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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015-2018 Linaro Limited.
*
* Author: Tor Jeremiassen <tor@ti.com>
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
*/
#include <linux/bitops.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/types.h>
#include <linux/zalloc.h>
#include <opencsd/ocsd_if_types.h>
#include <stdlib.h>
#include "auxtrace.h"
#include "color.h"
#include "cs-etm.h"
#include "cs-etm-decoder/cs-etm-decoder.h"
#include "debug.h"
#include "dso.h"
#include "evlist.h"
#include "intlist.h"
#include "machine.h"
#include "map.h"
#include "perf.h"
#include "session.h"
#include "map_symbol.h"
#include "branch.h"
#include "symbol.h"
#include "tool.h"
#include "thread.h"
#include "thread-stack.h"
#include <tools/libc_compat.h>
#include "util/synthetic-events.h"
#define MAX_TIMESTAMP (~0ULL)
struct cs_etm_auxtrace {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
struct auxtrace_heap heap;
struct itrace_synth_opts synth_opts;
struct perf_session *session;
struct machine *machine;
struct thread *unknown_thread;
u8 timeless_decoding;
u8 snapshot_mode;
u8 data_queued;
u8 sample_branches;
u8 sample_instructions;
int num_cpu;
u32 auxtrace_type;
u64 branches_sample_type;
u64 branches_id;
u64 instructions_sample_type;
u64 instructions_sample_period;
u64 instructions_id;
u64 **metadata;
u64 kernel_start;
unsigned int pmu_type;
};
struct cs_etm_traceid_queue {
u8 trace_chan_id;
pid_t pid, tid;
u64 period_instructions;
size_t last_branch_pos;
union perf_event *event_buf;
struct thread *thread;
struct branch_stack *last_branch;
struct branch_stack *last_branch_rb;
struct cs_etm_packet *prev_packet;
struct cs_etm_packet *packet;
struct cs_etm_packet_queue packet_queue;
};
struct cs_etm_queue {
struct cs_etm_auxtrace *etm;
struct cs_etm_decoder *decoder;
struct auxtrace_buffer *buffer;
unsigned int queue_nr;
u8 pending_timestamp;
u64 offset;
const unsigned char *buf;
size_t buf_len, buf_used;
/* Conversion between traceID and index in traceid_queues array */
struct intlist *traceid_queues_list;
struct cs_etm_traceid_queue **traceid_queues;
};
static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
pid_t tid);
static int cs_etm__get_data_block(struct cs_etm_queue *etmq);
static int cs_etm__decode_data_block(struct cs_etm_queue *etmq);
/* PTMs ETMIDR [11:8] set to b0011 */
#define ETMIDR_PTM_VERSION 0x00000300
/*
* A struct auxtrace_heap_item only has a queue_nr and a timestamp to
* work with. One option is to modify to auxtrace_heap_XYZ() API or simply
* encode the etm queue number as the upper 16 bit and the channel as
* the lower 16 bit.
*/
#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan) \
(queue_nr << 16 | trace_chan_id)
#define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16)
#define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff)
static u32 cs_etm__get_v7_protocol_version(u32 etmidr)
{
etmidr &= ETMIDR_PTM_VERSION;
if (etmidr == ETMIDR_PTM_VERSION)
return CS_ETM_PROTO_PTM;
return CS_ETM_PROTO_ETMV3;
}
static int cs_etm__get_magic(u8 trace_chan_id, u64 *magic)
{
struct int_node *inode;
u64 *metadata;
inode = intlist__find(traceid_list, trace_chan_id);
if (!inode)
return -EINVAL;
metadata = inode->priv;
*magic = metadata[CS_ETM_MAGIC];
return 0;
}
int cs_etm__get_cpu(u8 trace_chan_id, int *cpu)
{
struct int_node *inode;
u64 *metadata;
inode = intlist__find(traceid_list, trace_chan_id);
if (!inode)
return -EINVAL;
metadata = inode->priv;
*cpu = (int)metadata[CS_ETM_CPU];
return 0;
}
void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
u8 trace_chan_id)
{
/*
* Wnen a timestamp packet is encountered the backend code
* is stopped so that the front end has time to process packets
* that were accumulated in the traceID queue. Since there can
* be more than one channel per cs_etm_queue, we need to specify
* what traceID queue needs servicing.
