1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
12194
12195
12196
12197
12198
12199
12200
12201
12202
12203
12204
12205
12206
12207
12208
12209
12210
12211
12212
12213
12214
12215
12216
12217
12218
12219
12220
12221
12222
12223
12224
12225
12226
12227
12228
12229
12230
12231
12232
12233
12234
12235
12236
12237
12238
12239
12240
12241
12242
12243
12244
12245
12246
12247
12248
12249
12250
12251
12252
12253
12254
12255
12256
12257
12258
12259
12260
12261
12262
12263
12264
12265
12266
12267
12268
12269
12270
12271
12272
12273
12274
12275
12276
12277
12278
12279
12280
12281
12282
12283
12284
12285
12286
12287
12288
12289
12290
12291
12292
12293
12294
12295
12296
12297
12298
12299
12300
12301
12302
12303
12304
12305
12306
12307
12308
12309
12310
12311
12312
12313
12314
12315
12316
12317
12318
12319
12320
12321
12322
12323
12324
12325
12326
12327
12328
12329
12330
12331
12332
12333
12334
12335
12336
12337
12338
12339
12340
12341
12342
12343
12344
12345
12346
12347
12348
12349
12350
12351
12352
12353
12354
12355
12356
12357
12358
12359
12360
12361
12362
12363
12364
12365
12366
12367
12368
12369
12370
12371
12372
12373
12374
12375
12376
12377
12378
12379
12380
12381
12382
12383
12384
12385
12386
12387
12388
12389
12390
12391
12392
12393
12394
12395
12396
12397
12398
12399
12400
12401
12402
12403
12404
12405
12406
12407
12408
12409
12410
12411
12412
12413
12414
12415
12416
12417
12418
12419
12420
12421
12422
12423
12424
12425
12426
12427
12428
12429
12430
12431
12432
12433
12434
12435
12436
12437
12438
12439
12440
12441
12442
12443
12444
12445
12446
12447
12448
12449
12450
12451
12452
12453
12454
12455
12456
12457
12458
12459
12460
12461
12462
12463
12464
12465
12466
12467
12468
12469
12470
12471
12472
12473
12474
12475
12476
12477
12478
12479
12480
12481
12482
12483
12484
12485
12486
12487
12488
12489
12490
12491
12492
12493
12494
12495
12496
12497
12498
12499
12500
12501
12502
12503
12504
12505
12506
12507
12508
12509
12510
12511
12512
12513
12514
12515
12516
12517
12518
12519
12520
12521
12522
12523
12524
12525
12526
12527
12528
12529
12530
12531
12532
12533
12534
12535
12536
12537
12538
12539
12540
12541
12542
12543
12544
12545
12546
12547
12548
12549
12550
12551
12552
12553
12554
12555
12556
12557
12558
12559
12560
12561
12562
12563
12564
12565
12566
12567
12568
12569
12570
12571
12572
12573
12574
12575
12576
12577
12578
12579
12580
12581
12582
12583
12584
12585
12586
12587
12588
12589
12590
12591
12592
12593
12594
12595
12596
12597
12598
12599
12600
12601
12602
12603
12604
12605
12606
12607
12608
12609
12610
12611
12612
12613
12614
12615
12616
12617
12618
12619
12620
12621
12622
12623
12624
12625
12626
12627
12628
12629
12630
12631
12632
12633
12634
12635
12636
12637
12638
12639
12640
12641
12642
12643
12644
12645
12646
12647
12648
12649
12650
12651
12652
12653
12654
12655
12656
12657
12658
12659
12660
12661
12662
12663
12664
12665
12666
12667
12668
12669
12670
12671
12672
12673
12674
12675
12676
12677
12678
12679
12680
12681
12682
12683
12684
12685
12686
12687
12688
12689
12690
12691
12692
12693
12694
12695
12696
12697
12698
12699
12700
12701
12702
12703
12704
12705
12706
12707
12708
12709
12710
12711
12712
12713
12714
12715
12716
12717
12718
12719
12720
12721
12722
12723
12724
12725
12726
12727
12728
12729
12730
12731
12732
12733
12734
12735
12736
12737
12738
12739
12740
12741
12742
12743
12744
12745
12746
12747
12748
12749
12750
12751
12752
12753
12754
12755
12756
12757
12758
12759
12760
12761
12762
12763
12764
12765
12766
12767
12768
12769
12770
12771
12772
12773
12774
12775
12776
12777
12778
12779
12780
12781
12782
12783
12784
12785
12786
12787
12788
12789
12790
12791
12792
12793
12794
12795
12796
12797
12798
12799
12800
12801
12802
12803
12804
12805
12806
12807
12808
12809
12810
12811
12812
12813
12814
12815
12816
12817
12818
12819
12820
12821
12822
12823
12824
12825
12826
12827
12828
12829
12830
12831
12832
12833
12834
12835
12836
12837
12838
12839
12840
12841
12842
12843
12844
12845
12846
12847
12848
12849
12850
12851
12852
12853
12854
12855
12856
12857
12858
12859
12860
12861
12862
12863
12864
12865
12866
12867
12868
12869
12870
12871
12872
12873
12874
12875
12876
12877
12878
12879
12880
12881
12882
12883
12884
12885
12886
12887
12888
12889
12890
12891
12892
12893
12894
12895
12896
12897
12898
12899
12900
12901
12902
12903
12904
12905
12906
12907
12908
12909
12910
12911
12912
12913
12914
12915
12916
12917
12918
12919
12920
12921
12922
12923
12924
12925
12926
12927
12928
12929
12930
12931
12932
12933
12934
12935
12936
12937
12938
12939
12940
12941
12942
12943
12944
12945
12946
12947
12948
12949
12950
12951
12952
12953
12954
12955
12956
12957
12958
12959
12960
12961
12962
12963
12964
12965
12966
12967
12968
12969
12970
12971
12972
12973
12974
12975
12976
12977
12978
12979
12980
12981
12982
12983
12984
12985
12986
12987
12988
12989
12990
12991
12992
12993
12994
12995
12996
12997
12998
12999
13000
13001
13002
13003
13004
13005
13006
13007
13008
13009
13010
13011
13012
13013
13014
13015
13016
13017
13018
13019
13020
13021
13022
13023
13024
13025
13026
13027
13028
13029
13030
13031
13032
13033
13034
13035
13036
13037
13038
13039
13040
13041
13042
13043
13044
13045
13046
13047
13048
13049
13050
13051
13052
13053
13054
13055
13056
13057
13058
13059
13060
13061
13062
13063
13064
13065
13066
13067
13068
13069
13070
13071
13072
13073
13074
13075
13076
13077
13078
13079
13080
13081
13082
13083
13084
13085
13086
13087
13088
13089
13090
13091
13092
13093
13094
13095
13096
13097
13098
13099
13100
13101
13102
13103
13104
13105
13106
13107
13108
13109
13110
13111
13112
13113
13114
13115
13116
13117
13118
13119
13120
13121
13122
13123
13124
13125
13126
13127
13128
13129
13130
13131
13132
13133
13134
13135
13136
13137
13138
13139
13140
13141
13142
13143
13144
13145
13146
13147
13148
13149
13150
13151
13152
13153
13154
13155
13156
13157
13158
13159
13160
13161
13162
13163
13164
13165
13166
13167
13168
13169
13170
13171
13172
13173
13174
13175
13176
13177
13178
13179
13180
13181
13182
13183
13184
13185
13186
13187
13188
13189
13190
13191
13192
13193
13194
13195
13196
13197
13198
13199
13200
13201
13202
13203
13204
13205
13206
13207
13208
13209
13210
13211
13212
13213
13214
13215
13216
13217
13218
13219
13220
13221
13222
13223
13224
13225
13226
13227
13228
13229
13230
13231
13232
13233
13234
13235
13236
13237
13238
13239
13240
13241
13242
13243
13244
13245
13246
13247
13248
13249
13250
13251
13252
13253
13254
13255
13256
13257
13258
13259
13260
13261
13262
13263
13264
13265
13266
13267
13268
13269
13270
13271
13272
13273
13274
13275
13276
13277
13278
13279
13280
13281
13282
13283
13284
13285
13286
13287
13288
13289
13290
13291
13292
13293
13294
13295
13296
13297
13298
13299
13300
13301
13302
13303
13304
13305
13306
13307
13308
13309
13310
13311
13312
13313
13314
13315
13316
13317
13318
13319
13320
13321
13322
13323
13324
13325
13326
13327
13328
13329
13330
13331
13332
13333
13334
13335
13336
13337
13338
13339
13340
13341
13342
13343
13344
13345
13346
13347
13348
13349
13350
13351
13352
13353
13354
13355
13356
13357
13358
13359
13360
13361
13362
13363
13364
13365
13366
13367
13368
13369
13370
13371
13372
13373
13374
13375
13376
13377
13378
13379
13380
13381
13382
13383
13384
13385
13386
13387
13388
13389
13390
13391
13392
13393
13394
13395
13396
13397
13398
13399
13400
13401
13402
13403
13404
13405
13406
13407
13408
13409
13410
13411
13412
13413
13414
13415
13416
13417
13418
13419
13420
13421
13422
13423
13424
13425
13426
13427
13428
13429
13430
13431
13432
13433
13434
13435
13436
13437
13438
13439
13440
13441
13442
13443
13444
13445
13446
13447
13448
13449
13450
13451
13452
13453
13454
13455
13456
13457
13458
13459
13460
13461
13462
13463
13464
13465
13466
13467
13468
13469
13470
13471
13472
13473
13474
13475
13476
13477
13478
13479
13480
13481
13482
13483
13484
13485
13486
13487
13488
13489
13490
13491
13492
13493
13494
13495
13496
13497
13498
13499
13500
13501
13502
13503
13504
13505
13506
13507
13508
13509
|
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
* Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*/
#include <uapi/linux/btf.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>
#include <linux/ctype.h>
#include <linux/error-injection.h>
#include <linux/bpf_lsm.h>
#include <linux/btf_ids.h>
#include "disasm.h"
static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
[_id] = & _name ## _verifier_ops,
#define BPF_MAP_TYPE(_id, _ops)
#define BPF_LINK_TYPE(_id, _name)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
#undef BPF_LINK_TYPE
};
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
*
* The first pass is depth-first-search to check that the program is a DAG.
* It rejects the following programs:
* - larger than BPF_MAXINSNS insns
* - if loop is present (detected via back-edge)
* - unreachable insns exist (shouldn't be a forest. program = one function)
* - out of bounds or malformed jumps
* The second pass is all possible path descent from the 1st insn.
* Since it's analyzing all pathes through the program, the length of the
* analysis is limited to 64k insn, which may be hit even if total number of
* insn is less then 4K, but there are too many branches that change stack/regs.
* Number of 'branches to be analyzed' is limited to 1k
*
* On entry to each instruction, each register has a type, and the instruction
* changes the types of the registers depending on instruction semantics.
* If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
* copied to R1.
*
* All registers are 64-bit.
* R0 - return register
* R1-R5 argument passing registers
* R6-R9 callee saved registers
* R10 - frame pointer read-only
*
* At the start of BPF program the register R1 contains a pointer to bpf_context
* and has type PTR_TO_CTX.
*
* Verifier tracks arithmetic operations on pointers in case:
* BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
* BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
* 1st insn copies R10 (which has FRAME_PTR) type into R1
* and 2nd arithmetic instruction is pattern matched to recognize
* that it wants to construct a pointer to some element within stack.
* So after 2nd insn, the register R1 has type PTR_TO_STACK
* (and -20 constant is saved for further stack bounds checking).
* Meaning that this reg is a pointer to stack plus known immediate constant.
*
* Most of the time the registers have SCALAR_VALUE type, which
* means the register has some value, but it's not a valid pointer.
* (like pointer plus pointer becomes SCALAR_VALUE type)
*
* When verifier sees load or store instructions the type of base register
* can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are
* four pointer types recognized by check_mem_access() function.
*
* PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
* and the range of [ptr, ptr + map's value_size) is accessible.
*
* registers used to pass values to function calls are checked against
* function argument constraints.
*
* ARG_PTR_TO_MAP_KEY is one of such argument constraints.
* It means that the register type passed to this function must be
* PTR_TO_STACK and it will be used inside the function as
* 'pointer to map element key'
*
* For example the argument constraints for bpf_map_lookup_elem():
* .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
* .arg1_type = ARG_CONST_MAP_PTR,
* .arg2_type = ARG_PTR_TO_MAP_KEY,
*
* ret_type says that this function returns 'pointer to map elem value or null'
* function expects 1st argument to be a const pointer to 'struct bpf_map' and
* 2nd argument should be a pointer to stack, which will be used inside
* the helper function as a pointer to map element key.
*
* On the kernel side the helper function looks like:
* u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
* {
* struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
* void *key = (void *) (unsigned long) r2;
* void *value;
*
* here kernel can access 'key' and 'map' pointers safely, knowing that
* [key, key + map->key_size) bytes are valid and were initialized on
* the stack of eBPF program.
* }
*
* Corresponding eBPF program may look like:
* BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR
* BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
* BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP
* BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
* here verifier looks at prototype of map_lookup_elem() and sees:
* .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
* Now verifier knows that this map has key of R1->map_ptr->key_size bytes
*
* Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
* Now verifier checks that [R2, R2 + map's key_size) are within stack limits
* and were initialized prior to this call.
* If it's ok, then verifier allows this BPF_CALL insn and looks at
* .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
* R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
* returns ether pointer to map value or NULL.
*
* When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
* insn, the register holding that pointer in the true branch changes state to
* PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
* branch. See check_cond_jmp_op().
*
* After the call R0 is set to return type of the function and registers R1-R5
* are set to NOT_INIT to indicate that they are no longer readable.
*
* The following reference types represent a potential reference to a kernel
* resource which, after first being allocated, must be checked and freed by
* the BPF program:
* - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET
*
* When the verifier sees a helper call return a reference type, it allocates a
* pointer id for the reference and stores it in the current function state.
* Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into
* PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
* passes through a NULL-check conditional. For the branch wherein the state is
* changed to CONST_IMM, the verifier releases the reference.
*
* For each helper function that allocates a reference, such as
* bpf_sk_lookup_tcp(), there is a corresponding release function, such as
* bpf_sk_release(). When a reference type passes into the release function,
* the verifier also releases the reference. If any unchecked or unreleased
* reference remains at the end of the program, the verifier rejects it.
*/
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
/* verifer state is 'st'
* before processing instruction 'insn_idx'
* and after processing instruction 'prev_insn_idx'
*/
struct bpf_verifier_state st;
int insn_idx;
int prev_insn_idx;
struct bpf_verifier_stack_elem *next;
/* length of verifier log at the time this state was pushed on stack */
u32 log_pos;
};
#define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192
#define BPF_COMPLEXITY_LIMIT_STATES 64
#define BPF_MAP_KEY_POISON (1ULL << 63)
#define BPF_MAP_KEY_SEEN (1ULL << 62)
#define BPF_MAP_PTR_UNPRIV 1UL
#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
POISON_POINTER_DELTA))
#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON;
}
static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
{
return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV;
}
static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
const struct bpf_map *map, bool unpriv)
{
BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
unpriv |= bpf_map_ptr_unpriv(aux);
aux->map_ptr_state = (unsigned long)map |
(unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
}
static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux)
{
return aux->map_key_state & BPF_MAP_KEY_POISON;
}
static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux)
{
return !(aux->map_key_state & BPF_MAP_KEY_SEEN);
}
static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux)
{
return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON);
}
static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
{
bool poisoned = bpf_map_key_poisoned(aux);
aux->map_key_state = state | BPF_MAP_KEY_SEEN |
(poisoned ? BPF_MAP_KEY_POISON : 0ULL);
}
static bool bpf_pseudo_call(const struct bpf_insn *insn)
{
return insn->code == (BPF_JMP | BPF_CALL) &&
insn->src_reg == BPF_PSEUDO_CALL;
}
static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn)
{
return insn->code == (BPF_JMP | BPF_CALL) &&
insn->src_reg == BPF_PSEUDO_KFUNC_CALL;
}
static bool bpf_pseudo_func(const struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
insn->src_reg == BPF_PSEUDO_FUNC;
}
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
bool raw_mode;
bool pkt_access;
int regno;
int access_size;
int mem_size;
u64 msize_max_value;
int ref_obj_id;
int func_id;
struct btf *btf;
u32 btf_id;
struct btf *ret_btf;
u32 ret_btf_id;
u32 subprogno;
};
struct btf *btf_vmlinux;
static DEFINE_MUTEX(bpf_verifier_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
{
const struct bpf_line_info *linfo;
const struct bpf_prog *prog;
u32 i, nr_linfo;
prog = env->prog;
nr_linfo = prog->aux->nr_linfo;
if (!nr_linfo || insn_off >= prog->len)
return NULL;
linfo = prog->aux->linfo;
for (i = 1; i < nr_linfo; i++)
if (insn_off < linfo[i].insn_off)
break;
return &linfo[i - 1];
}
void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
va_list args)
{
unsigned int n;
n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
"verifier log line truncated - local buffer too short\n");
n = min(log->len_total - log->len_used - 1, n);
log->kbuf[n] = '\0';
if (log->level == BPF_LOG_KERNEL) {
pr_err("BPF:%s\n", log->kbuf);
return;
}
if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
log->len_used += n;
else
log->ubuf = NULL;
}
static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos)
{
char zero = 0;
if (!bpf_verifier_log_needed(log))
return;
log->len_used = new_pos;
if (put_user(zero, log->ubuf + new_pos))
log->ubuf = NULL;
}
/* log_level controls verbosity level of eBPF verifier.
* bpf_verifier_log_write() is used to dump the verification trace to the log,
* so the user can figure out what's wrong with the program
*/
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
const char *fmt, ...)
{
va_list args;
if (!bpf_verifier_log_needed(&env->log))
return;
va_start(args, fmt);
bpf_verifier_vlog(&env->log, fmt, args);
va_end(args);
}
EXPORT_SYMBOL_GPL(bpf_verifier_log_write);
__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
{
struct bpf_verifier_env *env = private_data;
va_list args;
if (!bpf_verifier_log_needed(&env->log))
return;
va_start(args, fmt);
bpf_verifier_vlog(&env->log, fmt, args);
va_end(args);
}
__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
const char *fmt, ...)
{
va_list args;
if (!bpf_verifier_log_needed(log))
return;
va_start(args, fmt);
bpf_verifier_vlog(log, fmt, args);
va_end(args);
}
static const char *ltrim(const char *s)
{
while (isspace(*s))
s++;
return s;
}
__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
u32 insn_off,
const char *prefix_fmt, ...)
{
const struct bpf_line_info *linfo;
if (!bpf_verifier_log_needed(&env->log))
return;
linfo = find_linfo(env, insn_off);
if (!linfo || linfo == env->prev_linfo)
return;
if (prefix_fmt) {
va_list args;
va_start(args, prefix_fmt);
bpf_verifier_vlog(&env->log, prefix_fmt, args);
va_end(args);
}
verbose(env, "%s\n",
ltrim(btf_name_by_offset(env->prog->aux->btf,
linfo->line_off)));
env->prev_linfo = linfo;
}
static void verbose_invalid_scalar(struct bpf_verifier_env *env,
struct bpf_reg_state *reg,
struct tnum *range, const char *ctx,
const char *reg_name)
{
char tn_buf[48];
verbose(env, "At %s the register %s ", ctx, reg_name);
if (!tnum_is_unknown(reg->var_off)) {
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "has value %s", tn_buf);
} else {
verbose(env, "has unknown scalar value");
}
tnum_strn(tn_buf, sizeof(tn_buf), *range);
verbose(env, " should have been in %s\n", tn_buf);
}
static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_PACKET ||
type == PTR_TO_PACKET_META;
}
static bool type_is_sk_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET ||
type == PTR_TO_SOCK_COMMON ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_XDP_SOCK;
}
static bool reg_type_not_null(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_MAP_VALUE ||
type == PTR_TO_MAP_KEY ||
type == PTR_TO_SOCK_COMMON;
}
static bool reg_type_may_be_null(enum bpf_reg_type type)
{
return type == PTR_TO_MAP_VALUE_OR_NULL ||
type == PTR_TO_SOCKET_OR_NULL ||
type == PTR_TO_SOCK_COMMON_OR_NULL ||
type == PTR_TO_TCP_SOCK_OR_NULL ||
type == PTR_TO_BTF_ID_OR_NULL ||
type == PTR_TO_MEM_OR_NULL ||
type == PTR_TO_RDONLY_BUF_OR_NULL ||
type == PTR_TO_RDWR_BUF_OR_NULL;
}
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return reg->type == PTR_TO_MAP_VALUE &&
map_value_has_spin_lock(reg->map_ptr);
}
static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
{
return type == PTR_TO_SOCKET ||
type == PTR_TO_SOCKET_OR_NULL ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_TCP_SOCK_OR_NULL ||
type == PTR_TO_MEM ||
type == PTR_TO_MEM_OR_NULL;
}
static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_SOCK_COMMON;
}
static bool arg_type_may_be_null(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
type == ARG_PTR_TO_MEM_OR_NULL ||
type == ARG_PTR_TO_CTX_OR_NULL ||
type == ARG_PTR_TO_SOCKET_OR_NULL ||
type == ARG_PTR_TO_ALLOC_MEM_OR_NULL ||
type == ARG_PTR_TO_STACK_OR_NULL;
}
/* Determine whether the function releases some resources allocated by another
* function call. The first reference type argument will be assumed to be
* released by release_reference().
*/
static bool is_release_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_release ||
func_id == BPF_FUNC_ringbuf_submit ||
func_id == BPF_FUNC_ringbuf_discard;
}
static bool may_be_acquire_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_lookup_tcp ||
func_id == BPF_FUNC_sk_lookup_udp ||
func_id == BPF_FUNC_skc_lookup_tcp ||
func_id == BPF_FUNC_map_lookup_elem ||
func_id == BPF_FUNC_ringbuf_reserve;
}
static bool is_acquire_function(enum bpf_func_id func_id,
const struct bpf_map *map)
{
enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC;
if (func_id == BPF_FUNC_sk_lookup_tcp ||
func_id == BPF_FUNC_sk_lookup_udp ||
func_id == BPF_FUNC_skc_lookup_tcp ||
func_id == BPF_FUNC_ringbuf_reserve)
return true;
if (func_id == BPF_FUNC_map_lookup_elem &&
(map_type == BPF_MAP_TYPE_SOCKMAP ||
map_type == BPF_MAP_TYPE_SOCKHASH))
return true;
return false;
}
static bool is_ptr_cast_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_tcp_sock ||
func_id == BPF_FUNC_sk_fullsock ||
func_id == BPF_FUNC_skc_to_tcp_sock ||
func_id == BPF_FUNC_skc_to_tcp6_sock ||
func_id == BPF_FUNC_skc_to_udp6_sock ||
func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
func_id == BPF_FUNC_skc_to_tcp_request_sock;
}
static bool is_cmpxchg_insn(const struct bpf_insn *insn)
{
return BPF_CLASS(insn->code) == BPF_STX &&
BPF_MODE(insn->code) == BPF_ATOMIC &&
insn->imm == BPF_CMPXCHG;
}
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
[SCALAR_VALUE] = "inv",
[PTR_TO_CTX] = "ctx",
[CONST_PTR_TO_MAP] = "map_ptr",
[PTR_TO_MAP_VALUE] = "map_value",
[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
[PTR_TO_STACK] = "fp",
[PTR_TO_PACKET] = "pkt",
[PTR_TO_PACKET_META] = "pkt_meta",
[PTR_TO_PACKET_END] = "pkt_end",
[PTR_TO_FLOW_KEYS] = "flow_keys",
[PTR_TO_SOCKET] = "sock",
[PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
[PTR_TO_SOCK_COMMON] = "sock_common",
[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
[PTR_TO_TCP_SOCK] = "tcp_sock",
[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
[PTR_TO_TP_BUFFER] = "tp_buffer",
[PTR_TO_XDP_SOCK] = "xdp_sock",
[PTR_TO_BTF_ID] = "ptr_",
[PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_",
[PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
[PTR_TO_MEM] = "mem",
[PTR_TO_MEM_OR_NULL] = "mem_or_null",
[PTR_TO_RDONLY_BUF] = "rdonly_buf",
[PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
[PTR_TO_RDWR_BUF] = "rdwr_buf",
[PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
[PTR_TO_FUNC] = "func",
[PTR_TO_MAP_KEY] = "map_key",
};
static char slot_type_char[] = {
[STACK_INVALID] = '?',
[STACK_SPILL] = 'r',
[STACK_MISC] = 'm',
[STACK_ZERO] = '0',
};
static void print_liveness(struct bpf_verifier_env *env,
enum bpf_reg_liveness live)
{
if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
verbose(env, "_");
if (live & REG_LIVE_READ)
verbose(env, "r");
if (live & REG_LIVE_WRITTEN)
verbose(env, "w");
if (live & REG_LIVE_DONE)
verbose(env, "D");
}
static struct bpf_func_state *func(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg)
{
struct bpf_verifier_state *cur = env->cur_state;
return cur->frame[reg->frameno];
}
static const char *kernel_type_name(const struct btf* btf, u32 id)
{
return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state)
{
const struct bpf_reg_state *reg;
enum bpf_reg_type t;
int i;
if (state->frameno)
verbose(env, " frame%d:", state->frameno);
for (i = 0; i < MAX_BPF_REG; i++) {
reg = &state->regs[i];
t = reg->type;
if (t == NOT_INIT)
continue;
verbose(env, " R%d", i);
print_liveness(env, reg->live);
verbose(env, "=%s", reg_type_str[t]);
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
tnum_is_const(reg->var_off)) {
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
if (t == PTR_TO_BTF_ID ||
t == PTR_TO_BTF_ID_OR_NULL ||
t == PTR_TO_PERCPU_BTF_ID)
verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id));
verbose(env, "(id=%d", reg->id);
if (reg_type_may_be_refcounted_or_null(t))
verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
if (t != SCALAR_VALUE)
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
else if (t == CONST_PTR_TO_MAP ||
t == PTR_TO_MAP_KEY ||
t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
if (tnum_is_const(reg->var_off)) {
/* Typically an immediate SCALAR_VALUE, but
* could be a pointer whose offset is too big
* for reg->off
*/
verbose(env, ",imm=%llx", reg->var_off.value);
} else {
if (reg->smin_value != reg->umin_value &&
reg->smin_value != S64_MIN)
verbose(env, ",smin_value=%lld",
(long long)reg->smin_value);
if (reg->smax_value != reg->umax_value &&
reg->smax_value != S64_MAX)
verbose(env, ",smax_value=%lld",
(long long)reg->smax_value);
if (reg->umin_value != 0)
verbose(env, ",umin_value=%llu",
(unsigned long long)reg->umin_value);
if (reg->umax_value != U64_MAX)
verbose(env, ",umax_value=%llu",
(unsigned long long)reg->umax_value);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, ",var_off=%s", tn_buf);
}
if (reg->s32_min_value != reg->smin_value &&
reg->s32_min_value != S32_MIN)
verbose(env, ",s32_min_value=%d",
(int)(reg->s32_min_value));
if (reg->s32_max_value != reg->smax_value &&
reg->s32_max_value != S32_MAX)
verbose(env, ",s32_max_value=%d",
(int)(reg->s32_max_value));
if (reg->u32_min_value != reg->umin_value &&
reg->u32_min_value != U32_MIN)
verbose(env, ",u32_min_value=%d",
(int)(reg->u32_min_value));
if (reg->u32_max_value != reg->umax_value &&
reg->u32_max_value != U32_MAX)
verbose(env, ",u32_max_value=%d",
(int)(reg->u32_max_value));
}
verbose(env, ")");
}
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
char types_buf[BPF_REG_SIZE + 1];
bool valid = false;
int j;
for (j = 0; j < BPF_REG_SIZE; j++) {
if (state->stack[i].slot_type[j] != STACK_INVALID)
valid = true;
types_buf[j] = slot_type_char[
state->stack[i].slot_type[j]];
}
types_buf[BPF_REG_SIZE] = 0;
if (!valid)
continue;
verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
print_liveness(env, state->stack[i].spilled_ptr.live);
if (state->stack[i].slot_type[0] == STACK_SPILL) {
reg = &state->stack[i].spilled_ptr;
t = reg->type;
verbose(env, "=%s", reg_type_str[t]);
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
verbose(env, "=%s", types_buf);
}
}
if (state->acquired_refs && state->refs[0].id) {
verbose(env, " refs=%d", state->refs[0].id);
for (i = 1; i < state->acquired_refs; i++)
if (state->refs[i].id)
verbose(env, ",%d", state->refs[i].id);
}
verbose(env, "\n");
}
#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \
static int copy_##NAME##_state(struct bpf_func_state *dst, \
const struct bpf_func_state *src) \
{ \
if (!src->FIELD) \
return 0; \
if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \
/* internal bug, make state invalid to reject the program */ \
memset(dst, 0, sizeof(*dst)); \
return -EFAULT; \
} \
memcpy(dst->FIELD, src->FIELD, \
sizeof(*src->FIELD) * (src->COUNT / SIZE)); \
return 0; \
}
/* copy_reference_state() */
COPY_STATE_FN(reference, acquired_refs, refs, 1)
/* copy_stack_state() */
COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
#undef COPY_STATE_FN
#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \
static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \
bool copy_old) \
{ \
u32 old_size = state->COUNT; \
struct bpf_##NAME##_state *new_##FIELD; \
int slot = size / SIZE; \
\
if (size <= old_size || !size) { \
if (copy_old) \
return 0; \
state->COUNT = slot * SIZE; \
if (!size && old_size) { \
kfree(state->FIELD); \
state->FIELD = NULL; \
} \
return 0; \
} \
new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \
GFP_KERNEL); \
if (!new_##FIELD) \
return -ENOMEM; \
if (copy_old) { \
if (state->FIELD) \
memcpy(new_##FIELD, state->FIELD, \
sizeof(*new_##FIELD) * (old_size / SIZE)); \
memset(new_##FIELD + old_size / SIZE, 0, \
sizeof(*new_##FIELD) * (size - old_size) / SIZE); \
} \
state->COUNT = slot * SIZE; \
kfree(state->FIELD); \
state->FIELD = new_##FIELD; \
return 0; \
}
/* realloc_reference_state() */
REALLOC_STATE_FN(reference, acquired_refs, refs, 1)
/* realloc_stack_state() */
REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
#undef REALLOC_STATE_FN
/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
* make it consume minimal amount of memory. check_stack_write() access from
* the program calls into realloc_func_state() to grow the stack size.
* Note there is a non-zero 'parent' pointer inside bpf_verifier_state
* which realloc_stack_state() copies over. It points to previous
* bpf_verifier_state which is never reallocated.
*/
static int realloc_func_state(struct bpf_func_state *state, int stack_size,
int refs_size, bool copy_old)
{
int err = realloc_reference_state(state, refs_size, copy_old);
if (err)
return err;
return realloc_stack_state(state, stack_size, copy_old);
}
/* Acquire a pointer id from the env and update the state->refs to include
* this new pointer reference.
* On success, returns a valid pointer id to associate with the register
* On failure, returns a negative errno.
*/
static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_func_state *state = cur_func(env);
int new_ofs = state->acquired_refs;
int id, err;
err = realloc_reference_state(state, state->acquired_refs + 1, true);
if (err)
return err;
id = ++env->id_gen;
state->refs[new_ofs].id = id;
state->refs[new_ofs].insn_idx = insn_idx;
return id;
}
/* release function corresponding to acquire_reference_state(). Idempotent. */
static int release_reference_state(struct bpf_func_state *state, int ptr_id)
{
int i, last_idx;
last_idx = state->acquired_refs - 1;
for (i = 0; i < state->acquired_refs; i++) {
if (state->refs[i].id == ptr_id) {
if (last_idx && i != last_idx)
memcpy(&state->refs[i], &state->refs[last_idx],
sizeof(*state->refs));
memset(&state->refs[last_idx], 0, sizeof(*state->refs));
state->acquired_refs--;
return 0;
}
}
return -EINVAL;
}
static int transfer_reference_state(struct bpf_func_state *dst,
struct bpf_func_state *src)
{
int err = realloc_reference_state(dst, src->acquired_refs, false);
if (err)
return err;
err = copy_reference_state(dst, src);
if (err)
return err;
return 0;
}
static void free_func_state(struct bpf_func_state *state)
{
if (!state)
return;
kfree(state->refs);
kfree(state->stack);
kfree(state);
}
static void clear_jmp_history(struct bpf_verifier_state *state)
{
kfree(state->jmp_history);
state->jmp_history = NULL;
state->jmp_history_cnt = 0;
}
static void free_verifier_state(struct bpf_verifier_state *state,
bool free_self)
{
int i;
for (i = 0; i <= state->curframe; i++) {
free_func_state(state->frame[i]);
state->frame[i] = NULL;
}
clear_jmp_history(state);
if (free_self)
kfree(state);
}
/* copy verifier state from src to dst growing dst stack space
* when necessary to accommodate larger src stack
*/
static int copy_func_state(struct bpf_func_state *dst,
const struct bpf_func_state *src)
{
int err;
err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs,
false);
if (err)
return err;
memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs));
err = copy_reference_state(dst, src);
if (err)
return err;
return copy_stack_state(dst, src);
}
static int copy_verifier_state(struct bpf_verifier_state *dst_state,
const struct bpf_verifier_state *src)
{
struct bpf_func_state *dst;
u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt;
int i, err;
if (dst_state->jmp_history_cnt < src->jmp_history_cnt) {
kfree(dst_state->jmp_history);
dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER);
if (!dst_state->jmp_history)
return -ENOMEM;
}
memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz);
dst_state->jmp_history_cnt = src->jmp_history_cnt;
/* if dst has more stack frames then src frame, free them */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
}
dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
dst_state->active_spin_lock = src->active_spin_lock;
dst_state->branches = src->branches;
dst_state->parent = src->parent;
dst_state->first_insn_idx = src->first_insn_idx;
dst_state->last_insn_idx = src->last_insn_idx;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (!dst)
return -ENOMEM;
dst_state->frame[i] = dst;
}
err = copy_func_state(dst, src->frame[i]);
if (err)
return err;
}
return 0;
}
static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
while (st) {
u32 br = --st->branches;
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
WARN_ONCE((int)br < 0,
"BUG update_branch_counts:branches_to_explore=%d\n",
br);
if (br)
break;
st = st->parent;
}
}
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
int *insn_idx, bool pop_log)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem, *head = env->head;
int err;
if (env->head == NULL)
return -ENOENT;
if (cur) {
err = copy_verifier_state(cur, &head->st);
if (err)
return err;
}
if (pop_log)
bpf_vlog_reset(&env->log, head->log_pos);
if (insn_idx)
*insn_idx = head->insn_idx;
if (prev_insn_idx)
*prev_insn_idx = head->prev_insn_idx;
elem = head->next;
free_verifier_state(&head->st, false);
kfree(head);
env->head = elem;
env->stack_size--;
return 0;
}
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx,
bool speculative)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem;
int err;
elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
if (!elem)
goto err;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
elem->next = env->head;
elem->log_pos = env->log.len_used;
env->head = elem;
env->stack_size++;
err = copy_verifier_state(&elem->st, cur);
if (err)
goto err;
elem->st.speculative |= speculative;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
verbose(env, "The sequence of %d jumps is too complex.\n",
env->stack_size);
goto err;
}
if (elem->st.parent) {
++elem->st.parent->branches;
/* WARN_ON(branches > 2) technically makes sense here,
* but
* 1. speculative states will bump 'branches' for non-branch
* instructions
* 2. is_state_visited() heuristics may decide not to create
* a new state for a sequence of branches and all such current
* and cloned states will be pointing to a single parent state
* which might have large 'branches' count.
*/
}
return &elem->st;
err:
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
/* pop all elements and return */
while (!pop_stack(env, NULL, NULL, false));
return NULL;
}
#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
static void __mark_reg_not_init(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg);
/* This helper doesn't clear reg->id */
static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
reg->var_off = tnum_const(imm);
reg->smin_value = (s64)imm;
reg->smax_value = (s64)imm;
reg->umin_value = imm;
reg->umax_value = imm;
reg->s32_min_value = (s32)imm;
reg->s32_max_value = (s32)imm;
reg->u32_min_value = (u32)imm;
reg->u32_max_value = (u32)imm;
}
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
*/
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
/* Clear id, off, and union(map_ptr, range) */
memset(((u8 *)reg) + sizeof(reg->type), 0,
offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
___mark_reg_known(reg, imm);
}
static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm)
{
reg->var_off = tnum_const_subreg(reg->var_off, imm);
reg->s32_min_value = (s32)imm;
reg->s32_max_value = (s32)imm;
reg->u32_min_value = (u32)imm;
reg->u32_max_value = (u32)imm;
}
/* Mark the 'variable offset' part of a register as zero. This should be
* used only on registers holding a pointer type.
*/
static void __mark_reg_known_zero(struct bpf_reg_state *reg)
{
__mark_reg_known(reg, 0);
}
static void __mark_reg_const_zero(struct bpf_reg_state *reg)
{
__mark_reg_known(reg, 0);
reg->type = SCALAR_VALUE;
}
static void mark_reg_known_zero(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
__mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
}
static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
{
switch (reg->type) {
case PTR_TO_MAP_VALUE_OR_NULL: {
const struct bpf_map *map = reg->map_ptr;
if (map->inner_map_meta) {
reg->type = CONST_PTR_TO_MAP;
reg->map_ptr = map->inner_map_meta;
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
reg->type = PTR_TO_XDP_SOCK;
} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
map->map_type == BPF_MAP_TYPE_SOCKHASH) {
reg->type = PTR_TO_SOCKET;
} else {
reg->type = PTR_TO_MAP_VALUE;
}
break;
}
case PTR_TO_SOCKET_OR_NULL:
reg->type = PTR_TO_SOCKET;
break;
case PTR_TO_SOCK_COMMON_OR_NULL:
reg->type = PTR_TO_SOCK_COMMON;
break;
case PTR_TO_TCP_SOCK_OR_NULL:
reg->type = PTR_TO_TCP_SOCK;
break;
case PTR_TO_BTF_ID_OR_NULL:
reg->type = PTR_TO_BTF_ID;
break;
case PTR_TO_MEM_OR_NULL:
reg->type = PTR_TO_MEM;
break;
case PTR_TO_RDONLY_BUF_OR_NULL:
reg->type = PTR_TO_RDONLY_BUF;
break;
case PTR_TO_RDWR_BUF_OR_NULL:
reg->type = PTR_TO_RDWR_BUF;
break;
default:
WARN_ONCE(1, "unknown nullable register type");
}
}
static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
{
return type_is_pkt_pointer(reg->type);
}
static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
{
return reg_is_pkt_pointer(reg) ||
reg->type == PTR_TO_PACKET_END;
}
/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
enum bpf_reg_type which)
{
/* The register can already have a range from prior markings.
* This is fine as long as it hasn't been advanced from its
* origin.
