summaryrefslogtreecommitdiffstats
path: root/drivers/net/hyperv/netvsc_drv.c
blob: 44142245343d95c753fe6c8b211cfdff0e606c9d (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
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/init.h>
#include <linux/atomic.h>
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/device.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/pci.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include <linux/netpoll.h>
#include <linux/bpf.h>

#include <net/arp.h>
#include <net/route.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>

#include "hyperv_net.h"

#define RING_SIZE_MIN	64

#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)

/* Macros to define the context of vf registration */
#define VF_REG_IN_PROBE		1
#define VF_REG_IN_NOTIFIER	2

static unsigned int ring_size __ro_after_init = 128;
module_param(ring_size, uint, 0444);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
unsigned int netvsc_ring_bytes __ro_after_init;

static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
				NETIF_MSG_LINK | NETIF_MSG_IFUP |
				NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
				NETIF_MSG_TX_ERR;

static int debug = -1;
module_param(debug, int, 0444);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");

static LIST_HEAD(netvsc_dev_list);

static void netvsc_change_rx_flags(struct net_device *net, int change)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
	int inc;

	if (!vf_netdev)
		return;

	if (change & IFF_PROMISC) {
		inc = (net->flags & IFF_PROMISC) ? 1 : -1;
		dev_set_promiscuity(vf_netdev, inc);
	}

	if (change & IFF_ALLMULTI) {
		inc = (net->flags & IFF_ALLMULTI) ? 1 : -1;
		dev_set_allmulti(vf_netdev, inc);
	}
}

static void netvsc_set_rx_mode(struct net_device *net)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct net_device *vf_netdev;
	struct netvsc_device *nvdev;

	rcu_read_lock();
	vf_netdev = rcu_dereference(ndev_ctx->vf_netdev);
	if (vf_netdev) {
		dev_uc_sync(vf_netdev, net);
		dev_mc_sync(vf_netdev, net);
	}

	nvdev = rcu_dereference(ndev_ctx->nvdev);
	if (nvdev)
		rndis_filter_update(nvdev);
	rcu_read_unlock();
}

static void netvsc_tx_enable(struct netvsc_device *nvscdev,
			     struct net_device *ndev)
{
	nvscdev->tx_disable = false;
	virt_wmb(); /* ensure queue wake up mechanism is on */

	netif_tx_wake_all_queues(ndev);
}

static int netvsc_open(struct net_device *net)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
	struct netvsc_device *nvdev = rtnl_dereference(ndev_ctx->nvdev);
	struct rndis_device *rdev;
	int ret = 0;

	netif_carrier_off(net);

	/* Open up the device */
	ret = rndis_filter_open(nvdev);
	if (ret != 0) {
		netdev_err(net, "unable to open device (ret %d).\n", ret);
		return ret;
	}

	rdev = nvdev->extension;
	if (!rdev->link_state) {
		netif_carrier_on(net);
		netvsc_tx_enable(nvdev, net);
	}

	if (vf_netdev) {
		/* Setting synthetic device up transparently sets
		 * slave as up. If open fails, then slave will be
		 * still be offline (and not used).
		 */
		ret = dev_open(vf_netdev, NULL);
		if (ret)
			netdev_warn(net,
				    "unable to open slave: %s: %d\n",
				    vf_netdev->name, ret);
	}
	return 0;
}

static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
{
	unsigned int retry = 0;
	int i;

	/* Ensure pending bytes in ring are read */
	for (;;) {
		u32 aread = 0;

		for (i = 0; i < nvdev->num_chn; i++) {
			struct vmbus_channel *chn
				= nvdev->chan_table[i].channel;

			if (!chn)
				continue;

			/* make sure receive not running now */
			napi_synchronize(&nvdev->chan_table[i].napi);

			aread = hv_get_bytes_to_read(&chn->inbound);
			if (aread)
				break;

			aread = hv_get_bytes_to_read(&chn->outbound);
			if (aread)
				break;
		}

		if (aread == 0)
			return 0;

		if (++retry > RETRY_MAX)
			return -ETIMEDOUT;

		usleep_range(RETRY_US_LO, RETRY_US_HI);
	}
}

static void netvsc_tx_disable(struct netvsc_device *nvscdev,
			      struct net_device *ndev)
{
	if (nvscdev) {
		nvscdev->tx_disable = true;
		virt_wmb(); /* ensure txq will not wake up after stop */
	}

	netif_tx_disable(ndev);
}

static int netvsc_close(struct net_device *net)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct net_device *vf_netdev
		= rtnl_dereference(net_device_ctx->vf_netdev);
	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
	int ret;

	netvsc_tx_disable(nvdev, net);

	/* No need to close rndis filter if it is removed already */
	if (!nvdev)
		return 0;

	ret = rndis_filter_close(nvdev);
	if (ret != 0) {
		netdev_err(net, "unable to close device (ret %d).\n", ret);
		return ret;
	}

	ret = netvsc_wait_until_empty(nvdev);
	if (ret)
		netdev_err(net, "Ring buffer not empty after closing rndis\n");

	if (vf_netdev)
		dev_close(vf_netdev);

	return ret;
}

static inline void *init_ppi_data(struct rndis_message *msg,
				  u32 ppi_size, u32 pkt_type)
{
	struct rndis_packet *rndis_pkt = &msg->msg.pkt;
	struct rndis_per_packet_info *ppi;

	rndis_pkt->data_offset += ppi_size;
	ppi = (void *)rndis_pkt + rndis_pkt->per_pkt_info_offset
		+ rndis_pkt->per_pkt_info_len;

	ppi->size = ppi_size;
	ppi->type = pkt_type;
	ppi->internal = 0;
	ppi->ppi_offset = sizeof(struct rndis_per_packet_info);

	rndis_pkt->per_pkt_info_len += ppi_size;

	return ppi + 1;
}

static inline int netvsc_get_tx_queue(struct net_device *ndev,
				      struct sk_buff *skb, int old_idx)
{
	const struct net_device_context *ndc = netdev_priv(ndev);
	struct sock *sk = skb->sk;
	int q_idx;

	q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) &
			      (VRSS_SEND_TAB_SIZE - 1)];

	/* If queue index changed record the new value */
	if (q_idx != old_idx &&
	    sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
		sk_tx_queue_set(sk, q_idx);

	return q_idx;
}

/*
 * Select queue for transmit.
 *
 * If a valid queue has already been assigned, then use that.
 * Otherwise compute tx queue based on hash and the send table.
 *
 * This is basically similar to default (netdev_pick_tx) with the added step
 * of using the host send_table when no other queue has been assigned.
 *
 * TODO support XPS - but get_xps_queue not exported
 */
static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
{
	int q_idx = sk_tx_queue_get(skb->sk);

	if (q_idx < 0 || skb->ooo_okay || q_idx >= ndev->real_num_tx_queues) {
		/* If forwarding a packet, we use the recorded queue when
		 * available for better cache locality.
		 */
		if (skb_rx_queue_recorded(skb))
			q_idx = skb_get_rx_queue(skb);
		else
			q_idx = netvsc_get_tx_queue(ndev, skb, q_idx);
	}

	return q_idx;
}

static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
			       struct net_device *sb_dev)
{
	struct net_device_context *ndc = netdev_priv(ndev);
	struct net_device *vf_netdev;
	u16 txq;

	rcu_read_lock();
	vf_netdev = rcu_dereference(ndc->vf_netdev);
	if (vf_netdev) {
		const struct net_device_ops *vf_ops = vf_netdev->netdev_ops;

		if (vf_ops->ndo_select_queue)
			txq = vf_ops->ndo_select_queue(vf_netdev, skb, sb_dev);
		else
			txq = netdev_pick_tx(vf_netdev, skb, NULL);

		/* Record the queue selected by VF so that it can be
		 * used for common case where VF has more queues than
		 * the synthetic device.
		 */
		qdisc_skb_cb(skb)->slave_dev_queue_mapping = txq;
	} else {
		txq = netvsc_pick_tx(ndev, skb);
	}
	rcu_read_unlock();

	while (txq >= ndev->real_num_tx_queues)
		txq -= ndev->real_num_tx_queues;

	return txq;
}

static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
		       struct hv_page_buffer *pb)
{
	int j = 0;

	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
	offset = offset & ~HV_HYP_PAGE_MASK;

	while (len > 0) {
		unsigned long bytes;

		bytes = HV_HYP_PAGE_SIZE - offset;
		if (bytes > len)
			bytes = len;
		pb[j].pfn = hvpfn;
		pb[j].offset = offset;
		pb[j].len = bytes;

		offset += bytes;
		len -= bytes;

		if (offset == HV_HYP_PAGE_SIZE && len) {
			hvpfn++;
			offset = 0;
			j++;
		}
	}

	return j + 1;
}

static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
			   struct hv_netvsc_packet *packet,
			   struct hv_page_buffer *pb)
{
	u32 slots_used = 0;
	char *data = skb->data;
	int frags = skb_shinfo(skb)->nr_frags;
	int i;

	/* The packet is laid out thus:
	 * 1. hdr: RNDIS header and PPI
	 * 2. skb linear data
	 * 3. skb fragment data
	 */
	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
				  offset_in_hvpage(hdr),
				  len,
				  &pb[slots_used]);

	packet->rmsg_size = len;
	packet->rmsg_pgcnt = slots_used;

	slots_used += fill_pg_buf(virt_to_hvpfn(data),
				  offset_in_hvpage(data),
				  skb_headlen(skb),
				  &pb[slots_used]);

	for (i = 0; i < frags; i++) {
		skb_frag_t *frag = skb_shinfo(skb)->frags + i;

		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
					  skb_frag_off(frag),
					  skb_frag_size(frag),
					  &pb[slots_used]);
	}
	return slots_used;
}

static int count_skb_frag_slots(struct sk_buff *skb)
{
	int i, frags = skb_shinfo(skb)->nr_frags;
	int pages = 0;

	for (i = 0; i < frags; i++) {
		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
		unsigned long size = skb_frag_size(frag);
		unsigned long offset = skb_frag_off(frag);

