum_err++;
		return;
	}

	/* It must be a TCP or UDP packet with a valid checksum */
	skb->ip_summed = CHECKSUM_UNNECESSARY;
}

static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val)
{
	rx_ring->next_to_use = val;

	/* update next to alloc since we have filled the ring */
	rx_ring->next_to_alloc = val;
	/*
	 * Force memory writes to complete before letting h/w
	 * know there are new descriptors to fetch.  (Only
	 * applicable for weak-ordered memory model archs,
	 * such as IA-64).
	 */
	wmb();
	ixgbe_write_tail(rx_ring, val);
}

static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
				    struct ixgbe_rx_buffer *bi)
{
	struct page *page = bi->page;
	dma_addr_t dma = bi->dma;

	/* since we are recycling buffers we should seldom need to alloc */
	if (likely(dma))
		return true;

	/* alloc new page for storage */
	if (likely(!page)) {
		page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP,
					 bi->skb, ixgbe_rx_pg_order(rx_ring));
		if (unlikely(!page)) {
			rx_ring->rx_stats.alloc_rx_page_failed++;
			return false;
		}
		bi->page = page;
	}

	/* map page for use */
	dma = dma_map_page(rx_ring->dev, page, 0,
			   ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);

	/*
	 * if mapping failed free memory back to system since
	 * there isn't much point in holding memory we can't use
	 */
	if (dma_mapping_error(rx_ring->dev, dma)) {
		__free_pages(page, ixgbe_rx_pg_order(rx_ring));
		bi->page = NULL;

		rx_ring->rx_stats.alloc_rx_page_failed++;
		return false;
	}

	bi->dma = dma;
	bi->page_offset = 0;

	return true;
}

/**
 * ixgbe_alloc_rx_buffers - Replace used receive buffers
 * @rx_ring: ring to place buffers on
 * @cleaned_count: number of buffers to replace
 **/
void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
{
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbe_rx_buffer *bi;
	u16 i = rx_ring->next_to_use;

	/* nothing to do */
	if (!cleaned_count)
		return;

	rx_desc = IXGBE_RX_DESC(rx_ring, i);
	bi = &rx_ring->rx_buffer_info[i];
	i -= rx_ring->count;

	do {
		if (!ixgbe_alloc_mapped_page(rx_ring, bi))
			break;

		/*
		 * Refresh the desc even if buffer_addrs didn't change
		 * because each write-back erases this info.
		 */
		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);

		rx_desc++;
		bi++;
		i++;
		if (unlikely(!i)) {
			rx_desc = IXGBE_RX_DESC(rx_ring, 0);
			bi = rx_ring->rx_buffer_info;
			i -= rx_ring->count;
		}

		/* clear the hdr_addr for the next_to_use descriptor */
		rx_desc->read.hdr_addr = 0;

		cleaned_count--;
	} while (cleaned_count);

	i += rx_ring->count;

	if (rx_ring->next_to_use != i)
		ixgbe_release_rx_desc(rx_ring, i);
}

/**
 * ixgbe_get_headlen - determine size of header for RSC/LRO/GRO/FCOE
 * @data: pointer to the start of the headers
 * @max_len: total length of section to find headers in
 *
 * This function is meant to determine the length of headers that will
 * be recognized by hardware for LRO, GRO, and RSC offloads.  The main
 * motivation of doing this is to only perform one pull for IPv4 TCP
 * packets so that we can do basic things like calculating the gso_size
 * based on the average data per packet.
 **/
static unsigned int ixgbe_get_headlen(unsigned char *data,
				      unsigned int max_len)
{
	union {
		unsigned char *network;
		/* l2 headers */
		struct ethhdr *eth;
		struct vlan_hdr *vlan;
		/* l3 headers */
		struct iphdr *ipv4;
		struct ipv6hdr *ipv6;
	} hdr;
	__be16 protocol;
	u8 nexthdr = 0;	/* default to not TCP */
	u8 hlen;

	/* this should never happen, but better safe than sorry */
	if (max_len < ETH_HLEN)
		return max_len;

	/* initialize network frame pointer */
	hdr.network = data;

	/* set first protocol and move network header forward */
	protocol = hdr.eth->h_proto;
	hdr.network += ETH_HLEN;

	/* handle any vlan tag if present */
	if (protocol == __constant_htons(ETH_P_8021Q)) {
		if ((hdr.network - data) > (max_len - VLAN_HLEN))
			return max_len;

		protocol = hdr.vlan->h_vlan_encapsulated_proto;
		hdr.network += VLAN_HLEN;
	}

	/* handle L3 protocols */
	if (protocol == __constant_htons(ETH_P_IP)) {
		if ((hdr.network - data) > (max_len - sizeof(struct iphdr)))
			return max_len;

		/* access ihl as a u8 to avoid unaligned access on ia64 */
		hlen = (hdr.network[0] & 0x0F) << 2;

		/* verify hlen meets minimum size requirements */
		if (hlen < sizeof(struct iphdr))
			return hdr.network - data;

		/* record next protocol if header is present */
		if (!(hdr.ipv4->frag_off & htons(IP_OFFSET)))
			nexthdr = hdr.ipv4->protocol;
	} else if (protocol == __constant_htons(ETH_P_IPV6)) {
		if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr)))
			return max_len;

		/* record next protocol */
		nexthdr = hdr.ipv6->nexthdr;
		hlen = sizeof(struct ipv6hdr);
#ifdef IXGBE_FCOE
	} else if (protocol == __constant_htons(ETH_P_FCOE)) {
		if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN))
			return max_len;
		hlen = FCOE_HEADER_LEN;
#endif
	} else {
		return hdr.network - data;
	}

	/* relocate pointer to start of L4 header */
	hdr.network += hlen;

	/* finally sort out TCP/UDP */
	if (nexthdr == IPPROTO_TCP) {
		if ((hdr.network - data) > (max_len - sizeof(struct tcphdr)))
			return max_len;

		/* access doff as a u8 to avoid unaligned access on ia64 */
		hlen = (hdr.network[12] & 0xF0) >> 2;

		/* verify hlen meets minimum size requirements */
		if (hlen < sizeof(struct tcphdr))
			return hdr.network - data;

		hdr.network += hlen;
	} else if (nexthdr == IPPROTO_UDP) {
		if ((hdr.network - data) > (max_len - sizeof(struct udphdr)))
			return max_len;

		hdr.network += sizeof(struct udphdr);
	}

	/*
	 * If everything has gone correctly hdr.network should be the
	 * data section of the packet and will be the end of the header.
	 * If not then it probably represents the end of the last recognized
	 * header.
	 */
	if ((hdr.network - data) < max_len)
		return hdr.network - data;
	else
		return max_len;
}

static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
				   struct sk_buff *skb)
{
	u16 hdr_len = skb_headlen(skb);

	/* set gso_size to avoid messing up TCP MSS */
	skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len),
						 IXGBE_CB(skb)->append_cnt);
	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
}

static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring,
				   struct sk_buff *skb)
{
	/* if append_cnt is 0 then frame is not RSC */
	if (!IXGBE_CB(skb)->append_cnt)
		return;

	rx_ring->rx_stats.rsc_count += IXGBE_CB(skb)->append_cnt;
	rx_ring->rx_stats.rsc_flush++;

	ixgbe_set_rsc_gso_size(rx_ring, skb);

	/* gso_size is computed using append_cnt so always clear it last */
	IXGBE_CB(skb)->append_cnt = 0;
}

/**
 * ixgbe_process_skb_fields - Populate skb header fields from Rx descriptor
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @rx_desc: pointer to the EOP Rx descriptor
 * @skb: pointer to current skb being populated
 *
 * This function checks the ring, descriptor, and packet information in
 * order to populate the hash, checksum, VLAN, timestamp, protocol, and
 * other fields within the skb.
 **/
static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
				     union ixgbe_adv_rx_desc *rx_desc,
				     struct sk_buff *skb)
{
	struct net_device *dev = rx_ring->netdev;

	ixgbe_update_rsc_stats(rx_ring, skb);

	ixgbe_rx_hash(rx_ring, rx_desc, skb);

	ixgbe_rx_checksum(rx_ring, rx_desc, skb);

	ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);

	if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
	    ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
		u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
	}

	skb_record_rx_queue(skb, rx_ring->queue_index);

	skb->protocol = eth_type_trans(skb, dev);
}

static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
			 struct sk_buff *skb)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;

	if (ixgbe_qv_busy_polling(q_vector))
		netif_receive_skb(skb);
	else if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
		napi_gro_receive(&q_vector->napi, skb);
	else
		netif_rx(skb);
}

/**
 * ixgbe_is_non_eop - process handling of non-EOP buffers
 * @rx_ring: Rx ring being processed
 * @rx_desc: Rx descriptor for current buffer
 * @skb: Current socket buffer containing buffer in progress
 *
 * This function updates next to clean.  If the buffer is an EOP buffer
 * this function exits returning false, otherwise it will place the
 * sk_buff in the next buffer to be chained and return true indicating
 * that this is in fact a non-EOP buffer.
 **/
static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
			     union ixgbe_adv_rx_desc *rx_desc,
			     struct sk_buff *skb)
{
	u32 ntc = rx_ring->next_to_clean + 1;

	/* fetch, update, and store next to clean */
	ntc = (ntc < rx_ring->count) ? ntc : 0;
	rx_ring->next_to_clean = ntc;

	prefetch(IXGBE_RX_DESC(rx_ring, ntc));

	/* update RSC append count if present */
	if (ring_is_rsc_enabled(rx_ring)) {
		__le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data &
				     cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK);

		if (unlikely(rsc_enabled)) {
			u32 rsc_cnt = le32_to_cpu(rsc_enabled);

			rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT;
			IXGBE_CB(skb)->append_cnt += rsc_cnt - 1;

			/* update ntc based on RSC value */
			ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
			ntc &= IXGBE_RXDADV_NEXTP_MASK;
			ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
		}
	}

	/* if we are the last buffer then there is nothing else to do */
	if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
		return false;

	/* place skb in next buffer to be received */
	rx_ring->rx_buffer_info[ntc].skb = skb;
	rx_ring->rx_stats.non_eop_descs++;

	return true;
}

/**
 * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @skb: pointer to current skb being adjusted
 *
 * This function is an ixgbe specific version of __pskb_pull_tail.  The
 * main difference between this version and the original function is that
 * this function can make several assumptions about the state of things
 * that allow for significant optimizations versus the standard function.
 * As a result we can do things like drop a frag and maintain an accurate
 * truesize for the skb.
 */
static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
			    struct sk_buff *skb)
{
	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
	unsigned char *va;
	unsigned int pull_len;

	/*
	 * it is valid to use page_address instead of kmap since we are
	 * working with pages allocated out of the lomem pool per
	 * alloc_page(GFP_ATOMIC)
	 */
	va = skb_frag_address(frag);

	/*
	 * we need the header to contain the greater of either ETH_HLEN or
	 * 60 bytes if the skb->len is less than 60 for skb_pad.
	 */
	pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);

	/* align pull length to size of long to optimize memcpy performance */
	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));

	/* update all of the pointers */
	skb_frag_size_sub(frag, pull_len);
	frag->page_offset += pull_len;
	skb->data_len -= pull_len;
	skb->tail += pull_len;
}

/**
 * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @skb: pointer to current skb being updated
 *
 * This function provides a basic DMA sync up for the first fragment of an
 * skb.  The reason for doing this is that the first fragment cannot be
 * unmapped until we have reached the end of packet descriptor for a buffer
 * chain.
 */
static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
				struct sk_buff *skb)
{
	/* if the page was released unmap it, else just sync our portion */
	if (unlikely(IXGBE_CB(skb)->page_released)) {
		dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
		IXGBE_CB(skb)->page_released = false;
	} else {
		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];

		dma_sync_single_range_for_cpu(rx_ring->dev,
					      IXGBE_CB(skb)->dma,
					      frag->page_offset,
					      ixgbe_rx_bufsz(rx_ring),
					      DMA_FROM_DEVICE);
	}
	IXGBE_CB(skb)->dma = 0;
}

/**
 * ixgbe_cleanup_headers - Correct corrupted or empty headers
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @rx_desc: pointer to the EOP Rx descriptor
 * @skb: pointer to current skb being fixed
 *
 * Check for corrupted packet headers caused by senders on the local L2
 * embedded NIC switch not setting up their Tx Descriptors right.  These
 * should be very rare.
 *
 * Also address the case where we are pulling data in on pages only
 * and as such no data is present in the skb header.
 *
 * In addition if skb is not at least 60 bytes we need to pad it so that
 * it is large enough to qualify as a valid Ethernet frame.
 *
 * Returns true if an error was encountered and skb was freed.
 **/
static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
				  union ixgbe_adv_rx_desc *rx_desc,
				  struct sk_buff *skb)
{
	struct net_device *netdev = rx_ring->netdev;

	/* verify that the packet does not have any known errors */
	if (unlikely(ixgbe_test_staterr(rx_desc,
					IXGBE_RXDADV_ERR_FRAME_ERR_MASK) &&
	    !(netdev->features & NETIF_F_RXALL))) {
		dev_kfree_skb_any(skb);
		return true;
	}

	/* place header in linear portion of buffer */
	if (skb_is_nonlinear(skb))
		ixgbe_pull_tail(rx_ring, skb);

#ifdef IXGBE_FCOE
	/* do not attempt to pad FCoE Frames as this will disrupt DDP */
	if (ixgbe_rx_is_fcoe(rx_ring, rx_desc))
		return false;

#endif
	/* if skb_pad returns an error the skb was freed */
	if (unlikely(skb->len < 60)) {
		int pad_len = 60 - skb->len;

		if (skb_pad(skb, pad_len))
			return true;
		__skb_put(skb, pad_len);
	}

	return false;
}

/**
 * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring
 * @rx_ring: rx descriptor ring to store buffers on
 * @old_buff: donor buffer to have page reused
 *
 * Synchronizes page for reuse by the adapter
 **/
static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
				struct ixgbe_rx_buffer *old_buff)
{
	struct ixgbe_rx_buffer *new_buff;
	u16 nta = rx_ring->next_to_alloc;

	new_buff = &rx_ring->rx_buffer_info[nta];

	/* update, and store next to alloc */
	nta++;
	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;

	/* transfer page from old buffer to new buffer */
	new_buff->page = old_buff->page;
	new_buff->dma = old_buff->dma;
	new_buff->page_offset = old_buff->page_offset;

	/* sync the buffer for use by the device */
	dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma,
					 new_buff->page_offset,
					 ixgbe_rx_bufsz(rx_ring),
					 DMA_FROM_DEVICE);
}

/**
 * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff
 * @rx_ring: rx descriptor ring to transact packets on
 * @rx_buffer: buffer containing page to add
 * @rx_desc: descriptor containing length of buffer written by hardware
 * @skb: sk_buff to place the data into
 *
 * This function will add the data contained in rx_buffer->page to the skb.
 * This is done either through a direct copy if the data in the buffer is
 * less than the skb header size, otherwise it will just attach the page as
 * a frag to the skb.
 *
 * The function will then update the page offset if necessary and return
 * true if the buffer can be reused by the adapter.
 **/
static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
			      struct ixgbe_rx_buffer *rx_buffer,
			      union ixgbe_adv_rx_desc *rx_desc,
			      struct sk_buff *skb)
{
	struct page *page = rx_buffer->page;
	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
#if (PAGE_SIZE < 8192)
	unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
#else
	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
				   ixgbe_rx_bufsz(rx_ring);
#endif

	if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
		unsigned char *va = page_address(page) + rx_buffer->page_offset;

