summaryrefslogtreecommitdiff
path: root/drivers/net/tun.c
blob: 5eadb7a1ad7bfec2237ffe33744efca336ea02f3 (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
/*
 *  TUN - Universal TUN/TAP device driver.
 *  Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com>
 *
 *  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.
 *
 *  $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $
 */

/*
 *  Changes:
 *
 *  Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14
 *    Add TUNSETLINK ioctl to set the link encapsulation
 *
 *  Mark Smith <markzzzsmith@yahoo.com.au>
 *    Use eth_random_addr() for tap MAC address.
 *
 *  Harald Roelle <harald.roelle@ifi.lmu.de>  2004/04/20
 *    Fixes in packet dropping, queue length setting and queue wakeup.
 *    Increased default tx queue length.
 *    Added ethtool API.
 *    Minor cleanups
 *
 *  Daniel Podlejski <underley@underley.eu.org>
 *    Modifications for 2.3.99-pre5 kernel.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#define DRV_NAME	"tun"
#define DRV_VERSION	"1.6"
#define DRV_DESCRIPTION	"Universal TUN/TAP device driver"
#define DRV_COPYRIGHT	"(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>"

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/miscdevice.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/if_vlan.h>
#include <linux/crc32.h>
#include <linux/nsproxy.h>
#include <linux/virtio_net.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
#include <linux/seq_file.h>
#include <linux/uio.h>
#include <linux/skb_array.h>

#include <asm/uaccess.h>

/* Uncomment to enable debugging */
/* #define TUN_DEBUG 1 */

#ifdef TUN_DEBUG
static int debug;

#define tun_debug(level, tun, fmt, args...)			\
do {								\
	if (tun->debug)						\
		netdev_printk(level, tun->dev, fmt, ##args);	\
} while (0)
#define DBG1(level, fmt, args...)				\
do {								\
	if (debug == 2)						\
		printk(level fmt, ##args);			\
} while (0)
#else
#define tun_debug(level, tun, fmt, args...)			\
do {								\
	if (0)							\
		netdev_printk(level, tun->dev, fmt, ##args);	\
} while (0)
#define DBG1(level, fmt, args...)				\
do {								\
	if (0)							\
		printk(level fmt, ##args);			\
} while (0)
#endif

/* TUN device flags */

/* IFF_ATTACH_QUEUE is never stored in device flags,
 * overload it to mean fasync when stored there.
 */
#define TUN_FASYNC	IFF_ATTACH_QUEUE
/* High bits in flags field are unused. */
#define TUN_VNET_LE     0x80000000
#define TUN_VNET_BE     0x40000000

#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
		      IFF_MULTI_QUEUE)
#define GOODCOPY_LEN 128

#define FLT_EXACT_COUNT 8
struct tap_filter {
	unsigned int    count;    /* Number of addrs. Zero means disabled */
	u32             mask[2];  /* Mask of the hashed addrs */
	unsigned char	addr[FLT_EXACT_COUNT][ETH_ALEN];
};

/* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal
 * to max number of VCPUs in guest. */
#define MAX_TAP_QUEUES 256
#define MAX_TAP_FLOWS  4096

#define TUN_FLOW_EXPIRE (3 * HZ)

struct tun_pcpu_stats {
	u64 rx_packets;
	u64 rx_bytes;
	u64 tx_packets;
	u64 tx_bytes;
	struct u64_stats_sync syncp;
	u32 rx_dropped;
	u32 tx_dropped;
	u32 rx_frame_errors;
};

/* A tun_file connects an open character device to a tuntap netdevice. It
 * also contains all socket related structures (except sock_fprog and tap_filter)
 * to serve as one transmit queue for tuntap device. The sock_fprog and
 * tap_filter were kept in tun_struct since they were used for filtering for the
 * netdevice not for a specific queue (at least I didn't see the requirement for
 * this).
 *
 * RCU usage:
 * The tun_file and tun_struct are loosely coupled, the pointer from one to the
 * other can only be read while rcu_read_lock or rtnl_lock is held.
 */
struct tun_file {
	struct sock sk;
	struct socket socket;
	struct socket_wq wq;
	struct tun_struct __rcu *tun;
	struct fasync_struct *fasync;
	/* only used for fasnyc */
	unsigned int flags;
	union {
		u16 queue_index;
		unsigned int ifindex;
	};
	struct list_head next;
	struct tun_struct *detached;
	struct skb_array tx_array;
};

struct tun_flow_entry {
	struct hlist_node hash_link;
	struct rcu_head rcu;
	struct tun_struct *tun;

	u32 rxhash;
	u32 rps_rxhash;
	int queue_index;
	unsigned long updated;
};

#define TUN_NUM_FLOW_ENTRIES 1024

/* Since the socket were moved to tun_file, to preserve the behavior of persist
 * device, socket filter, sndbuf and vnet header size were restore when the
 * file were attached to a persist device.
 */
struct tun_struct {
	struct tun_file __rcu	*tfiles[MAX_TAP_QUEUES];
	unsigned int            numqueues;
	unsigned int 		flags;
	kuid_t			owner;
	kgid_t			group;

	struct net_device	*dev;
	netdev_features_t	set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
			  NETIF_F_TSO6|NETIF_F_UFO)

	int			align;
	int			vnet_hdr_sz;
	int			sndbuf;
	struct tap_filter	txflt;
	struct sock_fprog	fprog;
	/* protected by rtnl lock */
	bool			filter_attached;
#ifdef TUN_DEBUG
	int debug;
#endif
	spinlock_t lock;
	struct hlist_head flows[TUN_NUM_FLOW_ENTRIES];
	struct timer_list flow_gc_timer;
	unsigned long ageing_time;
	unsigned int numdisabled;
	struct list_head disabled;
	void *security;
	u32 flow_count;
	struct tun_pcpu_stats __percpu *pcpu_stats;
};

#ifdef CONFIG_TUN_VNET_CROSS_LE
static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
{
	return tun->flags & TUN_VNET_BE ? false :
		virtio_legacy_is_little_endian();
}

static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
{
	int be = !!(tun->flags & TUN_VNET_BE);

	if (put_user(be, argp))
		return -EFAULT;

	return 0;
}

static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
{
	int be;

	if (get_user(be, argp))
		return -EFAULT;

	if (be)
		tun->flags |= TUN_VNET_BE;
	else
		tun->flags &= ~TUN_VNET_BE;

	return 0;
}
#else
static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
{
	return virtio_legacy_is_little_endian();
}

static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
{
	return -EINVAL;
}

static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
{
	return -EINVAL;
}
#endif /* CONFIG_TUN_VNET_CROSS_LE */

static inline bool tun_is_little_endian(struct tun_struct *tun)
{
	return tun->flags & TUN_VNET_LE ||
		tun_legacy_is_little_endian(tun);
}

static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
{
	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
}

static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
{
	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
}

static inline u32 tun_hashfn(u32 rxhash)
{
	return rxhash & 0x3ff;
}

static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash)
{
	struct tun_flow_entry *e;

	hlist_for_each_entry_rcu(e, head, hash_link) {
		if (e->rxhash == rxhash)
			return e;
	}
	return NULL;
}

static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun,
					      struct hlist_head *head,
					      u32 rxhash, u16 queue_index)
{
	struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC);

	if (e) {
		tun_debug(KERN_INFO, tun, "create flow: hash %u index %u\n",
			  rxhash, queue_index);
		e->updated = jiffies;
		e->rxhash = rxhash;
		e->rps_rxhash = 0;
		e->queue_index = queue_index;
		e->tun = tun;
		hlist_add_head_rcu(&e->hash_link, head);
		++tun->flow_count;
	}
	return e;
}

static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
{
	tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n",
		  e->rxhash, e->queue_index);
	hlist_del_rcu(&e->hash_link);
	kfree_rcu(e, rcu);
	--tun->flow_count;
}

static void tun_flow_flush(struct tun_struct *tun)
{
	int i;

	spin_lock_bh(&tun->lock);
	for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
		struct tun_flow_entry *e;
		struct hlist_node *n;

		hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link)
			tun_flow_delete(tun, e);
	}
	spin_unlock_bh(&tun->lock);
}

