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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Parts came from builtin-{top,stat,record}.c, see those files for further
* copyright notes.
*/
#include <byteswap.h>
#include <errno.h>
#include <inttypes.h>
#include <linux/bitops.h>
#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
#include <traceevent/event-parse.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/zalloc.h>
#include <sys/ioctl.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <dirent.h>
#include <stdlib.h>
#include <perf/evsel.h>
#include "asm/bug.h"
#include "callchain.h"
#include "cgroup.h"
#include "counts.h"
#include "event.h"
#include "evsel.h"
#include "evlist.h"
#include <perf/cpumap.h>
#include "thread_map.h"
#include "target.h"
#include "perf_regs.h"
#include "record.h"
#include "debug.h"
#include "trace-event.h"
#include "stat.h"
#include "string2.h"
#include "memswap.h"
#include "util.h"
#include "../perf-sys.h"
#include "util/parse-branch-options.h"
#include <internal/xyarray.h>
#include <internal/lib.h>
#include <linux/ctype.h>
struct perf_missing_features perf_missing_features;
static clockid_t clockid;
static int perf_evsel__no_extra_init(struct evsel *evsel __maybe_unused)
{
return 0;
}
void __weak test_attr__ready(void) { }
static void perf_evsel__no_extra_fini(struct evsel *evsel __maybe_unused)
{
}
static struct {
size_t size;
int (*init)(struct evsel *evsel);
void (*fini)(struct evsel *evsel);
} perf_evsel__object = {
.size = sizeof(struct evsel),
.init = perf_evsel__no_extra_init,
.fini = perf_evsel__no_extra_fini,
};
int perf_evsel__object_config(size_t object_size,
int (*init)(struct evsel *evsel),
void (*fini)(struct evsel *evsel))
{
if (object_size == 0)
goto set_methods;
if (perf_evsel__object.size > object_size)
return -EINVAL;
perf_evsel__object.size = object_size;
set_methods:
if (init != NULL)
perf_evsel__object.init = init;
if (fini != NULL)
perf_evsel__object.fini = fini;
return 0;
}
#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
int __perf_evsel__sample_size(u64 sample_type)
{
u64 mask = sample_type & PERF_SAMPLE_MASK;
int size = 0;
int i;
for (i = 0; i < 64; i++) {
if (mask & (1ULL << i))
size++;
}
size *= sizeof(u64);
return size;
}
/**
* __perf_evsel__calc_id_pos - calculate id_pos.
* @sample_type: sample type
*
* This function returns the position of the event id (PERF_SAMPLE_ID or
* PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
* perf_record_sample.
*/
static int __perf_evsel__calc_id_pos(u64 sample_type)
{
int idx = 0;
if (sample_type & PERF_SAMPLE_IDENTIFIER)
return 0;
if (!(sample_type & PERF_SAMPLE_ID))
return -1;
if (sample_type & PERF_SAMPLE_IP)
idx += 1;
if (sample_type & PERF_SAMPLE_TID)
idx += 1;
if (sample_type & PERF_SAMPLE_TIME)
idx += 1;
if (sample_type & PERF_SAMPLE_ADDR)
idx += 1;
return idx;
}
/**
* __perf_evsel__calc_is_pos - calculate is_pos.
* @sample_type: sample type
*
* This function returns the position (counting backwards) of the event id
* (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
* sample_id_all is used there is an id sample appended to non-sample events.
*/
static int __perf_evsel__calc_is_pos(u64 sample_type)
{
int idx = 1;
if (sample_type & PERF_SAMPLE_IDENTIFIER)
return 1;
if (!(sample_type & PERF_SAMPLE_ID))
return -1;
if (sample_type & PERF_SAMPLE_CPU)
idx += 1;
if (sample_type & PERF_SAMPLE_STREAM_ID)
idx += 1;
return idx;
}
void perf_evsel__calc_id_pos(struct evsel *evsel)
{
evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type);
evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type);
}
void __perf_evsel__set_sample_bit(struct evsel *evsel,
enum perf_event_sample_format bit)
{
if (!(evsel->core.attr.sample_type & bit)) {
evsel->core.attr.sample_type |= bit;
evsel->sample_size += sizeof(u64);
perf_evsel__calc_id_pos(evsel);
}
}
void __perf_evsel__reset_sample_bit(struct evsel *evsel,
enum perf_event_sample_format bit)
{
if (evsel->core.attr.sample_type & bit) {
evsel->core.attr.sample_type &= ~bit;
evsel->sample_size -= sizeof(u64);
perf_evsel__calc_id_pos(evsel);
}
}
void perf_evsel__set_sample_id(struct evsel *evsel,
bool can_sample_identifier)
{
if (can_sample_identifier) {
perf_evsel__reset_sample_bit(evsel, ID);
perf_evsel__set_sample_bit(evsel, IDENTIFIER);
} else {
perf_evsel__set_sample_bit(evsel, ID);
}
evsel->core.attr.read_format |= PERF_FORMAT_ID;
}
/**
* perf_evsel__is_function_event - Return whether given evsel is a function
* trace event
*
* @evsel - evsel selector to be tested
*
* Return %true if event is function trace event
*/
bool perf_evsel__is_function_event(struct evsel *evsel)
{
#define FUNCTION_EVENT "ftrace:function"
return evsel->name &&
!strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
#undef FUNCTION_EVENT
}
void evsel__init(struct evsel *evsel,
struct perf_event_attr *attr, int idx)
{
perf_evsel__init(&evsel->core, attr);
evsel->idx = idx;
evsel->tracking = !idx;
evsel->leader = evsel;
evsel->unit = "";
evsel->scale = 1.0;
evsel->max_events = ULONG_MAX;
evsel->evlist = NULL;
evsel->bpf_obj = NULL;
evsel->bpf_fd = -1;
INIT_LIST_HEAD(&evsel->config_terms);
perf_evsel__object.init(evsel);
evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
perf_evsel__calc_id_pos(evsel);
evsel->cmdline_group_boundary = false;
evsel->metric_expr = NULL;
evsel->metric_name = NULL;
evsel->metric_events = NULL;
evsel->collect_stat = false;
evsel->pmu_name = NULL;
}
struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
{
struct evsel *evsel = zalloc(perf_evsel__object.size);
if (!evsel)
return NULL;
evsel__init(evsel, attr, idx);
if (perf_evsel__is_bpf_output(evsel)) {
evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
evsel->core.attr.sample_period = 1;
}
if (perf_evsel__is_clock(evsel)) {
/*
* The evsel->unit points to static alias->unit
* so it's ok to use static string in here.
*/
static const char *unit = "msec";
evsel->unit = unit;
evsel->scale = 1e-6;
}
return evsel;
}
static bool perf_event_can_profile_kernel(void)
{
return perf_event_paranoid_check(1);
}
struct evsel *perf_evsel__new_cycles(bool precise)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
.exclude_kernel = !perf_event_can_profile_kernel(),
};
struct evsel *evsel;
event_attr_init(&attr);
if (!precise)
goto new_event;
/*
* Now let the usual logic to set up the perf_event_attr defaults
* to kick in when we return and before perf_evsel__open() is called.
*/
new_event:
evsel = evsel__new(&attr);
if (evsel == NULL)
goto out;
evsel->precise_max = true;
/* use asprintf() because free(evsel) assumes name is allocated */
if (asprintf(&evsel->name, "cycles%s%s%.*s",
(attr.precise_ip || attr.exclude_kernel) ? ":" : "",
attr.exclude_kernel ? "u" : "",
attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
goto error_free;
out:
return evsel;
error_free:
evsel__delete(evsel);
evsel = NULL;
goto out;
}
/*
* Returns pointer with encoded error via <linux/err.h> interface.
