summaryrefslogtreecommitdiffstats
path: root/net/mptcp/protocol.c
blob: 8cd6cc67c2c5cf9c94d9bb041b83058351c30cae (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
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
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
 *
 * Copyright (c) 2017 - 2019, Intel Corporation.
 */

#define pr_fmt(fmt) "MPTCP: " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
#include <linux/atomic.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
#include <net/xfrm.h>
#include <asm/ioctls.h>
#include "protocol.h"
#include "mib.h"

#define CREATE_TRACE_POINTS
#include <trace/events/mptcp.h>

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
struct mptcp6_sock {
	struct mptcp_sock msk;
	struct ipv6_pinfo np;
};
#endif

enum {
	MPTCP_CMSG_TS = BIT(0),
	MPTCP_CMSG_INQ = BIT(1),
};

static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;

static void __mptcp_destroy_sock(struct sock *sk);
static void __mptcp_check_send_data_fin(struct sock *sk);

DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
static struct net_device mptcp_napi_dev;

/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
 * completed yet or has failed, return the subflow socket.
 * Otherwise return NULL.
 */
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
{
	if (!msk->subflow || READ_ONCE(msk->can_ack))
		return NULL;

	return msk->subflow;
}

/* Returns end sequence number of the receiver's advertised window */
static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
{
	return READ_ONCE(msk->wnd_end);
}

static bool mptcp_is_tcpsk(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;

	if (unlikely(sk->sk_prot == &tcp_prot)) {
		/* we are being invoked after mptcp_accept() has
		 * accepted a non-mp-capable flow: sk is a tcp_sk,
		 * not an mptcp one.
		 *
		 * Hand the socket over to tcp so all further socket ops
		 * bypass mptcp.
		 */
		sock->ops = &inet_stream_ops;
		return true;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
		sock->ops = &inet6_stream_ops;
		return true;
#endif
	}

	return false;
}

static int __mptcp_socket_create(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	struct socket *ssock;
	int err;

	err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock);
	if (err)
		return err;

	msk->first = ssock->sk;
	msk->subflow = ssock;
	subflow = mptcp_subflow_ctx(ssock->sk);
	list_add(&subflow->node, &msk->conn_list);
	sock_hold(ssock->sk);
	subflow->request_mptcp = 1;

	/* This is the first subflow, always with id 0 */
	subflow->local_id_valid = 1;
	mptcp_sock_graft(msk->first, sk->sk_socket);

	return 0;
}

static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
{
	sk_drops_add(sk, skb);
	__kfree_skb(skb);
}

static void mptcp_rmem_charge(struct sock *sk, int size)
{
	mptcp_sk(sk)->rmem_fwd_alloc -= size;
}

static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
			       struct sk_buff *from)
{
	bool fragstolen;
	int delta;

	if (MPTCP_SKB_CB(from)->offset ||
	    !skb_try_coalesce(to, from, &fragstolen, &delta))
		return false;

	pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
		 MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
		 to->len, MPTCP_SKB_CB(from)->end_seq);
	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;

	/* note the fwd memory can reach a negative value after accounting
	 * for the delta, but the later skb free will restore a non
	 * negative one
	 */
	atomic_add(delta, &sk->sk_rmem_alloc);
	mptcp_rmem_charge(sk, delta);
	kfree_skb_partial(from, fragstolen);

	return true;
}

static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
				   struct sk_buff *from)
{
	if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq)
		return false;

	return mptcp_try_coalesce((struct sock *)msk, to, from);
}

static void __mptcp_rmem_reclaim(struct sock *sk, int amount)
{
	amount >>= PAGE_SHIFT;
	mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT;
	__sk_mem_reduce_allocated(sk, amount);
}

static void mptcp_rmem_uncharge(struct sock *sk, int size)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	int reclaimable;

	msk->rmem_fwd_alloc += size;
	reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk);

	/* see sk_mem_uncharge() for the rationale behind the following schema */
	if (unlikely(reclaimable >= PAGE_SIZE))
		__mptcp_rmem_reclaim(sk, reclaimable);
}

static void mptcp_rfree(struct sk_buff *skb)
{
	unsigned int len = skb->truesize;
	struct sock *sk = skb->sk;

	atomic_sub(len, &sk->sk_rmem_alloc);
	mptcp_rmem_uncharge(sk, len);
}

void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = mptcp_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	mptcp_rmem_charge(sk, skb->truesize);
}

/* "inspired" by tcp_data_queue_ofo(), main differences:
 * - use mptcp seqs
 * - don't cope with sacks
 */
static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
{
	struct sock *sk = (struct sock *)msk;
	struct rb_node **p, *parent;
	u64 seq, end_seq, max_seq;
	struct sk_buff *skb1;

	seq = MPTCP_SKB_CB(skb)->map_seq;
	end_seq = MPTCP_SKB_CB(skb)->end_seq;
	max_seq = atomic64_read(&msk->rcv_wnd_sent);

	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
	if (after64(end_seq, max_seq)) {
		/* out of window */
		mptcp_drop(sk, skb);
		pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
			 (unsigned long long)end_seq - (unsigned long)max_seq,
			 (unsigned long long)atomic64_read(&msk->rcv_wnd_sent));
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
		return;
	}

	p = &msk->out_of_order_queue.rb_node;
	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE);
	if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) {
		rb_link_node(&skb->rbnode, NULL, p);
		rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
		msk->ooo_last_skb = skb;
		goto end;
	}

	/* with 2 subflows, adding at end of ooo queue is quite likely
	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
	 */
	if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) {
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
		return;
	}

	/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
	if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) {
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
		parent = &msk->ooo_last_skb->rbnode;
		p = &parent->rb_right;
		goto insert;
	}

	/* Find place to insert this segment. Handle overlaps on the way. */
	parent = NULL;
	while (*p) {
		parent = *p;
		skb1 = rb_to_skb(parent);
		if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
			p = &parent->rb_left;
			continue;
		}
		if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) {
			if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) {
				/* All the bits are present. Drop. */
				mptcp_drop(sk, skb);
				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
				return;
			}
			if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
				/* partial overlap:
				 *     |     skb      |
				 *  |     skb1    |
				 * continue traversing
				 */
			} else {
				/* skb's seq == skb1's seq and skb covers skb1.
				 * Replace skb1 with skb.
				 */
				rb_replace_node(&skb1->rbnode, &skb->rbnode,
						&msk->out_of_order_queue);
				mptcp_drop(sk, skb1);
				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
				goto merge_right;
			}
		} else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) {
			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
			return;
		}
		p = &parent->rb_right;
	}

insert:
	/* Insert segment into RB tree. */
	rb_link_node(&skb->rbnode, parent, p);
	rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);

merge_right:
	/* Remove other segments covered by skb. */
	while ((skb1 = skb_rb_next(skb)) != NULL) {
		if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq))
			break;
		rb_erase(&skb1->rbnode, &msk->out_of_order_queue);
		mptcp_drop(sk, skb1);
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
	}
	/* If there is no skb after us, we are the last_skb ! */
	if (!skb1)
		msk->ooo_last_skb = skb;

end:
	skb_condense(skb);
	mptcp_set_owner_r(skb, sk);
}

static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	int amt, amount;

	if (size <= msk->rmem_fwd_alloc)
		return true;

	size -= msk->rmem_fwd_alloc;
	amt = sk_mem_pages(size);
	amount = amt << PAGE_SHIFT;
	if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV))
		return false;

	msk->rmem_fwd_alloc += amount;
	return true;
}

static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
			     struct sk_buff *skb, unsigned int offset,
			     size_t copy_len)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct sock *sk = (struct sock *)msk;
	struct sk_buff *tail;
	bool has_rxtstamp;

	__skb_unlink(skb, &ssk->sk_receive_queue);

	skb_ext_reset(skb);
	skb_orphan(skb);

	/* try to fetch required memory from subflow */
	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
		goto drop;

	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;

	/* the skb map_seq accounts for the skb offset:
	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
	 * value
	 */
	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
	MPTCP_SKB_CB(skb)->offset = offset;
	MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;

	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
		/* in sequence */
		WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
		tail = skb_peek_tail(&sk->sk_receive_queue);
		if (tail && mptcp_try_coalesce(sk, tail, skb))
			return true;

		mptcp_set_owner_r(skb, sk);
		__skb_queue_tail(&sk->sk_receive_queue, skb);
		return true;
	} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
		mptcp_data_queue_ofo(msk, skb);
		return false;
	}

	/* old data, keep it simple and drop the whole pkt, sender
	 * will retransmit as needed, if needed.
	 */
	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
drop:
	mptcp_drop(sk, skb);
	return false;
}

static void mptcp_stop_timer(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
	mptcp_sk(sk)->timer_ival = 0;
}

static void mptcp_close_wake_up(struct sock *sk)
{
	if (sock_flag(sk, SOCK_DEAD))
		return;

	sk->sk_state_change(sk);
	if (sk->sk_shutdown == SHUTDOWN_MASK ||
	    sk->sk_state == TCP_CLOSE)
		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
	else
		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}

static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	return !__mptcp_check_fallback(msk) &&
	       ((1 << sk->sk_state) &
		(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
	       msk->write_seq == READ_ONCE(msk->snd_una);
}

static void mptcp_check_data_fin_ack(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	/* Look for an acknowledged DATA_FIN */
	if (mptcp_pending_data_fin_ack(sk)) {
		WRITE_ONCE(msk->snd_data_fin_enable, 0);

		switch (sk->sk_state) {
		case TCP_FIN_WAIT1:
			inet_sk_state_store(sk, TCP_FIN_WAIT2);
			break;
		case TCP_CLOSING:
		case TCP_LAST_ACK:
			inet_sk_state_store(sk, TCP_CLOSE);
			break;
		}

		mptcp_close_wake_up(sk);
	}
}

static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (READ_ONCE(msk->rcv_data_fin) &&
	    ((1 << sk->sk_state) &
	     (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) {
		u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq);

		if (msk->ack_seq == rcv_data_fin_seq) {
			if (seq)
				*seq = rcv_data_fin_seq;

			return true;
		}
	}

	return false;
}

static void mptcp_set_datafin_timeout(const struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	u32 retransmits;

	retransmits = min_t(u32, icsk->icsk_retransmits,
			    ilog2(TCP_RTO_MAX / TCP_RTO_MIN));

	mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits;
}

static void __mptcp_set_timeout(struct sock *sk, long tout)
{
	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
}

static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow)
{
	const struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

	return inet_csk(ssk)->icsk_pending && !subflow->stale_count ?
	       inet_csk(ssk)->icsk_timeout - jiffies : 0;
}

static void mptcp_set_timeout(struct sock *sk)
{
	struct mptcp_subflow_context *subflow;
	long tout = 0;

	mptcp_for_each_subflow(mptcp_sk(sk), subflow)
		tout = max(tout, mptcp_timeout_from_subflow(subflow));
	__mptcp_set_timeout(sk, tout);
}

static inline bool tcp_can_send_ack(const struct sock *ssk)
{
	return !((1 << inet_sk_state_load(ssk)) &
	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
}

void __mptcp_subflow_send_ack(struct sock *ssk)
{
	if (tcp_can_send_ack(ssk))
		tcp_send_ack(ssk);
}

static void mptcp_subflow_send_ack(struct sock *ssk)
{
	bool slow;

	slow = lock_sock_fast(ssk);
	__mptcp_subflow_send_ack(ssk);
	unlock_sock_fast(ssk, slow);
}

static void mptcp_send_ack(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow;

	mptcp_for_each_subflow(msk, subflow)
		mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow));
}

static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
{
	bool slow;

	slow = lock_sock_fast(ssk);
	if (tcp_can_send_ack(ssk))
		tcp_cleanup_rbuf(ssk, 1);
	unlock_sock_fast(ssk, slow);
}

static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty)
{
	const struct inet_connection_sock *icsk = inet_csk(ssk);
	u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending);
	const struct tcp_sock *tp = tcp_sk(ssk);

	return (ack_pending & ICSK_ACK_SCHED) &&
		((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) >
		  READ_ONCE(icsk->icsk_ack.rcv_mss)) ||
		 (rx_empty && ack_pending &
			      (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));
}

static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
{
	int old_space = READ_ONCE(msk->old_wspace);
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	int space =  __mptcp_space(sk);
	bool cleanup, rx_empty;

	cleanup = (space > 0) && (space >= (old_space << 1));
	rx_empty = !__mptcp_rmem(sk);

