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
|
/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#ifndef _LINUX_BPF_H
#define _LINUX_BPF_H 1
#include <uapi/linux/bpf.h>
#include <uapi/linux/filter.h>
#include <linux/workqueue.h>
#include <linux/file.h>
#include <linux/percpu.h>
#include <linux/err.h>
#include <linux/rbtree_latch.h>
#include <linux/numa.h>
#include <linux/mm_types.h>
#include <linux/wait.h>
#include <linux/refcount.h>
#include <linux/mutex.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/capability.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>
#include <linux/percpu-refcount.h>
#include <linux/stddef.h>
#include <linux/bpfptr.h>
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/static_call.h>
#include <linux/memcontrol.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
struct perf_event;
struct bpf_prog;
struct bpf_prog_aux;
struct bpf_map;
struct sock;
struct seq_file;
struct btf;
struct btf_type;
struct exception_table_entry;
struct seq_operations;
struct bpf_iter_aux_info;
struct bpf_local_storage;
struct bpf_local_storage_map;
struct kobject;
struct mem_cgroup;
struct module;
struct bpf_func_state;
struct ftrace_ops;
struct cgroup;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
extern struct kobject *btf_kobj;
extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
extern bool bpf_global_ma_set;
typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
typedef unsigned int (*bpf_func_t)(const void *,
const struct bpf_insn *);
struct bpf_iter_seq_info {
const struct seq_operations *seq_ops;
bpf_iter_init_seq_priv_t init_seq_private;
bpf_iter_fini_seq_priv_t fini_seq_private;
u32 seq_priv_size;
};
/* map is generic key/value storage optionally accessible by eBPF programs */
struct bpf_map_ops {
/* funcs callable from userspace (via syscall) */
int (*map_alloc_check)(union bpf_attr *attr);
struct bpf_map *(*map_alloc)(union bpf_attr *attr);
void (*map_release)(struct bpf_map *map, struct file *map_file);
void (*map_free)(struct bpf_map *map);
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
void (*map_release_uref)(struct bpf_map *map);
void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key,
void *value, u64 flags);
int (*map_lookup_and_delete_batch)(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_update_batch)(struct bpf_map *map, struct file *map_file,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
long (*map_delete_elem)(struct bpf_map *map, void *key);
long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
long (*map_pop_elem)(struct bpf_map *map, void *value);
long (*map_peek_elem)(struct bpf_map *map, void *value);
void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu);
/* funcs called by prog_array and perf_event_array map */
void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
int fd);
void (*map_fd_put_ptr)(void *ptr);
int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
u32 (*map_fd_sys_lookup_elem)(void *ptr);
void (*map_seq_show_elem)(struct bpf_map *map, void *key,
struct seq_file *m);
int (*map_check_btf)(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
/* Prog poke tracking helpers. */
int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux);
void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux);
void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old,
struct bpf_prog *new);
/* Direct value access helpers. */
int (*map_direct_value_addr)(const struct bpf_map *map,
u64 *imm, u32 off);
int (*map_direct_value_meta)(const struct bpf_map *map,
u64 imm, u32 *off);
int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
struct poll_table_struct *pts);
/* Functions called by bpf_local_storage maps */
int (*map_local_storage_charge)(struct bpf_local_storage_map *smap,
void *owner, u32 size);
void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
void *owner, u32 size);
struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
/* Misc helpers.*/
long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags);
/* map_meta_equal must be implemented for maps that can be
* used as an inner map. It is a runtime check to ensure
* an inner map can be inserted to an outer map.
*
* Some properties of the inner map has been used during the
* verification time. When inserting an inner map at the runtime,
* map_meta_equal has to ensure the inserting map has the same
* properties that the verifier has used earlier.
*/
bool (*map_meta_equal)(const struct bpf_map *meta0,
const struct bpf_map *meta1);
int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee);
long (*map_for_each_callback)(struct bpf_map *map,
bpf_callback_t callback_fn,
void *callback_ctx, u64 flags);
u64 (*map_mem_usage)(const struct bpf_map *map);
/* BTF id of struct allocated by map_alloc */
int *map_btf_id;
/* bpf_iter info used to open a seq_file */
const struct bpf_iter_seq_info *iter_seq_info;
};
enum {
/* Support at most 10 fields in a BTF type */
BTF_FIELDS_MAX = 10,
};
enum btf_field_type {
BPF_SPIN_LOCK = (1 << 0),
BPF_TIMER = (1 << 1),
BPF_KPTR_UNREF = (1 << 2),
BPF_KPTR_REF = (1 << 3),
BPF_KPTR_PERCPU = (1 << 4),
BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU,
BPF_LIST_HEAD = (1 << 5),
BPF_LIST_NODE = (1 << 6),
BPF_RB_ROOT = (1 << 7),
BPF_RB_NODE = (1 << 8),
BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
BPF_RB_NODE | BPF_RB_ROOT,
BPF_REFCOUNT = (1 << 9),
};
typedef void (*btf_dtor_kfunc_t)(void *);
struct btf_field_kptr {
struct btf *btf;
struct module *module;
/* dtor used if btf_is_kernel(btf), otherwise the type is
* program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used
*/
btf_dtor_kfunc_t dtor;
u32 btf_id;
};
struct btf_field_graph_root {
struct btf *btf;
u32 value_btf_id;
u32 node_offset;
struct btf_record *value_rec;
};
struct btf_field {
u32 offset;
u32 size;
enum btf_field_type type;
union {
struct btf_field_kptr kptr;
struct btf_field_graph_root graph_root;
};
};
struct btf_record {
u32 cnt;
u32 field_mask;
int spin_lock_off;
int timer_off;
int refcount_off;
struct btf_field fields[];
};
/* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */
struct bpf_rb_node_kern {
struct rb_node rb_node;
void *owner;
} __attribute__((aligned(8)));
/* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */
struct bpf_list_node_kern {
struct list_head list_head;
void *owner;
} __attribute__((aligned(8)));
struct bpf_map {
/* The first two cachelines with read-mostly members of which some
* are also accessed in fast-path (e.g. ops, max_entries).
*/
const struct bpf_map_ops *ops ____cacheline_aligned;
struct bpf_map *inner_map_meta;
#ifdef CONFIG_SECURITY
void *security;
#endif
enum bpf_map_type map_type;
u32 key_size;
u32 value_size;
u32 max_entries;
u64 map_extra; /* any per-map-type extra fields */
u32 map_flags;
u32 id;
struct btf_record *record;
int numa_node;
u32 btf_key_type_id;
u32 btf_value_type_id;
u32 btf_vmlinux_value_type_id;
struct btf *btf;
#ifdef CONFIG_MEMCG_KMEM
struct obj_cgroup *objcg;
#endif
char name[BPF_OBJ_NAME_LEN];
/* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting.
*/
atomic64_t refcnt ____cacheline_aligned;
atomic64_t usercnt;
struct work_struct work;
struct mutex freeze_mutex;
atomic64_t writecnt;
/* 'Ownership' of program-containing map is claimed by the first program
* that is going to use this map or by the first program which FD is
* stored in the map to make sure that all callers and callees have the
* same prog type, JITed flag and xdp_has_frags flag.
