aboutsummaryrefslogtreecommitdiffstats
path: root/net/tipc/socket.c
blob: 656940692a445cea81eca88d03679daa7bdb7d29 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
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
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
/*
 * net/tipc/socket.c: TIPC socket API
 *
 * Copyright (c) 2001-2007, 2012-2017, Ericsson AB
 * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include <linux/rhashtable.h>
#include <linux/sched/signal.h>

#include "core.h"
#include "name_table.h"
#include "node.h"
#include "link.h"
#include "name_distr.h"
#include "socket.h"
#include "bcast.h"
#include "netlink.h"
#include "group.h"

#define CONN_TIMEOUT_DEFAULT    8000    /* default connect timeout = 8s */
#define CONN_PROBING_INTV	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
#define TIPC_FWD_MSG		1
#define TIPC_MAX_PORT		0xffffffff
#define TIPC_MIN_PORT		1
#define TIPC_ACK_RATE		4       /* ACK at 1/4 of of rcv window size */

enum {
	TIPC_LISTEN = TCP_LISTEN,
	TIPC_ESTABLISHED = TCP_ESTABLISHED,
	TIPC_OPEN = TCP_CLOSE,
	TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
	TIPC_CONNECTING = TCP_SYN_SENT,
};

struct sockaddr_pair {
	struct sockaddr_tipc sock;
	struct sockaddr_tipc member;
};

/**
 * struct tipc_sock - TIPC socket structure
 * @sk: socket - interacts with 'port' and with user via the socket API
 * @conn_type: TIPC type used when connection was established
 * @conn_instance: TIPC instance used when connection was established
 * @published: non-zero if port has one or more associated names
 * @max_pkt: maximum packet size "hint" used when building messages sent by port
 * @portid: unique port identity in TIPC socket hash table
 * @phdr: preformatted message header used when sending messages
 * #cong_links: list of congested links
 * @publications: list of publications for port
 * @blocking_link: address of the congested link we are currently sleeping on
 * @pub_count: total # of publications port has made during its lifetime
 * @conn_timeout: the time we can wait for an unresponded setup request
 * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
 * @cong_link_cnt: number of congested links
 * @snt_unacked: # messages sent by socket, and not yet acked by peer
 * @rcv_unacked: # messages read by user, but not yet acked back to peer
 * @peer: 'connected' peer for dgram/rdm
 * @node: hash table node
 * @mc_method: cookie for use between socket and broadcast layer
 * @rcu: rcu struct for tipc_sock
 */
struct tipc_sock {
	struct sock sk;
	u32 conn_type;
	u32 conn_instance;
	int published;
	u32 max_pkt;
	u32 portid;
	struct tipc_msg phdr;
	struct list_head cong_links;
	struct list_head publications;
	u32 pub_count;
	atomic_t dupl_rcvcnt;
	u16 conn_timeout;
	bool probe_unacked;
	u16 cong_link_cnt;
	u16 snt_unacked;
	u16 snd_win;
	u16 peer_caps;
	u16 rcv_unacked;
	u16 rcv_win;
	struct sockaddr_tipc peer;
	struct rhash_head node;
	struct tipc_mc_method mc_method;
	struct rcu_head rcu;
	struct tipc_group *group;
	bool group_is_open;
};

static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
static void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
		       bool kern);
static void tipc_sk_timeout(struct timer_list *t);
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
			   struct tipc_name_seq const *seq);
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
			    struct tipc_name_seq const *seq);
static int tipc_sk_leave(struct tipc_sock *tsk);
static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);

static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
static const struct proto_ops msg_ops;
static struct proto tipc_proto;
static const struct rhashtable_params tsk_rht_params;

static u32 tsk_own_node(struct tipc_sock *tsk)
{
	return msg_prevnode(&tsk->phdr);
}

static u32 tsk_peer_node(struct tipc_sock *tsk)
{
	return msg_destnode(&tsk->phdr);
}

static u32 tsk_peer_port(struct tipc_sock *tsk)
{
	return msg_destport(&tsk->phdr);
}

static  bool tsk_unreliable(struct tipc_sock *tsk)
{
	return msg_src_droppable(&tsk->phdr) != 0;
}

static void tsk_set_unreliable(struct tipc_sock *tsk, bool unreliable)
{
	msg_set_src_droppable(&tsk->phdr, unreliable ? 1 : 0);
}

static bool tsk_unreturnable(struct tipc_sock *tsk)
{
	return msg_dest_droppable(&tsk->phdr) != 0;
}

static void tsk_set_unreturnable(struct tipc_sock *tsk, bool unreturnable)
{
	msg_set_dest_droppable(&tsk->phdr, unreturnable ? 1 : 0);
}

static int tsk_importance(struct tipc_sock *tsk)
{
	return msg_importance(&tsk->phdr);
}

static int tsk_set_importance(struct tipc_sock *tsk, int imp)
{
	if (imp > TIPC_CRITICAL_IMPORTANCE)
		return -EINVAL;
	msg_set_importance(&tsk->phdr, (u32)imp);
	return 0;
}

static struct tipc_sock *tipc_sk(const struct sock *sk)
{
	return container_of(sk, struct tipc_sock, sk);
}

static bool tsk_conn_cong(struct tipc_sock *tsk)
{
	return tsk->snt_unacked > tsk->snd_win;
}

static u16 tsk_blocks(int len)
{
	return ((len / FLOWCTL_BLK_SZ) + 1);
}

/* tsk_blocks(): translate a buffer size in bytes to number of
 * advertisable blocks, taking into account the ratio truesize(len)/len
 * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ
 */
static u16 tsk_adv_blocks(int len)
{
	return len / FLOWCTL_BLK_SZ / 4;
}

/* tsk_inc(): increment counter for sent or received data
 * - If block based flow control is not supported by peer we
 *   fall back to message based ditto, incrementing the counter
 */
static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
{
	if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
		return ((msglen / FLOWCTL_BLK_SZ) + 1);
	return 1;
}

/**
 * tsk_advance_rx_queue - discard first buffer in socket receive queue
 *
 * Caller must hold socket lock
 */
static void tsk_advance_rx_queue(struct sock *sk)
{
	kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}

/* tipc_sk_respond() : send response message back to sender
 */
static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
{
	u32 selector;
	u32 dnode;
	u32 onode = tipc_own_addr(sock_net(sk));

	if (!tipc_msg_reverse(onode, &skb, err))
		return;

	dnode = msg_destnode(buf_msg(skb));
	selector = msg_origport(buf_msg(skb));
	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
}

/**
 * tsk_rej_rx_queue - reject all buffers in socket receive queue
 *
 * Caller must hold socket lock
 */
static void tsk_rej_rx_queue(struct sock *sk)
{
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(&sk->sk_receive_queue)))
		tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
}

static bool tipc_sk_connected(struct sock *sk)
{
	return sk->sk_state == TIPC_ESTABLISHED;
}

/* tipc_sk_type_connectionless - check if the socket is datagram socket
 * @sk: socket
 *
 * Returns true if connection less, false otherwise
 */
static bool tipc_sk_type_connectionless(struct sock *sk)
{
	return sk->sk_type == SOCK_RDM || sk->sk_type == SOCK_DGRAM;
}

/* tsk_peer_msg - verify if message was sent by connected port's peer
 *
 * Handles cases where the node's network address has changed from
 * the default of <0.0.0> to its configured setting.
 */
static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
{
	struct sock *sk = &tsk->sk;
	u32 self = tipc_own_addr(sock_net(sk));
	u32 peer_port = tsk_peer_port(tsk);
	u32 orig_node, peer_node;

	if (unlikely(!tipc_sk_connected(sk)))
		return false;

	if (unlikely(msg_origport(msg) != peer_port))
		return false;

	orig_node = msg_orignode(msg);
	peer_node = tsk_peer_node(tsk);

	if (likely(orig_node == peer_node))
		return true;

	if (!orig_node && peer_node == self)
		return true;

	if (!peer_node && orig_node == self)
		return true;

	return false;
}

/* tipc_set_sk_state - set the sk_state of the socket
 * @sk: socket
 *
 * Caller must hold socket lock
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_set_sk_state(struct sock *sk, int state)
{
	int oldsk_state = sk->sk_state;
	int res = -EINVAL;

	switch (state) {
	case TIPC_OPEN:
		res = 0;
		break;
	case TIPC_LISTEN:
	case TIPC_CONNECTING:
		if (oldsk_state == TIPC_OPEN)
			res = 0;
		break;
	case TIPC_ESTABLISHED:
		if (oldsk_state == TIPC_CONNECTING ||
		    oldsk_state == TIPC_OPEN)
			res = 0;
		break;
	case TIPC_DISCONNECTING:
		if (oldsk_state == TIPC_CONNECTING ||
		    oldsk_state == TIPC_ESTABLISHED)
			res = 0;
		break;
	}

	if (!res)
		sk->sk_state = state;

	return res;
}

static int tipc_sk_sock_err(struct socket *sock, long *timeout)
{
	struct sock *sk = sock->sk;
	int err = sock_error(sk);
	int typ = sock->type;

	if (err)
		return err;
	if (typ == SOCK_STREAM || typ == SOCK_SEQPACKET) {
		if (sk->sk_state == TIPC_DISCONNECTING)
			return -EPIPE;
		else if (!tipc_sk_connected(sk))
			return -ENOTCONN;
	}
	if (!*timeout)
		return -EAGAIN;
	if (signal_pending(current))
		return sock_intr_errno(*timeout);

	return 0;
}

#define tipc_wait_for_cond(sock_, timeo_, condition_)			       \
({                                                                             \
	struct sock *sk_;						       \
	int rc_;							       \
									       \
	while ((rc_ = !(condition_))) {					       \
		DEFINE_WAIT_FUNC(wait_, woken_wake_function);	               \
		sk_ = (sock_)->sk;					       \
		rc_ = tipc_sk_sock_err((sock_), timeo_);		       \
		if (rc_)						       \
			break;						       \
		prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE);    \
		release_sock(sk_);					       \
		*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
		sched_annotate_sleep();				               \
		lock_sock(sk_);						       \
		remove_wait_queue(sk_sleep(sk_), &wait_);		       \
	}								       \
	rc_;								       \
})

/**
 * tipc_sk_create - create a TIPC socket
 * @net: network namespace (must be default network)
 * @sock: pre-allocated socket structure
 * @protocol: protocol indicator (must be 0)
 * @kern: caused by kernel or by userspace?
 *
 * This routine creates additional data structures used by the TIPC socket,
 * initializes them, and links them together.
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_sk_create(struct net *net, struct socket *sock,
			  int protocol, int kern)
{
	const struct proto_ops *ops;
	struct sock *sk;
	struct tipc_sock *tsk;
	struct tipc_msg *msg;

	/* Validate arguments */
	if (unlikely(protocol != 0))
		return -EPROTONOSUPPORT;

	switch (sock->type) {
	case SOCK_STREAM:
		ops = &stream_ops;
		break;
	case SOCK_SEQPACKET:
		ops = &packet_ops;
		break;
	case SOCK_DGRAM:
	case SOCK_RDM:
		ops = &msg_ops;
		break;
	default:
		return -EPROTOTYPE;
	}

	/* Allocate socket's protocol area */
	sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto, kern);
	if (sk == NULL)
		return -ENOMEM;

	tsk = tipc_sk(sk);
	tsk->max_pkt = MAX_PKT_DEFAULT;
	INIT_LIST_HEAD(&tsk->publications);
	INIT_LIST_HEAD(&tsk->cong_links);
	msg = &tsk->phdr;

	/* Finish initializing socket data structures */
	sock->ops = ops;
	sock_init_data(sock, sk);
	tipc_set_sk_state(sk, TIPC_OPEN);
	if (tipc_sk_insert(tsk)) {
		pr_warn("Socket create failed; port number exhausted\n");
		return -EINVAL;
	}

