summaryrefslogtreecommitdiffstats
path: root/net/socket.c
blob: dae8c6b84a096c7b8066e719d22c6bcc9a7e8269 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
/*
 * NET		An implementation of the SOCKET network access protocol.
 *
 * Version:	@(#)socket.c	1.1.93	18/02/95
 *
 * Authors:	Orest Zborowski, <obz@Kodak.COM>
 *		Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * Fixes:
 *		Anonymous	:	NOTSOCK/BADF cleanup. Error fix in
 *					shutdown()
 *		Alan Cox	:	verify_area() fixes
 *		Alan Cox	:	Removed DDI
 *		Jonathan Kamens	:	SOCK_DGRAM reconnect bug
 *		Alan Cox	:	Moved a load of checks to the very
 *					top level.
 *		Alan Cox	:	Move address structures to/from user
 *					mode above the protocol layers.
 *		Rob Janssen	:	Allow 0 length sends.
 *		Alan Cox	:	Asynchronous I/O support (cribbed from the
 *					tty drivers).
 *		Niibe Yutaka	:	Asynchronous I/O for writes (4.4BSD style)
 *		Jeff Uphoff	:	Made max number of sockets command-line
 *					configurable.
 *		Matti Aarnio	:	Made the number of sockets dynamic,
 *					to be allocated when needed, and mr.
 *					Uphoff's max is used as max to be
 *					allowed to allocate.
 *		Linus		:	Argh. removed all the socket allocation
 *					altogether: it's in the inode now.
 *		Alan Cox	:	Made sock_alloc()/sock_release() public
 *					for NetROM and future kernel nfsd type
 *					stuff.
 *		Alan Cox	:	sendmsg/recvmsg basics.
 *		Tom Dyas	:	Export net symbols.
 *		Marcin Dalecki	:	Fixed problems with CONFIG_NET="n".
 *		Alan Cox	:	Added thread locking to sys_* calls
 *					for sockets. May have errors at the
 *					moment.
 *		Kevin Buhr	:	Fixed the dumb errors in the above.
 *		Andi Kleen	:	Some small cleanups, optimizations,
 *					and fixed a copy_from_user() bug.
 *		Tigran Aivazian	:	sys_send(args) calls sys_sendto(args, NULL, 0)
 *		Tigran Aivazian	:	Made listen(2) backlog sanity checks
 *					protocol-independent
 *
 *
 *		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 module is effectively the top level interface to the BSD socket
 *	paradigm.
 *
 *	Based upon Swansea University Computer Society NET3.039
 */

#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/thread_info.h>
#include <linux/rcupdate.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/wanrouter.h>
#include <linux/if_bridge.h>
#include <linux/if_frad.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/kmod.h>
#include <linux/audit.h>
#include <linux/wireless.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
#include <linux/slab.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>

#include <net/compat.h>
#include <net/wext.h>

#include <net/sock.h>
#include <linux/netfilter.h>

#include <linux/if_tun.h>
#include <linux/ipv6_route.h>
#include <linux/route.h>
#include <linux/sockios.h>
#include <linux/atalk.h>

static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
			 unsigned long nr_segs, loff_t pos);
static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
			  unsigned long nr_segs, loff_t pos);
static int sock_mmap(struct file *file, struct vm_area_struct *vma);

static int sock_close(struct inode *inode, struct file *file);
static unsigned int sock_poll(struct file *file,
			      struct poll_table_struct *wait);
static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
			      unsigned int cmd, unsigned long arg);
#endif
static int sock_fasync(int fd, struct file *filp, int on);
static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more);
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
			        struct pipe_inode_info *pipe, size_t len,
				unsigned int flags);

/*
 *	Socket files have a set of 'special' operations as well as the generic file ones. These don't appear
 *	in the operation structures but are done directly via the socketcall() multiplexor.
 */

static const struct file_operations socket_file_ops = {
	.owner =	THIS_MODULE,
	.llseek =	no_llseek,
	.aio_read =	sock_aio_read,
	.aio_write =	sock_aio_write,
	.poll =		sock_poll,
	.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = compat_sock_ioctl,
#endif
	.mmap =		sock_mmap,
	.open =		sock_no_open,	/* special open code to disallow open via /proc */
	.release =	sock_close,
	.fasync =	sock_fasync,
	.sendpage =	sock_sendpage,
	.splice_write = generic_splice_sendpage,
	.splice_read =	sock_splice_read,
};

/*
 *	The protocol list. Each protocol is registered in here.
 */

static DEFINE_SPINLOCK(net_family_lock);
static const struct net_proto_family *net_families[NPROTO] __read_mostly;

/*
 *	Statistics counters of the socket lists
 */

static DEFINE_PER_CPU(int, sockets_in_use) = 0;

/*
 * Support routines.
 * Move socket addresses back and forth across the kernel/user
 * divide and look after the messy bits.
 */

#define MAX_SOCK_ADDR	128		/* 108 for Unix domain -
					   16 for IP, 16 for IPX,
					   24 for IPv6,
					   about 80 for AX.25
					   must be at least one bigger than
					   the AF_UNIX size (see net/unix/af_unix.c
					   :unix_mkname()).
					 */

/**
 *	move_addr_to_kernel	-	copy a socket address into kernel space
 *	@uaddr: Address in user space
 *	@kaddr: Address in kernel space
 *	@ulen: Length in user space
 *
 *	The address is copied into kernel space. If the provided address is
 *	too long an error code of -EINVAL is returned. If the copy gives
 *	invalid addresses -EFAULT is returned. On a success 0 is returned.
 */

int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr)
{
	if (ulen < 0 || ulen > sizeof(struct sockaddr_storage))
		return -EINVAL;
	if (ulen == 0)
		return 0;
	if (copy_from_user(kaddr, uaddr, ulen))
		return -EFAULT;
	return audit_sockaddr(ulen, kaddr);
}

/**
 *	move_addr_to_user	-	copy an address to user space
 *	@kaddr: kernel space address
 *	@klen: length of address in kernel
 *	@uaddr: user space address
 *	@ulen: pointer to user length field
 *
 *	The value pointed to by ulen on entry is the buffer length available.
 *	This is overwritten with the buffer space used. -EINVAL is returned
 *	if an overlong buffer is specified or a negative buffer size. -EFAULT
 *	is returned if either the buffer or the length field are not
 *	accessible.
 *	After copying the data up to the limit the user specifies, the true
 *	length of the data is written over the length limit the user
 *	specified. Zero is returned for a success.
 */

int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr,
		      int __user *ulen)
{
	int err;
	int len;

	err = get_user(len, ulen);
	if (err)
		return err;
	if (len > klen)
		len = klen;
	if (len < 0 || len > sizeof(struct sockaddr_storage))
		return -EINVAL;
	if (len) {
		if (audit_sockaddr(klen, kaddr))
			return -ENOMEM;
		if (copy_to_user(uaddr, kaddr, len))
			return -EFAULT;
	}
	/*
	 *      "fromlen shall refer to the value before truncation.."
	 *                      1003.1g
	 */
	return __put_user(klen, ulen);
}

static struct kmem_cache *sock_inode_cachep __read_mostly;

static struct inode *sock_alloc_inode(struct super_block *sb)
{
	struct socket_alloc *ei;

	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
	if (!ei->socket.wq) {
		kmem_cache_free(sock_inode_cachep, ei);
		return NULL;
	}
	init_waitqueue_head(&ei->socket.wq->wait);
	ei->socket.wq->fasync_list = NULL;

	ei->socket.state = SS_UNCONNECTED;
	ei->socket.flags = 0;
	ei->socket.ops = NULL;
	ei->socket.sk = NULL;
	ei->socket.file = NULL;

	return &ei->vfs_inode;
}


static void wq_free_rcu(struct rcu_head *head)
{
	struct socket_wq *wq = container_of(head, struct socket_wq, rcu);

	kfree(wq);
}

static void sock_destroy_inode(struct inode *inode)
{
	struct socket_alloc *ei;

	ei = container_of(inode, struct socket_alloc, vfs_inode);
	call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
	kmem_cache_free(sock_inode_cachep, ei);
}

static void init_once(void *foo)
{
	struct socket_alloc *ei = (struct socket_alloc *)foo;

	inode_init_once(&ei->vfs_inode);
}

static int init_inodecache(void)
{
	sock_inode_cachep = kmem_cache_create("sock_inode_cache",
					      sizeof(struct socket_alloc),
					      0,
					      (SLAB_HWCACHE_ALIGN |
					       SLAB_RECLAIM_ACCOUNT |
					       SLAB_MEM_SPREAD),
					      init_once);
	if (sock_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static const struct super_operations sockfs_ops = {
	.alloc_inode =	sock_alloc_inode,
	.destroy_inode =sock_destroy_inode,
	.statfs =	simple_statfs,
};

static int sockfs_get_sb(struct file_system_type *fs_type,
			 int flags, const char *dev_name, void *data,
			 struct vfsmount *mnt)
{
	return get_sb_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC,
			     mnt);
}

static struct vfsmount *sock_mnt __read_mostly;

static struct file_system_type sock_fs_type = {
	.name =		"sockfs",
	.get_sb =	sockfs_get_sb,
	.kill_sb =	kill_anon_super,
};

/*
 * sockfs_dname() is called from d_path().
 */
static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
{
	return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
				dentry->d_inode->i_ino);
}

static const struct dentry_operations sockfs_dentry_operations = {
	.d_dname  = sockfs_dname,
};