*/
etmq->pending_timestamp = trace_chan_id;
}
static u64 cs_etm__etmq_get_timestamp(struct cs_etm_queue *etmq,
u8 *trace_chan_id)
{
struct cs_etm_packet_queue *packet_queue;
if (!etmq->pending_timestamp)
return 0;
if (trace_chan_id)
*trace_chan_id = etmq->pending_timestamp;
packet_queue = cs_etm__etmq_get_packet_queue(etmq,
etmq->pending_timestamp);
if (!packet_queue)
return 0;
/* Acknowledge pending status */
etmq->pending_timestamp = 0;
/* See function cs_etm_decoder__do_{hard|soft}_timestamp() */
return packet_queue->timestamp;
}
static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue)
{
int i;
queue->head = 0;
queue->tail = 0;
queue->packet_count = 0;
for (i = 0; i < CS_ETM_PACKET_MAX_BUFFER; i++) {
queue->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN;
queue->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
queue->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
queue->packet_buffer[i].instr_count = 0;
queue->packet_buffer[i].last_instr_taken_branch = false;
queue->packet_buffer[i].last_instr_size = 0;
queue->packet_buffer[i].last_instr_type = 0;
queue->packet_buffer[i].last_instr_subtype = 0;
queue->packet_buffer[i].last_instr_cond = 0;
queue->packet_buffer[i].flags = 0;
queue->packet_buffer[i].exception_number = UINT32_MAX;
queue->packet_buffer[i].trace_chan_id = UINT8_MAX;
queue->packet_buffer[i].cpu = INT_MIN;
}
}
static void cs_etm__clear_all_packet_queues(struct cs_etm_queue *etmq)
{
int idx;
struct int_node *inode;
struct cs_etm_traceid_queue *tidq;
struct intlist *traceid_queues_list = etmq->traceid_queues_list;
intlist__for_each_entry(inode, traceid_queues_list) {
idx = (int)(intptr_t)inode->priv;
tidq = etmq->traceid_queues[idx];
cs_etm__clear_packet_queue(&tidq->packet_queue);
}
}
static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq,
u8 trace_chan_id)
{
int rc = -ENOMEM;
struct auxtrace_queue *queue;
struct cs_etm_auxtrace *etm = etmq->etm;
cs_etm__clear_packet_queue(&tidq->packet_queue);
queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
tidq->tid = queue->tid;
tidq->pid = -1;
tidq->trace_chan_id = trace_chan_id;
tidq->packet = zalloc(sizeof(struct cs_etm_packet));
if (!tidq->packet)
goto out;
tidq->prev_packet = zalloc(sizeof(struct cs_etm_packet));
if (!tidq->prev_packet)
goto out_free;
if (etm->synth_opts.last_branch) {
size_t sz = sizeof(struct branch_stack);
sz += etm->synth_opts.last_branch_sz *
sizeof(struct branch_entry);
tidq->last_branch = zalloc(sz);
if (!tidq->last_branch)
goto out_free;
tidq->last_branch_rb = zalloc(sz);
if (!tidq->last_branch_rb)
goto out_free;
}
tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
if (!tidq->event_buf)
goto out_free;
return 0;
out_free:
zfree(&tidq->last_branch_rb);
zfree(&tidq->last_branch);
zfree(&tidq->prev_packet);
zfree(&tidq->packet);
out:
return rc;
}
static struct cs_etm_traceid_queue
*cs_etm__etmq_get_traceid_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
{
int idx;
struct int_node *inode;
struct intlist *traceid_queues_list;
struct cs_etm_traceid_queue *tidq, **traceid_queues;
struct cs_etm_auxtrace *etm = etmq->etm;
if (etm->timeless_decoding)
trace_chan_id = CS_ETM_PER_THREAD_TRACEID;
traceid_queues_list = etmq->traceid_queues_list;
/*
* Check if the traceid_queue exist for this traceID by looking
* in the queue list.