	/* Ensure tsk is visible before we read own_addr. */
	smp_mb();

	tipc_msg_init(tipc_own_addr(net), msg, TIPC_LOW_IMPORTANCE,
		      TIPC_NAMED_MSG, NAMED_H_SIZE, 0);

	msg_set_origport(msg, tsk->portid);
	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
	sk->sk_shutdown = 0;
	sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
	sk->sk_data_ready = tipc_data_ready;
	sk->sk_write_space = tipc_write_space;
	sk->sk_destruct = tipc_sock_destruct;
	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
	tsk->group_is_open = true;
	atomic_set(&tsk->dupl_rcvcnt, 0);

	/* Start out with safe limits until we receive an advertised window */
	tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
	tsk->rcv_win = tsk->snd_win;

	if (tipc_sk_type_connectionless(sk)) {
		tsk_set_unreturnable(tsk, true);
		if (sock->type == SOCK_DGRAM)
			tsk_set_unreliable(tsk, true);
	}

	return 0;
}

static void tipc_sk_callback(struct rcu_head *head)
{
	struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu);

	sock_put(&tsk->sk);
}

/* Caller should hold socket lock for the socket. */
static void __tipc_shutdown(struct socket *sock, int error)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct net *net = sock_net(sk);
	long timeout = CONN_TIMEOUT_DEFAULT;
	u32 dnode = tsk_peer_node(tsk);
	struct sk_buff *skb;

	/* Avoid that hi-prio shutdown msgs bypass msgs in link wakeup queue */
	tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt &&
					    !tsk_conn_cong(tsk)));

	/* Remove any pending SYN message */
	__skb_queue_purge(&sk->sk_write_queue);

	/* Reject all unreceived messages, except on an active connection
	 * (which disconnects locally & sends a 'FIN+' to peer).
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		if (TIPC_SKB_CB(skb)->bytes_read) {
			kfree_skb(skb);
			continue;
		}
		if (!tipc_sk_type_connectionless(sk) &&
		    sk->sk_state != TIPC_DISCONNECTING) {
			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
			tipc_node_remove_conn(net, dnode, tsk->portid);
		}
		tipc_sk_respond(sk, skb, error);
	}

	if (tipc_sk_type_connectionless(sk))
		return;

	if (sk->sk_state != TIPC_DISCONNECTING) {
		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
				      tsk_own_node(tsk), tsk_peer_port(tsk),
				      tsk->portid, error);
		if (skb)
			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
		tipc_node_remove_conn(net, dnode, tsk->portid);
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
	}
}

/**
 * tipc_release - destroy a TIPC socket
 * @sock: socket to destroy
 *
 * This routine cleans up any messages that are still queued on the socket.
 * For DGRAM and RDM socket types, all queued messages are rejected.
 * For SEQPACKET and STREAM socket types, the first message is rejected
 * and any others are discarded.  (If the first message on a STREAM socket
 * is partially-read, it is discarded and the next one is rejected instead.)
 *
 * NOTE: Rejected messages are not necessarily returned to the sender!  They
 * are returned or discarded according to the "destination droppable" setting
 * specified for the message by the sender.
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk;

	/*
	 * Exit if socket isn't fully initialized (occurs when a failed accept()
	 * releases a pre-allocated child socket that was never used)
	 */
	if (sk == NULL)
		return 0;

	tsk = tipc_sk(sk);
	lock_sock(sk);

	__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
	sk->sk_shutdown = SHUTDOWN_MASK;
	tipc_sk_leave(tsk);
	tipc_sk_withdraw(tsk, 0, NULL);
	sk_stop_timer(sk, &sk->sk_timer);
	tipc_sk_remove(tsk);

	sock_orphan(sk);
	/* Reject any messages that accumulated in backlog queue */
	release_sock(sk);
	tipc_dest_list_purge(&tsk->cong_links);
	tsk->cong_link_cnt = 0;
	call_rcu(&tsk->rcu, tipc_sk_callback);
	sock->sk = NULL;

	return 0;
}

/**
 * tipc_bind - associate or disassocate TIPC name(s) with a socket
 * @sock: socket structure
 * @uaddr: socket address describing name(s) and desired operation
 * @uaddr_len: size of socket address data structure
 *
 * Name and name sequence binding is indicated using a positive scope value;
 * a negative scope value unbinds the specified name.  Specifying no name
 * (i.e. a socket address length of 0) unbinds all names from the socket.
 *
 * Returns 0 on success, errno otherwise
 *
 * NOTE: This routine doesn't need to take the socket lock since it doesn't
 *       access any non-constant socket information.
 */
static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
		     int uaddr_len)
{
	struct sock *sk = sock->sk;
	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
	struct tipc_sock *tsk = tipc_sk(sk);
	int res = -EINVAL;

	lock_sock(sk);
	if (unlikely(!uaddr_len)) {
		res = tipc_sk_withdraw(tsk, 0, NULL);
		goto exit;
	}
	if (tsk->group) {
		res = -EACCES;
		goto exit;
	}
	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
		res = -EINVAL;
		goto exit;
	}
	if (addr->family != AF_TIPC) {
		res = -EAFNOSUPPORT;
		goto exit;
	}

	if (addr->addrtype == TIPC_ADDR_NAME)
		addr->addr.nameseq.upper = addr->addr.nameseq.lower;
	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
		res = -EAFNOSUPPORT;
		goto exit;
	}

	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
		res = -EACCES;
		goto exit;
	}

	res = (addr->scope >= 0) ?
		tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
		tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
exit:
	release_sock(sk);
	return res;
}

/**
 * tipc_getname - get port ID of socket or peer socket
 * @sock: socket structure
 * @uaddr: area for returned socket address
 * @uaddr_len: area for returned length of socket address
 * @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID
 *
 * Returns 0 on success, errno otherwise
 *
 * NOTE: This routine doesn't need to take the socket lock since it only
 *       accesses socket information that is unchanging (or which changes in
 *       a completely predictable manner).
 */
static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
			int peer)
{
	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);

	memset(addr, 0, sizeof(*addr));
	if (peer) {
		if ((!tipc_sk_connected(sk)) &&
		    ((peer != 2) || (sk->sk_state != TIPC_DISCONNECTING)))
			return -ENOTCONN;
		addr->addr.id.ref = tsk_peer_port(tsk);
		addr->addr.id.node = tsk_peer_node(tsk);
	} else {
		addr->addr.id.ref = tsk->portid;
		addr->addr.id.node = tipc_own_addr(sock_net(sk));
	}

	addr->addrtype = TIPC_ADDR_ID;
	addr->family = AF_TIPC;
	addr->scope = 0;
	addr->addr.name.domain = 0;

	return sizeof(*addr);
}

/**
 * tipc_poll - read and possibly block on pollmask
 * @file: file structure associated with the socket
 * @sock: socket for which to calculate the poll bits
 * @wait: ???
 *
 * Returns pollmask value
 *
 * COMMENTARY:
 * It appears that the usual socket locking mechanisms are not useful here
 * since the pollmask info is potentially out-of-date the moment this routine
 * exits.  TCP and other protocols seem to rely on higher level poll routines
 * to handle any preventable race conditions, so TIPC will do the same ...
 *
 * IMPORTANT: The fact that a read or write operation is indicated does NOT
 * imply that the operation will succeed, merely that it should be performed
 * and will not block.
 */
static __poll_t tipc_poll(struct file *file, struct socket *sock,
			      poll_table *wait)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	__poll_t revents = 0;

	sock_poll_wait(file, sock, wait);

	if (sk->sk_shutdown & RCV_SHUTDOWN)
		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		revents |= EPOLLHUP;

	switch (sk->sk_state) {
	case TIPC_ESTABLISHED:
	case TIPC_CONNECTING:
		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
			revents |= EPOLLOUT;
		/* fall thru' */
	case TIPC_LISTEN:
		if (!skb_queue_empty(&sk->sk_receive_queue))
			revents |= EPOLLIN | EPOLLRDNORM;
		break;
	case TIPC_OPEN:
		if (tsk->group_is_open && !tsk->cong_link_cnt)
			revents |= EPOLLOUT;
		if (!tipc_sk_type_connectionless(sk))
			break;
		if (skb_queue_empty(&sk->sk_receive_queue))
			break;
		revents |= EPOLLIN | EPOLLRDNORM;
		break;
	case TIPC_DISCONNECTING:
		revents = EPOLLIN | EPOLLRDNORM | EPOLLHUP;
		break;
	}
	return revents;
}

/**
 * tipc_sendmcast - send multicast message
 * @sock: socket structure
 * @seq: destination address
 * @msg: message to send
 * @dlen: length of data to send
 * @timeout: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
			  struct msghdr *msg, size_t dlen, long timeout)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = &tsk->phdr;
	struct net *net = sock_net(sk);
	int mtu = tipc_bcast_get_mtu(net);
	struct tipc_mc_method *method = &tsk->mc_method;
	struct sk_buff_head pkts;
	struct tipc_nlist dsts;
	int rc;

	if (tsk->group)
		return -EACCES;

	/* Block or return if any destination link is congested */
	rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
	if (unlikely(rc))
		return rc;

	/* Lookup destination nodes */
	tipc_nlist_init(&dsts, tipc_own_addr(net));
	tipc_nametbl_lookup_dst_nodes(net, seq->type, seq->lower,
				      seq->upper, &dsts);
	if (!dsts.local && !dsts.remote)
		return -EHOSTUNREACH;

	/* Build message header */
	msg_set_type(hdr, TIPC_MCAST_MSG);
	msg_set_hdr_sz(hdr, MCAST_H_SIZE);
	msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE);
	msg_set_destport(hdr, 0);
	msg_set_destnode(hdr, 0);
	msg_set_nametype(hdr, seq->type);
	msg_set_namelower(hdr, seq->lower);
	msg_set_nameupper(hdr, seq->upper);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);

	/* Send message if build was successful */
	if (unlikely(rc == dlen))
		rc = tipc_mcast_xmit(net, &pkts, method, &dsts,
				     &tsk->cong_link_cnt);

	tipc_nlist_purge(&dsts);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_msg - send a message to a member in the group
 * @net: network namespace
 * @m: message to send
 * @mb: group member
 * @dnode: destination node
 * @dport: destination port
 * @dlen: total length of message data
 */
static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
			       struct msghdr *m, struct tipc_member *mb,
			       u32 dnode, u32 dport, int dlen)
{
	u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group);
	struct tipc_mc_method *method = &tsk->mc_method;
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_msg *hdr = &tsk->phdr;
	struct sk_buff_head pkts;
	int mtu, rc;

	/* Complete message header */
	msg_set_type(hdr, TIPC_GRP_UCAST_MSG);
	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
	msg_set_destport(hdr, dport);
	msg_set_destnode(hdr, dnode);
	msg_set_grp_bc_seqno(hdr, bc_snd_nxt);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;

	/* Send message */
	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
	if (unlikely(rc == -ELINKCONG)) {
		tipc_dest_push(&tsk->cong_links, dnode, 0);
		tsk->cong_link_cnt++;
	}

	/* Update send window */
	tipc_group_update_member(mb, blks);

	/* A broadcast sent within next EXPIRE period must follow same path */
	method->rcast = true;
	method->mandatory = true;
	return dlen;
}

/**
 * tipc_send_group_unicast - send message to a member in the group
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
				   int dlen, long timeout)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct net *net = sock_net(sk);
	struct tipc_member *mb = NULL;
	u32 node, port;
	int rc;

	node = dest->addr.id.node;
	port = dest->addr.id.ref;
	if (!port && !node)
		return -EHOSTUNREACH;

	/* Block or return if destination link or member is congested */
	rc = tipc_wait_for_cond(sock, &timeout,
				!tipc_dest_find(&tsk->cong_links, node, 0) &&
				tsk->group &&
				!tipc_group_cong(tsk->group, node, port, blks,
						 &mb));
	if (unlikely(rc))
		return rc;

	if (unlikely(!mb))
		return -EHOSTUNREACH;

	rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_anycast - send message to any member with given identity
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
				   int dlen, long timeout)
{
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct list_head *cong_links = &tsk->cong_links;
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_msg *hdr = &tsk->phdr;
	struct tipc_member *first = NULL;
	struct tipc_member *mbr = NULL;
	struct net *net = sock_net(sk);
	u32 node, port, exclude;
	struct list_head dsts;
	u32 type, inst, scope;
	int lookups = 0;
	int dstcnt, rc;
	bool cong;

