aboutsummaryrefslogtreecommitdiff
path: root/net/core/sock.c
blob: d8e0aed19903439d41a63f4a677019bb6ecfa8a1 (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
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Generic socket support routines. Memory allocators, socket lock/release
 *		handler for protocols to use and generic option handler.
 *
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Fixes:
 *		Alan Cox	: 	Numerous verify_area() problems
 *		Alan Cox	:	Connecting on a connecting socket
 *					now returns an error for tcp.
 *		Alan Cox	:	sock->protocol is set correctly.
 *					and is not sometimes left as 0.
 *		Alan Cox	:	connect handles icmp errors on a
 *					connect properly. Unfortunately there
 *					is a restart syscall nasty there. I
 *					can't match BSD without hacking the C
 *					library. Ideas urgently sought!
 *		Alan Cox	:	Disallow bind() to addresses that are
 *					not ours - especially broadcast ones!!
 *		Alan Cox	:	Socket 1024 _IS_ ok for users. (fencepost)
 *		Alan Cox	:	sock_wfree/sock_rfree don't destroy sockets,
 *					instead they leave that for the DESTROY timer.
 *		Alan Cox	:	Clean up error flag in accept
 *		Alan Cox	:	TCP ack handling is buggy, the DESTROY timer
 *					was buggy. Put a remove_sock() in the handler
 *					for memory when we hit 0. Also altered the timer
 *					code. The ACK stuff can wait and needs major
 *					TCP layer surgery.
 *		Alan Cox	:	Fixed TCP ack bug, removed remove sock
 *					and fixed timer/inet_bh race.
 *		Alan Cox	:	Added zapped flag for TCP
 *		Alan Cox	:	Move kfree_skb into skbuff.c and tidied up surplus code
 *		Alan Cox	:	for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
 *		Alan Cox	:	kfree_s calls now are kfree_skbmem so we can track skb resources
 *		Alan Cox	:	Supports socket option broadcast now as does udp. Packet and raw need fixing.
 *		Alan Cox	:	Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
 *		Rick Sladkey	:	Relaxed UDP rules for matching packets.
 *		C.E.Hawkins	:	IFF_PROMISC/SIOCGHWADDR support
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Fixed connect() taking signals I think.
 *		Alan Cox	:	SO_LINGER supported
 *		Alan Cox	:	Error reporting fixes
 *		Anonymous	:	inet_create tidied up (sk->reuse setting)
 *		Alan Cox	:	inet sockets don't set sk->type!
 *		Alan Cox	:	Split socket option code
 *		Alan Cox	:	Callbacks
 *		Alan Cox	:	Nagle flag for Charles & Johannes stuff
 *		Alex		:	Removed restriction on inet fioctl
 *		Alan Cox	:	Splitting INET from NET core
 *		Alan Cox	:	Fixed bogus SO_TYPE handling in getsockopt()
 *		Adam Caldwell	:	Missing return in SO_DONTROUTE/SO_DEBUG code
 *		Alan Cox	:	Split IP from generic code
 *		Alan Cox	:	New kfree_skbmem()
 *		Alan Cox	:	Make SO_DEBUG superuser only.
 *		Alan Cox	:	Allow anyone to clear SO_DEBUG
 *					(compatibility fix)
 *		Alan Cox	:	Added optimistic memory grabbing for AF_UNIX throughput.
 *		Alan Cox	:	Allocator for a socket is settable.
 *		Alan Cox	:	SO_ERROR includes soft errors.
 *		Alan Cox	:	Allow NULL arguments on some SO_ opts
 *		Alan Cox	: 	Generic socket allocation to make hooks
 *					easier (suggested by Craig Metz).
 *		Michael Pall	:	SO_ERROR returns positive errno again
 *              Steve Whitehouse:       Added default destructor to free
 *                                      protocol private data.
 *              Steve Whitehouse:       Added various other default routines
 *                                      common to several socket families.
 *              Chris Evans     :       Call suser() check last on F_SETOWN
 *		Jay Schulist	:	Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
 *		Andi Kleen	:	Add sock_kmalloc()/sock_kfree_s()
 *		Andi Kleen	:	Fix write_space callback
 *		Chris Evans	:	Security fixes - signedness again
 *		Arnaldo C. Melo :       cleanups, use skb_queue_purge
 *
 * To Fix:
 *
 *
 *		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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>

#include <asm/uaccess.h>

#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/sock_diag.h>

#include <linux/filter.h>
#include <net/sock_reuseport.h>

#include <trace/events/sock.h>

#include <net/tcp.h>
#include <net/busy_poll.h>

static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);

/**
 * sk_ns_capable - General socket capability test
 * @sk: Socket to use a capability on or through
 * @user_ns: The user namespace of the capability to use
 * @cap: The capability to use
 *
 * Test to see if the opener of the socket had when the socket was
 * created and the current process has the capability @cap in the user
 * namespace @user_ns.
 */
bool sk_ns_capable(const struct sock *sk,
		   struct user_namespace *user_ns, int cap)
{
	return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
		ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(sk_ns_capable);

/**
 * sk_capable - Socket global capability test
 * @sk: Socket to use a capability on or through
 * @cap: The global capability to use
 *
 * Test to see if the opener of the socket had when the socket was
 * created and the current process has the capability @cap in all user
 * namespaces.
 */
bool sk_capable(const struct sock *sk, int cap)
{
	return sk_ns_capable(sk, &init_user_ns, cap);
}
EXPORT_SYMBOL(sk_capable);

/**
 * sk_net_capable - Network namespace socket capability test
 * @sk: Socket to use a capability on or through
 * @cap: The capability to use
 *
 * Test to see if the opener of the socket had when the socket was created
 * and the current process has the capability @cap over the network namespace
 * the socket is a member of.
 */
bool sk_net_capable(const struct sock *sk, int cap)
{
	return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
}
EXPORT_SYMBOL(sk_net_capable);

/*
 * Each address family might have different locking rules, so we have
 * one slock key per address family:
 */
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];

/*
 * Make lock validator output more readable. (we pre-construct these
 * strings build-time, so that runtime initialization of socket
 * locks is fast):
 */
static const char *const af_family_key_strings[AF_MAX+1] = {
  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
  "sk_lock-AF_RDS"   , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-AF_CAN"      ,
  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
  "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
  "sk_lock-AF_NFC"   , "sk_lock-AF_VSOCK"    , "sk_lock-AF_KCM"      ,
  "sk_lock-AF_QIPCRTR", "sk_lock-AF_MAX"
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
  "slock-AF_RDS"   , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
  "slock-27"       , "slock-28"          , "slock-AF_CAN"      ,
  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
  "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
  "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
  "slock-AF_NFC"   , "slock-AF_VSOCK"    ,"slock-AF_KCM"       ,
  "slock-AF_QIPCRTR", "slock-AF_MAX"
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
  "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
  "clock-AF_AX25"  , "clock-AF_IPX"      , "clock-AF_APPLETALK",
  "clock-AF_NETROM", "clock-AF_BRIDGE"   , "clock-AF_ATMPVC"   ,
  "clock-AF_X25"   , "clock-AF_INET6"    , "clock-AF_ROSE"     ,
  "clock-AF_DECnet", "clock-AF_NETBEUI"  , "clock-AF_SECURITY" ,
  "clock-AF_KEY"   , "clock-AF_NETLINK"  , "clock-AF_PACKET"   ,
  "clock-AF_ASH"   , "clock-AF_ECONET"   , "clock-AF_ATMSVC"   ,
  "clock-AF_RDS"   , "clock-AF_SNA"      , "clock-AF_IRDA"     ,
  "clock-AF_PPPOX" , "clock-AF_WANPIPE"  , "clock-AF_LLC"      ,
  "clock-27"       , "clock-28"          , "clock-AF_CAN"      ,
  "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
  "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
  "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
  "clock-AF_NFC"   , "clock-AF_VSOCK"    , "clock-AF_KCM"      ,
  "clock-AF_QIPCRTR", "clock-AF_MAX"
};

/*
 * sk_callback_lock locking rules are per-address-family,
 * so split the lock classes by using a per-AF key:
 */
static struct lock_class_key af_callback_keys[AF_MAX];

/* Take into consideration the size of the struct sk_buff overhead in the
 * determination of these values, since that is non-constant across
 * platforms.  This makes socket queueing behavior and performance
 * not depend upon such differences.
 */
#define _SK_MEM_PACKETS		256
#define _SK_MEM_OVERHEAD	SKB_TRUESIZE(256)
#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;

/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);

int sysctl_tstamp_allow_data __read_mostly = 1;

struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
EXPORT_SYMBOL_GPL(memalloc_socks);

/**
 * sk_set_memalloc - sets %SOCK_MEMALLOC
 * @sk: socket to set it on
 *
 * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
 * It's the responsibility of the admin to adjust min_free_kbytes
 * to meet the requirements
 */
void sk_set_memalloc(struct sock *sk)
{
	sock_set_flag(sk, SOCK_MEMALLOC);
	sk->sk_allocation |= __GFP_MEMALLOC;
	static_key_slow_inc(&memalloc_socks);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);

void sk_clear_memalloc(struct sock *sk)
{
	sock_reset_flag(sk, SOCK_MEMALLOC);
	sk->sk_allocation &= ~__GFP_MEMALLOC;
	static_key_slow_dec(&memalloc_socks);

