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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux Socket Filter - Kernel level socket filtering
*
* Based on the design of the Berkeley Packet Filter. The new
* internal format has been designed by PLUMgrid:
*
* Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
*
* Authors:
*
* Jay Schulist <jschlst@samba.org>
* Alexei Starovoitov <ast@plumgrid.com>
* Daniel Borkmann <dborkman@redhat.com>
*
* Andi Kleen - Fix a few bad bugs and races.
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
#include <uapi/linux/btf.h>
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/moduleloader.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/objtool.h>
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/log2.h>
#include <linux/bpf_verifier.h>
#include <linux/nodemask.h>
#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
#define BPF_R0 regs[BPF_REG_0]
#define BPF_R1 regs[BPF_REG_1]
#define BPF_R2 regs[BPF_REG_2]
#define BPF_R3 regs[BPF_REG_3]
#define BPF_R4 regs[BPF_REG_4]
#define BPF_R5 regs[BPF_REG_5]
#define BPF_R6 regs[BPF_REG_6]
#define BPF_R7 regs[BPF_REG_7]
#define BPF_R8 regs[BPF_REG_8]
#define BPF_R9 regs[BPF_REG_9]
#define BPF_R10 regs[BPF_REG_10]
/* Named registers */
#define DST regs[insn->dst_reg]
#define SRC regs[insn->src_reg]
#define FP regs[BPF_REG_FP]
#define AX regs[BPF_REG_AX]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
#define IMM insn->imm
/* No hurry in this branch
*
* Exported for the bpf jit load helper.
*/
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
u8 *ptr = NULL;
if (k >= SKF_NET_OFF)
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
else if (k >= SKF_LL_OFF)
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
return NULL;
}
struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
size = round_up(size, PAGE_SIZE);
fp = __vmalloc(size, gfp_flags);
if (fp == NULL)
return NULL;
aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags);
if (aux == NULL) {
vfree(fp);
return NULL;
}
fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags);
if (!fp->active) {
vfree(fp);
kfree(aux);
return NULL;
}
fp->pages = size / PAGE_SIZE;
fp->aux = aux;
fp->aux->prog = fp;
fp->jit_requested = ebpf_jit_enabled();
fp->blinding_requested = bpf_jit_blinding_enabled(fp);
INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
mutex_init(&fp->aux->used_maps_mutex);
mutex_init(&fp->aux->dst_mutex);
return fp;
}
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *prog;
int cpu;
prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags);
if (!prog)
return NULL;
prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
if (!prog->stats) {
free_percpu(prog->active);
kfree(prog->aux);
vfree(prog);
return NULL;
}
for_each_possible_cpu(cpu) {
struct bpf_prog_stats *pstats;
pstats = per_cpu_ptr(prog->stats, cpu);
u64_stats_init(&pstats->syncp);
}
return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_alloc);
int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
{
if (!prog->aux->nr_linfo || !prog->jit_requested)
return 0;
prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo,
sizeof(*prog->aux->jited_linfo),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!prog->aux->jited_linfo)
return -ENOMEM;
return 0;
}
void bpf_prog_jit_attempt_done(struct bpf_prog *prog)
{
if (prog->aux->jited_linfo &&
(!prog->jited || !prog->aux->jited_linfo[0])) {
kvfree(prog->aux->jited_linfo);
prog->aux->jited_linfo = NULL;
}
kfree(prog->aux->kfunc_tab);
prog->aux->kfunc_tab = NULL;
}
/* The jit engine is responsible to provide an array
* for insn_off to the jited_off mapping (insn_to_jit_off).
*
* The idx to this array is the insn_off. Hence, the insn_off
* here is relative to the prog itself instead of the main prog.
* This array has one entry for each xlated bpf insn.
*
* jited_off is the byte off to the end of the jited insn.
*
* Hence, with
* insn_start:
* The first bpf insn off of the prog. The insn off
* here is relative to the main prog.
* e.g. if prog is a subprog, insn_start > 0
* linfo_idx:
* The prog's idx to prog->aux->linfo and jited_linfo
*
* jited_linfo[linfo_idx] = prog->bpf_func
*
* For i > linfo_idx,
*
* jited_linfo[i] = prog->bpf_func +
* insn_to_jit_off[linfo[i].insn_off - insn_start - 1]
*/
void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
const u32 *insn_to_jit_off)
{
u32 linfo_idx, insn_start, insn_end, nr_linfo, i;
const struct bpf_line_info *linfo;
void **jited_linfo;
if (!prog->aux->jited_linfo)
/* Userspace did not provide linfo */
return;
linfo_idx = prog->aux->linfo_idx;
linfo = &prog->aux->linfo[linfo_idx];
insn_start = linfo[0].insn_off;
insn_end = insn_start + prog->len;
jited_linfo = &prog->aux->jited_linfo[linfo_idx];
jited_linfo[0] = prog->bpf_func;
nr_linfo = prog->aux->nr_linfo - linfo_idx;
for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++)
/* The verifier ensures that linfo[i].insn_off is
* strictly increasing
*/
jited_linfo[i] = prog->bpf_func +
insn_to_jit_off[linfo[i].insn_off - insn_start - 1];
}
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
u32 pages;
size = round_up(size, PAGE_SIZE);
pages = size / PAGE_SIZE;
if (pages <= fp_old->pages)
return fp_old;
fp = __vmalloc(size, gfp_flags);
if (fp) {
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
fp->pages = pages;
fp->aux->prog = fp;
/* We keep fp->aux from fp_old around in the new
* reallocated structure.
*/
fp_old->aux = NULL;
fp_old->stats = NULL;
fp_old->active = NULL;
__bpf_prog_free(fp_old);
}
return fp;
}
void __bpf_prog_free(struct bpf_prog *fp)
{
if (fp->aux) {
mutex_destroy(&fp->aux->used_maps_mutex);
mutex_destroy(&fp->aux->dst_mutex);
kfree(fp->aux->poke_tab);
kfree(fp->aux);
}
free_percpu(fp->stats);
free_percpu(fp->active);
vfree(fp);
}
int bpf_prog_calc_tag(struct bpf_prog *fp)
{
const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64);
u32 raw_size = bpf_prog_tag_scratch_size(fp);
u32 digest[SHA1_DIGEST_WORDS];
u32 ws[SHA1_WORKSPACE_WORDS];
u32 i, bsize, psize, blocks;
struct bpf_insn *dst;
bool was_ld_map;
u8 *raw, *todo;
__be32 *result;
__be64 *bits;
raw = vmalloc(raw_size);
if (!raw)
return -ENOMEM;
sha1_init(digest);
memset(ws, 0, sizeof(ws));
/* We need to take out the map fd for the digest calculation
* since they are unstable from user space side.
*/
dst = (void *)raw;
for (i = 0, was_ld_map = false; i < fp->len; i++) {
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
(dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
was_ld_map = true;
dst[i].imm = 0;
} else if (was_ld_map &&
dst[i].code == 0 &&
dst[i].dst_reg == 0 &&
dst[i].src_reg == 0 &&
dst[i].off == 0) {
was_ld_map = false;
dst[i].imm = 0;
} else {
was_ld_map = false;
}
}
psize = bpf_prog_insn_size(fp);
memset(&raw[psize], 0, raw_size - psize);
raw[psize++] = 0x80;
bsize = round_up(psize, SHA1_BLOCK_SIZE);
blocks = bsize / SHA1_BLOCK_SIZE;
todo = raw;
if (bsize - psize >= sizeof(__be64)) {
bits = (__be64 *)(todo + bsize - sizeof(__be64));
} else {
bits = (__be64 *)(todo + bsize + bits_offset);
blocks++;
}
*bits = cpu_to_be64((psize - 1) << 3);
while (blocks--) {
sha1_transform(digest, todo, ws);
todo += SHA1_BLOCK_SIZE;
}
result = (__force __be32 *)digest;
for (i = 0; i < SHA1_DIGEST_WORDS; i++)
result[i] = cpu_to_be32(digest[i]);
memcpy(fp->tag, result, sizeof(fp->tag));
vfree(raw);
return 0;
}
static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
s32 end_new, s32 curr, const bool probe_pass)
{
const s64 imm_min = S32_MIN, imm_max = S32_MAX;
s32 delta = end_new - end_old;
s64 imm = insn->imm;
if (curr < pos && curr + imm + 1 >= end_old)
imm += delta;
else if (curr >= end_new && curr + imm + 1 < end_new)
imm -= delta;
if (imm < imm_min || imm > imm_max)
return -ERANGE;
if (!probe_pass)
insn->imm = imm;
return 0;
}
static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
s32 end_new, s32 curr, const bool probe_pass)
{
const s32 off_min = S16_MIN, off_max = S16_MAX;
s32 delta = end_new - end_old;
s32 off = insn->off;
if (curr < pos && curr + off + 1 >= end_old)
off += delta;
else if (curr >= end_new && curr + off + 1 < end_new)
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
if (!probe_pass)
insn->off = off;
return 0;
}
static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
s32 end_new, const bool probe_pass)
{
u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0);
struct bpf_insn *insn = prog->insnsi;
int ret = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
u8 code;
/* In the probing pass we still operate on the original,
* unpatched image in order to check overflows before we
* do any other adjustments. Therefore skip the patchlet.
