aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/filter.c
blob: e6c412b94decba010662b90240959320c4e77921 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
/*
 * Linux Socket Filter - Kernel level socket filtering
 *
 * Based on the design of the Berkeley Packet Filter. The new
 * internal format has been designed by PLUMgrid:
 *
 *	Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
 *
 * Authors:
 *
 *	Jay Schulist <jschlst@samba.org>
 *	Alexei Starovoitov <ast@plumgrid.com>
 *	Daniel Borkmann <dborkman@redhat.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 *
 * Andi Kleen - Fix a few bad bugs and races.
 * Kris Katterjohn - Added many additional checks in bpf_check_classic()
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/gfp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/netlink.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/flow_dissector.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <linux/filter.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
#include <linux/bpf.h>
#include <net/sch_generic.h>
#include <net/cls_cgroup.h>
#include <net/dst_metadata.h>
#include <net/dst.h>
#include <net/sock_reuseport.h>

/**
 *	sk_filter_trim_cap - run a packet through a socket filter
 *	@sk: sock associated with &sk_buff
 *	@skb: buffer to filter
 *	@cap: limit on how short the eBPF program may trim the packet
 *
 * Run the eBPF program and then cut skb->data to correct size returned by
 * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
 * than pkt_len we keep whole skb->data. This is the socket level
 * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
 * be accepted or -EPERM if the packet should be tossed.
 *
 */
int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
{
	int err;
	struct sk_filter *filter;

	/*
	 * If the skb was allocated from pfmemalloc reserves, only
	 * allow SOCK_MEMALLOC sockets to use it as this socket is
	 * helping free memory
	 */
	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
		return -ENOMEM;

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

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

	rcu_read_lock();
	filter = rcu_dereference(sk->sk_filter);
	if (filter) {
		unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
	}
	rcu_read_unlock();

	return err;
}
EXPORT_SYMBOL(sk_filter_trim_cap);

BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb)
{
	return skb_get_poff(skb);
}

BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
{
	struct nlattr *nla;

	if (skb_is_nonlinear(skb))
		return 0;

	if (skb->len < sizeof(struct nlattr))
		return 0;

	if (a > skb->len - sizeof(struct nlattr))
		return 0;

	nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x);
	if (nla)
		return (void *) nla - (void *) skb->data;

	return 0;
}

BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
{
	struct nlattr *nla;

	if (skb_is_nonlinear(skb))
		return 0;

	if (skb->len < sizeof(struct nlattr))
		return 0;

	if (a > skb->len - sizeof(struct nlattr))
		return 0;

	nla = (struct nlattr *) &skb->data[a];
	if (nla->nla_len > skb->len - a)
		return 0;

	nla = nla_find_nested(nla, x);
	if (nla)
		return (void *) nla - (void *) skb->data;

	return 0;
}

BPF_CALL_0(__get_raw_cpu_id)
{
	return raw_smp_processor_id();
}

static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
	.func		= __get_raw_cpu_id,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
};

static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
			      struct bpf_insn *insn_buf)
{
	struct bpf_insn *insn = insn_buf;

	switch (skb_field) {
	case SKF_AD_MARK:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);

		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sk_buff, mark));
		break;

	case SKF_AD_PKTTYPE:
		*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET());
		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX);
#ifdef __BIG_ENDIAN_BITFIELD
		*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5);
#endif
		break;

	case SKF_AD_QUEUE:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);

		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
				      offsetof(struct sk_buff, queue_mapping));
		break;

	case SKF_AD_VLAN_TAG:
	case SKF_AD_VLAN_TAG_PRESENT:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);

		/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
				      offsetof(struct sk_buff, vlan_tci));
		if (skb_field == SKF_AD_VLAN_TAG) {
			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
						~VLAN_TAG_PRESENT);
		} else {
			/* dst_reg >>= 12 */
			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
			/* dst_reg &= 1 */
			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
		}
		break;
	}

	return insn - insn_buf;
}

static bool convert_bpf_extensions(struct sock_filter *fp,
				   struct bpf_insn **insnp)
{
	struct bpf_insn *insn = *insnp;
	u32 cnt;

	switch (fp->k) {
	case SKF_AD_OFF + SKF_AD_PROTOCOL:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);

		/* A = *(u16 *) (CTX + offsetof(protocol)) */
		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
				      offsetof(struct sk_buff, protocol));
		/* A = ntohs(A) [emitting a nop or swap16] */
		*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
		break;

	case SKF_AD_OFF + SKF_AD_PKTTYPE:
		cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn);
		insn += cnt - 1;
		break;

	case SKF_AD_OFF + SKF_AD_IFINDEX:
	case SKF_AD_OFF + SKF_AD_HATYPE:
		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);

		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev),
				      BPF_REG_TMP, BPF_REG_CTX,
				      offsetof(struct sk_buff, dev));
		/* if (tmp != 0) goto pc + 1 */
		*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
		*insn++ = BPF_EXIT_INSN();
		if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX)
			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP,
					    offsetof(struct net_device, ifindex));
		else
			*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP,
					    offsetof(struct net_device, type));
		break;

	case SKF_AD_OFF + SKF_AD_MARK:
		cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn);
		insn += cnt - 1;
		break;

	case SKF_AD_OFF + SKF_AD_RXHASH:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);

		*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
				    offsetof(struct sk_buff, hash));
		break;

	case SKF_AD_OFF + SKF_AD_QUEUE:
		cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn);
		insn += cnt - 1;
		break;

	case SKF_AD_OFF + SKF_AD_VLAN_TAG:
		cnt = convert_skb_access(SKF_AD_VLAN_TAG,
					 BPF_REG_A, BPF_REG_CTX, insn);
		insn += cnt - 1;
		break;

	case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
		cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
					 BPF_REG_A, BPF_REG_CTX, insn);
		insn += cnt - 1;
		break;

	case SKF_AD_OFF + SKF_AD_VLAN_TPID:
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);

		/* A = *(u16 *) (CTX + offsetof(vlan_proto)) */
		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
				      offsetof(struct sk_buff, vlan_proto));
		/* A = ntohs(A) [emitting a nop or swap16] */
		*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
		break;

	case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
	case SKF_AD_OFF + SKF_AD_NLATTR:
	case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
	case SKF_AD_OFF + SKF_AD_CPU:
	case SKF_AD_OFF + SKF_AD_RANDOM:
		/* arg1 = CTX */
		*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
		/* arg2 = A */
		*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A);
		/* arg3 = X */
		*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X);
		/* Emit call(arg1=CTX, arg2=A, arg3=X) */
		switch (fp->k) {
		case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
			*insn = BPF_EMIT_CALL(__skb_get_pay_offset);
			break;
		case SKF_AD_OFF + SKF_AD_NLATTR:
			*insn = BPF_EMIT_CALL(__skb_get_nlattr);
			break;
		case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
			*insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
			break;
		case SKF_AD_OFF + SKF_AD_CPU:
			*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
			break;
		case SKF_AD_OFF + SKF_AD_RANDOM:
			*insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
			bpf_user_rnd_init_once();
			break;
		}
		break;

	case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
		/* A ^= X */
		*insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X);
		break;

	default:
		/* This is just a dummy call to avoid letting the compiler
		 * evict __bpf_call_base() as an optimization. Placed here
		 * where no-one bothers.
		 */
		BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
		return false;
	}

	*insnp = insn;
	return true;
}

/**
 *	bpf_convert_filter - convert filter program
 *	@prog: the user passed filter program
 *	@len: the length of the user passed filter program
 *	@new_prog: buffer where converted program will be stored
 *	@new_len: pointer to store length of converted program
 *
 * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
 * Conversion workflow:
 *
 * 1) First pass for calculating the new program length:
 *   bpf_convert_filter(old_prog, old_len, NULL, &new_len)
 *
 * 2) 2nd pass to remap in two passes: 1st pass finds new
 *    jump offsets, 2nd pass remapping:
 *   new_prog = kmalloc(sizeof(struct bpf_insn) * new_len);
 *   bpf_convert_filter(old_prog, old_len, new_prog, &new_len);
 */
static int bpf_convert_filter(struct sock_filter *prog, int len,
			      struct bpf_insn *new_prog, int *new_len)
{
	int new_flen = 0, pass = 0, target, i;
	struct bpf_insn *new_insn;
	struct sock_filter *fp;
	int *addrs = NULL;
	u8 bpf_src;

	BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);

	if (len <= 0 || len > BPF_MAXINSNS)
		return -EINVAL;

	if (new_prog) {
		addrs = kcalloc(len, sizeof(*addrs),
				GFP_KERNEL | __GFP_NOWARN);
		if (!addrs)
			return -ENOMEM;
	}

do_pass:
	new_insn = new_prog;
	fp = prog;

	/* Classic BPF related prologue emission. */
	if (new_insn) {
		/* Classic BPF expects A and X to be reset first. These need
		 * to be guaranteed to be the first two instructions.
		 */
		*new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
		*new_insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_X, BPF_REG_X);

		/* All programs must keep CTX in callee saved BPF_REG_CTX.
		 * In eBPF case it's done by the compiler, here we need to
		 * do this ourself. Initial CTX is present in BPF_REG_ARG1.
		 */
		*new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
	} else {
		new_insn += 3;
	}

	for (i = 0; i < len; fp++, i++) {
		struct bpf_insn tmp_insns[6] = { };
		struct bpf_insn *insn = tmp_insns;

		if (addrs)
			addrs[i] = new_insn - new_prog;

		switch (fp->code) {
		/* All arithmetic insns and skb loads map as-is. */
		case BPF_ALU | BPF_ADD | BPF_X:
		case BPF_ALU | BPF_ADD | BPF_K:
		case BPF_ALU | BPF_SUB | BPF_X:
		case BPF_ALU | BPF_SUB | BPF_K:
		case BPF_ALU | BPF_AND | BPF_X:
		case BPF_ALU | BPF_AND | BPF_K:
		case BPF_ALU | BPF_OR | BPF_X:
		case BPF_ALU | BPF_OR | BPF_K:
		case BPF_ALU | BPF_LSH | BPF_X:
		case BPF_ALU | BPF_LSH | BPF_K:
		case BPF_ALU | BPF_RSH | BPF_X:
		case BPF_ALU | BPF_RSH | BPF_K:
		case BPF_ALU | BPF_XOR | BPF_X:
		case BPF_ALU | BPF_XOR | BPF_K:
		case BPF_ALU | BPF_MUL | BPF_X:
		case BPF_ALU | BPF_MUL | BPF_K:
		case BPF_ALU | BPF_DIV | BPF_X:
		case BPF_ALU | BPF_DIV | BPF_K:
		case BPF_ALU | BPF_MOD | BPF_X:
		case BPF_ALU | BPF_MOD | BPF_K:
		case BPF_ALU | BPF_NEG:
		case BPF_LD | BPF_ABS | BPF_W:
		case BPF_LD | BPF_ABS | BPF_H:
		case BPF_LD | BPF_ABS | BPF_B:
		case BPF_LD | BPF_IND | BPF_W:
		case BPF_LD | BPF_IND | BPF_H:
		case BPF_LD | BPF_IND | BPF_B:
			/* Check for overloaded BPF extension and
			 * directly convert it if found, otherwise
			 * just move on with mapping.
			 */
			if (BPF_CLASS(fp->code) == BPF_LD &&
			    BPF_MODE(fp->code) == BPF_ABS &&
			    convert_bpf_extensions(fp, &insn))
				break;