	/*
	 * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
	 * progress of swapping. SOCK_MEMALLOC may be cleared while
	 * it has rmem allocations due to the last swapfile being deactivated
	 * but there is a risk that the socket is unusable due to exceeding
	 * the rmem limits. Reclaim the reserves and obey rmem limits again.
	 */
	sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);

int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	int ret;
	unsigned long pflags = current->flags;

	/* these should have been dropped before queueing */
	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

	current->flags |= PF_MEMALLOC;
	ret = sk->sk_backlog_rcv(sk, skb);
	tsk_restore_flags(current, pflags, PF_MEMALLOC);

	return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
	struct timeval tv;

	if (optlen < sizeof(tv))
		return -EINVAL;
	if (copy_from_user(&tv, optval, sizeof(tv)))
		return -EFAULT;
	if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
		return -EDOM;

	if (tv.tv_sec < 0) {
		static int warned __read_mostly;

		*timeo_p = 0;
		if (warned < 10 && net_ratelimit()) {
			warned++;
			pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
				__func__, current->comm, task_pid_nr(current));
		}
		return 0;
	}
	*timeo_p = MAX_SCHEDULE_TIMEOUT;
	if (tv.tv_sec == 0 && tv.tv_usec == 0)
		return 0;
	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
		*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
	return 0;
}

static void sock_warn_obsolete_bsdism(const char *name)
{
	static int warned;
	static char warncomm[TASK_COMM_LEN];
	if (strcmp(warncomm, current->comm) && warned < 5) {
		strcpy(warncomm,  current->comm);
		pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
			warncomm, name);
		warned++;
	}
}

static bool sock_needs_netstamp(const struct sock *sk)
{
	switch (sk->sk_family) {
	case AF_UNSPEC:
	case AF_UNIX:
		return false;
	default:
		return true;
	}
}

static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
	if (sk->sk_flags & flags) {
		sk->sk_flags &= ~flags;
		if (sock_needs_netstamp(sk) &&
		    !(sk->sk_flags & SK_FLAGS_TIMESTAMP))
			net_disable_timestamp();
	}
}


int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	unsigned long flags;
	struct sk_buff_head *list = &sk->sk_receive_queue;

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
		atomic_inc(&sk->sk_drops);
		trace_sock_rcvqueue_full(sk, skb);
		return -ENOMEM;
	}

	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
		atomic_inc(&sk->sk_drops);
		return -ENOBUFS;
	}

	skb->dev = NULL;
	skb_set_owner_r(skb, sk);

	/* we escape from rcu protected region, make sure we dont leak
	 * a norefcounted dst
	 */
	skb_dst_force(skb);

	spin_lock_irqsave(&list->lock, flags);
	sock_skb_set_dropcount(sk, skb);
	__skb_queue_tail(list, skb);
	spin_unlock_irqrestore(&list->lock, flags);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk);
	return 0;
}
EXPORT_SYMBOL(__sock_queue_rcv_skb);

int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err;

	err = sk_filter(sk, skb);
	if (err)
		return err;

	return __sock_queue_rcv_skb(sk, skb);
}
EXPORT_SYMBOL(sock_queue_rcv_skb);

int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
		     const int nested, unsigned int trim_cap, bool refcounted)
{
	int rc = NET_RX_SUCCESS;

	if (sk_filter_trim_cap(sk, skb, trim_cap))
		goto discard_and_relse;

	skb->dev = NULL;

	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
		atomic_inc(&sk->sk_drops);
		goto discard_and_relse;
	}
	if (nested)
		bh_lock_sock_nested(sk);
	else
		bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		/*
		 * trylock + unlock semantics:
		 */
		mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);

		rc = sk_backlog_rcv(sk, skb);

		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
	} else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
		bh_unlock_sock(sk);
		atomic_inc(&sk->sk_drops);
		goto discard_and_relse;
	}

	bh_unlock_sock(sk);
out:
	if (refcounted)
		sock_put(sk);
	return rc;
discard_and_relse:
	kfree_skb(skb);
	goto out;
}
EXPORT_SYMBOL(__sk_receive_skb);

struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = __sk_dst_get(sk);

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
		sk_tx_queue_clear(sk);
		RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
		dst_release(dst);
		return NULL;
	}

	return dst;
}
EXPORT_SYMBOL(__sk_dst_check);

struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = sk_dst_get(sk);

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
		sk_dst_reset(sk);
		dst_release(dst);
		return NULL;
	}

	return dst;
}
EXPORT_SYMBOL(sk_dst_check);

static int sock_setbindtodevice(struct sock *sk, char __user *optval,
				int optlen)
{
	int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
	struct net *net = sock_net(sk);
	char devname[IFNAMSIZ];
	int index;

	/* Sorry... */
	ret = -EPERM;
	if (!ns_capable(net->user_ns, CAP_NET_RAW))
		goto out;

	ret = -EINVAL;
	if (optlen < 0)
		goto out;

	/* Bind this socket to a particular device like "eth0",
	 * as specified in the passed interface name. If the
	 * name is "" or the option length is zero the socket
	 * is not bound.
	 */
	if (optlen > IFNAMSIZ - 1)
		optlen = IFNAMSIZ - 1;
	memset(devname, 0, sizeof(devname));

	ret = -EFAULT;
	if (copy_from_user(devname, optval, optlen))
		goto out;

	index = 0;
	if (devname[0] != '\0') {
		struct net_device *dev;

		rcu_read_lock();
		dev = dev_get_by_name_rcu(net, devname);
		if (dev)
			index = dev->ifindex;
		rcu_read_unlock();
		ret = -ENODEV;
		if (!dev)
			goto out;
	}

	lock_sock(sk);
	sk->sk_bound_dev_if = index;
	sk_dst_reset(sk);
	release_sock(sk);

	ret = 0;

out:
#endif

	return ret;
}

static int sock_getbindtodevice(struct sock *sk, char __user *optval,
				int __user *optlen, int len)
{
	int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
	struct net *net = sock_net(sk);
	char devname[IFNAMSIZ];

	if (sk->sk_bound_dev_if == 0) {
		len = 0;
		goto zero;
	}

	ret = -EINVAL;
	if (len < IFNAMSIZ)
		goto out;

	ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
	if (ret)
		goto out;

	len = strlen(devname) + 1;

	ret = -EFAULT;
	if (copy_to_user(optval, devname, len))
		goto out;

zero:
	ret = -EFAULT;
	if (put_user(len, optlen))
		goto out;

	ret = 0;

out:
#endif

	return ret;
}

static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
{
	if (valbool)
		sock_set_flag(sk, bit);
	else
		sock_reset_flag(sk, bit);
}

bool sk_mc_loop(struct sock *sk)
{
	if (dev_recursion_level())
		return false;
	if (!sk)
		return true;
	switch (sk->sk_family) {
	case AF_INET:
		return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
	case AF_INET6:
		return inet6_sk(sk)->mc_loop;
#endif
	}
	WARN_ON(1);
	return true;
}
EXPORT_SYMBOL(sk_mc_loop);

/*
 *	This is meant for all protocols to use and covers goings on
 *	at the socket level. Everything here is generic.
 */

int sock_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, unsigned int optlen)
{
	struct sock *sk = sock->sk;
	int val;
	int valbool;
	struct linger ling;
	int ret = 0;

	/*
	 *	Options without arguments
	 */

	if (optname == SO_BINDTODEVICE)
		return sock_setbindtodevice(sk, optval, optlen);

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	valbool = val ? 1 : 0;

	lock_sock(sk);

	switch (optname) {
	case SO_DEBUG:
		if (val && !capable(CAP_NET_ADMIN))
			ret = -EACCES;
		else
			sock_valbool_flag(sk, SOCK_DBG, valbool);
		break;
	case SO_REUSEADDR:
		sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
		break;
	case SO_REUSEPORT:
		sk->sk_reuseport = valbool;
		break;
	case SO_TYPE:
	case SO_PROTOCOL:
	case SO_DOMAIN:
	case SO_ERROR:
		ret = -ENOPROTOOPT;
		break;
	case SO_DONTROUTE:
		sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
		break;
	case SO_BROADCAST:
		sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
		break;
	case SO_SNDBUF:
		/* Don't error on this BSD doesn't and if you think
		 * about it this is right. Otherwise apps have to
		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
		 * are treated in BSD as hints
		 */
		val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
		/* Wake up sending tasks if we upped the value. */
		sk->sk_write_space(sk);
		break;

	case SO_SNDBUFFORCE:
		if (!capable(CAP_NET_ADMIN)) {
			ret = -EPERM;
			break;
		}
		goto set_sndbuf;

	case SO_RCVBUF:
		/* Don't error on this BSD doesn't and if you think
		 * about it this is right. Otherwise apps have to
		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
		 * are treated in BSD as hints
		 */
		val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
		/*
		 * We double it on the way in to account for
		 * "struct sk_buff" etc. overhead.   Applications
		 * assume that the SO_RCVBUF setting they make will
		 * allow that much actual data to be received on that
		 * socket.
		 *
		 * Applications are unaware that "struct sk_buff" and
		 * other overheads allocate from the receive buffer
		 * during socket buffer allocation.
		 *
		 * And after considering the possible alternatives,
		 * returning the value we actually used in getsockopt
		 * is the most desirable behavior.
		 */
		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
		break;