*/
if (probe_pass && i == pos) {
i = end_new;
insn = prog->insnsi + end_old;
}
if (bpf_pseudo_func(insn)) {
ret = bpf_adj_delta_to_imm(insn, pos, end_old,
end_new, i, probe_pass);
if (ret)
return ret;
continue;
}
code = insn->code;
if ((BPF_CLASS(code) != BPF_JMP &&
BPF_CLASS(code) != BPF_JMP32) ||
BPF_OP(code) == BPF_EXIT)
continue;
/* Adjust offset of jmps if we cross patch boundaries. */
if (BPF_OP(code) == BPF_CALL) {
if (insn->src_reg != BPF_PSEUDO_CALL)
continue;
ret = bpf_adj_delta_to_imm(insn, pos, end_old,
end_new, i, probe_pass);
} else {
ret = bpf_adj_delta_to_off(insn, pos, end_old,
end_new, i, probe_pass);
}
if (ret)
break;
}
return ret;
}
static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta)
{
struct bpf_line_info *linfo;
u32 i, nr_linfo;
nr_linfo = prog->aux->nr_linfo;
if (!nr_linfo || !delta)
return;
linfo = prog->aux->linfo;
for (i = 0; i < nr_linfo; i++)
if (off < linfo[i].insn_off)
break;
/* Push all off < linfo[i].insn_off by delta */
for (; i < nr_linfo; i++)
linfo[i].insn_off += delta;
}
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len)
{
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
int err;
/* Since our patchlet doesn't expand the image, we're done. */
if (insn_delta == 0) {
memcpy(prog->insnsi + off, patch, sizeof(*patch));
return prog;
}
insn_adj_cnt = prog->len + insn_delta;
/* Reject anything that would potentially let the insn->off
* target overflow when we have excessive program expansions.
* We need to probe here before we do any reallocation where
* we afterwards may not fail anymore.
*/
if (insn_adj_cnt > cnt_max &&
(err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
return ERR_PTR(err);
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
* last page could have large enough tailroom.
*/
prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
GFP_USER);
if (!prog_adj)
return ERR_PTR(-ENOMEM);
prog_adj->len = insn_adj_cnt;
/* Patching happens in 3 steps:
*
* 1) Move over tail of insnsi from next instruction onwards,
* so we can patch the single target insn with one or more
* new ones (patching is always from 1 to n insns, n > 0).
* 2) Inject new instructions at the target location.
* 3) Adjust branch offsets if necessary.
*/
insn_rest = insn_adj_cnt - off - len;
memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
sizeof(*patch) * insn_rest);
memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
/* We are guaranteed to not fail at this point, otherwise
* the ship has sailed to reverse to the original state. An
* overflow cannot happen at this point.
*/
BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false));
bpf_adj_linfo(prog_adj, off, insn_delta);
return prog_adj;
}
int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
{
/* Branch offsets can't overflow when program is shrinking, no need
* to call bpf_adj_branches(..., true) here
*/
memmove(prog->insnsi + off, prog->insnsi + off + cnt,
sizeof(struct bpf_insn) * (prog->len - off - cnt));
prog->len -= cnt;
return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
}
static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
for (i = 0; i < fp->aux->func_cnt; i++)
bpf_prog_kallsyms_del(fp->aux->func[i]);
}
void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
{
bpf_prog_kallsyms_del_subprogs(fp);
bpf_prog_kallsyms_del(fp);
}
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
long bpf_jit_limit_max __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
{
WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
prog->aux->ksym.start = (unsigned long) prog->bpf_func;
prog->aux->ksym.end = prog->aux->ksym.start + prog->jited_len;
}
static void
bpf_prog_ksym_set_name(struct bpf_prog *prog)
{
char *sym = prog->aux->ksym.name;
const char *end = sym + KSYM_NAME_LEN;
const struct btf_type *type;
const char *func_name;
BUILD_BUG_ON(sizeof("bpf_prog_") +
sizeof(prog->tag) * 2 +
/* name has been null terminated.
* We should need +1 for the '_' preceding
* the name. However, the null character
* is double counted between the name and the
* sizeof("bpf_prog_") above, so we omit
* the +1 here.
*/
sizeof(prog->aux->name) > KSYM_NAME_LEN);
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
/* prog->aux->name will be ignored if full btf name is available */
if (prog->aux->func_info_cnt) {
type = btf_type_by_id(prog->aux->btf,
prog->aux->func_info[prog->aux->func_idx].type_id);
func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
snprintf(sym, (size_t)(end - sym), "_%s", func_name);
return;
}
if (prog->aux->name[0])
snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
else
*sym = 0;
}
static unsigned long bpf_get_ksym_start(struct latch_tree_node *n)
{
return container_of(n, struct bpf_ksym, tnode)->start;
}
static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
struct latch_tree_node *b)
{
return bpf_get_ksym_start(a) < bpf_get_ksym_start(b);
}
static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
{
unsigned long val = (unsigned long)key;
const struct bpf_ksym *ksym;
ksym = container_of(n, struct bpf_ksym, tnode);
if (val < ksym->start)
return -1;
if (val >= ksym->end)
return 1;
return 0;
}
static const struct latch_tree_ops bpf_tree_ops = {
.less = bpf_tree_less,
.comp = bpf_tree_comp,
};
static DEFINE_SPINLOCK(bpf_lock);
static LIST_HEAD(bpf_kallsyms);
static struct latch_tree_root bpf_tree __cacheline_aligned;
void bpf_ksym_add(struct bpf_ksym *ksym)
{
spin_lock_bh(&bpf_lock);
WARN_ON_ONCE(!list_empty(&ksym->lnode));
list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms);
latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
spin_unlock_bh(&bpf_lock);
}
static void __bpf_ksym_del(struct bpf_ksym *ksym)
{
if (list_empty(&ksym->lnode))
return;
latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
list_del_rcu(&ksym->lnode);
}
void bpf_ksym_del(struct bpf_ksym *ksym)
{
spin_lock_bh(&bpf_lock);
__bpf_ksym_del(ksym);
spin_unlock_bh(&bpf_lock);
}
static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
{
return fp->jited && !bpf_prog_was_classic(fp);
}
static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
{
return list_empty(&fp->aux->ksym.lnode) ||
fp->aux->ksym.lnode.prev == LIST_POISON2;
}
void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp) ||
!bpf_capable())
return;
bpf_prog_ksym_set_addr(fp);
bpf_prog_ksym_set_name(fp);
fp->aux->ksym.prog = true;
bpf_ksym_add(&fp->aux->ksym);
}
void bpf_prog_kallsyms_del(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp))
return;
bpf_ksym_del(&fp->aux->ksym);
}
static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
{
struct latch_tree_node *n;
n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
return n ? container_of(n, struct bpf_ksym, tnode) : NULL;
}
const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
unsigned long *off, char *sym)
{
struct bpf_ksym *ksym;
char *ret = NULL;
rcu_read_lock();
ksym = bpf_ksym_find(addr);
if (ksym) {
unsigned long symbol_start = ksym->start;
unsigned long symbol_end = ksym->end;
strncpy(sym, ksym->name, KSYM_NAME_LEN);
ret = sym;
if (size)
*size = symbol_end - symbol_start;
if (off)
*off = addr - symbol_start;
}
rcu_read_unlock();
return ret;
}
bool is_bpf_text_address(unsigned long addr)
{
bool ret;
rcu_read_lock();
ret = bpf_ksym_find(addr) != NULL;
rcu_read_unlock();
return ret;
}
static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
{
struct bpf_ksym *ksym = bpf_ksym_find(addr);
return ksym && ksym->prog ?
