summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/seccomp/seccomp_bpf.c
blob: 6944b898bb530929f8436873b9af395cd81e20cd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2012 The Chromium OS Authors. All rights reserved.
 *
 * Test code for seccomp bpf.
 */

#define _GNU_SOURCE
#include <sys/types.h>

/*
 * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
 * we need to use the kernel's siginfo.h file and trick glibc
 * into accepting it.
 */
#if !__GLIBC_PREREQ(2, 26)
# include <asm/siginfo.h>
# define __have_siginfo_t 1
# define __have_sigval_t 1
# define __have_sigevent_t 1
#endif

#include <errno.h>
#include <linux/filter.h>
#include <sys/prctl.h>
#include <sys/ptrace.h>
#include <sys/user.h>
#include <linux/prctl.h>
#include <linux/ptrace.h>
#include <linux/seccomp.h>
#include <pthread.h>
#include <semaphore.h>
#include <signal.h>
#include <stddef.h>
#include <stdbool.h>
#include <string.h>
#include <time.h>
#include <limits.h>
#include <linux/elf.h>
#include <sys/uio.h>
#include <sys/utsname.h>
#include <sys/fcntl.h>
#include <sys/mman.h>
#include <sys/times.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <linux/kcmp.h>

#include <unistd.h>
#include <sys/syscall.h>
#include <poll.h>

#include "../kselftest_harness.h"

#ifndef PR_SET_PTRACER
# define PR_SET_PTRACER 0x59616d61
#endif

#ifndef PR_SET_NO_NEW_PRIVS
#define PR_SET_NO_NEW_PRIVS 38
#define PR_GET_NO_NEW_PRIVS 39
#endif

#ifndef PR_SECCOMP_EXT
#define PR_SECCOMP_EXT 43
#endif

#ifndef SECCOMP_EXT_ACT
#define SECCOMP_EXT_ACT 1
#endif

#ifndef SECCOMP_EXT_ACT_TSYNC
#define SECCOMP_EXT_ACT_TSYNC 1
#endif

#ifndef SECCOMP_MODE_STRICT
#define SECCOMP_MODE_STRICT 1
#endif

#ifndef SECCOMP_MODE_FILTER
#define SECCOMP_MODE_FILTER 2
#endif

#ifndef SECCOMP_RET_ALLOW
struct seccomp_data {
	int nr;
	__u32 arch;
	__u64 instruction_pointer;
	__u64 args[6];
};
#endif

#ifndef SECCOMP_RET_KILL_PROCESS
#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
#define SECCOMP_RET_KILL_THREAD	 0x00000000U /* kill the thread */
#endif
#ifndef SECCOMP_RET_KILL
#define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
#define SECCOMP_RET_TRAP	 0x00030000U /* disallow and force a SIGSYS */
#define SECCOMP_RET_ERRNO	 0x00050000U /* returns an errno */
#define SECCOMP_RET_TRACE	 0x7ff00000U /* pass to a tracer or disallow */
#define SECCOMP_RET_ALLOW	 0x7fff0000U /* allow */
#endif
#ifndef SECCOMP_RET_LOG
#define SECCOMP_RET_LOG		 0x7ffc0000U /* allow after logging */
#endif

#ifndef __NR_seccomp
# if defined(__i386__)
#  define __NR_seccomp 354
# elif defined(__x86_64__)
#  define __NR_seccomp 317
# elif defined(__arm__)
#  define __NR_seccomp 383
# elif defined(__aarch64__)
#  define __NR_seccomp 277
# elif defined(__riscv)
#  define __NR_seccomp 277
# elif defined(__hppa__)
#  define __NR_seccomp 338
# elif defined(__powerpc__)
#  define __NR_seccomp 358
# elif defined(__s390__)
#  define __NR_seccomp 348
# else
#  warning "seccomp syscall number unknown for this architecture"
#  define __NR_seccomp 0xffff
# endif
#endif

#ifndef SECCOMP_SET_MODE_STRICT
#define SECCOMP_SET_MODE_STRICT 0
#endif

#ifndef SECCOMP_SET_MODE_FILTER
#define SECCOMP_SET_MODE_FILTER 1
#endif

#ifndef SECCOMP_GET_ACTION_AVAIL
#define SECCOMP_GET_ACTION_AVAIL 2
#endif

#ifndef SECCOMP_GET_NOTIF_SIZES
#define SECCOMP_GET_NOTIF_SIZES 3
#endif

#ifndef SECCOMP_FILTER_FLAG_TSYNC
#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
#endif

#ifndef SECCOMP_FILTER_FLAG_LOG
#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
#endif

#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
#endif

#ifndef PTRACE_SECCOMP_GET_METADATA
#define PTRACE_SECCOMP_GET_METADATA	0x420d

struct seccomp_metadata {
	__u64 filter_off;       /* Input: which filter */
	__u64 flags;             /* Output: filter's flags */
};
#endif

#ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER
#define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)

#define SECCOMP_RET_USER_NOTIF 0x7fc00000U

#define SECCOMP_IOC_MAGIC		'!'
#define SECCOMP_IO(nr)			_IO(SECCOMP_IOC_MAGIC, nr)
#define SECCOMP_IOR(nr, type)		_IOR(SECCOMP_IOC_MAGIC, nr, type)
#define SECCOMP_IOW(nr, type)		_IOW(SECCOMP_IOC_MAGIC, nr, type)
#define SECCOMP_IOWR(nr, type)		_IOWR(SECCOMP_IOC_MAGIC, nr, type)

/* Flags for seccomp notification fd ioctl. */
#define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
#define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
						struct seccomp_notif_resp)
#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)

struct seccomp_notif {
	__u64 id;
	__u32 pid;
	__u32 flags;
	struct seccomp_data data;
};

struct seccomp_notif_resp {
	__u64 id;
	__s64 val;
	__s32 error;
	__u32 flags;
};

struct seccomp_notif_sizes {
	__u16 seccomp_notif;
	__u16 seccomp_notif_resp;
	__u16 seccomp_data;
};
#endif

#ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY
#define PTRACE_EVENTMSG_SYSCALL_ENTRY	1
#define PTRACE_EVENTMSG_SYSCALL_EXIT	2
#endif

#ifndef SECCOMP_USER_NOTIF_FLAG_CONTINUE
#define SECCOMP_USER_NOTIF_FLAG_CONTINUE 0x00000001
#endif

#ifndef seccomp
int seccomp(unsigned int op, unsigned int flags, void *args)
{
	errno = 0;
	return syscall(__NR_seccomp, op, flags, args);
}
#endif

#if __BYTE_ORDER == __LITTLE_ENDIAN
#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
#elif __BYTE_ORDER == __BIG_ENDIAN
#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]) + sizeof(__u32))
#else
#error "wut? Unknown __BYTE_ORDER?!"
#endif

#define SIBLING_EXIT_UNKILLED	0xbadbeef
#define SIBLING_EXIT_FAILURE	0xbadface
#define SIBLING_EXIT_NEWPRIVS	0xbadfeed

TEST(mode_strict_support)
{
	long ret;

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_STRICT, NULL, NULL, NULL);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support CONFIG_SECCOMP");
	}
	syscall(__NR_exit, 0);
}

TEST_SIGNAL(mode_strict_cannot_call_prctl, SIGKILL)
{
	long ret;

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_STRICT, NULL, NULL, NULL);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support CONFIG_SECCOMP");
	}
	syscall(__NR_prctl, PR_SET_SECCOMP, SECCOMP_MODE_FILTER,
		NULL, NULL, NULL);
	EXPECT_FALSE(true) {
		TH_LOG("Unreachable!");
	}
}

/* Note! This doesn't test no new privs behavior */
TEST(no_new_privs_support)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	EXPECT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}
}

/* Tests kernel support by checking for a copy_from_user() fault on NULL. */
TEST(mode_filter_support)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, NULL, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, NULL, NULL, NULL);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EFAULT, errno) {
		TH_LOG("Kernel does not support CONFIG_SECCOMP_FILTER!");
	}
}

TEST(mode_filter_without_nnp)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_GET_NO_NEW_PRIVS, 0, NULL, 0, 0);
	ASSERT_LE(0, ret) {
		TH_LOG("Expected 0 or unsupported for NO_NEW_PRIVS");
	}
	errno = 0;
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	/* Succeeds with CAP_SYS_ADMIN, fails without */
	/* TODO(wad) check caps not euid */
	if (geteuid()) {
		EXPECT_EQ(-1, ret);
		EXPECT_EQ(EACCES, errno);
	} else {
		EXPECT_EQ(0, ret);
	}
}

#define MAX_INSNS_PER_PATH 32768

TEST(filter_size_limits)
{
	int i;
	int count = BPF_MAXINSNS + 1;
	struct sock_filter allow[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_filter *filter;
	struct sock_fprog prog = { };
	long ret;

	filter = calloc(count, sizeof(*filter));
	ASSERT_NE(NULL, filter);

	for (i = 0; i < count; i++)
		filter[i] = allow[0];

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	prog.filter = filter;
	prog.len = count;

	/* Too many filter instructions in a single filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_NE(0, ret) {
		TH_LOG("Installing %d insn filter was allowed", prog.len);
	}

	/* One less is okay, though. */
	prog.len -= 1;
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Installing %d insn filter wasn't allowed", prog.len);
	}
}