	case SO_RCVBUFFORCE:
		if (!capable(CAP_NET_ADMIN)) {
			ret = -EPERM;
			break;
		}
		goto set_rcvbuf;

	case SO_KEEPALIVE:
#ifdef CONFIG_INET
		if (sk->sk_protocol == IPPROTO_TCP &&
		    sk->sk_type == SOCK_STREAM)
			tcp_set_keepalive(sk, valbool);
#endif
		sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
		break;

	case SO_OOBINLINE:
		sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
		break;

	case SO_NO_CHECK:
		sk->sk_no_check_tx = valbool;
		break;

	case SO_PRIORITY:
		if ((val >= 0 && val <= 6) ||
		    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
			sk->sk_priority = val;
		else
			ret = -EPERM;
		break;

	case SO_LINGER:
		if (optlen < sizeof(ling)) {
			ret = -EINVAL;	/* 1003.1g */
			break;
		}
		if (copy_from_user(&ling, optval, sizeof(ling))) {
			ret = -EFAULT;
			break;
		}
		if (!ling.l_onoff)
			sock_reset_flag(sk, SOCK_LINGER);
		else {
#if (BITS_PER_LONG == 32)
			if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
				sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
			else
#endif
				sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
			sock_set_flag(sk, SOCK_LINGER);
		}
		break;

	case SO_BSDCOMPAT:
		sock_warn_obsolete_bsdism("setsockopt");
		break;

	case SO_PASSCRED:
		if (valbool)
			set_bit(SOCK_PASSCRED, &sock->flags);
		else
			clear_bit(SOCK_PASSCRED, &sock->flags);
		break;

	case SO_TIMESTAMP:
	case SO_TIMESTAMPNS:
		if (valbool)  {
			if (optname == SO_TIMESTAMP)
				sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
			else
				sock_set_flag(sk, SOCK_RCVTSTAMPNS);
			sock_set_flag(sk, SOCK_RCVTSTAMP);
			sock_enable_timestamp(sk, SOCK_TIMESTAMP);
		} else {
			sock_reset_flag(sk, SOCK_RCVTSTAMP);
			sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
		}
		break;

	case SO_TIMESTAMPING:
		if (val & ~SOF_TIMESTAMPING_MASK) {
			ret = -EINVAL;
			break;
		}

		if (val & SOF_TIMESTAMPING_OPT_ID &&
		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
			if (sk->sk_protocol == IPPROTO_TCP &&
			    sk->sk_type == SOCK_STREAM) {
				if ((1 << sk->sk_state) &
				    (TCPF_CLOSE | TCPF_LISTEN)) {
					ret = -EINVAL;
					break;
				}
				sk->sk_tskey = tcp_sk(sk)->snd_una;
			} else {
				sk->sk_tskey = 0;
			}
		}
		sk->sk_tsflags = val;
		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
			sock_enable_timestamp(sk,
					      SOCK_TIMESTAMPING_RX_SOFTWARE);
		else
			sock_disable_timestamp(sk,
					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
		break;

	case SO_RCVLOWAT:
		if (val < 0)
			val = INT_MAX;
		sk->sk_rcvlowat = val ? : 1;
		break;

	case SO_RCVTIMEO:
		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
		break;

	case SO_SNDTIMEO:
		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
		break;

	case SO_ATTACH_FILTER:
		ret = -EINVAL;
		if (optlen == sizeof(struct sock_fprog)) {
			struct sock_fprog fprog;

			ret = -EFAULT;
			if (copy_from_user(&fprog, optval, sizeof(fprog)))
				break;

			ret = sk_attach_filter(&fprog, sk);
		}
		break;

	case SO_ATTACH_BPF:
		ret = -EINVAL;
		if (optlen == sizeof(u32)) {
			u32 ufd;

			ret = -EFAULT;
			if (copy_from_user(&ufd, optval, sizeof(ufd)))
				break;

			ret = sk_attach_bpf(ufd, sk);
		}
		break;

	case SO_ATTACH_REUSEPORT_CBPF:
		ret = -EINVAL;
		if (optlen == sizeof(struct sock_fprog)) {
			struct sock_fprog fprog;

			ret = -EFAULT;
			if (copy_from_user(&fprog, optval, sizeof(fprog)))
				break;

			ret = sk_reuseport_attach_filter(&fprog, sk);
		}
		break;

	case SO_ATTACH_REUSEPORT_EBPF:
		ret = -EINVAL;
		if (optlen == sizeof(u32)) {
			u32 ufd;

			ret = -EFAULT;
			if (copy_from_user(&ufd, optval, sizeof(ufd)))
				break;

			ret = sk_reuseport_attach_bpf(ufd, sk);
		}
		break;

	case SO_DETACH_FILTER:
		ret = sk_detach_filter(sk);
		break;

	case SO_LOCK_FILTER:
		if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
			ret = -EPERM;
		else
			sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
		break;

	case SO_PASSSEC:
		if (valbool)
			set_bit(SOCK_PASSSEC, &sock->flags);
		else
			clear_bit(SOCK_PASSSEC, &sock->flags);
		break;
	case SO_MARK:
		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
			ret = -EPERM;
		else
			sk->sk_mark = val;
		break;

	case SO_RXQ_OVFL:
		sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
		break;

	case SO_WIFI_STATUS:
		sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
		break;

	case SO_PEEK_OFF:
		if (sock->ops->set_peek_off)
			ret = sock->ops->set_peek_off(sk, val);
		else
			ret = -EOPNOTSUPP;
		break;

	case SO_NOFCS:
		sock_valbool_flag(sk, SOCK_NOFCS, valbool);
		break;

	case SO_SELECT_ERR_QUEUE:
		sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
		break;

#ifdef CONFIG_NET_RX_BUSY_POLL
	case SO_BUSY_POLL:
		/* allow unprivileged users to decrease the value */
		if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
			ret = -EPERM;
		else {
			if (val < 0)
				ret = -EINVAL;
			else
				sk->sk_ll_usec = val;
		}
		break;
#endif

	case SO_MAX_PACING_RATE:
		sk->sk_max_pacing_rate = val;
		sk->sk_pacing_rate = min(sk->sk_pacing_rate,
					 sk->sk_max_pacing_rate);
		break;

	case SO_INCOMING_CPU:
		sk->sk_incoming_cpu = val;
		break;

	case SO_CNX_ADVICE:
		if (val == 1)
			dst_negative_advice(sk);
		break;
	default:
		ret = -ENOPROTOOPT;
		break;
	}
	release_sock(sk);
	return ret;
}
EXPORT_SYMBOL(sock_setsockopt);


static void cred_to_ucred(struct pid *pid, const struct cred *cred,
			  struct ucred *ucred)
{
	ucred->pid = pid_vnr(pid);
	ucred->uid = ucred->gid = -1;
	if (cred) {
		struct user_namespace *current_ns = current_user_ns();

		ucred->uid = from_kuid_munged(current_ns, cred->euid);
		ucred->gid = from_kgid_munged(current_ns, cred->egid);
	}
}

int sock_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	union {
		int val;
		struct linger ling;
		struct timeval tm;
	} v;

	int lv = sizeof(int);
	int len;

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

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

	switch (optname) {
	case SO_DEBUG:
		v.val = sock_flag(sk, SOCK_DBG);
		break;

	case SO_DONTROUTE:
		v.val = sock_flag(sk, SOCK_LOCALROUTE);
		break;

	case SO_BROADCAST:
		v.val = sock_flag(sk, SOCK_BROADCAST);
		break;

	case SO_SNDBUF:
		v.val = sk->sk_sndbuf;
		break;

	case SO_RCVBUF:
		v.val = sk->sk_rcvbuf;
		break;

	case SO_REUSEADDR:
		v.val = sk->sk_reuse;
		break;

	case SO_REUSEPORT:
		v.val = sk->sk_reuseport;
		break;

	case SO_KEEPALIVE:
		v.val = sock_flag(sk, SOCK_KEEPOPEN);
		break;

	case SO_TYPE:
		v.val = sk->sk_type;
		break;

	case SO_PROTOCOL:
		v.val = sk->sk_protocol;
		break;

	case SO_DOMAIN:
		v.val = sk->sk_family;
		break;

	case SO_ERROR:
		v.val = -sock_error(sk);
		if (v.val == 0)
			v.val = xchg(&sk->sk_err_soft, 0);
		break;

	case SO_OOBINLINE:
		v.val = sock_flag(sk, SOCK_URGINLINE);
		break;

	case SO_NO_CHECK:
		v.val = sk->sk_no_check_tx;
		break;

	case SO_PRIORITY:
		v.val = sk->sk_priority;
		break;

	case SO_LINGER:
		lv		= sizeof(v.ling);
		v.ling.l_onoff	= sock_flag(sk, SOCK_LINGER);
		v.ling.l_linger	= sk->sk_lingertime / HZ;
		break;

	case SO_BSDCOMPAT:
		sock_warn_obsolete_bsdism("getsockopt");
		break;

	case SO_TIMESTAMP:
		v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
				!sock_flag(sk, SOCK_RCVTSTAMPNS);
		break;

	case SO_TIMESTAMPNS:
		v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
		break;

	case SO_TIMESTAMPING:
		v.val = sk->sk_tsflags;
		break;

	case SO_RCVTIMEO:
		lv = sizeof(struct timeval);
		if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
			v.tm.tv_sec = 0;
			v.tm.tv_usec = 0;
		} else {
			v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
			v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
		}
		break;

	case SO_SNDTIMEO:
		lv = sizeof(struct timeval);
		if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
			v.tm.tv_sec = 0;
			v.tm.tv_usec = 0;
		} else {
			v.tm.tv_sec = sk->sk_sndtimeo / HZ;
			v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
		}
		break;

	case SO_RCVLOWAT:
		v.val = sk->sk_rcvlowat;
		break;

	case SO_SNDLOWAT:
		v.val = 1;
		break;

	case SO_PASSCRED:
		v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
		break;

	case SO_PEERCRED:
	{
		struct ucred peercred;
		if (len > sizeof(peercred))
			len = sizeof(peercred);
		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
		if (copy_to_user(optval, &peercred, len))
			return -EFAULT;
		goto lenout;
	}

	case SO_PEERNAME:
	{
		char address[128];

		if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
			return -ENOTCONN;
		if (lv < len)
			return -EINVAL;
		if (copy_to_user(optval, address, len))
			return -EFAULT;
		goto lenout;
	}