*/
return reg->type == which &&
reg->id == 0 &&
reg->off == 0 &&
tnum_equals_const(reg->var_off, 0);
}
/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
reg->smin_value = S64_MIN;
reg->smax_value = S64_MAX;
reg->umin_value = 0;
reg->umax_value = U64_MAX;
reg->s32_min_value = S32_MIN;
reg->s32_max_value = S32_MAX;
reg->u32_min_value = 0;
reg->u32_max_value = U32_MAX;
}
static void __mark_reg64_unbounded(struct bpf_reg_state *reg)
{
reg->smin_value = S64_MIN;
reg->smax_value = S64_MAX;
reg->umin_value = 0;
reg->umax_value = U64_MAX;
}
static void __mark_reg32_unbounded(struct bpf_reg_state *reg)
{
reg->s32_min_value = S32_MIN;
reg->s32_max_value = S32_MAX;
reg->u32_min_value = 0;
reg->u32_max_value = U32_MAX;
}
static void __update_reg32_bounds(struct bpf_reg_state *reg)
{
struct tnum var32_off = tnum_subreg(reg->var_off);
/* min signed is max(sign bit) | min(other bits) */
reg->s32_min_value = max_t(s32, reg->s32_min_value,
var32_off.value | (var32_off.mask & S32_MIN));
/* max signed is min(sign bit) | max(other bits) */
reg->s32_max_value = min_t(s32, reg->s32_max_value,
var32_off.value | (var32_off.mask & S32_MAX));
reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value);
reg->u32_max_value = min(reg->u32_max_value,
(u32)(var32_off.value | var32_off.mask));
}
static void __update_reg64_bounds(struct bpf_reg_state *reg)
{
/* min signed is max(sign bit) | min(other bits) */
reg->smin_value = max_t(s64, reg->smin_value,
reg->var_off.value | (reg->var_off.mask & S64_MIN));
/* max signed is min(sign bit) | max(other bits) */
reg->smax_value = min_t(s64, reg->smax_value,
reg->var_off.value | (reg->var_off.mask & S64_MAX));
reg->umin_value = max(reg->umin_value, reg->var_off.value);
reg->umax_value = min(reg->umax_value,
reg->var_off.value | reg->var_off.mask);
}
static void __update_reg_bounds(struct bpf_reg_state *reg)
{
__update_reg32_bounds(reg);
__update_reg64_bounds(reg);
}
/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
{
/* Learn sign from signed bounds.
* If we cannot cross the sign boundary, then signed and unsigned bounds
* are the same, so combine. This works even in the negative case, e.g.
* -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
reg->s32_min_value = reg->u32_min_value =
max_t(u32, reg->s32_min_value, reg->u32_min_value);
reg->s32_max_value = reg->u32_max_value =
min_t(u32, reg->s32_max_value, reg->u32_max_value);
return;
}
/* Learn sign from unsigned bounds. Signed bounds cross the sign
* boundary, so we must be careful.
*/
if ((s32)reg->u32_max_value >= 0) {
/* Positive. We can't learn anything from the smin, but smax
* is positive, hence safe.
*/
reg->s32_min_value = reg->u32_min_value;
reg->s32_max_value = reg->u32_max_value =
min_t(u32, reg->s32_max_value, reg->u32_max_value);
} else if ((s32)reg->u32_min_value < 0) {
/* Negative. We can't learn anything from the smax, but smin
* is negative, hence safe.
*/
reg->s32_min_value = reg->u32_min_value =
max_t(u32, reg->s32_min_value, reg->u32_min_value);
reg->s32_max_value = reg->u32_max_value;
}
}
static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
{
/* Learn sign from signed bounds.
* If we cannot cross the sign boundary, then signed and unsigned bounds
* are the same, so combine. This works even in the negative case, e.g.
* -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
*/
if (reg->smin_value >= 0 || reg->smax_value < 0) {
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
return;
}
/* Learn sign from unsigned bounds. Signed bounds cross the sign
* boundary, so we must be careful.
*/
if ((s64)reg->umax_value >= 0) {
/* Positive. We can't learn anything from the smin, but smax
* is positive, hence safe.
*/
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
reg->umax_value);
} else if ((s64)reg->umin_value < 0) {
/* Negative. We can't learn anything from the smax, but smin
* is negative, hence safe.
*/
reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
reg->umin_value);
reg->smax_value = reg->umax_value;
}
}
static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
__reg32_deduce_bounds(reg);
__reg64_deduce_bounds(reg);
}
/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
struct tnum var64_off = tnum_intersect(reg->var_off,
tnum_range(reg->umin_value,
reg->umax_value));
struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off),
tnum_range(reg->u32_min_value,
reg->u32_max_value));
reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
}
static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
{
reg->umin_value = reg->u32_min_value;
reg->umax_value = reg->u32_max_value;
/* Attempt to pull 32-bit signed bounds into 64-bit bounds
* but must be positive otherwise set to worse case bounds
* and refine later from tnum.
*/
if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
reg->smax_value = reg->s32_max_value;
else
reg->smax_value = U32_MAX;
if (reg->s32_min_value >= 0)
reg->smin_value = reg->s32_min_value;
else
reg->smin_value = 0;
}
static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
{
/* special case when 64-bit register has upper 32-bit register
* zeroed. Typically happens after zext or <<32, >>32 sequence
* allowing us to use 32-bit bounds directly,
*/
if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
__reg_assign_32_into_64(reg);
} else {
/* Otherwise the best we can do is push lower 32bit known and
* unknown bits into register (var_off set from jmp logic)
* then learn as much as possible from the 64-bit tnum
* known and unknown bits. The previous smin/smax bounds are
* invalid here because of jmp32 compare so mark them unknown
* so they do not impact tnum bounds calculation.
*/
__mark_reg64_unbounded(reg);
__update_reg_bounds(reg);
}
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__reg_deduce_bounds(reg);
__reg_bound_offset(reg);
__update_reg_bounds(reg);
}
static bool __reg64_bound_s32(s64 a)
{
return a > S32_MIN && a < S32_MAX;
}
static bool __reg64_bound_u32(u64 a)
{
return a > U32_MIN && a < U32_MAX;
}
static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
{
__mark_reg32_unbounded(reg);
if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
reg->s32_min_value = (s32)reg->smin_value;
reg->s32_max_value = (s32)reg->smax_value;
}
if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
reg->u32_min_value = (u32)reg->umin_value;
reg->u32_max_value = (u32)reg->umax_value;
}
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__reg_deduce_bounds(reg);
__reg_bound_offset(reg);
__update_reg_bounds(reg);
}
/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
/*
* Clear type, id, off, and union(map_ptr, range) and
* padding between 'type' and union
*/
memset(reg, 0, offsetof(struct bpf_reg_state, var_off));
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
reg->precise = env->subprog_cnt > 1 || !env->bpf_capable;
__mark_reg_unbounded(reg);
}
static void mark_reg_unknown(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_unknown(env, regs + regno);
}
static void __mark_reg_not_init(const struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
__mark_reg_unknown(env, reg);
reg->type = NOT_INIT;
}
static void mark_reg_not_init(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno)
{
if (WARN_ON(regno >= MAX_BPF_REG)) {
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
__mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_not_init(env, regs + regno);
}
static void mark_btf_ld_reg(struct bpf_verifier_env *env,
struct bpf_reg_state *regs, u32 regno,
enum bpf_reg_type reg_type,
struct btf *btf, u32 btf_id)
{
if (reg_type == SCALAR_VALUE) {
mark_reg_unknown(env, regs, regno);
return;
}
mark_reg_known_zero(env, regs, regno);
regs[regno].type = PTR_TO_BTF_ID;
regs[regno].btf = btf;
regs[regno].btf_id = btf_id;
}
#define DEF_NOT_SUBREG (0)
static void init_reg_state(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
regs[i].parent = NULL;
regs[i].subreg_def = DEF_NOT_SUBREG;
}
/* frame pointer */
regs[BPF_REG_FP].type = PTR_TO_STACK;
mark_reg_known_zero(env, regs, BPF_REG_FP);
regs[BPF_REG_FP].frameno = state->frameno;
}
#define BPF_MAIN_FUNC (-1)
static void init_func_state(struct bpf_verifier_env *env,
struct bpf_func_state *state,
int callsite, int frameno, int subprogno)
{
state->callsite = callsite;
state->frameno = frameno;
state->subprogno = subprogno;
init_reg_state(env, state);
}
enum reg_arg_type {
SRC_OP, /* register is used as source operand */
DST_OP, /* register is used as destination operand */
DST_OP_NO_MARK /* same as above, check only, don't mark */
};
static int cmp_subprogs(const void *a, const void *b)
{
return ((struct bpf_subprog_info *)a)->start -
((struct bpf_subprog_info *)b)->start;
}
static int find_subprog(struct bpf_verifier_env *env, int off)
{
struct bpf_subprog_info *p;
p = bsearch(&off, env->subprog_info, env->subprog_cnt,
sizeof(env->subprog_info[0]), cmp_subprogs);
if (!p)
return -ENOENT;
return p - env->subprog_info;
}
static int add_subprog(struct bpf_verifier_env *env, int off)
{
int insn_cnt = env->prog->len;
int ret;
if (off >= insn_cnt || off < 0) {
verbose(env, "call to invalid destination\n");
return -EINVAL;
}
ret = find_subprog(env, off);
if (ret >= 0)
return ret;
if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
verbose(env, "too many subprograms\n");
return -E2BIG;
}
/* determine subprog starts. The end is one before the next starts */
env->subprog_info[env->subprog_cnt++].start = off;
sort(env->subprog_info, env->subprog_cnt,
sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
return env->subprog_cnt - 1;
}
struct bpf_kfunc_desc {
struct btf_func_model func_model;
u32 func_id;
s32 imm;
};
#define MAX_KFUNC_DESCS 256
struct bpf_kfunc_desc_tab {
struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS];
u32 nr_descs;
};
static int kfunc_desc_cmp_by_id(const void *a, const void *b)
{
const struct bpf_kfunc_desc *d0 = a;
const struct bpf_kfunc_desc *d1 = b;
/* func_id is not greater than BTF_MAX_TYPE */
return d0->func_id - d1->func_id;
}
static const struct bpf_kfunc_desc *
find_kfunc_desc(const struct bpf_prog *prog, u32 func_id)
{
struct bpf_kfunc_desc desc = {
.func_id = func_id,
};
struct bpf_kfunc_desc_tab *tab;
tab = prog->aux->kfunc_tab;
return bsearch(&desc, tab->descs, tab->nr_descs,
sizeof(tab->descs[0]), kfunc_desc_cmp_by_id);
}
static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
{
const struct btf_type *func, *func_proto;
struct bpf_kfunc_desc_tab *tab;
struct bpf_prog_aux *prog_aux;
struct bpf_kfunc_desc *desc;
const char *func_name;
unsigned long addr;
int err;
prog_aux = env->prog->aux;
tab = prog_aux->kfunc_tab;
if (!tab) {
if (!btf_vmlinux) {
verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n");
return -ENOTSUPP;
}
if (!env->prog->jit_requested) {
verbose(env, "JIT is required for calling kernel function\n");
return -ENOTSUPP;
}
if (!bpf_jit_supports_kfunc_call()) {
verbose(env, "JIT does not support calling kernel function\n");
return -ENOTSUPP;
}
if (!env->prog->gpl_compatible) {
verbose(env, "cannot call kernel function from non-GPL compatible program\n");
return -EINVAL;
}
tab = kzalloc(sizeof(*tab), GFP_KERNEL);
if (!tab)
return -ENOMEM;
prog_aux->kfunc_tab = tab;
}
if (find_kfunc_desc(env->prog, func_id))
return 0;
if (tab->nr_descs == MAX_KFUNC_DESCS) {
verbose(env, "too many different kernel function calls\n");
return -E2BIG;
}
func = btf_type_by_id(btf_vmlinux, func_id);
if (!func || !btf_type_is_func(func)) {
verbose(env, "kernel btf_id %u is not a function\n",
func_id);
return -EINVAL;
}
func_proto = btf_type_by_id(btf_vmlinux, func->type);
if (!func_proto || !btf_type_is_func_proto(func_proto)) {
verbose(env, "kernel function btf_id %u does not have a valid func_proto\n",
func_id);
return -EINVAL;
}
func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
addr = kallsyms_lookup_name(func_name);
if (!addr) {
verbose(env, "cannot find address for kernel function %s\n",
func_name);
return -EINVAL;
}
desc = &tab->descs[tab->nr_descs++];
desc->func_id = func_id;
desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
err = btf_distill_func_proto(&env->log, btf_vmlinux,
func_proto, func_name,
&desc->func_model);
if (!err)
sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
kfunc_desc_cmp_by_id, NULL);
return err;
}
static int kfunc_desc_cmp_by_imm(const void *a, const void *b)
{
const struct bpf_kfunc_desc *d0 = a;
const struct bpf_kfunc_desc *d1 = b;
if (d0->imm > d1->imm)
return 1;
else if (d0->imm < d1->imm)
return -1;
return 0;
}
static void sort_kfunc_descs_by_imm(struct bpf_prog *prog)
{
struct bpf_kfunc_desc_tab *tab;
tab = prog->aux->kfunc_tab;
if (!tab)
return;
sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
kfunc_desc_cmp_by_imm, NULL);
}
bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog)
{
return !!prog->aux->kfunc_tab;
}
const struct btf_func_model *
bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
const struct bpf_insn *insn)
{
const struct bpf_kfunc_desc desc = {
.imm = insn->imm,
};
const struct bpf_kfunc_desc *res;
struct bpf_kfunc_desc_tab *tab;
tab = prog->aux->kfunc_tab;
res = bsearch(&desc, tab->descs, tab->nr_descs,
sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm);
return res ? &res->func_model : NULL;
}
static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
{
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
int i, ret, insn_cnt = env->prog->len;
/* Add entry function. */
ret = add_subprog(env, 0);
if (ret)
return ret;
for (i = 0; i < insn_cnt; i++, insn++) {
if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) &&
!bpf_pseudo_kfunc_call(insn))
continue;
if (!env->bpf_capable) {
verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
return -EPERM;
}
if (bpf_pseudo_func(insn)) {
ret = add_subprog(env, i + insn->imm + 1);
if (ret >= 0)
/* remember subprog */
insn[1].imm = ret;
} else if (bpf_pseudo_call(insn)) {
ret = add_subprog(env, i + insn->imm + 1);
} else {
ret = add_kfunc_call(env, insn->imm);
}
if (ret < 0)
return ret;
}
/* Add a fake 'exit' subprog which could simplify subprog iteration
* logic. 'subprog_cnt' should not be increased.
*/
subprog[env->subprog_cnt].start = insn_cnt;
if (env->log.level & BPF_LOG_LEVEL2)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, subprog[i].start);
return 0;
}
static int check_subprogs(struct bpf_verifier_env *env)
{
int i, subprog_start, subprog_end, off, cur_subprog = 0;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
/* now check that all jumps are within the same subprog */
subprog_start = subprog[cur_subprog].start;
subprog_end = subprog[cur_subprog + 1].start;
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
if (code == (BPF_JMP | BPF_CALL) &&
insn[i].imm == BPF_FUNC_tail_call &&
insn[i].src_reg != BPF_PSEUDO_CALL)
subprog[cur_subprog].has_tail_call = true;
if (BPF_CLASS(code) == BPF_LD &&
(BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
subprog[cur_subprog].has_ld_abs = true;
if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
}
next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
* or unconditional jump back
*/
if (code != (BPF_JMP | BPF_EXIT) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
}
subprog_start = subprog_end;
cur_subprog++;
if (cur_subprog < env->subprog_cnt)
subprog_end = subprog[cur_subprog + 1].start;
}
}
return 0;
}
/* Parentage chain of this register (or stack slot) should take care of all
* issues like callee-saved registers, stack slot allocation time, etc.
*/
static int mark_reg_read(struct bpf_verifier_env *env,
const struct bpf_reg_state *state,
struct bpf_reg_state *parent, u8 flag)
{
bool writes = parent == state->parent; /* Observe write marks */
int cnt = 0;
while (parent) {
/* if read wasn't screened by an earlier write ... */
if (writes && state->live & REG_LIVE_WRITTEN)
break;
if (parent->live & REG_LIVE_DONE) {
verbose(env, "verifier BUG type %s var_off %lld off %d\n",
reg_type_str[parent->type],
parent->var_off.value, parent->off);
return -EFAULT;
}
/* The first condition is more likely to be true than the
* second, checked it first.
*/
if ((parent->live & REG_LIVE_READ) == flag ||
parent->live & REG_LIVE_READ64)
/* The parentage chain never changes and
* this parent was already marked as LIVE_READ.
* There is no need to keep walking the chain again and
* keep re-marking all parents as LIVE_READ.
* This case happens when the same register is read
* multiple times without writes into it in-between.
* Also, if parent has the stronger REG_LIVE_READ64 set,
* then no need to set the weak REG_LIVE_READ32.
*/
break;
/* ... then we depend on parent's value */
parent->live |= flag;
/* REG_LIVE_READ64 overrides REG_LIVE_READ32. */
if (flag == REG_LIVE_READ64)
parent->live &= ~REG_LIVE_READ32;
state = parent;
parent = state->parent;
writes = true;
cnt++;
}
if (env->longest_mark_read_walk < cnt)
env->longest_mark_read_walk = cnt;
return 0;
}
/* This function is supposed to be used by the following 32-bit optimization
* code only. It returns TRUE if the source or destination register operates
* on 64-bit, otherwise return FALSE.
*/
static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t)
{
u8 code, class, op;
code = insn->code;
class = BPF_CLASS(code);
op = BPF_OP(code);
if (class == BPF_JMP) {
/* BPF_EXIT for "main" will reach here. Return TRUE
* conservatively.
*/
if (op == BPF_EXIT)
return true;
if (op == BPF_CALL) {
/* BPF to BPF call will reach here because of marking
* caller saved clobber with DST_OP_NO_MARK for which we
* don't care the register def because they are anyway
* marked as NOT_INIT already.
*/
if (insn->src_reg == BPF_PSEUDO_CALL)
return false;
/* Helper call will reach here because of arg type
* check, conservatively return TRUE.
*/
if (t == SRC_OP)
return true;
return false;
}
}
if (class == BPF_ALU64 || class == BPF_JMP ||
/* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
if (class == BPF_ALU || class == BPF_JMP32)
return false;
if (class == BPF_LDX) {
if (t != SRC_OP)
return BPF_SIZE(code) == BPF_DW;
/* LDX source must be ptr. */
return true;
}
if (class == BPF_STX) {
/* BPF_STX (including atomic variants) has multiple source
* operands, one of which is a ptr. Check whether the caller is
* asking about it.
*/
if (t == SRC_OP && reg->type != SCALAR_VALUE)
return true;
return BPF_SIZE(code) == BPF_DW;
}
if (class == BPF_LD) {
u8 mode = BPF_MODE(code);
/* LD_IMM64 */
if (mode == BPF_IMM)
return true;
/* Both LD_IND and LD_ABS return 32-bit data. */
if (t != SRC_OP)
return false;
/* Implicit ctx ptr. */
if (regno == BPF_REG_6)
return true;
/* Explicit source could be any width. */
return true;
}
if (class == BPF_ST)
/* The only source register for BPF_ST is a ptr. */
return true;
/* Conservatively return true at default. */
return true;
}
/* Return the regno defined by the insn, or -1. */
static int insn_def_regno(const struct bpf_insn *insn)
{
switch (BPF_CLASS(insn->code)) {
case BPF_JMP:
case BPF_JMP32:
case BPF_ST:
return -1;
case BPF_STX:
if (BPF_MODE(insn->code) == BPF_ATOMIC &&
(insn->imm & BPF_FETCH)) {
if (insn->imm == BPF_CMPXCHG)
return BPF_REG_0;
else
return insn->src_reg;
} else {
return -1;
}
default:
return insn->dst_reg;
}
}
/* Return TRUE if INSN has defined any 32-bit value explicitly. */
static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
int dst_reg = insn_def_regno(insn);
if (dst_reg == -1)
return false;
return !is_reg64(env, insn, dst_reg, NULL, DST_OP);
}
static void mark_insn_zext(struct bpf_verifier_env *env,
struct bpf_reg_state *reg)
{
s32 def_idx = reg->subreg_def;
if (def_idx == DEF_NOT_SUBREG)
return;
env->insn_aux_data[def_idx - 1].zext_dst = true;
/* The dst will be zero extended, so won't be sub-register anymore. */
reg->subreg_def = DEF_NOT_SUBREG;
}
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
enum reg_arg_type t)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
struct bpf_reg_state *reg, *regs = state->regs;
bool rw64;
if (regno >= MAX_BPF_REG) {
verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
reg = ®s[regno];
rw64 = is_reg64(env, insn, regno, reg, t);
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
if (reg->type == NOT_INIT) {
verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
/* We don't need to worry about FP liveness because it's read-only */
if (regno == BPF_REG_FP)
return 0;
if (rw64)
mark_insn_zext(env, reg);
return mark_reg_read(env, reg, reg->parent,
rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose(env, "frame pointer is read only\n");
return -EACCES;
}
reg->live |= REG_LIVE_WRITTEN;
reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
return 0;
}
/* for any branch, call, exit record the history of jmps in the given state */
static int push_jmp_history(struct bpf_verifier_env *env,
struct bpf_verifier_state *cur)
{
u32 cnt = cur->jmp_history_cnt;
struct bpf_idx_pair *p;
cnt++;
p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER);
if (!p)
return -ENOMEM;
p[cnt - 1].idx = env->insn_idx;
p[cnt - 1].prev_idx = env->prev_insn_idx;
cur->jmp_history = p;
cur->jmp_history_cnt = cnt;
return 0;
}
/* Backtrack one insn at a time. If idx is not at the top of recorded
* history then previous instruction came from straight line execution.
*/
static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
u32 *history)
{
u32 cnt = *history;
if (cnt && st->jmp_history[cnt - 1].idx == i) {
i = st->jmp_history[cnt - 1].prev_idx;
(*history)--;
} else {
i--;
}
return i;
}
static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
{
const struct btf_type *func;
if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
return NULL;
func = btf_type_by_id(btf_vmlinux, insn->imm);
return btf_name_by_offset(btf_vmlinux, func->name_off);
}
/* For given verifier state backtrack_insn() is called from the last insn to
* the first insn. Its purpose is to compute a bitmask of registers and
* stack slots that needs precision in the parent verifier state.
*/
static int backtrack_insn(struct bpf_verifier_env *env, int idx,
u32 *reg_mask, u64 *stack_mask)
{
const struct bpf_insn_cbs cbs = {
.cb_call = disasm_kfunc_name,
.cb_print = verbose,
.private_data = env,
};
struct bpf_insn *insn = env->prog->insnsi + idx;
u8 class = BPF_CLASS(insn->code);
u8 opcode = BPF_OP(insn->code);
u8 mode = BPF_MODE(insn->code);
u32 dreg = 1u << insn->dst_reg;
u32 sreg = 1u << insn->src_reg;
u32 spi;
if (insn->code == 0)
return 0;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
verbose(env, "%d: ", idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
if (class == BPF_ALU || class == BPF_ALU64) {
if (!(*reg_mask & dreg))
return 0;
if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
/* dreg = sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
*reg_mask &= ~dreg;
*reg_mask |= sreg;
} else {
/* dreg = K
* dreg needs precision after this insn.
* Corresponding register is already marked
* as precise=true in this verifier state.
* No further markings in parent are necessary
*/
*reg_mask &= ~dreg;
}
} else {
if (BPF_SRC(insn->code) == BPF_X) {
/* dreg += sreg
* both dreg and sreg need precision
* before this insn
*/
*reg_mask |= sreg;
} /* else dreg += K
* dreg still needs precision before this insn
*/
}
} else if (class == BPF_LDX) {
if (!(*reg_mask & dreg))
return 0;
*reg_mask &= ~dreg;
/* scalars can only be spilled into stack w/o losing precision.
* Load from any other memory can be zero extended.
* The desire to keep that precision is already indicated
* by 'precise' mark in corresponding register of this state.
* No further tracking necessary.
*/
if (insn->src_reg != BPF_REG_FP)
return 0;
if (BPF_SIZE(insn->code) != BPF_DW)
return 0;
/* dreg = *(u64 *)[fp - off] was a fill from the stack.
* that [fp - off] slot contains scalar that needs to be
* tracked with precision
*/
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
*stack_mask |= 1ull << spi;
} else if (class == BPF_STX || class == BPF_ST) {
if (*reg_mask & dreg)
/* stx & st shouldn't be using _scalar_ dst_reg
* to access memory. It means backtracking
* encountered a case of pointer subtraction.
*/
return -ENOTSUPP;
/* scalars can only be spilled into stack */
if (insn->dst_reg != BPF_REG_FP)
return 0;
if (BPF_SIZE(insn->code) != BPF_DW)
return 0;
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
if (!(*stack_mask & (1ull << spi)))
return 0;
*stack_mask &= ~(1ull << spi);
if (class == BPF_STX)
*reg_mask |= sreg;
} else if (class == BPF_JMP || class == BPF_JMP32) {
if (opcode == BPF_CALL) {
if (insn->src_reg == BPF_PSEUDO_CALL)
return -ENOTSUPP;
/* regular helper call sets R0 */
*reg_mask &= ~1;
if (*reg_mask & 0x3f) {
/* if backtracing was looking for registers R1-R5
* they should have been found already.
*/
verbose(env, "BUG regs %x\n", *reg_mask);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
} else if (opcode == BPF_EXIT) {
return -ENOTSUPP;
}
} else if (class == BPF_LD) {
if (!(*reg_mask & dreg))
return 0;
*reg_mask &= ~dreg;
/* It's ld_imm64 or ld_abs or ld_ind.
* For ld_imm64 no further tracking of precision
* into parent is necessary
*/
if (mode == BPF_IND || mode == BPF_ABS)
/* to be analyzed */
return -ENOTSUPP;
}
return 0;
}
/* the scalar precision tracking algorithm:
* . at the start all registers have precise=false.
* . scalar ranges are tracked as normal through alu and jmp insns.
* . once precise value of the scalar register is used in:
* . ptr + scalar alu
* . if (scalar cond K|scalar)
* . helper_call(.., scalar, ...) where ARG_CONST is expected
* backtrack through the verifier states and mark all registers and
* stack slots with spilled constants that these scalar regisers
* should be precise.
* . during state pruning two registers (or spilled stack slots)
* are equivalent if both are not precise.
*
* Note the verifier cannot simply walk register parentage chain,
* since many different registers and stack slots could have been
* used to compute single precise scalar.
*
* The approach of starting with precise=true for all registers and then
* backtrack to mark a register as not precise when the verifier detects
* that program doesn't care about specific value (e.g., when helper
* takes register as ARG_ANYTHING parameter) is not safe.
*
* It's ok to walk single parentage chain of the verifier states.
* It's possible that this backtracking will go all the way till 1st insn.
* All other branches will be explored for needing precision later.
*
* The backtracking needs to deal with cases like:
* R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0)
* r9 -= r8
* r5 = r9
* if r5 > 0x79f goto pc+7
* R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff))
* r5 += 1
* ...
* call bpf_perf_event_output#25
* where .arg5_type = ARG_CONST_SIZE_OR_ZERO
*
* and this case:
* r6 = 1
* call foo // uses callee's r6 inside to compute r0
* r0 += r6
* if r0 == 0 goto
*
* to track above reg_mask/stack_mask needs to be independent for each frame.
*
* Also if parent's curframe > frame where backtracking started,
* the verifier need to mark registers in both frames, otherwise callees
* may incorrectly prune callers. This is similar to
* commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences")
*
* For now backtracking falls back into conservative marking.
*/
static void mark_all_scalars_precise(struct bpf_verifier_env *env,
struct bpf_verifier_state *st)
{
struct bpf_func_state *func;
struct bpf_reg_state *reg;
int i, j;
/* big hammer: mark all scalars precise in this path.
* pop_stack may still get !precise scalars.
*/
for (; st; st = st->parent)
for (i = 0; i <= st->curframe; i++) {
func = st->frame[i];
for (j = 0; j < BPF_REG_FP; j++) {
reg = &func->regs[j];
if (reg->type != SCALAR_VALUE)
continue;
reg->precise = true;
}
for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
if (func->stack[j].slot_type[0] != STACK_SPILL)
continue;
reg = &func->stack[j].spilled_ptr;
if (reg->type != SCALAR_VALUE)
continue;
reg->precise = true;
}
}
}
static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
int spi)
{
struct bpf_verifier_state *st = env->cur_state;
int first_idx = st->first_insn_idx;
int last_idx = env->insn_idx;
struct bpf_func_state *func;
struct bpf_reg_state *reg;
u32 reg_mask = regno >= 0 ? 1u << regno : 0;
u64 stack_mask = spi >= 0 ? 1ull << spi : 0;
bool skip_first = true;
bool new_marks = false;
int i, err;
if (!env->bpf_capable)
return 0;
func = st->frame[st->curframe];
if (regno >= 0) {
reg = &func->regs[regno];
if (reg->type != SCALAR_VALUE) {
WARN_ONCE(1, "backtracing misuse");
return -EFAULT;
}
if (!reg->precise)
new_marks = true;
else
reg_mask = 0;
reg->precise = true;
}
while (spi >= 0) {
if (func->stack[spi].slot_type[0] != STACK_SPILL) {
stack_mask = 0;
break;
}
reg = &func->stack[spi].spilled_ptr;
if (reg->type != SCALAR_VALUE) {
stack_mask = 0;
break;
}
if (!reg->precise)
new_marks = true;
else
stack_mask = 0;
reg->precise = true;
break;
}
if (!new_marks)
return 0;
if (!reg_mask && !stack_mask)
return 0;
for (;;) {
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
if (env->log.level & BPF_LOG_LEVEL)
verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
for (i = last_idx;;) {
if (skip_first) {
err = 0;
skip_first = false;
} else {
err = backtrack_insn(env, i, ®_mask, &stack_mask);
}
if (err == -ENOTSUPP) {
mark_all_scalars_precise(env, st);
return 0;
} else if (err) {
return err;
}
if (!reg_mask && !stack_mask)
/* Found assignment(s) into tracked register in this state.
* Since this state is already marked, just return.
* Nothing to be tracked further in the parent state.
*/
return 0;
if (i == first_idx)
break;
i = get_prev_insn_idx(st, i, &history);
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
* and there are still reg_mask or stack_mask
* to backtrack.
* It means the backtracking missed the spot where
* particular register was initialized with a constant.
*/
verbose(env, "BUG backtracking idx %d\n", i);
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
}
st = st->parent;
if (!st)
break;
new_marks = false;
func = st->frame[st->curframe];
bitmap_from_u64(mask, reg_mask);
for_each_set_bit(i, mask, 32) {
reg = &func->regs[i];
if (reg->type != SCALAR_VALUE) {
reg_mask &= ~(1u << i);
continue;
}
if (!reg->precise)
new_marks = true;
reg->precise = true;
}
bitmap_from_u64(mask, stack_mask);
for_each_set_bit(i, mask, 64) {
if (i >= func->allocated_stack / BPF_REG_SIZE) {
/* the sequence of instructions:
* 2: (bf) r3 = r10
* 3: (7b) *(u64 *)(r3 -8) = r0
* 4: (79) r4 = *(u64 *)(r10 -8)
* doesn't contain jmps. It's backtracked
* as a single block.
* During backtracking insn 3 is not recognized as
* stack access, so at the end of backtracking
* stack slot fp-8 is still marked in stack_mask.
* However the parent state may not have accessed
* fp-8 and it's "unallocated" stack space.
* In such case fallback to conservative.
*/
mark_all_scalars_precise(env, st);
return 0;
}
if (func->stack[i].slot_type[0] != STACK_SPILL) {
stack_mask &= ~(1ull << i);
continue;
}
reg = &func->stack[i].spilled_ptr;
if (reg->type != SCALAR_VALUE) {
stack_mask &= ~(1ull << i);
continue;
}
if (!reg->precise)
new_marks = true;
reg->precise = true;
}
if (env->log.level & BPF_LOG_LEVEL) {
print_verifier_state(env, func);
verbose(env, "parent %s regs=%x stack=%llx marks\n",
new_marks ? "didn't have" : "already had",
reg_mask, stack_mask);
}
if (!reg_mask && !stack_mask)
break;
if (!new_marks)
break;
last_idx = st->last_insn_idx;
first_idx = st->first_insn_idx;
}
return 0;
}
static int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
return __mark_chain_precision(env, regno, -1);
}
static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi)
{
return __mark_chain_precision(env, -1, spi);
}
static bool is_spillable_regtype(enum bpf_reg_type type)
{
switch (type) {
case PTR_TO_MAP_VALUE:
case PTR_TO_MAP_VALUE_OR_NULL:
case PTR_TO_STACK:
case PTR_TO_CTX:
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
case PTR_TO_FLOW_KEYS:
case CONST_PTR_TO_MAP:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
case PTR_TO_BTF_ID_OR_NULL:
case PTR_TO_RDONLY_BUF:
case PTR_TO_RDONLY_BUF_OR_NULL:
case PTR_TO_RDWR_BUF:
case PTR_TO_RDWR_BUF_OR_NULL:
case PTR_TO_PERCPU_BTF_ID:
case PTR_TO_MEM:
case PTR_TO_MEM_OR_NULL:
case PTR_TO_FUNC:
case PTR_TO_MAP_KEY:
return true;
default:
return false;
}
}
/* Does this register contain a constant zero? */
static bool register_is_null(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}
static bool register_is_const(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
}
static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
{
return tnum_is_unknown(reg->var_off) &&
reg->smin_value == S64_MIN && reg->smax_value == S64_MAX &&
reg->umin_value == 0 && reg->umax_value == U64_MAX &&
reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX &&
reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX;
}
static bool register_is_bounded(struct bpf_reg_state *reg)
{
return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg);
}
static bool __is_pointer_value(bool allow_ptr_leaks,
const struct bpf_reg_state *reg)
{
if (allow_ptr_leaks)
return false;
return reg->type != SCALAR_VALUE;
}
static void save_register_state(struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg)
{
int i;
state->stack[spi].spilled_ptr = *reg;
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack[spi].slot_type[i] = STACK_SPILL;
}
/* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
/* stack frame we're writing to */
struct bpf_func_state *state,
int off, int size, int value_regno,
int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg;
struct bpf_reg_state *reg = NULL;
err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
state->acquired_refs, true);
if (err)
return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
if (!env->allow_ptr_leaks &&
state->stack[spi].slot_type[0] == STACK_SPILL &&
size != BPF_REG_SIZE) {
verbose(env, "attempt to corrupt spilled pointer on stack\n");
return -EACCES;
}
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
if (dst_reg != BPF_REG_FP) {
/* The backtracking logic can only recognize explicit
* stack slot address like [fp - 8]. Other spill of
* scalar via different register has to be conervative.
* Backtrack from here and mark all registers as precise
* that contributed into 'reg' being a constant.
*/
err = mark_chain_precision(env, value_regno);
if (err)
return err;
}
save_register_state(state, spi, reg);
} else if (reg && is_spillable_regtype(reg->type)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
verbose_linfo(env, insn_idx, "; ");
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
if (!env->bypass_spec_v4) {
bool sanitize = false;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
register_is_const(&state->stack[spi].spilled_ptr))
sanitize = true;
for (i = 0; i < BPF_REG_SIZE; i++)
if (state->stack[spi].slot_type[i] == STACK_MISC) {
sanitize = true;
break;
}
if (sanitize) {
int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
int soff = (-spi - 1) * BPF_REG_SIZE;
/* detected reuse of integer stack slot with a pointer
* which means either llvm is reusing stack slot or
* an attacker is trying to exploit CVE-2018-3639
* (speculative store bypass)
* Have to sanitize that slot with preemptive
* store of zero.
*/
if (*poff && *poff != soff) {
/* disallow programs where single insn stores
* into two different stack slots, since verifier
* cannot sanitize them
*/
verbose(env,
"insn %d cannot access two stack slots fp%d and fp%d",
insn_idx, *poff, soff);
return -EINVAL;
}
*poff = soff;
}
}
save_register_state(state, spi, reg);
} else {
u8 type = STACK_MISC;
/* regular write of data into stack destroys any spilled ptr */
state->stack[spi].spilled_ptr.type = NOT_INIT;
/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
if (state->stack[spi].slot_type[0] == STACK_SPILL)
for (i = 0; i < BPF_REG_SIZE; i++)
state->stack[spi].slot_type[i] = STACK_MISC;
/* only mark the slot as written if all 8 bytes were written
* otherwise read propagation may incorrectly stop too soon
* when stack slots are partially written.
* This heuristic means that read propagation will be
* conservative, since it will add reg_live_read marks
* to stack slots all the way to first state when programs
* writes+reads less than 8 bytes
*/
if (size == BPF_REG_SIZE)
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
/* when we zero initialize stack slots mark them as such */
if (reg && register_is_null(reg)) {
/* backtracking doesn't work for STACK_ZERO yet. */
err = mark_chain_precision(env, value_regno);
if (err)
return err;
type = STACK_ZERO;
}
/* Mark slots affected by this stack write. */
for (i = 0; i < size; i++)
state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
type;
}
return 0;
}
/* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is
* known to contain a variable offset.
* This function checks whether the write is permitted and conservatively
* tracks the effects of the write, considering that each stack slot in the
* dynamic range is potentially written to.
*
* 'off' includes 'regno->off'.
* 'value_regno' can be -1, meaning that an unknown value is being written to
* the stack.
*
* Spilled pointers in range are not marked as written because we don't know
* what's going to be actually written. This means that read propagation for
* future reads cannot be terminated by this write.
*
* For privileged programs, uninitialized stack slots are considered
* initialized by this write (even though we don't know exactly what offsets
* are going to be written to). The idea is that we don't want the verifier to
* reject future reads that access slots written to through variable offsets.
*/
static int check_stack_write_var_off(struct bpf_verifier_env *env,
/* func where register points to */
struct bpf_func_state *state,
int ptr_regno, int off, int size,
int value_regno, int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int min_off, max_off;
int i, err;
struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL;
bool writing_zero = false;
/* set if the fact that we're writing a zero is used to let any
* stack slots remain STACK_ZERO
*/
bool zero_used = false;
cur = env->cur_state->frame[env->cur_state->curframe];
ptr_reg = &cur->regs[ptr_regno];
min_off = ptr_reg->smin_value + off;
max_off = ptr_reg->smax_value + off + size;
if (value_regno >= 0)
value_reg = &cur->regs[value_regno];
if (value_reg && register_is_null(value_reg))
writing_zero = true;
err = realloc_func_state(state, round_up(-min_off, BPF_REG_SIZE),
state->acquired_refs, true);
if (err)
return err;
/* Variable offset writes destroy any spilled pointers in range. */
for (i = min_off; i < max_off; i++) {
u8 new_type, *stype;
int slot, spi;
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
if (!env->allow_ptr_leaks
&& *stype != NOT_INIT
&& *stype != SCALAR_VALUE) {
/* Reject the write if there's are spilled pointers in
* range. If we didn't reject here, the ptr status
* would be erased below (even though not all slots are
* actually overwritten), possibly opening the door to
* leaks.
*/
verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d",
insn_idx, i);
return -EINVAL;
}
/* Erase all spilled pointers. */
state->stack[spi].spilled_ptr.type = NOT_INIT;
/* Update the slot type. */
new_type = STACK_MISC;
if (writing_zero && *stype == STACK_ZERO) {
new_type = STACK_ZERO;
zero_used = true;
}
/* If the slot is STACK_INVALID, we check whether it's OK to
* pretend that it will be initialized by this write. The slot
* might not actually be written to, and so if we mark it as
* initialized future reads might leak uninitialized memory.
* For privileged programs, we will accept such reads to slots
* that may or may not be written because, if we're reject
* them, the error would be too confusing.
*/
if (*stype == STACK_INVALID && !env->allow_uninit_stack) {
verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d",
insn_idx, i);
return -EINVAL;
}
*stype = new_type;
}
if (zero_used) {
/* backtracking doesn't work for STACK_ZERO yet. */
err = mark_chain_precision(env, value_regno);
if (err)
return err;
}
return 0;
}
/* When register 'dst_regno' is assigned some values from stack[min_off,
* max_off), we set the register's type according to the types of the
* respective stack slots. If all the stack values are known to be zeros, then
* so is the destination reg. Otherwise, the register is considered to be
* SCALAR. This function does not deal with register filling; the caller must
* ensure that all spilled registers in the stack range have been marked as
* read.
*/
static void mark_reg_stack_read(struct bpf_verifier_env *env,
/* func where src register points to */
struct bpf_func_state *ptr_state,
int min_off, int max_off, int dst_regno)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
int i, slot, spi;
u8 *stype;
int zeros = 0;
for (i = min_off; i < max_off; i++) {
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
stype = ptr_state->stack[spi].slot_type;
if (stype[slot % BPF_REG_SIZE] != STACK_ZERO)
break;
zeros++;
}
if (zeros == max_off - min_off) {
/* any access_size read into register is zero extended,
* so the whole register == const_zero
*/
__mark_reg_const_zero(&state->regs[dst_regno]);
/* backtracking doesn't support STACK_ZERO yet,
* so mark it precise here, so that later
* backtracking can stop here.