		/* Skip unused frames from start of page */
		offset &= ~HV_HYP_PAGE_MASK;
		pages += HVPFN_UP(offset + size);
	}
	return pages;
}

static int netvsc_get_slots(struct sk_buff *skb)
{
	char *data = skb->data;
	unsigned int offset = offset_in_hvpage(data);
	unsigned int len = skb_headlen(skb);
	int slots;
	int frag_slots;

	slots = DIV_ROUND_UP(offset + len, HV_HYP_PAGE_SIZE);
	frag_slots = count_skb_frag_slots(skb);
	return slots + frag_slots;
}

static u32 net_checksum_info(struct sk_buff *skb)
{
	if (skb->protocol == htons(ETH_P_IP)) {
		struct iphdr *ip = ip_hdr(skb);

		if (ip->protocol == IPPROTO_TCP)
			return TRANSPORT_INFO_IPV4_TCP;
		else if (ip->protocol == IPPROTO_UDP)
			return TRANSPORT_INFO_IPV4_UDP;
	} else {
		struct ipv6hdr *ip6 = ipv6_hdr(skb);

		if (ip6->nexthdr == IPPROTO_TCP)
			return TRANSPORT_INFO_IPV6_TCP;
		else if (ip6->nexthdr == IPPROTO_UDP)
			return TRANSPORT_INFO_IPV6_UDP;
	}

	return TRANSPORT_INFO_NOT_IP;
}

/* Send skb on the slave VF device. */
static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
			  struct sk_buff *skb)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	unsigned int len = skb->len;
	int rc;

	skb->dev = vf_netdev;
	skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);

	rc = dev_queue_xmit(skb);
	if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
		struct netvsc_vf_pcpu_stats *pcpu_stats
			= this_cpu_ptr(ndev_ctx->vf_stats);

		u64_stats_update_begin(&pcpu_stats->syncp);
		pcpu_stats->tx_packets++;
		pcpu_stats->tx_bytes += len;
		u64_stats_update_end(&pcpu_stats->syncp);
	} else {
		this_cpu_inc(ndev_ctx->vf_stats->tx_dropped);
	}

	return rc;
}

static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct hv_netvsc_packet *packet = NULL;
	int ret;
	unsigned int num_data_pgs;
	struct rndis_message *rndis_msg;
	struct net_device *vf_netdev;
	u32 rndis_msg_size;
	u32 hash;
	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];

	/* If VF is present and up then redirect packets to it.
	 * Skip the VF if it is marked down or has no carrier.
	 * If netpoll is in uses, then VF can not be used either.
	 */
	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
	if (vf_netdev && netif_running(vf_netdev) &&
	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net) &&
	    net_device_ctx->data_path_is_vf)
		return netvsc_vf_xmit(net, vf_netdev, skb);

	/* We will atmost need two pages to describe the rndis
	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
	 * of pages in a single packet. If skb is scattered around
	 * more pages we try linearizing it.
	 */

	num_data_pgs = netvsc_get_slots(skb) + 2;

	if (unlikely(num_data_pgs > MAX_PAGE_BUFFER_COUNT)) {
		++net_device_ctx->eth_stats.tx_scattered;

		if (skb_linearize(skb))
			goto no_memory;

		num_data_pgs = netvsc_get_slots(skb) + 2;
		if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
			++net_device_ctx->eth_stats.tx_too_big;
			goto drop;
		}
	}

	/*
	 * Place the rndis header in the skb head room and
	 * the skb->cb will be used for hv_netvsc_packet
	 * structure.
	 */
	ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
	if (ret)
		goto no_memory;

	/* Use the skb control buffer for building up the packet */
	BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
			sizeof_field(struct sk_buff, cb));
	packet = (struct hv_netvsc_packet *)skb->cb;

	packet->q_idx = skb_get_queue_mapping(skb);

	packet->total_data_buflen = skb->len;
	packet->total_bytes = skb->len;
	packet->total_packets = 1;

	rndis_msg = (struct rndis_message *)skb->head;

	/* Add the rndis header */
	rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
	rndis_msg->msg_len = packet->total_data_buflen;

	rndis_msg->msg.pkt = (struct rndis_packet) {
		.data_offset = sizeof(struct rndis_packet),
		.data_len = packet->total_data_buflen,
		.per_pkt_info_offset = sizeof(struct rndis_packet),
	};

	rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);

	hash = skb_get_hash_raw(skb);
	if (hash != 0 && net->real_num_tx_queues > 1) {
		u32 *hash_info;

		rndis_msg_size += NDIS_HASH_PPI_SIZE;
		hash_info = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
					  NBL_HASH_VALUE);
		*hash_info = hash;
	}

	/* When using AF_PACKET we need to drop VLAN header from
	 * the frame and update the SKB to allow the HOST OS
	 * to transmit the 802.1Q packet
	 */
	if (skb->protocol == htons(ETH_P_8021Q)) {
		u16 vlan_tci;

		skb_reset_mac_header(skb);
		if (eth_type_vlan(eth_hdr(skb)->h_proto)) {
			if (unlikely(__skb_vlan_pop(skb, &vlan_tci) != 0)) {
				++net_device_ctx->eth_stats.vlan_error;
				goto drop;
			}

			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
			/* Update the NDIS header pkt lengths */
			packet->total_data_buflen -= VLAN_HLEN;
			packet->total_bytes -= VLAN_HLEN;
			rndis_msg->msg_len = packet->total_data_buflen;
			rndis_msg->msg.pkt.data_len = packet->total_data_buflen;
		}
	}

	if (skb_vlan_tag_present(skb)) {
		struct ndis_pkt_8021q_info *vlan;

		rndis_msg_size += NDIS_VLAN_PPI_SIZE;
		vlan = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
				     IEEE_8021Q_INFO);

		vlan->value = 0;
		vlan->vlanid = skb_vlan_tag_get_id(skb);
		vlan->cfi = skb_vlan_tag_get_cfi(skb);
		vlan->pri = skb_vlan_tag_get_prio(skb);
	}

	if (skb_is_gso(skb)) {
		struct ndis_tcp_lso_info *lso_info;

		rndis_msg_size += NDIS_LSO_PPI_SIZE;
		lso_info = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
					 TCP_LARGESEND_PKTINFO);

		lso_info->value = 0;
		lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
		if (skb->protocol == htons(ETH_P_IP)) {
			lso_info->lso_v2_transmit.ip_version =
				NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4;
			ip_hdr(skb)->tot_len = 0;
			ip_hdr(skb)->check = 0;
			tcp_hdr(skb)->check =
				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
						   ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
		} else {
			lso_info->lso_v2_transmit.ip_version =
				NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6;
			tcp_v6_gso_csum_prep(skb);
		}
		lso_info->lso_v2_transmit.tcp_header_offset = skb_transport_offset(skb);
		lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
		if (net_checksum_info(skb) & net_device_ctx->tx_checksum_mask) {
			struct ndis_tcp_ip_checksum_info *csum_info;

			rndis_msg_size += NDIS_CSUM_PPI_SIZE;
			csum_info = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
						  TCPIP_CHKSUM_PKTINFO);

			csum_info->value = 0;
			csum_info->transmit.tcp_header_offset = skb_transport_offset(skb);

			if (skb->protocol == htons(ETH_P_IP)) {
				csum_info->transmit.is_ipv4 = 1;

				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
					csum_info->transmit.tcp_checksum = 1;
				else
					csum_info->transmit.udp_checksum = 1;
			} else {
				csum_info->transmit.is_ipv6 = 1;

				if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
					csum_info->transmit.tcp_checksum = 1;
				else
					csum_info->transmit.udp_checksum = 1;
			}
		} else {
			/* Can't do offload of this type of checksum */
			if (skb_checksum_help(skb))
				goto drop;
		}
	}

	/* Start filling in the page buffers with the rndis hdr */
	rndis_msg->msg_len += rndis_msg_size;
	packet->total_data_buflen = rndis_msg->msg_len;
	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
					       skb, packet, pb);

	/* timestamp packet in software */
	skb_tx_timestamp(skb);

	ret = netvsc_send(net, packet, rndis_msg, pb, skb, xdp_tx);
	if (likely(ret == 0))
		return NETDEV_TX_OK;

	if (ret == -EAGAIN) {
		++net_device_ctx->eth_stats.tx_busy;
		return NETDEV_TX_BUSY;
	}

	if (ret == -ENOSPC)
		++net_device_ctx->eth_stats.tx_no_space;

drop:
	dev_kfree_skb_any(skb);
	net->stats.tx_dropped++;

	return NETDEV_TX_OK;

no_memory:
	++net_device_ctx->eth_stats.tx_no_memory;
	goto drop;
}

static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb,
				     struct net_device *ndev)
{
	return netvsc_xmit(skb, ndev, false);
}

/*
 * netvsc_linkstatus_callback - Link up/down notification
 */
void netvsc_linkstatus_callback(struct net_device *net,
				struct rndis_message *resp,
				void *data, u32 data_buflen)
{
	struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct netvsc_reconfig *event;
	unsigned long flags;

	/* Ensure the packet is big enough to access its fields */
	if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) {
		netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n",
			   resp->msg_len);
		return;
	}

	/* Copy the RNDIS indicate status into nvchan->recv_buf */
	memcpy(indicate, data + RNDIS_HEADER_SIZE, sizeof(*indicate));

	/* Update the physical link speed when changing to another vSwitch */
	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
		u32 speed;

		/* Validate status_buf_offset and status_buflen.
		 *
		 * Certain (pre-Fe) implementations of Hyper-V's vSwitch didn't account
		 * for the status buffer field in resp->msg_len; perform the validation
		 * using data_buflen (>= resp->msg_len).
		 */
		if (indicate->status_buflen < sizeof(speed) ||
		    indicate->status_buf_offset < sizeof(*indicate) ||
		    data_buflen - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
		    data_buflen - RNDIS_HEADER_SIZE - indicate->status_buf_offset
				< indicate->status_buflen) {
			netdev_err(net, "invalid rndis_indicate_status packet\n");
			return;
		}

		speed = *(u32 *)(data + RNDIS_HEADER_SIZE + indicate->status_buf_offset) / 10000;
		ndev_ctx->speed = speed;
		return;
	}