static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index)
{
	int i;

	spin_lock_bh(&tun->lock);
	for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
		struct tun_flow_entry *e;
		struct hlist_node *n;

		hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) {
			if (e->queue_index == queue_index)
				tun_flow_delete(tun, e);
		}
	}
	spin_unlock_bh(&tun->lock);
}

static void tun_flow_cleanup(unsigned long data)
{
	struct tun_struct *tun = (struct tun_struct *)data;
	unsigned long delay = tun->ageing_time;
	unsigned long next_timer = jiffies + delay;
	unsigned long count = 0;
	int i;

	tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n");

	spin_lock_bh(&tun->lock);
	for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
		struct tun_flow_entry *e;
		struct hlist_node *n;

		hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) {
			unsigned long this_timer;
			count++;
			this_timer = e->updated + delay;
			if (time_before_eq(this_timer, jiffies))
				tun_flow_delete(tun, e);
			else if (time_before(this_timer, next_timer))
				next_timer = this_timer;
		}
	}

	if (count)
		mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer));
	spin_unlock_bh(&tun->lock);
}

static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
			    struct tun_file *tfile)
{
	struct hlist_head *head;
	struct tun_flow_entry *e;
	unsigned long delay = tun->ageing_time;
	u16 queue_index = tfile->queue_index;

	if (!rxhash)
		return;
	else
		head = &tun->flows[tun_hashfn(rxhash)];

	rcu_read_lock();

	/* We may get a very small possibility of OOO during switching, not
	 * worth to optimize.*/
	if (tun->numqueues == 1 || tfile->detached)
		goto unlock;

	e = tun_flow_find(head, rxhash);
	if (likely(e)) {
		/* TODO: keep queueing to old queue until it's empty? */
		e->queue_index = queue_index;
		e->updated = jiffies;
		sock_rps_record_flow_hash(e->rps_rxhash);
	} else {
		spin_lock_bh(&tun->lock);
		if (!tun_flow_find(head, rxhash) &&
		    tun->flow_count < MAX_TAP_FLOWS)
			tun_flow_create(tun, head, rxhash, queue_index);

		if (!timer_pending(&tun->flow_gc_timer))
			mod_timer(&tun->flow_gc_timer,
				  round_jiffies_up(jiffies + delay));
		spin_unlock_bh(&tun->lock);
	}

unlock:
	rcu_read_unlock();
}

/**
 * Save the hash received in the stack receive path and update the
 * flow_hash table accordingly.
 */
static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
{
	if (unlikely(e->rps_rxhash != hash))
		e->rps_rxhash = hash;
}

/* We try to identify a flow through its rxhash first. The reason that
 * we do not check rxq no. is because some cards(e.g 82599), chooses
 * the rxq based on the txq where the last packet of the flow comes. As
 * the userspace application move between processors, we may get a
 * different rxq no. here. If we could not get rxhash, then we would
 * hope the rxq no. may help here.
 */
static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
			    void *accel_priv, select_queue_fallback_t fallback)
{
	struct tun_struct *tun = netdev_priv(dev);
	struct tun_flow_entry *e;
	u32 txq = 0;
	u32 numqueues = 0;

	rcu_read_lock();
	numqueues = ACCESS_ONCE(tun->numqueues);

	txq = skb_get_hash(skb);
	if (txq) {
		e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
		if (e) {
			tun_flow_save_rps_rxhash(e, txq);
			txq = e->queue_index;
		} else
			/* use multiply and shift instead of expensive divide */
			txq = ((u64)txq * numqueues) >> 32;
	} else if (likely(skb_rx_queue_recorded(skb))) {
		txq = skb_get_rx_queue(skb);
		while (unlikely(txq >= numqueues))
			txq -= numqueues;
	}

	rcu_read_unlock();
	return txq;
}

static inline bool tun_not_capable(struct tun_struct *tun)
{
	const struct cred *cred = current_cred();
	struct net *net = dev_net(tun->dev);

	return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
		  (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
		!ns_capable(net->user_ns, CAP_NET_ADMIN);
}

static void tun_set_real_num_queues(struct tun_struct *tun)
{
	netif_set_real_num_tx_queues(tun->dev, tun->numqueues);
	netif_set_real_num_rx_queues(tun->dev, tun->numqueues);
}

static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile)
{
	tfile->detached = tun;
	list_add_tail(&tfile->next, &tun->disabled);
	++tun->numdisabled;
}

static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
{
	struct tun_struct *tun = tfile->detached;

	tfile->detached = NULL;
	list_del_init(&tfile->next);
	--tun->numdisabled;
	return tun;
}

static void tun_queue_purge(struct tun_file *tfile)
{
	struct sk_buff *skb;

	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
		kfree_skb(skb);

	skb_queue_purge(&tfile->sk.sk_error_queue);
}

static void __tun_detach(struct tun_file *tfile, bool clean)
{
	struct tun_file *ntfile;
	struct tun_struct *tun;

	tun = rtnl_dereference(tfile->tun);

	if (tun && !tfile->detached) {
		u16 index = tfile->queue_index;
		BUG_ON(index >= tun->numqueues);

		rcu_assign_pointer(tun->tfiles[index],
				   tun->tfiles[tun->numqueues - 1]);
		ntfile = rtnl_dereference(tun->tfiles[index]);
		ntfile->queue_index = index;

		--tun->numqueues;
		if (clean) {
			RCU_INIT_POINTER(tfile->tun, NULL);
			sock_put(&tfile->sk);
		} else
			tun_disable_queue(tun, tfile);

		synchronize_net();
		tun_flow_delete_by_queue(tun, tun->numqueues + 1);
		/* Drop read queue */
		tun_queue_purge(tfile);
		tun_set_real_num_queues(tun);
	} else if (tfile->detached && clean) {
		tun = tun_enable_queue(tfile);
		sock_put(&tfile->sk);
	}

	if (clean) {
		if (tun && tun->numqueues == 0 && tun->numdisabled == 0) {
			netif_carrier_off(tun->dev);

			if (!(tun->flags & IFF_PERSIST) &&
			    tun->dev->reg_state == NETREG_REGISTERED)
				unregister_netdevice(tun->dev);
		}
		if (tun)
			skb_array_cleanup(&tfile->tx_array);
		sock_put(&tfile->sk);
	}
}

static void tun_detach(struct tun_file *tfile, bool clean)
{
	rtnl_lock();
	__tun_detach(tfile, clean);
	rtnl_unlock();
}

static void tun_detach_all(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	struct tun_file *tfile, *tmp;
	int i, n = tun->numqueues;

	for (i = 0; i < n; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		BUG_ON(!tfile);
		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
		RCU_INIT_POINTER(tfile->tun, NULL);
		--tun->numqueues;
	}
	list_for_each_entry(tfile, &tun->disabled, next) {
		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
		RCU_INIT_POINTER(tfile->tun, NULL);
	}
	BUG_ON(tun->numqueues != 0);

	synchronize_net();
	for (i = 0; i < n; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		/* Drop read queue */
		tun_queue_purge(tfile);
		sock_put(&tfile->sk);
	}
	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
		tun_enable_queue(tfile);
		tun_queue_purge(tfile);
		sock_put(&tfile->sk);
	}
	BUG_ON(tun->numdisabled != 0);

	if (tun->flags & IFF_PERSIST)
		module_put(THIS_MODULE);
}

static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
{
	struct tun_file *tfile = file->private_data;
	struct net_device *dev = tun->dev;
	int err;

	err = security_tun_dev_attach(tfile->socket.sk, tun->security);
	if (err < 0)
		goto out;

	err = -EINVAL;
	if (rtnl_dereference(tfile->tun) && !tfile->detached)
		goto out;

	err = -EBUSY;
	if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1)
		goto out;

	err = -E2BIG;
	if (!tfile->detached &&
	    tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES)
		goto out;

	err = 0;