	INIT_LIST_HEAD(&dsts);

	type = msg_nametype(hdr);
	inst = dest->addr.name.name.instance;
	scope = msg_lookup_scope(hdr);

	while (++lookups < 4) {
		exclude = tipc_group_exclude(tsk->group);

		first = NULL;

		/* Look for a non-congested destination member, if any */
		while (1) {
			if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
						 &dstcnt, exclude, false))
				return -EHOSTUNREACH;
			tipc_dest_pop(&dsts, &node, &port);
			cong = tipc_group_cong(tsk->group, node, port, blks,
					       &mbr);
			if (!cong)
				break;
			if (mbr == first)
				break;
			if (!first)
				first = mbr;
		}

		/* Start over if destination was not in member list */
		if (unlikely(!mbr))
			continue;

		if (likely(!cong && !tipc_dest_find(cong_links, node, 0)))
			break;

		/* Block or return if destination link or member is congested */
		rc = tipc_wait_for_cond(sock, &timeout,
					!tipc_dest_find(cong_links, node, 0) &&
					tsk->group &&
					!tipc_group_cong(tsk->group, node, port,
							 blks, &mbr));
		if (unlikely(rc))
			return rc;

		/* Send, unless destination disappeared while waiting */
		if (likely(mbr))
			break;
	}

	if (unlikely(lookups >= 4))
		return -EHOSTUNREACH;

	rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_bcast - send message to all members in communication group
 * @sk: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
				 int dlen, long timeout)
{
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_nlist *dsts = tipc_group_dests(tsk->group);
	struct tipc_mc_method *method = &tsk->mc_method;
	bool ack = method->mandatory && method->rcast;
	int blks = tsk_blocks(MCAST_H_SIZE + dlen);
	struct tipc_msg *hdr = &tsk->phdr;
	int mtu = tipc_bcast_get_mtu(net);
	struct sk_buff_head pkts;
	int rc = -EHOSTUNREACH;

	if (!dsts->local && !dsts->remote)
		return -EHOSTUNREACH;

	/* Block or return if any destination link or member is congested */
	rc = tipc_wait_for_cond(sock, &timeout,
				!tsk->cong_link_cnt && tsk->group &&
				!tipc_group_bc_cong(tsk->group, blks));
	if (unlikely(rc))
		return rc;

	/* Complete message header */
	if (dest) {
		msg_set_type(hdr, TIPC_GRP_MCAST_MSG);
		msg_set_nameinst(hdr, dest->addr.name.name.instance);
	} else {
		msg_set_type(hdr, TIPC_GRP_BCAST_MSG);
		msg_set_nameinst(hdr, 0);
	}
	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
	msg_set_destport(hdr, 0);
	msg_set_destnode(hdr, 0);
	msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group));

	/* Avoid getting stuck with repeated forced replicasts */
	msg_set_grp_bc_ack_req(hdr, ack);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;

	/* Send message */
	rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt);
	if (unlikely(rc))
		return rc;

	/* Update broadcast sequence number and send windows */
	tipc_group_update_bc_members(tsk->group, blks, ack);

	/* Broadcast link is now free to choose method for next broadcast */
	method->mandatory = false;
	method->expires = jiffies;

	return dlen;
}

/**
 * tipc_send_group_mcast - send message to all members with given identity
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
				 int dlen, long timeout)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_msg *hdr = &tsk->phdr;
	struct net *net = sock_net(sk);
	u32 type, inst, scope, exclude;
	struct list_head dsts;
	u32 dstcnt;

	INIT_LIST_HEAD(&dsts);

	type = msg_nametype(hdr);
	inst = dest->addr.name.name.instance;
	scope = msg_lookup_scope(hdr);
	exclude = tipc_group_exclude(grp);

	if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
				 &dstcnt, exclude, true))
		return -EHOSTUNREACH;

	if (dstcnt == 1) {
		tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref);
		return tipc_send_group_unicast(sock, m, dlen, timeout);
	}

	tipc_dest_list_purge(&dsts);
	return tipc_send_group_bcast(sock, m, dlen, timeout);
}

/**
 * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
 * @arrvq: queue with arriving messages, to be cloned after destination lookup
 * @inputq: queue with cloned messages, delivered to socket after dest lookup
 *
 * Multi-threaded: parallel calls with reference to same queues may occur
 */
void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
		       struct sk_buff_head *inputq)
{
	u32 self = tipc_own_addr(net);
	u32 type, lower, upper, scope;
	struct sk_buff *skb, *_skb;
	u32 portid, onode;
	struct sk_buff_head tmpq;
	struct list_head dports;
	struct tipc_msg *hdr;
	int user, mtyp, hlen;
	bool exact;

	__skb_queue_head_init(&tmpq);
	INIT_LIST_HEAD(&dports);

	skb = tipc_skb_peek(arrvq, &inputq->lock);
	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
		hdr = buf_msg(skb);
		user = msg_user(hdr);
		mtyp = msg_type(hdr);
		hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
		onode = msg_orignode(hdr);
		type = msg_nametype(hdr);

		if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
			spin_lock_bh(&inputq->lock);
			if (skb_peek(arrvq) == skb) {
				__skb_dequeue(arrvq);
				__skb_queue_tail(inputq, skb);
			}
			kfree_skb(skb);
			spin_unlock_bh(&inputq->lock);
			continue;
		}

		/* Group messages require exact scope match */
		if (msg_in_group(hdr)) {
			lower = 0;
			upper = ~0;
			scope = msg_lookup_scope(hdr);
			exact = true;
		} else {
			/* TIPC_NODE_SCOPE means "any scope" in this context */
			if (onode == self)
				scope = TIPC_NODE_SCOPE;
			else
				scope = TIPC_CLUSTER_SCOPE;
			exact = false;
			lower = msg_namelower(hdr);
			upper = msg_nameupper(hdr);
		}

		/* Create destination port list: */
		tipc_nametbl_mc_lookup(net, type, lower, upper,
				       scope, exact, &dports);

		/* Clone message per destination */
		while (tipc_dest_pop(&dports, NULL, &portid)) {
			_skb = __pskb_copy(skb, hlen, GFP_ATOMIC);
			if (_skb) {
				msg_set_destport(buf_msg(_skb), portid);
				__skb_queue_tail(&tmpq, _skb);
				continue;
			}
			pr_warn("Failed to clone mcast rcv buffer\n");
		}
		/* Append to inputq if not already done by other thread */
		spin_lock_bh(&inputq->lock);
		if (skb_peek(arrvq) == skb) {
			skb_queue_splice_tail_init(&tmpq, inputq);
			kfree_skb(__skb_dequeue(arrvq));
		}
		spin_unlock_bh(&inputq->lock);
		__skb_queue_purge(&tmpq);
		kfree_skb(skb);
	}
	tipc_sk_rcv(net, inputq);
}

/**
 * tipc_sk_conn_proto_rcv - receive a connection mng protocol message
 * @tsk: receiving socket
 * @skb: pointer to message buffer.
 */
static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
				   struct sk_buff_head *inputq,
				   struct sk_buff_head *xmitq)
{
	struct tipc_msg *hdr = buf_msg(skb);
	u32 onode = tsk_own_node(tsk);
	struct sock *sk = &tsk->sk;
	int mtyp = msg_type(hdr);
	bool conn_cong;

	/* Ignore if connection cannot be validated: */
	if (!tsk_peer_msg(tsk, hdr))
		goto exit;

	if (unlikely(msg_errcode(hdr))) {
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
		tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
				      tsk_peer_port(tsk));
		sk->sk_state_change(sk);

		/* State change is ignored if socket already awake,
		 * - convert msg to abort msg and add to inqueue
		 */
		msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE);
		msg_set_type(hdr, TIPC_CONN_MSG);
		msg_set_size(hdr, BASIC_H_SIZE);
		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
		__skb_queue_tail(inputq, skb);
		return;
	}

	tsk->probe_unacked = false;

	if (mtyp == CONN_PROBE) {
		msg_set_type(hdr, CONN_PROBE_REPLY);
		if (tipc_msg_reverse(onode, &skb, TIPC_OK))
			__skb_queue_tail(xmitq, skb);
		return;
	} else if (mtyp == CONN_ACK) {
		conn_cong = tsk_conn_cong(tsk);
		tsk->snt_unacked -= msg_conn_ack(hdr);
		if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
			tsk->snd_win = msg_adv_win(hdr);
		if (conn_cong)
			sk->sk_write_space(sk);
	} else if (mtyp != CONN_PROBE_REPLY) {
		pr_warn("Received unknown CONN_PROTO msg\n");
	}
exit:
	kfree_skb(skb);
}

/**
 * tipc_sendmsg - send message in connectionless manner
 * @sock: socket structure
 * @m: message to send
 * @dsz: amount of user data to be sent
 *
 * Message must have an destination specified explicitly.
 * Used for SOCK_RDM and SOCK_DGRAM messages,
 * and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections.
 * (Note: 'SYN+' is prohibited on SOCK_STREAM.)
 *
 * Returns the number of bytes sent on success, or errno otherwise
 */
static int tipc_sendmsg(struct socket *sock,
			struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	int ret;

	lock_sock(sk);
	ret = __tipc_sendmsg(sock, m, dsz);
	release_sock(sk);

	return ret;
}

static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
	struct list_head *clinks = &tsk->cong_links;
	bool syn = !tipc_sk_type_connectionless(sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_msg *hdr = &tsk->phdr;
	struct tipc_name_seq *seq;
	struct sk_buff_head pkts;
	u32 dport, dnode = 0;
	u32 type, inst;
	int mtu, rc;

	if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
		return -EMSGSIZE;

	if (likely(dest)) {
		if (unlikely(m->msg_namelen < sizeof(*dest)))
			return -EINVAL;
		if (unlikely(dest->family != AF_TIPC))
			return -EINVAL;
	}

	if (grp) {
		if (!dest)
			return tipc_send_group_bcast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_NAME)
			return tipc_send_group_anycast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_ID)
			return tipc_send_group_unicast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_MCAST)
			return tipc_send_group_mcast(sock, m, dlen, timeout);
		return -EINVAL;
	}

	if (unlikely(!dest)) {
		dest = &tsk->peer;
		if (!syn || dest->family != AF_TIPC)
			return -EDESTADDRREQ;
	}

	if (unlikely(syn)) {
		if (sk->sk_state == TIPC_LISTEN)
			return -EPIPE;
		if (sk->sk_state != TIPC_OPEN)
			return -EISCONN;
		if (tsk->published)
			return -EOPNOTSUPP;
		if (dest->addrtype == TIPC_ADDR_NAME) {
			tsk->conn_type = dest->addr.name.name.type;
			tsk->conn_instance = dest->addr.name.name.instance;
		}
		msg_set_syn(hdr, 1);
	}

	seq = &dest->addr.nameseq;
	if (dest->addrtype == TIPC_ADDR_MCAST)
		return tipc_sendmcast(sock, seq, m, dlen, timeout);

	if (dest->addrtype == TIPC_ADDR_NAME) {
		type = dest->addr.name.name.type;
		inst = dest->addr.name.name.instance;
		dnode = dest->addr.name.domain;
		msg_set_type(hdr, TIPC_NAMED_MSG);
		msg_set_hdr_sz(hdr, NAMED_H_SIZE);
		msg_set_nametype(hdr, type);
		msg_set_nameinst(hdr, inst);
		msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
		dport = tipc_nametbl_translate(net, type, inst, &dnode);
		msg_set_destnode(hdr, dnode);
		msg_set_destport(hdr, dport);
		if (unlikely(!dport && !dnode))
			return -EHOSTUNREACH;
	} else if (dest->addrtype == TIPC_ADDR_ID) {
		dnode = dest->addr.id.node;
		msg_set_type(hdr, TIPC_DIRECT_MSG);
		msg_set_lookup_scope(hdr, 0);
		msg_set_destnode(hdr, dnode);
		msg_set_destport(hdr, dest->addr.id.ref);
		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
	} else {
		return -EINVAL;
	}