	/* Handle these link change statuses below */
	if (indicate->status != RNDIS_STATUS_NETWORK_CHANGE &&
	    indicate->status != RNDIS_STATUS_MEDIA_CONNECT &&
	    indicate->status != RNDIS_STATUS_MEDIA_DISCONNECT)
		return;

	if (net->reg_state != NETREG_REGISTERED)
		return;

	event = kzalloc(sizeof(*event), GFP_ATOMIC);
	if (!event)
		return;
	event->event = indicate->status;

	spin_lock_irqsave(&ndev_ctx->lock, flags);
	list_add_tail(&event->list, &ndev_ctx->reconfig_events);
	spin_unlock_irqrestore(&ndev_ctx->lock, flags);

	schedule_delayed_work(&ndev_ctx->dwork, 0);
}

/* This function should only be called after skb_record_rx_queue() */
void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev)
{
	int rc;

	skb->queue_mapping = skb_get_rx_queue(skb);
	__skb_push(skb, ETH_HLEN);

	rc = netvsc_xmit(skb, ndev, true);

	if (dev_xmit_complete(rc))
		return;

	dev_kfree_skb_any(skb);
	ndev->stats.tx_dropped++;
}

static void netvsc_comp_ipcsum(struct sk_buff *skb)
{
	struct iphdr *iph = (struct iphdr *)skb->data;

	iph->check = 0;
	iph->check = ip_fast_csum(iph, iph->ihl);
}

static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
					     struct netvsc_channel *nvchan,
					     struct xdp_buff *xdp)
{
	struct napi_struct *napi = &nvchan->napi;
	const struct ndis_pkt_8021q_info *vlan = &nvchan->rsc.vlan;
	const struct ndis_tcp_ip_checksum_info *csum_info =
						&nvchan->rsc.csum_info;
	const u32 *hash_info = &nvchan->rsc.hash_info;
	u8 ppi_flags = nvchan->rsc.ppi_flags;
	struct sk_buff *skb;
	void *xbuf = xdp->data_hard_start;
	int i;

	if (xbuf) {
		unsigned int hdroom = xdp->data - xdp->data_hard_start;
		unsigned int xlen = xdp->data_end - xdp->data;
		unsigned int frag_size = xdp->frame_sz;

		skb = build_skb(xbuf, frag_size);

		if (!skb) {
			__free_page(virt_to_page(xbuf));
			return NULL;
		}

		skb_reserve(skb, hdroom);
		skb_put(skb, xlen);
		skb->dev = napi->dev;
	} else {
		skb = napi_alloc_skb(napi, nvchan->rsc.pktlen);

		if (!skb)
			return NULL;

		/* Copy to skb. This copy is needed here since the memory
		 * pointed by hv_netvsc_packet cannot be deallocated.
		 */
		for (i = 0; i < nvchan->rsc.cnt; i++)
			skb_put_data(skb, nvchan->rsc.data[i],
				     nvchan->rsc.len[i]);
	}

	skb->protocol = eth_type_trans(skb, net);

	/* skb is already created with CHECKSUM_NONE */
	skb_checksum_none_assert(skb);

	/* Incoming packets may have IP header checksum verified by the host.
	 * They may not have IP header checksum computed after coalescing.
	 * We compute it here if the flags are set, because on Linux, the IP
	 * checksum is always checked.
	 */
	if ((ppi_flags & NVSC_RSC_CSUM_INFO) && csum_info->receive.ip_checksum_value_invalid &&
	    csum_info->receive.ip_checksum_succeeded &&
	    skb->protocol == htons(ETH_P_IP)) {
		/* Check that there is enough space to hold the IP header. */
		if (skb_headlen(skb) < sizeof(struct iphdr)) {
			kfree_skb(skb);
			return NULL;
		}
		netvsc_comp_ipcsum(skb);
	}

	/* Do L4 checksum offload if enabled and present. */
	if ((ppi_flags & NVSC_RSC_CSUM_INFO) && (net->features & NETIF_F_RXCSUM)) {
		if (csum_info->receive.tcp_checksum_succeeded ||
		    csum_info->receive.udp_checksum_succeeded)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	if ((ppi_flags & NVSC_RSC_HASH_INFO) && (net->features & NETIF_F_RXHASH))
		skb_set_hash(skb, *hash_info, PKT_HASH_TYPE_L4);

	if (ppi_flags & NVSC_RSC_VLAN) {
		u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT) |
			(vlan->cfi ? VLAN_CFI_MASK : 0);

		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
				       vlan_tci);
	}

	return skb;
}

/*
 * netvsc_recv_callback -  Callback when we receive a packet from the
 * "wire" on the specified device.
 */
int netvsc_recv_callback(struct net_device *net,
			 struct netvsc_device *net_device,
			 struct netvsc_channel *nvchan)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct vmbus_channel *channel = nvchan->channel;
	u16 q_idx = channel->offermsg.offer.sub_channel_index;
	struct sk_buff *skb;
	struct netvsc_stats_rx *rx_stats = &nvchan->rx_stats;
	struct xdp_buff xdp;
	u32 act;

	if (net->reg_state != NETREG_REGISTERED)
		return NVSP_STAT_FAIL;

	act = netvsc_run_xdp(net, nvchan, &xdp);

	if (act == XDP_REDIRECT)
		return NVSP_STAT_SUCCESS;

	if (act != XDP_PASS && act != XDP_TX) {
		u64_stats_update_begin(&rx_stats->syncp);
		rx_stats->xdp_drop++;
		u64_stats_update_end(&rx_stats->syncp);

		return NVSP_STAT_SUCCESS; /* consumed by XDP */
	}

	/* Allocate a skb - TODO direct I/O to pages? */
	skb = netvsc_alloc_recv_skb(net, nvchan, &xdp);

	if (unlikely(!skb)) {
		++net_device_ctx->eth_stats.rx_no_memory;
		return NVSP_STAT_FAIL;
	}

	skb_record_rx_queue(skb, q_idx);

	/*
	 * Even if injecting the packet, record the statistics
	 * on the synthetic device because modifying the VF device
	 * statistics will not work correctly.
	 */
	u64_stats_update_begin(&rx_stats->syncp);
	if (act == XDP_TX)
		rx_stats->xdp_tx++;

	rx_stats->packets++;
	rx_stats->bytes += nvchan->rsc.pktlen;

	if (skb->pkt_type == PACKET_BROADCAST)
		++rx_stats->broadcast;
	else if (skb->pkt_type == PACKET_MULTICAST)
		++rx_stats->multicast;
	u64_stats_update_end(&rx_stats->syncp);

	if (act == XDP_TX) {
		netvsc_xdp_xmit(skb, net);
		return NVSP_STAT_SUCCESS;
	}

	napi_gro_receive(&nvchan->napi, skb);
	return NVSP_STAT_SUCCESS;
}

static void netvsc_get_drvinfo(struct net_device *net,
			       struct ethtool_drvinfo *info)
{
	strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
	strscpy(info->fw_version, "N/A", sizeof(info->fw_version));
}

static void netvsc_get_channels(struct net_device *net,
				struct ethtool_channels *channel)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);

	if (nvdev) {
		channel->max_combined	= nvdev->max_chn;
		channel->combined_count = nvdev->num_chn;
	}
}

/* Alloc struct netvsc_device_info, and initialize it from either existing
 * struct netvsc_device, or from default values.
 */
static
struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev)
{
	struct netvsc_device_info *dev_info;
	struct bpf_prog *prog;

	dev_info = kzalloc(sizeof(*dev_info), GFP_ATOMIC);

	if (!dev_info)
		return NULL;

	if (nvdev) {
		ASSERT_RTNL();

		dev_info->num_chn = nvdev->num_chn;
		dev_info->send_sections = nvdev->send_section_cnt;
		dev_info->send_section_size = nvdev->send_section_size;
		dev_info->recv_sections = nvdev->recv_section_cnt;
		dev_info->recv_section_size = nvdev->recv_section_size;

		memcpy(dev_info->rss_key, nvdev->extension->rss_key,
		       NETVSC_HASH_KEYLEN);

		prog = netvsc_xdp_get(nvdev);
		if (prog) {
			bpf_prog_inc(prog);
			dev_info->bprog = prog;
		}
	} else {
		dev_info->num_chn = VRSS_CHANNEL_DEFAULT;
		dev_info->send_sections = NETVSC_DEFAULT_TX;
		dev_info->send_section_size = NETVSC_SEND_SECTION_SIZE;
		dev_info->recv_sections = NETVSC_DEFAULT_RX;
		dev_info->recv_section_size = NETVSC_RECV_SECTION_SIZE;
	}

	return dev_info;
}

/* Free struct netvsc_device_info */
static void netvsc_devinfo_put(struct netvsc_device_info *dev_info)
{
	if (dev_info->bprog) {
		ASSERT_RTNL();
		bpf_prog_put(dev_info->bprog);
	}

	kfree(dev_info);
}

static int netvsc_detach(struct net_device *ndev,
			 struct netvsc_device *nvdev)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct hv_device *hdev = ndev_ctx->device_ctx;
	int ret;

	/* Don't try continuing to try and setup sub channels */
	if (cancel_work_sync(&nvdev->subchan_work))
		nvdev->num_chn = 1;

	netvsc_xdp_set(ndev, NULL, NULL, nvdev);

	/* If device was up (receiving) then shutdown */
	if (netif_running(ndev)) {
		netvsc_tx_disable(nvdev, ndev);

		ret = rndis_filter_close(nvdev);
		if (ret) {
			netdev_err(ndev,
				   "unable to close device (ret %d).\n", ret);
			return ret;
		}

		ret = netvsc_wait_until_empty(nvdev);
		if (ret) {
			netdev_err(ndev,
				   "Ring buffer not empty after closing rndis\n");
			return ret;
		}
	}

	netif_device_detach(ndev);

	rndis_filter_device_remove(hdev, nvdev);

	return 0;
}

static int netvsc_attach(struct net_device *ndev,
			 struct netvsc_device_info *dev_info)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct hv_device *hdev = ndev_ctx->device_ctx;
	struct netvsc_device *nvdev;
	struct rndis_device *rdev;
	struct bpf_prog *prog;
	int ret = 0;

	nvdev = rndis_filter_device_add(hdev, dev_info);
	if (IS_ERR(nvdev))
		return PTR_ERR(nvdev);

	if (nvdev->num_chn > 1) {
		ret = rndis_set_subchannel(ndev, nvdev, dev_info);