container_of(ksym, struct bpf_prog_aux, ksym)->prog :
NULL;
}
const struct exception_table_entry *search_bpf_extables(unsigned long addr)
{
const struct exception_table_entry *e = NULL;
struct bpf_prog *prog;
rcu_read_lock();
prog = bpf_prog_ksym_find(addr);
if (!prog)
goto out;
if (!prog->aux->num_exentries)
goto out;
e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr);
out:
rcu_read_unlock();
return e;
}
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *sym)
{
struct bpf_ksym *ksym;
unsigned int it = 0;
int ret = -ERANGE;
if (!bpf_jit_kallsyms_enabled())
return ret;
rcu_read_lock();
list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) {
if (it++ != symnum)
continue;
strncpy(sym, ksym->name, KSYM_NAME_LEN);
*value = ksym->start;
*type = BPF_SYM_ELF_TYPE;
ret = 0;
break;
}
rcu_read_unlock();
return ret;
}
int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
struct bpf_jit_poke_descriptor *poke)
{
struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
static const u32 poke_tab_max = 1024;
u32 slot = prog->aux->size_poke_tab;
u32 size = slot + 1;
if (size > poke_tab_max)
return -ENOSPC;
if (poke->tailcall_target || poke->tailcall_target_stable ||
poke->tailcall_bypass || poke->adj_off || poke->bypass_addr)
return -EINVAL;
switch (poke->reason) {
case BPF_POKE_REASON_TAIL_CALL:
if (!poke->tail_call.map)
return -EINVAL;
break;
default:
return -EINVAL;
}
tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL);
if (!tab)
return -ENOMEM;
memcpy(&tab[slot], poke, sizeof(*poke));
prog->aux->size_poke_tab = size;
prog->aux->poke_tab = tab;
return slot;
}
/*
* BPF program pack allocator.
*
* Most BPF programs are pretty small. Allocating a hole page for each
* program is sometime a waste. Many small bpf program also adds pressure
* to instruction TLB. To solve this issue, we introduce a BPF program pack
* allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86)
* to host BPF programs.
*/
#define BPF_PROG_CHUNK_SHIFT 6
#define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT)
#define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1))
struct bpf_prog_pack {
struct list_head list;
void *ptr;
unsigned long bitmap[];
};
#define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE)
static size_t bpf_prog_pack_size = -1;
static size_t bpf_prog_pack_mask = -1;
static int bpf_prog_chunk_count(void)
{
WARN_ON_ONCE(bpf_prog_pack_size == -1);
return bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE;
}
static DEFINE_MUTEX(pack_mutex);
static LIST_HEAD(pack_list);
/* PMD_SIZE is not available in some special config, e.g. ARCH=arm with
* CONFIG_MMU=n. Use PAGE_SIZE in these cases.
*/
#ifdef PMD_SIZE
#define BPF_HPAGE_SIZE PMD_SIZE
#define BPF_HPAGE_MASK PMD_MASK
#else
#define BPF_HPAGE_SIZE PAGE_SIZE
#define BPF_HPAGE_MASK PAGE_MASK
#endif
static size_t select_bpf_prog_pack_size(void)
{
size_t size;
void *ptr;
size = BPF_HPAGE_SIZE * num_online_nodes();
ptr = module_alloc(size);
/* Test whether we can get huge pages. If not just use PAGE_SIZE
* packs.
*/
if (!ptr || !is_vm_area_hugepages(ptr)) {
size = PAGE_SIZE;
bpf_prog_pack_mask = PAGE_MASK;
} else {
bpf_prog_pack_mask = BPF_HPAGE_MASK;
}
vfree(ptr);
return size;
}
static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_prog_pack *pack;
pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(bpf_prog_chunk_count())),
GFP_KERNEL);
if (!pack)
return NULL;
pack->ptr = module_alloc(bpf_prog_pack_size);
if (!pack->ptr) {
kfree(pack);
return NULL;
}
bpf_fill_ill_insns(pack->ptr, bpf_prog_pack_size);
bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE);
list_add_tail(&pack->list, &pack_list);
set_vm_flush_reset_perms(pack->ptr);
set_memory_ro((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
set_memory_x((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
return pack;
}
static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size);
struct bpf_prog_pack *pack;
unsigned long pos;
void *ptr = NULL;
mutex_lock(&pack_mutex);
if (bpf_prog_pack_size == -1)
bpf_prog_pack_size = select_bpf_prog_pack_size();
if (size > bpf_prog_pack_size) {
size = round_up(size, PAGE_SIZE);
ptr = module_alloc(size);
if (ptr) {
bpf_fill_ill_insns(ptr, size);
set_vm_flush_reset_perms(ptr);
set_memory_ro((unsigned long)ptr, size / PAGE_SIZE);
set_memory_x((unsigned long)ptr, size / PAGE_SIZE);
}
goto out;
}
list_for_each_entry(pack, &pack_list, list) {
pos = bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
nbits, 0);
if (pos < bpf_prog_chunk_count())
goto found_free_area;
}
pack = alloc_new_pack(bpf_fill_ill_insns);
if (!pack)
goto out;
pos = 0;
found_free_area:
bitmap_set(pack->bitmap, pos, nbits);
ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT);
out:
mutex_unlock(&pack_mutex);
return ptr;
}
static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
{
struct bpf_prog_pack *pack = NULL, *tmp;
unsigned int nbits;
unsigned long pos;
void *pack_ptr;
mutex_lock(&pack_mutex);
if (hdr->size > bpf_prog_pack_size) {
module_memfree(hdr);
goto out;
}
pack_ptr = (void *)((unsigned long)hdr & bpf_prog_pack_mask);
list_for_each_entry(tmp, &pack_list, list) {
if (tmp->ptr == pack_ptr) {
pack = tmp;
break;
}
}
if (WARN_ONCE(!pack, "bpf_prog_pack bug\n"))
goto out;
nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT;
WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
"bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
bitmap_clear(pack->bitmap, pos, nbits);
if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
bpf_prog_chunk_count(), 0) == 0) {
list_del(&pack->list);
module_memfree(pack->ptr);
kfree(pack);
}
out:
mutex_unlock(&pack_mutex);
}
static atomic_long_t bpf_jit_current;
/* Can be overridden by an arch's JIT compiler if it has a custom,
* dedicated BPF backend memory area, or if neither of the two
* below apply.
*/
u64 __weak bpf_jit_alloc_exec_limit(void)
{
#if defined(MODULES_VADDR)
return MODULES_END - MODULES_VADDR;
#else
return VMALLOC_END - VMALLOC_START;
#endif
}
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
PAGE_SIZE), LONG_MAX);
return 0;
}
pure_initcall(bpf_jit_charge_init);
int bpf_jit_charge_modmem(u32 size)
{
if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) {
if (!bpf_capable()) {
atomic_long_sub(size, &bpf_jit_current);
return -EPERM;
}
}
return 0;
}
void bpf_jit_uncharge_modmem(u32 size)
{
atomic_long_sub(size, &bpf_jit_current);
}
void *__weak bpf_jit_alloc_exec(unsigned long size)
{
return module_alloc(size);
}
void __weak bpf_jit_free_exec(void *addr)
{
module_memfree(addr);
}
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *hdr;
u32 size, hole, start;
WARN_ON_ONCE(!is_power_of_2(alignment) ||
alignment > BPF_IMAGE_ALIGNMENT);
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
* random section of illegal instructions.
*/
size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
if (bpf_jit_charge_modmem(size))
return NULL;
hdr = bpf_jit_alloc_exec(size);
if (!hdr) {
bpf_jit_uncharge_modmem(size);
return NULL;
}
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
hdr->size = size;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
/* Leave a random number of instructions before BPF code. */
*image_ptr = &hdr->image[start];
return hdr;
}
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
u32 size = hdr->size;
bpf_jit_free_exec(hdr);
bpf_jit_uncharge_modmem(size);
}
/* Allocate jit binary from bpf_prog_pack allocator.
* Since the allocated memory is RO+X, the JIT engine cannot write directly
* to the memory. To solve this problem, a RW buffer is also allocated at
* as the same time. The JIT engine should calculate offsets based on the
* RO memory address, but write JITed program to the RW buffer. Once the
* JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies
* the JITed program to the RO memory.