	/* Block or return if destination link is congested */
	rc = tipc_wait_for_cond(sock, &timeout,
				!tipc_dest_find(clinks, dnode, 0));
	if (unlikely(rc))
		return rc;

	skb_queue_head_init(&pkts);
	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;
	if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue)))
		return -ENOMEM;

	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
	if (unlikely(rc == -ELINKCONG)) {
		tipc_dest_push(clinks, dnode, 0);
		tsk->cong_link_cnt++;
		rc = 0;
	}

	if (unlikely(syn && !rc))
		tipc_set_sk_state(sk, TIPC_CONNECTING);

	return rc ? rc : dlen;
}

/**
 * tipc_sendstream - send stream-oriented data
 * @sock: socket structure
 * @m: data to send
 * @dsz: total length of data to be transmitted
 *
 * Used for SOCK_STREAM data.
 *
 * Returns the number of bytes sent on success (or partial success),
 * or errno if no data sent
 */
static int tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	int ret;

	lock_sock(sk);
	ret = __tipc_sendstream(sock, m, dsz);
	release_sock(sk);

	return ret;
}

static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = &tsk->phdr;
	struct net *net = sock_net(sk);
	struct sk_buff_head pkts;
	u32 dnode = tsk_peer_node(tsk);
	int send, sent = 0;
	int rc = 0;

	skb_queue_head_init(&pkts);

	if (unlikely(dlen > INT_MAX))
		return -EMSGSIZE;

	/* Handle implicit connection setup */
	if (unlikely(dest)) {
		rc = __tipc_sendmsg(sock, m, dlen);
		if (dlen && dlen == rc) {
			tsk->peer_caps = tipc_node_get_capabilities(net, dnode);
			tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr));
		}
		return rc;
	}

	do {
		rc = tipc_wait_for_cond(sock, &timeout,
					(!tsk->cong_link_cnt &&
					 !tsk_conn_cong(tsk) &&
					 tipc_sk_connected(sk)));
		if (unlikely(rc))
			break;

		send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE);
		rc = tipc_msg_build(hdr, m, sent, send, tsk->max_pkt, &pkts);
		if (unlikely(rc != send))
			break;

		rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
		if (unlikely(rc == -ELINKCONG)) {
			tsk->cong_link_cnt = 1;
			rc = 0;
		}
		if (likely(!rc)) {
			tsk->snt_unacked += tsk_inc(tsk, send + MIN_H_SIZE);
			sent += send;
		}
	} while (sent < dlen && !rc);

	return sent ? sent : rc;
}

/**
 * tipc_send_packet - send a connection-oriented message
 * @sock: socket structure
 * @m: message to send
 * @dsz: length of data to be transmitted
 *
 * Used for SOCK_SEQPACKET messages.
 *
 * Returns the number of bytes sent on success, or errno otherwise
 */
static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz)
{
	if (dsz > TIPC_MAX_USER_MSG_SIZE)
		return -EMSGSIZE;

	return tipc_sendstream(sock, m, dsz);
}

/* tipc_sk_finish_conn - complete the setup of a connection
 */
static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
				u32 peer_node)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct tipc_msg *msg = &tsk->phdr;

	msg_set_syn(msg, 0);
	msg_set_destnode(msg, peer_node);
	msg_set_destport(msg, peer_port);
	msg_set_type(msg, TIPC_CONN_MSG);
	msg_set_lookup_scope(msg, 0);
	msg_set_hdr_sz(msg, SHORT_H_SIZE);

	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
	tipc_set_sk_state(sk, TIPC_ESTABLISHED);
	tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
	tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
	tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
	__skb_queue_purge(&sk->sk_write_queue);
	if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
		return;

	/* Fall back to message based flow control */
	tsk->rcv_win = FLOWCTL_MSG_WIN;
	tsk->snd_win = FLOWCTL_MSG_WIN;
}

/**
 * tipc_sk_set_orig_addr - capture sender's address for received message
 * @m: descriptor for message info
 * @hdr: received message header
 *
 * Note: Address is not captured if not requested by receiver.
 */
static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
{
	DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name);
	struct tipc_msg *hdr = buf_msg(skb);

	if (!srcaddr)
		return;

	srcaddr->sock.family = AF_TIPC;
	srcaddr->sock.addrtype = TIPC_ADDR_ID;
	srcaddr->sock.scope = 0;
	srcaddr->sock.addr.id.ref = msg_origport(hdr);
	srcaddr->sock.addr.id.node = msg_orignode(hdr);
	srcaddr->sock.addr.name.domain = 0;
	m->msg_namelen = sizeof(struct sockaddr_tipc);

	if (!msg_in_group(hdr))
		return;

	/* Group message users may also want to know sending member's id */
	srcaddr->member.family = AF_TIPC;
	srcaddr->member.addrtype = TIPC_ADDR_NAME;
	srcaddr->member.scope = 0;
	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
	srcaddr->member.addr.name.domain = 0;
	m->msg_namelen = sizeof(*srcaddr);
}

/**
 * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
 * @m: descriptor for message info
 * @skb: received message buffer
 * @tsk: TIPC port associated with message
 *
 * Note: Ancillary data is not captured if not requested by receiver.
 *
 * Returns 0 if successful, otherwise errno
 */
static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
				 struct tipc_sock *tsk)
{
	struct tipc_msg *msg;
	u32 anc_data[3];
	u32 err;
	u32 dest_type;
	int has_name;
	int res;

	if (likely(m->msg_controllen == 0))
		return 0;
	msg = buf_msg(skb);

	/* Optionally capture errored message object(s) */
	err = msg ? msg_errcode(msg) : 0;
	if (unlikely(err)) {
		anc_data[0] = err;
		anc_data[1] = msg_data_sz(msg);
		res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data);
		if (res)
			return res;
		if (anc_data[1]) {
			if (skb_linearize(skb))
				return -ENOMEM;
			msg = buf_msg(skb);
			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
				       msg_data(msg));
			if (res)
				return res;
		}
	}

	/* Optionally capture message destination object */
	dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG;
	switch (dest_type) {
	case TIPC_NAMED_MSG:
		has_name = 1;
		anc_data[0] = msg_nametype(msg);
		anc_data[1] = msg_namelower(msg);
		anc_data[2] = msg_namelower(msg);
		break;
	case TIPC_MCAST_MSG:
		has_name = 1;
		anc_data[0] = msg_nametype(msg);
		anc_data[1] = msg_namelower(msg);
		anc_data[2] = msg_nameupper(msg);
		break;
	case TIPC_CONN_MSG:
		has_name = (tsk->conn_type != 0);
		anc_data[0] = tsk->conn_type;
		anc_data[1] = tsk->conn_instance;
		anc_data[2] = tsk->conn_instance;
		break;
	default:
		has_name = 0;
	}
	if (has_name) {
		res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data);
		if (res)
			return res;
	}

	return 0;
}

static void tipc_sk_send_ack(struct tipc_sock *tsk)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct sk_buff *skb = NULL;
	struct tipc_msg *msg;
	u32 peer_port = tsk_peer_port(tsk);
	u32 dnode = tsk_peer_node(tsk);

	if (!tipc_sk_connected(sk))
		return;
	skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
			      dnode, tsk_own_node(tsk), peer_port,
			      tsk->portid, TIPC_OK);
	if (!skb)
		return;
	msg = buf_msg(skb);
	msg_set_conn_ack(msg, tsk->rcv_unacked);
	tsk->rcv_unacked = 0;

	/* Adjust to and advertize the correct window limit */
	if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL) {
		tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf);
		msg_set_adv_win(msg, tsk->rcv_win);
	}
	tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg));
}

static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
{
	struct sock *sk = sock->sk;
	DEFINE_WAIT(wait);
	long timeo = *timeop;
	int err = sock_error(sk);

	if (err)
		return err;

	for (;;) {
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
			if (sk->sk_shutdown & RCV_SHUTDOWN) {
				err = -ENOTCONN;
				break;
			}
			release_sock(sk);
			timeo = schedule_timeout(timeo);
			lock_sock(sk);
		}
		err = 0;
		if (!skb_queue_empty(&sk->sk_receive_queue))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;

		err = sock_error(sk);
		if (err)
			break;
	}
	finish_wait(sk_sleep(sk), &wait);
	*timeop = timeo;
	return err;
}

/**
 * tipc_recvmsg - receive packet-oriented message
 * @m: descriptor for message info
 * @buflen: length of user buffer area
 * @flags: receive flags
 *
 * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
 * If the complete message doesn't fit in user area, truncate it.
 *
 * Returns size of returned message data, errno otherwise
 */
static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
			size_t buflen,	int flags)
{
	struct sock *sk = sock->sk;
	bool connected = !tipc_sk_type_connectionless(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	int rc, err, hlen, dlen, copy;
	struct sk_buff_head xmitq;
	struct tipc_msg *hdr;
	struct sk_buff *skb;
	bool grp_evt;
	long timeout;

	/* Catch invalid receive requests */
	if (unlikely(!buflen))
		return -EINVAL;

	lock_sock(sk);
	if (unlikely(connected && sk->sk_state == TIPC_OPEN)) {
		rc = -ENOTCONN;
		goto exit;
	}
	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	/* Step rcv queue to first msg with data or error; wait if necessary */
	do {
		rc = tipc_wait_for_rcvmsg(sock, &timeout);
		if (unlikely(rc))
			goto exit;
		skb = skb_peek(&sk->sk_receive_queue);
		hdr = buf_msg(skb);
		dlen = msg_data_sz(hdr);
		hlen = msg_hdr_sz(hdr);
		err = msg_errcode(hdr);
		grp_evt = msg_is_grp_evt(hdr);
		if (likely(dlen || err))
			break;
		tsk_advance_rx_queue(sk);
	} while (1);

	/* Collect msg meta data, including error code and rejected data */
	tipc_sk_set_orig_addr(m, skb);
	rc = tipc_sk_anc_data_recv(m, skb, tsk);
	if (unlikely(rc))
		goto exit;
	hdr = buf_msg(skb);

	/* Capture data if non-error msg, otherwise just set return value */
	if (likely(!err)) {
		copy = min_t(int, dlen, buflen);
		if (unlikely(copy != dlen))
			m->msg_flags |= MSG_TRUNC;
		rc = skb_copy_datagram_msg(skb, hlen, m, copy);
	} else {
		copy = 0;
		rc = 0;
		if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
			rc = -ECONNRESET;
	}
	if (unlikely(rc))
		goto exit;

	/* Mark message as group event if applicable */
	if (unlikely(grp_evt)) {
		if (msg_grp_evt(hdr) == TIPC_WITHDRAWN)
			m->msg_flags |= MSG_EOR;
		m->msg_flags |= MSG_OOB;
		copy = 0;
	}

	/* Caption of data or error code/rejected data was successful */
	if (unlikely(flags & MSG_PEEK))
		goto exit;

	/* Send group flow control advertisement when applicable */
	if (tsk->group && msg_in_group(hdr) && !grp_evt) {
		skb_queue_head_init(&xmitq);
		tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen),
					  msg_orignode(hdr), msg_origport(hdr),
					  &xmitq);
		tipc_node_distr_xmit(sock_net(sk), &xmitq);
	}

	tsk_advance_rx_queue(sk);

	if (likely(!connected))
		goto exit;

	/* Send connection flow control advertisement when applicable */
	tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
	if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
		tipc_sk_send_ack(tsk);
exit:
	release_sock(sk);
	return rc ? rc : copy;
}

/**
 * tipc_recvstream - receive stream-oriented data
 * @m: descriptor for message info
 * @buflen: total size of user buffer area
 * @flags: receive flags
 *
 * Used for SOCK_STREAM messages only.  If not enough data is available
 * will optionally wait for more; never truncates data.
 *
 * Returns size of returned message data, errno otherwise
 */
static int tipc_recvstream(struct socket *sock, struct msghdr *m,
			   size_t buflen, int flags)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct sk_buff *skb;
	struct tipc_msg *hdr;
	struct tipc_skb_cb *skb_cb;
	bool peek = flags & MSG_PEEK;
	int offset, required, copy, copied = 0;
	int hlen, dlen, err, rc;
	long timeout;