		/* if unavailable, just proceed with one queue */
		if (ret) {
			nvdev->max_chn = 1;
			nvdev->num_chn = 1;
		}
	}

	prog = dev_info->bprog;
	if (prog) {
		bpf_prog_inc(prog);
		ret = netvsc_xdp_set(ndev, prog, NULL, nvdev);
		if (ret) {
			bpf_prog_put(prog);
			goto err1;
		}
	}

	/* In any case device is now ready */
	nvdev->tx_disable = false;
	netif_device_attach(ndev);

	/* Note: enable and attach happen when sub-channels setup */
	netif_carrier_off(ndev);

	if (netif_running(ndev)) {
		ret = rndis_filter_open(nvdev);
		if (ret)
			goto err2;

		rdev = nvdev->extension;
		if (!rdev->link_state)
			netif_carrier_on(ndev);
	}

	return 0;

err2:
	netif_device_detach(ndev);

err1:
	rndis_filter_device_remove(hdev, nvdev);

	return ret;
}

static int netvsc_set_channels(struct net_device *net,
			       struct ethtool_channels *channels)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
	unsigned int orig, count = channels->combined_count;
	struct netvsc_device_info *device_info;
	int ret;

	/* We do not support separate count for rx, tx, or other */
	if (count == 0 ||
	    channels->rx_count || channels->tx_count || channels->other_count)
		return -EINVAL;

	if (!nvdev || nvdev->destroy)
		return -ENODEV;

	if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
		return -EINVAL;

	if (count > nvdev->max_chn)
		return -EINVAL;

	orig = nvdev->num_chn;

	device_info = netvsc_devinfo_get(nvdev);

	if (!device_info)
		return -ENOMEM;

	device_info->num_chn = count;

	ret = netvsc_detach(net, nvdev);
	if (ret)
		goto out;

	ret = netvsc_attach(net, device_info);
	if (ret) {
		device_info->num_chn = orig;
		if (netvsc_attach(net, device_info))
			netdev_err(net, "restoring channel setting failed\n");
	}

out:
	netvsc_devinfo_put(device_info);
	return ret;
}

static void netvsc_init_settings(struct net_device *dev)
{
	struct net_device_context *ndc = netdev_priv(dev);

	ndc->l4_hash = HV_DEFAULT_L4HASH;

	ndc->speed = SPEED_UNKNOWN;
	ndc->duplex = DUPLEX_FULL;

	dev->features = NETIF_F_LRO;
}

static int netvsc_get_link_ksettings(struct net_device *dev,
				     struct ethtool_link_ksettings *cmd)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct net_device *vf_netdev;

	vf_netdev = rtnl_dereference(ndc->vf_netdev);

	if (vf_netdev)
		return __ethtool_get_link_ksettings(vf_netdev, cmd);

	cmd->base.speed = ndc->speed;
	cmd->base.duplex = ndc->duplex;
	cmd->base.port = PORT_OTHER;

	return 0;
}

static int netvsc_set_link_ksettings(struct net_device *dev,
				     const struct ethtool_link_ksettings *cmd)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct net_device *vf_netdev = rtnl_dereference(ndc->vf_netdev);

	if (vf_netdev) {
		if (!vf_netdev->ethtool_ops->set_link_ksettings)
			return -EOPNOTSUPP;

		return vf_netdev->ethtool_ops->set_link_ksettings(vf_netdev,
								  cmd);
	}

	return ethtool_virtdev_set_link_ksettings(dev, cmd,
						  &ndc->speed, &ndc->duplex);
}

static int netvsc_change_mtu(struct net_device *ndev, int mtu)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
	int orig_mtu = ndev->mtu;
	struct netvsc_device_info *device_info;
	int ret = 0;

	if (!nvdev || nvdev->destroy)
		return -ENODEV;

	device_info = netvsc_devinfo_get(nvdev);

	if (!device_info)
		return -ENOMEM;

	/* Change MTU of underlying VF netdev first. */
	if (vf_netdev) {
		ret = dev_set_mtu(vf_netdev, mtu);
		if (ret)
			goto out;
	}

	ret = netvsc_detach(ndev, nvdev);
	if (ret)
		goto rollback_vf;

	WRITE_ONCE(ndev->mtu, mtu);

	ret = netvsc_attach(ndev, device_info);
	if (!ret)
		goto out;

	/* Attempt rollback to original MTU */
	WRITE_ONCE(ndev->mtu, orig_mtu);

	if (netvsc_attach(ndev, device_info))
		netdev_err(ndev, "restoring mtu failed\n");
rollback_vf:
	if (vf_netdev)
		dev_set_mtu(vf_netdev, orig_mtu);

out:
	netvsc_devinfo_put(device_info);
	return ret;
}

static void netvsc_get_vf_stats(struct net_device *net,
				struct netvsc_vf_pcpu_stats *tot)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	int i;

	memset(tot, 0, sizeof(*tot));

	for_each_possible_cpu(i) {
		const struct netvsc_vf_pcpu_stats *stats
			= per_cpu_ptr(ndev_ctx->vf_stats, i);
		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
		unsigned int start;

		do {
			start = u64_stats_fetch_begin(&stats->syncp);
			rx_packets = stats->rx_packets;
			tx_packets = stats->tx_packets;
			rx_bytes = stats->rx_bytes;
			tx_bytes = stats->tx_bytes;
		} while (u64_stats_fetch_retry(&stats->syncp, start));

		tot->rx_packets += rx_packets;
		tot->tx_packets += tx_packets;
		tot->rx_bytes   += rx_bytes;
		tot->tx_bytes   += tx_bytes;
		tot->tx_dropped += stats->tx_dropped;
	}
}

static void netvsc_get_pcpu_stats(struct net_device *net,
				  struct netvsc_ethtool_pcpu_stats *pcpu_tot)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
	int i;

	/* fetch percpu stats of vf */
	for_each_possible_cpu(i) {
		const struct netvsc_vf_pcpu_stats *stats =
			per_cpu_ptr(ndev_ctx->vf_stats, i);
		struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
		unsigned int start;

		do {
			start = u64_stats_fetch_begin(&stats->syncp);
			this_tot->vf_rx_packets = stats->rx_packets;
			this_tot->vf_tx_packets = stats->tx_packets;
			this_tot->vf_rx_bytes = stats->rx_bytes;
			this_tot->vf_tx_bytes = stats->tx_bytes;
		} while (u64_stats_fetch_retry(&stats->syncp, start));
		this_tot->rx_packets = this_tot->vf_rx_packets;
		this_tot->tx_packets = this_tot->vf_tx_packets;
		this_tot->rx_bytes   = this_tot->vf_rx_bytes;
		this_tot->tx_bytes   = this_tot->vf_tx_bytes;
	}

	/* fetch percpu stats of netvsc */
	for (i = 0; i < nvdev->num_chn; i++) {
		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
		const struct netvsc_stats_tx *tx_stats;
		const struct netvsc_stats_rx *rx_stats;
		struct netvsc_ethtool_pcpu_stats *this_tot =
			&pcpu_tot[nvchan->channel->target_cpu];
		u64 packets, bytes;
		unsigned int start;

		tx_stats = &nvchan->tx_stats;
		do {
			start = u64_stats_fetch_begin(&tx_stats->syncp);
			packets = tx_stats->packets;
			bytes = tx_stats->bytes;
		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));

		this_tot->tx_bytes	+= bytes;
		this_tot->tx_packets	+= packets;

		rx_stats = &nvchan->rx_stats;
		do {
			start = u64_stats_fetch_begin(&rx_stats->syncp);
			packets = rx_stats->packets;
			bytes = rx_stats->bytes;
		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));

		this_tot->rx_bytes	+= bytes;
		this_tot->rx_packets	+= packets;
	}
}

static void netvsc_get_stats64(struct net_device *net,
			       struct rtnl_link_stats64 *t)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct netvsc_device *nvdev;
	struct netvsc_vf_pcpu_stats vf_tot;
	int i;

	rcu_read_lock();

	nvdev = rcu_dereference(ndev_ctx->nvdev);
	if (!nvdev)
		goto out;

	netdev_stats_to_stats64(t, &net->stats);

	netvsc_get_vf_stats(net, &vf_tot);
	t->rx_packets += vf_tot.rx_packets;
	t->tx_packets += vf_tot.tx_packets;
	t->rx_bytes   += vf_tot.rx_bytes;
	t->tx_bytes   += vf_tot.tx_bytes;
	t->tx_dropped += vf_tot.tx_dropped;

	for (i = 0; i < nvdev->num_chn; i++) {
		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
		const struct netvsc_stats_tx *tx_stats;
		const struct netvsc_stats_rx *rx_stats;
		u64 packets, bytes, multicast;
		unsigned int start;

		tx_stats = &nvchan->tx_stats;
		do {
			start = u64_stats_fetch_begin(&tx_stats->syncp);
			packets = tx_stats->packets;
			bytes = tx_stats->bytes;
		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));

		t->tx_bytes	+= bytes;
		t->tx_packets	+= packets;

		rx_stats = &nvchan->rx_stats;
		do {
			start = u64_stats_fetch_begin(&rx_stats->syncp);
			packets = rx_stats->packets;
			bytes = rx_stats->bytes;
			multicast = rx_stats->multicast + rx_stats->broadcast;
		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));

		t->rx_bytes	+= bytes;
		t->rx_packets	+= packets;
		t->multicast	+= multicast;
	}
out:
	rcu_read_unlock();
}

static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
{
	struct net_device_context *ndc = netdev_priv(ndev);
	struct net_device *vf_netdev = rtnl_dereference(ndc->vf_netdev);
	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
	struct sockaddr *addr = p;
	int err;

	err = eth_prepare_mac_addr_change(ndev, p);
	if (err)
		return err;

	if (!nvdev)
		return -ENODEV;

	if (vf_netdev) {
		err = dev_set_mac_address(vf_netdev, addr, NULL);
		if (err)
			return err;
	}

	err = rndis_filter_set_device_mac(nvdev, addr->sa_data);
	if (!err) {
		eth_commit_mac_addr_change(ndev, p);
	} else if (vf_netdev) {
		/* rollback change on VF */
		memcpy(addr->sa_data, ndev->dev_addr, ETH_ALEN);
		dev_set_mac_address(vf_netdev, addr, NULL);
	}

	return err;
}

static const struct {
	char name[ETH_GSTRING_LEN];
	u16 offset;
} netvsc_stats[] = {
	{ "tx_scattered", offsetof(struct netvsc_ethtool_stats, tx_scattered) },
	{ "tx_no_memory", offsetof(struct netvsc_ethtool_stats, tx_no_memory) },
	{ "tx_no_space",  offsetof(struct netvsc_ethtool_stats, tx_no_space) },
	{ "tx_too_big",	  offsetof(struct netvsc_ethtool_stats, tx_too_big) },
	{ "tx_busy",	  offsetof(struct netvsc_ethtool_stats, tx_busy) },
	{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
	{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
	{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
	{ "vlan_error", offsetof(struct netvsc_ethtool_stats, vlan_error) },
}, pcpu_stats[] = {
	{ "cpu%u_rx_packets",
		offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
	{ "cpu%u_rx_bytes",
		offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
	{ "cpu%u_tx_packets",
		offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
	{ "cpu%u_tx_bytes",
		offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
	{ "cpu%u_vf_rx_packets",
		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
	{ "cpu%u_vf_rx_bytes",
		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
	{ "cpu%u_vf_tx_packets",
		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
	{ "cpu%u_vf_tx_bytes",
		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
}, vf_stats[] = {
	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
	{ "vf_tx_packets", offsetof(struct netvsc_vf_pcpu_stats, tx_packets) },
	{ "vf_tx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, tx_bytes) },
	{ "vf_tx_dropped", offsetof(struct netvsc_vf_pcpu_stats, tx_dropped) },
};