TEST(filter_chain_limits)
{
	int i;
	int count = BPF_MAXINSNS;
	struct sock_filter allow[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_filter *filter;
	struct sock_fprog prog = { };
	long ret;

	filter = calloc(count, sizeof(*filter));
	ASSERT_NE(NULL, filter);

	for (i = 0; i < count; i++)
		filter[i] = allow[0];

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	prog.filter = filter;
	prog.len = 1;

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	prog.len = count;

	/* Too many total filter instructions. */
	for (i = 0; i < MAX_INSNS_PER_PATH; i++) {
		ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
		if (ret != 0)
			break;
	}
	ASSERT_NE(0, ret) {
		TH_LOG("Allowed %d %d-insn filters (total with penalties:%d)",
		       i, count, i * (count + 4));
	}
}

TEST(mode_filter_cannot_move_to_strict)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_STRICT, NULL, 0, 0);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EINVAL, errno);
}


TEST(mode_filter_get_seccomp)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
	EXPECT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
	EXPECT_EQ(2, ret);
}


TEST(ALLOW_all)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);
}

TEST(empty_prog)
{
	struct sock_filter filter[] = {
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EINVAL, errno);
}

TEST(log_all)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);

	/* getppid() should succeed and be logged (no check for logging) */
	EXPECT_EQ(parent, syscall(__NR_getppid));
}

TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, 0x10000000U),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);
	EXPECT_EQ(0, syscall(__NR_getpid)) {
		TH_LOG("getpid() shouldn't ever return");
	}
}

/* return code >= 0x80000000 is unused. */
TEST_SIGNAL(unknown_ret_is_kill_above_allow, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, 0x90000000U),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);
	EXPECT_EQ(0, syscall(__NR_getpid)) {
		TH_LOG("getpid() shouldn't ever return");
	}
}

TEST_SIGNAL(KILL_all, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);
}

TEST_SIGNAL(KILL_one, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* getpid() should never return. */
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_SIGNAL(KILL_one_arg_one, SIGSYS)
{
	void *fatal_address;
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_times, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		/* Only both with lower 32-bit for now. */
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, syscall_arg(0)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K,
			(unsigned long)&fatal_address, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;
	pid_t parent = getppid();
	struct tms timebuf;
	clock_t clock = times(&timebuf);

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_LE(clock, syscall(__NR_times, &timebuf));
	/* times() should never return. */
	EXPECT_EQ(0, syscall(__NR_times, &fatal_address));
}

TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
{
#ifndef __NR_mmap2
	int sysno = __NR_mmap;
#else
	int sysno = __NR_mmap2;
#endif
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, sysno, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		/* Only both with lower 32-bit for now. */
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, syscall_arg(5)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, 0x0C0FFEE, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;
	pid_t parent = getppid();
	int fd;
	void *map1, *map2;
	int page_size = sysconf(_SC_PAGESIZE);

	ASSERT_LT(0, page_size);

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	ASSERT_EQ(0, ret);

	fd = open("/dev/zero", O_RDONLY);
	ASSERT_NE(-1, fd);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	map1 = (void *)syscall(sysno,
		NULL, page_size, PROT_READ, MAP_PRIVATE, fd, page_size);
	EXPECT_NE(MAP_FAILED, map1);
	/* mmap2() should never return. */
	map2 = (void *)syscall(sysno,
		 NULL, page_size, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE);
	EXPECT_EQ(MAP_FAILED, map2);

	/* The test failed, so clean up the resources. */
	munmap(map1, page_size);
	munmap(map2, page_size);
	close(fd);
}

/* This is a thread task to die via seccomp filter violation. */
void *kill_thread(void *data)
{
	bool die = (bool)data;

	if (die) {
		prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
		return (void *)SIBLING_EXIT_FAILURE;
	}

	return (void *)SIBLING_EXIT_UNKILLED;
}

/* Prepare a thread that will kill itself or both of us. */
void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process)
{
	pthread_t thread;
	void *status;
	/* Kill only when calling __NR_prctl. */
	struct sock_filter filter_thread[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog_thread = {
		.len = (unsigned short)ARRAY_SIZE(filter_thread),
		.filter = filter_thread,
	};
	struct sock_filter filter_process[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog_process = {
		.len = (unsigned short)ARRAY_SIZE(filter_process),
		.filter = filter_process,
	};

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0,
			     kill_process ? &prog_process : &prog_thread));

	/*
	 * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS
	 * flag cannot be downgraded by a new filter.
	 */
	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread));

	/* Start a thread that will exit immediately. */
	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false));
	ASSERT_EQ(0, pthread_join(thread, &status));
	ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status);

	/* Start a thread that will die immediately. */
	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true));
	ASSERT_EQ(0, pthread_join(thread, &status));
	ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status);

	/*
	 * If we get here, only the spawned thread died. Let the parent know
	 * the whole process didn't die (i.e. this thread, the spawner,
	 * stayed running).
	 */
	exit(42);
}

TEST(KILL_thread)
{
	int status;
	pid_t child_pid;

	child_pid = fork();
	ASSERT_LE(0, child_pid);
	if (child_pid == 0) {
		kill_thread_or_group(_metadata, false);
		_exit(38);
	}

	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));

	/* If only the thread was killed, we'll see exit 42. */
	ASSERT_TRUE(WIFEXITED(status));
	ASSERT_EQ(42, WEXITSTATUS(status));
}

TEST(KILL_process)
{
	int status;
	pid_t child_pid;

	child_pid = fork();
	ASSERT_LE(0, child_pid);
	if (child_pid == 0) {
		kill_thread_or_group(_metadata, true);
		_exit(38);
	}

	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));

	/* If the entire process was killed, we'll see SIGSYS. */
	ASSERT_TRUE(WIFSIGNALED(status));
	ASSERT_EQ(SIGSYS, WTERMSIG(status));
}

/* TODO(wad) add 64-bit versus 32-bit arg tests. */
TEST(arg_out_of_range)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, syscall_arg(6)),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EINVAL, errno);
}

#define ERRNO_FILTER(name, errno)					\
	struct sock_filter _read_filter_##name[] = {			\
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,				\
			offsetof(struct seccomp_data, nr)),		\
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),	\
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno),	\
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),		\
	};								\
	struct sock_fprog prog_##name = {				\
		.len = (unsigned short)ARRAY_SIZE(_read_filter_##name),	\
		.filter = _read_filter_##name,				\
	}

/* Make sure basic errno values are correctly passed through a filter. */
TEST(ERRNO_valid)
{
	ERRNO_FILTER(valid, E2BIG);
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_EQ(-1, read(0, NULL, 0));
	EXPECT_EQ(E2BIG, errno);
}

/* Make sure an errno of zero is correctly handled by the arch code. */
TEST(ERRNO_zero)
{
	ERRNO_FILTER(zero, 0);
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* "errno" of 0 is ok. */
	EXPECT_EQ(0, read(0, NULL, 0));
}

/*
 * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller.
 * This tests that the errno value gets capped correctly, fixed by
 * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO").
 */
TEST(ERRNO_capped)
{
	ERRNO_FILTER(capped, 4096);
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_EQ(-1, read(0, NULL, 0));
	EXPECT_EQ(4095, errno);
}

/*
 * Filters are processed in reverse order: last applied is executed first.
 * Since only the SECCOMP_RET_ACTION mask is tested for return values, the
 * SECCOMP_RET_DATA mask results will follow the most recently applied
 * matching filter return (and not the lowest or highest value).
 */
TEST(ERRNO_order)
{
	ERRNO_FILTER(first,  11);
	ERRNO_FILTER(second, 13);
	ERRNO_FILTER(third,  12);
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_EQ(-1, read(0, NULL, 0));
	EXPECT_EQ(12, errno);
}

FIXTURE_DATA(TRAP) {
	struct sock_fprog prog;
};

FIXTURE_SETUP(TRAP)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRAP),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};

	memset(&self->prog, 0, sizeof(self->prog));
	self->prog.filter = malloc(sizeof(filter));
	ASSERT_NE(NULL, self->prog.filter);
	memcpy(self->prog.filter, filter, sizeof(filter));
	self->prog.len = (unsigned short)ARRAY_SIZE(filter);
}

FIXTURE_TEARDOWN(TRAP)
{
	if (self->prog.filter)
		free(self->prog.filter);
}

TEST_F_SIGNAL(TRAP, dfl, SIGSYS)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog);
	ASSERT_EQ(0, ret);
	syscall(__NR_getpid);
}

/* Ensure that SIGSYS overrides SIG_IGN */
TEST_F_SIGNAL(TRAP, ign, SIGSYS)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	signal(SIGSYS, SIG_IGN);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog);
	ASSERT_EQ(0, ret);
	syscall(__NR_getpid);
}

static siginfo_t TRAP_info;
static volatile int TRAP_nr;
static void TRAP_action(int nr, siginfo_t *info, void *void_context)
{
	memcpy(&TRAP_info, info, sizeof(TRAP_info));
	TRAP_nr = nr;
}

TEST_F(TRAP, handler)
{
	int ret, test;
	struct sigaction act;
	sigset_t mask;

	memset(&act, 0, sizeof(act));
	sigemptyset(&mask);
	sigaddset(&mask, SIGSYS);

	act.sa_sigaction = &TRAP_action;
	act.sa_flags = SA_SIGINFO;
	ret = sigaction(SIGSYS, &act, NULL);
	ASSERT_EQ(0, ret) {
		TH_LOG("sigaction failed");
	}
	ret = sigprocmask(SIG_UNBLOCK, &mask, NULL);
	ASSERT_EQ(0, ret) {
		TH_LOG("sigprocmask failed");
	}

