summaryrefslogtreecommitdiffstats
path: root/drivers/net/virtio_net.c
blob: 511f8339fa963c300d41cfd2e27480ea43c6ed73 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
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
/* A network driver using virtio.
 *
 * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, see <http://www.gnu.org/licenses/>.
 */
//#define DEBUG
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_net.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/scatterlist.h>
#include <linux/if_vlan.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
#include <net/route.h>

static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);

static bool csum = true, gso = true, napi_tx;
module_param(csum, bool, 0444);
module_param(gso, bool, 0444);
module_param(napi_tx, bool, 0644);

/* FIXME: MTU in config. */
#define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
#define GOOD_COPY_LEN	128

#define VIRTNET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)

/* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
#define VIRTIO_XDP_HEADROOM 256

/* RX packet size EWMA. The average packet size is used to determine the packet
 * buffer size when refilling RX rings. As the entire RX ring may be refilled
 * at once, the weight is chosen so that the EWMA will be insensitive to short-
 * term, transient changes in packet size.
 */
DECLARE_EWMA(pkt_len, 0, 64)

#define VIRTNET_DRIVER_VERSION "1.0.0"

static const unsigned long guest_offloads[] = {
	VIRTIO_NET_F_GUEST_TSO4,
	VIRTIO_NET_F_GUEST_TSO6,
	VIRTIO_NET_F_GUEST_ECN,
	VIRTIO_NET_F_GUEST_UFO
};

struct virtnet_stats {
	struct u64_stats_sync tx_syncp;
	struct u64_stats_sync rx_syncp;
	u64 tx_bytes;
	u64 tx_packets;

	u64 rx_bytes;
	u64 rx_packets;
};

/* Internal representation of a send virtqueue */
struct send_queue {
	/* Virtqueue associated with this send _queue */
	struct virtqueue *vq;

	/* TX: fragments + linear part + virtio header */
	struct scatterlist sg[MAX_SKB_FRAGS + 2];

	/* Name of the send queue: output.$index */
	char name[40];

	struct napi_struct napi;
};

/* Internal representation of a receive virtqueue */
struct receive_queue {
	/* Virtqueue associated with this receive_queue */
	struct virtqueue *vq;

	struct napi_struct napi;

	struct bpf_prog __rcu *xdp_prog;

	/* Chain pages by the private ptr. */
	struct page *pages;

	/* Average packet length for mergeable receive buffers. */
	struct ewma_pkt_len mrg_avg_pkt_len;

	/* Page frag for packet buffer allocation. */
	struct page_frag alloc_frag;

	/* RX: fragments + linear part + virtio header */
	struct scatterlist sg[MAX_SKB_FRAGS + 2];

	/* Min single buffer size for mergeable buffers case. */
	unsigned int min_buf_len;

	/* Name of this receive queue: input.$index */
	char name[40];
};

struct virtnet_info {
	struct virtio_device *vdev;
	struct virtqueue *cvq;
	struct net_device *dev;
	struct send_queue *sq;
	struct receive_queue *rq;
	unsigned int status;

	/* Max # of queue pairs supported by the device */
	u16 max_queue_pairs;

	/* # of queue pairs currently used by the driver */
	u16 curr_queue_pairs;

	/* # of XDP queue pairs currently used by the driver */
	u16 xdp_queue_pairs;

	/* I like... big packets and I cannot lie! */
	bool big_packets;

	/* Host will merge rx buffers for big packets (shake it! shake it!) */
	bool mergeable_rx_bufs;

	/* Has control virtqueue */
	bool has_cvq;

	/* Host can handle any s/g split between our header and packet data */
	bool any_header_sg;

	/* Packet virtio header size */
	u8 hdr_len;

	/* Active statistics */
	struct virtnet_stats __percpu *stats;

	/* Work struct for refilling if we run low on memory. */
	struct delayed_work refill;

	/* Work struct for config space updates */
	struct work_struct config_work;

	/* Does the affinity hint is set for virtqueues? */
	bool affinity_hint_set;

	/* CPU hotplug instances for online & dead */
	struct hlist_node node;
	struct hlist_node node_dead;

	/* Control VQ buffers: protected by the rtnl lock */
	struct virtio_net_ctrl_hdr ctrl_hdr;
	virtio_net_ctrl_ack ctrl_status;
	struct virtio_net_ctrl_mq ctrl_mq;
	u8 ctrl_promisc;
	u8 ctrl_allmulti;
	u16 ctrl_vid;
	u64 ctrl_offloads;

	/* Ethtool settings */
	u8 duplex;
	u32 speed;

	unsigned long guest_offloads;
};

struct padded_vnet_hdr {
	struct virtio_net_hdr_mrg_rxbuf hdr;
	/*
	 * hdr is in a separate sg buffer, and data sg buffer shares same page
	 * with this header sg. This padding makes next sg 16 byte aligned
	 * after the header.
	 */
	char padding[4];
};

/* Converting between virtqueue no. and kernel tx/rx queue no.
 * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
 */
static int vq2txq(struct virtqueue *vq)
{
	return (vq->index - 1) / 2;
}

static int txq2vq(int txq)
{
	return txq * 2 + 1;
}

static int vq2rxq(struct virtqueue *vq)
{
	return vq->index / 2;
}

static int rxq2vq(int rxq)
{
	return rxq * 2;
}

static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb)
{
	return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb;
}

/*
 * private is used to chain pages for big packets, put the whole
 * most recent used list in the beginning for reuse
 */
static void give_pages(struct receive_queue *rq, struct page *page)
{
	struct page *end;

	/* Find end of list, sew whole thing into vi->rq.pages. */
	for (end = page; end->private; end = (struct page *)end->private);
	end->private = (unsigned long)rq->pages;
	rq->pages = page;
}

static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
{
	struct page *p = rq->pages;

	if (p) {
		rq->pages = (struct page *)p->private;
		/* clear private here, it is used to chain pages */
		p->private = 0;
	} else
		p = alloc_page(gfp_mask);
	return p;
}

static void virtqueue_napi_schedule(struct napi_struct *napi,
				    struct virtqueue *vq)
{
	if (napi_schedule_prep(napi)) {
		virtqueue_disable_cb(vq);
		__napi_schedule(napi);
	}
}

static void virtqueue_napi_complete(struct napi_struct *napi,
				    struct virtqueue *vq, int processed)
{
	int opaque;

	opaque = virtqueue_enable_cb_prepare(vq);
	if (napi_complete_done(napi, processed) &&
	    unlikely(virtqueue_poll(vq, opaque)))
		virtqueue_napi_schedule(napi, vq);
}

static void skb_xmit_done(struct virtqueue *vq)
{
	struct virtnet_info *vi = vq->vdev->priv;
	struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi;

	/* Suppress further interrupts. */
	virtqueue_disable_cb(vq);

	if (napi->weight)
		virtqueue_napi_schedule(napi, vq);
	else
		/* We were probably waiting for more output buffers. */
		netif_wake_subqueue(vi->dev, vq2txq(vq));
}

#define MRG_CTX_HEADER_SHIFT 22
static void *mergeable_len_to_ctx(unsigned int truesize,
				  unsigned int headroom)
{
	return (void *)(unsigned long)((headroom << MRG_CTX_HEADER_SHIFT) | truesize);
}

static unsigned int mergeable_ctx_to_headroom(void *mrg_ctx)
{
	return (unsigned long)mrg_ctx >> MRG_CTX_HEADER_SHIFT;
}

static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
{
	return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1);
}

/* Called from bottom half context */
static struct sk_buff *page_to_skb(struct virtnet_info *vi,
				   struct receive_queue *rq,
				   struct page *page, unsigned int offset,
				   unsigned int len, unsigned int truesize)
{
	struct sk_buff *skb;
	struct virtio_net_hdr_mrg_rxbuf *hdr;
	unsigned int copy, hdr_len, hdr_padded_len;
	char *p;

	p = page_address(page) + offset;

	/* copy small packet so we can reuse these pages for small data */
	skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN);
	if (unlikely(!skb))
		return NULL;

	hdr = skb_vnet_hdr(skb);

	hdr_len = vi->hdr_len;
	if (vi->mergeable_rx_bufs)
		hdr_padded_len = sizeof(*hdr);
	else
		hdr_padded_len = sizeof(struct padded_vnet_hdr);

	memcpy(hdr, p, hdr_len);

	len -= hdr_len;
	offset += hdr_padded_len;
	p += hdr_padded_len;

	copy = len;
	if (copy > skb_tailroom(skb))
		copy = skb_tailroom(skb);
	skb_put_data(skb, p, copy);

	len -= copy;
	offset += copy;

	if (vi->mergeable_rx_bufs) {
		if (len)
			skb_add_rx_frag(skb, 0, page, offset, len, truesize);
		else
			put_page(page);
		return skb;
	}