			*insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
			break;

		/* Jump transformation cannot use BPF block macros
		 * everywhere as offset calculation and target updates
		 * require a bit more work than the rest, i.e. jump
		 * opcodes map as-is, but offsets need adjustment.
		 */

#define BPF_EMIT_JMP							\
	do {								\
		if (target >= len || target < 0)			\
			goto err;					\
		insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0;	\
		/* Adjust pc relative offset for 2nd or 3rd insn. */	\
		insn->off -= insn - tmp_insns;				\
	} while (0)

		case BPF_JMP | BPF_JA:
			target = i + fp->k + 1;
			insn->code = fp->code;
			BPF_EMIT_JMP;
			break;

		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
			if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
				/* BPF immediates are signed, zero extend
				 * immediate into tmp register and use it
				 * in compare insn.
				 */
				*insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);

				insn->dst_reg = BPF_REG_A;
				insn->src_reg = BPF_REG_TMP;
				bpf_src = BPF_X;
			} else {
				insn->dst_reg = BPF_REG_A;
				insn->imm = fp->k;
				bpf_src = BPF_SRC(fp->code);
				insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0;
			}

			/* Common case where 'jump_false' is next insn. */
			if (fp->jf == 0) {
				insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
				target = i + fp->jt + 1;
				BPF_EMIT_JMP;
				break;
			}

			/* Convert JEQ into JNE when 'jump_true' is next insn. */
			if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
				insn->code = BPF_JMP | BPF_JNE | bpf_src;
				target = i + fp->jf + 1;
				BPF_EMIT_JMP;
				break;
			}

			/* Other jumps are mapped into two insns: Jxx and JA. */
			target = i + fp->jt + 1;
			insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
			BPF_EMIT_JMP;
			insn++;

			insn->code = BPF_JMP | BPF_JA;
			target = i + fp->jf + 1;
			BPF_EMIT_JMP;
			break;

		/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
		case BPF_LDX | BPF_MSH | BPF_B:
			/* tmp = A */
			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
			/* A = BPF_R0 = *(u8 *) (skb->data + K) */
			*insn++ = BPF_LD_ABS(BPF_B, fp->k);
			/* A &= 0xf */
			*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
			/* A <<= 2 */
			*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
			/* X = A */
			*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
			/* A = tmp */
			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
			break;

		/* RET_K is remaped into 2 insns. RET_A case doesn't need an
		 * extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
		 */
		case BPF_RET | BPF_A:
		case BPF_RET | BPF_K:
			if (BPF_RVAL(fp->code) == BPF_K)
				*insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0,
							0, fp->k);
			*insn = BPF_EXIT_INSN();
			break;

		/* Store to stack. */
		case BPF_ST:
		case BPF_STX:
			*insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
					    BPF_ST ? BPF_REG_A : BPF_REG_X,
					    -(BPF_MEMWORDS - fp->k) * 4);
			break;

		/* Load from stack. */
		case BPF_LD | BPF_MEM:
		case BPF_LDX | BPF_MEM:
			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD  ?
					    BPF_REG_A : BPF_REG_X, BPF_REG_FP,
					    -(BPF_MEMWORDS - fp->k) * 4);
			break;

		/* A = K or X = K */
		case BPF_LD | BPF_IMM:
		case BPF_LDX | BPF_IMM:
			*insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ?
					      BPF_REG_A : BPF_REG_X, fp->k);
			break;

		/* X = A */
		case BPF_MISC | BPF_TAX:
			*insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
			break;

		/* A = X */
		case BPF_MISC | BPF_TXA:
			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X);
			break;

		/* A = skb->len or X = skb->len */
		case BPF_LD | BPF_W | BPF_LEN:
		case BPF_LDX | BPF_W | BPF_LEN:
			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
					    BPF_REG_A : BPF_REG_X, BPF_REG_CTX,
					    offsetof(struct sk_buff, len));
			break;

		/* Access seccomp_data fields. */
		case BPF_LDX | BPF_ABS | BPF_W:
			/* A = *(u32 *) (ctx + K) */
			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
			break;

		/* Unknown instruction. */
		default:
			goto err;
		}

		insn++;
		if (new_prog)
			memcpy(new_insn, tmp_insns,
			       sizeof(*insn) * (insn - tmp_insns));
		new_insn += insn - tmp_insns;
	}

	if (!new_prog) {
		/* Only calculating new length. */
		*new_len = new_insn - new_prog;
		return 0;
	}

	pass++;
	if (new_flen != new_insn - new_prog) {
		new_flen = new_insn - new_prog;
		if (pass > 2)
			goto err;
		goto do_pass;
	}

	kfree(addrs);
	BUG_ON(*new_len != new_flen);
	return 0;
err:
	kfree(addrs);
	return -EINVAL;
}

/* Security:
 *
 * As we dont want to clear mem[] array for each packet going through
 * __bpf_prog_run(), we check that filter loaded by user never try to read
 * a cell if not previously written, and we check all branches to be sure
 * a malicious user doesn't try to abuse us.
 */
static int check_load_and_stores(const struct sock_filter *filter, int flen)
{
	u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */
	int pc, ret = 0;

	BUILD_BUG_ON(BPF_MEMWORDS > 16);

	masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL);
	if (!masks)
		return -ENOMEM;

	memset(masks, 0xff, flen * sizeof(*masks));

	for (pc = 0; pc < flen; pc++) {
		memvalid &= masks[pc];

		switch (filter[pc].code) {
		case BPF_ST:
		case BPF_STX:
			memvalid |= (1 << filter[pc].k);
			break;
		case BPF_LD | BPF_MEM:
		case BPF_LDX | BPF_MEM:
			if (!(memvalid & (1 << filter[pc].k))) {
				ret = -EINVAL;
				goto error;
			}
			break;
		case BPF_JMP | BPF_JA:
			/* A jump must set masks on target */
			masks[pc + 1 + filter[pc].k] &= memvalid;
			memvalid = ~0;
			break;
		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
			/* A jump must set masks on targets */
			masks[pc + 1 + filter[pc].jt] &= memvalid;
			masks[pc + 1 + filter[pc].jf] &= memvalid;
			memvalid = ~0;
			break;
		}
	}
error:
	kfree(masks);
	return ret;
}

static bool chk_code_allowed(u16 code_to_probe)
{
	static const bool codes[] = {
		/* 32 bit ALU operations */
		[BPF_ALU | BPF_ADD | BPF_K] = true,
		[BPF_ALU | BPF_ADD | BPF_X] = true,
		[BPF_ALU | BPF_SUB | BPF_K] = true,
		[BPF_ALU | BPF_SUB | BPF_X] = true,
		[BPF_ALU | BPF_MUL | BPF_K] = true,
		[BPF_ALU | BPF_MUL | BPF_X] = true,
		[BPF_ALU | BPF_DIV | BPF_K] = true,
		[BPF_ALU | BPF_DIV | BPF_X] = true,
		[BPF_ALU | BPF_MOD | BPF_K] = true,
		[BPF_ALU | BPF_MOD | BPF_X] = true,
		[BPF_ALU | BPF_AND | BPF_K] = true,
		[BPF_ALU | BPF_AND | BPF_X] = true,
		[BPF_ALU | BPF_OR | BPF_K] = true,
		[BPF_ALU | BPF_OR | BPF_X] = true,
		[BPF_ALU | BPF_XOR | BPF_K] = true,
		[BPF_ALU | BPF_XOR | BPF_X] = true,
		[BPF_ALU | BPF_LSH | BPF_K] = true,
		[BPF_ALU | BPF_LSH | BPF_X] = true,
		[BPF_ALU | BPF_RSH | BPF_K] = true,
		[BPF_ALU | BPF_RSH | BPF_X] = true,
		[BPF_ALU | BPF_NEG] = true,
		/* Load instructions */
		[BPF_LD | BPF_W | BPF_ABS] = true,
		[BPF_LD | BPF_H | BPF_ABS] = true,
		[BPF_LD | BPF_B | BPF_ABS] = true,
		[BPF_LD | BPF_W | BPF_LEN] = true,
		[BPF_LD | BPF_W | BPF_IND] = true,
		[BPF_LD | BPF_H | BPF_IND] = true,
		[BPF_LD | BPF_B | BPF_IND] = true,
		[BPF_LD | BPF_IMM] = true,
		[BPF_LD | BPF_MEM] = true,
		[BPF_LDX | BPF_W | BPF_LEN] = true,
		[BPF_LDX | BPF_B | BPF_MSH] = true,
		[BPF_LDX | BPF_IMM] = true,
		[BPF_LDX | BPF_MEM] = true,
		/* Store instructions */
		[BPF_ST] = true,
		[BPF_STX] = true,
		/* Misc instructions */
		[BPF_MISC | BPF_TAX] = true,
		[BPF_MISC | BPF_TXA] = true,
		/* Return instructions */
		[BPF_RET | BPF_K] = true,
		[BPF_RET | BPF_A] = true,
		/* Jump instructions */
		[BPF_JMP | BPF_JA] = true,
		[BPF_JMP | BPF_JEQ | BPF_K] = true,
		[BPF_JMP | BPF_JEQ | BPF_X] = true,
		[BPF_JMP | BPF_JGE | BPF_K] = true,
		[BPF_JMP | BPF_JGE | BPF_X] = true,
		[BPF_JMP | BPF_JGT | BPF_K] = true,
		[BPF_JMP | BPF_JGT | BPF_X] = true,
		[BPF_JMP | BPF_JSET | BPF_K] = true,
		[BPF_JMP | BPF_JSET | BPF_X] = true,
	};

	if (code_to_probe >= ARRAY_SIZE(codes))
		return false;

	return codes[code_to_probe];
}

static bool bpf_check_basics_ok(const struct sock_filter *filter,
				unsigned int flen)
{
	if (filter == NULL)
		return false;
	if (flen == 0 || flen > BPF_MAXINSNS)
		return false;

	return true;
}

/**
 *	bpf_check_classic - verify socket filter code
 *	@filter: filter to verify
 *	@flen: length of filter
 *
 * Check the user's filter code. If we let some ugly
 * filter code slip through kaboom! The filter must contain
 * no references or jumps that are out of range, no illegal
 * instructions, and must end with a RET instruction.
 *
 * All jumps are forward as they are not signed.
 *
 * Returns 0 if the rule set is legal or -EINVAL if not.
 */
static int bpf_check_classic(const struct sock_filter *filter,
			     unsigned int flen)
{
	bool anc_found;
	int pc;