*/
struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
{
struct evsel *evsel = zalloc(perf_evsel__object.size);
int err = -ENOMEM;
if (evsel == NULL) {
goto out_err;
} else {
struct perf_event_attr attr = {
.type = PERF_TYPE_TRACEPOINT,
.sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
};
if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
goto out_free;
evsel->tp_format = trace_event__tp_format(sys, name);
if (IS_ERR(evsel->tp_format)) {
err = PTR_ERR(evsel->tp_format);
goto out_free;
}
event_attr_init(&attr);
attr.config = evsel->tp_format->id;
attr.sample_period = 1;
evsel__init(evsel, &attr, idx);
}
return evsel;
out_free:
zfree(&evsel->name);
free(evsel);
out_err:
return ERR_PTR(err);
}
const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
"cycles",
"instructions",
"cache-references",
"cache-misses",
"branches",
"branch-misses",
"bus-cycles",
"stalled-cycles-frontend",
"stalled-cycles-backend",
"ref-cycles",
};
static const char *__perf_evsel__hw_name(u64 config)
{
if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
return perf_evsel__hw_names[config];
return "unknown-hardware";
}
static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
{
int colon = 0, r = 0;
struct perf_event_attr *attr = &evsel->core.attr;
bool exclude_guest_default = false;
#define MOD_PRINT(context, mod) do { \
if (!attr->exclude_##context) { \
if (!colon) colon = ++r; \
r += scnprintf(bf + r, size - r, "%c", mod); \
} } while(0)
if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) {
MOD_PRINT(kernel, 'k');
MOD_PRINT(user, 'u');
MOD_PRINT(hv, 'h');
exclude_guest_default = true;
}
if (attr->precise_ip) {
if (!colon)
colon = ++r;
r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
exclude_guest_default = true;
}
if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
MOD_PRINT(host, 'H');
MOD_PRINT(guest, 'G');
}
#undef MOD_PRINT
if (colon)
bf[colon - 1] = ':';
return r;
}
static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
"cpu-clock",
"task-clock",
"page-faults",
"context-switches",
"cpu-migrations",
"minor-faults",
"major-faults",
"alignment-faults",
"emulation-faults",
"dummy",
};
static const char *__perf_evsel__sw_name(u64 config)
{
if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
return perf_evsel__sw_names[config];
return "unknown-software";
}
static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
{
int r;
r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
if (type & HW_BREAKPOINT_R)
r += scnprintf(bf + r, size - r, "r");
if (type & HW_BREAKPOINT_W)
r += scnprintf(bf + r, size - r, "w");
if (type & HW_BREAKPOINT_X)
r += scnprintf(bf + r, size - r, "x");
return r;
}
static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
{
struct perf_event_attr *attr = &evsel->core.attr;
int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "L1-dcache", "l1-d", "l1d", "L1-data", },
{ "L1-icache", "l1-i", "l1i", "L1-instruction", },
{ "LLC", "L2", },
{ "dTLB", "d-tlb", "Data-TLB", },
{ "iTLB", "i-tlb", "Instruction-TLB", },
{ "branch", "branches", "bpu", "btb", "bpc", },
{ "node", },
};
const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "load", "loads", "read", },
{ "store", "stores", "write", },
{ "prefetch", "prefetches", "speculative-read", "speculative-load", },
};
const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "refs", "Reference", "ops", "access", },
{ "misses", "miss", },
};
#define C(x) PERF_COUNT_HW_CACHE_##x
#define CACHE_READ (1 << C(OP_READ))
#define CACHE_WRITE (1 << C(OP_WRITE))
#define CACHE_PREFETCH (1 << C(OP_PREFETCH))
#define COP(x) (1 << x)
/*
* cache operartion stat
* L1I : Read and prefetch only
* ITLB and BPU : Read-only
*/
static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
[C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(L1I)] = (CACHE_READ | CACHE_PREFETCH),
[C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(ITLB)] = (CACHE_READ),
[C(BPU)] = (CACHE_READ),
[C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
};
bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
{
if (perf_evsel__hw_cache_stat[type] & COP(op))
return true; /* valid */
else
return false; /* invalid */
}
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
char *bf, size_t size)
{
if (result) {
return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
perf_evsel__hw_cache_op[op][0],
perf_evsel__hw_cache_result[result][0]);
}
return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
perf_evsel__hw_cache_op[op][1]);
}
static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
{
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
if (type >= PERF_COUNT_HW_CACHE_MAX)
goto out_err;
op = (config >> 8) & 0xff;
err = "unknown-ext-hardware-cache-op";
if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
goto out_err;
result = (config >> 16) & 0xff;
err = "unknown-ext-hardware-cache-result";
if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
goto out_err;
err = "invalid-cache";
if (!perf_evsel__is_cache_op_valid(type, op))
goto out_err;
return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
out_err:
return scnprintf(bf, size, "%s", err);
}
static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
{
int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
{
int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int perf_evsel__tool_name(char *bf, size_t size)
{
int ret = scnprintf(bf, size, "duration_time");
return ret;
}
const char *perf_evsel__name(struct evsel *evsel)
{
char bf[128];
if (!evsel)
goto out_unknown;
if (evsel->name)
return evsel->name;
switch (evsel->core.attr.type) {
case PERF_TYPE_RAW:
perf_evsel__raw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HARDWARE:
perf_evsel__hw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HW_CACHE:
perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_SOFTWARE:
if (evsel->tool_event)
perf_evsel__tool_name(bf, sizeof(bf));
else
perf_evsel__sw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_TRACEPOINT:
scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
break;
case PERF_TYPE_BREAKPOINT:
perf_evsel__bp_name(evsel, bf, sizeof(bf));
break;
default:
scnprintf(bf, sizeof(bf), "unknown attr type: %d",
evsel->core.attr.type);
break;
}
evsel->name = strdup(bf);
if (evsel->name)
return evsel->name;
out_unknown:
return "unknown";
}
const char *perf_evsel__group_name(struct evsel *evsel)
{
return evsel->group_name ?: "anon group";
}
/*
* Returns the group details for the specified leader,
* with following rules.