/*
 *	Obtains the first available file descriptor and sets it up for use.
 *
 *	These functions create file structures and maps them to fd space
 *	of the current process. On success it returns file descriptor
 *	and file struct implicitly stored in sock->file.
 *	Note that another thread may close file descriptor before we return
 *	from this function. We use the fact that now we do not refer
 *	to socket after mapping. If one day we will need it, this
 *	function will increment ref. count on file by 1.
 *
 *	In any case returned fd MAY BE not valid!
 *	This race condition is unavoidable
 *	with shared fd spaces, we cannot solve it inside kernel,
 *	but we take care of internal coherence yet.
 */

static int sock_alloc_file(struct socket *sock, struct file **f, int flags)
{
	struct qstr name = { .name = "" };
	struct path path;
	struct file *file;
	int fd;

	fd = get_unused_fd_flags(flags);
	if (unlikely(fd < 0))
		return fd;

	path.dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
	if (unlikely(!path.dentry)) {
		put_unused_fd(fd);
		return -ENOMEM;
	}
	path.mnt = mntget(sock_mnt);

	path.dentry->d_op = &sockfs_dentry_operations;
	d_instantiate(path.dentry, SOCK_INODE(sock));
	SOCK_INODE(sock)->i_fop = &socket_file_ops;

	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
		  &socket_file_ops);
	if (unlikely(!file)) {
		/* drop dentry, keep inode */
		atomic_inc(&path.dentry->d_inode->i_count);
		path_put(&path);
		put_unused_fd(fd);
		return -ENFILE;
	}

	sock->file = file;
	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
	file->f_pos = 0;
	file->private_data = sock;

	*f = file;
	return fd;
}

int sock_map_fd(struct socket *sock, int flags)
{
	struct file *newfile;
	int fd = sock_alloc_file(sock, &newfile, flags);

	if (likely(fd >= 0))
		fd_install(fd, newfile);

	return fd;
}

static struct socket *sock_from_file(struct file *file, int *err)
{
	if (file->f_op == &socket_file_ops)
		return file->private_data;	/* set in sock_map_fd */

	*err = -ENOTSOCK;
	return NULL;
}

/**
 *	sockfd_lookup	- 	Go from a file number to its socket slot
 *	@fd: file handle
 *	@err: pointer to an error code return
 *
 *	The file handle passed in is locked and the socket it is bound
 *	too is returned. If an error occurs the err pointer is overwritten
 *	with a negative errno code and NULL is returned. The function checks
 *	for both invalid handles and passing a handle which is not a socket.
 *
 *	On a success the socket object pointer is returned.
 */

struct socket *sockfd_lookup(int fd, int *err)
{
	struct file *file;
	struct socket *sock;

	file = fget(fd);
	if (!file) {
		*err = -EBADF;
		return NULL;
	}

	sock = sock_from_file(file, err);
	if (!sock)
		fput(file);
	return sock;
}

static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
	struct file *file;
	struct socket *sock;

	*err = -EBADF;
	file = fget_light(fd, fput_needed);
	if (file) {
		sock = sock_from_file(file, err);
		if (sock)
			return sock;
		fput_light(file, *fput_needed);
	}
	return NULL;
}

/**
 *	sock_alloc	-	allocate a socket
 *
 *	Allocate a new inode and socket object. The two are bound together
 *	and initialised. The socket is then returned. If we are out of inodes
 *	NULL is returned.
 */

static struct socket *sock_alloc(void)
{
	struct inode *inode;
	struct socket *sock;

	inode = new_inode(sock_mnt->mnt_sb);
	if (!inode)
		return NULL;

	sock = SOCKET_I(inode);

	kmemcheck_annotate_bitfield(sock, type);
	inode->i_mode = S_IFSOCK | S_IRWXUGO;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();

	percpu_add(sockets_in_use, 1);
	return sock;
}

/*
 *	In theory you can't get an open on this inode, but /proc provides
 *	a back door. Remember to keep it shut otherwise you'll let the
 *	creepy crawlies in.
 */

static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
{
	return -ENXIO;
}

const struct file_operations bad_sock_fops = {
	.owner = THIS_MODULE,
	.open = sock_no_open,
};

/**
 *	sock_release	-	close a socket
 *	@sock: socket to close
 *
 *	The socket is released from the protocol stack if it has a release
 *	callback, and the inode is then released if the socket is bound to
 *	an inode not a file.
 */

void sock_release(struct socket *sock)
{
	if (sock->ops) {
		struct module *owner = sock->ops->owner;

		sock->ops->release(sock);
		sock->ops = NULL;
		module_put(owner);
	}

	if (sock->wq->fasync_list)
		printk(KERN_ERR "sock_release: fasync list not empty!\n");

	percpu_sub(sockets_in_use, 1);
	if (!sock->file) {
		iput(SOCK_INODE(sock));
		return;
	}
	sock->file = NULL;
}

int sock_tx_timestamp(struct msghdr *msg, struct sock *sk,
		      union skb_shared_tx *shtx)
{
	shtx->flags = 0;
	if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
		shtx->hardware = 1;
	if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE))
		shtx->software = 1;
	return 0;
}
EXPORT_SYMBOL(sock_tx_timestamp);

static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
				 struct msghdr *msg, size_t size)
{
	struct sock_iocb *si = kiocb_to_siocb(iocb);
	int err;

	si->sock = sock;
	si->scm = NULL;
	si->msg = msg;
	si->size = size;

	err = security_socket_sendmsg(sock, msg, size);
	if (err)
		return err;

	return sock->ops->sendmsg(iocb, sock, msg, size);
}

int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_sendmsg(&iocb, sock, msg, size);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
		   struct kvec *vec, size_t num, size_t size)
{
	mm_segment_t oldfs = get_fs();
	int result;

	set_fs(KERNEL_DS);
	/*
	 * the following is safe, since for compiler definitions of kvec and
	 * iovec are identical, yielding the same in-core layout and alignment
	 */
	msg->msg_iov = (struct iovec *)vec;
	msg->msg_iovlen = num;
	result = sock_sendmsg(sock, msg, size);
	set_fs(oldfs);
	return result;
}

static int ktime2ts(ktime_t kt, struct timespec *ts)
{
	if (kt.tv64) {
		*ts = ktime_to_timespec(kt);
		return 1;
	} else {
		return 0;
	}
}

/*
 * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
 */
void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb)
{
	int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
	struct timespec ts[3];
	int empty = 1;
	struct skb_shared_hwtstamps *shhwtstamps =
		skb_hwtstamps(skb);

	/* Race occurred between timestamp enabling and packet
	   receiving.  Fill in the current time for now. */
	if (need_software_tstamp && skb->tstamp.tv64 == 0)
		__net_timestamp(skb);

	if (need_software_tstamp) {
		if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
			struct timeval tv;
			skb_get_timestamp(skb, &tv);
			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP,
				 sizeof(tv), &tv);
		} else {
			skb_get_timestampns(skb, &ts[0]);
			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS,
				 sizeof(ts[0]), &ts[0]);
		}
	}


	memset(ts, 0, sizeof(ts));
	if (skb->tstamp.tv64 &&
	    sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) {
		skb_get_timestampns(skb, ts + 0);
		empty = 0;
	}
	if (shhwtstamps) {
		if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) &&
		    ktime2ts(shhwtstamps->syststamp, ts + 1))
			empty = 0;
		if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) &&
		    ktime2ts(shhwtstamps->hwtstamp, ts + 2))
			empty = 0;
	}
	if (!empty)
		put_cmsg(msg, SOL_SOCKET,
			 SCM_TIMESTAMPING, sizeof(ts), &ts);
}

EXPORT_SYMBOL_GPL(__sock_recv_timestamp);

inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
		put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
			sizeof(__u32), &skb->dropcount);
}

void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb)
{
	sock_recv_timestamp(msg, sk, skb);
	sock_recv_drops(msg, sk, skb);
}
EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);

static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
				       struct msghdr *msg, size_t size, int flags)
{
	struct sock_iocb *si = kiocb_to_siocb(iocb);

	si->sock = sock;
	si->scm = NULL;
	si->msg = msg;
	si->size = size;
	si->flags = flags;

	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
}

static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
				 struct msghdr *msg, size_t size, int flags)
{
	int err = security_socket_recvmsg(sock, msg, size, flags);

	return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags);
}

int sock_recvmsg(struct socket *sock, struct msghdr *msg,
		 size_t size, int flags)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
			      size_t size, int flags)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
		   struct kvec *vec, size_t num, size_t size, int flags)
{
	mm_segment_t oldfs = get_fs();
	int result;

	set_fs(KERNEL_DS);
	/*
	 * the following is safe, since for compiler definitions of kvec and
	 * iovec are identical, yielding the same in-core layout and alignment
	 */
	msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num;
	result = sock_recvmsg(sock, msg, size, flags);
	set_fs(oldfs);
	return result;
}

static void sock_aio_dtor(struct kiocb *iocb)
{
	kfree(iocb->private);
}

static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more)
{
	struct socket *sock;
	int flags;

	sock = file->private_data;

	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;
	if (more)
		flags |= MSG_MORE;

	return kernel_sendpage(sock, page, offset, size, flags);
}

static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
			        struct pipe_inode_info *pipe, size_t len,
				unsigned int flags)
{
	struct socket *sock = file->private_data;

	if (unlikely(!sock->ops->splice_read))
		return -EINVAL;