	/* Dubious BSD thing... Probably nobody even uses it, but
	 * the UNIX standard wants it for whatever reason... -DaveM
	 */
	case SO_ACCEPTCONN:
		v.val = sk->sk_state == TCP_LISTEN;
		break;

	case SO_PASSSEC:
		v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
		break;

	case SO_PEERSEC:
		return security_socket_getpeersec_stream(sock, optval, optlen, len);

	case SO_MARK:
		v.val = sk->sk_mark;
		break;

	case SO_RXQ_OVFL:
		v.val = sock_flag(sk, SOCK_RXQ_OVFL);
		break;

	case SO_WIFI_STATUS:
		v.val = sock_flag(sk, SOCK_WIFI_STATUS);
		break;

	case SO_PEEK_OFF:
		if (!sock->ops->set_peek_off)
			return -EOPNOTSUPP;

		v.val = sk->sk_peek_off;
		break;
	case SO_NOFCS:
		v.val = sock_flag(sk, SOCK_NOFCS);
		break;

	case SO_BINDTODEVICE:
		return sock_getbindtodevice(sk, optval, optlen, len);

	case SO_GET_FILTER:
		len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
		if (len < 0)
			return len;

		goto lenout;

	case SO_LOCK_FILTER:
		v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
		break;

	case SO_BPF_EXTENSIONS:
		v.val = bpf_tell_extensions();
		break;

	case SO_SELECT_ERR_QUEUE:
		v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
		break;

#ifdef CONFIG_NET_RX_BUSY_POLL
	case SO_BUSY_POLL:
		v.val = sk->sk_ll_usec;
		break;
#endif

	case SO_MAX_PACING_RATE:
		v.val = sk->sk_max_pacing_rate;
		break;

	case SO_INCOMING_CPU:
		v.val = sk->sk_incoming_cpu;
		break;

	default:
		/* We implement the SO_SNDLOWAT etc to not be settable
		 * (1003.1g 7).
		 */
		return -ENOPROTOOPT;
	}

	if (len > lv)
		len = lv;
	if (copy_to_user(optval, &v, len))
		return -EFAULT;
lenout:
	if (put_user(len, optlen))
		return -EFAULT;
	return 0;
}

/*
 * Initialize an sk_lock.
 *
 * (We also register the sk_lock with the lock validator.)
 */
static inline void sock_lock_init(struct sock *sk)
{
	sock_lock_init_class_and_name(sk,
			af_family_slock_key_strings[sk->sk_family],
			af_family_slock_keys + sk->sk_family,
			af_family_key_strings[sk->sk_family],
			af_family_keys + sk->sk_family);
}

/*
 * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
 * even temporarly, because of RCU lookups. sk_node should also be left as is.
 * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
 */
static void sock_copy(struct sock *nsk, const struct sock *osk)
{
#ifdef CONFIG_SECURITY_NETWORK
	void *sptr = nsk->sk_security;
#endif
	memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));

	memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
	       osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end));

#ifdef CONFIG_SECURITY_NETWORK
	nsk->sk_security = sptr;
	security_sk_clone(osk, nsk);
#endif
}

static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
		int family)
{
	struct sock *sk;
	struct kmem_cache *slab;

	slab = prot->slab;
	if (slab != NULL) {
		sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
		if (!sk)
			return sk;
		if (priority & __GFP_ZERO)
			sk_prot_clear_nulls(sk, prot->obj_size);
	} else
		sk = kmalloc(prot->obj_size, priority);

	if (sk != NULL) {
		kmemcheck_annotate_bitfield(sk, flags);

		if (security_sk_alloc(sk, family, priority))
			goto out_free;

		if (!try_module_get(prot->owner))
			goto out_free_sec;
		sk_tx_queue_clear(sk);
	}

	return sk;

out_free_sec:
	security_sk_free(sk);
out_free:
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	return NULL;
}

static void sk_prot_free(struct proto *prot, struct sock *sk)
{
	struct kmem_cache *slab;
	struct module *owner;

	owner = prot->owner;
	slab = prot->slab;

	cgroup_sk_free(&sk->sk_cgrp_data);
	mem_cgroup_sk_free(sk);
	security_sk_free(sk);
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	module_put(owner);
}

/**
 *	sk_alloc - All socket objects are allocated here
 *	@net: the applicable net namespace
 *	@family: protocol family
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@prot: struct proto associated with this new sock instance
 *	@kern: is this to be a kernel socket?
 */
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
		      struct proto *prot, int kern)
{
	struct sock *sk;

	sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
	if (sk) {
		sk->sk_family = family;
		/*
		 * See comment in struct sock definition to understand
		 * why we need sk_prot_creator -acme
		 */
		sk->sk_prot = sk->sk_prot_creator = prot;
		sock_lock_init(sk);
		sk->sk_net_refcnt = kern ? 0 : 1;
		if (likely(sk->sk_net_refcnt))
			get_net(net);
		sock_net_set(sk, net);
		atomic_set(&sk->sk_wmem_alloc, 1);

		mem_cgroup_sk_alloc(sk);
		cgroup_sk_alloc(&sk->sk_cgrp_data);
		sock_update_classid(&sk->sk_cgrp_data);
		sock_update_netprioidx(&sk->sk_cgrp_data);
	}

	return sk;
}
EXPORT_SYMBOL(sk_alloc);

/* Sockets having SOCK_RCU_FREE will call this function after one RCU
 * grace period. This is the case for UDP sockets and TCP listeners.
 */
static void __sk_destruct(struct rcu_head *head)
{
	struct sock *sk = container_of(head, struct sock, sk_rcu);
	struct sk_filter *filter;

	if (sk->sk_destruct)
		sk->sk_destruct(sk);

	filter = rcu_dereference_check(sk->sk_filter,
				       atomic_read(&sk->sk_wmem_alloc) == 0);
	if (filter) {
		sk_filter_uncharge(sk, filter);
		RCU_INIT_POINTER(sk->sk_filter, NULL);
	}
	if (rcu_access_pointer(sk->sk_reuseport_cb))
		reuseport_detach_sock(sk);

	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);

	if (atomic_read(&sk->sk_omem_alloc))
		pr_debug("%s: optmem leakage (%d bytes) detected\n",
			 __func__, atomic_read(&sk->sk_omem_alloc));

	if (sk->sk_frag.page) {
		put_page(sk->sk_frag.page);
		sk->sk_frag.page = NULL;
	}

	if (sk->sk_peer_cred)
		put_cred(sk->sk_peer_cred);
	put_pid(sk->sk_peer_pid);
	if (likely(sk->sk_net_refcnt))
		put_net(sock_net(sk));
	sk_prot_free(sk->sk_prot_creator, sk);
}

void sk_destruct(struct sock *sk)
{
	if (sock_flag(sk, SOCK_RCU_FREE))
		call_rcu(&sk->sk_rcu, __sk_destruct);
	else
		__sk_destruct(&sk->sk_rcu);
}

static void __sk_free(struct sock *sk)
{
	if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
		sock_diag_broadcast_destroy(sk);
	else
		sk_destruct(sk);
}

void sk_free(struct sock *sk)
{
	/*
	 * We subtract one from sk_wmem_alloc and can know if
	 * some packets are still in some tx queue.
	 * If not null, sock_wfree() will call __sk_free(sk) later
	 */
	if (atomic_dec_and_test(&sk->sk_wmem_alloc))
		__sk_free(sk);
}
EXPORT_SYMBOL(sk_free);

/**
 *	sk_clone_lock - clone a socket, and lock its clone
 *	@sk: the socket to clone
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *
 *	Caller must unlock socket even in error path (bh_unlock_sock(newsk))
 */
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
{
	struct sock *newsk;
	bool is_charged = true;

	newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
	if (newsk != NULL) {
		struct sk_filter *filter;

		sock_copy(newsk, sk);

		newsk->sk_prot_creator = sk->sk_prot;

