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
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Florian La Roche, <flla@stud.uni-sb.de>
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
* Linus Torvalds, <torvalds@cs.helsinki.fi>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Matthew Dillon, <dillon@apollo.west.oic.com>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Jorge Cwik, <jorge@laser.satlink.net>
*/
/*
* Changes: Pedro Roque : Retransmit queue handled by TCP.
* : Fragmentation on mtu decrease
* : Segment collapse on retransmit
* : AF independence
*
* Linus Torvalds : send_delayed_ack
* David S. Miller : Charge memory using the right skb
* during syn/ack processing.
* David S. Miller : Output engine completely rewritten.
* Andrea Arcangeli: SYNACK carry ts_recent in tsecr.
* Cacophonix Gaul : draft-minshall-nagle-01
* J Hadi Salim : ECN support
*
*/
#define pr_fmt(fmt) "TCP: " fmt
#include <net/tcp.h>
#include <net/mptcp.h>
#include <linux/compiler.h>
#include <linux/gfp.h>
#include <linux/module.h>
#include <linux/static_key.h>
#include <trace/events/tcp.h>
/* Refresh clocks of a TCP socket,
* ensuring monotically increasing values.
*/
void tcp_mstamp_refresh(struct tcp_sock *tp)
{
u64 val = tcp_clock_ns();
tp->tcp_clock_cache = val;
tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC);
}
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
/* Account for new data that has been sent to the network. */
static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned int prior_packets = tp->packets_out;
WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);
__skb_unlink(skb, &sk->sk_write_queue);
tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
if (tp->highest_sack == NULL)
tp->highest_sack = skb;
tp->packets_out += tcp_skb_pcount(skb);
if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
tcp_skb_pcount(skb));
tcp_check_space(sk);
}
/* SND.NXT, if window was not shrunk or the amount of shrunk was less than one
* window scaling factor due to loss of precision.
* If window has been shrunk, what should we make? It is not clear at all.
* Using SND.UNA we will fail to open window, SND.NXT is out of window. :-(
* Anything in between SND.UNA...SND.UNA+SND.WND also can be already
* invalid. OK, let's make this for now:
*/
static inline __u32 tcp_acceptable_seq(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
if (!before(tcp_wnd_end(tp), tp->snd_nxt) ||
(tp->rx_opt.wscale_ok &&
((tp->snd_nxt - tcp_wnd_end(tp)) < (1 << tp->rx_opt.rcv_wscale))))
return tp->snd_nxt;
else
return tcp_wnd_end(tp);
}
/* Calculate mss to advertise in SYN segment.
* RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that:
*
* 1. It is independent of path mtu.
* 2. Ideally, it is maximal possible segment size i.e. 65535-40.
* 3. For IPv4 it is reasonable to calculate it from maximal MTU of
* attached devices, because some buggy hosts are confused by
* large MSS.
* 4. We do not make 3, we advertise MSS, calculated from first
* hop device mtu, but allow to raise it to ip_rt_min_advmss.
* This may be overridden via information stored in routing table.
* 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible,
* probably even Jumbo".
*/
static __u16 tcp_advertise_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct dst_entry *dst = __sk_dst_get(sk);
int mss = tp->advmss;
if (dst) {
unsigned int metric = dst_metric_advmss(dst);
if (metric < mss) {
mss = metric;
tp->advmss = mss;
}
}
return (__u16)mss;
}
/* RFC2861. Reset CWND after idle period longer RTO to "restart window".
* This is the first part of cwnd validation mechanism.
*/
void tcp_cwnd_restart(struct sock *sk, s32 delta)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
u32 cwnd = tcp_snd_cwnd(tp);
tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
tp->snd_ssthresh = tcp_current_ssthresh(sk);
restart_cwnd = min(restart_cwnd, cwnd);
while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
cwnd >>= 1;
tcp_snd_cwnd_set(tp, max(cwnd, restart_cwnd));
tp->snd_cwnd_stamp = tcp_jiffies32;
tp->snd_cwnd_used = 0;
}
/* Congestion state accounting after a packet has been sent. */
static void tcp_event_data_sent(struct tcp_sock *tp,
struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_jiffies32;
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
tp->lsndtime = now;
/* If it is a reply for ato after last received
* packet, enter pingpong mode.
*/
if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
u32 rcv_nxt)
{
struct tcp_sock *tp = tcp_sk(sk);
if (unlikely(tp->compressed_ack)) {
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
tp->compressed_ack);
tp->compressed_ack = 0;
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
}
if (unlikely(rcv_nxt != tp->rcv_nxt))
return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
/* Determine a window scaling and initial window to offer.
* Based on the assumption that the given amount of space
* will be offered. Store the results in the tp structure.
* NOTE: for smooth operation initial space offering should
* be a multiple of mss if possible. We assume here that mss >= 1.
* This MUST be enforced by all callers.
*/
void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
__u32 *rcv_wnd, __u32 *window_clamp,
int wscale_ok, __u8 *rcv_wscale,
__u32 init_rcv_wnd)
{
unsigned int space = (__space < 0 ? 0 : __space);
/* If no clamp set the clamp to the max possible scaled window */
if (*window_clamp == 0)
(*window_clamp) = (U16_MAX << TCP_MAX_WSCALE);
space = min(*window_clamp, space);
/* Quantize space offering to a multiple of mss if possible. */
if (space > mss)
space = rounddown(space, mss);
/* NOTE: offering an initial window larger than 32767
* will break some buggy TCP stacks. If the admin tells us
* it is likely we could be speaking with such a buggy stack
* we will truncate our initial window offering to 32K-1
* unless the remote has sent us a window scaling option,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
*/
if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = min_t(u32, space, U16_MAX);
if (init_rcv_wnd)
*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
0, TCP_MAX_WSCALE);
}
/* Set the clamp no higher than max representable value */
(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
}
EXPORT_SYMBOL(tcp_select_initial_window);
/* Chose a new window to advertise, update state in tcp_sock for the
* socket, and return result with RFC1323 scaling applied. The return
* value can be stuffed directly into th->window for an outgoing
* frame.
*/
static u16 tcp_select_window(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 old_win = tp->rcv_wnd;
u32 cur_win = tcp_receive_window(tp);
u32 new_win = __tcp_select_window(sk);
/* Never shrink the offered window */
if (new_win < cur_win) {
/* Danger Will Robinson!
* Don't update rcv_wup/rcv_wnd here or else
* we will not be able to advertise a zero
* window in time. --DaveM
*
* Relax Will Robinson.
*/
if (new_win == 0)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPWANTZEROWINDOWADV);
new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
}
tp->rcv_wnd = new_win;
tp->rcv_wup = tp->rcv_nxt;
/* Make sure we do not exceed the maximum possible
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale &&
sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
/* RFC1323 scaling applied */
new_win >>= tp->rx_opt.rcv_wscale;
/* If we advertise zero window, disable fast path. */
if (new_win == 0) {
tp->pred_flags = 0;
if (old_win)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPTOZEROWINDOWADV);
} else if (old_win == 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
}
return new_win;
}
/* Packet ECN state for a SYN-ACK */
static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
if (!(tp->ecn_flags & TCP_ECN_OK))
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
else if (tcp_ca_needs_ecn(sk) ||
tcp_bpf_ca_needs_ecn(sk))
INET_ECN_xmit(sk);
}
/* Packet ECN state for a SYN. */
static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
if (!use_ecn) {
const struct dst_entry *dst = __sk_dst_get(sk);
if (dst && dst_feature(dst, RTAX_FEATURE_ECN))
use_ecn = true;
}
tp->ecn_flags = 0;
if (use_ecn) {
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
tp->ecn_flags = TCP_ECN_OK;
if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn)
INET_ECN_xmit(sk);
}
}
static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
{
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
/* tp->ecn_flags are cleared at a later point in time when
* SYN ACK is ultimatively being received.
*/
TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
}
static void
tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
{
if (inet_rsk(req)->ecn_ok)
th->ece = 1;
}
/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
* be sent.
*/
static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, int tcp_header_len)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->ecn_flags & TCP_ECN_OK) {
/* Not-retransmitted data segment: set ECT and inject CWR. */
if (skb->len != tcp_header_len &&
!before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {
INET_ECN_xmit(sk);
if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) {
tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
th->cwr = 1;
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
}
} else if (!tcp_ca_needs_ecn(sk)) {
/* ACK or retransmitted segment: clear ECT|CE */
INET_ECN_dontxmit(sk);
}
if (tp->ecn_flags & TCP_ECN_DEMAND_CWR)
th->ece = 1;
}
}
/* Constructs common control bits of non-data skb. If SYN/FIN is present,
* auto increment end seqno.
*/
static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
{
skb->ip_summed = CHECKSUM_PARTIAL;
TCP_SKB_CB(skb)->tcp_flags = flags;
TCP_SKB_CB(skb)->sacked = 0;
tcp_skb_pcount_set(skb, 1);
TCP_SKB_CB(skb)->seq = seq;
if (flags & (TCPHDR_SYN | TCPHDR_FIN))
seq++;
TCP_SKB_CB(skb)->end_seq = seq;
}
static inline bool tcp_urg_mode(const struct tcp_sock *tp)
{
return tp->snd_una != tp->snd_up;
}
#define OPTION_SACK_ADVERTISE (1 << 0)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
#define OPTION_WSCALE (1 << 3)
#define OPTION_FAST_OPEN_COOKIE (1 << 8)
#define OPTION_SMC (1 << 9)
#define OPTION_MPTCP (1 << 10)
static void smc_options_write(__be32 *ptr, u16 *options)
{
#if IS_ENABLED(CONFIG_SMC)
if (static_branch_unlikely(&tcp_have_smc)) {
if (unlikely(OPTION_SMC & *options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_EXP << 8) |
(TCPOLEN_EXP_SMC_BASE));
*ptr++ = htonl(TCPOPT_SMC_MAGIC);
}
}
#endif
}
struct tcp_out_options {
u16 options; /* bit field of OPTION_* */
u16 mss; /* 0 to disable */
u8 ws; /* window scale, 0 to disable */
u8 num_sack_blocks; /* number of SACK blocks to include */
u8 hash_size; /* bytes in hash_location */
u8 bpf_opt_len; /* length of BPF hdr option */
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
struct mptcp_out_options mptcp;
};
static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp,
struct tcp_out_options *opts)
{
#if IS_ENABLED(CONFIG_MPTCP)
if (unlikely(OPTION_MPTCP & opts->options))
mptcp_write_options(ptr, tp, &opts->mptcp);
#endif
}
#ifdef CONFIG_CGROUP_BPF
static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb,
enum tcp_synack_type synack_type)
{
if (unlikely(!skb))
return BPF_WRITE_HDR_TCP_CURRENT_MSS;
if (unlikely(synack_type == TCP_SYNACK_COOKIE))
return BPF_WRITE_HDR_TCP_SYNACK_COOKIE;
return 0;
}
/* req, syn_skb and synack_type are used when writing synack */
static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct sk_buff *syn_skb,
enum tcp_synack_type synack_type,
struct tcp_out_options *opts,
unsigned int *remaining)
{
struct bpf_sock_ops_kern sock_ops;
int err;
if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
!*remaining)
return;
/* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */
/* init sock_ops */
memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB;
if (req) {
/* The listen "sk" cannot be passed here because
* it is not locked. It would not make too much
* sense to do bpf_setsockopt(listen_sk) based
* on individual connection request also.
*
* Thus, "req" is passed here and the cgroup-bpf-progs
* of the listen "sk" will be run.
*
* "req" is also used here for fastopen even the "sk" here is
* a fullsock "child" sk. It is to keep the behavior
* consistent between fastopen and non-fastopen on
* the bpf programming side.