		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));

		/* we can reuse buffer as-is, just make sure it is local */
		if (likely(page_to_nid(page) == numa_node_id()))
			return true;

		/* this page cannot be reused so discard it */
		put_page(page);
		return false;
	}

	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
			rx_buffer->page_offset, size, truesize);

	/* avoid re-using remote pages */
	if (unlikely(page_to_nid(page) != numa_node_id()))
		return false;

#if (PAGE_SIZE < 8192)
	/* if we are only owner of page we can reuse it */
	if (unlikely(page_count(page) != 1))
		return false;

	/* flip page offset to other buffer */
	rx_buffer->page_offset ^= truesize;

	/*
	 * since we are the only owner of the page and we need to
	 * increment it, just set the value to 2 in order to avoid
	 * an unecessary locked operation
	 */
	atomic_set(&page->_count, 2);
#else
	/* move offset up to the next cache line */
	rx_buffer->page_offset += truesize;

	if (rx_buffer->page_offset > last_offset)
		return false;

	/* bump ref count on page before it is given to the stack */
	get_page(page);
#endif

	return true;
}

static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
					     union ixgbe_adv_rx_desc *rx_desc)
{
	struct ixgbe_rx_buffer *rx_buffer;
	struct sk_buff *skb;
	struct page *page;

	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
	page = rx_buffer->page;
	prefetchw(page);

	skb = rx_buffer->skb;

	if (likely(!skb)) {
		void *page_addr = page_address(page) +
				  rx_buffer->page_offset;

		/* prefetch first cache line of first page */
		prefetch(page_addr);
#if L1_CACHE_BYTES < 128
		prefetch(page_addr + L1_CACHE_BYTES);
#endif

		/* allocate a skb to store the frags */
		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
						IXGBE_RX_HDR_SIZE);
		if (unlikely(!skb)) {
			rx_ring->rx_stats.alloc_rx_buff_failed++;
			return NULL;
		}

		/*
		 * we will be copying header into skb->data in
		 * pskb_may_pull so it is in our interest to prefetch
		 * it now to avoid a possible cache miss
		 */
		prefetchw(skb->data);

		/*
		 * Delay unmapping of the first packet. It carries the
		 * header information, HW may still access the header
		 * after the writeback.  Only unmap it when EOP is
		 * reached
		 */
		if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
			goto dma_sync;

		IXGBE_CB(skb)->dma = rx_buffer->dma;
	} else {
		if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
			ixgbe_dma_sync_frag(rx_ring, skb);

dma_sync:
		/* we are reusing so sync this buffer for CPU use */
		dma_sync_single_range_for_cpu(rx_ring->dev,
					      rx_buffer->dma,
					      rx_buffer->page_offset,
					      ixgbe_rx_bufsz(rx_ring),
					      DMA_FROM_DEVICE);
	}

	/* pull page into skb */
	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
		/* hand second half of page back to the ring */
		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
	} else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
		/* the page has been released from the ring */
		IXGBE_CB(skb)->page_released = true;
	} else {
		/* we are not reusing the buffer so unmap it */
		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
			       ixgbe_rx_pg_size(rx_ring),
			       DMA_FROM_DEVICE);
	}

	/* clear contents of buffer_info */
	rx_buffer->skb = NULL;
	rx_buffer->dma = 0;
	rx_buffer->page = NULL;

	return skb;
}

/**
 * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
 * @q_vector: structure containing interrupt and ring information
 * @rx_ring: rx descriptor ring to transact packets on
 * @budget: Total limit on number of packets to process
 *
 * This function provides a "bounce buffer" approach to Rx interrupt
 * processing.  The advantage to this is that on systems that have
 * expensive overhead for IOMMU access this provides a means of avoiding
 * it by maintaining the mapping of the page to the syste.
 *
 * Returns amount of work completed
 **/
static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
			       struct ixgbe_ring *rx_ring,
			       const int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
#ifdef IXGBE_FCOE
	struct ixgbe_adapter *adapter = q_vector->adapter;
	int ddp_bytes;
	unsigned int mss = 0;
#endif /* IXGBE_FCOE */
	u16 cleaned_count = ixgbe_desc_unused(rx_ring);

	do {
		union ixgbe_adv_rx_desc *rx_desc;
		struct sk_buff *skb;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
			ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
			cleaned_count = 0;
		}

		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);

		if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD))
			break;

		/*
		 * This memory barrier is needed to keep us from reading
		 * any other fields out of the rx_desc until we know the
		 * RXD_STAT_DD bit is set
		 */
		rmb();

		/* retrieve a buffer from the ring */
		skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc);

		/* exit if we failed to retrieve a buffer */
		if (!skb)
			break;

		cleaned_count++;

		/* place incomplete frames back on ring for completion */
		if (ixgbe_is_non_eop(rx_ring, rx_desc, skb))
			continue;

		/* verify the packet layout is correct */
		if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
			continue;

		/* probably a little skewed due to removing CRC */
		total_rx_bytes += skb->len;

		/* populate checksum, timestamp, VLAN, and protocol */
		ixgbe_process_skb_fields(rx_ring, rx_desc, skb);

#ifdef IXGBE_FCOE
		/* if ddp, not passing to ULD unless for FCP_RSP or error */
		if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) {
			ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb);
			/* include DDPed FCoE data */
			if (ddp_bytes > 0) {
				if (!mss) {
					mss = rx_ring->netdev->mtu -
						sizeof(struct fcoe_hdr) -
						sizeof(struct fc_frame_header) -
						sizeof(struct fcoe_crc_eof);
					if (mss > 512)
						mss &= ~511;
				}
				total_rx_bytes += ddp_bytes;
				total_rx_packets += DIV_ROUND_UP(ddp_bytes,
								 mss);
			}
			if (!ddp_bytes) {
				dev_kfree_skb_any(skb);
				continue;
			}
		}

#endif /* IXGBE_FCOE */
		skb_mark_napi_id(skb, &q_vector->napi);
		ixgbe_rx_skb(q_vector, skb);

		/* update budget accounting */
		total_rx_packets++;
	} while (likely(total_rx_packets < budget));

	u64_stats_update_begin(&rx_ring->syncp);
	rx_ring->stats.packets += total_rx_packets;
	rx_ring->stats.bytes += total_rx_bytes;
	u64_stats_update_end(&rx_ring->syncp);
	q_vector->rx.total_packets += total_rx_packets;
	q_vector->rx.total_bytes += total_rx_bytes;

	if (cleaned_count)
		ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);

	return total_rx_packets;
}

#ifdef CONFIG_NET_RX_BUSY_POLL
/* must be called with local_bh_disable()d */
static int ixgbe_low_latency_recv(struct napi_struct *napi)
{
	struct ixgbe_q_vector *q_vector =
			container_of(napi, struct ixgbe_q_vector, napi);
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_ring  *ring;
	int found = 0;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return LL_FLUSH_FAILED;

	if (!ixgbe_qv_lock_poll(q_vector))
		return LL_FLUSH_BUSY;

	ixgbe_for_each_ring(ring, q_vector->rx) {
		found = ixgbe_clean_rx_irq(q_vector, ring, 4);
#ifdef BP_EXTENDED_STATS
		if (found)
			ring->stats.cleaned += found;
		else
			ring->stats.misses++;
#endif
		if (found)
			break;
	}

	ixgbe_qv_unlock_poll(q_vector);

	return found;
}
#endif	/* CONFIG_NET_RX_BUSY_POLL */

/**
 * ixgbe_configure_msix - Configure MSI-X hardware
 * @adapter: board private structure
 *
 * ixgbe_configure_msix sets up the hardware to properly generate MSI-X
 * interrupts.
 **/
static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
{
	struct ixgbe_q_vector *q_vector;
	int v_idx;
	u32 mask;

	/* Populate MSIX to EITR Select */
	if (adapter->num_vfs > 32) {
		u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1;
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel);
	}

	/*
	 * Populate the IVAR table and set the ITR values to the
	 * corresponding register.
	 */
	for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) {
		struct ixgbe_ring *ring;
		q_vector = adapter->q_vector[v_idx];

		ixgbe_for_each_ring(ring, q_vector->rx)
			ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx);

		ixgbe_for_each_ring(ring, q_vector->tx)
			ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx);

		ixgbe_write_eitr(q_vector);
	}

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82598EB:
		ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX,
			       v_idx);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		ixgbe_set_ivar(adapter, -1, 1, v_idx);
		break;
	default:
		break;
	}
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950);

	/* set up to autoclear timer, and the vectors */
	mask = IXGBE_EIMS_ENABLE_MASK;
	mask &= ~(IXGBE_EIMS_OTHER |
		  IXGBE_EIMS_MAILBOX |
		  IXGBE_EIMS_LSC);

	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
}

enum latency_range {
	lowest_latency = 0,
	low_latency = 1,
	bulk_latency = 2,
	latency_invalid = 255
};

/**
 * ixgbe_update_itr - update the dynamic ITR value based on statistics
 * @q_vector: structure containing interrupt and ring information
 * @ring_container: structure containing ring performance data
 *
 *      Stores a new ITR value based on packets and byte
 *      counts during the last interrupt.  The advantage of per interrupt
 *      computation is faster updates and more accurate ITR for the current
 *      traffic pattern.  Constants in this function were computed
 *      based on theoretical maximum wire speed and thresholds were set based
 *      on testing data as well as attempting to minimize response time
 *      while increasing bulk throughput.
 *      this functionality is controlled by the InterruptThrottleRate module
 *      parameter (see ixgbe_param.c)
 **/
static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
			     struct ixgbe_ring_container *ring_container)
{
	int bytes = ring_container->total_bytes;
	int packets = ring_container->total_packets;
	u32 timepassed_us;
	u64 bytes_perint;
	u8 itr_setting = ring_container->itr;

	if (packets == 0)
		return;

	/* simple throttlerate management
	 *   0-10MB/s   lowest (100000 ints/s)
	 *  10-20MB/s   low    (20000 ints/s)
	 *  20-1249MB/s bulk   (8000 ints/s)
	 */
	/* what was last interrupt timeslice? */
	timepassed_us = q_vector->itr >> 2;
	if (timepassed_us == 0)
		return;

	bytes_perint = bytes / timepassed_us; /* bytes/usec */

	switch (itr_setting) {
	case lowest_latency:
		if (bytes_perint > 10)
			itr_setting = low_latency;
		break;
	case low_latency:
		if (bytes_perint > 20)
			itr_setting = bulk_latency;
		else if (bytes_perint <= 10)
			itr_setting = lowest_latency;
		break;
	case bulk_latency:
		if (bytes_perint <= 20)
			itr_setting = low_latency;
		break;
	}

	/* clear work counters since we have the values we need */
	ring_container->total_bytes = 0;
	ring_container->total_packets = 0;

	/* write updated itr to ring container */
	ring_container->itr = itr_setting;
}

/**
 * ixgbe_write_eitr - write EITR register in hardware specific way
 * @q_vector: structure containing interrupt and ring information
 *
 * This function is made to be called by ethtool and by the driver
 * when it needs to update EITR registers at runtime.  Hardware
 * specific quirks/differences are taken care of here.
 */
void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_hw *hw = &adapter->hw;
	int v_idx = q_vector->v_idx;
	u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82598EB:
		/* must write high and low 16 bits to reset counter */
		itr_reg |= (itr_reg << 16);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		/*
		 * set the WDIS bit to not clear the timer bits and cause an
		 * immediate assertion of the interrupt
		 */
		itr_reg |= IXGBE_EITR_CNT_WDIS;
		break;
	default:
		break;
	}
	IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
}

static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
{
	u32 new_itr = q_vector->itr;
	u8 current_itr;

	ixgbe_update_itr(q_vector, &q_vector->tx);
	ixgbe_update_itr(q_vector, &q_vector->rx);

	current_itr = max(q_vector->rx.itr, q_vector->tx.itr);

	switch (current_itr) {
	/* counts and packets in update_itr are dependent on these numbers */
	case lowest_latency:
		new_itr = IXGBE_100K_ITR;
		break;
	case low_latency:
		new_itr = IXGBE_20K_ITR;
		break;
	case bulk_latency:
		new_itr = IXGBE_8K_ITR;
		break;
	default:
		break;
	}

	if (new_itr != q_vector->itr) {
		/* do an exponential smoothing */
		new_itr = (10 * new_itr * q_vector->itr) /
			  ((9 * new_itr) + q_vector->itr);

		/* save the algorithm value here */
		q_vector->itr = new_itr;

		ixgbe_write_eitr(q_vector);
	}
}

/**
 * ixgbe_check_overtemp_subtask - check for over temperature
 * @adapter: pointer to adapter
 **/
static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 eicr = adapter->interrupt_event;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return;

	if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
	    !(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_EVENT))
		return;

	adapter->flags2 &= ~IXGBE_FLAG2_TEMP_SENSOR_EVENT;

	switch (hw->device_id) {
	case IXGBE_DEV_ID_82599_T3_LOM:
		/*
		 * Since the warning interrupt is for both ports
		 * we don't have to check if:
		 *  - This interrupt wasn't for our port.
		 *  - We may have missed the interrupt so always have to
		 *    check if we  got a LSC
		 */
		if (!(eicr & IXGBE_EICR_GPI_SDP0) &&
		    !(eicr & IXGBE_EICR_LSC))
			return;

		if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) {
			u32 speed;
			bool link_up = false;

			hw->mac.ops.check_link(hw, &speed, &link_up, false);

			if (link_up)
				return;
		}

		/* Check if this is not due to overtemp */
		if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP)
			return;

		break;
	default:
		if (!(eicr & IXGBE_EICR_GPI_SDP0))
			return;
		break;
	}
	e_crit(drv,
	       "Network adapter has been stopped because it has over heated. "
	       "Restart the computer. If the problem persists, "
	       "power off the system and replace the adapter\n");

	adapter->interrupt_event = 0;
}

static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr)
{
	struct ixgbe_hw *hw = &adapter->hw;

	if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) &&
	    (eicr & IXGBE_EICR_GPI_SDP1)) {
		e_crit(probe, "Fan has stopped, replace the adapter\n");
		/* write to clear the interrupt */
		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
	}
}

static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
	if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE))
		return;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82599EB:
		/*
		 * Need to check link state so complete overtemp check
		 * on service task
		 */
		if (((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)) &&
		    (!test_bit(__IXGBE_DOWN, &adapter->state))) {
			adapter->interrupt_event = eicr;
			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT;
			ixgbe_service_event_schedule(adapter);
			return;
		}
		return;
	case ixgbe_mac_X540:
		if (!(eicr & IXGBE_EICR_TS))
			return;
		break;
	default:
		return;
	}

	e_crit(drv,
	       "Network adapter has been stopped because it has over heated. "
	       "Restart the computer. If the problem persists, "
	       "power off the system and replace the adapter\n");
}

static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
	struct ixgbe_hw *hw = &adapter->hw;

	if (eicr & IXGBE_EICR_GPI_SDP2) {
		/* Clear the interrupt */
		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
			adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
			ixgbe_service_event_schedule(adapter);
		}
	}

	if (eicr & IXGBE_EICR_GPI_SDP1) {
		/* Clear the interrupt */
		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
			adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
			ixgbe_service_event_schedule(adapter);
		}
	}
}

static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	adapter->lsc_int++;
	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
	adapter->link_check_timeout = jiffies;
	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
		IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC);
		IXGBE_WRITE_FLUSH(hw);
		ixgbe_service_event_schedule(adapter);
	}
}

static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
					   u64 qmask)
{
	u32 mask;
	struct ixgbe_hw *hw = &adapter->hw;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
		IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		mask = (qmask & 0xFFFFFFFF);
		if (mask)
			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
		mask = (qmask >> 32);
		if (mask)
			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
		break;
	default:
		break;
	}
	/* skip the flush */
}

static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
					    u64 qmask)
{
	u32 mask;
	struct ixgbe_hw *hw = &adapter->hw;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
		IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		mask = (qmask & 0xFFFFFFFF);
		if (mask)
			IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask);
		mask = (qmask >> 32);
		if (mask)
			IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask);
		break;
	default:
		break;
	}
	/* skip the flush */
}