		/* SANITY */
		if (likely(newsk->sk_net_refcnt))
			get_net(sock_net(newsk));
		sk_node_init(&newsk->sk_node);
		sock_lock_init(newsk);
		bh_lock_sock(newsk);
		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
		newsk->sk_backlog.len = 0;

		atomic_set(&newsk->sk_rmem_alloc, 0);
		/*
		 * sk_wmem_alloc set to one (see sk_free() and sock_wfree())
		 */
		atomic_set(&newsk->sk_wmem_alloc, 1);
		atomic_set(&newsk->sk_omem_alloc, 0);
		skb_queue_head_init(&newsk->sk_receive_queue);
		skb_queue_head_init(&newsk->sk_write_queue);

		rwlock_init(&newsk->sk_callback_lock);
		lockdep_set_class_and_name(&newsk->sk_callback_lock,
				af_callback_keys + newsk->sk_family,
				af_family_clock_key_strings[newsk->sk_family]);

		newsk->sk_dst_cache	= NULL;
		newsk->sk_wmem_queued	= 0;
		newsk->sk_forward_alloc = 0;
		atomic_set(&newsk->sk_drops, 0);
		newsk->sk_send_head	= NULL;
		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;

		sock_reset_flag(newsk, SOCK_DONE);
		skb_queue_head_init(&newsk->sk_error_queue);

		filter = rcu_dereference_protected(newsk->sk_filter, 1);
		if (filter != NULL)
			/* though it's an empty new sock, the charging may fail
			 * if sysctl_optmem_max was changed between creation of
			 * original socket and cloning
			 */
			is_charged = sk_filter_charge(newsk, filter);

		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
			/* We need to make sure that we don't uncharge the new
			 * socket if we couldn't charge it in the first place
			 * as otherwise we uncharge the parent's filter.
			 */
			if (!is_charged)
				RCU_INIT_POINTER(newsk->sk_filter, NULL);
			/* It is still raw copy of parent, so invalidate
			 * destructor and make plain sk_free() */
			newsk->sk_destruct = NULL;
			bh_unlock_sock(newsk);
			sk_free(newsk);
			newsk = NULL;
			goto out;
		}
		RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);

		newsk->sk_err	   = 0;
		newsk->sk_err_soft = 0;
		newsk->sk_priority = 0;
		newsk->sk_incoming_cpu = raw_smp_processor_id();
		atomic64_set(&newsk->sk_cookie, 0);

		mem_cgroup_sk_alloc(newsk);
		cgroup_sk_alloc(&newsk->sk_cgrp_data);

		/*
		 * Before updating sk_refcnt, we must commit prior changes to memory
		 * (Documentation/RCU/rculist_nulls.txt for details)
		 */
		smp_wmb();
		atomic_set(&newsk->sk_refcnt, 2);

		/*
		 * Increment the counter in the same struct proto as the master
		 * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
		 * is the same as sk->sk_prot->socks, as this field was copied
		 * with memcpy).
		 *
		 * This _changes_ the previous behaviour, where
		 * tcp_create_openreq_child always was incrementing the
		 * equivalent to tcp_prot->socks (inet_sock_nr), so this have
		 * to be taken into account in all callers. -acme
		 */
		sk_refcnt_debug_inc(newsk);
		sk_set_socket(newsk, NULL);
		newsk->sk_wq = NULL;

		if (newsk->sk_prot->sockets_allocated)
			sk_sockets_allocated_inc(newsk);

		if (sock_needs_netstamp(sk) &&
		    newsk->sk_flags & SK_FLAGS_TIMESTAMP)
			net_enable_timestamp();
	}
out:
	return newsk;
}
EXPORT_SYMBOL_GPL(sk_clone_lock);

void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
	u32 max_segs = 1;

	sk_dst_set(sk, dst);
	sk->sk_route_caps = dst->dev->features;
	if (sk->sk_route_caps & NETIF_F_GSO)
		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
	sk->sk_route_caps &= ~sk->sk_route_nocaps;
	if (sk_can_gso(sk)) {
		if (dst->header_len) {
			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
		} else {
			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
			sk->sk_gso_max_size = dst->dev->gso_max_size;
			max_segs = max_t(u32, dst->dev->gso_max_segs, 1);
		}
	}
	sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);

/*
 *	Simple resource managers for sockets.
 */


/*
 * Write buffer destructor automatically called from kfree_skb.
 */
void sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	unsigned int len = skb->truesize;

	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
		/*
		 * Keep a reference on sk_wmem_alloc, this will be released
		 * after sk_write_space() call
		 */
		atomic_sub(len - 1, &sk->sk_wmem_alloc);
		sk->sk_write_space(sk);
		len = 1;
	}
	/*
	 * if sk_wmem_alloc reaches 0, we must finish what sk_free()
	 * could not do because of in-flight packets
	 */
	if (atomic_sub_and_test(len, &sk->sk_wmem_alloc))
		__sk_free(sk);
}
EXPORT_SYMBOL(sock_wfree);

/* This variant of sock_wfree() is used by TCP,
 * since it sets SOCK_USE_WRITE_QUEUE.
 */
void __sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	if (atomic_sub_and_test(skb->truesize, &sk->sk_wmem_alloc))
		__sk_free(sk);
}

void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
#ifdef CONFIG_INET
	if (unlikely(!sk_fullsock(sk))) {
		skb->destructor = sock_edemux;
		sock_hold(sk);
		return;
	}
#endif
	skb->destructor = sock_wfree;
	skb_set_hash_from_sk(skb, sk);
	/*
	 * We used to take a refcount on sk, but following operation
	 * is enough to guarantee sk_free() wont free this sock until
	 * all in-flight packets are completed
	 */
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(skb_set_owner_w);

/* This helper is used by netem, as it can hold packets in its
 * delay queue. We want to allow the owner socket to send more
 * packets, as if they were already TX completed by a typical driver.
 * But we also want to keep skb->sk set because some packet schedulers
 * rely on it (sch_fq for example).
 */
void skb_orphan_partial(struct sk_buff *skb)
{
	if (skb_is_tcp_pure_ack(skb))
		return;

	if (skb->destructor == sock_wfree
#ifdef CONFIG_INET
	    || skb->destructor == tcp_wfree
#endif
		) {
		struct sock *sk = skb->sk;

		if (atomic_inc_not_zero(&sk->sk_refcnt)) {
			atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
			skb->destructor = sock_efree;
		}
	} else {
		skb_orphan(skb);
	}
}
EXPORT_SYMBOL(skb_orphan_partial);

/*
 * Read buffer destructor automatically called from kfree_skb.
 */
void sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	unsigned int len = skb->truesize;

	atomic_sub(len, &sk->sk_rmem_alloc);
	sk_mem_uncharge(sk, len);
}
EXPORT_SYMBOL(sock_rfree);

/*
 * Buffer destructor for skbs that are not used directly in read or write
 * path, e.g. for error handler skbs. Automatically called from kfree_skb.
 */
void sock_efree(struct sk_buff *skb)
{
	sock_put(skb->sk);
}
EXPORT_SYMBOL(sock_efree);

kuid_t sock_i_uid(struct sock *sk)
{
	kuid_t uid;

	read_lock_bh(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID;
	read_unlock_bh(&sk->sk_callback_lock);
	return uid;
}
EXPORT_SYMBOL(sock_i_uid);

unsigned long sock_i_ino(struct sock *sk)
{
	unsigned long ino;

	read_lock_bh(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock_bh(&sk->sk_callback_lock);
	return ino;
}
EXPORT_SYMBOL(sock_i_ino);

/*
 * Allocate a skb from the socket's send buffer.
 */
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority)
{
	if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
		struct sk_buff *skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}
EXPORT_SYMBOL(sock_wmalloc);

/*
 * Allocate a memory block from the socket's option memory buffer.
 */
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
	if ((unsigned int)size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		void *mem;
		/* First do the add, to avoid the race if kmalloc
		 * might sleep.
		 */
		atomic_add(size, &sk->sk_omem_alloc);
		mem = kmalloc(size, priority);
		if (mem)
			return mem;
		atomic_sub(size, &sk->sk_omem_alloc);
	}
	return NULL;
}
EXPORT_SYMBOL(sock_kmalloc);

/* Free an option memory block. Note, we actually want the inline
 * here as this allows gcc to detect the nullify and fold away the
 * condition entirely.
 */
static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
				  const bool nullify)
{
	if (WARN_ON_ONCE(!mem))
		return;
	if (nullify)
		kzfree(mem);
	else
		kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	__sock_kfree_s(sk, mem, size, false);
}
EXPORT_SYMBOL(sock_kfree_s);

void sock_kzfree_s(struct sock *sk, void *mem, int size)
{
	__sock_kfree_s(sk, mem, size, true);
}
EXPORT_SYMBOL(sock_kzfree_s);

/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
   I think, these locks should be removed for datagram sockets.
 */
static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
	for (;;) {
		if (!timeo)
			break;
		if (signal_pending(current))
			break;
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
			break;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			break;
		if (sk->sk_err)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk_sleep(sk), &wait);
	return timeo;
}


/*
 *	Generic send/receive buffer handlers
 */

struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
				     unsigned long data_len, int noblock,
				     int *errcode, int max_page_order)
{
	struct sk_buff *skb;
	long timeo;
	int err;

	timeo = sock_sndtimeo(sk, noblock);
	for (;;) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

		err = -EPIPE;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			goto failure;