	/* Catch invalid receive attempts */
	if (unlikely(!buflen))
		return -EINVAL;

	lock_sock(sk);

	if (unlikely(sk->sk_state == TIPC_OPEN)) {
		rc = -ENOTCONN;
		goto exit;
	}
	required = sock_rcvlowat(sk, flags & MSG_WAITALL, buflen);
	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	do {
		/* Look at first msg in receive queue; wait if necessary */
		rc = tipc_wait_for_rcvmsg(sock, &timeout);
		if (unlikely(rc))
			break;
		skb = skb_peek(&sk->sk_receive_queue);
		skb_cb = TIPC_SKB_CB(skb);
		hdr = buf_msg(skb);
		dlen = msg_data_sz(hdr);
		hlen = msg_hdr_sz(hdr);
		err = msg_errcode(hdr);

		/* Discard any empty non-errored (SYN-) message */
		if (unlikely(!dlen && !err)) {
			tsk_advance_rx_queue(sk);
			continue;
		}

		/* Collect msg meta data, incl. error code and rejected data */
		if (!copied) {
			tipc_sk_set_orig_addr(m, skb);
			rc = tipc_sk_anc_data_recv(m, skb, tsk);
			if (rc)
				break;
			hdr = buf_msg(skb);
		}

		/* Copy data if msg ok, otherwise return error/partial data */
		if (likely(!err)) {
			offset = skb_cb->bytes_read;
			copy = min_t(int, dlen - offset, buflen - copied);
			rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
			if (unlikely(rc))
				break;
			copied += copy;
			offset += copy;
			if (unlikely(offset < dlen)) {
				if (!peek)
					skb_cb->bytes_read = offset;
				break;
			}
		} else {
			rc = 0;
			if ((err != TIPC_CONN_SHUTDOWN) && !m->msg_control)
				rc = -ECONNRESET;
			if (copied || rc)
				break;
		}

		if (unlikely(peek))
			break;

		tsk_advance_rx_queue(sk);

		/* Send connection flow control advertisement when applicable */
		tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
		if (unlikely(tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE))
			tipc_sk_send_ack(tsk);

		/* Exit if all requested data or FIN/error received */
		if (copied == buflen || err)
			break;

	} while (!skb_queue_empty(&sk->sk_receive_queue) || copied < required);
exit:
	release_sock(sk);
	return copied ? copied : rc;
}

/**
 * tipc_write_space - wake up thread if port congestion is released
 * @sk: socket
 */
static void tipc_write_space(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, EPOLLOUT |
						EPOLLWRNORM | EPOLLWRBAND);
	rcu_read_unlock();
}

/**
 * tipc_data_ready - wake up threads to indicate messages have been received
 * @sk: socket
 * @len: the length of messages
 */
static void tipc_data_ready(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, EPOLLIN |
						EPOLLRDNORM | EPOLLRDBAND);
	rcu_read_unlock();
}

static void tipc_sock_destruct(struct sock *sk)
{
	__skb_queue_purge(&sk->sk_receive_queue);
}

static void tipc_sk_proto_rcv(struct sock *sk,
			      struct sk_buff_head *inputq,
			      struct sk_buff_head *xmitq)
{
	struct sk_buff *skb = __skb_dequeue(inputq);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = buf_msg(skb);
	struct tipc_group *grp = tsk->group;
	bool wakeup = false;

	switch (msg_user(hdr)) {
	case CONN_MANAGER:
		tipc_sk_conn_proto_rcv(tsk, skb, inputq, xmitq);
		return;
	case SOCK_WAKEUP:
		tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
		tsk->cong_link_cnt--;
		wakeup = true;
		break;
	case GROUP_PROTOCOL:
		tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq);
		break;
	case TOP_SRV:
		tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf,
				      hdr, inputq, xmitq);
		break;
	default:
		break;
	}

	if (wakeup)
		sk->sk_write_space(sk);

	kfree_skb(skb);
}

/**
 * tipc_sk_filter_connect - check incoming message for a connection-based socket
 * @tsk: TIPC socket
 * @skb: pointer to message buffer.
 * Returns true if message should be added to receive queue, false otherwise
 */
static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct tipc_msg *hdr = buf_msg(skb);
	bool con_msg = msg_connected(hdr);
	u32 pport = tsk_peer_port(tsk);
	u32 pnode = tsk_peer_node(tsk);
	u32 oport = msg_origport(hdr);
	u32 onode = msg_orignode(hdr);
	int err = msg_errcode(hdr);
	unsigned long delay;

	if (unlikely(msg_mcast(hdr)))
		return false;

	switch (sk->sk_state) {
	case TIPC_CONNECTING:
		/* Setup ACK */
		if (likely(con_msg)) {
			if (err)
				break;
			tipc_sk_finish_conn(tsk, oport, onode);
			msg_set_importance(&tsk->phdr, msg_importance(hdr));
			/* ACK+ message with data is added to receive queue */
			if (msg_data_sz(hdr))
				return true;
			/* Empty ACK-, - wake up sleeping connect() and drop */
			sk->sk_data_ready(sk);
			msg_set_dest_droppable(hdr, 1);
			return false;
		}
		/* Ignore connectionless message if not from listening socket */
		if (oport != pport || onode != pnode)
			return false;

		/* Rejected SYN */
		if (err != TIPC_ERR_OVERLOAD)
			break;

		/* Prepare for new setup attempt if we have a SYN clone */
		if (skb_queue_empty(&sk->sk_write_queue))
			break;
		get_random_bytes(&delay, 2);
		delay %= (tsk->conn_timeout / 4);
		delay = msecs_to_jiffies(delay + 100);
		sk_reset_timer(sk, &sk->sk_timer, jiffies + delay);
		return false;
	case TIPC_OPEN:
	case TIPC_DISCONNECTING:
		return false;
	case TIPC_LISTEN:
		/* Accept only SYN message */
		if (!msg_is_syn(hdr) &&
		    tipc_node_get_capabilities(net, onode) & TIPC_SYN_BIT)
			return false;
		if (!con_msg && !err)
			return true;
		return false;
	case TIPC_ESTABLISHED:
		/* Accept only connection-based messages sent by peer */
		if (likely(con_msg && !err && pport == oport && pnode == onode))
			return true;
		if (!tsk_peer_msg(tsk, hdr))
			return false;
		if (!err)
			return true;
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
		tipc_node_remove_conn(net, pnode, tsk->portid);
		sk->sk_state_change(sk);
		return true;
	default:
		pr_err("Unknown sk_state %u\n", sk->sk_state);
	}
	/* Abort connection setup attempt */
	tipc_set_sk_state(sk, TIPC_DISCONNECTING);
	sk->sk_err = ECONNREFUSED;
	sk->sk_state_change(sk);
	return true;
}

/**
 * rcvbuf_limit - get proper overload limit of socket receive queue
 * @sk: socket
 * @skb: message
 *
 * For connection oriented messages, irrespective of importance,
 * default queue limit is 2 MB.
 *
 * For connectionless messages, queue limits are based on message
 * importance as follows:
 *
 * TIPC_LOW_IMPORTANCE       (2 MB)
 * TIPC_MEDIUM_IMPORTANCE    (4 MB)
 * TIPC_HIGH_IMPORTANCE      (8 MB)
 * TIPC_CRITICAL_IMPORTANCE  (16 MB)
 *
 * Returns overload limit according to corresponding message importance
 */
static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
{
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = buf_msg(skb);

	if (unlikely(msg_in_group(hdr)))
		return sk->sk_rcvbuf;

	if (unlikely(!msg_connected(hdr)))
		return sk->sk_rcvbuf << msg_importance(hdr);

	if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
		return sk->sk_rcvbuf;

	return FLOWCTL_MSG_LIM;
}

/**
 * tipc_sk_filter_rcv - validate incoming message
 * @sk: socket
 * @skb: pointer to message.
 *
 * Enqueues message on receive queue if acceptable; optionally handles
 * disconnect indication for a connected socket.
 *
 * Called with socket lock already taken
 *
 */
static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
			       struct sk_buff_head *xmitq)
{
	bool sk_conn = !tipc_sk_type_connectionless(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_msg *hdr = buf_msg(skb);
	struct net *net = sock_net(sk);
	struct sk_buff_head inputq;
	int limit, err = TIPC_OK;

	TIPC_SKB_CB(skb)->bytes_read = 0;
	__skb_queue_head_init(&inputq);
	__skb_queue_tail(&inputq, skb);

	if (unlikely(!msg_isdata(hdr)))
		tipc_sk_proto_rcv(sk, &inputq, xmitq);

	if (unlikely(grp))
		tipc_group_filter_msg(grp, &inputq, xmitq);

	/* Validate and add to receive buffer if there is space */
	while ((skb = __skb_dequeue(&inputq))) {
		hdr = buf_msg(skb);
		limit = rcvbuf_limit(sk, skb);
		if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
		    (!sk_conn && msg_connected(hdr)) ||
		    (!grp && msg_in_group(hdr)))
			err = TIPC_ERR_NO_PORT;
		else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) {
			atomic_inc(&sk->sk_drops);
			err = TIPC_ERR_OVERLOAD;
		}

		if (unlikely(err)) {
			tipc_skb_reject(net, err, skb, xmitq);
			err = TIPC_OK;
			continue;
		}
		__skb_queue_tail(&sk->sk_receive_queue, skb);
		skb_set_owner_r(skb, sk);
		sk->sk_data_ready(sk);
	}
}

/**
 * tipc_sk_backlog_rcv - handle incoming message from backlog queue
 * @sk: socket
 * @skb: message
 *
 * Caller must hold socket lock
 */
static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	unsigned int before = sk_rmem_alloc_get(sk);
	struct sk_buff_head xmitq;
	unsigned int added;

	__skb_queue_head_init(&xmitq);

	tipc_sk_filter_rcv(sk, skb, &xmitq);
	added = sk_rmem_alloc_get(sk) - before;
	atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt);

	/* Send pending response/rejected messages, if any */
	tipc_node_distr_xmit(sock_net(sk), &xmitq);
	return 0;
}

/**
 * tipc_sk_enqueue - extract all buffers with destination 'dport' from
 *                   inputq and try adding them to socket or backlog queue
 * @inputq: list of incoming buffers with potentially different destinations
 * @sk: socket where the buffers should be enqueued
 * @dport: port number for the socket
 *
 * Caller must hold socket lock
 */
static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
			    u32 dport, struct sk_buff_head *xmitq)
{
	unsigned long time_limit = jiffies + 2;
	struct sk_buff *skb;
	unsigned int lim;
	atomic_t *dcnt;
	u32 onode;

	while (skb_queue_len(inputq)) {
		if (unlikely(time_after_eq(jiffies, time_limit)))
			return;

		skb = tipc_skb_dequeue(inputq, dport);
		if (unlikely(!skb))
			return;

		/* Add message directly to receive queue if possible */
		if (!sock_owned_by_user(sk)) {
			tipc_sk_filter_rcv(sk, skb, xmitq);
			continue;
		}

		/* Try backlog, compensating for double-counted bytes */
		dcnt = &tipc_sk(sk)->dupl_rcvcnt;
		if (!sk->sk_backlog.len)
			atomic_set(dcnt, 0);
		lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
		if (likely(!sk_add_backlog(sk, skb, lim)))
			continue;

		/* Overload => reject message back to sender */
		onode = tipc_own_addr(sock_net(sk));
		atomic_inc(&sk->sk_drops);
		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
			__skb_queue_tail(xmitq, skb);
		break;
	}
}

/**
 * tipc_sk_rcv - handle a chain of incoming buffers
 * @inputq: buffer list containing the buffers
 * Consumes all buffers in list until inputq is empty
 * Note: may be called in multiple threads referring to the same queue
 */
void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
{
	struct sk_buff_head xmitq;
	u32 dnode, dport = 0;
	int err;
	struct tipc_sock *tsk;
	struct sock *sk;
	struct sk_buff *skb;