*
* For record -e '{cycles,instructions}'
* 'anon group { cycles:u, instructions:u }'
*
* For record -e 'cycles,instructions' and report --group
* 'cycles:u, instructions:u'
*/
int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
{
int ret = 0;
struct evsel *pos;
const char *group_name = perf_evsel__group_name(evsel);
if (!evsel->forced_leader)
ret = scnprintf(buf, size, "%s { ", group_name);
ret += scnprintf(buf + ret, size - ret, "%s",
perf_evsel__name(evsel));
for_each_group_member(pos, evsel)
ret += scnprintf(buf + ret, size - ret, ", %s",
perf_evsel__name(pos));
if (!evsel->forced_leader)
ret += scnprintf(buf + ret, size - ret, " }");
return ret;
}
static void __perf_evsel__config_callchain(struct evsel *evsel,
struct record_opts *opts,
struct callchain_param *param)
{
bool function = perf_evsel__is_function_event(evsel);
struct perf_event_attr *attr = &evsel->core.attr;
perf_evsel__set_sample_bit(evsel, CALLCHAIN);
attr->sample_max_stack = param->max_stack;
if (opts->kernel_callchains)
attr->exclude_callchain_user = 1;
if (opts->user_callchains)
attr->exclude_callchain_kernel = 1;
if (param->record_mode == CALLCHAIN_LBR) {
if (!opts->branch_stack) {
if (attr->exclude_user) {
pr_warning("LBR callstack option is only available "
"to get user callchain information. "
"Falling back to framepointers.\n");
} else {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
PERF_SAMPLE_BRANCH_NO_FLAGS;
}
} else
pr_warning("Cannot use LBR callstack with branch stack. "
"Falling back to framepointers.\n");
}
if (param->record_mode == CALLCHAIN_DWARF) {
if (!function) {
perf_evsel__set_sample_bit(evsel, REGS_USER);
perf_evsel__set_sample_bit(evsel, STACK_USER);
if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
attr->sample_regs_user |= DWARF_MINIMAL_REGS;
pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
"specifying a subset with --user-regs may render DWARF unwinding unreliable, "
"so the minimal registers set (IP, SP) is explicitly forced.\n");
} else {
attr->sample_regs_user |= PERF_REGS_MASK;
}
attr->sample_stack_user = param->dump_size;
attr->exclude_callchain_user = 1;
} else {
pr_info("Cannot use DWARF unwind for function trace event,"
" falling back to framepointers.\n");
}
}
if (function) {
pr_info("Disabling user space callchains for function trace event.\n");
attr->exclude_callchain_user = 1;
}
}
void perf_evsel__config_callchain(struct evsel *evsel,
struct record_opts *opts,
struct callchain_param *param)
{
if (param->enabled)
return __perf_evsel__config_callchain(evsel, opts, param);
}
static void
perf_evsel__reset_callgraph(struct evsel *evsel,
struct callchain_param *param)
{
struct perf_event_attr *attr = &evsel->core.attr;
perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
if (param->record_mode == CALLCHAIN_LBR) {
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK);
}
if (param->record_mode == CALLCHAIN_DWARF) {
perf_evsel__reset_sample_bit(evsel, REGS_USER);
perf_evsel__reset_sample_bit(evsel, STACK_USER);
}
}
static void apply_config_terms(struct evsel *evsel,
struct record_opts *opts, bool track)
{
struct perf_evsel_config_term *term;
struct list_head *config_terms = &evsel->config_terms;
struct perf_event_attr *attr = &evsel->core.attr;
/* callgraph default */
struct callchain_param param = {
.record_mode = callchain_param.record_mode,
};
u32 dump_size = 0;
int max_stack = 0;
const char *callgraph_buf = NULL;
list_for_each_entry(term, config_terms, list) {
switch (term->type) {
case PERF_EVSEL__CONFIG_TERM_PERIOD:
if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
attr->sample_period = term->val.period;
attr->freq = 0;
perf_evsel__reset_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_FREQ:
if (!(term->weak && opts->user_freq != UINT_MAX)) {
attr->sample_freq = term->val.freq;
attr->freq = 1;
perf_evsel__set_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_TIME:
if (term->val.time)
perf_evsel__set_sample_bit(evsel, TIME);
else
perf_evsel__reset_sample_bit(evsel, TIME);
break;
case PERF_EVSEL__CONFIG_TERM_CALLGRAPH:
callgraph_buf = term->val.callgraph;
break;
case PERF_EVSEL__CONFIG_TERM_BRANCH:
if (term->val.branch && strcmp(term->val.branch, "no")) {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
parse_branch_str(term->val.branch,
&attr->branch_sample_type);
} else
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
break;
case PERF_EVSEL__CONFIG_TERM_STACK_USER:
dump_size = term->val.stack_user;
break;
case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
max_stack = term->val.max_stack;
break;
case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
evsel->max_events = term->val.max_events;
break;
case PERF_EVSEL__CONFIG_TERM_INHERIT:
/*
* attr->inherit should has already been set by
* perf_evsel__config. If user explicitly set
* inherit using config terms, override global
* opt->no_inherit setting.
*/
attr->inherit = term->val.inherit ? 1 : 0;
break;
case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
attr->write_backward = term->val.overwrite ? 1 : 0;
break;
case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
break;
case PERF_EVSEL__CONFIG_TERM_PERCORE:
break;
case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT:
attr->aux_output = term->val.aux_output ? 1 : 0;
break;
default:
break;
}
}
/* User explicitly set per-event callgraph, clear the old setting and reset. */
if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
bool sample_address = false;
if (max_stack) {
param.max_stack = max_stack;
if (callgraph_buf == NULL)
callgraph_buf = "fp";
}
/* parse callgraph parameters */
if (callgraph_buf != NULL) {
if (!strcmp(callgraph_buf, "no")) {
param.enabled = false;
param.record_mode = CALLCHAIN_NONE;
} else {
param.enabled = true;
if (parse_callchain_record(callgraph_buf, ¶m)) {
pr_err("per-event callgraph setting for %s failed. "
"Apply callgraph global setting for it\n",
evsel->name);
return;
}
if (param.record_mode == CALLCHAIN_DWARF)
sample_address = true;
}
}
if (dump_size > 0) {
dump_size = round_up(dump_size, sizeof(u64));
param.dump_size = dump_size;
}
/* If global callgraph set, clear it */
if (callchain_param.enabled)
perf_evsel__reset_callgraph(evsel, &callchain_param);
/* set perf-event callgraph */
if (param.enabled) {
if (sample_address) {
perf_evsel__set_sample_bit(evsel, ADDR);
perf_evsel__set_sample_bit(evsel, DATA_SRC);
evsel->core.attr.mmap_data = track;
}
perf_evsel__config_callchain(evsel, opts, ¶m);
}
}
}
static bool is_dummy_event(struct evsel *evsel)
{
return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
(evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
}
/*
* The enable_on_exec/disabled value strategy:
*
* 1) For any type of traced program:
* - all independent events and group leaders are disabled
* - all group members are enabled
*
* Group members are ruled by group leaders. They need to
* be enabled, because the group scheduling relies on that.
*
* 2) For traced programs executed by perf:
* - all independent events and group leaders have
* enable_on_exec set
* - we don't specifically enable or disable any event during
* the record command
*
* Independent events and group leaders are initially disabled
* and get enabled by exec. Group members are ruled by group
* leaders as stated in 1).
*
* 3) For traced programs attached by perf (pid/tid):
* - we specifically enable or disable all events during
* the record command
*
* When attaching events to already running traced we
* enable/disable events specifically, as there's no
* initial traced exec call.
*/
void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
struct callchain_param *callchain)
{
struct evsel *leader = evsel->leader;
struct perf_event_attr *attr = &evsel->core.attr;
int track = evsel->tracking;
bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
attr->inherit = !opts->no_inherit;
attr->write_backward = opts->overwrite ? 1 : 0;
perf_evsel__set_sample_bit(evsel, IP);
perf_evsel__set_sample_bit(evsel, TID);
if (evsel->sample_read) {
perf_evsel__set_sample_bit(evsel, READ);
/*
* We need ID even in case of single event, because
* PERF_SAMPLE_READ process ID specific data.
*/
perf_evsel__set_sample_id(evsel, false);
/*
* Apply group format only if we belong to group
* with more than one members.
*/
if (leader->core.nr_members > 1) {
attr->read_format |= PERF_FORMAT_GROUP;
attr->inherit = 0;
}
}
/*
* We default some events to have a default interval. But keep
* it a weak assumption overridable by the user.
*/
if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
opts->user_interval != ULLONG_MAX)) {
if (opts->freq) {
perf_evsel__set_sample_bit(evsel, PERIOD);
attr->freq = 1;
attr->sample_freq = opts->freq;
} else {
attr->sample_period = opts->default_interval;
}
}
/*
* Disable sampling for all group members other
* than leader in case leader 'leads' the sampling.
*/
if ((leader != evsel) && leader->sample_read) {
attr->freq = 0;
attr->sample_freq = 0;
attr->sample_period = 0;
attr->write_backward = 0;
/*
* We don't get sample for slave events, we make them
* when delivering group leader sample. Set the slave
* event to follow the master sample_type to ease up
* report.
*/
attr->sample_type = leader->core.attr.sample_type;
}
if (opts->no_samples)
attr->sample_freq = 0;
if (opts->inherit_stat) {
evsel->core.attr.read_format |=
PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING |
PERF_FORMAT_ID;
attr->inherit_stat = 1;
}
if (opts->sample_address) {
perf_evsel__set_sample_bit(evsel, ADDR);
attr->mmap_data = track;
}
/*
* We don't allow user space callchains for function trace
* event, due to issues with page faults while tracing page
* fault handler and its overall trickiness nature.