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))
			mptcp_subflow_cleanup_rbuf(ssk);
	}
}

static bool mptcp_check_data_fin(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	u64 rcv_data_fin_seq;
	bool ret = false;

	if (__mptcp_check_fallback(msk))
		return ret;

	/* Need to ack a DATA_FIN received from a peer while this side
	 * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
	 * msk->rcv_data_fin was set when parsing the incoming options
	 * at the subflow level and the msk lock was not held, so this
	 * is the first opportunity to act on the DATA_FIN and change
	 * the msk state.
	 *
	 * If we are caught up to the sequence number of the incoming
	 * DATA_FIN, send the DATA_ACK now and do state transition.  If
	 * not caught up, do nothing and let the recv code send DATA_ACK
	 * when catching up.
	 */

	if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
		WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
		WRITE_ONCE(msk->rcv_data_fin, 0);

		sk->sk_shutdown |= RCV_SHUTDOWN;
		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */

		switch (sk->sk_state) {
		case TCP_ESTABLISHED:
			inet_sk_state_store(sk, TCP_CLOSE_WAIT);
			break;
		case TCP_FIN_WAIT1:
			inet_sk_state_store(sk, TCP_CLOSING);
			break;
		case TCP_FIN_WAIT2:
			inet_sk_state_store(sk, TCP_CLOSE);
			break;
		default:
			/* Other states not expected */
			WARN_ON_ONCE(1);
			break;
		}

		ret = true;
		mptcp_send_ack(msk);
		mptcp_close_wake_up(sk);
	}
	return ret;
}

static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
					   struct sock *ssk,
					   unsigned int *bytes)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct sock *sk = (struct sock *)msk;
	unsigned int moved = 0;
	bool more_data_avail;
	struct tcp_sock *tp;
	bool done = false;
	int sk_rbuf;

	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);

	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
		int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);

		if (unlikely(ssk_rbuf > sk_rbuf)) {
			WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
			sk_rbuf = ssk_rbuf;
		}
	}

	pr_debug("msk=%p ssk=%p", msk, ssk);
	tp = tcp_sk(ssk);
	do {
		u32 map_remaining, offset;
		u32 seq = tp->copied_seq;
		struct sk_buff *skb;
		bool fin;

		/* try to move as much data as available */
		map_remaining = subflow->map_data_len -
				mptcp_subflow_get_map_offset(subflow);

		skb = skb_peek(&ssk->sk_receive_queue);
		if (!skb) {
			/* With racing move_skbs_to_msk() and __mptcp_move_skbs(),
			 * a different CPU can have already processed the pending
			 * data, stop here or we can enter an infinite loop
			 */
			if (!moved)
				done = true;
			break;
		}

		if (__mptcp_check_fallback(msk)) {
			/* Under fallback skbs have no MPTCP extension and TCP could
			 * collapse them between the dummy map creation and the
			 * current dequeue. Be sure to adjust the map size.
			 */
			map_remaining = skb->len;
			subflow->map_data_len = skb->len;
		}

		offset = seq - TCP_SKB_CB(skb)->seq;
		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
		if (fin) {
			done = true;
			seq++;
		}

		if (offset < skb->len) {
			size_t len = skb->len - offset;

			if (tp->urg_data)
				done = true;

			if (__mptcp_move_skb(msk, ssk, skb, offset, len))
				moved += len;
			seq += len;

			if (WARN_ON_ONCE(map_remaining < len))
				break;
		} else {
			WARN_ON_ONCE(!fin);
			sk_eat_skb(ssk, skb);
			done = true;
		}

		WRITE_ONCE(tp->copied_seq, seq);
		more_data_avail = mptcp_subflow_data_available(ssk);

		if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
			done = true;
			break;
		}
	} while (more_data_avail);

	*bytes += moved;
	return done;
}

static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
{
	struct sock *sk = (struct sock *)msk;
	struct sk_buff *skb, *tail;
	bool moved = false;
	struct rb_node *p;
	u64 end_seq;

	p = rb_first(&msk->out_of_order_queue);
	pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
	while (p) {
		skb = rb_to_skb(p);
		if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
			break;

		p = rb_next(p);
		rb_erase(&skb->rbnode, &msk->out_of_order_queue);

		if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq,
				      msk->ack_seq))) {
			mptcp_drop(sk, skb);
			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
			continue;
		}

		end_seq = MPTCP_SKB_CB(skb)->end_seq;
		tail = skb_peek_tail(&sk->sk_receive_queue);
		if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) {
			int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;

			/* skip overlapping data, if any */
			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
				 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
				 delta);
			MPTCP_SKB_CB(skb)->offset += delta;
			MPTCP_SKB_CB(skb)->map_seq += delta;
			__skb_queue_tail(&sk->sk_receive_queue, skb);
		}
		msk->ack_seq = end_seq;
		moved = true;
	}
	return moved;
}

/* In most cases we will be able to lock the mptcp socket.  If its already
 * owned, we need to defer to the work queue to avoid ABBA deadlock.
 */
static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
{
	struct sock *sk = (struct sock *)msk;
	unsigned int moved = 0;

	__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
	__mptcp_ofo_queue(msk);
	if (unlikely(ssk->sk_err)) {
		if (!sock_owned_by_user(sk))
			__mptcp_error_report(sk);
		else
			__set_bit(MPTCP_ERROR_REPORT,  &msk->cb_flags);
	}

	/* If the moves have caught up with the DATA_FIN sequence number
	 * it's time to ack the DATA_FIN and change socket state, but
	 * this is not a good place to change state. Let the workqueue
	 * do it.
	 */
	if (mptcp_pending_data_fin(sk, NULL))
		mptcp_schedule_work(sk);
	return moved > 0;
}

void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct mptcp_sock *msk = mptcp_sk(sk);
	int sk_rbuf, ssk_rbuf;

	/* The peer can send data while we are shutting down this
	 * subflow at msk destruction time, but we must avoid enqueuing
	 * more data to the msk receive queue
	 */
	if (unlikely(subflow->disposable))
		return;

	ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
	if (unlikely(ssk_rbuf > sk_rbuf))
		sk_rbuf = ssk_rbuf;

	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
	if (__mptcp_rmem(sk) > sk_rbuf) {
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
		return;
	}

	/* Wake-up the reader only for in-sequence data */
	mptcp_data_lock(sk);
	if (move_skbs_to_msk(msk, ssk))
		sk->sk_data_ready(sk);

	mptcp_data_unlock(sk);
}

static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
{
	struct sock *sk = (struct sock *)msk;

	if (sk->sk_state != TCP_ESTABLISHED)
		return false;

	/* attach to msk socket only after we are sure we will deal with it
	 * at close time
	 */
	if (sk->sk_socket && !ssk->sk_socket)
		mptcp_sock_graft(ssk, sk->sk_socket);

	mptcp_propagate_sndbuf((struct sock *)msk, ssk);
	mptcp_sockopt_sync_locked(msk, ssk);
	return true;
}

static void __mptcp_flush_join_list(struct sock *sk)
{
	struct mptcp_subflow_context *tmp, *subflow;
	struct mptcp_sock *msk = mptcp_sk(sk);

	list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast(ssk);

		list_move_tail(&subflow->node, &msk->conn_list);
		if (!__mptcp_finish_join(msk, ssk))
			mptcp_subflow_reset(ssk);
		unlock_sock_fast(ssk, slow);
	}
}

static bool mptcp_timer_pending(struct sock *sk)
{
	return timer_pending(&inet_csk(sk)->icsk_retransmit_timer);
}

static void mptcp_reset_timer(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	unsigned long tout;

	/* prevent rescheduling on close */
	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
		return;

	tout = mptcp_sk(sk)->timer_ival;
	sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
}

bool mptcp_schedule_work(struct sock *sk)
{
	if (inet_sk_state_load(sk) != TCP_CLOSE &&
	    schedule_work(&mptcp_sk(sk)->work)) {
		/* each subflow already holds a reference to the sk, and the
		 * workqueue is invoked by a subflow, so sk can't go away here.
		 */
		sock_hold(sk);
		return true;
	}
	return false;
}

void mptcp_subflow_eof(struct sock *sk)
{
	if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
		mptcp_schedule_work(sk);
}

static void mptcp_check_for_eof(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	int receivers = 0;

	mptcp_for_each_subflow(msk, subflow)
		receivers += !subflow->rx_eof;
	if (receivers)
		return;

	if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
		/* hopefully temporary hack: propagate shutdown status
		 * to msk, when all subflows agree on it
		 */
		sk->sk_shutdown |= RCV_SHUTDOWN;

		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
		sk->sk_data_ready(sk);
	}

	switch (sk->sk_state) {
	case TCP_ESTABLISHED:
		inet_sk_state_store(sk, TCP_CLOSE_WAIT);
		break;
	case TCP_FIN_WAIT1:
		inet_sk_state_store(sk, TCP_CLOSING);
		break;
	case TCP_FIN_WAIT2:
		inet_sk_state_store(sk, TCP_CLOSE);
		break;
	default:
		return;
	}
	mptcp_close_wake_up(sk);
}

static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;

	sock_owned_by_me(sk);

	mptcp_for_each_subflow(msk, subflow) {
		if (READ_ONCE(subflow->data_avail))
			return mptcp_subflow_tcp_sock(subflow);
	}

	return NULL;
}

static bool mptcp_skb_can_collapse_to(u64 write_seq,
				      const struct sk_buff *skb,
				      const struct mptcp_ext *mpext)
{
	if (!tcp_skb_can_collapse_to(skb))
		return false;

	/* can collapse only if MPTCP level sequence is in order and this
	 * mapping has not been xmitted yet
	 */
	return mpext && mpext->data_seq + mpext->data_len == write_seq &&
	       !mpext->frozen;
}

/* we can append data to the given data frag if:
 * - there is space available in the backing page_frag
 * - the data frag tail matches the current page_frag free offset
 * - the data frag end sequence number matches the current write seq
 */
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
				       const struct page_frag *pfrag,
				       const struct mptcp_data_frag *df)
{
	return df && pfrag->page == df->page &&
		pfrag->size - pfrag->offset > 0 &&
		pfrag->offset == (df->offset + df->data_len) &&
		df->data_seq + df->data_len == msk->write_seq;
}

static void dfrag_uncharge(struct sock *sk, int len)
{
	sk_mem_uncharge(sk, len);
	sk_wmem_queued_add(sk, -len);
}

static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
{
	int len = dfrag->data_len + dfrag->overhead;

	list_del(&dfrag->list);
	dfrag_uncharge(sk, len);
	put_page(dfrag->page);
}

static void __mptcp_clean_una(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_data_frag *dtmp, *dfrag;
	u64 snd_una;

	/* on fallback we just need to ignore snd_una, as this is really
	 * plain TCP
	 */
	if (__mptcp_check_fallback(msk))
		msk->snd_una = READ_ONCE(msk->snd_nxt);

	snd_una = msk->snd_una;
	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
		if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
			break;

		if (unlikely(dfrag == msk->first_pending)) {
			/* in recovery mode can see ack after the current snd head */
			if (WARN_ON_ONCE(!msk->recovery))
				break;

			WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
		}

		dfrag_clear(sk, dfrag);
	}

	dfrag = mptcp_rtx_head(sk);
	if (dfrag && after64(snd_una, dfrag->data_seq)) {
		u64 delta = snd_una - dfrag->data_seq;

		/* prevent wrap around in recovery mode */
		if (unlikely(delta > dfrag->already_sent)) {
			if (WARN_ON_ONCE(!msk->recovery))
				goto out;
			if (WARN_ON_ONCE(delta > dfrag->data_len))
				goto out;
			dfrag->already_sent += delta - dfrag->already_sent;
		}

		dfrag->data_seq += delta;
		dfrag->offset += delta;
		dfrag->data_len -= delta;
		dfrag->already_sent -= delta;

		dfrag_uncharge(sk, delta);
	}

	/* all retransmitted data acked, recovery completed */
	if (unlikely(msk->recovery) && after64(msk->snd_una, msk->recovery_snd_nxt))
		msk->recovery = false;

out:
	if (snd_una == READ_ONCE(msk->snd_nxt) &&
	    snd_una == READ_ONCE(msk->write_seq)) {
		if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
			mptcp_stop_timer(sk);
	} else {
		mptcp_reset_timer(sk);
	}
}

static void __mptcp_clean_una_wakeup(struct sock *sk)
{
	lockdep_assert_held_once(&sk->sk_lock.slock);