	__skb_queue_head_init(&xmitq);
	while (skb_queue_len(inputq)) {
		dport = tipc_skb_peek_port(inputq, dport);
		tsk = tipc_sk_lookup(net, dport);

		if (likely(tsk)) {
			sk = &tsk->sk;
			if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
				tipc_sk_enqueue(inputq, sk, dport, &xmitq);
				spin_unlock_bh(&sk->sk_lock.slock);
			}
			/* Send pending response/rejected messages, if any */
			tipc_node_distr_xmit(sock_net(sk), &xmitq);
			sock_put(sk);
			continue;
		}
		/* No destination socket => dequeue skb if still there */
		skb = tipc_skb_dequeue(inputq, dport);
		if (!skb)
			return;

		/* Try secondary lookup if unresolved named message */
		err = TIPC_ERR_NO_PORT;
		if (tipc_msg_lookup_dest(net, skb, &err))
			goto xmit;

		/* Prepare for message rejection */
		if (!tipc_msg_reverse(tipc_own_addr(net), &skb, err))
			continue;
xmit:
		dnode = msg_destnode(buf_msg(skb));
		tipc_node_xmit_skb(net, skb, dnode, dport);
	}
}

static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
{
	DEFINE_WAIT_FUNC(wait, woken_wake_function);
	struct sock *sk = sock->sk;
	int done;

	do {
		int err = sock_error(sk);
		if (err)
			return err;
		if (!*timeo_p)
			return -ETIMEDOUT;
		if (signal_pending(current))
			return sock_intr_errno(*timeo_p);

		add_wait_queue(sk_sleep(sk), &wait);
		done = sk_wait_event(sk, timeo_p,
				     sk->sk_state != TIPC_CONNECTING, &wait);
		remove_wait_queue(sk_sleep(sk), &wait);
	} while (!done);
	return 0;
}

/**
 * tipc_connect - establish a connection to another TIPC port
 * @sock: socket structure
 * @dest: socket address for destination port
 * @destlen: size of socket address data structure
 * @flags: file-related flags associated with socket
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_connect(struct socket *sock, struct sockaddr *dest,
			int destlen, int flags)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
	struct msghdr m = {NULL,};
	long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout;
	int previous;
	int res = 0;

	if (destlen != sizeof(struct sockaddr_tipc))
		return -EINVAL;

	lock_sock(sk);

	if (tsk->group) {
		res = -EINVAL;
		goto exit;
	}

	if (dst->family == AF_UNSPEC) {
		memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
		if (!tipc_sk_type_connectionless(sk))
			res = -EINVAL;
		goto exit;
	} else if (dst->family != AF_TIPC) {
		res = -EINVAL;
	}
	if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
		res = -EINVAL;
	if (res)
		goto exit;

	/* DGRAM/RDM connect(), just save the destaddr */
	if (tipc_sk_type_connectionless(sk)) {
		memcpy(&tsk->peer, dest, destlen);
		goto exit;
	}

	previous = sk->sk_state;

	switch (sk->sk_state) {
	case TIPC_OPEN:
		/* Send a 'SYN-' to destination */
		m.msg_name = dest;
		m.msg_namelen = destlen;

		/* If connect is in non-blocking case, set MSG_DONTWAIT to
		 * indicate send_msg() is never blocked.
		 */
		if (!timeout)
			m.msg_flags = MSG_DONTWAIT;

		res = __tipc_sendmsg(sock, &m, 0);
		if ((res < 0) && (res != -EWOULDBLOCK))
			goto exit;

		/* Just entered TIPC_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		res = -EINPROGRESS;
		/* fall thru' */
	case TIPC_CONNECTING:
		if (!timeout) {
			if (previous == TIPC_CONNECTING)
				res = -EALREADY;
			goto exit;
		}
		timeout = msecs_to_jiffies(timeout);
		/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
		res = tipc_wait_for_connect(sock, &timeout);
		break;
	case TIPC_ESTABLISHED:
		res = -EISCONN;
		break;
	default:
		res = -EINVAL;
	}

exit:
	release_sock(sk);
	return res;
}

/**
 * tipc_listen - allow socket to listen for incoming connections
 * @sock: socket structure
 * @len: (unused)
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_listen(struct socket *sock, int len)
{
	struct sock *sk = sock->sk;
	int res;

	lock_sock(sk);
	res = tipc_set_sk_state(sk, TIPC_LISTEN);
	release_sock(sk);

	return res;
}

static int tipc_wait_for_accept(struct socket *sock, long timeo)
{
	struct sock *sk = sock->sk;
	DEFINE_WAIT(wait);
	int err;

	/* True wake-one mechanism for incoming connections: only
	 * one process gets woken up, not the 'whole herd'.
	 * Since we do not 'race & poll' for established sockets
	 * anymore, the common case will execute the loop only once.
	*/
	for (;;) {
		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
					  TASK_INTERRUPTIBLE);
		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
			release_sock(sk);
			timeo = schedule_timeout(timeo);
			lock_sock(sk);
		}
		err = 0;
		if (!skb_queue_empty(&sk->sk_receive_queue))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
	}
	finish_wait(sk_sleep(sk), &wait);
	return err;
}

/**
 * tipc_accept - wait for connection request
 * @sock: listening socket
 * @newsock: new socket that is to be connected
 * @flags: file-related flags associated with socket
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
		       bool kern)
{
	struct sock *new_sk, *sk = sock->sk;
	struct sk_buff *buf;
	struct tipc_sock *new_tsock;
	struct tipc_msg *msg;
	long timeo;
	int res;

	lock_sock(sk);

	if (sk->sk_state != TIPC_LISTEN) {
		res = -EINVAL;
		goto exit;
	}
	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
	res = tipc_wait_for_accept(sock, timeo);
	if (res)
		goto exit;

	buf = skb_peek(&sk->sk_receive_queue);

	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
	if (res)
		goto exit;
	security_sk_clone(sock->sk, new_sock->sk);

	new_sk = new_sock->sk;
	new_tsock = tipc_sk(new_sk);
	msg = buf_msg(buf);

	/* we lock on new_sk; but lockdep sees the lock on sk */
	lock_sock_nested(new_sk, SINGLE_DEPTH_NESTING);

	/*
	 * Reject any stray messages received by new socket
	 * before the socket lock was taken (very, very unlikely)
	 */
	tsk_rej_rx_queue(new_sk);

	/* Connect new socket to it's peer */
	tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));

	tsk_set_importance(new_tsock, msg_importance(msg));
	if (msg_named(msg)) {
		new_tsock->conn_type = msg_nametype(msg);
		new_tsock->conn_instance = msg_nameinst(msg);
	}

	/*
	 * Respond to 'SYN-' by discarding it & returning 'ACK'-.
	 * Respond to 'SYN+' by queuing it on new socket.
	 */
	if (!msg_data_sz(msg)) {
		struct msghdr m = {NULL,};

		tsk_advance_rx_queue(sk);
		__tipc_sendstream(new_sock, &m, 0);
	} else {
		__skb_dequeue(&sk->sk_receive_queue);
		__skb_queue_head(&new_sk->sk_receive_queue, buf);
		skb_set_owner_r(buf, new_sk);
	}
	release_sock(new_sk);
exit:
	release_sock(sk);
	return res;
}

/**
 * tipc_shutdown - shutdown socket connection
 * @sock: socket structure
 * @how: direction to close (must be SHUT_RDWR)
 *
 * Terminates connection (if necessary), then purges socket's receive queue.
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	int res;

	if (how != SHUT_RDWR)
		return -EINVAL;

	lock_sock(sk);

	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
	sk->sk_shutdown = SEND_SHUTDOWN;

	if (sk->sk_state == TIPC_DISCONNECTING) {
		/* Discard any unreceived messages */
		__skb_queue_purge(&sk->sk_receive_queue);

		/* Wake up anyone sleeping in poll */
		sk->sk_state_change(sk);
		res = 0;
	} else {
		res = -ENOTCONN;
	}

	release_sock(sk);
	return res;
}

static void tipc_sk_check_probing_state(struct sock *sk,
					struct sk_buff_head *list)
{
	struct tipc_sock *tsk = tipc_sk(sk);
	u32 pnode = tsk_peer_node(tsk);
	u32 pport = tsk_peer_port(tsk);
	u32 self = tsk_own_node(tsk);
	u32 oport = tsk->portid;
	struct sk_buff *skb;

	if (tsk->probe_unacked) {
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
		sk->sk_err = ECONNABORTED;
		tipc_node_remove_conn(sock_net(sk), pnode, pport);
		sk->sk_state_change(sk);
		return;
	}
	/* Prepare new probe */
	skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0,
			      pnode, self, pport, oport, TIPC_OK);
	if (skb)
		__skb_queue_tail(list, skb);
	tsk->probe_unacked = true;
	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
}

static void tipc_sk_retry_connect(struct sock *sk, struct sk_buff_head *list)
{
	struct tipc_sock *tsk = tipc_sk(sk);

	/* Try again later if dest link is congested */
	if (tsk->cong_link_cnt) {
		sk_reset_timer(sk, &sk->sk_timer, msecs_to_jiffies(100));
		return;
	}
	/* Prepare SYN for retransmit */
	tipc_msg_skb_clone(&sk->sk_write_queue, list);
}

static void tipc_sk_timeout(struct timer_list *t)
{
	struct sock *sk = from_timer(sk, t, sk_timer);
	struct tipc_sock *tsk = tipc_sk(sk);
	u32 pnode = tsk_peer_node(tsk);
	struct sk_buff_head list;
	int rc = 0;

	skb_queue_head_init(&list);
	bh_lock_sock(sk);

	/* Try again later if socket is busy */
	if (sock_owned_by_user(sk)) {
		sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20);
		bh_unlock_sock(sk);
		return;
	}

	if (sk->sk_state == TIPC_ESTABLISHED)
		tipc_sk_check_probing_state(sk, &list);
	else if (sk->sk_state == TIPC_CONNECTING)
		tipc_sk_retry_connect(sk, &list);

	bh_unlock_sock(sk);

	if (!skb_queue_empty(&list))
		rc = tipc_node_xmit(sock_net(sk), &list, pnode, tsk->portid);

	/* SYN messages may cause link congestion */
	if (rc == -ELINKCONG) {
		tipc_dest_push(&tsk->cong_links, pnode, 0);
		tsk->cong_link_cnt = 1;
	}
	sock_put(sk);
}

static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
			   struct tipc_name_seq const *seq)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct publication *publ;
	u32 key;

	if (scope != TIPC_NODE_SCOPE)
		scope = TIPC_CLUSTER_SCOPE;

	if (tipc_sk_connected(sk))
		return -EINVAL;
	key = tsk->portid + tsk->pub_count + 1;
	if (key == tsk->portid)
		return -EADDRINUSE;

	publ = tipc_nametbl_publish(net, seq->type, seq->lower, seq->upper,
				    scope, tsk->portid, key);
	if (unlikely(!publ))
		return -EINVAL;

	list_add(&publ->binding_sock, &tsk->publications);
	tsk->pub_count++;
	tsk->published = 1;
	return 0;
}

static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
			    struct tipc_name_seq const *seq)
{
	struct net *net = sock_net(&tsk->sk);
	struct publication *publ;
	struct publication *safe;
	int rc = -EINVAL;

	if (scope != TIPC_NODE_SCOPE)
		scope = TIPC_CLUSTER_SCOPE;

	list_for_each_entry_safe(publ, safe, &tsk->publications, binding_sock) {
		if (seq) {
			if (publ->scope != scope)
				continue;
			if (publ->type != seq->type)
				continue;
			if (publ->lower != seq->lower)
				continue;
			if (publ->upper != seq->upper)
				break;
			tipc_nametbl_withdraw(net, publ->type, publ->lower,
					      publ->upper, publ->key);
			rc = 0;
			break;
		}
		tipc_nametbl_withdraw(net, publ->type, publ->lower,
				      publ->upper, publ->key);
		rc = 0;
	}
	if (list_empty(&tsk->publications))
		tsk->published = 0;
	return rc;
}