* Backtracking may not need this if this register
* doesn't participate in pointer adjustment.
* Forward propagation of precise flag is not
* necessary either. This mark is only to stop
* backtracking. Any register that contributed
* to const 0 was marked precise before spill.
*/
state->regs[dst_regno].precise = true;
} else {
/* have read misc data from the stack */
mark_reg_unknown(env, state->regs, dst_regno);
}
state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
}
/* Read the stack at 'off' and put the results into the register indicated by
* 'dst_regno'. It handles reg filling if the addressed stack slot is a
* spilled reg.
*
* 'dst_regno' can be -1, meaning that the read value is not going to a
* register.
*
* The access is assumed to be within the current stack bounds.
*/
static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
/* func where src register points to */
struct bpf_func_state *reg_state,
int off, int size, int dst_regno)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
struct bpf_reg_state *reg;
u8 *stype;
stype = reg_state->stack[spi].slot_type;
reg = ®_state->stack[spi].spilled_ptr;
if (stype[0] == STACK_SPILL) {
if (size != BPF_REG_SIZE) {
if (reg->type != SCALAR_VALUE) {
verbose_linfo(env, env->insn_idx, "; ");
verbose(env, "invalid size of register fill\n");
return -EACCES;
}
if (dst_regno >= 0) {
mark_reg_unknown(env, state->regs, dst_regno);
state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
}
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
return 0;
}
for (i = 1; i < BPF_REG_SIZE; i++) {
if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
verbose(env, "corrupted spill memory\n");
return -EACCES;
}
}
if (dst_regno >= 0) {
/* restore register state from stack */
state->regs[dst_regno] = *reg;
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
*/
state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
} else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
/* If dst_regno==-1, the caller is asking us whether
* it is acceptable to use this value as a SCALAR_VALUE
* (e.g. for XADD).
* We must not allow unprivileged callers to do that
* with spilled pointers.
*/
verbose(env, "leaking pointer from stack off %d\n",
off);
return -EACCES;
}
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
} else {
u8 type;
for (i = 0; i < size; i++) {
type = stype[(slot - i) % BPF_REG_SIZE];
if (type == STACK_MISC)
continue;
if (type == STACK_ZERO)
continue;
verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
if (dst_regno >= 0)
mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
}
return 0;
}
enum stack_access_src {
ACCESS_DIRECT = 1, /* the access is performed by an instruction */
ACCESS_HELPER = 2, /* the access is performed by a helper */
};
static int check_stack_range_initialized(struct bpf_verifier_env *env,
int regno, int off, int access_size,
bool zero_size_allowed,
enum stack_access_src type,
struct bpf_call_arg_meta *meta);
static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
{
return cur_regs(env) + regno;
}
/* Read the stack at 'ptr_regno + off' and put the result into the register
* 'dst_regno'.
* 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'),
* but not its variable offset.
* 'size' is assumed to be <= reg size and the access is assumed to be aligned.
*
* As opposed to check_stack_read_fixed_off, this function doesn't deal with
* filling registers (i.e. reads of spilled register cannot be detected when
* the offset is not fixed). We conservatively mark 'dst_regno' as containing
* SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable
* offset; for a fixed offset check_stack_read_fixed_off should be used
* instead.
*/
static int check_stack_read_var_off(struct bpf_verifier_env *env,
int ptr_regno, int off, int size, int dst_regno)
{
/* The state of the source register. */
struct bpf_reg_state *reg = reg_state(env, ptr_regno);
struct bpf_func_state *ptr_state = func(env, reg);
int err;
int min_off, max_off;
/* Note that we pass a NULL meta, so raw access will not be permitted.
*/
err = check_stack_range_initialized(env, ptr_regno, off, size,
false, ACCESS_DIRECT, NULL);
if (err)
return err;
min_off = reg->smin_value + off;
max_off = reg->smax_value + off;
mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno);
return 0;
}
/* check_stack_read dispatches to check_stack_read_fixed_off or
* check_stack_read_var_off.
*
* The caller must ensure that the offset falls within the allocated stack
* bounds.
*
* 'dst_regno' is a register which will receive the value from the stack. It
* can be -1, meaning that the read value is not going to a register.
*/
static int check_stack_read(struct bpf_verifier_env *env,
int ptr_regno, int off, int size,
int dst_regno)
{
struct bpf_reg_state *reg = reg_state(env, ptr_regno);
struct bpf_func_state *state = func(env, reg);
int err;
/* Some accesses are only permitted with a static offset. */
bool var_off = !tnum_is_const(reg->var_off);
/* The offset is required to be static when reads don't go to a
* register, in order to not leak pointers (see
* check_stack_read_fixed_off).
*/
if (dst_regno < 0 && var_off) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n",
tn_buf, off, size);
return -EACCES;
}
/* Variable offset is prohibited for unprivileged mode for simplicity
* since it requires corresponding support in Spectre masking for stack
* ALU. See also retrieve_ptr_limit().
*/
if (!env->bypass_spec_v1 && var_off) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n",
ptr_regno, tn_buf);
return -EACCES;
}
if (!var_off) {
off += reg->var_off.value;
err = check_stack_read_fixed_off(env, state, off, size,
dst_regno);
} else {
/* Variable offset stack reads need more conservative handling
* than fixed offset ones. Note that dst_regno >= 0 on this
* branch.
*/
err = check_stack_read_var_off(env, ptr_regno, off, size,
dst_regno);
}
return err;
}
/* check_stack_write dispatches to check_stack_write_fixed_off or
* check_stack_write_var_off.
*
* 'ptr_regno' is the register used as a pointer into the stack.
* 'off' includes 'ptr_regno->off', but not its variable offset (if any).
* 'value_regno' is the register whose value we're writing to the stack. It can
* be -1, meaning that we're not writing from a register.
*
* The caller must ensure that the offset falls within the maximum stack size.
*/
static int check_stack_write(struct bpf_verifier_env *env,
int ptr_regno, int off, int size,
int value_regno, int insn_idx)
{
struct bpf_reg_state *reg = reg_state(env, ptr_regno);
struct bpf_func_state *state = func(env, reg);
int err;
if (tnum_is_const(reg->var_off)) {
off += reg->var_off.value;
err = check_stack_write_fixed_off(env, state, off, size,
value_regno, insn_idx);
} else {
/* Variable offset stack reads need more conservative handling
* than fixed offset ones.
*/
err = check_stack_write_var_off(env, state,
ptr_regno, off, size,
value_regno, insn_idx);
}
return err;
}
static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
int off, int size, enum bpf_access_type type)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_map *map = regs[regno].map_ptr;
u32 cap = bpf_map_flags_to_cap(map);
if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
return 0;
}
/* check read/write into memory region (e.g., map value, ringbuf sample, etc) */
static int __check_mem_access(struct bpf_verifier_env *env, int regno,
int off, int size, u32 mem_size,
bool zero_size_allowed)
{
bool size_ok = size > 0 || (size == 0 && zero_size_allowed);
struct bpf_reg_state *reg;
if (off >= 0 && size_ok && (u64)off + size <= mem_size)
return 0;
reg = &cur_regs(env)[regno];
switch (reg->type) {
case PTR_TO_MAP_KEY:
verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n",
mem_size, off, size);
break;
case PTR_TO_MAP_VALUE:
verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
mem_size, off, size);
break;
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
off, size, regno, reg->id, off, mem_size);
break;
case PTR_TO_MEM:
default:
verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n",
mem_size, off, size);
}
return -EACCES;
}
/* check read/write into a memory region with possible variable offset */
static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, u32 mem_size,
bool zero_size_allowed)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regno];
int err;
/* We may have adjusted the register pointing to memory region, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, state);
/* The minimum value is only important with signed
* comparisons where we can't assume the floor of a
* value is 0. If we are using signed variables for our
* index'es we need to make sure that whatever we use
* will have a set floor within our range.
*/
if (reg->smin_value < 0 &&
(reg->smin_value == S64_MIN ||
(off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) ||
reg->smin_value + off < 0)) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
err = __check_mem_access(env, regno, reg->smin_value + off, size,
mem_size, zero_size_allowed);
if (err) {
verbose(env, "R%d min value is outside of the allowed memory range\n",
regno);
return err;
}
/* If we haven't set a max value then we need to bail since we can't be
* sure we won't do bad things.
* If reg->umax_value + off could overflow, treat that as unbounded too.
*/
if (reg->umax_value >= BPF_MAX_VAR_OFF) {
verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n",
regno);
return -EACCES;
}
err = __check_mem_access(env, regno, reg->umax_value + off, size,
mem_size, zero_size_allowed);
if (err) {
verbose(env, "R%d max value is outside of the allowed memory range\n",
regno);
return err;
}
return 0;
}
/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, u32 regno,
int off, int size, bool zero_size_allowed)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regno];
struct bpf_map *map = reg->map_ptr;
int err;
err = check_mem_region_access(env, regno, off, size, map->value_size,
zero_size_allowed);
if (err)
return err;
if (map_value_has_spin_lock(map)) {
u32 lock = map->spin_lock_off;
/* if any part of struct bpf_spin_lock can be touched by
* load/store reject this program.
* To check that [x1, x2) overlaps with [y1, y2)
* it is sufficient to check x1 < y2 && y1 < x2.
*/
if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) &&
lock < reg->umax_value + off + size) {
verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n");
return -EACCES;
}
}
return err;
}
#define MAX_PACKET_OFF 0xffff
static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
{
return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
}
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_access_type t)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
switch (prog_type) {
/* Program types only with direct read access go here! */
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
fallthrough;
/* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_LWT_XMIT:
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
if (meta)
return meta->pkt_access;
env->seen_direct_write = true;
return true;
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
if (t == BPF_WRITE)
env->seen_direct_write = true;
return true;
default:
return false;
}
}
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = ®s[regno];
int err;
/* We may have added a variable offset to the packet pointer; but any
* reg->range we have comes after that. We are only checking the fixed
* offset.
*/
/* We don't allow negative numbers, because we aren't tracking enough
* detail to prove they're safe.
*/
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
err = reg->range < 0 ? -EINVAL :
__check_mem_access(env, regno, off, size, reg->range,
zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
/* __check_mem_access has made sure "off + size - 1" is within u16.
* reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
* otherwise find_good_pkt_pointers would have refused to set range info
* that __check_mem_access would have rejected this pkt access.
* Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
*/
env->prog->aux->max_pkt_offset =
max_t(u32, env->prog->aux->max_pkt_offset,
off + reg->umax_value + size - 1);
return err;
}
/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
enum bpf_access_type t, enum bpf_reg_type *reg_type,
struct btf **btf, u32 *btf_id)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
.log = &env->log,
};
if (env->ops->is_valid_access &&
env->ops->is_valid_access(off, size, t, env->prog, &info)) {
/* A non zero info.ctx_field_size indicates that this field is a
* candidate for later verifier transformation to load the whole
* field and then apply a mask when accessed with a narrower
* access than actual ctx access size. A zero info.ctx_field_size
* will only allow for whole field access and rejects any other
* type of narrower access.
*/
*reg_type = info.reg_type;
if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
*btf = info.btf;
*btf_id = info.btf_id;
} else {
env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
}
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
return 0;
}
verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
return -EACCES;
}
static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
int size)
{
if (size < 0 || off < 0 ||
(u64)off + size > sizeof(struct bpf_flow_keys)) {
verbose(env, "invalid access to flow keys off=%d size=%d\n",
off, size);
return -EACCES;
}
return 0;
}
static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
u32 regno, int off, int size,
enum bpf_access_type t)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = ®s[regno];
struct bpf_insn_access_aux info = {};
bool valid;
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
regno);
return -EACCES;
}
switch (reg->type) {
case PTR_TO_SOCK_COMMON:
valid = bpf_sock_common_is_valid_access(off, size, t, &info);
break;
case PTR_TO_SOCKET:
valid = bpf_sock_is_valid_access(off, size, t, &info);
break;
case PTR_TO_TCP_SOCK:
valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
break;
case PTR_TO_XDP_SOCK:
valid = bpf_xdp_sock_is_valid_access(off, size, t, &info);
break;
default:
valid = false;
}
if (valid) {
env->insn_aux_data[insn_idx].ctx_field_size =
info.ctx_field_size;
return 0;
}
verbose(env, "R%d invalid %s access off=%d size=%d\n",
regno, reg_type_str[reg->type], off, size);
return -EACCES;
}
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
}
static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return reg->type == PTR_TO_CTX;
}
static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return type_is_sk_pointer(reg->type);
}
static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
return type_is_pkt_pointer(reg->type);
}
static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
{
const struct bpf_reg_state *reg = reg_state(env, regno);
/* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */
return reg->type == PTR_TO_FLOW_KEYS;
}
static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int off, int size, bool strict)
{
struct tnum reg_off;
int ip_align;
/* Byte size accesses are always allowed. */
if (!strict || size == 1)
return 0;
/* For platforms that do not have a Kconfig enabling
* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
* NET_IP_ALIGN is universally set to '2'. And on platforms
* that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
* to this code only in strict mode where we want to emulate
* the NET_IP_ALIGN==2 checking. Therefore use an
* unconditional IP align value of '2'.
*/
ip_align = 2;
reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off));
if (!tnum_is_aligned(reg_off, size)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env,
"misaligned packet access off %d+%s+%d+%d size %d\n",
ip_align, tn_buf, reg->off, off, size);
return -EACCES;
}
return 0;
}
static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
const char *pointer_desc,
int off, int size, bool strict)
{
struct tnum reg_off;
/* Byte size accesses are always allowed. */
if (!strict || size == 1)
return 0;
reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off));
if (!tnum_is_aligned(reg_off, size)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
pointer_desc, tn_buf, reg->off, off, size);
return -EACCES;
}
return 0;
}
static int check_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int off,
int size, bool strict_alignment_once)
{
bool strict = env->strict_alignment || strict_alignment_once;
const char *pointer_desc = "";
switch (reg->type) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
/* Special case, because of NET_IP_ALIGN. Given metadata sits
* right in front, treat it the very same way.
*/
return check_pkt_ptr_alignment(env, reg, off, size, strict);
case PTR_TO_FLOW_KEYS:
pointer_desc = "flow keys ";
break;
case PTR_TO_MAP_KEY:
pointer_desc = "key ";
break;
case PTR_TO_MAP_VALUE:
pointer_desc = "value ";
break;
case PTR_TO_CTX:
pointer_desc = "context ";
break;
case PTR_TO_STACK:
pointer_desc = "stack ";
/* The stack spill tracking logic in check_stack_write_fixed_off()
* and check_stack_read_fixed_off() relies on stack accesses being
* aligned.
*/
strict = true;
break;
case PTR_TO_SOCKET:
pointer_desc = "sock ";
break;
case PTR_TO_SOCK_COMMON:
pointer_desc = "sock_common ";
break;
case PTR_TO_TCP_SOCK:
pointer_desc = "tcp_sock ";
break;
case PTR_TO_XDP_SOCK:
pointer_desc = "xdp_sock ";
break;
default:
break;
}
return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
strict);
}
static int update_stack_depth(struct bpf_verifier_env *env,
const struct bpf_func_state *func,
int off)
{
u16 stack = env->subprog_info[func->subprogno].stack_depth;
if (stack >= -off)
return 0;
/* update known max for given subprogram */
env->subprog_info[func->subprogno].stack_depth = -off;
return 0;
}
/* starting from main bpf function walk all instructions of the function
* and recursively walk all callees that given function can call.
* Ignore jump and exit insns.
* Since recursion is prevented by check_cfg() this algorithm
* only needs a local stack of MAX_CALL_FRAMES to remember callsites
*/
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
bool tail_call_reachable = false;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
int j;
process_func:
/* protect against potential stack overflow that might happen when
* bpf2bpf calls get combined with tailcalls. Limit the caller's stack
* depth for such case down to 256 so that the worst case scenario
* would result in 8k stack size (32 which is tailcall limit * 256 =
* 8k).
*
* To get the idea what might happen, see an example:
* func1 -> sub rsp, 128
* subfunc1 -> sub rsp, 256
* tailcall1 -> add rsp, 256
* func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
* subfunc2 -> sub rsp, 64
* subfunc22 -> sub rsp, 128
* tailcall2 -> add rsp, 128
* func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
*
* tailcall will unwind the current stack frame but it will not get rid
* of caller's stack as shown on the example above.
*/
if (idx && subprog[idx].has_tail_call && depth >= 256) {
verbose(env,
"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
depth);
return -EACCES;
}
/* round up to 32-bytes, since this is granularity
* of interpreter stack size
*/
depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
if (depth > MAX_BPF_STACK) {
verbose(env, "combined stack size of %d calls is %d. Too large\n",
frame + 1, depth);
return -EACCES;
}
continue_func:
subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
/* remember insn and function to return to */
ret_insn[frame] = i + 1;
ret_prog[frame] = idx;
/* find the callee */
i = i + insn[i].imm + 1;
idx = find_subprog(env, i);
if (idx < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i);
return -EFAULT;
}
if (subprog[idx].has_tail_call)
tail_call_reachable = true;
frame++;
if (frame >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep !\n",
frame);
return -E2BIG;
}
goto process_func;
}
/* if tail call got detected across bpf2bpf calls then mark each of the
* currently present subprog frames as tail call reachable subprogs;
* this info will be utilized by JIT so that we will be preserving the
* tail call counter throughout bpf2bpf calls combined with tailcalls
*/
if (tail_call_reachable)
for (j = 0; j < frame; j++)
subprog[ret_prog[j]].tail_call_reachable = true;
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
*/
if (frame == 0)
return 0;
depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
frame--;
i = ret_insn[frame];
idx = ret_prog[frame];
goto continue_func;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int idx)
{
int start = idx + insn->imm + 1, subprog;
subprog = find_subprog(env, start);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
start);
return -EFAULT;
}
return env->subprog_info[subprog].stack_depth;
}
#endif
int check_ctx_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno)
{
/* Access to ctx or passing it to a helper is only allowed in
* its original, unmodified form.
*/
if (reg->off) {
verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
regno, reg->off);
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
return -EACCES;
}
return 0;
}
static int __check_buffer_access(struct bpf_verifier_env *env,
const char *buf_info,
const struct bpf_reg_state *reg,
int regno, int off, int size)
{
if (off < 0) {
verbose(env,
"R%d invalid %s buffer access: off=%d, size=%d\n",
regno, buf_info, off, size);
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env,
"R%d invalid variable buffer offset: off=%d, var_off=%s\n",
regno, off, tn_buf);
return -EACCES;
}
return 0;
}
static int check_tp_buffer_access(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int regno, int off, int size)
{
int err;
err = __check_buffer_access(env, "tracepoint", reg, regno, off, size);
if (err)
return err;
if (off + size > env->prog->aux->max_tp_access)
env->prog->aux->max_tp_access = off + size;
return 0;
}
static int check_buffer_access(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int regno, int off, int size,
bool zero_size_allowed,
const char *buf_info,
u32 *max_access)
{
int err;
err = __check_buffer_access(env, buf_info, reg, regno, off, size);
if (err)
return err;
if (off + size > *max_access)
*max_access = off + size;
return 0;
}
/* BPF architecture zero extends alu32 ops into 64-bit registesr */
static void zext_32_to_64(struct bpf_reg_state *reg)
{
reg->var_off = tnum_subreg(reg->var_off);
__reg_assign_32_into_64(reg);
}
/* truncate register to smaller size (in bytes)
* must be called with size < BPF_REG_SIZE
*/
static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
{
u64 mask;
/* clear high bits in bit representation */
reg->var_off = tnum_cast(reg->var_off, size);
/* fix arithmetic bounds */
mask = ((u64)1 << (size * 8)) - 1;
if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
reg->umin_value &= mask;
reg->umax_value &= mask;
} else {
reg->umin_value = 0;
reg->umax_value = mask;
}
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value;
/* If size is smaller than 32bit register the 32bit register
* values are also truncated so we push 64-bit bounds into
* 32-bit bounds. Above were truncated < 32-bits already.
*/
if (size >= 4)
return;
__reg_combine_64_into_32(reg);
}
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
}
static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
{
void *ptr;
u64 addr;
int err;
err = map->ops->map_direct_value_addr(map, &addr, off);
if (err)
return err;
ptr = (void *)(long)addr + off;
switch (size) {
case sizeof(u8):
*val = (u64)*(u8 *)ptr;
break;
case sizeof(u16):
*val = (u64)*(u16 *)ptr;
break;
case sizeof(u32):
*val = (u64)*(u32 *)ptr;
break;
case sizeof(u64):
*val = *(u64 *)ptr;
break;
default:
return -EINVAL;
}
return 0;
}
static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
struct bpf_reg_state *regs,
int regno, int off, int size,
enum bpf_access_type atype,
int value_regno)
{
struct bpf_reg_state *reg = regs + regno;
const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
const char *tname = btf_name_by_offset(reg->btf, t->name_off);
u32 btf_id;
int ret;
if (off < 0) {
verbose(env,
"R%d is ptr_%s invalid negative access: off=%d\n",
regno, tname, off);
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env,
"R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n",
regno, tname, off, tn_buf);
return -EACCES;
}
if (env->ops->btf_struct_access) {
ret = env->ops->btf_struct_access(&env->log, reg->btf, t,
off, size, atype, &btf_id);
} else {
if (atype != BPF_READ) {
verbose(env, "only read is supported\n");
return -EACCES;
}
ret = btf_struct_access(&env->log, reg->btf, t, off, size,
atype, &btf_id);
}
if (ret < 0)
return ret;
if (atype == BPF_READ && value_regno >= 0)
mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id);
return 0;
}
static int check_ptr_to_map_access(struct bpf_verifier_env *env,
struct bpf_reg_state *regs,
int regno, int off, int size,
enum bpf_access_type atype,
int value_regno)
{
struct bpf_reg_state *reg = regs + regno;
struct bpf_map *map = reg->map_ptr;
const struct btf_type *t;
const char *tname;
u32 btf_id;
int ret;
if (!btf_vmlinux) {
verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n");
return -ENOTSUPP;
}
if (!map->ops->map_btf_id || !*map->ops->map_btf_id) {
verbose(env, "map_ptr access not supported for map type %d\n",
map->map_type);
return -ENOTSUPP;
}
t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id);
tname = btf_name_by_offset(btf_vmlinux, t->name_off);
if (!env->allow_ptr_to_map_access) {
verbose(env,
"%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
tname);
return -EPERM;
}
if (off < 0) {
verbose(env, "R%d is %s invalid negative access: off=%d\n",
regno, tname, off);
return -EACCES;
}
if (atype != BPF_READ) {
verbose(env, "only read from %s is supported\n", tname);
return -EACCES;
}
ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id);
if (ret < 0)
return ret;
if (value_regno >= 0)
mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id);
return 0;
}
/* Check that the stack access at the given offset is within bounds. The
* maximum valid offset is -1.
*
* The minimum valid offset is -MAX_BPF_STACK for writes, and
* -state->allocated_stack for reads.
*/
static int check_stack_slot_within_bounds(int off,
struct bpf_func_state *state,
enum bpf_access_type t)
{
int min_valid_off;
if (t == BPF_WRITE)
min_valid_off = -MAX_BPF_STACK;
else
min_valid_off = -state->allocated_stack;
if (off < min_valid_off || off > -1)
return -EACCES;
return 0;
}
/* Check that the stack access at 'regno + off' falls within the maximum stack
* bounds.
*
* 'off' includes `regno->offset`, but not its dynamic part (if any).
*/
static int check_stack_access_within_bounds(
struct bpf_verifier_env *env,
int regno, int off, int access_size,
enum stack_access_src src, enum bpf_access_type type)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
struct bpf_func_state *state = func(env, reg);
int min_off, max_off;
int err;
char *err_extra;
if (src == ACCESS_HELPER)
/* We don't know if helpers are reading or writing (or both). */
err_extra = " indirect access to";
else if (type == BPF_READ)
err_extra = " read from";
else
err_extra = " write to";
if (tnum_is_const(reg->var_off)) {
min_off = reg->var_off.value + off;
if (access_size > 0)
max_off = min_off + access_size - 1;
else
max_off = min_off;
} else {
if (reg->smax_value >= BPF_MAX_VAR_OFF ||
reg->smin_value <= -BPF_MAX_VAR_OFF) {
verbose(env, "invalid unbounded variable-offset%s stack R%d\n",
err_extra, regno);
return -EACCES;
}
min_off = reg->smin_value + off;
if (access_size > 0)
max_off = reg->smax_value + off + access_size - 1;
else
max_off = min_off;
}
err = check_stack_slot_within_bounds(min_off, state, type);
if (!err)
err = check_stack_slot_within_bounds(max_off, state, type);
if (err) {
if (tnum_is_const(reg->var_off)) {
verbose(env, "invalid%s stack R%d off=%d size=%d\n",
err_extra, regno, off, access_size);
} else {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n",
err_extra, regno, tn_buf, access_size);
}
}
return err;
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
* if t==write && value_regno==-1, some unknown value is stored into memory
* if t==read && value_regno==-1, don't care what we read from memory
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
int value_regno, bool strict_alignment_once)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
struct bpf_func_state *state;
int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
if (size < 0)
return size;
/* alignment checks will add in reg->off themselves */
err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
if (err)
return err;
/* for access checks, reg->off is just part of off */
off += reg->off;
if (reg->type == PTR_TO_MAP_KEY) {
if (t == BPF_WRITE) {
verbose(env, "write to change key R%d not allowed\n", regno);
return -EACCES;
}
err = check_mem_region_access(env, regno, off, size,
reg->map_ptr->key_size, false);
if (err)
return err;
if (value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
err = check_map_access_type(env, regno, off, size, t);
if (err)
return err;
err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0) {
struct bpf_map *map = reg->map_ptr;
/* if map is read-only, track its contents as scalars */
if (tnum_is_const(reg->var_off) &&
bpf_map_is_rdonly(map) &&
map->ops->map_direct_value_addr) {
int map_off = off + reg->var_off.value;
u64 val = 0;
err = bpf_map_direct_read(map, map_off, size,
&val);
if (err)
return err;
regs[value_regno].type = SCALAR_VALUE;
__mark_reg_known(®s[value_regno], val);
} else {
mark_reg_unknown(env, regs, value_regno);
}
}
} else if (reg->type == PTR_TO_MEM) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into mem\n", value_regno);
return -EACCES;
}
err = check_mem_region_access(env, regno, off, size,
reg->mem_size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
struct btf *btf = NULL;
u32 btf_id = 0;
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id);
if (err)
verbose_linfo(env, insn_idx, "; ");
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
* PTR_TO_PACKET[_META,_END]. In the latter
* case, we know the offset is zero.
*/
if (reg_type == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
} else {
mark_reg_known_zero(env, regs,
value_regno);
if (reg_type_may_be_null(reg_type))
regs[value_regno].id = ++env->id_gen;
/* A load of ctx field could have different
* actual load size with the one encoded in the
* insn. When the dst is PTR, it is for sure not
* a sub-register.
*/
regs[value_regno].subreg_def = DEF_NOT_SUBREG;
if (reg_type == PTR_TO_BTF_ID ||
reg_type == PTR_TO_BTF_ID_OR_NULL) {
regs[value_regno].btf = btf;
regs[value_regno].btf_id = btf_id;
}
}
regs[value_regno].type = reg_type;
}
} else if (reg->type == PTR_TO_STACK) {
/* Basic bounds checks. */
err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t);
if (err)
return err;
state = func(env, reg);
err = update_stack_depth(env, state, off);
if (err)
return err;
if (t == BPF_READ)
err = check_stack_read(env, regno, off, size,
value_regno);
else
err = check_stack_write(env, regno, off, size,
value_regno, insn_idx);
} else if (reg_is_pkt_pointer(reg)) {
if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
verbose(env, "cannot write into packet\n");
return -EACCES;
}
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into packet\n",
value_regno);
return -EACCES;
}
err = check_packet_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_FLOW_KEYS) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into flow keys\n",
value_regno);
return -EACCES;
}
err = check_flow_keys_access(env, off, size);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (type_is_sk_pointer(reg->type)) {
if (t == BPF_WRITE) {
verbose(env, "R%d cannot write into %s\n",
regno, reg_type_str[reg->type]);
return -EACCES;
}
err = check_sock_access(env, insn_idx, regno, off, size, t);
if (!err && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_TP_BUFFER) {
err = check_tp_buffer_access(env, reg, regno, off, size);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_BTF_ID) {
err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
value_regno);
} else if (reg->type == CONST_PTR_TO_MAP) {
err = check_ptr_to_map_access(env, regs, regno, off, size, t,
value_regno);
} else if (reg->type == PTR_TO_RDONLY_BUF) {
if (t == BPF_WRITE) {
verbose(env, "R%d cannot write into %s\n",
regno, reg_type_str[reg->type]);
return -EACCES;
}
err = check_buffer_access(env, reg, regno, off, size, false,
"rdonly",
&env->prog->aux->max_rdonly_access);
if (!err && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_RDWR_BUF) {
err = check_buffer_access(env, reg, regno, off, size, false,
"rdwr",
&env->prog->aux->max_rdwr_access);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
reg_type_str[reg->type]);
return -EACCES;
}
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
/* b/h/w load zero-extends, mark upper bits as known 0 */
coerce_reg_to_size(®s[value_regno], size);
}
return err;
}
static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
int load_reg;
int err;
switch (insn->imm) {
case BPF_ADD:
case BPF_ADD | BPF_FETCH:
case BPF_AND:
case BPF_AND | BPF_FETCH:
case BPF_OR:
case BPF_OR | BPF_FETCH:
case BPF_XOR:
case BPF_XOR | BPF_FETCH:
case BPF_XCHG:
case BPF_CMPXCHG:
break;
default:
verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm);
return -EINVAL;
}
if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) {
verbose(env, "invalid atomic operand size\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (insn->imm == BPF_CMPXCHG) {
/* Check comparison of R0 with memory location */
err = check_reg_arg(env, BPF_REG_0, SRC_OP);
if (err)
return err;
}
if (is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
return -EACCES;
}
if (is_ctx_reg(env, insn->dst_reg) ||
is_pkt_reg(env, insn->dst_reg) ||
is_flow_key_reg(env, insn->dst_reg) ||
is_sk_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
insn->dst_reg,
reg_type_str[reg_state(env, insn->dst_reg)->type]);
return -EACCES;
}
if (insn->imm & BPF_FETCH) {
if (insn->imm == BPF_CMPXCHG)
load_reg = BPF_REG_0;
else
load_reg = insn->src_reg;
/* check and record load of old value */
err = check_reg_arg(env, load_reg, DST_OP);
if (err)
return err;
} else {
/* This instruction accesses a memory location but doesn't
* actually load it into a register.
*/
load_reg = -1;
}
/* check whether we can read the memory */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, load_reg, true);
if (err)
return err;
/* check whether we can write into the same memory */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
if (err)
return err;
return 0;
}
/* When register 'regno' is used to read the stack (either directly or through
* a helper function) make sure that it's within stack boundary and, depending
* on the access type, that all elements of the stack are initialized.
*
* 'off' includes 'regno->off', but not its dynamic part (if any).
*
* All registers that have been spilled on the stack in the slots within the
* read offsets are marked as read.
*/
static int check_stack_range_initialized(
struct bpf_verifier_env *env, int regno, int off,
int access_size, bool zero_size_allowed,
enum stack_access_src type, struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *reg = reg_state(env, regno);
struct bpf_func_state *state = func(env, reg);
int err, min_off, max_off, i, j, slot, spi;
char *err_extra = type == ACCESS_HELPER ? " indirect" : "";
enum bpf_access_type bounds_check_type;
/* Some accesses can write anything into the stack, others are
* read-only.
*/
bool clobber = false;
if (access_size == 0 && !zero_size_allowed) {
verbose(env, "invalid zero-sized read\n");
return -EACCES;
}
if (type == ACCESS_HELPER) {
/* The bounds checks for writes are more permissive than for
* reads. However, if raw_mode is not set, we'll do extra
* checks below.
*/
bounds_check_type = BPF_WRITE;
clobber = true;
} else {
bounds_check_type = BPF_READ;
}
err = check_stack_access_within_bounds(env, regno, off, access_size,
type, bounds_check_type);
if (err)
return err;
if (tnum_is_const(reg->var_off)) {
min_off = max_off = reg->var_off.value + off;
} else {
/* Variable offset is prohibited for unprivileged mode for
* simplicity since it requires corresponding support in
* Spectre masking for stack ALU.
* See also retrieve_ptr_limit().
*/
if (!env->bypass_spec_v1) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n",
regno, err_extra, tn_buf);
return -EACCES;
}
/* Only initialized buffer on stack is allowed to be accessed
* with variable offset. With uninitialized buffer it's hard to
* guarantee that whole memory is marked as initialized on
* helper return since specific bounds are unknown what may
* cause uninitialized stack leaking.
*/
if (meta && meta->raw_mode)
meta = NULL;
min_off = reg->smin_value + off;
max_off = reg->smax_value + off;
}
if (meta && meta->raw_mode) {
meta->access_size = access_size;
meta->regno = regno;
return 0;
}
for (i = min_off; i < max_off + access_size; i++) {
u8 *stype;
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
if (state->allocated_stack <= slot)
goto err;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
if (*stype == STACK_MISC)
goto mark;
if (*stype == STACK_ZERO) {
if (clobber) {
/* helper can write anything into the stack */
*stype = STACK_MISC;
}
goto mark;
}
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
goto mark;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
(state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
env->allow_ptr_leaks)) {
if (clobber) {
__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
state->stack[spi].slot_type[j] = STACK_MISC;
}
goto mark;
}
err:
if (tnum_is_const(reg->var_off)) {
verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n",
err_extra, regno, min_off, i - min_off, access_size);
} else {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n",
err_extra, regno, tn_buf, i - min_off, access_size);
}
return -EACCES;
mark:
/* reading any byte out of 8-byte 'spill_slot' will cause
* the whole slot to be marked as 'read'
*/
mark_reg_read(env, &state->stack[spi].spilled_ptr,
state->stack[spi].spilled_ptr.parent,
REG_LIVE_READ64);
}
return update_stack_depth(env, state, min_off);
}
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
int access_size, bool zero_size_allowed,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
switch (reg->type) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_KEY:
return check_mem_region_access(env, regno, reg->off, access_size,
reg->map_ptr->key_size, false);
case PTR_TO_MAP_VALUE:
if (check_map_access_type(env, regno, reg->off, access_size,
meta && meta->raw_mode ? BPF_WRITE :
BPF_READ))
return -EACCES;
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MEM:
return check_mem_region_access(env, regno, reg->off,
access_size, reg->mem_size,
zero_size_allowed);
case PTR_TO_RDONLY_BUF:
if (meta && meta->raw_mode)
return -EACCES;
return check_buffer_access(env, reg, regno, reg->off,
access_size, zero_size_allowed,
"rdonly",
&env->prog->aux->max_rdonly_access);
case PTR_TO_RDWR_BUF:
return check_buffer_access(env, reg, regno, reg->off,
access_size, zero_size_allowed,
"rdwr",
&env->prog->aux->max_rdwr_access);
case PTR_TO_STACK:
return check_stack_range_initialized(
env,
regno, reg->off, access_size,
zero_size_allowed, ACCESS_HELPER, meta);
default: /* scalar_value or invalid ptr */
/* Allow zero-byte read from NULL, regardless of pointer type */
if (zero_size_allowed && access_size == 0 &&
register_is_null(reg))
return 0;
verbose(env, "R%d type=%s expected=%s\n", regno,
reg_type_str[reg->type],
reg_type_str[PTR_TO_STACK]);
return -EACCES;
}
}
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno, u32 mem_size)
{
if (register_is_null(reg))
return 0;
if (reg_type_may_be_null(reg->type)) {
/* Assuming that the register contains a value check if the memory
* access is safe. Temporarily save and restore the register's state as
* the conversion shouldn't be visible to a caller.
*/
const struct bpf_reg_state saved_reg = *reg;
int rv;
mark_ptr_not_null_reg(reg);
rv = check_helper_mem_access(env, regno, mem_size, true, NULL);
*reg = saved_reg;
return rv;
}
return check_helper_mem_access(env, regno, mem_size, true, NULL);
}
/* Implementation details:
* bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
* Two bpf_map_lookups (even with the same key) will have different reg->id.
* For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after
* value_or_null->value transition, since the verifier only cares about
* the range of access to valid map value pointer and doesn't care about actual
* address of the map element.
* For maps with 'struct bpf_spin_lock' inside map value the verifier keeps
* reg->id > 0 after value_or_null->value transition. By doing so
* two bpf_map_lookups will be considered two different pointers that
* point to different bpf_spin_locks.
* The verifier allows taking only one bpf_spin_lock at a time to avoid
* dead-locks.
* Since only one bpf_spin_lock is allowed the checks are simpler than
* reg_is_refcounted() logic. The verifier needs to remember only
* one spin_lock instead of array of acquired_refs.
* cur_state->active_spin_lock remembers which map value element got locked
* and clears it after bpf_spin_unlock.