	/*
	 * Verify that we can indeed put this data into a skb.
	 * This is here to handle cases when the device erroneously
	 * tries to receive more than is possible. This is usually
	 * the case of a broken device.
	 */
	if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) {
		net_dbg_ratelimited("%s: too much data\n", skb->dev->name);
		dev_kfree_skb(skb);
		return NULL;
	}
	BUG_ON(offset >= PAGE_SIZE);
	while (len) {
		unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len);
		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset,
				frag_size, truesize);
		len -= frag_size;
		page = (struct page *)page->private;
		offset = 0;
	}

	if (page)
		give_pages(rq, page);

	return skb;
}

static bool virtnet_xdp_xmit(struct virtnet_info *vi,
			     struct receive_queue *rq,
			     struct xdp_buff *xdp)
{
	struct virtio_net_hdr_mrg_rxbuf *hdr;
	unsigned int len;
	struct send_queue *sq;
	unsigned int qp;
	void *xdp_sent;
	int err;

	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
	sq = &vi->sq[qp];

	/* Free up any pending old buffers before queueing new ones. */
	while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
		struct page *sent_page = virt_to_head_page(xdp_sent);

		put_page(sent_page);
	}

	xdp->data -= vi->hdr_len;
	/* Zero header and leave csum up to XDP layers */
	hdr = xdp->data;
	memset(hdr, 0, vi->hdr_len);

	sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);

	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp->data, GFP_ATOMIC);
	if (unlikely(err)) {
		struct page *page = virt_to_head_page(xdp->data);

		put_page(page);
		return false;
	}

	virtqueue_kick(sq->vq);
	return true;
}

static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
{
	return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
}

/* We copy the packet for XDP in the following cases:
 *
 * 1) Packet is scattered across multiple rx buffers.
 * 2) Headroom space is insufficient.
 *
 * This is inefficient but it's a temporary condition that
 * we hit right after XDP is enabled and until queue is refilled
 * with large buffers with sufficient headroom - so it should affect
 * at most queue size packets.
 * Afterwards, the conditions to enable
 * XDP should preclude the underlying device from sending packets
 * across multiple buffers (num_buf > 1), and we make sure buffers
 * have enough headroom.
 */
static struct page *xdp_linearize_page(struct receive_queue *rq,
				       u16 *num_buf,
				       struct page *p,
				       int offset,
				       int page_off,
				       unsigned int *len)
{
	struct page *page = alloc_page(GFP_ATOMIC);

	if (!page)
		return NULL;

	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
	page_off += *len;

	while (--*num_buf) {
		unsigned int buflen;
		void *buf;
		int off;

		buf = virtqueue_get_buf(rq->vq, &buflen);
		if (unlikely(!buf))
			goto err_buf;

		p = virt_to_head_page(buf);
		off = buf - page_address(p);

		/* guard against a misconfigured or uncooperative backend that
		 * is sending packet larger than the MTU.
		 */
		if ((page_off + buflen) > PAGE_SIZE) {
			put_page(p);
			goto err_buf;
		}

		memcpy(page_address(page) + page_off,
		       page_address(p) + off, buflen);
		page_off += buflen;
		put_page(p);
	}

	/* Headroom does not contribute to packet length */
	*len = page_off - VIRTIO_XDP_HEADROOM;
	return page;
err_buf:
	__free_pages(page, 0);
	return NULL;
}

static struct sk_buff *receive_small(struct net_device *dev,
				     struct virtnet_info *vi,
				     struct receive_queue *rq,
				     void *buf, void *ctx,
				     unsigned int len)
{
	struct sk_buff *skb;
	struct bpf_prog *xdp_prog;
	unsigned int xdp_headroom = (unsigned long)ctx;
	unsigned int header_offset = VIRTNET_RX_PAD + xdp_headroom;
	unsigned int headroom = vi->hdr_len + header_offset;
	unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
	struct page *page = virt_to_head_page(buf);
	unsigned int delta = 0;
	struct page *xdp_page;
	len -= vi->hdr_len;

	rcu_read_lock();
	xdp_prog = rcu_dereference(rq->xdp_prog);
	if (xdp_prog) {
		struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
		struct xdp_buff xdp;
		void *orig_data;
		u32 act;

		if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
			goto err_xdp;

		if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) {
			int offset = buf - page_address(page) + header_offset;
			unsigned int tlen = len + vi->hdr_len;
			u16 num_buf = 1;

			xdp_headroom = virtnet_get_headroom(vi);
			header_offset = VIRTNET_RX_PAD + xdp_headroom;
			headroom = vi->hdr_len + header_offset;
			buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
			xdp_page = xdp_linearize_page(rq, &num_buf, page,
						      offset, header_offset,
						      &tlen);
			if (!xdp_page)
				goto err_xdp;

			buf = page_address(xdp_page);
			put_page(page);
			page = xdp_page;
		}

		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
		xdp.data = xdp.data_hard_start + xdp_headroom;
		xdp.data_end = xdp.data + len;
		orig_data = xdp.data;
		act = bpf_prog_run_xdp(xdp_prog, &xdp);

		switch (act) {
		case XDP_PASS:
			/* Recalculate length in case bpf program changed it */
			delta = orig_data - xdp.data;
			break;
		case XDP_TX:
			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
				trace_xdp_exception(vi->dev, xdp_prog, act);
			rcu_read_unlock();
			goto xdp_xmit;
		default:
			bpf_warn_invalid_xdp_action(act);
		case XDP_ABORTED:
			trace_xdp_exception(vi->dev, xdp_prog, act);
		case XDP_DROP:
			goto err_xdp;
		}
	}
	rcu_read_unlock();

	skb = build_skb(buf, buflen);
	if (!skb) {
		put_page(page);
		goto err;
	}
	skb_reserve(skb, headroom - delta);
	skb_put(skb, len + delta);
	if (!delta) {
		buf += header_offset;
		memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
	} /* keep zeroed vnet hdr since packet was changed by bpf */

err:
	return skb;

err_xdp:
	rcu_read_unlock();
	dev->stats.rx_dropped++;
	put_page(page);
xdp_xmit:
	return NULL;
}

static struct sk_buff *receive_big(struct net_device *dev,
				   struct virtnet_info *vi,
				   struct receive_queue *rq,
				   void *buf,
				   unsigned int len)
{
	struct page *page = buf;
	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);

	if (unlikely(!skb))
		goto err;

	return skb;

err:
	dev->stats.rx_dropped++;
	give_pages(rq, page);
	return NULL;
}

static struct sk_buff *receive_mergeable(struct net_device *dev,
					 struct virtnet_info *vi,
					 struct receive_queue *rq,
					 void *buf,
					 void *ctx,
					 unsigned int len)
{
	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
	struct page *page = virt_to_head_page(buf);
	int offset = buf - page_address(page);
	struct sk_buff *head_skb, *curr_skb;
	struct bpf_prog *xdp_prog;
	unsigned int truesize;
	unsigned int headroom = mergeable_ctx_to_headroom(ctx);

	head_skb = NULL;

	rcu_read_lock();
	xdp_prog = rcu_dereference(rq->xdp_prog);
	if (xdp_prog) {
		struct page *xdp_page;
		struct xdp_buff xdp;
		void *data;
		u32 act;

		/* This happens when rx buffer size is underestimated */
		if (unlikely(num_buf > 1 ||
			     headroom < virtnet_get_headroom(vi))) {
			/* linearize data for XDP */
			xdp_page = xdp_linearize_page(rq, &num_buf,
						      page, offset,
						      VIRTIO_XDP_HEADROOM,
						      &len);
			if (!xdp_page)
				goto err_xdp;
			offset = VIRTIO_XDP_HEADROOM;
		} else {
			xdp_page = page;
		}

		/* Transient failure which in theory could occur if
		 * in-flight packets from before XDP was enabled reach
		 * the receive path after XDP is loaded. In practice I
		 * was not able to create this condition.
		 */
		if (unlikely(hdr->hdr.gso_type))
			goto err_xdp;

		/* Allow consuming headroom but reserve enough space to push
		 * the descriptor on if we get an XDP_TX return code.
		 */
		data = page_address(xdp_page) + offset;
		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
		xdp.data = data + vi->hdr_len;
		xdp.data_end = xdp.data + (len - vi->hdr_len);
		act = bpf_prog_run_xdp(xdp_prog, &xdp);

		switch (act) {
		case XDP_PASS:
			/* recalculate offset to account for any header
			 * adjustments. Note other cases do not build an
			 * skb and avoid using offset
			 */
			offset = xdp.data -
					page_address(xdp_page) - vi->hdr_len;