*/
struct bpf_binary_header *
bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
struct bpf_binary_header **rw_header,
u8 **rw_image,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *ro_header;
u32 size, hole, start;
WARN_ON_ONCE(!is_power_of_2(alignment) ||
alignment > BPF_IMAGE_ALIGNMENT);
/* add 16 bytes for a random section of illegal instructions */
size = round_up(proglen + sizeof(*ro_header) + 16, BPF_PROG_CHUNK_SIZE);
if (bpf_jit_charge_modmem(size))
return NULL;
ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns);
if (!ro_header) {
bpf_jit_uncharge_modmem(size);
return NULL;
}
*rw_header = kvmalloc(size, GFP_KERNEL);
if (!*rw_header) {
bpf_arch_text_copy(&ro_header->size, &size, sizeof(size));
bpf_prog_pack_free(ro_header);
bpf_jit_uncharge_modmem(size);
return NULL;
}
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(*rw_header, size);
(*rw_header)->size = size;
hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)),
BPF_PROG_CHUNK_SIZE - sizeof(*ro_header));
start = (get_random_int() % hole) & ~(alignment - 1);
*image_ptr = &ro_header->image[start];
*rw_image = &(*rw_header)->image[start];
return ro_header;
}
/* Copy JITed text from rw_header to its final location, the ro_header. */
int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
struct bpf_binary_header *ro_header,
struct bpf_binary_header *rw_header)
{
void *ptr;
ptr = bpf_arch_text_copy(ro_header, rw_header, rw_header->size);
kvfree(rw_header);
if (IS_ERR(ptr)) {
bpf_prog_pack_free(ro_header);
return PTR_ERR(ptr);
}
prog->aux->use_bpf_prog_pack = true;
return 0;
}
/* bpf_jit_binary_pack_free is called in two different scenarios:
* 1) when the program is freed after;
* 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize).
* For case 2), we need to free both the RO memory and the RW buffer.
*
* bpf_jit_binary_pack_free requires proper ro_header->size. However,
* bpf_jit_binary_pack_alloc does not set it. Therefore, ro_header->size
* must be set with either bpf_jit_binary_pack_finalize (normal path) or
* bpf_arch_text_copy (when jit fails).
*/
void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
struct bpf_binary_header *rw_header)
{
u32 size = ro_header->size;
bpf_prog_pack_free(ro_header);
kvfree(rw_header);
bpf_jit_uncharge_modmem(size);
}
static inline struct bpf_binary_header *
bpf_jit_binary_hdr(const struct bpf_prog *fp)
{
unsigned long real_start = (unsigned long)fp->bpf_func;
unsigned long addr;
if (fp->aux->use_bpf_prog_pack)
addr = real_start & BPF_PROG_CHUNK_MASK;
else
addr = real_start & PAGE_MASK;
return (void *)addr;
}
/* This symbol is only overridden by archs that have different
* requirements than the usual eBPF JITs, f.e. when they only
* implement cBPF JIT, do not set images read-only, etc.
*/
void __weak bpf_jit_free(struct bpf_prog *fp)
{
if (fp->jited) {
struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
if (fp->aux->use_bpf_prog_pack)
bpf_jit_binary_pack_free(hdr, NULL /* rw_buffer */);
else
bpf_jit_binary_free(hdr);
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
}
bpf_prog_unlock_free(fp);
}
int bpf_jit_get_func_addr(const struct bpf_prog *prog,
const struct bpf_insn *insn, bool extra_pass,
u64 *func_addr, bool *func_addr_fixed)
{
s16 off = insn->off;
s32 imm = insn->imm;
u8 *addr;
*func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
if (!*func_addr_fixed) {
/* Place-holder address till the last pass has collected
* all addresses for JITed subprograms in which case we
* can pick them up from prog->aux.
*/
if (!extra_pass)
addr = NULL;
else if (prog->aux->func &&
off >= 0 && off < prog->aux->func_cnt)
addr = (u8 *)prog->aux->func[off]->bpf_func;
else
return -EINVAL;
} else {
/* Address of a BPF helper call. Since part of the core
* kernel, it's always at a fixed location. __bpf_call_base
* and the helper with imm relative to it are both in core
* kernel.
*/
addr = (u8 *)__bpf_call_base + imm;
}
*func_addr = (unsigned long)addr;
return 0;
}
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
struct bpf_insn *to_buff,
bool emit_zext)
{
struct bpf_insn *to = to_buff;
u32 imm_rnd = get_random_int();
s16 off;
BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG);
BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);
/* Constraints on AX register:
*
* AX register is inaccessible from user space. It is mapped in
* all JITs, and used here for constant blinding rewrites. It is
* typically "stateless" meaning its contents are only valid within
* the executed instruction, but not across several instructions.
* There are a few exceptions however which are further detailed
* below.
*
* Constant blinding is only used by JITs, not in the interpreter.
* The interpreter uses AX in some occasions as a local temporary
* register e.g. in DIV or MOD instructions.
*
* In restricted circumstances, the verifier can also use the AX
* register for rewrites as long as they do not interfere with
* the above cases!
*/
if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX)
goto out;
if (from->imm == 0 &&
(from->code == (BPF_ALU | BPF_MOV | BPF_K) ||
from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
*to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg);
goto out;
}
switch (from->code) {
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_MOV | BPF_K:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU | BPF_MOD | BPF_K:
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
break;
case BPF_ALU64 | BPF_ADD | BPF_K:
case BPF_ALU64 | BPF_SUB | BPF_K:
case BPF_ALU64 | BPF_AND | BPF_K:
case BPF_ALU64 | BPF_OR | BPF_K:
case BPF_ALU64 | BPF_XOR | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MOV | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_K:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JNE | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JLE | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_K:
case BPF_JMP | BPF_JSET | BPF_K:
/* Accommodate for extra offset in case of a backjump. */
off = from->off;
if (off < 0)
off -= 2;
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
break;
case BPF_JMP32 | BPF_JEQ | BPF_K:
case BPF_JMP32 | BPF_JNE | BPF_K:
case BPF_JMP32 | BPF_JGT | BPF_K:
case BPF_JMP32 | BPF_JLT | BPF_K:
case BPF_JMP32 | BPF_JGE | BPF_K:
case BPF_JMP32 | BPF_JLE | BPF_K:
case BPF_JMP32 | BPF_JSGT | BPF_K:
case BPF_JMP32 | BPF_JSLT | BPF_K:
case BPF_JMP32 | BPF_JSGE | BPF_K:
case BPF_JMP32 | BPF_JSLE | BPF_K:
case BPF_JMP32 | BPF_JSET | BPF_K:
/* Accommodate for extra offset in case of a backjump. */
off = from->off;
if (off < 0)
off -= 2;
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX,
off);
break;
case BPF_LD | BPF_IMM | BPF_DW:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
*to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX);
break;
case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
if (emit_zext)
*to++ = BPF_ZEXT_REG(BPF_REG_AX);
*to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX);
break;
case BPF_ST | BPF_MEM | BPF_DW:
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
}
out:
return to - to_buff;
}
static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags);
if (fp != NULL) {
/* aux->prog still points to the fp_other one, so
* when promoting the clone to the real program,
* this still needs to be adapted.
*/
memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE);
}
return fp;
}
static void bpf_prog_clone_free(struct bpf_prog *fp)
{
/* aux was stolen by the other clone, so we cannot free
* it from this path! It will be freed eventually by the
* other program on release.
*
* At this point, we don't need a deferred release since
* clone is guaranteed to not be locked.
*/
fp->aux = NULL;
fp->stats = NULL;
fp->active = NULL;
__bpf_prog_free(fp);
}
void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
{
/* We have to repoint aux->prog to self, as we don't
* know whether fp here is the clone or the original.
*/
fp->aux->prog = fp;
bpf_prog_clone_free(fp_other);
}
struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
{
struct bpf_insn insn_buff[16], aux[2];
struct bpf_prog *clone, *tmp;
int insn_delta, insn_cnt;
struct bpf_insn *insn;
int i, rewritten;
if (!prog->blinding_requested || prog->blinded)
return prog;
clone = bpf_prog_clone_create(prog, GFP_USER);
if (!clone)
return ERR_PTR(-ENOMEM);
insn_cnt = clone->len;
insn = clone->insnsi;
for (i = 0; i < insn_cnt; i++, insn++) {
if (bpf_pseudo_func(insn)) {
/* ld_imm64 with an address of bpf subprog is not
* a user controlled constant. Don't randomize it,
* since it will conflict with jit_subprogs() logic.