*/
struct {
spinlock_t lock;
enum bpf_prog_type type;
bool jited;
bool xdp_has_frags;
} owner;
bool bypass_spec_v1;
bool frozen; /* write-once; write-protected by freeze_mutex */
s64 __percpu *elem_count;
};
static inline const char *btf_field_type_name(enum btf_field_type type)
{
switch (type) {
case BPF_SPIN_LOCK:
return "bpf_spin_lock";
case BPF_TIMER:
return "bpf_timer";
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
return "kptr";
case BPF_KPTR_PERCPU:
return "percpu_kptr";
case BPF_LIST_HEAD:
return "bpf_list_head";
case BPF_LIST_NODE:
return "bpf_list_node";
case BPF_RB_ROOT:
return "bpf_rb_root";
case BPF_RB_NODE:
return "bpf_rb_node";
case BPF_REFCOUNT:
return "bpf_refcount";
default:
WARN_ON_ONCE(1);
return "unknown";
}
}
static inline u32 btf_field_type_size(enum btf_field_type type)
{
switch (type) {
case BPF_SPIN_LOCK:
return sizeof(struct bpf_spin_lock);
case BPF_TIMER:
return sizeof(struct bpf_timer);
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
return sizeof(u64);
case BPF_LIST_HEAD:
return sizeof(struct bpf_list_head);
case BPF_LIST_NODE:
return sizeof(struct bpf_list_node);
case BPF_RB_ROOT:
return sizeof(struct bpf_rb_root);
case BPF_RB_NODE:
return sizeof(struct bpf_rb_node);
case BPF_REFCOUNT:
return sizeof(struct bpf_refcount);
default:
WARN_ON_ONCE(1);
return 0;
}
}
static inline u32 btf_field_type_align(enum btf_field_type type)
{
switch (type) {
case BPF_SPIN_LOCK:
return __alignof__(struct bpf_spin_lock);
case BPF_TIMER:
return __alignof__(struct bpf_timer);
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
return __alignof__(u64);
case BPF_LIST_HEAD:
return __alignof__(struct bpf_list_head);
case BPF_LIST_NODE:
return __alignof__(struct bpf_list_node);
case BPF_RB_ROOT:
return __alignof__(struct bpf_rb_root);
case BPF_RB_NODE:
return __alignof__(struct bpf_rb_node);
case BPF_REFCOUNT:
return __alignof__(struct bpf_refcount);
default:
WARN_ON_ONCE(1);
return 0;
}
}
static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
{
memset(addr, 0, field->size);
switch (field->type) {
case BPF_REFCOUNT:
refcount_set((refcount_t *)addr, 1);
break;
case BPF_RB_NODE:
RB_CLEAR_NODE((struct rb_node *)addr);
break;
case BPF_LIST_HEAD:
case BPF_LIST_NODE:
INIT_LIST_HEAD((struct list_head *)addr);
break;
case BPF_RB_ROOT:
/* RB_ROOT_CACHED 0-inits, no need to do anything after memset */
case BPF_SPIN_LOCK:
case BPF_TIMER:
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
break;
default:
WARN_ON_ONCE(1);
return;
}
}
static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type)
{
if (IS_ERR_OR_NULL(rec))
return false;
return rec->field_mask & type;
}
static inline void bpf_obj_init(const struct btf_record *rec, void *obj)
{
int i;
if (IS_ERR_OR_NULL(rec))
return;
for (i = 0; i < rec->cnt; i++)
bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset);
}
/* 'dst' must be a temporary buffer and should not point to memory that is being
* used in parallel by a bpf program or bpf syscall, otherwise the access from
* the bpf program or bpf syscall may be corrupted by the reinitialization,
* leading to weird problems. Even 'dst' is newly-allocated from bpf memory
* allocator, it is still possible for 'dst' to be used in parallel by a bpf
* program or bpf syscall.
*/
static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
{
bpf_obj_init(map->record, dst);
}
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
* Best-effort only. No barriers here, since it _will_ race with concurrent
* updates from BPF programs. Called from bpf syscall and mostly used with
* size 8 or 16 bytes, so ask compiler to inline it.
*/
static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
{
const long *lsrc = src;
long *ldst = dst;
size /= sizeof(long);
while (size--)
data_race(*ldst++ = *lsrc++);
}
/* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */
static inline void bpf_obj_memcpy(struct btf_record *rec,
void *dst, void *src, u32 size,
bool long_memcpy)
{
u32 curr_off = 0;
int i;
if (IS_ERR_OR_NULL(rec)) {
if (long_memcpy)
bpf_long_memcpy(dst, src, round_up(size, 8));
else
memcpy(dst, src, size);
return;
}
for (i = 0; i < rec->cnt; i++) {
u32 next_off = rec->fields[i].offset;
u32 sz = next_off - curr_off;
memcpy(dst + curr_off, src + curr_off, sz);
curr_off += rec->fields[i].size + sz;
}
memcpy(dst + curr_off, src + curr_off, size - curr_off);
}
static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
{
bpf_obj_memcpy(map->record, dst, src, map->value_size, false);
}
static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src)
{
bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
}
static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size)
{
u32 curr_off = 0;
int i;
if (IS_ERR_OR_NULL(rec)) {
memset(dst, 0, size);
return;
}
for (i = 0; i < rec->cnt; i++) {
u32 next_off = rec->fields[i].offset;
u32 sz = next_off - curr_off;
memset(dst + curr_off, 0, sz);
curr_off += rec->fields[i].size + sz;
}
memset(dst + curr_off, 0, size - curr_off);
}
static inline void zero_map_value(struct bpf_map *map, void *dst)
{
bpf_obj_memzero(map->record, dst, map->value_size);
}
void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
bool lock_src);
void bpf_timer_cancel_and_free(void *timer);
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock);
void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
struct bpf_spin_lock *spin_lock);
int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
struct bpf_offload_dev;
struct bpf_offloaded_map;
struct bpf_map_dev_ops {
int (*map_get_next_key)(struct bpf_offloaded_map *map,
void *key, void *next_key);
int (*map_lookup_elem)(struct bpf_offloaded_map *map,
void *key, void *value);
int (*map_update_elem)(struct bpf_offloaded_map *map,
void *key, void *value, u64 flags);
int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key);
};
struct bpf_offloaded_map {
struct bpf_map map;
struct net_device *netdev;
const struct bpf_map_dev_ops *dev_ops;
void *dev_priv;
struct list_head offloads;
};
static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
{
return container_of(map, struct bpf_offloaded_map, map);
}
static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
{
return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) &&
map->ops->map_seq_show_elem;
}
int map_check_no_btf(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
bool bpf_map_meta_equal(const struct bpf_map *meta0,
const struct bpf_map *meta1);
extern const struct bpf_map_ops bpf_map_offload_ops;
/* bpf_type_flag contains a set of flags that are applicable to the values of
* arg_type, ret_type and reg_type. For example, a pointer value may be null,
* or a memory is read-only. We classify types into two categories: base types
* and extended types. Extended types are base types combined with a type flag.
*
* Currently there are no more than 32 base types in arg_type, ret_type and
* reg_types.
*/
#define BPF_BASE_TYPE_BITS 8
enum bpf_type_flag {
/* PTR may be NULL. */
PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS),
/* MEM is read-only. When applied on bpf_arg, it indicates the arg is
* compatible with both mutable and immutable memory.
*/
MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS),
/* MEM points to BPF ring buffer reservation. */
MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS),
/* MEM is in user address space. */
MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS),
/* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged
* with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In
* order to drop this tag, it must be passed into bpf_per_cpu_ptr()
* or bpf_this_cpu_ptr(), which will return the pointer corresponding
* to the specified cpu.
*/
MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS),
/* Indicates that the argument will be released. */
OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS),
/* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark
* unreferenced and referenced kptr loaded from map value using a load
* instruction, so that they can only be dereferenced but not escape the
* BPF program into the kernel (i.e. cannot be passed as arguments to
* kfunc or bpf helpers).
*/
PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS),
MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS),
/* DYNPTR points to memory local to the bpf program. */
DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS),
/* DYNPTR points to a kernel-produced ringbuf record. */
DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS),
/* Size is known at compile time. */
MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS),
/* MEM is of an allocated object of type in program BTF. This is used to
* tag PTR_TO_BTF_ID allocated using bpf_obj_new.
*/
MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS),
/* PTR was passed from the kernel in a trusted context, and may be
* passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions.
* Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above.
* PTR_UNTRUSTED refers to a kptr that was read directly from a map
* without invoking bpf_kptr_xchg(). What we really need to know is
* whether a pointer is safe to pass to a kfunc or BPF helper function.
* While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF
* helpers, they do not cover all possible instances of unsafe
* pointers. For example, a pointer that was obtained from walking a
* struct will _not_ get the PTR_UNTRUSTED type modifier, despite the
* fact that it may be NULL, invalid, etc. This is due to backwards
* compatibility requirements, as this was the behavior that was first
* introduced when kptrs were added. The behavior is now considered
* deprecated, and PTR_UNTRUSTED will eventually be removed.
*
* PTR_TRUSTED, on the other hand, is a pointer that the kernel
* guarantees to be valid and safe to pass to kfuncs and BPF helpers.
* For example, pointers passed to tracepoint arguments are considered
* PTR_TRUSTED, as are pointers that are passed to struct_ops
* callbacks. As alluded to above, pointers that are obtained from
* walking PTR_TRUSTED pointers are _not_ trusted. For example, if a
* struct task_struct *task is PTR_TRUSTED, then accessing
* task->last_wakee will lose the PTR_TRUSTED modifier when it's stored
* in a BPF register. Similarly, pointers passed to certain programs
* types such as kretprobes are not guaranteed to be valid, as they may
* for example contain an object that was recently freed.
*/
PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS),
/* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */
MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS),
/* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning.
* Currently only valid for linked-list and rbtree nodes. If the nodes
* have a bpf_refcount_field, they must be tagged MEM_RCU as well.
*/
NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS),
/* DYNPTR points to sk_buff */
DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS),
/* DYNPTR points to xdp_buff */
DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS),
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \
| DYNPTR_TYPE_XDP)
/* Max number of base types. */
#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
/* Max number of all types. */
#define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1))
/* function argument constraints */
enum bpf_arg_type {
ARG_DONTCARE = 0, /* unused argument in helper function */
/* the following constraints used to prototype
* bpf_map_lookup/update/delete_elem() functions
*/
ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */
ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
/* Used to prototype bpf_memcmp() and other functions that access data
* on eBPF program stack
*/
ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */
ARG_CONST_SIZE, /* number of bytes accessed from memory */
ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
ARG_PTR_TO_INT, /* pointer to int */
ARG_PTR_TO_LONG, /* pointer to long */
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */
ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */
ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */
ARG_PTR_TO_FUNC, /* pointer to a bpf program function */
ARG_PTR_TO_STACK, /* pointer to stack */
ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */
ARG_PTR_TO_TIMER, /* pointer to bpf_timer */
ARG_PTR_TO_KPTR, /* pointer to referenced kptr */
ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
__BPF_ARG_TYPE_MAX,
/* Extended arg_types. */
ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE,
ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM,
ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX,
ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
/* pointer to memory does not need to be initialized, helper function must fill
* all bytes or clear them in error case.