#define NETVSC_GLOBAL_STATS_LEN	ARRAY_SIZE(netvsc_stats)
#define NETVSC_VF_STATS_LEN	ARRAY_SIZE(vf_stats)

/* statistics per queue (rx/tx packets/bytes) */
#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))

/* 8 statistics per queue (rx/tx packets/bytes, XDP actions) */
#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 8)

static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);

	if (!nvdev)
		return -ENODEV;

	switch (string_set) {
	case ETH_SS_STATS:
		return NETVSC_GLOBAL_STATS_LEN
			+ NETVSC_VF_STATS_LEN
			+ NETVSC_QUEUE_STATS_LEN(nvdev)
			+ NETVSC_PCPU_STATS_LEN;
	default:
		return -EINVAL;
	}
}

static void netvsc_get_ethtool_stats(struct net_device *dev,
				     struct ethtool_stats *stats, u64 *data)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
	const void *nds = &ndc->eth_stats;
	const struct netvsc_stats_tx *tx_stats;
	const struct netvsc_stats_rx *rx_stats;
	struct netvsc_vf_pcpu_stats sum;
	struct netvsc_ethtool_pcpu_stats *pcpu_sum;
	unsigned int start;
	u64 packets, bytes;
	u64 xdp_drop;
	u64 xdp_redirect;
	u64 xdp_tx;
	u64 xdp_xmit;
	int i, j, cpu;

	if (!nvdev)
		return;

	for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
		data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);

	netvsc_get_vf_stats(dev, &sum);
	for (j = 0; j < NETVSC_VF_STATS_LEN; j++)
		data[i++] = *(u64 *)((void *)&sum + vf_stats[j].offset);

	for (j = 0; j < nvdev->num_chn; j++) {
		tx_stats = &nvdev->chan_table[j].tx_stats;

		do {
			start = u64_stats_fetch_begin(&tx_stats->syncp);
			packets = tx_stats->packets;
			bytes = tx_stats->bytes;
			xdp_xmit = tx_stats->xdp_xmit;
		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
		data[i++] = packets;
		data[i++] = bytes;
		data[i++] = xdp_xmit;

		rx_stats = &nvdev->chan_table[j].rx_stats;
		do {
			start = u64_stats_fetch_begin(&rx_stats->syncp);
			packets = rx_stats->packets;
			bytes = rx_stats->bytes;
			xdp_drop = rx_stats->xdp_drop;
			xdp_redirect = rx_stats->xdp_redirect;
			xdp_tx = rx_stats->xdp_tx;
		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
		data[i++] = packets;
		data[i++] = bytes;
		data[i++] = xdp_drop;
		data[i++] = xdp_redirect;
		data[i++] = xdp_tx;
	}

	pcpu_sum = kvmalloc_array(num_possible_cpus(),
				  sizeof(struct netvsc_ethtool_pcpu_stats),
				  GFP_KERNEL);
	if (!pcpu_sum)
		return;

	netvsc_get_pcpu_stats(dev, pcpu_sum);
	for_each_present_cpu(cpu) {
		struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];

		for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
			data[i++] = *(u64 *)((void *)this_sum
					     + pcpu_stats[j].offset);
	}
	kvfree(pcpu_sum);
}

static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
	u8 *p = data;
	int i, cpu;

	if (!nvdev)
		return;

	switch (stringset) {
	case ETH_SS_STATS:
		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
			ethtool_puts(&p, netvsc_stats[i].name);

		for (i = 0; i < ARRAY_SIZE(vf_stats); i++)
			ethtool_puts(&p, vf_stats[i].name);

		for (i = 0; i < nvdev->num_chn; i++) {
			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
			ethtool_sprintf(&p, "tx_queue_%u_xdp_xmit", i);
			ethtool_sprintf(&p, "rx_queue_%u_packets", i);
			ethtool_sprintf(&p, "rx_queue_%u_bytes", i);
			ethtool_sprintf(&p, "rx_queue_%u_xdp_drop", i);
			ethtool_sprintf(&p, "rx_queue_%u_xdp_redirect", i);
			ethtool_sprintf(&p, "rx_queue_%u_xdp_tx", i);
		}

		for_each_present_cpu(cpu) {
			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++)
				ethtool_sprintf(&p, pcpu_stats[i].name, cpu);
		}

		break;
	}
}

static int
netvsc_get_rss_hash_opts(struct net_device_context *ndc,
			 struct ethtool_rxnfc *info)
{
	const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;

	info->data = RXH_IP_SRC | RXH_IP_DST;

	switch (info->flow_type) {
	case TCP_V4_FLOW:
		if (ndc->l4_hash & HV_TCP4_L4HASH)
			info->data |= l4_flag;

		break;

	case TCP_V6_FLOW:
		if (ndc->l4_hash & HV_TCP6_L4HASH)
			info->data |= l4_flag;

		break;

	case UDP_V4_FLOW:
		if (ndc->l4_hash & HV_UDP4_L4HASH)
			info->data |= l4_flag;

		break;

	case UDP_V6_FLOW:
		if (ndc->l4_hash & HV_UDP6_L4HASH)
			info->data |= l4_flag;

		break;

	case IPV4_FLOW:
	case IPV6_FLOW:
		break;
	default:
		info->data = 0;
		break;
	}

	return 0;
}

static int
netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
		 u32 *rules)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);

	if (!nvdev)
		return -ENODEV;

	switch (info->cmd) {
	case ETHTOOL_GRXRINGS:
		info->data = nvdev->num_chn;
		return 0;

	case ETHTOOL_GRXFH:
		return netvsc_get_rss_hash_opts(ndc, info);
	}
	return -EOPNOTSUPP;
}

static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
				    struct ethtool_rxnfc *info)
{
	if (info->data == (RXH_IP_SRC | RXH_IP_DST |
			   RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
		switch (info->flow_type) {
		case TCP_V4_FLOW:
			ndc->l4_hash |= HV_TCP4_L4HASH;
			break;

		case TCP_V6_FLOW:
			ndc->l4_hash |= HV_TCP6_L4HASH;
			break;

		case UDP_V4_FLOW:
			ndc->l4_hash |= HV_UDP4_L4HASH;
			break;

		case UDP_V6_FLOW:
			ndc->l4_hash |= HV_UDP6_L4HASH;
			break;

		default:
			return -EOPNOTSUPP;
		}

		return 0;
	}

	if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
		switch (info->flow_type) {
		case TCP_V4_FLOW:
			ndc->l4_hash &= ~HV_TCP4_L4HASH;
			break;

		case TCP_V6_FLOW:
			ndc->l4_hash &= ~HV_TCP6_L4HASH;
			break;

		case UDP_V4_FLOW:
			ndc->l4_hash &= ~HV_UDP4_L4HASH;
			break;

		case UDP_V6_FLOW:
			ndc->l4_hash &= ~HV_UDP6_L4HASH;
			break;

		default:
			return -EOPNOTSUPP;
		}

		return 0;
	}

	return -EOPNOTSUPP;
}

static int
netvsc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *info)
{
	struct net_device_context *ndc = netdev_priv(ndev);

	if (info->cmd == ETHTOOL_SRXFH)
		return netvsc_set_rss_hash_opts(ndc, info);

	return -EOPNOTSUPP;
}

static u32 netvsc_get_rxfh_key_size(struct net_device *dev)
{
	return NETVSC_HASH_KEYLEN;
}

static u32 netvsc_rss_indir_size(struct net_device *dev)
{
	struct net_device_context *ndc = netdev_priv(dev);

	return ndc->rx_table_sz;
}

static int netvsc_get_rxfh(struct net_device *dev,
			   struct ethtool_rxfh_param *rxfh)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
	struct rndis_device *rndis_dev;
	int i;

	if (!ndev)
		return -ENODEV;

	rxfh->hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */

	rndis_dev = ndev->extension;
	if (rxfh->indir) {
		for (i = 0; i < ndc->rx_table_sz; i++)
			rxfh->indir[i] = ndc->rx_table[i];
	}

	if (rxfh->key)
		memcpy(rxfh->key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);

	return 0;
}

static int netvsc_set_rxfh(struct net_device *dev,
			   struct ethtool_rxfh_param *rxfh,
			   struct netlink_ext_ack *extack)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
	struct rndis_device *rndis_dev;
	u8 *key = rxfh->key;
	int i;

	if (!ndev)
		return -ENODEV;