*/
inode = intlist__find(traceid_queues_list, trace_chan_id);
if (inode) {
idx = (int)(intptr_t)inode->priv;
return etmq->traceid_queues[idx];
}
/* We couldn't find a traceid_queue for this traceID, allocate one */
tidq = malloc(sizeof(*tidq));
if (!tidq)
return NULL;
memset(tidq, 0, sizeof(*tidq));
/* Get a valid index for the new traceid_queue */
idx = intlist__nr_entries(traceid_queues_list);
/* Memory for the inode is free'ed in cs_etm_free_traceid_queues () */
inode = intlist__findnew(traceid_queues_list, trace_chan_id);
if (!inode)
goto out_free;
/* Associate this traceID with this index */
inode->priv = (void *)(intptr_t)idx;
if (cs_etm__init_traceid_queue(etmq, tidq, trace_chan_id))
goto out_free;
/* Grow the traceid_queues array by one unit */
traceid_queues = etmq->traceid_queues;
traceid_queues = reallocarray(traceid_queues,
idx + 1,
sizeof(*traceid_queues));
/*
* On failure reallocarray() returns NULL and the original block of
* memory is left untouched.
*/
if (!traceid_queues)
goto out_free;
traceid_queues[idx] = tidq;
etmq->traceid_queues = traceid_queues;
return etmq->traceid_queues[idx];
out_free:
/*
* Function intlist__remove() removes the inode from the list
* and delete the memory associated to it.
*/
intlist__remove(traceid_queues_list, inode);
free(tidq);
return NULL;
}
struct cs_etm_packet_queue
*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
{
struct cs_etm_traceid_queue *tidq;
tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
if (tidq)
return &tidq->packet_queue;
return NULL;
}
static void cs_etm__packet_dump(const char *pkt_string)
{
const char *color = PERF_COLOR_BLUE;
int len = strlen(pkt_string);
if (len && (pkt_string[len-1] == '\n'))
color_fprintf(stdout, color, " %s", pkt_string);
else
color_fprintf(stdout, color, " %s\n", pkt_string);
fflush(stdout);
}
static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
struct cs_etm_auxtrace *etm, int idx,
u32 etmidr)
{
u64 **metadata = etm->metadata;
t_params[idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
t_params[idx].etmv3.reg_ctrl = metadata[idx][CS_ETM_ETMCR];
t_params[idx].etmv3.reg_trc_id = metadata[idx][CS_ETM_ETMTRACEIDR];
}
static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params,
struct cs_etm_auxtrace *etm, int idx)
{
u64 **metadata = etm->metadata;
t_params[idx].protocol = CS_ETM_PROTO_ETMV4i;
t_params[idx].etmv4.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0];
t_params[idx].etmv4.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1];
t_params[idx].etmv4.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2];
t_params[idx].etmv4.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8];
t_params[idx].etmv4.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR];
t_params[idx].etmv4.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR];
}
static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
struct cs_etm_auxtrace *etm)
{
int i;
u32 etmidr;
u64 architecture;
for (i = 0; i < etm->num_cpu; i++) {
architecture = etm->metadata[i][CS_ETM_MAGIC];
switch (architecture) {
case __perf_cs_etmv3_magic:
etmidr = etm->metadata[i][CS_ETM_ETMIDR];
cs_etm__set_trace_param_etmv3(t_params, etm, i, etmidr);
break;
case __perf_cs_etmv4_magic:
cs_etm__set_trace_param_etmv4(t_params, etm, i);
break;
default:
return -EINVAL;
}
}
return 0;
}
static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params,
struct cs_etm_queue *etmq,
enum cs_etm_decoder_operation mode)
{
int ret = -EINVAL;
if (!(mode < CS_ETM_OPERATION_MAX))
goto out;
d_params->packet_printer = cs_etm__packet_dump;
d_params->operation = mode;
d_params->data = etmq;
d_params->formatted = true;
d_params->fsyncs = false;
d_params->hsyncs = false;
d_params->frame_aligned = true;
ret = 0;
out:
return ret;
}