	/* Check the filter code now */
	for (pc = 0; pc < flen; pc++) {
		const struct sock_filter *ftest = &filter[pc];

		/* May we actually operate on this code? */
		if (!chk_code_allowed(ftest->code))
			return -EINVAL;

		/* Some instructions need special checks */
		switch (ftest->code) {
		case BPF_ALU | BPF_DIV | BPF_K:
		case BPF_ALU | BPF_MOD | BPF_K:
			/* Check for division by zero */
			if (ftest->k == 0)
				return -EINVAL;
			break;
		case BPF_ALU | BPF_LSH | BPF_K:
		case BPF_ALU | BPF_RSH | BPF_K:
			if (ftest->k >= 32)
				return -EINVAL;
			break;
		case BPF_LD | BPF_MEM:
		case BPF_LDX | BPF_MEM:
		case BPF_ST:
		case BPF_STX:
			/* Check for invalid memory addresses */
			if (ftest->k >= BPF_MEMWORDS)
				return -EINVAL;
			break;
		case BPF_JMP | BPF_JA:
			/* Note, the large ftest->k might cause loops.
			 * Compare this with conditional jumps below,
			 * where offsets are limited. --ANK (981016)
			 */
			if (ftest->k >= (unsigned int)(flen - pc - 1))
				return -EINVAL;
			break;
		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
			/* Both conditionals must be safe */
			if (pc + ftest->jt + 1 >= flen ||
			    pc + ftest->jf + 1 >= flen)
				return -EINVAL;
			break;
		case BPF_LD | BPF_W | BPF_ABS:
		case BPF_LD | BPF_H | BPF_ABS:
		case BPF_LD | BPF_B | BPF_ABS:
			anc_found = false;
			if (bpf_anc_helper(ftest) & BPF_ANC)
				anc_found = true;
			/* Ancillary operation unknown or unsupported */
			if (anc_found == false && ftest->k >= SKF_AD_OFF)
				return -EINVAL;
		}
	}

	/* Last instruction must be a RET code */
	switch (filter[flen - 1].code) {
	case BPF_RET | BPF_K:
	case BPF_RET | BPF_A:
		return check_load_and_stores(filter, flen);
	}

	return -EINVAL;
}

static int bpf_prog_store_orig_filter(struct bpf_prog *fp,
				      const struct sock_fprog *fprog)
{
	unsigned int fsize = bpf_classic_proglen(fprog);
	struct sock_fprog_kern *fkprog;

	fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
	if (!fp->orig_prog)
		return -ENOMEM;

	fkprog = fp->orig_prog;
	fkprog->len = fprog->len;

	fkprog->filter = kmemdup(fp->insns, fsize,
				 GFP_KERNEL | __GFP_NOWARN);
	if (!fkprog->filter) {
		kfree(fp->orig_prog);
		return -ENOMEM;
	}

	return 0;
}

static void bpf_release_orig_filter(struct bpf_prog *fp)
{
	struct sock_fprog_kern *fprog = fp->orig_prog;

	if (fprog) {
		kfree(fprog->filter);
		kfree(fprog);
	}
}

static void __bpf_prog_release(struct bpf_prog *prog)
{
	if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) {
		bpf_prog_put(prog);
	} else {
		bpf_release_orig_filter(prog);
		bpf_prog_free(prog);
	}
}

static void __sk_filter_release(struct sk_filter *fp)
{
	__bpf_prog_release(fp->prog);
	kfree(fp);
}

/**
 * 	sk_filter_release_rcu - Release a socket filter by rcu_head
 *	@rcu: rcu_head that contains the sk_filter to free
 */
static void sk_filter_release_rcu(struct rcu_head *rcu)
{
	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);

	__sk_filter_release(fp);
}

/**
 *	sk_filter_release - release a socket filter
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */
static void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
		call_rcu(&fp->rcu, sk_filter_release_rcu);
}

void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
{
	u32 filter_size = bpf_prog_size(fp->prog->len);

	atomic_sub(filter_size, &sk->sk_omem_alloc);
	sk_filter_release(fp);
}

/* try to charge the socket memory if there is space available
 * return true on success
 */
bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
	u32 filter_size = bpf_prog_size(fp->prog->len);

	/* same check as in sock_kmalloc() */
	if (filter_size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
		atomic_inc(&fp->refcnt);
		atomic_add(filter_size, &sk->sk_omem_alloc);
		return true;
	}
	return false;
}

static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
{
	struct sock_filter *old_prog;
	struct bpf_prog *old_fp;
	int err, new_len, old_len = fp->len;

	/* We are free to overwrite insns et al right here as it
	 * won't be used at this point in time anymore internally
	 * after the migration to the internal BPF instruction
	 * representation.
	 */
	BUILD_BUG_ON(sizeof(struct sock_filter) !=
		     sizeof(struct bpf_insn));

	/* Conversion cannot happen on overlapping memory areas,
	 * so we need to keep the user BPF around until the 2nd
	 * pass. At this time, the user BPF is stored in fp->insns.
	 */
	old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
			   GFP_KERNEL | __GFP_NOWARN);
	if (!old_prog) {
		err = -ENOMEM;
		goto out_err;
	}

	/* 1st pass: calculate the new program length. */
	err = bpf_convert_filter(old_prog, old_len, NULL, &new_len);
	if (err)
		goto out_err_free;

	/* Expand fp for appending the new filter representation. */
	old_fp = fp;
	fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0);
	if (!fp) {
		/* The old_fp is still around in case we couldn't
		 * allocate new memory, so uncharge on that one.
		 */
		fp = old_fp;
		err = -ENOMEM;
		goto out_err_free;
	}

	fp->len = new_len;

	/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
	err = bpf_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
	if (err)
		/* 2nd bpf_convert_filter() can fail only if it fails
		 * to allocate memory, remapping must succeed. Note,
		 * that at this time old_fp has already been released
		 * by krealloc().
		 */
		goto out_err_free;

	/* We are guaranteed to never error here with cBPF to eBPF
	 * transitions, since there's no issue with type compatibility
	 * checks on program arrays.
	 */
	fp = bpf_prog_select_runtime(fp, &err);

	kfree(old_prog);
	return fp;

out_err_free:
	kfree(old_prog);
out_err:
	__bpf_prog_release(fp);
	return ERR_PTR(err);
}

static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
					   bpf_aux_classic_check_t trans)
{
	int err;

	fp->bpf_func = NULL;
	fp->jited = 0;

	err = bpf_check_classic(fp->insns, fp->len);
	if (err) {
		__bpf_prog_release(fp);
		return ERR_PTR(err);
	}

	/* There might be additional checks and transformations
	 * needed on classic filters, f.e. in case of seccomp.
	 */
	if (trans) {
		err = trans(fp->insns, fp->len);
		if (err) {
			__bpf_prog_release(fp);
			return ERR_PTR(err);
		}
	}

	/* Probe if we can JIT compile the filter and if so, do
	 * the compilation of the filter.
	 */
	bpf_jit_compile(fp);

	/* JIT compiler couldn't process this filter, so do the
	 * internal BPF translation for the optimized interpreter.
	 */
	if (!fp->jited)
		fp = bpf_migrate_filter(fp);

	return fp;
}

/**
 *	bpf_prog_create - create an unattached filter
 *	@pfp: the unattached filter that is created
 *	@fprog: the filter program
 *
 * Create a filter independent of any socket. We first run some
 * sanity checks on it to make sure it does not explode on us later.
 * If an error occurs or there is insufficient memory for the filter
 * a negative errno code is returned. On success the return is zero.
 */
int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
{
	unsigned int fsize = bpf_classic_proglen(fprog);
	struct bpf_prog *fp;

	/* Make sure new filter is there and in the right amounts. */
	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
		return -EINVAL;

	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
	if (!fp)
		return -ENOMEM;

	memcpy(fp->insns, fprog->filter, fsize);

	fp->len = fprog->len;
	/* Since unattached filters are not copied back to user
	 * space through sk_get_filter(), we do not need to hold
	 * a copy here, and can spare us the work.
	 */
	fp->orig_prog = NULL;

	/* bpf_prepare_filter() already takes care of freeing
	 * memory in case something goes wrong.
	 */
	fp = bpf_prepare_filter(fp, NULL);
	if (IS_ERR(fp))
		return PTR_ERR(fp);

	*pfp = fp;
	return 0;
}
EXPORT_SYMBOL_GPL(bpf_prog_create);

/**
 *	bpf_prog_create_from_user - create an unattached filter from user buffer
 *	@pfp: the unattached filter that is created
 *	@fprog: the filter program
 *	@trans: post-classic verifier transformation handler
 *	@save_orig: save classic BPF program
 *
 * This function effectively does the same as bpf_prog_create(), only
 * that it builds up its insns buffer from user space provided buffer.
 * It also allows for passing a bpf_aux_classic_check_t handler.
 */
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
			      bpf_aux_classic_check_t trans, bool save_orig)
{
	unsigned int fsize = bpf_classic_proglen(fprog);
	struct bpf_prog *fp;
	int err;

	/* Make sure new filter is there and in the right amounts. */
	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
		return -EINVAL;

	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
	if (!fp)
		return -ENOMEM;

	if (copy_from_user(fp->insns, fprog->filter, fsize)) {
		__bpf_prog_free(fp);
		return -EFAULT;
	}

	fp->len = fprog->len;
	fp->orig_prog = NULL;

	if (save_orig) {
		err = bpf_prog_store_orig_filter(fp, fprog);
		if (err) {
			__bpf_prog_free(fp);
			return -ENOMEM;
		}
	}

	/* bpf_prepare_filter() already takes care of freeing
	 * memory in case something goes wrong.
	 */
	fp = bpf_prepare_filter(fp, trans);
	if (IS_ERR(fp))
		return PTR_ERR(fp);

	*pfp = fp;
	return 0;
}
EXPORT_SYMBOL_GPL(bpf_prog_create_from_user);

void bpf_prog_destroy(struct bpf_prog *fp)
{
	__bpf_prog_release(fp);
}
EXPORT_SYMBOL_GPL(bpf_prog_destroy);

static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
{
	struct sk_filter *fp, *old_fp;

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

	fp->prog = prog;
	atomic_set(&fp->refcnt, 0);

	if (!sk_filter_charge(sk, fp)) {
		kfree(fp);
		return -ENOMEM;
	}

	old_fp = rcu_dereference_protected(sk->sk_filter,
					   lockdep_sock_is_held(sk));
	rcu_assign_pointer(sk->sk_filter, fp);

	if (old_fp)
		sk_filter_uncharge(sk, old_fp);

	return 0;
}

static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk)
{
	struct bpf_prog *old_prog;
	int err;

	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
		return -ENOMEM;

	if (sk_unhashed(sk) && sk->sk_reuseport) {
		err = reuseport_alloc(sk);
		if (err)
			return err;
	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
		/* The socket wasn't bound with SO_REUSEPORT */
		return -EINVAL;
	}

	old_prog = reuseport_attach_prog(sk, prog);
	if (old_prog)
		bpf_prog_destroy(old_prog);

	return 0;
}

static
struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
{
	unsigned int fsize = bpf_classic_proglen(fprog);
	struct bpf_prog *prog;
	int err;

	if (sock_flag(sk, SOCK_FILTER_LOCKED))
		return ERR_PTR(-EPERM);