			/* We can only create skb based on xdp_page. */
			if (unlikely(xdp_page != page)) {
				rcu_read_unlock();
				put_page(page);
				head_skb = page_to_skb(vi, rq, xdp_page,
						       offset, len, PAGE_SIZE);
				ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
				return head_skb;
			}
			break;
		case XDP_TX:
			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
				trace_xdp_exception(vi->dev, xdp_prog, act);
			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
			if (unlikely(xdp_page != page))
				goto err_xdp;
			rcu_read_unlock();
			goto xdp_xmit;
		default:
			bpf_warn_invalid_xdp_action(act);
		case XDP_ABORTED:
			trace_xdp_exception(vi->dev, xdp_prog, act);
		case XDP_DROP:
			if (unlikely(xdp_page != page))
				__free_pages(xdp_page, 0);
			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
			goto err_xdp;
		}
	}
	rcu_read_unlock();

	truesize = mergeable_ctx_to_truesize(ctx);
	if (unlikely(len > truesize)) {
		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
			 dev->name, len, (unsigned long)ctx);
		dev->stats.rx_length_errors++;
		goto err_skb;
	}

	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
	curr_skb = head_skb;

	if (unlikely(!curr_skb))
		goto err_skb;
	while (--num_buf) {
		int num_skb_frags;

		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
		if (unlikely(!ctx)) {
			pr_debug("%s: rx error: %d buffers out of %d missing\n",
				 dev->name, num_buf,
				 virtio16_to_cpu(vi->vdev,
						 hdr->num_buffers));
			dev->stats.rx_length_errors++;
			goto err_buf;
		}

		page = virt_to_head_page(buf);

		truesize = mergeable_ctx_to_truesize(ctx);
		if (unlikely(len > truesize)) {
			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
				 dev->name, len, (unsigned long)ctx);
			dev->stats.rx_length_errors++;
			goto err_skb;
		}

		num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
		if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
			struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC);

			if (unlikely(!nskb))
				goto err_skb;
			if (curr_skb == head_skb)
				skb_shinfo(curr_skb)->frag_list = nskb;
			else
				curr_skb->next = nskb;
			curr_skb = nskb;
			head_skb->truesize += nskb->truesize;
			num_skb_frags = 0;
		}
		if (curr_skb != head_skb) {
			head_skb->data_len += len;
			head_skb->len += len;
			head_skb->truesize += truesize;
		}
		offset = buf - page_address(page);
		if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
			put_page(page);
			skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
					     len, truesize);
		} else {
			skb_add_rx_frag(curr_skb, num_skb_frags, page,
					offset, len, truesize);
		}
	}

	ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len);
	return head_skb;

err_xdp:
	rcu_read_unlock();
err_skb:
	put_page(page);
	while (--num_buf) {
		buf = virtqueue_get_buf(rq->vq, &len);
		if (unlikely(!buf)) {
			pr_debug("%s: rx error: %d buffers missing\n",
				 dev->name, num_buf);
			dev->stats.rx_length_errors++;
			break;
		}
		page = virt_to_head_page(buf);
		put_page(page);
	}
err_buf:
	dev->stats.rx_dropped++;
	dev_kfree_skb(head_skb);
xdp_xmit:
	return NULL;
}

static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
		       void *buf, unsigned int len, void **ctx)
{
	struct net_device *dev = vi->dev;
	struct sk_buff *skb;
	struct virtio_net_hdr_mrg_rxbuf *hdr;
	int ret;

	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
		pr_debug("%s: short packet %i\n", dev->name, len);
		dev->stats.rx_length_errors++;
		if (vi->mergeable_rx_bufs) {
			put_page(virt_to_head_page(buf));
		} else if (vi->big_packets) {
			give_pages(rq, buf);
		} else {
			put_page(virt_to_head_page(buf));
		}
		return 0;
	}

	if (vi->mergeable_rx_bufs)
		skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
	else if (vi->big_packets)
		skb = receive_big(dev, vi, rq, buf, len);
	else
		skb = receive_small(dev, vi, rq, buf, ctx, len);

	if (unlikely(!skb))
		return 0;

	hdr = skb_vnet_hdr(skb);

	ret = skb->len;

	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
				  virtio_is_little_endian(vi->vdev))) {
		net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n",
				     dev->name, hdr->hdr.gso_type,
				     hdr->hdr.gso_size);
		goto frame_err;
	}

	skb->protocol = eth_type_trans(skb, dev);
	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
		 ntohs(skb->protocol), skb->len, skb->pkt_type);

	napi_gro_receive(&rq->napi, skb);
	return ret;

frame_err:
	dev->stats.rx_frame_errors++;
	dev_kfree_skb(skb);
	return 0;
}

/* Unlike mergeable buffers, all buffers are allocated to the
 * same size, except for the headroom. For this reason we do
 * not need to use  mergeable_len_to_ctx here - it is enough
 * to store the headroom as the context ignoring the truesize.
 */
static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
			     gfp_t gfp)
{
	struct page_frag *alloc_frag = &rq->alloc_frag;
	char *buf;
	unsigned int xdp_headroom = virtnet_get_headroom(vi);
	void *ctx = (void *)(unsigned long)xdp_headroom;
	int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom;
	int err;

	len = SKB_DATA_ALIGN(len) +
	      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
		return -ENOMEM;

	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
	get_page(alloc_frag->page);
	alloc_frag->offset += len;
	sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom,
		    vi->hdr_len + GOOD_PACKET_LEN);
	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
	if (err < 0)
		put_page(virt_to_head_page(buf));
	return err;
}

static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
			   gfp_t gfp)
{
	struct page *first, *list = NULL;
	char *p;
	int i, err, offset;

	sg_init_table(rq->sg, MAX_SKB_FRAGS + 2);

	/* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
		first = get_a_page(rq, gfp);
		if (!first) {
			if (list)
				give_pages(rq, list);
			return -ENOMEM;
		}
		sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE);

		/* chain new page in list head to match sg */
		first->private = (unsigned long)list;
		list = first;
	}

	first = get_a_page(rq, gfp);
	if (!first) {
		give_pages(rq, list);
		return -ENOMEM;
	}
	p = page_address(first);

	/* rq->sg[0], rq->sg[1] share the same page */
	/* a separated rq->sg[0] for header - required in case !any_header_sg */
	sg_set_buf(&rq->sg[0], p, vi->hdr_len);

	/* rq->sg[1] for data packet, from offset */
	offset = sizeof(struct padded_vnet_hdr);
	sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset);

	/* chain first in list head */
	first->private = (unsigned long)list;
	err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
				  first, gfp);
	if (err < 0)
		give_pages(rq, first);

	return err;
}

static unsigned int get_mergeable_buf_len(struct receive_queue *rq,
					  struct ewma_pkt_len *avg_pkt_len)
{
	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
	unsigned int len;

	len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len),
				rq->min_buf_len, PAGE_SIZE - hdr_len);
	return ALIGN(len, L1_CACHE_BYTES);
}

static int add_recvbuf_mergeable(struct virtnet_info *vi,
				 struct receive_queue *rq, gfp_t gfp)
{
	struct page_frag *alloc_frag = &rq->alloc_frag;
	unsigned int headroom = virtnet_get_headroom(vi);
	char *buf;
	void *ctx;
	int err;
	unsigned int len, hole;

	len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len);
	if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
		return -ENOMEM;

	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
	buf += headroom; /* advance address leaving hole at front of pkt */
	get_page(alloc_frag->page);
	alloc_frag->offset += len + headroom;
	hole = alloc_frag->size - alloc_frag->offset;
	if (hole < len + headroom) {
		/* To avoid internal fragmentation, if there is very likely not
		 * enough space for another buffer, add the remaining space to
		 * the current buffer.
		 */
		len += hole;
		alloc_frag->offset += hole;
	}

	sg_init_one(rq->sg, buf, len);
	ctx = mergeable_len_to_ctx(len, headroom);
	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
	if (err < 0)
		put_page(virt_to_head_page(buf));

	return err;
}

/*
 * Returns false if we couldn't fill entirely (OOM).
 *
 * Normally run in the receive path, but can also be run from ndo_open
 * before we're receiving packets, or from refill_work which is
 * careful to disable receiving (using napi_disable).
 */
static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
			  gfp_t gfp)
{
	int err;
	bool oom;

	gfp |= __GFP_COLD;
	do {
		if (vi->mergeable_rx_bufs)
			err = add_recvbuf_mergeable(vi, rq, gfp);
		else if (vi->big_packets)
			err = add_recvbuf_big(vi, rq, gfp);
		else
			err = add_recvbuf_small(vi, rq, gfp);

		oom = err == -ENOMEM;
		if (err)
			break;
	} while (rq->vq->num_free);
	virtqueue_kick(rq->vq);
	return !oom;
}

static void skb_recv_done(struct virtqueue *rvq)
{
	struct virtnet_info *vi = rvq->vdev->priv;
	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];

	virtqueue_napi_schedule(&rq->napi, rvq);
}

static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
{
	napi_enable(napi);