static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
struct auxtrace_buffer *buffer)
{
int ret;
const char *color = PERF_COLOR_BLUE;
struct cs_etm_decoder_params d_params;
struct cs_etm_trace_params *t_params;
struct cs_etm_decoder *decoder;
size_t buffer_used = 0;
fprintf(stdout, "\n");
color_fprintf(stdout, color,
". ... CoreSight ETM Trace data: size %zu bytes\n",
buffer->size);
/* Use metadata to fill in trace parameters for trace decoder */
t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
if (!t_params)
return;
if (cs_etm__init_trace_params(t_params, etm))
goto out_free;
/* Set decoder parameters to simply print the trace packets */
if (cs_etm__init_decoder_params(&d_params, NULL,
CS_ETM_OPERATION_PRINT))
goto out_free;
decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
if (!decoder)
goto out_free;
do {
size_t consumed;
ret = cs_etm_decoder__process_data_block(
decoder, buffer->offset,
&((u8 *)buffer->data)[buffer_used],
buffer->size - buffer_used, &consumed);
if (ret)
break;
buffer_used += consumed;
} while (buffer_used < buffer->size);
cs_etm_decoder__free(decoder);
out_free:
zfree(&t_params);
}
static int cs_etm__flush_events(struct perf_session *session,
struct perf_tool *tool)
{
int ret;
struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
struct cs_etm_auxtrace,
auxtrace);
if (dump_trace)
return 0;
if (!tool->ordered_events)
return -EINVAL;
ret = cs_etm__update_queues(etm);
if (ret < 0)
return ret;
if (etm->timeless_decoding)
return cs_etm__process_timeless_queues(etm, -1);
return cs_etm__process_queues(etm);
}
static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
{
int idx;
uintptr_t priv;
struct int_node *inode, *tmp;
struct cs_etm_traceid_queue *tidq;
struct intlist *traceid_queues_list = etmq->traceid_queues_list;
intlist__for_each_entry_safe(inode, tmp, traceid_queues_list) {
priv = (uintptr_t)inode->priv;
idx = priv;
/* Free this traceid_queue from the array */
tidq = etmq->traceid_queues[idx];
thread__zput(tidq->thread);
zfree(&tidq->event_buf);
zfree(&tidq->last_branch);
zfree(&tidq->last_branch_rb);
zfree(&tidq->prev_packet);
zfree(&tidq->packet);
zfree(&tidq);
/*
* Function intlist__remove() removes the inode from the list
* and delete the memory associated to it.
*/
intlist__remove(traceid_queues_list, inode);
}
/* Then the RB tree itself */
intlist__delete(traceid_queues_list);
etmq->traceid_queues_list = NULL;
/* finally free the traceid_queues array */
zfree(&etmq->traceid_queues);
}
static void cs_etm__free_queue(void *priv)
{
struct cs_etm_queue *etmq = priv;
if (!etmq)
return;
cs_etm_decoder__free(etmq->decoder);
cs_etm__free_traceid_queues(etmq);
free(etmq);
}
static void cs_etm__free_events(struct perf_session *session)
{
unsigned int i;
struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
struct cs_etm_auxtrace,
auxtrace);
struct auxtrace_queues *queues = &aux->queues;
for (i = 0; i < queues->nr_queues; i++) {
cs_etm__free_queue(queues->queue_array[i].priv);
queues->queue_array[i].priv = NULL;
}
auxtrace_queues__free(queues);
}
static void cs_etm__free(struct perf_session *session)
{
int i;
struct int_node *inode, *tmp;
struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
struct cs_etm_auxtrace,
auxtrace);
cs_etm__free_events(session);
session->auxtrace = NULL;
/* First remove all traceID/metadata nodes for the RB tree */
intlist__for_each_entry_safe(inode, tmp, traceid_list)
intlist__remove(traceid_list, inode);
/* Then the RB tree itself */
intlist__delete(traceid_list);
for (i = 0; i < aux->num_cpu; i++)
zfree(&aux->metadata[i]);
thread__zput(aux->unknown_thread);
zfree(&aux->metadata);
zfree(&aux);
}
static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
{
struct machine *machine;
machine = etmq->etm->machine;