*/
sock_ops.sk = (struct sock *)req;
sock_ops.syn_skb = syn_skb;
} else {
sock_owned_by_me(sk);
sock_ops.is_fullsock = 1;
sock_ops.sk = sk;
}
sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
sock_ops.remaining_opt_len = *remaining;
/* tcp_current_mss() does not pass a skb */
if (skb)
bpf_skops_init_skb(&sock_ops, skb, 0);
err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
if (err || sock_ops.remaining_opt_len == *remaining)
return;
opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len;
/* round up to 4 bytes */
opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3;
*remaining -= opts->bpf_opt_len;
}
static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct sk_buff *syn_skb,
enum tcp_synack_type synack_type,
struct tcp_out_options *opts)
{
u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len;
struct bpf_sock_ops_kern sock_ops;
int err;
if (likely(!max_opt_len))
return;
memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
if (req) {
sock_ops.sk = (struct sock *)req;
sock_ops.syn_skb = syn_skb;
} else {
sock_owned_by_me(sk);
sock_ops.is_fullsock = 1;
sock_ops.sk = sk;
}
sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
sock_ops.remaining_opt_len = max_opt_len;
first_opt_off = tcp_hdrlen(skb) - max_opt_len;
bpf_skops_init_skb(&sock_ops, skb, first_opt_off);
err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
if (err)
nr_written = 0;
else
nr_written = max_opt_len - sock_ops.remaining_opt_len;
if (nr_written < max_opt_len)
memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP,
max_opt_len - nr_written);
}
#else
static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct sk_buff *syn_skb,
enum tcp_synack_type synack_type,
struct tcp_out_options *opts,
unsigned int *remaining)
{
}
static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct sk_buff *syn_skb,
enum tcp_synack_type synack_type,
struct tcp_out_options *opts)
{
}
#endif
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
* TCP options, we learned this through the hard way, so be careful here.
* Luckily we can at least blame others for their non-compliance but from
* inter-operability perspective it seems that we're somewhat stuck with
* the ordering which we have been using if we want to keep working with
* those broken things (not that it currently hurts anybody as there isn't
* particular reason why the ordering would need to be changed).
*
* At least SACK_PERM as the first option is known to lead to a disaster
* (but it may well be that other scenarios fail similarly).
*/
static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
struct tcp_out_options *opts)
{
u16 options = opts->options; /* mungable copy */
if (unlikely(OPTION_MD5 & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
/* overload cookie hash location */
opts->hash_location = (__u8 *)ptr;
ptr += 4;
}
if (unlikely(opts->mss)) {
*ptr++ = htonl((TCPOPT_MSS << 24) |
(TCPOLEN_MSS << 16) |
opts->mss);
}
if (likely(OPTION_TS & options)) {
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
options &= ~OPTION_SACK_ADVERTISE;
} else {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
}
*ptr++ = htonl(opts->tsval);
*ptr++ = htonl(opts->tsecr);
}
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
}
if (unlikely(OPTION_WSCALE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
opts->ws);
}
if (unlikely(opts->num_sack_blocks)) {
struct tcp_sack_block *sp = tp->rx_opt.dsack ?
tp->duplicate_sack : tp->selective_acks;
int this_sack;
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK << 8) |
(TCPOLEN_SACK_BASE + (opts->num_sack_blocks *
TCPOLEN_SACK_PERBLOCK)));
for (this_sack = 0; this_sack < opts->num_sack_blocks;
++this_sack) {
*ptr++ = htonl(sp[this_sack].start_seq);
*ptr++ = htonl(sp[this_sack].end_seq);
}
tp->rx_opt.dsack = 0;
}
if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
u8 *p = (u8 *)ptr;
u32 len; /* Fast Open option length */
if (foc->exp) {
len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
*ptr = htonl((TCPOPT_EXP << 24) | (len << 16) |
TCPOPT_FASTOPEN_MAGIC);
p += TCPOLEN_EXP_FASTOPEN_BASE;
} else {
len = TCPOLEN_FASTOPEN_BASE + foc->len;
*p++ = TCPOPT_FASTOPEN;
*p++ = len;
}
memcpy(p, foc->val, foc->len);
if ((len & 3) == 2) {
p[foc->len] = TCPOPT_NOP;
p[foc->len + 1] = TCPOPT_NOP;
}
ptr += (len + 3) >> 2;
}
smc_options_write(ptr, &options);
mptcp_options_write(ptr, tp, opts);
}
static void smc_set_option(const struct tcp_sock *tp,
struct tcp_out_options *opts,
unsigned int *remaining)
{
#if IS_ENABLED(CONFIG_SMC)
if (static_branch_unlikely(&tcp_have_smc)) {
if (tp->syn_smc) {
if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
opts->options |= OPTION_SMC;
*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
}
}
}
#endif
}
static void smc_set_option_cond(const struct tcp_sock *tp,
const struct inet_request_sock *ireq,
struct tcp_out_options *opts,
unsigned int *remaining)
{
#if IS_ENABLED(CONFIG_SMC)
if (static_branch_unlikely(&tcp_have_smc)) {
if (tp->syn_smc && ireq->smc_ok) {
if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
opts->options |= OPTION_SMC;
*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
}
}
}
#endif
}
static void mptcp_set_option_cond(const struct request_sock *req,
struct tcp_out_options *opts,
unsigned int *remaining)
{
if (rsk_is_mptcp(req)) {
unsigned int size;
if (mptcp_synack_options(req, &size, &opts->mptcp)) {
if (*remaining >= size) {
opts->options |= OPTION_MPTCP;
*remaining -= size;
}
}
}
}
/* Compute TCP options for SYN packets. This is not the final
* network wire format yet.
*/
static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
*md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
if (static_branch_unlikely(&tcp_md5_needed) &&
rcu_access_pointer(tp->md5sig_info)) {
*md5 = tp->af_specific->md5_lookup(sk, sk);
if (*md5) {
opts->options |= OPTION_MD5;
remaining -= TCPOLEN_MD5SIG_ALIGNED;
}
}
#endif
/* We always get an MSS option. The option bytes which will be seen in
* normal data packets should timestamps be used, must be in the MSS
* advertised. But we subtract them from tp->mss_cache so that
* calculations in tcp_sendmsg are simpler etc. So account for this
* fact here if necessary. If we don't do this correctly, as a
* receiver we won't recognize data packets as being full sized when we
* should, and thus we won't abide by the delayed ACK rules correctly.
* SACKs don't matter, we never delay an ACK when we have any of those
* going out. */
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
opts->options |= OPTION_TS;
opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
}
if (fastopen && fastopen->cookie.len >= 0) {
u32 need = fastopen->cookie.len;
need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE :
TCPOLEN_FASTOPEN_BASE;
need = (need + 3) & ~3U; /* Align to 32 bits */
if (remaining >= need) {
opts->options |= OPTION_FAST_OPEN_COOKIE;
opts->fastopen_cookie = &fastopen->cookie;
remaining -= need;
tp->syn_fastopen = 1;
tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0;
}
}
smc_set_option(tp, opts, &remaining);
if (sk_is_mptcp(sk)) {
unsigned int size;
if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) {
opts->options |= OPTION_MPTCP;
remaining -= size;
}
}
bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
return MAX_TCP_OPTION_SPACE - remaining;
}
/* Set up TCP options for SYN-ACKs. */
static unsigned int tcp_synack_options(const struct sock *sk,
struct request_sock *req,
unsigned int mss, struct sk_buff *skb,
struct tcp_out_options *opts,
const struct tcp_md5sig_key *md5,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
#ifdef CONFIG_TCP_MD5SIG
if (md5) {
opts->options |= OPTION_MD5;
remaining -= TCPOLEN_MD5SIG_ALIGNED;
/* We can't fit any SACK blocks in a packet with MD5 + TS
* options. There was discussion about disabling SACK
* rather than TS in order to fit in better with old,
* buggy kernels, but that was deemed to be unnecessary.
*/
if (synack_type != TCP_SYNACK_COOKIE)
ireq->tstamp_ok &= !ireq->sack_ok;
}
#endif
/* We always send an MSS option. */
opts->mss = mss;
remaining -= TCPOLEN_MSS_ALIGNED;
if (likely(ireq->wscale_ok)) {
opts->ws = ireq->rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
if (likely(ireq->tstamp_ok)) {
opts->options |= OPTION_TS;
opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off;
opts->tsecr = req->ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
if (likely(ireq->sack_ok)) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!ireq->tstamp_ok))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
}
if (foc != NULL && foc->len >= 0) {
u32 need = foc->len;
need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE :
TCPOLEN_FASTOPEN_BASE;
need = (need + 3) & ~3U; /* Align to 32 bits */
if (remaining >= need) {
opts->options |= OPTION_FAST_OPEN_COOKIE;
opts->fastopen_cookie = foc;
remaining -= need;
}
}
mptcp_set_option_cond(req, opts, &remaining);
smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
synack_type, opts, &remaining);
return MAX_TCP_OPTION_SPACE - remaining;
}
/* Compute TCP options for ESTABLISHED sockets. This is not the
* final wire format yet.
*/
static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int size = 0;
unsigned int eff_sacks;
opts->options = 0;
*md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
if (static_branch_unlikely(&tcp_md5_needed) &&
rcu_access_pointer(tp->md5sig_info)) {
*md5 = tp->af_specific->md5_lookup(sk, sk);
if (*md5) {
opts->options |= OPTION_MD5;
size += TCPOLEN_MD5SIG_ALIGNED;
}
}
#endif
if (likely(tp->rx_opt.tstamp_ok)) {
opts->options |= OPTION_TS;
opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0;
opts->tsecr = tp->rx_opt.ts_recent;
size += TCPOLEN_TSTAMP_ALIGNED;
}
/* MPTCP options have precedence over SACK for the limited TCP
* option space because a MPTCP connection would be forced to
* fall back to regular TCP if a required multipath option is
* missing. SACK still gets a chance to use whatever space is
* left.
*/
if (sk_is_mptcp(sk)) {
unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
unsigned int opt_size = 0;
if (mptcp_established_options(sk, skb, &opt_size, remaining,
&opts->mptcp)) {
opts->options |= OPTION_MPTCP;
size += opt_size;
}
}
eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
if (unlikely(eff_sacks)) {
const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
TCPOLEN_SACK_PERBLOCK))
return size;
opts->num_sack_blocks =
min_t(unsigned int, eff_sacks,
(remaining - TCPOLEN_SACK_BASE_ALIGNED) /
TCPOLEN_SACK_PERBLOCK);
size += TCPOLEN_SACK_BASE_ALIGNED +
opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
}
if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
size = MAX_TCP_OPTION_SPACE - remaining;
}
return size;
}
/* TCP SMALL QUEUES (TSQ)
*
* TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev)
* to reduce RTT and bufferbloat.
* We do this using a special skb destructor (tcp_wfree).
*
* Its important tcp_wfree() can be replaced by sock_wfree() in the event skb
* needs to be reallocated in a driver.
* The invariant being skb->truesize subtracted from sk->sk_wmem_alloc
*
* Since transmit from skb destructor is forbidden, we use a tasklet
* to process all sockets that eventually need to send more skbs.
* We use one tasklet per cpu, with its own queue of sockets.
*/
struct tsq_tasklet {
struct tasklet_struct tasklet;
struct list_head head; /* queue of tcp sockets */
};
static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);
static void tcp_tsq_write(struct sock *sk)
{
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) {
struct tcp_sock *tp = tcp_sk(sk);
if (tp->lost_out > tp->retrans_out &&
tcp_snd_cwnd(tp) > tcp_packets_in_flight(tp)) {
tcp_mstamp_refresh(tp);
tcp_xmit_retransmit_queue(sk);
}
tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
0, GFP_ATOMIC);
}
}
static void tcp_tsq_handler(struct sock *sk)
{
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
tcp_tsq_write(sk);
else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
sock_hold(sk);
bh_unlock_sock(sk);
}
/*
* One tasklet per cpu tries to send more skbs.