*/
static int process_spin_lock(struct bpf_verifier_env *env, int regno,
bool is_lock)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
struct bpf_verifier_state *cur = env->cur_state;
bool is_const = tnum_is_const(reg->var_off);
struct bpf_map *map = reg->map_ptr;
u64 val = reg->var_off.value;
if (!is_const) {
verbose(env,
"R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
regno);
return -EINVAL;
}
if (!map->btf) {
verbose(env,
"map '%s' has to have BTF in order to use bpf_spin_lock\n",
map->name);
return -EINVAL;
}
if (!map_value_has_spin_lock(map)) {
if (map->spin_lock_off == -E2BIG)
verbose(env,
"map '%s' has more than one 'struct bpf_spin_lock'\n",
map->name);
else if (map->spin_lock_off == -ENOENT)
verbose(env,
"map '%s' doesn't have 'struct bpf_spin_lock'\n",
map->name);
else
verbose(env,
"map '%s' is not a struct type or bpf_spin_lock is mangled\n",
map->name);
return -EINVAL;
}
if (map->spin_lock_off != val + reg->off) {
verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n",
val + reg->off);
return -EINVAL;
}
if (is_lock) {
if (cur->active_spin_lock) {
verbose(env,
"Locking two bpf_spin_locks are not allowed\n");
return -EINVAL;
}
cur->active_spin_lock = reg->id;
} else {
if (!cur->active_spin_lock) {
verbose(env, "bpf_spin_unlock without taking a lock\n");
return -EINVAL;
}
if (cur->active_spin_lock != reg->id) {
verbose(env, "bpf_spin_unlock of different lock\n");
return -EINVAL;
}
cur->active_spin_lock = 0;
}
return 0;
}
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MEM ||
type == ARG_PTR_TO_MEM_OR_NULL ||
type == ARG_PTR_TO_UNINIT_MEM;
}
static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
return type == ARG_CONST_SIZE ||
type == ARG_CONST_SIZE_OR_ZERO;
}
static bool arg_type_is_alloc_size(enum bpf_arg_type type)
{
return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
}
static bool arg_type_is_int_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_INT ||
type == ARG_PTR_TO_LONG;
}
static int int_ptr_type_to_size(enum bpf_arg_type type)
{
if (type == ARG_PTR_TO_INT)
return sizeof(u32);
else if (type == ARG_PTR_TO_LONG)
return sizeof(u64);
return -EINVAL;
}
static int resolve_map_arg_type(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_arg_type *arg_type)
{
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->type\n");
return -EACCES;
}
switch (meta->map_ptr->map_type) {
case BPF_MAP_TYPE_SOCKMAP:
case BPF_MAP_TYPE_SOCKHASH:
if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
*arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
} else {
verbose(env, "invalid arg_type for sockmap/sockhash\n");
return -EINVAL;
}
break;
default:
break;
}
return 0;
}
struct bpf_reg_types {
const enum bpf_reg_type types[10];
u32 *btf_id;
};
static const struct bpf_reg_types map_key_value_types = {
.types = {
PTR_TO_STACK,
PTR_TO_PACKET,
PTR_TO_PACKET_META,
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
},
};
static const struct bpf_reg_types sock_types = {
.types = {
PTR_TO_SOCK_COMMON,
PTR_TO_SOCKET,
PTR_TO_TCP_SOCK,
PTR_TO_XDP_SOCK,
},
};
#ifdef CONFIG_NET
static const struct bpf_reg_types btf_id_sock_common_types = {
.types = {
PTR_TO_SOCK_COMMON,
PTR_TO_SOCKET,
PTR_TO_TCP_SOCK,
PTR_TO_XDP_SOCK,
PTR_TO_BTF_ID,
},
.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
};
#endif
static const struct bpf_reg_types mem_types = {
.types = {
PTR_TO_STACK,
PTR_TO_PACKET,
PTR_TO_PACKET_META,
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
PTR_TO_MEM,
PTR_TO_RDONLY_BUF,
PTR_TO_RDWR_BUF,
},
};
static const struct bpf_reg_types int_ptr_types = {
.types = {
PTR_TO_STACK,
PTR_TO_PACKET,
PTR_TO_PACKET_META,
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
},
};
static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } };
static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
[ARG_PTR_TO_MAP_VALUE] = &map_key_value_types,
[ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types,
[ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types,
[ARG_CONST_SIZE] = &scalar_types,
[ARG_CONST_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_MAP_PTR] = &const_map_ptr_types,
[ARG_PTR_TO_CTX] = &context_types,
[ARG_PTR_TO_CTX_OR_NULL] = &context_types,
[ARG_PTR_TO_SOCK_COMMON] = &sock_types,
#ifdef CONFIG_NET
[ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types,
#endif
[ARG_PTR_TO_SOCKET] = &fullsock_types,
[ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types,
[ARG_PTR_TO_BTF_ID] = &btf_ptr_types,
[ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types,
[ARG_PTR_TO_MEM] = &mem_types,
[ARG_PTR_TO_MEM_OR_NULL] = &mem_types,
[ARG_PTR_TO_UNINIT_MEM] = &mem_types,
[ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types,
[ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types,
[ARG_PTR_TO_INT] = &int_ptr_types,
[ARG_PTR_TO_LONG] = &int_ptr_types,
[ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
[ARG_PTR_TO_FUNC] = &func_ptr_types,
[ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types,
[ARG_PTR_TO_CONST_STR] = &const_str_ptr_types,
};
static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
const u32 *arg_btf_id)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
enum bpf_reg_type expected, type = reg->type;
const struct bpf_reg_types *compatible;
int i, j;
compatible = compatible_reg_types[arg_type];
if (!compatible) {
verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
return -EFAULT;
}
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
if (expected == NOT_INIT)
break;
if (type == expected)
goto found;
}
verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
for (j = 0; j + 1 < i; j++)
verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
return -EACCES;
found:
if (type == PTR_TO_BTF_ID) {
if (!arg_btf_id) {
if (!compatible->btf_id) {
verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
return -EFAULT;
}
arg_btf_id = compatible->btf_id;
}
if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
btf_vmlinux, *arg_btf_id)) {
verbose(env, "R%d is of type %s but %s is expected\n",
regno, kernel_type_name(reg->btf, reg->btf_id),
kernel_type_name(btf_vmlinux, *arg_btf_id));
return -EACCES;
}
if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
regno);
return -EACCES;
}
}
return 0;
}
static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
struct bpf_call_arg_meta *meta,
const struct bpf_func_proto *fn)
{
u32 regno = BPF_REG_1 + arg;
struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
enum bpf_arg_type arg_type = fn->arg_type[arg];
enum bpf_reg_type type = reg->type;
int err = 0;
if (arg_type == ARG_DONTCARE)
return 0;
err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
if (arg_type == ARG_ANYTHING) {
if (is_pointer_value(env, regno)) {
verbose(env, "R%d leaks addr into helper function\n",
regno);
return -EACCES;
}
return 0;
}
if (type_is_pkt_pointer(type) &&
!may_access_direct_pkt_data(env, meta, BPF_READ)) {
verbose(env, "helper access to the packet is not allowed\n");
return -EACCES;
}
if (arg_type == ARG_PTR_TO_MAP_VALUE ||
arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
err = resolve_map_arg_type(env, meta, &arg_type);
if (err)
return err;
}
if (register_is_null(reg) && arg_type_may_be_null(arg_type))
/* A NULL register has a SCALAR_VALUE type, so skip
* type checking.
*/
goto skip_type_check;
err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);
if (err)
return err;
if (type == PTR_TO_CTX) {
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
}
skip_type_check:
if (reg->ref_obj_id) {
if (meta->ref_obj_id) {
verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
regno, reg->ref_obj_id,
meta->ref_obj_id);
return -EFAULT;
}
meta->ref_obj_id = reg->ref_obj_id;
}
if (arg_type == ARG_CONST_MAP_PTR) {
/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
meta->map_ptr = reg->map_ptr;
} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
/* bpf_map_xxx(..., map_ptr, ..., key) call:
* check that [key, key + map->key_size) are within
* stack limits and initialized
*/
if (!meta->map_ptr) {
/* in function declaration map_ptr must come before
* map_key, so that it's verified and known before
* we have to check map_key here. Otherwise it means
* that kernel subsystem misconfigured verifier
*/
verbose(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
(arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
!register_is_null(reg)) ||
arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
err = check_helper_mem_access(env, regno,
meta->map_ptr->value_size, false,
meta);
} else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) {
if (!reg->btf_id) {
verbose(env, "Helper has invalid btf_id in R%d\n", regno);
return -EACCES;
}
meta->ret_btf = reg->btf;
meta->ret_btf_id = reg->btf_id;
} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
if (meta->func_id == BPF_FUNC_spin_lock) {
if (process_spin_lock(env, regno, true))
return -EACCES;
} else if (meta->func_id == BPF_FUNC_spin_unlock) {
if (process_spin_lock(env, regno, false))
return -EACCES;
} else {
verbose(env, "verifier internal error\n");
return -EFAULT;
}
} else if (arg_type == ARG_PTR_TO_FUNC) {
meta->subprogno = reg->subprogno;
} else if (arg_type_is_mem_ptr(arg_type)) {
/* The access to this pointer is only checked when we hit the
* next is_mem_size argument below.
*/
meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
/* This is used to refine r0 return value bounds for helpers
* that enforce this value as an upper bound on return values.
* See do_refine_retval_range() for helpers that can refine
* the return value. C type of helper is u32 so we pull register
* bound from umax_value however, if negative verifier errors
* out. Only upper bounds can be learned because retval is an
* int type and negative retvals are allowed.
*/
meta->msize_max_value = reg->umax_value;
/* The register is SCALAR_VALUE; the access check
* happens using its boundaries.
*/
if (!tnum_is_const(reg->var_off))
/* For unprivileged variable accesses, disable raw
* mode so that the program is required to
* initialize all the memory that the helper could
* just partially fill up.
*/
meta = NULL;
if (reg->smin_value < 0) {
verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
regno);
return -EACCES;
}
if (reg->umin_value == 0) {
err = check_helper_mem_access(env, regno - 1, 0,
zero_size_allowed,
meta);
if (err)
return err;
}
if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
regno);
return -EACCES;
}
err = check_helper_mem_access(env, regno - 1,
reg->umax_value,
zero_size_allowed, meta);
if (!err)
err = mark_chain_precision(env, regno);
} else if (arg_type_is_alloc_size(arg_type)) {
if (!tnum_is_const(reg->var_off)) {
verbose(env, "R%d is not a known constant'\n",
regno);
return -EACCES;
}
meta->mem_size = reg->var_off.value;
} else if (arg_type_is_int_ptr(arg_type)) {
int size = int_ptr_type_to_size(arg_type);
err = check_helper_mem_access(env, regno, size, false, meta);
if (err)
return err;
err = check_ptr_alignment(env, reg, 0, size, true);
} else if (arg_type == ARG_PTR_TO_CONST_STR) {
struct bpf_map *map = reg->map_ptr;
int map_off;
u64 map_addr;
char *str_ptr;
if (!bpf_map_is_rdonly(map)) {
verbose(env, "R%d does not point to a readonly map'\n", regno);
return -EACCES;
}
if (!tnum_is_const(reg->var_off)) {
verbose(env, "R%d is not a constant address'\n", regno);
return -EACCES;
}
if (!map->ops->map_direct_value_addr) {
verbose(env, "no direct value access support for this map type\n");
return -EACCES;
}
err = check_map_access(env, regno, reg->off,
map->value_size - reg->off, false);
if (err)
return err;
map_off = reg->off + reg->var_off.value;
err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
if (err) {
verbose(env, "direct value access on string failed\n");
return err;
}
str_ptr = (char *)(long)(map_addr);
if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
verbose(env, "string is not zero-terminated\n");
return -EINVAL;
}
}
return err;
}
static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
{
enum bpf_attach_type eatype = env->prog->expected_attach_type;
enum bpf_prog_type type = resolve_prog_type(env->prog);
if (func_id != BPF_FUNC_map_update_elem)
return false;
/* It's not possible to get access to a locked struct sock in these
* contexts, so updating is safe.
*/
switch (type) {
case BPF_PROG_TYPE_TRACING:
if (eatype == BPF_TRACE_ITER)
return true;
break;
case BPF_PROG_TYPE_SOCKET_FILTER:
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_SK_LOOKUP:
return true;
default:
break;
}
verbose(env, "cannot update sockmap in this context\n");
return false;
}
static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
{
return env->prog->jit_requested && IS_ENABLED(CONFIG_X86_64);
}
static int check_map_func_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map, int func_id)
{
if (!map)
return 0;
/* We need a two way check, first is from map perspective ... */
switch (map->map_type) {
case BPF_MAP_TYPE_PROG_ARRAY:
if (func_id != BPF_FUNC_tail_call)
goto error;
break;
case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
if (func_id != BPF_FUNC_perf_event_read &&
func_id != BPF_FUNC_perf_event_output &&
func_id != BPF_FUNC_skb_output &&
func_id != BPF_FUNC_perf_event_read_value &&
func_id != BPF_FUNC_xdp_output)
goto error;
break;
case BPF_MAP_TYPE_RINGBUF:
if (func_id != BPF_FUNC_ringbuf_output &&
func_id != BPF_FUNC_ringbuf_reserve &&
func_id != BPF_FUNC_ringbuf_submit &&
func_id != BPF_FUNC_ringbuf_discard &&
func_id != BPF_FUNC_ringbuf_query)
goto error;
break;
case BPF_MAP_TYPE_STACK_TRACE:
if (func_id != BPF_FUNC_get_stackid)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
if (func_id != BPF_FUNC_skb_under_cgroup &&
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
if (func_id != BPF_FUNC_get_local_storage)
goto error;
break;
case BPF_MAP_TYPE_DEVMAP:
case BPF_MAP_TYPE_DEVMAP_HASH:
if (func_id != BPF_FUNC_redirect_map &&
func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
/* Restrict bpf side of cpumap and xskmap, open when use-cases
* appear.
*/
case BPF_MAP_TYPE_CPUMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
case BPF_MAP_TYPE_XSKMAP:
if (func_id != BPF_FUNC_redirect_map &&
func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
case BPF_MAP_TYPE_SOCKMAP:
if (func_id != BPF_FUNC_sk_redirect_map &&
func_id != BPF_FUNC_sock_map_update &&
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_msg_redirect_map &&
func_id != BPF_FUNC_sk_select_reuseport &&
func_id != BPF_FUNC_map_lookup_elem &&
!may_update_sockmap(env, func_id))
goto error;
break;
case BPF_MAP_TYPE_SOCKHASH:
if (func_id != BPF_FUNC_sk_redirect_hash &&
func_id != BPF_FUNC_sock_hash_update &&
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_msg_redirect_hash &&
func_id != BPF_FUNC_sk_select_reuseport &&
func_id != BPF_FUNC_map_lookup_elem &&
!may_update_sockmap(env, func_id))
goto error;
break;
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
if (func_id != BPF_FUNC_sk_select_reuseport)
goto error;
break;
case BPF_MAP_TYPE_QUEUE:
case BPF_MAP_TYPE_STACK:
if (func_id != BPF_FUNC_map_peek_elem &&
func_id != BPF_FUNC_map_pop_elem &&
func_id != BPF_FUNC_map_push_elem)
goto error;
break;
case BPF_MAP_TYPE_SK_STORAGE:
if (func_id != BPF_FUNC_sk_storage_get &&
func_id != BPF_FUNC_sk_storage_delete)
goto error;
break;
case BPF_MAP_TYPE_INODE_STORAGE:
if (func_id != BPF_FUNC_inode_storage_get &&
func_id != BPF_FUNC_inode_storage_delete)
goto error;
break;
case BPF_MAP_TYPE_TASK_STORAGE:
if (func_id != BPF_FUNC_task_storage_get &&
func_id != BPF_FUNC_task_storage_delete)
goto error;
break;
default:
break;
}
/* ... and second from the function itself. */
switch (func_id) {
case BPF_FUNC_tail_call:
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
goto error;
if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) {
verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
return -EINVAL;
}
break;
case BPF_FUNC_perf_event_read:
case BPF_FUNC_perf_event_output:
case BPF_FUNC_perf_event_read_value:
case BPF_FUNC_skb_output:
case BPF_FUNC_xdp_output:
if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
goto error;
break;
case BPF_FUNC_get_stackid:
if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
goto error;
break;
case BPF_FUNC_current_task_under_cgroup:
case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
case BPF_FUNC_redirect_map:
if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
map->map_type != BPF_MAP_TYPE_DEVMAP_HASH &&
map->map_type != BPF_MAP_TYPE_CPUMAP &&
map->map_type != BPF_MAP_TYPE_XSKMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
case BPF_FUNC_msg_redirect_map:
case BPF_FUNC_sock_map_update:
if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_hash:
case BPF_FUNC_msg_redirect_hash:
case BPF_FUNC_sock_hash_update:
if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
case BPF_FUNC_get_local_storage:
if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
goto error;
break;
case BPF_FUNC_sk_select_reuseport:
if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
map->map_type != BPF_MAP_TYPE_SOCKMAP &&
map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
case BPF_FUNC_map_peek_elem:
case BPF_FUNC_map_pop_elem:
case BPF_FUNC_map_push_elem:
if (map->map_type != BPF_MAP_TYPE_QUEUE &&
map->map_type != BPF_MAP_TYPE_STACK)
goto error;
break;
case BPF_FUNC_sk_storage_get:
case BPF_FUNC_sk_storage_delete:
if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
goto error;
break;
case BPF_FUNC_inode_storage_get:
case BPF_FUNC_inode_storage_delete:
if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
goto error;
break;
case BPF_FUNC_task_storage_get:
case BPF_FUNC_task_storage_delete:
if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
goto error;
break;
default:
break;
}
return 0;
error:
verbose(env, "cannot pass map_type %d into func %s#%d\n",
map->map_type, func_id_name(func_id), func_id);
return -EINVAL;
}
static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
{
int count = 0;
if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
count++;
if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
count++;
/* We only support one arg being in raw mode at the moment,
* which is sufficient for the helper functions we have
* right now.
*/
return count <= 1;
}
static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
enum bpf_arg_type arg_next)
{
return (arg_type_is_mem_ptr(arg_curr) &&
!arg_type_is_mem_size(arg_next)) ||
(!arg_type_is_mem_ptr(arg_curr) &&
arg_type_is_mem_size(arg_next));
}
static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
{
/* bpf_xxx(..., buf, len) call will access 'len'
* bytes from memory 'buf'. Both arg types need
* to be paired, so make sure there's no buggy
* helper function specification.
*/
if (arg_type_is_mem_size(fn->arg1_type) ||
arg_type_is_mem_ptr(fn->arg5_type) ||
check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
return false;
return true;
}
static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
{
int count = 0;
if (arg_type_may_be_refcounted(fn->arg1_type))
count++;
if (arg_type_may_be_refcounted(fn->arg2_type))
count++;
if (arg_type_may_be_refcounted(fn->arg3_type))
count++;
if (arg_type_may_be_refcounted(fn->arg4_type))
count++;
if (arg_type_may_be_refcounted(fn->arg5_type))
count++;
/* A reference acquiring function cannot acquire
* another refcounted ptr.
*/
if (may_be_acquire_function(func_id) && count)
return false;
/* We only support one arg being unreferenced at the moment,
* which is sufficient for the helper functions we have right now.
*/
return count <= 1;
}
static bool check_btf_id_ok(const struct bpf_func_proto *fn)
{
int i;
for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
return false;
if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
return false;
}
return true;
}
static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
{
return check_raw_mode_ok(fn) &&
check_arg_pair_ok(fn) &&
check_btf_id_ok(fn) &&
check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
}
/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
* are now invalid, so turn them into unknown SCALAR_VALUE.
*/
static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (reg_is_pkt_pointer_any(®s[i]))
mark_reg_unknown(env, regs, i);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
if (reg_is_pkt_pointer_any(reg))
__mark_reg_unknown(env, reg);
}
}
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *vstate = env->cur_state;
int i;
for (i = 0; i <= vstate->curframe; i++)
__clear_all_pkt_pointers(env, vstate->frame[i]);
}
enum {
AT_PKT_END = -1,
BEYOND_PKT_END = -2,
};
static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regn];
if (reg->type != PTR_TO_PACKET)
/* PTR_TO_PACKET_META is not supported yet */
return;
/* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
* How far beyond pkt_end it goes is unknown.
* if (!range_open) it's the case of pkt >= pkt_end
* if (range_open) it's the case of pkt > pkt_end
* hence this pointer is at least 1 byte bigger than pkt_end
*/
if (range_open)
reg->range = BEYOND_PKT_END;
else
reg->range = AT_PKT_END;
}
static void release_reg_references(struct bpf_verifier_env *env,
struct bpf_func_state *state,
int ref_obj_id)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].ref_obj_id == ref_obj_id)
mark_reg_unknown(env, regs, i);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
if (reg->ref_obj_id == ref_obj_id)
__mark_reg_unknown(env, reg);
}
}
/* The pointer with the specified id has released its reference to kernel
* resources. Identify all copies of the same pointer and clear the reference.
*/
static int release_reference(struct bpf_verifier_env *env,
int ref_obj_id)
{
struct bpf_verifier_state *vstate = env->cur_state;
int err;
int i;
err = release_reference_state(cur_func(env), ref_obj_id);
if (err)
return err;
for (i = 0; i <= vstate->curframe; i++)
release_reg_references(env, vstate->frame[i], ref_obj_id);
return 0;
}
static void clear_caller_saved_regs(struct bpf_verifier_env *env,
struct bpf_reg_state *regs)
{
int i;
/* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
}
typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee,
int insn_idx);
static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx, int subprog,
set_callee_state_fn set_callee_state_cb)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_info_aux *func_info_aux;
struct bpf_func_state *caller, *callee;
int err;
bool is_global = false;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
state->curframe + 2);
return -E2BIG;
}
caller = state->frame[state->curframe];
if (state->frame[state->curframe + 1]) {
verbose(env, "verifier bug. Frame %d already allocated\n",
state->curframe + 1);
return -EFAULT;
}
func_info_aux = env->prog->aux->func_info_aux;
if (func_info_aux)
is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
err = btf_check_subprog_arg_match(env, subprog, caller->regs);
if (err == -EFAULT)
return err;
if (is_global) {
if (err) {
verbose(env, "Caller passes invalid args into func#%d\n",
subprog);
return err;
} else {
if (env->log.level & BPF_LOG_LEVEL)
verbose(env,
"Func#%d is global and valid. Skipping.\n",
subprog);
clear_caller_saved_regs(env, caller->regs);
/* All global functions return a 64-bit SCALAR_VALUE */
mark_reg_unknown(env, caller->regs, BPF_REG_0);
caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
/* continue with next insn after call */
return 0;
}
}
callee = kzalloc(sizeof(*callee), GFP_KERNEL);
if (!callee)
return -ENOMEM;
state->frame[state->curframe + 1] = callee;
/* callee cannot access r0, r6 - r9 for reading and has to write
* into its own stack before reading from it.
* callee can read/write into caller's stack
*/
init_func_state(env, callee,
/* remember the callsite, it will be used by bpf_exit */
*insn_idx /* callsite */,
state->curframe + 1 /* frameno within this callchain */,
subprog /* subprog number within this prog */);
/* Transfer references to the callee */
err = transfer_reference_state(callee, caller);
if (err)
return err;
err = set_callee_state_cb(env, caller, callee, *insn_idx);
if (err)
return err;
clear_caller_saved_regs(env, caller->regs);
/* only increment it after check_reg_arg() finished */
state->curframe++;
/* and go analyze first insn of the callee */
*insn_idx = env->subprog_info[subprog].start - 1;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
print_verifier_state(env, caller);
verbose(env, "callee:\n");
print_verifier_state(env, callee);
}
return 0;
}
int map_set_for_each_callback_args(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee)
{
/* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn,
* void *callback_ctx, u64 flags);
* callback_fn(struct bpf_map *map, void *key, void *value,
* void *callback_ctx);
*/
callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];
callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr;
callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr;
/* pointer to stack or null */
callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3];
/* unused */
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
return 0;
}
static int set_callee_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee, int insn_idx)
{
int i;
/* copy r1 - r5 args that callee can access. The copy includes parent
* pointers, which connects us up to the liveness chain
*/
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
return 0;
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
int subprog, target_insn;
target_insn = *insn_idx + insn->imm + 1;
subprog = find_subprog(env, target_insn);
if (subprog < 0) {
verbose(env, "verifier bug. No program starts at insn %d\n",
target_insn);
return -EFAULT;
}
return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
}
static int set_map_elem_callback_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee,
int insn_idx)
{
struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx];
struct bpf_map *map;
int err;
if (bpf_map_ptr_poisoned(insn_aux)) {
verbose(env, "tail_call abusing map_ptr\n");
return -EINVAL;
}
map = BPF_MAP_PTR(insn_aux->map_ptr_state);
if (!map->ops->map_set_for_each_callback_args ||
!map->ops->map_for_each_callback) {
verbose(env, "callback function not allowed for map\n");
return -ENOTSUPP;
}
err = map->ops->map_set_for_each_callback_args(env, caller, callee);
if (err)
return err;
callee->in_callback_fn = true;
return 0;
}
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
struct bpf_reg_state *r0;
int err;
callee = state->frame[state->curframe];
r0 = &callee->regs[BPF_REG_0];
if (r0->type == PTR_TO_STACK) {
/* technically it's ok to return caller's stack pointer
* (or caller's caller's pointer) back to the caller,
* since these pointers are valid. Only current stack
* pointer will be invalid as soon as function exits,
* but let's be conservative
*/
verbose(env, "cannot return stack pointer to the caller\n");
return -EINVAL;
}
state->curframe--;
caller = state->frame[state->curframe];
if (callee->in_callback_fn) {
/* enforce R0 return value range [0, 1]. */
struct tnum range = tnum_range(0, 1);
if (r0->type != SCALAR_VALUE) {
verbose(env, "R0 not a scalar value\n");
return -EACCES;
}
if (!tnum_in(range, r0->var_off)) {
verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
return -EINVAL;
}
} else {
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
}
/* Transfer references to the caller */
err = transfer_reference_state(caller, callee);
if (err)
return err;
*insn_idx = callee->callsite + 1;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee);
verbose(env, "to caller at %d:\n", *insn_idx);
print_verifier_state(env, caller);
}
/* clear everything in the callee */
free_func_state(callee);
state->frame[state->curframe + 1] = NULL;
return 0;
}
static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
int func_id,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *ret_reg = ®s[BPF_REG_0];
if (ret_type != RET_INTEGER ||
(func_id != BPF_FUNC_get_stack &&
func_id != BPF_FUNC_get_task_stack &&
func_id != BPF_FUNC_probe_read_str &&
func_id != BPF_FUNC_probe_read_kernel_str &&
func_id != BPF_FUNC_probe_read_user_str))
return;
ret_reg->smax_value = meta->msize_max_value;
ret_reg->s32_max_value = meta->msize_max_value;
ret_reg->smin_value = -MAX_ERRNO;
ret_reg->s32_min_value = -MAX_ERRNO;
__reg_deduce_bounds(ret_reg);
__reg_bound_offset(ret_reg);
__update_reg_bounds(ret_reg);
}
static int
record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
int func_id, int insn_idx)
{
struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
struct bpf_map *map = meta->map_ptr;
if (func_id != BPF_FUNC_tail_call &&
func_id != BPF_FUNC_map_lookup_elem &&
func_id != BPF_FUNC_map_update_elem &&
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_map_push_elem &&
func_id != BPF_FUNC_map_pop_elem &&
func_id != BPF_FUNC_map_peek_elem &&
func_id != BPF_FUNC_for_each_map_elem &&
func_id != BPF_FUNC_redirect_map)
return 0;
if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
/* In case of read-only, some additional restrictions
* need to be applied in order to prevent altering the
* state of the map from program side.
*/
if ((map->map_flags & BPF_F_RDONLY_PROG) &&
(func_id == BPF_FUNC_map_delete_elem ||
func_id == BPF_FUNC_map_update_elem ||
func_id == BPF_FUNC_map_push_elem ||
func_id == BPF_FUNC_map_pop_elem)) {
verbose(env, "write into map forbidden\n");
return -EACCES;
}
if (!BPF_MAP_PTR(aux->map_ptr_state))
bpf_map_ptr_store(aux, meta->map_ptr,
!meta->map_ptr->bypass_spec_v1);
else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr)
bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
!meta->map_ptr->bypass_spec_v1);
return 0;
}
static int
record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
int func_id, int insn_idx)
{
struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
struct bpf_reg_state *regs = cur_regs(env), *reg;
struct bpf_map *map = meta->map_ptr;
struct tnum range;
u64 val;
int err;
if (func_id != BPF_FUNC_tail_call)
return 0;
if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) {
verbose(env, "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
range = tnum_range(0, map->max_entries - 1);
reg = ®s[BPF_REG_3];
if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) {
bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
return 0;
}
err = mark_chain_precision(env, BPF_REG_3);
if (err)
return err;
val = reg->var_off.value;
if (bpf_map_key_unseen(aux))
bpf_map_key_store(aux, val);
else if (!bpf_map_key_poisoned(aux) &&
bpf_map_key_immediate(aux) != val)
bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
return 0;
}
static int check_reference_leak(struct bpf_verifier_env *env)
{
struct bpf_func_state *state = cur_func(env);
int i;
for (i = 0; i < state->acquired_refs; i++) {
verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
state->refs[i].id, state->refs[i].insn_idx);
}
return state->acquired_refs ? -EINVAL : 0;
}
static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
struct bpf_reg_state *regs)
{
struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3];
struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5];
struct bpf_map *fmt_map = fmt_reg->map_ptr;
int err, fmt_map_off, num_args;
u64 fmt_addr;
char *fmt;
/* data must be an array of u64 */
if (data_len_reg->var_off.value % 8)
return -EINVAL;
num_args = data_len_reg->var_off.value / 8;
/* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const
* and map_direct_value_addr is set.
*/
fmt_map_off = fmt_reg->off + fmt_reg->var_off.value;
err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
fmt_map_off);
if (err) {
verbose(env, "verifier bug\n");
return -EFAULT;
}
fmt = (char *)(long)fmt_addr + fmt_map_off;
/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
* can focus on validating the format specifiers.
*/
err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args);
if (err < 0)
verbose(env, "Invalid format string\n");
return err;
}
static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
const struct bpf_func_proto *fn = NULL;
struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
int insn_idx = *insn_idx_p;
bool changes_data;
int i, err, func_id;
/* find function prototype */
func_id = insn->imm;
if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
func_id);
return -EINVAL;
}
if (env->ops->get_func_proto)
fn = env->ops->get_func_proto(func_id, env->prog);
if (!fn) {
verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
func_id);
return -EINVAL;
}
/* eBPF programs must be GPL compatible to use GPL-ed functions */
if (!env->prog->gpl_compatible && fn->gpl_only) {
verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n");
return -EINVAL;
}
if (fn->allowed && !fn->allowed(env->prog)) {
verbose(env, "helper call is not allowed in probe\n");
return -EINVAL;
}
/* With LD_ABS/IND some JITs save/restore skb from r1. */
changes_data = bpf_helper_changes_pkt_data(fn->func);
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
func_id_name(func_id), func_id);
return -EINVAL;
}
memset(&meta, 0, sizeof(meta));
meta.pkt_access = fn->pkt_access;
err = check_func_proto(fn, func_id);
if (err) {
verbose(env, "kernel subsystem misconfigured func %s#%d\n",
func_id_name(func_id), func_id);
return err;
}
meta.func_id = func_id;
/* check args */
for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
err = check_func_arg(env, i, &meta, fn);
if (err)
return err;
}
err = record_func_map(env, &meta, func_id, insn_idx);
if (err)
return err;
err = record_func_key(env, &meta, func_id, insn_idx);
if (err)
return err;
/* Mark slots with STACK_MISC in case of raw mode, stack offset
* is inferred from register state.
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
BPF_WRITE, -1, false);
if (err)
return err;
}
if (func_id == BPF_FUNC_tail_call) {
err = check_reference_leak(env);
if (err) {
verbose(env, "tail_call would lead to reference leak\n");
return err;
}
} else if (is_release_function(func_id)) {
err = release_reference(env, meta.ref_obj_id);
if (err) {
verbose(env, "func %s#%d reference has not been acquired before\n",
func_id_name(func_id), func_id);
return err;
}
}
regs = cur_regs(env);
/* check that flags argument in get_local_storage(map, flags) is 0,
* this is required because get_local_storage() can't return an error.
*/
if (func_id == BPF_FUNC_get_local_storage &&
!register_is_null(®s[BPF_REG_2])) {
verbose(env, "get_local_storage() doesn't support non-zero flags\n");
return -EINVAL;
}
if (func_id == BPF_FUNC_for_each_map_elem) {
err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
set_map_elem_callback_state);
if (err < 0)
return -EINVAL;
}
if (func_id == BPF_FUNC_snprintf) {
err = check_bpf_snprintf_call(env, regs);
if (err < 0)
return err;
}
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* helper call returns 64-bit value. */
regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
/* update return register (already marked as written above) */
if (fn->ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
fn->ret_type == RET_PTR_TO_MAP_VALUE) {
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
* can check 'value_size' boundary of memory access
* to map element returned from bpf_map_lookup_elem()
*/
if (meta.map_ptr == NULL) {
verbose(env,
"kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
if (map_value_has_spin_lock(meta.map_ptr))
regs[BPF_REG_0].id = ++env->id_gen;
} else {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
}
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
} else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
regs[BPF_REG_0].mem_size = meta.mem_size;
} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
const struct btf_type *t;
mark_reg_known_zero(env, regs, BPF_REG_0);
t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL);
if (!btf_type_is_struct(t)) {
u32 tsize;
const struct btf_type *ret;
const char *tname;
/* resolve the type size of ksym. */
ret = btf_resolve_size(meta.ret_btf, t, &tsize);
if (IS_ERR(ret)) {
tname = btf_name_by_offset(meta.ret_btf, t->name_off);
verbose(env, "unable to resolve the size of type '%s': %ld\n",
tname, PTR_ERR(ret));
return -EINVAL;
}
regs[BPF_REG_0].type =
fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
regs[BPF_REG_0].mem_size = tsize;
} else {
regs[BPF_REG_0].type =
fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
fn->ret_type == RET_PTR_TO_BTF_ID) {
int ret_btf_id;
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
PTR_TO_BTF_ID :
PTR_TO_BTF_ID_OR_NULL;
ret_btf_id = *fn->ret_btf_id;
if (ret_btf_id == 0) {
verbose(env, "invalid return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
return -EINVAL;
}
/* current BPF helper definitions are only coming from
* built-in code with type IDs from vmlinux BTF
*/
regs[BPF_REG_0].btf = btf_vmlinux;
regs[BPF_REG_0].btf_id = ret_btf_id;
} else {
verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
return -EINVAL;
}
if (reg_type_may_be_null(regs[BPF_REG_0].type))
regs[BPF_REG_0].id = ++env->id_gen;
if (is_ptr_cast_function(func_id)) {
/* For release_reference() */
regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
} else if (is_acquire_function(func_id, meta.map_ptr)) {
int id = acquire_reference_state(env, insn_idx);
if (id < 0)
return id;
/* For mark_ptr_or_null_reg() */
regs[BPF_REG_0].id = id;
/* For release_reference() */
regs[BPF_REG_0].ref_obj_id = id;
}
do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
return err;
if ((func_id == BPF_FUNC_get_stack ||
func_id == BPF_FUNC_get_task_stack) &&
!env->prog->has_callchain_buf) {
const char *err_str;
#ifdef CONFIG_PERF_EVENTS
err = get_callchain_buffers(sysctl_perf_event_max_stack);
err_str = "cannot get callchain buffer for func %s#%d\n";
#else
err = -ENOTSUPP;
err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
#endif
if (err) {
verbose(env, err_str, func_id_name(func_id), func_id);
return err;
}
env->prog->has_callchain_buf = true;
}
if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
env->prog->call_get_stack = true;
if (changes_data)
clear_all_pkt_pointers(env);
return 0;
}
/* mark_btf_func_reg_size() is used when the reg size is determined by
* the BTF func_proto's return value size and argument.
*/
static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno,
size_t reg_size)
{
struct bpf_reg_state *reg = &cur_regs(env)[regno];
if (regno == BPF_REG_0) {
/* Function return value */
reg->live |= REG_LIVE_WRITTEN;
reg->subreg_def = reg_size == sizeof(u64) ?
DEF_NOT_SUBREG : env->insn_idx + 1;
} else {
/* Function argument */
if (reg_size == sizeof(u64)) {
mark_insn_zext(env, reg);
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
} else {
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ32);
}
}
}
static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
const struct btf_type *t, *func, *func_proto, *ptr_type;
struct bpf_reg_state *regs = cur_regs(env);
const char *func_name, *ptr_type_name;
u32 i, nargs, func_id, ptr_type_id;
const struct btf_param *args;
int err;
func_id = insn->imm;
func = btf_type_by_id(btf_vmlinux, func_id);
func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
func_proto = btf_type_by_id(btf_vmlinux, func->type);
if (!env->ops->check_kfunc_call ||
!env->ops->check_kfunc_call(func_id)) {
verbose(env, "calling kernel function %s is not allowed\n",
func_name);
return -EACCES;
}
/* Check the arguments */
err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs);
if (err)
return err;
for (i = 0; i < CALLER_SAVED_REGS; i++)
mark_reg_not_init(env, regs, caller_saved[i]);
/* Check return type */
t = btf_type_skip_modifiers(btf_vmlinux, func_proto->type, NULL);
if (btf_type_is_scalar(t)) {
mark_reg_unknown(env, regs, BPF_REG_0);
mark_btf_func_reg_size(env, BPF_REG_0, t->size);
} else if (btf_type_is_ptr(t)) {
ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type,
&ptr_type_id);
if (!btf_type_is_struct(ptr_type)) {
ptr_type_name = btf_name_by_offset(btf_vmlinux,
ptr_type->name_off);
verbose(env, "kernel function %s returns pointer type %s %s is not supported\n",
func_name, btf_type_str(ptr_type),
ptr_type_name);
return -EINVAL;
}
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].btf = btf_vmlinux;
regs[BPF_REG_0].type = PTR_TO_BTF_ID;
regs[BPF_REG_0].btf_id = ptr_type_id;
mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
} /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */
nargs = btf_type_vlen(func_proto);
args = (const struct btf_param *)(func_proto + 1);
for (i = 0; i < nargs; i++) {
u32 regno = i + 1;
t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL);
if (btf_type_is_ptr(t))
mark_btf_func_reg_size(env, regno, sizeof(void *));
else
/* scalar. ensured by btf_check_kfunc_arg_match() */
mark_btf_func_reg_size(env, regno, t->size);
}
return 0;
}
static bool signed_add_overflows(s64 a, s64 b)
{
/* Do the add in u64, where overflow is well-defined */
s64 res = (s64)((u64)a + (u64)b);
if (b < 0)
return res > a;
return res < a;
}
static bool signed_add32_overflows(s32 a, s32 b)
{
/* Do the add in u32, where overflow is well-defined */
s32 res = (s32)((u32)a + (u32)b);
if (b < 0)
return res > a;
return res < a;
}
static bool signed_sub_overflows(s64 a, s64 b)
{
/* Do the sub in u64, where overflow is well-defined */
s64 res = (s64)((u64)a - (u64)b);
if (b < 0)
return res < a;
return res > a;
}
static bool signed_sub32_overflows(s32 a, s32 b)
{
/* Do the sub in u32, where overflow is well-defined */
s32 res = (s32)((u32)a - (u32)b);
if (b < 0)
return res < a;
return res > a;
}
static bool check_reg_sane_offset(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
enum bpf_reg_type type)
{
bool known = tnum_is_const(reg->var_off);
s64 val = reg->var_off.value;
s64 smin = reg->smin_value;
if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
verbose(env, "math between %s pointer and %lld is not allowed\n",
reg_type_str[type], val);
return false;
}
if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
verbose(env, "%s pointer offset %d is not allowed\n",
reg_type_str[type], reg->off);
return false;
}
if (smin == S64_MIN) {
verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
reg_type_str[type]);
return false;
}
if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
verbose(env, "value %lld makes %s pointer be out of bounds\n",
smin, reg_type_str[type]);
return false;
}
return true;
}
static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
{
return &env->insn_aux_data[env->insn_idx];
}
enum {
REASON_BOUNDS = -1,
REASON_TYPE = -2,
REASON_PATHS = -3,
REASON_LIMIT = -4,
REASON_STACK = -5,
};
static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
const struct bpf_reg_state *off_reg,
u32 *alu_limit, u8 opcode)
{
bool off_is_neg = off_reg->smin_value < 0;
bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
(opcode == BPF_SUB && !off_is_neg);
u32 max = 0, ptr_limit = 0;
if (!tnum_is_const(off_reg->var_off) &&
(off_reg->smin_value < 0) != (off_reg->smax_value < 0))
return REASON_BOUNDS;
switch (ptr_reg->type) {
case PTR_TO_STACK:
/* Offset 0 is out-of-bounds, but acceptable start for the
* left direction, see BPF_REG_FP. Also, unknown scalar
* offset where we would need to deal with min/max bounds is
* currently prohibited for unprivileged.
*/
max = MAX_BPF_STACK + mask_to_left;
ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
break;
case PTR_TO_MAP_VALUE:
max = ptr_reg->map_ptr->value_size;
ptr_limit = (mask_to_left ?
ptr_reg->smin_value :
ptr_reg->umax_value) + ptr_reg->off;
break;
default:
return REASON_TYPE;
}
if (ptr_limit >= max)
return REASON_LIMIT;
*alu_limit = ptr_limit;
return 0;
}
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
}
static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
u32 alu_state, u32 alu_limit)
{
/* If we arrived here from different branches with different
* state or limits to sanitize, then this won't work.
*/
if (aux->alu_state &&
(aux->alu_state != alu_state ||
aux->alu_limit != alu_limit))
return REASON_PATHS;
/* Corresponding fixup done in do_misc_fixups(). */
aux->alu_state = alu_state;
aux->alu_limit = alu_limit;
return 0;
}
static int sanitize_val_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
struct bpf_insn_aux_data *aux = cur_aux(env);
if (can_skip_alu_sanitation(env, insn))
return 0;
return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}
static bool sanitize_needed(u8 opcode)
{
return opcode == BPF_ADD || opcode == BPF_SUB;
}
static int sanitize_ptr_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
const struct bpf_reg_state *off_reg,
struct bpf_reg_state *dst_reg,
struct bpf_insn_aux_data *tmp_aux,
const bool commit_window)
{
struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
struct bpf_verifier_state *vstate = env->cur_state;
bool off_is_neg = off_reg->smin_value < 0;
bool ptr_is_dst_reg = ptr_reg == dst_reg;
u8 opcode = BPF_OP(insn->code);
u32 alu_state, alu_limit;
struct bpf_reg_state tmp;
bool ret;
int err;
if (can_skip_alu_sanitation(env, insn))
return 0;
/* We already marked aux for masking from non-speculative
* paths, thus we got here in the first place. We only care
* to explore bad access from here.