if (address >= etmq->etm->kernel_start) {
if (machine__is_host(machine))
return PERF_RECORD_MISC_KERNEL;
else
return PERF_RECORD_MISC_GUEST_KERNEL;
} else {
if (machine__is_host(machine))
return PERF_RECORD_MISC_USER;
else if (perf_guest)
return PERF_RECORD_MISC_GUEST_USER;
else
return PERF_RECORD_MISC_HYPERVISOR;
}
}
static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
u64 address, size_t size, u8 *buffer)
{
u8 cpumode;
u64 offset;
int len;
struct thread *thread;
struct machine *machine;
struct addr_location al;
struct cs_etm_traceid_queue *tidq;
if (!etmq)
return 0;
machine = etmq->etm->machine;
cpumode = cs_etm__cpu_mode(etmq, address);
tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
if (!tidq)
return 0;
thread = tidq->thread;
if (!thread) {
if (cpumode != PERF_RECORD_MISC_KERNEL)
return 0;
thread = etmq->etm->unknown_thread;
}
if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso)
return 0;
if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
dso__data_status_seen(al.map->dso, DSO_DATA_STATUS_SEEN_ITRACE))
return 0;
offset = al.map->map_ip(al.map, address);
map__load(al.map);
len = dso__data_read_offset(al.map->dso, machine, offset, buffer, size);
if (len <= 0)
return 0;
return len;
}
static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
{
struct cs_etm_decoder_params d_params;
struct cs_etm_trace_params *t_params = NULL;
struct cs_etm_queue *etmq;
etmq = zalloc(sizeof(*etmq));
if (!etmq)
return NULL;
etmq->traceid_queues_list = intlist__new(NULL);
if (!etmq->traceid_queues_list)
goto out_free;
/* Use metadata to fill in trace parameters for trace decoder */
t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
if (!t_params)
goto out_free;
if (cs_etm__init_trace_params(t_params, etm))
goto out_free;
/* Set decoder parameters to decode trace packets */
if (cs_etm__init_decoder_params(&d_params, etmq,
CS_ETM_OPERATION_DECODE))
goto out_free;
etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
if (!etmq->decoder)
goto out_free;
/*
* Register a function to handle all memory accesses required by
* the trace decoder library.
*/
if (cs_etm_decoder__add_mem_access_cb(etmq->decoder,
0x0L, ((u64) -1L),
cs_etm__mem_access))
goto out_free_decoder;
zfree(&t_params);
return etmq;
out_free_decoder:
cs_etm_decoder__free(etmq->decoder);
out_free:
intlist__delete(etmq->traceid_queues_list);
free(etmq);
return NULL;
}
static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
struct auxtrace_queue *queue,
unsigned int queue_nr)
{
int ret = 0;
unsigned int cs_queue_nr;
u8 trace_chan_id;
u64 timestamp;
struct cs_etm_queue *etmq = queue->priv;
if (list_empty(&queue->head) || etmq)
goto out;
etmq = cs_etm__alloc_queue(etm);
if (!etmq) {
ret = -ENOMEM;
goto out;
}
queue->priv = etmq;
etmq->etm = etm;
etmq->queue_nr = queue_nr;
etmq->offset = 0;
if (etm->timeless_decoding)
goto out;
/*
* We are under a CPU-wide trace scenario. As such we need to know
* when the code that generated the traces started to execute so that
* it can be correlated with execution on other CPUs. So we get a
* handle on the beginning of traces and decode until we find a
* timestamp. The timestamp is then added to the auxtrace min heap
* in order to know what nibble (of all the etmqs) to decode first.
*/
while (1) {
/*
* Fetch an aux_buffer from this etmq. Bail if no more
* blocks or an error has been encountered.
*/
ret = cs_etm__get_data_block(etmq);
if (ret <= 0)
goto out;
/*
* Run decoder on the trace block. The decoder will stop when
* encountering a timestamp, a full packet queue or the end of
* trace for that block.
*/
ret = cs_etm__decode_data_block(etmq);
if (ret)
goto out;
/*
* Function cs_etm_decoder__do_{hard|soft}_timestamp() does all
* the timestamp calculation for us.