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog);
	ASSERT_EQ(0, ret);
	TRAP_nr = 0;
	memset(&TRAP_info, 0, sizeof(TRAP_info));
	/* Expect the registers to be rolled back. (nr = error) may vary
	 * based on arch. */
	ret = syscall(__NR_getpid);
	/* Silence gcc warning about volatile. */
	test = TRAP_nr;
	EXPECT_EQ(SIGSYS, test);
	struct local_sigsys {
		void *_call_addr;	/* calling user insn */
		int _syscall;		/* triggering system call number */
		unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
	} *sigsys = (struct local_sigsys *)
#ifdef si_syscall
		&(TRAP_info.si_call_addr);
#else
		&TRAP_info.si_pid;
#endif
	EXPECT_EQ(__NR_getpid, sigsys->_syscall);
	/* Make sure arch is non-zero. */
	EXPECT_NE(0, sigsys->_arch);
	EXPECT_NE(0, (unsigned long)sigsys->_call_addr);
}

FIXTURE_DATA(precedence) {
	struct sock_fprog allow;
	struct sock_fprog log;
	struct sock_fprog trace;
	struct sock_fprog error;
	struct sock_fprog trap;
	struct sock_fprog kill;
};

FIXTURE_SETUP(precedence)
{
	struct sock_filter allow_insns[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_filter log_insns[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
	};
	struct sock_filter trace_insns[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE),
	};
	struct sock_filter error_insns[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO),
	};
	struct sock_filter trap_insns[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRAP),
	};
	struct sock_filter kill_insns[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
	};

	memset(self, 0, sizeof(*self));
#define FILTER_ALLOC(_x) \
	self->_x.filter = malloc(sizeof(_x##_insns)); \
	ASSERT_NE(NULL, self->_x.filter); \
	memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \
	self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns)
	FILTER_ALLOC(allow);
	FILTER_ALLOC(log);
	FILTER_ALLOC(trace);
	FILTER_ALLOC(error);
	FILTER_ALLOC(trap);
	FILTER_ALLOC(kill);
}

FIXTURE_TEARDOWN(precedence)
{
#define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter)
	FILTER_FREE(allow);
	FILTER_FREE(log);
	FILTER_FREE(trace);
	FILTER_FREE(error);
	FILTER_FREE(trap);
	FILTER_FREE(kill);
}

TEST_F(precedence, allow_ok)
{
	pid_t parent, res = 0;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->kill);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	res = syscall(__NR_getppid);
	EXPECT_EQ(parent, res);
}

TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS)
{
	pid_t parent, res = 0;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->kill);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	res = syscall(__NR_getppid);
	EXPECT_EQ(parent, res);
	/* getpid() should never return. */
	res = syscall(__NR_getpid);
	EXPECT_EQ(0, res);
}

TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->kill);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* getpid() should never return. */
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* getpid() should never return. */
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* getpid() should never return. */
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_F(precedence, errno_is_third)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_F(precedence, errno_is_third_in_any_order)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST_F(precedence, trace_is_fourth)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* No ptracer */
	EXPECT_EQ(-1, syscall(__NR_getpid));
}

TEST_F(precedence, trace_is_fourth_in_any_order)
{
	pid_t parent;
	long ret;

	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* No ptracer */
	EXPECT_EQ(-1, syscall(__NR_getpid));
}

TEST_F(precedence, log_is_fifth)
{
	pid_t mypid, parent;
	long ret;

	mypid = getpid();
	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* Should also work just fine */
	EXPECT_EQ(mypid, syscall(__NR_getpid));
}

TEST_F(precedence, log_is_fifth_in_any_order)
{
	pid_t mypid, parent;
	long ret;

	mypid = getpid();
	parent = getppid();
	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
	ASSERT_EQ(0, ret);
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
	ASSERT_EQ(0, ret);
	/* Should work just fine. */
	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* Should also work just fine */
	EXPECT_EQ(mypid, syscall(__NR_getpid));
}

#ifndef PTRACE_O_TRACESECCOMP
#define PTRACE_O_TRACESECCOMP	0x00000080
#endif

/* Catch the Ubuntu 12.04 value error. */
#if PTRACE_EVENT_SECCOMP != 7
#undef PTRACE_EVENT_SECCOMP
#endif

#ifndef PTRACE_EVENT_SECCOMP
#define PTRACE_EVENT_SECCOMP 7
#endif

#define IS_SECCOMP_EVENT(status) ((status >> 16) == PTRACE_EVENT_SECCOMP)
bool tracer_running;
void tracer_stop(int sig)
{
	tracer_running = false;
}

typedef void tracer_func_t(struct __test_metadata *_metadata,
			   pid_t tracee, int status, void *args);

void start_tracer(struct __test_metadata *_metadata, int fd, pid_t tracee,
	    tracer_func_t tracer_func, void *args, bool ptrace_syscall)
{
	int ret = -1;
	struct sigaction action = {
		.sa_handler = tracer_stop,
	};

	/* Allow external shutdown. */
	tracer_running = true;
	ASSERT_EQ(0, sigaction(SIGUSR1, &action, NULL));

	errno = 0;
	while (ret == -1 && errno != EINVAL)
		ret = ptrace(PTRACE_ATTACH, tracee, NULL, 0);
	ASSERT_EQ(0, ret) {
		kill(tracee, SIGKILL);
	}
	/* Wait for attach stop */
	wait(NULL);

	ret = ptrace(PTRACE_SETOPTIONS, tracee, NULL, ptrace_syscall ?
						      PTRACE_O_TRACESYSGOOD :
						      PTRACE_O_TRACESECCOMP);
	ASSERT_EQ(0, ret) {
		TH_LOG("Failed to set PTRACE_O_TRACESECCOMP");
		kill(tracee, SIGKILL);
	}
	ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT,
		     tracee, NULL, 0);
	ASSERT_EQ(0, ret);

	/* Unblock the tracee */
	ASSERT_EQ(1, write(fd, "A", 1));
	ASSERT_EQ(0, close(fd));

	/* Run until we're shut down. Must assert to stop execution. */
	while (tracer_running) {
		int status;

		if (wait(&status) != tracee)
			continue;
		if (WIFSIGNALED(status) || WIFEXITED(status))
			/* Child is dead. Time to go. */
			return;

		/* Check if this is a seccomp event. */
		ASSERT_EQ(!ptrace_syscall, IS_SECCOMP_EVENT(status));

		tracer_func(_metadata, tracee, status, args);

		ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT,
			     tracee, NULL, 0);
		ASSERT_EQ(0, ret);
	}
	/* Directly report the status of our test harness results. */
	syscall(__NR_exit, _metadata->passed ? EXIT_SUCCESS : EXIT_FAILURE);
}

/* Common tracer setup/teardown functions. */
void cont_handler(int num)
{ }
pid_t setup_trace_fixture(struct __test_metadata *_metadata,
			  tracer_func_t func, void *args, bool ptrace_syscall)
{
	char sync;
	int pipefd[2];
	pid_t tracer_pid;
	pid_t tracee = getpid();

	/* Setup a pipe for clean synchronization. */
	ASSERT_EQ(0, pipe(pipefd));

	/* Fork a child which we'll promote to tracer */
	tracer_pid = fork();
	ASSERT_LE(0, tracer_pid);
	signal(SIGALRM, cont_handler);
	if (tracer_pid == 0) {
		close(pipefd[0]);
		start_tracer(_metadata, pipefd[1], tracee, func, args,
			     ptrace_syscall);
		syscall(__NR_exit, 0);
	}
	close(pipefd[1]);
	prctl(PR_SET_PTRACER, tracer_pid, 0, 0, 0);
	read(pipefd[0], &sync, 1);
	close(pipefd[0]);

	return tracer_pid;
}
void teardown_trace_fixture(struct __test_metadata *_metadata,
			    pid_t tracer)
{
	if (tracer) {
		int status;
		/*
		 * Extract the exit code from the other process and
		 * adopt it for ourselves in case its asserts failed.
		 */
		ASSERT_EQ(0, kill(tracer, SIGUSR1));
		ASSERT_EQ(tracer, waitpid(tracer, &status, 0));
		if (WEXITSTATUS(status))
			_metadata->passed = 0;
	}
}

/* "poke" tracer arguments and function. */
struct tracer_args_poke_t {
	unsigned long poke_addr;
};

void tracer_poke(struct __test_metadata *_metadata, pid_t tracee, int status,
		 void *args)
{
	int ret;
	unsigned long msg;
	struct tracer_args_poke_t *info = (struct tracer_args_poke_t *)args;

	ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg);
	EXPECT_EQ(0, ret);
	/* If this fails, don't try to recover. */
	ASSERT_EQ(0x1001, msg) {
		kill(tracee, SIGKILL);
	}
	/*
	 * Poke in the message.
	 * Registers are not touched to try to keep this relatively arch
	 * agnostic.
	 */
	ret = ptrace(PTRACE_POKEDATA, tracee, info->poke_addr, 0x1001);
	EXPECT_EQ(0, ret);
}

FIXTURE_DATA(TRACE_poke) {
	struct sock_fprog prog;
	pid_t tracer;
	long poked;
	struct tracer_args_poke_t tracer_args;
};