	/* Re-attach the filter to persist device */
	if (!skip_filter && (tun->filter_attached == true)) {
		lock_sock(tfile->socket.sk);
		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
		release_sock(tfile->socket.sk);
		if (!err)
			goto out;
	}

	if (!tfile->detached &&
	    skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) {
		err = -ENOMEM;
		goto out;
	}

	tfile->queue_index = tun->numqueues;
	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
	rcu_assign_pointer(tfile->tun, tun);
	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
	tun->numqueues++;

	if (tfile->detached)
		tun_enable_queue(tfile);
	else
		sock_hold(&tfile->sk);

	tun_set_real_num_queues(tun);

	/* device is allowed to go away first, so no need to hold extra
	 * refcnt.
	 */

out:
	return err;
}

static struct tun_struct *__tun_get(struct tun_file *tfile)
{
	struct tun_struct *tun;

	rcu_read_lock();
	tun = rcu_dereference(tfile->tun);
	if (tun)
		dev_hold(tun->dev);
	rcu_read_unlock();

	return tun;
}

static struct tun_struct *tun_get(struct file *file)
{
	return __tun_get(file->private_data);
}

static void tun_put(struct tun_struct *tun)
{
	dev_put(tun->dev);
}

/* TAP filtering */
static void addr_hash_set(u32 *mask, const u8 *addr)
{
	int n = ether_crc(ETH_ALEN, addr) >> 26;
	mask[n >> 5] |= (1 << (n & 31));
}

static unsigned int addr_hash_test(const u32 *mask, const u8 *addr)
{
	int n = ether_crc(ETH_ALEN, addr) >> 26;
	return mask[n >> 5] & (1 << (n & 31));
}

static int update_filter(struct tap_filter *filter, void __user *arg)
{
	struct { u8 u[ETH_ALEN]; } *addr;
	struct tun_filter uf;
	int err, alen, n, nexact;

	if (copy_from_user(&uf, arg, sizeof(uf)))
		return -EFAULT;

	if (!uf.count) {
		/* Disabled */
		filter->count = 0;
		return 0;
	}

	alen = ETH_ALEN * uf.count;
	addr = kmalloc(alen, GFP_KERNEL);
	if (!addr)
		return -ENOMEM;

	if (copy_from_user(addr, arg + sizeof(uf), alen)) {
		err = -EFAULT;
		goto done;
	}

	/* The filter is updated without holding any locks. Which is
	 * perfectly safe. We disable it first and in the worst
	 * case we'll accept a few undesired packets. */
	filter->count = 0;
	wmb();

	/* Use first set of addresses as an exact filter */
	for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++)
		memcpy(filter->addr[n], addr[n].u, ETH_ALEN);

	nexact = n;

	/* Remaining multicast addresses are hashed,
	 * unicast will leave the filter disabled. */
	memset(filter->mask, 0, sizeof(filter->mask));
	for (; n < uf.count; n++) {
		if (!is_multicast_ether_addr(addr[n].u)) {
			err = 0; /* no filter */
			goto done;
		}
		addr_hash_set(filter->mask, addr[n].u);
	}

	/* For ALLMULTI just set the mask to all ones.
	 * This overrides the mask populated above. */
	if ((uf.flags & TUN_FLT_ALLMULTI))
		memset(filter->mask, ~0, sizeof(filter->mask));

	/* Now enable the filter */
	wmb();
	filter->count = nexact;

	/* Return the number of exact filters */
	err = nexact;

done:
	kfree(addr);
	return err;
}

/* Returns: 0 - drop, !=0 - accept */
static int run_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
	/* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect
	 * at this point. */
	struct ethhdr *eh = (struct ethhdr *) skb->data;
	int i;

	/* Exact match */
	for (i = 0; i < filter->count; i++)
		if (ether_addr_equal(eh->h_dest, filter->addr[i]))
			return 1;

	/* Inexact match (multicast only) */
	if (is_multicast_ether_addr(eh->h_dest))
		return addr_hash_test(filter->mask, eh->h_dest);

	return 0;
}

/*
 * Checks whether the packet is accepted or not.
 * Returns: 0 - drop, !=0 - accept
 */
static int check_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
	if (!filter->count)
		return 1;

	return run_filter(filter, skb);
}

/* Network device part of the driver */

static const struct ethtool_ops tun_ethtool_ops;

/* Net device detach from fd. */
static void tun_net_uninit(struct net_device *dev)
{
	tun_detach_all(dev);
}

/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
	netif_tx_start_all_queues(dev);
	return 0;
}

/* Net device close. */
static int tun_net_close(struct net_device *dev)
{
	netif_tx_stop_all_queues(dev);
	return 0;
}

/* Net device start xmit */
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	int txq = skb->queue_mapping;
	struct tun_file *tfile;
	u32 numqueues = 0;

	rcu_read_lock();
	tfile = rcu_dereference(tun->tfiles[txq]);
	numqueues = ACCESS_ONCE(tun->numqueues);

	/* Drop packet if interface is not attached */
	if (txq >= numqueues)
		goto drop;

#ifdef CONFIG_RPS
	if (numqueues == 1 && static_key_false(&rps_needed)) {
		/* Select queue was not called for the skbuff, so we extract the
		 * RPS hash and save it into the flow_table here.
		 */
		__u32 rxhash;

		rxhash = skb_get_hash(skb);
		if (rxhash) {
			struct tun_flow_entry *e;
			e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)],
					rxhash);
			if (e)
				tun_flow_save_rps_rxhash(e, rxhash);
		}
	}
#endif

	tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);

	BUG_ON(!tfile);

	/* Drop if the filter does not like it.
	 * This is a noop if the filter is disabled.
	 * Filter can be enabled only for the TAP devices. */
	if (!check_filter(&tun->txflt, skb))
		goto drop;

	if (tfile->socket.sk->sk_filter &&
	    sk_filter(tfile->socket.sk, skb))
		goto drop;

	/* Limit the number of packets queued by dividing txq length with the
	 * number of queues.
	 */
	if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) * numqueues
			  >= dev->tx_queue_len)
		goto drop;

	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
		goto drop;

	if (skb->sk && sk_fullsock(skb->sk)) {
		sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags,
				  &skb_shinfo(skb)->tx_flags);
		sw_tx_timestamp(skb);
	}

	/* Orphan the skb - required as we might hang on to it
	 * for indefinite time.
	 */
	skb_orphan(skb);

	nf_reset(skb);

	if (skb_array_produce(&tfile->tx_array, skb))
		goto drop;

	/* Notify and wake up reader process */
	if (tfile->flags & TUN_FASYNC)
		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
	tfile->socket.sk->sk_data_ready(tfile->socket.sk);

	rcu_read_unlock();
	return NETDEV_TX_OK;

drop:
	this_cpu_inc(tun->pcpu_stats->tx_dropped);
	skb_tx_error(skb);
	kfree_skb(skb);
	rcu_read_unlock();
	return NET_XMIT_DROP;
}

static void tun_net_mclist(struct net_device *dev)
{
	/*
	 * This callback is supposed to deal with mc filter in
	 * _rx_ path and has nothing to do with the _tx_ path.
	 * In rx path we always accept everything userspace gives us.
	 */
}

#define MIN_MTU 68
#define MAX_MTU 65535

static int
tun_net_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static netdev_features_t tun_net_fix_features(struct net_device *dev,
	netdev_features_t features)
{
	struct tun_struct *tun = netdev_priv(dev);

	return (features & tun->set_features) | (features & ~TUN_USER_FEATURES);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void tun_poll_controller(struct net_device *dev)
{
	/*
	 * Tun only receives frames when:
	 * 1) the char device endpoint gets data from user space
	 * 2) the tun socket gets a sendmsg call from user space
	 * Since both of those are synchronous operations, we are guaranteed
	 * never to have pending data when we poll for it
	 * so there is nothing to do here but return.
	 * We need this though so netpoll recognizes us as an interface that
	 * supports polling, which enables bridge devices in virt setups to
	 * still use netconsole
	 */
	return;
}
#endif

static void tun_set_headroom(struct net_device *dev, int new_hr)
{
	struct tun_struct *tun = netdev_priv(dev);

	if (new_hr < NET_SKB_PAD)
		new_hr = NET_SKB_PAD;

	tun->align = new_hr;
}

static struct rtnl_link_stats64 *
tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
	u32 rx_dropped = 0, tx_dropped = 0, rx_frame_errors = 0;
	struct tun_struct *tun = netdev_priv(dev);
	struct tun_pcpu_stats *p;
	int i;

	for_each_possible_cpu(i) {
		u64 rxpackets, rxbytes, txpackets, txbytes;
		unsigned int start;

		p = per_cpu_ptr(tun->pcpu_stats, i);
		do {
			start = u64_stats_fetch_begin(&p->syncp);
			rxpackets	= p->rx_packets;
			rxbytes		= p->rx_bytes;
			txpackets	= p->tx_packets;
			txbytes		= p->tx_bytes;
		} while (u64_stats_fetch_retry(&p->syncp, start));

		stats->rx_packets	+= rxpackets;
		stats->rx_bytes		+= rxbytes;
		stats->tx_packets	+= txpackets;
		stats->tx_bytes		+= txbytes;