*/
insn++;
i++;
continue;
}
/* We temporarily need to hold the original ld64 insn
* so that we can still access the first part in the
* second blinding run.
*/
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) &&
insn[1].code == 0)
memcpy(aux, insn, sizeof(aux));
rewritten = bpf_jit_blind_insn(insn, aux, insn_buff,
clone->aux->verifier_zext);
if (!rewritten)
continue;
tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
if (IS_ERR(tmp)) {
/* Patching may have repointed aux->prog during
* realloc from the original one, so we need to
* fix it up here on error.
*/
bpf_jit_prog_release_other(prog, clone);
return tmp;
}
clone = tmp;
insn_delta = rewritten - 1;
/* Walk new program and skip insns we just inserted. */
insn = clone->insnsi + i + insn_delta;
insn_cnt += insn_delta;
i += insn_delta;
}
clone->blinded = 1;
return clone;
}
#endif /* CONFIG_BPF_JIT */
/* Base function for offset calculation. Needs to go into .text section,
* therefore keeping it non-static as well; will also be used by JITs
* anyway later on, so do not let the compiler omit it. This also needs
* to go into kallsyms for correlation from e.g. bpftool, so naming
* must not change.
*/
noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return 0;
}
EXPORT_SYMBOL_GPL(__bpf_call_base);
/* All UAPI available opcodes. */
#define BPF_INSN_MAP(INSN_2, INSN_3) \
/* 32 bit ALU operations. */ \
/* Register based. */ \
INSN_3(ALU, ADD, X), \
INSN_3(ALU, SUB, X), \
INSN_3(ALU, AND, X), \
INSN_3(ALU, OR, X), \
INSN_3(ALU, LSH, X), \
INSN_3(ALU, RSH, X), \
INSN_3(ALU, XOR, X), \
INSN_3(ALU, MUL, X), \
INSN_3(ALU, MOV, X), \
INSN_3(ALU, ARSH, X), \
INSN_3(ALU, DIV, X), \
INSN_3(ALU, MOD, X), \
INSN_2(ALU, NEG), \
INSN_3(ALU, END, TO_BE), \
INSN_3(ALU, END, TO_LE), \
/* Immediate based. */ \
INSN_3(ALU, ADD, K), \
INSN_3(ALU, SUB, K), \
INSN_3(ALU, AND, K), \
INSN_3(ALU, OR, K), \
INSN_3(ALU, LSH, K), \
INSN_3(ALU, RSH, K), \
INSN_3(ALU, XOR, K), \
INSN_3(ALU, MUL, K), \
INSN_3(ALU, MOV, K), \
INSN_3(ALU, ARSH, K), \
INSN_3(ALU, DIV, K), \
INSN_3(ALU, MOD, K), \
/* 64 bit ALU operations. */ \
/* Register based. */ \
INSN_3(ALU64, ADD, X), \
INSN_3(ALU64, SUB, X), \
INSN_3(ALU64, AND, X), \
INSN_3(ALU64, OR, X), \
INSN_3(ALU64, LSH, X), \
INSN_3(ALU64, RSH, X), \
INSN_3(ALU64, XOR, X), \
INSN_3(ALU64, MUL, X), \
INSN_3(ALU64, MOV, X), \
INSN_3(ALU64, ARSH, X), \
INSN_3(ALU64, DIV, X), \
INSN_3(ALU64, MOD, X), \
INSN_2(ALU64, NEG), \
/* Immediate based. */ \
INSN_3(ALU64, ADD, K), \
INSN_3(ALU64, SUB, K), \
INSN_3(ALU64, AND, K), \
INSN_3(ALU64, OR, K), \
INSN_3(ALU64, LSH, K), \
INSN_3(ALU64, RSH, K), \
INSN_3(ALU64, XOR, K), \
INSN_3(ALU64, MUL, K), \
INSN_3(ALU64, MOV, K), \
INSN_3(ALU64, ARSH, K), \
INSN_3(ALU64, DIV, K), \
INSN_3(ALU64, MOD, K), \
/* Call instruction. */ \
INSN_2(JMP, CALL), \
/* Exit instruction. */ \
INSN_2(JMP, EXIT), \
/* 32-bit Jump instructions. */ \
/* Register based. */ \
INSN_3(JMP32, JEQ, X), \
INSN_3(JMP32, JNE, X), \
INSN_3(JMP32, JGT, X), \
INSN_3(JMP32, JLT, X), \
INSN_3(JMP32, JGE, X), \
INSN_3(JMP32, JLE, X), \
INSN_3(JMP32, JSGT, X), \
INSN_3(JMP32, JSLT, X), \
INSN_3(JMP32, JSGE, X), \
INSN_3(JMP32, JSLE, X), \
INSN_3(JMP32, JSET, X), \
/* Immediate based. */ \
INSN_3(JMP32, JEQ, K), \
INSN_3(JMP32, JNE, K), \
INSN_3(JMP32, JGT, K), \
INSN_3(JMP32, JLT, K), \
INSN_3(JMP32, JGE, K), \
INSN_3(JMP32, JLE, K), \
INSN_3(JMP32, JSGT, K), \
INSN_3(JMP32, JSLT, K), \
INSN_3(JMP32, JSGE, K), \
INSN_3(JMP32, JSLE, K), \
INSN_3(JMP32, JSET, K), \
/* Jump instructions. */ \
/* Register based. */ \
INSN_3(JMP, JEQ, X), \
INSN_3(JMP, JNE, X), \
INSN_3(JMP, JGT, X), \
INSN_3(JMP, JLT, X), \
INSN_3(JMP, JGE, X), \
INSN_3(JMP, JLE, X), \
INSN_3(JMP, JSGT, X), \
INSN_3(JMP, JSLT, X), \
INSN_3(JMP, JSGE, X), \
INSN_3(JMP, JSLE, X), \
INSN_3(JMP, JSET, X), \
/* Immediate based. */ \
INSN_3(JMP, JEQ, K), \
INSN_3(JMP, JNE, K), \
INSN_3(JMP, JGT, K), \
INSN_3(JMP, JLT, K), \
INSN_3(JMP, JGE, K), \
INSN_3(JMP, JLE, K), \
INSN_3(JMP, JSGT, K), \
INSN_3(JMP, JSLT, K), \
INSN_3(JMP, JSGE, K), \
INSN_3(JMP, JSLE, K), \
INSN_3(JMP, JSET, K), \
INSN_2(JMP, JA), \
/* Store instructions. */ \
/* Register based. */ \
INSN_3(STX, MEM, B), \
INSN_3(STX, MEM, H), \
INSN_3(STX, MEM, W), \
INSN_3(STX, MEM, DW), \
INSN_3(STX, ATOMIC, W), \
INSN_3(STX, ATOMIC, DW), \
/* Immediate based. */ \
INSN_3(ST, MEM, B), \
INSN_3(ST, MEM, H), \
INSN_3(ST, MEM, W), \
INSN_3(ST, MEM, DW), \
/* Load instructions. */ \
/* Register based. */ \
INSN_3(LDX, MEM, B), \
INSN_3(LDX, MEM, H), \
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
/* Immediate based. */ \
INSN_3(LD, IMM, DW)
bool bpf_opcode_in_insntable(u8 code)
{
#define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true
#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
static const bool public_insntable[256] = {
[0 ... 255] = false,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
/* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
[BPF_LD | BPF_ABS | BPF_B] = true,
[BPF_LD | BPF_ABS | BPF_H] = true,
[BPF_LD | BPF_ABS | BPF_W] = true,
[BPF_LD | BPF_IND | BPF_B] = true,
[BPF_LD | BPF_IND | BPF_H] = true,
[BPF_LD | BPF_IND | BPF_W] = true,
};
#undef BPF_INSN_3_TBL
#undef BPF_INSN_2_TBL
return public_insntable[code];
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
{
memset(dst, 0, size);
return -EFAULT;
}
/**
* ___bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
* @insn: is the array of eBPF instructions
*
* Decode and execute eBPF instructions.