*/
if (perf_evsel__is_function_event(evsel))
evsel->core.attr.exclude_callchain_user = 1;
if (callchain && callchain->enabled && !evsel->no_aux_samples)
perf_evsel__config_callchain(evsel, opts, callchain);
if (opts->sample_intr_regs) {
attr->sample_regs_intr = opts->sample_intr_regs;
perf_evsel__set_sample_bit(evsel, REGS_INTR);
}
if (opts->sample_user_regs) {
attr->sample_regs_user |= opts->sample_user_regs;
perf_evsel__set_sample_bit(evsel, REGS_USER);
}
if (target__has_cpu(&opts->target) || opts->sample_cpu)
perf_evsel__set_sample_bit(evsel, CPU);
/*
* When the user explicitly disabled time don't force it here.
*/
if (opts->sample_time &&
(!perf_missing_features.sample_id_all &&
(!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu ||
opts->sample_time_set)))
perf_evsel__set_sample_bit(evsel, TIME);
if (opts->raw_samples && !evsel->no_aux_samples) {
perf_evsel__set_sample_bit(evsel, TIME);
perf_evsel__set_sample_bit(evsel, RAW);
perf_evsel__set_sample_bit(evsel, CPU);
}
if (opts->sample_address)
perf_evsel__set_sample_bit(evsel, DATA_SRC);
if (opts->sample_phys_addr)
perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
if (opts->no_buffering) {
attr->watermark = 0;
attr->wakeup_events = 1;
}
if (opts->branch_stack && !evsel->no_aux_samples) {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = opts->branch_stack;
}
if (opts->sample_weight)
perf_evsel__set_sample_bit(evsel, WEIGHT);
attr->task = track;
attr->mmap = track;
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
attr->ksymbol = track && !perf_missing_features.ksymbol;
attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf;
if (opts->record_namespaces)
attr->namespaces = track;
if (opts->record_switch_events)
attr->context_switch = track;
if (opts->sample_transaction)
perf_evsel__set_sample_bit(evsel, TRANSACTION);
if (opts->running_time) {
evsel->core.attr.read_format |=
PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
}
/*
* XXX see the function comment above
*
* Disabling only independent events or group leaders,
* keeping group members enabled.
*/
if (perf_evsel__is_group_leader(evsel))
attr->disabled = 1;
/*
* Setting enable_on_exec for independent events and
* group leaders for traced executed by perf.
*/
if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
!opts->initial_delay)
attr->enable_on_exec = 1;
if (evsel->immediate) {
attr->disabled = 0;
attr->enable_on_exec = 0;
}
clockid = opts->clockid;
if (opts->use_clockid) {
attr->use_clockid = 1;
attr->clockid = opts->clockid;
}
if (evsel->precise_max)
attr->precise_ip = 3;
if (opts->all_user) {
attr->exclude_kernel = 1;
attr->exclude_user = 0;
}
if (opts->all_kernel) {
attr->exclude_kernel = 0;
attr->exclude_user = 1;
}
if (evsel->core.own_cpus || evsel->unit)
evsel->core.attr.read_format |= PERF_FORMAT_ID;
/*
* Apply event specific term settings,
* it overloads any global configuration.
*/
apply_config_terms(evsel, opts, track);
evsel->ignore_missing_thread = opts->ignore_missing_thread;
/* The --period option takes the precedence. */
if (opts->period_set) {
if (opts->period)
perf_evsel__set_sample_bit(evsel, PERIOD);
else
perf_evsel__reset_sample_bit(evsel, PERIOD);
}
/*
* For initial_delay, a dummy event is added implicitly.
* The software event will trigger -EOPNOTSUPP error out,
* if BRANCH_STACK bit is set.
*/
if (opts->initial_delay && is_dummy_event(evsel))
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
}
int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
{
char *new_filter = strdup(filter);
if (new_filter != NULL) {
free(evsel->filter);
evsel->filter = new_filter;
return 0;
}
return -1;
}
static int perf_evsel__append_filter(struct evsel *evsel,
const char *fmt, const char *filter)
{
char *new_filter;
if (evsel->filter == NULL)
return perf_evsel__set_filter(evsel, filter);
if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) {
free(evsel->filter);
evsel->filter = new_filter;
return 0;
}
return -1;
}
int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter)
{
return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
}
int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
{
return perf_evsel__append_filter(evsel, "%s,%s", filter);
}
int evsel__enable(struct evsel *evsel)
{
int err = perf_evsel__enable(&evsel->core);
if (!err)
evsel->disabled = false;
return err;
}
int evsel__disable(struct evsel *evsel)
{
int err = perf_evsel__disable(&evsel->core);
/*
* We mark it disabled here so that tools that disable a event can
* ignore events after they disable it. I.e. the ring buffer may have
* already a few more events queued up before the kernel got the stop
* request.
*/
if (!err)
evsel->disabled = true;
return err;
}
int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads)
{
if (ncpus == 0 || nthreads == 0)
return 0;
if (evsel->core.system_wide)
nthreads = 1;
evsel->core.sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
if (evsel->core.sample_id == NULL)
return -ENOMEM;
evsel->core.id = zalloc(ncpus * nthreads * sizeof(u64));
if (evsel->core.id == NULL) {
xyarray__delete(evsel->core.sample_id);
evsel->core.sample_id = NULL;
return -ENOMEM;
}
return 0;
}
static void perf_evsel__free_id(struct evsel *evsel)
{
xyarray__delete(evsel->core.sample_id);
evsel->core.sample_id = NULL;
zfree(&evsel->core.id);
evsel->ids = 0;
}
static void perf_evsel__free_config_terms(struct evsel *evsel)
{
struct perf_evsel_config_term *term, *h;
list_for_each_entry_safe(term, h, &evsel->config_terms, list) {
list_del_init(&term->list);
free(term);
}
}
void perf_evsel__exit(struct evsel *evsel)
{
assert(list_empty(&evsel->core.node));
assert(evsel->evlist == NULL);
perf_evsel__free_counts(evsel);
perf_evsel__free_fd(&evsel->core);
perf_evsel__free_id(evsel);
perf_evsel__free_config_terms(evsel);
cgroup__put(evsel->cgrp);
perf_cpu_map__put(evsel->core.cpus);
perf_cpu_map__put(evsel->core.own_cpus);
perf_thread_map__put(evsel->core.threads);
zfree(&evsel->group_name);
zfree(&evsel->name);
perf_evsel__object.fini(evsel);
}
void evsel__delete(struct evsel *evsel)
{
perf_evsel__exit(evsel);
free(evsel);
}
void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values tmp;
if (!evsel->prev_raw_counts)
return;
if (cpu == -1) {
tmp = evsel->prev_raw_counts->aggr;
evsel->prev_raw_counts->aggr = *count;
} else {
tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
}
count->val = count->val - tmp.val;
count->ena = count->ena - tmp.ena;
count->run = count->run - tmp.run;
}
void perf_counts_values__scale(struct perf_counts_values *count,
bool scale, s8 *pscaled)
{
s8 scaled = 0;
if (scale) {
if (count->run == 0) {
scaled = -1;
count->val = 0;
} else if (count->run < count->ena) {
scaled = 1;
count->val = (u64)((double) count->val * count->ena / count->run);
}
}
if (pscaled)
*pscaled = scaled;
}
static int
perf_evsel__read_one(struct evsel *evsel, int cpu, int thread)
{
struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
return perf_evsel__read(&evsel->core, cpu, thread, count);
}
static void
perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
u64 val, u64 ena, u64 run)
{
struct perf_counts_values *count;
count = perf_counts(counter->counts, cpu, thread);