* We run in tasklet context but need to disable irqs when
* transferring tsq->head because tcp_wfree() might
* interrupt us (non NAPI drivers)
*/
static void tcp_tasklet_func(struct tasklet_struct *t)
{
struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet);
LIST_HEAD(list);
unsigned long flags;
struct list_head *q, *n;
struct tcp_sock *tp;
struct sock *sk;
local_irq_save(flags);
list_splice_init(&tsq->head, &list);
local_irq_restore(flags);
list_for_each_safe(q, n, &list) {
tp = list_entry(q, struct tcp_sock, tsq_node);
list_del(&tp->tsq_node);
sk = (struct sock *)tp;
smp_mb__before_atomic();
clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags);
tcp_tsq_handler(sk);
sk_free(sk);
}
}
#define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \
TCPF_WRITE_TIMER_DEFERRED | \
TCPF_DELACK_TIMER_DEFERRED | \
TCPF_MTU_REDUCED_DEFERRED)
/**
* tcp_release_cb - tcp release_sock() callback
* @sk: socket
*
* called from release_sock() to perform protocol dependent
* actions before socket release.
*/
void tcp_release_cb(struct sock *sk)
{
unsigned long flags, nflags;
/* perform an atomic operation only if at least one flag is set */
do {
flags = sk->sk_tsq_flags;
if (!(flags & TCP_DEFERRED_ALL))
return;
nflags = flags & ~TCP_DEFERRED_ALL;
} while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags);
if (flags & TCPF_TSQ_DEFERRED) {
tcp_tsq_write(sk);
__sock_put(sk);
}
/* Here begins the tricky part :
* We are called from release_sock() with :
* 1) BH disabled
* 2) sk_lock.slock spinlock held
* 3) socket owned by us (sk->sk_lock.owned == 1)
*
* But following code is meant to be called from BH handlers,
* so we should keep BH disabled, but early release socket ownership
*/
sock_release_ownership(sk);
if (flags & TCPF_WRITE_TIMER_DEFERRED) {
tcp_write_timer_handler(sk);
__sock_put(sk);
}
if (flags & TCPF_DELACK_TIMER_DEFERRED) {
tcp_delack_timer_handler(sk);
__sock_put(sk);
}
if (flags & TCPF_MTU_REDUCED_DEFERRED) {
inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
__sock_put(sk);
}
}
EXPORT_SYMBOL(tcp_release_cb);
void __init tcp_tasklet_init(void)
{
int i;
for_each_possible_cpu(i) {
struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
INIT_LIST_HEAD(&tsq->head);
tasklet_setup(&tsq->tasklet, tcp_tasklet_func);
}
}
/*
* Write buffer destructor automatically called from kfree_skb.
* We can't xmit new skbs from this context, as we might already
* hold qdisc lock.
*/
void tcp_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct tcp_sock *tp = tcp_sk(sk);
unsigned long flags, nval, oval;
/* Keep one reference on sk_wmem_alloc.
* Will be released by sk_free() from here or tcp_tasklet_func()
*/
WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc));
/* If this softirq is serviced by ksoftirqd, we are likely under stress.
* Wait until our queues (qdisc + devices) are drained.
* This gives :
* - less callbacks to tcp_write_xmit(), reducing stress (batches)
* - chance for incoming ACK (processed by another cpu maybe)
* to migrate this flow (skb->ooo_okay will be eventually set)
*/
if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current)
goto out;
for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) {
struct tsq_tasklet *tsq;
bool empty;
if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED))
goto out;
nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED;
nval = cmpxchg(&sk->sk_tsq_flags, oval, nval);
if (nval != oval)
continue;
/* queue this socket to tasklet queue */
local_irq_save(flags);
tsq = this_cpu_ptr(&tsq_tasklet);
empty = list_empty(&tsq->head);
list_add(&tp->tsq_node, &tsq->head);
if (empty)
tasklet_schedule(&tsq->tasklet);
local_irq_restore(flags);
return;
}
out:
sk_free(sk);
}
/* Note: Called under soft irq.
* We can call TCP stack right away, unless socket is owned by user.
*/
enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
{
struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer);
struct sock *sk = (struct sock *)tp;
tcp_tsq_handler(sk);
sock_put(sk);
return HRTIMER_NORESTART;
}
static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb,
u64 prior_wstamp)
{
struct tcp_sock *tp = tcp_sk(sk);
if (sk->sk_pacing_status != SK_PACING_NONE) {
unsigned long rate = sk->sk_pacing_rate;
/* Original sch_fq does not pace first 10 MSS
* Note that tp->data_segs_out overflows after 2^32 packets,
* this is a minor annoyance.
*/
if (rate != ~0UL && rate && tp->data_segs_out >= 10) {
u64 len_ns = div64_ul((u64)skb->len * NSEC_PER_SEC, rate);
u64 credit = tp->tcp_wstamp_ns - prior_wstamp;
/* take into account OS jitter */
len_ns -= min_t(u64, len_ns / 2, credit);
tp->tcp_wstamp_ns += len_ns;
}
}
list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
}
INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
INDIRECT_CALLABLE_DECLARE(void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb));
/* This routine actually transmits TCP packets queued in by
* tcp_do_sendmsg(). This is used by both the initial
* transmission and possible later retransmissions.
* All SKB's seen here are completely headerless. It is our
* job to build the TCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
struct tcp_sock *tp;
struct tcp_skb_cb *tcb;
struct tcp_out_options opts;
unsigned int tcp_options_size, tcp_header_size;
struct sk_buff *oskb = NULL;
struct tcp_md5sig_key *md5;
struct tcphdr *th;
u64 prior_wstamp;
int err;
BUG_ON(!skb || !tcp_skb_pcount(skb));
tp = tcp_sk(sk);
prior_wstamp = tp->tcp_wstamp_ns;
tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
if (clone_it) {
TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
- tp->snd_una;
oskb = skb;
tcp_skb_tsorted_save(oskb) {
if (unlikely(skb_cloned(oskb)))
skb = pskb_copy(oskb, gfp_mask);
else
skb = skb_clone(oskb, gfp_mask);
} tcp_skb_tsorted_restore(oskb);
if (unlikely(!skb))
return -ENOBUFS;
/* retransmit skbs might have a non zero value in skb->dev
* because skb->dev is aliased with skb->rbnode.rb_left
*/
skb->dev = NULL;
}
inet = inet_sk(sk);
tcb = TCP_SKB_CB(skb);
memset(&opts, 0, sizeof(opts));
if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) {
tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5);
} else {
tcp_options_size = tcp_established_options(sk, skb, &opts,
&md5);
/* Force a PSH flag on all (GSO) packets to expedite GRO flush
* at receiver : This slightly improve GRO performance.
* Note that we do not force the PSH flag for non GSO packets,
* because they might be sent under high congestion events,
* and in this case it is better to delay the delivery of 1-MSS
* packets and thus the corresponding ACK packet that would
* release the following packet.
*/
if (tcp_skb_pcount(skb) > 1)
tcb->tcp_flags |= TCPHDR_PSH;
}
tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
/* if no packet is in qdisc/device queue, then allow XPS to select
* another queue. We can be called from tcp_tsq_handler()
* which holds one reference to sk.
*
* TODO: Ideally, in-flight pure ACK packets should not matter here.
* One way to get this would be to set skb->truesize = 2 on them.
*/
skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1);
/* If we had to use memory reserve to allocate this skb,
* this might cause drops if packet is looped back :
* Other socket might not have SOCK_MEMALLOC.
* Packets not looped back do not care about pfmemalloc.
*/
skb->pfmemalloc = 0;
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
skb_orphan(skb);
skb->sk = sk;
skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree;
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm);
/* Build TCP header and checksum it. */
th = (struct tcphdr *)skb->data;
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);
th->check = 0;
th->urg_ptr = 0;
/* The urg_mode check is necessary during a below snd_una win probe */
if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) {
if (before(tp->snd_up, tcb->seq + 0x10000)) {
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
th->urg_ptr = htons(0xFFFF);
th->urg = 1;
}
}
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) {
th->window = htons(tcp_select_window(sk));
tcp_ecn_send(sk, skb, th, tcp_header_size);
} else {
/* RFC1323: The window in SYN & SYN/ACK segments
* is never scaled.
*/
th->window = htons(min(tp->rcv_wnd, 65535U));
}
tcp_options_write((__be32 *)(th + 1), tp, &opts);
#ifdef CONFIG_TCP_MD5SIG
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
sk_nocaps_add(sk, NETIF_F_GSO_MASK);
tp->af_specific->calc_md5_hash(opts.hash_location,
md5, sk, skb);
}
#endif
/* BPF prog is the last one writing header option */
bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
tcp_v6_send_check, tcp_v4_send_check,
sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
tp->data_segs_out += tcp_skb_pcount(skb);
tp->bytes_sent += skb->len - tcp_header_size;
}
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
tcp_skb_pcount(skb));
tp->segs_out += tcp_skb_pcount(skb);
skb_set_hash_from_sk(skb, sk);
/* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */
skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);
/* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */
/* Cleanup our debris for IP stacks */
memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
sizeof(struct inet6_skb_parm)));
tcp_add_tx_delay(skb, tp);
err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit,
inet6_csk_xmit, ip_queue_xmit,
sk, skb, &inet->cork.fl);
if (unlikely(err > 0)) {
tcp_enter_cwr(sk);
err = net_xmit_eval(err);
}
if (!err && oskb) {
tcp_update_skb_after_send(sk, oskb, prior_wstamp);
tcp_rate_skb_sent(sk, oskb);
}
return err;
}
static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
gfp_t gfp_mask)
{
return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
tcp_sk(sk)->rcv_nxt);
}
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
* otherwise socket can stall.
*/
static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Advance write_seq and place onto the write_queue. */
WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
__skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
}
/* Initialize TSO segments for a packet. */
static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
{
if (skb->len <= mss_now) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
tcp_skb_pcount_set(skb, 1);
TCP_SKB_CB(skb)->tcp_gso_size = 0;
} else {
tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
TCP_SKB_CB(skb)->tcp_gso_size = mss_now;
}
}
/* Pcount in the middle of the write queue got changed, we need to do various
* tweaks to fix counters
*/
static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->packets_out -= decr;
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= decr;
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= decr;
if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
tp->lost_out -= decr;
/* Reno case is special. Sigh... */
if (tcp_is_reno(tp) && decr > 0)
tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
if (tp->lost_skb_hint &&
before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
tp->lost_cnt_hint -= decr;
tcp_verify_left_out(tp);
}
static bool tcp_has_tx_tstamp(const struct sk_buff *skb)
{
return TCP_SKB_CB(skb)->txstamp_ack ||
(skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP);
}
static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
if (unlikely(tcp_has_tx_tstamp(skb)) &&
!before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) {
struct skb_shared_info *shinfo2 = skb_shinfo(skb2);
u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP;
shinfo->tx_flags &= ~tsflags;
shinfo2->tx_flags |= tsflags;
swap(shinfo->tskey, shinfo2->tskey);
TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack;
TCP_SKB_CB(skb)->txstamp_ack = 0;
}
}
static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2)
{
TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor;
TCP_SKB_CB(skb)->eor = 0;
}
/* Insert buff after skb on the write or rtx queue of sk. */
static void tcp_insert_write_queue_after(struct sk_buff *skb,
struct sk_buff *buff,
struct sock *sk,
enum tcp_queue tcp_queue)
{
if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE)
__skb_queue_after(&sk->sk_write_queue, skb, buff);
else
tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
}
/* Function to create two new TCP segments. Shrinks the given segment
* to the specified size and appends a new segment with the rest of the
* packet to the list. This won't be called frequently, I hope.
* Remember, these are still headerless SKBs at this point.
*/
int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
struct sk_buff *skb, u32 len,
unsigned int mss_now, gfp_t gfp)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
int nsize, old_factor;
long limit;
int nlen;
u8 flags;
if (WARN_ON(len > skb->len))
return -EINVAL;
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
* We need some allowance to not penalize applications setting small
* SO_SNDBUF values.