	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
}

static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
					 struct sock_iocb *siocb)
{
	if (!is_sync_kiocb(iocb)) {
		siocb = kmalloc(sizeof(*siocb), GFP_KERNEL);
		if (!siocb)
			return NULL;
		iocb->ki_dtor = sock_aio_dtor;
	}

	siocb->kiocb = iocb;
	iocb->private = siocb;
	return siocb;
}

static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
		struct file *file, const struct iovec *iov,
		unsigned long nr_segs)
{
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;

	for (i = 0; i < nr_segs; i++)
		size += iov[i].iov_len;

	msg->msg_name = NULL;
	msg->msg_namelen = 0;
	msg->msg_control = NULL;
	msg->msg_controllen = 0;
	msg->msg_iov = (struct iovec *)iov;
	msg->msg_iovlen = nr_segs;
	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;

	return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
}

static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos)
{
	struct sock_iocb siocb, *x;

	if (pos != 0)
		return -ESPIPE;

	if (iocb->ki_left == 0)	/* Match SYS5 behaviour */
		return 0;


	x = alloc_sock_iocb(iocb, &siocb);
	if (!x)
		return -ENOMEM;
	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}

static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
			struct file *file, const struct iovec *iov,
			unsigned long nr_segs)
{
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;

	for (i = 0; i < nr_segs; i++)
		size += iov[i].iov_len;

	msg->msg_name = NULL;
	msg->msg_namelen = 0;
	msg->msg_control = NULL;
	msg->msg_controllen = 0;
	msg->msg_iov = (struct iovec *)iov;
	msg->msg_iovlen = nr_segs;
	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
	if (sock->type == SOCK_SEQPACKET)
		msg->msg_flags |= MSG_EOR;

	return __sock_sendmsg(iocb, sock, msg, size);
}

static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
			  unsigned long nr_segs, loff_t pos)
{
	struct sock_iocb siocb, *x;

	if (pos != 0)
		return -ESPIPE;

	x = alloc_sock_iocb(iocb, &siocb);
	if (!x)
		return -ENOMEM;

	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}

/*
 * Atomic setting of ioctl hooks to avoid race
 * with module unload.
 */

static DEFINE_MUTEX(br_ioctl_mutex);
static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg) = NULL;

void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
{
	mutex_lock(&br_ioctl_mutex);
	br_ioctl_hook = hook;
	mutex_unlock(&br_ioctl_mutex);
}

EXPORT_SYMBOL(brioctl_set);

static DEFINE_MUTEX(vlan_ioctl_mutex);
static int (*vlan_ioctl_hook) (struct net *, void __user *arg);

void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
{
	mutex_lock(&vlan_ioctl_mutex);
	vlan_ioctl_hook = hook;
	mutex_unlock(&vlan_ioctl_mutex);
}

EXPORT_SYMBOL(vlan_ioctl_set);

static DEFINE_MUTEX(dlci_ioctl_mutex);
static int (*dlci_ioctl_hook) (unsigned int, void __user *);

void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
{
	mutex_lock(&dlci_ioctl_mutex);
	dlci_ioctl_hook = hook;
	mutex_unlock(&dlci_ioctl_mutex);
}

EXPORT_SYMBOL(dlci_ioctl_set);

static long sock_do_ioctl(struct net *net, struct socket *sock,
				 unsigned int cmd, unsigned long arg)
{
	int err;
	void __user *argp = (void __user *)arg;

	err = sock->ops->ioctl(sock, cmd, arg);

	/*
	 * If this ioctl is unknown try to hand it down
	 * to the NIC driver.
	 */
	if (err == -ENOIOCTLCMD)
		err = dev_ioctl(net, cmd, argp);

	return err;
}

/*
 *	With an ioctl, arg may well be a user mode pointer, but we don't know
 *	what to do with it - that's up to the protocol still.
 */

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	struct socket *sock;
	struct sock *sk;
	void __user *argp = (void __user *)arg;
	int pid, err;
	struct net *net;

	sock = file->private_data;
	sk = sock->sk;
	net = sock_net(sk);
	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
		err = dev_ioctl(net, cmd, argp);
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = dev_ioctl(net, cmd, argp);
	} else
#endif
		switch (cmd) {
		case FIOSETOWN:
		case SIOCSPGRP:
			err = -EFAULT;
			if (get_user(pid, (int __user *)argp))
				break;
			err = f_setown(sock->file, pid, 1);
			break;
		case FIOGETOWN:
		case SIOCGPGRP:
			err = put_user(f_getown(sock->file),
				       (int __user *)argp);
			break;
		case SIOCGIFBR:
		case SIOCSIFBR:
		case SIOCBRADDBR:
		case SIOCBRDELBR:
			err = -ENOPKG;
			if (!br_ioctl_hook)
				request_module("bridge");

			mutex_lock(&br_ioctl_mutex);
			if (br_ioctl_hook)
				err = br_ioctl_hook(net, cmd, argp);
			mutex_unlock(&br_ioctl_mutex);
			break;
		case SIOCGIFVLAN:
		case SIOCSIFVLAN:
			err = -ENOPKG;
			if (!vlan_ioctl_hook)
				request_module("8021q");

			mutex_lock(&vlan_ioctl_mutex);
			if (vlan_ioctl_hook)
				err = vlan_ioctl_hook(net, argp);
			mutex_unlock(&vlan_ioctl_mutex);
			break;
		case SIOCADDDLCI:
		case SIOCDELDLCI:
			err = -ENOPKG;
			if (!dlci_ioctl_hook)
				request_module("dlci");

			mutex_lock(&dlci_ioctl_mutex);
			if (dlci_ioctl_hook)
				err = dlci_ioctl_hook(cmd, argp);
			mutex_unlock(&dlci_ioctl_mutex);
			break;
		default:
			err = sock_do_ioctl(net, sock, cmd, arg);
			break;
		}
	return err;
}

int sock_create_lite(int family, int type, int protocol, struct socket **res)
{
	int err;
	struct socket *sock = NULL;

	err = security_socket_create(family, type, protocol, 1);
	if (err)
		goto out;

	sock = sock_alloc();
	if (!sock) {
		err = -ENOMEM;
		goto out;
	}

	sock->type = type;
	err = security_socket_post_create(sock, family, type, protocol, 1);
	if (err)
		goto out_release;

out:
	*res = sock;
	return err;
out_release:
	sock_release(sock);
	sock = NULL;
	goto out;
}

/* No kernel lock held - perfect */
static unsigned int sock_poll(struct file *file, poll_table *wait)
{
	struct socket *sock;

	/*
	 *      We can't return errors to poll, so it's either yes or no.
	 */
	sock = file->private_data;
	return sock->ops->poll(file, sock, wait);
}

static int sock_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct socket *sock = file->private_data;

	return sock->ops->mmap(file, sock, vma);
}

static int sock_close(struct inode *inode, struct file *filp)
{
	/*
	 *      It was possible the inode is NULL we were
	 *      closing an unfinished socket.
	 */

	if (!inode) {
		printk(KERN_DEBUG "sock_close: NULL inode\n");
		return 0;
	}
	sock_release(SOCKET_I(inode));
	return 0;
}

/*
 *	Update the socket async list
 *
 *	Fasync_list locking strategy.
 *
 *	1. fasync_list is modified only under process context socket lock
 *	   i.e. under semaphore.
 *	2. fasync_list is used under read_lock(&sk->sk_callback_lock)
 *	   or under socket lock
 */

static int sock_fasync(int fd, struct file *filp, int on)
{
	struct socket *sock = filp->private_data;
	struct sock *sk = sock->sk;

	if (sk == NULL)
		return -EINVAL;

	lock_sock(sk);

	fasync_helper(fd, filp, on, &sock->wq->fasync_list);

	if (!sock->wq->fasync_list)
		sock_reset_flag(sk, SOCK_FASYNC);
	else
		sock_set_flag(sk, SOCK_FASYNC);

	release_sock(sk);
	return 0;
}

/* This function may be called only under socket lock or callback_lock or rcu_lock */

int sock_wake_async(struct socket *sock, int how, int band)
{
	struct socket_wq *wq;

	if (!sock)
		return -1;
	rcu_read_lock();
	wq = rcu_dereference(sock->wq);
	if (!wq || !wq->fasync_list) {
		rcu_read_unlock();
		return -1;
	}
	switch (how) {
	case SOCK_WAKE_WAITD:
		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
			break;
		goto call_kill;
	case SOCK_WAKE_SPACE:
		if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
			break;
		/* fall through */
	case SOCK_WAKE_IO:
call_kill:
		kill_fasync(&wq->fasync_list, SIGIO, band);
		break;
	case SOCK_WAKE_URG:
		kill_fasync(&wq->fasync_list, SIGURG, band);
	}
	rcu_read_unlock();
	return 0;
}

static int __sock_create(struct net *net, int family, int type, int protocol,
			 struct socket **res, int kern)
{
	int err;
	struct socket *sock;
	const struct net_proto_family *pf;

	/*
	 *      Check protocol is in range
	 */
	if (family < 0 || family >= NPROTO)
		return -EAFNOSUPPORT;
	if (type < 0 || type >= SOCK_MAX)
		return -EINVAL;

	/* Compatibility.