	__mptcp_clean_una(sk);
	mptcp_write_space(sk);
}

static void mptcp_clean_una_wakeup(struct sock *sk)
{
	mptcp_data_lock(sk);
	__mptcp_clean_una_wakeup(sk);
	mptcp_data_unlock(sk);
}

static void mptcp_enter_memory_pressure(struct sock *sk)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_sock *msk = mptcp_sk(sk);
	bool first = true;

	sk_stream_moderate_sndbuf(sk);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		if (first)
			tcp_enter_memory_pressure(ssk);
		sk_stream_moderate_sndbuf(ssk);
		first = false;
	}
}

/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
 * data
 */
static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
	if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag),
					pfrag, sk->sk_allocation)))
		return true;

	mptcp_enter_memory_pressure(sk);
	return false;
}

static struct mptcp_data_frag *
mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
		      int orig_offset)
{
	int offset = ALIGN(orig_offset, sizeof(long));
	struct mptcp_data_frag *dfrag;

	dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset);
	dfrag->data_len = 0;
	dfrag->data_seq = msk->write_seq;
	dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
	dfrag->offset = offset + sizeof(struct mptcp_data_frag);
	dfrag->already_sent = 0;
	dfrag->page = pfrag->page;

	return dfrag;
}

struct mptcp_sendmsg_info {
	int mss_now;
	int size_goal;
	u16 limit;
	u16 sent;
	unsigned int flags;
	bool data_lock_held;
};

static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk,
				    u64 data_seq, int avail_size)
{
	u64 window_end = mptcp_wnd_end(msk);
	u64 mptcp_snd_wnd;

	if (__mptcp_check_fallback(msk))
		return avail_size;

	mptcp_snd_wnd = window_end - data_seq;
	avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size);

	if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd)) {
		tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd);
		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_SNDWNDSHARED);
	}

	return avail_size;
}

static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp)
{
	struct skb_ext *mpext = __skb_ext_alloc(gfp);

	if (!mpext)
		return false;
	__skb_ext_set(skb, SKB_EXT_MPTCP, mpext);
	return true;
}

static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
{
	struct sk_buff *skb;

	skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
	if (likely(skb)) {
		if (likely(__mptcp_add_ext(skb, gfp))) {
			skb_reserve(skb, MAX_TCP_HEADER);
			skb->ip_summed = CHECKSUM_PARTIAL;
			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
			return skb;
		}
		__kfree_skb(skb);
	} else {
		mptcp_enter_memory_pressure(sk);
	}
	return NULL;
}

static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
{
	struct sk_buff *skb;

	skb = __mptcp_do_alloc_tx_skb(sk, gfp);
	if (!skb)
		return NULL;

	if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
		tcp_skb_entail(ssk, skb);
		return skb;
	}
	tcp_skb_tsorted_anchor_cleanup(skb);
	kfree_skb(skb);
	return NULL;
}

static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
{
	gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation;

	return __mptcp_alloc_tx_skb(sk, ssk, gfp);
}

/* note: this always recompute the csum on the whole skb, even
 * if we just appended a single frag. More status info needed
 */
static void mptcp_update_data_checksum(struct sk_buff *skb, int added)
{
	struct mptcp_ext *mpext = mptcp_get_ext(skb);
	__wsum csum = ~csum_unfold(mpext->csum);
	int offset = skb->len - added;

	mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset));
}

static void mptcp_update_infinite_map(struct mptcp_sock *msk,
				      struct sock *ssk,
				      struct mptcp_ext *mpext)
{
	if (!mpext)
		return;

	mpext->infinite_map = 1;
	mpext->data_len = 0;

	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
	pr_fallback(msk);
	mptcp_do_fallback(ssk);
}

static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
			      struct mptcp_data_frag *dfrag,
			      struct mptcp_sendmsg_info *info)
{
	u64 data_seq = dfrag->data_seq + info->sent;
	int offset = dfrag->offset + info->sent;
	struct mptcp_sock *msk = mptcp_sk(sk);
	bool zero_window_probe = false;
	struct mptcp_ext *mpext = NULL;
	bool can_coalesce = false;
	bool reuse_skb = true;
	struct sk_buff *skb;
	size_t copy;
	int i;

	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);

	if (WARN_ON_ONCE(info->sent > info->limit ||
			 info->limit > dfrag->data_len))
		return 0;

	if (unlikely(!__tcp_can_send(ssk)))
		return -EAGAIN;

	/* compute send limit */
	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
	copy = info->size_goal;

	skb = tcp_write_queue_tail(ssk);
	if (skb && copy > skb->len) {
		/* Limit the write to the size available in the
		 * current skb, if any, so that we create at most a new skb.
		 * Explicitly tells TCP internals to avoid collapsing on later
		 * queue management operation, to avoid breaking the ext <->
		 * SSN association set here
		 */
		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
		if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
			TCP_SKB_CB(skb)->eor = 1;
			goto alloc_skb;
		}

		i = skb_shinfo(skb)->nr_frags;
		can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
		if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
			tcp_mark_push(tcp_sk(ssk), skb);
			goto alloc_skb;
		}

		copy -= skb->len;
	} else {
alloc_skb:
		skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held);
		if (!skb)
			return -ENOMEM;

		i = skb_shinfo(skb)->nr_frags;
		reuse_skb = false;
		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
	}

	/* Zero window and all data acked? Probe. */
	copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy);
	if (copy == 0) {
		u64 snd_una = READ_ONCE(msk->snd_una);

		if (snd_una != msk->snd_nxt) {
			tcp_remove_empty_skb(ssk);
			return 0;
		}

		zero_window_probe = true;
		data_seq = snd_una - 1;
		copy = 1;

		/* all mptcp-level data is acked, no skbs should be present into the
		 * ssk write queue
		 */
		WARN_ON_ONCE(reuse_skb);
	}

	copy = min_t(size_t, copy, info->limit - info->sent);
	if (!sk_wmem_schedule(ssk, copy)) {
		tcp_remove_empty_skb(ssk);
		return -ENOMEM;
	}

	if (can_coalesce) {
		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
	} else {
		get_page(dfrag->page);
		skb_fill_page_desc(skb, i, dfrag->page, offset, copy);
	}

	skb->len += copy;
	skb->data_len += copy;
	skb->truesize += copy;
	sk_wmem_queued_add(ssk, copy);
	sk_mem_charge(ssk, copy);
	WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy);
	TCP_SKB_CB(skb)->end_seq += copy;
	tcp_skb_pcount_set(skb, 0);

	/* on skb reuse we just need to update the DSS len */
	if (reuse_skb) {
		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
		mpext->data_len += copy;
		WARN_ON_ONCE(zero_window_probe);
		goto out;
	}

	memset(mpext, 0, sizeof(*mpext));
	mpext->data_seq = data_seq;
	mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
	mpext->data_len = copy;
	mpext->use_map = 1;
	mpext->dsn64 = 1;

	pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
		 mpext->data_seq, mpext->subflow_seq, mpext->data_len,
		 mpext->dsn64);

	if (zero_window_probe) {
		mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
		mpext->frozen = 1;
		if (READ_ONCE(msk->csum_enabled))
			mptcp_update_data_checksum(skb, copy);
		tcp_push_pending_frames(ssk);
		return 0;
	}
out:
	if (READ_ONCE(msk->csum_enabled))
		mptcp_update_data_checksum(skb, copy);
	if (mptcp_subflow_ctx(ssk)->send_infinite_map)
		mptcp_update_infinite_map(msk, ssk, mpext);
	trace_mptcp_sendmsg_frag(mpext);
	mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
	return copy;
}

#define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
					 sizeof(struct tcphdr) - \
					 MAX_TCP_OPTION_SPACE - \
					 sizeof(struct ipv6hdr) - \
					 sizeof(struct frag_hdr))

struct subflow_send_info {
	struct sock *ssk;
	u64 linger_time;
};

void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow)
{
	if (!subflow->stale)
		return;

	subflow->stale = 0;
	MPTCP_INC_STATS(sock_net(mptcp_subflow_tcp_sock(subflow)), MPTCP_MIB_SUBFLOWRECOVER);
}

bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
{
	if (unlikely(subflow->stale)) {
		u32 rcv_tstamp = READ_ONCE(tcp_sk(mptcp_subflow_tcp_sock(subflow))->rcv_tstamp);

		if (subflow->stale_rcv_tstamp == rcv_tstamp)
			return false;

		mptcp_subflow_set_active(subflow);
	}
	return __mptcp_subflow_active(subflow);
}

#define SSK_MODE_ACTIVE	0
#define SSK_MODE_BACKUP	1
#define SSK_MODE_MAX	2

/* implement the mptcp packet scheduler;
 * returns the subflow that will transmit the next DSS
 * additionally updates the rtx timeout
 */
static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
{
	struct subflow_send_info send_info[SSK_MODE_MAX];
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	u32 pace, burst, wmem;
	int i, nr_active = 0;
	struct sock *ssk;
	u64 linger_time;
	long tout = 0;

	sock_owned_by_me(sk);

	if (__mptcp_check_fallback(msk)) {
		if (!msk->first)
			return NULL;
		return __tcp_can_send(msk->first) &&
		       sk_stream_memory_free(msk->first) ? msk->first : NULL;
	}

	/* re-use last subflow, if the burst allow that */
	if (msk->last_snd && msk->snd_burst > 0 &&
	    sk_stream_memory_free(msk->last_snd) &&
	    mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
		mptcp_set_timeout(sk);
		return msk->last_snd;
	}

	/* pick the subflow with the lower wmem/wspace ratio */
	for (i = 0; i < SSK_MODE_MAX; ++i) {
		send_info[i].ssk = NULL;
		send_info[i].linger_time = -1;
	}

	mptcp_for_each_subflow(msk, subflow) {
		trace_mptcp_subflow_get_send(subflow);
		ssk =  mptcp_subflow_tcp_sock(subflow);
		if (!mptcp_subflow_active(subflow))
			continue;

		tout = max(tout, mptcp_timeout_from_subflow(subflow));
		nr_active += !subflow->backup;
		pace = subflow->avg_pacing_rate;
		if (unlikely(!pace)) {
			/* init pacing rate from socket */
			subflow->avg_pacing_rate = READ_ONCE(ssk->sk_pacing_rate);
			pace = subflow->avg_pacing_rate;
			if (!pace)
				continue;
		}

		linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
		if (linger_time < send_info[subflow->backup].linger_time) {
			send_info[subflow->backup].ssk = ssk;
			send_info[subflow->backup].linger_time = linger_time;
		}
	}
	__mptcp_set_timeout(sk, tout);

	/* pick the best backup if no other subflow is active */
	if (!nr_active)
		send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk;

	/* According to the blest algorithm, to avoid HoL blocking for the
	 * faster flow, we need to:
	 * - estimate the faster flow linger time
	 * - use the above to estimate the amount of byte transferred
	 *   by the faster flow
	 * - check that the amount of queued data is greter than the above,
	 *   otherwise do not use the picked, slower, subflow
	 * We select the subflow with the shorter estimated time to flush
	 * the queued mem, which basically ensure the above. We just need
	 * to check that subflow has a non empty cwin.
	 */
	ssk = send_info[SSK_MODE_ACTIVE].ssk;
	if (!ssk || !sk_stream_memory_free(ssk))
		return NULL;

	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
	wmem = READ_ONCE(ssk->sk_wmem_queued);
	if (!burst) {
		msk->last_snd = NULL;
		return ssk;
	}

	subflow = mptcp_subflow_ctx(ssk);
	subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
					   READ_ONCE(ssk->sk_pacing_rate) * burst,
					   burst + wmem);
	msk->last_snd = ssk;
	msk->snd_burst = burst;
	return ssk;
}

static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info)
{
	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
	release_sock(ssk);
}

static void mptcp_update_post_push(struct mptcp_sock *msk,
				   struct mptcp_data_frag *dfrag,
				   u32 sent)
{
	u64 snd_nxt_new = dfrag->data_seq;

	dfrag->already_sent += sent;

	msk->snd_burst -= sent;

	snd_nxt_new += dfrag->already_sent;