FIXTURE_SETUP(TRACE_poke)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1001),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};

	self->poked = 0;
	memset(&self->prog, 0, sizeof(self->prog));
	self->prog.filter = malloc(sizeof(filter));
	ASSERT_NE(NULL, self->prog.filter);
	memcpy(self->prog.filter, filter, sizeof(filter));
	self->prog.len = (unsigned short)ARRAY_SIZE(filter);

	/* Set up tracer args. */
	self->tracer_args.poke_addr = (unsigned long)&self->poked;

	/* Launch tracer. */
	self->tracer = setup_trace_fixture(_metadata, tracer_poke,
					   &self->tracer_args, false);
}

FIXTURE_TEARDOWN(TRACE_poke)
{
	teardown_trace_fixture(_metadata, self->tracer);
	if (self->prog.filter)
		free(self->prog.filter);
}

TEST_F(TRACE_poke, read_has_side_effects)
{
	ssize_t ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(0, self->poked);
	ret = read(-1, NULL, 0);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(0x1001, self->poked);
}

TEST_F(TRACE_poke, getpid_runs_normally)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	EXPECT_EQ(0, self->poked);
	EXPECT_NE(0, syscall(__NR_getpid));
	EXPECT_EQ(0, self->poked);
}

#if defined(__x86_64__)
# define ARCH_REGS	struct user_regs_struct
# define SYSCALL_NUM	orig_rax
# define SYSCALL_RET	rax
#elif defined(__i386__)
# define ARCH_REGS	struct user_regs_struct
# define SYSCALL_NUM	orig_eax
# define SYSCALL_RET	eax
#elif defined(__arm__)
# define ARCH_REGS	struct pt_regs
# define SYSCALL_NUM	ARM_r7
# define SYSCALL_RET	ARM_r0
#elif defined(__aarch64__)
# define ARCH_REGS	struct user_pt_regs
# define SYSCALL_NUM	regs[8]
# define SYSCALL_RET	regs[0]
#elif defined(__riscv) && __riscv_xlen == 64
# define ARCH_REGS	struct user_regs_struct
# define SYSCALL_NUM	a7
# define SYSCALL_RET	a0
#elif defined(__hppa__)
# define ARCH_REGS	struct user_regs_struct
# define SYSCALL_NUM	gr[20]
# define SYSCALL_RET	gr[28]
#elif defined(__powerpc__)
# define ARCH_REGS	struct pt_regs
# define SYSCALL_NUM	gpr[0]
# define SYSCALL_RET	gpr[3]
#elif defined(__s390__)
# define ARCH_REGS     s390_regs
# define SYSCALL_NUM   gprs[2]
# define SYSCALL_RET   gprs[2]
#elif defined(__mips__)
# define ARCH_REGS	struct pt_regs
# define SYSCALL_NUM	regs[2]
# define SYSCALL_SYSCALL_NUM regs[4]
# define SYSCALL_RET	regs[2]
# define SYSCALL_NUM_RET_SHARE_REG
#else
# error "Do not know how to find your architecture's registers and syscalls"
#endif

/* When the syscall return can't be changed, stub out the tests for it. */
#ifdef SYSCALL_NUM_RET_SHARE_REG
# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(-1, action)
#else
# define EXPECT_SYSCALL_RETURN(val, action)		\
	do {						\
		errno = 0;				\
		if (val < 0) {				\
			EXPECT_EQ(-1, action);		\
			EXPECT_EQ(-(val), errno);	\
		} else {				\
			EXPECT_EQ(val, action);		\
		}					\
	} while (0)
#endif

/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
 * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
 */
#if defined(__x86_64__) || defined(__i386__) || defined(__mips__)
#define HAVE_GETREGS
#endif

/* Architecture-specific syscall fetching routine. */
int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
{
	ARCH_REGS regs;
#ifdef HAVE_GETREGS
	EXPECT_EQ(0, ptrace(PTRACE_GETREGS, tracee, 0, &regs)) {
		TH_LOG("PTRACE_GETREGS failed");
		return -1;
	}
#else
	struct iovec iov;

	iov.iov_base = &regs;
	iov.iov_len = sizeof(regs);
	EXPECT_EQ(0, ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov)) {
		TH_LOG("PTRACE_GETREGSET failed");
		return -1;
	}
#endif

#if defined(__mips__)
	if (regs.SYSCALL_NUM == __NR_O32_Linux)
		return regs.SYSCALL_SYSCALL_NUM;
#endif
	return regs.SYSCALL_NUM;
}

/* Architecture-specific syscall changing routine. */
void change_syscall(struct __test_metadata *_metadata,
		    pid_t tracee, int syscall, int result)
{
	int ret;
	ARCH_REGS regs;
#ifdef HAVE_GETREGS
	ret = ptrace(PTRACE_GETREGS, tracee, 0, &regs);
#else
	struct iovec iov;
	iov.iov_base = &regs;
	iov.iov_len = sizeof(regs);
	ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov);
#endif
	EXPECT_EQ(0, ret) {}

#if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
	defined(__s390__) || defined(__hppa__) || defined(__riscv)
	{
		regs.SYSCALL_NUM = syscall;
	}
#elif defined(__mips__)
	{
		if (regs.SYSCALL_NUM == __NR_O32_Linux)
			regs.SYSCALL_SYSCALL_NUM = syscall;
		else
			regs.SYSCALL_NUM = syscall;
	}

#elif defined(__arm__)
# ifndef PTRACE_SET_SYSCALL
#  define PTRACE_SET_SYSCALL   23
# endif
	{
		ret = ptrace(PTRACE_SET_SYSCALL, tracee, NULL, syscall);
		EXPECT_EQ(0, ret);
	}

#elif defined(__aarch64__)
# ifndef NT_ARM_SYSTEM_CALL
#  define NT_ARM_SYSTEM_CALL 0x404
# endif
	{
		iov.iov_base = &syscall;
		iov.iov_len = sizeof(syscall);
		ret = ptrace(PTRACE_SETREGSET, tracee, NT_ARM_SYSTEM_CALL,
			     &iov);
		EXPECT_EQ(0, ret);
	}

#else
	ASSERT_EQ(1, 0) {
		TH_LOG("How is the syscall changed on this architecture?");
	}
#endif

	/* If syscall is skipped, change return value. */
	if (syscall == -1)
#ifdef SYSCALL_NUM_RET_SHARE_REG
		TH_LOG("Can't modify syscall return on this architecture");
#else
		regs.SYSCALL_RET = result;
#endif

#ifdef HAVE_GETREGS
	ret = ptrace(PTRACE_SETREGS, tracee, 0, &regs);
#else
	iov.iov_base = &regs;
	iov.iov_len = sizeof(regs);
	ret = ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &iov);
#endif
	EXPECT_EQ(0, ret);
}

void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee,
		    int status, void *args)
{
	int ret;
	unsigned long msg;

	/* Make sure we got the right message. */
	ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg);
	EXPECT_EQ(0, ret);

	/* Validate and take action on expected syscalls. */
	switch (msg) {
	case 0x1002:
		/* change getpid to getppid. */
		EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee));
		change_syscall(_metadata, tracee, __NR_getppid, 0);
		break;
	case 0x1003:
		/* skip gettid with valid return code. */
		EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee));
		change_syscall(_metadata, tracee, -1, 45000);
		break;
	case 0x1004:
		/* skip openat with error. */
		EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee));
		change_syscall(_metadata, tracee, -1, -ESRCH);
		break;
	case 0x1005:
		/* do nothing (allow getppid) */
		EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee));
		break;
	default:
		EXPECT_EQ(0, msg) {
			TH_LOG("Unknown PTRACE_GETEVENTMSG: 0x%lx", msg);
			kill(tracee, SIGKILL);
		}
	}

}

void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
		   int status, void *args)
{
	int ret, nr;
	unsigned long msg;
	static bool entry;

	/*
	 * The traditional way to tell PTRACE_SYSCALL entry/exit
	 * is by counting.
	 */
	entry = !entry;

	/* Make sure we got an appropriate message. */
	ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg);
	EXPECT_EQ(0, ret);
	EXPECT_EQ(entry ? PTRACE_EVENTMSG_SYSCALL_ENTRY
			: PTRACE_EVENTMSG_SYSCALL_EXIT, msg);

	if (!entry)
		return;

	nr = get_syscall(_metadata, tracee);

	if (nr == __NR_getpid)
		change_syscall(_metadata, tracee, __NR_getppid, 0);
	if (nr == __NR_gettid)
		change_syscall(_metadata, tracee, -1, 45000);
	if (nr == __NR_openat)
		change_syscall(_metadata, tracee, -1, -ESRCH);
}

FIXTURE_DATA(TRACE_syscall) {
	struct sock_fprog prog;
	pid_t tracer, mytid, mypid, parent;
};

FIXTURE_SETUP(TRACE_syscall)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};

	memset(&self->prog, 0, sizeof(self->prog));
	self->prog.filter = malloc(sizeof(filter));
	ASSERT_NE(NULL, self->prog.filter);
	memcpy(self->prog.filter, filter, sizeof(filter));
	self->prog.len = (unsigned short)ARRAY_SIZE(filter);