	   This uglymoron is moved from INET layer to here to avoid
	   deadlock in module load.
	 */
	if (family == PF_INET && type == SOCK_PACKET) {
		static int warned;
		if (!warned) {
			warned = 1;
			printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n",
			       current->comm);
		}
		family = PF_PACKET;
	}

	err = security_socket_create(family, type, protocol, kern);
	if (err)
		return err;

	/*
	 *	Allocate the socket and allow the family to set things up. if
	 *	the protocol is 0, the family is instructed to select an appropriate
	 *	default.
	 */
	sock = sock_alloc();
	if (!sock) {
		if (net_ratelimit())
			printk(KERN_WARNING "socket: no more sockets\n");
		return -ENFILE;	/* Not exactly a match, but its the
				   closest posix thing */
	}

	sock->type = type;

#ifdef CONFIG_MODULES
	/* Attempt to load a protocol module if the find failed.
	 *
	 * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user
	 * requested real, full-featured networking support upon configuration.
	 * Otherwise module support will break!
	 */
	if (net_families[family] == NULL)
		request_module("net-pf-%d", family);
#endif

	rcu_read_lock();
	pf = rcu_dereference(net_families[family]);
	err = -EAFNOSUPPORT;
	if (!pf)
		goto out_release;

	/*
	 * We will call the ->create function, that possibly is in a loadable
	 * module, so we have to bump that loadable module refcnt first.
	 */
	if (!try_module_get(pf->owner))
		goto out_release;

	/* Now protected by module ref count */
	rcu_read_unlock();

	err = pf->create(net, sock, protocol, kern);
	if (err < 0)
		goto out_module_put;

	/*
	 * Now to bump the refcnt of the [loadable] module that owns this
	 * socket at sock_release time we decrement its refcnt.
	 */
	if (!try_module_get(sock->ops->owner))
		goto out_module_busy;

	/*
	 * Now that we're done with the ->create function, the [loadable]
	 * module can have its refcnt decremented
	 */
	module_put(pf->owner);
	err = security_socket_post_create(sock, family, type, protocol, kern);
	if (err)
		goto out_sock_release;
	*res = sock;

	return 0;

out_module_busy:
	err = -EAFNOSUPPORT;
out_module_put:
	sock->ops = NULL;
	module_put(pf->owner);
out_sock_release:
	sock_release(sock);
	return err;

out_release:
	rcu_read_unlock();
	goto out_sock_release;
}

int sock_create(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
}

int sock_create_kern(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(&init_net, family, type, protocol, res, 1);
}

SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
	int retval;
	struct socket *sock;
	int flags;

	/* Check the SOCK_* constants for consistency.  */
	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
	BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);

	flags = type & ~SOCK_TYPE_MASK;
	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;
	type &= SOCK_TYPE_MASK;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	retval = sock_create(family, type, protocol, &sock);
	if (retval < 0)
		goto out;

	retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
	if (retval < 0)
		goto out_release;

out:
	/* It may be already another descriptor 8) Not kernel problem. */
	return retval;

out_release:
	sock_release(sock);
	return retval;
}

/*
 *	Create a pair of connected sockets.
 */

SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
		int __user *, usockvec)
{
	struct socket *sock1, *sock2;
	int fd1, fd2, err;
	struct file *newfile1, *newfile2;
	int flags;

	flags = type & ~SOCK_TYPE_MASK;
	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;
	type &= SOCK_TYPE_MASK;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	/*
	 * Obtain the first socket and check if the underlying protocol
	 * supports the socketpair call.
	 */

	err = sock_create(family, type, protocol, &sock1);
	if (err < 0)
		goto out;

	err = sock_create(family, type, protocol, &sock2);
	if (err < 0)
		goto out_release_1;

	err = sock1->ops->socketpair(sock1, sock2);
	if (err < 0)
		goto out_release_both;

	fd1 = sock_alloc_file(sock1, &newfile1, flags);
	if (unlikely(fd1 < 0)) {
		err = fd1;
		goto out_release_both;
	}

	fd2 = sock_alloc_file(sock2, &newfile2, flags);
	if (unlikely(fd2 < 0)) {
		err = fd2;
		fput(newfile1);
		put_unused_fd(fd1);
		sock_release(sock2);
		goto out;
	}

	audit_fd_pair(fd1, fd2);
	fd_install(fd1, newfile1);
	fd_install(fd2, newfile2);
	/* fd1 and fd2 may be already another descriptors.
	 * Not kernel problem.
	 */

	err = put_user(fd1, &usockvec[0]);
	if (!err)
		err = put_user(fd2, &usockvec[1]);
	if (!err)
		return 0;

	sys_close(fd2);
	sys_close(fd1);
	return err;

out_release_both:
	sock_release(sock2);
out_release_1:
	sock_release(sock1);
out:
	return err;
}

/*
 *	Bind a name to a socket. Nothing much to do here since it's
 *	the protocol's responsibility to handle the local address.
 *
 *	We move the socket address to kernel space before we call
 *	the protocol layer (having also checked the address is ok).
 */

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
		if (err >= 0) {
			err = security_socket_bind(sock,
						   (struct sockaddr *)&address,
						   addrlen);
			if (!err)
				err = sock->ops->bind(sock,
						      (struct sockaddr *)
						      &address, addrlen);
		}
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Perform a listen. Basically, we allow the protocol to do anything
 *	necessary for a listen, and if that works, we mark the socket as
 *	ready for listening.
 */

SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
	struct socket *sock;
	int err, fput_needed;
	int somaxconn;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
		if ((unsigned)backlog > somaxconn)
			backlog = somaxconn;

		err = security_socket_listen(sock, backlog);
		if (!err)
			err = sock->ops->listen(sock, backlog);

		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	For accept, we attempt to create a new socket, set up the link
 *	with the client, wake up the client, then return the new
 *	connected fd. We collect the address of the connector in kernel
 *	space and move it to user at the very end. This is unclean because
 *	we open the socket then return an error.
 *
 *	1003.1g adds the ability to recvmsg() to query connection pending
 *	status to recvmsg. We need to add that support in a way thats
 *	clean when we restucture accept also.
 */

SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen, int, flags)
{
	struct socket *sock, *newsock;
	struct file *newfile;
	int err, len, newfd, fput_needed;
	struct sockaddr_storage address;

	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = -ENFILE;
	if (!(newsock = sock_alloc()))
		goto out_put;

	newsock->type = sock->type;
	newsock->ops = sock->ops;

	/*
	 * We don't need try_module_get here, as the listening socket (sock)
	 * has the protocol module (sock->ops->owner) held.
	 */
	__module_get(newsock->ops->owner);

	newfd = sock_alloc_file(newsock, &newfile, flags);
	if (unlikely(newfd < 0)) {
		err = newfd;
		sock_release(newsock);
		goto out_put;
	}

	err = security_socket_accept(sock, newsock);
	if (err)
		goto out_fd;

	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
	if (err < 0)
		goto out_fd;

	if (upeer_sockaddr) {
		if (newsock->ops->getname(newsock, (struct sockaddr *)&address,
					  &len, 2) < 0) {
			err = -ECONNABORTED;
			goto out_fd;
		}
		err = move_addr_to_user((struct sockaddr *)&address,
					len, upeer_sockaddr, upeer_addrlen);
		if (err < 0)
			goto out_fd;
	}

	/* File flags are not inherited via accept() unlike another OSes. */

	fd_install(newfd, newfile);
	err = newfd;

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
out_fd:
	fput(newfile);
	put_unused_fd(newfd);
	goto out_put;
}

SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen)
{
	return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
}

/*
 *	Attempt to connect to a socket with the server address.  The address
 *	is in user space so we verify it is OK and move it to kernel space.
 *
 *	For 1003.1g we need to add clean support for a bind to AF_UNSPEC to
 *	break bindings
 *
 *	NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and
 *	other SEQPACKET protocols that take time to connect() as it doesn't
 *	include the -EINPROGRESS status for such sockets.
 */

SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
		int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;
	err = move_addr_to_kernel(uservaddr, addrlen, (struct sockaddr *)&address);
	if (err < 0)
		goto out_put;

	err =
	    security_socket_connect(sock, (struct sockaddr *)&address, addrlen);
	if (err)
		goto out_put;

	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
				 sock->file->f_flags);
out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the local address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = security_socket_getsockname(sock);
	if (err)
		goto out_put;

	err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0);
	if (err)
		goto out_put;
	err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the remote address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getpeername(sock);
		if (err) {
			fput_light(sock->file, fput_needed);
			return err;
		}

		err =
		    sock->ops->getname(sock, (struct sockaddr *)&address, &len,
				       1);
		if (!err)
			err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr,
						usockaddr_len);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Send a datagram to a given address. We move the address into kernel
 *	space and check the user space data area is readable before invoking
 *	the protocol.
 */

SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
		unsigned, flags, struct sockaddr __user *, addr,
		int, addr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err;
	struct msghdr msg;
	struct iovec iov;
	int fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	iov.iov_base = buff;
	iov.iov_len = len;
	msg.msg_name = NULL;
	msg.msg_iov = &iov;
	msg.msg_iovlen = 1;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;
	if (addr) {
		err = move_addr_to_kernel(addr, addr_len, (struct sockaddr *)&address);
		if (err < 0)
			goto out_put;
		msg.msg_name = (struct sockaddr *)&address;
		msg.msg_namelen = addr_len;
	}
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	msg.msg_flags = flags;
	err = sock_sendmsg(sock, &msg, len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Send a datagram down a socket.
 */

SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
		unsigned, flags)
{
	return sys_sendto(fd, buff, len, flags, NULL, 0);
}

/*
 *	Receive a frame from the socket and optionally record the address of the
 *	sender. We verify the buffers are writable and if needed move the
 *	sender address from kernel to user space.
 */

SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
		unsigned, flags, struct sockaddr __user *, addr,
		int __user *, addr_len)
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	struct sockaddr_storage address;
	int err, err2;
	int fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_iovlen = 1;
	msg.msg_iov = &iov;
	iov.iov_len = size;
	iov.iov_base = ubuf;
	msg.msg_name = (struct sockaddr *)&address;
	msg.msg_namelen = sizeof(address);
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = sock_recvmsg(sock, &msg, size, flags);

	if (err >= 0 && addr != NULL) {
		err2 = move_addr_to_user((struct sockaddr *)&address,
					 msg.msg_namelen, addr, addr_len);
		if (err2 < 0)
			err = err2;
	}