	/* snd_nxt_new can be smaller than snd_nxt in case mptcp
	 * is recovering after a failover. In that event, this re-sends
	 * old segments.
	 *
	 * Thus compute snd_nxt_new candidate based on
	 * the dfrag->data_seq that was sent and the data
	 * that has been handed to the subflow for transmission
	 * and skip update in case it was old dfrag.
	 */
	if (likely(after64(snd_nxt_new, msk->snd_nxt)))
		msk->snd_nxt = snd_nxt_new;
}

void mptcp_check_and_set_pending(struct sock *sk)
{
	if (mptcp_send_head(sk))
		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
}

void __mptcp_push_pending(struct sock *sk, unsigned int flags)
{
	struct sock *prev_ssk = NULL, *ssk = NULL;
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_sendmsg_info info = {
				.flags = flags,
	};
	bool do_check_data_fin = false;
	struct mptcp_data_frag *dfrag;
	int len;

	while ((dfrag = mptcp_send_head(sk))) {
		info.sent = dfrag->already_sent;
		info.limit = dfrag->data_len;
		len = dfrag->data_len - dfrag->already_sent;
		while (len > 0) {
			int ret = 0;

			prev_ssk = ssk;
			ssk = mptcp_subflow_get_send(msk);

			/* First check. If the ssk has changed since
			 * the last round, release prev_ssk
			 */
			if (ssk != prev_ssk && prev_ssk)
				mptcp_push_release(prev_ssk, &info);
			if (!ssk)
				goto out;

			/* Need to lock the new subflow only if different
			 * from the previous one, otherwise we are still
			 * helding the relevant lock
			 */
			if (ssk != prev_ssk)
				lock_sock(ssk);

			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
			if (ret <= 0) {
				if (ret == -EAGAIN)
					continue;
				mptcp_push_release(ssk, &info);
				goto out;
			}

			do_check_data_fin = true;
			info.sent += ret;
			len -= ret;

			mptcp_update_post_push(msk, dfrag, ret);
		}
		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
	}

	/* at this point we held the socket lock for the last subflow we used */
	if (ssk)
		mptcp_push_release(ssk, &info);

out:
	/* ensure the rtx timer is running */
	if (!mptcp_timer_pending(sk))
		mptcp_reset_timer(sk);
	if (do_check_data_fin)
		__mptcp_check_send_data_fin(sk);
}

static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_sendmsg_info info = {
		.data_lock_held = true,
	};
	struct mptcp_data_frag *dfrag;
	struct sock *xmit_ssk;
	int len, copied = 0;

	info.flags = 0;
	while ((dfrag = mptcp_send_head(sk))) {
		info.sent = dfrag->already_sent;
		info.limit = dfrag->data_len;
		len = dfrag->data_len - dfrag->already_sent;
		while (len > 0) {
			int ret = 0;

			/* check for a different subflow usage only after
			 * spooling the first chunk of data
			 */
			xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
			if (!xmit_ssk)
				goto out;
			if (xmit_ssk != ssk) {
				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
						       MPTCP_DELEGATE_SEND);
				goto out;
			}

			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
			if (ret <= 0)
				goto out;

			info.sent += ret;
			copied += ret;
			len -= ret;
			first = false;

			mptcp_update_post_push(msk, dfrag, ret);
		}
		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
	}

out:
	/* __mptcp_alloc_tx_skb could have released some wmem and we are
	 * not going to flush it via release_sock()
	 */
	if (copied) {
		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
			 info.size_goal);
		if (!mptcp_timer_pending(sk))
			mptcp_reset_timer(sk);

		if (msk->snd_data_fin_enable &&
		    msk->snd_nxt + 1 == msk->write_seq)
			mptcp_schedule_work(sk);
	}
}

static void mptcp_set_nospace(struct sock *sk)
{
	/* enable autotune */
	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);

	/* will be cleared on avail space */
	set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
}

static int mptcp_disconnect(struct sock *sk, int flags);

static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
				  size_t len, int *copied_syn)
{
	unsigned int saved_flags = msg->msg_flags;
	struct mptcp_sock *msk = mptcp_sk(sk);
	int ret;

	lock_sock(ssk);
	msg->msg_flags |= MSG_DONTWAIT;
	msk->connect_flags = O_NONBLOCK;
	msk->fastopening = 1;
	ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
	msk->fastopening = 0;
	msg->msg_flags = saved_flags;
	release_sock(ssk);

	/* do the blocking bits of inet_stream_connect outside the ssk socket lock */
	if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) {
		ret = __inet_stream_connect(sk->sk_socket, msg->msg_name,
					    msg->msg_namelen, msg->msg_flags, 1);

		/* Keep the same behaviour of plain TCP: zero the copied bytes in
		 * case of any error, except timeout or signal
		 */
		if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
			*copied_syn = 0;
	} else if (ret && ret != -EINPROGRESS) {
		mptcp_disconnect(sk, 0);
	}

	return ret;
}

static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct page_frag *pfrag;
	struct socket *ssock;
	size_t copied = 0;
	int ret = 0;
	long timeo;

	/* silently ignore everything else */
	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN;

	lock_sock(sk);

	ssock = __mptcp_nmpc_socket(msk);
	if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect ||
			       msg->msg_flags & MSG_FASTOPEN))) {
		int copied_syn = 0;

		ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
		copied += copied_syn;
		if (ret == -EINPROGRESS && copied_syn > 0)
			goto out;
		else if (ret)
			goto do_error;
	}

	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
		ret = sk_stream_wait_connect(sk, &timeo);
		if (ret)
			goto do_error;
	}

	ret = -EPIPE;
	if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)))
		goto do_error;

	pfrag = sk_page_frag(sk);

	while (msg_data_left(msg)) {
		int total_ts, frag_truesize = 0;
		struct mptcp_data_frag *dfrag;
		bool dfrag_collapsed;
		size_t psize, offset;

		/* reuse tail pfrag, if possible, or carve a new one from the
		 * page allocator
		 */
		dfrag = mptcp_pending_tail(sk);
		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
		if (!dfrag_collapsed) {
			if (!sk_stream_memory_free(sk))
				goto wait_for_memory;

			if (!mptcp_page_frag_refill(sk, pfrag))
				goto wait_for_memory;

			dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
			frag_truesize = dfrag->overhead;
		}

		/* we do not bound vs wspace, to allow a single packet.
		 * memory accounting will prevent execessive memory usage
		 * anyway
		 */
		offset = dfrag->offset + dfrag->data_len;
		psize = pfrag->size - offset;
		psize = min_t(size_t, psize, msg_data_left(msg));
		total_ts = psize + frag_truesize;

		if (!sk_wmem_schedule(sk, total_ts))
			goto wait_for_memory;

		if (copy_page_from_iter(dfrag->page, offset, psize,
					&msg->msg_iter) != psize) {
			ret = -EFAULT;
			goto do_error;
		}

		/* data successfully copied into the write queue */
		sk->sk_forward_alloc -= total_ts;
		copied += psize;
		dfrag->data_len += psize;
		frag_truesize += psize;
		pfrag->offset += frag_truesize;
		WRITE_ONCE(msk->write_seq, msk->write_seq + psize);

		/* charge data on mptcp pending queue to the msk socket
		 * Note: we charge such data both to sk and ssk
		 */
		sk_wmem_queued_add(sk, frag_truesize);
		if (!dfrag_collapsed) {
			get_page(dfrag->page);
			list_add_tail(&dfrag->list, &msk->rtx_queue);
			if (!msk->first_pending)
				WRITE_ONCE(msk->first_pending, dfrag);
		}
		pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
			 !dfrag_collapsed);

		continue;

wait_for_memory:
		mptcp_set_nospace(sk);
		__mptcp_push_pending(sk, msg->msg_flags);
		ret = sk_stream_wait_memory(sk, &timeo);
		if (ret)
			goto do_error;
	}

	if (copied)
		__mptcp_push_pending(sk, msg->msg_flags);

out:
	release_sock(sk);
	return copied;

do_error:
	if (copied)
		goto out;

	copied = sk_stream_error(sk, msg->msg_flags, ret);
	goto out;
}

static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
				struct msghdr *msg,
				size_t len, int flags,
				struct scm_timestamping_internal *tss,
				int *cmsg_flags)
{
	struct sk_buff *skb, *tmp;
	int copied = 0;

	skb_queue_walk_safe(&msk->receive_queue, skb, tmp) {
		u32 offset = MPTCP_SKB_CB(skb)->offset;
		u32 data_len = skb->len - offset;
		u32 count = min_t(size_t, len - copied, data_len);
		int err;

		if (!(flags & MSG_TRUNC)) {
			err = skb_copy_datagram_msg(skb, offset, msg, count);
			if (unlikely(err < 0)) {
				if (!copied)
					return err;
				break;
			}
		}

		if (MPTCP_SKB_CB(skb)->has_rxtstamp) {
			tcp_update_recv_tstamps(skb, tss);
			*cmsg_flags |= MPTCP_CMSG_TS;
		}

		copied += count;

		if (count < data_len) {
			if (!(flags & MSG_PEEK)) {
				MPTCP_SKB_CB(skb)->offset += count;
				MPTCP_SKB_CB(skb)->map_seq += count;
			}
			break;
		}

		if (!(flags & MSG_PEEK)) {
			/* we will bulk release the skb memory later */
			skb->destructor = NULL;
			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
			__skb_unlink(skb, &msk->receive_queue);
			__kfree_skb(skb);
		}

		if (copied >= len)
			break;
	}

	return copied;
}

/* receive buffer autotuning.  See tcp_rcv_space_adjust for more information.
 *
 * Only difference: Use highest rtt estimate of the subflows in use.
 */
static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	u32 time, advmss = 1;
	u64 rtt_us, mstamp;

	sock_owned_by_me(sk);

	if (copied <= 0)
		return;

	msk->rcvq_space.copied += copied;

	mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
	time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time);

	rtt_us = msk->rcvq_space.rtt_us;
	if (rtt_us && time < (rtt_us >> 3))
		return;

	rtt_us = 0;
	mptcp_for_each_subflow(msk, subflow) {
		const struct tcp_sock *tp;
		u64 sf_rtt_us;
		u32 sf_advmss;

		tp = tcp_sk(mptcp_subflow_tcp_sock(subflow));

		sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us);
		sf_advmss = READ_ONCE(tp->advmss);

		rtt_us = max(sf_rtt_us, rtt_us);
		advmss = max(sf_advmss, advmss);
	}

	msk->rcvq_space.rtt_us = rtt_us;
	if (time < (rtt_us >> 3) || rtt_us == 0)
		return;

	if (msk->rcvq_space.copied <= msk->rcvq_space.space)
		goto new_measure;

	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
		int rcvmem, rcvbuf;
		u64 rcvwin, grow;

		rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss;

		grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space);

		do_div(grow, msk->rcvq_space.space);
		rcvwin += (grow << 1);

		rcvmem = SKB_TRUESIZE(advmss + MAX_TCP_HEADER);
		while (tcp_win_from_space(sk, rcvmem) < advmss)
			rcvmem += 128;

		do_div(rcvwin, advmss);
		rcvbuf = min_t(u64, rcvwin * rcvmem,
			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));

		if (rcvbuf > sk->sk_rcvbuf) {
			u32 window_clamp;

			window_clamp = tcp_win_from_space(sk, rcvbuf);
			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);