*/
timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
/* We found a timestamp, no need to continue. */
if (timestamp)
break;
/*
* We didn't find a timestamp so empty all the traceid packet
* queues before looking for another timestamp packet, either
* in the current data block or a new one. Packets that were
* just decoded are useless since no timestamp has been
* associated with them. As such simply discard them.
*/
cs_etm__clear_all_packet_queues(etmq);
}
/*
* We have a timestamp. Add it to the min heap to reflect when
* instructions conveyed by the range packets of this traceID queue
* started to execute. Once the same has been done for all the traceID
* queues of each etmq, redenring and decoding can start in
* chronological order.
*
* Note that packets decoded above are still in the traceID's packet
* queue and will be processed in cs_etm__process_queues().
*/
cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan);
ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
out:
return ret;
}
static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
{
unsigned int i;
int ret;
if (!etm->kernel_start)
etm->kernel_start = machine__kernel_start(etm->machine);
for (i = 0; i < etm->queues.nr_queues; i++) {
ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i);
if (ret)
return ret;
}
return 0;
}
static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
{
if (etm->queues.new_data) {
etm->queues.new_data = false;
return cs_etm__setup_queues(etm);
}
return 0;
}
static inline
void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
struct branch_stack *bs_src = tidq->last_branch_rb;
struct branch_stack *bs_dst = tidq->last_branch;
size_t nr = 0;
/*
* Set the number of records before early exit: ->nr is used to
* determine how many branches to copy from ->entries.
*/
bs_dst->nr = bs_src->nr;
/*
* Early exit when there is nothing to copy.
*/
if (!bs_src->nr)
return;
/*
* As bs_src->entries is a circular buffer, we need to copy from it in
* two steps. First, copy the branches from the most recently inserted
* branch ->last_branch_pos until the end of bs_src->entries buffer.
*/
nr = etmq->etm->synth_opts.last_branch_sz - tidq->last_branch_pos;
memcpy(&bs_dst->entries[0],
&bs_src->entries[tidq->last_branch_pos],
sizeof(struct branch_entry) * nr);
/*
* If we wrapped around at least once, the branches from the beginning
* of the bs_src->entries buffer and until the ->last_branch_pos element
* are older valid branches: copy them over. The total number of
* branches copied over will be equal to the number of branches asked by
* the user in last_branch_sz.
*/
if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
memcpy(&bs_dst->entries[nr],
&bs_src->entries[0],
sizeof(struct branch_entry) * tidq->last_branch_pos);
}
}
static inline
void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq)
{
tidq->last_branch_pos = 0;
tidq->last_branch_rb->nr = 0;
}
static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq,
u8 trace_chan_id, u64 addr)
{
u8 instrBytes[2];
cs_etm__mem_access(etmq, trace_chan_id, addr,
ARRAY_SIZE(instrBytes), instrBytes);
/*
* T32 instruction size is indicated by bits[15:11] of the first
* 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111
* denote a 32-bit instruction.
*/
return ((instrBytes[1] & 0xF8) >= 0xE8) ? 4 : 2;
}
static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
{
/* Returns 0 for the CS_ETM_DISCONTINUITY packet */
if (packet->sample_type == CS_ETM_DISCONTINUITY)
return 0;
return packet->start_addr;
}
static inline
u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet)
{
/* Returns 0 for the CS_ETM_DISCONTINUITY packet */
if (packet->sample_type == CS_ETM_DISCONTINUITY)
return 0;
return packet->end_addr - packet->last_instr_size;
}
static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
u64 trace_chan_id,
const struct cs_etm_packet *packet,
u64 offset)
{
if (packet->isa == CS_ETM_ISA_T32) {
u64 addr = packet->start_addr;
while (offset > 0) {
addr += cs_etm__t32_instr_size(etmq,
trace_chan_id, addr);
offset--;
}
return addr;
}
/* Assume a 4 byte instruction size (A32/A64) */
return packet->start_addr + offset * 4;
}
static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
struct branch_stack *bs = tidq->last_branch_rb;
struct branch_entry *be;
/*
* The branches are recorded in a circular buffer in reverse
* chronological order: we start recording from the last element of the
* buffer down. After writing the first element of the stack, move the
* insert position back to the end of the buffer.