	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Receive a datagram from a socket.
 */

asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size,
			 unsigned flags)
{
	return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
}

/*
 *	Set a socket option. Because we don't know the option lengths we have
 *	to pass the user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	if (optlen < 0)
		return -EINVAL;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_setsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_setsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->setsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Get a socket option. Because we don't know the option lengths we have
 *	to pass a user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int __user *, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_getsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->getsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Shutdown a socket.
 */

SYSCALL_DEFINE2(shutdown, int, fd, int, how)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_shutdown(sock, how);
		if (!err)
			err = sock->ops->shutdown(sock, how);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/* A couple of helpful macros for getting the address of the 32/64 bit
 * fields which are the same type (int / unsigned) on our platforms.
 */
#define COMPAT_MSG(msg, member)	((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member)
#define COMPAT_NAMELEN(msg)	COMPAT_MSG(msg, msg_namelen)
#define COMPAT_FLAGS(msg)	COMPAT_MSG(msg, msg_flags)

/*
 *	BSD sendmsg interface
 */

SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags)
{
	struct compat_msghdr __user *msg_compat =
	    (struct compat_msghdr __user *)msg;
	struct socket *sock;
	struct sockaddr_storage address;
	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
	unsigned char ctl[sizeof(struct cmsghdr) + 20]
	    __attribute__ ((aligned(sizeof(__kernel_size_t))));
	/* 20 is size of ipv6_pktinfo */
	unsigned char *ctl_buf = ctl;
	struct msghdr msg_sys;
	int err, ctl_len, iov_size, total_len;
	int fput_needed;

	err = -EFAULT;
	if (MSG_CMSG_COMPAT & flags) {
		if (get_compat_msghdr(&msg_sys, msg_compat))
			return -EFAULT;
	}
	else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr)))
		return -EFAULT;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	/* do not move before msg_sys is valid */
	err = -EMSGSIZE;
	if (msg_sys.msg_iovlen > UIO_MAXIOV)
		goto out_put;

	/* Check whether to allocate the iovec area */
	err = -ENOMEM;
	iov_size = msg_sys.msg_iovlen * sizeof(struct iovec);
	if (msg_sys.msg_iovlen > UIO_FASTIOV) {
		iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL);
		if (!iov)
			goto out_put;
	}

	/* This will also move the address data into kernel space */
	if (MSG_CMSG_COMPAT & flags) {
		err = verify_compat_iovec(&msg_sys, iov,
					  (struct sockaddr *)&address,
					  VERIFY_READ);
	} else
		err = verify_iovec(&msg_sys, iov,
				   (struct sockaddr *)&address,
				   VERIFY_READ);
	if (err < 0)
		goto out_freeiov;
	total_len = err;

	err = -ENOBUFS;

	if (msg_sys.msg_controllen > INT_MAX)
		goto out_freeiov;
	ctl_len = msg_sys.msg_controllen;
	if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
		err =
		    cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl,
						     sizeof(ctl));
		if (err)
			goto out_freeiov;
		ctl_buf = msg_sys.msg_control;
		ctl_len = msg_sys.msg_controllen;
	} else if (ctl_len) {
		if (ctl_len > sizeof(ctl)) {
			ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL);
			if (ctl_buf == NULL)
				goto out_freeiov;
		}
		err = -EFAULT;
		/*
		 * Careful! Before this, msg_sys.msg_control contains a user pointer.
		 * Afterwards, it will be a kernel pointer. Thus the compiler-assisted
		 * checking falls down on this.
		 */
		if (copy_from_user(ctl_buf, (void __user *)msg_sys.msg_control,
				   ctl_len))
			goto out_freectl;
		msg_sys.msg_control = ctl_buf;
	}
	msg_sys.msg_flags = flags;

	if (sock->file->f_flags & O_NONBLOCK)
		msg_sys.msg_flags |= MSG_DONTWAIT;
	err = sock_sendmsg(sock, &msg_sys, total_len);

out_freectl:
	if (ctl_buf != ctl)
		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
out_freeiov:
	if (iov != iovstack)
		sock_kfree_s(sock->sk, iov, iov_size);
out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
			 struct msghdr *msg_sys, unsigned flags, int nosec)
{
	struct compat_msghdr __user *msg_compat =
	    (struct compat_msghdr __user *)msg;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov = iovstack;
	unsigned long cmsg_ptr;
	int err, iov_size, total_len, len;

	/* kernel mode address */
	struct sockaddr_storage addr;

	/* user mode address pointers */
	struct sockaddr __user *uaddr;
	int __user *uaddr_len;

	if (MSG_CMSG_COMPAT & flags) {
		if (get_compat_msghdr(msg_sys, msg_compat))
			return -EFAULT;
	}
	else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
		return -EFAULT;

	err = -EMSGSIZE;
	if (msg_sys->msg_iovlen > UIO_MAXIOV)
		goto out;

	/* Check whether to allocate the iovec area */
	err = -ENOMEM;
	iov_size = msg_sys->msg_iovlen * sizeof(struct iovec);
	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
		iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL);
		if (!iov)
			goto out;
	}

	/*
	 *      Save the user-mode address (verify_iovec will change the
	 *      kernel msghdr to use the kernel address space)
	 */

	uaddr = (__force void __user *)msg_sys->msg_name;
	uaddr_len = COMPAT_NAMELEN(msg);
	if (MSG_CMSG_COMPAT & flags) {
		err = verify_compat_iovec(msg_sys, iov,
					  (struct sockaddr *)&addr,
					  VERIFY_WRITE);
	} else
		err = verify_iovec(msg_sys, iov,
				   (struct sockaddr *)&addr,
				   VERIFY_WRITE);
	if (err < 0)
		goto out_freeiov;
	total_len = err;

	cmsg_ptr = (unsigned long)msg_sys->msg_control;
	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);

	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
							  total_len, flags);
	if (err < 0)
		goto out_freeiov;
	len = err;

	if (uaddr != NULL) {
		err = move_addr_to_user((struct sockaddr *)&addr,
					msg_sys->msg_namelen, uaddr,
					uaddr_len);
		if (err < 0)
			goto out_freeiov;
	}
	err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT),
			 COMPAT_FLAGS(msg));
	if (err)
		goto out_freeiov;
	if (MSG_CMSG_COMPAT & flags)
		err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr,
				 &msg_compat->msg_controllen);
	else
		err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr,
				 &msg->msg_controllen);
	if (err)
		goto out_freeiov;
	err = len;

out_freeiov:
	if (iov != iovstack)
		sock_kfree_s(sock->sk, iov, iov_size);
out:
	return err;
}

/*
 *	BSD recvmsg interface
 */

SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg,
		unsigned int, flags)
{
	int fput_needed, err;
	struct msghdr msg_sys;
	struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed);

	if (!sock)
		goto out;

	err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0);

	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *     Linux recvmmsg interface
 */

int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
		   unsigned int flags, struct timespec *timeout)
{
	int fput_needed, err, datagrams;
	struct socket *sock;
	struct mmsghdr __user *entry;
	struct compat_mmsghdr __user *compat_entry;
	struct msghdr msg_sys;
	struct timespec end_time;

	if (timeout &&
	    poll_select_set_timeout(&end_time, timeout->tv_sec,
				    timeout->tv_nsec))
		return -EINVAL;

	datagrams = 0;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		return err;

	err = sock_error(sock->sk);
	if (err)
		goto out_put;

	entry = mmsg;
	compat_entry = (struct compat_mmsghdr __user *)mmsg;

	while (datagrams < vlen) {
		/*
		 * No need to ask LSM for more than the first datagram.
		 */
		if (MSG_CMSG_COMPAT & flags) {
			err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
					    &msg_sys, flags, datagrams);
			if (err < 0)
				break;
			err = __put_user(err, &compat_entry->msg_len);
			++compat_entry;
		} else {
			err = __sys_recvmsg(sock, (struct msghdr __user *)entry,
					    &msg_sys, flags, datagrams);
			if (err < 0)
				break;
			err = put_user(err, &entry->msg_len);
			++entry;
		}

		if (err)
			break;
		++datagrams;

		/* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */
		if (flags & MSG_WAITFORONE)
			flags |= MSG_DONTWAIT;

		if (timeout) {
			ktime_get_ts(timeout);
			*timeout = timespec_sub(end_time, *timeout);
			if (timeout->tv_sec < 0) {
				timeout->tv_sec = timeout->tv_nsec = 0;
				break;
			}

			/* Timeout, return less than vlen datagrams */
			if (timeout->tv_nsec == 0 && timeout->tv_sec == 0)
				break;
		}