			/* Make subflows follow along.  If we do not do this, we
			 * get drops at subflow level if skbs can't be moved to
			 * the mptcp rx queue fast enough (announced rcv_win can
			 * exceed ssk->sk_rcvbuf).
			 */
			mptcp_for_each_subflow(msk, subflow) {
				struct sock *ssk;
				bool slow;

				ssk = mptcp_subflow_tcp_sock(subflow);
				slow = lock_sock_fast(ssk);
				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
				tcp_sk(ssk)->window_clamp = window_clamp;
				tcp_cleanup_rbuf(ssk, 1);
				unlock_sock_fast(ssk, slow);
			}
		}
	}

	msk->rcvq_space.space = msk->rcvq_space.copied;
new_measure:
	msk->rcvq_space.copied = 0;
	msk->rcvq_space.time = mstamp;
}

static void __mptcp_update_rmem(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (!msk->rmem_released)
		return;

	atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
	mptcp_rmem_uncharge(sk, msk->rmem_released);
	WRITE_ONCE(msk->rmem_released, 0);
}

static void __mptcp_splice_receive_queue(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue);
}

static bool __mptcp_move_skbs(struct mptcp_sock *msk)
{
	struct sock *sk = (struct sock *)msk;
	unsigned int moved = 0;
	bool ret, done;

	do {
		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
		bool slowpath;

		/* we can have data pending in the subflows only if the msk
		 * receive buffer was full at subflow_data_ready() time,
		 * that is an unlikely slow path.
		 */
		if (likely(!ssk))
			break;

		slowpath = lock_sock_fast(ssk);
		mptcp_data_lock(sk);
		__mptcp_update_rmem(sk);
		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
		mptcp_data_unlock(sk);

		if (unlikely(ssk->sk_err))
			__mptcp_error_report(sk);
		unlock_sock_fast(ssk, slowpath);
	} while (!done);

	/* acquire the data lock only if some input data is pending */
	ret = moved > 0;
	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
	    !skb_queue_empty_lockless(&sk->sk_receive_queue)) {
		mptcp_data_lock(sk);
		__mptcp_update_rmem(sk);
		ret |= __mptcp_ofo_queue(msk);
		__mptcp_splice_receive_queue(sk);
		mptcp_data_unlock(sk);
	}
	if (ret)
		mptcp_check_data_fin((struct sock *)msk);
	return !skb_queue_empty(&msk->receive_queue);
}

static unsigned int mptcp_inq_hint(const struct sock *sk)
{
	const struct mptcp_sock *msk = mptcp_sk(sk);
	const struct sk_buff *skb;

	skb = skb_peek(&msk->receive_queue);
	if (skb) {
		u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;

		if (hint_val >= INT_MAX)
			return INT_MAX;

		return (unsigned int)hint_val;
	}

	if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
		return 1;

	return 0;
}

static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
			 int flags, int *addr_len)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct scm_timestamping_internal tss;
	int copied = 0, cmsg_flags = 0;
	int target;
	long timeo;

	/* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */
	if (unlikely(flags & MSG_ERRQUEUE))
		return inet_recv_error(sk, msg, len, addr_len);

	lock_sock(sk);
	if (unlikely(sk->sk_state == TCP_LISTEN)) {
		copied = -ENOTCONN;
		goto out_err;
	}

	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	len = min_t(size_t, len, INT_MAX);
	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

	if (unlikely(msk->recvmsg_inq))
		cmsg_flags = MPTCP_CMSG_INQ;

	while (copied < len) {
		int bytes_read;

		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
		if (unlikely(bytes_read < 0)) {
			if (!copied)
				copied = bytes_read;
			goto out_err;
		}

		copied += bytes_read;

		/* be sure to advertise window change */
		mptcp_cleanup_rbuf(msk);

		if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
			continue;

		/* only the master socket status is relevant here. The exit
		 * conditions mirror closely tcp_recvmsg()
		 */
		if (copied >= target)
			break;

		if (copied) {
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current))
				break;
		} else {
			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
				mptcp_check_for_eof(msk);

			if (sk->sk_shutdown & RCV_SHUTDOWN) {
				/* race breaker: the shutdown could be after the
				 * previous receive queue check
				 */
				if (__mptcp_move_skbs(msk))
					continue;
				break;
			}

			if (sk->sk_state == TCP_CLOSE) {
				copied = -ENOTCONN;
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

		pr_debug("block timeout %ld", timeo);
		sk_wait_data(sk, &timeo, NULL);
	}

out_err:
	if (cmsg_flags && copied >= 0) {
		if (cmsg_flags & MPTCP_CMSG_TS)
			tcp_recv_timestamp(msg, sk, &tss);

		if (cmsg_flags & MPTCP_CMSG_INQ) {
			unsigned int inq = mptcp_inq_hint(sk);

			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
		}
	}

	pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
		 skb_queue_empty(&msk->receive_queue), copied);
	if (!(flags & MSG_PEEK))
		mptcp_rcv_space_adjust(msk, copied);

	release_sock(sk);
	return copied;
}

static void mptcp_retransmit_timer(struct timer_list *t)
{
	struct inet_connection_sock *icsk = from_timer(icsk, t,
						       icsk_retransmit_timer);
	struct sock *sk = &icsk->icsk_inet.sk;
	struct mptcp_sock *msk = mptcp_sk(sk);

	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		/* we need a process context to retransmit */
		if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags))
			mptcp_schedule_work(sk);
	} else {
		/* delegate our work to tcp_release_cb() */
		__set_bit(MPTCP_RETRANSMIT, &msk->cb_flags);
	}
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void mptcp_timeout_timer(struct timer_list *t)
{
	struct sock *sk = from_timer(sk, t, sk_timer);

	mptcp_schedule_work(sk);
	sock_put(sk);
}

/* Find an idle subflow.  Return NULL if there is unacked data at tcp
 * level.
 *
 * A backup subflow is returned only if that is the only kind available.
 */
static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
{
	struct sock *backup = NULL, *pick = NULL;
	struct mptcp_subflow_context *subflow;
	int min_stale_count = INT_MAX;

	sock_owned_by_me((const struct sock *)msk);

	if (__mptcp_check_fallback(msk))
		return NULL;

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		if (!__mptcp_subflow_active(subflow))
			continue;

		/* still data outstanding at TCP level? skip this */
		if (!tcp_rtx_and_write_queues_empty(ssk)) {
			mptcp_pm_subflow_chk_stale(msk, ssk);
			min_stale_count = min_t(int, min_stale_count, subflow->stale_count);
			continue;
		}

		if (subflow->backup) {
			if (!backup)
				backup = ssk;
			continue;
		}

		if (!pick)
			pick = ssk;
	}

	if (pick)
		return pick;

	/* use backup only if there are no progresses anywhere */
	return min_stale_count > 1 ? backup : NULL;
}

static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
{
	if (msk->subflow) {
		iput(SOCK_INODE(msk->subflow));
		msk->subflow = NULL;
	}
}

bool __mptcp_retransmit_pending_data(struct sock *sk)
{
	struct mptcp_data_frag *cur, *rtx_head;
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (__mptcp_check_fallback(msk))
		return false;

	if (tcp_rtx_and_write_queues_empty(sk))
		return false;

	/* the closing socket has some data untransmitted and/or unacked:
	 * some data in the mptcp rtx queue has not really xmitted yet.
	 * keep it simple and re-inject the whole mptcp level rtx queue
	 */
	mptcp_data_lock(sk);
	__mptcp_clean_una_wakeup(sk);
	rtx_head = mptcp_rtx_head(sk);
	if (!rtx_head) {
		mptcp_data_unlock(sk);
		return false;
	}

	msk->recovery_snd_nxt = msk->snd_nxt;
	msk->recovery = true;
	mptcp_data_unlock(sk);

	msk->first_pending = rtx_head;
	msk->snd_burst = 0;

	/* be sure to clear the "sent status" on all re-injected fragments */
	list_for_each_entry(cur, &msk->rtx_queue, list) {
		if (!cur->already_sent)
			break;
		cur->already_sent = 0;
	}

	return true;
}

/* flags for __mptcp_close_ssk() */
#define MPTCP_CF_PUSH		BIT(1)
#define MPTCP_CF_FASTCLOSE	BIT(2)

/* subflow sockets can be either outgoing (connect) or incoming
 * (accept).
 *
 * Outgoing subflows use in-kernel sockets.
 * Incoming subflows do not have their own 'struct socket' allocated,
 * so we need to use tcp_close() after detaching them from the mptcp
 * parent socket.
 */
static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
			      struct mptcp_subflow_context *subflow,
			      unsigned int flags)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	bool need_push, dispose_it;

	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
	if (dispose_it)
		list_del(&subflow->node);

	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);

	if (flags & MPTCP_CF_FASTCLOSE) {
		/* be sure to force the tcp_disconnect() path,
		 * to generate the egress reset
		 */
		ssk->sk_lingertime = 0;
		sock_set_flag(ssk, SOCK_LINGER);
		subflow->send_fastclose = 1;
	}

	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
	if (!dispose_it) {
		tcp_disconnect(ssk, 0);
		msk->subflow->state = SS_UNCONNECTED;
		mptcp_subflow_ctx_reset(subflow);
		release_sock(ssk);

		goto out;
	}

	sock_orphan(ssk);
	subflow->disposable = 1;

	/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
	 * the ssk has been already destroyed, we just need to release the
	 * reference owned by msk;
	 */
	if (!inet_csk(ssk)->icsk_ulp_ops) {
		kfree_rcu(subflow, rcu);
	} else {
		/* otherwise tcp will dispose of the ssk and subflow ctx */
		if (ssk->sk_state == TCP_LISTEN) {
			tcp_set_state(ssk, TCP_CLOSE);
			mptcp_subflow_queue_clean(sk, ssk);
			inet_csk_listen_stop(ssk);
			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
		}
		__tcp_close(ssk, 0);

		/* close acquired an extra ref */
		__sock_put(ssk);
	}
	release_sock(ssk);

	sock_put(ssk);

	if (ssk == msk->first)
		msk->first = NULL;

out:
	if (ssk == msk->last_snd)
		msk->last_snd = NULL;

	if (need_push)
		__mptcp_push_pending(sk, 0);
}

void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
		     struct mptcp_subflow_context *subflow)
{
	if (sk->sk_state == TCP_ESTABLISHED)
		mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);

	/* subflow aborted before reaching the fully_established status
	 * attempt the creation of the next subflow
	 */
	mptcp_pm_subflow_check_next(mptcp_sk(sk), ssk, subflow);

	__mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH);
}

static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
{
	return 0;
}

static void __mptcp_close_subflow(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow, *tmp;

	might_sleep();

	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		if (inet_sk_state_load(ssk) != TCP_CLOSE)
			continue;

		/* 'subflow_data_ready' will re-sched once rx queue is empty */
		if (!skb_queue_empty_lockless(&ssk->sk_receive_queue))
			continue;

		mptcp_close_ssk((struct sock *)msk, ssk, subflow);
	}
}

static bool mptcp_check_close_timeout(const struct sock *sk)
{
	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
	struct mptcp_subflow_context *subflow;

	if (delta >= TCP_TIMEWAIT_LEN)
		return true;

	/* if all subflows are in closed status don't bother with additional
	 * timeout
	 */
	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
		if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
		    TCP_CLOSE)
			return false;
	}
	return true;
}

static void mptcp_check_fastclose(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow, *tmp;
	struct sock *sk = (struct sock *)msk;

	if (likely(!READ_ONCE(msk->rcv_fastclose)))
		return;

	mptcp_token_destroy(msk);

	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
		bool slow;

		slow = lock_sock_fast(tcp_sk);
		if (tcp_sk->sk_state != TCP_CLOSE) {
			tcp_send_active_reset(tcp_sk, GFP_ATOMIC);
			tcp_set_state(tcp_sk, TCP_CLOSE);
		}
		unlock_sock_fast(tcp_sk, slow);
	}

	/* Mirror the tcp_reset() error propagation */
	switch (sk->sk_state) {
	case TCP_SYN_SENT:
		sk->sk_err = ECONNREFUSED;
		break;
	case TCP_CLOSE_WAIT:
		sk->sk_err = EPIPE;
		break;
	case TCP_CLOSE:
		return;
	default:
		sk->sk_err = ECONNRESET;
	}

	inet_sk_state_store(sk, TCP_CLOSE);
	sk->sk_shutdown = SHUTDOWN_MASK;
	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);

	/* the calling mptcp_worker will properly destroy the socket */
	if (sock_flag(sk, SOCK_DEAD))
		return;

	sk->sk_state_change(sk);
	sk_error_report(sk);
}

static void __mptcp_retrans(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_sendmsg_info info = {};
	struct mptcp_data_frag *dfrag;
	size_t copied = 0;
	struct sock *ssk;
	int ret;

	mptcp_clean_una_wakeup(sk);