count->val = val;
count->ena = ena;
count->run = run;
perf_counts__set_loaded(counter->counts, cpu, thread, true);
}
static int
perf_evsel__process_group_data(struct evsel *leader,
int cpu, int thread, u64 *data)
{
u64 read_format = leader->core.attr.read_format;
struct sample_read_value *v;
u64 nr, ena = 0, run = 0, i;
nr = *data++;
if (nr != (u64) leader->core.nr_members)
return -EINVAL;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
ena = *data++;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
run = *data++;
v = (struct sample_read_value *) data;
perf_evsel__set_count(leader, cpu, thread,
v[0].value, ena, run);
for (i = 1; i < nr; i++) {
struct evsel *counter;
counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
if (!counter)
return -EINVAL;
perf_evsel__set_count(counter, cpu, thread,
v[i].value, ena, run);
}
return 0;
}
static int
perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
{
struct perf_stat_evsel *ps = leader->stats;
u64 read_format = leader->core.attr.read_format;
int size = perf_evsel__read_size(&leader->core);
u64 *data = ps->group_data;
if (!(read_format & PERF_FORMAT_ID))
return -EINVAL;
if (!perf_evsel__is_group_leader(leader))
return -EINVAL;
if (!data) {
data = zalloc(size);
if (!data)
return -ENOMEM;
ps->group_data = data;
}
if (FD(leader, cpu, thread) < 0)
return -EINVAL;
if (readn(FD(leader, cpu, thread), data, size) <= 0)
return -errno;
return perf_evsel__process_group_data(leader, cpu, thread, data);
}
int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread)
{
u64 read_format = evsel->core.attr.read_format;
if (read_format & PERF_FORMAT_GROUP)
return perf_evsel__read_group(evsel, cpu, thread);
else
return perf_evsel__read_one(evsel, cpu, thread);
}
int __perf_evsel__read_on_cpu(struct evsel *evsel,
int cpu, int thread, bool scale)
{
struct perf_counts_values count;
size_t nv = scale ? 3 : 1;
if (FD(evsel, cpu, thread) < 0)
return -EINVAL;
if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
return -ENOMEM;
if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
perf_evsel__compute_deltas(evsel, cpu, thread, &count);
perf_counts_values__scale(&count, scale, NULL);
*perf_counts(evsel->counts, cpu, thread) = count;
return 0;
}
static int get_group_fd(struct evsel *evsel, int cpu, int thread)
{
struct evsel *leader = evsel->leader;
int fd;
if (perf_evsel__is_group_leader(evsel))
return -1;
/*
* Leader must be already processed/open,
* if not it's a bug.
*/
BUG_ON(!leader->core.fd);
fd = FD(leader, cpu, thread);
BUG_ON(fd == -1);
return fd;
}
struct bit_names {
int bit;
const char *name;
};
static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
{
bool first_bit = true;
int i = 0;
do {
if (value & bits[i].bit) {
buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
first_bit = false;
}
} while (bits[++i].name != NULL);
}
static void __p_sample_type(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_SAMPLE_##n, #n }
struct bit_names bits[] = {
bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
bit_name(WEIGHT), bit_name(PHYS_ADDR),
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
static void __p_branch_sample_type(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
struct bit_names bits[] = {
bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
static void __p_read_format(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_FORMAT_##n, #n }
struct bit_names bits[] = {
bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
bit_name(ID), bit_name(GROUP),
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
#define BUF_SIZE 1024
#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val)
#define PRINT_ATTRn(_n, _f, _p) \
do { \
if (attr->_f) { \
_p(attr->_f); \
ret += attr__fprintf(fp, _n, buf, priv);\
} \
} while (0)
#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p)
int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
attr__fprintf_f attr__fprintf, void *priv)
{
char buf[BUF_SIZE];
int ret = 0;
PRINT_ATTRf(type, p_unsigned);
PRINT_ATTRf(size, p_unsigned);
PRINT_ATTRf(config, p_hex);
PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
PRINT_ATTRf(sample_type, p_sample_type);
PRINT_ATTRf(read_format, p_read_format);
PRINT_ATTRf(disabled, p_unsigned);
PRINT_ATTRf(inherit, p_unsigned);
PRINT_ATTRf(pinned, p_unsigned);
PRINT_ATTRf(exclusive, p_unsigned);
PRINT_ATTRf(exclude_user, p_unsigned);
PRINT_ATTRf(exclude_kernel, p_unsigned);
PRINT_ATTRf(exclude_hv, p_unsigned);
PRINT_ATTRf(exclude_idle, p_unsigned);
PRINT_ATTRf(mmap, p_unsigned);
PRINT_ATTRf(comm, p_unsigned);
PRINT_ATTRf(freq, p_unsigned);
PRINT_ATTRf(inherit_stat, p_unsigned);
PRINT_ATTRf(enable_on_exec, p_unsigned);
PRINT_ATTRf(task, p_unsigned);
PRINT_ATTRf(watermark, p_unsigned);
PRINT_ATTRf(precise_ip, p_unsigned);
PRINT_ATTRf(mmap_data, p_unsigned);
PRINT_ATTRf(sample_id_all, p_unsigned);
PRINT_ATTRf(exclude_host, p_unsigned);
PRINT_ATTRf(exclude_guest, p_unsigned);
PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
PRINT_ATTRf(exclude_callchain_user, p_unsigned);
PRINT_ATTRf(mmap2, p_unsigned);
PRINT_ATTRf(comm_exec, p_unsigned);
PRINT_ATTRf(use_clockid, p_unsigned);
PRINT_ATTRf(context_switch, p_unsigned);
PRINT_ATTRf(write_backward, p_unsigned);
PRINT_ATTRf(namespaces, p_unsigned);
PRINT_ATTRf(ksymbol, p_unsigned);
PRINT_ATTRf(bpf_event, p_unsigned);
PRINT_ATTRf(aux_output, p_unsigned);
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
PRINT_ATTRf(bp_type, p_unsigned);
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
PRINT_ATTRf(sample_regs_user, p_hex);
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
PRINT_ATTRf(aux_watermark, p_unsigned);
PRINT_ATTRf(sample_max_stack, p_unsigned);
return ret;
}
static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
void *priv __maybe_unused)
{
return fprintf(fp, " %-32s %s\n", name, val);
}
static void perf_evsel__remove_fd(struct evsel *pos,
int nr_cpus, int nr_threads,
int thread_idx)
{
for (int cpu = 0; cpu < nr_cpus; cpu++)
for (int thread = thread_idx; thread < nr_threads - 1; thread++)
FD(pos, cpu, thread) = FD(pos, cpu, thread + 1);
}
static int update_fds(struct evsel *evsel,
int nr_cpus, int cpu_idx,
int nr_threads, int thread_idx)
{
struct evsel *pos;
if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
return -EINVAL;
evlist__for_each_entry(evsel->evlist, pos) {
nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
/*
* Since fds for next evsel has not been created,
* there is no need to iterate whole event list.
*/
if (pos == evsel)
break;
}
return 0;
}
static bool ignore_missing_thread(struct evsel *evsel,
int nr_cpus, int cpu,
struct perf_thread_map *threads,
int thread, int err)
{
pid_t ignore_pid = perf_thread_map__pid(threads, thread);
if (!evsel->ignore_missing_thread)
return false;
/* The system wide setup does not work with threads. */
if (evsel->core.system_wide)
return false;
/* The -ESRCH is perf event syscall errno for pid's not found. */
if (err != -ESRCH)
return false;
/* If there's only one thread, let it fail. */
if (threads->nr == 1)
return false;
/*
* We should remove fd for missing_thread first
* because thread_map__remove() will decrease threads->nr.