		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
			break;

		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		err = -EAGAIN;
		if (!timeo)
			goto failure;
		if (signal_pending(current))
			goto interrupted;
		timeo = sock_wait_for_wmem(sk, timeo);
	}
	skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
				   errcode, sk->sk_allocation);
	if (skb)
		skb_set_owner_w(skb, sk);
	return skb;

interrupted:
	err = sock_intr_errno(timeo);
failure:
	*errcode = err;
	return NULL;
}
EXPORT_SYMBOL(sock_alloc_send_pskb);

struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
				    int noblock, int *errcode)
{
	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
}
EXPORT_SYMBOL(sock_alloc_send_skb);

int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
		     struct sockcm_cookie *sockc)
{
	u32 tsflags;

	switch (cmsg->cmsg_type) {
	case SO_MARK:
		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
			return -EPERM;
		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
			return -EINVAL;
		sockc->mark = *(u32 *)CMSG_DATA(cmsg);
		break;
	case SO_TIMESTAMPING:
		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
			return -EINVAL;

		tsflags = *(u32 *)CMSG_DATA(cmsg);
		if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK)
			return -EINVAL;

		sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
		sockc->tsflags |= tsflags;
		break;
	/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
	case SCM_RIGHTS:
	case SCM_CREDENTIALS:
		break;
	default:
		return -EINVAL;
	}
	return 0;
}
EXPORT_SYMBOL(__sock_cmsg_send);

int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
		   struct sockcm_cookie *sockc)
{
	struct cmsghdr *cmsg;
	int ret;

	for_each_cmsghdr(cmsg, msg) {
		if (!CMSG_OK(msg, cmsg))
			return -EINVAL;
		if (cmsg->cmsg_level != SOL_SOCKET)
			continue;
		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
		if (ret)
			return ret;
	}
	return 0;
}
EXPORT_SYMBOL(sock_cmsg_send);

/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER	get_order(32768)

/**
 * skb_page_frag_refill - check that a page_frag contains enough room
 * @sz: minimum size of the fragment we want to get
 * @pfrag: pointer to page_frag
 * @gfp: priority for memory allocation
 *
 * Note: While this allocator tries to use high order pages, there is
 * no guarantee that allocations succeed. Therefore, @sz MUST be
 * less or equal than PAGE_SIZE.
 */
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
{
	if (pfrag->page) {
		if (page_ref_count(pfrag->page) == 1) {
			pfrag->offset = 0;
			return true;
		}
		if (pfrag->offset + sz <= pfrag->size)
			return true;
		put_page(pfrag->page);
	}

	pfrag->offset = 0;
	if (SKB_FRAG_PAGE_ORDER) {
		/* Avoid direct reclaim but allow kswapd to wake */
		pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
					  __GFP_COMP | __GFP_NOWARN |
					  __GFP_NORETRY,
					  SKB_FRAG_PAGE_ORDER);
		if (likely(pfrag->page)) {
			pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
			return true;
		}
	}
	pfrag->page = alloc_page(gfp);
	if (likely(pfrag->page)) {
		pfrag->size = PAGE_SIZE;
		return true;
	}
	return false;
}
EXPORT_SYMBOL(skb_page_frag_refill);

bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
	if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
		return true;

	sk_enter_memory_pressure(sk);
	sk_stream_moderate_sndbuf(sk);
	return false;
}
EXPORT_SYMBOL(sk_page_frag_refill);

static void __lock_sock(struct sock *sk)
	__releases(&sk->sk_lock.slock)
	__acquires(&sk->sk_lock.slock)
{
	DEFINE_WAIT(wait);

	for (;;) {
		prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
					TASK_UNINTERRUPTIBLE);
		spin_unlock_bh(&sk->sk_lock.slock);
		schedule();
		spin_lock_bh(&sk->sk_lock.slock);
		if (!sock_owned_by_user(sk))
			break;
	}
	finish_wait(&sk->sk_lock.wq, &wait);
}

static void __release_sock(struct sock *sk)
	__releases(&sk->sk_lock.slock)
	__acquires(&sk->sk_lock.slock)
{
	struct sk_buff *skb, *next;

	while ((skb = sk->sk_backlog.head) != NULL) {
		sk->sk_backlog.head = sk->sk_backlog.tail = NULL;

		spin_unlock_bh(&sk->sk_lock.slock);

		do {
			next = skb->next;
			prefetch(next);
			WARN_ON_ONCE(skb_dst_is_noref(skb));
			skb->next = NULL;
			sk_backlog_rcv(sk, skb);

			cond_resched();

			skb = next;
		} while (skb != NULL);

		spin_lock_bh(&sk->sk_lock.slock);
	}

	/*
	 * Doing the zeroing here guarantee we can not loop forever
	 * while a wild producer attempts to flood us.
	 */
	sk->sk_backlog.len = 0;
}

void __sk_flush_backlog(struct sock *sk)
{
	spin_lock_bh(&sk->sk_lock.slock);
	__release_sock(sk);
	spin_unlock_bh(&sk->sk_lock.slock);
}

/**
 * sk_wait_data - wait for data to arrive at sk_receive_queue
 * @sk:    sock to wait on
 * @timeo: for how long
 * @skb:   last skb seen on sk_receive_queue
 *
 * Now socket state including sk->sk_err is changed only under lock,
 * hence we may omit checks after joining wait queue.
 * We check receive queue before schedule() only as optimization;
 * it is very likely that release_sock() added new data.
 */
int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
	int rc;
	DEFINE_WAIT(wait);

	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	finish_wait(sk_sleep(sk), &wait);
	return rc;
}
EXPORT_SYMBOL(sk_wait_data);

/**
 *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
 *	@sk: socket
 *	@size: memory size to allocate
 *	@kind: allocation type
 *
 *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
 *	rmem allocation. This function assumes that protocols which have
 *	memory_pressure use sk_wmem_queued as write buffer accounting.
 */
int __sk_mem_schedule(struct sock *sk, int size, int kind)
{
	struct proto *prot = sk->sk_prot;
	int amt = sk_mem_pages(size);
	long allocated;

	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;

	allocated = sk_memory_allocated_add(sk, amt);

	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
		goto suppress_allocation;

	/* Under limit. */
	if (allocated <= sk_prot_mem_limits(sk, 0)) {
		sk_leave_memory_pressure(sk);
		return 1;
	}

	/* Under pressure. */
	if (allocated > sk_prot_mem_limits(sk, 1))
		sk_enter_memory_pressure(sk);

	/* Over hard limit. */
	if (allocated > sk_prot_mem_limits(sk, 2))
		goto suppress_allocation;

	/* guarantee minimum buffer size under pressure */
	if (kind == SK_MEM_RECV) {
		if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
			return 1;

	} else { /* SK_MEM_SEND */
		if (sk->sk_type == SOCK_STREAM) {
			if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
				return 1;
		} else if (atomic_read(&sk->sk_wmem_alloc) <
			   prot->sysctl_wmem[0])
				return 1;
	}

	if (sk_has_memory_pressure(sk)) {
		int alloc;

		if (!sk_under_memory_pressure(sk))
			return 1;
		alloc = sk_sockets_allocated_read_positive(sk);
		if (sk_prot_mem_limits(sk, 2) > alloc *
		    sk_mem_pages(sk->sk_wmem_queued +
				 atomic_read(&sk->sk_rmem_alloc) +
				 sk->sk_forward_alloc))
			return 1;
	}

suppress_allocation:

	if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
		sk_stream_moderate_sndbuf(sk);

		/* Fail only if socket is _under_ its sndbuf.
		 * In this case we cannot block, so that we have to fail.
		 */
		if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
			return 1;
	}

	trace_sock_exceed_buf_limit(sk, prot, allocated);

	/* Alas. Undo changes. */
	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;

	sk_memory_allocated_sub(sk, amt);

	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
		mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);

	return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);

/**
 *	__sk_mem_reclaim - reclaim memory_allocated
 *	@sk: socket
 *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
 */
void __sk_mem_reclaim(struct sock *sk, int amount)
{
	amount >>= SK_MEM_QUANTUM_SHIFT;
	sk_memory_allocated_sub(sk, amount);
	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;

	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);

	if (sk_under_memory_pressure(sk) &&
	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
		sk_leave_memory_pressure(sk);
}
EXPORT_SYMBOL(__sk_mem_reclaim);

int sk_set_peek_off(struct sock *sk, int val)
{
	if (val < 0)
		return -EINVAL;

	sk->sk_peek_off = val;
	return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);

/*
 * Set of default routines for initialising struct proto_ops when
 * the protocol does not support a particular function. In certain
 * cases where it makes no sense for a protocol to have a "do nothing"
 * function, some default processing is provided.
 */

int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_bind);

int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
		    int len, int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_connect);

int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_socketpair);

int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_accept);

int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
		    int *len, int peer)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getname);

unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
{
	return 0;
}
EXPORT_SYMBOL(sock_no_poll);

int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_ioctl);

int sock_no_listen(struct socket *sock, int backlog)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_listen);

int sock_no_shutdown(struct socket *sock, int how)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_shutdown);

int sock_no_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, unsigned int optlen)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_setsockopt);

int sock_no_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getsockopt);

int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg);

int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
		    int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_recvmsg);

int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma)
{
	/* Mirror missing mmap method error code */
	return -ENODEV;
}
EXPORT_SYMBOL(sock_no_mmap);

ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
	ssize_t res;
	struct msghdr msg = {.msg_flags = flags};
	struct kvec iov;
	char *kaddr = kmap(page);
	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	res = kernel_sendmsg(sock, &msg, &iov, 1, size);
	kunmap(page);
	return res;
}
EXPORT_SYMBOL(sock_no_sendpage);

/*
 *	Default Socket Callbacks
 */

static void sock_def_wakeup(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_all(&wq->wait);
	rcu_read_unlock();
}

static void sock_def_error_report(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_poll(&wq->wait, POLLERR);
	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
	rcu_read_unlock();
}

static void sock_def_readable(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
						POLLRDNORM | POLLRDBAND);
	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
	rcu_read_unlock();
}

static void sock_def_write_space(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();

	/* Do not wake up a writer until he can make "significant"
	 * progress.  --DaveM
	 */
	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
		wq = rcu_dereference(sk->sk_wq);
		if (skwq_has_sleeper(wq))
			wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
						POLLWRNORM | POLLWRBAND);

		/* Should agree with poll, otherwise some programs break */
		if (sock_writeable(sk))
			sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
	}

	rcu_read_unlock();
}

static void sock_def_destruct(struct sock *sk)
{
}

void sk_send_sigurg(struct sock *sk)
{
	if (sk->sk_socket && sk->sk_socket->file)
		if (send_sigurg(&sk->sk_socket->file->f_owner))
			sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
EXPORT_SYMBOL(sk_send_sigurg);

void sk_reset_timer(struct sock *sk, struct timer_list* timer,
		    unsigned long expires)
{
	if (!mod_timer(timer, expires))
		sock_hold(sk);
}
EXPORT_SYMBOL(sk_reset_timer);

void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
	if (del_timer(timer))
		__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);

void sock_init_data(struct socket *sock, struct sock *sk)
{
	skb_queue_head_init(&sk->sk_receive_queue);
	skb_queue_head_init(&sk->sk_write_queue);
	skb_queue_head_init(&sk->sk_error_queue);

	sk->sk_send_head	=	NULL;

	init_timer(&sk->sk_timer);

	sk->sk_allocation	=	GFP_KERNEL;
	sk->sk_rcvbuf		=	sysctl_rmem_default;
	sk->sk_sndbuf		=	sysctl_wmem_default;
	sk->sk_state		=	TCP_CLOSE;
	sk_set_socket(sk, sock);

	sock_set_flag(sk, SOCK_ZAPPED);

	if (sock) {
		sk->sk_type	=	sock->type;
		sk->sk_wq	=	sock->wq;
		sock->sk	=	sk;
	} else
		sk->sk_wq	=	NULL;

	rwlock_init(&sk->sk_callback_lock);
	lockdep_set_class_and_name(&sk->sk_callback_lock,
			af_callback_keys + sk->sk_family,
			af_family_clock_key_strings[sk->sk_family]);

	sk->sk_state_change	=	sock_def_wakeup;
	sk->sk_data_ready	=	sock_def_readable;
	sk->sk_write_space	=	sock_def_write_space;
	sk->sk_error_report	=	sock_def_error_report;
	sk->sk_destruct		=	sock_def_destruct;

	sk->sk_frag.page	=	NULL;
	sk->sk_frag.offset	=	0;
	sk->sk_peek_off		=	-1;

	sk->sk_peer_pid 	=	NULL;
	sk->sk_peer_cred	=	NULL;
	sk->sk_write_pending	=	0;
	sk->sk_rcvlowat		=	1;
	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;

	sk->sk_stamp = ktime_set(-1L, 0);

#ifdef CONFIG_NET_RX_BUSY_POLL
	sk->sk_napi_id		=	0;
	sk->sk_ll_usec		=	sysctl_net_busy_read;
#endif

	sk->sk_max_pacing_rate = ~0U;
	sk->sk_pacing_rate = ~0U;
	sk->sk_incoming_cpu = -1;
	/*
	 * Before updating sk_refcnt, we must commit prior changes to memory
	 * (Documentation/RCU/rculist_nulls.txt for details)
	 */
	smp_wmb();
	atomic_set(&sk->sk_refcnt, 1);
	atomic_set(&sk->sk_drops, 0);
}
EXPORT_SYMBOL(sock_init_data);

void lock_sock_nested(struct sock *sk, int subclass)
{
	might_sleep();
	spin_lock_bh(&sk->sk_lock.slock);
	if (sk->sk_lock.owned)
		__lock_sock(sk);
	sk->sk_lock.owned = 1;
	spin_unlock_bh(&sk->sk_lock.slock);
	/*
	 * The sk_lock has mutex_lock() semantics here:
	 */
	mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
}
EXPORT_SYMBOL(lock_sock_nested);

void release_sock(struct sock *sk)
{
	spin_lock_bh(&sk->sk_lock.slock);
	if (sk->sk_backlog.tail)
		__release_sock(sk);

	/* Warning : release_cb() might need to release sk ownership,
	 * ie call sock_release_ownership(sk) before us.
	 */
	if (sk->sk_prot->release_cb)
		sk->sk_prot->release_cb(sk);

	sock_release_ownership(sk);
	if (waitqueue_active(&sk->sk_lock.wq))
		wake_up(&sk->sk_lock.wq);
	spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);

/**
 * lock_sock_fast - fast version of lock_sock
 * @sk: socket
 *
 * This version should be used for very small section, where process wont block
 * return false if fast path is taken
 *   sk_lock.slock locked, owned = 0, BH disabled
 * return true if slow path is taken
 *   sk_lock.slock unlocked, owned = 1, BH enabled
 */
bool lock_sock_fast(struct sock *sk)
{
	might_sleep();
	spin_lock_bh(&sk->sk_lock.slock);

	if (!sk->sk_lock.owned)
		/*
		 * Note : We must disable BH
		 */
		return false;

	__lock_sock(sk);
	sk->sk_lock.owned = 1;
	spin_unlock(&sk->sk_lock.slock);
	/*
	 * The sk_lock has mutex_lock() semantics here:
	 */
	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
	local_bh_enable();
	return true;
}
EXPORT_SYMBOL(lock_sock_fast);

int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
	struct timeval tv;
	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
	tv = ktime_to_timeval(sk->sk_stamp);
	if (tv.tv_sec == -1)
		return -ENOENT;
	if (tv.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		tv = ktime_to_timeval(sk->sk_stamp);
	}
	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestamp);

int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
	struct timespec ts;
	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
	ts = ktime_to_timespec(sk->sk_stamp);
	if (ts.tv_sec == -1)
		return -ENOENT;
	if (ts.tv_sec == 0) {
		sk->sk_stamp = ktime_get_real();
		ts = ktime_to_timespec(sk->sk_stamp);
	}
	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestampns);

void sock_enable_timestamp(struct sock *sk, int flag)
{
	if (!sock_flag(sk, flag)) {
		unsigned long previous_flags = sk->sk_flags;

		sock_set_flag(sk, flag);
		/*
		 * we just set one of the two flags which require net
		 * time stamping, but time stamping might have been on
		 * already because of the other one
		 */
		if (sock_needs_netstamp(sk) &&
		    !(previous_flags & SK_FLAGS_TIMESTAMP))
			net_enable_timestamp();
	}
}

int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
		       int level, int type)
{
	struct sock_exterr_skb *serr;
	struct sk_buff *skb;
	int copied, err;

	err = -EAGAIN;
	skb = sock_dequeue_err_skb(sk);
	if (skb == NULL)
		goto out;

	copied = skb->len;
	if (copied > len) {
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}
	err = skb_copy_datagram_msg(skb, 0, msg, copied);
	if (err)
		goto out_free_skb;

	sock_recv_timestamp(msg, sk, skb);

	serr = SKB_EXT_ERR(skb);
	put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee);

	msg->msg_flags |= MSG_ERRQUEUE;
	err = copied;

out_free_skb:
	kfree_skb(skb);
out:
	return err;
}
EXPORT_SYMBOL(sock_recv_errqueue);

/*
 *	Get a socket option on an socket.
 *
 *	FIX: POSIX 1003.1g is very ambiguous here. It states that
 *	asynchronous errors should be reported by getsockopt. We assume
 *	this means if you specify SO_ERROR (otherwise whats the point of it).
 */
int sock_common_getsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_getsockopt);

#ifdef CONFIG_COMPAT
int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	if (sk->sk_prot->compat_getsockopt != NULL)
		return sk->sk_prot->compat_getsockopt(sk, level, optname,
						      optval, optlen);
	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_getsockopt);
#endif

int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
			int flags)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

	err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}
EXPORT_SYMBOL(sock_common_recvmsg);

/*
 *	Set socket options on an inet socket.
 */
int sock_common_setsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, unsigned int optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_setsockopt);

#ifdef CONFIG_COMPAT
int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, unsigned int optlen)
{
	struct sock *sk = sock->sk;

	if (sk->sk_prot->compat_setsockopt != NULL)
		return sk->sk_prot->compat_setsockopt(sk, level, optname,
						      optval, optlen);
	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_setsockopt);
#endif

void sk_common_release(struct sock *sk)
{
	if (sk->sk_prot->destroy)
		sk->sk_prot->destroy(sk);