*
* Return: whatever value is in %BPF_R0 at program exit
*/
static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
{
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
static const void * const jumptable[256] __annotate_jump_table = {
[0 ... 255] = &&default_label,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
[BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
u32 tail_call_cnt = 0;
#define CONT ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })
select_insn:
goto *jumptable[insn->code];
/* Explicitly mask the register-based shift amounts with 63 or 31
* to avoid undefined behavior. Normally this won't affect the
* generated code, for example, in case of native 64 bit archs such
* as x86-64 or arm64, the compiler is optimizing the AND away for
* the interpreter. In case of JITs, each of the JIT backends compiles
* the BPF shift operations to machine instructions which produce
* implementation-defined results in such a case; the resulting
* contents of the register may be arbitrary, but program behaviour
* as a whole remains defined. In other words, in case of JIT backends,
* the AND must /not/ be added to the emitted LSH/RSH/ARSH translation.
*/
/* ALU (shifts) */
#define SHT(OPCODE, OP) \
ALU64_##OPCODE##_X: \
DST = DST OP (SRC & 63); \
CONT; \
ALU_##OPCODE##_X: \
DST = (u32) DST OP ((u32) SRC & 31); \
CONT; \
ALU64_##OPCODE##_K: \
DST = DST OP IMM; \
CONT; \
ALU_##OPCODE##_K: \
DST = (u32) DST OP (u32) IMM; \
CONT;
/* ALU (rest) */
#define ALU(OPCODE, OP) \
ALU64_##OPCODE##_X: \
DST = DST OP SRC; \
CONT; \
ALU_##OPCODE##_X: \
DST = (u32) DST OP (u32) SRC; \
CONT; \
ALU64_##OPCODE##_K: \
DST = DST OP IMM; \
CONT; \
ALU_##OPCODE##_K: \
DST = (u32) DST OP (u32) IMM; \
CONT;
ALU(ADD, +)
ALU(SUB, -)
ALU(AND, &)
ALU(OR, |)
ALU(XOR, ^)
ALU(MUL, *)
SHT(LSH, <<)
SHT(RSH, >>)
#undef SHT
#undef ALU
ALU_NEG:
DST = (u32) -DST;
CONT;
ALU64_NEG:
DST = -DST;
CONT;
ALU_MOV_X:
DST = (u32) SRC;
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
DST = SRC;
CONT;
ALU64_MOV_K:
DST = IMM;
CONT;
LD_IMM_DW:
DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
insn++;
CONT;
ALU_ARSH_X:
DST = (u64) (u32) (((s32) DST) >> (SRC & 31));
CONT;
ALU_ARSH_K:
DST = (u64) (u32) (((s32) DST) >> IMM);
CONT;
ALU64_ARSH_X:
(*(s64 *) &DST) >>= (SRC & 63);
CONT;
ALU64_ARSH_K:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
div64_u64_rem(DST, SRC, &AX);
DST = AX;
CONT;
ALU_MOD_X:
AX = (u32) DST;
DST = do_div(AX, (u32) SRC);
CONT;
ALU64_MOD_K:
div64_u64_rem(DST, IMM, &AX);
DST = AX;
CONT;
ALU_MOD_K:
AX = (u32) DST;
DST = do_div(AX, (u32) IMM);
CONT;
ALU64_DIV_X:
DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
AX = (u32) DST;
do_div(AX, (u32) SRC);
DST = (u32) AX;
CONT;
ALU64_DIV_K:
DST = div64_u64(DST, IMM);
CONT;
ALU_DIV_K:
AX = (u32) DST;
do_div(AX, (u32) IMM);
DST = (u32) AX;
CONT;
ALU_END_TO_BE:
switch (IMM) {
case 16:
DST = (__force u16) cpu_to_be16(DST);
break;
case 32:
DST = (__force u32) cpu_to_be32(DST);
break;
case 64:
DST = (__force u64) cpu_to_be64(DST);
break;
}
CONT;
ALU_END_TO_LE:
switch (IMM) {
case 16:
DST = (__force u16) cpu_to_le16(DST);
break;
case 32:
DST = (__force u32) cpu_to_le32(DST);
break;
case 64:
DST = (__force u64) cpu_to_le64(DST);
break;
}
CONT;
/* CALL */
JMP_CALL:
/* Function call scratches BPF_R1-BPF_R5 registers,
* preserves BPF_R6-BPF_R9, and stores return value
* into BPF_R0.
*/
BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
BPF_R4, BPF_R5);
CONT;
JMP_CALL_ARGS:
BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
BPF_R3, BPF_R4,
BPF_R5,
insn + insn->off + 1);
CONT;
JMP_TAIL_CALL: {
struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog;
u32 index = BPF_R3;
if (unlikely(index >= array->map.max_entries))
goto out;
if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT))
goto out;
tail_call_cnt++;
prog = READ_ONCE(array->ptrs[index]);
if (!prog)
goto out;
/* ARG1 at this point is guaranteed to point to CTX from
* the verifier side due to the fact that the tail call is
* handled like a helper, that is, bpf_tail_call_proto,
* where arg1_type is ARG_PTR_TO_CTX.
*/
insn = prog->insnsi;
goto select_insn;
out:
CONT;
}
JMP_JA:
insn += insn->off;
CONT;
JMP_EXIT:
return BPF_R0;
/* JMP */
#define COND_JMP(SIGN, OPCODE, CMP_OP) \
JMP_##OPCODE##_X: \
if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \
insn += insn->off; \
CONT_JMP; \
} \
CONT; \
JMP32_##OPCODE##_X: \
if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \
insn += insn->off; \
CONT_JMP; \
} \
CONT; \
JMP_##OPCODE##_K: \
if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \
insn += insn->off; \
CONT_JMP; \
} \
CONT; \
JMP32_##OPCODE##_K: \
if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \
insn += insn->off; \
CONT_JMP; \
} \
CONT;
COND_JMP(u, JEQ, ==)
COND_JMP(u, JNE, !=)
COND_JMP(u, JGT, >)
COND_JMP(u, JLT, <)
COND_JMP(u, JGE, >=)
COND_JMP(u, JLE, <=)
COND_JMP(u, JSET, &)
COND_JMP(s, JSGT, >)
COND_JMP(s, JSLT, <)
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
/* ST, STX and LDX*/
ST_NOSPEC:
/* Speculation barrier for mitigating Speculative Store Bypass.
* In case of arm64, we rely on the firmware mitigation as
* controlled via the ssbd kernel parameter. Whenever the
* mitigation is enabled, it works for all of the kernel code
* with no need to provide any additional instructions here.
* In case of x86, we use 'lfence' insn for mitigation. We
* reuse preexisting logic from Spectre v1 mitigation that
* happens to produce the required code on x86 for v4 as well.
*/
#ifdef CONFIG_X86
barrier_nospec();
#endif
CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
CONT; \
ST_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = IMM; \
CONT; \
LDX_MEM_##SIZEOP: \
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT; \
LDX_PROBE_MEM_##SIZEOP: \
bpf_probe_read_kernel(&DST, sizeof(SIZE), \
(const void *)(long) (SRC + insn->off)); \
DST = *((SIZE *)&DST); \
CONT;
LDST(B, u8)
LDST(H, u16)
LDST(W, u32)
LDST(DW, u64)
#undef LDST
#define ATOMIC_ALU_OP(BOP, KOP) \
case BOP: \
if (BPF_SIZE(insn->code) == BPF_W) \
atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \
(DST + insn->off)); \
else \
atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \
(DST + insn->off)); \
break; \
case BOP | BPF_FETCH: \
if (BPF_SIZE(insn->code) == BPF_W) \
SRC = (u32) atomic_fetch_##KOP( \
(u32) SRC, \
(atomic_t *)(unsigned long) (DST + insn->off)); \
else \
SRC = (u64) atomic64_fetch_##KOP( \
(u64) SRC, \
(atomic64_t *)(unsigned long) (DST + insn->off)); \
break;
STX_ATOMIC_DW:
STX_ATOMIC_W:
switch (IMM) {
ATOMIC_ALU_OP(BPF_ADD, add)
ATOMIC_ALU_OP(BPF_AND, and)
ATOMIC_ALU_OP(BPF_OR, or)
ATOMIC_ALU_OP(BPF_XOR, xor)
#undef ATOMIC_ALU_OP
case BPF_XCHG:
if (BPF_SIZE(insn->code) == BPF_W)
SRC = (u32) atomic_xchg(
(atomic_t *)(unsigned long) (DST + insn->off),
(u32) SRC);
else
SRC = (u64) atomic64_xchg(
(atomic64_t *)(unsigned long) (DST + insn->off),
(u64) SRC);
break;
case BPF_CMPXCHG:
if (BPF_SIZE(insn->code) == BPF_W)
BPF_R0 = (u32) atomic_cmpxchg(
(atomic_t *)(unsigned long) (DST + insn->off),
(u32) BPF_R0, (u32) SRC);
else
BPF_R0 = (u64) atomic64_cmpxchg(
(atomic64_t *)(unsigned long) (DST + insn->off),
(u64) BPF_R0, (u64) SRC);
break;
default:
goto default_label;
}
CONT;
default_label:
/* If we ever reach this, we have a bug somewhere. Die hard here
* instead of just returning 0; we could be somewhere in a subprog,
* so execution could continue otherwise which we do /not/ want.