/**
 * ixgbe_irq_enable - Enable default interrupt generation settings
 * @adapter: board private structure
 **/
static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
				    bool flush)
{
	u32 mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);

	/* don't reenable LSC while waiting for link */
	if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)
		mask &= ~IXGBE_EIMS_LSC;

	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
		switch (adapter->hw.mac.type) {
		case ixgbe_mac_82599EB:
			mask |= IXGBE_EIMS_GPI_SDP0;
			break;
		case ixgbe_mac_X540:
			mask |= IXGBE_EIMS_TS;
			break;
		default:
			break;
		}
	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
		mask |= IXGBE_EIMS_GPI_SDP1;
	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82599EB:
		mask |= IXGBE_EIMS_GPI_SDP1;
		mask |= IXGBE_EIMS_GPI_SDP2;
	case ixgbe_mac_X540:
		mask |= IXGBE_EIMS_ECC;
		mask |= IXGBE_EIMS_MAILBOX;
		break;
	default:
		break;
	}

	if (adapter->hw.mac.type == ixgbe_mac_X540)
		mask |= IXGBE_EIMS_TIMESYNC;

	if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
	    !(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT))
		mask |= IXGBE_EIMS_FLOW_DIR;

	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
	if (queues)
		ixgbe_irq_enable_queues(adapter, ~0);
	if (flush)
		IXGBE_WRITE_FLUSH(&adapter->hw);
}

static irqreturn_t ixgbe_msix_other(int irq, void *data)
{
	struct ixgbe_adapter *adapter = data;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 eicr;

	/*
	 * Workaround for Silicon errata.  Use clear-by-write instead
	 * of clear-by-read.  Reading with EICS will return the
	 * interrupt causes without clearing, which later be done
	 * with the write to EICR.
	 */
	eicr = IXGBE_READ_REG(hw, IXGBE_EICS);

	/* The lower 16bits of the EICR register are for the queue interrupts
	 * which should be masked here in order to not accidently clear them if
	 * the bits are high when ixgbe_msix_other is called. There is a race
	 * condition otherwise which results in possible performance loss
	 * especially if the ixgbe_msix_other interrupt is triggering
	 * consistently (as it would when PPS is turned on for the X540 device)
	 */
	eicr &= 0xFFFF0000;

	IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr);

	if (eicr & IXGBE_EICR_LSC)
		ixgbe_check_lsc(adapter);

	if (eicr & IXGBE_EICR_MAILBOX)
		ixgbe_msg_task(adapter);

	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		if (eicr & IXGBE_EICR_ECC)
			e_info(link, "Received unrecoverable ECC Err, please "
			       "reboot\n");
		/* Handle Flow Director Full threshold interrupt */
		if (eicr & IXGBE_EICR_FLOW_DIR) {
			int reinit_count = 0;
			int i;
			for (i = 0; i < adapter->num_tx_queues; i++) {
				struct ixgbe_ring *ring = adapter->tx_ring[i];
				if (test_and_clear_bit(__IXGBE_TX_FDIR_INIT_DONE,
						       &ring->state))
					reinit_count++;
			}
			if (reinit_count) {
				/* no more flow director interrupts until after init */
				IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_FLOW_DIR);
				adapter->flags2 |= IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
				ixgbe_service_event_schedule(adapter);
			}
		}
		ixgbe_check_sfp_event(adapter, eicr);
		ixgbe_check_overtemp_event(adapter, eicr);
		break;
	default:
		break;
	}

	ixgbe_check_fan_failure(adapter, eicr);

	if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
		ixgbe_ptp_check_pps_event(adapter, eicr);

	/* re-enable the original interrupt state, no lsc, no queues */
	if (!test_bit(__IXGBE_DOWN, &adapter->state))
		ixgbe_irq_enable(adapter, false, false);

	return IRQ_HANDLED;
}

static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data)
{
	struct ixgbe_q_vector *q_vector = data;

	/* EIAM disabled interrupts (on this vector) for us */

	if (q_vector->rx.ring || q_vector->tx.ring)
		napi_schedule(&q_vector->napi);

	return IRQ_HANDLED;
}

/**
 * ixgbe_poll - NAPI Rx polling callback
 * @napi: structure for representing this polling device
 * @budget: how many packets driver is allowed to clean
 *
 * This function is used for legacy and MSI, NAPI mode
 **/
int ixgbe_poll(struct napi_struct *napi, int budget)
{
	struct ixgbe_q_vector *q_vector =
				container_of(napi, struct ixgbe_q_vector, napi);
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_ring *ring;
	int per_ring_budget;
	bool clean_complete = true;

#ifdef CONFIG_IXGBE_DCA
	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
		ixgbe_update_dca(q_vector);
#endif

	ixgbe_for_each_ring(ring, q_vector->tx)
		clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring);

	if (!ixgbe_qv_lock_napi(q_vector))
		return budget;

	/* attempt to distribute budget to each queue fairly, but don't allow
	 * the budget to go below 1 because we'll exit polling */
	if (q_vector->rx.count > 1)
		per_ring_budget = max(budget/q_vector->rx.count, 1);
	else
		per_ring_budget = budget;

	ixgbe_for_each_ring(ring, q_vector->rx)
		clean_complete &= (ixgbe_clean_rx_irq(q_vector, ring,
				   per_ring_budget) < per_ring_budget);

	ixgbe_qv_unlock_napi(q_vector);
	/* If all work not completed, return budget and keep polling */
	if (!clean_complete)
		return budget;

	/* all work done, exit the polling mode */
	napi_complete(napi);
	if (adapter->rx_itr_setting & 1)
		ixgbe_set_itr(q_vector);
	if (!test_bit(__IXGBE_DOWN, &adapter->state))
		ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));

	return 0;
}

/**
 * ixgbe_request_msix_irqs - Initialize MSI-X interrupts
 * @adapter: board private structure
 *
 * ixgbe_request_msix_irqs allocates MSI-X vectors and requests
 * interrupts from the kernel.
 **/
static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int vector, err;
	int ri = 0, ti = 0;

	for (vector = 0; vector < adapter->num_q_vectors; vector++) {
		struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
		struct msix_entry *entry = &adapter->msix_entries[vector];

		if (q_vector->tx.ring && q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "TxRx", ri++);
			ti++;
		} else if (q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "rx", ri++);
		} else if (q_vector->tx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "tx", ti++);
		} else {
			/* skip this unused q_vector */
			continue;
		}
		err = request_irq(entry->vector, &ixgbe_msix_clean_rings, 0,
				  q_vector->name, q_vector);
		if (err) {
			e_err(probe, "request_irq failed for MSIX interrupt "
			      "Error: %d\n", err);
			goto free_queue_irqs;
		}
		/* If Flow Director is enabled, set interrupt affinity */
		if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
			/* assign the mask for this irq */
			irq_set_affinity_hint(entry->vector,
					      &q_vector->affinity_mask);
		}
	}

	err = request_irq(adapter->msix_entries[vector].vector,
			  ixgbe_msix_other, 0, netdev->name, adapter);
	if (err) {
		e_err(probe, "request_irq for msix_other failed: %d\n", err);
		goto free_queue_irqs;
	}

	return 0;

free_queue_irqs:
	while (vector) {
		vector--;
		irq_set_affinity_hint(adapter->msix_entries[vector].vector,
				      NULL);
		free_irq(adapter->msix_entries[vector].vector,
			 adapter->q_vector[vector]);
	}
	adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
	pci_disable_msix(adapter->pdev);
	kfree(adapter->msix_entries);
	adapter->msix_entries = NULL;
	return err;
}

/**
 * ixgbe_intr - legacy mode Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t ixgbe_intr(int irq, void *data)
{
	struct ixgbe_adapter *adapter = data;
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
	u32 eicr;

	/*
	 * Workaround for silicon errata #26 on 82598.  Mask the interrupt
	 * before the read of EICR.
	 */
	IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK);

	/* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read
	 * therefore no explicit interrupt disable is necessary */
	eicr = IXGBE_READ_REG(hw, IXGBE_EICR);
	if (!eicr) {
		/*
		 * shared interrupt alert!
		 * make sure interrupts are enabled because the read will
		 * have disabled interrupts due to EIAM
		 * finish the workaround of silicon errata on 82598.  Unmask
		 * the interrupt that we masked before the EICR read.
		 */
		if (!test_bit(__IXGBE_DOWN, &adapter->state))
			ixgbe_irq_enable(adapter, true, true);
		return IRQ_NONE;	/* Not our interrupt */
	}

	if (eicr & IXGBE_EICR_LSC)
		ixgbe_check_lsc(adapter);

	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
		ixgbe_check_sfp_event(adapter, eicr);
		/* Fall through */
	case ixgbe_mac_X540:
		if (eicr & IXGBE_EICR_ECC)
			e_info(link, "Received unrecoverable ECC err, please "
				     "reboot\n");
		ixgbe_check_overtemp_event(adapter, eicr);
		break;
	default:
		break;
	}

	ixgbe_check_fan_failure(adapter, eicr);
	if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
		ixgbe_ptp_check_pps_event(adapter, eicr);

	/* would disable interrupts here but EIAM disabled it */
	napi_schedule(&q_vector->napi);

	/*
	 * re-enable link(maybe) and non-queue interrupts, no flush.
	 * ixgbe_poll will re-enable the queue interrupts
	 */
	if (!test_bit(__IXGBE_DOWN, &adapter->state))
		ixgbe_irq_enable(adapter, false, false);

	return IRQ_HANDLED;
}

/**
 * ixgbe_request_irq - initialize interrupts
 * @adapter: board private structure
 *
 * Attempts to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
static int ixgbe_request_irq(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int err;

	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
		err = ixgbe_request_msix_irqs(adapter);
	else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED)
		err = request_irq(adapter->pdev->irq, ixgbe_intr, 0,
				  netdev->name, adapter);
	else
		err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED,
				  netdev->name, adapter);

	if (err)
		e_err(probe, "request_irq failed, Error %d\n", err);

	return err;
}

static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
{
	int vector;

	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
		free_irq(adapter->pdev->irq, adapter);
		return;
	}

	for (vector = 0; vector < adapter->num_q_vectors; vector++) {
		struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
		struct msix_entry *entry = &adapter->msix_entries[vector];

		/* free only the irqs that were actually requested */
		if (!q_vector->rx.ring && !q_vector->tx.ring)
			continue;

		/* clear the affinity_mask in the IRQ descriptor */
		irq_set_affinity_hint(entry->vector, NULL);

		free_irq(entry->vector, q_vector);
	}

	free_irq(adapter->msix_entries[vector++].vector, adapter);
}

/**
 * ixgbe_irq_disable - Mask off interrupt generation on the NIC
 * @adapter: board private structure
 **/
static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
{
	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82598EB:
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
		break;
	default:
		break;
	}
	IXGBE_WRITE_FLUSH(&adapter->hw);
	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
		int vector;

		for (vector = 0; vector < adapter->num_q_vectors; vector++)
			synchronize_irq(adapter->msix_entries[vector].vector);

		synchronize_irq(adapter->msix_entries[vector++].vector);
	} else {
		synchronize_irq(adapter->pdev->irq);
	}
}

/**
 * ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts
 *
 **/
static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter)
{
	struct ixgbe_q_vector *q_vector = adapter->q_vector[0];

	ixgbe_write_eitr(q_vector);

	ixgbe_set_ivar(adapter, 0, 0, 0);
	ixgbe_set_ivar(adapter, 1, 0, 0);

	e_info(hw, "Legacy interrupt IVAR setup done\n");
}

/**
 * ixgbe_configure_tx_ring - Configure 8259x Tx ring after Reset
 * @adapter: board private structure
 * @ring: structure containing ring specific data
 *
 * Configure the Tx descriptor ring after a reset.
 **/
void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
			     struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u64 tdba = ring->dma;
	int wait_loop = 10;
	u32 txdctl = IXGBE_TXDCTL_ENABLE;
	u8 reg_idx = ring->reg_idx;

	/* disable queue to avoid issues while updating state */
	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
	IXGBE_WRITE_FLUSH(hw);

	IXGBE_WRITE_REG(hw, IXGBE_TDBAL(reg_idx),
			(tdba & DMA_BIT_MASK(32)));
	IXGBE_WRITE_REG(hw, IXGBE_TDBAH(reg_idx), (tdba >> 32));
	IXGBE_WRITE_REG(hw, IXGBE_TDLEN(reg_idx),
			ring->count * sizeof(union ixgbe_adv_tx_desc));
	IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0);
	IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0);
	ring->tail = adapter->io_addr + IXGBE_TDT(reg_idx);

	/*
	 * set WTHRESH to encourage burst writeback, it should not be set
	 * higher than 1 when:
	 * - ITR is 0 as it could cause false TX hangs
	 * - ITR is set to > 100k int/sec and BQL is enabled
	 *
	 * In order to avoid issues WTHRESH + PTHRESH should always be equal
	 * to or less than the number of on chip descriptors, which is
	 * currently 40.
	 */
#if IS_ENABLED(CONFIG_BQL)
	if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR))
#else
	if (!ring->q_vector || (ring->q_vector->itr < 8))
#endif
		txdctl |= (1 << 16);	/* WTHRESH = 1 */
	else
		txdctl |= (8 << 16);	/* WTHRESH = 8 */

	/*
	 * Setting PTHRESH to 32 both improves performance
	 * and avoids a TX hang with DFP enabled
	 */
	txdctl |= (1 << 8) |	/* HTHRESH = 1 */
		   32;		/* PTHRESH = 32 */

	/* reinitialize flowdirector state */
	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
		ring->atr_sample_rate = adapter->atr_sample_rate;
		ring->atr_count = 0;
		set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state);
	} else {
		ring->atr_sample_rate = 0;
	}

	/* initialize XPS */
	if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) {
		struct ixgbe_q_vector *q_vector = ring->q_vector;

		if (q_vector)
			netif_set_xps_queue(ring->netdev,
					    &q_vector->affinity_mask,
					    ring->queue_index);
	}

	clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);

	/* enable queue */
	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);

	/* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */
	if (hw->mac.type == ixgbe_mac_82598EB &&
	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
		return;

	/* poll to verify queue is enabled */
	do {
		usleep_range(1000, 2000);
		txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
	} while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE));
	if (!wait_loop)
		e_err(drv, "Could not enable Tx Queue %d\n", reg_idx);
}

static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 rttdcs, mtqc;
	u8 tcs = netdev_get_num_tc(adapter->netdev);

	if (hw->mac.type == ixgbe_mac_82598EB)
		return;