	/* If all buffers were filled by other side before we napi_enabled, we
	 * won't get another interrupt, so process any outstanding packets now.
	 * Call local_bh_enable after to trigger softIRQ processing.
	 */
	local_bh_disable();
	virtqueue_napi_schedule(napi, vq);
	local_bh_enable();
}

static void virtnet_napi_tx_enable(struct virtnet_info *vi,
				   struct virtqueue *vq,
				   struct napi_struct *napi)
{
	if (!napi->weight)
		return;

	/* Tx napi touches cachelines on the cpu handling tx interrupts. Only
	 * enable the feature if this is likely affine with the transmit path.
	 */
	if (!vi->affinity_hint_set) {
		napi->weight = 0;
		return;
	}

	return virtnet_napi_enable(vq, napi);
}

static void virtnet_napi_tx_disable(struct napi_struct *napi)
{
	if (napi->weight)
		napi_disable(napi);
}

static void refill_work(struct work_struct *work)
{
	struct virtnet_info *vi =
		container_of(work, struct virtnet_info, refill.work);
	bool still_empty;
	int i;

	for (i = 0; i < vi->curr_queue_pairs; i++) {
		struct receive_queue *rq = &vi->rq[i];

		napi_disable(&rq->napi);
		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
		virtnet_napi_enable(rq->vq, &rq->napi);

		/* In theory, this can happen: if we don't get any buffers in
		 * we will *never* try to fill again.
		 */
		if (still_empty)
			schedule_delayed_work(&vi->refill, HZ/2);
	}
}

static int virtnet_receive(struct receive_queue *rq, int budget)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	unsigned int len, received = 0, bytes = 0;
	void *buf;
	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);

	if (!vi->big_packets || vi->mergeable_rx_bufs) {
		void *ctx;

		while (received < budget &&
		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
			bytes += receive_buf(vi, rq, buf, len, ctx);
			received++;
		}
	} else {
		while (received < budget &&
		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
			bytes += receive_buf(vi, rq, buf, len, NULL);
			received++;
		}
	}

	if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
		if (!try_fill_recv(vi, rq, GFP_ATOMIC))
			schedule_delayed_work(&vi->refill, 0);
	}

	u64_stats_update_begin(&stats->rx_syncp);
	stats->rx_bytes += bytes;
	stats->rx_packets += received;
	u64_stats_update_end(&stats->rx_syncp);

	return received;
}

static void free_old_xmit_skbs(struct send_queue *sq)
{
	struct sk_buff *skb;
	unsigned int len;
	struct virtnet_info *vi = sq->vq->vdev->priv;
	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
	unsigned int packets = 0;
	unsigned int bytes = 0;

	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
		pr_debug("Sent skb %p\n", skb);

		bytes += skb->len;
		packets++;

		dev_consume_skb_any(skb);
	}

	/* Avoid overhead when no packets have been processed
	 * happens when called speculatively from start_xmit.
	 */
	if (!packets)
		return;

	u64_stats_update_begin(&stats->tx_syncp);
	stats->tx_bytes += bytes;
	stats->tx_packets += packets;
	u64_stats_update_end(&stats->tx_syncp);
}

static void virtnet_poll_cleantx(struct receive_queue *rq)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	unsigned int index = vq2rxq(rq->vq);
	struct send_queue *sq = &vi->sq[index];
	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);

	if (!sq->napi.weight)
		return;

	if (__netif_tx_trylock(txq)) {
		free_old_xmit_skbs(sq);
		__netif_tx_unlock(txq);
	}

	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
		netif_tx_wake_queue(txq);
}

static int virtnet_poll(struct napi_struct *napi, int budget)
{
	struct receive_queue *rq =
		container_of(napi, struct receive_queue, napi);
	unsigned int received;

	virtnet_poll_cleantx(rq);

	received = virtnet_receive(rq, budget);

	/* Out of packets? */
	if (received < budget)
		virtqueue_napi_complete(napi, rq->vq, received);

	return received;
}

static int virtnet_open(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		if (i < vi->curr_queue_pairs)
			/* Make sure we have some buffers: if oom use wq. */
			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
				schedule_delayed_work(&vi->refill, 0);
		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
	}

	return 0;
}

static int virtnet_poll_tx(struct napi_struct *napi, int budget)
{
	struct send_queue *sq = container_of(napi, struct send_queue, napi);
	struct virtnet_info *vi = sq->vq->vdev->priv;
	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq));

	__netif_tx_lock(txq, raw_smp_processor_id());
	free_old_xmit_skbs(sq);
	__netif_tx_unlock(txq);

	virtqueue_napi_complete(napi, sq->vq, 0);

	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
		netif_tx_wake_queue(txq);

	return 0;
}

static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
{
	struct virtio_net_hdr_mrg_rxbuf *hdr;
	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
	struct virtnet_info *vi = sq->vq->vdev->priv;
	int num_sg;
	unsigned hdr_len = vi->hdr_len;
	bool can_push;

	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);

	can_push = vi->any_header_sg &&
		!((unsigned long)skb->data & (__alignof__(*hdr) - 1)) &&
		!skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len;
	/* Even if we can, don't push here yet as this would skew
	 * csum_start offset below. */
	if (can_push)
		hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len);
	else
		hdr = skb_vnet_hdr(skb);

	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
				    virtio_is_little_endian(vi->vdev), false))
		BUG();

	if (vi->mergeable_rx_bufs)
		hdr->num_buffers = 0;

	sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2));
	if (can_push) {
		__skb_push(skb, hdr_len);
		num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len);
		if (unlikely(num_sg < 0))
			return num_sg;
		/* Pull header back to avoid skew in tx bytes calculations. */
		__skb_pull(skb, hdr_len);
	} else {
		sg_set_buf(sq->sg, hdr, hdr_len);
		num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len);
		if (unlikely(num_sg < 0))
			return num_sg;
		num_sg++;
	}
	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
}

static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int qnum = skb_get_queue_mapping(skb);
	struct send_queue *sq = &vi->sq[qnum];
	int err;
	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
	bool kick = !skb->xmit_more;
	bool use_napi = sq->napi.weight;

	/* Free up any pending old buffers before queueing new ones. */
	free_old_xmit_skbs(sq);

	if (use_napi && kick)
		virtqueue_enable_cb_delayed(sq->vq);

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

	/* Try to transmit */
	err = xmit_skb(sq, skb);

	/* This should not happen! */
	if (unlikely(err)) {
		dev->stats.tx_fifo_errors++;
		if (net_ratelimit())
			dev_warn(&dev->dev,
				 "Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
		dev->stats.tx_dropped++;
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	/* Don't wait up for transmitted skbs to be freed. */
	if (!use_napi) {
		skb_orphan(skb);
		nf_reset(skb);
	}

	/* If running out of space, stop queue to avoid getting packets that we
	 * are then unable to transmit.
	 * An alternative would be to force queuing layer to requeue the skb by
	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
	 * returned in a normal path of operation: it means that driver is not
	 * maintaining the TX queue stop/start state properly, and causes
	 * the stack to do a non-trivial amount of useless work.
	 * Since most packets only take 1 or 2 ring slots, stopping the queue
	 * early means 16 slots are typically wasted.
	 */
	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
		netif_stop_subqueue(dev, qnum);
		if (!use_napi &&
		    unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
			/* More just got used, free them then recheck. */
			free_old_xmit_skbs(sq);
			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
				netif_start_subqueue(dev, qnum);
				virtqueue_disable_cb(sq->vq);
			}
		}
	}

	if (kick || netif_xmit_stopped(txq))
		virtqueue_kick(sq->vq);

	return NETDEV_TX_OK;
}

/*
 * Send command via the control virtqueue and check status.  Commands
 * supported by the hypervisor, as indicated by feature bits, should
 * never fail unless improperly formatted.
 */
static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
				 struct scatterlist *out)
{
	struct scatterlist *sgs[4], hdr, stat;
	unsigned out_num = 0, tmp;

	/* Caller should know better */
	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));

	vi->ctrl_status = ~0;
	vi->ctrl_hdr.class = class;
	vi->ctrl_hdr.cmd = cmd;
	/* Add header */
	sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
	sgs[out_num++] = &hdr;

	if (out)
		sgs[out_num++] = out;

	/* Add return status. */
	sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
	sgs[out_num] = &stat;

	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
	virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);

	if (unlikely(!virtqueue_kick(vi->cvq)))
		return vi->ctrl_status == VIRTIO_NET_OK;

	/* Spin for a response, the kick causes an ioport write, trapping
	 * into the hypervisor, so the request should be handled immediately.
	 */
	while (!virtqueue_get_buf(vi->cvq, &tmp) &&
	       !virtqueue_is_broken(vi->cvq))
		cpu_relax();

	return vi->ctrl_status == VIRTIO_NET_OK;
}

static int virtnet_set_mac_address(struct net_device *dev, void *p)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_device *vdev = vi->vdev;
	int ret;
	struct sockaddr *addr;
	struct scatterlist sg;