*/
if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
return false;
if (thread_map__remove(threads, thread))
return false;
pr_warning("WARNING: Ignored open failure for pid %d\n",
ignore_pid);
return true;
}
static void display_attr(struct perf_event_attr *attr)
{
if (verbose >= 2) {
fprintf(stderr, "%.60s\n", graph_dotted_line);
fprintf(stderr, "perf_event_attr:\n");
perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
fprintf(stderr, "%.60s\n", graph_dotted_line);
}
}
static int perf_event_open(struct evsel *evsel,
pid_t pid, int cpu, int group_fd,
unsigned long flags)
{
int precise_ip = evsel->core.attr.precise_ip;
int fd;
while (1) {
pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
pid, cpu, group_fd, flags);
fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, group_fd, flags);
if (fd >= 0)
break;
/* Do not try less precise if not requested. */
if (!evsel->precise_max)
break;
/*
* We tried all the precise_ip values, and it's
* still failing, so leave it to standard fallback.
*/
if (!evsel->core.attr.precise_ip) {
evsel->core.attr.precise_ip = precise_ip;
break;
}
pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
evsel->core.attr.precise_ip--;
pr_debug2("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip);
display_attr(&evsel->core.attr);
}
return fd;
}
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads)
{
int cpu, thread, nthreads;
unsigned long flags = PERF_FLAG_FD_CLOEXEC;
int pid = -1, err;
enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
(perf_missing_features.aux_output && evsel->core.attr.aux_output))
return -EINVAL;
if (cpus == NULL) {
static struct perf_cpu_map *empty_cpu_map;
if (empty_cpu_map == NULL) {
empty_cpu_map = perf_cpu_map__dummy_new();
if (empty_cpu_map == NULL)
return -ENOMEM;
}
cpus = empty_cpu_map;
}
if (threads == NULL) {
static struct perf_thread_map *empty_thread_map;
if (empty_thread_map == NULL) {
empty_thread_map = thread_map__new_by_tid(-1);
if (empty_thread_map == NULL)
return -ENOMEM;
}
threads = empty_thread_map;
}
if (evsel->core.system_wide)
nthreads = 1;
else
nthreads = threads->nr;
if (evsel->core.fd == NULL &&
perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0)
return -ENOMEM;
if (evsel->cgrp) {
flags |= PERF_FLAG_PID_CGROUP;
pid = evsel->cgrp->fd;
}
fallback_missing_features:
if (perf_missing_features.clockid_wrong)
evsel->core.attr.clockid = CLOCK_MONOTONIC; /* should always work */
if (perf_missing_features.clockid) {
evsel->core.attr.use_clockid = 0;
evsel->core.attr.clockid = 0;
}
if (perf_missing_features.cloexec)
flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
if (perf_missing_features.mmap2)
evsel->core.attr.mmap2 = 0;
if (perf_missing_features.exclude_guest)
evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
if (perf_missing_features.lbr_flags)
evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
PERF_SAMPLE_BRANCH_NO_CYCLES);
if (perf_missing_features.group_read && evsel->core.attr.inherit)
evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
if (perf_missing_features.ksymbol)
evsel->core.attr.ksymbol = 0;
if (perf_missing_features.bpf)
evsel->core.attr.bpf_event = 0;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->core.attr.sample_id_all = 0;
display_attr(&evsel->core.attr);
for (cpu = 0; cpu < cpus->nr; cpu++) {
for (thread = 0; thread < nthreads; thread++) {
int fd, group_fd;
if (!evsel->cgrp && !evsel->core.system_wide)
pid = perf_thread_map__pid(threads, thread);
group_fd = get_group_fd(evsel, cpu, thread);
retry_open:
test_attr__ready();
fd = perf_event_open(evsel, pid, cpus->map[cpu],
group_fd, flags);
FD(evsel, cpu, thread) = fd;
if (fd < 0) {
err = -errno;
if (ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
/*
* We just removed 1 thread, so take a step
* back on thread index and lower the upper
* nthreads limit.
*/
nthreads--;
thread--;
/* ... and pretend like nothing have happened. */
err = 0;
continue;
}
pr_debug2("\nsys_perf_event_open failed, error %d\n",
err);
goto try_fallback;
}
pr_debug2(" = %d\n", fd);
if (evsel->bpf_fd >= 0) {
int evt_fd = fd;
int bpf_fd = evsel->bpf_fd;
err = ioctl(evt_fd,
PERF_EVENT_IOC_SET_BPF,
bpf_fd);
if (err && errno != EEXIST) {
pr_err("failed to attach bpf fd %d: %s\n",
bpf_fd, strerror(errno));
err = -EINVAL;
goto out_close;
}
}
set_rlimit = NO_CHANGE;
/*
* If we succeeded but had to kill clockid, fail and
* have perf_evsel__open_strerror() print us a nice
* error.
*/
if (perf_missing_features.clockid ||
perf_missing_features.clockid_wrong) {
err = -EINVAL;
goto out_close;
}
}
}
return 0;
try_fallback:
/*
* perf stat needs between 5 and 22 fds per CPU. When we run out
* of them try to increase the limits.
*/
if (err == -EMFILE && set_rlimit < INCREASED_MAX) {
struct rlimit l;
int old_errno = errno;
if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
if (set_rlimit == NO_CHANGE)
l.rlim_cur = l.rlim_max;
else {
l.rlim_cur = l.rlim_max + 1000;
l.rlim_max = l.rlim_cur;
}
if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
set_rlimit++;
errno = old_errno;
goto retry_open;
}
}
errno = old_errno;
}
if (err != -EINVAL || cpu > 0 || thread > 0)
goto out_close;
/*
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
perf_missing_features.aux_output = true;
pr_debug2("Kernel has no attr.aux_output support, bailing out\n");
goto out_close;
} else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) {
perf_missing_features.bpf = true;
pr_debug2("switching off bpf_event\n");
goto fallback_missing_features;
} else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) {
perf_missing_features.ksymbol = true;
pr_debug2("switching off ksymbol\n");
goto fallback_missing_features;
} else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) {
perf_missing_features.write_backward = true;
pr_debug2("switching off write_backward\n");
goto out_close;
} else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) {
perf_missing_features.clockid_wrong = true;
pr_debug2("switching off clockid\n");
goto fallback_missing_features;
} else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) {
perf_missing_features.clockid = true;
pr_debug2("switching off use_clockid\n");
goto fallback_missing_features;
} else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
perf_missing_features.cloexec = true;
pr_debug2("switching off cloexec flag\n");
goto fallback_missing_features;
} else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) {
perf_missing_features.mmap2 = true;
pr_debug2("switching off mmap2\n");
goto fallback_missing_features;
} else if (!perf_missing_features.exclude_guest &&
(evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
perf_missing_features.exclude_guest = true;
pr_debug2("switching off exclude_guest, exclude_host\n");
goto fallback_missing_features;
} else if (!perf_missing_features.sample_id_all) {
perf_missing_features.sample_id_all = true;
pr_debug2("switching off sample_id_all\n");
goto retry_sample_id;
} else if (!perf_missing_features.lbr_flags &&
(evsel->core.attr.branch_sample_type &
(PERF_SAMPLE_BRANCH_NO_CYCLES |
PERF_SAMPLE_BRANCH_NO_FLAGS))) {
perf_missing_features.lbr_flags = true;
pr_debug2("switching off branch sample type no (cycles/flags)\n");
goto fallback_missing_features;
} else if (!perf_missing_features.group_read &&
evsel->core.attr.inherit &&
(evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
perf_evsel__is_group_leader(evsel)) {
perf_missing_features.group_read = true;
pr_debug2("switching off group read\n");
goto fallback_missing_features;
}
out_close:
if (err)
threads->err_thread = thread;
do {
while (--thread >= 0) {
close(FD(evsel, cpu, thread));
FD(evsel, cpu, thread) = -1;
}
thread = nthreads;
} while (--cpu >= 0);
return err;
}
void evsel__close(struct evsel *evsel)
{
perf_evsel__close(&evsel->core);
perf_evsel__free_id(evsel);
}
int perf_evsel__open_per_cpu(struct evsel *evsel,
struct perf_cpu_map *cpus)
{
return evsel__open(evsel, cpus, NULL);
}
int perf_evsel__open_per_thread(struct evsel *evsel,
struct perf_thread_map *threads)
{
return evsel__open(evsel, NULL, threads);
}
static int perf_evsel__parse_id_sample(const struct evsel *evsel,
const union perf_event *event,
struct perf_sample *sample)
{
u64 type = evsel->core.attr.sample_type;
const __u64 *array = event->sample.array;
bool swapped = evsel->needs_swap;
union u64_swap u;
array += ((event->header.size -
sizeof(event->header)) / sizeof(u64)) - 1;
if (type & PERF_SAMPLE_IDENTIFIER) {
sample->id = *array;
array--;
}
if (type & PERF_SAMPLE_CPU) {
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
}
sample->cpu = u.val32[0];
array--;
}
if (type & PERF_SAMPLE_STREAM_ID) {
sample->stream_id = *array;
array--;
}
if (type & PERF_SAMPLE_ID) {
sample->id = *array;
array--;
}
if (type & PERF_SAMPLE_TIME) {
sample->time = *array;
array--;
}
if (type & PERF_SAMPLE_TID) {
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
sample->pid = u.val32[0];
sample->tid = u.val32[1];
array--;
}
return 0;
}
static inline bool overflow(const void *endp, u16 max_size, const void *offset,
u64 size)
{
return size > max_size || offset + size > endp;
}
#define OVERFLOW_CHECK(offset, size, max_size) \
do { \
if (overflow(endp, (max_size), (offset), (size))) \
return -EFAULT; \
} while (0)
#define OVERFLOW_CHECK_u64(offset) \
OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
static int
perf_event__check_size(union perf_event *event, unsigned int sample_size)
{
/*
* The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
* up to PERF_SAMPLE_PERIOD. After that overflow() must be used to
* check the format does not go past the end of the event.