	/* disable the arbiter while setting MTQC */
	rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS);
	rttdcs |= IXGBE_RTTDCS_ARBDIS;
	IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);

	/* set transmit pool layout */
	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
		mtqc = IXGBE_MTQC_VT_ENA;
		if (tcs > 4)
			mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
		else if (tcs > 1)
			mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
		else if (adapter->ring_feature[RING_F_RSS].indices == 4)
			mtqc |= IXGBE_MTQC_32VF;
		else
			mtqc |= IXGBE_MTQC_64VF;
	} else {
		if (tcs > 4)
			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
		else if (tcs > 1)
			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
		else
			mtqc = IXGBE_MTQC_64Q_1PB;
	}

	IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc);

	/* Enable Security TX Buffer IFG for multiple pb */
	if (tcs) {
		u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
		sectx |= IXGBE_SECTX_DCB;
		IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx);
	}

	/* re-enable the arbiter */
	rttdcs &= ~IXGBE_RTTDCS_ARBDIS;
	IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
}

/**
 * ixgbe_configure_tx - Configure 8259x Transmit Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Tx unit of the MAC after a reset.
 **/
static void ixgbe_configure_tx(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 dmatxctl;
	u32 i;

	ixgbe_setup_mtqc(adapter);

	if (hw->mac.type != ixgbe_mac_82598EB) {
		/* DMATXCTL.EN must be before Tx queues are enabled */
		dmatxctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
		dmatxctl |= IXGBE_DMATXCTL_TE;
		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, dmatxctl);
	}

	/* Setup the HW Tx Head and Tail descriptor pointers */
	for (i = 0; i < adapter->num_tx_queues; i++)
		ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]);
}

static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter,
				 struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u8 reg_idx = ring->reg_idx;
	u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx));

	srrctl |= IXGBE_SRRCTL_DROP_EN;

	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
}

static void ixgbe_disable_rx_drop(struct ixgbe_adapter *adapter,
				  struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u8 reg_idx = ring->reg_idx;
	u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx));

	srrctl &= ~IXGBE_SRRCTL_DROP_EN;

	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
}

#ifdef CONFIG_IXGBE_DCB
void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
#else
static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
#endif
{
	int i;
	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;

	if (adapter->ixgbe_ieee_pfc)
		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);

	/*
	 * We should set the drop enable bit if:
	 *  SR-IOV is enabled
	 *   or
	 *  Number of Rx queues > 1 and flow control is disabled
	 *
	 *  This allows us to avoid head of line blocking for security
	 *  and performance reasons.
	 */
	if (adapter->num_vfs || (adapter->num_rx_queues > 1 &&
	    !(adapter->hw.fc.current_mode & ixgbe_fc_tx_pause) && !pfc_en)) {
		for (i = 0; i < adapter->num_rx_queues; i++)
			ixgbe_enable_rx_drop(adapter, adapter->rx_ring[i]);
	} else {
		for (i = 0; i < adapter->num_rx_queues; i++)
			ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]);
	}
}

#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2

static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
				   struct ixgbe_ring *rx_ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 srrctl;
	u8 reg_idx = rx_ring->reg_idx;

	if (hw->mac.type == ixgbe_mac_82598EB) {
		u16 mask = adapter->ring_feature[RING_F_RSS].mask;

		/*
		 * if VMDq is not active we must program one srrctl register
		 * per RSS queue since we have enabled RDRXCTL.MVMEN
		 */
		reg_idx &= mask;
	}

	/* configure header buffer length, needed for RSC */
	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;

	/* configure the packet buffer length */
	srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;

	/* configure descriptor type */
	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;

	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
}

static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	static const u32 seed[10] = { 0xE291D73D, 0x1805EC6C, 0x2A94B30D,
			  0xA54F2BEC, 0xEA49AF7C, 0xE214AD3D, 0xB855AABE,
			  0x6A3E67EA, 0x14364D17, 0x3BED200D};
	u32 mrqc = 0, reta = 0;
	u32 rxcsum;
	int i, j;
	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;

	/*
	 * Program table for at least 2 queues w/ SR-IOV so that VFs can
	 * make full use of any rings they may have.  We will use the
	 * PSRTYPE register to control how many rings we use within the PF.
	 */
	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (rss_i < 2))
		rss_i = 2;

	/* Fill out hash function seeds */
	for (i = 0; i < 10; i++)
		IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), seed[i]);

	/* Fill out redirection table */
	for (i = 0, j = 0; i < 128; i++, j++) {
		if (j == rss_i)
			j = 0;
		/* reta = 4-byte sliding window of
		 * 0x00..(indices-1)(indices-1)00..etc. */
		reta = (reta << 8) | (j * 0x11);
		if ((i & 3) == 3)
			IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta);
	}

	/* Disable indicating checksum in descriptor, enables RSS hash */
	rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM);
	rxcsum |= IXGBE_RXCSUM_PCSD;
	IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum);

	if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
		if (adapter->ring_feature[RING_F_RSS].mask)
			mrqc = IXGBE_MRQC_RSSEN;
	} else {
		u8 tcs = netdev_get_num_tc(adapter->netdev);

		if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
			if (tcs > 4)
				mrqc = IXGBE_MRQC_VMDQRT8TCEN;	/* 8 TCs */
			else if (tcs > 1)
				mrqc = IXGBE_MRQC_VMDQRT4TCEN;	/* 4 TCs */
			else if (adapter->ring_feature[RING_F_RSS].indices == 4)
				mrqc = IXGBE_MRQC_VMDQRSS32EN;
			else
				mrqc = IXGBE_MRQC_VMDQRSS64EN;
		} else {
			if (tcs > 4)
				mrqc = IXGBE_MRQC_RTRSS8TCEN;
			else if (tcs > 1)
				mrqc = IXGBE_MRQC_RTRSS4TCEN;
			else
				mrqc = IXGBE_MRQC_RSSEN;
		}
	}

	/* Perform hash on these packet types */
	mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 |
		IXGBE_MRQC_RSS_FIELD_IPV4_TCP |
		IXGBE_MRQC_RSS_FIELD_IPV6 |
		IXGBE_MRQC_RSS_FIELD_IPV6_TCP;

	if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP)
		mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP;
	if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP)
		mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP;

	IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc);
}

/**
 * ixgbe_configure_rscctl - enable RSC for the indicated ring
 * @adapter:    address of board private structure
 * @index:      index of ring to set
 **/
static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
				   struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 rscctrl;
	u8 reg_idx = ring->reg_idx;

	if (!ring_is_rsc_enabled(ring))
		return;

	rscctrl = IXGBE_READ_REG(hw, IXGBE_RSCCTL(reg_idx));
	rscctrl |= IXGBE_RSCCTL_RSCEN;
	/*
	 * we must limit the number of descriptors so that the
	 * total size of max desc * buf_len is not greater
	 * than 65536
	 */
	rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
	IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl);
}

#define IXGBE_MAX_RX_DESC_POLL 10
static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter,
				       struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int wait_loop = IXGBE_MAX_RX_DESC_POLL;
	u32 rxdctl;
	u8 reg_idx = ring->reg_idx;

	if (ixgbe_removed(hw->hw_addr))
		return;
	/* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */
	if (hw->mac.type == ixgbe_mac_82598EB &&
	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
		return;

	do {
		usleep_range(1000, 2000);
		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
	} while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE));

	if (!wait_loop) {
		e_err(drv, "RXDCTL.ENABLE on Rx queue %d not set within "
		      "the polling period\n", reg_idx);
	}
}

void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter,
			    struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int wait_loop = IXGBE_MAX_RX_DESC_POLL;
	u32 rxdctl;
	u8 reg_idx = ring->reg_idx;

	if (ixgbe_removed(hw->hw_addr))
		return;
	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
	rxdctl &= ~IXGBE_RXDCTL_ENABLE;

	/* write value back with RXDCTL.ENABLE bit cleared */
	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);

	if (hw->mac.type == ixgbe_mac_82598EB &&
	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
		return;

	/* the hardware may take up to 100us to really disable the rx queue */
	do {
		udelay(10);
		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
	} while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE));

	if (!wait_loop) {
		e_err(drv, "RXDCTL.ENABLE on Rx queue %d not cleared within "
		      "the polling period\n", reg_idx);
	}
}

void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
			     struct ixgbe_ring *ring)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u64 rdba = ring->dma;
	u32 rxdctl;
	u8 reg_idx = ring->reg_idx;

	/* disable queue to avoid issues while updating state */
	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
	ixgbe_disable_rx_queue(adapter, ring);

	IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32)));
	IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32));
	IXGBE_WRITE_REG(hw, IXGBE_RDLEN(reg_idx),
			ring->count * sizeof(union ixgbe_adv_rx_desc));
	IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0);
	IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0);
	ring->tail = adapter->io_addr + IXGBE_RDT(reg_idx);

	ixgbe_configure_srrctl(adapter, ring);
	ixgbe_configure_rscctl(adapter, ring);

	if (hw->mac.type == ixgbe_mac_82598EB) {
		/*
		 * enable cache line friendly hardware writes:
		 * PTHRESH=32 descriptors (half the internal cache),
		 * this also removes ugly rx_no_buffer_count increment
		 * HTHRESH=4 descriptors (to minimize latency on fetch)
		 * WTHRESH=8 burst writeback up to two cache lines
		 */
		rxdctl &= ~0x3FFFFF;
		rxdctl |=  0x080420;
	}

	/* enable receive descriptor ring */
	rxdctl |= IXGBE_RXDCTL_ENABLE;
	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);

	ixgbe_rx_desc_queue_enable(adapter, ring);
	ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
}

static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int rss_i = adapter->ring_feature[RING_F_RSS].indices;
	u16 pool;

	/* PSRTYPE must be initialized in non 82598 adapters */
	u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
		      IXGBE_PSRTYPE_UDPHDR |
		      IXGBE_PSRTYPE_IPV4HDR |
		      IXGBE_PSRTYPE_L2HDR |
		      IXGBE_PSRTYPE_IPV6HDR;

	if (hw->mac.type == ixgbe_mac_82598EB)
		return;

	if (rss_i > 3)
		psrtype |= 2 << 29;
	else if (rss_i > 1)
		psrtype |= 1 << 29;

	for_each_set_bit(pool, &adapter->fwd_bitmask, 32)
		IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype);
}

static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 reg_offset, vf_shift;
	u32 gcr_ext, vmdctl;
	int i;

	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
		return;

	vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
	vmdctl |= IXGBE_VMD_CTL_VMDQ_EN;
	vmdctl &= ~IXGBE_VT_CTL_POOL_MASK;
	vmdctl |= VMDQ_P(0) << IXGBE_VT_CTL_POOL_SHIFT;
	vmdctl |= IXGBE_VT_CTL_REPLEN;
	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);

	vf_shift = VMDQ_P(0) % 32;
	reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0;

	/* Enable only the PF's pool for Tx/Rx */
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (~0) << vf_shift);
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (~0) << vf_shift);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1);
	if (adapter->flags2 & IXGBE_FLAG2_BRIDGE_MODE_VEB)
		IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);

	/* Map PF MAC address in RAR Entry 0 to first pool following VFs */
	hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0));

	/*
	 * Set up VF register offsets for selected VT Mode,
	 * i.e. 32 or 64 VFs for SR-IOV
	 */
	switch (adapter->ring_feature[RING_F_VMDQ].mask) {
	case IXGBE_82599_VMDQ_8Q_MASK:
		gcr_ext = IXGBE_GCR_EXT_VT_MODE_16;
		break;
	case IXGBE_82599_VMDQ_4Q_MASK:
		gcr_ext = IXGBE_GCR_EXT_VT_MODE_32;
		break;
	default:
		gcr_ext = IXGBE_GCR_EXT_VT_MODE_64;
		break;
	}

	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext);


	/* Enable MAC Anti-Spoofing */
	hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0),
					  adapter->num_vfs);
	/* For VFs that have spoof checking turned off */
	for (i = 0; i < adapter->num_vfs; i++) {
		if (!adapter->vfinfo[i].spoofchk_enabled)
			ixgbe_ndo_set_vf_spoofchk(adapter->netdev, i, false);
	}
}

static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	struct ixgbe_ring *rx_ring;
	int i;
	u32 mhadd, hlreg0;

#ifdef IXGBE_FCOE
	/* adjust max frame to be able to do baby jumbo for FCoE */
	if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
	    (max_frame < IXGBE_FCOE_JUMBO_FRAME_SIZE))
		max_frame = IXGBE_FCOE_JUMBO_FRAME_SIZE;

#endif /* IXGBE_FCOE */

	/* adjust max frame to be at least the size of a standard frame */
	if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
		max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN);

	mhadd = IXGBE_READ_REG(hw, IXGBE_MHADD);
	if (max_frame != (mhadd >> IXGBE_MHADD_MFS_SHIFT)) {
		mhadd &= ~IXGBE_MHADD_MFS_MASK;
		mhadd |= max_frame << IXGBE_MHADD_MFS_SHIFT;

		IXGBE_WRITE_REG(hw, IXGBE_MHADD, mhadd);
	}

	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
	/* set jumbo enable since MHADD.MFS is keeping size locked at max_frame */
	hlreg0 |= IXGBE_HLREG0_JUMBOEN;
	IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);

	/*
	 * Setup the HW Rx Head and Tail Descriptor Pointers and
	 * the Base and Length of the Rx Descriptor Ring
	 */
	for (i = 0; i < adapter->num_rx_queues; i++) {
		rx_ring = adapter->rx_ring[i];
		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
			set_ring_rsc_enabled(rx_ring);
		else
			clear_ring_rsc_enabled(rx_ring);
	}
}

static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		/*
		 * For VMDq support of different descriptor types or
		 * buffer sizes through the use of multiple SRRCTL
		 * registers, RDRXCTL.MVMEN must be set to 1
		 *
		 * also, the manual doesn't mention it clearly but DCA hints
		 * will only use queue 0's tags unless this bit is set.  Side
		 * effects of setting this bit are only that SRRCTL must be
		 * fully programmed [0..15]
		 */
		rdrxctl |= IXGBE_RDRXCTL_MVMEN;
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		/* Disable RSC for ACK packets */
		IXGBE_WRITE_REG(hw, IXGBE_RSCDBU,
		   (IXGBE_RSCDBU_RSCACKDIS | IXGBE_READ_REG(hw, IXGBE_RSCDBU)));
		rdrxctl &= ~IXGBE_RDRXCTL_RSCFRSTSIZE;
		/* hardware requires some bits to be set by default */
		rdrxctl |= (IXGBE_RDRXCTL_RSCACKC | IXGBE_RDRXCTL_FCOE_WRFIX);
		rdrxctl |= IXGBE_RDRXCTL_CRCSTRIP;
		break;
	default:
		/* We should do nothing since we don't know this hardware */
		return;
	}

	IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
}

/**
 * ixgbe_configure_rx - Configure 8259x Receive Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Rx unit of the MAC after a reset.
 **/
static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int i;
	u32 rxctrl, rfctl;

	/* disable receives while setting up the descriptors */
	rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
	IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN);

	ixgbe_setup_psrtype(adapter);
	ixgbe_setup_rdrxctl(adapter);

	/* RSC Setup */
	rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL);
	rfctl &= ~IXGBE_RFCTL_RSC_DIS;
	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))
		rfctl |= IXGBE_RFCTL_RSC_DIS;
	IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl);