*/
ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM,
/* Pointer to valid memory of size known at compile time. */
ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
/* This must be the last entry. Its purpose is to ensure the enum is
* wide enough to hold the higher bits reserved for bpf_type_flag.
*/
__BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* type of values returned from helper functions */
enum bpf_return_type {
RET_INTEGER, /* function returns integer */
RET_VOID, /* function doesn't return anything */
RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */
RET_PTR_TO_SOCKET, /* returns a pointer to a socket */
RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */
RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */
RET_PTR_TO_MEM, /* returns a pointer to memory */
RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */
RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */
__BPF_RET_TYPE_MAX,
/* Extended ret_types. */
RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE,
RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET,
RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM,
RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM,
RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID,
/* This must be the last entry. Its purpose is to ensure the enum is
* wide enough to hold the higher bits reserved for bpf_type_flag.
*/
__BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
* to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
* instructions after verifying
*/
struct bpf_func_proto {
u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
bool gpl_only;
bool pkt_access;
bool might_sleep;
enum bpf_return_type ret_type;
union {
struct {
enum bpf_arg_type arg1_type;
enum bpf_arg_type arg2_type;
enum bpf_arg_type arg3_type;
enum bpf_arg_type arg4_type;
enum bpf_arg_type arg5_type;
};
enum bpf_arg_type arg_type[5];
};
union {
struct {
u32 *arg1_btf_id;
u32 *arg2_btf_id;
u32 *arg3_btf_id;
u32 *arg4_btf_id;
u32 *arg5_btf_id;
};
u32 *arg_btf_id[5];
struct {
size_t arg1_size;
size_t arg2_size;
size_t arg3_size;
size_t arg4_size;
size_t arg5_size;
};
size_t arg_size[5];
};
int *ret_btf_id; /* return value btf_id */
bool (*allowed)(const struct bpf_prog *prog);
};
/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
* the first argument to eBPF programs.
* For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
*/
struct bpf_context;
enum bpf_access_type {
BPF_READ = 1,
BPF_WRITE = 2
};
/* types of values stored in eBPF registers */
/* Pointer types represent:
* pointer
* pointer + imm
* pointer + (u16) var
* pointer + (u16) var + imm
* if (range > 0) then [ptr, ptr + range - off) is safe to access
* if (id > 0) means that some 'var' was added
* if (off > 0) means that 'imm' was added
*/
enum bpf_reg_type {
NOT_INIT = 0, /* nothing was written into register */
SCALAR_VALUE, /* reg doesn't contain a valid pointer */
PTR_TO_CTX, /* reg points to bpf_context */
CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
PTR_TO_MAP_VALUE, /* reg points to map element value */
PTR_TO_MAP_KEY, /* reg points to a map element key */
PTR_TO_STACK, /* reg == frame_pointer + offset */
PTR_TO_PACKET_META, /* skb->data - meta_len */
PTR_TO_PACKET, /* reg points to skb->data */
PTR_TO_PACKET_END, /* skb->data + headlen */
PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */
PTR_TO_SOCKET, /* reg points to struct bpf_sock */
PTR_TO_SOCK_COMMON, /* reg points to sock_common */
PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */
PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */
PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */
/* PTR_TO_BTF_ID points to a kernel struct that does not need
* to be null checked by the BPF program. This does not imply the
* pointer is _not_ null and in practice this can easily be a null
* pointer when reading pointer chains. The assumption is program
* context will handle null pointer dereference typically via fault
* handling. The verifier must keep this in mind and can make no
* assumptions about null or non-null when doing branch analysis.
* Further, when passed into helpers the helpers can not, without
* additional context, assume the value is non-null.
*/
PTR_TO_BTF_ID,
/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
* been checked for null. Used primarily to inform the verifier
* an explicit null check is required for this struct.
*/
PTR_TO_MEM, /* reg points to valid memory region */
PTR_TO_BUF, /* reg points to a read/write buffer */
PTR_TO_FUNC, /* reg points to a bpf program function */
CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */
__BPF_REG_TYPE_MAX,
/* Extended reg_types. */
PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE,
PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET,
PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID,
/* This must be the last entry. Its purpose is to ensure the enum is
* wide enough to hold the higher bits reserved for bpf_type_flag.
*/
__BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* The information passed from prog-specific *_is_valid_access
* back to the verifier.
*/
struct bpf_insn_access_aux {
enum bpf_reg_type reg_type;
union {
int ctx_field_size;
struct {
struct btf *btf;
u32 btf_id;
};
};
struct bpf_verifier_log *log; /* for verbose logs */
};
static inline void
bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
{
aux->ctx_field_size = size;
}
static bool bpf_is_ldimm64(const struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
{
return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
}
struct bpf_prog_ops {
int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
};
struct bpf_reg_state;
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
const struct bpf_func_proto *
(*get_func_proto)(enum bpf_func_id func_id,
const struct bpf_prog *prog);
/* return true if 'size' wide access at offset 'off' within bpf_context
* with 'type' (read or write) is allowed
*/
bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
const struct bpf_prog *prog);
int (*gen_ld_abs)(const struct bpf_insn *orig,
struct bpf_insn *insn_buf);
u32 (*convert_ctx_access)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog, u32 *target_size);
int (*btf_struct_access)(struct bpf_verifier_log *log,
const struct bpf_reg_state *reg,
int off, int size);
};
struct bpf_prog_offload_ops {
/* verifier basic callbacks */
int (*insn_hook)(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int (*finalize)(struct bpf_verifier_env *env);
/* verifier optimization callbacks (called after .finalize) */
int (*replace_insn)(struct bpf_verifier_env *env, u32 off,
struct bpf_insn *insn);
int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt);
/* program management callbacks */
int (*prepare)(struct bpf_prog *prog);
int (*translate)(struct bpf_prog *prog);
void (*destroy)(struct bpf_prog *prog);
};
struct bpf_prog_offload {
struct bpf_prog *prog;
struct net_device *netdev;
struct bpf_offload_dev *offdev;
void *dev_priv;
struct list_head offloads;
bool dev_state;
bool opt_failed;
void *jited_image;
u32 jited_len;
};
enum bpf_cgroup_storage_type {
BPF_CGROUP_STORAGE_SHARED,
BPF_CGROUP_STORAGE_PERCPU,
__BPF_CGROUP_STORAGE_MAX
};
#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
/* The longest tracepoint has 12 args.
* See include/trace/bpf_probe.h
*/
#define MAX_BPF_FUNC_ARGS 12
/* The maximum number of arguments passed through registers
* a single function may have.
*/
#define MAX_BPF_FUNC_REG_ARGS 5
/* The argument is a structure. */
#define BTF_FMODEL_STRUCT_ARG BIT(0)
/* The argument is signed. */
#define BTF_FMODEL_SIGNED_ARG BIT(1)
struct btf_func_model {
u8 ret_size;
u8 ret_flags;
u8 nr_args;
u8 arg_size[MAX_BPF_FUNC_ARGS];
u8 arg_flags[MAX_BPF_FUNC_ARGS];
};
/* Restore arguments before returning from trampoline to let original function
* continue executing. This flag is used for fentry progs when there are no
* fexit progs.
*/
#define BPF_TRAMP_F_RESTORE_REGS BIT(0)
/* Call original function after fentry progs, but before fexit progs.
* Makes sense for fentry/fexit, normal calls and indirect calls.
*/
#define BPF_TRAMP_F_CALL_ORIG BIT(1)
/* Skip current frame and return to parent. Makes sense for fentry/fexit
* programs only. Should not be used with normal calls and indirect calls.
*/
#define BPF_TRAMP_F_SKIP_FRAME BIT(2)
/* Store IP address of the caller on the trampoline stack,
* so it's available for trampoline's programs.
*/
#define BPF_TRAMP_F_IP_ARG BIT(3)
/* Return the return value of fentry prog. Only used by bpf_struct_ops. */
#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4)
/* Get original function from stack instead of from provided direct address.
* Makes sense for trampolines with fexit or fmod_ret programs.
*/
#define BPF_TRAMP_F_ORIG_STACK BIT(5)
/* This trampoline is on a function with another ftrace_ops with IPMODIFY,
* e.g., a live patch. This flag is set and cleared by ftrace call backs,
*/
#define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6)
/* Indicate that current trampoline is in a tail call context. Then, it has to
* cache and restore tail_call_cnt to avoid infinite tail call loop.
*/
#define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7)
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
* bytes on x86.