		/* u32 counters */
		rx_dropped	+= p->rx_dropped;
		rx_frame_errors	+= p->rx_frame_errors;
		tx_dropped	+= p->tx_dropped;
	}
	stats->rx_dropped  = rx_dropped;
	stats->rx_frame_errors = rx_frame_errors;
	stats->tx_dropped = tx_dropped;
	return stats;
}

static const struct net_device_ops tun_netdev_ops = {
	.ndo_uninit		= tun_net_uninit,
	.ndo_open		= tun_net_open,
	.ndo_stop		= tun_net_close,
	.ndo_start_xmit		= tun_net_xmit,
	.ndo_change_mtu		= tun_net_change_mtu,
	.ndo_fix_features	= tun_net_fix_features,
	.ndo_select_queue	= tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= tun_poll_controller,
#endif
	.ndo_set_rx_headroom	= tun_set_headroom,
	.ndo_get_stats64	= tun_net_get_stats64,
};

static const struct net_device_ops tap_netdev_ops = {
	.ndo_uninit		= tun_net_uninit,
	.ndo_open		= tun_net_open,
	.ndo_stop		= tun_net_close,
	.ndo_start_xmit		= tun_net_xmit,
	.ndo_change_mtu		= tun_net_change_mtu,
	.ndo_fix_features	= tun_net_fix_features,
	.ndo_set_rx_mode	= tun_net_mclist,
	.ndo_set_mac_address	= eth_mac_addr,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_select_queue	= tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= tun_poll_controller,
#endif
	.ndo_features_check	= passthru_features_check,
	.ndo_set_rx_headroom	= tun_set_headroom,
	.ndo_get_stats64	= tun_net_get_stats64,
};

static void tun_flow_init(struct tun_struct *tun)
{
	int i;

	for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++)
		INIT_HLIST_HEAD(&tun->flows[i]);

	tun->ageing_time = TUN_FLOW_EXPIRE;
	setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun);
	mod_timer(&tun->flow_gc_timer,
		  round_jiffies_up(jiffies + tun->ageing_time));
}

static void tun_flow_uninit(struct tun_struct *tun)
{
	del_timer_sync(&tun->flow_gc_timer);
	tun_flow_flush(tun);
}

/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	switch (tun->flags & TUN_TYPE_MASK) {
	case IFF_TUN:
		dev->netdev_ops = &tun_netdev_ops;

		/* Point-to-Point TUN Device */
		dev->hard_header_len = 0;
		dev->addr_len = 0;
		dev->mtu = 1500;

		/* Zero header length */
		dev->type = ARPHRD_NONE;
		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
		break;

	case IFF_TAP:
		dev->netdev_ops = &tap_netdev_ops;
		/* Ethernet TAP Device */
		ether_setup(dev);
		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
		dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

		eth_hw_addr_random(dev);

		break;
	}
}

/* Character device part */

/* Poll */
static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun = __tun_get(tfile);
	struct sock *sk;
	unsigned int mask = 0;

	if (!tun)
		return POLLERR;

	sk = tfile->socket.sk;

	tun_debug(KERN_INFO, tun, "tun_chr_poll\n");

	poll_wait(file, sk_sleep(sk), wait);

	if (!skb_array_empty(&tfile->tx_array))
		mask |= POLLIN | POLLRDNORM;

	if (sock_writeable(sk) ||
	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
	     sock_writeable(sk)))
		mask |= POLLOUT | POLLWRNORM;

	if (tun->dev->reg_state != NETREG_REGISTERED)
		mask = POLLERR;

	tun_put(tun);
	return mask;
}

/* prepad is the amount to reserve at front.  len is length after that.
 * linear is a hint as to how much to copy (usually headers). */
static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
				     size_t prepad, size_t len,
				     size_t linear, int noblock)
{
	struct sock *sk = tfile->socket.sk;
	struct sk_buff *skb;
	int err;

	/* Under a page?  Don't bother with paged skb. */
	if (prepad + len < PAGE_SIZE || !linear)
		linear = len;

	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
				   &err, 0);
	if (!skb)
		return ERR_PTR(err);

	skb_reserve(skb, prepad);
	skb_put(skb, linear);
	skb->data_len = len - linear;
	skb->len += len - linear;

	return skb;
}

/* Get packet from user space buffer */
static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
			    void *msg_control, struct iov_iter *from,
			    int noblock)
{
	struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
	struct sk_buff *skb;
	size_t total_len = iov_iter_count(from);
	size_t len = total_len, align = tun->align, linear;
	struct virtio_net_hdr gso = { 0 };
	struct tun_pcpu_stats *stats;
	int good_linear;
	int copylen;
	bool zerocopy = false;
	int err;
	u32 rxhash;
	ssize_t n;

	if (!(tun->dev->flags & IFF_UP))
		return -EIO;

	if (!(tun->flags & IFF_NO_PI)) {
		if (len < sizeof(pi))
			return -EINVAL;
		len -= sizeof(pi);

		n = copy_from_iter(&pi, sizeof(pi), from);
		if (n != sizeof(pi))
			return -EFAULT;
	}

	if (tun->flags & IFF_VNET_HDR) {
		if (len < tun->vnet_hdr_sz)
			return -EINVAL;
		len -= tun->vnet_hdr_sz;

		n = copy_from_iter(&gso, sizeof(gso), from);
		if (n != sizeof(gso))
			return -EFAULT;

		if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
		    tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len))
			gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2);

		if (tun16_to_cpu(tun, gso.hdr_len) > len)
			return -EINVAL;
		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
	}

	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
		align += NET_IP_ALIGN;
		if (unlikely(len < ETH_HLEN ||
			     (gso.hdr_len && tun16_to_cpu(tun, gso.hdr_len) < ETH_HLEN)))
			return -EINVAL;
	}

	good_linear = SKB_MAX_HEAD(align);

	if (msg_control) {
		struct iov_iter i = *from;

		/* There are 256 bytes to be copied in skb, so there is
		 * enough room for skb expand head in case it is used.
		 * The rest of the buffer is mapped from userspace.
		 */
		copylen = gso.hdr_len ? tun16_to_cpu(tun, gso.hdr_len) : GOODCOPY_LEN;
		if (copylen > good_linear)
			copylen = good_linear;
		linear = copylen;
		iov_iter_advance(&i, copylen);
		if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
			zerocopy = true;
	}

	if (!zerocopy) {
		copylen = len;
		if (tun16_to_cpu(tun, gso.hdr_len) > good_linear)
			linear = good_linear;
		else
			linear = tun16_to_cpu(tun, gso.hdr_len);
	}

	skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
	if (IS_ERR(skb)) {
		if (PTR_ERR(skb) != -EAGAIN)
			this_cpu_inc(tun->pcpu_stats->rx_dropped);
		return PTR_ERR(skb);
	}

	if (zerocopy)
		err = zerocopy_sg_from_iter(skb, from);
	else {
		err = skb_copy_datagram_from_iter(skb, 0, from, len);
		if (!err && msg_control) {
			struct ubuf_info *uarg = msg_control;
			uarg->callback(uarg, false);
		}
	}

	if (err) {
		this_cpu_inc(tun->pcpu_stats->rx_dropped);
		kfree_skb(skb);
		return -EFAULT;
	}

	err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun));
	if (err) {
		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
		kfree_skb(skb);
		return -EINVAL;
	}

	switch (tun->flags & TUN_TYPE_MASK) {
	case IFF_TUN:
		if (tun->flags & IFF_NO_PI) {
			switch (skb->data[0] & 0xf0) {
			case 0x40:
				pi.proto = htons(ETH_P_IP);
				break;
			case 0x60:
				pi.proto = htons(ETH_P_IPV6);
				break;
			default:
				this_cpu_inc(tun->pcpu_stats->rx_dropped);
				kfree_skb(skb);
				return -EINVAL;
			}
		}

		skb_reset_mac_header(skb);
		skb->protocol = pi.proto;
		skb->dev = tun->dev;
		break;
	case IFF_TAP:
		skb->protocol = eth_type_trans(skb, tun->dev);
		break;
	}