* Also allow first and last skb in retransmit queue to be split.
*/
limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
skb != tcp_rtx_queue_head(sk) &&
skb != tcp_rtx_queue_tail(sk))) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
return -ENOMEM;
}
if (skb_unclone_keeptruesize(skb, gfp))
return -ENOMEM;
/* Get a new skb... force flag on. */
buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
if (!buff)
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
nlen = skb->len - len - nsize;
buff->truesize += nlen;
skb->truesize -= nlen;
/* Correct the sequence numbers. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->tcp_flags;
TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
TCP_SKB_CB(buff)->tcp_flags = flags;
TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
tcp_skb_fragment_eor(skb, buff);
skb_split(skb, buff, len);
buff->ip_summed = CHECKSUM_PARTIAL;
buff->tstamp = skb->tstamp;
tcp_fragment_tstamp(skb, buff);
old_factor = tcp_skb_pcount(skb);
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(skb, mss_now);
tcp_set_skb_tso_segs(buff, mss_now);
/* Update delivered info for the new segment */
TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx;
/* If this packet has been sent out already, we must
* adjust the various packet counters.
*/
if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
int diff = old_factor - tcp_skb_pcount(skb) -
tcp_skb_pcount(buff);
if (diff)
tcp_adjust_pcount(sk, skb, diff);
}
/* Link BUFF into the send queue. */
__skb_header_release(buff);
tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE)
list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor);
return 0;
}
/* This is similar to __pskb_pull_tail(). The difference is that pulled
* data is not copied, but immediately discarded.
*/
static int __pskb_trim_head(struct sk_buff *skb, int len)
{
struct skb_shared_info *shinfo;
int i, k, eat;
eat = min_t(int, len, skb_headlen(skb));
if (eat) {
__skb_pull(skb, eat);
len -= eat;
if (!len)
return 0;
}
eat = len;
k = 0;
shinfo = skb_shinfo(skb);
for (i = 0; i < shinfo->nr_frags; i++) {
int size = skb_frag_size(&shinfo->frags[i]);
if (size <= eat) {
skb_frag_unref(skb, i);
eat -= size;
} else {
shinfo->frags[k] = shinfo->frags[i];
if (eat) {
skb_frag_off_add(&shinfo->frags[k], eat);
skb_frag_size_sub(&shinfo->frags[k], eat);
eat = 0;
}
k++;
}
}
shinfo->nr_frags = k;
skb->data_len -= len;
skb->len = skb->data_len;
return len;
}
/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
u32 delta_truesize;
if (skb_unclone_keeptruesize(skb, GFP_ATOMIC))
return -ENOMEM;
delta_truesize = __pskb_trim_head(skb, len);
TCP_SKB_CB(skb)->seq += len;
skb->ip_summed = CHECKSUM_PARTIAL;
if (delta_truesize) {
skb->truesize -= delta_truesize;
sk_wmem_queued_add(sk, -delta_truesize);
sk_mem_uncharge(sk, delta_truesize);
}
/* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb));
return 0;
}
/* Calculate MSS not accounting any TCP options. */
static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
int mss_now;
/* Calculate base mss without TCP options:
It is MMS_S - sizeof(tcphdr) of rfc1122
*/
mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);
/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
if (icsk->icsk_af_ops->net_frag_header_len) {
const struct dst_entry *dst = __sk_dst_get(sk);
if (dst && dst_allfrag(dst))
mss_now -= icsk->icsk_af_ops->net_frag_header_len;
}
/* Clamp it (mss_clamp does not include tcp options) */
if (mss_now > tp->rx_opt.mss_clamp)
mss_now = tp->rx_opt.mss_clamp;
/* Now subtract optional transport overhead */
mss_now -= icsk->icsk_ext_hdr_len;
/* Then reserve room for full set of TCP options and 8 bytes of data */
mss_now = max(mss_now,
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss));
return mss_now;
}
/* Calculate MSS. Not accounting for SACKs here. */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
/* Subtract TCP options size, not including SACKs */
return __tcp_mtu_to_mss(sk, pmtu) -
(tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}
EXPORT_SYMBOL(tcp_mtu_to_mss);
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
int mtu;
mtu = mss +
tp->tcp_header_len +
icsk->icsk_ext_hdr_len +
icsk->icsk_af_ops->net_header_len;
/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
if (icsk->icsk_af_ops->net_frag_header_len) {
const struct dst_entry *dst = __sk_dst_get(sk);
if (dst && dst_allfrag(dst))
mtu += icsk->icsk_af_ops->net_frag_header_len;
}
return mtu;
}
EXPORT_SYMBOL(tcp_mss_to_mtu);
/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
icsk->icsk_af_ops->net_header_len;
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss));
icsk->icsk_mtup.probe_size = 0;
if (icsk->icsk_mtup.enabled)
icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
}
EXPORT_SYMBOL(tcp_mtup_init);
/* This function synchronize snd mss to current pmtu/exthdr set.
tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
for TCP options, but includes only bare TCP header.
tp->rx_opt.mss_clamp is mss negotiated at connection setup.
It is minimum of user_mss and mss received with SYN.
It also does not include TCP options.
inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function.
tp->mss_cache is current effective sending mss, including
all tcp options except for SACKs. It is evaluated,
taking into account current pmtu, but never exceeds
tp->rx_opt.mss_clamp.
NOTE1. rfc1122 clearly states that advertised MSS
DOES NOT include either tcp or ip options.
NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache
are READ ONLY outside this function. --ANK (980731)
*/
unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int mss_now;
if (icsk->icsk_mtup.search_high > pmtu)
icsk->icsk_mtup.search_high = pmtu;
mss_now = tcp_mtu_to_mss(sk, pmtu);
mss_now = tcp_bound_to_half_wnd(tp, mss_now);
/* And store cached results */
icsk->icsk_pmtu_cookie = pmtu;
if (icsk->icsk_mtup.enabled)
mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low));
tp->mss_cache = mss_now;
return mss_now;
}
EXPORT_SYMBOL(tcp_sync_mss);
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
*/
unsigned int tcp_current_mss(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct dst_entry *dst = __sk_dst_get(sk);
u32 mss_now;
unsigned int header_len;
struct tcp_out_options opts;
struct tcp_md5sig_key *md5;
mss_now = tp->mss_cache;
if (dst) {
u32 mtu = dst_mtu(dst);
if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
mss_now = tcp_sync_mss(sk, mtu);
}
header_len = tcp_established_options(sk, NULL, &opts, &md5) +
sizeof(struct tcphdr);
/* The mss_cache is sized based on tp->tcp_header_len, which assumes
* some common options. If this is an odd packet (because we have SACK
* blocks etc) then our calculated header_len will be different, and
* we have to adjust mss_now correspondingly */
if (header_len != tp->tcp_header_len) {
int delta = (int) header_len - tp->tcp_header_len;
mss_now -= delta;
}
return mss_now;
}
/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
* As additional protections, we do not touch cwnd in retransmission phases,
* and if application hit its sndbuf limit recently.
*/
static void tcp_cwnd_application_limited(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
/* Limited by application or receiver window. */
u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
u32 win_used = max(tp->snd_cwnd_used, init_win);
if (win_used < tcp_snd_cwnd(tp)) {
tp->snd_ssthresh = tcp_current_ssthresh(sk);
tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1);
}
tp->snd_cwnd_used = 0;
}
tp->snd_cwnd_stamp = tcp_jiffies32;
}
static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
{
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
/* Track the maximum number of outstanding packets in each
* window, and remember whether we were cwnd-limited then.
*/
if (!before(tp->snd_una, tp->max_packets_seq) ||
tp->packets_out > tp->max_packets_out ||
is_cwnd_limited) {
tp->max_packets_out = tp->packets_out;
tp->max_packets_seq = tp->snd_nxt;
tp->is_cwnd_limited = is_cwnd_limited;
}
if (tcp_is_cwnd_limited(sk)) {
/* Network is feed fully. */
tp->snd_cwnd_used = 0;
tp->snd_cwnd_stamp = tcp_jiffies32;
} else {
/* Network starves. */
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
(s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
!ca_ops->cong_control)
tcp_cwnd_application_limited(sk);
/* The following conditions together indicate the starvation
* is caused by insufficient sender buffer:
* 1) just sent some data (see tcp_write_xmit)
* 2) not cwnd limited (this else condition)
* 3) no more data to send (tcp_write_queue_empty())
* 4) application is hitting buffer limit (SOCK_NOSPACE)
*/
if (tcp_write_queue_empty(sk) && sk->sk_socket &&
test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) &&
(1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
}
/* Minshall's variant of the Nagle send check. */
static bool tcp_minshall_check(const struct tcp_sock *tp)
{
return after(tp->snd_sml, tp->snd_una) &&
!after(tp->snd_sml, tp->snd_nxt);
}
/* Update snd_sml if this skb is under mss
* Note that a TSO packet might end with a sub-mss segment
* The test is really :
* if ((skb->len % mss) != 0)
* tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
* But we can avoid doing the divide again given we already have
* skb_pcount = skb->len / mss_now
*/
static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now,
const struct sk_buff *skb)
{
if (skb->len < tcp_skb_pcount(skb) * mss_now)
tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}
/* Return false, if packet can be sent now without violation Nagle's rules:
* 1. It is full sized. (provided by caller in %partial bool)
* 2. Or it contains FIN. (already checked by caller)
* 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
* 4. Or TCP_CORK is not set, and all sent packets are ACKed.
* With Minshall's modification: all sent small packets are ACKed.
*/
static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
int nonagle)
{
return partial &&
((nonagle & TCP_NAGLE_CORK) ||
(!nonagle && tp->packets_out && tcp_minshall_check(tp)));
}
/* Return how many segs we'd like on a TSO packet,
* to send one TSO packet per ms
*/
static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
int min_tso_segs)
{
u32 bytes, segs;
bytes = min_t(unsigned long,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
/* Goal is to send at least one packet per ms,
* not one big TSO packet every 100 ms.
* This preserves ACK clocking and is consistent
* with tcp_tso_should_defer() heuristic.
*/
segs = max_t(u32, bytes / mss_now, min_tso_segs);
return segs;
}
/* Return the number of segments we want in the skb we are transmitting.
* See if congestion control module wants to decide; otherwise, autosize.
*/
static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
{
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
u32 min_tso, tso_segs;
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
}
/* Returns the portion of skb which can be sent right away */
static unsigned int tcp_mss_split_point(const struct sock *sk,
const struct sk_buff *skb,
unsigned int mss_now,
unsigned int max_segs,
int nonagle)
{
const struct tcp_sock *tp = tcp_sk(sk);
u32 partial, needed, window, max_len;
window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
max_len = mss_now * max_segs;
if (likely(max_len <= window && skb != tcp_write_queue_tail(sk)))
return max_len;
needed = min(skb->len, window);
if (max_len <= needed)
return max_len;
partial = needed % mss_now;
/* If last segment is not a full MSS, check if Nagle rules allow us
* to include this last segment in this skb.
* Otherwise, we'll split the skb at last MSS boundary
*/
if (tcp_nagle_check(partial != 0, tp, nonagle))
return needed - partial;
return needed;
}
/* Can at least one segment of SKB be sent right now, according to the
* congestion window rules? If so, return how many segments are allowed.
*/
static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
const struct sk_buff *skb)
{
u32 in_flight, cwnd, halfcwnd;
/* Don't be strict about the congestion window for the final FIN. */
if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) &&
tcp_skb_pcount(skb) == 1)
return 1;
in_flight = tcp_packets_in_flight(tp);
cwnd = tcp_snd_cwnd(tp);
if (in_flight >= cwnd)
return 0;
/* For better scheduling, ensure we have at least
* 2 GSO packets in flight.
*/
halfcwnd = max(cwnd >> 1, 1U);
return min(halfcwnd, cwnd - in_flight);
}
/* Initialize TSO state of a skb.