*/
enum {
#if defined(__s390x__)
BPF_MAX_TRAMP_LINKS = 27,
#else
BPF_MAX_TRAMP_LINKS = 38,
#endif
};
struct bpf_tramp_links {
struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
int nr_links;
};
struct bpf_tramp_run_ctx;
/* Different use cases for BPF trampoline:
* 1. replace nop at the function entry (kprobe equivalent)
* flags = BPF_TRAMP_F_RESTORE_REGS
* fentry = a set of programs to run before returning from trampoline
*
* 2. replace nop at the function entry (kprobe + kretprobe equivalent)
* flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME
* orig_call = fentry_ip + MCOUNT_INSN_SIZE
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*
* 3. replace direct call instruction anywhere in the function body
* or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid)
* With flags = 0
* fentry = a set of programs to run before returning from trampoline
* With flags = BPF_TRAMP_F_CALL_ORIG
* orig_call = original callback addr or direct function addr
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*/
struct bpf_tramp_image;
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_links *tlinks,
void *orig_call);
u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx);
void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
struct bpf_tramp_run_ctx *run_ctx);
void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx);
typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
struct bpf_tramp_run_ctx *run_ctx);
bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
struct bpf_ksym {
unsigned long start;
unsigned long end;
char name[KSYM_NAME_LEN];
struct list_head lnode;
struct latch_tree_node tnode;
bool prog;
};
enum bpf_tramp_prog_type {
BPF_TRAMP_FENTRY,
BPF_TRAMP_FEXIT,
BPF_TRAMP_MODIFY_RETURN,
BPF_TRAMP_MAX,
BPF_TRAMP_REPLACE, /* more than MAX */
};
struct bpf_tramp_image {
void *image;
struct bpf_ksym ksym;
struct percpu_ref pcref;
void *ip_after_call;
void *ip_epilogue;
union {
struct rcu_head rcu;
struct work_struct work;
};
};
struct bpf_trampoline {
/* hlist for trampoline_table */
struct hlist_node hlist;
struct ftrace_ops *fops;
/* serializes access to fields of this trampoline */
struct mutex mutex;
refcount_t refcnt;
u32 flags;
u64 key;
struct {
struct btf_func_model model;
void *addr;
bool ftrace_managed;
} func;
/* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF
* program by replacing one of its functions. func.addr is the address
* of the function it replaced.
*/
struct bpf_prog *extension_prog;
/* list of BPF programs using this trampoline */
struct hlist_head progs_hlist[BPF_TRAMP_MAX];
/* Number of attached programs. A counter per kind. */
int progs_cnt[BPF_TRAMP_MAX];
/* Executable image of trampoline */
struct bpf_tramp_image *cur_image;
struct module *mod;
};
struct bpf_attach_target_info {
struct btf_func_model fmodel;
long tgt_addr;
struct module *tgt_mod;
const char *tgt_name;
const struct btf_type *tgt_type;
};
#define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
struct bpf_dispatcher_prog {
struct bpf_prog *prog;
refcount_t users;
};
struct bpf_dispatcher {
/* dispatcher mutex */
struct mutex mutex;
void *func;
struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX];
int num_progs;
void *image;
void *rw_image;
u32 image_off;
struct bpf_ksym ksym;
#ifdef CONFIG_HAVE_STATIC_CALL
struct static_call_key *sc_key;
void *sc_tramp;
#endif
};
static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
const void *ctx,
const struct bpf_insn *insnsi,
bpf_func_t bpf_func)
{
return bpf_func(ctx, insnsi);
}
/* the implementation of the opaque uapi struct bpf_dynptr */
struct bpf_dynptr_kern {
void *data;
/* Size represents the number of usable bytes of dynptr data.
* If for example the offset is at 4 for a local dynptr whose data is
* of type u64, the number of usable bytes is 4.
*
* The upper 8 bits are reserved. It is as follows:
* Bits 0 - 23 = size
* Bits 24 - 30 = dynptr type
* Bit 31 = whether dynptr is read-only
*/
u32 size;
u32 offset;
} __aligned(8);
enum bpf_dynptr_type {
BPF_DYNPTR_TYPE_INVALID,
/* Points to memory that is local to the bpf program */
BPF_DYNPTR_TYPE_LOCAL,
/* Underlying data is a ringbuf record */
BPF_DYNPTR_TYPE_RINGBUF,
/* Underlying data is a sk_buff */
BPF_DYNPTR_TYPE_SKB,
/* Underlying data is a xdp_buff */
BPF_DYNPTR_TYPE_XDP,
};
int bpf_dynptr_check_size(u32 size);
u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
#ifdef CONFIG_BPF_JIT
int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
void bpf_trampoline_put(struct bpf_trampoline *tr);
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
/*
* When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
* indirection with a direct call to the bpf program. If the architecture does
* not have STATIC_CALL, avoid a double-indirection.
*/
#ifdef CONFIG_HAVE_STATIC_CALL
#define __BPF_DISPATCHER_SC_INIT(_name) \
.sc_key = &STATIC_CALL_KEY(_name), \
.sc_tramp = STATIC_CALL_TRAMP_ADDR(_name),
#define __BPF_DISPATCHER_SC(name) \
DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func)
#define __BPF_DISPATCHER_CALL(name) \
static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func)
#define __BPF_DISPATCHER_UPDATE(_d, _new) \
__static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new))
#else
#define __BPF_DISPATCHER_SC_INIT(name)
#define __BPF_DISPATCHER_SC(name)
#define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi)
#define __BPF_DISPATCHER_UPDATE(_d, _new)
#endif
#define BPF_DISPATCHER_INIT(_name) { \
.mutex = __MUTEX_INITIALIZER(_name.mutex), \
.func = &_name##_func, \
.progs = {}, \
.num_progs = 0, \
.image = NULL, \
.image_off = 0, \
.ksym = { \
.name = #_name, \
.lnode = LIST_HEAD_INIT(_name.ksym.lnode), \
}, \
__BPF_DISPATCHER_SC_INIT(_name##_call) \
}
#define DEFINE_BPF_DISPATCHER(name) \
__BPF_DISPATCHER_SC(name); \
noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
bpf_func_t bpf_func) \
{ \
return __BPF_DISPATCHER_CALL(name); \
} \
EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \
struct bpf_dispatcher bpf_dispatcher_##name = \
BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
#define DECLARE_BPF_DISPATCHER(name) \
unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
bpf_func_t bpf_func); \
extern struct bpf_dispatcher bpf_dispatcher_##name;
#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
struct bpf_prog *to);
/* Called only from JIT-enabled code, so there's no need for stubs. */
void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
void bpf_image_ksym_del(struct bpf_ksym *ksym);
void bpf_ksym_add(struct bpf_ksym *ksym);
void bpf_ksym_del(struct bpf_ksym *ksym);
int bpf_jit_charge_modmem(u32 size);
void bpf_jit_uncharge_modmem(u32 size);
bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
#else
static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr)
{
return -ENOTSUPP;
}
static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr)
{
return -ENOTSUPP;
}
static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info)
{
return NULL;
}
static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
#define DEFINE_BPF_DISPATCHER(name)
#define DECLARE_BPF_DISPATCHER(name)
#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func
#define BPF_DISPATCHER_PTR(name) NULL
static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
struct bpf_prog *from,
struct bpf_prog *to) {}
static inline bool is_bpf_image_address(unsigned long address)
{
return false;
}
static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
{
return false;
}
#endif
struct bpf_func_info_aux {
u16 linkage;
bool unreliable;
};
enum bpf_jit_poke_reason {
BPF_POKE_REASON_TAIL_CALL,
};
/* Descriptor of pokes pointing /into/ the JITed image. */
struct bpf_jit_poke_descriptor {
void *tailcall_target;
void *tailcall_bypass;
void *bypass_addr;
void *aux;
union {
struct {
struct bpf_map *map;
u32 key;
} tail_call;
};
bool tailcall_target_stable;
u8 adj_off;
u16 reason;
u32 insn_idx;
};
/* reg_type info for ctx arguments */
struct bpf_ctx_arg_aux {
u32 offset;
enum bpf_reg_type reg_type;
u32 btf_id;
};
struct btf_mod_pair {
struct btf *btf;
struct module *module;
};
struct bpf_kfunc_desc_tab;
struct bpf_prog_aux {
atomic64_t refcnt;
u32 used_map_cnt;
u32 used_btf_cnt;
u32 max_ctx_offset;
u32 max_pkt_offset;
u32 max_tp_access;
u32 stack_depth;
u32 id;
u32 func_cnt; /* used by non-func prog as the number of func progs */
u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */
u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
u32 attach_btf_id; /* in-kernel BTF type id to attach to */
u32 ctx_arg_info_size;
u32 max_rdonly_access;
u32 max_rdwr_access;
struct btf *attach_btf;
const struct bpf_ctx_arg_aux *ctx_arg_info;
struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
struct bpf_prog *dst_prog;
struct bpf_trampoline *dst_trampoline;
enum bpf_prog_type saved_dst_prog_type;
enum bpf_attach_type saved_dst_attach_type;
bool verifier_zext; /* Zero extensions has been inserted by verifier. */
bool dev_bound; /* Program is bound to the netdev. */
bool offload_requested; /* Program is bound and offloaded to the netdev. */
bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
bool func_proto_unreliable;
bool sleepable;
bool tail_call_reachable;
bool xdp_has_frags;
bool exception_cb;
bool exception_boundary;
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
/* function name for valid attach_btf_id */
const char *attach_func_name;
struct bpf_prog **func;
void *jit_data; /* JIT specific data. arch dependent */
struct bpf_jit_poke_descriptor *poke_tab;
struct bpf_kfunc_desc_tab *kfunc_tab;
struct bpf_kfunc_btf_tab *kfunc_btf_tab;
u32 size_poke_tab;
struct bpf_ksym ksym;
const struct bpf_prog_ops *ops;
struct bpf_map **used_maps;
struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
struct btf_mod_pair *used_btfs;
struct bpf_prog *prog;
struct user_struct *user;
u64 load_time; /* ns since boottime */
u32 verified_insns;
int cgroup_atype; /* enum cgroup_bpf_attach_type */
struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
char name[BPF_OBJ_NAME_LEN];
unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp);
#ifdef CONFIG_SECURITY
void *security;
#endif
struct bpf_prog_offload *offload;
struct btf *btf;
struct bpf_func_info *func_info;
struct bpf_func_info_aux *func_info_aux;
/* bpf_line_info loaded from userspace. linfo->insn_off
* has the xlated insn offset.