*/
if (vstate->speculative)
goto do_sim;
err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
if (err < 0)
return err;
if (commit_window) {
/* In commit phase we narrow the masking window based on
* the observed pointer move after the simulated operation.
*/
alu_state = tmp_aux->alu_state;
alu_limit = abs(tmp_aux->alu_limit - alu_limit);
} else {
alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
}
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
if (err < 0)
return err;
do_sim:
/* If we're in commit phase, we're done here given we already
* pushed the truncated dst_reg into the speculative verification
* stack.
*/
if (commit_window)
return 0;
/* Simulate and find potential out-of-bounds access under
* speculative execution from truncation as a result of
* masking when off was not within expected range. If off
* sits in dst, then we temporarily need to move ptr there
* to simulate dst (== 0) +/-= ptr. Needed, for example,
* for cases where we use K-based arithmetic in one direction
* and truncated reg-based in the other in order to explore
* bad access.
*/
if (!ptr_is_dst_reg) {
tmp = *dst_reg;
*dst_reg = *ptr_reg;
}
ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
if (!ptr_is_dst_reg && ret)
*dst_reg = tmp;
return !ret ? REASON_STACK : 0;
}
static int sanitize_err(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int reason,
const struct bpf_reg_state *off_reg,
const struct bpf_reg_state *dst_reg)
{
static const char *err = "pointer arithmetic with it prohibited for !root";
const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
u32 dst = insn->dst_reg, src = insn->src_reg;
switch (reason) {
case REASON_BOUNDS:
verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
off_reg == dst_reg ? dst : src, err);
break;
case REASON_TYPE:
verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
off_reg == dst_reg ? src : dst, err);
break;
case REASON_PATHS:
verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
dst, op, err);
break;
case REASON_LIMIT:
verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
dst, op, err);
break;
case REASON_STACK:
verbose(env, "R%d could not be pushed for speculative verification, %s\n",
dst, err);
break;
default:
verbose(env, "verifier internal error: unknown reason (%d)\n",
reason);
break;
}
return -EACCES;
}
/* check that stack access falls within stack limits and that 'reg' doesn't
* have a variable offset.
*
* Variable offset is prohibited for unprivileged mode for simplicity since it
* requires corresponding support in Spectre masking for stack ALU. See also
* retrieve_ptr_limit().
*
*
* 'off' includes 'reg->off'.
*/
static int check_stack_access_for_ptr_arithmetic(
struct bpf_verifier_env *env,
int regno,
const struct bpf_reg_state *reg,
int off)
{
if (!tnum_is_const(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n",
regno, tn_buf, off);
return -EACCES;
}
if (off >= 0 || off < -MAX_BPF_STACK) {
verbose(env, "R%d stack pointer arithmetic goes out of range, "
"prohibited for !root; off=%d\n", regno, off);
return -EACCES;
}
return 0;
}
static int sanitize_check_bounds(struct bpf_verifier_env *env,
const struct bpf_insn *insn,
const struct bpf_reg_state *dst_reg)
{
u32 dst = insn->dst_reg;
/* For unprivileged we require that resulting offset must be in bounds
* in order to be able to sanitize access later on.
*/
if (env->bypass_spec_v1)
return 0;
switch (dst_reg->type) {
case PTR_TO_STACK:
if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
dst_reg->off + dst_reg->var_off.value))
return -EACCES;
break;
case PTR_TO_MAP_VALUE:
if (check_map_access(env, dst, dst_reg->off, 1, false)) {
verbose(env, "R%d pointer arithmetic of map value goes out of range, "
"prohibited for !root\n", dst);
return -EACCES;
}
break;
default:
break;
}
return 0;
}
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
* If we return -EACCES, caller may want to try again treating pointer as a
* scalar. So we only emit a diagnostic if !env->allow_ptr_leaks.
*/
static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
const struct bpf_reg_state *off_reg)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs, *dst_reg;
bool known = tnum_is_const(off_reg->var_off);
s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
struct bpf_insn_aux_data tmp_aux = {};
u8 opcode = BPF_OP(insn->code);
u32 dst = insn->dst_reg;
int ret;
dst_reg = ®s[dst];
if ((known && (smin_val != smax_val || umin_val != umax_val)) ||
smin_val > smax_val || umin_val > umax_val) {
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
__mark_reg_unknown(env, dst_reg);
return 0;
}
if (BPF_CLASS(insn->code) != BPF_ALU64) {
/* 32-bit ALU ops on pointers produce (meaningless) scalars */
if (opcode == BPF_SUB && env->allow_ptr_leaks) {
__mark_reg_unknown(env, dst_reg);
return 0;
}
verbose(env,
"R%d 32-bit pointer arithmetic prohibited\n",
dst);
return -EACCES;
}
switch (ptr_reg->type) {
case PTR_TO_MAP_VALUE_OR_NULL:
verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
case CONST_PTR_TO_MAP:
/* smin_val represents the known value */
if (known && smin_val == 0 && opcode == BPF_ADD)
break;
fallthrough;
case PTR_TO_PACKET_END:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
default:
break;
}
/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
* The id may be overwritten later if we create a new variable offset.
*/
dst_reg->type = ptr_reg->type;
dst_reg->id = ptr_reg->id;
if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
!check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
return -EINVAL;
/* pointer types do not carry 32-bit bounds at the moment. */
__mark_reg32_unbounded(dst_reg);
if (sanitize_needed(opcode)) {
ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
&tmp_aux, false);
if (ret < 0)
return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
switch (opcode) {
case BPF_ADD:
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
if (known && (ptr_reg->off + smin_val ==
(s64)(s32)(ptr_reg->off + smin_val))) {
/* pointer += K. Accumulate it into fixed offset */
dst_reg->smin_value = smin_ptr;
dst_reg->smax_value = smax_ptr;
dst_reg->umin_value = umin_ptr;
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->off = ptr_reg->off + smin_val;
dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. Note that off_reg->off
* == 0, since it's a scalar.
* dst_reg gets the pointer type and since some positive
* integer value was added to the pointer, give it a new 'id'
* if it's a PTR_TO_PACKET.
* this creates a new 'base' pointer, off_reg (variable) gets
* added into the variable offset, and we copy the fixed offset
* from ptr_reg.
*/
if (signed_add_overflows(smin_ptr, smin_val) ||
signed_add_overflows(smax_ptr, smax_val)) {
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = smin_ptr + smin_val;
dst_reg->smax_value = smax_ptr + smax_val;
}
if (umin_ptr + umin_val < umin_ptr ||
umax_ptr + umax_val < umax_ptr) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value = umin_ptr + umin_val;
dst_reg->umax_value = umax_ptr + umax_val;
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
}
break;
case BPF_SUB:
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
dst);
return -EACCES;
}
/* We don't allow subtraction from FP, because (according to
* test_verifier.c test "invalid fp arithmetic", JITs might not
* be able to deal with it.
*/
if (ptr_reg->type == PTR_TO_STACK) {
verbose(env, "R%d subtraction from stack pointer prohibited\n",
dst);
return -EACCES;
}
if (known && (ptr_reg->off - smin_val ==
(s64)(s32)(ptr_reg->off - smin_val))) {
/* pointer -= K. Subtract it from fixed offset */
dst_reg->smin_value = smin_ptr;
dst_reg->smax_value = smax_ptr;
dst_reg->umin_value = umin_ptr;
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->id = ptr_reg->id;
dst_reg->off = ptr_reg->off - smin_val;
dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. If the subtrahend is known
* nonnegative, then any reg->range we had before is still good.
*/
if (signed_sub_overflows(smin_ptr, smax_val) ||
signed_sub_overflows(smax_ptr, smin_val)) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = smin_ptr - smax_val;
dst_reg->smax_value = smax_ptr - smin_val;
}
if (umin_ptr < umax_val) {
/* Overflow possible, we know nothing */
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
/* Cannot overflow (as long as bounds are consistent) */
dst_reg->umin_value = umin_ptr - umax_val;
dst_reg->umax_value = umax_ptr - umin_val;
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
}
break;
case BPF_AND:
case BPF_OR:
case BPF_XOR:
/* bitwise ops on pointers are troublesome, prohibit. */
verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
default:
/* other operators (e.g. MUL,LSH) produce non-pointer results */
verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
dst, bpf_alu_string[opcode >> 4]);
return -EACCES;
}
if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
return -EINVAL;
__update_reg_bounds(dst_reg);
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
if (sanitize_check_bounds(env, insn, dst_reg) < 0)
return -EACCES;
if (sanitize_needed(opcode)) {
ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
&tmp_aux, true);
if (ret < 0)
return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
return 0;
}
static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s32 smin_val = src_reg->s32_min_value;
s32 smax_val = src_reg->s32_max_value;
u32 umin_val = src_reg->u32_min_value;
u32 umax_val = src_reg->u32_max_value;
if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) ||
signed_add32_overflows(dst_reg->s32_max_value, smax_val)) {
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
} else {
dst_reg->s32_min_value += smin_val;
dst_reg->s32_max_value += smax_val;
}
if (dst_reg->u32_min_value + umin_val < umin_val ||
dst_reg->u32_max_value + umax_val < umax_val) {
dst_reg->u32_min_value = 0;
dst_reg->u32_max_value = U32_MAX;
} else {
dst_reg->u32_min_value += umin_val;
dst_reg->u32_max_value += umax_val;
}
}
static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s64 smin_val = src_reg->smin_value;
s64 smax_val = src_reg->smax_value;
u64 umin_val = src_reg->umin_value;
u64 umax_val = src_reg->umax_value;
if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
signed_add_overflows(dst_reg->smax_value, smax_val)) {
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value += smin_val;
dst_reg->smax_value += smax_val;
}
if (dst_reg->umin_value + umin_val < umin_val ||
dst_reg->umax_value + umax_val < umax_val) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value += umin_val;
dst_reg->umax_value += umax_val;
}
}
static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s32 smin_val = src_reg->s32_min_value;
s32 smax_val = src_reg->s32_max_value;
u32 umin_val = src_reg->u32_min_value;
u32 umax_val = src_reg->u32_max_value;
if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) ||
signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) {
/* Overflow possible, we know nothing */
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
} else {
dst_reg->s32_min_value -= smax_val;
dst_reg->s32_max_value -= smin_val;
}
if (dst_reg->u32_min_value < umax_val) {
/* Overflow possible, we know nothing */
dst_reg->u32_min_value = 0;
dst_reg->u32_max_value = U32_MAX;
} else {
/* Cannot overflow (as long as bounds are consistent) */
dst_reg->u32_min_value -= umax_val;
dst_reg->u32_max_value -= umin_val;
}
}
static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s64 smin_val = src_reg->smin_value;
s64 smax_val = src_reg->smax_value;
u64 umin_val = src_reg->umin_value;
u64 umax_val = src_reg->umax_value;
if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
signed_sub_overflows(dst_reg->smax_value, smin_val)) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value -= smax_val;
dst_reg->smax_value -= smin_val;
}
if (dst_reg->umin_value < umax_val) {
/* Overflow possible, we know nothing */
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
/* Cannot overflow (as long as bounds are consistent) */
dst_reg->umin_value -= umax_val;
dst_reg->umax_value -= umin_val;
}
}
static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s32 smin_val = src_reg->s32_min_value;
u32 umin_val = src_reg->u32_min_value;
u32 umax_val = src_reg->u32_max_value;
if (smin_val < 0 || dst_reg->s32_min_value < 0) {
/* Ain't nobody got time to multiply that sign */
__mark_reg32_unbounded(dst_reg);
return;
}
/* Both values are positive, so we can work with unsigned and
* copy the result to signed (unless it exceeds S32_MAX).
*/
if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) {
/* Potential overflow, we know nothing */
__mark_reg32_unbounded(dst_reg);
return;
}
dst_reg->u32_min_value *= umin_val;
dst_reg->u32_max_value *= umax_val;
if (dst_reg->u32_max_value > S32_MAX) {
/* Overflow possible, we know nothing */
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
} else {
dst_reg->s32_min_value = dst_reg->u32_min_value;
dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
static void scalar_min_max_mul(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
s64 smin_val = src_reg->smin_value;
u64 umin_val = src_reg->umin_value;
u64 umax_val = src_reg->umax_value;
if (smin_val < 0 || dst_reg->smin_value < 0) {
/* Ain't nobody got time to multiply that sign */
__mark_reg64_unbounded(dst_reg);
return;
}
/* Both values are positive, so we can work with unsigned and
* copy the result to signed (unless it exceeds S64_MAX).
*/
if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
/* Potential overflow, we know nothing */
__mark_reg64_unbounded(dst_reg);
return;
}
dst_reg->umin_value *= umin_val;
dst_reg->umax_value *= umax_val;
if (dst_reg->umax_value > S64_MAX) {
/* Overflow possible, we know nothing */
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
}
static void scalar32_min_max_and(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
s32 smin_val = src_reg->s32_min_value;
u32 umax_val = src_reg->u32_max_value;
/* Assuming scalar64_min_max_and will be called so its safe
* to skip updating register for known 32-bit case.
*/
if (src_known && dst_known)
return;
/* We get our minimum from the var_off, since that's inherently
* bitwise. Our maximum is the minimum of the operands' maxima.
*/
dst_reg->u32_min_value = var32_off.value;
dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val);
if (dst_reg->s32_min_value < 0 || smin_val < 0) {
/* Lose signed bounds when ANDing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
} else {
/* ANDing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->s32_min_value = dst_reg->u32_min_value;
dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
static void scalar_min_max_and(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_is_const(src_reg->var_off);
bool dst_known = tnum_is_const(dst_reg->var_off);
s64 smin_val = src_reg->smin_value;
u64 umax_val = src_reg->umax_value;
if (src_known && dst_known) {
__mark_reg_known(dst_reg, dst_reg->var_off.value);
return;
}
/* We get our minimum from the var_off, since that's inherently
* bitwise. Our maximum is the minimum of the operands' maxima.
*/
dst_reg->umin_value = dst_reg->var_off.value;
dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
if (dst_reg->smin_value < 0 || smin_val < 0) {
/* Lose signed bounds when ANDing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
/* ANDing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
}
static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
s32 smin_val = src_reg->s32_min_value;
u32 umin_val = src_reg->u32_min_value;
/* Assuming scalar64_min_max_or will be called so it is safe
* to skip updating register for known case.
*/
if (src_known && dst_known)
return;
/* We get our maximum from the var_off, and our minimum is the
* maximum of the operands' minima
*/
dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val);
dst_reg->u32_max_value = var32_off.value | var32_off.mask;
if (dst_reg->s32_min_value < 0 || smin_val < 0) {
/* Lose signed bounds when ORing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
} else {
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->s32_min_value = dst_reg->u32_min_value;
dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
static void scalar_min_max_or(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_is_const(src_reg->var_off);
bool dst_known = tnum_is_const(dst_reg->var_off);
s64 smin_val = src_reg->smin_value;
u64 umin_val = src_reg->umin_value;
if (src_known && dst_known) {
__mark_reg_known(dst_reg, dst_reg->var_off.value);
return;
}
/* We get our maximum from the var_off, and our minimum is the
* maximum of the operands' minima
*/
dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask;
if (dst_reg->smin_value < 0 || smin_val < 0) {
/* Lose signed bounds when ORing negative numbers,
* ain't nobody got time for that.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
} else {
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
}
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
}
static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
s32 smin_val = src_reg->s32_min_value;
/* Assuming scalar64_min_max_xor will be called so it is safe
* to skip updating register for known case.
*/
if (src_known && dst_known)
return;
/* We get both minimum and maximum from the var32_off. */
dst_reg->u32_min_value = var32_off.value;
dst_reg->u32_max_value = var32_off.value | var32_off.mask;
if (dst_reg->s32_min_value >= 0 && smin_val >= 0) {
/* XORing two positive sign numbers gives a positive,
* so safe to cast u32 result into s32.
*/
dst_reg->s32_min_value = dst_reg->u32_min_value;
dst_reg->s32_max_value = dst_reg->u32_max_value;
} else {
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
}
}
static void scalar_min_max_xor(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
bool src_known = tnum_is_const(src_reg->var_off);
bool dst_known = tnum_is_const(dst_reg->var_off);
s64 smin_val = src_reg->smin_value;
if (src_known && dst_known) {
/* dst_reg->var_off.value has been updated earlier */
__mark_reg_known(dst_reg, dst_reg->var_off.value);
return;
}
/* We get both minimum and maximum from the var_off. */
dst_reg->umin_value = dst_reg->var_off.value;
dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask;
if (dst_reg->smin_value >= 0 && smin_val >= 0) {
/* XORing two positive sign numbers gives a positive,
* so safe to cast u64 result into s64.
*/
dst_reg->smin_value = dst_reg->umin_value;
dst_reg->smax_value = dst_reg->umax_value;
} else {
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
}
__update_reg_bounds(dst_reg);
}
static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
u64 umin_val, u64 umax_val)
{
/* We lose all sign bit information (except what we can pick
* up from var_off)
*/
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
/* If we might shift our top bit out, then we know nothing */
if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) {
dst_reg->u32_min_value = 0;
dst_reg->u32_max_value = U32_MAX;
} else {
dst_reg->u32_min_value <<= umin_val;
dst_reg->u32_max_value <<= umax_val;
}
}
static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
u32 umax_val = src_reg->u32_max_value;
u32 umin_val = src_reg->u32_min_value;
/* u32 alu operation will zext upper bits */
struct tnum subreg = tnum_subreg(dst_reg->var_off);
__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val));
/* Not required but being careful mark reg64 bounds as unknown so
* that we are forced to pick them up from tnum and zext later and
* if some path skips this step we are still safe.
*/
__mark_reg64_unbounded(dst_reg);
__update_reg32_bounds(dst_reg);
}
static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg,
u64 umin_val, u64 umax_val)
{
/* Special case <<32 because it is a common compiler pattern to sign
* extend subreg by doing <<32 s>>32. In this case if 32bit bounds are
* positive we know this shift will also be positive so we can track
* bounds correctly. Otherwise we lose all sign bit information except
* what we can pick up from var_off. Perhaps we can generalize this
* later to shifts of any length.
*/
if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0)
dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32;
else
dst_reg->smax_value = S64_MAX;
if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0)
dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32;
else
dst_reg->smin_value = S64_MIN;
/* If we might shift our top bit out, then we know nothing */
if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
} else {
dst_reg->umin_value <<= umin_val;
dst_reg->umax_value <<= umax_val;
}
}
static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
u64 umax_val = src_reg->umax_value;
u64 umin_val = src_reg->umin_value;
/* scalar64 calc uses 32bit unshifted bounds so must be called first */
__scalar64_min_max_lsh(dst_reg, umin_val, umax_val);
__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
}
static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
struct tnum subreg = tnum_subreg(dst_reg->var_off);
u32 umax_val = src_reg->u32_max_value;
u32 umin_val = src_reg->u32_min_value;
/* BPF_RSH is an unsigned shift. If the value in dst_reg might
* be negative, then either:
* 1) src_reg might be zero, so the sign bit of the result is
* unknown, so we lose our signed bounds
* 2) it's known negative, thus the unsigned bounds capture the
* signed bounds
* 3) the signed bounds cross zero, so they tell us nothing
* about the result
* If the value in dst_reg is known nonnegative, then again the
* unsigned bounds capture the signed bounds.
* Thus, in all cases it suffices to blow away our signed bounds
* and rely on inferring new ones from the unsigned bounds and
* var_off of the result.
*/
dst_reg->s32_min_value = S32_MIN;
dst_reg->s32_max_value = S32_MAX;
dst_reg->var_off = tnum_rshift(subreg, umin_val);
dst_reg->u32_min_value >>= umax_val;
dst_reg->u32_max_value >>= umin_val;
__mark_reg64_unbounded(dst_reg);
__update_reg32_bounds(dst_reg);
}
static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
u64 umax_val = src_reg->umax_value;
u64 umin_val = src_reg->umin_value;
/* BPF_RSH is an unsigned shift. If the value in dst_reg might
* be negative, then either:
* 1) src_reg might be zero, so the sign bit of the result is
* unknown, so we lose our signed bounds
* 2) it's known negative, thus the unsigned bounds capture the
* signed bounds
* 3) the signed bounds cross zero, so they tell us nothing
* about the result
* If the value in dst_reg is known nonnegative, then again the
* unsigned bounds capture the signed bounds.
* Thus, in all cases it suffices to blow away our signed bounds
* and rely on inferring new ones from the unsigned bounds and
* var_off of the result.
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
dst_reg->umin_value >>= umax_val;
dst_reg->umax_value >>= umin_val;
/* Its not easy to operate on alu32 bounds here because it depends
* on bits being shifted in. Take easy way out and mark unbounded
* so we can recalculate later from tnum.
*/
__mark_reg32_unbounded(dst_reg);
__update_reg_bounds(dst_reg);
}
static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
u64 umin_val = src_reg->u32_min_value;
/* Upon reaching here, src_known is true and
* umax_val is equal to umin_val.
*/
dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val);
dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val);
dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32);
/* blow away the dst_reg umin_value/umax_value and rely on
* dst_reg var_off to refine the result.
*/
dst_reg->u32_min_value = 0;
dst_reg->u32_max_value = U32_MAX;
__mark_reg64_unbounded(dst_reg);
__update_reg32_bounds(dst_reg);
}
static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg)
{
u64 umin_val = src_reg->umin_value;
/* Upon reaching here, src_known is true and umax_val is equal
* to umin_val.
*/
dst_reg->smin_value >>= umin_val;
dst_reg->smax_value >>= umin_val;
dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64);
/* blow away the dst_reg umin_value/umax_value and rely on
* dst_reg var_off to refine the result.
*/
dst_reg->umin_value = 0;
dst_reg->umax_value = U64_MAX;
/* Its not easy to operate on alu32 bounds here because it depends
* on bits being shifted in from upper 32-bits. Take easy way out
* and mark unbounded so we can recalculate later from tnum.
*/
__mark_reg32_unbounded(dst_reg);
__update_reg_bounds(dst_reg);
}
/* WARNING: This function does calculations on 64-bit values, but the actual
* execution may occur on 32-bit values. Therefore, things like bitshifts
* need extra checks in the 32-bit case.
*/
static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn,
struct bpf_reg_state *dst_reg,
struct bpf_reg_state src_reg)
{
struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
bool src_known;
s64 smin_val, smax_val;
u64 umin_val, umax_val;
s32 s32_min_val, s32_max_val;
u32 u32_min_val, u32_max_val;
u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
int ret;
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
umin_val = src_reg.umin_value;
umax_val = src_reg.umax_value;
s32_min_val = src_reg.s32_min_value;
s32_max_val = src_reg.s32_max_value;
u32_min_val = src_reg.u32_min_value;
u32_max_val = src_reg.u32_max_value;
if (alu32) {
src_known = tnum_subreg_is_const(src_reg.var_off);
if ((src_known &&
(s32_min_val != s32_max_val || u32_min_val != u32_max_val)) ||
s32_min_val > s32_max_val || u32_min_val > u32_max_val) {
/* Taint dst register if offset had invalid bounds
* derived from e.g. dead branches.
*/
__mark_reg_unknown(env, dst_reg);
return 0;
}
} else {
src_known = tnum_is_const(src_reg.var_off);
if ((src_known &&
(smin_val != smax_val || umin_val != umax_val)) ||
smin_val > smax_val || umin_val > umax_val) {
/* Taint dst register if offset had invalid bounds
* derived from e.g. dead branches.
*/
__mark_reg_unknown(env, dst_reg);
return 0;
}
}
if (!src_known &&
opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
__mark_reg_unknown(env, dst_reg);
return 0;
}
if (sanitize_needed(opcode)) {
ret = sanitize_val_alu(env, insn);
if (ret < 0)
return sanitize_err(env, insn, ret, NULL, NULL);
}
/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
* There are two classes of instructions: The first class we track both
* alu32 and alu64 sign/unsigned bounds independently this provides the
* greatest amount of precision when alu operations are mixed with jmp32
* operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD,
* and BPF_OR. This is possible because these ops have fairly easy to
* understand and calculate behavior in both 32-bit and 64-bit alu ops.
* See alu32 verifier tests for examples. The second class of
* operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy
* with regards to tracking sign/unsigned bounds because the bits may
* cross subreg boundaries in the alu64 case. When this happens we mark
* the reg unbounded in the subreg bound space and use the resulting
* tnum to calculate an approximation of the sign/unsigned bounds.
*/
switch (opcode) {
case BPF_ADD:
scalar32_min_max_add(dst_reg, &src_reg);
scalar_min_max_add(dst_reg, &src_reg);
dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
break;
case BPF_SUB:
scalar32_min_max_sub(dst_reg, &src_reg);
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
break;
case BPF_MUL:
dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_mul(dst_reg, &src_reg);
scalar_min_max_mul(dst_reg, &src_reg);
break;
case BPF_AND:
dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_and(dst_reg, &src_reg);
scalar_min_max_and(dst_reg, &src_reg);
break;
case BPF_OR:
dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_or(dst_reg, &src_reg);
scalar_min_max_or(dst_reg, &src_reg);
break;
case BPF_XOR:
dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_xor(dst_reg, &src_reg);
scalar_min_max_xor(dst_reg, &src_reg);
break;
case BPF_LSH:
if (umax_val >= insn_bitness) {
/* Shifts greater than 31 or 63 are undefined.
* This includes shifts by a negative number.
*/
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
if (alu32)
scalar32_min_max_lsh(dst_reg, &src_reg);
else
scalar_min_max_lsh(dst_reg, &src_reg);
break;
case BPF_RSH:
if (umax_val >= insn_bitness) {
/* Shifts greater than 31 or 63 are undefined.
* This includes shifts by a negative number.
*/
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
if (alu32)
scalar32_min_max_rsh(dst_reg, &src_reg);
else
scalar_min_max_rsh(dst_reg, &src_reg);
break;
case BPF_ARSH:
if (umax_val >= insn_bitness) {
/* Shifts greater than 31 or 63 are undefined.
* This includes shifts by a negative number.
*/
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
if (alu32)
scalar32_min_max_arsh(dst_reg, &src_reg);
else
scalar_min_max_arsh(dst_reg, &src_reg);
break;
default:
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
/* ALU32 ops are zero extended into 64bit register */
if (alu32)
zext_32_to_64(dst_reg);
__update_reg_bounds(dst_reg);
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
return 0;
}
/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max
* and var_off.
*/
static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
u8 opcode = BPF_OP(insn->code);
int err;
dst_reg = ®s[insn->dst_reg];
src_reg = NULL;
if (dst_reg->type != SCALAR_VALUE)
ptr_reg = dst_reg;
else
/* Make sure ID is cleared otherwise dst_reg min/max could be
* incorrectly propagated into other registers by find_equal_scalars()
*/
dst_reg->id = 0;
if (BPF_SRC(insn->code) == BPF_X) {
src_reg = ®s[insn->src_reg];
if (src_reg->type != SCALAR_VALUE) {
if (dst_reg->type != SCALAR_VALUE) {
/* Combining two pointers by any ALU op yields
* an arbitrary scalar. Disallow all math except
* pointer subtraction
*/
if (opcode == BPF_SUB && env->allow_ptr_leaks) {
mark_reg_unknown(env, regs, insn->dst_reg);
return 0;
}
verbose(env, "R%d pointer %s pointer prohibited\n",
insn->dst_reg,
bpf_alu_string[opcode >> 4]);
return -EACCES;
} else {
/* scalar += pointer
* This is legal, but we have to reverse our
* src/dest handling in computing the range
*/
err = mark_chain_precision(env, insn->dst_reg);
if (err)
return err;
return adjust_ptr_min_max_vals(env, insn,
src_reg, dst_reg);
}
} else if (ptr_reg) {
/* pointer += scalar */
err = mark_chain_precision(env, insn->src_reg);
if (err)
return err;
return adjust_ptr_min_max_vals(env, insn,
dst_reg, src_reg);
}
} else {
/* Pretend the src is a reg with a known value, since we only
* need to be able to read from this state.
*/
off_reg.type = SCALAR_VALUE;
__mark_reg_known(&off_reg, insn->imm);
src_reg = &off_reg;
if (ptr_reg) /* pointer += K */
return adjust_ptr_min_max_vals(env, insn,
ptr_reg, src_reg);
}
/* Got here implies adding two SCALAR_VALUEs */
if (WARN_ON_ONCE(ptr_reg)) {
print_verifier_state(env, state);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
return -EINVAL;
}
if (WARN_ON(!src_reg)) {
print_verifier_state(env, state);
verbose(env, "verifier internal error: no src_reg\n");
return -EINVAL;
}
return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
}
/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
int err;
if (opcode == BPF_END || opcode == BPF_NEG) {
if (opcode == BPF_NEG) {
if (BPF_SRC(insn->code) != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->off != 0 || insn->imm != 0) {
verbose(env, "BPF_NEG uses reserved fields\n");
return -EINVAL;
}
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
BPF_CLASS(insn->code) == BPF_ALU64) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
}
/* check src operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->dst_reg)) {
verbose(env, "R%d pointer arithmetic prohibited\n",
insn->dst_reg);
return -EACCES;
}
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP);
if (err)
return err;
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
}
/* check dest operand, mark as required later */
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
if (BPF_SRC(insn->code) == BPF_X) {
struct bpf_reg_state *src_reg = regs + insn->src_reg;
struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
/* case: R1 = R2
* copy register state to dest reg
*/
if (src_reg->type == SCALAR_VALUE && !src_reg->id)
/* Assign src and dst registers the same ID
* that will be used by find_equal_scalars()
* to propagate min/max range.
*/
src_reg->id = ++env->id_gen;
*dst_reg = *src_reg;
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = DEF_NOT_SUBREG;
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
verbose(env,
"R%d partial copy of pointer\n",
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
*dst_reg = *src_reg;
/* Make sure ID is cleared otherwise
* dst_reg min/max could be incorrectly
* propagated into src_reg by find_equal_scalars()
*/
dst_reg->id = 0;
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = env->insn_idx + 1;
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
}
zext_32_to_64(dst_reg);
}
} else {
/* case: R = imm
* remember the value we stored into this reg
*/
/* clear any state __mark_reg_known doesn't set */
mark_reg_unknown(env, regs, insn->dst_reg);
regs[insn->dst_reg].type = SCALAR_VALUE;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
__mark_reg_known(regs + insn->dst_reg,
insn->imm);
} else {
__mark_reg_known(regs + insn->dst_reg,
(u32)insn->imm);
}
}
} else if (opcode > BPF_END) {
verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
return -EINVAL;
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
}
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
verbose(env, "div by zero\n");
return -EINVAL;
}
if ((opcode == BPF_LSH || opcode == BPF_RSH ||
opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
if (insn->imm < 0 || insn->imm >= size) {
verbose(env, "invalid shift %d\n", insn->imm);
return -EINVAL;
}
}
/* check dest operand */
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
return adjust_reg_min_max_vals(env, insn);
}
return 0;
}
static void __find_good_pkt_pointers(struct bpf_func_state *state,
struct bpf_reg_state *dst_reg,
enum bpf_reg_type type, int new_range)
{
struct bpf_reg_state *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
reg = &state->regs[i];
if (reg->type == type && reg->id == dst_reg->id)
/* keep the maximum range already checked */
reg->range = max(reg->range, new_range);
}
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
if (reg->type == type && reg->id == dst_reg->id)
reg->range = max(reg->range, new_range);
}
}
static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
struct bpf_reg_state *dst_reg,
enum bpf_reg_type type,
bool range_right_open)
{
int new_range, i;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
/* This doesn't give us any range */
return;
if (dst_reg->umax_value > MAX_PACKET_OFF ||
dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF)
/* Risk of overflow. For instance, ptr + (1<<63) may be less
* than pkt_end, but that's because it's also less than pkt.
*/
return;
new_range = dst_reg->off;
if (range_right_open)
new_range--;
/* Examples for register markings:
*
* pkt_data in dst register:
*
* r2 = r3;
* r2 += 8;
* if (r2 > pkt_end) goto <handle exception>
* <access okay>
*
* r2 = r3;
* r2 += 8;
* if (r2 < pkt_end) goto <access okay>
* <handle exception>
*
* Where:
* r2 == dst_reg, pkt_end == src_reg
* r2=pkt(id=n,off=8,r=0)
* r3=pkt(id=n,off=0,r=0)
*
* pkt_data in src register:
*
* r2 = r3;
* r2 += 8;
* if (pkt_end >= r2) goto <access okay>
* <handle exception>
*
* r2 = r3;
* r2 += 8;
* if (pkt_end <= r2) goto <handle exception>
* <access okay>
*
* Where:
* pkt_end == dst_reg, r2 == src_reg
* r2=pkt(id=n,off=8,r=0)
* r3=pkt(id=n,off=0,r=0)
*
* Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
* or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
* and [r3, r3 + 8-1) respectively is safe to access depending on
* the check.
*/
/* If our ids match, then we must have the same max_value. And we
* don't care about the other reg's fixed offset, since if it's too big
* the range won't allow anything.
* dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
*/
for (i = 0; i <= vstate->curframe; i++)
__find_good_pkt_pointers(vstate->frame[i], dst_reg, type,
new_range);
}
static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
{
struct tnum subreg = tnum_subreg(reg->var_off);
s32 sval = (s32)val;
switch (opcode) {
case BPF_JEQ:
if (tnum_is_const(subreg))
return !!tnum_equals_const(subreg, val);
break;
case BPF_JNE:
if (tnum_is_const(subreg))
return !tnum_equals_const(subreg, val);
break;
case BPF_JSET:
if ((~subreg.mask & subreg.value) & val)
return 1;
if (!((subreg.mask | subreg.value) & val))
return 0;
break;
case BPF_JGT:
if (reg->u32_min_value > val)
return 1;
else if (reg->u32_max_value <= val)
return 0;
break;
case BPF_JSGT:
if (reg->s32_min_value > sval)
return 1;
else if (reg->s32_max_value <= sval)
return 0;
break;
case BPF_JLT:
if (reg->u32_max_value < val)
return 1;
else if (reg->u32_min_value >= val)
return 0;
break;
case BPF_JSLT:
if (reg->s32_max_value < sval)
return 1;
else if (reg->s32_min_value >= sval)
return 0;
break;
case BPF_JGE:
if (reg->u32_min_value >= val)
return 1;
else if (reg->u32_max_value < val)
return 0;
break;
case BPF_JSGE:
if (reg->s32_min_value >= sval)
return 1;
else if (reg->s32_max_value < sval)
return 0;
break;
case BPF_JLE:
if (reg->u32_max_value <= val)
return 1;
else if (reg->u32_min_value > val)
return 0;
break;
case BPF_JSLE:
if (reg->s32_max_value <= sval)
return 1;
else if (reg->s32_min_value > sval)
return 0;
break;
}
return -1;
}
static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
{
s64 sval = (s64)val;
switch (opcode) {
case BPF_JEQ:
if (tnum_is_const(reg->var_off))
return !!tnum_equals_const(reg->var_off, val);
break;
case BPF_JNE:
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
break;
case BPF_JSET:
if ((~reg->var_off.mask & reg->var_off.value) & val)
return 1;
if (!((reg->var_off.mask | reg->var_off.value) & val))
return 0;
break;
case BPF_JGT:
if (reg->umin_value > val)
return 1;
else if (reg->umax_value <= val)
return 0;
break;
case BPF_JSGT:
if (reg->smin_value > sval)
return 1;
else if (reg->smax_value <= sval)
return 0;
break;
case BPF_JLT:
if (reg->umax_value < val)
return 1;
else if (reg->umin_value >= val)
return 0;
break;
case BPF_JSLT:
if (reg->smax_value < sval)
return 1;
else if (reg->smin_value >= sval)
return 0;
break;
case BPF_JGE:
if (reg->umin_value >= val)
return 1;
else if (reg->umax_value < val)
return 0;
break;
case BPF_JSGE:
if (reg->smin_value >= sval)
return 1;
else if (reg->smax_value < sval)
return 0;
break;
case BPF_JLE:
if (reg->umax_value <= val)
return 1;
else if (reg->umin_value > val)
return 0;
break;
case BPF_JSLE:
if (reg->smax_value <= sval)
return 1;
else if (reg->smin_value > sval)
return 0;
break;
}
return -1;
}
/* compute branch direction of the expression "if (reg opcode val) goto target;"
* and return:
* 1 - branch will be taken and "goto target" will be executed
* 0 - branch will not be taken and fall-through to next insn
* -1 - unknown. Example: "if (reg < 5)" is unknown when register value
* range [0,10]
*/
static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
bool is_jmp32)
{
if (__is_pointer_value(false, reg)) {
if (!reg_type_not_null(reg->type))
return -1;
/* If pointer is valid tests against zero will fail so we can
* use this to direct branch taken.
*/
if (val != 0)
return -1;
switch (opcode) {
case BPF_JEQ:
return 0;
case BPF_JNE:
return 1;
default:
return -1;
}
}
if (is_jmp32)
return is_branch32_taken(reg, val, opcode);
return is_branch64_taken(reg, val, opcode);
}
static int flip_opcode(u32 opcode)
{
/* How can we transform "a <op> b" into "b <op> a"? */
static const u8 opcode_flip[16] = {
/* these stay the same */
[BPF_JEQ >> 4] = BPF_JEQ,
[BPF_JNE >> 4] = BPF_JNE,
[BPF_JSET >> 4] = BPF_JSET,
/* these swap "lesser" and "greater" (L and G in the opcodes) */
[BPF_JGE >> 4] = BPF_JLE,
[BPF_JGT >> 4] = BPF_JLT,
[BPF_JLE >> 4] = BPF_JGE,
[BPF_JLT >> 4] = BPF_JGT,
[BPF_JSGE >> 4] = BPF_JSLE,
[BPF_JSGT >> 4] = BPF_JSLT,
[BPF_JSLE >> 4] = BPF_JSGE,
[BPF_JSLT >> 4] = BPF_JSGT
};
return opcode_flip[opcode >> 4];
}
static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg,
u8 opcode)
{
struct bpf_reg_state *pkt;
if (src_reg->type == PTR_TO_PACKET_END) {
pkt = dst_reg;
} else if (dst_reg->type == PTR_TO_PACKET_END) {
pkt = src_reg;
opcode = flip_opcode(opcode);
} else {
return -1;
}
if (pkt->range >= 0)
return -1;
switch (opcode) {
case BPF_JLE:
/* pkt <= pkt_end */
fallthrough;
case BPF_JGT:
/* pkt > pkt_end */
if (pkt->range == BEYOND_PKT_END)
/* pkt has at last one extra byte beyond pkt_end */
return opcode == BPF_JGT;
break;
case BPF_JLT:
/* pkt < pkt_end */
fallthrough;
case BPF_JGE:
/* pkt >= pkt_end */
if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
return opcode == BPF_JGE;
break;
}
return -1;
}
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
* In JEQ/JNE cases we also adjust the var_off values.
*/
static void reg_set_min_max(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg,
u64 val, u32 val32,
u8 opcode, bool is_jmp32)
{
struct tnum false_32off = tnum_subreg(false_reg->var_off);
struct tnum false_64off = false_reg->var_off;
struct tnum true_32off = tnum_subreg(true_reg->var_off);
struct tnum true_64off = true_reg->var_off;
s64 sval = (s64)val;
s32 sval32 = (s32)val32;
/* If the dst_reg is a pointer, we can't learn anything about its
* variable offset from the compare (unless src_reg were a pointer into
* the same object, but we don't bother with that.
* Since false_reg and true_reg have the same type by construction, we
* only need to check one of them for pointerness.