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

	ret = eth_prepare_mac_addr_change(dev, addr);
	if (ret)
		goto out;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
		sg_init_one(&sg, addr->sa_data, dev->addr_len);
		if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
					  VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) {
			dev_warn(&vdev->dev,
				 "Failed to set mac address by vq command.\n");
			ret = -EINVAL;
			goto out;
		}
	} else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) &&
		   !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
		unsigned int i;

		/* Naturally, this has an atomicity problem. */
		for (i = 0; i < dev->addr_len; i++)
			virtio_cwrite8(vdev,
				       offsetof(struct virtio_net_config, mac) +
				       i, addr->sa_data[i]);
	}

	eth_commit_mac_addr_change(dev, p);
	ret = 0;

out:
	kfree(addr);
	return ret;
}

static void virtnet_stats(struct net_device *dev,
			  struct rtnl_link_stats64 *tot)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int cpu;
	unsigned int start;

	for_each_possible_cpu(cpu) {
		struct virtnet_stats *stats = per_cpu_ptr(vi->stats, cpu);
		u64 tpackets, tbytes, rpackets, rbytes;

		do {
			start = u64_stats_fetch_begin_irq(&stats->tx_syncp);
			tpackets = stats->tx_packets;
			tbytes   = stats->tx_bytes;
		} while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start));

		do {
			start = u64_stats_fetch_begin_irq(&stats->rx_syncp);
			rpackets = stats->rx_packets;
			rbytes   = stats->rx_bytes;
		} while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start));

		tot->rx_packets += rpackets;
		tot->tx_packets += tpackets;
		tot->rx_bytes   += rbytes;
		tot->tx_bytes   += tbytes;
	}

	tot->tx_dropped = dev->stats.tx_dropped;
	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
	tot->rx_dropped = dev->stats.rx_dropped;
	tot->rx_length_errors = dev->stats.rx_length_errors;
	tot->rx_frame_errors = dev->stats.rx_frame_errors;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void virtnet_netpoll(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int i;

	for (i = 0; i < vi->curr_queue_pairs; i++)
		napi_schedule(&vi->rq[i].napi);
}
#endif

static void virtnet_ack_link_announce(struct virtnet_info *vi)
{
	rtnl_lock();
	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE,
				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL))
		dev_warn(&vi->dev->dev, "Failed to ack link announce.\n");
	rtnl_unlock();
}

static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
{
	struct scatterlist sg;
	struct net_device *dev = vi->dev;

	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
		return 0;

	vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
	sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
			 queue_pairs);
		return -EINVAL;
	} else {
		vi->curr_queue_pairs = queue_pairs;
		/* virtnet_open() will refill when device is going to up. */
		if (dev->flags & IFF_UP)
			schedule_delayed_work(&vi->refill, 0);
	}

	return 0;
}

static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
{
	int err;

	rtnl_lock();
	err = _virtnet_set_queues(vi, queue_pairs);
	rtnl_unlock();
	return err;
}

static int virtnet_close(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int i;

	/* Make sure refill_work doesn't re-enable napi! */
	cancel_delayed_work_sync(&vi->refill);

	for (i = 0; i < vi->max_queue_pairs; i++) {
		napi_disable(&vi->rq[i].napi);
		virtnet_napi_tx_disable(&vi->sq[i].napi);
	}

	return 0;
}

static void virtnet_set_rx_mode(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg[2];
	struct virtio_net_ctrl_mac *mac_data;
	struct netdev_hw_addr *ha;
	int uc_count;
	int mc_count;
	void *buf;
	int i;

	/* We can't dynamically set ndo_set_rx_mode, so return gracefully */
	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
		return;

	vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
	vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);

	sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
			 vi->ctrl_promisc ? "en" : "dis");

	sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
			 vi->ctrl_allmulti ? "en" : "dis");

	uc_count = netdev_uc_count(dev);
	mc_count = netdev_mc_count(dev);
	/* MAC filter - use one buffer for both lists */
	buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) +
		      (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
	mac_data = buf;
	if (!buf)
		return;

	sg_init_table(sg, 2);

	/* Store the unicast list and count in the front of the buffer */
	mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count);
	i = 0;
	netdev_for_each_uc_addr(ha, dev)
		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);

	sg_set_buf(&sg[0], mac_data,
		   sizeof(mac_data->entries) + (uc_count * ETH_ALEN));

	/* multicast list and count fill the end */
	mac_data = (void *)&mac_data->macs[uc_count][0];

	mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count);
	i = 0;
	netdev_for_each_mc_addr(ha, dev)
		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);

	sg_set_buf(&sg[1], mac_data,
		   sizeof(mac_data->entries) + (mc_count * ETH_ALEN));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
				  VIRTIO_NET_CTRL_MAC_TABLE_SET, sg))
		dev_warn(&dev->dev, "Failed to set MAC filter table.\n");

	kfree(buf);
}

static int virtnet_vlan_rx_add_vid(struct net_device *dev,
				   __be16 proto, u16 vid)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg;

	vi->ctrl_vid = vid;
	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
				  VIRTIO_NET_CTRL_VLAN_ADD, &sg))
		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
	return 0;
}

static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
				    __be16 proto, u16 vid)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg;

	vi->ctrl_vid = vid;
	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
				  VIRTIO_NET_CTRL_VLAN_DEL, &sg))
		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
	return 0;
}

static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
{
	int i;

	if (vi->affinity_hint_set) {
		for (i = 0; i < vi->max_queue_pairs; i++) {
			virtqueue_set_affinity(vi->rq[i].vq, -1);
			virtqueue_set_affinity(vi->sq[i].vq, -1);
		}

		vi->affinity_hint_set = false;
	}
}

static void virtnet_set_affinity(struct virtnet_info *vi)
{
	int i;
	int cpu;

	/* In multiqueue mode, when the number of cpu is equal to the number of
	 * queue pairs, we let the queue pairs to be private to one cpu by
	 * setting the affinity hint to eliminate the contention.
	 */
	if (vi->curr_queue_pairs == 1 ||
	    vi->max_queue_pairs != num_online_cpus()) {
		virtnet_clean_affinity(vi, -1);
		return;
	}

	i = 0;
	for_each_online_cpu(cpu) {
		virtqueue_set_affinity(vi->rq[i].vq, cpu);
		virtqueue_set_affinity(vi->sq[i].vq, cpu);
		netif_set_xps_queue(vi->dev, cpumask_of(cpu), i);
		i++;
	}

	vi->affinity_hint_set = true;
}

static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node)
{
	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
						   node);
	virtnet_set_affinity(vi);
	return 0;
}

static int virtnet_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
						   node_dead);
	virtnet_set_affinity(vi);
	return 0;
}

static int virtnet_cpu_down_prep(unsigned int cpu, struct hlist_node *node)
{
	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
						   node);

	virtnet_clean_affinity(vi, cpu);
	return 0;
}

static enum cpuhp_state virtionet_online;

static int virtnet_cpu_notif_add(struct virtnet_info *vi)
{
	int ret;

	ret = cpuhp_state_add_instance_nocalls(virtionet_online, &vi->node);
	if (ret)
		return ret;
	ret = cpuhp_state_add_instance_nocalls(CPUHP_VIRT_NET_DEAD,
					       &vi->node_dead);
	if (!ret)
		return ret;
	cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node);
	return ret;
}

static void virtnet_cpu_notif_remove(struct virtnet_info *vi)
{
	cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node);
	cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_NET_DEAD,
					    &vi->node_dead);
}

static void virtnet_get_ringparam(struct net_device *dev,
				struct ethtool_ringparam *ring)
{
	struct virtnet_info *vi = netdev_priv(dev);

	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
	ring->rx_pending = ring->rx_max_pending;
	ring->tx_pending = ring->tx_max_pending;
}


static void virtnet_get_drvinfo(struct net_device *dev,
				struct ethtool_drvinfo *info)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_device *vdev = vi->vdev;

	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
	strlcpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
	strlcpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));

}

/* TODO: Eliminate OOO packets during switching */
static int virtnet_set_channels(struct net_device *dev,
				struct ethtool_channels *channels)
{
	struct virtnet_info *vi = netdev_priv(dev);
	u16 queue_pairs = channels->combined_count;
	int err;

	/* We don't support separate rx/tx channels.
	 * We don't allow setting 'other' channels.
	 */
	if (channels->rx_count || channels->tx_count || channels->other_count)
		return -EINVAL;

	if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0)
		return -EINVAL;