* Both the main and sub prog share the same linfo.
* The subprog can access its first linfo by
* using the linfo_idx.
*/
struct bpf_line_info *linfo;
/* jited_linfo is the jited addr of the linfo. It has a
* one to one mapping to linfo:
* jited_linfo[i] is the jited addr for the linfo[i]->insn_off.
* Both the main and sub prog share the same jited_linfo.
* The subprog can access its first jited_linfo by
* using the linfo_idx.
*/
void **jited_linfo;
u32 func_info_cnt;
u32 nr_linfo;
/* subprog can use linfo_idx to access its first linfo and
* jited_linfo.
* main prog always has linfo_idx == 0
*/
u32 linfo_idx;
struct module *mod;
u32 num_exentries;
struct exception_table_entry *extable;
union {
struct work_struct work;
struct rcu_head rcu;
};
};
struct bpf_prog {
u16 pages; /* Number of allocated pages */
u16 jited:1, /* Is our filter JIT'ed? */
jit_requested:1,/* archs need to JIT the prog */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1, /* Do we need dst entry? */
blinding_requested:1, /* needs constant blinding */
blinded:1, /* Was blinded */
is_func:1, /* program is a bpf function */
kprobe_override:1, /* Do we override a kprobe? */
has_callchain_buf:1, /* callchain buffer allocated? */
enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
call_get_func_ip:1, /* Do we call get_func_ip() */
tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */
enum bpf_prog_type type; /* Type of BPF program */
enum bpf_attach_type expected_attach_type; /* For some prog types */
u32 len; /* Number of filter blocks */
u32 jited_len; /* Size of jited insns in bytes */
u8 tag[BPF_TAG_SIZE];
struct bpf_prog_stats __percpu *stats;
int __percpu *active;
unsigned int (*bpf_func)(const void *ctx,
const struct bpf_insn *insn);
struct bpf_prog_aux *aux; /* Auxiliary fields */
struct sock_fprog_kern *orig_prog; /* Original BPF program */
/* Instructions for interpreter */
union {
DECLARE_FLEX_ARRAY(struct sock_filter, insns);
DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi);
};
};
struct bpf_array_aux {
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
struct mutex poke_mutex;
struct work_struct work;
};
struct bpf_link {
atomic64_t refcnt;
u32 id;
enum bpf_link_type type;
const struct bpf_link_ops *ops;
struct bpf_prog *prog;
struct work_struct work;
};
struct bpf_link_ops {
void (*release)(struct bpf_link *link);
void (*dealloc)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog);
void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
int (*fill_link_info)(const struct bpf_link *link,
struct bpf_link_info *info);
int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
struct bpf_map *old_map);
};
struct bpf_tramp_link {
struct bpf_link link;
struct hlist_node tramp_hlist;
u64 cookie;
};
struct bpf_shim_tramp_link {
struct bpf_tramp_link link;
struct bpf_trampoline *trampoline;
};
struct bpf_tracing_link {
struct bpf_tramp_link link;
enum bpf_attach_type attach_type;
struct bpf_trampoline *trampoline;
struct bpf_prog *tgt_prog;
};
struct bpf_link_primer {
struct bpf_link *link;
struct file *file;
int fd;
u32 id;
};
struct bpf_struct_ops_value;
struct btf_member;
#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
/**
* struct bpf_struct_ops - A structure of callbacks allowing a subsystem to
* define a BPF_MAP_TYPE_STRUCT_OPS map type composed
* of BPF_PROG_TYPE_STRUCT_OPS progs.
* @verifier_ops: A structure of callbacks that are invoked by the verifier
* when determining whether the struct_ops progs in the
* struct_ops map are valid.
* @init: A callback that is invoked a single time, and before any other
* callback, to initialize the structure. A nonzero return value means
* the subsystem could not be initialized.
* @check_member: When defined, a callback invoked by the verifier to allow
* the subsystem to determine if an entry in the struct_ops map
* is valid. A nonzero return value means that the map is
* invalid and should be rejected by the verifier.
* @init_member: A callback that is invoked for each member of the struct_ops
* map to allow the subsystem to initialize the member. A nonzero
* value means the member could not be initialized. This callback
* is exclusive with the @type, @type_id, @value_type, and
* @value_id fields.
* @reg: A callback that is invoked when the struct_ops map has been
* initialized and is being attached to. Zero means the struct_ops map
* has been successfully registered and is live. A nonzero return value
* means the struct_ops map could not be registered.
* @unreg: A callback that is invoked when the struct_ops map should be
* unregistered.
* @update: A callback that is invoked when the live struct_ops map is being
* updated to contain new values. This callback is only invoked when
* the struct_ops map is loaded with BPF_F_LINK. If not defined, the
* it is assumed that the struct_ops map cannot be updated.
* @validate: A callback that is invoked after all of the members have been
* initialized. This callback should perform static checks on the
* map, meaning that it should either fail or succeed
* deterministically. A struct_ops map that has been validated may
* not necessarily succeed in being registered if the call to @reg
* fails. For example, a valid struct_ops map may be loaded, but
* then fail to be registered due to there being another active
* struct_ops map on the system in the subsystem already. For this
* reason, if this callback is not defined, the check is skipped as
* the struct_ops map will have final verification performed in
* @reg.
* @type: BTF type.
* @value_type: Value type.
* @name: The name of the struct bpf_struct_ops object.
* @func_models: Func models
* @type_id: BTF type id.
* @value_id: BTF value id.
*/
struct bpf_struct_ops {
const struct bpf_verifier_ops *verifier_ops;
int (*init)(struct btf *btf);
int (*check_member)(const struct btf_type *t,
const struct btf_member *member,
const struct bpf_prog *prog);
int (*init_member)(const struct btf_type *t,
const struct btf_member *member,
void *kdata, const void *udata);
int (*reg)(void *kdata);
void (*unreg)(void *kdata);
int (*update)(void *kdata, void *old_kdata);
int (*validate)(void *kdata);
const struct btf_type *type;
const struct btf_type *value_type;
const char *name;
struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
u32 type_id;
u32 value_id;
};
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log);
bool bpf_struct_ops_get(const void *kdata);
void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
struct bpf_tramp_link *link,
const struct btf_func_model *model,
void *image, void *image_end);
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
return bpf_struct_ops_get(data);
else
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
bpf_struct_ops_put(data);
else
module_put(owner);
}
int bpf_struct_ops_link_create(union bpf_attr *attr);
#ifdef CONFIG_NET
/* Define it here to avoid the use of forward declaration */
struct bpf_dummy_ops_state {
int val;
};
struct bpf_dummy_ops {
int (*test_1)(struct bpf_dummy_ops_state *cb);
int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
char a3, unsigned long a4);
int (*test_sleepable)(struct bpf_dummy_ops_state *cb);
};
int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
#endif
#else
static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
{
return NULL;
}
static inline void bpf_struct_ops_init(struct btf *btf,
struct bpf_verifier_log *log)
{
}
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
module_put(owner);
}
static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
void *key,
void *value)
{
return -EINVAL;
}
static inline int bpf_struct_ops_link_create(union bpf_attr *attr)
{
return -EOPNOTSUPP;
}
#endif
#if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
int cgroup_atype);
void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog);
#else
static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
int cgroup_atype)
{
return -EOPNOTSUPP;
}
static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
{
}
#endif
struct bpf_array {
struct bpf_map map;
u32 elem_size;
u32 index_mask;
struct bpf_array_aux *aux;
union {
DECLARE_FLEX_ARRAY(char, value) __aligned(8);
DECLARE_FLEX_ARRAY(void *, ptrs) __aligned(8);
DECLARE_FLEX_ARRAY(void __percpu *, pptrs) __aligned(8);
};
};
#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */
#define MAX_TAIL_CALL_CNT 33
/* Maximum number of loops for bpf_loop and bpf_iter_num.