	/* copy skb_ubuf_info for callback when skb has no error */
	if (zerocopy) {
		skb_shinfo(skb)->destructor_arg = msg_control;
		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
	}

	skb_reset_network_header(skb);
	skb_probe_transport_header(skb, 0);

	rxhash = skb_get_hash(skb);
	netif_rx_ni(skb);

	stats = get_cpu_ptr(tun->pcpu_stats);
	u64_stats_update_begin(&stats->syncp);
	stats->rx_packets++;
	stats->rx_bytes += len;
	u64_stats_update_end(&stats->syncp);
	put_cpu_ptr(stats);

	tun_flow_update(tun, rxhash, tfile);
	return total_len;
}

static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct tun_struct *tun = tun_get(file);
	struct tun_file *tfile = file->private_data;
	ssize_t result;

	if (!tun)
		return -EBADFD;

	result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK);

	tun_put(tun);
	return result;
}

/* Put packet to the user space buffer */
static ssize_t tun_put_user(struct tun_struct *tun,
			    struct tun_file *tfile,
			    struct sk_buff *skb,
			    struct iov_iter *iter)
{
	struct tun_pi pi = { 0, skb->protocol };
	struct tun_pcpu_stats *stats;
	ssize_t total;
	int vlan_offset = 0;
	int vlan_hlen = 0;
	int vnet_hdr_sz = 0;

	if (skb_vlan_tag_present(skb))
		vlan_hlen = VLAN_HLEN;

	if (tun->flags & IFF_VNET_HDR)
		vnet_hdr_sz = tun->vnet_hdr_sz;

	total = skb->len + vlan_hlen + vnet_hdr_sz;

	if (!(tun->flags & IFF_NO_PI)) {
		if (iov_iter_count(iter) < sizeof(pi))
			return -EINVAL;

		total += sizeof(pi);
		if (iov_iter_count(iter) < total) {
			/* Packet will be striped */
			pi.flags |= TUN_PKT_STRIP;
		}

		if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi))
			return -EFAULT;
	}

	if (vnet_hdr_sz) {
		struct virtio_net_hdr gso = { 0 }; /* no info leak */
		int ret;

		if (iov_iter_count(iter) < vnet_hdr_sz)
			return -EINVAL;

		ret = virtio_net_hdr_from_skb(skb, &gso,
					      tun_is_little_endian(tun));
		if (ret) {
			struct skb_shared_info *sinfo = skb_shinfo(skb);
			pr_err("unexpected GSO type: "
			       "0x%x, gso_size %d, hdr_len %d\n",
			       sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
			       tun16_to_cpu(tun, gso.hdr_len));
			print_hex_dump(KERN_ERR, "tun: ",
				       DUMP_PREFIX_NONE,
				       16, 1, skb->head,
				       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
			WARN_ON_ONCE(1);
			return -EINVAL;
		}

		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
			return -EFAULT;

		iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso));
	}

	if (vlan_hlen) {
		int ret;
		struct {
			__be16 h_vlan_proto;
			__be16 h_vlan_TCI;
		} veth;

		veth.h_vlan_proto = skb->vlan_proto;
		veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb));

		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);

		ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
		if (ret || !iov_iter_count(iter))
			goto done;

		ret = copy_to_iter(&veth, sizeof(veth), iter);
		if (ret != sizeof(veth) || !iov_iter_count(iter))
			goto done;
	}

	skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset);

done:
	/* caller is in process context, */
	stats = get_cpu_ptr(tun->pcpu_stats);
	u64_stats_update_begin(&stats->syncp);
	stats->tx_packets++;
	stats->tx_bytes += skb->len + vlan_hlen;
	u64_stats_update_end(&stats->syncp);
	put_cpu_ptr(tun->pcpu_stats);

	return total;
}

static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock,
				     int *err)
{
	DECLARE_WAITQUEUE(wait, current);
	struct sk_buff *skb = NULL;
	int error = 0;

	skb = skb_array_consume(&tfile->tx_array);
	if (skb)
		goto out;
	if (noblock) {
		error = -EAGAIN;
		goto out;
	}

	add_wait_queue(&tfile->wq.wait, &wait);
	current->state = TASK_INTERRUPTIBLE;

	while (1) {
		skb = skb_array_consume(&tfile->tx_array);
		if (skb)
			break;
		if (signal_pending(current)) {
			error = -ERESTARTSYS;
			break;
		}
		if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) {
			error = -EFAULT;
			break;
		}

		schedule();
	}

	current->state = TASK_RUNNING;
	remove_wait_queue(&tfile->wq.wait, &wait);

out:
	*err = error;
	return skb;
}

static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
			   struct iov_iter *to,
			   int noblock)
{
	struct sk_buff *skb;
	ssize_t ret;
	int err;

	tun_debug(KERN_INFO, tun, "tun_do_read\n");

	if (!iov_iter_count(to))
		return 0;

	/* Read frames from ring */
	skb = tun_ring_recv(tfile, noblock, &err);
	if (!skb)
		return err;

	ret = tun_put_user(tun, tfile, skb, to);
	if (unlikely(ret < 0))
		kfree_skb(skb);
	else
		consume_skb(skb);

	return ret;
}

static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun = __tun_get(tfile);
	ssize_t len = iov_iter_count(to), ret;

	if (!tun)
		return -EBADFD;
	ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK);
	ret = min_t(ssize_t, ret, len);
	if (ret > 0)
		iocb->ki_pos = ret;
	tun_put(tun);
	return ret;
}

static void tun_free_netdev(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	BUG_ON(!(list_empty(&tun->disabled)));
	free_percpu(tun->pcpu_stats);
	tun_flow_uninit(tun);
	security_tun_dev_free_security(tun->security);
	free_netdev(dev);
}

static void tun_setup(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	tun->owner = INVALID_UID;
	tun->group = INVALID_GID;

	dev->ethtool_ops = &tun_ethtool_ops;
	dev->destructor = tun_free_netdev;
	/* We prefer our own queue length */
	dev->tx_queue_len = TUN_READQ_SIZE;
}

/* Trivial set of netlink ops to allow deleting tun or tap
 * device with netlink.
 */
static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
{
	return -EINVAL;
}

static struct rtnl_link_ops tun_link_ops __read_mostly = {
	.kind		= DRV_NAME,
	.priv_size	= sizeof(struct tun_struct),
	.setup		= tun_setup,
	.validate	= tun_validate,
};

static void tun_sock_write_space(struct sock *sk)
{
	struct tun_file *tfile;
	wait_queue_head_t *wqueue;

	if (!sock_writeable(sk))
		return;

	if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
		return;

	wqueue = sk_sleep(sk);
	if (wqueue && waitqueue_active(wqueue))
		wake_up_interruptible_sync_poll(wqueue, POLLOUT |
						POLLWRNORM | POLLWRBAND);

	tfile = container_of(sk, struct tun_file, sk);
	kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
}

static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
{
	int ret;
	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
	struct tun_struct *tun = __tun_get(tfile);

	if (!tun)
		return -EBADFD;

	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
			   m->msg_flags & MSG_DONTWAIT);
	tun_put(tun);
	return ret;
}

static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
		       int flags)
{
	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
	struct tun_struct *tun = __tun_get(tfile);
	int ret;

	if (!tun)
		return -EBADFD;