*
* Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
*/
pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n",
insn->code, insn->imm);
BUG_ON(1);
return 0;
}
#define PROG_NAME(stack_size) __bpf_prog_run##stack_size
#define DEFINE_BPF_PROG_RUN(stack_size) \
static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
{ \
u64 stack[stack_size / sizeof(u64)]; \
u64 regs[MAX_BPF_EXT_REG]; \
\
FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
ARG1 = (u64) (unsigned long) ctx; \
return ___bpf_prog_run(regs, insn); \
}
#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
#define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \
static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
const struct bpf_insn *insn) \
{ \
u64 stack[stack_size / sizeof(u64)]; \
u64 regs[MAX_BPF_EXT_REG]; \
\
FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
BPF_R1 = r1; \
BPF_R2 = r2; \
BPF_R3 = r3; \
BPF_R4 = r4; \
BPF_R5 = r5; \
return ___bpf_prog_run(regs, insn); \
}
#define EVAL1(FN, X) FN(X)
#define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y)
#define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y)
#define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y)
#define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y)
#define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y)
EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192);
EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384);
EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512);
EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192);
EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384);
EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);
#define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),
static unsigned int (*interpreters[])(const void *ctx,
const struct bpf_insn *insn) = {
EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
};
#undef PROG_NAME_LIST
#define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size),
static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
const struct bpf_insn *insn) = {
EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
};
#undef PROG_NAME_LIST
void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
{
stack_depth = max_t(u32, stack_depth, 1);
insn->off = (s16) insn->imm;
insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
__bpf_call_base_args;
insn->code = BPF_JMP | BPF_CALL_ARGS;
}
#else
static unsigned int __bpf_prog_ret0_warn(const void *ctx,
const struct bpf_insn *insn)
{
/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
* is not working properly, so warn about it!
*/
WARN_ON_ONCE(1);
return 0;
}
#endif
bool bpf_prog_map_compatible(struct bpf_map *map,
const struct bpf_prog *fp)
{
bool ret;
if (fp->kprobe_override)
return false;
spin_lock(&map->owner.lock);
if (!map->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
map->owner.type = fp->type;
map->owner.jited = fp->jited;
map->owner.xdp_has_frags = fp->aux->xdp_has_frags;
ret = true;
} else {
ret = map->owner.type == fp->type &&
map->owner.jited == fp->jited &&
map->owner.xdp_has_frags == fp->aux->xdp_has_frags;
}
spin_unlock(&map->owner.lock);
return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
int i, ret = 0;
mutex_lock(&aux->used_maps_mutex);
for (i = 0; i < aux->used_map_cnt; i++) {
struct bpf_map *map = aux->used_maps[i];
if (!map_type_contains_progs(map))
continue;
if (!bpf_prog_map_compatible(map, fp)) {
ret = -EINVAL;
goto out;
}
}
out:
mutex_unlock(&aux->used_maps_mutex);
return ret;
}
static void bpf_prog_select_func(struct bpf_prog *fp)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
#else
fp->bpf_func = __bpf_prog_ret0_warn;
#endif
}
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with BPF program
* @err: pointer to error variable
*
* Try to JIT eBPF program, if JIT is not available, use interpreter.
* The BPF program will be executed via bpf_prog_run() function.
*
* Return: the &fp argument along with &err set to 0 for success or
* a negative errno code on failure
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
/* In case of BPF to BPF calls, verifier did all the prep
* work with regards to JITing, etc.
*/
bool jit_needed = false;
if (fp->bpf_func)
goto finalize;
if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) ||
bpf_prog_has_kfunc_call(fp))
jit_needed = true;
bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
* blinding, bpf_int_jit_compile() must always return a
* valid program, which in this case would simply not
* be JITed, but falls back to the interpreter.
*/
if (!bpf_prog_is_dev_bound(fp->aux)) {
*err = bpf_prog_alloc_jited_linfo(fp);
if (*err)
return fp;
fp = bpf_int_jit_compile(fp);
bpf_prog_jit_attempt_done(fp);
if (!fp->jited && jit_needed) {
*err = -ENOTSUPP;
return fp;
}
} else {
*err = bpf_prog_offload_compile(fp);
if (*err)
return fp;
}
finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
* this late stage as we need to determine, if we deal
* with JITed or non JITed program concatenations and not
* all eBPF JITs might immediately support all features.
*/
*err = bpf_check_tail_call(fp);
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
static unsigned int __bpf_prog_ret1(const void *ctx,
const struct bpf_insn *insn)
{
return 1;
}
static struct bpf_prog_dummy {
struct bpf_prog prog;
} dummy_bpf_prog = {
.prog = {
.bpf_func = __bpf_prog_ret1,
},
};
struct bpf_empty_prog_array bpf_empty_prog_array = {
.null_prog = NULL,
};
EXPORT_SYMBOL(bpf_empty_prog_array);
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
{
if (prog_cnt)
return kzalloc(sizeof(struct bpf_prog_array) +
sizeof(struct bpf_prog_array_item) *
(prog_cnt + 1),
flags);
return &bpf_empty_prog_array.hdr;
}
void bpf_prog_array_free(struct bpf_prog_array *progs)
{
if (!progs || progs == &bpf_empty_prog_array.hdr)
return;
kfree_rcu(progs, rcu);
}
static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu)
{
struct bpf_prog_array *progs;
progs = container_of(rcu, struct bpf_prog_array, rcu);
kfree_rcu(progs, rcu);
}
void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs)
{
if (!progs || progs == &bpf_empty_prog_array.hdr)
return;
call_rcu_tasks_trace(&progs->rcu, __bpf_prog_array_free_sleepable_cb);
}
int bpf_prog_array_length(struct bpf_prog_array *array)
{
struct bpf_prog_array_item *item;
u32 cnt = 0;
for (item = array->items; item->prog; item++)
if (item->prog != &dummy_bpf_prog.prog)
cnt++;
return cnt;
}
bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
{
struct bpf_prog_array_item *item;
for (item = array->items; item->prog; item++)
if (item->prog != &dummy_bpf_prog.prog)
return false;
return true;
}
static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
u32 *prog_ids,
u32 request_cnt)
{
struct bpf_prog_array_item *item;
int i = 0;
for (item = array->items; item->prog; item++) {
if (item->prog == &dummy_bpf_prog.prog)
continue;
prog_ids[i] = item->prog->aux->id;
if (++i == request_cnt) {
item++;
break;
}
}
return !!(item->prog);
}
int bpf_prog_array_copy_to_user(struct bpf_prog_array *array,
__u32 __user *prog_ids, u32 cnt)
{
unsigned long err = 0;
bool nospc;
u32 *ids;
/* users of this function are doing:
* cnt = bpf_prog_array_length();
* if (cnt > 0)
* bpf_prog_array_copy_to_user(..., cnt);
* so below kcalloc doesn't need extra cnt > 0 check.
*/
ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
if (!ids)
return -ENOMEM;
nospc = bpf_prog_array_copy_core(array, ids, cnt);
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
if (err)
return -EFAULT;
if (nospc)
return -ENOSPC;
return 0;
}
void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
struct bpf_prog *old_prog)
{
struct bpf_prog_array_item *item;
for (item = array->items; item->prog; item++)
if (item->prog == old_prog) {
WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
break;
}
}
/**
* bpf_prog_array_delete_safe_at() - Replaces the program at the given
* index into the program array with
* a dummy no-op program.
* @array: a bpf_prog_array
* @index: the index of the program to replace
*
* Skips over dummy programs, by not counting them, when calculating
* the position of the program to replace.