	/* Prepare some testable syscall results. */
	self->mytid = syscall(__NR_gettid);
	ASSERT_GT(self->mytid, 0);
	ASSERT_NE(self->mytid, 1) {
		TH_LOG("Running this test as init is not supported. :)");
	}

	self->mypid = getpid();
	ASSERT_GT(self->mypid, 0);
	ASSERT_EQ(self->mytid, self->mypid);

	self->parent = getppid();
	ASSERT_GT(self->parent, 0);
	ASSERT_NE(self->parent, self->mypid);

	/* Launch tracer. */
	self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL,
					   false);
}

FIXTURE_TEARDOWN(TRACE_syscall)
{
	teardown_trace_fixture(_metadata, self->tracer);
	if (self->prog.filter)
		free(self->prog.filter);
}

TEST_F(TRACE_syscall, ptrace_syscall_redirected)
{
	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
	teardown_trace_fixture(_metadata, self->tracer);
	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
					   true);

	/* Tracer will redirect getpid to getppid. */
	EXPECT_NE(self->mypid, syscall(__NR_getpid));
}

TEST_F(TRACE_syscall, ptrace_syscall_errno)
{
	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
	teardown_trace_fixture(_metadata, self->tracer);
	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
					   true);

	/* Tracer should skip the open syscall, resulting in ESRCH. */
	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
}

TEST_F(TRACE_syscall, ptrace_syscall_faked)
{
	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
	teardown_trace_fixture(_metadata, self->tracer);
	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
					   true);

	/* Tracer should skip the gettid syscall, resulting fake pid. */
	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
}

TEST_F(TRACE_syscall, syscall_allowed)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* getppid works as expected (no changes). */
	EXPECT_EQ(self->parent, syscall(__NR_getppid));
	EXPECT_NE(self->mypid, syscall(__NR_getppid));
}

TEST_F(TRACE_syscall, syscall_redirected)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* getpid has been redirected to getppid as expected. */
	EXPECT_EQ(self->parent, syscall(__NR_getpid));
	EXPECT_NE(self->mypid, syscall(__NR_getpid));
}

TEST_F(TRACE_syscall, syscall_errno)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* openat has been skipped and an errno return. */
	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
}

TEST_F(TRACE_syscall, syscall_faked)
{
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* gettid has been skipped and an altered return value stored. */
	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
}

TEST_F(TRACE_syscall, skip_after_RET_TRACE)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install fixture filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install "errno on getppid" filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Tracer will redirect getpid to getppid, and we should see EPERM. */
	errno = 0;
	EXPECT_EQ(-1, syscall(__NR_getpid));
	EXPECT_EQ(EPERM, errno);
}

TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install fixture filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install "death on getppid" filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Tracer will redirect getpid to getppid, and we should die. */
	EXPECT_NE(self->mypid, syscall(__NR_getpid));
}

TEST_F(TRACE_syscall, skip_after_ptrace)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
	teardown_trace_fixture(_metadata, self->tracer);
	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
					   true);

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install "errno on getppid" filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Tracer will redirect getpid to getppid, and we should see EPERM. */
	EXPECT_EQ(-1, syscall(__NR_getpid));
	EXPECT_EQ(EPERM, errno);
}

TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
	teardown_trace_fixture(_metadata, self->tracer);
	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
					   true);

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	/* Install "death on getppid" filter. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
	ASSERT_EQ(0, ret);

	/* Tracer will redirect getpid to getppid, and we should die. */
	EXPECT_NE(self->mypid, syscall(__NR_getpid));
}

TEST(seccomp_syscall)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	/* Reject insane operation. */
	ret = seccomp(-1, 0, &prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Did not reject crazy op value!");
	}

	/* Reject strict with flags or pointer. */
	ret = seccomp(SECCOMP_SET_MODE_STRICT, -1, NULL);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Did not reject mode strict with flags!");
	}
	ret = seccomp(SECCOMP_SET_MODE_STRICT, 0, &prog);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Did not reject mode strict with uargs!");
	}

	/* Reject insane args for filter. */
	ret = seccomp(SECCOMP_SET_MODE_FILTER, -1, &prog);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Did not reject crazy filter flags!");
	}
	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, NULL);
	EXPECT_EQ(EFAULT, errno) {
		TH_LOG("Did not reject NULL filter!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog);
	EXPECT_EQ(0, errno) {
		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER: %s",
			strerror(errno));
	}
}

TEST(seccomp_syscall_mode_lock)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, NULL, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	EXPECT_EQ(0, ret) {
		TH_LOG("Could not install filter!");
	}

	/* Make sure neither entry point will switch to strict. */
	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_STRICT, 0, 0, 0);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Switched to mode strict!");
	}

	ret = seccomp(SECCOMP_SET_MODE_STRICT, 0, NULL);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Switched to mode strict!");
	}
}

/*
 * Test detection of known and unknown filter flags. Userspace needs to be able
 * to check if a filter flag is supported by the current kernel and a good way
 * of doing that is by attempting to enter filter mode, with the flag bit in
 * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
 * that the flag is valid and EINVAL indicates that the flag is invalid.
 */
TEST(detect_seccomp_filter_flags)
{
	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
				 SECCOMP_FILTER_FLAG_LOG,
				 SECCOMP_FILTER_FLAG_SPEC_ALLOW,
				 SECCOMP_FILTER_FLAG_NEW_LISTENER };
	unsigned int exclusive[] = {
				SECCOMP_FILTER_FLAG_TSYNC,
				SECCOMP_FILTER_FLAG_NEW_LISTENER };
	unsigned int flag, all_flags, exclusive_mask;
	int i;
	long ret;

	/* Test detection of individual known-good filter flags */
	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
		int bits = 0;

		flag = flags[i];
		/* Make sure the flag is a single bit! */
		while (flag) {
			if (flag & 0x1)
				bits ++;
			flag >>= 1;
		}
		ASSERT_EQ(1, bits);
		flag = flags[i];

		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
		ASSERT_NE(ENOSYS, errno) {
			TH_LOG("Kernel does not support seccomp syscall!");
		}
		EXPECT_EQ(-1, ret);
		EXPECT_EQ(EFAULT, errno) {
			TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
			       flag);
		}

		all_flags |= flag;
	}

	/*
	 * Test detection of all known-good filter flags combined. But
	 * for the exclusive flags we need to mask them out and try them
	 * individually for the "all flags" testing.
	 */
	exclusive_mask = 0;
	for (i = 0; i < ARRAY_SIZE(exclusive); i++)
		exclusive_mask |= exclusive[i];
	for (i = 0; i < ARRAY_SIZE(exclusive); i++) {
		flag = all_flags & ~exclusive_mask;
		flag |= exclusive[i];

		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
		EXPECT_EQ(-1, ret);
		EXPECT_EQ(EFAULT, errno) {
			TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
			       flag);
		}
	}

	/* Test detection of an unknown filter flags, without exclusives. */
	flag = -1;
	flag &= ~exclusive_mask;
	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
		       flag);
	}

	/*
	 * Test detection of an unknown filter flag that may simply need to be
	 * added to this test
	 */
	flag = flags[ARRAY_SIZE(flags) - 1] << 1;
	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
	EXPECT_EQ(-1, ret);
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
		       flag);
	}
}

TEST(TSYNC_first)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
	long ret;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, NULL, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	EXPECT_EQ(0, ret) {
		TH_LOG("Could not install initial filter with TSYNC!");
	}
}

#define TSYNC_SIBLINGS 2
struct tsync_sibling {
	pthread_t tid;
	pid_t system_tid;
	sem_t *started;
	pthread_cond_t *cond;
	pthread_mutex_t *mutex;
	int diverge;
	int num_waits;
	struct sock_fprog *prog;
	struct __test_metadata *metadata;
};

/*
 * To avoid joining joined threads (which is not allowed by Bionic),
 * make sure we both successfully join and clear the tid to skip a
 * later join attempt during fixture teardown. Any remaining threads
 * will be directly killed during teardown.
 */
#define PTHREAD_JOIN(tid, status)					\
	do {								\
		int _rc = pthread_join(tid, status);			\
		if (_rc) {						\
			TH_LOG("pthread_join of tid %u failed: %d\n",	\
				(unsigned int)tid, _rc);		\
		} else {						\
			tid = 0;					\
		}							\
	} while (0)

FIXTURE_DATA(TSYNC) {
	struct sock_fprog root_prog, apply_prog;
	struct tsync_sibling sibling[TSYNC_SIBLINGS];
	sem_t started;
	pthread_cond_t cond;
	pthread_mutex_t mutex;
	int sibling_count;
};