	/* first check ssk: need to kick "stale" logic */
	ssk = mptcp_subflow_get_retrans(msk);
	dfrag = mptcp_rtx_head(sk);
	if (!dfrag) {
		if (mptcp_data_fin_enabled(msk)) {
			struct inet_connection_sock *icsk = inet_csk(sk);

			icsk->icsk_retransmits++;
			mptcp_set_datafin_timeout(sk);
			mptcp_send_ack(msk);

			goto reset_timer;
		}

		if (!mptcp_send_head(sk))
			return;

		goto reset_timer;
	}

	if (!ssk)
		goto reset_timer;

	lock_sock(ssk);

	/* limit retransmission to the bytes already sent on some subflows */
	info.sent = 0;
	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
	while (info.sent < info.limit) {
		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
		if (ret <= 0)
			break;

		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
		copied += ret;
		info.sent += ret;
	}
	if (copied) {
		dfrag->already_sent = max(dfrag->already_sent, info.sent);
		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
			 info.size_goal);
		WRITE_ONCE(msk->allow_infinite_fallback, false);
	}

	release_sock(ssk);

reset_timer:
	mptcp_check_and_set_pending(sk);

	if (!mptcp_timer_pending(sk))
		mptcp_reset_timer(sk);
}

/* schedule the timeout timer for the relevant event: either close timeout
 * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
 */
void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
{
	struct sock *sk = (struct sock *)msk;
	unsigned long timeout, close_timeout;

	if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
		return;

	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;

	/* the close timeout takes precedence on the fail one, and here at least one of
	 * them is active
	 */
	timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;

	sk_reset_timer(sk, &sk->sk_timer, timeout);
}

static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
{
	struct sock *ssk = msk->first;
	bool slow;

	if (!ssk)
		return;

	pr_debug("MP_FAIL doesn't respond, reset the subflow");

	slow = lock_sock_fast(ssk);
	mptcp_subflow_reset(ssk);
	WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
	unlock_sock_fast(ssk, slow);

	mptcp_reset_timeout(msk, 0);
}

static void mptcp_do_fastclose(struct sock *sk)
{
	struct mptcp_subflow_context *subflow, *tmp;
	struct mptcp_sock *msk = mptcp_sk(sk);

	mptcp_for_each_subflow_safe(msk, subflow, tmp)
		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
				  subflow, MPTCP_CF_FASTCLOSE);
}

static void mptcp_worker(struct work_struct *work)
{
	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
	struct sock *sk = (struct sock *)msk;
	unsigned long fail_tout;
	int state;

	lock_sock(sk);
	state = sk->sk_state;
	if (unlikely(state == TCP_CLOSE))
		goto unlock;

	mptcp_check_data_fin_ack(sk);

	mptcp_check_fastclose(msk);

	mptcp_pm_nl_work(msk);

	if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
		mptcp_check_for_eof(msk);

	__mptcp_check_send_data_fin(sk);
	mptcp_check_data_fin(sk);

	/* There is no point in keeping around an orphaned sk timedout or
	 * closed, but we need the msk around to reply to incoming DATA_FIN,
	 * even if it is orphaned and in FIN_WAIT2 state
	 */
	if (sock_flag(sk, SOCK_DEAD)) {
		if (mptcp_check_close_timeout(sk)) {
			inet_sk_state_store(sk, TCP_CLOSE);
			mptcp_do_fastclose(sk);
		}
		if (sk->sk_state == TCP_CLOSE) {
			__mptcp_destroy_sock(sk);
			goto unlock;
		}
	}

	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
		__mptcp_close_subflow(msk);

	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
		__mptcp_retrans(sk);

	fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;
	if (fail_tout && time_after(jiffies, fail_tout))
		mptcp_mp_fail_no_response(msk);

unlock:
	release_sock(sk);
	sock_put(sk);
}

static int __mptcp_init_sock(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	INIT_LIST_HEAD(&msk->conn_list);
	INIT_LIST_HEAD(&msk->join_list);
	INIT_LIST_HEAD(&msk->rtx_queue);
	INIT_WORK(&msk->work, mptcp_worker);
	__skb_queue_head_init(&msk->receive_queue);
	msk->out_of_order_queue = RB_ROOT;
	msk->first_pending = NULL;
	msk->rmem_fwd_alloc = 0;
	WRITE_ONCE(msk->rmem_released, 0);
	msk->timer_ival = TCP_RTO_MIN;

	msk->first = NULL;
	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
	WRITE_ONCE(msk->allow_infinite_fallback, true);
	msk->recovery = false;

	mptcp_pm_data_init(msk);

	/* re-use the csk retrans timer for MPTCP-level retrans */
	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);

	return 0;
}

static void mptcp_ca_reset(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	tcp_assign_congestion_control(sk);
	strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);

	/* no need to keep a reference to the ops, the name will suffice */
	tcp_cleanup_congestion_control(sk);
	icsk->icsk_ca_ops = NULL;
}

static int mptcp_init_sock(struct sock *sk)
{
	struct net *net = sock_net(sk);
	int ret;

	ret = __mptcp_init_sock(sk);
	if (ret)
		return ret;

	if (!mptcp_is_enabled(net))
		return -ENOPROTOOPT;

	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
		return -ENOMEM;

	ret = __mptcp_socket_create(mptcp_sk(sk));
	if (ret)
		return ret;

	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);

	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
	 * propagate the correct value
	 */
	mptcp_ca_reset(sk);

	sk_sockets_allocated_inc(sk);
	sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
	sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);

	return 0;
}

static void __mptcp_clear_xmit(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_data_frag *dtmp, *dfrag;

	WRITE_ONCE(msk->first_pending, NULL);
	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
		dfrag_clear(sk, dfrag);
}

void mptcp_cancel_work(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (cancel_work_sync(&msk->work))
		__sock_put(sk);
}

void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
{
	lock_sock(ssk);

	switch (ssk->sk_state) {
	case TCP_LISTEN:
		if (!(how & RCV_SHUTDOWN))
			break;
		fallthrough;
	case TCP_SYN_SENT:
		tcp_disconnect(ssk, O_NONBLOCK);
		break;
	default:
		if (__mptcp_check_fallback(mptcp_sk(sk))) {
			pr_debug("Fallback");
			ssk->sk_shutdown |= how;
			tcp_shutdown(ssk, how);
		} else {
			pr_debug("Sending DATA_FIN on subflow %p", ssk);
			tcp_send_ack(ssk);
			if (!mptcp_timer_pending(sk))
				mptcp_reset_timer(sk);
		}
		break;
	}

	release_sock(ssk);
}

static const unsigned char new_state[16] = {
	/* current state:     new state:      action:	*/
	[0 /* (Invalid) */] = TCP_CLOSE,
	[TCP_ESTABLISHED]   = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
	[TCP_SYN_SENT]      = TCP_CLOSE,
	[TCP_SYN_RECV]      = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
	[TCP_FIN_WAIT1]     = TCP_FIN_WAIT1,
	[TCP_FIN_WAIT2]     = TCP_FIN_WAIT2,
	[TCP_TIME_WAIT]     = TCP_CLOSE,	/* should not happen ! */
	[TCP_CLOSE]         = TCP_CLOSE,
	[TCP_CLOSE_WAIT]    = TCP_LAST_ACK  | TCP_ACTION_FIN,
	[TCP_LAST_ACK]      = TCP_LAST_ACK,
	[TCP_LISTEN]        = TCP_CLOSE,
	[TCP_CLOSING]       = TCP_CLOSING,
	[TCP_NEW_SYN_RECV]  = TCP_CLOSE,	/* should not happen ! */
};

static int mptcp_close_state(struct sock *sk)
{
	int next = (int)new_state[sk->sk_state];
	int ns = next & TCP_STATE_MASK;

	inet_sk_state_store(sk, ns);

	return next & TCP_ACTION_FIN;
}

static void __mptcp_check_send_data_fin(struct sock *sk)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_sock *msk = mptcp_sk(sk);

	pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
		 msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
		 msk->snd_nxt, msk->write_seq);

	/* we still need to enqueue subflows or not really shutting down,
	 * skip this
	 */
	if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
	    mptcp_send_head(sk))
		return;

	WRITE_ONCE(msk->snd_nxt, msk->write_seq);

	/* fallback socket will not get data_fin/ack, can move to the next
	 * state now
	 */
	if (__mptcp_check_fallback(msk)) {
		WRITE_ONCE(msk->snd_una, msk->write_seq);
		if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
			inet_sk_state_store(sk, TCP_CLOSE);
			mptcp_close_wake_up(sk);
		} else if (sk->sk_state == TCP_FIN_WAIT1) {
			inet_sk_state_store(sk, TCP_FIN_WAIT2);
		}
	}

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);

		mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
	}
}

static void __mptcp_wr_shutdown(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
		 msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
		 !!mptcp_send_head(sk));

	/* will be ignored by fallback sockets */
	WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
	WRITE_ONCE(msk->snd_data_fin_enable, 1);

	__mptcp_check_send_data_fin(sk);
}

static void __mptcp_destroy_sock(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	pr_debug("msk=%p", msk);

	might_sleep();

	mptcp_stop_timer(sk);
	sk_stop_timer(sk, &sk->sk_timer);
	msk->pm.status = 0;

	sk->sk_prot->destroy(sk);

	WARN_ON_ONCE(msk->rmem_fwd_alloc);
	WARN_ON_ONCE(msk->rmem_released);
	sk_stream_kill_queues(sk);
	xfrm_sk_free_policy(sk);

	sk_refcnt_debug_release(sk);
	sock_put(sk);
}

static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
{
	/* Concurrent splices from sk_receive_queue into receive_queue will
	 * always show at least one non-empty queue when checked in this order.
	 */
	if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&
	    skb_queue_empty_lockless(&msk->receive_queue))
		return 0;

	return EPOLLIN | EPOLLRDNORM;
}

bool __mptcp_close(struct sock *sk, long timeout)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_sock *msk = mptcp_sk(sk);
	bool do_cancel_work = false;

	sk->sk_shutdown = SHUTDOWN_MASK;

	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
		inet_sk_state_store(sk, TCP_CLOSE);
		goto cleanup;
	}

	if (mptcp_check_readable(msk)) {
		/* the msk has read data, do the MPTCP equivalent of TCP reset */
		inet_sk_state_store(sk, TCP_CLOSE);
		mptcp_do_fastclose(sk);
	} else if (mptcp_close_state(sk)) {
		__mptcp_wr_shutdown(sk);
	}

	sk_stream_wait_close(sk, timeout);

cleanup:
	/* orphan all the subflows */
	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast_nested(ssk);

		/* since the close timeout takes precedence on the fail one,
		 * cancel the latter
		 */
		if (ssk == msk->first)
			subflow->fail_tout = 0;

		/* detach from the parent socket, but allow data_ready to
		 * push incoming data into the mptcp stack, to properly ack it
		 */
		ssk->sk_socket = NULL;
		ssk->sk_wq = NULL;
		unlock_sock_fast(ssk, slow);
	}
	sock_orphan(sk);

	sock_hold(sk);
	pr_debug("msk=%p state=%d", sk, sk->sk_state);
	if (msk->token)
		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);

	if (sk->sk_state == TCP_CLOSE) {
		__mptcp_destroy_sock(sk);
		do_cancel_work = true;
	} else {
		mptcp_reset_timeout(msk, 0);
	}

	return do_cancel_work;
}

static void mptcp_close(struct sock *sk, long timeout)
{
	bool do_cancel_work;

	lock_sock(sk);

	do_cancel_work = __mptcp_close(sk, timeout);
	release_sock(sk);
	if (do_cancel_work)
		mptcp_cancel_work(sk);

	sock_put(sk);
}

void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
	struct ipv6_pinfo *msk6 = inet6_sk(msk);

	msk->sk_v6_daddr = ssk->sk_v6_daddr;
	msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr;

	if (msk6 && ssk6) {
		msk6->saddr = ssk6->saddr;
		msk6->flow_label = ssk6->flow_label;
	}
#endif

	inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num;
	inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport;
	inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport;
	inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr;
	inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr;
	inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr;
}

static int mptcp_disconnect(struct sock *sk, int flags)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	/* We are on the fastopen error path. We can't call straight into the
	 * subflows cleanup code due to lock nesting (we are already under
	 * msk->firstsocket lock). Do nothing and leave the cleanup to the
	 * caller.
	 */
	if (msk->fastopening)
		return 0;

	inet_sk_state_store(sk, TCP_CLOSE);

	mptcp_stop_timer(sk);
	sk_stop_timer(sk, &sk->sk_timer);

	if (msk->token)
		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);