/* tipc_sk_reinit: set non-zero address in all existing sockets
 *                 when we go from standalone to network mode.
 */
void tipc_sk_reinit(struct net *net)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	struct rhashtable_iter iter;
	struct tipc_sock *tsk;
	struct tipc_msg *msg;

	rhashtable_walk_enter(&tn->sk_rht, &iter);

	do {
		rhashtable_walk_start(&iter);

		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
			sock_hold(&tsk->sk);
			rhashtable_walk_stop(&iter);
			lock_sock(&tsk->sk);
			msg = &tsk->phdr;
			msg_set_prevnode(msg, tipc_own_addr(net));
			msg_set_orignode(msg, tipc_own_addr(net));
			release_sock(&tsk->sk);
			rhashtable_walk_start(&iter);
			sock_put(&tsk->sk);
		}

		rhashtable_walk_stop(&iter);
	} while (tsk == ERR_PTR(-EAGAIN));

	rhashtable_walk_exit(&iter);
}

static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	struct tipc_sock *tsk;

	rcu_read_lock();
	tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params);
	if (tsk)
		sock_hold(&tsk->sk);
	rcu_read_unlock();

	return tsk;
}

static int tipc_sk_insert(struct tipc_sock *tsk)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1;
	u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT;

	while (remaining--) {
		portid++;
		if ((portid < TIPC_MIN_PORT) || (portid > TIPC_MAX_PORT))
			portid = TIPC_MIN_PORT;
		tsk->portid = portid;
		sock_hold(&tsk->sk);
		if (!rhashtable_lookup_insert_fast(&tn->sk_rht, &tsk->node,
						   tsk_rht_params))
			return 0;
		sock_put(&tsk->sk);
	}

	return -1;
}

static void tipc_sk_remove(struct tipc_sock *tsk)
{
	struct sock *sk = &tsk->sk;
	struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);

	if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) {
		WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
}

static const struct rhashtable_params tsk_rht_params = {
	.nelem_hint = 192,
	.head_offset = offsetof(struct tipc_sock, node),
	.key_offset = offsetof(struct tipc_sock, portid),
	.key_len = sizeof(u32), /* portid */
	.max_size = 1048576,
	.min_size = 256,
	.automatic_shrinking = true,
};

int tipc_sk_rht_init(struct net *net)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);

	return rhashtable_init(&tn->sk_rht, &tsk_rht_params);
}

void tipc_sk_rht_destroy(struct net *net)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);

	/* Wait for socket readers to complete */
	synchronize_net();

	rhashtable_destroy(&tn->sk_rht);
}

static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
{
	struct net *net = sock_net(&tsk->sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_msg *hdr = &tsk->phdr;
	struct tipc_name_seq seq;
	int rc;

	if (mreq->type < TIPC_RESERVED_TYPES)
		return -EACCES;
	if (mreq->scope > TIPC_NODE_SCOPE)
		return -EINVAL;
	if (grp)
		return -EACCES;
	grp = tipc_group_create(net, tsk->portid, mreq, &tsk->group_is_open);
	if (!grp)
		return -ENOMEM;
	tsk->group = grp;
	msg_set_lookup_scope(hdr, mreq->scope);
	msg_set_nametype(hdr, mreq->type);
	msg_set_dest_droppable(hdr, true);
	seq.type = mreq->type;
	seq.lower = mreq->instance;
	seq.upper = seq.lower;
	tipc_nametbl_build_group(net, grp, mreq->type, mreq->scope);
	rc = tipc_sk_publish(tsk, mreq->scope, &seq);
	if (rc) {
		tipc_group_delete(net, grp);
		tsk->group = NULL;
		return rc;
	}
	/* Eliminate any risk that a broadcast overtakes sent JOINs */
	tsk->mc_method.rcast = true;
	tsk->mc_method.mandatory = true;
	tipc_group_join(net, grp, &tsk->sk.sk_rcvbuf);
	return rc;
}

static int tipc_sk_leave(struct tipc_sock *tsk)
{
	struct net *net = sock_net(&tsk->sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_name_seq seq;
	int scope;

	if (!grp)
		return -EINVAL;
	tipc_group_self(grp, &seq, &scope);
	tipc_group_delete(net, grp);
	tsk->group = NULL;
	tipc_sk_withdraw(tsk, scope, &seq);
	return 0;
}

/**
 * tipc_setsockopt - set socket option
 * @sock: socket structure
 * @lvl: option level
 * @opt: option identifier
 * @ov: pointer to new option value
 * @ol: length of option value
 *
 * For stream sockets only, accepts and ignores all IPPROTO_TCP options
 * (to ease compatibility).
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
			   char __user *ov, unsigned int ol)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group_req mreq;
	u32 value = 0;
	int res = 0;

	if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM))
		return 0;
	if (lvl != SOL_TIPC)
		return -ENOPROTOOPT;

	switch (opt) {
	case TIPC_IMPORTANCE:
	case TIPC_SRC_DROPPABLE:
	case TIPC_DEST_DROPPABLE:
	case TIPC_CONN_TIMEOUT:
		if (ol < sizeof(value))
			return -EINVAL;
		if (get_user(value, (u32 __user *)ov))
			return -EFAULT;
		break;
	case TIPC_GROUP_JOIN:
		if (ol < sizeof(mreq))
			return -EINVAL;
		if (copy_from_user(&mreq, ov, sizeof(mreq)))
			return -EFAULT;
		break;
	default:
		if (ov || ol)
			return -EINVAL;
	}

	lock_sock(sk);

	switch (opt) {
	case TIPC_IMPORTANCE:
		res = tsk_set_importance(tsk, value);
		break;
	case TIPC_SRC_DROPPABLE:
		if (sock->type != SOCK_STREAM)
			tsk_set_unreliable(tsk, value);
		else
			res = -ENOPROTOOPT;
		break;
	case TIPC_DEST_DROPPABLE:
		tsk_set_unreturnable(tsk, value);
		break;
	case TIPC_CONN_TIMEOUT:
		tipc_sk(sk)->conn_timeout = value;
		break;
	case TIPC_MCAST_BROADCAST:
		tsk->mc_method.rcast = false;
		tsk->mc_method.mandatory = true;
		break;
	case TIPC_MCAST_REPLICAST:
		tsk->mc_method.rcast = true;
		tsk->mc_method.mandatory = true;
		break;
	case TIPC_GROUP_JOIN:
		res = tipc_sk_join(tsk, &mreq);
		break;
	case TIPC_GROUP_LEAVE:
		res = tipc_sk_leave(tsk);
		break;
	default:
		res = -EINVAL;
	}

	release_sock(sk);

	return res;
}

/**
 * tipc_getsockopt - get socket option
 * @sock: socket structure
 * @lvl: option level
 * @opt: option identifier
 * @ov: receptacle for option value
 * @ol: receptacle for length of option value
 *
 * For stream sockets only, returns 0 length result for all IPPROTO_TCP options
 * (to ease compatibility).
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
			   char __user *ov, int __user *ol)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_name_seq seq;
	int len, scope;
	u32 value;
	int res;

	if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM))
		return put_user(0, ol);
	if (lvl != SOL_TIPC)
		return -ENOPROTOOPT;
	res = get_user(len, ol);
	if (res)
		return res;

	lock_sock(sk);

	switch (opt) {
	case TIPC_IMPORTANCE:
		value = tsk_importance(tsk);
		break;
	case TIPC_SRC_DROPPABLE:
		value = tsk_unreliable(tsk);
		break;
	case TIPC_DEST_DROPPABLE:
		value = tsk_unreturnable(tsk);
		break;
	case TIPC_CONN_TIMEOUT:
		value = tsk->conn_timeout;
		/* no need to set "res", since already 0 at this point */
		break;
	case TIPC_NODE_RECVQ_DEPTH:
		value = 0; /* was tipc_queue_size, now obsolete */
		break;
	case TIPC_SOCK_RECVQ_DEPTH:
		value = skb_queue_len(&sk->sk_receive_queue);
		break;
	case TIPC_GROUP_JOIN:
		seq.type = 0;
		if (tsk->group)
			tipc_group_self(tsk->group, &seq, &scope);
		value = seq.type;
		break;
	default:
		res = -EINVAL;
	}

	release_sock(sk);

	if (res)
		return res;	/* "get" failed */

	if (len < sizeof(value))
		return -EINVAL;

	if (copy_to_user(ov, &value, sizeof(value)))
		return -EFAULT;

	return put_user(sizeof(value), ol);
}

static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct net *net = sock_net(sock->sk);
	struct tipc_sioc_nodeid_req nr = {0};
	struct tipc_sioc_ln_req lnr;
	void __user *argp = (void __user *)arg;

	switch (cmd) {
	case SIOCGETLINKNAME:
		if (copy_from_user(&lnr, argp, sizeof(lnr)))
			return -EFAULT;
		if (!tipc_node_get_linkname(net,
					    lnr.bearer_id & 0xffff, lnr.peer,
					    lnr.linkname, TIPC_MAX_LINK_NAME)) {
			if (copy_to_user(argp, &lnr, sizeof(lnr)))
				return -EFAULT;
			return 0;
		}
		return -EADDRNOTAVAIL;
	case SIOCGETNODEID:
		if (copy_from_user(&nr, argp, sizeof(nr)))
			return -EFAULT;
		if (!tipc_node_get_id(net, nr.peer, nr.node_id))
			return -EADDRNOTAVAIL;
		if (copy_to_user(argp, &nr, sizeof(nr)))
			return -EFAULT;
		return 0;
	default:
		return -ENOIOCTLCMD;
	}
}

static int tipc_socketpair(struct socket *sock1, struct socket *sock2)
{
	struct tipc_sock *tsk2 = tipc_sk(sock2->sk);
	struct tipc_sock *tsk1 = tipc_sk(sock1->sk);
	u32 onode = tipc_own_addr(sock_net(sock1->sk));

	tsk1->peer.family = AF_TIPC;
	tsk1->peer.addrtype = TIPC_ADDR_ID;
	tsk1->peer.scope = TIPC_NODE_SCOPE;
	tsk1->peer.addr.id.ref = tsk2->portid;
	tsk1->peer.addr.id.node = onode;
	tsk2->peer.family = AF_TIPC;
	tsk2->peer.addrtype = TIPC_ADDR_ID;
	tsk2->peer.scope = TIPC_NODE_SCOPE;
	tsk2->peer.addr.id.ref = tsk1->portid;
	tsk2->peer.addr.id.node = onode;

	tipc_sk_finish_conn(tsk1, tsk2->portid, onode);
	tipc_sk_finish_conn(tsk2, tsk1->portid, onode);
	return 0;
}

/* Protocol switches for the various types of TIPC sockets */

static const struct proto_ops msg_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= tipc_release,
	.bind		= tipc_bind,
	.connect	= tipc_connect,
	.socketpair	= tipc_socketpair,
	.accept		= sock_no_accept,
	.getname	= tipc_getname,
	.poll		= tipc_poll,
	.ioctl		= tipc_ioctl,
	.listen		= sock_no_listen,
	.shutdown	= tipc_shutdown,
	.setsockopt	= tipc_setsockopt,
	.getsockopt	= tipc_getsockopt,
	.sendmsg	= tipc_sendmsg,
	.recvmsg	= tipc_recvmsg,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct proto_ops packet_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= tipc_release,
	.bind		= tipc_bind,
	.connect	= tipc_connect,
	.socketpair	= tipc_socketpair,
	.accept		= tipc_accept,
	.getname	= tipc_getname,
	.poll		= tipc_poll,
	.ioctl		= tipc_ioctl,
	.listen		= tipc_listen,
	.shutdown	= tipc_shutdown,
	.setsockopt	= tipc_setsockopt,
	.getsockopt	= tipc_getsockopt,
	.sendmsg	= tipc_send_packet,
	.recvmsg	= tipc_recvmsg,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct proto_ops stream_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= tipc_release,
	.bind		= tipc_bind,
	.connect	= tipc_connect,
	.socketpair	= tipc_socketpair,
	.accept		= tipc_accept,
	.getname	= tipc_getname,
	.poll		= tipc_poll,
	.ioctl		= tipc_ioctl,
	.listen		= tipc_listen,
	.shutdown	= tipc_shutdown,
	.setsockopt	= tipc_setsockopt,
	.getsockopt	= tipc_getsockopt,
	.sendmsg	= tipc_sendstream,
	.recvmsg	= tipc_recvstream,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct net_proto_family tipc_family_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.create		= tipc_sk_create
};

static struct proto tipc_proto = {
	.name		= "TIPC",
	.owner		= THIS_MODULE,
	.obj_size	= sizeof(struct tipc_sock),
	.sysctl_rmem	= sysctl_tipc_rmem
};