* It's enum to expose it (and thus make it discoverable) through BTF.
*/
enum {
BPF_MAX_LOOPS = 8 * 1024 * 1024,
};
#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \
BPF_F_RDONLY_PROG | \
BPF_F_WRONLY | \
BPF_F_WRONLY_PROG)
#define BPF_MAP_CAN_READ BIT(0)
#define BPF_MAP_CAN_WRITE BIT(1)
/* Maximum number of user-producer ring buffer samples that can be drained in
* a call to bpf_user_ringbuf_drain().
*/
#define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024)
static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
{
u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
* not possible.
*/
if (access_flags & BPF_F_RDONLY_PROG)
return BPF_MAP_CAN_READ;
else if (access_flags & BPF_F_WRONLY_PROG)
return BPF_MAP_CAN_WRITE;
else
return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
}
static inline bool bpf_map_flags_access_ok(u32 access_flags)
{
return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
(BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
}
struct bpf_event_entry {
struct perf_event *event;
struct file *perf_file;
struct file *map_file;
struct rcu_head rcu;
};
static inline bool map_type_contains_progs(struct bpf_map *map)
{
return map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
map->map_type == BPF_MAP_TYPE_DEVMAP ||
map->map_type == BPF_MAP_TYPE_CPUMAP;
}
bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp);
int bpf_prog_calc_tag(struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void);
typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
unsigned long off, unsigned long len);
typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog,
u32 *target_size);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
/* an array of programs to be executed under rcu_lock.
*
* Typical usage:
* ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run);
*
* the structure returned by bpf_prog_array_alloc() should be populated
* with program pointers and the last pointer must be NULL.
* The user has to keep refcnt on the program and make sure the program
* is removed from the array before bpf_prog_put().
* The 'struct bpf_prog_array *' should only be replaced with xchg()
* since other cpus are walking the array of pointers in parallel.
*/
struct bpf_prog_array_item {
struct bpf_prog *prog;
union {
struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
u64 bpf_cookie;
};
};
struct bpf_prog_array {
struct rcu_head rcu;
struct bpf_prog_array_item items[];
};
struct bpf_empty_prog_array {
struct bpf_prog_array hdr;
struct bpf_prog *null_prog;
};
/* to avoid allocating empty bpf_prog_array for cgroups that
* don't have bpf program attached use one global 'bpf_empty_prog_array'
* It will not be modified the caller of bpf_prog_array_alloc()
* (since caller requested prog_cnt == 0)
* that pointer should be 'freed' by bpf_prog_array_free()
*/
extern struct bpf_empty_prog_array bpf_empty_prog_array;
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
void bpf_prog_array_free(struct bpf_prog_array *progs);
/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */
void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs);
int bpf_prog_array_length(struct bpf_prog_array *progs);
bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
__u32 __user *prog_ids, u32 cnt);
void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index);
int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
struct bpf_prog *prog);
int bpf_prog_array_copy_info(struct bpf_prog_array *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
u64 bpf_cookie,
struct bpf_prog_array **new_array);
struct bpf_run_ctx {};
struct bpf_cg_run_ctx {
struct bpf_run_ctx run_ctx;
const struct bpf_prog_array_item *prog_item;
int retval;
};
struct bpf_trace_run_ctx {
struct bpf_run_ctx run_ctx;
u64 bpf_cookie;
bool is_uprobe;
};
struct bpf_tramp_run_ctx {
struct bpf_run_ctx run_ctx;
u64 bpf_cookie;
struct bpf_run_ctx *saved_run_ctx;
};
static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
{
struct bpf_run_ctx *old_ctx = NULL;
#ifdef CONFIG_BPF_SYSCALL
old_ctx = current->bpf_ctx;
current->bpf_ctx = new_ctx;
#endif
return old_ctx;
}
static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
{
#ifdef CONFIG_BPF_SYSCALL
current->bpf_ctx = old_ctx;
#endif
}
/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */
#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0)
/* BPF program asks to set CN on the packet. */
#define BPF_RET_SET_CN (1 << 0)
typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
static __always_inline u32
bpf_prog_run_array(const struct bpf_prog_array *array,
const void *ctx, bpf_prog_run_fn run_prog)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
struct bpf_run_ctx *old_run_ctx;
struct bpf_trace_run_ctx run_ctx;
u32 ret = 1;
RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held");
if (unlikely(!array))
return ret;
run_ctx.is_uprobe = false;
migrate_disable();
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
item = &array->items[0];
while ((prog = READ_ONCE(item->prog))) {
run_ctx.bpf_cookie = item->bpf_cookie;
ret &= run_prog(prog, ctx);
item++;
}
bpf_reset_run_ctx(old_run_ctx);
migrate_enable();
return ret;
}
/* Notes on RCU design for bpf_prog_arrays containing sleepable programs:
*
* We use the tasks_trace rcu flavor read section to protect the bpf_prog_array
* overall. As a result, we must use the bpf_prog_array_free_sleepable
* in order to use the tasks_trace rcu grace period.
*
* When a non-sleepable program is inside the array, we take the rcu read
* section and disable preemption for that program alone, so it can access
* rcu-protected dynamically sized maps.
*/
static __always_inline u32
bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
const void *ctx, bpf_prog_run_fn run_prog)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
const struct bpf_prog_array *array;
struct bpf_run_ctx *old_run_ctx;
struct bpf_trace_run_ctx run_ctx;
u32 ret = 1;
might_fault();
rcu_read_lock_trace();
migrate_disable();
run_ctx.is_uprobe = true;
array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
if (unlikely(!array))
goto out;
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
item = &array->items[0];
while ((prog = READ_ONCE(item->prog))) {
if (!prog->aux->sleepable)
rcu_read_lock();
run_ctx.bpf_cookie = item->bpf_cookie;
ret &= run_prog(prog, ctx);
item++;
if (!prog->aux->sleepable)
rcu_read_unlock();
}
bpf_reset_run_ctx(old_run_ctx);
out:
migrate_enable();
rcu_read_unlock_trace();
return ret;
}
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern struct mutex bpf_stats_enabled_mutex;
/*
* Block execution of BPF programs attached to instrumentation (perf,
* kprobes, tracepoints) to prevent deadlocks on map operations as any of
* these events can happen inside a region which holds a map bucket lock
* and can deadlock on it.
*/
static inline void bpf_disable_instrumentation(void)
{
migrate_disable();
this_cpu_inc(bpf_prog_active);
}
static inline void bpf_enable_instrumentation(void)
{
this_cpu_dec(bpf_prog_active);
migrate_enable();
}
extern const struct file_operations bpf_map_fops;
extern const struct file_operations bpf_prog_fops;
extern const struct file_operations bpf_iter_fops;
#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
extern const struct bpf_prog_ops _name ## _prog_ops; \
extern const struct bpf_verifier_ops _name ## _verifier_ops;
#define BPF_MAP_TYPE(_id, _ops) \
extern const struct bpf_map_ops _ops;
#define BPF_LINK_TYPE(_id, _name)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
#undef BPF_LINK_TYPE
extern const struct bpf_prog_ops bpf_offload_prog_ops;
extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
extern const struct bpf_verifier_ops xdp_analyzer_ops;
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
bool attach_drv);
void bpf_prog_add(struct bpf_prog *prog, int i);
void bpf_prog_sub(struct bpf_prog *prog, int i);
void bpf_prog_inc(struct bpf_prog *prog);
struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
void bpf_prog_free_id(struct bpf_prog *prog);
void bpf_map_free_id(struct bpf_map *map);
struct btf_field *btf_record_find(const struct btf_record *rec,
u32 offset, u32 field_mask);
void btf_record_free(struct btf_record *rec);
void bpf_map_free_record(struct bpf_map *map);
struct btf_record *btf_record_dup(const struct btf_record *rec);
bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
struct bpf_map *bpf_map_get(u32 ufd);
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
void bpf_map_inc(struct bpf_map *map);
void bpf_map_inc_with_uref(struct bpf_map *map);
struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref);
struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
void bpf_map_area_free(void *base);
bool bpf_map_write_active(const struct bpf_map *map);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
#ifdef CONFIG_MEMCG_KMEM
void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
int node);
void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags);
void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size,
gfp_t flags);
void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
size_t align, gfp_t flags);
#else
static inline void *
bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
int node)
{
return kmalloc_node(size, flags, node);
}
static inline void *
bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
{
return kzalloc(size, flags);
}
static inline void *
bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags)
{
return kvcalloc(n, size, flags);
}
static inline void __percpu *
bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
gfp_t flags)
{
return __alloc_percpu_gfp(size, align, flags);
}
#endif
static inline int
bpf_map_init_elem_count(struct bpf_map *map)
{
size_t size = sizeof(*map->elem_count), align = size;
gfp_t flags = GFP_USER | __GFP_NOWARN;
map->elem_count = bpf_map_alloc_percpu(map, size, align, flags);
if (!map->elem_count)
return -ENOMEM;
return 0;
}
static inline void
bpf_map_free_elem_count(struct bpf_map *map)
{
free_percpu(map->elem_count);
}
static inline void bpf_map_inc_elem_count(struct bpf_map *map)
{
this_cpu_inc(*map->elem_count);
}
static inline void bpf_map_dec_elem_count(struct bpf_map *map)
{
this_cpu_dec(*map->elem_count);
}
extern int sysctl_unprivileged_bpf_disabled;
static inline bool bpf_allow_ptr_leaks(void)
{
return perfmon_capable();
}
static inline bool bpf_allow_uninit_stack(void)
{
return perfmon_capable();
}
static inline bool bpf_bypass_spec_v1(void)
{
return cpu_mitigations_off() || perfmon_capable();
}
static inline bool bpf_bypass_spec_v4(void)
{
return cpu_mitigations_off() || perfmon_capable();
}
int bpf_map_new_fd(struct bpf_map *map, int flags);
int bpf_prog_new_fd(struct bpf_prog *prog);
void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
const struct bpf_link_ops *ops, struct bpf_prog *prog);
int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
int bpf_link_settle(struct bpf_link_primer *primer);
void bpf_link_cleanup(struct bpf_link_primer *primer);
void bpf_link_inc(struct bpf_link *link);
void bpf_link_put(struct bpf_link *link);
int bpf_link_new_fd(struct bpf_link *link);
struct bpf_link *bpf_link_get_from_fd(u32 ufd);
struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
#define BPF_ITER_FUNC_PREFIX "bpf_iter_"
#define DEFINE_BPF_ITER_FUNC(target, args...) \
extern int bpf_iter_ ## target(args); \
int __init bpf_iter_ ## target(args) { return 0; }
/*
* The task type of iterators.