	/* msk->subflow is still intact, the following will not free the first
	 * subflow
	 */
	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
	msk->last_snd = NULL;
	WRITE_ONCE(msk->flags, 0);
	msk->cb_flags = 0;
	msk->push_pending = 0;
	msk->recovery = false;
	msk->can_ack = false;
	msk->fully_established = false;
	msk->rcv_data_fin = false;
	msk->snd_data_fin_enable = false;
	msk->rcv_fastclose = false;
	msk->use_64bit_ack = false;
	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
	mptcp_pm_data_reset(msk);
	mptcp_ca_reset(sk);

	sk->sk_shutdown = 0;
	sk_error_report(sk);
	return 0;
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
{
	unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo);

	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
#endif

struct sock *mptcp_sk_clone(const struct sock *sk,
			    const struct mptcp_options_received *mp_opt,
			    struct request_sock *req)
{
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
	struct mptcp_sock *msk;

	if (!nsk)
		return NULL;

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (nsk->sk_family == AF_INET6)
		inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif

	__mptcp_init_sock(nsk);

	msk = mptcp_sk(nsk);
	msk->local_key = subflow_req->local_key;
	msk->token = subflow_req->token;
	msk->subflow = NULL;
	WRITE_ONCE(msk->fully_established, false);
	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
		WRITE_ONCE(msk->csum_enabled, true);

	msk->write_seq = subflow_req->idsn + 1;
	msk->snd_nxt = msk->write_seq;
	msk->snd_una = msk->write_seq;
	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;

	sock_reset_flag(nsk, SOCK_RCU_FREE);
	/* will be fully established after successful MPC subflow creation */
	inet_sk_state_store(nsk, TCP_SYN_RECV);

	security_inet_csk_clone(nsk, req);
	bh_unlock_sock(nsk);

	/* keep a single reference */
	__sock_put(nsk);
	return nsk;
}

void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
{
	const struct tcp_sock *tp = tcp_sk(ssk);

	msk->rcvq_space.copied = 0;
	msk->rcvq_space.rtt_us = 0;

	msk->rcvq_space.time = tp->tcp_mstamp;

	/* initial rcv_space offering made to peer */
	msk->rcvq_space.space = min_t(u32, tp->rcv_wnd,
				      TCP_INIT_CWND * tp->advmss);
	if (msk->rcvq_space.space == 0)
		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;

	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}

static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
				 bool kern)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct socket *listener;
	struct sock *newsk;

	listener = __mptcp_nmpc_socket(msk);
	if (WARN_ON_ONCE(!listener)) {
		*err = -EINVAL;
		return NULL;
	}

	pr_debug("msk=%p, listener=%p", msk, mptcp_subflow_ctx(listener->sk));
	newsk = inet_csk_accept(listener->sk, flags, err, kern);
	if (!newsk)
		return NULL;

	pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk));
	if (sk_is_mptcp(newsk)) {
		struct mptcp_subflow_context *subflow;
		struct sock *new_mptcp_sock;

		subflow = mptcp_subflow_ctx(newsk);
		new_mptcp_sock = subflow->conn;

		/* is_mptcp should be false if subflow->conn is missing, see
		 * subflow_syn_recv_sock()
		 */
		if (WARN_ON_ONCE(!new_mptcp_sock)) {
			tcp_sk(newsk)->is_mptcp = 0;
			goto out;
		}

		/* acquire the 2nd reference for the owning socket */
		sock_hold(new_mptcp_sock);
		newsk = new_mptcp_sock;
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
	} else {
		MPTCP_INC_STATS(sock_net(sk),
				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
	}

out:
	newsk->sk_kern_sock = kern;
	return newsk;
}

void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
{
	struct mptcp_subflow_context *subflow, *tmp;
	struct sock *sk = (struct sock *)msk;

	__mptcp_clear_xmit(sk);

	/* join list will be eventually flushed (with rst) at sock lock release time */
	mptcp_for_each_subflow_safe(msk, subflow, tmp)
		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags);

	/* move to sk_receive_queue, sk_stream_kill_queues will purge it */
	mptcp_data_lock(sk);
	skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_receive_queue);
	skb_rbtree_purge(&msk->out_of_order_queue);
	mptcp_data_unlock(sk);

	/* move all the rx fwd alloc into the sk_mem_reclaim_final in
	 * inet_sock_destruct() will dispose it
	 */
	sk->sk_forward_alloc += msk->rmem_fwd_alloc;
	msk->rmem_fwd_alloc = 0;
	mptcp_token_destroy(msk);
	mptcp_pm_free_anno_list(msk);
	mptcp_free_local_addr_list(msk);
}

static void mptcp_destroy(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	/* clears msk->subflow, allowing the following to close
	 * even the initial subflow
	 */
	mptcp_dispose_initial_subflow(msk);
	mptcp_destroy_common(msk, 0);
	sk_sockets_allocated_dec(sk);
}

void __mptcp_data_acked(struct sock *sk)
{
	if (!sock_owned_by_user(sk))
		__mptcp_clean_una(sk);
	else
		__set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags);

	if (mptcp_pending_data_fin_ack(sk))
		mptcp_schedule_work(sk);
}

void __mptcp_check_push(struct sock *sk, struct sock *ssk)
{
	if (!mptcp_send_head(sk))
		return;

	if (!sock_owned_by_user(sk))
		__mptcp_subflow_push_pending(sk, ssk, false);
	else
		__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
}

#define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \
				      BIT(MPTCP_RETRANSMIT) | \
				      BIT(MPTCP_FLUSH_JOIN_LIST))

/* processes deferred events and flush wmem */
static void mptcp_release_cb(struct sock *sk)
	__must_hold(&sk->sk_lock.slock)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	for (;;) {
		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
				      msk->push_pending;
		if (!flags)
			break;

		/* the following actions acquire the subflow socket lock
		 *
		 * 1) can't be invoked in atomic scope
		 * 2) must avoid ABBA deadlock with msk socket spinlock: the RX
		 *    datapath acquires the msk socket spinlock while helding
		 *    the subflow socket lock
		 */
		msk->push_pending = 0;
		msk->cb_flags &= ~flags;
		spin_unlock_bh(&sk->sk_lock.slock);
		if (flags & BIT(MPTCP_FLUSH_JOIN_LIST))
			__mptcp_flush_join_list(sk);
		if (flags & BIT(MPTCP_PUSH_PENDING))
			__mptcp_push_pending(sk, 0);
		if (flags & BIT(MPTCP_RETRANSMIT))
			__mptcp_retrans(sk);

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

	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
		__mptcp_clean_una_wakeup(sk);
	if (unlikely(&msk->cb_flags)) {
		/* be sure to set the current sk state before tacking actions
		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
		 */
		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
			__mptcp_set_connected(sk);
		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
			__mptcp_error_report(sk);
		if (__test_and_clear_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags))
			msk->last_snd = NULL;
	}

	__mptcp_update_rmem(sk);
}

/* MP_JOIN client subflow must wait for 4th ack before sending any data:
 * TCP can't schedule delack timer before the subflow is fully established.
 * MPTCP uses the delack timer to do 3rd ack retransmissions
 */
static void schedule_3rdack_retransmission(struct sock *ssk)
{
	struct inet_connection_sock *icsk = inet_csk(ssk);
	struct tcp_sock *tp = tcp_sk(ssk);
	unsigned long timeout;

	if (mptcp_subflow_ctx(ssk)->fully_established)
		return;

	/* reschedule with a timeout above RTT, as we must look only for drop */
	if (tp->srtt_us)
		timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1));
	else
		timeout = TCP_TIMEOUT_INIT;
	timeout += jiffies;

	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
	icsk->icsk_ack.timeout = timeout;
	sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
}

void mptcp_subflow_process_delegated(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct sock *sk = subflow->conn;

	if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
		mptcp_data_lock(sk);
		if (!sock_owned_by_user(sk))
			__mptcp_subflow_push_pending(sk, ssk, true);
		else
			__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
		mptcp_data_unlock(sk);
		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND);
	}
	if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) {
		schedule_3rdack_retransmission(ssk);
		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK);
	}
}

static int mptcp_hash(struct sock *sk)
{
	/* should never be called,
	 * we hash the TCP subflows not the master socket
	 */
	WARN_ON_ONCE(1);
	return 0;
}

static void mptcp_unhash(struct sock *sk)
{
	/* called from sk_common_release(), but nothing to do here */
}

static int mptcp_get_port(struct sock *sk, unsigned short snum)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct socket *ssock;

	ssock = __mptcp_nmpc_socket(msk);
	pr_debug("msk=%p, subflow=%p", msk, ssock);
	if (WARN_ON_ONCE(!ssock))
		return -EINVAL;

	return inet_csk_get_port(ssock->sk, snum);
}

void mptcp_finish_connect(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_sock *msk;
	struct sock *sk;

	subflow = mptcp_subflow_ctx(ssk);
	sk = subflow->conn;
	msk = mptcp_sk(sk);

	pr_debug("msk=%p, token=%u", sk, subflow->token);

	subflow->map_seq = subflow->iasn;
	subflow->map_subflow_seq = 1;

	/* the socket is not connected yet, no msk/subflow ops can access/race
	 * accessing the field below
	 */
	WRITE_ONCE(msk->local_key, subflow->local_key);
	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
	WRITE_ONCE(msk->snd_una, msk->write_seq);

	mptcp_pm_new_connection(msk, ssk, 0);

	mptcp_rcv_space_init(msk, ssk);
}

void mptcp_sock_graft(struct sock *sk, struct socket *parent)
{
	write_lock_bh(&sk->sk_callback_lock);
	rcu_assign_pointer(sk->sk_wq, &parent->wq);
	sk_set_socket(sk, parent);
	sk->sk_uid = SOCK_INODE(parent)->i_uid;
	write_unlock_bh(&sk->sk_callback_lock);
}

bool mptcp_finish_join(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
	struct sock *parent = (void *)msk;
	bool ret = true;

	pr_debug("msk=%p, subflow=%p", msk, subflow);

	/* mptcp socket already closing? */
	if (!mptcp_is_fully_established(parent)) {
		subflow->reset_reason = MPTCP_RST_EMPTCP;
		return false;
	}

	if (!list_empty(&subflow->node))
		goto out;

	if (!mptcp_pm_allow_new_subflow(msk))
		goto err_prohibited;

	/* active connections are already on conn_list.
	 * If we can't acquire msk socket lock here, let the release callback
	 * handle it
	 */
	mptcp_data_lock(parent);
	if (!sock_owned_by_user(parent)) {
		ret = __mptcp_finish_join(msk, ssk);
		if (ret) {
			sock_hold(ssk);
			list_add_tail(&subflow->node, &msk->conn_list);
		}
	} else {
		sock_hold(ssk);
		list_add_tail(&subflow->node, &msk->join_list);
		__set_bit(MPTCP_FLUSH_JOIN_LIST, &msk->cb_flags);
	}
	mptcp_data_unlock(parent);

	if (!ret) {
err_prohibited:
		subflow->reset_reason = MPTCP_RST_EPROHIBIT;
		return false;
	}

	subflow->map_seq = READ_ONCE(msk->ack_seq);
	WRITE_ONCE(msk->allow_infinite_fallback, false);

out:
	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
	return true;
}

static void mptcp_shutdown(struct sock *sk, int how)
{
	pr_debug("sk=%p, how=%d", sk, how);

	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
		__mptcp_wr_shutdown(sk);
}

static int mptcp_forward_alloc_get(const struct sock *sk)
{
	return sk->sk_forward_alloc + mptcp_sk(sk)->rmem_fwd_alloc;
}

static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)
{
	const struct sock *sk = (void *)msk;
	u64 delta;

	if (sk->sk_state == TCP_LISTEN)
		return -EINVAL;