*/
if (sample_size + sizeof(event->header) > event->header.size)
return -EFAULT;
return 0;
}
int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
struct perf_sample *data)
{
u64 type = evsel->core.attr.sample_type;
bool swapped = evsel->needs_swap;
const __u64 *array;
u16 max_size = event->header.size;
const void *endp = (void *)event + max_size;
u64 sz;
/*
* used for cross-endian analysis. See git commit 65014ab3
* for why this goofiness is needed.
*/
union u64_swap u;
memset(data, 0, sizeof(*data));
data->cpu = data->pid = data->tid = -1;
data->stream_id = data->id = data->time = -1ULL;
data->period = evsel->core.attr.sample_period;
data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
data->misc = event->header.misc;
data->id = -1ULL;
data->data_src = PERF_MEM_DATA_SRC_NONE;
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!evsel->core.attr.sample_id_all)
return 0;
return perf_evsel__parse_id_sample(evsel, event, data);
}
array = event->sample.array;
if (perf_event__check_size(event, evsel->sample_size))
return -EFAULT;
if (type & PERF_SAMPLE_IDENTIFIER) {
data->id = *array;
array++;
}
if (type & PERF_SAMPLE_IP) {
data->ip = *array;
array++;
}
if (type & PERF_SAMPLE_TID) {
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
data->pid = u.val32[0];
data->tid = u.val32[1];
array++;
}
if (type & PERF_SAMPLE_TIME) {
data->time = *array;
array++;
}
if (type & PERF_SAMPLE_ADDR) {
data->addr = *array;
array++;
}
if (type & PERF_SAMPLE_ID) {
data->id = *array;
array++;
}
if (type & PERF_SAMPLE_STREAM_ID) {
data->stream_id = *array;
array++;
}
if (type & PERF_SAMPLE_CPU) {
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
}
data->cpu = u.val32[0];
array++;
}
if (type & PERF_SAMPLE_PERIOD) {
data->period = *array;
array++;
}
if (type & PERF_SAMPLE_READ) {
u64 read_format = evsel->core.attr.read_format;
OVERFLOW_CHECK_u64(array);
if (read_format & PERF_FORMAT_GROUP)
data->read.group.nr = *array;
else
data->read.one.value = *array;
array++;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
OVERFLOW_CHECK_u64(array);
data->read.time_enabled = *array;
array++;
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
OVERFLOW_CHECK_u64(array);
data->read.time_running = *array;
array++;
}
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
const u64 max_group_nr = UINT64_MAX /
sizeof(struct sample_read_value);
if (data->read.group.nr > max_group_nr)
return -EFAULT;
sz = data->read.group.nr *
sizeof(struct sample_read_value);
OVERFLOW_CHECK(array, sz, max_size);
data->read.group.values =
(struct sample_read_value *)array;
array = (void *)array + sz;
} else {
OVERFLOW_CHECK_u64(array);
data->read.one.id = *array;
array++;
}
}
if (evsel__has_callchain(evsel)) {
const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
OVERFLOW_CHECK_u64(array);
data->callchain = (struct ip_callchain *)array++;
if (data->callchain->nr > max_callchain_nr)
return -EFAULT;
sz = data->callchain->nr * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_RAW) {
OVERFLOW_CHECK_u64(array);
u.val64 = *array;
/*
* Undo swap of u64, then swap on individual u32s,
* get the size of the raw area and undo all of the
* swap. The pevent interface handles endianity by
* itself.
*/
if (swapped) {
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
data->raw_size = u.val32[0];
/*
* The raw data is aligned on 64bits including the
* u32 size, so it's safe to use mem_bswap_64.