	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
	    rxfh->hfunc != ETH_RSS_HASH_TOP)
		return -EOPNOTSUPP;

	rndis_dev = ndev->extension;
	if (rxfh->indir) {
		for (i = 0; i < ndc->rx_table_sz; i++)
			if (rxfh->indir[i] >= ndev->num_chn)
				return -EINVAL;

		for (i = 0; i < ndc->rx_table_sz; i++)
			ndc->rx_table[i] = rxfh->indir[i];
	}

	if (!key) {
		if (!rxfh->indir)
			return 0;

		key = rndis_dev->rss_key;
	}

	return rndis_filter_set_rss_param(rndis_dev, key);
}

/* Hyper-V RNDIS protocol does not have ring in the HW sense.
 * It does have pre-allocated receive area which is divided into sections.
 */
static void __netvsc_get_ringparam(struct netvsc_device *nvdev,
				   struct ethtool_ringparam *ring)
{
	u32 max_buf_size;

	ring->rx_pending = nvdev->recv_section_cnt;
	ring->tx_pending = nvdev->send_section_cnt;

	if (nvdev->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
		max_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
	else
		max_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;

	ring->rx_max_pending = max_buf_size / nvdev->recv_section_size;
	ring->tx_max_pending = NETVSC_SEND_BUFFER_SIZE
		/ nvdev->send_section_size;
}

static void netvsc_get_ringparam(struct net_device *ndev,
				 struct ethtool_ringparam *ring,
				 struct kernel_ethtool_ringparam *kernel_ring,
				 struct netlink_ext_ack *extack)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);

	if (!nvdev)
		return;

	__netvsc_get_ringparam(nvdev, ring);
}

static int netvsc_set_ringparam(struct net_device *ndev,
				struct ethtool_ringparam *ring,
				struct kernel_ethtool_ringparam *kernel_ring,
				struct netlink_ext_ack *extack)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
	struct netvsc_device_info *device_info;
	struct ethtool_ringparam orig;
	u32 new_tx, new_rx;
	int ret = 0;

	if (!nvdev || nvdev->destroy)
		return -ENODEV;

	memset(&orig, 0, sizeof(orig));
	__netvsc_get_ringparam(nvdev, &orig);

	new_tx = clamp_t(u32, ring->tx_pending,
			 NETVSC_MIN_TX_SECTIONS, orig.tx_max_pending);
	new_rx = clamp_t(u32, ring->rx_pending,
			 NETVSC_MIN_RX_SECTIONS, orig.rx_max_pending);

	if (new_tx == orig.tx_pending &&
	    new_rx == orig.rx_pending)
		return 0;	 /* no change */

	device_info = netvsc_devinfo_get(nvdev);

	if (!device_info)
		return -ENOMEM;

	device_info->send_sections = new_tx;
	device_info->recv_sections = new_rx;

	ret = netvsc_detach(ndev, nvdev);
	if (ret)
		goto out;

	ret = netvsc_attach(ndev, device_info);
	if (ret) {
		device_info->send_sections = orig.tx_pending;
		device_info->recv_sections = orig.rx_pending;

		if (netvsc_attach(ndev, device_info))
			netdev_err(ndev, "restoring ringparam failed");
	}

out:
	netvsc_devinfo_put(device_info);
	return ret;
}

static netdev_features_t netvsc_fix_features(struct net_device *ndev,
					     netdev_features_t features)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);

	if (!nvdev || nvdev->destroy)
		return features;

	if ((features & NETIF_F_LRO) && netvsc_xdp_get(nvdev)) {
		features ^= NETIF_F_LRO;
		netdev_info(ndev, "Skip LRO - unsupported with XDP\n");
	}

	return features;
}

static int netvsc_set_features(struct net_device *ndev,
			       netdev_features_t features)
{
	netdev_features_t change = features ^ ndev->features;
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
	struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
	struct ndis_offload_params offloads;
	int ret = 0;

	if (!nvdev || nvdev->destroy)
		return -ENODEV;

	if (!(change & NETIF_F_LRO))
		goto syncvf;

	memset(&offloads, 0, sizeof(struct ndis_offload_params));

	if (features & NETIF_F_LRO) {
		offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED;
		offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED;
	} else {
		offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED;
		offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED;
	}

	ret = rndis_filter_set_offload_params(ndev, nvdev, &offloads);

	if (ret) {
		features ^= NETIF_F_LRO;
		ndev->features = features;
	}

syncvf:
	if (!vf_netdev)
		return ret;

	vf_netdev->wanted_features = features;
	netdev_update_features(vf_netdev);

	return ret;
}

static int netvsc_get_regs_len(struct net_device *netdev)
{
	return VRSS_SEND_TAB_SIZE * sizeof(u32);
}

static void netvsc_get_regs(struct net_device *netdev,
			    struct ethtool_regs *regs, void *p)
{
	struct net_device_context *ndc = netdev_priv(netdev);
	u32 *regs_buff = p;

	/* increase the version, if buffer format is changed. */
	regs->version = 1;

	memcpy(regs_buff, ndc->tx_table, VRSS_SEND_TAB_SIZE * sizeof(u32));
}

static u32 netvsc_get_msglevel(struct net_device *ndev)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);

	return ndev_ctx->msg_enable;
}

static void netvsc_set_msglevel(struct net_device *ndev, u32 val)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);

	ndev_ctx->msg_enable = val;
}

static const struct ethtool_ops ethtool_ops = {
	.get_drvinfo	= netvsc_get_drvinfo,
	.get_regs_len	= netvsc_get_regs_len,
	.get_regs	= netvsc_get_regs,
	.get_msglevel	= netvsc_get_msglevel,
	.set_msglevel	= netvsc_set_msglevel,
	.get_link	= ethtool_op_get_link,
	.get_ethtool_stats = netvsc_get_ethtool_stats,
	.get_sset_count = netvsc_get_sset_count,
	.get_strings	= netvsc_get_strings,
	.get_channels   = netvsc_get_channels,
	.set_channels   = netvsc_set_channels,
	.get_ts_info	= ethtool_op_get_ts_info,
	.get_rxnfc	= netvsc_get_rxnfc,
	.set_rxnfc	= netvsc_set_rxnfc,
	.get_rxfh_key_size = netvsc_get_rxfh_key_size,
	.get_rxfh_indir_size = netvsc_rss_indir_size,
	.get_rxfh	= netvsc_get_rxfh,
	.set_rxfh	= netvsc_set_rxfh,
	.get_link_ksettings = netvsc_get_link_ksettings,
	.set_link_ksettings = netvsc_set_link_ksettings,
	.get_ringparam	= netvsc_get_ringparam,
	.set_ringparam	= netvsc_set_ringparam,
};

static const struct net_device_ops device_ops = {
	.ndo_open =			netvsc_open,
	.ndo_stop =			netvsc_close,
	.ndo_start_xmit =		netvsc_start_xmit,
	.ndo_change_rx_flags =		netvsc_change_rx_flags,
	.ndo_set_rx_mode =		netvsc_set_rx_mode,
	.ndo_fix_features =		netvsc_fix_features,
	.ndo_set_features =		netvsc_set_features,
	.ndo_change_mtu =		netvsc_change_mtu,
	.ndo_validate_addr =		eth_validate_addr,
	.ndo_set_mac_address =		netvsc_set_mac_addr,
	.ndo_select_queue =		netvsc_select_queue,
	.ndo_get_stats64 =		netvsc_get_stats64,
	.ndo_bpf =			netvsc_bpf,
	.ndo_xdp_xmit =			netvsc_ndoxdp_xmit,
};

/*
 * Handle link status changes. For RNDIS_STATUS_NETWORK_CHANGE emulate link
 * down/up sequence. In case of RNDIS_STATUS_MEDIA_CONNECT when carrier is
 * present send GARP packet to network peers with netif_notify_peers().
 */
static void netvsc_link_change(struct work_struct *w)
{
	struct net_device_context *ndev_ctx =
		container_of(w, struct net_device_context, dwork.work);
	struct hv_device *device_obj = ndev_ctx->device_ctx;
	struct net_device *net = hv_get_drvdata(device_obj);
	unsigned long flags, next_reconfig, delay;
	struct netvsc_reconfig *event = NULL;
	struct netvsc_device *net_device;
	struct rndis_device *rdev;
	bool reschedule = false;

	/* if changes are happening, comeback later */
	if (!rtnl_trylock()) {
		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
		return;
	}

	net_device = rtnl_dereference(ndev_ctx->nvdev);
	if (!net_device)
		goto out_unlock;

	rdev = net_device->extension;

	next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
	if (time_is_after_jiffies(next_reconfig)) {
		/* link_watch only sends one notification with current state
		 * per second, avoid doing reconfig more frequently. Handle
		 * wrap around.
		 */
		delay = next_reconfig - jiffies;
		delay = delay < LINKCHANGE_INT ? delay : LINKCHANGE_INT;
		schedule_delayed_work(&ndev_ctx->dwork, delay);
		goto out_unlock;
	}
	ndev_ctx->last_reconfig = jiffies;

	spin_lock_irqsave(&ndev_ctx->lock, flags);
	if (!list_empty(&ndev_ctx->reconfig_events)) {
		event = list_first_entry(&ndev_ctx->reconfig_events,
					 struct netvsc_reconfig, list);
		list_del(&event->list);
		reschedule = !list_empty(&ndev_ctx->reconfig_events);
	}
	spin_unlock_irqrestore(&ndev_ctx->lock, flags);

	if (!event)
		goto out_unlock;

	switch (event->event) {
		/* Only the following events are possible due to the check in
		 * netvsc_linkstatus_callback()
		 */
	case RNDIS_STATUS_MEDIA_CONNECT:
		if (rdev->link_state) {
			rdev->link_state = false;
			netif_carrier_on(net);
			netvsc_tx_enable(net_device, net);
		} else {
			__netdev_notify_peers(net);
		}
		kfree(event);
		break;
	case RNDIS_STATUS_MEDIA_DISCONNECT:
		if (!rdev->link_state) {
			rdev->link_state = true;
			netif_carrier_off(net);
			netvsc_tx_disable(net_device, net);
		}
		kfree(event);
		break;
	case RNDIS_STATUS_NETWORK_CHANGE:
		/* Only makes sense if carrier is present */
		if (!rdev->link_state) {
			rdev->link_state = true;
			netif_carrier_off(net);
			netvsc_tx_disable(net_device, net);
			event->event = RNDIS_STATUS_MEDIA_CONNECT;
			spin_lock_irqsave(&ndev_ctx->lock, flags);
			list_add(&event->list, &ndev_ctx->reconfig_events);
			spin_unlock_irqrestore(&ndev_ctx->lock, flags);
			reschedule = true;
		}
		break;
	}

	rtnl_unlock();