*/
if (!tidq->last_branch_pos)
tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
tidq->last_branch_pos -= 1;
be = &bs->entries[tidq->last_branch_pos];
be->from = cs_etm__last_executed_instr(tidq->prev_packet);
be->to = cs_etm__first_executed_instr(tidq->packet);
/* No support for mispredict */
be->flags.mispred = 0;
be->flags.predicted = 1;
/*
* Increment bs->nr until reaching the number of last branches asked by
* the user on the command line.
*/
if (bs->nr < etmq->etm->synth_opts.last_branch_sz)
bs->nr += 1;
}
static int cs_etm__inject_event(union perf_event *event,
struct perf_sample *sample, u64 type)
{
event->header.size = perf_event__sample_event_size(sample, type, 0);
return perf_event__synthesize_sample(event, type, 0, sample);
}
static int
cs_etm__get_trace(struct cs_etm_queue *etmq)
{
struct auxtrace_buffer *aux_buffer = etmq->buffer;
struct auxtrace_buffer *old_buffer = aux_buffer;
struct auxtrace_queue *queue;
queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
aux_buffer = auxtrace_buffer__next(queue, aux_buffer);
/* If no more data, drop the previous auxtrace_buffer and return */
if (!aux_buffer) {
if (old_buffer)
auxtrace_buffer__drop_data(old_buffer);
etmq->buf_len = 0;
return 0;
}
etmq->buffer = aux_buffer;
/* If the aux_buffer doesn't have data associated, try to load it */
if (!aux_buffer->data) {
/* get the file desc associated with the perf data file */
int fd = perf_data__fd(etmq->etm->session->data);
aux_buffer->data = auxtrace_buffer__get_data(aux_buffer, fd);
if (!aux_buffer->data)
return -ENOMEM;
}
/* If valid, drop the previous buffer */
if (old_buffer)
auxtrace_buffer__drop_data(old_buffer);
etmq->buf_used = 0;
etmq->buf_len = aux_buffer->size;
etmq->buf = aux_buffer->data;
return etmq->buf_len;
}
static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
struct cs_etm_traceid_queue *tidq)
{
if ((!tidq->thread) && (tidq->tid != -1))
tidq->thread = machine__find_thread(etm->machine, -1,
tidq->tid);
if (tidq->thread)
tidq->pid = tidq->thread->pid_;
}
int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
pid_t tid, u8 trace_chan_id)
{
int cpu, err = -EINVAL;
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_traceid_queue *tidq;
tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
if (!tidq)
return err;
if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
return err;
err = machine__set_current_tid(etm->machine, cpu, tid, tid);
if (err)
return err;
tidq->tid = tid;
thread__zput(tidq->thread);
cs_etm__set_pid_tid_cpu(etm, tidq);
return 0;
}
bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
{
return !!etmq->etm->timeless_decoding;
}
static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
u64 trace_chan_id,
const struct cs_etm_packet *packet,
struct perf_sample *sample)
{
/*
* It's pointless to read instructions for the CS_ETM_DISCONTINUITY
* packet, so directly bail out with 'insn_len' = 0.
*/
if (packet->sample_type == CS_ETM_DISCONTINUITY) {
sample->insn_len = 0;
return;
}
/*
* T32 instruction size might be 32-bit or 16-bit, decide by calling
* cs_etm__t32_instr_size().
*/
if (packet->isa == CS_ETM_ISA_T32)
sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id,
sample->ip);
/* Otherwise, A64 and A32 instruction size are always 32-bit. */
else
sample->insn_len = 4;
cs_etm__mem_access(etmq, trace_chan_id, sample->ip,
sample->insn_len, (void *)sample->insn);
}
static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq,
u64 addr, u64 period)
{
int ret = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
union perf_event *event = tidq->event_buf;
struct perf_sample sample = {.ip = 0,};
event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
event->sample.header.size = sizeof(struct perf_event_header);
sample.ip = addr;
sample.pid = tidq->pid;
sample.tid = tidq->tid;
sample.id = etmq->etm->instructions_id;
sample.stream_id = etmq->etm->instructions_id;
sample.period = period;
sample.cpu = tidq->packet->cpu;
sample.flags = tidq->prev_packet->flags;
sample.cpumode = event->sample.header.misc;
cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
if (etm->synth_opts.last_branch) {
cs_etm__copy_last_branch_rb(etmq, tidq);
sample.branch_stack = tidq->last_branch;
}
if (etm->synth_opts.inject) {
ret = cs_etm__inject_event(event, &sample,
etm->instructions_sample_type);
if (ret)
return ret;
}
ret = perf_session__deliver_synth_event(etm->session, event, &sample);
if (ret)
pr_err(
"CS ETM Trace: failed to deliver instruction event, error %d\n",
ret);
if (etm->synth_opts.last_branch)
cs_etm__reset_last_branch_rb(tidq);
return ret;
}
/*
* The cs etm packet encodes an instruction range between a branch target
* and the next taken branch. Generate sample accordingly.