FIXTURE_SETUP(TSYNC)
{
	struct sock_filter root_filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_filter apply_filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};

	memset(&self->root_prog, 0, sizeof(self->root_prog));
	memset(&self->apply_prog, 0, sizeof(self->apply_prog));
	memset(&self->sibling, 0, sizeof(self->sibling));
	self->root_prog.filter = malloc(sizeof(root_filter));
	ASSERT_NE(NULL, self->root_prog.filter);
	memcpy(self->root_prog.filter, &root_filter, sizeof(root_filter));
	self->root_prog.len = (unsigned short)ARRAY_SIZE(root_filter);

	self->apply_prog.filter = malloc(sizeof(apply_filter));
	ASSERT_NE(NULL, self->apply_prog.filter);
	memcpy(self->apply_prog.filter, &apply_filter, sizeof(apply_filter));
	self->apply_prog.len = (unsigned short)ARRAY_SIZE(apply_filter);

	self->sibling_count = 0;
	pthread_mutex_init(&self->mutex, NULL);
	pthread_cond_init(&self->cond, NULL);
	sem_init(&self->started, 0, 0);
	self->sibling[0].tid = 0;
	self->sibling[0].cond = &self->cond;
	self->sibling[0].started = &self->started;
	self->sibling[0].mutex = &self->mutex;
	self->sibling[0].diverge = 0;
	self->sibling[0].num_waits = 1;
	self->sibling[0].prog = &self->root_prog;
	self->sibling[0].metadata = _metadata;
	self->sibling[1].tid = 0;
	self->sibling[1].cond = &self->cond;
	self->sibling[1].started = &self->started;
	self->sibling[1].mutex = &self->mutex;
	self->sibling[1].diverge = 0;
	self->sibling[1].prog = &self->root_prog;
	self->sibling[1].num_waits = 1;
	self->sibling[1].metadata = _metadata;
}

FIXTURE_TEARDOWN(TSYNC)
{
	int sib = 0;

	if (self->root_prog.filter)
		free(self->root_prog.filter);
	if (self->apply_prog.filter)
		free(self->apply_prog.filter);

	for ( ; sib < self->sibling_count; ++sib) {
		struct tsync_sibling *s = &self->sibling[sib];

		if (!s->tid)
			continue;
		/*
		 * If a thread is still running, it may be stuck, so hit
		 * it over the head really hard.
		 */
		pthread_kill(s->tid, 9);
	}
	pthread_mutex_destroy(&self->mutex);
	pthread_cond_destroy(&self->cond);
	sem_destroy(&self->started);
}

void *tsync_sibling(void *data)
{
	long ret = 0;
	struct tsync_sibling *me = data;

	me->system_tid = syscall(__NR_gettid);

	pthread_mutex_lock(me->mutex);
	if (me->diverge) {
		/* Just re-apply the root prog to fork the tree */
		ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER,
				me->prog, 0, 0);
	}
	sem_post(me->started);
	/* Return outside of started so parent notices failures. */
	if (ret) {
		pthread_mutex_unlock(me->mutex);
		return (void *)SIBLING_EXIT_FAILURE;
	}
	do {
		pthread_cond_wait(me->cond, me->mutex);
		me->num_waits = me->num_waits - 1;
	} while (me->num_waits);
	pthread_mutex_unlock(me->mutex);

	ret = prctl(PR_GET_NO_NEW_PRIVS, 0, 0, 0, 0);
	if (!ret)
		return (void *)SIBLING_EXIT_NEWPRIVS;
	read(0, NULL, 0);
	return (void *)SIBLING_EXIT_UNKILLED;
}

void tsync_start_sibling(struct tsync_sibling *sibling)
{
	pthread_create(&sibling->tid, NULL, tsync_sibling, (void *)sibling);
}

TEST_F(TSYNC, siblings_fail_prctl)
{
	long ret;
	void *status;
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EINVAL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	/* Check prctl failure detection by requesting sib 0 diverge. */
	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_EQ(0, ret) {
		TH_LOG("setting filter failed");
	}

	self->sibling[0].diverge = 1;
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);

	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	/* Signal the threads to clean up*/
	pthread_mutex_lock(&self->mutex);
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);

	/* Ensure diverging sibling failed to call prctl. */
	PTHREAD_JOIN(self->sibling[0].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_FAILURE, (long)status);
	PTHREAD_JOIN(self->sibling[1].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
}

TEST_F(TSYNC, two_siblings_with_ancestor)
{
	long ret;
	void *status;

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
	}
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);

	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_EQ(0, ret) {
		TH_LOG("Could install filter on all threads!");
	}
	/* Tell the siblings to test the policy */
	pthread_mutex_lock(&self->mutex);
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);
	/* Ensure they are both killed and don't exit cleanly. */
	PTHREAD_JOIN(self->sibling[0].tid, &status);
	EXPECT_EQ(0x0, (long)status);
	PTHREAD_JOIN(self->sibling[1].tid, &status);
	EXPECT_EQ(0x0, (long)status);
}

TEST_F(TSYNC, two_sibling_want_nnp)
{
	void *status;

	/* start siblings before any prctl() operations */
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);
	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	/* Tell the siblings to test no policy */
	pthread_mutex_lock(&self->mutex);
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);

	/* Ensure they are both upset about lacking nnp. */
	PTHREAD_JOIN(self->sibling[0].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_NEWPRIVS, (long)status);
	PTHREAD_JOIN(self->sibling[1].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_NEWPRIVS, (long)status);
}

TEST_F(TSYNC, two_siblings_with_no_filter)
{
	long ret;
	void *status;

	/* start siblings before any prctl() operations */
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);
	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_EQ(0, ret) {
		TH_LOG("Could install filter on all threads!");
	}

	/* Tell the siblings to test the policy */
	pthread_mutex_lock(&self->mutex);
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);

	/* Ensure they are both killed and don't exit cleanly. */
	PTHREAD_JOIN(self->sibling[0].tid, &status);
	EXPECT_EQ(0x0, (long)status);
	PTHREAD_JOIN(self->sibling[1].tid, &status);
	EXPECT_EQ(0x0, (long)status);
}

TEST_F(TSYNC, two_siblings_with_one_divergence)
{
	long ret;
	void *status;

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
	}
	self->sibling[0].diverge = 1;
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);

	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_EQ(self->sibling[0].system_tid, ret) {
		TH_LOG("Did not fail on diverged sibling.");
	}

	/* Wake the threads */
	pthread_mutex_lock(&self->mutex);
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);

	/* Ensure they are both unkilled. */
	PTHREAD_JOIN(self->sibling[0].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
	PTHREAD_JOIN(self->sibling[1].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
}

TEST_F(TSYNC, two_siblings_not_under_filter)
{
	long ret, sib;
	void *status;
	struct timespec delay = { .tv_nsec = 100000000 };

	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	/*
	 * Sibling 0 will have its own seccomp policy
	 * and Sibling 1 will not be under seccomp at
	 * all. Sibling 1 will enter seccomp and 0
	 * will cause failure.
	 */
	self->sibling[0].diverge = 1;
	tsync_start_sibling(&self->sibling[0]);
	tsync_start_sibling(&self->sibling[1]);

	while (self->sibling_count < TSYNC_SIBLINGS) {
		sem_wait(&self->started);
		self->sibling_count++;
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
	}

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_EQ(ret, self->sibling[0].system_tid) {
		TH_LOG("Did not fail on diverged sibling.");
	}
	sib = 1;
	if (ret == self->sibling[0].system_tid)
		sib = 0;

	pthread_mutex_lock(&self->mutex);

	/* Increment the other siblings num_waits so we can clean up
	 * the one we just saw.
	 */
	self->sibling[!sib].num_waits += 1;

	/* Signal the thread to clean up*/
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);
	PTHREAD_JOIN(self->sibling[sib].tid, &status);
	EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
	/* Poll for actual task death. pthread_join doesn't guarantee it. */
	while (!kill(self->sibling[sib].system_tid, 0))
		nanosleep(&delay, NULL);
	/* Switch to the remaining sibling */
	sib = !sib;

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_EQ(0, ret) {
		TH_LOG("Expected the remaining sibling to sync");
	};

	pthread_mutex_lock(&self->mutex);

	/* If remaining sibling didn't have a chance to wake up during
	 * the first broadcast, manually reduce the num_waits now.
	 */
	if (self->sibling[sib].num_waits > 1)
		self->sibling[sib].num_waits = 1;
	ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
		TH_LOG("cond broadcast non-zero");
	}
	pthread_mutex_unlock(&self->mutex);
	PTHREAD_JOIN(self->sibling[sib].tid, &status);
	EXPECT_EQ(0, (long)status);
	/* Poll for actual task death. pthread_join doesn't guarantee it. */
	while (!kill(self->sibling[sib].system_tid, 0))
		nanosleep(&delay, NULL);

	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
		      &self->apply_prog);
	ASSERT_EQ(0, ret);  /* just us chickens */
}

/* Make sure restarted syscalls are seen directly as "restart_syscall". */
TEST(syscall_restart)
{
	long ret;
	unsigned long msg;
	pid_t child_pid;
	int pipefd[2];
	int status;
	siginfo_t info = { };
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			 offsetof(struct seccomp_data, nr)),

#ifdef __NR_sigreturn
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 6, 0),
#endif
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 5, 0),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 4, 0),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 3, 0),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 4, 0),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_restart_syscall, 4, 0),

		/* Allow __NR_write for easy logging. */
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_write, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		/* The nanosleep jump target. */
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x100),
		/* The restart_syscall jump target. */
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x200),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};
#if defined(__arm__)
	struct utsname utsbuf;
#endif

	ASSERT_EQ(0, pipe(pipefd));

	child_pid = fork();
	ASSERT_LE(0, child_pid);
	if (child_pid == 0) {
		/* Child uses EXPECT not ASSERT to deliver status correctly. */
		char buf = ' ';
		struct timespec timeout = { };

		/* Attach parent as tracer and stop. */
		EXPECT_EQ(0, ptrace(PTRACE_TRACEME));
		EXPECT_EQ(0, raise(SIGSTOP));

		EXPECT_EQ(0, close(pipefd[1]));

		EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
			TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
		}

		ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0);
		EXPECT_EQ(0, ret) {
			TH_LOG("Failed to install filter!");
		}

		EXPECT_EQ(1, read(pipefd[0], &buf, 1)) {
			TH_LOG("Failed to read() sync from parent");
		}
		EXPECT_EQ('.', buf) {
			TH_LOG("Failed to get sync data from read()");
		}

		/* Start nanosleep to be interrupted. */
		timeout.tv_sec = 1;
		errno = 0;
		EXPECT_EQ(0, nanosleep(&timeout, NULL)) {
			TH_LOG("Call to nanosleep() failed (errno %d)", errno);
		}

		/* Read final sync from parent. */
		EXPECT_EQ(1, read(pipefd[0], &buf, 1)) {
			TH_LOG("Failed final read() from parent");
		}
		EXPECT_EQ('!', buf) {
			TH_LOG("Failed to get final data from read()");
		}

		/* Directly report the status of our test harness results. */
		syscall(__NR_exit, _metadata->passed ? EXIT_SUCCESS
						     : EXIT_FAILURE);
	}
	EXPECT_EQ(0, close(pipefd[0]));

	/* Attach to child, setup options, and release. */
	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	ASSERT_EQ(true, WIFSTOPPED(status));
	ASSERT_EQ(0, ptrace(PTRACE_SETOPTIONS, child_pid, NULL,
			    PTRACE_O_TRACESECCOMP));
	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
	ASSERT_EQ(1, write(pipefd[1], ".", 1));

	/* Wait for nanosleep() to start. */
	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	ASSERT_EQ(true, WIFSTOPPED(status));
	ASSERT_EQ(SIGTRAP, WSTOPSIG(status));
	ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
	ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));
	ASSERT_EQ(0x100, msg);
	EXPECT_EQ(__NR_nanosleep, get_syscall(_metadata, child_pid));

	/* Might as well check siginfo for sanity while we're here. */
	ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
	ASSERT_EQ(SIGTRAP, info.si_signo);
	ASSERT_EQ(SIGTRAP | (PTRACE_EVENT_SECCOMP << 8), info.si_code);
	EXPECT_EQ(0, info.si_errno);
	EXPECT_EQ(getuid(), info.si_uid);
	/* Verify signal delivery came from child (seccomp-triggered). */
	EXPECT_EQ(child_pid, info.si_pid);

	/* Interrupt nanosleep with SIGSTOP (which we'll need to handle). */
	ASSERT_EQ(0, kill(child_pid, SIGSTOP));
	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	ASSERT_EQ(true, WIFSTOPPED(status));
	ASSERT_EQ(SIGSTOP, WSTOPSIG(status));
	ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
	/*
	 * There is no siginfo on SIGSTOP any more, so we can't verify
	 * signal delivery came from parent now (getpid() == info.si_pid).
	 * https://lkml.kernel.org/r/CAGXu5jJaZAOzP1qFz66tYrtbuywqb+UN2SOA1VLHpCCOiYvYeg@mail.gmail.com
	 * At least verify the SIGSTOP via PTRACE_GETSIGINFO.
	 */
	EXPECT_EQ(SIGSTOP, info.si_signo);

	/* Restart nanosleep with SIGCONT, which triggers restart_syscall. */
	ASSERT_EQ(0, kill(child_pid, SIGCONT));
	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	ASSERT_EQ(true, WIFSTOPPED(status));
	ASSERT_EQ(SIGCONT, WSTOPSIG(status));
	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));

	/* Wait for restart_syscall() to start. */
	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	ASSERT_EQ(true, WIFSTOPPED(status));
	ASSERT_EQ(SIGTRAP, WSTOPSIG(status));
	ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
	ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));

	ASSERT_EQ(0x200, msg);
	ret = get_syscall(_metadata, child_pid);
#if defined(__arm__)
	/*
	 * FIXME:
	 * - native ARM registers do NOT expose true syscall.
	 * - compat ARM registers on ARM64 DO expose true syscall.
	 */
	ASSERT_EQ(0, uname(&utsbuf));
	if (strncmp(utsbuf.machine, "arm", 3) == 0) {
		EXPECT_EQ(__NR_nanosleep, ret);
	} else
#endif
	{
		EXPECT_EQ(__NR_restart_syscall, ret);
	}

	/* Write again to end test. */
	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
	ASSERT_EQ(1, write(pipefd[1], "!", 1));
	EXPECT_EQ(0, close(pipefd[1]));

	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
	if (WIFSIGNALED(status) || WEXITSTATUS(status))
		_metadata->passed = 0;
}

TEST_SIGNAL(filter_flag_log, SIGSYS)
{
	struct sock_filter allow_filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_filter kill_filter[] = {
		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog allow_prog = {
		.len = (unsigned short)ARRAY_SIZE(allow_filter),
		.filter = allow_filter,
	};
	struct sock_fprog kill_prog = {
		.len = (unsigned short)ARRAY_SIZE(kill_filter),
		.filter = kill_filter,
	};
	long ret;
	pid_t parent = getppid();

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret);

	/* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */
	ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG,
		      &allow_prog);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	EXPECT_NE(0, ret) {
		TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!");
	}
	EXPECT_EQ(EINVAL, errno) {
		TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!");
	}

	/* Verify that a simple, permissive filter can be added with no flags */
	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
	EXPECT_EQ(0, ret);

	/* See if the same filter can be added with the FILTER_FLAG_LOG flag */
	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
		      &allow_prog);
	ASSERT_NE(EINVAL, errno) {
		TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!");
	}
	EXPECT_EQ(0, ret);

	/* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */
	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
		      &kill_prog);
	EXPECT_EQ(0, ret);

	EXPECT_EQ(parent, syscall(__NR_getppid));
	/* getpid() should never return. */
	EXPECT_EQ(0, syscall(__NR_getpid));
}

TEST(get_action_avail)
{
	__u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP,
			    SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE,
			    SECCOMP_RET_LOG,   SECCOMP_RET_ALLOW };
	__u32 unknown_action = 0x10000000U;
	int i;
	long ret;

	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]);
	ASSERT_NE(ENOSYS, errno) {
		TH_LOG("Kernel does not support seccomp syscall!");
	}
	ASSERT_NE(EINVAL, errno) {
		TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!");
	}
	EXPECT_EQ(ret, 0);

	for (i = 0; i < ARRAY_SIZE(actions); i++) {
		ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]);
		EXPECT_EQ(ret, 0) {
			TH_LOG("Expected action (0x%X) not available!",
			       actions[i]);
		}
	}

	/* Check that an unknown action is handled properly (EOPNOTSUPP) */
	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action);
	EXPECT_EQ(ret, -1);
	EXPECT_EQ(errno, EOPNOTSUPP);
}

TEST(get_metadata)
{
	pid_t pid;
	int pipefd[2];
	char buf;
	struct seccomp_metadata md;
	long ret;

	/* Only real root can get metadata. */
	if (geteuid()) {
		XFAIL(return, "get_metadata requires real root");
		return;
	}

	ASSERT_EQ(0, pipe(pipefd));

	pid = fork();
	ASSERT_GE(pid, 0);
	if (pid == 0) {
		struct sock_filter filter[] = {
			BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
		};
		struct sock_fprog prog = {
			.len = (unsigned short)ARRAY_SIZE(filter),
			.filter = filter,
		};

		/* one with log, one without */
		EXPECT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER,
				     SECCOMP_FILTER_FLAG_LOG, &prog));
		EXPECT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog));

		EXPECT_EQ(0, close(pipefd[0]));
		ASSERT_EQ(1, write(pipefd[1], "1", 1));
		ASSERT_EQ(0, close(pipefd[1]));

		while (1)
			sleep(100);
	}

	ASSERT_EQ(0, close(pipefd[1]));
	ASSERT_EQ(1, read(pipefd[0], &buf, 1));

	ASSERT_EQ(0, ptrace(PTRACE_ATTACH, pid));
	ASSERT_EQ(pid, waitpid(pid, NULL, 0));

	/* Past here must not use ASSERT or child process is never killed. */

	md.filter_off = 0;
	errno = 0;
	ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md);
	EXPECT_EQ(sizeof(md), ret) {
		if (errno == EINVAL)
			XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)");
	}

	EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG);
	EXPECT_EQ(md.filter_off, 0);

	md.filter_off = 1;
	ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md);
	EXPECT_EQ(sizeof(md), ret);
	EXPECT_EQ(md.flags, 0);
	EXPECT_EQ(md.filter_off, 1);

skip:
	ASSERT_EQ(0, kill(pid, SIGKILL));
}

static int user_trap_syscall(int nr, unsigned int flags)
{
	struct sock_filter filter[] = {
		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
			offsetof(struct seccomp_data, nr)),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
	};

	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};

	return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog);
}

#define USER_NOTIF_MAGIC INT_MAX
TEST(user_notification_basic)
{
	pid_t pid;
	long ret;
	int status, listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};
	struct pollfd pollfd;

	struct sock_filter filter[] = {
		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)ARRAY_SIZE(filter),
		.filter = filter,
	};

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	pid = fork();
	ASSERT_GE(pid, 0);

	/* Check that we get -ENOSYS with no listener attached */
	if (pid == 0) {
		if (user_trap_syscall(__NR_getppid, 0) < 0)
			exit(1);
		ret = syscall(__NR_getppid);
		exit(ret >= 0 || errno != ENOSYS);
	}

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));