		/* Out of band data, return right away */
		if (msg_sys.msg_flags & MSG_OOB)
			break;
	}

out_put:
	fput_light(sock->file, fput_needed);

	if (err == 0)
		return datagrams;

	if (datagrams != 0) {
		/*
		 * We may return less entries than requested (vlen) if the
		 * sock is non block and there aren't enough datagrams...
		 */
		if (err != -EAGAIN) {
			/*
			 * ... or  if recvmsg returns an error after we
			 * received some datagrams, where we record the
			 * error to return on the next call or if the
			 * app asks about it using getsockopt(SO_ERROR).
			 */
			sock->sk->sk_err = -err;
		}

		return datagrams;
	}

	return err;
}

SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
		unsigned int, vlen, unsigned int, flags,
		struct timespec __user *, timeout)
{
	int datagrams;
	struct timespec timeout_sys;

	if (!timeout)
		return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL);

	if (copy_from_user(&timeout_sys, timeout, sizeof(timeout_sys)))
		return -EFAULT;

	datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys);

	if (datagrams > 0 &&
	    copy_to_user(timeout, &timeout_sys, sizeof(timeout_sys)))
		datagrams = -EFAULT;

	return datagrams;
}

#ifdef __ARCH_WANT_SYS_SOCKETCALL
/* Argument list sizes for sys_socketcall */
#define AL(x) ((x) * sizeof(unsigned long))
static const unsigned char nargs[20] = {
	AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
	AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
	AL(6),AL(2),AL(5),AL(5),AL(3),AL(3),
	AL(4),AL(5)
};

#undef AL

/*
 *	System call vectors.
 *
 *	Argument checking cleaned up. Saved 20% in size.
 *  This function doesn't need to set the kernel lock because
 *  it is set by the callees.
 */

SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
{
	unsigned long a[6];
	unsigned long a0, a1;
	int err;
	unsigned int len;

	if (call < 1 || call > SYS_RECVMMSG)
		return -EINVAL;

	len = nargs[call];
	if (len > sizeof(a))
		return -EINVAL;

	/* copy_from_user should be SMP safe. */
	if (copy_from_user(a, args, len))
		return -EFAULT;

	audit_socketcall(nargs[call] / sizeof(unsigned long), a);

	a0 = a[0];
	a1 = a[1];

	switch (call) {
	case SYS_SOCKET:
		err = sys_socket(a0, a1, a[2]);
		break;
	case SYS_BIND:
		err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
		break;
	case SYS_CONNECT:
		err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
		break;
	case SYS_LISTEN:
		err = sys_listen(a0, a1);
		break;
	case SYS_ACCEPT:
		err = sys_accept4(a0, (struct sockaddr __user *)a1,
				  (int __user *)a[2], 0);
		break;
	case SYS_GETSOCKNAME:
		err =
		    sys_getsockname(a0, (struct sockaddr __user *)a1,
				    (int __user *)a[2]);
		break;
	case SYS_GETPEERNAME:
		err =
		    sys_getpeername(a0, (struct sockaddr __user *)a1,
				    (int __user *)a[2]);
		break;
	case SYS_SOCKETPAIR:
		err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
		break;
	case SYS_SEND:
		err = sys_send(a0, (void __user *)a1, a[2], a[3]);
		break;
	case SYS_SENDTO:
		err = sys_sendto(a0, (void __user *)a1, a[2], a[3],
				 (struct sockaddr __user *)a[4], a[5]);
		break;
	case SYS_RECV:
		err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
		break;
	case SYS_RECVFROM:
		err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
				   (struct sockaddr __user *)a[4],
				   (int __user *)a[5]);
		break;
	case SYS_SHUTDOWN:
		err = sys_shutdown(a0, a1);
		break;
	case SYS_SETSOCKOPT:
		err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
		break;
	case SYS_GETSOCKOPT:
		err =
		    sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
				   (int __user *)a[4]);
		break;
	case SYS_SENDMSG:
		err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]);
		break;
	case SYS_RECVMSG:
		err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]);
		break;
	case SYS_RECVMMSG:
		err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3],
				   (struct timespec __user *)a[4]);
		break;
	case SYS_ACCEPT4:
		err = sys_accept4(a0, (struct sockaddr __user *)a1,
				  (int __user *)a[2], a[3]);
		break;
	default:
		err = -EINVAL;
		break;
	}
	return err;
}

#endif				/* __ARCH_WANT_SYS_SOCKETCALL */

/**
 *	sock_register - add a socket protocol handler
 *	@ops: description of protocol
 *
 *	This function is called by a protocol handler that wants to
 *	advertise its address family, and have it linked into the
 *	socket interface. The value ops->family coresponds to the
 *	socket system call protocol family.
 */
int sock_register(const struct net_proto_family *ops)
{
	int err;

	if (ops->family >= NPROTO) {
		printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family,
		       NPROTO);
		return -ENOBUFS;
	}

	spin_lock(&net_family_lock);
	if (net_families[ops->family])
		err = -EEXIST;
	else {
		net_families[ops->family] = ops;
		err = 0;
	}
	spin_unlock(&net_family_lock);

	printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family);
	return err;
}

/**
 *	sock_unregister - remove a protocol handler
 *	@family: protocol family to remove
 *
 *	This function is called by a protocol handler that wants to
 *	remove its address family, and have it unlinked from the
 *	new socket creation.
 *
 *	If protocol handler is a module, then it can use module reference
 *	counts to protect against new references. If protocol handler is not
 *	a module then it needs to provide its own protection in
 *	the ops->create routine.
 */
void sock_unregister(int family)
{
	BUG_ON(family < 0 || family >= NPROTO);

	spin_lock(&net_family_lock);
	net_families[family] = NULL;
	spin_unlock(&net_family_lock);

	synchronize_rcu();

	printk(KERN_INFO "NET: Unregistered protocol family %d\n", family);
}

static int __init sock_init(void)
{
	/*
	 *      Initialize sock SLAB cache.
	 */

	sk_init();

	/*
	 *      Initialize skbuff SLAB cache
	 */
	skb_init();

	/*
	 *      Initialize the protocols module.
	 */

	init_inodecache();
	register_filesystem(&sock_fs_type);
	sock_mnt = kern_mount(&sock_fs_type);

	/* The real protocol initialization is performed in later initcalls.
	 */

#ifdef CONFIG_NETFILTER
	netfilter_init();
#endif

	return 0;
}

core_initcall(sock_init);	/* early initcall */

#ifdef CONFIG_PROC_FS
void socket_seq_show(struct seq_file *seq)
{
	int cpu;
	int counter = 0;

	for_each_possible_cpu(cpu)
	    counter += per_cpu(sockets_in_use, cpu);

	/* It can be negative, by the way. 8) */
	if (counter < 0)
		counter = 0;

	seq_printf(seq, "sockets: used %d\n", counter);
}
#endif				/* CONFIG_PROC_FS */

#ifdef CONFIG_COMPAT
static int do_siocgstamp(struct net *net, struct socket *sock,
			 unsigned int cmd, struct compat_timeval __user *up)
{
	mm_segment_t old_fs = get_fs();
	struct timeval ktv;
	int err;

	set_fs(KERNEL_DS);
	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
	set_fs(old_fs);
	if (!err) {
		err = put_user(ktv.tv_sec, &up->tv_sec);
		err |= __put_user(ktv.tv_usec, &up->tv_usec);
	}
	return err;
}

static int do_siocgstampns(struct net *net, struct socket *sock,
			 unsigned int cmd, struct compat_timespec __user *up)
{
	mm_segment_t old_fs = get_fs();
	struct timespec kts;
	int err;

	set_fs(KERNEL_DS);
	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
	set_fs(old_fs);
	if (!err) {
		err = put_user(kts.tv_sec, &up->tv_sec);
		err |= __put_user(kts.tv_nsec, &up->tv_nsec);
	}
	return err;
}

static int dev_ifname32(struct net *net, struct compat_ifreq __user *uifr32)
{
	struct ifreq __user *uifr;
	int err;

	uifr = compat_alloc_user_space(sizeof(struct ifreq));
	if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq)))
		return -EFAULT;

	err = dev_ioctl(net, SIOCGIFNAME, uifr);
	if (err)
		return err;

	if (copy_in_user(uifr32, uifr, sizeof(struct compat_ifreq)))
		return -EFAULT;

	return 0;
}

static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
{
	struct compat_ifconf ifc32;
	struct ifconf ifc;
	struct ifconf __user *uifc;
	struct compat_ifreq __user *ifr32;
	struct ifreq __user *ifr;
	unsigned int i, j;
	int err;

	if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf)))
		return -EFAULT;

	if (ifc32.ifcbuf == 0) {
		ifc32.ifc_len = 0;
		ifc.ifc_len = 0;
		ifc.ifc_req = NULL;
		uifc = compat_alloc_user_space(sizeof(struct ifconf));
	} else {
		size_t len =((ifc32.ifc_len / sizeof (struct compat_ifreq)) + 1) *
			sizeof (struct ifreq);
		uifc = compat_alloc_user_space(sizeof(struct ifconf) + len);
		ifc.ifc_len = len;
		ifr = ifc.ifc_req = (void __user *)(uifc + 1);
		ifr32 = compat_ptr(ifc32.ifcbuf);
		for (i = 0; i < ifc32.ifc_len; i += sizeof (struct compat_ifreq)) {
			if (copy_in_user(ifr, ifr32, sizeof(struct compat_ifreq)))
				return -EFAULT;
			ifr++;
			ifr32++;
		}
	}
	if (copy_to_user(uifc, &ifc, sizeof(struct ifconf)))
		return -EFAULT;

	err = dev_ioctl(net, SIOCGIFCONF, uifc);
	if (err)
		return err;

	if (copy_from_user(&ifc, uifc, sizeof(struct ifconf)))
		return -EFAULT;

	ifr = ifc.ifc_req;
	ifr32 = compat_ptr(ifc32.ifcbuf);
	for (i = 0, j = 0;
             i + sizeof (struct compat_ifreq) <= ifc32.ifc_len && j < ifc.ifc_len;
	     i += sizeof (struct compat_ifreq), j += sizeof (struct ifreq)) {
		if (copy_in_user(ifr32, ifr, sizeof (struct compat_ifreq)))
			return -EFAULT;
		ifr32++;
		ifr++;
	}