*/
if (swapped)
mem_bswap_64((void *) array, data->raw_size);
array = (void *)array + sizeof(u32);
OVERFLOW_CHECK(array, data->raw_size, max_size);
data->raw_data = (void *)array;
array = (void *)array + data->raw_size;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
const u64 max_branch_nr = UINT64_MAX /
sizeof(struct branch_entry);
OVERFLOW_CHECK_u64(array);
data->branch_stack = (struct branch_stack *)array++;
if (data->branch_stack->nr > max_branch_nr)
return -EFAULT;
sz = data->branch_stack->nr * sizeof(struct branch_entry);
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_REGS_USER) {
OVERFLOW_CHECK_u64(array);
data->user_regs.abi = *array;
array++;
if (data->user_regs.abi) {
u64 mask = evsel->core.attr.sample_regs_user;
sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->user_regs.mask = mask;
data->user_regs.regs = (u64 *)array;
array = (void *)array + sz;
}
}
if (type & PERF_SAMPLE_STACK_USER) {
OVERFLOW_CHECK_u64(array);
sz = *array++;
data->user_stack.offset = ((char *)(array - 1)
- (char *) event);
if (!sz) {
data->user_stack.size = 0;
} else {
OVERFLOW_CHECK(array, sz, max_size);
data->user_stack.data = (char *)array;
array = (void *)array + sz;
OVERFLOW_CHECK_u64(array);
data->user_stack.size = *array++;
if (WARN_ONCE(data->user_stack.size > sz,
"user stack dump failure\n"))
return -EFAULT;
}
}
if (type & PERF_SAMPLE_WEIGHT) {
OVERFLOW_CHECK_u64(array);
data->weight = *array;
array++;
}
if (type & PERF_SAMPLE_DATA_SRC) {
OVERFLOW_CHECK_u64(array);
data->data_src = *array;
array++;
}
if (type & PERF_SAMPLE_TRANSACTION) {
OVERFLOW_CHECK_u64(array);
data->transaction = *array;
array++;
}
data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
if (type & PERF_SAMPLE_REGS_INTR) {
OVERFLOW_CHECK_u64(array);
data->intr_regs.abi = *array;
array++;
if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
u64 mask = evsel->core.attr.sample_regs_intr;
sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->intr_regs.mask = mask;
data->intr_regs.regs = (u64 *)array;
array = (void *)array + sz;
}
}
data->phys_addr = 0;
if (type & PERF_SAMPLE_PHYS_ADDR) {
data->phys_addr = *array;
array++;
}
return 0;
}
int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
union perf_event *event,
u64 *timestamp)
{
u64 type = evsel->core.attr.sample_type;
const __u64 *array;
if (!(type & PERF_SAMPLE_TIME))
return -1;
if (event->header.type != PERF_RECORD_SAMPLE) {
struct perf_sample data = {
.time = -1ULL,
};
if (!evsel->core.attr.sample_id_all)
return -1;
if (perf_evsel__parse_id_sample(evsel, event, &data))
return -1;
*timestamp = data.time;
return 0;
}
array = event->sample.array;
if (perf_event__check_size(event, evsel->sample_size))
return -EFAULT;
if (type & PERF_SAMPLE_IDENTIFIER)
array++;
if (type & PERF_SAMPLE_IP)
array++;
if (type & PERF_SAMPLE_TID)
array++;
if (type & PERF_SAMPLE_TIME)
*timestamp = *array;
return 0;
}
struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name)
{
return tep_find_field(evsel->tp_format, name);
}
void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
const char *name)
{
struct tep_format_field *field = perf_evsel__field(evsel, name);
int offset;
if (!field)
return NULL;
offset = field->offset;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
offset = *(int *)(sample->raw_data + field->offset);
offset &= 0xffff;
}
return sample->raw_data + offset;
}
u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
bool needs_swap)
{
u64 value;
void *ptr = sample->raw_data + field->offset;
switch (field->size) {
case 1:
return *(u8 *)ptr;
case 2:
value = *(u16 *)ptr;
break;
case 4:
value = *(u32 *)ptr;
break;
case 8:
memcpy(&value, ptr, sizeof(u64));
break;
default:
return 0;
}
if (!needs_swap)
return value;
switch (field->size) {
case 2:
return bswap_16(value);
case 4:
return bswap_32(value);
case 8:
return bswap_64(value);
default:
return 0;
}
return 0;
}
u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
const char *name)
{
struct tep_format_field *field = perf_evsel__field(evsel, name);
if (!field)
return 0;
return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
}
bool perf_evsel__fallback(struct evsel *evsel, int err,
char *msg, size_t msgsize)
{
int paranoid;
if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
evsel->core.attr.type == PERF_TYPE_HARDWARE &&
evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) {
/*
* If it's cycles then fall back to hrtimer based
* cpu-clock-tick sw counter, which is always available even if
* no PMU support.
*
* PPC returns ENXIO until 2.6.37 (behavior changed with commit
* b0a873e).
*/
scnprintf(msg, msgsize, "%s",
"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
evsel->core.attr.type = PERF_TYPE_SOFTWARE;
evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK;
zfree(&evsel->name);
return true;
} else if (err == EACCES && !evsel->core.attr.exclude_kernel &&
(paranoid = perf_event_paranoid()) > 1) {
const char *name = perf_evsel__name(evsel);
char *new_name;
const char *sep = ":";
/* Is there already the separator in the name. */
if (strchr(name, '/') ||
strchr(name, ':'))
sep = "";
if (asprintf(&new_name, "%s%su", name, sep) < 0)
return false;
if (evsel->name)
free(evsel->name);
evsel->name = new_name;
scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying "
"to fall back to excluding kernel and hypervisor "
" samples", paranoid);
evsel->core.attr.exclude_kernel = 1;
evsel->core.attr.exclude_hv = 1;
return true;
}
return false;
}
static bool find_process(const char *name)
{
size_t len = strlen(name);
DIR *dir;
struct dirent *d;
int ret = -1;
dir = opendir(procfs__mountpoint());
if (!dir)
return false;
/* Walk through the directory. */
while (ret && (d = readdir(dir)) != NULL) {
char path[PATH_MAX];
char *data;
size_t size;
if ((d->d_type != DT_DIR) ||
!strcmp(".", d->d_name) ||
!strcmp("..", d->d_name))
continue;
scnprintf(path, sizeof(path), "%s/%s/comm",
procfs__mountpoint(), d->d_name);
if (filename__read_str(path, &data, &size))
continue;
ret = strncmp(name, data, len);
free(data);
}
closedir(dir);
return ret ? false : true;
}
int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
int err, char *msg, size_t size)
{
char sbuf[STRERR_BUFSIZE];
int printed = 0;
switch (err) {
case EPERM:
case EACCES:
if (err == EPERM)
printed = scnprintf(msg, size,
"No permission to enable %s event.\n\n",
perf_evsel__name(evsel));
return scnprintf(msg + printed, size - printed,
"You may not have permission to collect %sstats.\n\n"
"Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
"which controls use of the performance events system by\n"
"unprivileged users (without CAP_SYS_ADMIN).\n\n"
"The current value is %d:\n\n"
" -1: Allow use of (almost) all events by all users\n"
" Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
"To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
" kernel.perf_event_paranoid = -1\n" ,
target->system_wide ? "system-wide " : "",
perf_event_paranoid());
case ENOENT:
return scnprintf(msg, size, "The %s event is not supported.",
perf_evsel__name(evsel));
case EMFILE:
return scnprintf(msg, size, "%s",
"Too many events are opened.\n"
"Probably the maximum number of open file descriptors has been reached.\n"
"Hint: Try again after reducing the number of events.\n"
"Hint: Try increasing the limit with 'ulimit -n <limit>'");
case ENOMEM:
if (evsel__has_callchain(evsel) &&
access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0)
return scnprintf(msg, size,
"Not enough memory to setup event with callchain.\n"
"Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
"Hint: Current value: %d", sysctl__max_stack());
break;
case ENODEV:
if (target->cpu_list)
return scnprintf(msg, size, "%s",
"No such device - did you specify an out-of-range profile CPU?");
break;
case EOPNOTSUPP:
if (evsel->core.attr.sample_period != 0)
return scnprintf(msg, size,
"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
perf_evsel__name(evsel));
if (evsel->core.attr.precise_ip)
return scnprintf(msg, size, "%s",
"\'precise\' request may not be supported. Try removing 'p' modifier.");
#if defined(__i386__) || defined(__x86_64__)
if (evsel->core.attr.type == PERF_TYPE_HARDWARE)
return scnprintf(msg, size, "%s",
"No hardware sampling interrupt available.\n");
#endif
break;
case EBUSY:
if (find_process("oprofiled"))
return scnprintf(msg, size,
"The PMU counters are busy/taken by another profiler.\n"
"We found oprofile daemon running, please stop it and try again.");
break;
case EINVAL:
if (evsel->core.attr.write_backward && perf_missing_features.write_backward)
return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
if (perf_missing_features.clockid)
return scnprintf(msg, size, "clockid feature not supported.");
if (perf_missing_features.clockid_wrong)
return scnprintf(msg, size, "wrong clockid (%d).", clockid);
if (perf_missing_features.aux_output)
return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
break;
default:
break;
}
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg | grep -i perf may provide additional information.\n",
err, str_error_r(err, sbuf, sizeof(sbuf)),
perf_evsel__name(evsel));
}
struct perf_env *perf_evsel__env(struct evsel *evsel)
{
if (evsel && evsel->evlist)
return evsel->evlist->env;
return NULL;
}
static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
{
int cpu, thread;
for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
thread++) {
int fd = FD(evsel, cpu, thread);
if (perf_evlist__id_add_fd(evlist, evsel,
cpu, thread, fd) < 0)
return -1;
}
}
return 0;
}
int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
{
struct perf_cpu_map *cpus = evsel->core.cpus;
struct perf_thread_map *threads = evsel->core.threads;
if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
return -ENOMEM;
return store_evsel_ids(evsel, evlist);
}
|