	/* For now we don't support modifying channels while XDP is loaded
	 * also when XDP is loaded all RX queues have XDP programs so we only
	 * need to check a single RX queue.
	 */
	if (vi->rq[0].xdp_prog)
		return -EINVAL;

	get_online_cpus();
	err = _virtnet_set_queues(vi, queue_pairs);
	if (!err) {
		netif_set_real_num_tx_queues(dev, queue_pairs);
		netif_set_real_num_rx_queues(dev, queue_pairs);

		virtnet_set_affinity(vi);
	}
	put_online_cpus();

	return err;
}

static void virtnet_get_channels(struct net_device *dev,
				 struct ethtool_channels *channels)
{
	struct virtnet_info *vi = netdev_priv(dev);

	channels->combined_count = vi->curr_queue_pairs;
	channels->max_combined = vi->max_queue_pairs;
	channels->max_other = 0;
	channels->rx_count = 0;
	channels->tx_count = 0;
	channels->other_count = 0;
}

/* Check if the user is trying to change anything besides speed/duplex */
static bool
virtnet_validate_ethtool_cmd(const struct ethtool_link_ksettings *cmd)
{
	struct ethtool_link_ksettings diff1 = *cmd;
	struct ethtool_link_ksettings diff2 = {};

	/* cmd is always set so we need to clear it, validate the port type
	 * and also without autonegotiation we can ignore advertising
	 */
	diff1.base.speed = 0;
	diff2.base.port = PORT_OTHER;
	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
	diff1.base.duplex = 0;
	diff1.base.cmd = 0;
	diff1.base.link_mode_masks_nwords = 0;

	return !memcmp(&diff1.base, &diff2.base, sizeof(diff1.base)) &&
		bitmap_empty(diff1.link_modes.supported,
			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
		bitmap_empty(diff1.link_modes.advertising,
			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
		bitmap_empty(diff1.link_modes.lp_advertising,
			     __ETHTOOL_LINK_MODE_MASK_NBITS);
}

static int virtnet_set_link_ksettings(struct net_device *dev,
				      const struct ethtool_link_ksettings *cmd)
{
	struct virtnet_info *vi = netdev_priv(dev);
	u32 speed;

	speed = cmd->base.speed;
	/* don't allow custom speed and duplex */
	if (!ethtool_validate_speed(speed) ||
	    !ethtool_validate_duplex(cmd->base.duplex) ||
	    !virtnet_validate_ethtool_cmd(cmd))
		return -EINVAL;
	vi->speed = speed;
	vi->duplex = cmd->base.duplex;

	return 0;
}

static int virtnet_get_link_ksettings(struct net_device *dev,
				      struct ethtool_link_ksettings *cmd)
{
	struct virtnet_info *vi = netdev_priv(dev);

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

	return 0;
}

static void virtnet_init_settings(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);

	vi->speed = SPEED_UNKNOWN;
	vi->duplex = DUPLEX_UNKNOWN;
}

static const struct ethtool_ops virtnet_ethtool_ops = {
	.get_drvinfo = virtnet_get_drvinfo,
	.get_link = ethtool_op_get_link,
	.get_ringparam = virtnet_get_ringparam,
	.set_channels = virtnet_set_channels,
	.get_channels = virtnet_get_channels,
	.get_ts_info = ethtool_op_get_ts_info,
	.get_link_ksettings = virtnet_get_link_ksettings,
	.set_link_ksettings = virtnet_set_link_ksettings,
};

static void virtnet_freeze_down(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	int i;

	/* Make sure no work handler is accessing the device */
	flush_work(&vi->config_work);

	netif_device_detach(vi->dev);
	netif_tx_disable(vi->dev);
	cancel_delayed_work_sync(&vi->refill);

	if (netif_running(vi->dev)) {
		for (i = 0; i < vi->max_queue_pairs; i++) {
			napi_disable(&vi->rq[i].napi);
			virtnet_napi_tx_disable(&vi->sq[i].napi);
		}
	}
}

static int init_vqs(struct virtnet_info *vi);

static int virtnet_restore_up(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	int err, i;

	err = init_vqs(vi);
	if (err)
		return err;

	virtio_device_ready(vdev);

	if (netif_running(vi->dev)) {
		for (i = 0; i < vi->curr_queue_pairs; i++)
			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
				schedule_delayed_work(&vi->refill, 0);

		for (i = 0; i < vi->max_queue_pairs; i++) {
			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
					       &vi->sq[i].napi);
		}
	}

	netif_device_attach(vi->dev);
	return err;
}

static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
{
	struct scatterlist sg;
	vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);

	sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
				  VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
		dev_warn(&vi->dev->dev, "Fail to set guest offload. \n");
		return -EINVAL;
	}

	return 0;
}

static int virtnet_clear_guest_offloads(struct virtnet_info *vi)
{
	u64 offloads = 0;

	if (!vi->guest_offloads)
		return 0;

	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
		offloads = 1ULL << VIRTIO_NET_F_GUEST_CSUM;

	return virtnet_set_guest_offloads(vi, offloads);
}

static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
{
	u64 offloads = vi->guest_offloads;

	if (!vi->guest_offloads)
		return 0;
	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
		offloads |= 1ULL << VIRTIO_NET_F_GUEST_CSUM;

	return virtnet_set_guest_offloads(vi, offloads);
}

static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
			   struct netlink_ext_ack *extack)
{
	unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
	struct virtnet_info *vi = netdev_priv(dev);
	struct bpf_prog *old_prog;
	u16 xdp_qp = 0, curr_qp;
	int i, err;

	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)
	    && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO))) {
		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO, disable LRO first");
		return -EOPNOTSUPP;
	}

	if (vi->mergeable_rx_bufs && !vi->any_header_sg) {
		NL_SET_ERR_MSG_MOD(extack, "XDP expects header/data in single page, any_header_sg required");
		return -EINVAL;
	}

	if (dev->mtu > max_sz) {
		NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP");
		netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz);
		return -EINVAL;
	}

	curr_qp = vi->curr_queue_pairs - vi->xdp_queue_pairs;
	if (prog)
		xdp_qp = nr_cpu_ids;

	/* XDP requires extra queues for XDP_TX */
	if (curr_qp + xdp_qp > vi->max_queue_pairs) {
		NL_SET_ERR_MSG_MOD(extack, "Too few free TX rings available");
		netdev_warn(dev, "request %i queues but max is %i\n",
			    curr_qp + xdp_qp, vi->max_queue_pairs);
		return -ENOMEM;
	}

	if (prog) {
		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
		if (IS_ERR(prog))
			return PTR_ERR(prog);
	}

	/* Make sure NAPI is not using any XDP TX queues for RX. */
	for (i = 0; i < vi->max_queue_pairs; i++)
		napi_disable(&vi->rq[i].napi);

	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
	if (err)
		goto err;
	vi->xdp_queue_pairs = xdp_qp;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
		rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
		if (i == 0) {
			if (!old_prog)
				virtnet_clear_guest_offloads(vi);
			if (!prog)
				virtnet_restore_guest_offloads(vi);
		}
		if (old_prog)
			bpf_prog_put(old_prog);
		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
	}

	return 0;

err:
	for (i = 0; i < vi->max_queue_pairs; i++)
		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
	if (prog)
		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
	return err;
}

static u32 virtnet_xdp_query(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	const struct bpf_prog *xdp_prog;
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		xdp_prog = rtnl_dereference(vi->rq[i].xdp_prog);
		if (xdp_prog)
			return xdp_prog->aux->id;
	}
	return 0;
}

static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
{
	switch (xdp->command) {
	case XDP_SETUP_PROG:
		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
	case XDP_QUERY_PROG:
		xdp->prog_id = virtnet_xdp_query(dev);
		xdp->prog_attached = !!xdp->prog_id;
		return 0;
	default:
		return -EINVAL;
	}
}

static const struct net_device_ops virtnet_netdev = {
	.ndo_open            = virtnet_open,
	.ndo_stop   	     = virtnet_close,
	.ndo_start_xmit      = start_xmit,
	.ndo_validate_addr   = eth_validate_addr,
	.ndo_set_mac_address = virtnet_set_mac_address,
	.ndo_set_rx_mode     = virtnet_set_rx_mode,
	.ndo_get_stats64     = virtnet_stats,
	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller = virtnet_netpoll,
#endif
	.ndo_xdp		= virtnet_xdp,
	.ndo_features_check	= passthru_features_check,
};

static void virtnet_config_changed_work(struct work_struct *work)
{
	struct virtnet_info *vi =
		container_of(work, struct virtnet_info, config_work);
	u16 v;

	if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS,
				 struct virtio_net_config, status, &v) < 0)
		return;

	if (v & VIRTIO_NET_S_ANNOUNCE) {
		netdev_notify_peers(vi->dev);
		virtnet_ack_link_announce(vi);
	}