	/* Program registers for the distribution of queues */
	ixgbe_setup_mrqc(adapter);

	/* set_rx_buffer_len must be called before ring initialization */
	ixgbe_set_rx_buffer_len(adapter);

	/*
	 * Setup the HW Rx Head and Tail Descriptor Pointers and
	 * the Base and Length of the Rx Descriptor Ring
	 */
	for (i = 0; i < adapter->num_rx_queues; i++)
		ixgbe_configure_rx_ring(adapter, adapter->rx_ring[i]);

	/* disable drop enable for 82598 parts */
	if (hw->mac.type == ixgbe_mac_82598EB)
		rxctrl |= IXGBE_RXCTRL_DMBYPS;

	/* enable all receives */
	rxctrl |= IXGBE_RXCTRL_RXEN;
	hw->mac.ops.enable_rx_dma(hw, rxctrl);
}

static int ixgbe_vlan_rx_add_vid(struct net_device *netdev,
				 __be16 proto, u16 vid)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

	/* add VID to filter table */
	hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true);
	set_bit(vid, adapter->active_vlans);

	return 0;
}

static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
				  __be16 proto, u16 vid)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

	/* remove VID from filter table */
	hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), false);
	clear_bit(vid, adapter->active_vlans);

	return 0;
}

/**
 * ixgbe_vlan_filter_disable - helper to disable hw vlan filtering
 * @adapter: driver data
 */
static void ixgbe_vlan_filter_disable(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vlnctrl;

	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
	vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN);
	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
}

/**
 * ixgbe_vlan_filter_enable - helper to enable hw vlan filtering
 * @adapter: driver data
 */
static void ixgbe_vlan_filter_enable(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vlnctrl;

	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
	vlnctrl |= IXGBE_VLNCTRL_VFE;
	vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
}

/**
 * ixgbe_vlan_strip_disable - helper to disable hw vlan stripping
 * @adapter: driver data
 */
static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vlnctrl;
	int i, j;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
		vlnctrl &= ~IXGBE_VLNCTRL_VME;
		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		for (i = 0; i < adapter->num_rx_queues; i++) {
			struct ixgbe_ring *ring = adapter->rx_ring[i];

			if (ring->l2_accel_priv)
				continue;
			j = ring->reg_idx;
			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
			vlnctrl &= ~IXGBE_RXDCTL_VME;
			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
		}
		break;
	default:
		break;
	}
}

/**
 * ixgbe_vlan_strip_enable - helper to enable hw vlan stripping
 * @adapter: driver data
 */
static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vlnctrl;
	int i, j;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
		vlnctrl |= IXGBE_VLNCTRL_VME;
		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		for (i = 0; i < adapter->num_rx_queues; i++) {
			struct ixgbe_ring *ring = adapter->rx_ring[i];

			if (ring->l2_accel_priv)
				continue;
			j = ring->reg_idx;
			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
			vlnctrl |= IXGBE_RXDCTL_VME;
			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
		}
		break;
	default:
		break;
	}
}

static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
{
	u16 vid;

	ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0);

	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
		ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid);
}

/**
 * ixgbe_write_uc_addr_list - write unicast addresses to RAR table
 * @netdev: network interface device structure
 *
 * Writes unicast address list to the RAR table.
 * Returns: -ENOMEM on failure/insufficient address space
 *                0 on no addresses written
 *                X on writing X addresses to the RAR table
 **/
static int ixgbe_write_uc_addr_list(struct net_device *netdev)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	unsigned int rar_entries = hw->mac.num_rar_entries - 1;
	int count = 0;

	/* In SR-IOV/VMDQ modes significantly less RAR entries are available */
	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
		rar_entries = IXGBE_MAX_PF_MACVLANS - 1;

	/* return ENOMEM indicating insufficient memory for addresses */
	if (netdev_uc_count(netdev) > rar_entries)
		return -ENOMEM;

	if (!netdev_uc_empty(netdev)) {
		struct netdev_hw_addr *ha;
		/* return error if we do not support writing to RAR table */
		if (!hw->mac.ops.set_rar)
			return -ENOMEM;

		netdev_for_each_uc_addr(ha, netdev) {
			if (!rar_entries)
				break;
			hw->mac.ops.set_rar(hw, rar_entries--, ha->addr,
					    VMDQ_P(0), IXGBE_RAH_AV);
			count++;
		}
	}
	/* write the addresses in reverse order to avoid write combining */
	for (; rar_entries > 0 ; rar_entries--)
		hw->mac.ops.clear_rar(hw, rar_entries);

	return count;
}

/**
 * ixgbe_set_rx_mode - Unicast, Multicast and Promiscuous mode set
 * @netdev: network interface device structure
 *
 * The set_rx_method entry point is called whenever the unicast/multicast
 * address list or the network interface flags are updated.  This routine is
 * responsible for configuring the hardware for proper unicast, multicast and
 * promiscuous mode.
 **/
void ixgbe_set_rx_mode(struct net_device *netdev)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
	int count;

	/* Check for Promiscuous and All Multicast modes */

	fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);

	/* set all bits that we expect to always be set */
	fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */
	fctrl |= IXGBE_FCTRL_BAM;
	fctrl |= IXGBE_FCTRL_DPF; /* discard pause frames when FC enabled */
	fctrl |= IXGBE_FCTRL_PMCF;

	/* clear the bits we are changing the status of */
	fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);

	if (netdev->flags & IFF_PROMISC) {
		hw->addr_ctrl.user_set_promisc = true;
		fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
		vmolr |= (IXGBE_VMOLR_ROPE | IXGBE_VMOLR_MPE);
		/* Only disable hardware filter vlans in promiscuous mode
		 * if SR-IOV and VMDQ are disabled - otherwise ensure
		 * that hardware VLAN filters remain enabled.
		 */
		if (!(adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED |
					IXGBE_FLAG_SRIOV_ENABLED)))
			ixgbe_vlan_filter_disable(adapter);
		else
			ixgbe_vlan_filter_enable(adapter);
	} else {
		if (netdev->flags & IFF_ALLMULTI) {
			fctrl |= IXGBE_FCTRL_MPE;
			vmolr |= IXGBE_VMOLR_MPE;
		}
		ixgbe_vlan_filter_enable(adapter);
		hw->addr_ctrl.user_set_promisc = false;
	}

	/*
	 * Write addresses to available RAR registers, if there is not
	 * sufficient space to store all the addresses then enable
	 * unicast promiscuous mode
	 */
	count = ixgbe_write_uc_addr_list(netdev);
	if (count < 0) {
		fctrl |= IXGBE_FCTRL_UPE;
		vmolr |= IXGBE_VMOLR_ROPE;
	}

	/* Write addresses to the MTA, if the attempt fails
	 * then we should just turn on promiscuous mode so
	 * that we can at least receive multicast traffic
	 */
	hw->mac.ops.update_mc_addr_list(hw, netdev);
	vmolr |= IXGBE_VMOLR_ROMPE;

	if (adapter->num_vfs)
		ixgbe_restore_vf_multicasts(adapter);

	if (hw->mac.type != ixgbe_mac_82598EB) {
		vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) &
			 ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE |
			   IXGBE_VMOLR_ROPE);
		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(0)), vmolr);
	}

	/* This is useful for sniffing bad packets. */
	if (adapter->netdev->features & NETIF_F_RXALL) {
		/* UPE and MPE will be handled by normal PROMISC logic
		 * in e1000e_set_rx_mode */
		fctrl |= (IXGBE_FCTRL_SBP | /* Receive bad packets */
			  IXGBE_FCTRL_BAM | /* RX All Bcast Pkts */
			  IXGBE_FCTRL_PMCF); /* RX All MAC Ctrl Pkts */

		fctrl &= ~(IXGBE_FCTRL_DPF);
		/* NOTE:  VLAN filtering is disabled by setting PROMISC */
	}

	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);

	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
		ixgbe_vlan_strip_enable(adapter);
	else
		ixgbe_vlan_strip_disable(adapter);
}

static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter)
{
	int q_idx;

	for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) {
		ixgbe_qv_init_lock(adapter->q_vector[q_idx]);
		napi_enable(&adapter->q_vector[q_idx]->napi);
	}
}

static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
{
	int q_idx;

	for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) {
		napi_disable(&adapter->q_vector[q_idx]->napi);
		while (!ixgbe_qv_disable(adapter->q_vector[q_idx])) {
			pr_info("QV %d locked\n", q_idx);
			usleep_range(1000, 20000);
		}
	}
}

#ifdef CONFIG_IXGBE_DCB
/**
 * ixgbe_configure_dcb - Configure DCB hardware
 * @adapter: ixgbe adapter struct
 *
 * This is called by the driver on open to configure the DCB hardware.
 * This is also called by the gennetlink interface when reconfiguring
 * the DCB state.
 */
static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN;

	if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) {
		if (hw->mac.type == ixgbe_mac_82598EB)
			netif_set_gso_max_size(adapter->netdev, 65536);
		return;
	}

	if (hw->mac.type == ixgbe_mac_82598EB)
		netif_set_gso_max_size(adapter->netdev, 32768);

#ifdef IXGBE_FCOE
	if (adapter->netdev->features & NETIF_F_FCOE_MTU)
		max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
#endif

	/* reconfigure the hardware */
	if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) {
		ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
						DCB_TX_CONFIG);
		ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
						DCB_RX_CONFIG);
		ixgbe_dcb_hw_config(hw, &adapter->dcb_cfg);
	} else if (adapter->ixgbe_ieee_ets && adapter->ixgbe_ieee_pfc) {
		ixgbe_dcb_hw_ets(&adapter->hw,
				 adapter->ixgbe_ieee_ets,
				 max_frame);
		ixgbe_dcb_hw_pfc_config(&adapter->hw,
					adapter->ixgbe_ieee_pfc->pfc_en,
					adapter->ixgbe_ieee_ets->prio_tc);
	}

	/* Enable RSS Hash per TC */
	if (hw->mac.type != ixgbe_mac_82598EB) {
		u32 msb = 0;
		u16 rss_i = adapter->ring_feature[RING_F_RSS].indices - 1;

		while (rss_i) {
			msb++;
			rss_i >>= 1;
		}

		/* write msb to all 8 TCs in one write */
		IXGBE_WRITE_REG(hw, IXGBE_RQTC, msb * 0x11111111);
	}
}
#endif

/* Additional bittime to account for IXGBE framing */
#define IXGBE_ETH_FRAMING 20

/**
 * ixgbe_hpbthresh - calculate high water mark for flow control
 *
 * @adapter: board private structure to calculate for
 * @pb: packet buffer to calculate
 */
static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *dev = adapter->netdev;
	int link, tc, kb, marker;
	u32 dv_id, rx_pba;

	/* Calculate max LAN frame size */
	tc = link = dev->mtu + ETH_HLEN + ETH_FCS_LEN + IXGBE_ETH_FRAMING;

#ifdef IXGBE_FCOE
	/* FCoE traffic class uses FCOE jumbo frames */
	if ((dev->features & NETIF_F_FCOE_MTU) &&
	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
	    (pb == ixgbe_fcoe_get_tc(adapter)))
		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;

#endif
	/* Calculate delay value for device */
	switch (hw->mac.type) {
	case ixgbe_mac_X540:
		dv_id = IXGBE_DV_X540(link, tc);
		break;
	default:
		dv_id = IXGBE_DV(link, tc);
		break;
	}

	/* Loopback switch introduces additional latency */
	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
		dv_id += IXGBE_B2BT(tc);

	/* Delay value is calculated in bit times convert to KB */
	kb = IXGBE_BT2KB(dv_id);
	rx_pba = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(pb)) >> 10;

	marker = rx_pba - kb;

	/* It is possible that the packet buffer is not large enough
	 * to provide required headroom. In this case throw an error
	 * to user and a do the best we can.
	 */
	if (marker < 0) {
		e_warn(drv, "Packet Buffer(%i) can not provide enough"
			    "headroom to support flow control."
			    "Decrease MTU or number of traffic classes\n", pb);
		marker = tc + 1;
	}

	return marker;
}

/**
 * ixgbe_lpbthresh - calculate low water mark for for flow control
 *
 * @adapter: board private structure to calculate for
 * @pb: packet buffer to calculate
 */
static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *dev = adapter->netdev;
	int tc;
	u32 dv_id;

	/* Calculate max LAN frame size */
	tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN;

	/* Calculate delay value for device */
	switch (hw->mac.type) {
	case ixgbe_mac_X540:
		dv_id = IXGBE_LOW_DV_X540(tc);
		break;
	default:
		dv_id = IXGBE_LOW_DV(tc);
		break;
	}

	/* Delay value is calculated in bit times convert to KB */
	return IXGBE_BT2KB(dv_id);
}

/*
 * ixgbe_pbthresh_setup - calculate and setup high low water marks
 */
static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int num_tc = netdev_get_num_tc(adapter->netdev);
	int i;

	if (!num_tc)
		num_tc = 1;

	hw->fc.low_water = ixgbe_lpbthresh(adapter);

	for (i = 0; i < num_tc; i++) {
		hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i);

		/* Low water marks must not be larger than high water marks */
		if (hw->fc.low_water > hw->fc.high_water[i])
			hw->fc.low_water = 0;
	}
}

static void ixgbe_configure_pb(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int hdrm;
	u8 tc = netdev_get_num_tc(adapter->netdev);

	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE ||
	    adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
		hdrm = 32 << adapter->fdir_pballoc;
	else
		hdrm = 0;

	hw->mac.ops.set_rxpba(hw, tc, hdrm, PBA_STRATEGY_EQUAL);
	ixgbe_pbthresh_setup(adapter);
}

static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct hlist_node *node2;
	struct ixgbe_fdir_filter *filter;

	spin_lock(&adapter->fdir_perfect_lock);

	if (!hlist_empty(&adapter->fdir_filter_list))
		ixgbe_fdir_set_input_mask_82599(hw, &adapter->fdir_mask);

	hlist_for_each_entry_safe(filter, node2,
				  &adapter->fdir_filter_list, fdir_node) {
		ixgbe_fdir_write_perfect_filter_82599(hw,
				&filter->filter,
				filter->sw_idx,
				(filter->action == IXGBE_FDIR_DROP_QUEUE) ?
				IXGBE_FDIR_DROP_QUEUE :
				adapter->rx_ring[filter->action]->reg_idx);
	}

	spin_unlock(&adapter->fdir_perfect_lock);
}

static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool,
				      struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vmolr;

	/* No unicast promiscuous support for VMDQ devices. */
	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool));
	vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE);

	/* clear the affected bit */
	vmolr &= ~IXGBE_VMOLR_MPE;

	if (dev->flags & IFF_ALLMULTI) {
		vmolr |= IXGBE_VMOLR_MPE;
	} else {
		vmolr |= IXGBE_VMOLR_ROMPE;
		hw->mac.ops.update_mc_addr_list(hw, dev);
	}
	ixgbe_write_uc_addr_list(adapter->netdev);
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr);
}

static void ixgbe_add_mac_filter(struct ixgbe_adapter *adapter,
				 u8 *addr, u16 pool)
{
	struct ixgbe_hw *hw = &adapter->hw;
	unsigned int entry;

	entry = hw->mac.num_rar_entries - pool;
	hw->mac.ops.set_rar(hw, entry, addr, VMDQ_P(pool), IXGBE_RAH_AV);
}

static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter)
{
	struct ixgbe_adapter *adapter = vadapter->real_adapter;
	int rss_i = adapter->num_rx_queues_per_pool;
	struct ixgbe_hw *hw = &adapter->hw;
	u16 pool = vadapter->pool;
	u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
		      IXGBE_PSRTYPE_UDPHDR |
		      IXGBE_PSRTYPE_IPV4HDR |
		      IXGBE_PSRTYPE_L2HDR |
		      IXGBE_PSRTYPE_IPV6HDR;

	if (hw->mac.type == ixgbe_mac_82598EB)
		return;

	if (rss_i > 3)
		psrtype |= 2 << 29;
	else if (rss_i > 1)
		psrtype |= 1 << 29;

	IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype);
}

/**
 * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
 * @rx_ring: ring to free buffers from
 **/
static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
{
	struct device *dev = rx_ring->dev;
	unsigned long size;
	u16 i;

	/* ring already cleared, nothing to do */
	if (!rx_ring->rx_buffer_info)
		return;

	/* Free all the Rx ring sk_buffs */
	for (i = 0; i < rx_ring->count; i++) {
		struct ixgbe_rx_buffer *rx_buffer;

		rx_buffer = &rx_ring->rx_buffer_info[i];
		if (rx_buffer->skb) {
			struct sk_buff *skb = rx_buffer->skb;
			if (IXGBE_CB(skb)->page_released) {
				dma_unmap_page(dev,
					       IXGBE_CB(skb)->dma,
					       ixgbe_rx_bufsz(rx_ring),
					       DMA_FROM_DEVICE);
				IXGBE_CB(skb)->page_released = false;
			}
			dev_kfree_skb(skb);
		}
		rx_buffer->skb = NULL;
		if (rx_buffer->dma)
			dma_unmap_page(dev, rx_buffer->dma,
				       ixgbe_rx_pg_size(rx_ring),
				       DMA_FROM_DEVICE);
		rx_buffer->dma = 0;
		if (rx_buffer->page)
			__free_pages(rx_buffer->page,
				     ixgbe_rx_pg_order(rx_ring));
		rx_buffer->page = NULL;
	}

	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
	memset(rx_ring->rx_buffer_info, 0, size);

	/* Zero out the descriptor ring */
	memset(rx_ring->desc, 0, rx_ring->size);

	rx_ring->next_to_alloc = 0;
	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;
}

static void ixgbe_disable_fwd_ring(struct ixgbe_fwd_adapter *vadapter,
				   struct ixgbe_ring *rx_ring)
{
	struct ixgbe_adapter *adapter = vadapter->real_adapter;
	int index = rx_ring->queue_index + vadapter->rx_base_queue;

	/* shutdown specific queue receive and wait for dma to settle */
	ixgbe_disable_rx_queue(adapter, rx_ring);
	usleep_range(10000, 20000);
	ixgbe_irq_disable_queues(adapter, ((u64)1 << index));
	ixgbe_clean_rx_ring(rx_ring);
	rx_ring->l2_accel_priv = NULL;
}

static int ixgbe_fwd_ring_down(struct net_device *vdev,
			       struct ixgbe_fwd_adapter *accel)
{
	struct ixgbe_adapter *adapter = accel->real_adapter;
	unsigned int rxbase = accel->rx_base_queue;
	unsigned int txbase = accel->tx_base_queue;
	int i;

	netif_tx_stop_all_queues(vdev);

	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
		ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]);
		adapter->rx_ring[rxbase + i]->netdev = adapter->netdev;
	}

	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
		adapter->tx_ring[txbase + i]->l2_accel_priv = NULL;
		adapter->tx_ring[txbase + i]->netdev = adapter->netdev;
	}


	return 0;
}

static int ixgbe_fwd_ring_up(struct net_device *vdev,
			     struct ixgbe_fwd_adapter *accel)
{
	struct ixgbe_adapter *adapter = accel->real_adapter;
	unsigned int rxbase, txbase, queues;
	int i, baseq, err = 0;

	if (!test_bit(accel->pool, &adapter->fwd_bitmask))
		return 0;

	baseq = accel->pool * adapter->num_rx_queues_per_pool;
	netdev_dbg(vdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n",
		   accel->pool, adapter->num_rx_pools,
		   baseq, baseq + adapter->num_rx_queues_per_pool,
		   adapter->fwd_bitmask);

	accel->netdev = vdev;
	accel->rx_base_queue = rxbase = baseq;
	accel->tx_base_queue = txbase = baseq;

	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
		ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]);

	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
		adapter->rx_ring[rxbase + i]->netdev = vdev;
		adapter->rx_ring[rxbase + i]->l2_accel_priv = accel;
		ixgbe_configure_rx_ring(adapter, adapter->rx_ring[rxbase + i]);
	}

	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
		adapter->tx_ring[txbase + i]->netdev = vdev;
		adapter->tx_ring[txbase + i]->l2_accel_priv = accel;
	}

	queues = min_t(unsigned int,
		       adapter->num_rx_queues_per_pool, vdev->num_tx_queues);
	err = netif_set_real_num_tx_queues(vdev, queues);
	if (err)
		goto fwd_queue_err;

	err = netif_set_real_num_rx_queues(vdev, queues);
	if (err)
		goto fwd_queue_err;

	if (is_valid_ether_addr(vdev->dev_addr))
		ixgbe_add_mac_filter(adapter, vdev->dev_addr, accel->pool);

	ixgbe_fwd_psrtype(accel);
	ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter);
	return err;
fwd_queue_err:
	ixgbe_fwd_ring_down(vdev, accel);
	return err;
}

static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
{
	struct net_device *upper;
	struct list_head *iter;
	int err;

	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
		if (netif_is_macvlan(upper)) {
			struct macvlan_dev *dfwd = netdev_priv(upper);
			struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;

			if (dfwd->fwd_priv) {
				err = ixgbe_fwd_ring_up(upper, vadapter);
				if (err)
					continue;
			}
		}
	}
}

static void ixgbe_configure(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	ixgbe_configure_pb(adapter);
#ifdef CONFIG_IXGBE_DCB
	ixgbe_configure_dcb(adapter);
#endif
	/*
	 * We must restore virtualization before VLANs or else
	 * the VLVF registers will not be populated
	 */
	ixgbe_configure_virtualization(adapter);

	ixgbe_set_rx_mode(adapter->netdev);
	ixgbe_restore_vlan(adapter);

	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		hw->mac.ops.disable_rx_buff(hw);
		break;
	default:
		break;
	}

	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
		ixgbe_init_fdir_signature_82599(&adapter->hw,
						adapter->fdir_pballoc);
	} else if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) {
		ixgbe_init_fdir_perfect_82599(&adapter->hw,
					      adapter->fdir_pballoc);
		ixgbe_fdir_filter_restore(adapter);
	}

	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		hw->mac.ops.enable_rx_buff(hw);
		break;
	default:
		break;
	}

#ifdef IXGBE_FCOE
	/* configure FCoE L2 filters, redirection table, and Rx control */
	ixgbe_configure_fcoe(adapter);

#endif /* IXGBE_FCOE */
	ixgbe_configure_tx(adapter);
	ixgbe_configure_rx(adapter);
	ixgbe_configure_dfwd(adapter);
}

static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
{
	switch (hw->phy.type) {
	case ixgbe_phy_sfp_avago:
	case ixgbe_phy_sfp_ftl:
	case ixgbe_phy_sfp_intel:
	case ixgbe_phy_sfp_unknown:
	case ixgbe_phy_sfp_passive_tyco:
	case ixgbe_phy_sfp_passive_unknown:
	case ixgbe_phy_sfp_active_unknown:
	case ixgbe_phy_sfp_ftl_active:
	case ixgbe_phy_qsfp_passive_unknown:
	case ixgbe_phy_qsfp_active_unknown:
	case ixgbe_phy_qsfp_intel:
	case ixgbe_phy_qsfp_unknown:
		return true;
	case ixgbe_phy_nl:
		if (hw->mac.type == ixgbe_mac_82598EB)
			return true;
	default:
		return false;
	}
}

/**
 * ixgbe_sfp_link_config - set up SFP+ link
 * @adapter: pointer to private adapter struct
 **/
static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
{
	/*
	 * We are assuming the worst case scenario here, and that
	 * is that an SFP was inserted/removed after the reset
	 * but before SFP detection was enabled.  As such the best
	 * solution is to just start searching as soon as we start
	 */
	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
		adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP;

	adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
}

/**
 * ixgbe_non_sfp_link_config - set up non-SFP+ link
 * @hw: pointer to private hardware struct
 *
 * Returns 0 on success, negative on failure
 **/
static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
{
	u32 speed;
	bool autoneg, link_up = false;
	u32 ret = IXGBE_ERR_LINK_SETUP;

	if (hw->mac.ops.check_link)
		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);

	if (ret)
		goto link_cfg_out;

	speed = hw->phy.autoneg_advertised;
	if ((!speed) && (hw->mac.ops.get_link_capabilities))
		ret = hw->mac.ops.get_link_capabilities(hw, &speed,
							&autoneg);
	if (ret)
		goto link_cfg_out;

	if (hw->mac.ops.setup_link)
		ret = hw->mac.ops.setup_link(hw, speed, link_up);
link_cfg_out:
	return ret;
}

static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 gpie = 0;

	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
		gpie = IXGBE_GPIE_MSIX_MODE | IXGBE_GPIE_PBA_SUPPORT |
		       IXGBE_GPIE_OCD;
		gpie |= IXGBE_GPIE_EIAME;
		/*
		 * use EIAM to auto-mask when MSI-X interrupt is asserted
		 * this saves a register write for every interrupt
		 */
		switch (hw->mac.type) {
		case ixgbe_mac_82598EB:
			IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
			break;
		case ixgbe_mac_82599EB:
		case ixgbe_mac_X540:
		default:
			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
			break;
		}
	} else {
		/* legacy interrupts, use EIAM to auto-mask when reading EICR,
		 * specifically only auto mask tx and rx interrupts */
		IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
	}

	/* XXX: to interrupt immediately for EICS writes, enable this */
	/* gpie |= IXGBE_GPIE_EIMEN; */

	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
		gpie &= ~IXGBE_GPIE_VTMODE_MASK;

		switch (adapter->ring_feature[RING_F_VMDQ].mask) {
		case IXGBE_82599_VMDQ_8Q_MASK:
			gpie |= IXGBE_GPIE_VTMODE_16;
			break;
		case IXGBE_82599_VMDQ_4Q_MASK:
			gpie |= IXGBE_GPIE_VTMODE_32;
			break;
		default:
			gpie |= IXGBE_GPIE_VTMODE_64;
			break;
		}
	}

	/* Enable Thermal over heat sensor interrupt */
	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) {
		switch (adapter->hw.mac.type) {
		case ixgbe_mac_82599EB:
			gpie |= IXGBE_SDP0_GPIEN;
			break;
		case ixgbe_mac_X540:
			gpie |= IXGBE_EIMS_TS;
			break;
		default:
			break;
		}
	}

	/* Enable fan failure interrupt */
	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
		gpie |= IXGBE_SDP1_GPIEN;

	if (hw->mac.type == ixgbe_mac_82599EB) {
		gpie |= IXGBE_SDP1_GPIEN;
		gpie |= IXGBE_SDP2_GPIEN;
	}

	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
}

static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *upper;
	struct list_head *iter;
	int err;
	u32 ctrl_ext;

	ixgbe_get_hw_control(adapter);
	ixgbe_setup_gpie(adapter);

	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
		ixgbe_configure_msix(adapter);
	else
		ixgbe_configure_msi_and_legacy(adapter);

	/* enable the optics for 82599 SFP+ fiber */
	if (hw->mac.ops.enable_tx_laser)
		hw->mac.ops.enable_tx_laser(hw);

	smp_mb__before_clear_bit();
	clear_bit(__IXGBE_DOWN, &adapter->state);
	ixgbe_napi_enable_all(adapter);

	if (ixgbe_is_sfp(hw)) {
		ixgbe_sfp_link_config(adapter);
	} else {
		err = ixgbe_non_sfp_link_config(hw);
		if (err)
			e_err(probe, "link_config FAILED %d\n", err);
	}

	/* clear any pending interrupts, may auto mask */
	IXGBE_READ_REG(hw, IXGBE_EICR);
	ixgbe_irq_enable(adapter, true, true);

	/*
	 * If this adapter has a fan, check to see if we had a failure
	 * before we enabled the interrupt.
	 */
	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) {
		u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
		if (esdp & IXGBE_ESDP_SDP1)
			e_crit(drv, "Fan has stopped, replace the adapter\n");
	}

	/* enable transmits */
	netif_tx_start_all_queues(adapter->netdev);

	/* enable any upper devices */
	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
		if (netif_is_macvlan(upper)) {
			struct macvlan_dev *vlan = netdev_priv(upper);

			if (vlan->fwd_priv)
				netif_tx_start_all_queues(upper);
		}
	}

	/* bring the link up in the watchdog, this could race with our first
	 * link up interrupt but shouldn't be a problem */
	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
	adapter->link_check_timeout = jiffies;
	mod_timer(&adapter->service_timer, jiffies);

	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
	ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT);
	ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD;
	IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
}

void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
{
	WARN_ON(in_interrupt());
	/* put off any impending NetWatchDogTimeout */
	adapter->netdev->trans_start = jiffies;

	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
		usleep_range(1000, 2000);
	ixgbe_down(adapter);
	/*
	 * If SR-IOV enabled then wait a bit before bringing the adapter
	 * back up to give the VFs time to respond to the reset.  The
	 * two second wait is based upon the watchdog timer cycle in
	 * the VF driver.
	 */
	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
		msleep(2000);
	ixgbe_up(adapter);
	clear_bit(__IXGBE_RESETTING, &adapter->state);
}

void ixgbe_up(struct ixgbe_adapter *adapter)
{
	/* hardware has been reset, we need to reload some things */
	ixgbe_configure(adapter);

	ixgbe_up_complete(adapter);
}

void ixgbe_reset(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int err;

	if (ixgbe_removed(hw->hw_addr))
		return;
	/* lock SFP init bit to prevent race conditions with the watchdog */
	while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state))
		usleep_range(1000, 2000);

	/* clear all SFP and link config related flags while holding SFP_INIT */
	adapter->flags2 &= ~(IXGBE_FLAG2_SEARCH_FOR_SFP |
			     IXGBE_FLAG2_SFP_NEEDS_RESET);
	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;

	err = hw->mac.ops.init_hw(hw);
	switch (err) {
	case 0:
	case IXGBE_ERR_SFP_NOT_PRESENT:
	case IXGBE_ERR_SFP_NOT_SUPPORTED:
		break;
	case IXGBE_ERR_MASTER_REQUESTS_PENDING:
		e_dev_err("master disable timed out\n");
		break;
	case IXGBE_ERR_EEPROM_VERSION:
		/* We are running on a pre-production device, log a warning */
		e_dev_warn("This device is a pre-production adapter/LOM. "
			   "Please be aware there may be issues associated with "
			   "your hardware.  If you are experiencing problems "
			   "please contact your Intel or hardware "
			   "representative who provided you with this "
			   "hardware.\n");
		break;
	default:
		e_dev_err("Hardware Error: %d\n", err);
	}

	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);

	/* reprogram the RAR[0] in case user changed it. */
	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV);

	/* update SAN MAC vmdq pool selection */
	if (hw->mac.san_mac_rar_index)
		hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0));