	/* Make sure new filter is there and in the right amounts. */
	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
		return ERR_PTR(-EINVAL);

	prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
	if (!prog)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(prog->insns, fprog->filter, fsize)) {
		__bpf_prog_free(prog);
		return ERR_PTR(-EFAULT);
	}

	prog->len = fprog->len;

	err = bpf_prog_store_orig_filter(prog, fprog);
	if (err) {
		__bpf_prog_free(prog);
		return ERR_PTR(-ENOMEM);
	}

	/* bpf_prepare_filter() already takes care of freeing
	 * memory in case something goes wrong.
	 */
	return bpf_prepare_filter(prog, NULL);
}

/**
 *	sk_attach_filter - attach a socket filter
 *	@fprog: the filter program
 *	@sk: the socket to use
 *
 * Attach the user's filter code. We first run some sanity checks on
 * it to make sure it does not explode on us later. If an error
 * occurs or there is insufficient memory for the filter a negative
 * errno code is returned. On success the return is zero.
 */
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
	struct bpf_prog *prog = __get_filter(fprog, sk);
	int err;

	if (IS_ERR(prog))
		return PTR_ERR(prog);

	err = __sk_attach_prog(prog, sk);
	if (err < 0) {
		__bpf_prog_release(prog);
		return err;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);

int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
	struct bpf_prog *prog = __get_filter(fprog, sk);
	int err;

	if (IS_ERR(prog))
		return PTR_ERR(prog);

	err = __reuseport_attach_prog(prog, sk);
	if (err < 0) {
		__bpf_prog_release(prog);
		return err;
	}

	return 0;
}

static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
{
	if (sock_flag(sk, SOCK_FILTER_LOCKED))
		return ERR_PTR(-EPERM);

	return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
}

int sk_attach_bpf(u32 ufd, struct sock *sk)
{
	struct bpf_prog *prog = __get_bpf(ufd, sk);
	int err;

	if (IS_ERR(prog))
		return PTR_ERR(prog);

	err = __sk_attach_prog(prog, sk);
	if (err < 0) {
		bpf_prog_put(prog);
		return err;
	}

	return 0;
}

int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
{
	struct bpf_prog *prog = __get_bpf(ufd, sk);
	int err;

	if (IS_ERR(prog))
		return PTR_ERR(prog);

	err = __reuseport_attach_prog(prog, sk);
	if (err < 0) {
		bpf_prog_put(prog);
		return err;
	}

	return 0;
}

struct bpf_scratchpad {
	union {
		__be32 diff[MAX_BPF_STACK / sizeof(__be32)];
		u8     buff[MAX_BPF_STACK];
	};
};

static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);

static inline int __bpf_try_make_writable(struct sk_buff *skb,
					  unsigned int write_len)
{
	return skb_ensure_writable(skb, write_len);
}

static inline int bpf_try_make_writable(struct sk_buff *skb,
					unsigned int write_len)
{
	int err = __bpf_try_make_writable(skb, write_len);

	bpf_compute_data_end(skb);
	return err;
}

static int bpf_try_make_head_writable(struct sk_buff *skb)
{
	return bpf_try_make_writable(skb, skb_headlen(skb));
}

static inline void bpf_push_mac_rcsum(struct sk_buff *skb)
{
	if (skb_at_tc_ingress(skb))
		skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
}

static inline void bpf_pull_mac_rcsum(struct sk_buff *skb)
{
	if (skb_at_tc_ingress(skb))
		skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len);
}

BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset,
	   const void *, from, u32, len, u64, flags)
{
	void *ptr;

	if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
		return -EINVAL;
	if (unlikely(offset > 0xffff))
		return -EFAULT;
	if (unlikely(bpf_try_make_writable(skb, offset + len)))
		return -EFAULT;

	ptr = skb->data + offset;
	if (flags & BPF_F_RECOMPUTE_CSUM)
		__skb_postpull_rcsum(skb, ptr, len, offset);

	memcpy(ptr, from, len);

	if (flags & BPF_F_RECOMPUTE_CSUM)
		__skb_postpush_rcsum(skb, ptr, len, offset);
	if (flags & BPF_F_INVALIDATE_HASH)
		skb_clear_hash(skb);

	return 0;
}

static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
	.func		= bpf_skb_store_bytes,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_STACK,
	.arg4_type	= ARG_CONST_STACK_SIZE,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset,
	   void *, to, u32, len)
{
	void *ptr;

	if (unlikely(offset > 0xffff))
		goto err_clear;

	ptr = skb_header_pointer(skb, offset, len, to);
	if (unlikely(!ptr))
		goto err_clear;
	if (ptr != to)
		memcpy(to, ptr, len);

	return 0;
err_clear:
	memset(to, 0, len);
	return -EFAULT;
}

static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
	.func		= bpf_skb_load_bytes,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_RAW_STACK,
	.arg4_type	= ARG_CONST_STACK_SIZE,
};

BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
{
	/* Idea is the following: should the needed direct read/write
	 * test fail during runtime, we can pull in more data and redo
	 * again, since implicitly, we invalidate previous checks here.
	 *
	 * Or, since we know how much we need to make read/writeable,
	 * this can be done once at the program beginning for direct
	 * access case. By this we overcome limitations of only current
	 * headroom being accessible.
	 */
	return bpf_try_make_writable(skb, len ? : skb_headlen(skb));
}

static const struct bpf_func_proto bpf_skb_pull_data_proto = {
	.func		= bpf_skb_pull_data,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};

BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
	   u64, from, u64, to, u64, flags)
{
	__sum16 *ptr;

	if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
		return -EINVAL;
	if (unlikely(offset > 0xffff || offset & 1))
		return -EFAULT;
	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
		return -EFAULT;

	ptr = (__sum16 *)(skb->data + offset);
	switch (flags & BPF_F_HDR_FIELD_MASK) {
	case 0:
		if (unlikely(from != 0))
			return -EINVAL;

		csum_replace_by_diff(ptr, to);
		break;
	case 2:
		csum_replace2(ptr, from, to);
		break;
	case 4:
		csum_replace4(ptr, from, to);
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static const struct bpf_func_proto bpf_l3_csum_replace_proto = {
	.func		= bpf_l3_csum_replace,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_ANYTHING,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset,
	   u64, from, u64, to, u64, flags)
{
	bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
	bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
	__sum16 *ptr;

	if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
			       BPF_F_HDR_FIELD_MASK)))
		return -EINVAL;
	if (unlikely(offset > 0xffff || offset & 1))
		return -EFAULT;
	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
		return -EFAULT;

	ptr = (__sum16 *)(skb->data + offset);
	if (is_mmzero && !*ptr)
		return 0;

	switch (flags & BPF_F_HDR_FIELD_MASK) {
	case 0:
		if (unlikely(from != 0))
			return -EINVAL;

		inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo);
		break;
	case 2:
		inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
		break;
	case 4:
		inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo);
		break;
	default:
		return -EINVAL;
	}

	if (is_mmzero && !*ptr)
		*ptr = CSUM_MANGLED_0;
	return 0;
}

static const struct bpf_func_proto bpf_l4_csum_replace_proto = {
	.func		= bpf_l4_csum_replace,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_ANYTHING,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
	   __be32 *, to, u32, to_size, __wsum, seed)
{
	struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
	u32 diff_size = from_size + to_size;
	int i, j = 0;

	/* This is quite flexible, some examples:
	 *
	 * from_size == 0, to_size > 0,  seed := csum --> pushing data
	 * from_size > 0,  to_size == 0, seed := csum --> pulling data
	 * from_size > 0,  to_size > 0,  seed := 0    --> diffing data
	 *
	 * Even for diffing, from_size and to_size don't need to be equal.
	 */
	if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) ||
		     diff_size > sizeof(sp->diff)))
		return -EINVAL;

	for (i = 0; i < from_size / sizeof(__be32); i++, j++)
		sp->diff[j] = ~from[i];
	for (i = 0; i <   to_size / sizeof(__be32); i++, j++)
		sp->diff[j] = to[i];

	return csum_partial(sp->diff, diff_size, seed);
}

static const struct bpf_func_proto bpf_csum_diff_proto = {
	.func		= bpf_csum_diff,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_STACK,
	.arg2_type	= ARG_CONST_STACK_SIZE_OR_ZERO,
	.arg3_type	= ARG_PTR_TO_STACK,
	.arg4_type	= ARG_CONST_STACK_SIZE_OR_ZERO,
	.arg5_type	= ARG_ANYTHING,
};

BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum)
{
	/* The interface is to be used in combination with bpf_csum_diff()
	 * for direct packet writes. csum rotation for alignment as well
	 * as emulating csum_sub() can be done from the eBPF program.
	 */
	if (skb->ip_summed == CHECKSUM_COMPLETE)
		return (skb->csum = csum_add(skb->csum, csum));

	return -ENOTSUPP;
}

static const struct bpf_func_proto bpf_csum_update_proto = {
	.func		= bpf_csum_update,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};

static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
{
	return dev_forward_skb(dev, skb);
}

static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
				      struct sk_buff *skb)
{
	int ret = ____dev_forward_skb(dev, skb);

	if (likely(!ret)) {
		skb->dev = dev;
		ret = netif_rx(skb);
	}

	return ret;
}

static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
{
	int ret;

	if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
		kfree_skb(skb);
		return -ENETDOWN;
	}

	skb->dev = dev;

	__this_cpu_inc(xmit_recursion);
	ret = dev_queue_xmit(skb);
	__this_cpu_dec(xmit_recursion);

	return ret;
}

static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
				 u32 flags)
{
	/* skb->mac_len is not set on normal egress */
	unsigned int mlen = skb->network_header - skb->mac_header;

	__skb_pull(skb, mlen);

	/* At ingress, the mac header has already been pulled once.
	 * At egress, skb_pospull_rcsum has to be done in case that
	 * the skb is originated from ingress (i.e. a forwarded skb)
	 * to ensure that rcsum starts at net header.
	 */
	if (!skb_at_tc_ingress(skb))
		skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
	skb_pop_mac_header(skb);
	skb_reset_mac_len(skb);
	return flags & BPF_F_INGRESS ?
	       __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb);
}

static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
				 u32 flags)
{
	/* Verify that a link layer header is carried */
	if (unlikely(skb->mac_header >= skb->network_header)) {
		kfree_skb(skb);
		return -ERANGE;
	}

	bpf_push_mac_rcsum(skb);
	return flags & BPF_F_INGRESS ?
	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}

static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
			  u32 flags)
{
	if (dev_is_mac_header_xmit(dev))
		return __bpf_redirect_common(skb, dev, flags);
	else
		return __bpf_redirect_no_mac(skb, dev, flags);
}

BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
{
	struct net_device *dev;
	struct sk_buff *clone;
	int ret;

	if (unlikely(flags & ~(BPF_F_INGRESS)))
		return -EINVAL;

	dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
	if (unlikely(!dev))
		return -EINVAL;

	clone = skb_clone(skb, GFP_ATOMIC);
	if (unlikely(!clone))
		return -ENOMEM;

	/* For direct write, we need to keep the invariant that the skbs
	 * we're dealing with need to be uncloned. Should uncloning fail
	 * here, we need to free the just generated clone to unclone once
	 * again.
	 */
	ret = bpf_try_make_head_writable(skb);
	if (unlikely(ret)) {
		kfree_skb(clone);
		return -ENOMEM;
	}

	return __bpf_redirect(clone, dev, flags);
}

static const struct bpf_func_proto bpf_clone_redirect_proto = {
	.func           = bpf_clone_redirect,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
	.arg2_type      = ARG_ANYTHING,
	.arg3_type      = ARG_ANYTHING,
};

struct redirect_info {
	u32 ifindex;
	u32 flags;
};

static DEFINE_PER_CPU(struct redirect_info, redirect_info);

BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
{
	struct redirect_info *ri = this_cpu_ptr(&redirect_info);

	if (unlikely(flags & ~(BPF_F_INGRESS)))
		return TC_ACT_SHOT;

	ri->ifindex = ifindex;
	ri->flags = flags;

	return TC_ACT_REDIRECT;
}

int skb_do_redirect(struct sk_buff *skb)
{
	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
	struct net_device *dev;

	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex);
	ri->ifindex = 0;
	if (unlikely(!dev)) {
		kfree_skb(skb);
		return -EINVAL;
	}

	return __bpf_redirect(skb, dev, ri->flags);
}

static const struct bpf_func_proto bpf_redirect_proto = {
	.func           = bpf_redirect,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_ANYTHING,
	.arg2_type      = ARG_ANYTHING,
};

BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
{
	return task_get_classid(skb);
}

static const struct bpf_func_proto bpf_get_cgroup_classid_proto = {
	.func           = bpf_get_cgroup_classid,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
};

BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb)
{
	return dst_tclassid(skb);
}

static const struct bpf_func_proto bpf_get_route_realm_proto = {
	.func           = bpf_get_route_realm,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
};

BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb)
{
	/* If skb_clear_hash() was called due to mangling, we can
	 * trigger SW recalculation here. Later access to hash
	 * can then use the inline skb->hash via context directly
	 * instead of calling this helper again.
	 */
	return skb_get_hash(skb);
}

static const struct bpf_func_proto bpf_get_hash_recalc_proto = {
	.func		= bpf_get_hash_recalc,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
};

BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb)
{
	/* After all direct packet write, this can be used once for
	 * triggering a lazy recalc on next skb_get_hash() invocation.
	 */
	skb_clear_hash(skb);
	return 0;
}

static const struct bpf_func_proto bpf_set_hash_invalid_proto = {
	.func		= bpf_set_hash_invalid,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
};

BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
	   u16, vlan_tci)
{
	int ret;

	if (unlikely(vlan_proto != htons(ETH_P_8021Q) &&
		     vlan_proto != htons(ETH_P_8021AD)))
		vlan_proto = htons(ETH_P_8021Q);

	bpf_push_mac_rcsum(skb);
	ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
	bpf_pull_mac_rcsum(skb);

	bpf_compute_data_end(skb);
	return ret;
}

const struct bpf_func_proto bpf_skb_vlan_push_proto = {
	.func           = bpf_skb_vlan_push,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
	.arg2_type      = ARG_ANYTHING,
	.arg3_type      = ARG_ANYTHING,
};
EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto);

BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
{
	int ret;

	bpf_push_mac_rcsum(skb);
	ret = skb_vlan_pop(skb);
	bpf_pull_mac_rcsum(skb);

	bpf_compute_data_end(skb);
	return ret;
}

const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
	.func           = bpf_skb_vlan_pop,
	.gpl_only       = false,
	.ret_type       = RET_INTEGER,
	.arg1_type      = ARG_PTR_TO_CTX,
};
EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);

static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
{
	/* Caller already did skb_cow() with len as headroom,
	 * so no need to do it here.
	 */
	skb_push(skb, len);
	memmove(skb->data, skb->data + len, off);
	memset(skb->data + off, 0, len);

	/* No skb_postpush_rcsum(skb, skb->data + off, len)
	 * needed here as it does not change the skb->csum
	 * result for checksum complete when summing over
	 * zeroed blocks.
	 */
	return 0;
}

static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
{
	/* skb_ensure_writable() is not needed here, as we're
	 * already working on an uncloned skb.
	 */
	if (unlikely(!pskb_may_pull(skb, off + len)))
		return -ENOMEM;

	skb_postpull_rcsum(skb, skb->data + off, len);
	memmove(skb->data + len, skb->data, off);
	__skb_pull(skb, len);

	return 0;
}

static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len)
{
	bool trans_same = skb->transport_header == skb->network_header;
	int ret;

	/* There's no need for __skb_push()/__skb_pull() pair to
	 * get to the start of the mac header as we're guaranteed
	 * to always start from here under eBPF.
	 */
	ret = bpf_skb_generic_push(skb, off, len);
	if (likely(!ret)) {
		skb->mac_header -= len;
		skb->network_header -= len;
		if (trans_same)
			skb->transport_header = skb->network_header;
	}

	return ret;
}

static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len)
{
	bool trans_same = skb->transport_header == skb->network_header;
	int ret;

	/* Same here, __skb_push()/__skb_pull() pair not needed. */
	ret = bpf_skb_generic_pop(skb, off, len);
	if (likely(!ret)) {
		skb->mac_header += len;
		skb->network_header += len;
		if (trans_same)
			skb->transport_header = skb->network_header;
	}

	return ret;
}

static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
{
	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
	u32 off = skb->network_header - skb->mac_header;
	int ret;

	ret = skb_cow(skb, len_diff);
	if (unlikely(ret < 0))
		return ret;

	ret = bpf_skb_net_hdr_push(skb, off, len_diff);
	if (unlikely(ret < 0))
		return ret;

	if (skb_is_gso(skb)) {
		/* SKB_GSO_UDP stays as is. SKB_GSO_TCPV4 needs to
		 * be changed into SKB_GSO_TCPV6.
		 */
		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
			skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4;
			skb_shinfo(skb)->gso_type |=  SKB_GSO_TCPV6;
		}

		/* Due to IPv6 header, MSS needs to be downgraded. */
		skb_shinfo(skb)->gso_size -= len_diff;
		/* Header must be checked, and gso_segs recomputed. */
		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
		skb_shinfo(skb)->gso_segs = 0;
	}

	skb->protocol = htons(ETH_P_IPV6);
	skb_clear_hash(skb);

	return 0;
}

static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
{
	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
	u32 off = skb->network_header - skb->mac_header;
	int ret;

	ret = skb_unclone(skb, GFP_ATOMIC);
	if (unlikely(ret < 0))
		return ret;

	ret = bpf_skb_net_hdr_pop(skb, off, len_diff);
	if (unlikely(ret < 0))
		return ret;

	if (skb_is_gso(skb)) {
		/* SKB_GSO_UDP stays as is. SKB_GSO_TCPV6 needs to
		 * be changed into SKB_GSO_TCPV4.
		 */
		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
			skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6;
			skb_shinfo(skb)->gso_type |=  SKB_GSO_TCPV4;
		}

		/* Due to IPv4 header, MSS can be upgraded. */
		skb_shinfo(skb)->gso_size += len_diff;
		/* Header must be checked, and gso_segs recomputed. */
		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
		skb_shinfo(skb)->gso_segs = 0;
	}

	skb->protocol = htons(ETH_P_IP);
	skb_clear_hash(skb);

	return 0;
}

static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
{
	__be16 from_proto = skb->protocol;

	if (from_proto == htons(ETH_P_IP) &&
	      to_proto == htons(ETH_P_IPV6))
		return bpf_skb_proto_4_to_6(skb);

	if (from_proto == htons(ETH_P_IPV6) &&
	      to_proto == htons(ETH_P_IP))
		return bpf_skb_proto_6_to_4(skb);

	return -ENOTSUPP;
}

BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
	   u64, flags)
{
	int ret;

	if (unlikely(flags))
		return -EINVAL;

	/* General idea is that this helper does the basic groundwork
	 * needed for changing the protocol, and eBPF program fills the
	 * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace()
	 * and other helpers, rather than passing a raw buffer here.
	 *
	 * The rationale is to keep this minimal and without a need to
	 * deal with raw packet data. F.e. even if we would pass buffers
	 * here, the program still needs to call the bpf_lX_csum_replace()
	 * helpers anyway. Plus, this way we keep also separation of
	 * concerns, since f.e. bpf_skb_store_bytes() should only take
	 * care of stores.
	 *
	 * Currently, additional options and extension header space are
	 * not supported, but flags register is reserved so we can adapt
	 * that. For offloads, we mark packet as dodgy, so that headers
	 * need to be verified first.
	 */
	ret = bpf_skb_proto_xlat(skb, proto);
	bpf_compute_data_end(skb);
	return ret;
}

static const struct bpf_func_proto bpf_skb_change_proto_proto = {
	.func		= bpf_skb_change_proto,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type)
{
	/* We only allow a restricted subset to be changed for now. */
	if (unlikely(!skb_pkt_type_ok(skb->pkt_type) ||
		     !skb_pkt_type_ok(pkt_type)))
		return -EINVAL;

	skb->pkt_type = pkt_type;
	return 0;
}

static const struct bpf_func_proto bpf_skb_change_type_proto = {
	.func		= bpf_skb_change_type,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};

static u32 __bpf_skb_min_len(const struct sk_buff *skb)
{
	u32 min_len = skb_network_offset(skb);

	if (skb_transport_header_was_set(skb))
		min_len = skb_transport_offset(skb);
	if (skb->ip_summed == CHECKSUM_PARTIAL)
		min_len = skb_checksum_start_offset(skb) +
			  skb->csum_offset + sizeof(__sum16);
	return min_len;
}

static u32 __bpf_skb_max_len(const struct sk_buff *skb)
{
	return skb->dev->mtu + skb->dev->hard_header_len;
}

static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len)
{
	unsigned int old_len = skb->len;
	int ret;

	ret = __skb_grow_rcsum(skb, new_len);
	if (!ret)
		memset(skb->data + old_len, 0, new_len - old_len);
	return ret;
}

static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
{
	return __skb_trim_rcsum(skb, new_len);
}

BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
	   u64, flags)
{
	u32 max_len = __bpf_skb_max_len(skb);
	u32 min_len = __bpf_skb_min_len(skb);
	int ret;

	if (unlikely(flags || new_len > max_len || new_len < min_len))
		return -EINVAL;
	if (skb->encapsulation)
		return -ENOTSUPP;