	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
		ret = -EINVAL;
		goto out;
	}
	if (flags & MSG_ERRQUEUE) {
		ret = sock_recv_errqueue(sock->sk, m, total_len,
					 SOL_PACKET, TUN_TX_TIMESTAMP);
		goto out;
	}
	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT);
	if (ret > (ssize_t)total_len) {
		m->msg_flags |= MSG_TRUNC;
		ret = flags & MSG_TRUNC ? ret : total_len;
	}
out:
	tun_put(tun);
	return ret;
}

static int tun_peek_len(struct socket *sock)
{
	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
	struct tun_struct *tun;
	int ret = 0;

	tun = __tun_get(tfile);
	if (!tun)
		return 0;

	ret = skb_array_peek_len(&tfile->tx_array);
	tun_put(tun);

	return ret;
}

/* Ops structure to mimic raw sockets with tun */
static const struct proto_ops tun_socket_ops = {
	.peek_len = tun_peek_len,
	.sendmsg = tun_sendmsg,
	.recvmsg = tun_recvmsg,
};

static struct proto tun_proto = {
	.name		= "tun",
	.owner		= THIS_MODULE,
	.obj_size	= sizeof(struct tun_file),
};

static int tun_flags(struct tun_struct *tun)
{
	return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP);
}

static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
	return sprintf(buf, "0x%x\n", tun_flags(tun));
}

static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
	return uid_valid(tun->owner)?
		sprintf(buf, "%u\n",
			from_kuid_munged(current_user_ns(), tun->owner)):
		sprintf(buf, "-1\n");
}

static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
	return gid_valid(tun->group) ?
		sprintf(buf, "%u\n",
			from_kgid_munged(current_user_ns(), tun->group)):
		sprintf(buf, "-1\n");
}

static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL);
static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL);
static DEVICE_ATTR(group, 0444, tun_show_group, NULL);

static struct attribute *tun_dev_attrs[] = {
	&dev_attr_tun_flags.attr,
	&dev_attr_owner.attr,
	&dev_attr_group.attr,
	NULL
};

static const struct attribute_group tun_attr_group = {
	.attrs = tun_dev_attrs
};

static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
	struct tun_struct *tun;
	struct tun_file *tfile = file->private_data;
	struct net_device *dev;
	int err;

	if (tfile->detached)
		return -EINVAL;

	dev = __dev_get_by_name(net, ifr->ifr_name);
	if (dev) {
		if (ifr->ifr_flags & IFF_TUN_EXCL)
			return -EBUSY;
		if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
			tun = netdev_priv(dev);
		else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops)
			tun = netdev_priv(dev);
		else
			return -EINVAL;

		if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) !=
		    !!(tun->flags & IFF_MULTI_QUEUE))
			return -EINVAL;

		if (tun_not_capable(tun))
			return -EPERM;
		err = security_tun_dev_open(tun->security);
		if (err < 0)
			return err;

		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER);
		if (err < 0)
			return err;

		if (tun->flags & IFF_MULTI_QUEUE &&
		    (tun->numqueues + tun->numdisabled > 1)) {
			/* One or more queue has already been attached, no need
			 * to initialize the device again.
			 */
			return 0;
		}
	}
	else {
		char *name;
		unsigned long flags = 0;
		int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ?
			     MAX_TAP_QUEUES : 1;

		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			return -EPERM;
		err = security_tun_dev_create();
		if (err < 0)
			return err;

		/* Set dev type */
		if (ifr->ifr_flags & IFF_TUN) {
			/* TUN device */
			flags |= IFF_TUN;
			name = "tun%d";
		} else if (ifr->ifr_flags & IFF_TAP) {
			/* TAP device */
			flags |= IFF_TAP;
			name = "tap%d";
		} else
			return -EINVAL;

		if (*ifr->ifr_name)
			name = ifr->ifr_name;

		dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
				       NET_NAME_UNKNOWN, tun_setup, queues,
				       queues);

		if (!dev)
			return -ENOMEM;

		dev_net_set(dev, net);
		dev->rtnl_link_ops = &tun_link_ops;
		dev->ifindex = tfile->ifindex;
		dev->sysfs_groups[0] = &tun_attr_group;

		tun = netdev_priv(dev);
		tun->dev = dev;
		tun->flags = flags;
		tun->txflt.count = 0;
		tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);

		tun->align = NET_SKB_PAD;
		tun->filter_attached = false;
		tun->sndbuf = tfile->socket.sk->sk_sndbuf;

		tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats);
		if (!tun->pcpu_stats) {
			err = -ENOMEM;
			goto err_free_dev;
		}

		spin_lock_init(&tun->lock);

		err = security_tun_dev_alloc_security(&tun->security);
		if (err < 0)
			goto err_free_stat;

		tun_net_init(dev);
		tun_flow_init(tun);

		dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
				   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
				   NETIF_F_HW_VLAN_STAG_TX;
		dev->features = dev->hw_features | NETIF_F_LLTX;
		dev->vlan_features = dev->features &
				     ~(NETIF_F_HW_VLAN_CTAG_TX |
				       NETIF_F_HW_VLAN_STAG_TX);

		INIT_LIST_HEAD(&tun->disabled);
		err = tun_attach(tun, file, false);
		if (err < 0)
			goto err_free_flow;

		err = register_netdevice(tun->dev);
		if (err < 0)
			goto err_detach;
	}

	netif_carrier_on(tun->dev);

	tun_debug(KERN_INFO, tun, "tun_set_iff\n");

	tun->flags = (tun->flags & ~TUN_FEATURES) |
		(ifr->ifr_flags & TUN_FEATURES);

	/* Make sure persistent devices do not get stuck in
	 * xoff state.
	 */
	if (netif_running(tun->dev))
		netif_tx_wake_all_queues(tun->dev);

	strcpy(ifr->ifr_name, tun->dev->name);
	return 0;

err_detach:
	tun_detach_all(dev);
err_free_flow:
	tun_flow_uninit(tun);
	security_tun_dev_free_security(tun->security);
err_free_stat:
	free_percpu(tun->pcpu_stats);
err_free_dev:
	free_netdev(dev);
	return err;
}

static void tun_get_iff(struct net *net, struct tun_struct *tun,
		       struct ifreq *ifr)
{
	tun_debug(KERN_INFO, tun, "tun_get_iff\n");

	strcpy(ifr->ifr_name, tun->dev->name);

	ifr->ifr_flags = tun_flags(tun);

}

/* This is like a cut-down ethtool ops, except done via tun fd so no
 * privs required. */
static int set_offload(struct tun_struct *tun, unsigned long arg)
{
	netdev_features_t features = 0;

	if (arg & TUN_F_CSUM) {
		features |= NETIF_F_HW_CSUM;
		arg &= ~TUN_F_CSUM;

		if (arg & (TUN_F_TSO4|TUN_F_TSO6)) {
			if (arg & TUN_F_TSO_ECN) {
				features |= NETIF_F_TSO_ECN;
				arg &= ~TUN_F_TSO_ECN;
			}
			if (arg & TUN_F_TSO4)
				features |= NETIF_F_TSO;
			if (arg & TUN_F_TSO6)
				features |= NETIF_F_TSO6;
			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
		}

		if (arg & TUN_F_UFO) {
			features |= NETIF_F_UFO;
			arg &= ~TUN_F_UFO;
		}
	}

	/* This gives the user a way to test for new features in future by
	 * trying to set them. */
	if (arg)
		return -EINVAL;

	tun->set_features = features;
	netdev_update_features(tun->dev);

	return 0;
}

static void tun_detach_filter(struct tun_struct *tun, int n)
{
	int i;
	struct tun_file *tfile;

	for (i = 0; i < n; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		lock_sock(tfile->socket.sk);
		sk_detach_filter(tfile->socket.sk);
		release_sock(tfile->socket.sk);
	}

	tun->filter_attached = false;
}

static int tun_attach_filter(struct tun_struct *tun)
{
	int i, ret = 0;
	struct tun_file *tfile;

	for (i = 0; i < tun->numqueues; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		lock_sock(tfile->socket.sk);
		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
		release_sock(tfile->socket.sk);
		if (ret) {
			tun_detach_filter(tun, i);
			return ret;
		}
	}