	/* Add some no-op filters for grins. */
	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);
	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);
	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);
	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);

	/* Check that the basic notification machinery works */
	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	/* Installing a second listener in the chain should EBUSY */
	EXPECT_EQ(user_trap_syscall(__NR_getppid,
				    SECCOMP_FILTER_FLAG_NEW_LISTENER),
		  -1);
	EXPECT_EQ(errno, EBUSY);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0) {
		ret = syscall(__NR_getppid);
		exit(ret != USER_NOTIF_MAGIC);
	}

	pollfd.fd = listener;
	pollfd.events = POLLIN | POLLOUT;

	EXPECT_GT(poll(&pollfd, 1, -1), 0);
	EXPECT_EQ(pollfd.revents, POLLIN);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);

	pollfd.fd = listener;
	pollfd.events = POLLIN | POLLOUT;

	EXPECT_GT(poll(&pollfd, 1, -1), 0);
	EXPECT_EQ(pollfd.revents, POLLOUT);

	EXPECT_EQ(req.data.nr,  __NR_getppid);

	resp.id = req.id;
	resp.error = 0;
	resp.val = USER_NOTIF_MAGIC;

	/* check that we make sure flags == 0 */
	resp.flags = 1;
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
	EXPECT_EQ(errno, EINVAL);

	resp.flags = 0;
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
}

TEST(user_notification_kill_in_middle)
{
	pid_t pid;
	long ret;
	int listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	/*
	 * Check that nothing bad happens when we kill the task in the middle
	 * of a syscall.
	 */
	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0) {
		ret = syscall(__NR_getppid);
		exit(ret != USER_NOTIF_MAGIC);
	}

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req.id), 0);

	EXPECT_EQ(kill(pid, SIGKILL), 0);
	EXPECT_EQ(waitpid(pid, NULL, 0), pid);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req.id), -1);

	resp.id = req.id;
	ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp);
	EXPECT_EQ(ret, -1);
	EXPECT_EQ(errno, ENOENT);
}

static int handled = -1;

static void signal_handler(int signal)
{
	if (write(handled, "c", 1) != 1)
		perror("write from signal");
}

TEST(user_notification_signal)
{
	pid_t pid;
	long ret;
	int status, listener, sk_pair[2];
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};
	char c;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0);

	listener = user_trap_syscall(__NR_gettid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0) {
		close(sk_pair[0]);
		handled = sk_pair[1];
		if (signal(SIGUSR1, signal_handler) == SIG_ERR) {
			perror("signal");
			exit(1);
		}
		/*
		 * ERESTARTSYS behavior is a bit hard to test, because we need
		 * to rely on a signal that has not yet been handled. Let's at
		 * least check that the error code gets propagated through, and
		 * hope that it doesn't break when there is actually a signal :)
		 */
		ret = syscall(__NR_gettid);
		exit(!(ret == -1 && errno == 512));
	}

	close(sk_pair[1]);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);

	EXPECT_EQ(kill(pid, SIGUSR1), 0);

	/*
	 * Make sure the signal really is delivered, which means we're not
	 * stuck in the user notification code any more and the notification
	 * should be dead.
	 */
	EXPECT_EQ(read(sk_pair[0], &c, 1), 1);

	resp.id = req.id;
	resp.error = -EPERM;
	resp.val = 0;

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
	EXPECT_EQ(errno, ENOENT);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);

	resp.id = req.id;
	resp.error = -512; /* -ERESTARTSYS */
	resp.val = 0;

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
}

TEST(user_notification_closed_listener)
{
	pid_t pid;
	long ret;
	int status, listener;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	/*
	 * Check that we get an ENOSYS when the listener is closed.
	 */
	pid = fork();
	ASSERT_GE(pid, 0);
	if (pid == 0) {
		close(listener);
		ret = syscall(__NR_getppid);
		exit(ret != -1 && errno != ENOSYS);
	}

	close(listener);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
}

/*
 * Check that a pid in a child namespace still shows up as valid in ours.
 */
TEST(user_notification_child_pid_ns)
{
	pid_t pid;
	int status, listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};

	ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0);

	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0)
		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
	EXPECT_EQ(req.pid, pid);

	resp.id = req.id;
	resp.error = 0;
	resp.val = USER_NOTIF_MAGIC;

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
	close(listener);
}

/*
 * Check that a pid in a sibling (i.e. unrelated) namespace shows up as 0, i.e.
 * invalid.
 */
TEST(user_notification_sibling_pid_ns)
{
	pid_t pid, pid2;
	int status, listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};

	ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0) {
		ASSERT_EQ(unshare(CLONE_NEWPID), 0);

		pid2 = fork();
		ASSERT_GE(pid2, 0);

		if (pid2 == 0)
			exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);

		EXPECT_EQ(waitpid(pid2, &status, 0), pid2);
		EXPECT_EQ(true, WIFEXITED(status));
		EXPECT_EQ(0, WEXITSTATUS(status));
		exit(WEXITSTATUS(status));
	}

	/* Create the sibling ns, and sibling in it. */
	ASSERT_EQ(unshare(CLONE_NEWPID), 0);
	ASSERT_EQ(errno, 0);

	pid2 = fork();
	ASSERT_GE(pid2, 0);

	if (pid2 == 0) {
		ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
		/*
		 * The pid should be 0, i.e. the task is in some namespace that
		 * we can't "see".
		 */
		EXPECT_EQ(req.pid, 0);

		resp.id = req.id;
		resp.error = 0;
		resp.val = USER_NOTIF_MAGIC;

		ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
		exit(0);
	}

	close(listener);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));

	EXPECT_EQ(waitpid(pid2, &status, 0), pid2);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
}

TEST(user_notification_fault_recv)
{
	pid_t pid;
	int status, listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};

	ASSERT_EQ(unshare(CLONE_NEWUSER), 0);

	listener = user_trap_syscall(__NR_getppid,
				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0)
		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);

	/* Do a bad recv() */
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, NULL), -1);
	EXPECT_EQ(errno, EFAULT);

	/* We should still be able to receive this notification, though. */
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
	EXPECT_EQ(req.pid, pid);

	resp.id = req.id;
	resp.error = 0;
	resp.val = USER_NOTIF_MAGIC;

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);

	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status));
}

TEST(seccomp_get_notif_sizes)
{
	struct seccomp_notif_sizes sizes;

	ASSERT_EQ(seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes), 0);
	EXPECT_EQ(sizes.seccomp_notif, sizeof(struct seccomp_notif));
	EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp));
}

static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2)
{
#ifdef __NR_kcmp
	return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2);
#else
	errno = ENOSYS;
	return -1;
#endif
}

TEST(user_notification_continue)
{
	pid_t pid;
	long ret;
	int status, listener;
	struct seccomp_notif req = {};
	struct seccomp_notif_resp resp = {};
	struct pollfd pollfd;

	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
	ASSERT_EQ(0, ret) {
		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
	}

	listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER);
	ASSERT_GE(listener, 0);

	pid = fork();
	ASSERT_GE(pid, 0);

	if (pid == 0) {
		int dup_fd, pipe_fds[2];
		pid_t self;

		ret = pipe(pipe_fds);
		if (ret < 0)
			exit(1);

		dup_fd = dup(pipe_fds[0]);
		if (dup_fd < 0)
			exit(1);

		self = getpid();

		ret = filecmp(self, self, pipe_fds[0], dup_fd);
		if (ret)
			exit(2);

		exit(0);
	}

	pollfd.fd = listener;
	pollfd.events = POLLIN | POLLOUT;

	EXPECT_GT(poll(&pollfd, 1, -1), 0);
	EXPECT_EQ(pollfd.revents, POLLIN);

	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);

	pollfd.fd = listener;
	pollfd.events = POLLIN | POLLOUT;

	EXPECT_GT(poll(&pollfd, 1, -1), 0);
	EXPECT_EQ(pollfd.revents, POLLOUT);

	EXPECT_EQ(req.data.nr, __NR_dup);

	resp.id = req.id;
	resp.flags = SECCOMP_USER_NOTIF_FLAG_CONTINUE;

	/*
	 * Verify that setting SECCOMP_USER_NOTIF_FLAG_CONTINUE enforces other
	 * args be set to 0.
	 */
	resp.error = 0;
	resp.val = USER_NOTIF_MAGIC;
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
	EXPECT_EQ(errno, EINVAL);

	resp.error = USER_NOTIF_MAGIC;
	resp.val = 0;
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
	EXPECT_EQ(errno, EINVAL);

	resp.error = 0;
	resp.val = 0;
	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) {
		if (errno == EINVAL)
			XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE");
	}

skip:
	EXPECT_EQ(waitpid(pid, &status, 0), pid);
	EXPECT_EQ(true, WIFEXITED(status));
	EXPECT_EQ(0, WEXITSTATUS(status)) {
		if (WEXITSTATUS(status) == 2) {
			XFAIL(return, "Kernel does not support kcmp() syscall");
			return;
		}
	}
}

/*
 * TODO:
 * - add microbenchmarks
 * - expand NNP testing
 * - better arch-specific TRACE and TRAP handlers.
 * - endianness checking when appropriate
 * - 64-bit arg prodding
 * - arch value testing (x86 modes especially)
 * - verify that FILTER_FLAG_LOG filters generate log messages
 * - verify that RET_LOG generates log messages
 * - ...
 */

TEST_HARNESS_MAIN