	/* Ignore unknown (future) status bits */
	v &= VIRTIO_NET_S_LINK_UP;

	if (vi->status == v)
		return;

	vi->status = v;

	if (vi->status & VIRTIO_NET_S_LINK_UP) {
		netif_carrier_on(vi->dev);
		netif_tx_wake_all_queues(vi->dev);
	} else {
		netif_carrier_off(vi->dev);
		netif_tx_stop_all_queues(vi->dev);
	}
}

static void virtnet_config_changed(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;

	schedule_work(&vi->config_work);
}

static void virtnet_free_queues(struct virtnet_info *vi)
{
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		napi_hash_del(&vi->rq[i].napi);
		netif_napi_del(&vi->rq[i].napi);
		netif_napi_del(&vi->sq[i].napi);
	}

	/* We called napi_hash_del() before netif_napi_del(),
	 * we need to respect an RCU grace period before freeing vi->rq
	 */
	synchronize_net();

	kfree(vi->rq);
	kfree(vi->sq);
}

static void _free_receive_bufs(struct virtnet_info *vi)
{
	struct bpf_prog *old_prog;
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		while (vi->rq[i].pages)
			__free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);

		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
		RCU_INIT_POINTER(vi->rq[i].xdp_prog, NULL);
		if (old_prog)
			bpf_prog_put(old_prog);
	}
}

static void free_receive_bufs(struct virtnet_info *vi)
{
	rtnl_lock();
	_free_receive_bufs(vi);
	rtnl_unlock();
}

static void free_receive_page_frags(struct virtnet_info *vi)
{
	int i;
	for (i = 0; i < vi->max_queue_pairs; i++)
		if (vi->rq[i].alloc_frag.page)
			put_page(vi->rq[i].alloc_frag.page);
}

static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
{
	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
		return false;
	else if (q < vi->curr_queue_pairs)
		return true;
	else
		return false;
}

static void free_unused_bufs(struct virtnet_info *vi)
{
	void *buf;
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		struct virtqueue *vq = vi->sq[i].vq;
		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
			if (!is_xdp_raw_buffer_queue(vi, i))
				dev_kfree_skb(buf);
			else
				put_page(virt_to_head_page(buf));
		}
	}

	for (i = 0; i < vi->max_queue_pairs; i++) {
		struct virtqueue *vq = vi->rq[i].vq;

		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
			if (vi->mergeable_rx_bufs) {
				put_page(virt_to_head_page(buf));
			} else if (vi->big_packets) {
				give_pages(&vi->rq[i], buf);
			} else {
				put_page(virt_to_head_page(buf));
			}
		}
	}
}

static void virtnet_del_vqs(struct virtnet_info *vi)
{
	struct virtio_device *vdev = vi->vdev;

	virtnet_clean_affinity(vi, -1);

	vdev->config->del_vqs(vdev);

	virtnet_free_queues(vi);
}

/* How large should a single buffer be so a queue full of these can fit at
 * least one full packet?
 * Logic below assumes the mergeable buffer header is used.
 */
static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq)
{
	const unsigned int hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
	unsigned int rq_size = virtqueue_get_vring_size(vq);
	unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu;
	unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len;
	unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size);

	return max(max(min_buf_len, hdr_len) - hdr_len,
		   (unsigned int)GOOD_PACKET_LEN);
}

static int virtnet_find_vqs(struct virtnet_info *vi)
{
	vq_callback_t **callbacks;
	struct virtqueue **vqs;
	int ret = -ENOMEM;
	int i, total_vqs;
	const char **names;
	bool *ctx;

	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
	 * possible control vq.
	 */
	total_vqs = vi->max_queue_pairs * 2 +
		    virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);

	/* Allocate space for find_vqs parameters */
	vqs = kzalloc(total_vqs * sizeof(*vqs), GFP_KERNEL);
	if (!vqs)
		goto err_vq;
	callbacks = kmalloc(total_vqs * sizeof(*callbacks), GFP_KERNEL);
	if (!callbacks)
		goto err_callback;
	names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
	if (!names)
		goto err_names;
	if (!vi->big_packets || vi->mergeable_rx_bufs) {
		ctx = kzalloc(total_vqs * sizeof(*ctx), GFP_KERNEL);
		if (!ctx)
			goto err_ctx;
	} else {
		ctx = NULL;
	}

	/* Parameters for control virtqueue, if any */
	if (vi->has_cvq) {
		callbacks[total_vqs - 1] = NULL;
		names[total_vqs - 1] = "control";
	}

	/* Allocate/initialize parameters for send/receive virtqueues */
	for (i = 0; i < vi->max_queue_pairs; i++) {
		callbacks[rxq2vq(i)] = skb_recv_done;
		callbacks[txq2vq(i)] = skb_xmit_done;
		sprintf(vi->rq[i].name, "input.%d", i);
		sprintf(vi->sq[i].name, "output.%d", i);
		names[rxq2vq(i)] = vi->rq[i].name;
		names[txq2vq(i)] = vi->sq[i].name;
		if (ctx)
			ctx[rxq2vq(i)] = true;
	}

	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
					 names, ctx, NULL);
	if (ret)
		goto err_find;

	if (vi->has_cvq) {
		vi->cvq = vqs[total_vqs - 1];
		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
			vi->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
	}

	for (i = 0; i < vi->max_queue_pairs; i++) {
		vi->rq[i].vq = vqs[rxq2vq(i)];
		vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq);
		vi->sq[i].vq = vqs[txq2vq(i)];
	}

	kfree(names);
	kfree(callbacks);
	kfree(vqs);
	kfree(ctx);

	return 0;

err_find:
	kfree(ctx);
err_ctx:
	kfree(names);
err_names:
	kfree(callbacks);
err_callback:
	kfree(vqs);
err_vq:
	return ret;
}

static int virtnet_alloc_queues(struct virtnet_info *vi)
{
	int i;

	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
	if (!vi->sq)
		goto err_sq;
	vi->rq = kzalloc(sizeof(*vi->rq) * vi->max_queue_pairs, GFP_KERNEL);
	if (!vi->rq)
		goto err_rq;

	INIT_DELAYED_WORK(&vi->refill, refill_work);
	for (i = 0; i < vi->max_queue_pairs; i++) {
		vi->rq[i].pages = NULL;
		netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
			       napi_weight);
		netif_tx_napi_add(vi->dev, &vi->sq[i].napi, virtnet_poll_tx,
				  napi_tx ? napi_weight : 0);

		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
	}

	return 0;

err_rq:
	kfree(vi->sq);
err_sq:
	return -ENOMEM;
}

static int init_vqs(struct virtnet_info *vi)
{
	int ret;

	/* Allocate send & receive queues */
	ret = virtnet_alloc_queues(vi);
	if (ret)
		goto err;

	ret = virtnet_find_vqs(vi);
	if (ret)
		goto err_free;

	get_online_cpus();
	virtnet_set_affinity(vi);
	put_online_cpus();

	return 0;

err_free:
	virtnet_free_queues(vi);
err:
	return ret;
}

#ifdef CONFIG_SYSFS
static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue,
		char *buf)
{
	struct virtnet_info *vi = netdev_priv(queue->dev);
	unsigned int queue_index = get_netdev_rx_queue_index(queue);
	struct ewma_pkt_len *avg;

	BUG_ON(queue_index >= vi->max_queue_pairs);
	avg = &vi->rq[queue_index].mrg_avg_pkt_len;
	return sprintf(buf, "%u\n",
		       get_mergeable_buf_len(&vi->rq[queue_index], avg));
}

static struct rx_queue_attribute mergeable_rx_buffer_size_attribute =
	__ATTR_RO(mergeable_rx_buffer_size);

static struct attribute *virtio_net_mrg_rx_attrs[] = {
	&mergeable_rx_buffer_size_attribute.attr,
	NULL
};

static const struct attribute_group virtio_net_mrg_rx_group = {
	.name = "virtio_net",
	.attrs = virtio_net_mrg_rx_attrs
};
#endif

static bool virtnet_fail_on_feature(struct virtio_device *vdev,
				    unsigned int fbit,
				    const char *fname, const char *dname)
{
	if (!virtio_has_feature(vdev, fbit))
		return false;

	dev_err(&vdev->dev, "device advertises feature %s but not %s",
		fname, dname);

	return true;
}

#define VIRTNET_FAIL_ON(vdev, fbit, dbit)			\
	virtnet_fail_on_feature(vdev, fbit, #fbit, dbit)

static bool virtnet_validate_features(struct virtio_device *vdev)
{
	if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ) &&
	    (VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_RX,
			     "VIRTIO_NET_F_CTRL_VQ") ||
	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_VLAN,
			     "VIRTIO_NET_F_CTRL_VQ") ||
	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE,
			     "VIRTIO_NET_F_CTRL_VQ") ||
	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") ||
	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR,
			     "VIRTIO_NET_F_CTRL_VQ"))) {
		return false;
	}

	return true;
}

#define MIN_MTU ETH_MIN_MTU
#define MAX_MTU ETH_MAX_MTU

static int virtnet_validate(struct virtio_device *vdev)
{
	if (!vdev->config->get) {
		dev_err(&vdev->dev, "%s failure: config access disabled\n",
			__func__);
		return -EINVAL;
	}

	if (!virtnet_validate_features(vdev))
		return -EINVAL;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
		int mtu = virtio_cread16(vdev,
					 offsetof(struct virtio_net_config,
						  mtu));
		if (mtu < MIN_MTU)
			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
	}

	return 0;
}

static int virtnet_probe(struct virtio_device *vdev)
{
	int i, err;
	struct net_device *dev;
	struct virtnet_info *vi;
	u16 max_queue_pairs;
	int mtu;