	if (ifc32.ifcbuf == 0) {
		/* Translate from 64-bit structure multiple to
		 * a 32-bit one.
		 */
		i = ifc.ifc_len;
		i = ((i / sizeof(struct ifreq)) * sizeof(struct compat_ifreq));
		ifc32.ifc_len = i;
	} else {
		ifc32.ifc_len = i;
	}
	if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf)))
		return -EFAULT;

	return 0;
}

static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32)
{
	struct ifreq __user *ifr;
	u32 data;
	void __user *datap;

	ifr = compat_alloc_user_space(sizeof(*ifr));

	if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ))
		return -EFAULT;

	if (get_user(data, &ifr32->ifr_ifru.ifru_data))
		return -EFAULT;

	datap = compat_ptr(data);
	if (put_user(datap, &ifr->ifr_ifru.ifru_data))
		return -EFAULT;

	return dev_ioctl(net, SIOCETHTOOL, ifr);
}

static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32)
{
	void __user *uptr;
	compat_uptr_t uptr32;
	struct ifreq __user *uifr;

	uifr = compat_alloc_user_space(sizeof (*uifr));
	if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq)))
		return -EFAULT;

	if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu))
		return -EFAULT;

	uptr = compat_ptr(uptr32);

	if (put_user(uptr, &uifr->ifr_settings.ifs_ifsu.raw_hdlc))
		return -EFAULT;

	return dev_ioctl(net, SIOCWANDEV, uifr);
}

static int bond_ioctl(struct net *net, unsigned int cmd,
			 struct compat_ifreq __user *ifr32)
{
	struct ifreq kifr;
	struct ifreq __user *uifr;
	mm_segment_t old_fs;
	int err;
	u32 data;
	void __user *datap;

	switch (cmd) {
	case SIOCBONDENSLAVE:
	case SIOCBONDRELEASE:
	case SIOCBONDSETHWADDR:
	case SIOCBONDCHANGEACTIVE:
		if (copy_from_user(&kifr, ifr32, sizeof(struct compat_ifreq)))
			return -EFAULT;

		old_fs = get_fs();
		set_fs (KERNEL_DS);
		err = dev_ioctl(net, cmd, &kifr);
		set_fs (old_fs);

		return err;
	case SIOCBONDSLAVEINFOQUERY:
	case SIOCBONDINFOQUERY:
		uifr = compat_alloc_user_space(sizeof(*uifr));
		if (copy_in_user(&uifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ))
			return -EFAULT;

		if (get_user(data, &ifr32->ifr_ifru.ifru_data))
			return -EFAULT;

		datap = compat_ptr(data);
		if (put_user(datap, &uifr->ifr_ifru.ifru_data))
			return -EFAULT;

		return dev_ioctl(net, cmd, uifr);
	default:
		return -EINVAL;
	};
}

static int siocdevprivate_ioctl(struct net *net, unsigned int cmd,
				 struct compat_ifreq __user *u_ifreq32)
{
	struct ifreq __user *u_ifreq64;
	char tmp_buf[IFNAMSIZ];
	void __user *data64;
	u32 data32;

	if (copy_from_user(&tmp_buf[0], &(u_ifreq32->ifr_ifrn.ifrn_name[0]),
			   IFNAMSIZ))
		return -EFAULT;
	if (__get_user(data32, &u_ifreq32->ifr_ifru.ifru_data))
		return -EFAULT;
	data64 = compat_ptr(data32);

	u_ifreq64 = compat_alloc_user_space(sizeof(*u_ifreq64));

	/* Don't check these user accesses, just let that get trapped
	 * in the ioctl handler instead.
	 */
	if (copy_to_user(&u_ifreq64->ifr_ifrn.ifrn_name[0], &tmp_buf[0],
			 IFNAMSIZ))
		return -EFAULT;
	if (__put_user(data64, &u_ifreq64->ifr_ifru.ifru_data))
		return -EFAULT;

	return dev_ioctl(net, cmd, u_ifreq64);
}

static int dev_ifsioc(struct net *net, struct socket *sock,
			 unsigned int cmd, struct compat_ifreq __user *uifr32)
{
	struct ifreq __user *uifr;
	int err;

	uifr = compat_alloc_user_space(sizeof(*uifr));
	if (copy_in_user(uifr, uifr32, sizeof(*uifr32)))
		return -EFAULT;

	err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr);

	if (!err) {
		switch (cmd) {
		case SIOCGIFFLAGS:
		case SIOCGIFMETRIC:
		case SIOCGIFMTU:
		case SIOCGIFMEM:
		case SIOCGIFHWADDR:
		case SIOCGIFINDEX:
		case SIOCGIFADDR:
		case SIOCGIFBRDADDR:
		case SIOCGIFDSTADDR:
		case SIOCGIFNETMASK:
		case SIOCGIFPFLAGS:
		case SIOCGIFTXQLEN:
		case SIOCGMIIPHY:
		case SIOCGMIIREG:
			if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
				err = -EFAULT;
			break;
		}
	}
	return err;
}

static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
			struct compat_ifreq __user *uifr32)
{
	struct ifreq ifr;
	struct compat_ifmap __user *uifmap32;
	mm_segment_t old_fs;
	int err;

	uifmap32 = &uifr32->ifr_ifru.ifru_map;
	err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name));
	err |= __get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
	err |= __get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
	err |= __get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
	err |= __get_user(ifr.ifr_map.irq, &uifmap32->irq);
	err |= __get_user(ifr.ifr_map.dma, &uifmap32->dma);
	err |= __get_user(ifr.ifr_map.port, &uifmap32->port);
	if (err)
		return -EFAULT;

	old_fs = get_fs();
	set_fs (KERNEL_DS);
	err = dev_ioctl(net, cmd, (void __user *)&ifr);
	set_fs (old_fs);

	if (cmd == SIOCGIFMAP && !err) {
		err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name));
		err |= __put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
		err |= __put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
		err |= __put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
		err |= __put_user(ifr.ifr_map.irq, &uifmap32->irq);
		err |= __put_user(ifr.ifr_map.dma, &uifmap32->dma);
		err |= __put_user(ifr.ifr_map.port, &uifmap32->port);
		if (err)
			err = -EFAULT;
	}
	return err;
}

static int compat_siocshwtstamp(struct net *net, struct compat_ifreq __user *uifr32)
{
	void __user *uptr;
	compat_uptr_t uptr32;
	struct ifreq __user *uifr;

	uifr = compat_alloc_user_space(sizeof (*uifr));
	if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq)))
		return -EFAULT;

	if (get_user(uptr32, &uifr32->ifr_data))
		return -EFAULT;

	uptr = compat_ptr(uptr32);

	if (put_user(uptr, &uifr->ifr_data))
		return -EFAULT;

	return dev_ioctl(net, SIOCSHWTSTAMP, uifr);
}

struct rtentry32 {
	u32   		rt_pad1;
	struct sockaddr rt_dst;         /* target address               */
	struct sockaddr rt_gateway;     /* gateway addr (RTF_GATEWAY)   */
	struct sockaddr rt_genmask;     /* target network mask (IP)     */
	unsigned short  rt_flags;
	short           rt_pad2;
	u32   		rt_pad3;
	unsigned char   rt_tos;
	unsigned char   rt_class;
	short           rt_pad4;
	short           rt_metric;      /* +1 for binary compatibility! */
	/* char * */ u32 rt_dev;        /* forcing the device at add    */
	u32   		rt_mtu;         /* per route MTU/Window         */
	u32   		rt_window;      /* Window clamping              */
	unsigned short  rt_irtt;        /* Initial RTT                  */
};

struct in6_rtmsg32 {
	struct in6_addr		rtmsg_dst;
	struct in6_addr		rtmsg_src;
	struct in6_addr		rtmsg_gateway;
	u32			rtmsg_type;
	u16			rtmsg_dst_len;
	u16			rtmsg_src_len;
	u32			rtmsg_metric;
	u32			rtmsg_info;
	u32			rtmsg_flags;
	s32			rtmsg_ifindex;
};

static int routing_ioctl(struct net *net, struct socket *sock,
			 unsigned int cmd, void __user *argp)
{
	int ret;
	void *r = NULL;
	struct in6_rtmsg r6;
	struct rtentry r4;
	char devname[16];
	u32 rtdev;
	mm_segment_t old_fs = get_fs();

	if (sock && sock->sk && sock->sk->sk_family == AF_INET6) { /* ipv6 */
		struct in6_rtmsg32 __user *ur6 = argp;
		ret = copy_from_user (&r6.rtmsg_dst, &(ur6->rtmsg_dst),
			3 * sizeof(struct in6_addr));
		ret |= __get_user (r6.rtmsg_type, &(ur6->rtmsg_type));
		ret |= __get_user (r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
		ret |= __get_user (r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
		ret |= __get_user (r6.rtmsg_metric, &(ur6->rtmsg_metric));
		ret |= __get_user (r6.rtmsg_info, &(ur6->rtmsg_info));
		ret |= __get_user (r6.rtmsg_flags, &(ur6->rtmsg_flags));
		ret |= __get_user (r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));

		r = (void *) &r6;
	} else { /* ipv4 */
		struct rtentry32 __user *ur4 = argp;
		ret = copy_from_user (&r4.rt_dst, &(ur4->rt_dst),
					3 * sizeof(struct sockaddr));
		ret |= __get_user (r4.rt_flags, &(ur4->rt_flags));
		ret |= __get_user (r4.rt_metric, &(ur4->rt_metric));
		ret |= __get_user (r4.rt_mtu, &(ur4->rt_mtu));
		ret |= __get_user (r4.rt_window, &(ur4->rt_window));
		ret |= __get_user (r4.rt_irtt, &(ur4->rt_irtt));
		ret |= __get_user (rtdev, &(ur4->rt_dev));
		if (rtdev) {
			ret |= copy_from_user (devname, compat_ptr(rtdev), 15);
			r4.rt_dev = devname; devname[15] = 0;
		} else
			r4.rt_dev = NULL;

		r = (void *) &r4;
	}

	if (ret) {
		ret = -EFAULT;
		goto out;
	}

	set_fs (KERNEL_DS);
	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
	set_fs (old_fs);

out:
	return ret;
}

/* Since old style bridge ioctl's endup using SIOCDEVPRIVATE
 * for some operations; this forces use of the newer bridge-utils that
 * use compatiable ioctls
 */
static int old_bridge_ioctl(compat_ulong_t __user *argp)
{
	compat_ulong_t tmp;

	if (get_user(tmp, argp))
		return -EFAULT;
	if (tmp == BRCTL_GET_VERSION)
		return BRCTL_VERSION + 1;
	return -EINVAL;
}

static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
			 unsigned int cmd, unsigned long arg)
{
	void __user *argp = compat_ptr(arg);
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);