	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state))
		ixgbe_ptp_reset(adapter);
}

/**
 * ixgbe_clean_tx_ring - Free Tx Buffers
 * @tx_ring: ring to be cleaned
 **/
static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
{
	struct ixgbe_tx_buffer *tx_buffer_info;
	unsigned long size;
	u16 i;

	/* ring already cleared, nothing to do */
	if (!tx_ring->tx_buffer_info)
		return;

	/* Free all the Tx ring sk_buffs */
	for (i = 0; i < tx_ring->count; i++) {
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
	}

	netdev_tx_reset_queue(txring_txq(tx_ring));

	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
	memset(tx_ring->tx_buffer_info, 0, size);

	/* Zero out the descriptor ring */
	memset(tx_ring->desc, 0, tx_ring->size);

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;
}

/**
 * ixgbe_clean_all_rx_rings - Free Rx Buffers for all queues
 * @adapter: board private structure
 **/
static void ixgbe_clean_all_rx_rings(struct ixgbe_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_rx_queues; i++)
		ixgbe_clean_rx_ring(adapter->rx_ring[i]);
}

/**
 * ixgbe_clean_all_tx_rings - Free Tx Buffers for all queues
 * @adapter: board private structure
 **/
static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_tx_queues; i++)
		ixgbe_clean_tx_ring(adapter->tx_ring[i]);
}

static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter)
{
	struct hlist_node *node2;
	struct ixgbe_fdir_filter *filter;

	spin_lock(&adapter->fdir_perfect_lock);

	hlist_for_each_entry_safe(filter, node2,
				  &adapter->fdir_filter_list, fdir_node) {
		hlist_del(&filter->fdir_node);
		kfree(filter);
	}
	adapter->fdir_filter_count = 0;

	spin_unlock(&adapter->fdir_perfect_lock);
}

void ixgbe_down(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *upper;
	struct list_head *iter;
	u32 rxctrl;
	int i;

	/* signal that we are down to the interrupt handler */
	if (test_and_set_bit(__IXGBE_DOWN, &adapter->state))
		return; /* do nothing if already down */

	/* disable receives */
	rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
	IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN);

	/* disable all enabled rx queues */
	for (i = 0; i < adapter->num_rx_queues; i++)
		/* this call also flushes the previous write */
		ixgbe_disable_rx_queue(adapter, adapter->rx_ring[i]);

	usleep_range(10000, 20000);

	netif_tx_stop_all_queues(netdev);

	/* call carrier off first to avoid false dev_watchdog timeouts */
	netif_carrier_off(netdev);
	netif_tx_disable(netdev);

	/* disable any upper devices */
	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
		if (netif_is_macvlan(upper)) {
			struct macvlan_dev *vlan = netdev_priv(upper);

			if (vlan->fwd_priv) {
				netif_tx_stop_all_queues(upper);
				netif_carrier_off(upper);
				netif_tx_disable(upper);
			}
		}
	}

	ixgbe_irq_disable(adapter);

	ixgbe_napi_disable_all(adapter);

	adapter->flags2 &= ~(IXGBE_FLAG2_FDIR_REQUIRES_REINIT |
			     IXGBE_FLAG2_RESET_REQUESTED);
	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE;

	del_timer_sync(&adapter->service_timer);

	if (adapter->num_vfs) {
		/* Clear EITR Select mapping */
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0);

		/* Mark all the VFs as inactive */
		for (i = 0 ; i < adapter->num_vfs; i++)
			adapter->vfinfo[i].clear_to_send = false;

		/* ping all the active vfs to let them know we are going down */
		ixgbe_ping_all_vfs(adapter);

		/* Disable all VFTE/VFRE TX/RX */
		ixgbe_disable_tx_rx(adapter);
	}

	/* disable transmits in the hardware now that interrupts are off */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		u8 reg_idx = adapter->tx_ring[i]->reg_idx;
		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
	}

	/* Disable the Tx DMA engine on 82599 and X540 */
	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
				 ~IXGBE_DMATXCTL_TE));
		break;
	default:
		break;
	}

	if (!pci_channel_offline(adapter->pdev))
		ixgbe_reset(adapter);

	/* power down the optics for 82599 SFP+ fiber */
	if (hw->mac.ops.disable_tx_laser)
		hw->mac.ops.disable_tx_laser(hw);

	ixgbe_clean_all_tx_rings(adapter);
	ixgbe_clean_all_rx_rings(adapter);

#ifdef CONFIG_IXGBE_DCA
	/* since we reset the hardware DCA settings were cleared */
	ixgbe_setup_dca(adapter);
#endif
}

/**
 * ixgbe_tx_timeout - Respond to a Tx Hang
 * @netdev: network interface device structure
 **/
static void ixgbe_tx_timeout(struct net_device *netdev)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);

	/* Do the reset outside of interrupt context */
	ixgbe_tx_timeout_reset(adapter);
}

/**
 * ixgbe_sw_init - Initialize general software structures (struct ixgbe_adapter)
 * @adapter: board private structure to initialize
 *
 * ixgbe_sw_init initializes the Adapter private data structure.
 * Fields are initialized based on PCI device information and
 * OS network device settings (MTU size).
 **/
static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct pci_dev *pdev = adapter->pdev;
	unsigned int rss, fdir;
	u32 fwsm;
#ifdef CONFIG_IXGBE_DCB
	int j;
	struct tc_configuration *tc;
#endif

	/* PCI config space info */

	hw->vendor_id = pdev->vendor;
	hw->device_id = pdev->device;
	hw->revision_id = pdev->revision;
	hw->subsystem_vendor_id = pdev->subsystem_vendor;
	hw->subsystem_device_id = pdev->subsystem_device;

	/* Set common capability flags and settings */
	rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus());
	adapter->ring_feature[RING_F_RSS].limit = rss;
	adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
	adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
	adapter->max_q_vectors = MAX_Q_VECTORS_82599;
	adapter->atr_sample_rate = 20;
	fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus());
	adapter->ring_feature[RING_F_FDIR].limit = fdir;
	adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K;
#ifdef CONFIG_IXGBE_DCA
	adapter->flags |= IXGBE_FLAG_DCA_CAPABLE;
#endif
#ifdef IXGBE_FCOE
	adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
	adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
#ifdef CONFIG_IXGBE_DCB
	/* Default traffic class to use for FCoE */
	adapter->fcoe.up = IXGBE_FCOE_DEFTC;
#endif /* CONFIG_IXGBE_DCB */
#endif /* IXGBE_FCOE */

	/* Set MAC specific capability flags and exceptions */
	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE;
		adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED;

		if (hw->device_id == IXGBE_DEV_ID_82598AT)
			adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE;

		adapter->max_q_vectors = MAX_Q_VECTORS_82598;
		adapter->ring_feature[RING_F_FDIR].limit = 0;
		adapter->atr_sample_rate = 0;
		adapter->fdir_pballoc = 0;
#ifdef IXGBE_FCOE
		adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
		adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
#ifdef CONFIG_IXGBE_DCB
		adapter->fcoe.up = 0;
#endif /* IXGBE_DCB */
#endif /* IXGBE_FCOE */
		break;
	case ixgbe_mac_82599EB:
		if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM)
			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
		break;
	case ixgbe_mac_X540:
		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
		if (fwsm & IXGBE_FWSM_TS_ENABLED)
			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
		break;
	default:
		break;
	}

#ifdef IXGBE_FCOE
	/* FCoE support exists, always init the FCoE lock */
	spin_lock_init(&adapter->fcoe.lock);

#endif
	/* n-tuple support exists, always init our spinlock */
	spin_lock_init(&adapter->fdir_perfect_lock);

#ifdef CONFIG_IXGBE_DCB
	switch (hw->mac.type) {
	case ixgbe_mac_X540:
		adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS;
		adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS;
		break;
	default:
		adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS;
		adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS;
		break;
	}

	/* Configure DCB traffic classes */
	for (j = 0; j < MAX_TRAFFIC_CLASS; j++) {
		tc = &adapter->dcb_cfg.tc_config[j];
		tc->path[DCB_TX_CONFIG].bwg_id = 0;
		tc->path[DCB_TX_CONFIG].bwg_percent = 12 + (j & 1);
		tc->path[DCB_RX_CONFIG].bwg_id = 0;
		tc->path[DCB_RX_CONFIG].bwg_percent = 12 + (j & 1);
		tc->dcb_pfc = pfc_disabled;
	}

	/* Initialize default user to priority mapping, UPx->TC0 */
	tc = &adapter->dcb_cfg.tc_config[0];
	tc->path[DCB_TX_CONFIG].up_to_tc_bitmap = 0xFF;
	tc->path[DCB_RX_CONFIG].up_to_tc_bitmap = 0xFF;

	adapter->dcb_cfg.bw_percentage[DCB_TX_CONFIG][0] = 100;
	adapter->dcb_cfg.bw_percentage[DCB_RX_CONFIG][0] = 100;
	adapter->dcb_cfg.pfc_mode_enable = false;
	adapter->dcb_set_bitmap = 0x00;
	adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE;
	memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
	       sizeof(adapter->temp_dcb_cfg));

#endif

	/* default flow control settings */
	hw->fc.requested_mode = ixgbe_fc_full;
	hw->fc.current_mode = ixgbe_fc_full;	/* init for ethtool output */
	ixgbe_pbthresh_setup(adapter);
	hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE;
	hw->fc.send_xon = true;
	hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw);

#ifdef CONFIG_PCI_IOV
	if (max_vfs > 0)
		e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n");

	/* assign number of SR-IOV VFs */
	if (hw->mac.type != ixgbe_mac_82598EB) {
		if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) {
			adapter->num_vfs = 0;
			e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n");
		} else {
			adapter->num_vfs = max_vfs;
		}
	}
#endif /* CONFIG_PCI_IOV */

	/* enable itr by default in dynamic mode */
	adapter->rx_itr_setting = 1;
	adapter->tx_itr_setting = 1;

	/* set default ring sizes */
	adapter->tx_ring_count = IXGBE_DEFAULT_TXD;
	adapter->rx_ring_count = IXGBE_DEFAULT_RXD;

	/* set default work limits */
	adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;

	/* initialize eeprom parameters */
	if (ixgbe_init_eeprom_params_generic(hw)) {
		e_dev_err("EEPROM initialization failed\n");
		return -EIO;
	}

	/* PF holds first pool slot */
	set_bit(0, &adapter->fwd_bitmask);
	set_bit(__IXGBE_DOWN, &adapter->state);

	return 0;
}

/**
 * ixgbe_setup_tx_resources - allocate Tx resources (Descriptors)
 * @tx_ring:    tx descriptor ring (for a specific queue) to setup
 *
 * Return 0 on success, negative on failure
 **/
int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
{
	struct device *dev = tx_ring->dev;
	int orig_node = dev_to_node(dev);
	int numa_node = -1;
	int size;

	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;

	if (tx_ring->q_vector)
		numa_node = tx_ring->q_vector->numa_node;

	tx_ring->tx_buffer_info = vzalloc_node(size, numa_node);
	if (!tx_ring->tx_buffer_info)
		tx_ring->tx_buffer_info = vzalloc(size);
	if (!tx_ring->tx_buffer_info)
		goto err;

	u64_stats_init(&tx_ring->syncp);

	/* round up to nearest 4K */
	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
	tx_ring->size = ALIGN(tx_ring->size, 4096);

	set_dev_node(dev, numa_node);
	tx_ring->desc = dma_alloc_coherent(dev,
					   tx_ring->size,
					   &tx_ring->dma,
					   GFP_KERNEL);
	set_dev_node(dev, orig_node);
	if (!tx_ring->desc)
		tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
						   &tx_ring->dma, GFP_KERNEL);
	if (!tx_ring->desc)
		goto err;

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;
	return 0;

err:
	vfree(tx_ring->tx_buffer_info);
	tx_ring->tx_buffer_info = NULL;
	dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n");
	return -ENOMEM;
}

/**
 * ixgbe_setup_all_tx_resources - allocate all queues Tx resources
 * @adapter: board private structure
 *
 * If this function returns with an error, then it's possible one or
 * more of the rings is populated (while the rest are not).  It is the
 * callers duty to clean those orphaned rings.
 *
 * Return 0 on success, negative on failure
 **/
static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
{
	int i, err = 0;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		err = ixgbe_setup_tx_resources(adapter->tx_ring[i]);
		if (!err)
			continue;

		e_err(probe, "Allocation for Tx Queue %u failed\n", i);
		goto err_setup_tx;
	}

	return 0;
err_setup_tx:
	/* rewind the index freeing the rings as we go */
	while (i--)
		ixgbe_free_tx_resources(adapter->tx_ring[i]);
	return err;
}

/**
 * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors)
 * @rx_ring:    rx descriptor ring (for a specific queue) to setup
 *
 * Returns 0 on success, negative on failure
 **/
int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
{
	struct device *dev = rx_ring->dev;
	int orig_node = dev_to_node(dev);
	int numa_node = -1;
	int size;

	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;

	if (rx_ring->q_vector)
		numa_node = rx_ring->q_vector->numa_node;

	rx_ring->rx_buffer_info = vzalloc_node(size, numa_node);
	if (!rx_ring->rx_buffer_info)
		rx_ring->rx_buffer_info = vzalloc(size);
	if (!rx_ring->rx_buffer_info)
		goto err;

	u64_stats_init(&rx_ring->syncp);

	/* Round up to nearest 4K */
	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
	rx_ring->size = ALIGN(rx_ring->size, 4096);

	set_dev_node(dev, numa_node);
	rx_ring->desc = dma_alloc_coherent(dev,
					   rx_ring->size,
					   &rx_ring->dma,
					   GFP_KERNEL);
	set_dev_node(dev, orig_node);
	if (!rx_ring->desc)
		rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
						   &rx_ring->dma, GFP_KERNEL);
	if (!rx_ring->desc)
		goto err;

	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;

	return 0;
err:
	vfree(rx_ring->rx_buffer_info);
	rx_ring->rx_buffer_info = NULL;
	dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n");
	return -ENOMEM;
}

/**
 * ixgbe_setup_all_rx_resources - allocate all queues Rx resources
 * @adapter: board private structure
 *
 * If this function returns with an error, then it's possible one or
 * more of the rings is populated (while the rest are not).  It is the
 * callers duty to clean those orphaned rings.
 *
 * Return 0 on success, negative on failure
 **/
static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter)
{
	int i, err = 0;

	for (i = 0; i < adapter->num_rx_queues; i++) {
		err = ixgbe_setup_rx_resources(adapter->rx_ring[i]);
		if (!err)
			continue;

		e_err(probe, "Allocation for Rx Queue %u failed\n", i);
		goto err_setup_rx;
	}

#ifdef IXGBE_FCOE
	err = ixgbe_setup_fcoe_ddp_resources(adapter);
	if (!err)
#endif
		return 0;
err_setup_rx:
	/* rewind the index freeing the rings as we go */
	while (i--)
		ixgbe_free_rx_resources(adapter->rx_ring[i]);
	return err;
}

/**
 * ixgbe_free_tx_resources - Free Tx Resources per Queue
 * @tx_ring: Tx descriptor ring for a specific queue
 *
 * Free all transmit software resources
 **/
void ixgbe_free_tx_resources(struct ixgbe_ring *tx_ring)
{
	ixgbe_clean_tx_ring(tx_ring);

	vfree(tx_ring->tx_buffer_info);
	tx_ring->tx_buffer_info = NULL;