* This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now)
{
int tso_segs = tcp_skb_pcount(skb);
if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
tcp_set_skb_tso_segs(skb, mss_now);
tso_segs = tcp_skb_pcount(skb);
}
return tso_segs;
}
/* Return true if the Nagle test allows this packet to be
* sent now.
*/
static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb,
unsigned int cur_mss, int nonagle)
{
/* Nagle rule does not apply to frames, which sit in the middle of the
* write_queue (they have no chances to get new data).
*
* This is implemented in the callers, where they modify the 'nonagle'
* argument based upon the location of SKB in the send queue.
*/
if (nonagle & TCP_NAGLE_PUSH)
return true;
/* Don't use the nagle rule for urgent data (or for the final FIN). */
if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
return true;
if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle))
return true;
return false;
}
/* Does at least the first segment of SKB fit into the send window? */
static bool tcp_snd_wnd_test(const struct tcp_sock *tp,
const struct sk_buff *skb,
unsigned int cur_mss)
{
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (skb->len > cur_mss)
end_seq = TCP_SKB_CB(skb)->seq + cur_mss;
return !after(end_seq, tcp_wnd_end(tp));
}
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
* which is put after SKB on the list. It is very much like
* tcp_fragment() except that it may make several kinds of assumptions
* in order to speed up the splitting operation. In particular, we
* know that all the data is in scatter-gather pages, and that the
* packet has never been sent out before (and thus is not cloned).
*/
static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
unsigned int mss_now, gfp_t gfp)
{
int nlen = skb->len - len;
struct sk_buff *buff;
u8 flags;
/* All of a TSO frame must be composed of paged data. */
if (skb->len != skb->data_len)
return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
skb, len, mss_now, gfp);
buff = sk_stream_alloc_skb(sk, 0, gfp, true);
if (unlikely(!buff))
return -ENOMEM;
skb_copy_decrypted(buff, skb);
mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
buff->truesize += nlen;
skb->truesize -= nlen;
/* Correct the sequence numbers. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->tcp_flags;
TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
TCP_SKB_CB(buff)->tcp_flags = flags;
/* This packet was never sent out yet, so no SACK bits. */
TCP_SKB_CB(buff)->sacked = 0;
tcp_skb_fragment_eor(skb, buff);
buff->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
tcp_fragment_tstamp(skb, buff);
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(skb, mss_now);
tcp_set_skb_tso_segs(buff, mss_now);
/* Link BUFF into the send queue. */
__skb_header_release(buff);
tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE);
return 0;
}
/* Try to defer sending, if possible, in order to minimize the amount
* of TSO splitting we do. View it as a kind of TSO Nagle test.
*
* This algorithm is from John Heffner.
*/
static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
bool *is_cwnd_limited,
bool *is_rwnd_limited,
u32 max_segs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 send_win, cong_win, limit, in_flight;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *head;
int win_divisor;
s64 delta;
if (icsk->icsk_ca_state >= TCP_CA_Recovery)
goto send_now;
/* Avoid bursty behavior by allowing defer
* only if the last write was recent (1 ms).
* Note that tp->tcp_wstamp_ns can be in the future if we have
* packets waiting in a qdisc or device for EDT delivery.
*/
delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC;
if (delta > 0)
goto send_now;
in_flight = tcp_packets_in_flight(tp);
BUG_ON(tcp_skb_pcount(skb) <= 1);
BUG_ON(tcp_snd_cwnd(tp) <= in_flight);
send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* From in_flight test above, we know that cwnd > in_flight. */
cong_win = (tcp_snd_cwnd(tp) - in_flight) * tp->mss_cache;
limit = min(send_win, cong_win);
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= max_segs * tp->mss_cache)
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
goto send_now;
win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
if (win_divisor) {
u32 chunk = min(tp->snd_wnd, tcp_snd_cwnd(tp) * tp->mss_cache);
/* If at least some fraction of a window is available,
* just use it.
*/
chunk /= win_divisor;
if (limit >= chunk)
goto send_now;
} else {
/* Different approach, try not to defer past a single
* ACK. Receiver should ACK every other full sized
* frame, so if we have space for more than 3 frames
* then send now.
*/
if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache)
goto send_now;
}
/* TODO : use tsorted_sent_queue ? */
head = tcp_rtx_queue_head(sk);
if (!head)
goto send_now;
delta = tp->tcp_clock_cache - head->tstamp;
/* If next ACK is likely to come too late (half srtt), do not defer */
if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
goto send_now;
/* Ok, it looks like it is advisable to defer.
* Three cases are tracked :
* 1) We are cwnd-limited
* 2) We are rwnd-limited
* 3) We are application limited.
*/
if (cong_win < send_win) {
if (cong_win <= skb->len) {
*is_cwnd_limited = true;
return true;
}
} else {
if (send_win <= skb->len) {
*is_rwnd_limited = true;
return true;
}
}
/* If this packet won't get more data, do not wait. */
if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) ||
TCP_SKB_CB(skb)->eor)
goto send_now;
return true;
send_now:
return false;
}
static inline void tcp_mtu_check_reprobe(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
u32 interval;
s32 delta;
interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
if (unlikely(delta >= interval * HZ)) {
int mss = tcp_current_mss(sk);
/* Update current search range */
icsk->icsk_mtup.probe_size = 0;
icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp +
sizeof(struct tcphdr) +
icsk->icsk_af_ops->net_header_len;
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
/* Update probe time stamp */
icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
}
}
static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
{
struct sk_buff *skb, *next;
skb = tcp_send_head(sk);
tcp_for_write_queue_from_safe(skb, next, sk) {
if (len <= skb->len)
break;
if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
return false;
len -= skb->len;
}
return true;
}
/* Create a new MTU probe if we are ready.
* MTU probe is regularly attempting to increase the path MTU by
* deliberately sending larger packets. This discovers routing
* changes resulting in larger path MTUs.
*
* Returns 0 if we should wait to probe (no cwnd available),
* 1 if a probe was sent,
* -1 otherwise
*/
static int tcp_mtu_probe(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb, *nskb, *next;
struct net *net = sock_net(sk);
int probe_size;
int size_needed;
int copy, len;
int mss_now;
int interval;
/* Not currently probing/verifying,
* not in recovery,
* have enough cwnd, and
* not SACKing (the variable headers throw things off)
*/
if (likely(!icsk->icsk_mtup.enabled ||
icsk->icsk_mtup.probe_size ||
inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
tcp_snd_cwnd(tp) < 11 ||
tp->rx_opt.num_sacks || tp->rx_opt.dsack))
return -1;
/* Use binary search for probe_size between tcp_mss_base,
* and current mss_clamp. if (search_high - search_low)
* smaller than a threshold, backoff from probing.
*/
mss_now = tcp_current_mss(sk);
probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
icsk->icsk_mtup.search_low) >> 1);
size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
/* When misfortune happens, we are reprobing actively,
* and then reprobe timer has expired. We stick with current
* probing process by not resetting search range to its orignal.
*/
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
/* Check whether enough time has elaplased for
* another round of probing.
*/
tcp_mtu_check_reprobe(sk);
return -1;
}
/* Have enough data in the send queue to probe? */
if (tp->write_seq - tp->snd_nxt < size_needed)
return -1;
if (tp->snd_wnd < size_needed)
return -1;
if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp)))
return 0;
/* Do we need to wait to drain cwnd? With none in flight, don't stall */
if (tcp_packets_in_flight(tp) + 2 > tcp_snd_cwnd(tp)) {
if (!tcp_packets_in_flight(tp))
return -1;
else
return 0;
}
if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
return -1;
/* We're allowed to probe. Build it now. */
nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
return -1;
sk_wmem_queued_add(sk, nskb->truesize);
sk_mem_charge(sk, nskb->truesize);
skb = tcp_send_head(sk);
skb_copy_decrypted(nskb, skb);
mptcp_skb_ext_copy(nskb, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK;
TCP_SKB_CB(nskb)->sacked = 0;
nskb->csum = 0;
nskb->ip_summed = CHECKSUM_PARTIAL;
tcp_insert_write_queue_before(nskb, skb, sk);
tcp_highest_sack_replace(sk, skb, nskb);
len = 0;
tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
* Throw it away. */
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
/* If this is the last SKB we copy and eor is set
* we need to propagate it to the new skb.
*/
TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
tcp_skb_collapse_tstamp(nskb, skb);
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
} else {
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags &
~(TCPHDR_FIN|TCPHDR_PSH);
if (!skb_shinfo(skb)->nr_frags) {
skb_pull(skb, copy);
} else {
__pskb_trim_head(skb, copy);
tcp_set_skb_tso_segs(skb, mss_now);
}
TCP_SKB_CB(skb)->seq += copy;
}
len += copy;
if (len >= probe_size)
break;
}
tcp_init_tso_segs(nskb, nskb->len);
/* We're ready to send. If this fails, the probe will
* be resegmented into mss-sized pieces by tcp_write_xmit().
*/
if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
/* Decrement cwnd here because we are sending
* effectively two packets. */
tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1);
tcp_event_new_data_sent(sk, nskb);
icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq;
return 1;
}
return -1;
}
static bool tcp_pacing_check(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (!tcp_needs_internal_pacing(sk))
return false;
if (tp->tcp_wstamp_ns <= tp->tcp_clock_cache)
return false;
if (!hrtimer_is_queued(&tp->pacing_timer)) {
hrtimer_start(&tp->pacing_timer,
ns_to_ktime(tp->tcp_wstamp_ns),
HRTIMER_MODE_ABS_PINNED_SOFT);
sock_hold(sk);
}
return true;
}
/* TCP Small Queues :
* Control number of packets in qdisc/devices to two packets / or ~1 ms.
* (These limits are doubled for retransmits)
* This allows for :
* - better RTT estimation and ACK scheduling
* - faster recovery
* - high rates
* Alas, some drivers / subsystems require a fair amount
* of queued bytes to ensure line rate.
* One example is wifi aggregation (802.11 AMPDU)
*/
static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
unsigned int factor)
{
unsigned long limit;
limit = max_t(unsigned long,
2 * skb->truesize,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
tcp_sk(sk)->tcp_tx_delay) {
u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay;
/* TSQ is based on skb truesize sum (sk_wmem_alloc), so we
* approximate our needs assuming an ~100% skb->truesize overhead.
* USEC_PER_SEC is approximated by 2^20.
* do_div(extra_bytes, USEC_PER_SEC/2) is replaced by a right shift.
*/
extra_bytes >>= (20 - 1);
limit += extra_bytes;
}
if (refcount_read(&sk->sk_wmem_alloc) > limit) {
/* Always send skb if rtx queue is empty.
* No need to wait for TX completion to call us back,
* after softirq/tasklet schedule.
* This helps when TX completions are delayed too much.
*/
if (tcp_rtx_queue_empty(sk))
return false;
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
/* It is possible TX completion already happened
* before we set TSQ_THROTTLED, so we must
* test again the condition.
*/
smp_mb__after_atomic();
if (refcount_read(&sk->sk_wmem_alloc) > limit)
return true;
}
return false;
}
static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new)
{
const u32 now = tcp_jiffies32;
enum tcp_chrono old = tp->chrono_type;
if (old > TCP_CHRONO_UNSPEC)
tp->chrono_stat[old - 1] += now - tp->chrono_start;
tp->chrono_start = now;
tp->chrono_type = new;
}
void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type)
{
struct tcp_sock *tp = tcp_sk(sk);
/* If there are multiple conditions worthy of tracking in a
* chronograph then the highest priority enum takes precedence
* over the other conditions. So that if something "more interesting"
* starts happening, stop the previous chrono and start a new one.
*/
if (type > tp->chrono_type)
tcp_chrono_set(tp, type);
}
void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type)
{
struct tcp_sock *tp = tcp_sk(sk);
/* There are multiple conditions worthy of tracking in a
* chronograph, so that the highest priority enum takes
* precedence over the other conditions (see tcp_chrono_start).