*
* For BPF task iterators, they can be parameterized with various
* parameters to visit only some of tasks.
*
* BPF_TASK_ITER_ALL (default)
* Iterate over resources of every task.
*
* BPF_TASK_ITER_TID
* Iterate over resources of a task/tid.
*
* BPF_TASK_ITER_TGID
* Iterate over resources of every task of a process / task group.
*/
enum bpf_iter_task_type {
BPF_TASK_ITER_ALL = 0,
BPF_TASK_ITER_TID,
BPF_TASK_ITER_TGID,
};
struct bpf_iter_aux_info {
/* for map_elem iter */
struct bpf_map *map;
/* for cgroup iter */
struct {
struct cgroup *start; /* starting cgroup */
enum bpf_cgroup_iter_order order;
} cgroup;
struct {
enum bpf_iter_task_type type;
u32 pid;
} task;
};
typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
struct seq_file *seq);
typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
typedef const struct bpf_func_proto *
(*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id,
const struct bpf_prog *prog);
enum bpf_iter_feature {
BPF_ITER_RESCHED = BIT(0),
};
#define BPF_ITER_CTX_ARG_MAX 2
struct bpf_iter_reg {
const char *target;
bpf_iter_attach_target_t attach_target;
bpf_iter_detach_target_t detach_target;
bpf_iter_show_fdinfo_t show_fdinfo;
bpf_iter_fill_link_info_t fill_link_info;
bpf_iter_get_func_proto_t get_func_proto;
u32 ctx_arg_info_size;
u32 feature;
struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
const struct bpf_iter_seq_info *seq_info;
};
struct bpf_iter_meta {
__bpf_md_ptr(struct seq_file *, seq);
u64 session_id;
u64 seq_num;
};
struct bpf_iter__bpf_map_elem {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct bpf_map *, map);
__bpf_md_ptr(void *, key);
__bpf_md_ptr(void *, value);
};
int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
bool bpf_iter_prog_supported(struct bpf_prog *prog);
const struct bpf_func_proto *
bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog);
int bpf_iter_new_fd(struct bpf_link *link);
bool bpf_link_is_iter(struct bpf_link *link);
struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
struct seq_file *seq);
int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
int map_set_for_each_callback_args(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_get_file_flag(int flags);
int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
size_t actual_size);
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size);
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
#endif
struct btf *bpf_get_btf_vmlinux(void);
/* Map specifics */
struct xdp_frame;
struct sk_buff;
struct bpf_dtab_netdev;
struct bpf_cpu_map_entry;
void __dev_flush(void);
int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
struct net_device *dev_rx);
int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
struct bpf_map *map, bool exclude_ingress);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
struct bpf_prog *xdp_prog, struct bpf_map *map,
bool exclude_ingress);
void __cpu_map_flush(void);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
struct net_device *dev_rx);
int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
struct sk_buff *skb);
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
return (attr->map_flags & BPF_F_NUMA_NODE) ?
attr->numa_node : NUMA_NO_NODE;
}
struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
int array_map_alloc_check(union bpf_attr *attr);
int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_tracing(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_nf(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
static inline bool bpf_tracing_ctx_access(int off, int size,
enum bpf_access_type type)
{
if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
return false;
if (type != BPF_READ)
return false;
if (off % size != 0)
return false;
return true;
}
static inline bool bpf_tracing_btf_ctx_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (!bpf_tracing_ctx_access(off, size, type))
return false;
return btf_ctx_access(off, size, type, prog, info);
}
int btf_struct_access(struct bpf_verifier_log *log,
const struct bpf_reg_state *reg,
int off, int size, enum bpf_access_type atype,
u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name);
bool btf_struct_ids_match(struct bpf_verifier_log *log,
const struct btf *btf, u32 id, int off,
const struct btf *need_btf, u32 need_type_id,
bool strict);
int btf_distill_func_proto(struct bpf_verifier_log *log,
struct btf *btf,
const struct btf_type *func_proto,
const char *func_name,
struct btf_func_model *m);
struct bpf_reg_state;
int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *regs);
int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *regs);
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg, bool is_ex_cb);
int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
struct btf *btf, const struct btf_type *t);
const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
int comp_idx, const char *tag_key);
struct bpf_prog *bpf_prog_by_id(u32 id);
struct bpf_link *bpf_link_by_id(u32 id);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
void bpf_task_storage_free(struct task_struct *task);
void bpf_cgrp_storage_free(struct cgroup *cgroup);
bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
const struct btf_func_model *
bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
const struct bpf_insn *insn);
int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id,
u16 btf_fd_idx, u8 **func_addr);
struct bpf_core_ctx {
struct bpf_verifier_log *log;
const struct btf *btf;
};
bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
const struct bpf_reg_state *reg,
const char *field_name, u32 btf_id, const char *suffix);
bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log,
const struct btf *reg_btf, u32 reg_id,
const struct btf *arg_btf, u32 arg_id);
int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
int relo_idx, void *insn);
static inline bool unprivileged_ebpf_enabled(void)
{
return !sysctl_unprivileged_bpf_disabled;
}
/* Not all bpf prog type has the bpf_ctx.
* For the bpf prog type that has initialized the bpf_ctx,
* this function can be used to decide if a kernel function
* is called by a bpf program.