*/
if (__is_pointer_value(false, false_reg))
return;
switch (opcode) {
case BPF_JEQ:
case BPF_JNE:
{
struct bpf_reg_state *reg =
opcode == BPF_JEQ ? true_reg : false_reg;
/* JEQ/JNE comparison doesn't change the register equivalence.
* r1 = r2;
* if (r1 == 42) goto label;
* ...
* label: // here both r1 and r2 are known to be 42.
*
* Hence when marking register as known preserve it's ID.
*/
if (is_jmp32)
__mark_reg32_known(reg, val32);
else
___mark_reg_known(reg, val);
break;
}
case BPF_JSET:
if (is_jmp32) {
false_32off = tnum_and(false_32off, tnum_const(~val32));
if (is_power_of_2(val32))
true_32off = tnum_or(true_32off,
tnum_const(val32));
} else {
false_64off = tnum_and(false_64off, tnum_const(~val));
if (is_power_of_2(val))
true_64off = tnum_or(true_64off,
tnum_const(val));
}
break;
case BPF_JGE:
case BPF_JGT:
{
if (is_jmp32) {
u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1;
u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
false_reg->u32_max_value = min(false_reg->u32_max_value,
false_umax);
true_reg->u32_min_value = max(true_reg->u32_min_value,
true_umin);
} else {
u64 false_umax = opcode == BPF_JGT ? val : val - 1;
u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
false_reg->umax_value = min(false_reg->umax_value, false_umax);
true_reg->umin_value = max(true_reg->umin_value, true_umin);
}
break;
}
case BPF_JSGE:
case BPF_JSGT:
{
if (is_jmp32) {
s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1;
s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
} else {
s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1;
s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
false_reg->smax_value = min(false_reg->smax_value, false_smax);
true_reg->smin_value = max(true_reg->smin_value, true_smin);
}
break;
}
case BPF_JLE:
case BPF_JLT:
{
if (is_jmp32) {
u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1;
u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
false_reg->u32_min_value = max(false_reg->u32_min_value,
false_umin);
true_reg->u32_max_value = min(true_reg->u32_max_value,
true_umax);
} else {
u64 false_umin = opcode == BPF_JLT ? val : val + 1;
u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
false_reg->umin_value = max(false_reg->umin_value, false_umin);
true_reg->umax_value = min(true_reg->umax_value, true_umax);
}
break;
}
case BPF_JSLE:
case BPF_JSLT:
{
if (is_jmp32) {
s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1;
s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
} else {
s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1;
s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
false_reg->smin_value = max(false_reg->smin_value, false_smin);
true_reg->smax_value = min(true_reg->smax_value, true_smax);
}
break;
}
default:
return;
}
if (is_jmp32) {
false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
tnum_subreg(false_32off));
true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
tnum_subreg(true_32off));
__reg_combine_32_into_64(false_reg);
__reg_combine_32_into_64(true_reg);
} else {
false_reg->var_off = false_64off;
true_reg->var_off = true_64off;
__reg_combine_64_into_32(false_reg);
__reg_combine_64_into_32(true_reg);
}
}
/* Same as above, but for the case that dst_reg holds a constant and src_reg is
* the variable reg.
*/
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
struct bpf_reg_state *false_reg,
u64 val, u32 val32,
u8 opcode, bool is_jmp32)
{
opcode = flip_opcode(opcode);
/* This uses zero as "not present in table"; luckily the zero opcode,
* BPF_JA, can't get here.
*/
if (opcode)
reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
}
/* Regs are known to be equal, so intersect their min/max/var_off */
static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
struct bpf_reg_state *dst_reg)
{
src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
dst_reg->umin_value);
src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
dst_reg->umax_value);
src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
dst_reg->smin_value);
src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
dst_reg->smax_value);
src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
dst_reg->var_off);
/* We might have learned new bounds from the var_off. */
__update_reg_bounds(src_reg);
__update_reg_bounds(dst_reg);
/* We might have learned something about the sign bit. */
__reg_deduce_bounds(src_reg);
__reg_deduce_bounds(dst_reg);
/* We might have learned some bits from the bounds. */
__reg_bound_offset(src_reg);
__reg_bound_offset(dst_reg);
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
*/
__update_reg_bounds(src_reg);
__update_reg_bounds(dst_reg);
}
static void reg_combine_min_max(struct bpf_reg_state *true_src,
struct bpf_reg_state *true_dst,
struct bpf_reg_state *false_src,
struct bpf_reg_state *false_dst,
u8 opcode)
{
switch (opcode) {
case BPF_JEQ:
__reg_combine_min_max(true_src, true_dst);
break;
case BPF_JNE:
__reg_combine_min_max(false_src, false_dst);
break;
}
}
static void mark_ptr_or_null_reg(struct bpf_func_state *state,
struct bpf_reg_state *reg, u32 id,
bool is_null)
{
if (reg_type_may_be_null(reg->type) && reg->id == id &&
!WARN_ON_ONCE(!reg->id)) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
* arithmetic on pointers that might be NULL.
*/
if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
!tnum_equals_const(reg->var_off, 0) ||
reg->off)) {
__mark_reg_known_zero(reg);
reg->off = 0;
}
if (is_null) {
reg->type = SCALAR_VALUE;
/* We don't need id and ref_obj_id from this point
* onwards anymore, thus we should better reset it,
* so that state pruning has chances to take effect.
*/
reg->id = 0;
reg->ref_obj_id = 0;
return;
}
mark_ptr_not_null_reg(reg);
if (!reg_may_point_to_spin_lock(reg)) {
/* For not-NULL ptr, reg->ref_obj_id will be reset
* in release_reg_references().
*
* reg->id is still used by spin_lock ptr. Other
* than spin_lock ptr type, reg->id can be reset.
*/
reg->id = 0;
}
}
}
static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id,
bool is_null)
{
struct bpf_reg_state *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
mark_ptr_or_null_reg(state, &state->regs[i], id, is_null);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
mark_ptr_or_null_reg(state, reg, id, is_null);
}
}
/* The logic is similar to find_good_pkt_pointers(), both could eventually
* be folded together at some point.
*/
static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
bool is_null)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *regs = state->regs;
u32 ref_obj_id = regs[regno].ref_obj_id;
u32 id = regs[regno].id;
int i;
if (ref_obj_id && ref_obj_id == id && is_null)
/* regs[regno] is in the " == NULL" branch.
* No one could have freed the reference state before
* doing the NULL check.
*/
WARN_ON_ONCE(release_reference_state(state, id));
for (i = 0; i <= vstate->curframe; i++)
__mark_ptr_or_null_regs(vstate->frame[i], id, is_null);
}
static bool try_match_pkt_pointers(const struct bpf_insn *insn,
struct bpf_reg_state *dst_reg,
struct bpf_reg_state *src_reg,
struct bpf_verifier_state *this_branch,
struct bpf_verifier_state *other_branch)
{
if (BPF_SRC(insn->code) != BPF_X)
return false;
/* Pointers are always 64-bit. */
if (BPF_CLASS(insn->code) == BPF_JMP32)
return false;
switch (BPF_OP(insn->code)) {
case BPF_JGT:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, false);
mark_pkt_end(other_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end > pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, true);
mark_pkt_end(this_branch, insn->src_reg, false);
} else {
return false;
}
break;
case BPF_JLT:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, true);
mark_pkt_end(this_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end < pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, false);
mark_pkt_end(other_branch, insn->src_reg, true);
} else {
return false;
}
break;
case BPF_JGE:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, true);
mark_pkt_end(other_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, false);
mark_pkt_end(this_branch, insn->src_reg, true);
} else {
return false;
}
break;
case BPF_JLE:
if ((dst_reg->type == PTR_TO_PACKET &&
src_reg->type == PTR_TO_PACKET_END) ||
(dst_reg->type == PTR_TO_PACKET_META &&
reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, false);
mark_pkt_end(this_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
src_reg->type == PTR_TO_PACKET_META)) {
/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, true);
mark_pkt_end(other_branch, insn->src_reg, false);
} else {
return false;
}
break;
default:
return false;
}
return true;
}
static void find_equal_scalars(struct bpf_verifier_state *vstate,
struct bpf_reg_state *known_reg)
{
struct bpf_func_state *state;
struct bpf_reg_state *reg;
int i, j;
for (i = 0; i <= vstate->curframe; i++) {
state = vstate->frame[i];
for (j = 0; j < MAX_BPF_REG; j++) {
reg = &state->regs[j];
if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
*reg = *known_reg;
}
bpf_for_each_spilled_reg(j, state, reg) {
if (!reg)
continue;
if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
*reg = *known_reg;
}
}
}
static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
struct bpf_verifier_state *this_branch = env->cur_state;
struct bpf_verifier_state *other_branch;
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
u8 opcode = BPF_OP(insn->code);
bool is_jmp32;
int pred = -1;
int err;
/* Only conditional jumps are expected to reach here. */
if (opcode == BPF_JA || opcode > BPF_JSLE) {
verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode);
return -EINVAL;
}
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
src_reg = ®s[insn->src_reg];
} else {
if (insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
}
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
dst_reg = ®s[insn->dst_reg];
is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
if (BPF_SRC(insn->code) == BPF_K) {
pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
} else if (src_reg->type == SCALAR_VALUE &&
is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
pred = is_branch_taken(dst_reg,
tnum_subreg(src_reg->var_off).value,
opcode,
is_jmp32);
} else if (src_reg->type == SCALAR_VALUE &&
!is_jmp32 && tnum_is_const(src_reg->var_off)) {
pred = is_branch_taken(dst_reg,
src_reg->var_off.value,
opcode,
is_jmp32);
} else if (reg_is_pkt_pointer_any(dst_reg) &&
reg_is_pkt_pointer_any(src_reg) &&
!is_jmp32) {
pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
}
if (pred >= 0) {
/* If we get here with a dst_reg pointer type it is because
* above is_branch_taken() special cased the 0 comparison.
*/
if (!__is_pointer_value(false, dst_reg))
err = mark_chain_precision(env, insn->dst_reg);
if (BPF_SRC(insn->code) == BPF_X && !err &&
!__is_pointer_value(false, src_reg))
err = mark_chain_precision(env, insn->src_reg);
if (err)
return err;
}
if (pred == 1) {
/* only follow the goto, ignore fall-through */
*insn_idx += insn->off;
return 0;
} else if (pred == 0) {
/* only follow fall-through branch, since
* that's where the program will go
*/
return 0;
}
other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
false);
if (!other_branch)
return -EFAULT;
other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
/* detect if we are comparing against a constant value so we can adjust
* our min/max values for our dst register.
* this is only legit if both are scalars (or pointers to the same
* object, I suppose, but we don't support that right now), because
* otherwise the different base pointers mean the offsets aren't
* comparable.
*/
if (BPF_SRC(insn->code) == BPF_X) {
struct bpf_reg_state *src_reg = ®s[insn->src_reg];
if (dst_reg->type == SCALAR_VALUE &&
src_reg->type == SCALAR_VALUE) {
if (tnum_is_const(src_reg->var_off) ||
(is_jmp32 &&
tnum_is_const(tnum_subreg(src_reg->var_off))))
reg_set_min_max(&other_branch_regs[insn->dst_reg],
dst_reg,
src_reg->var_off.value,
tnum_subreg(src_reg->var_off).value,
opcode, is_jmp32);
else if (tnum_is_const(dst_reg->var_off) ||
(is_jmp32 &&
tnum_is_const(tnum_subreg(dst_reg->var_off))))
reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
src_reg,
dst_reg->var_off.value,
tnum_subreg(dst_reg->var_off).value,
opcode, is_jmp32);
else if (!is_jmp32 &&
(opcode == BPF_JEQ || opcode == BPF_JNE))
/* Comparing for equality, we can combine knowledge */
reg_combine_min_max(&other_branch_regs[insn->src_reg],
&other_branch_regs[insn->dst_reg],
src_reg, dst_reg, opcode);
if (src_reg->id &&
!WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
find_equal_scalars(this_branch, src_reg);
find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
}
}
} else if (dst_reg->type == SCALAR_VALUE) {
reg_set_min_max(&other_branch_regs[insn->dst_reg],
dst_reg, insn->imm, (u32)insn->imm,
opcode, is_jmp32);
}
if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
!WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
find_equal_scalars(this_branch, dst_reg);
find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]);
}
/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
* NOTE: these optimizations below are related with pointer comparison
* which will never be JMP32.
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
reg_type_may_be_null(dst_reg->type)) {
/* Mark all identical registers in each branch as either
* safe or unknown depending R == 0 or R != 0 conditional.
*/
mark_ptr_or_null_regs(this_branch, insn->dst_reg,
opcode == BPF_JNE);
mark_ptr_or_null_regs(other_branch, insn->dst_reg,
opcode == BPF_JEQ);
} else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg],
this_branch, other_branch) &&
is_pointer_value(env, insn->dst_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->dst_reg);
return -EACCES;
}
if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_insn_aux_data *aux = cur_aux(env);
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *dst_reg;
struct bpf_map *map;
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
verbose(env, "invalid BPF_LD_IMM insn\n");
return -EINVAL;
}
if (insn->off != 0) {
verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
return -EINVAL;
}
err = check_reg_arg(env, insn->dst_reg, DST_OP);
if (err)
return err;
dst_reg = ®s[insn->dst_reg];
if (insn->src_reg == 0) {
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
dst_reg->type = SCALAR_VALUE;
__mark_reg_known(®s[insn->dst_reg], imm);
return 0;
}
if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->type = aux->btf_var.reg_type;
switch (dst_reg->type) {
case PTR_TO_MEM:
dst_reg->mem_size = aux->btf_var.mem_size;
break;
case PTR_TO_BTF_ID:
case PTR_TO_PERCPU_BTF_ID:
dst_reg->btf = aux->btf_var.btf;
dst_reg->btf_id = aux->btf_var.btf_id;
break;
default:
verbose(env, "bpf verifier is misconfigured\n");
return -EFAULT;
}
return 0;
}
if (insn->src_reg == BPF_PSEUDO_FUNC) {
struct bpf_prog_aux *aux = env->prog->aux;
u32 subprogno = insn[1].imm;
if (!aux->func_info) {
verbose(env, "missing btf func_info\n");
return -EINVAL;
}
if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) {
verbose(env, "callback function not static\n");
return -EINVAL;
}
dst_reg->type = PTR_TO_FUNC;
dst_reg->subprogno = subprogno;
return 0;
}
map = env->used_maps[aux->map_index];
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->map_ptr = map;
if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
dst_reg->type = PTR_TO_MAP_VALUE;
dst_reg->off = aux->map_off;
if (map_value_has_spin_lock(map))
dst_reg->id = ++env->id_gen;
} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
dst_reg->type = CONST_PTR_TO_MAP;
} else {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
return 0;
}
static bool may_access_skb(enum bpf_prog_type type)
{
switch (type) {
case BPF_PROG_TYPE_SOCKET_FILTER:
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
return true;
default:
return false;
}
}
/* verify safety of LD_ABS|LD_IND instructions:
* - they can only appear in the programs where ctx == skb
* - since they are wrappers of function calls, they scratch R1-R5 registers,
* preserve R6-R9, and store return value into R0
*
* Implicit input:
* ctx == skb == R6 == CTX
*
* Explicit input:
* SRC == any register
* IMM == 32-bit immediate
*
* Output:
* R0 - 8/16/32-bit skb data converted to cpu endianness
*/
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
static const int ctx_reg = BPF_REG_6;
u8 mode = BPF_MODE(insn->code);
int i, err;
if (!may_access_skb(resolve_prog_type(env->prog))) {
verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
return -EINVAL;
}
if (!env->ops->gen_ld_abs) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
BPF_SIZE(insn->code) == BPF_DW ||
(mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
return -EINVAL;
}
/* check whether implicit source operand (register R6) is readable */
err = check_reg_arg(env, ctx_reg, SRC_OP);
if (err)
return err;
/* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as
* gen_ld_abs() may terminate the program at runtime, leading to
* reference leak.
*/
err = check_reference_leak(env);
if (err) {
verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
return err;
}
if (env->cur_state->active_spin_lock) {
verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n");
return -EINVAL;
}
if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
}
if (mode == BPF_IND) {
/* check explicit source operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
}
err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg);
if (err < 0)
return err;
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
/* mark destination R0 register as readable, since it contains
* the value fetched from the packet.
* Already marked as written above.
*/
mark_reg_unknown(env, regs, BPF_REG_0);
/* ld_abs load up to 32-bit skb data. */
regs[BPF_REG_0].subreg_def = env->insn_idx + 1;
return 0;
}
static int check_return_code(struct bpf_verifier_env *env)
{
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
struct tnum range = tnum_range(0, 1);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
const bool is_subprog = env->cur_state->frame[0]->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
if (!is_subprog &&
(prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
prog_type == BPF_PROG_TYPE_LSM) &&
!prog->aux->attach_func_proto->type)
return 0;
/* eBPF calling convetion is such that R0 is used
* to return the value from eBPF program.
* Make sure that it's readable at this time
* of bpf_exit, which means that program wrote
* something into it earlier
*/
err = check_reg_arg(env, BPF_REG_0, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, BPF_REG_0)) {
verbose(env, "R0 leaks addr as return value\n");
return -EACCES;
}
reg = cur_regs(env) + BPF_REG_0;
if (is_subprog) {
if (reg->type != SCALAR_VALUE) {
verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
reg_type_str[reg->type]);
return -EINVAL;
}
return 0;
}
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
range = tnum_range(1, 1);
if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
range = tnum_range(0, 3);
break;
case BPF_PROG_TYPE_CGROUP_SKB:
if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
range = tnum_range(0, 3);
enforce_attach_type_range = tnum_range(2, 3);
}
break;
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
break;
case BPF_PROG_TYPE_RAW_TRACEPOINT:
if (!env->prog->aux->attach_btf_id)
return 0;
range = tnum_const(0);
break;
case BPF_PROG_TYPE_TRACING:
switch (env->prog->expected_attach_type) {
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
range = tnum_const(0);
break;
case BPF_TRACE_RAW_TP:
case BPF_MODIFY_RETURN:
return 0;
case BPF_TRACE_ITER:
break;
default:
return -ENOTSUPP;
}
break;
case BPF_PROG_TYPE_SK_LOOKUP:
range = tnum_range(SK_DROP, SK_PASS);
break;
case BPF_PROG_TYPE_EXT:
/* freplace program can return anything as its return value
* depends on the to-be-replaced kernel func or bpf program.
*/
default:
return 0;
}
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
reg_type_str[reg->type]);
return -EINVAL;
}
if (!tnum_in(range, reg->var_off)) {
verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
return -EINVAL;
}
if (!tnum_is_unknown(enforce_attach_type_range) &&
tnum_in(enforce_attach_type_range, reg->var_off))
env->prog->enforce_expected_attach_type = 1;
return 0;
}
/* non-recursive DFS pseudo code
* 1 procedure DFS-iterative(G,v):
* 2 label v as discovered
* 3 let S be a stack
* 4 S.push(v)
* 5 while S is not empty
* 6 t <- S.pop()
* 7 if t is what we're looking for:
* 8 return t
* 9 for all edges e in G.adjacentEdges(t) do
* 10 if edge e is already labelled
* 11 continue with the next edge
* 12 w <- G.adjacentVertex(t,e)
* 13 if vertex w is not discovered and not explored
* 14 label e as tree-edge
* 15 label w as discovered
* 16 S.push(w)
* 17 continue at 5
* 18 else if vertex w is discovered
* 19 label e as back-edge
* 20 else
* 21 // vertex w is explored
* 22 label e as forward- or cross-edge
* 23 label t as explored
* 24 S.pop()
*
* convention:
* 0x10 - discovered
* 0x11 - discovered and fall-through edge labelled
* 0x12 - discovered and fall-through and branch edges labelled
* 0x20 - explored
*/
enum {
DISCOVERED = 0x10,
EXPLORED = 0x20,
FALLTHROUGH = 1,
BRANCH = 2,
};
static u32 state_htab_size(struct bpf_verifier_env *env)
{
return env->prog->len;
}
static struct bpf_verifier_state_list **explored_state(
struct bpf_verifier_env *env,
int idx)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_func_state *state = cur->frame[cur->curframe];
return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
}
static void init_explored_state(struct bpf_verifier_env *env, int idx)
{
env->insn_aux_data[idx].prune_point = true;
}
enum {
DONE_EXPLORING = 0,
KEEP_EXPLORING = 1,
};
/* t, w, e - match pseudo-code above:
* t - index of current instruction
* w - next instruction
* e - edge
*/
static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
bool loop_ok)
{
int *insn_stack = env->cfg.insn_stack;
int *insn_state = env->cfg.insn_state;
if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
return DONE_EXPLORING;
if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
return DONE_EXPLORING;
if (w < 0 || w >= env->prog->len) {
verbose_linfo(env, t, "%d: ", t);
verbose(env, "jump out of range from insn %d to %d\n", t, w);
return -EINVAL;
}
if (e == BRANCH)
/* mark branch target for state pruning */
init_explored_state(env, w);
if (insn_state[w] == 0) {
/* tree-edge */
insn_state[t] = DISCOVERED | e;
insn_state[w] = DISCOVERED;
if (env->cfg.cur_stack >= env->prog->len)
return -E2BIG;
insn_stack[env->cfg.cur_stack++] = w;
return KEEP_EXPLORING;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
if (loop_ok && env->bpf_capable)
return DONE_EXPLORING;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
verbose(env, "back-edge from insn %d to %d\n", t, w);
return -EINVAL;
} else if (insn_state[w] == EXPLORED) {
/* forward- or cross-edge */
insn_state[t] = DISCOVERED | e;
} else {
verbose(env, "insn state internal bug\n");
return -EFAULT;
}
return DONE_EXPLORING;
}
static int visit_func_call_insn(int t, int insn_cnt,
struct bpf_insn *insns,
struct bpf_verifier_env *env,
bool visit_callee)
{
int ret;
ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
if (ret)
return ret;
if (t + 1 < insn_cnt)
init_explored_state(env, t + 1);
if (visit_callee) {
init_explored_state(env, t);
ret = push_insn(t, t + insns[t].imm + 1, BRANCH,
env, false);
}
return ret;
}
/* Visits the instruction at index t and returns one of the following:
* < 0 - an error occurred
* DONE_EXPLORING - the instruction was fully explored
* KEEP_EXPLORING - there is still work to be done before it is fully explored
*/
static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi;
int ret;
if (bpf_pseudo_func(insns + t))
return visit_func_call_insn(t, insn_cnt, insns, env, true);
/* All non-branch instructions have a single fall-through edge. */
if (BPF_CLASS(insns[t].code) != BPF_JMP &&
BPF_CLASS(insns[t].code) != BPF_JMP32)
return push_insn(t, t + 1, FALLTHROUGH, env, false);
switch (BPF_OP(insns[t].code)) {
case BPF_EXIT:
return DONE_EXPLORING;
case BPF_CALL:
return visit_func_call_insn(t, insn_cnt, insns, env,
insns[t].src_reg == BPF_PSEUDO_CALL);
case BPF_JA:
if (BPF_SRC(insns[t].code) != BPF_K)
return -EINVAL;
/* unconditional jump with single edge */
ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env,
true);
if (ret)
return ret;
/* unconditional jmp is not a good pruning point,
* but it's marked, since backtracking needs
* to record jmp history in is_state_visited().
*/
init_explored_state(env, t + insns[t].off + 1);
/* tell verifier to check for equivalent states
* after every call and jump
*/
if (t + 1 < insn_cnt)
init_explored_state(env, t + 1);
return ret;
default:
/* conditional jump with two edges */
init_explored_state(env, t);
ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
if (ret)
return ret;
return push_insn(t, t + insns[t].off + 1, BRANCH, env, true);
}
}
/* non-recursive depth-first-search to detect loops in BPF program
* loop == back-edge in directed graph
*/
static int check_cfg(struct bpf_verifier_env *env)
{
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
int ret = 0;
int i;
insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_stack) {
kvfree(insn_state);
return -ENOMEM;
}
insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
insn_stack[0] = 0; /* 0 is the first instruction */
env->cfg.cur_stack = 1;
while (env->cfg.cur_stack > 0) {
int t = insn_stack[env->cfg.cur_stack - 1];
ret = visit_insn(t, insn_cnt, env);
switch (ret) {
case DONE_EXPLORING:
insn_state[t] = EXPLORED;
env->cfg.cur_stack--;
break;
case KEEP_EXPLORING:
break;
default:
if (ret > 0) {
verbose(env, "visit_insn internal bug\n");
ret = -EFAULT;
}
goto err_free;
}
}
if (env->cfg.cur_stack < 0) {
verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
}
for (i = 0; i < insn_cnt; i++) {
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
}
ret = 0; /* cfg looks good */
err_free:
kvfree(insn_state);
kvfree(insn_stack);
env->cfg.insn_state = env->cfg.insn_stack = NULL;
return ret;
}
static int check_abnormal_return(struct bpf_verifier_env *env)
{
int i;
for (i = 1; i < env->subprog_cnt; i++) {
if (env->subprog_info[i].has_ld_abs) {
verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
return -EINVAL;
}
if (env->subprog_info[i].has_tail_call) {
verbose(env, "tail_call is not allowed in subprogs without BTF\n");
return -EINVAL;
}
}
return 0;
}
/* The minimum supported BTF func info size */
#define MIN_BPF_FUNCINFO_SIZE 8
#define MAX_FUNCINFO_REC_SIZE 252
static int check_btf_func(struct bpf_verifier_env *env,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
const struct btf_type *type, *func_proto, *ret_type;
u32 i, nfuncs, urec_size, min_size;
u32 krec_size = sizeof(struct bpf_func_info);
struct bpf_func_info *krecord;
struct bpf_func_info_aux *info_aux = NULL;
struct bpf_prog *prog;
const struct btf *btf;
void __user *urecord;
u32 prev_offset = 0;
bool scalar_return;
int ret = -ENOMEM;
nfuncs = attr->func_info_cnt;
if (!nfuncs) {
if (check_abnormal_return(env))
return -EINVAL;
return 0;
}
if (nfuncs != env->subprog_cnt) {
verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
return -EINVAL;
}
urec_size = attr->func_info_rec_size;
if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
urec_size > MAX_FUNCINFO_REC_SIZE ||
urec_size % sizeof(u32)) {
verbose(env, "invalid func info rec size %u\n", urec_size);
return -EINVAL;
}
prog = env->prog;
btf = prog->aux->btf;
urecord = u64_to_user_ptr(attr->func_info);
min_size = min_t(u32, krec_size, urec_size);
krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
if (!info_aux)
goto err_free;
for (i = 0; i < nfuncs; i++) {
ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
if (ret) {
if (ret == -E2BIG) {
verbose(env, "nonzero tailing record in func info");
/* set the size kernel expects so loader can zero
* out the rest of the record.
*/
if (put_user(min_size, &uattr->func_info_rec_size))
ret = -EFAULT;
}
goto err_free;
}
if (copy_from_user(&krecord[i], urecord, min_size)) {
ret = -EFAULT;
goto err_free;
}
/* check insn_off */
ret = -EINVAL;
if (i == 0) {
if (krecord[i].insn_off) {
verbose(env,
"nonzero insn_off %u for the first func info record",
krecord[i].insn_off);
goto err_free;
}
} else if (krecord[i].insn_off <= prev_offset) {
verbose(env,
"same or smaller insn offset (%u) than previous func info record (%u)",
krecord[i].insn_off, prev_offset);
goto err_free;
}
if (env->subprog_info[i].start != krecord[i].insn_off) {
verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
goto err_free;
}
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
if (!type || !btf_type_is_func(type)) {
verbose(env, "invalid type id %d in func info",
krecord[i].type_id);
goto err_free;
}
info_aux[i].linkage = BTF_INFO_VLEN(type->info);
func_proto = btf_type_by_id(btf, type->type);
if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
/* btf_func_check() already verified it during BTF load */
goto err_free;
ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
scalar_return =
btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
goto err_free;
}
if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
goto err_free;
}
prev_offset = krecord[i].insn_off;
urecord += urec_size;
}
prog->aux->func_info = krecord;
prog->aux->func_info_cnt = nfuncs;
prog->aux->func_info_aux = info_aux;
return 0;
err_free:
kvfree(krecord);
kfree(info_aux);
return ret;
}
static void adjust_btf_func(struct bpf_verifier_env *env)
{
struct bpf_prog_aux *aux = env->prog->aux;
int i;
if (!aux->func_info)
return;
for (i = 0; i < env->subprog_cnt; i++)
aux->func_info[i].insn_off = env->subprog_info[i].start;
}
#define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \
sizeof(((struct bpf_line_info *)(0))->line_col))
#define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE
static int check_btf_line(struct bpf_verifier_env *env,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0;
struct bpf_subprog_info *sub;
struct bpf_line_info *linfo;
struct bpf_prog *prog;
const struct btf *btf;
void __user *ulinfo;
int err;
nr_linfo = attr->line_info_cnt;
if (!nr_linfo)
return 0;
rec_size = attr->line_info_rec_size;
if (rec_size < MIN_BPF_LINEINFO_SIZE ||
rec_size > MAX_LINEINFO_REC_SIZE ||
rec_size & (sizeof(u32) - 1))
return -EINVAL;
/* Need to zero it in case the userspace may
* pass in a smaller bpf_line_info object.
*/
linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info),
GFP_KERNEL | __GFP_NOWARN);
if (!linfo)
return -ENOMEM;
prog = env->prog;
btf = prog->aux->btf;
s = 0;
sub = env->subprog_info;
ulinfo = u64_to_user_ptr(attr->line_info);
expected_size = sizeof(struct bpf_line_info);
ncopy = min_t(u32, expected_size, rec_size);
for (i = 0; i < nr_linfo; i++) {
err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size);
if (err) {
if (err == -E2BIG) {
verbose(env, "nonzero tailing record in line_info");
if (put_user(expected_size,
&uattr->line_info_rec_size))
err = -EFAULT;
}
goto err_free;
}
if (copy_from_user(&linfo[i], ulinfo, ncopy)) {
err = -EFAULT;
goto err_free;
}
/*
* Check insn_off to ensure
* 1) strictly increasing AND
* 2) bounded by prog->len
*
* The linfo[0].insn_off == 0 check logically falls into
* the later "missing bpf_line_info for func..." case
* because the first linfo[0].insn_off must be the
* first sub also and the first sub must have
* subprog_info[0].start == 0.
*/
if ((i && linfo[i].insn_off <= prev_offset) ||
linfo[i].insn_off >= prog->len) {
verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n",
i, linfo[i].insn_off, prev_offset,
prog->len);
err = -EINVAL;
goto err_free;
}
if (!prog->insnsi[linfo[i].insn_off].code) {
verbose(env,
"Invalid insn code at line_info[%u].insn_off\n",
i);
err = -EINVAL;
goto err_free;
}
if (!btf_name_by_offset(btf, linfo[i].line_off) ||
!btf_name_by_offset(btf, linfo[i].file_name_off)) {
verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
err = -EINVAL;
goto err_free;
}
if (s != env->subprog_cnt) {
if (linfo[i].insn_off == sub[s].start) {
sub[s].linfo_idx = i;
s++;
} else if (sub[s].start < linfo[i].insn_off) {
verbose(env, "missing bpf_line_info for func#%u\n", s);
err = -EINVAL;
goto err_free;
}
}
prev_offset = linfo[i].insn_off;
ulinfo += rec_size;
}
if (s != env->subprog_cnt) {
verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n",
env->subprog_cnt - s, s);
err = -EINVAL;
goto err_free;
}
prog->aux->linfo = linfo;
prog->aux->nr_linfo = nr_linfo;
return 0;
err_free:
kvfree(linfo);
return err;
}
static int check_btf_info(struct bpf_verifier_env *env,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
struct btf *btf;
int err;
if (!attr->func_info_cnt && !attr->line_info_cnt) {
if (check_abnormal_return(env))
return -EINVAL;
return 0;
}
btf = btf_get_by_fd(attr->prog_btf_fd);
if (IS_ERR(btf))
return PTR_ERR(btf);
if (btf_is_kernel(btf)) {
btf_put(btf);
return -EACCES;
}
env->prog->aux->btf = btf;
err = check_btf_func(env, attr, uattr);
if (err)
return err;
err = check_btf_line(env, attr, uattr);
if (err)
return err;
return 0;
}
/* check %cur's range satisfies %old's */
static bool range_within(struct bpf_reg_state *old,
struct bpf_reg_state *cur)
{
return old->umin_value <= cur->umin_value &&
old->umax_value >= cur->umax_value &&
old->smin_value <= cur->smin_value &&
old->smax_value >= cur->smax_value &&
old->u32_min_value <= cur->u32_min_value &&
old->u32_max_value >= cur->u32_max_value &&
old->s32_min_value <= cur->s32_min_value &&
old->s32_max_value >= cur->s32_max_value;
}
/* Maximum number of register states that can exist at once */
#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
struct idpair {
u32 old;
u32 cur;
};
/* If in the old state two registers had the same id, then they need to have
* the same id in the new state as well. But that id could be different from
* the old state, so we need to track the mapping from old to new ids.
* Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent
* regs with old id 5 must also have new id 9 for the new state to be safe. But
* regs with a different old id could still have new id 9, we don't care about
* that.
* So we look through our idmap to see if this old id has been seen before. If
* so, we require the new id to match; otherwise, we add the id pair to the map.
*/
static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
{
unsigned int i;
for (i = 0; i < ID_MAP_SIZE; i++) {
if (!idmap[i].old) {
/* Reached an empty slot; haven't seen this id before */
idmap[i].old = old_id;
idmap[i].cur = cur_id;
return true;
}
if (idmap[i].old == old_id)
return idmap[i].cur == cur_id;
}
/* We ran out of idmap slots, which should be impossible */
WARN_ON_ONCE(1);
return false;
}
static void clean_func_state(struct bpf_verifier_env *env,
struct bpf_func_state *st)
{
enum bpf_reg_liveness live;
int i, j;
for (i = 0; i < BPF_REG_FP; i++) {
live = st->regs[i].live;
/* liveness must not touch this register anymore */
st->regs[i].live |= REG_LIVE_DONE;
if (!(live & REG_LIVE_READ))
/* since the register is unused, clear its state
* to make further comparison simpler
*/
__mark_reg_not_init(env, &st->regs[i]);
}
for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
live = st->stack[i].spilled_ptr.live;
/* liveness must not touch this stack slot anymore */
st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
if (!(live & REG_LIVE_READ)) {
__mark_reg_not_init(env, &st->stack[i].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
st->stack[i].slot_type[j] = STACK_INVALID;
}
}
}
static void clean_verifier_state(struct bpf_verifier_env *env,
struct bpf_verifier_state *st)
{
int i;
if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
/* all regs in this state in all frames were already marked */
return;
for (i = 0; i <= st->curframe; i++)
clean_func_state(env, st->frame[i]);
}
/* the parentage chains form a tree.
* the verifier states are added to state lists at given insn and
* pushed into state stack for future exploration.
* when the verifier reaches bpf_exit insn some of the verifer states
* stored in the state lists have their final liveness state already,
* but a lot of states will get revised from liveness point of view when
* the verifier explores other branches.
* Example:
* 1: r0 = 1
* 2: if r1 == 100 goto pc+1
* 3: r0 = 2
* 4: exit
* when the verifier reaches exit insn the register r0 in the state list of
* insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch
* of insn 2 and goes exploring further. At the insn 4 it will walk the
* parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ.
*
* Since the verifier pushes the branch states as it sees them while exploring
* the program the condition of walking the branch instruction for the second
* time means that all states below this branch were already explored and
* their final liveness markes are already propagated.
* Hence when the verifier completes the search of state list in is_state_visited()
* we can call this clean_live_states() function to mark all liveness states
* as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
* will not be used.
* This function also clears the registers and stack for states that !READ
* to simplify state merging.
*
* Important note here that walking the same branch instruction in the callee
* doesn't meant that the states are DONE. The verifier has to compare
* the callsites
*/
static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
struct bpf_verifier_state_list *sl;
int i;
sl = *explored_state(env, insn);
while (sl) {
if (sl->state.branches)
goto next;
if (sl->state.insn_idx != insn ||
sl->state.curframe != cur->curframe)
goto next;
for (i = 0; i <= cur->curframe; i++)
if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
goto next;
clean_verifier_state(env, &sl->state);
next:
sl = sl->next;
}
}
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
struct idpair *idmap)
{
bool equal;
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
return true;
equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0;
if (rold->type == PTR_TO_STACK)
/* two stack pointers are equal only if they're pointing to
* the same stack frame, since fp-8 in foo != fp-8 in bar
*/
return equal && rold->frameno == rcur->frameno;
if (equal)
return true;
if (rold->type == NOT_INIT)
/* explored state can't have used this */
return true;
if (rcur->type == NOT_INIT)
return false;
switch (rold->type) {
case SCALAR_VALUE:
if (rcur->type == SCALAR_VALUE) {
if (!rold->precise && !rcur->precise)
return true;
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
} else {
/* We're trying to use a pointer in place of a scalar.
* Even if the scalar was unbounded, this could lead to
* pointer leaks because scalars are allowed to leak
* while pointers are not. We could make this safe in
* special cases if root is calling us, but it's
* probably not worth the hassle.
*/
return false;
}
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
* 'id' is not compared, since it's only used for maps with
* bpf_spin_lock inside map element and in such cases if
* the rest of the prog is valid for one map element then
* it's valid for all map elements regardless of the key
* used in bpf_map_lookup()
*/
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
case PTR_TO_MAP_VALUE_OR_NULL:
/* a PTR_TO_MAP_VALUE could be safe to use as a
* PTR_TO_MAP_VALUE_OR_NULL into the same map.
* However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
* checked, doing so could have affected others with the same
* id, and we can't check for that because we lost the id when
* we converted to a PTR_TO_MAP_VALUE.
*/
if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
return false;
if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
return false;
/* Check our ids match any regs they're supposed to */
return check_ids(rold->id, rcur->id, idmap);
case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
if (rcur->type != rold->type)
return false;
/* We must have at least as much range as the old ptr
* did, so that any accesses which were safe before are
* still safe. This is true even if old range < old off,
* since someone could have accessed through (ptr - k), or
* even done ptr -= k in a register, to get a safe access.
*/
if (rold->range > rcur->range)
return false;
/* If the offsets don't match, we can't trust our alignment;
* nor can we be sure that we won't fall out of range.
*/
if (rold->off != rcur->off)
return false;
/* id relations must be preserved */
if (rold->id && !check_ids(rold->id, rcur->id, idmap))
return false;
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
case PTR_TO_CTX:
case CONST_PTR_TO_MAP:
case PTR_TO_PACKET_END:
case PTR_TO_FLOW_KEYS:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
/* Only valid matches are exact, which memcmp() above
* would have accepted
*/
default:
/* Don't know what's going on, just say it's not safe */
return false;
}
/* Shouldn't get here; if we do, say it's not safe */
WARN_ON_ONCE(1);
return false;
}
static bool stacksafe(struct bpf_func_state *old,
struct bpf_func_state *cur,
struct idpair *idmap)
{
int i, spi;
/* walk slots of the explored stack and ignore any additional
* slots in the current stack, since explored(safe) state
* didn't use them
*/
for (i = 0; i < old->allocated_stack; i++) {
spi = i / BPF_REG_SIZE;
if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
i += BPF_REG_SIZE - 1;
/* explored state didn't use this */
continue;
}
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
continue;
/* explored stack has more populated slots than current stack
* and these slots were used
*/
if (i >= cur->allocated_stack)
return false;
/* if old state was safe with misc data in the stack
* it will be safe with zero-initialized stack.
* The opposite is not true
*/
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC &&
cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO)
continue;
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
cur->stack[spi].slot_type[i % BPF_REG_SIZE])
/* Ex: old explored (safe) state has STACK_SPILL in
* this stack slot, but current has STACK_MISC ->
* this verifier states are not equivalent,
* return false to continue verification of this path
*/
return false;
if (i % BPF_REG_SIZE)
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
if (!regsafe(&old->stack[spi].spilled_ptr,
&cur->stack[spi].spilled_ptr,
idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
* Ex: explored safe path could have stored
* (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
* but current path has stored:
* (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
* such verifier states are not equivalent.