*
* Return:
* * 0 - Success
* * -EINVAL - Invalid index value. Must be a non-negative integer.
* * -ENOENT - Index out of range
*/
int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index)
{
return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog);
}
/**
* bpf_prog_array_update_at() - Updates the program at the given index
* into the program array.
* @array: a bpf_prog_array
* @index: the index of the program to update
* @prog: the program to insert into the array
*
* Skips over dummy programs, by not counting them, when calculating
* the position of the program to update.
*
* Return:
* * 0 - Success
* * -EINVAL - Invalid index value. Must be a non-negative integer.
* * -ENOENT - Index out of range
*/
int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
struct bpf_prog *prog)
{
struct bpf_prog_array_item *item;
if (unlikely(index < 0))
return -EINVAL;
for (item = array->items; item->prog; item++) {
if (item->prog == &dummy_bpf_prog.prog)
continue;
if (!index) {
WRITE_ONCE(item->prog, prog);
return 0;
}
index--;
}
return -ENOENT;
}
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)
{
int new_prog_cnt, carry_prog_cnt = 0;
struct bpf_prog_array_item *existing, *new;
struct bpf_prog_array *array;
bool found_exclude = false;
/* Figure out how many existing progs we need to carry over to
* the new array.
*/
if (old_array) {
existing = old_array->items;
for (; existing->prog; existing++) {
if (existing->prog == exclude_prog) {
found_exclude = true;
continue;
}
if (existing->prog != &dummy_bpf_prog.prog)
carry_prog_cnt++;
if (existing->prog == include_prog)
return -EEXIST;
}
}
if (exclude_prog && !found_exclude)
return -ENOENT;
/* How many progs (not NULL) will be in the new array? */
new_prog_cnt = carry_prog_cnt;
if (include_prog)
new_prog_cnt += 1;
/* Do we have any prog (not NULL) in the new array? */
if (!new_prog_cnt) {
*new_array = NULL;
return 0;
}
/* +1 as the end of prog_array is marked with NULL */
array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
if (!array)
return -ENOMEM;
new = array->items;
/* Fill in the new prog array */
if (carry_prog_cnt) {
existing = old_array->items;
for (; existing->prog; existing++) {
if (existing->prog == exclude_prog ||
existing->prog == &dummy_bpf_prog.prog)
continue;
new->prog = existing->prog;
new->bpf_cookie = existing->bpf_cookie;
new++;
}
}
if (include_prog) {
new->prog = include_prog;
new->bpf_cookie = bpf_cookie;
new++;
}
new->prog = NULL;
*new_array = array;
return 0;
}
int bpf_prog_array_copy_info(struct bpf_prog_array *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
u32 cnt = 0;
if (array)
cnt = bpf_prog_array_length(array);
*prog_cnt = cnt;
/* return early if user requested only program count or nothing to copy */
if (!request_cnt || !cnt)
return 0;
/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
: 0;
}
void __bpf_free_used_maps(struct bpf_prog_aux *aux,
struct bpf_map **used_maps, u32 len)
{
struct bpf_map *map;
u32 i;
for (i = 0; i < len; i++) {
map = used_maps[i];
if (map->ops->map_poke_untrack)
map->ops->map_poke_untrack(map, aux);
bpf_map_put(map);
}
}
static void bpf_free_used_maps(struct bpf_prog_aux *aux)
{
__bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt);
kfree(aux->used_maps);
}
void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
struct btf_mod_pair *used_btfs, u32 len)
{
#ifdef CONFIG_BPF_SYSCALL
struct btf_mod_pair *btf_mod;
u32 i;
for (i = 0; i < len; i++) {
btf_mod = &used_btfs[i];
if (btf_mod->module)
module_put(btf_mod->module);
btf_put(btf_mod->btf);
}
#endif
}
static void bpf_free_used_btfs(struct bpf_prog_aux *aux)
{
__bpf_free_used_btfs(aux, aux->used_btfs, aux->used_btf_cnt);
kfree(aux->used_btfs);
}
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
int i;
aux = container_of(work, struct bpf_prog_aux, work);
#ifdef CONFIG_BPF_SYSCALL
bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab);
#endif
bpf_free_used_maps(aux);
bpf_free_used_btfs(aux);
if (bpf_prog_is_dev_bound(aux))
bpf_prog_offload_destroy(aux->prog);
#ifdef CONFIG_PERF_EVENTS
if (aux->prog->has_callchain_buf)
put_callchain_buffers();
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
for (i = 0; i < aux->func_cnt; i++) {
/* We can just unlink the subprog poke descriptor table as
* it was originally linked to the main program and is also
* released along with it.
*/
aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
}
if (aux->func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
} else {
bpf_jit_free(aux->prog);
}
}
void bpf_prog_free(struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
if (aux->dst_prog)
bpf_prog_put(aux->dst_prog);
INIT_WORK(&aux->work, bpf_prog_free_deferred);
schedule_work(&aux->work);
}
EXPORT_SYMBOL_GPL(bpf_prog_free);
/* RNG for unpriviledged user space with separated state from prandom_u32(). */
static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state);
void bpf_user_rnd_init_once(void)
{
prandom_init_once(&bpf_user_rnd_state);
}
BPF_CALL_0(bpf_user_rnd_u32)
{
/* Should someone ever have the rather unwise idea to use some
* of the registers passed into this function, then note that
* this function is called from native eBPF and classic-to-eBPF
* transformations. Register assignments from both sides are
* different, f.e. classic always sets fn(ctx, A, X) here.
*/
struct rnd_state *state;
u32 res;
state = &get_cpu_var(bpf_user_rnd_state);
res = prandom_u32_state(state);
put_cpu_var(bpf_user_rnd_state);
return res;
}
BPF_CALL_0(bpf_get_raw_cpu_id)
{
return raw_smp_processor_id();
}
/* Weak definitions of helper functions in case we don't have bpf syscall. */
const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
const struct bpf_func_proto bpf_map_update_elem_proto __weak;
const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
const struct bpf_func_proto bpf_map_push_elem_proto __weak;
const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak;
const struct bpf_func_proto bpf_spin_lock_proto __weak;
const struct bpf_func_proto bpf_spin_unlock_proto __weak;
const struct bpf_func_proto bpf_jiffies64_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak;
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
const struct bpf_func_proto bpf_get_local_storage_proto __weak;
const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
return NULL;
}
const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
{
return NULL;
}
u64 __weak
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)
{
return -ENOTSUPP;
}
EXPORT_SYMBOL_GPL(bpf_event_output);
/* Always built-in helper functions. */
const struct bpf_func_proto bpf_tail_call_proto = {
.func = NULL,
.gpl_only = false,
.ret_type = RET_VOID,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
};
/* Stub for JITs that only support cBPF. eBPF programs are interpreted.
* It is encouraged to implement bpf_int_jit_compile() instead, so that
* eBPF and implicitly also cBPF can get JITed!
*/
struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
{
return prog;
}
/* Stub for JITs that support eBPF. All cBPF code gets transformed into
* eBPF by the kernel and is later compiled by bpf_int_jit_compile().
*/
void __weak bpf_jit_compile(struct bpf_prog *prog)
{
}
bool __weak bpf_helper_changes_pkt_data(void *func)
{
return false;
}
/* Return TRUE if the JIT backend wants verifier to enable sub-register usage
* analysis code and wants explicit zero extension inserted by verifier.
* Otherwise, return FALSE.
*
* The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if
* you don't override this. JITs that don't want these extra insns can detect
* them using insn_is_zext.
*/
bool __weak bpf_jit_needs_zext(void)
{
return false;
}
/* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */
bool __weak bpf_jit_supports_subprog_tailcalls(void)
{
return false;
}
bool __weak bpf_jit_supports_kfunc_call(void)
{
return false;
}
/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
* skb_copy_bits(), so provide a weak definition of it for NET-less config.
*/
int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
int len)
{
return -EFAULT;
}
int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2)
{
return -ENOTSUPP;
}
void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len)
{
return ERR_PTR(-ENOTSUPP);
}
int __weak bpf_arch_text_invalidate(void *dst, size_t len)
{
return -ENOTSUPP;
}
DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
EXPORT_SYMBOL(bpf_stats_enabled_key);
/* All definitions of tracepoints related to BPF. */
#define CREATE_TRACE_POINTS
#include <linux/bpf_trace.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);
|