	/* if not set, then don't free */
	if (!tx_ring->desc)
		return;

	dma_free_coherent(tx_ring->dev, tx_ring->size,
			  tx_ring->desc, tx_ring->dma);

	tx_ring->desc = NULL;
}

/**
 * ixgbe_free_all_tx_resources - Free Tx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all transmit software resources
 **/
static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_tx_queues; i++)
		if (adapter->tx_ring[i]->desc)
			ixgbe_free_tx_resources(adapter->tx_ring[i]);
}

/**
 * ixgbe_free_rx_resources - Free Rx Resources
 * @rx_ring: ring to clean the resources from
 *
 * Free all receive software resources
 **/
void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring)
{
	ixgbe_clean_rx_ring(rx_ring);

	vfree(rx_ring->rx_buffer_info);
	rx_ring->rx_buffer_info = NULL;

	/* if not set, then don't free */
	if (!rx_ring->desc)
		return;

	dma_free_coherent(rx_ring->dev, rx_ring->size,
			  rx_ring->desc, rx_ring->dma);

	rx_ring->desc = NULL;
}

/**
 * ixgbe_free_all_rx_resources - Free Rx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all receive software resources
 **/
static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter)
{
	int i;

#ifdef IXGBE_FCOE
	ixgbe_free_fcoe_ddp_resources(adapter);

#endif
	for (i = 0; i < adapter->num_rx_queues; i++)
		if (adapter->rx_ring[i]->desc)
			ixgbe_free_rx_resources(adapter->rx_ring[i]);
}

/**
 * ixgbe_change_mtu - Change the Maximum Transfer Unit
 * @netdev: network interface device structure
 * @new_mtu: new value for maximum frame size
 *
 * Returns 0 on success, negative on failure
 **/
static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;

	/* MTU < 68 is an error and causes problems on some kernels */
	if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE))
		return -EINVAL;

	/*
	 * For 82599EB we cannot allow legacy VFs to enable their receive
	 * paths when MTU greater than 1500 is configured.  So display a
	 * warning that legacy VFs will be disabled.
	 */
	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) &&
	    (adapter->hw.mac.type == ixgbe_mac_82599EB) &&
	    (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
		e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n");

	e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);

	/* must set new MTU before calling down or up */
	netdev->mtu = new_mtu;

	if (netif_running(netdev))
		ixgbe_reinit_locked(adapter);

	return 0;
}

/**
 * ixgbe_open - Called when a network interface is made active
 * @netdev: network interface device structure
 *
 * Returns 0 on success, negative value on failure
 *
 * The open entry point is called when a network interface is made
 * active by the system (IFF_UP).  At this point all resources needed
 * for transmit and receive operations are allocated, the interrupt
 * handler is registered with the OS, the watchdog timer is started,
 * and the stack is notified that the interface is ready.
 **/
static int ixgbe_open(struct net_device *netdev)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	int err, queues;

	/* disallow open during test */
	if (test_bit(__IXGBE_TESTING, &adapter->state))
		return -EBUSY;

	netif_carrier_off(netdev);

	/* allocate transmit descriptors */
	err = ixgbe_setup_all_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

	/* allocate receive descriptors */
	err = ixgbe_setup_all_rx_resources(adapter);
	if (err)
		goto err_setup_rx;

	ixgbe_configure(adapter);

	err = ixgbe_request_irq(adapter);
	if (err)
		goto err_req_irq;

	/* Notify the stack of the actual queue counts. */
	if (adapter->num_rx_pools > 1)
		queues = adapter->num_rx_queues_per_pool;
	else
		queues = adapter->num_tx_queues;

	err = netif_set_real_num_tx_queues(netdev, queues);
	if (err)
		goto err_set_queues;

	if (adapter->num_rx_pools > 1 &&
	    adapter->num_rx_queues > IXGBE_MAX_L2A_QUEUES)
		queues = IXGBE_MAX_L2A_QUEUES;
	else
		queues = adapter->num_rx_queues;
	err = netif_set_real_num_rx_queues(netdev, queues);
	if (err)
		goto err_set_queues;

	ixgbe_ptp_init(adapter);

	ixgbe_up_complete(adapter);

	return 0;

err_set_queues:
	ixgbe_free_irq(adapter);
err_req_irq:
	ixgbe_free_all_rx_resources(adapter);
err_setup_rx:
	ixgbe_free_all_tx_resources(adapter);
err_setup_tx:
	ixgbe_reset(adapter);

	return err;
}

/**
 * ixgbe_close - Disables a network interface
 * @netdev: network interface device structure
 *
 * Returns 0, this is not allowed to fail
 *
 * The close entry point is called when an interface is de-activated
 * by the OS.  The hardware is still under the drivers control, but
 * needs to be disabled.  A global MAC reset is issued to stop the
 * hardware, and all transmit and receive resources are freed.
 **/
static int ixgbe_close(struct net_device *netdev)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);

	ixgbe_ptp_stop(adapter);

	ixgbe_down(adapter);
	ixgbe_free_irq(adapter);

	ixgbe_fdir_filter_exit(adapter);

	ixgbe_free_all_tx_resources(adapter);
	ixgbe_free_all_rx_resources(adapter);

	ixgbe_release_hw_control(adapter);

	return 0;
}

#ifdef CONFIG_PM
static int ixgbe_resume(struct pci_dev *pdev)
{
	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
	struct net_device *netdev = adapter->netdev;
	u32 err;

	pci_set_power_state(pdev, PCI_D0);
	pci_restore_state(pdev);
	/*
	 * pci_restore_state clears dev->state_saved so call
	 * pci_save_state to restore it.
	 */
	pci_save_state(pdev);

	err = pci_enable_device_mem(pdev);
	if (err) {
		e_dev_err("Cannot enable PCI device from suspend\n");
		return err;
	}
	pci_set_master(pdev);

	pci_wake_from_d3(pdev, false);

	ixgbe_reset(adapter);

	IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);

	rtnl_lock();
	err = ixgbe_init_interrupt_scheme(adapter);
	if (!err && netif_running(netdev))
		err = ixgbe_open(netdev);

	rtnl_unlock();

	if (err)
		return err;

	netif_device_attach(netdev);

	return 0;
}
#endif /* CONFIG_PM */

static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
{
	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 ctrl, fctrl;
	u32 wufc = adapter->wol;
#ifdef CONFIG_PM
	int retval = 0;
#endif

	netif_device_detach(netdev);

	rtnl_lock();
	if (netif_running(netdev)) {
		ixgbe_down(adapter);
		ixgbe_free_irq(adapter);
		ixgbe_free_all_tx_resources(adapter);
		ixgbe_free_all_rx_resources(adapter);
	}
	rtnl_unlock();

	ixgbe_clear_interrupt_scheme(adapter);

#ifdef CONFIG_PM
	retval = pci_save_state(pdev);
	if (retval)
		return retval;

#endif
	if (hw->mac.ops.stop_link_on_d3)
		hw->mac.ops.stop_link_on_d3(hw);

	if (wufc) {
		ixgbe_set_rx_mode(netdev);

		/* enable the optics for 82599 SFP+ fiber as we can WoL */
		if (hw->mac.ops.enable_tx_laser)
			hw->mac.ops.enable_tx_laser(hw);

		/* turn on all-multi mode if wake on multicast is enabled */
		if (wufc & IXGBE_WUFC_MC) {
			fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
			fctrl |= IXGBE_FCTRL_MPE;
			IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);
		}

		ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
		ctrl |= IXGBE_CTRL_GIO_DIS;
		IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);

		IXGBE_WRITE_REG(hw, IXGBE_WUFC, wufc);
	} else {
		IXGBE_WRITE_REG(hw, IXGBE_WUC, 0);
		IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
	}

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		pci_wake_from_d3(pdev, false);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		pci_wake_from_d3(pdev, !!wufc);
		break;
	default:
		break;
	}

	*enable_wake = !!wufc;

	ixgbe_release_hw_control(adapter);

	pci_disable_device(pdev);

	return 0;
}

#ifdef CONFIG_PM
static int ixgbe_suspend(struct pci_dev *pdev, pm_message_t state)
{
	int retval;
	bool wake;

	retval = __ixgbe_shutdown(pdev, &wake);
	if (retval)
		return retval;

	if (wake) {
		pci_prepare_to_sleep(pdev);
	} else {
		pci_wake_from_d3(pdev, false);
		pci_set_power_state(pdev, PCI_D3hot);
	}

	return 0;
}
#endif /* CONFIG_PM */

static void ixgbe_shutdown(struct pci_dev *pdev)
{
	bool wake;

	__ixgbe_shutdown(pdev, &wake);

	if (system_state == SYSTEM_POWER_OFF) {
		pci_wake_from_d3(pdev, wake);
		pci_set_power_state(pdev, PCI_D3hot);
	}
}

/**
 * ixgbe_update_stats - Update the board statistics counters.
 * @adapter: board private structure
 **/
void ixgbe_update_stats(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_hw_stats *hwstats = &adapter->stats;
	u64 total_mpc = 0;
	u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
	u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0;
	u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0;
	u64 bytes = 0, packets = 0, hw_csum_rx_error = 0;

	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
	    test_bit(__IXGBE_RESETTING, &adapter->state))
		return;

	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
		u64 rsc_count = 0;
		u64 rsc_flush = 0;
		for (i = 0; i < adapter->num_rx_queues; i++) {
			rsc_count += adapter->rx_ring[i]->rx_stats.rsc_count;
			rsc_flush += adapter->rx_ring[i]->rx_stats.rsc_flush;
		}
		adapter->rsc_total_count = rsc_count;
		adapter->rsc_total_flush = rsc_flush;
	}

	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
		alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
		hw_csum_rx_error += rx_ring->rx_stats.csum_err;
		bytes += rx_ring->stats.bytes;
		packets += rx_ring->stats.packets;
	}
	adapter->non_eop_descs = non_eop_descs;
	adapter->alloc_rx_page_failed = alloc_rx_page_failed;
	adapter->alloc_rx_buff_failed = alloc_rx_buff_failed;
	adapter->hw_csum_rx_error = hw_csum_rx_error;
	netdev->stats.rx_bytes = bytes;
	netdev->stats.rx_packets = packets;

	bytes = 0;
	packets = 0;
	/* gather some stats to the adapter struct that are per queue */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
		restart_queue += tx_ring->tx_stats.restart_queue;
		tx_busy += tx_ring->tx_stats.tx_busy;
		bytes += tx_ring->stats.bytes;
		packets += tx_ring->stats.packets;
	}
	adapter->restart_queue = restart_queue;
	adapter->tx_busy = tx_busy;
	netdev->stats.tx_bytes = bytes;
	netdev->stats.tx_packets = packets;

	hwstats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);

	/* 8 register reads */
	for (i = 0; i < 8; i++) {
		/* for packet buffers not used, the register should read 0 */
		mpc = IXGBE_READ_REG(hw, IXGBE_MPC(i));
		missed_rx += mpc;
		hwstats->mpc[i] += mpc;
		total_mpc += hwstats->mpc[i];
		hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i));
		hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i));
		switch (hw->mac.type) {
		case ixgbe_mac_82598EB:
			hwstats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i));
			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i));
			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i));
			hwstats->pxonrxc[i] +=
				IXGBE_READ_REG(hw, IXGBE_PXONRXC(i));
			break;
		case ixgbe_mac_82599EB:
		case ixgbe_mac_X540:
			hwstats->pxonrxc[i] +=
				IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
			break;
		default:
			break;
		}
	}

	/*16 register reads */
	for (i = 0; i < 16; i++) {
		hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
		hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
		if ((hw->mac.type == ixgbe_mac_82599EB) ||
		    (hw->mac.type == ixgbe_mac_X540)) {
			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i));
			IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */
			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i));
			IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)); /* to clear */
		}
	}

	hwstats->gprc += IXGBE_READ_REG(hw, IXGBE_GPRC);
	/* work around hardware counting issue */
	hwstats->gprc -= missed_rx;

	ixgbe_update_xoff_received(adapter);

	/* 82598 hardware only has a 32 bit counter in the high register */
	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXC);
		hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCH);
		hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH);
		hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORH);
		break;
	case ixgbe_mac_X540:
		/* OS2BMC stats are X540 only*/
		hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC);
		hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC);
		hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC);
		hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC);
	case ixgbe_mac_82599EB:
		for (i = 0; i < 16; i++)
			adapter->hw_rx_no_dma_resources +=
					     IXGBE_READ_REG(hw, IXGBE_QPRDC(i));
		hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL);
		IXGBE_READ_REG(hw, IXGBE_GORCH); /* to clear */
		hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCL);
		IXGBE_READ_REG(hw, IXGBE_GOTCH); /* to clear */
		hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORL);
		IXGBE_READ_REG(hw, IXGBE_TORH); /* to clear */
		hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXCNT);
		hwstats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH);
		hwstats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS);
#ifdef IXGBE_FCOE
		hwstats->fccrc += IXGBE_READ_REG(hw, IXGBE_FCCRC);
		hwstats->fcoerpdc += IXGBE_READ_REG(hw, IXGBE_FCOERPDC);
		hwstats->fcoeprc += IXGBE_READ_REG(hw, IXGBE_FCOEPRC);
		hwstats->fcoeptc += IXGBE_READ_REG(hw, IXGBE_FCOEPTC);
		hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC);
		hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC);
		/* Add up per cpu counters for total ddp aloc fail */
		if (adapter->fcoe.ddp_pool) {
			struct ixgbe_fcoe *fcoe = &adapter->fcoe;
			struct ixgbe_fcoe_ddp_pool *ddp_pool;
			unsigned int cpu;
			u64 noddp = 0, noddp_ext_buff = 0;
			for_each_possible_cpu(cpu) {
				ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu);
				noddp += ddp_pool->noddp;
				noddp_ext_buff += ddp_pool->noddp_ext_buff;
			}
			hwstats->fcoe_noddp = noddp;
			hwstats->fcoe_noddp_ext_buff = noddp_ext_buff;
		}
#endif /* IXGBE_FCOE */
		break;
	default:
		break;
	}
	bprc = IXGBE_READ_REG(hw, IXGBE_BPRC);
	hwstats->bprc += bprc;
	hwstats->mprc += IXGBE_READ_REG(hw, IXGBE_MPRC);
	if (hw->mac.type == ixgbe_mac_82598EB)
		hwstats->mprc -= bprc;
	hwstats->roc += IXGBE_READ_REG(hw, IXGBE_ROC);
	hwstats->prc64 += IXGBE_READ_REG(hw, IXGBE_PRC64);
	hwstats->prc127 += IXGBE_READ_REG(hw, IXGBE_PRC127);
	hwstats->prc255 += IXGBE_READ_REG(hw, IXGBE_PRC255);
	hwstats->prc511 += IXGBE_READ_REG(hw, IXGBE_PRC511);
	hwstats->prc1023 += IXGBE_READ_REG(hw, IXGBE_PRC1023);
	hwstats->prc1522 += IXGBE_READ_REG(hw, IXGBE_PRC1522);
	hwstats->rlec += IXGBE_READ_REG(hw, IXGBE_RLEC);
	lxon = IXGBE_READ_REG(hw, IXGBE_LXONTXC);
	hwstats->lxontxc += lxon;
	lxoff = IXGBE_READ_REG