* If a condition stops, we only stop chrono tracking if
* it's the "most interesting" or current chrono we are
* tracking and starts busy chrono if we have pending data.
*/
if (tcp_rtx_and_write_queues_empty(sk))
tcp_chrono_set(tp, TCP_CHRONO_UNSPEC);
else if (type == tp->chrono_type)
tcp_chrono_set(tp, TCP_CHRONO_BUSY);
}
/* This routine writes packets to the network. It advances the
* send_head. This happens as incoming acks open up the remote
* window for us.
*
* LARGESEND note: !tcp_urg_mode is overkill, only frames between
* snd_up-64k-mss .. snd_up cannot be large. However, taking into
* account rare use of URG, this is not a big flaw.
*
* Send at most one packet when push_one > 0. Temporarily ignore
* cwnd limit to force at most one packet out when push_one == 2.
* Returns true, if no segments are in flight and we have queued segments,
* but cannot send anything now because of SWS or another problem.
*/
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
unsigned int tso_segs, sent_pkts;
int cwnd_quota;
int result;
bool is_cwnd_limited = false, is_rwnd_limited = false;
u32 max_segs;
sent_pkts = 0;
tcp_mstamp_refresh(tp);
if (!push_one) {
/* Do MTU probing. */
result = tcp_mtu_probe(sk);
if (!result) {
return false;
} else if (result > 0) {
sent_pkts = 1;
}
}
max_segs = tcp_tso_segs(sk, mss_now);
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
tcp_init_tso_segs(skb, mss_now);
goto repair; /* Skip network transmission */
}
if (tcp_pacing_check(sk))
break;
tso_segs = tcp_init_tso_segs(skb, mss_now);
BUG_ON(!tso_segs);
cwnd_quota = tcp_cwnd_test(tp, skb);
if (!cwnd_quota) {
if (push_one == 2)
/* Force out a loss probe pkt. */
cwnd_quota = 1;
else
break;
}
if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) {
is_rwnd_limited = true;
break;
}
if (tso_segs == 1) {
if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
(tcp_skb_is_last(sk, skb) ?
nonagle : TCP_NAGLE_PUSH))))
break;
} else {
if (!push_one &&
tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
&is_rwnd_limited, max_segs))
break;
}
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
min_t(unsigned int,
cwnd_quota,
max_segs),
nonagle);
if (skb->len > limit &&
unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
break;
if (tcp_small_queue_check(sk, skb, 0))
break;
/* Argh, we hit an empty skb(), presumably a thread
* is sleeping in sendmsg()/sk_stream_wait_memory().
* We do not want to send a pure-ack packet and have
* a strange looking rtx queue with empty packet(s).
*/
if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
break;
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
repair:
/* Advance the send_head. This one is sent out.
* This call will increment packets_out.
*/
tcp_event_new_data_sent(sk, skb);
tcp_minshall_update(tp, mss_now, skb);
sent_pkts += tcp_skb_pcount(skb);
if (push_one)
break;
}
if (is_rwnd_limited)
tcp_chrono_start(sk, TCP_CHRONO_RWND_LIMITED);
else
tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED);
is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tcp_snd_cwnd(tp));
if (likely(sent_pkts || is_cwnd_limited))
tcp_cwnd_validate(sk, is_cwnd_limited);
if (likely(sent_pkts)) {
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += sent_pkts;
/* Send one loss probe per tail loss episode. */
if (push_one != 2)
tcp_schedule_loss_probe(sk, false);
return false;
}
return !tp->packets_out && !tcp_write_queue_empty(sk);
}
bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, rto_delta_us;
int early_retrans;
/* Don't do any loss probe on a Fast Open connection before 3WHS
* finishes.
*/
if (rcu_access_pointer(tp->fastopen_rsk))
return false;
early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
/* Schedule a loss probe in 2*RTT for SACK capable connections
* not in loss recovery, that are either limited by cwnd or application.
*/
if ((early_retrans != 3 && early_retrans != 4) ||
!tp->packets_out || !tcp_is_sack(tp) ||
(icsk->icsk_ca_state != TCP_CA_Open &&
icsk->icsk_ca_state != TCP_CA_CWR))
return false;
/* Probe timeout is 2*rtt. Add minimum RTO to account
* for delayed ack when there's one outstanding packet. If no RTT
* sample is available then probe after TCP_TIMEOUT_INIT.
*/
if (tp->srtt_us) {
timeout = usecs_to_jiffies(tp->srtt_us >> 2);
if (tp->packets_out == 1)
timeout += TCP_RTO_MIN;
else
timeout += TCP_TIMEOUT_MIN;
} else {
timeout = TCP_TIMEOUT_INIT;
}
/* If the RTO formula yields an earlier time, then use that time. */
rto_delta_us = advancing_rto ?
jiffies_to_usecs(inet_csk(sk)->icsk_rto) :
tcp_rto_delta_us(sk); /* How far in future is RTO? */
if (rto_delta_us > 0)
timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX);
return true;
}
/* Thanks to skb fast clones, we can detect if a prior transmit of
* a packet is still in a qdisc or driver queue.
* In this case, there is very little point doing a retransmit !
*/
static bool skb_still_in_host_queue(struct sock *sk,
const struct sk_buff *skb)
{
if (unlikely(skb_fclone_busy(sk, skb))) {
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
smp_mb__after_atomic();
if (skb_fclone_busy(sk, skb)) {
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
return true;
}
}
return false;
}
/* When probe timeout (PTO) fires, try send a new segment if possible, else
* retransmit the last segment.
*/
void tcp_send_loss_probe(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int pcount;
int mss = tcp_current_mss(sk);
/* At most one outstanding TLP */
if (tp->tlp_high_seq)
goto rearm_timer;
tp->tlp_retrans = 0;
skb = tcp_send_head(sk);
if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
pcount = tp->packets_out;
tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
if (tp->packets_out > pcount)
goto probe_sent;
goto rearm_timer;
}
skb = skb_rb_last(&sk->tcp_rtx_queue);
if (unlikely(!skb)) {
WARN_ONCE(tp->packets_out,
"invalid inflight: %u state %u cwnd %u mss %d\n",
tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss);
inet_csk(sk)->icsk_pending = 0;
return;
}
if (skb_still_in_host_queue(sk, skb))
goto rearm_timer;
pcount = tcp_skb_pcount(skb);
if (WARN_ON(!pcount))
goto rearm_timer;
if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
(pcount - 1) * mss, mss,
GFP_ATOMIC)))
goto rearm_timer;
skb = skb_rb_next(skb);
}
if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
goto rearm_timer;
if (__tcp_retransmit_skb(sk, skb, 1))
goto rearm_timer;
tp->tlp_retrans = 1;
probe_sent:
/* Record snd_nxt for loss detection. */
tp->tlp_high_seq = tp->snd_nxt;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
/* Reset s.t. tcp_rearm_rto will restart timer from now */
inet_csk(sk)->icsk_pending = 0;
rearm_timer:
tcp_rearm_rto(sk);
}
/* Push out any pending frames which were held back due to
* TCP_CORK or attempt at coalescing tiny packets.
* The socket must be locked by the caller.
*/
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle)
{
/* If we are closed, the bytes will have to remain here.
* In time closedown will finish, we empty the write queue and
* all will be happy.
*/
if (unlikely(sk->sk_state == TCP_CLOSE))
return;
if (tcp_write_xmit(sk, cur_mss, nonagle, 0,
sk_gfp_mask(sk, GFP_ATOMIC)))
tcp_check_probe_timer(sk);
}
/* Send _single_ skb sitting at the send head. This function requires
* true push pending frames to setup probe timer etc.
*/
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
struct sk_buff *skb = tcp_send_head(sk);
BUG_ON(!skb || skb->len < mss_now);
tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation);
}
/* This function returns the amount that we can raise the
* usable window based on the following constraints
*
* 1. The window can never be shrunk once it is offered (RFC 793)
* 2. We limit memory per socket
*
* RFC 1122:
* "the suggested [SWS] avoidance algorithm for the receiver is to keep
* RECV.NEXT + RCV.WIN fixed until:
* RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)"
*
* i.e. don't raise the right edge of the window until you can raise
* it at least MSS bytes.
*
* Unfortunately, the recommended algorithm breaks header prediction,
* since header prediction assumes th->window stays fixed.
*
* Strictly speaking, keeping th->window fixed violates the receiver
* side SWS prevention criteria. The problem is that under this rule
* a stream of single byte packets will cause the right side of the
* window to always advance by a single byte.
*
* Of course, if the sender implements sender side SWS prevention
* then this will not be a problem.
*
* BSD seems to make the following compromise:
*
* If the free space is less than the 1/4 of the maximum
* space available and the free space is less than 1/2 mss,
* then set the window to 0.
* [ Actually, bsd uses MSS and 1/4 of maximal _window_ ]
* Otherwise, just prevent the window from shrinking
* and from being larger than the largest representable value.
*
* This prevents incremental opening of the window in the regime
* where TCP is limited by the speed of the reader side taking
* data out of the TCP receive queue. It does nothing about
* those cases where the window is constrained on the sender side
* because the pipeline is full.
*
* BSD also seems to "accidentally" limit itself to windows that are a
* multiple of MSS, at least until the free space gets quite small.
* This would appear to be a side effect of the mbuf implementation.
* Combining these two algorithms results in the observed behavior
* of having a fixed window size at almost all times.
*
* Below we obtain similar behavior by forcing the offered window to
* a multiple of the mss when it is feasible to do so.
*
* Note, we don't "adjust" for TIMESTAMP or SACK option bytes.
* Regular options like TIMESTAMP are taken into account.
*/
u32 __tcp_select_window(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* MSS for the peer's data. Previous versions used mss_clamp
* here. I don't know if the value based on our guesses
* of peer's MSS is better for the performance. It's more correct
* but may be worse for the performance because of rcv_mss
* fluctuations. --SAW 1998/11/1
*/
int mss = icsk->icsk_ack.rcv_mss;
int free_space = tcp_space(sk);
int allowed_space = tcp_full_space(sk);
int full_space, window;
if (sk_is_mptcp(sk))
mptcp_space(sk, &free_space, &allowed_space);
full_space = min_t(int, tp->window_clamp, allowed_space);
if (unlikely(mss > full_space)) {
mss = full_space;
if (mss <= 0)
return 0;
}
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh,
4U * tp->advmss);
/* free_space might become our new window, make sure we don't
* increase it due to wscale.
*/
free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale);
/* if free space is less than mss estimate, or is below 1/16th
* of the maximum allowed, try to move to zero-window, else
* tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and
* new incoming data is dropped due to memory limits.
* With large window, mss test triggers way too late in order
* to announce zero window in time before rmem limit kicks in.
*/
if (free_space < (allowed_space >> 4) || free_space < mss)
return 0;
}
if (free_space > tp->rcv_ssthresh)
free_space = tp->rcv_ssthresh;
/* Don't do rounding if we are using window scaling, since the
* scaled window will not line up with the MSS boundary anyway.
*/
if (tp->rx_opt.rcv_wscale) {
window = free_space;
/* Advertise enough space so that it won't get scaled away.
* Import case: prevent zero window announcement if
* 1<<rcv_wscale > mss.
*/
window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale));
} else {
window = tp->rcv_wnd;
/* Get the largest window that is a nice multiple of mss.
* Window clamp already applied above.
* If our current window offering is within 1 mss of the
* free space we just keep it. This prevents the divide
* and multiply from happening most of the time.
* We also don't do any window rounding when the free space
* is too small.