	/* The basic idea of this helper is that it's performing the
	 * needed work to either grow or trim an skb, and eBPF program
	 * rewrites the rest via helpers like bpf_skb_store_bytes(),
	 * bpf_lX_csum_replace() and others rather than passing a raw
	 * buffer here. This one is a slow path helper and intended
	 * for replies with control messages.
	 *
	 * Like in bpf_skb_change_proto(), we want to keep this rather
	 * minimal and without protocol specifics so that we are able
	 * to separate concerns as in bpf_skb_store_bytes() should only
	 * be the one responsible for writing buffers.
	 *
	 * It's really expected to be a slow path operation here for
	 * control message replies, so we're implicitly linearizing,
	 * uncloning and drop offloads from the skb by this.
	 */
	ret = __bpf_try_make_writable(skb, skb->len);
	if (!ret) {
		if (new_len > skb->len)
			ret = bpf_skb_grow_rcsum(skb, new_len);
		else if (new_len < skb->len)
			ret = bpf_skb_trim_rcsum(skb, new_len);
		if (!ret && skb_is_gso(skb))
			skb_gso_reset(skb);
	}

	bpf_compute_data_end(skb);
	return ret;
}

static const struct bpf_func_proto bpf_skb_change_tail_proto = {
	.func		= bpf_skb_change_tail,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
	   u64, flags)
{
	u32 max_len = __bpf_skb_max_len(skb);
	u32 new_len = skb->len + head_room;
	int ret;

	if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) ||
		     new_len < skb->len))
		return -EINVAL;

	ret = skb_cow(skb, head_room);
	if (likely(!ret)) {
		/* Idea for this helper is that we currently only
		 * allow to expand on mac header. This means that
		 * skb->protocol network header, etc, stay as is.
		 * Compared to bpf_skb_change_tail(), we're more
		 * flexible due to not needing to linearize or
		 * reset GSO. Intention for this helper is to be
		 * used by an L3 skb that needs to push mac header
		 * for redirection into L2 device.
		 */
		__skb_push(skb, head_room);
		memset(skb->data, 0, head_room);
		skb_reset_mac_header(skb);
	}

	bpf_compute_data_end(skb);
	return 0;
}

static const struct bpf_func_proto bpf_skb_change_head_proto = {
	.func		= bpf_skb_change_head,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_ANYTHING,
};

BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
{
	void *data = xdp->data + offset;

	if (unlikely(data < xdp->data_hard_start ||
		     data > xdp->data_end - ETH_HLEN))
		return -EINVAL;

	xdp->data = data;

	return 0;
}

static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
	.func		= bpf_xdp_adjust_head,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_ANYTHING,
};

bool bpf_helper_changes_pkt_data(void *func)
{
	if (func == bpf_skb_vlan_push ||
	    func == bpf_skb_vlan_pop ||
	    func == bpf_skb_store_bytes ||
	    func == bpf_skb_change_proto ||
	    func == bpf_skb_change_head ||
	    func == bpf_skb_change_tail ||
	    func == bpf_skb_pull_data ||
	    func == bpf_l3_csum_replace ||
	    func == bpf_l4_csum_replace ||
	    func == bpf_xdp_adjust_head)
		return true;

	return false;
}

static unsigned long bpf_skb_copy(void *dst_buff, const void *skb,
				  unsigned long off, unsigned long len)
{
	void *ptr = skb_header_pointer(skb, off, len, dst_buff);

	if (unlikely(!ptr))
		return len;
	if (ptr != dst_buff)
		memcpy(dst_buff, ptr, len);

	return 0;
}

BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map,
	   u64, flags, void *, meta, u64, meta_size)
{
	u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32;

	if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
		return -EINVAL;
	if (unlikely(skb_size > skb->len))
		return -EFAULT;

	return bpf_event_output(map, flags, meta, meta_size, skb, skb_size,
				bpf_skb_copy);
}

static const struct bpf_func_proto bpf_skb_event_output_proto = {
	.func		= bpf_skb_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_STACK,
	.arg5_type	= ARG_CONST_STACK_SIZE,
};

static unsigned short bpf_tunnel_key_af(u64 flags)
{
	return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET;
}

BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to,
	   u32, size, u64, flags)
{
	const struct ip_tunnel_info *info = skb_tunnel_info(skb);
	u8 compat[sizeof(struct bpf_tunnel_key)];
	void *to_orig = to;
	int err;

	if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6)))) {
		err = -EINVAL;
		goto err_clear;
	}
	if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) {
		err = -EPROTO;
		goto err_clear;
	}
	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
		err = -EINVAL;
		switch (size) {
		case offsetof(struct bpf_tunnel_key, tunnel_label):
		case offsetof(struct bpf_tunnel_key, tunnel_ext):
			goto set_compat;
		case offsetof(struct bpf_tunnel_key, remote_ipv6[1]):
			/* Fixup deprecated structure layouts here, so we have
			 * a common path later on.
			 */
			if (ip_tunnel_info_af(info) != AF_INET)
				goto err_clear;
set_compat:
			to = (struct bpf_tunnel_key *)compat;
			break;
		default:
			goto err_clear;
		}
	}

	to->tunnel_id = be64_to_cpu(info->key.tun_id);
	to->tunnel_tos = info->key.tos;
	to->tunnel_ttl = info->key.ttl;

	if (flags & BPF_F_TUNINFO_IPV6) {
		memcpy(to->remote_ipv6, &info->key.u.ipv6.src,
		       sizeof(to->remote_ipv6));
		to->tunnel_label = be32_to_cpu(info->key.label);
	} else {
		to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src);
	}

	if (unlikely(size != sizeof(struct bpf_tunnel_key)))
		memcpy(to_orig, to, size);

	return 0;
err_clear:
	memset(to_orig, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = {
	.func		= bpf_skb_get_tunnel_key,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_RAW_STACK,
	.arg3_type	= ARG_CONST_STACK_SIZE,
	.arg4_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size)
{
	const struct ip_tunnel_info *info = skb_tunnel_info(skb);
	int err;

	if (unlikely(!info ||
		     !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) {
		err = -ENOENT;
		goto err_clear;
	}
	if (unlikely(size < info->options_len)) {
		err = -ENOMEM;
		goto err_clear;
	}

	ip_tunnel_info_opts_get(to, info);
	if (size > info->options_len)
		memset(to + info->options_len, 0, size - info->options_len);

	return info->options_len;
err_clear:
	memset(to, 0, size);
	return err;
}

static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = {
	.func		= bpf_skb_get_tunnel_opt,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_RAW_STACK,
	.arg3_type	= ARG_CONST_STACK_SIZE,
};

static struct metadata_dst __percpu *md_dst;

BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
	   const struct bpf_tunnel_key *, from, u32, size, u64, flags)
{
	struct metadata_dst *md = this_cpu_ptr(md_dst);
	u8 compat[sizeof(struct bpf_tunnel_key)];
	struct ip_tunnel_info *info;

	if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
			       BPF_F_DONT_FRAGMENT)))
		return -EINVAL;
	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
		switch (size) {
		case offsetof(struct bpf_tunnel_key, tunnel_label):
		case offsetof(struct bpf_tunnel_key, tunnel_ext):
		case offsetof(struct bpf_tunnel_key, remote_ipv6[1]):
			/* Fixup deprecated structure layouts here, so we have
			 * a common path later on.
			 */
			memcpy(compat, from, size);
			memset(compat + size, 0, sizeof(compat) - size);
			from = (const struct bpf_tunnel_key *) compat;
			break;
		default:
			return -EINVAL;
		}
	}
	if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) ||
		     from->tunnel_ext))
		return -EINVAL;

	skb_dst_drop(skb);
	dst_hold((struct dst_entry *) md);
	skb_dst_set(skb, (struct dst_entry *) md);

	info = &md->u.tun_info;
	info->mode = IP_TUNNEL_INFO_TX;

	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
	if (flags & BPF_F_DONT_FRAGMENT)
		info->key.tun_flags |= TUNNEL_DONT_FRAGMENT;

	info->key.tun_id = cpu_to_be64(from->tunnel_id);
	info->key.tos = from->tunnel_tos;
	info->key.ttl = from->tunnel_ttl;

	if (flags & BPF_F_TUNINFO_IPV6) {
		info->mode |= IP_TUNNEL_INFO_IPV6;
		memcpy(&info->key.u.ipv6.dst, from->remote_ipv6,
		       sizeof(from->remote_ipv6));
		info->key.label = cpu_to_be32(from->tunnel_label) &
				  IPV6_FLOWLABEL_MASK;
	} else {
		info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
		if (flags & BPF_F_ZERO_CSUM_TX)
			info->key.tun_flags &= ~TUNNEL_CSUM;
	}

	return 0;
}

static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = {
	.func		= bpf_skb_set_tunnel_key,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_STACK,
	.arg3_type	= ARG_CONST_STACK_SIZE,
	.arg4_type	= ARG_ANYTHING,
};

BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb,
	   const u8 *, from, u32, size)
{
	struct ip_tunnel_info *info = skb_tunnel_info(skb);
	const struct metadata_dst *md = this_cpu_ptr(md_dst);

	if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1))))
		return -EINVAL;
	if (unlikely(size > IP_TUNNEL_OPTS_MAX))
		return -ENOMEM;

	ip_tunnel_info_opts_set(info, from, size);

	return 0;
}

static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = {
	.func		= bpf_skb_set_tunnel_opt,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_STACK,
	.arg3_type	= ARG_CONST_STACK_SIZE,
};

static const struct bpf_func_proto *
bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
{
	if (!md_dst) {
		/* Race is not possible, since it's called from verifier
		 * that is holding verifier mutex.
		 */
		md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
						   GFP_KERNEL);
		if (!md_dst)
			return NULL;
	}

	switch (which) {
	case BPF_FUNC_skb_set_tunnel_key:
		return &bpf_skb_set_tunnel_key_proto;
	case BPF_FUNC_skb_set_tunnel_opt:
		return &bpf_skb_set_tunnel_opt_proto;
	default:
		return NULL;
	}
}

BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map,
	   u32, idx)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct cgroup *cgrp;
	struct sock *sk;

	sk = skb_to_full_sk(skb);
	if (!sk || !sk_fullsock(sk))
		return -ENOENT;
	if (unlikely(idx >= array->map.max_entries))
		return -E2BIG;

	cgrp = READ_ONCE(array->ptrs[idx]);
	if (unlikely(!cgrp))
		return -EAGAIN;

	return sk_under_cgroup_hierarchy(sk, cgrp);
}

static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
	.func		= bpf_skb_under_cgroup,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
				  unsigned long off, unsigned long len)
{
	memcpy(dst_buff, src_buff + off, len);
	return 0;
}

BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map,
	   u64, flags, void *, meta, u64, meta_size)
{
	u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32;

	if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
		return -EINVAL;
	if (unlikely(xdp_size > (unsigned long)(xdp->data_end - xdp->data)))
		return -EFAULT;

	return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size,
				bpf_xdp_copy);
}

static const struct bpf_func_proto bpf_xdp_event_output_proto = {
	.func		= bpf_xdp_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_STACK,
	.arg5_type	= ARG_CONST_STACK_SIZE,
};

static const struct bpf_func_proto *
sk_filter_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_get_prandom_u32:
		return &bpf_get_prandom_u32_proto;
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_raw_smp_processor_id_proto;
	case BPF_FUNC_get_numa_node_id:
		return &bpf_get_numa_node_id_proto;
	case BPF_FUNC_tail_call:
		return &bpf_tail_call_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	case BPF_FUNC_trace_printk:
		if (capable(CAP_SYS_ADMIN))
			return bpf_get_trace_printk_proto();
	default:
		return NULL;
	}
}

static const struct bpf_func_proto *
tc_cls_act_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_skb_store_bytes:
		return &bpf_skb_store_bytes_proto;
	case BPF_FUNC_skb_load_bytes:
		return &bpf_skb_load_bytes_proto;
	case BPF_FUNC_skb_pull_data:
		return &bpf_skb_pull_data_proto;
	case BPF_FUNC_csum_diff:
		return &bpf_csum_diff_proto;
	case BPF_FUNC_csum_update:
		return &bpf_csum_update_proto;
	case BPF_FUNC_l3_csum_replace:
		return &bpf_l3_csum_replace_proto;
	case BPF_FUNC_l4_csum_replace:
		return &bpf_l4_csum_replace_proto;
	case BPF_FUNC_clone_redirect:
		return &bpf_clone_redirect_proto;
	case BPF_FUNC_get_cgroup_classid:
		return &bpf_get_cgroup_classid_proto;
	case BPF_FUNC_skb_vlan_push:
		return &bpf_skb_vlan_push_proto;
	case BPF_FUNC_skb_vlan_pop:
		return &bpf_skb_vlan_pop_proto;
	case BPF_FUNC_skb_change_proto:
		return &bpf_skb_change_proto_proto;
	case BPF_FUNC_skb_change_type:
		return &bpf_skb_change_type_proto;
	case BPF_FUNC_skb_change_tail:
		return &bpf_skb_change_tail_proto;
	case BPF_FUNC_skb_get_tunnel_key:
		return &bpf_skb_get_tunnel_key_proto;
	case BPF_FUNC_skb_set_tunnel_key:
		return bpf_get_skb_set_tunnel_proto(func_id);
	case BPF_FUNC_skb_get_tunnel_opt:
		return &bpf_skb_get_tunnel_opt_proto;
	case BPF_FUNC_skb_set_tunnel_opt:
		return bpf_get_skb_set_tunnel_proto(func_id);
	case BPF_FUNC_redirect:
		return &bpf_redirect_proto;
	case BPF_FUNC_get_route_realm:
		return &bpf_get_route_realm_proto;
	case BPF_FUNC_get_hash_recalc:
		return &bpf_get_hash_recalc_proto;
	case BPF_FUNC_set_hash_invalid:
		return &bpf_set_hash_invalid_proto;
	case BPF_FUNC_perf_event_output:
		return &bpf_skb_event_output_proto;
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_skb_under_cgroup:
		return &bpf_skb_under_cgroup_proto;
	default:
		return sk_filter_func_proto(func_id);
	}
}

static const struct bpf_func_proto *
xdp_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_xdp_event_output_proto;
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_xdp_adjust_head:
		return &bpf_xdp_adjust_head_proto;
	default:
		return sk_filter_func_proto(func_id);
	}
}

static const struct bpf_func_proto *
cg_skb_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_skb_load_bytes:
		return &bpf_skb_load_bytes_proto;
	default:
		return sk_filter_func_proto(func_id);
	}
}

static const struct bpf_func_proto *
lwt_inout_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_skb_load_bytes:
		return &bpf_skb_load_bytes_proto;
	case BPF_FUNC_skb_pull_data:
		return &bpf_skb_pull_data_proto;
	case BPF_FUNC_csum_diff:
		return &bpf_csum_diff_proto;
	case BPF_FUNC_get_cgroup_classid:
		return &bpf_get_cgroup_classid_proto;
	case BPF_FUNC_get_route_realm:
		return &bpf_get_route_realm_proto;
	case BPF_FUNC_get_hash_recalc:
		return &bpf_get_hash_recalc_proto;
	case BPF_FUNC_perf_event_output:
		return &bpf_skb_event_output_proto;
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_skb_under_cgroup:
		return &bpf_skb_under_cgroup_proto;
	default:
		return sk_filter_func_proto(func_id);
	}
}

static const struct bpf_func_proto *
lwt_xmit_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_skb_get_tunnel_key:
		return &bpf_skb_get_tunnel_key_proto;
	case BPF_FUNC_skb_set_tunnel_key:
		return bpf_get_skb_set_tunnel_proto(func_id);
	case BPF_FUNC_skb_get_tunnel_opt:
		return &bpf_skb_get_tunnel_opt_proto;
	case BPF_FUNC_skb_set_tunnel_opt:
		return bpf_get_skb_set_tunnel_proto(func_id);
	case BPF_FUNC_redirect:
		return &bpf_redirect_proto;
	case BPF_FUNC_clone_redirect:
		return &bpf_clone_redirect_proto;
	case BPF_FUNC_skb_change_tail:
		return &bpf_skb_change_tail_proto;
	case BPF_FUNC_skb_change_head:
		return &bpf_skb_change_head_proto;
	case BPF_FUNC_skb_store_bytes:
		return &bpf_skb_store_bytes_proto;
	case BPF_FUNC_csum_update:
		return &bpf_csum_update_proto;
	case BPF_FUNC_l3_csum_replace:
		return &bpf_l3_csum_replace_proto;
	case BPF_FUNC_l4_csum_replace:
		return &bpf_l4_csum_replace_proto;
	case BPF_FUNC_set_hash_invalid:
		return &bpf_set_hash_invalid_proto;
	default:
		return lwt_inout_func_proto(func_id);
	}
}

static bool __is_valid_access(int off, int size)
{
	if (off < 0 || off >= sizeof(struct __sk_buff))
		return false;
	/* The verifier guarantees that size > 0. */
	if (off % size != 0)
		return false;
	if (size != sizeof(__u32))
		return false;

	return true;
}

static bool sk_filter_is_valid_access(int off, int size,
				      enum bpf_access_type type,
				      enum bpf_reg_type *reg_type)
{
	switch (off) {
	case offsetof(struct __sk_buff, tc_classid):
	case offsetof(struct __sk_buff, data):
	case offsetof(struct __sk_buff, data_end):
		return false;
	}

	if (type == BPF_WRITE) {
		switch (off) {
		case offsetof(struct __sk_buff, cb[0]) ...
		     offsetof(struct __sk_buff, cb[4]):
			break;
		default:
			return false;
		}
	}

	return __is_valid_access(off, size);
}

static bool lwt_is_valid_access(int off, int size,
				enum bpf_access_type type,
				enum bpf_reg_type *reg_type)
{
	switch (off) {
	case offsetof(struct __sk_buff, tc_classid):
		return false;
	}

	if (type == BPF_WRITE) {
		switch (off) {
		case offsetof(struct __sk_buff, mark):
		case offsetof(struct __sk_buff, priority):
		case offsetof(struct __sk_buff, cb[0]) ...
		     offsetof(struct __sk_buff, cb[4]):
			break;
		default:
			return false;
		}
	}

	switch (off) {
	case offsetof(struct __sk_buff, data):
		*reg_type = PTR_TO_PACKET;
		break;
	case offsetof(struct __sk_buff, data_end):
		*reg_type = PTR_TO_PACKET_END;
		break;
	}

	return __is_valid_access(off, size);
}

static bool sock_filter_is_valid_access(int off, int size,
					enum bpf_access_type type,
					enum bpf_reg_type *reg_type)
{
	if (type == BPF_WRITE) {
		switch (off) {
		case offsetof(struct bpf_sock, bound_dev_if):
			break;
		default:
			return false;
		}
	}

	if (off < 0 || off + size > sizeof(struct bpf_sock))
		return false;
	/* The verifier guarantees that size > 0. */
	if (off % size != 0)
		return false;
	if (size != sizeof(__u32))
		return false;

	return true;
}

static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
			       const struct bpf_prog *prog)
{
	struct bpf_insn *insn = insn_buf;

	if (!direct_write)
		return 0;

	/* if (!skb->cloned)
	 *       goto start;
	 *
	 * (Fast-path, otherwise approximation that we might be
	 *  a clone, do the rest in helper.)
	 */
	*insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET());
	*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK);
	*insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7);

	/* ret = bpf_skb_pull_data(skb, 0); */
	*insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
	*insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2);
	*insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
			       BPF_FUNC_skb_pull_data);
	/* if (!ret)
	 *      goto restore;
	 * return TC_ACT_SHOT;
	 */
	*insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2);
	*insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, TC_ACT_SHOT);
	*insn++ = BPF_EXIT_INSN();

	/* restore: */
	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
	/* start: */
	*insn++ = prog->insnsi[0];

	return insn - insn_buf;
}

static bool tc_cls_act_is_valid_access(int off, int size,
				       enum bpf_access_type type,
				       enum bpf_reg_type *reg_type)
{
	if (type == BPF_WRITE) {
		switch (off) {
		case offsetof(struct __sk_buff, mark):
		case offsetof(struct __sk_buff, tc_index):
		case offsetof(struct __sk_buff, priority):
		case offsetof(struct __sk_buff, cb[0]) ...
		     offsetof(struct __sk_buff, cb[4]):
		case offsetof(struct __sk_buff, tc_classid):
			break;
		default:
			return false;
		}
	}

	switch (off) {
	case offsetof(struct __sk_buff, data):
		*reg_type = PTR_TO_PACKET;
		break;
	case offsetof(struct __sk_buff, data_end):
		*reg_type = PTR_TO_PACKET_END;
		break;
	}

	return __is_valid_access(off, size);
}

static bool __is_valid_xdp_access(int off, int size)
{
	if (off < 0 || off >= sizeof(struct xdp_md))
		return false;
	if (off % size != 0)
		return false;
	if (size != sizeof(__u32))
		return false;

	return true;
}

static bool xdp_is_valid_access(int off, int size,
				enum bpf_access_type type,
				enum bpf_reg_type *reg_type)
{
	if (type == BPF_WRITE)
		return false;

	switch (off) {
	case offsetof(struct xdp_md, data):
		*reg_type = PTR_TO_PACKET;
		break;
	case offsetof(struct xdp_md, data_end):
		*reg_type = PTR_TO_PACKET_END;
		break;
	}

	return __is_valid_xdp_access(off, size);
}

void bpf_warn_invalid_xdp_action(u32 act)
{
	WARN_ONCE(1, "Illegal XDP return value %u, expect packet loss\n", act);
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);

void bpf_warn_invalid_xdp_buffer(void)
{
	WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);

static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
					int src_reg, int ctx_off,
					struct bpf_insn *insn_buf,
					struct bpf_prog *prog)
{
	struct bpf_insn *insn = insn_buf;

	switch (ctx_off) {
	case offsetof(struct __sk_buff, len):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);