*/
static inline bool has_current_bpf_ctx(void)
{
return !!current->bpf_ctx;
}
void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog);
void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
enum bpf_dynptr_type type, u32 offset, u32 size);
void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr);
bool dev_check_flush(void);
bool cpu_map_check_flush(void);
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
enum bpf_prog_type type,
bool attach_drv)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_prog_add(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
static inline void bpf_prog_inc(struct bpf_prog *prog)
{
}
static inline struct bpf_prog *__must_check
bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
const struct bpf_link_ops *ops,
struct bpf_prog *prog)
{
}
static inline int bpf_link_prime(struct bpf_link *link,
struct bpf_link_primer *primer)
{
return -EOPNOTSUPP;
}
static inline int bpf_link_settle(struct bpf_link_primer *primer)
{
return -EOPNOTSUPP;
}
static inline void bpf_link_cleanup(struct bpf_link_primer *primer)
{
}
static inline void bpf_link_inc(struct bpf_link *link)
{
}
static inline void bpf_link_put(struct bpf_link *link)
{
}
static inline int bpf_obj_get_user(const char __user *pathname, int flags)
{
return -EOPNOTSUPP;
}
static inline void __dev_flush(void)
{
}
struct xdp_frame;
struct bpf_dtab_netdev;
struct bpf_cpu_map_entry;
static inline
int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
return 0;
}
static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
return 0;
}
static inline
int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
struct bpf_map *map, bool exclude_ingress)
{
return 0;
}
struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
return 0;
}
static inline
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
struct bpf_prog *xdp_prog, struct bpf_map *map,
bool exclude_ingress)
{
return 0;
}
static inline void __cpu_map_flush(void)
{
}
static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
return 0;
}
static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
struct sk_buff *skb)
{
return -EOPNOTSUPP;
}
static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
enum bpf_prog_type type)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline void bpf_map_put(struct bpf_map *map)
{
}
static inline struct bpf_prog *bpf_prog_by_id(u32 id)
{
return ERR_PTR(-ENOTSUPP);
}
static inline int btf_struct_access(struct bpf_verifier_log *log,
const struct bpf_reg_state *reg,
int off, int size, enum bpf_access_type atype,
u32 *next_btf_id, enum bpf_type_flag *flag,
const char **field_name)
{
return -EACCES;
}
static inline const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
return NULL;
}
static inline void bpf_task_storage_free(struct task_struct *task)
{
}
static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog)
{
return false;
}
static inline const struct btf_func_model *
bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
const struct bpf_insn *insn)
{
return NULL;
}
static inline int
bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id,
u16 btf_fd_idx, u8 **func_addr)
{
return -ENOTSUPP;
}
static inline bool unprivileged_ebpf_enabled(void)
{
return false;
}
static inline bool has_current_bpf_ctx(void)
{
return false;
}
static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog)
{
}
static inline void bpf_cgrp_storage_free(struct cgroup *cgroup)
{
}
static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
enum bpf_dynptr_type type, u32 offset, u32 size)
{
}
static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
{
}
static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
{
}
#endif /* CONFIG_BPF_SYSCALL */
static __always_inline int
bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
{
int ret = -EFAULT;
if (IS_ENABLED(CONFIG_BPF_EVENTS))
ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
return ret;
}
void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
struct btf_mod_pair *used_btfs, u32 len);
static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
enum bpf_prog_type type)
{
return bpf_prog_get_type_dev(ufd, type, false);
}
void __bpf_free_used_maps(struct bpf_prog_aux *aux,
struct bpf_map **used_maps, u32 len);
bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
int bpf_prog_offload_compile(struct bpf_prog *prog);
void bpf_prog_dev_bound_destroy(struct bpf_prog *prog);
int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
struct bpf_prog *prog);
int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map);
int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value);
int bpf_map_offload_update_elem(struct bpf_map *map,
void *key, void *value, u64 flags);
int bpf_map_offload_delete_elem(struct bpf_map *map, void *key);
int bpf_map_offload_get_next_key(struct bpf_map *map,
void *key, void *next_key);
bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
struct bpf_offload_dev *
bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv);
void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev);
int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
struct net_device *netdev);
void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
struct net_device *netdev);
bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
void unpriv_ebpf_notify(int new_state);
#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
struct bpf_prog_aux *prog_aux);
void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id);
int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr);
int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog);
void bpf_dev_bound_netdev_unregister(struct net_device *dev);
static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
{
return aux->dev_bound;
}
static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux)
{
return aux->offload_requested;
}
bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs);
static inline bool bpf_map_is_offloaded(struct bpf_map *map)
{
return unlikely(map->ops == &bpf_map_offload_ops);
}
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
void bpf_map_offload_map_free(struct bpf_map *map);
u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map);
int bpf_prog_test_run_syscall(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
int sock_map_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr);
void sock_map_unhash(struct sock *sk);
void sock_map_destroy(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#else
static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
struct bpf_prog_aux *prog_aux)
{
return -EOPNOTSUPP;
}
static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog,
u32 func_id)
{
return NULL;
}
static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog,
union bpf_attr *attr)
{
return -EOPNOTSUPP;
}
static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog,
struct bpf_prog *old_prog)
{
return -EOPNOTSUPP;
}
static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev)
{
}
static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
{
return false;
}
static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux)
{
return false;
}
static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs)
{
return false;
}
static inline bool bpf_map_is_offloaded(struct bpf_map *map)
{
return false;
}
static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_map_offload_map_free(struct bpf_map *map)
{
}
static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map)
{
return 0;
}
static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
#ifdef CONFIG_BPF_SYSCALL
static inline int sock_map_get_from_fd(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
static inline int sock_map_prog_detach(const union bpf_attr *attr,
enum bpf_prog_type ptype)
{
return -EOPNOTSUPP;
}
static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
u64 flags)
{
return -EOPNOTSUPP;
}
static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return -EINVAL;
}
#endif /* CONFIG_BPF_SYSCALL */
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
static __always_inline void
bpf_prog_inc_misses_counters(const struct bpf_prog_array *array)
{
const struct bpf_prog_array_item *item;
struct bpf_prog *prog;
if (unlikely(!array))
return;
item = &array->items[0];
while ((prog = READ_ONCE(item->prog))) {
bpf_prog_inc_misses_counter(prog);
item++;
}
}
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
void bpf_sk_reuseport_detach(struct sock *sk);
int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
void *value);
int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags);
#else
static inline void bpf_sk_reuseport_detach(struct sock *sk)
{
}
#ifdef CONFIG_BPF_SYSCALL
static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
void *key, void *value)
{
return -EOPNOTSUPP;
}
static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
void *key, void *value,
u64 map_flags)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_BPF_SYSCALL */
#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
/* verifier prototypes for helper functions called from eBPF programs */
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
extern const struct bpf_func_proto bpf_map_delete_elem_proto;
extern const struct bpf_func_proto bpf_map_push_elem_proto;
extern const struct bpf_func_proto bpf_map_pop_elem_proto;
extern const struct bpf_func_proto bpf_map_peek_elem_proto;
extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto;
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
extern const struct bpf_func_proto bpf_tail_call_proto;
extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto;
extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto;
extern const struct bpf_func_proto bpf_get_stack_proto;
extern const struct bpf_func_proto bpf_get_task_stack_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
extern const struct bpf_func_proto bpf_get_stack_proto_pe;
extern const struct bpf_func_proto bpf_sock_map_update_proto;
extern const struct bpf_func_proto bpf_sock_hash_update_proto;
extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto;
extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto;
extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
extern const struct bpf_func_proto bpf_spin_lock_proto;
extern const struct bpf_func_proto bpf_spin_unlock_proto;
extern const struct bpf_func_proto bpf_get_local_storage_proto;
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
extern const struct bpf_func_proto bpf_tcp_sock_proto;
extern const struct bpf_func_proto bpf_jiffies64_proto;
extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_event_output_data_proto;
extern const struct bpf_func_proto bpf_ringbuf_output_proto;
extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
extern const struct bpf_func_proto bpf_ringbuf_query_proto;
extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto;
extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto;
extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto;
extern const struct bpf_func_proto bpf_copy_from_user_proto;
extern const struct bpf_func_proto bpf_snprintf_btf_proto;
extern const struct bpf_func_proto bpf_snprintf_proto;
extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
extern const struct bpf_func_proto bpf_sock_from_file_proto;
extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto;
extern const struct bpf_func_proto bpf_task_storage_get_recur_proto;
extern const struct bpf_func_proto bpf_task_storage_get_proto;
extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto;
extern const struct bpf_func_proto bpf_task_storage_delete_proto;
extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto;
extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto;
extern const struct bpf_func_proto bpf_find_vma_proto;
extern const struct bpf_func_proto bpf_loop_proto;
extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
extern const struct bpf_func_proto bpf_set_retval_proto;
extern const struct bpf_func_proto bpf_get_retval_proto;
extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto;
extern const struct bpf_func_proto bpf_cgrp_storage_get_proto;
extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto;
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
#if defined(CONFIG_NET)
bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info);
bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
struct bpf_dynptr_kern *ptr);
#else
static inline bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline bool bpf_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
struct bpf_dynptr_kern *ptr)
{
return -EOPNOTSUPP;
}
#endif
#ifdef CONFIG_INET
struct sk_reuseport_kern {
struct sk_buff *skb;
struct sock *sk;
struct sock *selected_sk;
struct sock *migrating_sk;
void *data_end;
u32 hash;
u32 reuseport_id;
bool bind_inany;
};
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
#else
static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
static inline bool bpf_xdp_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
#endif /* CONFIG_INET */
enum bpf_text_poke_type {
BPF_MOD_CALL,
BPF_MOD_JUMP,
};
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
struct bpf_prog *new, struct bpf_prog *old);
void *bpf_arch_text_copy(void *dst, void *src, size_t len);
int bpf_arch_text_invalidate(void *dst, size_t len);
struct btf_id_set;
bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
#define MAX_BPRINTF_VARARGS 12
#define MAX_BPRINTF_BUF 1024
struct bpf_bprintf_data {
u32 *bin_args;
char *buf;
bool get_bin_args;
bool get_buf;
};
int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
u32 num_args, struct bpf_bprintf_data *data);
void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
#ifdef CONFIG_BPF_LSM
void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
void bpf_cgroup_atype_put(int cgroup_atype);
#else
static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {}
static inline void bpf_cgroup_atype_put(int cgroup_atype) {}
#endif /* CONFIG_BPF_LSM */
struct key;
#ifdef CONFIG_KEYS
struct bpf_key {
struct key *key;
bool has_ref;
};
#endif /* CONFIG_KEYS */
static inline bool type_is_alloc(u32 type)
{
return type & MEM_ALLOC;
}
static inline gfp_t bpf_memcg_flags(gfp_t flags)
{
if (memcg_bpf_enabled())
return flags | __GFP_ACCOUNT;
return flags;
}
static inline bool bpf_is_subprog(const struct bpf_prog *prog)
{
return prog->aux->func_idx != 0;
}
#endif /* _LINUX_BPF_H */
|