	/*
	 * Observation: when sock_common_release is called, processes have
	 * no access to socket. But net still has.
	 * Step one, detach it from networking:
	 *
	 * A. Remove from hash tables.
	 */

	sk->sk_prot->unhash(sk);

	/*
	 * In this point socket cannot receive new packets, but it is possible
	 * that some packets are in flight because some CPU runs receiver and
	 * did hash table lookup before we unhashed socket. They will achieve
	 * receive queue and will be purged by socket destructor.
	 *
	 * Also we still have packets pending on receive queue and probably,
	 * our own packets waiting in device queues. sock_destroy will drain
	 * receive queue, but transmitted packets will delay socket destruction
	 * until the last reference will be released.
	 */

	sock_orphan(sk);

	xfrm_sk_free_policy(sk);

	sk_refcnt_debug_release(sk);

	sock_put(sk);
}
EXPORT_SYMBOL(sk_common_release);

#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR	64	/* should be enough for the first time */
struct prot_inuse {
	int val[PROTO_INUSE_NR];
};

static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);

#ifdef CONFIG_NET_NS
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
	__this_cpu_add(net->core.inuse->val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);

int sock_prot_inuse_get(struct net *net, struct proto *prot)
{
	int cpu, idx = prot->inuse_idx;
	int res = 0;

	for_each_possible_cpu(cpu)
		res += per_cpu_ptr(net->core.inuse, cpu)->val[idx];

	return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);

static int __net_init sock_inuse_init_net(struct net *net)
{
	net->core.inuse = alloc_percpu(struct prot_inuse);
	return net->core.inuse ? 0 : -ENOMEM;
}

static void __net_exit sock_inuse_exit_net(struct net *net)
{
	free_percpu(net->core.inuse);
}

static struct pernet_operations net_inuse_ops = {
	.init = sock_inuse_init_net,
	.exit = sock_inuse_exit_net,
};

static __init int net_inuse_init(void)
{
	if (register_pernet_subsys(&net_inuse_ops))
		panic("Cannot initialize net inuse counters");

	return 0;
}

core_initcall(net_inuse_init);
#else
static DEFINE_PER_CPU(struct prot_inuse, prot_inuse);

void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
	__this_cpu_add(prot_inuse.val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);

int sock_prot_inuse_get(struct net *net, struct proto *prot)
{
	int cpu, idx = prot->inuse_idx;
	int res = 0;

	for_each_possible_cpu(cpu)
		res += per_cpu(prot_inuse, cpu).val[idx];

	return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
#endif

static void assign_proto_idx(struct proto *prot)
{
	prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);

	if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
		pr_err("PROTO_INUSE_NR exhausted\n");
		return;
	}

	set_bit(prot->inuse_idx, proto_inuse_idx);
}

static void release_proto_idx(struct proto *prot)
{
	if (prot->inuse_idx != PROTO_INUSE_NR - 1)
		clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
static inline void assign_proto_idx(struct proto *prot)
{
}

static inline void release_proto_idx(struct proto *prot)
{
}
#endif

static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
{
	if (!rsk_prot)
		return;
	kfree(rsk_prot->slab_name);
	rsk_prot->slab_name = NULL;
	kmem_cache_destroy(rsk_prot->slab);
	rsk_prot->slab = NULL;
}

static int req_prot_init(const struct proto *prot)
{
	struct request_sock_ops *rsk_prot = prot->rsk_prot;

	if (!rsk_prot)
		return 0;

	rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
					prot->name);
	if (!rsk_prot->slab_name)
		return -ENOMEM;

	rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
					   rsk_prot->obj_size, 0,
					   prot->slab_flags, NULL);

	if (!rsk_prot->slab) {
		pr_crit("%s: Can't create request sock SLAB cache!\n",
			prot->name);
		return -ENOMEM;
	}
	return 0;
}

int proto_register(struct proto *prot, int alloc_slab)
{
	if (alloc_slab) {
		prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
					SLAB_HWCACHE_ALIGN | prot->slab_flags,
					NULL);

		if (prot->slab == NULL) {
			pr_crit("%s: Can't create sock SLAB cache!\n",
				prot->name);
			goto out;
		}

		if (req_prot_init(prot))
			goto out_free_request_sock_slab;

		if (prot->twsk_prot != NULL) {
			prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);

			if (prot->twsk_prot->twsk_slab_name == NULL)
				goto out_free_request_sock_slab;

			prot->twsk_prot->twsk_slab =
				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
						  prot->twsk_prot->twsk_obj_size,
						  0,
						  prot->slab_flags,
						  NULL);
			if (prot->twsk_prot->twsk_slab == NULL)
				goto out_free_timewait_sock_slab_name;
		}
	}

	mutex_lock(&proto_list_mutex);
	list_add(&prot->node, &proto_list);
	assign_proto_idx(prot);
	mutex_unlock(&proto_list_mutex);
	return 0;

out_free_timewait_sock_slab_name:
	kfree(prot->twsk_prot->twsk_slab_name);
out_free_request_sock_slab:
	req_prot_cleanup(prot->rsk_prot);

	kmem_cache_destroy(prot->slab);
	prot->slab = NULL;
out:
	return -ENOBUFS;
}
EXPORT_SYMBOL(proto_register);

void proto_unregister(struct proto *prot)
{
	mutex_lock(&proto_list_mutex);
	release_proto_idx(prot);
	list_del(&prot->node);
	mutex_unlock(&proto_list_mutex);

	kmem_cache_destroy(prot->slab);
	prot->slab = NULL;

	req_prot_cleanup(prot->rsk_prot);

	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
		kfree(prot->twsk_prot->twsk_slab_name);
		prot->twsk_prot->twsk_slab = NULL;
	}
}
EXPORT_SYMBOL(proto_unregister);

#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(proto_list_mutex)
{
	mutex_lock(&proto_list_mutex);
	return seq_list_start_head(&proto_list, *pos);
}

static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	return seq_list_next(v, &proto_list, pos);
}

static void proto_seq_stop(struct seq_file *seq, void *v)
	__releases(proto_list_mutex)
{
	mutex_unlock(&proto_list_mutex);
}

static char proto_method_implemented(const void *method)
{
	return method == NULL ? 'n' : 'y';
}
static long sock_prot_memory_allocated(struct proto *proto)
{
	return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
}

static char *sock_prot_memory_pressure(struct proto *proto)
{
	return proto->memory_pressure != NULL ?
	proto_memory_pressure(proto) ? "yes" : "no" : "NI";
}

static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{

	seq_printf(seq, "%-9s %4u %6d  %6ld   %-3s %6u   %-3s  %-10s "
			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
		   proto->name,
		   proto->obj_size,
		   sock_prot_inuse_get(seq_file_net(seq), proto),
		   sock_prot_memory_allocated(proto),
		   sock_prot_memory_pressure(proto),
		   proto->max_header,
		   proto->slab == NULL ? "no" : "yes",
		   module_name(proto->owner),
		   proto_method_implemented(proto->close),
		   proto_method_implemented(proto->connect),
		   proto_method_implemented(proto->disconnect),
		   proto_method_implemented(proto->accept),
		   proto_method_implemented(proto->ioctl),
		   proto_method_implemented(proto->init),
		   proto_method_implemented(proto->destroy),
		   proto_method_implemented(proto->shutdown),
		   proto_method_implemented(proto->setsockopt),
		   proto_method_implemented(proto->getsockopt),
		   proto_method_implemented(proto->sendmsg),
		   proto_method_implemented(proto->recvmsg),
		   proto_method_implemented(proto->sendpage),
		   proto_method_implemented(proto->bind),
		   proto_method_implemented(proto->backlog_rcv),
		   proto_method_implemented(proto->hash),
		   proto_method_implemented(proto->unhash),
		   proto_method_implemented(proto->get_port),
		   proto_method_implemented(proto->enter_memory_pressure));
}

static int proto_seq_show(struct seq_file *seq, void *v)
{
	if (v == &proto_list)
		seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
			   "protocol",
			   "size",
			   "sockets",
			   "memory",
			   "press",
			   "maxhdr",
			   "slab",
			   "module",
			   "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
	else
		proto_seq_printf(seq, list_entry(v, struct proto, node));
	return 0;
}

static const struct seq_operations proto_seq_ops = {
	.start  = proto_seq_start,
	.next   = proto_seq_next,
	.stop   = proto_seq_stop,
	.show   = proto_seq_show,
};

static int proto_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &proto_seq_ops,
			    sizeof(struct seq_net_private));
}

static const struct file_operations proto_seq_fops = {
	.owner		= THIS_MODULE,
	.open		= proto_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_net,
};

static __net_init int proto_init_net(struct net *net)
{
	if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops))
		return -ENOMEM;

	return 0;
}

static __net_exit void proto_exit_net(struct net *net)
{
	remove_proc_entry("protocols", net->proc_net);
}


static __net_initdata struct pernet_operations proto_net_ops = {
	.init = proto_init_net,
	.exit = proto_exit_net,
};

static int __init proto_init(void)
{
	return register_pernet_subsys(&proto_net_ops);
}

subsys_initcall(proto_init);

#endif /* PROC_FS */