	/* Find if host supports multiqueue virtio_net device */
	err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ,
				   struct virtio_net_config,
				   max_virtqueue_pairs, &max_queue_pairs);

	/* We need at least 2 queue's */
	if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
	    max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
	    !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
		max_queue_pairs = 1;

	/* Allocate ourselves a network device with room for our info */
	dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs);
	if (!dev)
		return -ENOMEM;

	/* Set up network device as normal. */
	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
	dev->netdev_ops = &virtnet_netdev;
	dev->features = NETIF_F_HIGHDMA;

	dev->ethtool_ops = &virtnet_ethtool_ops;
	SET_NETDEV_DEV(dev, &vdev->dev);

	/* Do we support "hardware" checksums? */
	if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
		/* This opens up the world of extra features. */
		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG;
		if (csum)
			dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;

		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
			dev->hw_features |= NETIF_F_TSO
				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
		}
		/* Individual feature bits: what can host handle? */
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4))
			dev->hw_features |= NETIF_F_TSO;
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6))
			dev->hw_features |= NETIF_F_TSO6;
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
			dev->hw_features |= NETIF_F_TSO_ECN;

		dev->features |= NETIF_F_GSO_ROBUST;

		if (gso)
			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
		/* (!csum && gso) case will be fixed by register_netdev() */
	}
	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
		dev->features |= NETIF_F_RXCSUM;

	dev->vlan_features = dev->features;

	/* MTU range: 68 - 65535 */
	dev->min_mtu = MIN_MTU;
	dev->max_mtu = MAX_MTU;

	/* Configuration may specify what MAC to use.  Otherwise random. */
	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC))
		virtio_cread_bytes(vdev,
				   offsetof(struct virtio_net_config, mac),
				   dev->dev_addr, dev->addr_len);
	else
		eth_hw_addr_random(dev);

	/* Set up our device-specific information */
	vi = netdev_priv(dev);
	vi->dev = dev;
	vi->vdev = vdev;
	vdev->priv = vi;
	vi->stats = alloc_percpu(struct virtnet_stats);
	err = -ENOMEM;
	if (vi->stats == NULL)
		goto free;

	for_each_possible_cpu(i) {
		struct virtnet_stats *virtnet_stats;
		virtnet_stats = per_cpu_ptr(vi->stats, i);
		u64_stats_init(&virtnet_stats->tx_syncp);
		u64_stats_init(&virtnet_stats->rx_syncp);
	}

	INIT_WORK(&vi->config_work, virtnet_config_changed_work);

	/* If we can receive ANY GSO packets, we must allocate large ones. */
	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
		vi->big_packets = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
		vi->mergeable_rx_bufs = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
		vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
	else
		vi->hdr_len = sizeof(struct virtio_net_hdr);

	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
		vi->any_header_sg = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
		vi->has_cvq = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
		mtu = virtio_cread16(vdev,
				     offsetof(struct virtio_net_config,
					      mtu));
		if (mtu < dev->min_mtu) {
			/* Should never trigger: MTU was previously validated
			 * in virtnet_validate.
			 */
			dev_err(&vdev->dev, "device MTU appears to have changed "
				"it is now %d < %d", mtu, dev->min_mtu);
			goto free_stats;
		}

		dev->mtu = mtu;
		dev->max_mtu = mtu;

		/* TODO: size buffers correctly in this case. */
		if (dev->mtu > ETH_DATA_LEN)
			vi->big_packets = true;
	}

	if (vi->any_header_sg)
		dev->needed_headroom = vi->hdr_len;

	/* Enable multiqueue by default */
	if (num_online_cpus() >= max_queue_pairs)
		vi->curr_queue_pairs = max_queue_pairs;
	else
		vi->curr_queue_pairs = num_online_cpus();
	vi->max_queue_pairs = max_queue_pairs;

	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
	err = init_vqs(vi);
	if (err)
		goto free_stats;

#ifdef CONFIG_SYSFS
	if (vi->mergeable_rx_bufs)
		dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group;
#endif
	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);

	virtnet_init_settings(dev);

	err = register_netdev(dev);
	if (err) {
		pr_debug("virtio_net: registering device failed\n");
		goto free_vqs;
	}

	virtio_device_ready(vdev);

	err = virtnet_cpu_notif_add(vi);
	if (err) {
		pr_debug("virtio_net: registering cpu notifier failed\n");
		goto free_unregister_netdev;
	}

	virtnet_set_queues(vi, vi->curr_queue_pairs);

	/* Assume link up if device can't report link status,
	   otherwise get link status from config. */
	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
		netif_carrier_off(dev);
		schedule_work(&vi->config_work);
	} else {
		vi->status = VIRTIO_NET_S_LINK_UP;
		netif_carrier_on(dev);
	}

	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
			set_bit(guest_offloads[i], &vi->guest_offloads);

	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
		 dev->name, max_queue_pairs);

	return 0;

free_unregister_netdev:
	vi->vdev->config->reset(vdev);

	unregister_netdev(dev);
free_vqs:
	cancel_delayed_work_sync(&vi->refill);
	free_receive_page_frags(vi);
	virtnet_del_vqs(vi);
free_stats:
	free_percpu(vi->stats);
free:
	free_netdev(dev);
	return err;
}

static void remove_vq_common(struct virtnet_info *vi)
{
	vi->vdev->config->reset(vi->vdev);

	/* Free unused buffers in both send and recv, if any. */
	free_unused_bufs(vi);

	free_receive_bufs(vi);

	free_receive_page_frags(vi);

	virtnet_del_vqs(vi);
}

static void virtnet_remove(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;

	virtnet_cpu_notif_remove(vi);

	/* Make sure no work handler is accessing the device. */
	flush_work(&vi->config_work);

	unregister_netdev(vi->dev);

	remove_vq_common(vi);

	free_percpu(vi->stats);
	free_netdev(vi->dev);
}

static __maybe_unused int virtnet_freeze(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;

	virtnet_cpu_notif_remove(vi);
	virtnet_freeze_down(vdev);
	remove_vq_common(vi);

	return 0;
}

static __maybe_unused int virtnet_restore(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	int err;

	err = virtnet_restore_up(vdev);
	if (err)
		return err;
	virtnet_set_queues(vi, vi->curr_queue_pairs);

	err = virtnet_cpu_notif_add(vi);
	if (err)
		return err;

	return 0;
}

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

#define VIRTNET_FEATURES \
	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, \
	VIRTIO_NET_F_MAC, \
	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \
	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \
	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \
	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \
	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \
	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
	VIRTIO_NET_F_CTRL_MAC_ADDR, \
	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS

static unsigned int features[] = {
	VIRTNET_FEATURES,
};

static unsigned int features_legacy[] = {
	VIRTNET_FEATURES,
	VIRTIO_NET_F_GSO,
	VIRTIO_F_ANY_LAYOUT,
};

static struct virtio_driver virtio_net_driver = {
	.feature_table = features,
	.feature_table_size = ARRAY_SIZE(features),
	.feature_table_legacy = features_legacy,
	.feature_table_size_legacy = ARRAY_SIZE(features_legacy),
	.driver.name =	KBUILD_MODNAME,
	.driver.owner =	THIS_MODULE,
	.id_table =	id_table,
	.validate =	virtnet_validate,
	.probe =	virtnet_probe,
	.remove =	virtnet_remove,
	.config_changed = virtnet_config_changed,
#ifdef CONFIG_PM_SLEEP
	.freeze =	virtnet_freeze,
	.restore =	virtnet_restore,
#endif
};

static __init int virtio_net_driver_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
				      virtnet_cpu_online,
				      virtnet_cpu_down_prep);
	if (ret < 0)
		goto out;
	virtionet_online = ret;
	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
				      NULL, virtnet_cpu_dead);
	if (ret)
		goto err_dead;

        ret = register_virtio_driver(&virtio_net_driver);
	if (ret)
		goto err_virtio;
	return 0;
err_virtio:
	cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD);
err_dead:
	cpuhp_remove_multi_state(virtionet_online);
out:
	return ret;
}
module_init(virtio_net_driver_init);

static __exit void virtio_net_driver_exit(void)
{
	unregister_virtio_driver(&virtio_net_driver);
	cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD);
	cpuhp_remove_multi_state(virtionet_online);
}
module_exit(virtio_net_driver_exit);

MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio network driver");
MODULE_LICENSE("GPL");