	tun->filter_attached = true;
	return ret;
}

static void tun_set_sndbuf(struct tun_struct *tun)
{
	struct tun_file *tfile;
	int i;

	for (i = 0; i < tun->numqueues; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		tfile->socket.sk->sk_sndbuf = tun->sndbuf;
	}
}

static int tun_set_queue(struct file *file, struct ifreq *ifr)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun;
	int ret = 0;

	rtnl_lock();

	if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
		tun = tfile->detached;
		if (!tun) {
			ret = -EINVAL;
			goto unlock;
		}
		ret = security_tun_dev_attach_queue(tun->security);
		if (ret < 0)
			goto unlock;
		ret = tun_attach(tun, file, false);
	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
		tun = rtnl_dereference(tfile->tun);
		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
			ret = -EINVAL;
		else
			__tun_detach(tfile, false);
	} else
		ret = -EINVAL;

unlock:
	rtnl_unlock();
	return ret;
}

static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
			    unsigned long arg, int ifreq_len)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun;
	void __user* argp = (void __user*)arg;
	struct ifreq ifr;
	kuid_t owner;
	kgid_t group;
	int sndbuf;
	int vnet_hdr_sz;
	unsigned int ifindex;
	int le;
	int ret;

	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
		if (copy_from_user(&ifr, argp, ifreq_len))
			return -EFAULT;
	} else {
		memset(&ifr, 0, sizeof(ifr));
	}
	if (cmd == TUNGETFEATURES) {
		/* Currently this just means: "what IFF flags are valid?".
		 * This is needed because we never checked for invalid flags on
		 * TUNSETIFF.
		 */
		return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
				(unsigned int __user*)argp);
	} else if (cmd == TUNSETQUEUE)
		return tun_set_queue(file, &ifr);

	ret = 0;
	rtnl_lock();

	tun = __tun_get(tfile);
	if (cmd == TUNSETIFF && !tun) {
		ifr.ifr_name[IFNAMSIZ-1] = '\0';

		ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr);

		if (ret)
			goto unlock;

		if (copy_to_user(argp, &ifr, ifreq_len))
			ret = -EFAULT;
		goto unlock;
	}
	if (cmd == TUNSETIFINDEX) {
		ret = -EPERM;
		if (tun)
			goto unlock;

		ret = -EFAULT;
		if (copy_from_user(&ifindex, argp, sizeof(ifindex)))
			goto unlock;

		ret = 0;
		tfile->ifindex = ifindex;
		goto unlock;
	}

	ret = -EBADFD;
	if (!tun)
		goto unlock;

	tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd);

	ret = 0;
	switch (cmd) {
	case TUNGETIFF:
		tun_get_iff(current->nsproxy->net_ns, tun, &ifr);

		if (tfile->detached)
			ifr.ifr_flags |= IFF_DETACH_QUEUE;
		if (!tfile->socket.sk->sk_filter)
			ifr.ifr_flags |= IFF_NOFILTER;

		if (copy_to_user(argp, &ifr, ifreq_len))
			ret = -EFAULT;
		break;

	case TUNSETNOCSUM:
		/* Disable/Enable checksum */

		/* [unimplemented] */
		tun_debug(KERN_INFO, tun, "ignored: set checksum %s\n",
			  arg ? "disabled" : "enabled");
		break;

	case TUNSETPERSIST:
		/* Disable/Enable persist mode. Keep an extra reference to the
		 * module to prevent the module being unprobed.
		 */
		if (arg && !(tun->flags & IFF_PERSIST)) {
			tun->flags |= IFF_PERSIST;
			__module_get(THIS_MODULE);
		}
		if (!arg && (tun->flags & IFF_PERSIST)) {
			tun->flags &= ~IFF_PERSIST;
			module_put(THIS_MODULE);
		}

		tun_debug(KERN_INFO, tun, "persist %s\n",
			  arg ? "enabled" : "disabled");
		break;

	case TUNSETOWNER:
		/* Set owner of the device */
		owner = make_kuid(current_user_ns(), arg);
		if (!uid_valid(owner)) {
			ret = -EINVAL;
			break;
		}
		tun->owner = owner;
		tun_debug(KERN_INFO, tun, "owner set to %u\n",
			  from_kuid(&init_user_ns, tun->owner));
		break;

	case TUNSETGROUP:
		/* Set group of the device */
		group = make_kgid(current_user_ns(), arg);
		if (!gid_valid(group)) {
			ret = -EINVAL;
			break;
		}
		tun->group = group;
		tun_debug(KERN_INFO, tun, "group set to %u\n",
			  from_kgid(&init_user_ns, tun->group));
		break;

	case TUNSETLINK:
		/* Only allow setting the type when the interface is down */
		if (tun->dev->flags & IFF_UP) {
			tun_debug(KERN_INFO, tun,
				  "Linktype set failed because interface is up\n");
			ret = -EBUSY;
		} else {
			tun->dev->type = (int) arg;
			tun_debug(KERN_INFO, tun, "linktype set to %d\n",
				  tun->dev->type);
			ret = 0;
		}
		break;

#ifdef TUN_DEBUG
	case TUNSETDEBUG:
		tun->debug = arg;
		break;
#endif
	case TUNSETOFFLOAD:
		ret = set_offload(tun, arg);
		break;

	case TUNSETTXFILTER:
		/* Can be set only for TAPs */
		ret = -EINVAL;
		if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
			break;
		ret = update_filter(&tun->txflt, (void __user *)arg);
		break;

	case SIOCGIFHWADDR:
		/* Get hw address */
		memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
		ifr.ifr_hwaddr.sa_family = tun->dev->type;
		if (copy_to_user(argp, &ifr, ifreq_len))
			ret = -EFAULT;
		break;

	case SIOCSIFHWADDR:
		/* Set hw address */
		tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n",
			  ifr.ifr_hwaddr.sa_data);

		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
		break;

	case TUNGETSNDBUF:
		sndbuf = tfile->socket.sk->sk_sndbuf;
		if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
			ret = -EFAULT;
		break;

	case TUNSETSNDBUF:
		if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) {
			ret = -EFAULT;
			break;
		}

		tun->sndbuf = sndbuf;
		tun_set_sndbuf(tun);
		break;

	case TUNGETVNETHDRSZ:
		vnet_hdr_sz = tun->vnet_hdr_sz;
		if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
			ret = -EFAULT;
		break;

	case TUNSETVNETHDRSZ:
		if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) {
			ret = -EFAULT;
			break;
		}
		if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) {
			ret = -EINVAL;
			break;
		}

		tun->vnet_hdr_sz = vnet_hdr_sz;
		break;

	case TUNGETVNETLE:
		le = !!(tun->flags & TUN_VNET_LE);
		if (put_user(le, (int __user *)argp))
			ret = -EFAULT;
		break;

	case TUNSETVNETLE:
		if (get_user(le, (int __user *)argp)) {
			ret = -EFAULT;
			break;
		}
		if (le)
			tun->flags |= TUN_VNET_LE;
		else
			tun->flags &= ~TUN_VNET_LE;
		break;

	case TUNGETVNETBE:
		ret = tun_get_vnet_be(tun, argp);
		break;

	case TUNSETVNETBE:
		ret = tun_set_vnet_be(tun, argp);
		break;

	case TUNATTACHFILTER:
		/* Can be set only for TAPs */
		ret = -EINVAL;
		if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
			break;
		ret = -EFAULT;
		if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog)))
			break;

		ret = tun_attach_filter(tun);
		break;

	case TUNDETACHFILTER:
		/* Can be set only for TAPs */
		ret = -EINVAL;
		if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
			break;
		ret = 0;
		tun_detach_filter(tun, tun->numqueues);
		break;

	case TUNGETFILTER:
		ret = -EINVAL;
		if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
			break;
		ret = -EFAULT;
		if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog)))
			break;
		ret = 0;
		break;

	default:
		ret = -EINVAL;
		break;
	}

unlock:
	rtnl_unlock();
	if (tun)
		tun_put(tun);
	return ret;
}

static long tun_chr_ioctl(struct file *file,
			  unsigned int cmd, unsigned long arg)
{
	return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq));
}