		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sk_buff, len));
		break;

	case offsetof(struct __sk_buff, protocol):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);

		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
				      offsetof(struct sk_buff, protocol));
		break;

	case offsetof(struct __sk_buff, vlan_proto):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);

		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
				      offsetof(struct sk_buff, vlan_proto));
		break;

	case offsetof(struct __sk_buff, priority):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);

		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
					      offsetof(struct sk_buff, priority));
		else
			*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
					      offsetof(struct sk_buff, priority));
		break;

	case offsetof(struct __sk_buff, ingress_ifindex):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4);

		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sk_buff, skb_iif));
		break;

	case offsetof(struct __sk_buff, ifindex):
		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);

		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev),
				      dst_reg, src_reg,
				      offsetof(struct sk_buff, dev));
		*insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1);
		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg,
				      offsetof(struct net_device, ifindex));
		break;

	case offsetof(struct __sk_buff, hash):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);

		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sk_buff, hash));
		break;

	case offsetof(struct __sk_buff, mark):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);

		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
					      offsetof(struct sk_buff, mark));
		else
			*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
					      offsetof(struct sk_buff, mark));
		break;

	case offsetof(struct __sk_buff, pkt_type):
		return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn);

	case offsetof(struct __sk_buff, queue_mapping):
		return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn);

	case offsetof(struct __sk_buff, vlan_present):
		return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
					  dst_reg, src_reg, insn);

	case offsetof(struct __sk_buff, vlan_tci):
		return convert_skb_access(SKF_AD_VLAN_TAG,
					  dst_reg, src_reg, insn);

	case offsetof(struct __sk_buff, cb[0]) ...
	     offsetof(struct __sk_buff, cb[4]):
		BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);

		prog->cb_access = 1;
		ctx_off -= offsetof(struct __sk_buff, cb[0]);
		ctx_off += offsetof(struct sk_buff, cb);
		ctx_off += offsetof(struct qdisc_skb_cb, data);
		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
		else
			*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
		break;

	case offsetof(struct __sk_buff, tc_classid):
		ctx_off -= offsetof(struct __sk_buff, tc_classid);
		ctx_off += offsetof(struct sk_buff, cb);
		ctx_off += offsetof(struct qdisc_skb_cb, tc_classid);
		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off);
		else
			*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, ctx_off);
		break;

	case offsetof(struct __sk_buff, data):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
				      dst_reg, src_reg,
				      offsetof(struct sk_buff, data));
		break;

	case offsetof(struct __sk_buff, data_end):
		ctx_off -= offsetof(struct __sk_buff, data_end);
		ctx_off += offsetof(struct sk_buff, cb);
		ctx_off += offsetof(struct bpf_skb_data_end, data_end);
		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), dst_reg, src_reg,
				      ctx_off);
		break;

	case offsetof(struct __sk_buff, tc_index):
#ifdef CONFIG_NET_SCHED
		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2);

		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg,
					      offsetof(struct sk_buff, tc_index));
		else
			*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
					      offsetof(struct sk_buff, tc_index));
		break;
#else
		if (type == BPF_WRITE)
			*insn++ = BPF_MOV64_REG(dst_reg, dst_reg);
		else
			*insn++ = BPF_MOV64_IMM(dst_reg, 0);
		break;
#endif
	}

	return insn - insn_buf;
}

static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
					  int dst_reg, int src_reg,
					  int ctx_off,
					  struct bpf_insn *insn_buf,
					  struct bpf_prog *prog)
{
	struct bpf_insn *insn = insn_buf;

	switch (ctx_off) {
	case offsetof(struct bpf_sock, bound_dev_if):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4);

		if (type == BPF_WRITE)
			*insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
					offsetof(struct sock, sk_bound_dev_if));
		else
			*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sock, sk_bound_dev_if));
		break;

	case offsetof(struct bpf_sock, family):
		BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2);

		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
				      offsetof(struct sock, sk_family));
		break;

	case offsetof(struct bpf_sock, type):
		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sock, __sk_flags_offset));
		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_TYPE_MASK);
		*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_TYPE_SHIFT);
		break;

	case offsetof(struct bpf_sock, protocol):
		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
				      offsetof(struct sock, __sk_flags_offset));
		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_PROTO_MASK);
		*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_PROTO_SHIFT);
		break;
	}

	return insn - insn_buf;
}

static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg,
					 int src_reg, int ctx_off,
					 struct bpf_insn *insn_buf,
					 struct bpf_prog *prog)
{
	struct bpf_insn *insn = insn_buf;

	switch (ctx_off) {
	case offsetof(struct __sk_buff, ifindex):
		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);

		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev),
				      dst_reg, src_reg,
				      offsetof(struct sk_buff, dev));
		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg,
				      offsetof(struct net_device, ifindex));
		break;
	default:
		return sk_filter_convert_ctx_access(type, dst_reg, src_reg,
						    ctx_off, insn_buf, prog);
	}

	return insn - insn_buf;
}

static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg,
				  int src_reg, int ctx_off,
				  struct bpf_insn *insn_buf,
				  struct bpf_prog *prog)
{
	struct bpf_insn *insn = insn_buf;

	switch (ctx_off) {
	case offsetof(struct xdp_md, data):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data),
				      dst_reg, src_reg,
				      offsetof(struct xdp_buff, data));
		break;
	case offsetof(struct xdp_md, data_end):
		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end),
				      dst_reg, src_reg,
				      offsetof(struct xdp_buff, data_end));
		break;
	}

	return insn - insn_buf;
}

static const struct bpf_verifier_ops sk_filter_ops = {
	.get_func_proto		= sk_filter_func_proto,
	.is_valid_access	= sk_filter_is_valid_access,
	.convert_ctx_access	= sk_filter_convert_ctx_access,
};

static const struct bpf_verifier_ops tc_cls_act_ops = {
	.get_func_proto		= tc_cls_act_func_proto,
	.is_valid_access	= tc_cls_act_is_valid_access,
	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
	.gen_prologue		= tc_cls_act_prologue,
};

static const struct bpf_verifier_ops xdp_ops = {
	.get_func_proto		= xdp_func_proto,
	.is_valid_access	= xdp_is_valid_access,
	.convert_ctx_access	= xdp_convert_ctx_access,
};

static const struct bpf_verifier_ops cg_skb_ops = {
	.get_func_proto		= cg_skb_func_proto,
	.is_valid_access	= sk_filter_is_valid_access,
	.convert_ctx_access	= sk_filter_convert_ctx_access,
};

static const struct bpf_verifier_ops lwt_inout_ops = {
	.get_func_proto		= lwt_inout_func_proto,
	.is_valid_access	= lwt_is_valid_access,
	.convert_ctx_access	= sk_filter_convert_ctx_access,
};

static const struct bpf_verifier_ops lwt_xmit_ops = {
	.get_func_proto		= lwt_xmit_func_proto,
	.is_valid_access	= lwt_is_valid_access,
	.convert_ctx_access	= sk_filter_convert_ctx_access,
	.gen_prologue		= tc_cls_act_prologue,
};

static const struct bpf_verifier_ops cg_sock_ops = {
	.get_func_proto		= sk_filter_func_proto,
	.is_valid_access	= sock_filter_is_valid_access,
	.convert_ctx_access	= sock_filter_convert_ctx_access,
};

static struct bpf_prog_type_list sk_filter_type __read_mostly = {
	.ops	= &sk_filter_ops,
	.type	= BPF_PROG_TYPE_SOCKET_FILTER,
};

static struct bpf_prog_type_list sched_cls_type __read_mostly = {
	.ops	= &tc_cls_act_ops,
	.type	= BPF_PROG_TYPE_SCHED_CLS,
};

static struct bpf_prog_type_list sched_act_type __read_mostly = {
	.ops	= &tc_cls_act_ops,
	.type	= BPF_PROG_TYPE_SCHED_ACT,
};

static struct bpf_prog_type_list xdp_type __read_mostly = {
	.ops	= &xdp_ops,
	.type	= BPF_PROG_TYPE_XDP,
};

static struct bpf_prog_type_list cg_skb_type __read_mostly = {
	.ops	= &cg_skb_ops,
	.type	= BPF_PROG_TYPE_CGROUP_SKB,
};

static struct bpf_prog_type_list lwt_in_type __read_mostly = {
	.ops	= &lwt_inout_ops,
	.type	= BPF_PROG_TYPE_LWT_IN,
};

static struct bpf_prog_type_list lwt_out_type __read_mostly = {
	.ops	= &lwt_inout_ops,
	.type	= BPF_PROG_TYPE_LWT_OUT,
};

static struct bpf_prog_type_list lwt_xmit_type __read_mostly = {
	.ops	= &lwt_xmit_ops,
	.type	= BPF_PROG_TYPE_LWT_XMIT,
};

static struct bpf_prog_type_list cg_sock_type __read_mostly = {
	.ops	= &cg_sock_ops,
	.type	= BPF_PROG_TYPE_CGROUP_SOCK
};

static int __init register_sk_filter_ops(void)
{
	bpf_register_prog_type(&sk_filter_type);
	bpf_register_prog_type(&sched_cls_type);
	bpf_register_prog_type(&sched_act_type);
	bpf_register_prog_type(&xdp_type);
	bpf_register_prog_type(&cg_skb_type);
	bpf_register_prog_type(&cg_sock_type);
	bpf_register_prog_type(&lwt_in_type);
	bpf_register_prog_type(&lwt_out_type);
	bpf_register_prog_type(&lwt_xmit_type);

	return 0;
}
late_initcall(register_sk_filter_ops);

int sk_detach_filter(struct sock *sk)
{
	int ret = -ENOENT;
	struct sk_filter *filter;

	if (sock_flag(sk, SOCK_FILTER_LOCKED))
		return -EPERM;

	filter = rcu_dereference_protected(sk->sk_filter,
					   lockdep_sock_is_held(sk));
	if (filter) {
		RCU_INIT_POINTER(sk->sk_filter, NULL);
		sk_filter_uncharge(sk, filter);
		ret = 0;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(sk_detach_filter);

int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
		  unsigned int len)
{
	struct sock_fprog_kern *fprog;
	struct sk_filter *filter;
	int ret = 0;

	lock_sock(sk);
	filter = rcu_dereference_protected(sk->sk_filter,
					   lockdep_sock_is_held(sk));
	if (!filter)
		goto out;

	/* We're copying the filter that has been originally attached,
	 * so no conversion/decode needed anymore. eBPF programs that
	 * have no original program cannot be dumped through this.
	 */
	ret = -EACCES;
	fprog = filter->prog->orig_prog;
	if (!fprog)
		goto out;

	ret = fprog->len;
	if (!len)
		/* User space only enquires number of filter blocks. */
		goto out;

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

	ret = -EFAULT;
	if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog)))
		goto out;

	/* Instead of bytes, the API requests to return the number
	 * of filter blocks.
	 */
	ret = fprog->len;
out:
	release_sock(sk);
	return ret;
}