	/* link_watch only sends one notification with current state per
	 * second, handle next reconfig event in 2 seconds.
	 */
	if (reschedule)
		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);

	return;

out_unlock:
	rtnl_unlock();
}

static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
{
	struct net_device_context *net_device_ctx;
	struct net_device *dev;

	dev = netdev_master_upper_dev_get(vf_netdev);
	if (!dev || dev->netdev_ops != &device_ops)
		return NULL;	/* not a netvsc device */

	net_device_ctx = netdev_priv(dev);
	if (!rtnl_dereference(net_device_ctx->nvdev))
		return NULL;	/* device is removed */

	return dev;
}

/* Called when VF is injecting data into network stack.
 * Change the associated network device from VF to netvsc.
 * note: already called with rcu_read_lock
 */
static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
{
	struct sk_buff *skb = *pskb;
	struct net_device *ndev = rcu_dereference(skb->dev->rx_handler_data);
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct netvsc_vf_pcpu_stats *pcpu_stats
		 = this_cpu_ptr(ndev_ctx->vf_stats);

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (unlikely(!skb))
		return RX_HANDLER_CONSUMED;

	*pskb = skb;

	skb->dev = ndev;

	u64_stats_update_begin(&pcpu_stats->syncp);
	pcpu_stats->rx_packets++;
	pcpu_stats->rx_bytes += skb->len;
	u64_stats_update_end(&pcpu_stats->syncp);

	return RX_HANDLER_ANOTHER;
}

static int netvsc_vf_join(struct net_device *vf_netdev,
			  struct net_device *ndev, int context)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	int ret;

	ret = netdev_rx_handler_register(vf_netdev,
					 netvsc_vf_handle_frame, ndev);
	if (ret != 0) {
		netdev_err(vf_netdev,
			   "can not register netvsc VF receive handler (err = %d)\n",
			   ret);
		goto rx_handler_failed;
	}

	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
					   NULL, NULL, NULL);
	if (ret != 0) {
		netdev_err(vf_netdev,
			   "can not set master device %s (err = %d)\n",
			   ndev->name, ret);
		goto upper_link_failed;
	}

	/* If this registration is called from probe context vf_takeover
	 * is taken care of later in probe itself.
	 */
	if (context == VF_REG_IN_NOTIFIER)
		schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);

	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);

	netdev_info(vf_netdev, "joined to %s\n", ndev->name);
	return 0;

upper_link_failed:
	netdev_rx_handler_unregister(vf_netdev);
rx_handler_failed:
	return ret;
}

static void __netvsc_vf_setup(struct net_device *ndev,
			      struct net_device *vf_netdev)
{
	int ret;

	/* Align MTU of VF with master */
	ret = dev_set_mtu(vf_netdev, ndev->mtu);
	if (ret)
		netdev_warn(vf_netdev,
			    "unable to change mtu to %u\n", ndev->mtu);

	/* set multicast etc flags on VF */
	dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE, NULL);

	/* sync address list from ndev to VF */
	netif_addr_lock_bh(ndev);
	dev_uc_sync(vf_netdev, ndev);
	dev_mc_sync(vf_netdev, ndev);
	netif_addr_unlock_bh(ndev);

	if (netif_running(ndev)) {
		ret = dev_open(vf_netdev, NULL);
		if (ret)
			netdev_warn(vf_netdev,
				    "unable to open: %d\n", ret);
	}
}

/* Setup VF as slave of the synthetic device.
 * Runs in workqueue to avoid recursion in netlink callbacks.
 */
static void netvsc_vf_setup(struct work_struct *w)
{
	struct net_device_context *ndev_ctx
		= container_of(w, struct net_device_context, vf_takeover.work);
	struct net_device *ndev = hv_get_drvdata(ndev_ctx->device_ctx);
	struct net_device *vf_netdev;

	if (!rtnl_trylock()) {
		schedule_delayed_work(&ndev_ctx->vf_takeover, 0);
		return;
	}

	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
	if (vf_netdev)
		__netvsc_vf_setup(ndev, vf_netdev);

	rtnl_unlock();
}

/* Find netvsc by VF serial number.
 * The PCI hyperv controller records the serial number as the slot kobj name.
 */
static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
{
	struct device *parent = vf_netdev->dev.parent;
	struct net_device_context *ndev_ctx;
	struct net_device *ndev;
	struct pci_dev *pdev;
	u32 serial;

	if (!parent || !dev_is_pci(parent))
		return NULL; /* not a PCI device */

	pdev = to_pci_dev(parent);
	if (!pdev->slot) {
		netdev_notice(vf_netdev, "no PCI slot information\n");
		return NULL;
	}

	if (kstrtou32(pci_slot_name(pdev->slot), 10, &serial)) {
		netdev_notice(vf_netdev, "Invalid vf serial:%s\n",
			      pci_slot_name(pdev->slot));
		return NULL;
	}

	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
		if (!ndev_ctx->vf_alloc)
			continue;

		if (ndev_ctx->vf_serial != serial)
			continue;

		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
		if (ndev->addr_len != vf_netdev->addr_len ||
		    memcmp(ndev->perm_addr, vf_netdev->perm_addr,
			   ndev->addr_len) != 0)
			continue;

		return ndev;

	}

	/* Fallback path to check synthetic vf with help of mac addr.
	 * Because this function can be called before vf_netdev is
	 * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied
	 * from dev_addr, also try to match to its dev_addr.
	 * Note: On Hyper-V and Azure, it's not possible to set a MAC address
	 * on a VF that matches to the MAC of a unrelated NETVSC device.
	 */
	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) ||
		    ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr))
			return ndev;
	}

	netdev_notice(vf_netdev,
		      "no netdev found for vf serial:%u\n", serial);
	return NULL;
}

static int netvsc_prepare_bonding(struct net_device *vf_netdev)
{
	struct net_device *ndev;

	ndev = get_netvsc_byslot(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	/* set slave flag before open to prevent IPv6 addrconf */
	vf_netdev->flags |= IFF_SLAVE;
	return NOTIFY_DONE;
}

static int netvsc_register_vf(struct net_device *vf_netdev, int context)
{
	struct net_device_context *net_device_ctx;
	struct netvsc_device *netvsc_dev;
	struct bpf_prog *prog;
	struct net_device *ndev;
	int ret;

	if (vf_netdev->addr_len != ETH_ALEN)
		return NOTIFY_DONE;

	ndev = get_netvsc_byslot(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
		return NOTIFY_DONE;

	/* if synthetic interface is a different namespace,
	 * then move the VF to that namespace; join will be
	 * done again in that context.
	 */
	if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
		ret = dev_change_net_namespace(vf_netdev,
					       dev_net(ndev), "eth%d");
		if (ret)
			netdev_err(vf_netdev,
				   "could not move to same namespace as %s: %d\n",
				   ndev->name, ret);
		else
			netdev_info(vf_netdev,
				    "VF moved to namespace with: %s\n",
				    ndev->name);
		return NOTIFY_DONE;
	}

	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);

	if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
		return NOTIFY_DONE;

	dev_hold(vf_netdev);
	rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);

	if (ndev->needed_headroom < vf_netdev->needed_headroom)
		ndev->needed_headroom = vf_netdev->needed_headroom;

	vf_netdev->wanted_features = ndev->features;
	netdev_update_features(vf_netdev);

	prog = netvsc_xdp_get(netvsc_dev);
	netvsc_vf_setxdp(vf_netdev, prog);

	return NOTIFY_OK;
}

/* Change the data path when VF UP/DOWN/CHANGE are detected.
 *
 * Typically a UP or DOWN event is followed by a CHANGE event, so
 * net_device_ctx->data_path_is_vf is used to cache the current data path
 * to avoid the duplicate call of netvsc_switch_datapath() and the duplicate
 * message.
 *
 * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network
 * interface, there is only the CHANGE event and no UP or DOWN event.
 */
static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
{
	struct net_device_context *net_device_ctx;
	struct netvsc_device *netvsc_dev;
	struct net_device *ndev;
	bool vf_is_up = false;
	int ret;

	if (event != NETDEV_GOING_DOWN)
		vf_is_up = netif_running(vf_netdev);

	ndev = get_netvsc_byref(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
	if (!netvsc_dev)
		return NOTIFY_DONE;

	if (net_device_ctx->data_path_is_vf == vf_is_up)
		return NOTIFY_OK;

	if (vf_is_up && !net_device_ctx->vf_alloc) {
		netdev_info(ndev, "Waiting for the VF association from host\n");
		wait_for_completion(&net_device_ctx->vf_add);
	}

	ret = netvsc_switch_datapath(ndev, vf_is_up);

	if (ret) {
		netdev_err(ndev,
			   "Data path failed to switch %s VF: %s, err: %d\n",
			   vf_is_up ? "to" : "from", vf_netdev->name, ret);
		return NOTIFY_DONE;
	} else {
		netdev_info(ndev, "Data path switched %s VF: %s\n",
			    vf_is_up ? "to" : "from", vf_netdev->name);
	}

	return NOTIFY_OK;
}

static int netvsc_unregister_vf(struct net_device *vf_netdev)
{
	struct net_device *ndev;
	struct net_device_context *net_device_ctx;

	ndev = get_netvsc_byref(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	cancel_delayed_work_sync(&net_device_ctx->vf_takeover);

	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);

	netvsc_vf_setxdp(vf_netdev, NULL);

	reinit_completion(&net_device_ctx->vf_add);
	netdev_rx_handler_unregister(vf_netdev);
	netdev_upper_dev_unlink(vf_netdev, ndev);
	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
	dev_put(vf_netdev);

	ndev->needed_headroom = RNDIS_AND_PPI_SIZE;

	return NOTIFY_OK;
}

static int check_dev_is_matching_vf(struct net_device *event_ndev)
{
	/* Skip NetVSC interfaces */
	if (event_ndev->netdev_ops == &device_ops)
		return -ENODEV;

	/* Avoid non-Ethernet type devices */
	if (event_ndev->type != ARPHRD_ETHER)
		return -ENODEV;

	/* Avoid Vlan dev with same MAC registering as VF */
	if (is_vlan_dev(event_ndev))
		return -ENODEV;