#ifdef CONFIG_COMPAT
static long tun_chr_compat_ioctl(struct file *file,
			 unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case TUNSETIFF:
	case TUNGETIFF:
	case TUNSETTXFILTER:
	case TUNGETSNDBUF:
	case TUNSETSNDBUF:
	case SIOCGIFHWADDR:
	case SIOCSIFHWADDR:
		arg = (unsigned long)compat_ptr(arg);
		break;
	default:
		arg = (compat_ulong_t)arg;
		break;
	}

	/*
	 * compat_ifreq is shorter than ifreq, so we must not access beyond
	 * the end of that structure. All fields that are used in this
	 * driver are compatible though, we don't need to convert the
	 * contents.
	 */
	return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq));
}
#endif /* CONFIG_COMPAT */

static int tun_chr_fasync(int fd, struct file *file, int on)
{
	struct tun_file *tfile = file->private_data;
	int ret;

	if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
		goto out;

	if (on) {
		__f_setown(file, task_pid(current), PIDTYPE_PID, 0);
		tfile->flags |= TUN_FASYNC;
	} else
		tfile->flags &= ~TUN_FASYNC;
	ret = 0;
out:
	return ret;
}

static int tun_chr_open(struct inode *inode, struct file * file)
{
	struct net *net = current->nsproxy->net_ns;
	struct tun_file *tfile;

	DBG1(KERN_INFO, "tunX: tun_chr_open\n");

	tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
					    &tun_proto, 0);
	if (!tfile)
		return -ENOMEM;
	RCU_INIT_POINTER(tfile->tun, NULL);
	tfile->flags = 0;
	tfile->ifindex = 0;

	init_waitqueue_head(&tfile->wq.wait);
	RCU_INIT_POINTER(tfile->socket.wq, &tfile->wq);

	tfile->socket.file = file;
	tfile->socket.ops = &tun_socket_ops;

	sock_init_data(&tfile->socket, &tfile->sk);

	tfile->sk.sk_write_space = tun_sock_write_space;
	tfile->sk.sk_sndbuf = INT_MAX;

	file->private_data = tfile;
	INIT_LIST_HEAD(&tfile->next);

	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);

	return 0;
}

static int tun_chr_close(struct inode *inode, struct file *file)
{
	struct tun_file *tfile = file->private_data;

	tun_detach(tfile, true);

	return 0;
}

#ifdef CONFIG_PROC_FS
static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct tun_struct *tun;
	struct ifreq ifr;

	memset(&ifr, 0, sizeof(ifr));

	rtnl_lock();
	tun = tun_get(f);
	if (tun)
		tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
	rtnl_unlock();

	if (tun)
		tun_put(tun);

	seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
}
#endif

static const struct file_operations tun_fops = {
	.owner	= THIS_MODULE,
	.llseek = no_llseek,
	.read_iter  = tun_chr_read_iter,
	.write_iter = tun_chr_write_iter,
	.poll	= tun_chr_poll,
	.unlocked_ioctl	= tun_chr_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = tun_chr_compat_ioctl,
#endif
	.open	= tun_chr_open,
	.release = tun_chr_close,
	.fasync = tun_chr_fasync,
#ifdef CONFIG_PROC_FS
	.show_fdinfo = tun_chr_show_fdinfo,
#endif
};

static struct miscdevice tun_miscdev = {
	.minor = TUN_MINOR,
	.name = "tun",
	.nodename = "net/tun",
	.fops = &tun_fops,
};

/* ethtool interface */

static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
	cmd->supported		= 0;
	cmd->advertising	= 0;
	ethtool_cmd_speed_set(cmd, SPEED_10);
	cmd->duplex		= DUPLEX_FULL;
	cmd->port		= PORT_TP;
	cmd->phy_address	= 0;
	cmd->transceiver	= XCVR_INTERNAL;
	cmd->autoneg		= AUTONEG_DISABLE;
	cmd->maxtxpkt		= 0;
	cmd->maxrxpkt		= 0;
	return 0;
}

static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	struct tun_struct *tun = netdev_priv(dev);

	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
	strlcpy(info->version, DRV_VERSION, sizeof(info->version));

	switch (tun->flags & TUN_TYPE_MASK) {
	case IFF_TUN:
		strlcpy(info->bus_info, "tun", sizeof(info->bus_info));
		break;
	case IFF_TAP:
		strlcpy(info->bus_info, "tap", sizeof(info->bus_info));
		break;
	}
}

static u32 tun_get_msglevel(struct net_device *dev)
{
#ifdef TUN_DEBUG
	struct tun_struct *tun = netdev_priv(dev);
	return tun->debug;
#else
	return -EOPNOTSUPP;
#endif
}

static void tun_set_msglevel(struct net_device *dev, u32 value)
{
#ifdef TUN_DEBUG
	struct tun_struct *tun = netdev_priv(dev);
	tun->debug = value;
#endif
}

static const struct ethtool_ops tun_ethtool_ops = {
	.get_settings	= tun_get_settings,
	.get_drvinfo	= tun_get_drvinfo,
	.get_msglevel	= tun_get_msglevel,
	.set_msglevel	= tun_set_msglevel,
	.get_link	= ethtool_op_get_link,
	.get_ts_info	= ethtool_op_get_ts_info,
};

static int tun_queue_resize(struct tun_struct *tun)
{
	struct net_device *dev = tun->dev;
	struct tun_file *tfile;
	struct skb_array **arrays;
	int n = tun->numqueues + tun->numdisabled;
	int ret, i;

	arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL);
	if (!arrays)
		return -ENOMEM;

	for (i = 0; i < tun->numqueues; i++) {
		tfile = rtnl_dereference(tun->tfiles[i]);
		arrays[i] = &tfile->tx_array;
	}
	list_for_each_entry(tfile, &tun->disabled, next)
		arrays[i++] = &tfile->tx_array;

	ret = skb_array_resize_multiple(arrays, n,
					dev->tx_queue_len, GFP_KERNEL);

	kfree(arrays);
	return ret;
}

static int tun_device_event(struct notifier_block *unused,
			    unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct tun_struct *tun = netdev_priv(dev);

	switch (event) {
	case NETDEV_CHANGE_TX_QUEUE_LEN:
		if (tun_queue_resize(tun))
			return NOTIFY_BAD;
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

static struct notifier_block tun_notifier_block __read_mostly = {
	.notifier_call	= tun_device_event,
};

static int __init tun_init(void)
{
	int ret = 0;

	pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
	pr_info("%s\n", DRV_COPYRIGHT);

	ret = rtnl_link_register(&tun_link_ops);
	if (ret) {
		pr_err("Can't register link_ops\n");
		goto err_linkops;
	}

	ret = misc_register(&tun_miscdev);
	if (ret) {
		pr_err("Can't register misc device %d\n", TUN_MINOR);
		goto err_misc;
	}

	register_netdevice_notifier(&tun_notifier_block);
	return  0;
err_misc:
	rtnl_link_unregister(&tun_link_ops);
err_linkops:
	return ret;
}

static void tun_cleanup(void)
{
	misc_deregister(&tun_miscdev);
	rtnl_link_unregister(&tun_link_ops);
	unregister_netdevice_notifier(&tun_notifier_block);
}

/* Get an underlying socket object from tun file.  Returns error unless file is
 * attached to a device.  The returned object works like a packet socket, it
 * can be used for sock_sendmsg/sock_recvmsg.  The caller is responsible for
 * holding a reference to the file for as long as the socket is in use. */
struct socket *tun_get_socket(struct file *file)
{
	struct tun_file *tfile;
	if (file->f_op != &tun_fops)
		return ERR_PTR(-EINVAL);
	tfile = file->private_data;
	if (!tfile)
		return ERR_PTR(-EBADFD);
	return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);

module_init(tun_init);
module_exit(tun_cleanup);
MODULE_DESCRIPTION(DRV_DESCRIPTION);
MODULE_AUTHOR(DRV_COPYRIGHT);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(TUN_MINOR);
MODULE_ALIAS("devname:net/tun");