/**
 * tipc_socket_init - initialize TIPC socket interface
 *
 * Returns 0 on success, errno otherwise
 */
int tipc_socket_init(void)
{
	int res;

	res = proto_register(&tipc_proto, 1);
	if (res) {
		pr_err("Failed to register TIPC protocol type\n");
		goto out;
	}

	res = sock_register(&tipc_family_ops);
	if (res) {
		pr_err("Failed to register TIPC socket type\n");
		proto_unregister(&tipc_proto);
		goto out;
	}
 out:
	return res;
}

/**
 * tipc_socket_stop - stop TIPC socket interface
 */
void tipc_socket_stop(void)
{
	sock_unregister(tipc_family_ops.family);
	proto_unregister(&tipc_proto);
}

/* Caller should hold socket lock for the passed tipc socket. */
static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
{
	u32 peer_node;
	u32 peer_port;
	struct nlattr *nest;

	peer_node = tsk_peer_node(tsk);
	peer_port = tsk_peer_port(tsk);

	nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);

	if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node))
		goto msg_full;
	if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port))
		goto msg_full;

	if (tsk->conn_type != 0) {
		if (nla_put_flag(skb, TIPC_NLA_CON_FLAG))
			goto msg_full;
		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type))
			goto msg_full;
		if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance))
			goto msg_full;
	}
	nla_nest_end(skb, nest);

	return 0;

msg_full:
	nla_nest_cancel(skb, nest);

	return -EMSGSIZE;
}

static int __tipc_nl_add_sk_info(struct sk_buff *skb, struct tipc_sock
			  *tsk)
{
	struct net *net = sock_net(skb->sk);
	struct sock *sk = &tsk->sk;

	if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tipc_own_addr(net)))
		return -EMSGSIZE;

	if (tipc_sk_connected(sk)) {
		if (__tipc_nl_add_sk_con(skb, tsk))
			return -EMSGSIZE;
	} else if (!list_empty(&tsk->publications)) {
		if (nla_put_flag(skb, TIPC_NLA_SOCK_HAS_PUBL))
			return -EMSGSIZE;
	}
	return 0;
}

/* Caller should hold socket lock for the passed tipc socket. */
static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
			    struct tipc_sock *tsk)
{
	struct nlattr *attrs;
	void *hdr;

	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
			  &tipc_genl_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
	if (!hdr)
		goto msg_cancel;

	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
	if (!attrs)
		goto genlmsg_cancel;

	if (__tipc_nl_add_sk_info(skb, tsk))
		goto attr_msg_cancel;

	nla_nest_end(skb, attrs);
	genlmsg_end(skb, hdr);

	return 0;

attr_msg_cancel:
	nla_nest_cancel(skb, attrs);
genlmsg_cancel:
	genlmsg_cancel(skb, hdr);
msg_cancel:
	return -EMSGSIZE;
}

int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb,
		    int (*skb_handler)(struct sk_buff *skb,
				       struct netlink_callback *cb,
				       struct tipc_sock *tsk))
{
	struct rhashtable_iter *iter = (void *)cb->args[4];
	struct tipc_sock *tsk;
	int err;

	rhashtable_walk_start(iter);
	while ((tsk = rhashtable_walk_next(iter)) != NULL) {
		if (IS_ERR(tsk)) {
			err = PTR_ERR(tsk);
			if (err == -EAGAIN) {
				err = 0;
				continue;
			}
			break;
		}

		sock_hold(&tsk->sk);
		rhashtable_walk_stop(iter);
		lock_sock(&tsk->sk);
		err = skb_handler(skb, cb, tsk);
		if (err) {
			release_sock(&tsk->sk);
			sock_put(&tsk->sk);
			goto out;
		}
		release_sock(&tsk->sk);
		rhashtable_walk_start(iter);
		sock_put(&tsk->sk);
	}
	rhashtable_walk_stop(iter);
out:
	return skb->len;
}
EXPORT_SYMBOL(tipc_nl_sk_walk);

int tipc_dump_start(struct netlink_callback *cb)
{
	return __tipc_dump_start(cb, sock_net(cb->skb->sk));
}
EXPORT_SYMBOL(tipc_dump_start);

int __tipc_dump_start(struct netlink_callback *cb, struct net *net)
{
	/* tipc_nl_name_table_dump() uses cb->args[0...3]. */
	struct rhashtable_iter *iter = (void *)cb->args[4];
	struct tipc_net *tn = tipc_net(net);

	if (!iter) {
		iter = kmalloc(sizeof(*iter), GFP_KERNEL);
		if (!iter)
			return -ENOMEM;

		cb->args[4] = (long)iter;
	}

	rhashtable_walk_enter(&tn->sk_rht, iter);
	return 0;
}

int tipc_dump_done(struct netlink_callback *cb)
{
	struct rhashtable_iter *hti = (void *)cb->args[4];

	rhashtable_walk_exit(hti);
	kfree(hti);
	return 0;
}
EXPORT_SYMBOL(tipc_dump_done);

int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
			   struct tipc_sock *tsk, u32 sk_filter_state,
			   u64 (*tipc_diag_gen_cookie)(struct sock *sk))
{
	struct sock *sk = &tsk->sk;
	struct nlattr *attrs;
	struct nlattr *stat;

	/*filter response w.r.t sk_state*/
	if (!(sk_filter_state & (1 << sk->sk_state)))
		return 0;

	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
	if (!attrs)
		goto msg_cancel;

	if (__tipc_nl_add_sk_info(skb, tsk))
		goto attr_msg_cancel;

	if (nla_put_u32(skb, TIPC_NLA_SOCK_TYPE, (u32)sk->sk_type) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_TIPC_STATE, (u32)sk->sk_state) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_INO, sock_i_ino(sk)) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_UID,
			from_kuid_munged(sk_user_ns(NETLINK_CB(cb->skb).sk),
					 sock_i_uid(sk))) ||
	    nla_put_u64_64bit(skb, TIPC_NLA_SOCK_COOKIE,
			      tipc_diag_gen_cookie(sk),
			      TIPC_NLA_SOCK_PAD))
		goto attr_msg_cancel;

	stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT);
	if (!stat)
		goto attr_msg_cancel;

	if (nla_put_u32(skb, TIPC_NLA_SOCK_STAT_RCVQ,
			skb_queue_len(&sk->sk_receive_queue)) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_STAT_SENDQ,
			skb_queue_len(&sk->sk_write_queue)) ||
	    nla_put_u32(skb, TIPC_NLA_SOCK_STAT_DROP,
			atomic_read(&sk->sk_drops)))
		goto stat_msg_cancel;

	if (tsk->cong_link_cnt &&
	    nla_put_flag(skb, TIPC_NLA_SOCK_STAT_LINK_CONG))
		goto stat_msg_cancel;

	if (tsk_conn_cong(tsk) &&
	    nla_put_flag(skb, TIPC_NLA_SOCK_STAT_CONN_CONG))
		goto stat_msg_cancel;

	nla_nest_end(skb, stat);

	if (tsk->group)
		if (tipc_group_fill_sock_diag(tsk->group, skb))
			goto stat_msg_cancel;

	nla_nest_end(skb, attrs);

	return 0;

stat_msg_cancel:
	nla_nest_cancel(skb, stat);
attr_msg_cancel:
	nla_nest_cancel(skb, attrs);
msg_cancel:
	return -EMSGSIZE;
}
EXPORT_SYMBOL(tipc_sk_fill_sock_diag);

int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	return tipc_nl_sk_walk(skb, cb, __tipc_nl_add_sk);
}

/* Caller should hold socket lock for the passed tipc socket. */
static int __tipc_nl_add_sk_publ(struct sk_buff *skb,
				 struct netlink_callback *cb,
				 struct publication *publ)
{
	void *hdr;
	struct nlattr *attrs;

	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
			  &tipc_genl_family, NLM_F_MULTI, TIPC_NL_PUBL_GET);
	if (!hdr)
		goto msg_cancel;

	attrs = nla_nest_start(skb, TIPC_NLA_PUBL);
	if (!attrs)
		goto genlmsg_cancel;

	if (nla_put_u32(skb, TIPC_NLA_PUBL_KEY, publ->key))
		goto attr_msg_cancel;
	if (nla_put_u32(skb, TIPC_NLA_PUBL_TYPE, publ->type))
		goto attr_msg_cancel;
	if (nla_put_u32(skb, TIPC_NLA_PUBL_LOWER, publ->lower))
		goto attr_msg_cancel;
	if (nla_put_u32(skb, TIPC_NLA_PUBL_UPPER, publ->upper))
		goto attr_msg_cancel;

	nla_nest_end(skb, attrs);
	genlmsg_end(skb, hdr);

	return 0;

attr_msg_cancel:
	nla_nest_cancel(skb, attrs);
genlmsg_cancel:
	genlmsg_cancel(skb, hdr);
msg_cancel:
	return -EMSGSIZE;
}

/* Caller should hold socket lock for the passed tipc socket. */
static int __tipc_nl_list_sk_publ(struct sk_buff *skb,
				  struct netlink_callback *cb,
				  struct tipc_sock *tsk, u32 *last_publ)
{
	int err;
	struct publication *p;

	if (*last_publ) {
		list_for_each_entry(p, &tsk->publications, binding_sock) {
			if (p->key == *last_publ)
				break;
		}
		if (p->key != *last_publ) {
			/* We never set seq or call nl_dump_check_consistent()
			 * this means that setting prev_seq here will cause the
			 * consistence check to fail in the netlink callback
			 * handler. Resulting in the last NLMSG_DONE message
			 * having the NLM_F_DUMP_INTR flag set.
			 */
			cb->prev_seq = 1;
			*last_publ = 0;
			return -EPIPE;
		}
	} else {
		p = list_first_entry(&tsk->publications, struct publication,
				     binding_sock);
	}

	list_for_each_entry_from(p, &tsk->publications, binding_sock) {
		err = __tipc_nl_add_sk_publ(skb, cb, p);
		if (err) {
			*last_publ = p->key;
			return err;
		}
	}
	*last_publ = 0;

	return 0;
}

int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	int err;
	u32 tsk_portid = cb->args[0];
	u32 last_publ = cb->args[1];
	u32 done = cb->args[2];
	struct net *net = sock_net(skb->sk);
	struct tipc_sock *tsk;

	if (!tsk_portid) {
		struct nlattr **attrs;
		struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];

		err = tipc_nlmsg_parse(cb->nlh, &attrs);
		if (err)
			return err;

		if (!attrs[TIPC_NLA_SOCK])
			return -EINVAL;

		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
				       attrs[TIPC_NLA_SOCK],
				       tipc_nl_sock_policy, NULL);
		if (err)
			return err;

		if (!sock[TIPC_NLA_SOCK_REF])
			return -EINVAL;

		tsk_portid = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
	}

	if (done)
		return 0;

	tsk = tipc_sk_lookup(net, tsk_portid);
	if (!tsk)
		return -EINVAL;

	lock_sock(&tsk->sk);
	err = __tipc_nl_list_sk_publ(skb, cb, tsk, &last_publ);
	if (!err)
		done = 1;
	release_sock(&tsk->sk);
	sock_put(&tsk->sk);

	cb->args[0] = tsk_portid;
	cb->args[1] = last_publ;
	cb->args[2] = done;

	return skb->len;
}