	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))
		return siocdevprivate_ioctl(net, cmd, argp);

	switch (cmd) {
	case SIOCSIFBR:
	case SIOCGIFBR:
		return old_bridge_ioctl(argp);
	case SIOCGIFNAME:
		return dev_ifname32(net, argp);
	case SIOCGIFCONF:
		return dev_ifconf(net, argp);
	case SIOCETHTOOL:
		return ethtool_ioctl(net, argp);
	case SIOCWANDEV:
		return compat_siocwandev(net, argp);
	case SIOCGIFMAP:
	case SIOCSIFMAP:
		return compat_sioc_ifmap(net, cmd, argp);
	case SIOCBONDENSLAVE:
	case SIOCBONDRELEASE:
	case SIOCBONDSETHWADDR:
	case SIOCBONDSLAVEINFOQUERY:
	case SIOCBONDINFOQUERY:
	case SIOCBONDCHANGEACTIVE:
		return bond_ioctl(net, cmd, argp);
	case SIOCADDRT:
	case SIOCDELRT:
		return routing_ioctl(net, sock, cmd, argp);
	case SIOCGSTAMP:
		return do_siocgstamp(net, sock, cmd, argp);
	case SIOCGSTAMPNS:
		return do_siocgstampns(net, sock, cmd, argp);
	case SIOCSHWTSTAMP:
		return compat_siocshwtstamp(net, argp);

	case FIOSETOWN:
	case SIOCSPGRP:
	case FIOGETOWN:
	case SIOCGPGRP:
	case SIOCBRADDBR:
	case SIOCBRDELBR:
	case SIOCGIFVLAN:
	case SIOCSIFVLAN:
	case SIOCADDDLCI:
	case SIOCDELDLCI:
		return sock_ioctl(file, cmd, arg);

	case SIOCGIFFLAGS:
	case SIOCSIFFLAGS:
	case SIOCGIFMETRIC:
	case SIOCSIFMETRIC:
	case SIOCGIFMTU:
	case SIOCSIFMTU:
	case SIOCGIFMEM:
	case SIOCSIFMEM:
	case SIOCGIFHWADDR:
	case SIOCSIFHWADDR:
	case SIOCADDMULTI:
	case SIOCDELMULTI:
	case SIOCGIFINDEX:
	case SIOCGIFADDR:
	case SIOCSIFADDR:
	case SIOCSIFHWBROADCAST:
	case SIOCDIFADDR:
	case SIOCGIFBRDADDR:
	case SIOCSIFBRDADDR:
	case SIOCGIFDSTADDR:
	case SIOCSIFDSTADDR:
	case SIOCGIFNETMASK:
	case SIOCSIFNETMASK:
	case SIOCSIFPFLAGS:
	case SIOCGIFPFLAGS:
	case SIOCGIFTXQLEN:
	case SIOCSIFTXQLEN:
	case SIOCBRADDIF:
	case SIOCBRDELIF:
	case SIOCSIFNAME:
	case SIOCGMIIPHY:
	case SIOCGMIIREG:
	case SIOCSMIIREG:
		return dev_ifsioc(net, sock, cmd, argp);

	case SIOCSARP:
	case SIOCGARP:
	case SIOCDARP:
	case SIOCATMARK:
		return sock_do_ioctl(net, sock, cmd, arg);
	}

	/* Prevent warning from compat_sys_ioctl, these always
	 * result in -EINVAL in the native case anyway. */
	switch (cmd) {
	case SIOCRTMSG:
	case SIOCGIFCOUNT:
	case SIOCSRARP:
	case SIOCGRARP:
	case SIOCDRARP:
	case SIOCSIFLINK:
	case SIOCGIFSLAVE:
	case SIOCSIFSLAVE:
		return -EINVAL;
	}

	return -ENOIOCTLCMD;
}

static long compat_sock_ioctl(struct file *file, unsigned cmd,
			      unsigned long arg)
{
	struct socket *sock = file->private_data;
	int ret = -ENOIOCTLCMD;
	struct sock *sk;
	struct net *net;

	sk = sock->sk;
	net = sock_net(sk);

	if (sock->ops->compat_ioctl)
		ret = sock->ops->compat_ioctl(sock, cmd, arg);

	if (ret == -ENOIOCTLCMD &&
	    (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST))
		ret = compat_wext_handle_ioctl(net, cmd, arg);

	if (ret == -ENOIOCTLCMD)
		ret = compat_sock_ioctl_trans(file, sock, cmd, arg);

	return ret;
}
#endif

int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
{
	return sock->ops->bind(sock, addr, addrlen);
}

int kernel_listen(struct socket *sock, int backlog)
{
	return sock->ops->listen(sock, backlog);
}

int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
{
	struct sock *sk = sock->sk;
	int err;

	err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol,
			       newsock);
	if (err < 0)
		goto done;

	err = sock->ops->accept(sock, *newsock, flags);
	if (err < 0) {
		sock_release(*newsock);
		*newsock = NULL;
		goto done;
	}

	(*newsock)->ops = sock->ops;
	__module_get((*newsock)->ops->owner);

done:
	return err;
}

int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
		   int flags)
{
	return sock->ops->connect(sock, addr, addrlen, flags);
}

int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
			 int *addrlen)
{
	return sock->ops->getname(sock, addr, addrlen, 0);
}

int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
			 int *addrlen)
{
	return sock->ops->getname(sock, addr, addrlen, 1);
}

int kernel_getsockopt(struct socket *sock, int level, int optname,
			char *optval, int *optlen)
{
	mm_segment_t oldfs = get_fs();
	int err;

	set_fs(KERNEL_DS);
	if (level == SOL_SOCKET)
		err = sock_getsockopt(sock, level, optname, optval, optlen);
	else
		err = sock->ops->getsockopt(sock, level, optname, optval,
					    optlen);
	set_fs(oldfs);
	return err;
}

int kernel_setsockopt(struct socket *sock, int level, int optname,
			char *optval, unsigned int optlen)
{
	mm_segment_t oldfs = get_fs();
	int err;

	set_fs(KERNEL_DS);
	if (level == SOL_SOCKET)
		err = sock_setsockopt(sock, level, optname, optval, optlen);
	else
		err = sock->ops->setsockopt(sock, level, optname, optval,
					    optlen);
	set_fs(oldfs);
	return err;
}

int kernel_sendpage(struct socket *sock, struct page *page, int offset,
		    size_t size, int flags)
{
	if (sock->ops->sendpage)
		return sock->ops->sendpage(sock, page, offset, size, flags);

	return sock_no_sendpage(sock, page, offset, size, flags);
}

int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg)
{
	mm_segment_t oldfs = get_fs();
	int err;

	set_fs(KERNEL_DS);
	err = sock->ops->ioctl(sock, cmd, arg);
	set_fs(oldfs);

	return err;
}

int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
{
	return sock->ops->shutdown(sock, how);
}

EXPORT_SYMBOL(sock_create);
EXPORT_SYMBOL(sock_create_kern);
EXPORT_SYMBOL(sock_create_lite);
EXPORT_SYMBOL(sock_map_fd);
EXPORT_SYMBOL(sock_recvmsg);
EXPORT_SYMBOL(sock_register);
EXPORT_SYMBOL(sock_release);
EXPORT_SYMBOL(sock_sendmsg);
EXPORT_SYMBOL(sock_unregister);
EXPORT_SYMBOL(sock_wake_async);
EXPORT_SYMBOL(sockfd_lookup);
EXPORT_SYMBOL(kernel_sendmsg);
EXPORT_SYMBOL(kernel_recvmsg);
EXPORT_SYMBOL(kernel_bind);
EXPORT_SYMBOL(kernel_listen);
EXPORT_SYMBOL(kernel_accept);
EXPORT_SYMBOL(kernel_connect);
EXPORT_SYMBOL(kernel_getsockname);
EXPORT_SYMBOL(kernel_getpeername);
EXPORT_SYMBOL(kernel_getsockopt);
EXPORT_SYMBOL(kernel_setsockopt);
EXPORT_SYMBOL(kernel_sendpage);
EXPORT_SYMBOL(kernel_sock_ioctl);
EXPORT_SYMBOL(kernel_sock_shutdown);