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
		return 0;

	delta = msk->write_seq - v;
	if (__mptcp_check_fallback(msk) && msk->first) {
		struct tcp_sock *tp = tcp_sk(msk->first);

		/* the first subflow is disconnected after close - see
		 * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq
		 * so ignore that status, too.
		 */
		if (!((1 << msk->first->sk_state) &
		      (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)))
			delta += READ_ONCE(tp->write_seq) - tp->snd_una;
	}
	if (delta > INT_MAX)
		delta = INT_MAX;

	return (int)delta;
}

static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	bool slow;
	int answ;

	switch (cmd) {
	case SIOCINQ:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		lock_sock(sk);
		__mptcp_move_skbs(msk);
		answ = mptcp_inq_hint(sk);
		release_sock(sk);
		break;
	case SIOCOUTQ:
		slow = lock_sock_fast(sk);
		answ = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una));
		unlock_sock_fast(sk, slow);
		break;
	case SIOCOUTQNSD:
		slow = lock_sock_fast(sk);
		answ = mptcp_ioctl_outq(msk, msk->snd_nxt);
		unlock_sock_fast(sk, slow);
		break;
	default:
		return -ENOIOCTLCMD;
	}

	return put_user(answ, (int __user *)arg);
}

static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
					 struct mptcp_subflow_context *subflow)
{
	subflow->request_mptcp = 0;
	__mptcp_do_fallback(msk);
}

static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct socket *ssock;
	int err = -EINVAL;

	ssock = __mptcp_nmpc_socket(msk);
	if (!ssock)
		return -EINVAL;

	mptcp_token_destroy(msk);
	inet_sk_state_store(sk, TCP_SYN_SENT);
	subflow = mptcp_subflow_ctx(ssock->sk);
#ifdef CONFIG_TCP_MD5SIG
	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
	 * TCP option space.
	 */
	if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
		mptcp_subflow_early_fallback(msk, subflow);
#endif
	if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) {
		MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT);
		mptcp_subflow_early_fallback(msk, subflow);
	}
	if (likely(!__mptcp_check_fallback(msk)))
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);

	/* if reaching here via the fastopen/sendmsg path, the caller already
	 * acquired the subflow socket lock, too.
	 */
	if (msk->fastopening)
		err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
	else
		err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
	inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;

	/* on successful connect, the msk state will be moved to established by
	 * subflow_finish_connect()
	 */
	if (unlikely(err && err != -EINPROGRESS)) {
		inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
		return err;
	}

	mptcp_copy_inaddrs(sk, ssock->sk);

	/* unblocking connect, mptcp-level inet_stream_connect will error out
	 * without changing the socket state, update it here.
	 */
	if (err == -EINPROGRESS)
		sk->sk_socket->state = ssock->state;
	return err;
}

static struct proto mptcp_prot = {
	.name		= "MPTCP",
	.owner		= THIS_MODULE,
	.init		= mptcp_init_sock,
	.connect	= mptcp_connect,
	.disconnect	= mptcp_disconnect,
	.close		= mptcp_close,
	.accept		= mptcp_accept,
	.setsockopt	= mptcp_setsockopt,
	.getsockopt	= mptcp_getsockopt,
	.shutdown	= mptcp_shutdown,
	.destroy	= mptcp_destroy,
	.sendmsg	= mptcp_sendmsg,
	.ioctl		= mptcp_ioctl,
	.recvmsg	= mptcp_recvmsg,
	.release_cb	= mptcp_release_cb,
	.hash		= mptcp_hash,
	.unhash		= mptcp_unhash,
	.get_port	= mptcp_get_port,
	.forward_alloc_get	= mptcp_forward_alloc_get,
	.sockets_allocated	= &mptcp_sockets_allocated,

	.memory_allocated	= &tcp_memory_allocated,
	.per_cpu_fw_alloc	= &tcp_memory_per_cpu_fw_alloc,

	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
	.sysctl_mem	= sysctl_tcp_mem,
	.obj_size	= sizeof(struct mptcp_sock),
	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
	.no_autobind	= true,
};

static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct mptcp_sock *msk = mptcp_sk(sock->sk);
	struct socket *ssock;
	int err;

	lock_sock(sock->sk);
	ssock = __mptcp_nmpc_socket(msk);
	if (!ssock) {
		err = -EINVAL;
		goto unlock;
	}

	err = ssock->ops->bind(ssock, uaddr, addr_len);
	if (!err)
		mptcp_copy_inaddrs(sock->sk, ssock->sk);

unlock:
	release_sock(sock->sk);
	return err;
}

static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
				int addr_len, int flags)
{
	int ret;

	lock_sock(sock->sk);
	mptcp_sk(sock->sk)->connect_flags = flags;
	ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
	release_sock(sock->sk);
	return ret;
}

static int mptcp_listen(struct socket *sock, int backlog)
{
	struct mptcp_sock *msk = mptcp_sk(sock->sk);
	struct socket *ssock;
	int err;

	pr_debug("msk=%p", msk);

	lock_sock(sock->sk);
	ssock = __mptcp_nmpc_socket(msk);
	if (!ssock) {
		err = -EINVAL;
		goto unlock;
	}

	mptcp_token_destroy(msk);
	inet_sk_state_store(sock->sk, TCP_LISTEN);
	sock_set_flag(sock->sk, SOCK_RCU_FREE);

	err = ssock->ops->listen(ssock, backlog);
	inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
	if (!err)
		mptcp_copy_inaddrs(sock->sk, ssock->sk);

	mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED);

unlock:
	release_sock(sock->sk);
	return err;
}

static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
			       int flags, bool kern)
{
	struct mptcp_sock *msk = mptcp_sk(sock->sk);
	struct socket *ssock;
	int err;

	pr_debug("msk=%p", msk);

	ssock = __mptcp_nmpc_socket(msk);
	if (!ssock)
		return -EINVAL;

	err = ssock->ops->accept(sock, newsock, flags, kern);
	if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
		struct mptcp_sock *msk = mptcp_sk(newsock->sk);
		struct mptcp_subflow_context *subflow;
		struct sock *newsk = newsock->sk;

		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);

		lock_sock(newsk);

		/* PM/worker can now acquire the first subflow socket
		 * lock without racing with listener queue cleanup,
		 * we can notify it, if needed.
		 *
		 * Even if remote has reset the initial subflow by now
		 * the refcnt is still at least one.
		 */
		subflow = mptcp_subflow_ctx(msk->first);
		list_add(&subflow->node, &msk->conn_list);
		sock_hold(msk->first);
		if (mptcp_is_fully_established(newsk))
			mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL);

		mptcp_rcv_space_init(msk, msk->first);
		mptcp_propagate_sndbuf(newsk, msk->first);

		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
		 * This is needed so NOSPACE flag can be set from tcp stack.
		 */
		mptcp_for_each_subflow(msk, subflow) {
			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

			if (!ssk->sk_socket)
				mptcp_sock_graft(ssk, newsock);
		}
		release_sock(newsk);
	}

	return err;
}

static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
{
	struct sock *sk = (struct sock *)msk;

	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
		return EPOLLOUT | EPOLLWRNORM;

	if (sk_stream_is_writeable(sk))
		return EPOLLOUT | EPOLLWRNORM;

	mptcp_set_nospace(sk);
	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
	if (sk_stream_is_writeable(sk))
		return EPOLLOUT | EPOLLWRNORM;

	return 0;
}

static __poll_t mptcp_poll(struct file *file, struct socket *sock,
			   struct poll_table_struct *wait)
{
	struct sock *sk = sock->sk;
	struct mptcp_sock *msk;
	__poll_t mask = 0;
	int state;

	msk = mptcp_sk(sk);
	sock_poll_wait(file, sock, wait);

	state = inet_sk_state_load(sk);
	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
	if (state == TCP_LISTEN) {
		if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk))
			return 0;

		return inet_csk_listen_poll(msk->subflow->sk);
	}

	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
		mask |= mptcp_check_readable(msk);
		mask |= mptcp_check_writeable(msk);
	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
		/* cf tcp_poll() note about TFO */
		mask |= EPOLLOUT | EPOLLWRNORM;
	}
	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
		mask |= EPOLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;

	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
	smp_rmb();
	if (sk->sk_err)
		mask |= EPOLLERR;

	return mask;
}

static const struct proto_ops mptcp_stream_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = mptcp_bind,
	.connect	   = mptcp_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = mptcp_stream_accept,
	.getname	   = inet_getname,
	.poll		   = mptcp_poll,
	.ioctl		   = inet_ioctl,
	.gettstamp	   = sock_gettstamp,
	.listen		   = mptcp_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
};

static struct inet_protosw mptcp_protosw = {
	.type		= SOCK_STREAM,
	.protocol	= IPPROTO_MPTCP,
	.prot		= &mptcp_prot,
	.ops		= &mptcp_stream_ops,
	.flags		= INET_PROTOSW_ICSK,
};

static int mptcp_napi_poll(struct napi_struct *napi, int budget)
{
	struct mptcp_delegated_action *delegated;
	struct mptcp_subflow_context *subflow;
	int work_done = 0;

	delegated = container_of(napi, struct mptcp_delegated_action, napi);
	while ((subflow = mptcp_subflow_delegated_next(delegated)) != NULL) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		bh_lock_sock_nested(ssk);
		if (!sock_owned_by_user(ssk) &&
		    mptcp_subflow_has_delegated_action(subflow))
			mptcp_subflow_process_delegated(ssk);
		/* ... elsewhere tcp_release_cb_override already processed
		 * the action or will do at next release_sock().
		 * In both case must dequeue the subflow here - on the same
		 * CPU that scheduled it.
		 */
		bh_unlock_sock(ssk);
		sock_put(ssk);

		if (++work_done == budget)
			return budget;
	}

	/* always provide a 0 'work_done' argument, so that napi_complete_done
	 * will not try accessing the NULL napi->dev ptr
	 */
	napi_complete_done(napi, 0);
	return work_done;
}

void __init mptcp_proto_init(void)
{
	struct mptcp_delegated_action *delegated;
	int cpu;

	mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo;

	if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL))
		panic("Failed to allocate MPTCP pcpu counter\n");

	init_dummy_netdev(&mptcp_napi_dev);
	for_each_possible_cpu(cpu) {
		delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu);
		INIT_LIST_HEAD(&delegated->head);
		netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi,
				  mptcp_napi_poll);
		napi_enable(&delegated->napi);
	}

	mptcp_subflow_init();
	mptcp_pm_init();
	mptcp_token_init();

	if (proto_register(&mptcp_prot, 1) != 0)
		panic("Failed to register MPTCP proto.\n");

	inet_register_protosw(&mptcp_protosw);

	BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb));
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static const struct proto_ops mptcp_v6_stream_ops = {
	.family		   = PF_INET6,
	.owner		   = THIS_MODULE,
	.release	   = inet6_release,
	.bind		   = mptcp_bind,
	.connect	   = mptcp_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = mptcp_stream_accept,
	.getname	   = inet6_getname,
	.poll		   = mptcp_poll,
	.ioctl		   = inet6_ioctl,
	.gettstamp	   = sock_gettstamp,
	.listen		   = mptcp_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet6_sendmsg,
	.recvmsg	   = inet6_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
#ifdef CONFIG_COMPAT
	.compat_ioctl	   = inet6_compat_ioctl,
#endif
};

static struct proto mptcp_v6_prot;

static struct inet_protosw mptcp_v6_protosw = {
	.type		= SOCK_STREAM,
	.protocol	= IPPROTO_MPTCP,
	.prot		= &mptcp_v6_prot,
	.ops		= &mptcp_v6_stream_ops,
	.flags		= INET_PROTOSW_ICSK,
};

int __init mptcp_proto_v6_init(void)
{
	int err;

	mptcp_v6_prot = mptcp_prot;
	strcpy(mptcp_v6_prot.name, "MPTCPv6");
	mptcp_v6_prot.slab = NULL;
	mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock);

	err = proto_register(&mptcp_v6_prot, 1);
	if (err)
		return err;

	err = inet6_register_protosw(&mptcp_v6_protosw);
	if (err)
		proto_unregister(&mptcp_v6_prot);

	return err;
}
#endif