	/* Avoid Bonding master dev with same MAC registering as VF */
	if (netif_is_bond_master(event_ndev))
		return -ENODEV;

	return 0;
}

static int netvsc_probe(struct hv_device *dev,
			const struct hv_vmbus_device_id *dev_id)
{
	struct net_device *net = NULL, *vf_netdev;
	struct net_device_context *net_device_ctx;
	struct netvsc_device_info *device_info = NULL;
	struct netvsc_device *nvdev;
	int ret = -ENOMEM;

	net = alloc_etherdev_mq(sizeof(struct net_device_context),
				VRSS_CHANNEL_MAX);
	if (!net)
		goto no_net;

	netif_carrier_off(net);

	netvsc_init_settings(net);

	net_device_ctx = netdev_priv(net);
	net_device_ctx->device_ctx = dev;
	net_device_ctx->msg_enable = netif_msg_init(debug, default_msg);
	if (netif_msg_probe(net_device_ctx))
		netdev_dbg(net, "netvsc msg_enable: %d\n",
			   net_device_ctx->msg_enable);

	hv_set_drvdata(dev, net);

	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);

	init_completion(&net_device_ctx->vf_add);
	spin_lock_init(&net_device_ctx->lock);
	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
	INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup);

	net_device_ctx->vf_stats
		= netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats);
	if (!net_device_ctx->vf_stats)
		goto no_stats;

	net->netdev_ops = &device_ops;
	net->ethtool_ops = &ethtool_ops;
	SET_NETDEV_DEV(net, &dev->device);
	dma_set_min_align_mask(&dev->device, HV_HYP_PAGE_SIZE - 1);

	/* We always need headroom for rndis header */
	net->needed_headroom = RNDIS_AND_PPI_SIZE;

	/* Initialize the number of queues to be 1, we may change it if more
	 * channels are offered later.
	 */
	netif_set_real_num_tx_queues(net, 1);
	netif_set_real_num_rx_queues(net, 1);

	/* Notify the netvsc driver of the new device */
	device_info = netvsc_devinfo_get(NULL);

	if (!device_info) {
		ret = -ENOMEM;
		goto devinfo_failed;
	}

	/* We must get rtnl lock before scheduling nvdev->subchan_work,
	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
	 * all subchannels to show up, but that may not happen because
	 * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer()
	 * -> ... -> device_add() -> ... -> __device_attach() can't get
	 * the device lock, so all the subchannels can't be processed --
	 * finally netvsc_subchan_work() hangs forever.
	 *
	 * The rtnl lock also needs to be held before rndis_filter_device_add()
	 * which advertises nvsp_2_vsc_capability / sriov bit, and triggers
	 * VF NIC offering and registering. If VF NIC finished register_netdev()
	 * earlier it may cause name based config failure.
	 */
	rtnl_lock();

	nvdev = rndis_filter_device_add(dev, device_info);
	if (IS_ERR(nvdev)) {
		ret = PTR_ERR(nvdev);
		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
		goto rndis_failed;
	}

	eth_hw_addr_set(net, device_info->mac_adr);

	if (nvdev->num_chn > 1)
		schedule_work(&nvdev->subchan_work);

	/* hw_features computed in rndis_netdev_set_hwcaps() */
	net->features = net->hw_features |
		NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX |
		NETIF_F_HW_VLAN_CTAG_RX;
	net->vlan_features = net->features;

	netdev_lockdep_set_classes(net);

	net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
			    NETDEV_XDP_ACT_NDO_XMIT;

	/* MTU range: 68 - 1500 or 65521 */
	net->min_mtu = NETVSC_MTU_MIN;
	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
		net->max_mtu = NETVSC_MTU - ETH_HLEN;
	else
		net->max_mtu = ETH_DATA_LEN;

	nvdev->tx_disable = false;

	ret = register_netdevice(net);
	if (ret != 0) {
		pr_err("Unable to register netdev.\n");
		goto register_failed;
	}

	list_add(&net_device_ctx->list, &netvsc_dev_list);

	/* When the hv_netvsc driver is unloaded and reloaded, the
	 * NET_DEVICE_REGISTER for the vf device is replayed before probe
	 * is complete. This is because register_netdevice_notifier() gets
	 * registered before vmbus_driver_register() so that callback func
	 * is set before probe and we don't miss events like NETDEV_POST_INIT
	 * So, in this section we try to register the matching vf device that
	 * is present as a netdevice, knowing that its register call is not
	 * processed in the netvsc_netdev_notifier(as probing is progress and
	 * get_netvsc_byslot fails).
	 */
	for_each_netdev(dev_net(net), vf_netdev) {
		ret = check_dev_is_matching_vf(vf_netdev);
		if (ret != 0)
			continue;

		if (net != get_netvsc_byslot(vf_netdev))
			continue;

		netvsc_prepare_bonding(vf_netdev);
		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
		__netvsc_vf_setup(net, vf_netdev);
		break;
	}
	rtnl_unlock();

	netvsc_devinfo_put(device_info);
	return 0;

register_failed:
	rndis_filter_device_remove(dev, nvdev);
rndis_failed:
	rtnl_unlock();
	netvsc_devinfo_put(device_info);
devinfo_failed:
	free_percpu(net_device_ctx->vf_stats);
no_stats:
	hv_set_drvdata(dev, NULL);
	free_netdev(net);
no_net:
	return ret;
}

static void netvsc_remove(struct hv_device *dev)
{
	struct net_device_context *ndev_ctx;
	struct net_device *vf_netdev, *net;
	struct netvsc_device *nvdev;

	net = hv_get_drvdata(dev);
	if (net == NULL) {
		dev_err(&dev->device, "No net device to remove\n");
		return;
	}

	ndev_ctx = netdev_priv(net);

	cancel_delayed_work_sync(&ndev_ctx->dwork);

	rtnl_lock();
	nvdev = rtnl_dereference(ndev_ctx->nvdev);
	if (nvdev) {
		cancel_work_sync(&nvdev->subchan_work);
		netvsc_xdp_set(net, NULL, NULL, nvdev);
	}

	/*
	 * Call to the vsc driver to let it know that the device is being
	 * removed. Also blocks mtu and channel changes.
	 */
	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
	if (vf_netdev)
		netvsc_unregister_vf(vf_netdev);

	if (nvdev)
		rndis_filter_device_remove(dev, nvdev);

	unregister_netdevice(net);
	list_del(&ndev_ctx->list);

	rtnl_unlock();

	hv_set_drvdata(dev, NULL);

	free_percpu(ndev_ctx->vf_stats);
	free_netdev(net);
}

static int netvsc_suspend(struct hv_device *dev)
{
	struct net_device_context *ndev_ctx;
	struct netvsc_device *nvdev;
	struct net_device *net;
	int ret;

	net = hv_get_drvdata(dev);

	ndev_ctx = netdev_priv(net);
	cancel_delayed_work_sync(&ndev_ctx->dwork);

	rtnl_lock();

	nvdev = rtnl_dereference(ndev_ctx->nvdev);
	if (nvdev == NULL) {
		ret = -ENODEV;
		goto out;
	}

	/* Save the current config info */
	ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);
	if (!ndev_ctx->saved_netvsc_dev_info) {
		ret = -ENOMEM;
		goto out;
	}
	ret = netvsc_detach(net, nvdev);
out:
	rtnl_unlock();

	return ret;
}

static int netvsc_resume(struct hv_device *dev)
{
	struct net_device *net = hv_get_drvdata(dev);
	struct net_device_context *net_device_ctx;
	struct netvsc_device_info *device_info;
	int ret;

	rtnl_lock();

	net_device_ctx = netdev_priv(net);

	/* Reset the data path to the netvsc NIC before re-opening the vmbus
	 * channel. Later netvsc_netdev_event() will switch the data path to
	 * the VF upon the UP or CHANGE event.
	 */
	net_device_ctx->data_path_is_vf = false;
	device_info = net_device_ctx->saved_netvsc_dev_info;

	ret = netvsc_attach(net, device_info);

	netvsc_devinfo_put(device_info);
	net_device_ctx->saved_netvsc_dev_info = NULL;

	rtnl_unlock();

	return ret;
}
static const struct hv_vmbus_device_id id_table[] = {
	/* Network guid */
	{ HV_NIC_GUID, },
	{ },
};

MODULE_DEVICE_TABLE(vmbus, id_table);

/* The one and only one */
static struct  hv_driver netvsc_drv = {
	.name = KBUILD_MODNAME,
	.id_table = id_table,
	.probe = netvsc_probe,
	.remove = netvsc_remove,
	.suspend = netvsc_suspend,
	.resume = netvsc_resume,
	.driver = {
		.probe_type = PROBE_FORCE_SYNCHRONOUS,
	},
};

/*
 * On Hyper-V, every VF interface is matched with a corresponding
 * synthetic interface. The synthetic interface is presented first
 * to the guest. When the corresponding VF instance is registered,
 * we will take care of switching the data path.
 */
static int netvsc_netdev_event(struct notifier_block *this,
			       unsigned long event, void *ptr)
{
	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
	int ret = 0;

	ret = check_dev_is_matching_vf(event_dev);
	if (ret != 0)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_POST_INIT:
		return netvsc_prepare_bonding(event_dev);
	case NETDEV_REGISTER:
		return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
	case NETDEV_UNREGISTER:
		return netvsc_unregister_vf(event_dev);
	case NETDEV_UP:
	case NETDEV_DOWN:
	case NETDEV_CHANGE:
	case NETDEV_GOING_DOWN:
		return netvsc_vf_changed(event_dev, event);
	default:
		return NOTIFY_DONE;
	}
}

static struct notifier_block netvsc_netdev_notifier = {
	.notifier_call = netvsc_netdev_event,
};

static void __exit netvsc_drv_exit(void)
{
	unregister_netdevice_notifier(&netvsc_netdev_notifier);
	vmbus_driver_unregister(&netvsc_drv);
}

static int __init netvsc_drv_init(void)
{
	int ret;

	if (ring_size < RING_SIZE_MIN) {
		ring_size = RING_SIZE_MIN;
		pr_info("Increased ring_size to %u (min allowed)\n",
			ring_size);
	}
	netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);

	register_netdevice_notifier(&netvsc_netdev_notifier);

	ret = vmbus_driver_register(&netvsc_drv);
	if (ret)
		goto err_vmbus_reg;

	return 0;

err_vmbus_reg:
	unregister_netdevice_notifier(&netvsc_netdev_notifier);
	return ret;
}

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Microsoft Hyper-V network driver");

module_init(netvsc_drv_init);
module_exit(netvsc_drv_exit);