*/
if (window <= free_space - mss || window > free_space)
window = rounddown(free_space, mss);
else if (mss == full_space &&
free_space > window + (full_space >> 1))
window = free_space;
}
return window;
}
void tcp_skb_collapse_tstamp(struct sk_buff *skb,
const struct sk_buff *next_skb)
{
if (unlikely(tcp_has_tx_tstamp(next_skb))) {
const struct skb_shared_info *next_shinfo =
skb_shinfo(next_skb);
struct skb_shared_info *shinfo = skb_shinfo(skb);
shinfo->tx_flags |= next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;
shinfo->tskey = next_shinfo->tskey;
TCP_SKB_CB(skb)->txstamp_ack |=
TCP_SKB_CB(next_skb)->txstamp_ack;
}
}
/* Collapses two adjacent SKB's during retransmission. */
static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *next_skb = skb_rb_next(skb);
int next_skb_size;
next_skb_size = next_skb->len;
BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
if (next_skb_size) {
if (next_skb_size <= skb_availroom(skb))
skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
next_skb_size);
else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size))
return false;
}
tcp_highest_sack_replace(sk, next_skb, skb);
/* Update sequence range on original skb. */
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
/* Merge over control information. This moves PSH/FIN etc. over */
TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags;
/* All done, get rid of second SKB and account for it so
* packet counting does not break.
*/
TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS;
TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor;
/* changed transmit queue under us so clear hints */
tcp_clear_retrans_hints_partial(tp);
if (next_skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = skb;
tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
tcp_skb_collapse_tstamp(skb, next_skb);
tcp_rtx_queue_unlink_and_free(next_skb, sk);
return true;
}
/* Check if coalescing SKBs is legal. */
static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
{
if (tcp_skb_pcount(skb) > 1)
return false;
if (skb_cloned(skb))
return false;
/* Some heuristics for collapsing over SACK'd could be invented */
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
return false;
return true;
}
/* Collapse packets in the retransmit queue to make to create
* less packets on the wire. This is only done on retransmission.
*/
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
int space)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = to, *tmp;
bool first = true;
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
return;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
return;
skb_rbtree_walk_from_safe(skb, tmp) {
if (!tcp_can_collapse(sk, skb))
break;
if (!tcp_skb_can_collapse(to, skb))
break;
space -= skb->len;
if (first) {
first = false;
continue;
}
if (space < 0)
break;
if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))
break;
if (!tcp_collapse_retrans(sk, to))
break;
}
}
/* This retransmits one SKB. Policy decisions and retransmit queue
* state updates are done by the caller. Returns non-zero if an
* error occurred which prevented the send.
*/
int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cur_mss;
int diff, len, err;
int avail_wnd;
/* Inconclusive MTU probe */
if (icsk->icsk_mtup.probe_size)
icsk->icsk_mtup.probe_size = 0;
if (skb_still_in_host_queue(sk, skb))
return -EBUSY;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
WARN_ON_ONCE(1);
return -EINVAL;
}
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
cur_mss = tcp_current_mss(sk);
avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
* our retransmit of one segment serves as a zero window probe.
*/
if (avail_wnd <= 0) {
if (TCP_SKB_CB(skb)->seq != tp->snd_una)
return -EAGAIN;
avail_wnd = cur_mss;
}
len = cur_mss * segs;
if (len > avail_wnd) {
len = rounddown(avail_wnd, cur_mss);
if (!len)
len = avail_wnd;
}
if (skb->len > len) {
if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
cur_mss, GFP_ATOMIC))
return -ENOMEM; /* We'll try again later. */
} else {
if (skb_unclone_keeptruesize(skb, GFP_ATOMIC))
return -ENOMEM;
diff = tcp_skb_pcount(skb);
tcp_set_skb_tso_segs(skb, cur_mss);
diff -= tcp_skb_pcount(skb);
if (diff)
tcp_adjust_pcount(sk, skb, diff);
avail_wnd = min_t(int, avail_wnd, cur_mss);
if (skb->len < avail_wnd)
tcp_retrans_try_collapse(sk, skb, avail_wnd);
}
/* RFC3168, section 6.1.1.1. ECN fallback */
if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
tcp_ecn_clear_syn(sk, skb);
/* Update global and local TCP statistics. */
segs = tcp_skb_pcount(skb);
TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
tp->total_retrans += segs;
tp->bytes_retrans += skb->len;
/* make sure skb->data is aligned on arches that require it
* and check if ack-trimming & collapsing extended the headroom
* beyond what csum_start can cover.
*/
if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
skb_headroom(skb) >= 0xFFFF)) {
struct sk_buff *nskb;
tcp_skb_tsorted_save(skb) {
nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
if (nskb) {
nskb->dev = NULL;
err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC);
} else {
err = -ENOBUFS;
}
} tcp_skb_tsorted_restore(skb);
if (!err) {
tcp_update_skb_after_send(sk, skb, tp->tcp_wstamp_ns);
tcp_rate_skb_sent(sk, skb);
}
} else {
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
/* To avoid taking spuriously low RTT samples based on a timestamp
* for a transmit that never happened, always mark EVER_RETRANS
*/
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
TCP_SKB_CB(skb)->seq, segs, err);
if (likely(!err)) {
trace_tcp_retransmit_skb(sk, skb);
} else if (err != -EBUSY) {
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
}
return err;
}
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
{
struct tcp_sock *tp = tcp_sk(sk);
int err = __tcp_retransmit_skb(sk, skb, segs);
if (err == 0) {
#if FASTRETRANS_DEBUG > 0
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
net_dbg_ratelimited("retrans_out leaked\n");
}
#endif
TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
tp->retrans_out += tcp_skb_pcount(skb);
}
/* Save stamp of the first (attempted) retransmit. */
if (!tp->retrans_stamp)
tp->retrans_stamp = tcp_skb_timestamp(skb);
if (tp->undo_retrans < 0)
tp->undo_retrans = 0;
tp->undo_retrans += tcp_skb_pcount(skb);
return err;
}
/* This gets called after a retransmit timeout, and the initially
* retransmitted data is acknowledged. It tries to continue
* resending the rest of the retransmit queue, until either
* we've sent it all or the congestion window limit is reached.
*/
void tcp_xmit_retransmit_queue(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb, *rtx_head, *hole = NULL;
struct tcp_sock *tp = tcp_sk(sk);
bool rearm_timer = false;
u32 max_segs;
int mib_idx;
if (!tp->packets_out)
return;
rtx_head = tcp_rtx_queue_head(sk);
skb = tp->retransmit_skb_hint ?: rtx_head;
max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
skb_rbtree_walk_from(skb) {
__u8 sacked;
int segs;
if (tcp_pacing_check(sk))
break;
/* we could do better than to assign each time */
if (!hole)
tp->retransmit_skb_hint = skb;
segs = tcp_snd_cwnd(tp) - tcp_packets_in_flight(tp);
if (segs <= 0)
break;
sacked = TCP_SKB_CB(skb)->sacked;
/* In case tcp_shift_skb_data() have aggregated large skbs,
* we need to make sure not sending too bigs TSO packets
*/
segs = min_t(int, segs, max_segs);
if (tp->retrans_out >= tp->lost_out) {
break;
} else if (!(sacked & TCPCB_LOST)) {
if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
hole = skb;
continue;
} else {
if (icsk->icsk_ca_state != TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPFASTRETRANS;
else
mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS;
}
if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
continue;
if (tcp_small_queue_check(sk, skb, 1))
break;
if (tcp_retransmit_skb(sk, skb, segs))
break;
NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb));
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += tcp_skb_pcount(skb);
if (skb == rtx_head &&
icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
rearm_timer = true;
}
if (rearm_timer)
tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto,
TCP_RTO_MAX);
}
/* We allow to exceed memory limits for FIN packets to expedite
* connection tear down and (memory) recovery.
* Otherwise tcp_send_fin() could be tempted to either delay FIN
* or even be forced to close flow without any FIN.
* In general, we want to allow one skb per socket to avoid hangs
* with edge trigger epoll()
*/
void sk_forced_mem_schedule(struct sock *sk, int size)
{
int delta, amt;
delta = size - sk->sk_forward_alloc;
if (delta <= 0)
return;
amt = sk_mem_pages(delta);
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
sk_memory_allocated_add(sk, amt);
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_charge_skmem(sk->sk_memcg, amt,
gfp_memcg_charge() | __GFP_NOFAIL);
}
/* Send a FIN. The caller locks the socket for us.
* We should try to send a FIN packet really hard, but eventually give up.
*/
void tcp_send_fin(struct sock *sk)
{
struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* Optimization, tack on the FIN if we have one skb in write queue and
* this skb was not yet sent, or we are under memory pressure.
* Note: in the latter case, FIN packet will be sent after a timeout,
* as TCP stack thinks it has already been transmitted.
*/
tskb = tail;
if (!tskb && tcp_under_memory_pressure(sk))
tskb = skb_rb_last(&sk->tcp_rtx_queue);
if (tskb) {
TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
if (!tail) {
/* This means tskb was already sent.
* Pretend we included the FIN on previous transmit.
* We need to set tp->snd_nxt to the value it would have
* if FIN had been sent. This is because retransmit path
* does not change tp->snd_nxt.
*/
WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1);
return;
}
} else {
skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
if (unlikely(!skb))
return;
INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
skb_reserve(skb, MAX_TCP_HEADER);
sk_forced_mem_schedule(sk, skb->truesize);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
* an explicit close() or as a byproduct of exit()'ing) and there
* was unread data in the receive queue. This behavior is recommended
* by RFC 2525, section 2.17. -DaveM
*/
void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
struct sk_buff *skb;
TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, MAX_TCP_HEADER);
tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
TCPHDR_ACK | TCPHDR_RST);
tcp_mstamp_refresh(tcp_sk(sk));
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
/* skb of trace_tcp_send_reset() keeps the skb that caused RST,
* skb here is different to the troublesome skb, so use NULL
*/
trace_tcp_send_reset(sk, NULL);
}
/* Send a crossed SYN-ACK during socket establishment.
* WARNING: This routine must only be called when we have already sent
* a SYN packet that crossed the incoming SYN that caused this routine
* to get called. If this assumption fails then the initial rcv_wnd
* and rcv_wscale values will not be correct.
*/
int tcp_send_synack(struct sock *sk)
{
struct sk_buff *skb;
skb = tcp_rtx_queue_head(sk);
if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
pr_err("%s: wrong queue state\n", __func__);
return -EFAULT;
}
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
if (skb_cloned(skb)) {
struct sk_buff *nskb;
tcp_skb_tsorted_save(skb) {
nskb = skb_copy(skb, GFP_ATOMIC);
} tcp_skb_tsorted_restore(skb);
if (!nskb)
return -ENOMEM;
INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
tcp_highest_sack_replace(sk, skb, nskb);
tcp_rtx_queue_unlink_and_free(skb, sk);
__skb_header_release(nskb);
tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
sk_wmem_queued_add(sk, nskb->truesize);
sk_mem_charge(sk, nskb->truesize);
skb = nskb;
}
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
tcp_ecn_send_synack(sk, skb);
}
return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
/**
* tcp_make_synack - Allocate one skb and build a SYNACK packet.
* @sk: listener socket
* @dst: dst entry attached to the SYNACK. It is consumed and caller
* should not use it again.
* @req: request_sock pointer
* @foc: cookie for tcp fast open
* @synack_type: Type of synack to prepare
* @syn_skb: SYN packet just received. It could be NULL for rtx case.
*/
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
const struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *md5 = NULL;
struct tcp_out_options opts;
struct sk_buff *skb;
int tcp_header_size;
struct tcphdr *th;
int mss;
u64 now;
skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
}
/* Reserve space for headers. */
skb_reserve(skb, MAX_TCP_HEADER);
switch (synack_type) {
case TCP_SYNACK_NORMAL:
skb_set_owner_w(skb, req_to_sk(req));
break;
case TCP_SYNACK_COOKIE:
/* Under synflood, we do not attach skb to a socket,
* to avoid false sharing.
*/
break;
case TCP_SYNACK_FASTOPEN:
/* sk is a const pointer, because we want to express multiple
* cpu might call us concurrently.
* sk->sk_wmem_alloc in an atomic, we can promote to rw.