* return false to continue verification of this path
*/
return false;
}
return true;
}
static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur)
{
if (old->acquired_refs != cur->acquired_refs)
return false;
return !memcmp(old->refs, cur->refs,
sizeof(*old->refs) * old->acquired_refs);
}
/* compare two verifier states
*
* all states stored in state_list are known to be valid, since
* verifier reached 'bpf_exit' instruction through them
*
* this function is called when verifier exploring different branches of
* execution popped from the state stack. If it sees an old state that has
* more strict register state and more strict stack state then this execution
* branch doesn't need to be explored further, since verifier already
* concluded that more strict state leads to valid finish.
*
* Therefore two states are equivalent if register state is more conservative
* and explored stack state is more conservative than the current one.
* Example:
* explored current
* (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
* (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
*
* In other words if current stack state (one being explored) has more
* valid slots than old one that already passed validation, it means
* the verifier can stop exploring and conclude that current state is valid too
*
* Similarly with registers. If explored state has register type as invalid
* whereas register type in current state is meaningful, it means that
* the current state will reach 'bpf_exit' instruction safely
*/
static bool func_states_equal(struct bpf_func_state *old,
struct bpf_func_state *cur)
{
struct idpair *idmap;
bool ret = false;
int i;
idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL);
/* If we failed to allocate the idmap, just say it's not safe */
if (!idmap)
return false;
for (i = 0; i < MAX_BPF_REG; i++) {
if (!regsafe(&old->regs[i], &cur->regs[i], idmap))
goto out_free;
}
if (!stacksafe(old, cur, idmap))
goto out_free;
if (!refsafe(old, cur))
goto out_free;
ret = true;
out_free:
kfree(idmap);
return ret;
}
static bool states_equal(struct bpf_verifier_env *env,
struct bpf_verifier_state *old,
struct bpf_verifier_state *cur)
{
int i;
if (old->curframe != cur->curframe)
return false;
/* Verification state from speculative execution simulation
* must never prune a non-speculative execution one.
*/
if (old->speculative && !cur->speculative)
return false;
if (old->active_spin_lock != cur->active_spin_lock)
return false;
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
for (i = 0; i <= old->curframe; i++) {
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
if (!func_states_equal(old->frame[i], cur->frame[i]))
return false;
}
return true;
}
/* Return 0 if no propagation happened. Return negative error code if error
* happened. Otherwise, return the propagated bit.
*/
static int propagate_liveness_reg(struct bpf_verifier_env *env,
struct bpf_reg_state *reg,
struct bpf_reg_state *parent_reg)
{
u8 parent_flag = parent_reg->live & REG_LIVE_READ;
u8 flag = reg->live & REG_LIVE_READ;
int err;
/* When comes here, read flags of PARENT_REG or REG could be any of
* REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need
* of propagation if PARENT_REG has strongest REG_LIVE_READ64.
*/
if (parent_flag == REG_LIVE_READ64 ||
/* Or if there is no read flag from REG. */
!flag ||
/* Or if the read flag from REG is the same as PARENT_REG. */
parent_flag == flag)
return 0;
err = mark_reg_read(env, reg, parent_reg, flag);
if (err)
return err;
return flag;
}
/* A write screens off any subsequent reads; but write marks come from the
* straight-line code between a state and its parent. When we arrive at an
* equivalent state (jump target or such) we didn't arrive by the straight-line
* code, so read marks in the state must propagate to the parent regardless
* of the state's write marks. That's what 'parent == state->parent' comparison
* in mark_reg_read() is for.
*/
static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
struct bpf_verifier_state *vparent)
{
struct bpf_reg_state *state_reg, *parent_reg;
struct bpf_func_state *state, *parent;
int i, frame, err = 0;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
vparent->curframe, vstate->curframe);
return -EFAULT;
}
/* Propagate read liveness of registers... */
BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
for (frame = 0; frame <= vstate->curframe; frame++) {
parent = vparent->frame[frame];
state = vstate->frame[frame];
parent_reg = parent->regs;
state_reg = state->regs;
/* We don't need to worry about FP liveness, it's read-only */
for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) {
err = propagate_liveness_reg(env, &state_reg[i],
&parent_reg[i]);
if (err < 0)
return err;
if (err == REG_LIVE_READ64)
mark_insn_zext(env, &parent_reg[i]);
}
/* Propagate stack slots. */
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
i < parent->allocated_stack / BPF_REG_SIZE; i++) {
parent_reg = &parent->stack[i].spilled_ptr;
state_reg = &state->stack[i].spilled_ptr;
err = propagate_liveness_reg(env, state_reg,
parent_reg);
if (err < 0)
return err;
}
}
return 0;
}
/* find precise scalars in the previous equivalent state and
* propagate them into the current state
*/
static int propagate_precision(struct bpf_verifier_env *env,
const struct bpf_verifier_state *old)
{
struct bpf_reg_state *state_reg;
struct bpf_func_state *state;
int i, err = 0;
state = old->frame[old->curframe];
state_reg = state->regs;
for (i = 0; i < BPF_REG_FP; i++, state_reg++) {
if (state_reg->type != SCALAR_VALUE ||
!state_reg->precise)
continue;
if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "propagating r%d\n", i);
err = mark_chain_precision(env, i);
if (err < 0)
return err;
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
if (state->stack[i].slot_type[0] != STACK_SPILL)
continue;
state_reg = &state->stack[i].spilled_ptr;
if (state_reg->type != SCALAR_VALUE ||
!state_reg->precise)
continue;
if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "propagating fp%d\n",
(-i - 1) * BPF_REG_SIZE);
err = mark_chain_precision_stack(env, i);
if (err < 0)
return err;
}
return 0;
}
static bool states_maybe_looping(struct bpf_verifier_state *old,
struct bpf_verifier_state *cur)
{
struct bpf_func_state *fold, *fcur;
int i, fr = cur->curframe;
if (old->curframe != fr)
return false;
fold = old->frame[fr];
fcur = cur->frame[fr];
for (i = 0; i < MAX_BPF_REG; i++)
if (memcmp(&fold->regs[i], &fcur->regs[i],
offsetof(struct bpf_reg_state, parent)))
return false;
return true;
}
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl, **pprev;
struct bpf_verifier_state *cur = env->cur_state, *new;
int i, j, err, states_cnt = 0;
bool add_new_state = env->test_state_freq ? true : false;
cur->last_insn_idx = env->prev_insn_idx;
if (!env->insn_aux_data[insn_idx].prune_point)
/* this 'insn_idx' instruction wasn't marked, so we will not
* be doing state search here
*/
return 0;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
* Do not add new state for future pruning if the verifier hasn't seen
* at least 2 jumps and at least 8 instructions.
* This heuristics helps decrease 'total_states' and 'peak_states' metric.
* In tests that amounts to up to 50% reduction into total verifier
* memory consumption and 20% verifier time speedup.
*/
if (env->jmps_processed - env->prev_jmps_processed >= 2 &&
env->insn_processed - env->prev_insn_processed >= 8)
add_new_state = true;
pprev = explored_state(env, insn_idx);
sl = *pprev;
clean_live_states(env, insn_idx, cur);
while (sl) {
states_cnt++;
if (sl->state.insn_idx != insn_idx)
goto next;
if (sl->state.branches) {
if (states_maybe_looping(&sl->state, cur) &&
states_equal(env, &sl->state, cur)) {
verbose_linfo(env, insn_idx, "; ");
verbose(env, "infinite loop detected at insn %d\n", insn_idx);
return -EINVAL;
}
/* if the verifier is processing a loop, avoid adding new state
* too often, since different loop iterations have distinct
* states and may not help future pruning.
* This threshold shouldn't be too low to make sure that
* a loop with large bound will be rejected quickly.
* The most abusive loop will be:
* r1 += 1
* if r1 < 1000000 goto pc-2
* 1M insn_procssed limit / 100 == 10k peak states.
* This threshold shouldn't be too high either, since states
* at the end of the loop are likely to be useful in pruning.
*/
if (env->jmps_processed - env->prev_jmps_processed < 20 &&
env->insn_processed - env->prev_insn_processed < 100)
add_new_state = false;
goto miss;
}
if (states_equal(env, &sl->state, cur)) {
sl->hit_cnt++;
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
* If we have any write marks in env->cur_state, they
* will prevent corresponding reads in the continuation
* from reaching our parent (an explored_state). Our
* own state will get the read marks recorded, but
* they'll be immediately forgotten as we're pruning
* this state and will pop a new one.
*/
err = propagate_liveness(env, &sl->state, cur);
/* if previous state reached the exit with precision and
* current state is equivalent to it (except precsion marks)
* the precision needs to be propagated back in
* the current state.
*/
err = err ? : push_jmp_history(env, cur);
err = err ? : propagate_precision(env, &sl->state);
if (err)
return err;
return 1;
}
miss:
/* when new state is not going to be added do not increase miss count.
* Otherwise several loop iterations will remove the state
* recorded earlier. The goal of these heuristics is to have
* states from some iterations of the loop (some in the beginning
* and some at the end) to help pruning.
*/
if (add_new_state)
sl->miss_cnt++;
/* heuristic to determine whether this state is beneficial
* to keep checking from state equivalence point of view.
* Higher numbers increase max_states_per_insn and verification time,
* but do not meaningfully decrease insn_processed.
*/
if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
/* the state is unlikely to be useful. Remove it to
* speed up verification
*/
*pprev = sl->next;
if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
u32 br = sl->state.branches;
WARN_ONCE(br,
"BUG live_done but branches_to_explore %d\n",
br);
free_verifier_state(&sl->state, false);
kfree(sl);
env->peak_states--;
} else {
/* cannot free this state, since parentage chain may
* walk it later. Add it for free_list instead to
* be freed at the end of verification
*/
sl->next = env->free_list;
env->free_list = sl;
}
sl = *pprev;
continue;
}
next:
pprev = &sl->next;
sl = *pprev;
}
if (env->max_states_per_insn < states_cnt)
env->max_states_per_insn = states_cnt;
if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
return push_jmp_history(env, cur);
if (!add_new_state)
return push_jmp_history(env, cur);
/* There were no equivalent states, remember the current one.
* Technically the current state is not proven to be safe yet,
* but it will either reach outer most bpf_exit (which means it's safe)
* or it will be rejected. When there are no loops the verifier won't be
* seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
* again on the way to bpf_exit.
* When looping the sl->state.branches will be > 0 and this state
* will not be considered for equivalence until branches == 0.
*/
new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
env->total_states++;
env->peak_states++;
env->prev_jmps_processed = env->jmps_processed;
env->prev_insn_processed = env->insn_processed;
/* add new state to the head of linked list */
new = &new_sl->state;
err = copy_verifier_state(new, cur);
if (err) {
free_verifier_state(new, false);
kfree(new_sl);
return err;
}
new->insn_idx = insn_idx;
WARN_ONCE(new->branches != 1,
"BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx);
cur->parent = new;
cur->first_insn_idx = insn_idx;
clear_jmp_history(cur);
new_sl->next = *explored_state(env, insn_idx);
*explored_state(env, insn_idx) = new_sl;
/* connect new state to parentage chain. Current frame needs all
* registers connected. Only r6 - r9 of the callers are alive (pushed
* to the stack implicitly by JITs) so in callers' frames connect just
* r6 - r9 as an optimization. Callers will have r1 - r5 connected to
* the state of the call instruction (with WRITTEN set), and r0 comes
* from callee with its full parentage chain, anyway.
*/
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
* their parent and current state never has children yet. Only
* explored_states can get read marks.)
*/
for (j = 0; j <= cur->curframe; j++) {
for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
for (i = 0; i < BPF_REG_FP; i++)
cur->frame[j]->regs[i].live = REG_LIVE_NONE;
}
/* all stack frames are accessible from callee, clear them all */
for (j = 0; j <= cur->curframe; j++) {
struct bpf_func_state *frame = cur->frame[j];
struct bpf_func_state *newframe = new->frame[j];
for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) {
frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
frame->stack[i].spilled_ptr.parent =
&newframe->stack[i].spilled_ptr;
}
}
return 0;
}
/* Return true if it's OK to have the same insn return a different type. */
static bool reg_type_mismatch_ok(enum bpf_reg_type type)
{
switch (type) {
case PTR_TO_CTX:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
case PTR_TO_BTF_ID_OR_NULL:
return false;
default:
return true;
}
}
/* If an instruction was previously used with particular pointer types, then we
* need to be careful to avoid cases such as the below, where it may be ok
* for one branch accessing the pointer, but not ok for the other branch:
*
* R1 = sock_ptr
* goto X;
* ...
* R1 = some_other_valid_ptr;
* goto X;
* ...
* R2 = *(u32 *)(R1 + 0);
*/
static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
{
return src != prev && (!reg_type_mismatch_ok(src) ||
!reg_type_mismatch_ok(prev));
}
static int do_check(struct bpf_verifier_env *env)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
bool do_print_state = false;
int prev_insn_idx = -1;
for (;;) {
struct bpf_insn *insn;
u8 class;
int err;
env->prev_insn_idx = prev_insn_idx;
if (env->insn_idx >= insn_cnt) {
verbose(env, "invalid insn idx %d insn_cnt %d\n",
env->insn_idx, insn_cnt);
return -EFAULT;
}
insn = &insns[env->insn_idx];
class = BPF_CLASS(insn->code);
if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
"BPF program is too large. Processed %d insn\n",
env->insn_processed);
return -E2BIG;
}
err = is_state_visited(env, env->insn_idx);
if (err < 0)
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
if (env->log.level & BPF_LOG_LEVEL) {
if (do_print_state)
verbose(env, "\nfrom %d to %d%s: safe\n",
env->prev_insn_idx, env->insn_idx,
env->cur_state->speculative ?
" (speculative execution)" : "");
else
verbose(env, "%d: safe\n", env->insn_idx);
}
goto process_bpf_exit;
}
if (signal_pending(current))
return -EAGAIN;
if (need_resched())
cond_resched();
if (env->log.level & BPF_LOG_LEVEL2 ||
(env->log.level & BPF_LOG_LEVEL && do_print_state)) {
if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "%d:", env->insn_idx);
else
verbose(env, "\nfrom %d to %d%s:",
env->prev_insn_idx, env->insn_idx,
env->cur_state->speculative ?
" (speculative execution)" : "");
print_verifier_state(env, state->frame[state->curframe]);
do_print_state = false;
}
if (env->log.level & BPF_LOG_LEVEL) {
const struct bpf_insn_cbs cbs = {
.cb_call = disasm_kfunc_name,
.cb_print = verbose,
.private_data = env,
};
verbose_linfo(env, env->insn_idx, "; ");
verbose(env, "%d: ", env->insn_idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
err = bpf_prog_offload_verify_insn(env, env->insn_idx,
env->prev_insn_idx);
if (err)
return err;
}
regs = cur_regs(env);
env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
prev_insn_idx = env->insn_idx;
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
if (err)
return err;
} else if (class == BPF_LDX) {
enum bpf_reg_type *prev_src_type, src_reg_type;
/* check for reserved fields is already done */
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
src_reg_type = regs[insn->src_reg].type;
/* check that memory (src_reg + off) is readable,
* the state of dst_reg will be updated by this func
*/
err = check_mem_access(env, env->insn_idx, insn->src_reg,
insn->off, BPF_SIZE(insn->code),
BPF_READ, insn->dst_reg, false);
if (err)
return err;
prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type;
if (*prev_src_type == NOT_INIT) {
/* saw a valid insn
* dst_reg = *(u32 *)(src_reg + off)
* save type to validate intersecting paths
*/
*prev_src_type = src_reg_type;
} else if (reg_type_mismatch(src_reg_type, *prev_src_type)) {
/* ABuser program is trying to use the same insn
* dst_reg = *(u32*) (src_reg + off)
* with different pointer types:
* src_reg == ctx in one branch and
* src_reg == stack|map in some other branch.
* Reject it.
*/
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
} else if (class == BPF_STX) {
enum bpf_reg_type *prev_dst_type, dst_reg_type;
if (BPF_MODE(insn->code) == BPF_ATOMIC) {
err = check_atomic(env, env->insn_idx, insn);
if (err)
return err;
env->insn_idx++;
continue;
}
if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
verbose(env, "BPF_STX uses reserved fields\n");
return -EINVAL;
}
/* check src1 operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
return err;
/* check src2 operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
dst_reg_type = regs[insn->dst_reg].type;
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
BPF_WRITE, insn->src_reg, false);
if (err)
return err;
prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type;
if (*prev_dst_type == NOT_INIT) {
*prev_dst_type = dst_reg_type;
} else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) {
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
} else if (class == BPF_ST) {
if (BPF_MODE(insn->code) != BPF_MEM ||
insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_ST uses reserved fields\n");
return -EINVAL;
}
/* check src operand */
err = check_reg_arg(env, insn->dst_reg, SRC_OP);
if (err)
return err;
if (is_ctx_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
insn->dst_reg,
reg_type_str[reg_state(env, insn->dst_reg)->type]);
return -EACCES;
}
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
BPF_WRITE, -1, false);
if (err)
return err;
} else if (class == BPF_JMP || class == BPF_JMP32) {
u8 opcode = BPF_OP(insn->code);
env->jmps_processed++;
if (opcode == BPF_CALL) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->off != 0 ||
(insn->src_reg != BPF_REG_0 &&
insn->src_reg != BPF_PSEUDO_CALL &&
insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
insn->dst_reg != BPF_REG_0 ||
class == BPF_JMP32) {
verbose(env, "BPF_CALL uses reserved fields\n");
return -EINVAL;
}
if (env->cur_state->active_spin_lock &&
(insn->src_reg == BPF_PSEUDO_CALL ||
insn->imm != BPF_FUNC_spin_unlock)) {
verbose(env, "function calls are not allowed while holding a lock\n");
return -EINVAL;
}
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
err = check_kfunc_call(env, insn);
else
err = check_helper_call(env, insn, &env->insn_idx);
if (err)
return err;
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
class == BPF_JMP32) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
env->insn_idx += insn->off + 1;
continue;
} else if (opcode == BPF_EXIT) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
class == BPF_JMP32) {
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
if (env->cur_state->active_spin_lock) {
verbose(env, "bpf_spin_unlock is missing\n");
return -EINVAL;
}
if (state->curframe) {
/* exit from nested function */
err = prepare_func_exit(env, &env->insn_idx);
if (err)
return err;
do_print_state = true;
continue;
}
err = check_reference_leak(env);
if (err)
return err;
err = check_return_code(env);
if (err)
return err;
process_bpf_exit:
update_branch_counts(env, env->cur_state);
err = pop_stack(env, &prev_insn_idx,
&env->insn_idx, pop_log);
if (err < 0) {
if (err != -ENOENT)
return err;
break;
} else {
do_print_state = true;
continue;
}
} else {
err = check_cond_jmp_op(env, insn, &env->insn_idx);
if (err)
return err;
}
} else if (class == BPF_LD) {
u8 mode = BPF_MODE(insn->code);
if (mode == BPF_ABS || mode == BPF_IND) {
err = check_ld_abs(env, insn);
if (err)
return err;
} else if (mode == BPF_IMM) {
err = check_ld_imm(env, insn);
if (err)
return err;
env->insn_idx++;
env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
}
} else {
verbose(env, "unknown insn class %d\n", class);
return -EINVAL;
}
env->insn_idx++;
}
return 0;
}
static int find_btf_percpu_datasec(struct btf *btf)
{
const struct btf_type *t;
const char *tname;
int i, n;
/*
* Both vmlinux and module each have their own ".data..percpu"
* DATASECs in BTF. So for module's case, we need to skip vmlinux BTF
* types to look at only module's own BTF types.
*/
n = btf_nr_types(btf);
if (btf_is_module(btf))
i = btf_nr_types(btf_vmlinux);
else
i = 1;
for(; i < n; i++) {
t = btf_type_by_id(btf, i);
if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
continue;
tname = btf_name_by_offset(btf, t->name_off);
if (!strcmp(tname, ".data..percpu"))
return i;
}
return -ENOENT;
}
/* replace pseudo btf_id with kernel symbol address */
static int check_pseudo_btf_id(struct bpf_verifier_env *env,
struct bpf_insn *insn,
struct bpf_insn_aux_data *aux)
{
const struct btf_var_secinfo *vsi;
const struct btf_type *datasec;
struct btf_mod_pair *btf_mod;
const struct btf_type *t;
const char *sym_name;
bool percpu = false;
u32 type, id = insn->imm;
struct btf *btf;
s32 datasec_id;
u64 addr;
int i, btf_fd, err;
btf_fd = insn[1].imm;
if (btf_fd) {
btf = btf_get_by_fd(btf_fd);
if (IS_ERR(btf)) {
verbose(env, "invalid module BTF object FD specified.\n");
return -EINVAL;
}
} else {
if (!btf_vmlinux) {
verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
return -EINVAL;
}
btf = btf_vmlinux;
btf_get(btf);
}
t = btf_type_by_id(btf, id);
if (!t) {
verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
err = -ENOENT;
goto err_put;
}
if (!btf_type_is_var(t)) {
verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id);
err = -EINVAL;
goto err_put;
}
sym_name = btf_name_by_offset(btf, t->name_off);
addr = kallsyms_lookup_name(sym_name);
if (!addr) {
verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
sym_name);
err = -ENOENT;
goto err_put;
}
datasec_id = find_btf_percpu_datasec(btf);
if (datasec_id > 0) {
datasec = btf_type_by_id(btf, datasec_id);
for_each_vsi(i, datasec, vsi) {
if (vsi->type == id) {
percpu = true;
break;
}
}
}
insn[0].imm = (u32)addr;
insn[1].imm = addr >> 32;
type = t->type;
t = btf_type_skip_modifiers(btf, type, NULL);
if (percpu) {
aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
aux->btf_var.btf = btf;
aux->btf_var.btf_id = type;
} else if (!btf_type_is_struct(t)) {
const struct btf_type *ret;
const char *tname;
u32 tsize;
/* resolve the type size of ksym. */
ret = btf_resolve_size(btf, t, &tsize);
if (IS_ERR(ret)) {
tname = btf_name_by_offset(btf, t->name_off);
verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
tname, PTR_ERR(ret));
err = -EINVAL;
goto err_put;
}
aux->btf_var.reg_type = PTR_TO_MEM;
aux->btf_var.mem_size = tsize;
} else {
aux->btf_var.reg_type = PTR_TO_BTF_ID;
aux->btf_var.btf = btf;
aux->btf_var.btf_id = type;
}
/* check whether we recorded this BTF (and maybe module) already */
for (i = 0; i < env->used_btf_cnt; i++) {
if (env->used_btfs[i].btf == btf) {
btf_put(btf);
return 0;
}
}
if (env->used_btf_cnt >= MAX_USED_BTFS) {
err = -E2BIG;
goto err_put;
}
btf_mod = &env->used_btfs[env->used_btf_cnt];
btf_mod->btf = btf;
btf_mod->module = NULL;
/* if we reference variables from kernel module, bump its refcount */
if (btf_is_module(btf)) {
btf_mod->module = btf_try_get_module(btf);
if (!btf_mod->module) {
err = -ENXIO;
goto err_put;
}
}
env->used_btf_cnt++;
return 0;
err_put:
btf_put(btf);
return err;
}
static int check_map_prealloc(struct bpf_map *map)
{
return (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
!(map->map_flags & BPF_F_NO_PREALLOC);
}
static bool is_tracing_prog_type(enum bpf_prog_type type)
{
switch (type) {
case BPF_PROG_TYPE_KPROBE:
case BPF_PROG_TYPE_TRACEPOINT:
case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_RAW_TRACEPOINT:
return true;
default:
return false;
}
}
static bool is_preallocated_map(struct bpf_map *map)
{
if (!check_map_prealloc(map))
return false;
if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta))
return false;
return true;
}
static int check_map_prog_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map,
struct bpf_prog *prog)
{
enum bpf_prog_type prog_type = resolve_prog_type(prog);
/*
* Validate that trace type programs use preallocated hash maps.
*
* For programs attached to PERF events this is mandatory as the
* perf NMI can hit any arbitrary code sequence.
*
* All other trace types using preallocated hash maps are unsafe as
* well because tracepoint or kprobes can be inside locked regions
* of the memory allocator or at a place where a recursion into the
* memory allocator would see inconsistent state.
*
* On RT enabled kernels run-time allocation of all trace type
* programs is strictly prohibited due to lock type constraints. On
* !RT kernels it is allowed for backwards compatibility reasons for
* now, but warnings are emitted so developers are made aware of
* the unsafety and can fix their programs before this is enforced.
*/
if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) {
if (prog_type == BPF_PROG_TYPE_PERF_EVENT) {
verbose(env, "perf_event programs can only use preallocated hash map\n");
return -EINVAL;
}
if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
verbose(env, "trace type programs can only use preallocated hash map\n");
return -EINVAL;
}
WARN_ONCE(1, "trace type BPF program uses run-time allocation\n");
verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
}
if (map_value_has_spin_lock(map)) {
if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
if (is_tracing_prog_type(prog_type)) {
verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
if (prog->aux->sleepable) {
verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
return -EINVAL;
}
if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
verbose(env, "bpf_struct_ops map cannot be used in prog\n");
return -EINVAL;
}
if (prog->aux->sleepable)
switch (map->map_type) {
case BPF_MAP_TYPE_HASH:
case BPF_MAP_TYPE_LRU_HASH:
case BPF_MAP_TYPE_ARRAY:
case BPF_MAP_TYPE_PERCPU_HASH:
case BPF_MAP_TYPE_PERCPU_ARRAY:
case BPF_MAP_TYPE_LRU_PERCPU_HASH:
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (!is_preallocated_map(map)) {
verbose(env,
"Sleepable programs can only use preallocated maps\n");
return -EINVAL;
}
break;
case BPF_MAP_TYPE_RINGBUF:
break;
default:
verbose(env,
"Sleepable programs can only use array, hash, and ringbuf maps\n");
return -EINVAL;
}
return 0;
}
static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
{
return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
}
/* find and rewrite pseudo imm in ld_imm64 instructions:
*
* 1. if it accesses map FD, replace it with actual map pointer.
* 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
*
* NOTE: btf_vmlinux is required for converting pseudo btf_id.
*/
static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
int i, j, err;
err = bpf_prog_calc_tag(env->prog);
if (err)
return err;
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
(BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
struct bpf_insn_aux_data *aux;
struct bpf_map *map;
struct fd f;
u64 addr;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
insn[1].off != 0) {
verbose(env, "invalid bpf_ld_imm64 insn\n");
return -EINVAL;
}
if (insn[0].src_reg == 0)
/* valid generic load 64-bit imm */
goto next_insn;
if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
aux = &env->insn_aux_data[i];
err = check_pseudo_btf_id(env, insn, aux);
if (err)
return err;
goto next_insn;
}
if (insn[0].src_reg == BPF_PSEUDO_FUNC) {
aux = &env->insn_aux_data[i];
aux->ptr_type = PTR_TO_FUNC;
goto next_insn;
}
/* In final convert_pseudo_ld_imm64() step, this is
* converted into regular 64-bit imm load insn.
*/
if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
(insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
insn[1].imm != 0)) {
verbose(env,
"unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
f = fdget(insn[0].imm);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
verbose(env, "fd %d is not pointing to valid bpf_map\n",
insn[0].imm);
return PTR_ERR(map);
}
err = check_map_prog_compatibility(env, map, env->prog);
if (err) {
fdput(f);
return err;
}
aux = &env->insn_aux_data[i];
if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
addr = (unsigned long)map;
} else {
u32 off = insn[1].imm;
if (off >= BPF_MAX_VAR_OFF) {
verbose(env, "direct value offset of %u is not allowed\n", off);
fdput(f);
return -EINVAL;
}
if (!map->ops->map_direct_value_addr) {
verbose(env, "no direct value access support for this map type\n");
fdput(f);
return -EINVAL;
}
err = map->ops->map_direct_value_addr(map, &addr, off);
if (err) {
verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
map->value_size, off);
fdput(f);
return err;
}
aux->map_off = off;
addr += off;
}
insn[0].imm = (u32)addr;
insn[1].imm = addr >> 32;
/* check whether we recorded this map already */
for (j = 0; j < env->used_map_cnt; j++) {
if (env->used_maps[j] == map) {
aux->map_index = j;
fdput(f);
goto next_insn;
}
}
if (env->used_map_cnt >= MAX_USED_MAPS) {
fdput(f);
return -E2BIG;
}
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
* and all maps are released in free_used_maps()
*/
bpf_map_inc(map);
aux->map_index = env->used_map_cnt;
env->used_maps[env->used_map_cnt++] = map;
if (bpf_map_is_cgroup_storage(map) &&
bpf_cgroup_storage_assign(env->prog->aux, map)) {
verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
}
fdput(f);
next_insn:
insn++;
i++;
continue;
}
/* Basic sanity check before we invest more work here. */
if (!bpf_opcode_in_insntable(insn->code)) {
verbose(env, "unknown opcode %02x\n", insn->code);
return -EINVAL;
}
}
/* now all pseudo BPF_LD_IMM64 instructions load valid
* 'struct bpf_map *' into a register instead of user map_fd.
* These pointers will be used later by verifier to validate map access.
*/
return 0;
}
/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
__bpf_free_used_maps(env->prog->aux, env->used_maps,
env->used_map_cnt);
}
/* drop refcnt of maps used by the rejected program */
static void release_btfs(struct bpf_verifier_env *env)
{
__bpf_free_used_btfs(env->prog->aux, env->used_btfs,
env->used_btf_cnt);
}
/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++, insn++) {
if (insn->code != (BPF_LD | BPF_IMM | BPF_DW))
continue;
if (insn->src_reg == BPF_PSEUDO_FUNC)
continue;
insn->src_reg = 0;
}
}
/* single env->prog->insni[off] instruction was replaced with the range
* insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
* [0, off) and [off, end) to new locations, so the patched range stays zero
*/
static int adjust_insn_aux_data(struct bpf_verifier_env *env,
struct bpf_prog *new_prog, u32 off, u32 cnt)
{
struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
struct bpf_insn *insn = new_prog->insnsi;
u32 prog_len;
int i;
/* aux info at OFF always needs adjustment, no matter fast path
* (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the
* original insn at old prog.
*/
old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1);
if (cnt == 1)
return 0;
prog_len = new_prog->len;
new_data = vzalloc(array_size(prog_len,
sizeof(struct bpf_insn_aux_data)));
if (!new_data)
return -ENOMEM;
memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++) {
new_data[i].seen = env->pass_cnt;
new_data[i].zext_dst = insn_has_def32(env, insn + i);
}
env->insn_aux_data = new_data;
vfree(old_data);
return 0;
}
static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
{
int i;
if (len == 1)
return;
/* NOTE: fake 'exit' subprog should be updated as well. */
for (i = 0; i <= env->subprog_cnt; i++) {
if (env->subprog_info[i].start <= off)
continue;
env->subprog_info[i].start += len - 1;
}
}
static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
{
struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
int i, sz = prog->aux->size_poke_tab;
struct bpf_jit_poke_descriptor *desc;
for (i = 0; i < sz; i++) {
desc = &tab[i];
desc->insn_idx += len - 1;
}
}
static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
const struct bpf_insn *patch, u32 len)
{
struct bpf_prog *new_prog;
new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
if (IS_ERR(new_prog)) {
if (PTR_ERR(new_prog) == -ERANGE)
verbose(env,
"insn %d cannot be patched due to 16-bit range\n",
env->insn_aux_data[off].orig_idx);
return NULL;
}
if (adjust_insn_aux_data(env, new_prog, off, len))
return NULL;
adjust_subprog_starts(env, off, len);
adjust_poke_descs(new_prog, len);
return new_prog;
}
static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
u32 off, u32 cnt)
{
int i, j;
/* find first prog starting at or after off (first to remove) */
for (i = 0; i < env->subprog_cnt; i++)
if (env->subprog_info[i].start >= off)
break;
/* find first prog starting at or after off + cnt (first to stay) */
for (j = i; j < env->subprog_cnt; j++)
if (env->subprog_info[j].start >= off + cnt)
break;
/* if j doesn't start exactly at off + cnt, we are just removing
* the front of previous prog
*/
if (env->subprog_info[j].start != off + cnt)
j--;
if (j > i) {
struct bpf_prog_aux *aux = env->prog->aux;
int move;
/* move fake 'exit' subprog as well */
move = env->subprog_cnt + 1 - j;
memmove(env->subprog_info + i,
env->subprog_info + j,
sizeof(*env->subprog_info) * move);
env->subprog_cnt -= j - i;
/* remove func_info */
if (aux->func_info) {
move = aux->func_info_cnt - j;
memmove(aux->func_info + i,
aux->func_info + j,
sizeof(*aux->func_info) * move);
aux->func_info_cnt -= j - i;
/* func_info->insn_off is set after all code rewrites,
* in adjust_btf_func() - no need to adjust
*/
}
} else {
/* convert i from "first prog to remove" to "first to adjust" */
if (env->subprog_info[i].start == off)
i++;
}
/* update fake 'exit' subprog as well */
for (; i <= env->subprog_cnt; i++)
env->subprog_info[i].start -= cnt;
return 0;
}
static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off,
u32 cnt)
{
struct bpf_prog *prog = env->prog;
u32 i, l_off, l_cnt, nr_linfo;
struct bpf_line_info *linfo;
nr_linfo = prog->aux->nr_linfo;
if (!nr_linfo)
return 0;
linfo = prog->aux->linfo;
/* find first line info to remove, count lines to be removed */
for (i = 0; i < nr_linfo; i++)
if (linfo[i].insn_off >= off)
break;
l_off = i;
l_cnt = 0;
for (; i < nr_linfo; i++)
if (linfo[i].insn_off < off + cnt)
l_cnt++;
else
break;
/* First live insn doesn't match first live linfo, it needs to "inherit"
* last removed linfo. prog is already modified, so prog->len == off
* means no live instructions after (tail of the program was removed).
*/
if (prog->len != off && l_cnt &&
(i == nr_linfo || linfo[i].insn_off != off + cnt)) {
l_cnt--;
linfo[--i].insn_off = off + cnt;
}
/* remove the line info which refer to the removed instructions */
if (l_cnt) {
memmove(linfo + l_off, linfo + i,
sizeof(*linfo) * (nr_linfo - i));
prog->aux->nr_linfo -= l_cnt;
nr_linfo = prog->aux->nr_linfo;
}
/* pull all linfo[i].insn_off >= off + cnt in by cnt */
for (i = l_off; i < nr_linfo; i++)
linfo[i].insn_off -= cnt;
/* fix up all subprogs (incl. 'exit') which start >= off */
for (i = 0; i <= env->subprog_cnt; i++)
if (env->subprog_info[i].linfo_idx > l_off) {
/* program may have started in the removed region but
* may not be fully removed
*/
if (env->subprog_info[i].linfo_idx >= l_off + l_cnt)
env->subprog_info[i].linfo_idx -= l_cnt;
else
env->subprog_info[i].linfo_idx = l_off;
}
return 0;
}
static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
{
struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
unsigned int orig_prog_len = env->prog->len;
int err;
if (bpf_prog_is_dev_bound(env->prog->aux))
bpf_prog_offload_remove_insns(env, off, cnt);
err = bpf_remove_insns(env->prog, off, cnt);
if (err)
return err;
err = adjust_subprog_starts_after_remove(env, off, cnt);
if (err)
return err;
err = bpf_adj_linfo_after_remove(env, off, cnt);
if (err)
return err;
memmove(aux_data + off, aux_data + off + cnt,
sizeof(*aux_data) * (orig_prog_len - off - cnt));
return 0;
}
/* The verifier does more data flow analysis than llvm and will not
* explore branches that are dead at run time. Malicious programs can
* have dead code too. Therefore replace all dead at-run-time code
* with 'ja -1'.
*
* Just nops are not optimal, e.g. if they would sit at the end of the
* program and through another bug we would manage to jump there, then
* we'd execute beyond program memory otherwise. Returning exception
* code also wouldn't work since we can have subprogs where the dead
* code could be located.
*/
static void sanitize_dead_code(struct bpf_verifier_env *env)
{
struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
struct bpf_insn *insn = env->prog->insnsi;
const int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++) {
if (aux_data[i].seen)
continue;
memcpy(insn + i, &trap, sizeof(trap));
}
}
static bool insn_is_cond_jump(u8 code)
{
u8 op;
if (BPF_CLASS(code) == BPF_JMP32)
return true;
if (BPF_CLASS(code) != BPF_JMP)
return false;
op = BPF_OP(code);
return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
}
static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
{
struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
struct bpf_insn *insn = env->prog->insnsi;
const int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++, insn++) {
if (!insn_is_cond_jump(insn->code))
continue;
if (!aux_data[i + 1].seen)
ja.off = insn->off;
else if (!aux_data[i + 1 + insn->off].seen)
ja.off = 0;
else
continue;
if (bpf_prog_is_dev_bound(env->prog->aux))
bpf_prog_offload_replace_insn(env, i, &ja);
memcpy(insn, &ja, sizeof(ja));
}
}
static int opt_remove_dead_code(struct bpf_verifier_env *env)
{
struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
int insn_cnt = env->prog->len;
int i, err;
for (i = 0; i < insn_cnt; i++) {
int j;
j = 0;
while (i + j < insn_cnt && !aux_data[i + j].seen)
j++;
if (!j)
continue;
err = verifier_remove_insns(env, i, j);
if (err)
return err;
insn_cnt = env->prog->len;
}
return 0;
}
static int opt_remove_nops(struct bpf_verifier_env *env)
{
const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
int i, err;
for (i = 0; i < insn_cnt; i++) {
if (memcmp(&insn[i], &ja, sizeof(ja)))
continue;
err = verifier_remove_insns(env, i, 1);
if (err)
return err;
insn_cnt--;
i--;
}
return 0;
}
static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
const union bpf_attr *attr)
{
struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4];
struct bpf_insn_aux_data *aux = env->insn_aux_data;
int i, patch_len, delta = 0, len = env->prog->len;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_prog *new_prog;
bool rnd_hi32;
rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32;
zext_patch[1] = BPF_ZEXT_REG(0);
rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0);
rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX);
for (i = 0; i < len; i++) {
int adj_idx = i + delta;
struct bpf_insn insn;
int load_reg;
insn = insns[adj_idx];
load_reg = insn_def_regno(&insn);
if (!aux[adj_idx].zext_dst) {
u8 code, class;
u32 imm_rnd;
if (!rnd_hi32)
continue;
code = insn.code;
class = BPF_CLASS(code);
if (load_reg == -1)
continue;
/* NOTE: arg "reg" (the fourth one) is only used for
* BPF_STX + SRC_OP, so it is safe to pass NULL
* here.
*/
if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) {
if (class == BPF_LD &&
BPF_MODE(code) == BPF_IMM)
i++;
continue;
}
/* ctx load could be transformed into wider load. */
if (class == BPF_LDX &&
aux[adj_idx].ptr_type == PTR_TO_CTX)
continue;
imm_rnd = get_random_int();
rnd_hi32_patch[0] = insn;
rnd_hi32_patch[1].imm = imm_rnd;
rnd_hi32_patch[3].dst_reg = load_reg;
patch = rnd_hi32_patch;
patch_len = 4;
goto apply_patch_buffer;
}
/* Add in an zero-extend instruction if a) the JIT has requested
* it or b) it's a CMPXCHG.
*
* The latter is because: BPF_CMPXCHG always loads a value into
* R0, therefore always zero-extends. However some archs'
* equivalent instruction only does this load when the
* comparison is successful. This detail of CMPXCHG is
* orthogonal to the general zero-extension behaviour of the
* CPU, so it's treated independently of bpf_jit_needs_zext.
*/
if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn))
continue;
if (WARN_ON(load_reg == -1)) {
verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n");
return -EFAULT;
}
zext_patch[0] = insn;
zext_patch[1].dst_reg = load_reg;
zext_patch[1].src_reg = load_reg;
patch = zext_patch;
patch_len = 2;
apply_patch_buffer:
new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len);
if (!new_prog)
return -ENOMEM;
env->prog = new_prog;
insns = new_prog->insnsi;
aux = env->insn_aux_data;
delta += patch_len - 1;
}
return 0;
}
/* convert load instructions that access fields of a context type into a
* sequence of instructions that access fields of the underlying structure:
* struct __sk_buff -> struct sk_buff
* struct bpf_sock_ops -> struct sock
*/
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
const struct bpf_verifier_ops *ops = env->ops;
int i, cnt, size, ctx_field_size, delta = 0;
const int insn_cnt = env->prog->len;
struct bpf_insn insn_buf[16], *insn;
u32 target_size, size_default, off;
struct bpf_prog *new_prog;
enum bpf_access_type type;
bool is_narrower_load;
if (ops->gen_prologue || env->seen_direct_write) {
if (!ops->gen_prologue) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
} else if (cnt) {
new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
env->prog = new_prog;
delta += cnt - 1;
}
}
if (bpf_prog_is_dev_bound(env->prog->aux))
return 0;
insn = env->prog->insnsi + delta;
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
type = BPF_READ;
else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
insn->code == (BPF_STX | BPF_MEM | BPF_DW))
type = BPF_WRITE;
else
continue;
if (type == BPF_WRITE &&
env->insn_aux_data[i + delta].sanitize_stack_off) {
struct bpf_insn patch[] = {
/* Sanitize suspicious stack slot with zero.
* There are no memory dependencies for this store,
* since it's only using frame pointer and immediate
* constant of zero
*/
BPF_ST_MEM(BPF_DW, BPF_REG_FP,
env->insn_aux_data[i + delta].sanitize_stack_off,
0),
/* the original STX instruction will immediately
* overwrite the same stack slot with appropriate value
*/
*insn,
};
cnt = ARRAY_SIZE(patch);
new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
switch (env->insn_aux_data[i + delta].ptr_type) {
case PTR_TO_CTX:
if (!ops->convert_ctx_access)
continue;
convert_ctx_access = ops->convert_ctx_access;
break;
case PTR_TO_SOCKET:
case PTR_TO_SOCK_COMMON:
convert_ctx_access = bpf_sock_convert_ctx_access;
break;
case PTR_TO_TCP_SOCK:
convert_ctx_access = bpf_tcp_sock_convert_ctx_access;
break;
case PTR_TO_XDP_SOCK:
convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
break;
case PTR_TO_BTF_ID:
if (type == BPF_READ) {
insn->code = BPF_LDX | BPF_PROBE_MEM |
BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
} else if (resolve_prog_type(env->prog) != BPF_PROG_TYPE_STRUCT_OPS) {
verbose(env, "Writes through BTF pointers are not allowed\n");
return -EINVAL;
}
continue;
default:
continue;
}
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
* convert_ctx_access changes. If conversion is successful,
* we will apply proper mask to the result.
*/
is_narrower_load = size < ctx_field_size;
size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
off = insn->off;
if (is_narrower_load) {
u8 size_code;
if (type == BPF_WRITE) {
verbose(env, "bpf verifier narrow ctx access misconfigured\n");
return -EINVAL;
}
size_code = BPF_H;
if (ctx_field_size == 4)
size_code = BPF_W;
else if (ctx_field_size == 8)
size_code = BPF_DW;
insn->off = off & ~(size_default - 1);
insn->code = BPF_LDX | BPF_MEM | size_code;
}
target_size = 0;
cnt = convert_ctx_access(type, insn, insn_buf, env->prog,
&target_size);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
(ctx_field_size && !target_size)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
if (is_narrower_load && size < target_size) {
u8 shift = bpf_ctx_narrow_access_offset(
off, size, size_default) * 8;
if (ctx_field_size <= 4) {
if (shift)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
insn->dst_reg,
shift);
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
(1 << size * 8) - 1);
} else {
if (shift)
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
insn->dst_reg,
shift);
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
(1ULL << size * 8) - 1);
}
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
/* keep walking new program and skip insns we just inserted */
env->prog = new_prog;
insn = new_prog->insnsi + i + delta;
}
return 0;
}
static int jit_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog, **func, *tmp;
int i, j, subprog_start, subprog_end = 0, len, subprog;
struct bpf_map *map_ptr;
struct bpf_insn *insn;
void *old_bpf_func;
int err, num_exentries;
if (env->subprog_cnt <= 1)
return 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (bpf_pseudo_func(insn)) {
env->insn_aux_data[i].call_imm = insn->imm;
/* subprog is encoded in insn[1].imm */
continue;
}
if (!bpf_pseudo_call(insn))
continue;
/* Upon error here we cannot fall back to interpreter but
* need a hard reject of the program. Thus -EFAULT is
* propagated in any case.
*/
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i + insn->imm + 1);
return -EFAULT;
}
/* temporarily remember subprog id inside insn instead of
* aux_data, since next loop will split up all insns into funcs
*/
insn->off = subprog;
/* remember original imm in case JIT fails and fallback
* to interpreter will be needed
*/
env->insn_aux_data[i].call_imm = insn->imm;
/* point imm to __bpf_call_base+1 from JITs point of view */
insn->imm = 1;
}
err = bpf_prog_alloc_jited_linfo(prog);
if (err)
goto out_undo_insn;
err = -ENOMEM;
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
subprog_end = env->subprog_info[i + 1].start;
len = subprog_end - subprog_start;
/* BPF_PROG_RUN doesn't call subprogs directly,
* hence main prog stats include the runtime of subprogs.
* subprogs don't have IDs and not reachable via prog_get_next_id
* func[i]->stats will never be accessed and stays NULL
*/
func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER);
if (!func[i])
goto out_free;
memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
len * sizeof(struct bpf_insn));
func[i]->type = prog->type;
func[i]->len = len;
if (bpf_prog_calc_tag(func[i]))
goto out_free;
func[i]->is_func = 1;
func[i]->aux->func_idx = i;
/* the btf and func_info will be freed only at prog->aux */
func[i]->aux->btf = prog->aux->btf;
func[i]->aux->func_info = prog->aux->func_info;
for (j = 0; j < prog->aux->size_poke_tab; j++) {
u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
int ret;
if (!(insn_idx >= subprog_start &&
insn_idx <= subprog_end))
continue;
ret = bpf_jit_add_poke_descriptor(func[i],
&prog->aux->poke_tab[j]);
if (ret < 0) {
verbose(env, "adding tail call poke descriptor failed\n");
goto out_free;
}
func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
if (ret < 0) {
verbose(env, "tracking tail call prog failed\n");
goto out_free;
}
}
/* Use bpf_prog_F_tag to indicate functions in stack traces.
* Long term would need debug info to populate names
*/
func[i]->aux->name[0] = 'F';
func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
func[i]->jit_requested = 1;
func[i]->aux->kfunc_tab = prog->aux->kfunc_tab;
func[i]->aux->linfo = prog->aux->linfo;
func[i]->aux->nr_linfo = prog->aux->nr_linfo;
func[i]->aux->jited_linfo = prog->aux->jited_linfo;
func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
num_exentries = 0;
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
BPF_MODE(insn->code) == BPF_PROBE_MEM)
num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
goto out_free;
}
cond_resched();
}
/* Untrack main program's aux structs so that during map_poke_run()
* we will not stumble upon the unfilled poke descriptors; each
* of the main program's poke descs got distributed across subprogs
* and got tracked onto map, so we are sure that none of them will
* be missed after the operation below
*/
for (i = 0; i < prog->aux->size_poke_tab; i++) {
map_ptr = prog->aux->poke_tab[i].tail_call.map;
map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
}
/* at this point all bpf functions were successfully JITed
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
*/
for (i = 0; i < env->subprog_cnt; i++) {
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (bpf_pseudo_func(insn)) {
subprog = insn[1].imm;
insn[0].imm = (u32)(long)func[subprog]->bpf_func;
insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32;
continue;
}
if (!bpf_pseudo_call(insn))
continue;
subprog = insn->off;
insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
__bpf_call_base;
}
/* we use the aux data to keep a list of the start addresses
* of the JITed images for each function in the program
*
* for some architectures, such as powerpc64, the imm field
* might not be large enough to hold the offset of the start
* address of the callee's JITed image from __bpf_call_base
*
* in such cases, we can lookup the start address of a callee
* by using its subprog id, available from the off field of
* the call instruction, as an index for this list
*/
func[i]->aux->func = func;
func[i]->aux->func_cnt = env->subprog_cnt;
}
for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
err = -ENOTSUPP;
goto out_free;
}
cond_resched();
}
/* finally lock prog and jit images for all functions and
* populate kallsysm
*/
for (i = 0; i < env->subprog_cnt; i++) {
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
/* Last step: make now unused interpreter insns from main
* prog consistent for later dump requests, so they can
* later look the same as if they were interpreted only.
*/
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (bpf_pseudo_func(insn)) {
insn[0].imm = env->insn_aux_data[i].call_imm;
insn[1].imm = find_subprog(env, i + insn[0].imm + 1);
continue;
}
if (!bpf_pseudo_call(insn))
continue;
insn->off = env->insn_aux_data[i].call_imm;
subprog = find_subprog(env, i + insn->off + 1);
insn->imm = subprog;
}
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
prog->aux->func_cnt = env->subprog_cnt;
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
for (i = 0; i < env->subprog_cnt; i++) {
if (!func[i])
continue;
for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
}
bpf_jit_free(func[i]);
}
kfree(func);
out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (!bpf_pseudo_call(insn))
continue;
insn->off = 0;
insn->imm = env->insn_aux_data[i].call_imm;
}
bpf_prog_jit_attempt_done(prog);
return err;
}
static int fixup_call_args(struct bpf_verifier_env *env)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
struct bpf_prog *prog = env->prog;
struct bpf_insn *insn = prog->insnsi;
bool has_kfunc_call = bpf_prog_has_kfunc_call(prog);
int i, depth;
#endif
int err = 0;
if (env->prog->jit_requested &&
!bpf_prog_is_dev_bound(env->prog->aux)) {
err = jit_subprogs(env);
if (err == 0)
return 0;
if (err == -EFAULT)
return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
if (has_kfunc_call) {
verbose(env, "calling kernel functions are not allowed in non-JITed programs\n");
return -EINVAL;
}
if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) {
/* When JIT fails the progs with bpf2bpf calls and tail_calls
* have to be rejected, since interpreter doesn't support them yet.
*/
verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
return -EINVAL;
}
for (i = 0; i < prog->len; i++, insn++) {
if (bpf_pseudo_func(insn)) {
/* When JIT fails the progs with callback calls
* have to be rejected, since interpreter doesn't support them yet.
*/
verbose(env, "callbacks are not allowed in non-JITed programs\n");
return -EINVAL;
}
if (!bpf_pseudo_call(insn))
continue;
depth = get_callee_stack_depth(env, insn, i);
if (depth < 0)
return depth;
bpf_patch_call_args(insn, depth);
}
err = 0;
#endif
return err;
}
static int fixup_kfunc_call(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
const struct bpf_kfunc_desc *desc;
/* insn->imm has the btf func_id. Replace it with
* an address (relative to __bpf_base_call).
*/
desc = find_kfunc_desc(env->prog, insn->imm);
if (!desc) {
verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n",
insn->imm);
return -EFAULT;
}
insn->imm = desc->imm;
return 0;
}
/* Do various post-verification rewrites in a single program pass.
* These rewrites simplify JIT and interpreter implementations.
*/
static int do_misc_fixups(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
bool expect_blinding = bpf_jit_blinding_enabled(prog);
struct bpf_insn *insn = prog->insnsi;
const struct bpf_func_proto *fn;
const int insn_cnt = prog->len;
const struct bpf_map_ops *ops;
struct bpf_insn_aux_data *aux;
struct bpf_insn insn_buf[16];
struct bpf_prog *new_prog;
struct bpf_map *map_ptr;
int i, ret, cnt, delta = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
/* Make divide-by-zero exceptions impossible. */
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
bool isdiv = BPF_OP(insn->code) == BPF_DIV;
struct bpf_insn *patchlet;
struct bpf_insn chk_and_div[] = {
/* [R,W]x div 0 -> 0 */
BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
BPF_JNE | BPF_K, insn->src_reg,
0, 2, 0),
BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
*insn,
};
struct bpf_insn chk_and_mod[] = {
/* [R,W]x mod 0 -> [R,W]x */
BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
BPF_JEQ | BPF_K, insn->src_reg,
0, 1 + (is64 ? 0 : 1), 0),
*insn,
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
BPF_MOV32_REG(insn->dst_reg, insn->dst_reg),
};
patchlet = isdiv ? chk_and_div : chk_and_mod;
cnt = isdiv ? ARRAY_SIZE(chk_and_div) :
ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0);
new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
/* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */
if (BPF_CLASS(insn->code) == BPF_LD &&
(BPF_MODE(insn->code) == BPF_ABS ||
BPF_MODE(insn->code) == BPF_IND)) {
cnt = env->ops->gen_ld_abs(insn, insn_buf);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
/* Rewrite pointer arithmetic to mitigate speculation attacks. */
if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) ||
insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
struct bpf_insn *patch = &insn_buf[0];
bool issrc, isneg;
u32 off_reg;
aux = &env->insn_aux_data[i + delta];
if (!aux->alu_state ||
aux->alu_state == BPF_ALU_NON_POINTER)
continue;
isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
BPF_ALU_SANITIZE_SRC;
off_reg = issrc ? insn->src_reg : insn->dst_reg;
if (isneg)
*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
*patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
*patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg);
if (!issrc)
*patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg);
insn->src_reg = BPF_REG_AX;
if (isneg)
insn->code = insn->code == code_add ?
code_sub : code_add;
*patch++ = *insn;
if (issrc && isneg)
*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
cnt = patch - insn_buf;
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
if (insn->code != (BPF_JMP | BPF_CALL))
continue;
if (insn->src_reg == BPF_PSEUDO_CALL)
continue;
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
ret = fixup_kfunc_call(env, insn);
if (ret)
return ret;
continue;
}
if (insn->imm == BPF_FUNC_get_route_realm)
prog->dst_needed = 1;
if (insn->imm == BPF_FUNC_get_prandom_u32)
bpf_user_rnd_init_once();
if (insn->imm == BPF_FUNC_override_return)
prog->kprobe_override = 1;
if (insn->imm == BPF_FUNC_tail_call) {
/* If we tail call into other programs, we
* cannot make any assumptions since they can
* be replaced dynamically during runtime in
* the program array.
*/
prog->cb_access = 1;
if (!allow_tail_call_in_subprogs(env))
prog->aux->stack_depth = MAX_BPF_STACK;
prog->aux->max_pkt_offset = MAX_PACKET_OFF;
/* mark bpf_tail_call as different opcode to avoid
* conditional branch in the interpeter for every normal
* call and to prevent accidental JITing by JIT compiler
* that doesn't support bpf_tail_call yet
*/
insn->imm = 0;
insn->code = BPF_JMP | BPF_TAIL_CALL;
aux = &env->insn_aux_data[i + delta];
if (env->bpf_capable && !expect_blinding &&
prog->jit_requested &&
!bpf_map_key_poisoned(aux) &&
!bpf_map_ptr_poisoned(aux) &&
!bpf_map_ptr_unpriv(aux)) {
struct bpf_jit_poke_descriptor desc = {
.reason = BPF_POKE_REASON_TAIL_CALL,
.tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
.tail_call.key = bpf_map_key_immediate(aux),
.insn_idx = i + delta,
};
ret = bpf_jit_add_poke_descriptor(prog, &desc);
if (ret < 0) {
verbose(env, "adding tail call poke descriptor failed\n");
return ret;
}
insn->imm = ret + 1;
continue;
}
if (!bpf_map_ptr_unpriv(aux))
continue;
/* instead of changing every JIT dealing with tail_call
* emit two extra insns:
* if (index >= max_entries) goto out;
* index &= array->index_mask;
* to avoid out-of-bounds cpu speculation
*/
if (bpf_map_ptr_poisoned(aux)) {
verbose(env, "tail_call abusing map_ptr\n");
return -EINVAL;
}
map_ptr = BPF_MAP_PTR(aux->map_ptr_state);
insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
map_ptr->max_entries, 2);
insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
container_of(map_ptr,
struct bpf_array,
map)->index_mask);
insn_buf[2] = *insn;
cnt = 3;
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
* and other inlining handlers are currently limited to 64 bit
* only.
*/
if (prog->jit_requested && BITS_PER_LONG == 64 &&
(insn->imm == BPF_FUNC_map_lookup_elem ||
insn->imm == BPF_FUNC_map_update_elem ||
insn->imm == BPF_FUNC_map_delete_elem ||
insn->imm == BPF_FUNC_map_push_elem ||
insn->imm == BPF_FUNC_map_pop_elem ||
insn->imm == BPF_FUNC_map_peek_elem ||
insn->imm == BPF_FUNC_redirect_map)) {
aux = &env->insn_aux_data[i + delta];
if (bpf_map_ptr_poisoned(aux))
goto patch_call_imm;
map_ptr = BPF_MAP_PTR(aux->map_ptr_state);
ops = map_ptr->ops;
if (insn->imm == BPF_FUNC_map_lookup_elem &&
ops->map_gen_lookup) {
cnt = ops->map_gen_lookup(map_ptr, insn_buf);
if (cnt == -EOPNOTSUPP)
goto patch_map_ops_generic;
if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
new_prog = bpf_patch_insn_data(env, i + delta,
insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
BUILD_BUG_ON(!__same_type(ops->map_lookup_elem,
(void *(*)(struct bpf_map *map, void *key))NULL));
BUILD_BUG_ON(!__same_type(ops->map_delete_elem,
(int (*)(struct bpf_map *map, void *key))NULL));
BUILD_BUG_ON(!__same_type(ops->map_update_elem,
(int (*)(struct bpf_map *map, void *key, void *value,
u64 flags))NULL));
BUILD_BUG_ON(!__same_type(ops->map_push_elem,
(int (*)(struct bpf_map *map, void *value,
u64 flags))NULL));
BUILD_BUG_ON(!__same_type(ops->map_pop_elem,
(int (*)(struct bpf_map *map, void *value))NULL));
BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
(int (*)(struct bpf_map *map, void *value))NULL));
BUILD_BUG_ON(!__same_type(ops->map_redirect,
(int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
patch_map_ops_generic:
switch (insn->imm) {
case BPF_FUNC_map_lookup_elem:
insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_map_update_elem:
insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_map_delete_elem:
insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_map_push_elem:
insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_map_pop_elem:
insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_map_peek_elem:
insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_redirect_map:
insn->imm = BPF_CAST_CALL(ops->map_redirect) -
__bpf_call_base;
continue;
}
goto patch_call_imm;
}
/* Implement bpf_jiffies64 inline. */
if (prog->jit_requested && BITS_PER_LONG == 64 &&
insn->imm == BPF_FUNC_jiffies64) {
struct bpf_insn ld_jiffies_addr[2] = {
BPF_LD_IMM64(BPF_REG_0,
(unsigned long)&jiffies),
};
insn_buf[0] = ld_jiffies_addr[0];
insn_buf[1] = ld_jiffies_addr[1];
insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0,
BPF_REG_0, 0);
cnt = 3;
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
if (!fn->func) {
verbose(env,
"kernel subsystem misconfigured func %s#%d\n",
func_id_name(insn->imm), insn->imm);
return -EFAULT;
}
insn->imm = fn->func - __bpf_call_base;
}
/* Since poke tab is now finalized, publish aux to tracker. */
for (i = 0; i < prog->aux->size_poke_tab; i++) {
map_ptr = prog->aux->poke_tab[i].tail_call.map;
if (!map_ptr->ops->map_poke_track ||
!map_ptr->ops->map_poke_untrack ||
!map_ptr->ops->map_poke_run) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux);
if (ret < 0) {
verbose(env, "tracking tail call prog failed\n");
return ret;
}
}
sort_kfunc_descs_by_imm(env->prog);
return 0;
}
static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl, *sln;
int i;
sl = env->free_list;
while (sl) {
sln = sl->next;
free_verifier_state(&sl->state, false);
kfree(sl);
sl = sln;
}
env->free_list = NULL;
if (!env->explored_states)
return;
for (i = 0; i < state_htab_size(env); i++) {
sl = env->explored_states[i];
while (sl) {
sln = sl->next;
free_verifier_state(&sl->state, false);
kfree(sl);
sl = sln;
}
env->explored_states[i] = NULL;
}
}
/* The verifier is using insn_aux_data[] to store temporary data during
* verification and to store information for passes that run after the
* verification like dead code sanitization. do_check_common() for subprogram N
* may analyze many other subprograms. sanitize_insn_aux_data() clears all
* temporary data after do_check_common() finds that subprogram N cannot be
* verified independently. pass_cnt counts the number of times
* do_check_common() was run and insn->aux->seen tells the pass number
* insn_aux_data was touched. These variables are compared to clear temporary
* data from failed pass. For testing and experiments do_check_common() can be
* run multiple times even when prior attempt to verify is unsuccessful.
*/
static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
struct bpf_insn_aux_data *aux;
int i, class;
for (i = 0; i < env->prog->len; i++) {
class = BPF_CLASS(insn[i].code);
if (class != BPF_LDX && class != BPF_STX)
continue;
aux = &env->insn_aux_data[i];
if (aux->seen != env->pass_cnt)
continue;
memset(aux, 0, offsetof(typeof(*aux), orig_idx));
}
}
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state;
struct bpf_reg_state *regs;
int ret, i;
env->prev_linfo = NULL;
env->pass_cnt++;
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->speculative = false;
state->branches = 1;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
}
env->cur_state = state;
init_func_state(env, state->frame[0],
BPF_MAIN_FUNC /* callsite */,
0 /* frameno */,
subprog);
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
ret = btf_prepare_func_args(env, subprog, regs);
if (ret)
goto out;
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
if (regs[i].type == PTR_TO_CTX)
mark_reg_known_zero(env, regs, i);
else if (regs[i].type == SCALAR_VALUE)
mark_reg_unknown(env, regs, i);
else if (regs[i].type == PTR_TO_MEM_OR_NULL) {
const u32 mem_size = regs[i].mem_size;
mark_reg_known_zero(env, regs, i);
regs[i].mem_size = mem_size;
regs[i].id = ++env->id_gen;
}
}
} else {
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, BPF_REG_1);
ret = btf_check_subprog_arg_match(env, subprog, regs);
if (ret == -EFAULT)
/* unlikely verifier bug. abort.
* ret == 0 and ret < 0 are sadly acceptable for
* main() function due to backward compatibility.
* Like socket filter program may be written as:
* int bpf_prog(struct pt_regs *ctx)
* and never dereference that ctx in the program.
* 'struct pt_regs' is a type mismatch for socket
* filter that should be using 'struct __sk_buff'.
*/
goto out;
}
ret = do_check(env);
out:
/* check for NULL is necessary, since cur_state can be freed inside
* do_check() under memory pressure.
*/
if (env->cur_state) {
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
}
while (!pop_stack(env, NULL, NULL, false));
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
if (ret)
/* clean aux data in case subprog was rejected */
sanitize_insn_aux_data(env);
return ret;
}
/* Verify all global functions in a BPF program one by one based on their BTF.
* All global functions must pass verification. Otherwise the whole program is rejected.
* Consider:
* int bar(int);
* int foo(int f)
* {
* return bar(f);
* }
* int bar(int b)
* {
* ...
* }
* foo() will be verified first for R1=any_scalar_value. During verification it
* will be assumed that bar() already verified successfully and call to bar()
* from foo() will be checked for type match only. Later bar() will be verified
* independently to check that it's safe for R1=any_scalar_value.
*/
static int do_check_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog_aux *aux = env->prog->aux;
int i, ret;
if (!aux->func_info)
return 0;
for (i = 1; i < env->subprog_cnt; i++) {
if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
continue;
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
ret = do_check_common(env, i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
verbose(env,
"Func#%d is safe for any args that match its prototype\n",
i);
}
}
return 0;
}
static int do_check_main(struct bpf_verifier_env *env)
{
int ret;
env->insn_idx = 0;
ret = do_check_common(env, 0);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
}
static void print_verification_stats(struct bpf_verifier_env *env)
{
int i;
if (env->log.level & BPF_LOG_STATS) {
verbose(env, "verification time %lld usec\n",
div_u64(env->verification_time, 1000));
verbose(env, "stack depth ");
for (i = 0; i < env->subprog_cnt; i++) {
u32 depth = env->subprog_info[i].stack_depth;
verbose(env, "%d", depth);
if (i + 1 < env->subprog_cnt)
verbose(env, "+");
}
verbose(env, "\n");
}
verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
"total_states %d peak_states %d mark_read %d\n",
env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
env->max_states_per_insn, env->total_states,
env->peak_states, env->longest_mark_read_walk);
}
static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
{
const struct btf_type *t, *func_proto;
const struct bpf_struct_ops *st_ops;
const struct btf_member *member;
struct bpf_prog *prog = env->prog;
u32 btf_id, member_idx;
const char *mname;
if (!prog->gpl_compatible) {
verbose(env, "struct ops programs must have a GPL compatible license\n");
return -EINVAL;
}
btf_id = prog->aux->attach_btf_id;
st_ops = bpf_struct_ops_find(btf_id);
if (!st_ops) {
verbose(env, "attach_btf_id %u is not a supported struct\n",
btf_id);
return -ENOTSUPP;
}
t = st_ops->type;
member_idx = prog->expected_attach_type;
if (member_idx >= btf_type_vlen(t)) {
verbose(env, "attach to invalid member idx %u of struct %s\n",
member_idx, st_ops->name);
return -EINVAL;
}
member = &btf_type_member(t)[member_idx];
mname = btf_name_by_offset(btf_vmlinux, member->name_off);
func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
NULL);
if (!func_proto) {
verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
mname, member_idx, st_ops->name);
return -EINVAL;
}
if (st_ops->check_member) {
int err = st_ops->check_member(t, member);
if (err) {
verbose(env, "attach to unsupported member %s of struct %s\n",
mname, st_ops->name);
return err;
}
}
prog->aux->attach_func_proto = func_proto;
prog->aux->attach_func_name = mname;
env->ops = st_ops->verifier_ops;
return 0;
}
#define SECURITY_PREFIX "security_"
static int check_attach_modify_return(unsigned long addr, const char *func_name)
{
if (within_error_injection_list(addr) ||
!strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
return 0;
return -EINVAL;
}
/* list of non-sleepable functions that are otherwise on
* ALLOW_ERROR_INJECTION list
*/
BTF_SET_START(btf_non_sleepable_error_inject)
/* Three functions below can be called from sleepable and non-sleepable context.
* Assume non-sleepable from bpf safety point of view.
*/
BTF_ID(func, __add_to_page_cache_locked)
BTF_ID(func, should_fail_alloc_page)
BTF_ID(func, should_failslab)
BTF_SET_END(btf_non_sleepable_error_inject)
static int check_non_sleepable_error_inject(u32 btf_id)
{
return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
}
int bpf_check_attach_target(struct bpf_verifier_log *log,
const struct bpf_prog *prog,
const struct bpf_prog *tgt_prog,
u32 btf_id,
struct bpf_attach_target_info *tgt_info)
{
bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
const char prefix[] = "btf_trace_";
int ret = 0, subprog = -1, i;
const struct btf_type *t;
bool conservative = true;
const char *tname;
struct btf *btf;
long addr = 0;
if (!btf_id) {
bpf_log(log, "Tracing programs must provide btf_id\n");
return -EINVAL;
}
btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf;
if (!btf) {
bpf_log(log,
"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
return -EINVAL;
}
t = btf_type_by_id(btf, btf_id);
if (!t) {
bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
return -EINVAL;
}
tname = btf_name_by_offset(btf, t->name_off);
if (!tname) {
bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
return -EINVAL;
}
if (tgt_prog) {
struct bpf_prog_aux *aux = tgt_prog->aux;
for (i = 0; i < aux->func_info_cnt; i++)
if (aux->func_info[i].type_id == btf_id) {
subprog = i;
break;
}
if (subprog == -1) {
bpf_log(log, "Subprog %s doesn't exist\n", tname);
return -EINVAL;
}
conservative = aux->func_info_aux[subprog].unreliable;
if (prog_extension) {
if (conservative) {
bpf_log(log,
"Cannot replace static functions\n");
return -EINVAL;
}
if (!prog->jit_requested) {
bpf_log(log,
"Extension programs should be JITed\n");
return -EINVAL;
}
}
if (!tgt_prog->jited) {
bpf_log(log, "Can attach to only JITed progs\n");
return -EINVAL;
}
if (tgt_prog->type == prog->type) {
/* Cannot fentry/fexit another fentry/fexit program.
* Cannot attach program extension to another extension.
* It's ok to attach fentry/fexit to extension program.
*/
bpf_log(log, "Cannot recursively attach\n");
return -EINVAL;
}
if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
prog_extension &&
(tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) {
/* Program extensions can extend all program types
* except fentry/fexit. The reason is the following.
* The fentry/fexit programs are used for performance
* analysis, stats and can be attached to any program
* type except themselves. When extension program is
* replacing XDP function it is necessary to allow
* performance analysis of all functions. Both original
* XDP program and its program extension. Hence
* attaching fentry/fexit to BPF_PROG_TYPE_EXT is
* allowed. If extending of fentry/fexit was allowed it
* would be possible to create long call chain
* fentry->extension->fentry->extension beyond
* reasonable stack size. Hence extending fentry is not
* allowed.
*/
bpf_log(log, "Cannot extend fentry/fexit\n");
return -EINVAL;
}
} else {
if (prog_extension) {
bpf_log(log, "Cannot replace kernel functions\n");
return -EINVAL;
}
}
switch (prog->expected_attach_type) {
case BPF_TRACE_RAW_TP:
if (tgt_prog) {
bpf_log(log,
"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
return -EINVAL;
}
if (!btf_type_is_typedef(t)) {
bpf_log(log, "attach_btf_id %u is not a typedef\n",
btf_id);
return -EINVAL;
}
if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
btf_id, tname);
return -EINVAL;
}
tname += sizeof(prefix) - 1;
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_ptr(t))
/* should never happen in valid vmlinux build */
return -EINVAL;
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_func_proto(t))
/* should never happen in valid vmlinux build */
return -EINVAL;
break;
case BPF_TRACE_ITER:
if (!btf_type_is_func(t)) {
bpf_log(log, "attach_btf_id %u is not a function\n",
btf_id);
return -EINVAL;
}
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_func_proto(t))
return -EINVAL;
ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
if (ret)
return ret;
break;
default:
if (!prog_extension)
return -EINVAL;
fallthrough;
case BPF_MODIFY_RETURN:
case BPF_LSM_MAC:
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
if (!btf_type_is_func(t)) {
bpf_log(log, "attach_btf_id %u is not a function\n",
btf_id);
return -EINVAL;
}
if (prog_extension &&
btf_check_type_match(log, prog, btf, t))
return -EINVAL;
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_func_proto(t))
return -EINVAL;
if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
(!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
return -EINVAL;
if (tgt_prog && conservative)
t = NULL;
ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
if (ret < 0)
return ret;
if (tgt_prog) {
if (subprog == 0)
addr = (long) tgt_prog->bpf_func;
else
addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
} else {
addr = kallsyms_lookup_name(tname);
if (!addr) {
bpf_log(log,
"The address of function %s cannot be found\n",
tname);
return -ENOENT;
}
}
if (prog->aux->sleepable) {
ret = -EINVAL;
switch (prog->type) {
case BPF_PROG_TYPE_TRACING:
/* fentry/fexit/fmod_ret progs can be sleepable only if they are
* attached to ALLOW_ERROR_INJECTION and are not in denylist.
*/
if (!check_non_sleepable_error_inject(btf_id) &&
within_error_injection_list(addr))
ret = 0;
break;
case BPF_PROG_TYPE_LSM:
/* LSM progs check that they are attached to bpf_lsm_*() funcs.
* Only some of them are sleepable.
*/
if (bpf_lsm_is_sleepable_hook(btf_id))
ret = 0;
break;
default:
break;
}
if (ret) {
bpf_log(log, "%s is not sleepable\n", tname);
return ret;
}
} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
if (tgt_prog) {
bpf_log(log, "can't modify return codes of BPF programs\n");
return -EINVAL;
}
ret = check_attach_modify_return(addr, tname);
if (ret) {
bpf_log(log, "%s() is not modifiable\n", tname);
return ret;
}
}
break;
}
tgt_info->tgt_addr = addr;
tgt_info->tgt_name = tname;
tgt_info->tgt_type = t;
return 0;
}
static int check_attach_btf_id(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
struct bpf_prog *tgt_prog = prog->aux->dst_prog;
struct bpf_attach_target_info tgt_info = {};
u32 btf_id = prog->aux->attach_btf_id;
struct bpf_trampoline *tr;
int ret;
u64 key;
if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
prog->type != BPF_PROG_TYPE_LSM) {
verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
return -EINVAL;
}
if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
return check_struct_ops_btf_id(env);
if (prog->type != BPF_PROG_TYPE_TRACING &&
prog->type != BPF_PROG_TYPE_LSM &&
prog->type != BPF_PROG_TYPE_EXT)
return 0;
ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
if (ret)
return ret;
if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
/* to make freplace equivalent to their targets, they need to
* inherit env->ops and expected_attach_type for the rest of the
* verification
*/
env->ops = bpf_verifier_ops[tgt_prog->type];
prog->expected_attach_type = tgt_prog->expected_attach_type;
}
/* store info about the attachment target that will be used later */
prog->aux->attach_func_proto = tgt_info.tgt_type;
prog->aux->attach_func_name = tgt_info.tgt_name;
if (tgt_prog) {
prog->aux->saved_dst_prog_type = tgt_prog->type;
prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
}
if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
prog->aux->attach_btf_trace = true;
return 0;
} else if (prog->expected_attach_type == BPF_TRACE_ITER) {
if (!bpf_iter_prog_supported(prog))
return -EINVAL;
return 0;
}
if (prog->type == BPF_PROG_TYPE_LSM) {
ret = bpf_lsm_verify_prog(&env->log, prog);
if (ret < 0)
return ret;
}
key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);
tr = bpf_trampoline_get(key, &tgt_info);
if (!tr)
return -ENOMEM;
prog->aux->dst_trampoline = tr;
return 0;
}
struct btf *bpf_get_btf_vmlinux(void)
{
if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
mutex_lock(&bpf_verifier_lock);
if (!btf_vmlinux)
btf_vmlinux = btf_parse_vmlinux();
mutex_unlock(&bpf_verifier_lock);
}
return btf_vmlinux;
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
union bpf_attr __user *uattr)
{
u64 start_time = ktime_get_ns();
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
int i, len, ret = -EINVAL;
bool is_priv;
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
return -EINVAL;
/* 'struct bpf_verifier_env' can be global, but since it's not small,
* allocate/free it every time bpf_check() is called
*/
env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
if (!env)
return -ENOMEM;
log = &env->log;
len = (*prog)->len;
env->insn_aux_data =
vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));
ret = -ENOMEM;
if (!env->insn_aux_data)
goto err_free_env;
for (i = 0; i < len; i++)
env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
is_priv = bpf_capable();
bpf_get_btf_vmlinux();
/* grab the mutex to protect few globals used by verifier */
if (!is_priv)
mutex_lock(&bpf_verifier_lock);
if (attr->log_level || attr->log_buf || attr->log_size) {
/* user requested verbose verifier output
* and supplied buffer to store the verification trace
*/
log->level = attr->log_level;
log->ubuf = (char __user *) (unsigned long) attr->log_buf;
log->len_total = attr->log_size;
ret = -EINVAL;
/* log attributes have to be sane */
if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 ||
!log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
goto err_unlock;
}
if (IS_ERR(btf_vmlinux)) {
/* Either gcc or pahole or kernel are broken. */
verbose(env, "in-kernel BTF is malformed\n");
ret = PTR_ERR(btf_vmlinux);
goto skip_full_check;
}
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
env->allow_ptr_leaks = bpf_allow_ptr_leaks();
env->allow_uninit_stack = bpf_allow_uninit_stack();
env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access();
env->bypass_spec_v1 = bpf_bypass_spec_v1();
env->bypass_spec_v4 = bpf_bypass_spec_v4();
env->bpf_capable = bpf_capable();
if (is_priv)
env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env->prog);
if (ret)
goto skip_full_check;
}
env->explored_states = kvcalloc(state_htab_size(env),
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
ret = -ENOMEM;
if (!env->explored_states)
goto skip_full_check;
ret = add_subprog_and_kfunc(env);
if (ret < 0)
goto skip_full_check;
ret = check_subprogs(env);
if (ret < 0)
goto skip_full_check;
ret = check_btf_info(env, attr, uattr);
if (ret < 0)
goto skip_full_check;
ret = check_attach_btf_id(env);
if (ret)
goto skip_full_check;
ret = resolve_pseudo_ldimm64(env);
if (ret < 0)
goto skip_full_check;
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
ret = do_check_subprogs(env);
ret = ret ?: do_check_main(env);
if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
ret = bpf_prog_offload_finalize(env);
skip_full_check:
kvfree(env->explored_states);
if (ret == 0)
ret = check_max_stack_depth(env);
/* instruction rewrites happen after this point */
if (is_priv) {
if (ret == 0)
opt_hard_wire_dead_code_branches(env);
if (ret == 0)
ret = opt_remove_dead_code(env);
if (ret == 0)
ret = opt_remove_nops(env);
} else {
if (ret == 0)
sanitize_dead_code(env);
}
if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
if (ret == 0)
ret = do_misc_fixups(env);
/* do 32-bit optimization after insn patching has done so those patched
* insns could be handled correctly.
*/
if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) {
ret = opt_subreg_zext_lo32_rnd_hi32(env, attr);
env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret
: false;
}
if (ret == 0)
ret = fixup_call_args(env);
env->verification_time = ktime_get_ns() - start_time;
print_verification_stats(env);
if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
if (log->level && !log->ubuf) {
ret = -EFAULT;
goto err_release_maps;
}
if (ret)
goto err_release_maps;
if (env->used_map_cnt) {
/* if program passed verifier, update used_maps in bpf_prog_info */
env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
sizeof(env->used_maps[0]),
GFP_KERNEL);
if (!env->prog->aux->used_maps) {
ret = -ENOMEM;
goto err_release_maps;
}
memcpy(env->prog->aux->used_maps, env->used_maps,
sizeof(env->used_maps[0]) * env->used_map_cnt);
env->prog->aux->used_map_cnt = env->used_map_cnt;
}
if (env->used_btf_cnt) {
/* if program passed verifier, update used_btfs in bpf_prog_aux */
env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt,
sizeof(env->used_btfs[0]),
GFP_KERNEL);
if (!env->prog->aux->used_btfs) {
ret = -ENOMEM;
goto err_release_maps;
}
memcpy(env->prog->aux->used_btfs, env->used_btfs,
sizeof(env->used_btfs[0]) * env->used_btf_cnt);
env->prog->aux->used_btf_cnt = env->used_btf_cnt;
}
if (env->used_map_cnt || env->used_btf_cnt) {
/* program is valid. Convert pseudo bpf_ld_imm64 into generic
* bpf_ld_imm64 instructions
*/
convert_pseudo_ld_imm64(env);
}
adjust_btf_func(env);
err_release_maps:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
* them now. Otherwise free_used_maps() will release them.
*/
release_maps(env);
if (!env->prog->aux->used_btfs)
release_btfs(env);
/* extension progs temporarily inherit the attach_type of their targets
for verification purposes, so set it back to zero before returning
*/
if (env->prog->type == BPF_PROG_TYPE_EXT)
env->prog->expected_attach_type = 0;
*prog = env->prog;
err_unlock:
if (!is_priv)
mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
err_free_env:
kfree(env);
return ret;
}
|