*/
skb_set_owner_w(skb, (struct sock *)sk);
break;
}
skb_dst_set(skb, dst);
mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
memset(&opts, 0, sizeof(opts));
now = tcp_clock_ns();
#ifdef CONFIG_SYN_COOKIES
if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
skb->skb_mstamp_ns = cookie_init_timestamp(req, now);
else
#endif
{
skb->skb_mstamp_ns = now;
if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */
tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb);
}
#ifdef CONFIG_TCP_MD5SIG
rcu_read_lock();
md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
#endif
skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
/* bpf program will be interested in the tcp_flags */
TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
foc, synack_type,
syn_skb) + sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
th = (struct tcphdr *)skb->data;
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
tcp_ecn_make_synack(req, th);
th->source = htons(ireq->ir_num);
th->dest = ireq->ir_rmt_port;
skb->mark = ireq->ir_mark;
skb->ip_summed = CHECKSUM_PARTIAL;
th->seq = htonl(tcp_rsk(req)->snt_isn);
/* XXX data is queued and acked as is. No buffer/window check */
th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(min(req->rsk_rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), NULL, &opts);
th->doff = (tcp_header_size >> 2);
__TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5)
tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
md5, req_to_sk(req), skb);
rcu_read_unlock();
#endif
bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
synack_type, &opts);
skb->skb_mstamp_ns = now;
tcp_add_tx_delay(skb, tp);
return skb;
}
EXPORT_SYMBOL(tcp_make_synack);
static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
{
struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_congestion_ops *ca;
u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
if (ca_key == TCP_CA_UNSPEC)
return;
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
}
rcu_read_unlock();
}
/* Do all connect socket setups that can be done AF independent. */
static void tcp_connect_init(struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_sock *tp = tcp_sk(sk);
__u8 rcv_wscale;
u32 rcv_wnd;
/* We'll fix this up when we get a response from the other end.
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr);
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk))
tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
/* If user gave his TCP_MAXSEG, record it to clamp */
if (tp->rx_opt.user_mss)
tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
tp->max_window = 0;
tcp_mtup_init(sk);
tcp_sync_mss(sk, dst_mtu(dst));
tcp_ca_dst_init(sk, dst);
if (!tp->window_clamp)
tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
tcp_initialize_rcv_mss(sk);
/* limit the window selection if the user enforce a smaller rx buffer */
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
(tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
tp->window_clamp = tcp_full_space(sk);
rcv_wnd = tcp_rwnd_init_bpf(sk);
if (rcv_wnd == 0)
rcv_wnd = dst_metric(dst, RTAX_INITRWND);
tcp_select_initial_window(sk, tcp_full_space(sk),
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling),
&rcv_wscale,
rcv_wnd);
tp->rx_opt.rcv_wscale = rcv_wscale;
tp->rcv_ssthresh = tp->rcv_wnd;
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
tcp_init_wl(tp, 0);
tcp_write_queue_purge(sk);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
WRITE_ONCE(tp->snd_nxt, tp->write_seq);
if (likely(!tp->repair))
tp->rcv_nxt = 0;
else
tp->rcv_tstamp = tcp_jiffies32;
tp->rcv_wup = tp->rcv_nxt;
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
inet_csk(sk)->icsk_retransmits = 0;
tcp_clear_retrans(tp);
}
static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
tcb->end_seq += skb->len;
__skb_header_release(skb);
sk_wmem_queued_add(sk, skb->truesize);
sk_mem_charge(sk, skb->truesize);
WRITE_ONCE(tp->write_seq, tcb->end_seq);
tp->packets_out += tcp_skb_pcount(skb);
}
/* Build and send a SYN with data and (cached) Fast Open cookie. However,
* queue a data-only packet after the regular SYN, such that regular SYNs
* are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges
* only the SYN sequence, the data are retransmitted in the first ACK.
* If cookie is not cached or other error occurs, falls back to send a
* regular SYN with Fast Open cookie request option.
*/
static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
int space, err = 0;
struct sk_buff *syn_data;
tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie))
goto fallback;
/* MSS for SYN-data is based on cached MSS and bounded by PMTU and
* user-MSS. Reserve maximum option space for middleboxes that add
* private TCP options. The cost is reduced data space in SYN :(
*/
tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
/* Sync mss_cache after updating the mss_clamp */
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
space = min_t(size_t, space, fo->size);
/* limit to order-0 allocations */
space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false);
if (!syn_data)
goto fallback;
syn_data->ip_summed = CHECKSUM_PARTIAL;
memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
if (space) {
int copied = copy_from_iter(skb_put(syn_data, space), space,
&fo->data->msg_iter);
if (unlikely(!copied)) {
tcp_skb_tsorted_anchor_cleanup(syn_data);
kfree_skb(syn_data);
goto fallback;
}
if (copied != space) {
skb_trim(syn_data, copied);
space = copied;
}
skb_zcopy_set(syn_data, fo->uarg, NULL);
}
/* No more data pending in inet_wait_for_connect() */
if (space == fo->size)
fo->data = NULL;
fo->copied = space;
tcp_connect_queue_skb(sk, syn_data);
if (syn_data->len)
tcp_chrono_start(sk, TCP_CHRONO_BUSY);
err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
syn->skb_mstamp_ns = syn_data->skb_mstamp_ns;
/* Now full SYN+DATA was cloned and sent (or not),
* remove the SYN from the original skb (syn_data)
* we keep in write queue in case of a retransmit, as we
* also have the SYN packet (with no data) in the same queue.
*/
TCP_SKB_CB(syn_data)->seq++;
TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
if (!err) {
tp->syn_data = (fo->copied > 0);
tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
goto done;
}
/* data was not sent, put it in write_queue */
__skb_queue_tail(&sk->sk_write_queue, syn_data);
tp->packets_out -= tcp_skb_pcount(syn_data);
fallback:
/* Send a regular SYN with Fast Open cookie request option */
if (fo->cookie.len > 0)
fo->cookie.len = 0;
err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
if (err)
tp->syn_fastopen = 0;
done:
fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */
return err;
}
/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
int err;
tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
tcp_connect_init(sk);
if (unlikely(tp->repair)) {
tcp_finish_connect(sk, NULL);
return 0;
}
buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true);
if (unlikely(!buff))
return -ENOBUFS;
tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
tcp_mstamp_refresh(tp);
tp->retrans_stamp = tcp_time_stamp(tp);
tcp_connect_queue_skb(sk, buff);
tcp_ecn_send_syn(sk, buff);
tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
/* Send off SYN; include data in Fast Open. */
err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
if (err == -ECONNREFUSED)
return err;
/* We change tp->snd_nxt after the tcp_transmit_skb() call
* in order to make this packet get counted in tcpOutSegs.
*/
WRITE_ONCE(tp->snd_nxt, tp->write_seq);
tp->pushed_seq = tp->write_seq;
buff = tcp_send_head(sk);
if (unlikely(buff)) {
WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq);
tp->pushed_seq = TCP_SKB_CB(buff)->seq;
}
TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
return 0;
}
EXPORT_SYMBOL(tcp_connect);
/* Send out a delayed ack, the caller does the policy checking
* to see if we should even be here. See tcp_input.c:tcp_ack_snd_check()
* for details.
*/
void tcp_send_delayed_ack(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
if (inet_csk_in_pingpong_mode(sk) ||
(icsk->icsk_ack.pending & ICSK_ACK_PUSHED))
max_ato = TCP_DELACK_MAX;
/* Slow path, intersegment interval is "high". */
/* If some rtt estimate is known, use it to bound delayed ack.
* Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
* directly.
*/
if (tp->srtt_us) {
int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3),
TCP_DELACK_MIN);
if (rtt < max_ato)
max_ato = rtt;
}
ato = min(ato, max_ato);
}
ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
/* Stay within the limit we were given */
timeout = jiffies + ato;
/* Use new timeout only if there wasn't a older one earlier. */
if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
/* If delack timer is about to expire, send ACK now. */
if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
tcp_send_ack(sk);
return;
}
if (!time_before(timeout, icsk->icsk_ack.timeout))
timeout = icsk->icsk_ack.timeout;
}
icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = timeout;
sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
}
/* This routine sends an ack and also updates the window. */
void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;
/* If we have been reset, we may not send again. */
if (sk->sk_state == TCP_CLOSE)
return;
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
*/
buff = alloc_skb(MAX_TCP_HEADER,
sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
if (unlikely(!buff)) {
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long delay;
delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
if (delay < TCP_RTO_MAX)
icsk->icsk_ack.retry++;
inet_csk_schedule_ack(sk);
icsk->icsk_ack.ato = TCP_ATO_MIN;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(buff, MAX_TCP_HEADER);
tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
/* We do not want pure acks influencing TCP Small Queues or fq/pacing
* too much.
* SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784
*/
skb_set_tcp_pure_ack(buff);
/* Send it off, this clears delayed acks for us. */
__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
}
EXPORT_SYMBOL_GPL(__tcp_send_ack);
void tcp_send_ack(struct sock *sk)
{
__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
*
* Question: what should we make while urgent mode?
* 4.4BSD forces sending single byte of data. We cannot send
* out of window data, because we have SND.NXT==SND.MAX...
*
* Current solution: to send TWO zero-length segments in urgent mode:
* one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is
* out-of-date with SND.UNA-1 to probe window.
*/
static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
/* We don't queue it, tcp_transmit_skb() sets ownership. */
skb = alloc_skb(MAX_TCP_HEADER,
sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
if (!skb)
return -1;
/* Reserve space for headers and set control bits. */
skb_reserve(skb, MAX_TCP_HEADER);
/* Use a previous sequence. This should cause the other
* end to send an ack. Don't queue or clone SKB, just
* send it.
*/
tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
NET_INC_STATS(sock_net(sk), mib);
return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0);
}
/* Called from setsockopt( ... TCP_REPAIR ) */
void tcp_send_window_probe(struct sock *sk)
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
tcp_mstamp_refresh(tcp_sk(sk));
tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE);
}
}
/* Initiate keepalive or window probe from timer. */
int tcp_write_wakeup(struct sock *sk, int mib)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
if (sk->sk_state == TCP_CLOSE)
return -1;
skb = tcp_send_head(sk);
if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
int err;
unsigned int mss = tcp_current_mss(sk);
unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
tp->pushed_seq = TCP_SKB_CB(skb)->end_seq;
/* We are probing the opening of a window
* but the window size is != 0
* must have been a result SWS avoidance ( sender )
*/
if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq ||
skb->len > mss) {
seg_size = min(seg_size, mss);
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
skb, seg_size, mss, GFP_ATOMIC))
return -1;
} else if (!tcp_skb_pcount(skb))
tcp_set_skb_tso_segs(skb, mss);
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
if (!err)
tcp_event_new_data_sent(sk, skb);
return err;
} else {
if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
tcp_xmit_probe_skb(sk, 1, mib);
return tcp_xmit_probe_skb(sk, 0, mib);
}
}
/* A window probe timeout has occurred. If window is not closed send
* a partial packet else a zero probe.
*/
void tcp_send_probe0(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
unsigned long timeout;
int err;
err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
if (tp->packets_out || tcp_write_queue_empty(sk)) {
/* Cancel probe timer, if it is not required. */
icsk->icsk_probes_out = 0;
icsk->icsk_backoff = 0;
icsk->icsk_probes_tstamp = 0;
return;
}
icsk->icsk_probes_out++;
if (err <= 0) {
if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
icsk->icsk_backoff++;
timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
} else {
/* If packet was not sent due to local congestion,
* Let senders fight for local resources conservatively.
*/
timeout = TCP_RESOURCE_PROBE_INTERVAL;
}
timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX);
}
int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
{
const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific;
struct flowi fl;
int res;
tcp_rsk(req)->txhash = net_tx_rndhash();
res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
NULL);
if (!res) {
TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
if (unlikely(tcp_passive_fastopen(sk)))
tcp_sk(sk)->total_retrans++;
trace_tcp_retransmit_synack(sk, req);
}
return res;
}
EXPORT_SYMBOL(tcp_rtx_synack);
|