*/
static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
int ret = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
struct perf_sample sample = {.ip = 0,};
union perf_event *event = tidq->event_buf;
struct dummy_branch_stack {
u64 nr;
struct branch_entry entries;
} dummy_bs;
u64 ip;
ip = cs_etm__last_executed_instr(tidq->prev_packet);
event->sample.header.type = PERF_RECORD_SAMPLE;
event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
event->sample.header.size = sizeof(struct perf_event_header);
sample.ip = ip;
sample.pid = tidq->pid;
sample.tid = tidq->tid;
sample.addr = cs_etm__first_executed_instr(tidq->packet);
sample.id = etmq->etm->branches_id;
sample.stream_id = etmq->etm->branches_id;
sample.period = 1;
sample.cpu = tidq->packet->cpu;
sample.flags = tidq->prev_packet->flags;
sample.cpumode = event->sample.header.misc;
cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet,
&sample);
/*
* perf report cannot handle events without a branch stack
*/
if (etm->synth_opts.last_branch) {
dummy_bs = (struct dummy_branch_stack){
.nr = 1,
.entries = {
.from = sample.ip,
.to = sample.addr,
},
};
sample.branch_stack = (struct branch_stack *)&dummy_bs;
}
if (etm->synth_opts.inject) {
ret = cs_etm__inject_event(event, &sample,
etm->branches_sample_type);
if (ret)
return ret;
}
ret = perf_session__deliver_synth_event(etm->session, event, &sample);
if (ret)
pr_err(
"CS ETM Trace: failed to deliver instruction event, error %d\n",
ret);
return ret;
}
struct cs_etm_synth {
struct perf_tool dummy_tool;
struct perf_session *session;
};
static int cs_etm__event_synth(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct cs_etm_synth *cs_etm_synth =
container_of(tool, struct cs_etm_synth, dummy_tool);
return perf_session__deliver_synth_event(cs_etm_synth->session,
event, NULL);
}
static int cs_etm__synth_event(struct perf_session *session,
struct perf_event_attr *attr, u64 id)
{
struct cs_etm_synth cs_etm_synth;
memset(&cs_etm_synth, 0, sizeof(struct cs_etm_synth));
cs_etm_synth.session = session;
return perf_event__synthesize_attr(&cs_etm_synth.dummy_tool, attr, 1,
&id, cs_etm__event_synth);
}
static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
struct perf_session *session)
{
struct evlist *evlist = session->evlist;
struct evsel *evsel;
struct perf_event_attr attr;
bool found = false;
u64 id;
int err;
evlist__for_each_entry(evlist, evsel) {
if (evsel->core.attr.type == etm->pmu_type) {
found = true;
break;
}
}
if (!found) {
pr_debug("No selected events with CoreSight Trace data\n");
return 0;
}
memset(&attr, 0, sizeof(struct perf_event_attr));
attr.size = sizeof(struct perf_event_attr);
attr.type = PERF_TYPE_HARDWARE;
attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
PERF_SAMPLE_PERIOD;
if (etm->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
attr.sample_type |= PERF_SAMPLE_TIME;
attr.exclude_user = evsel->core.attr.exclude_user;
attr.exclude_kernel = evsel->core.attr.exclude_kernel;
attr.exclude_hv = evsel->core.attr.exclude_hv;
attr.exclude_host = evsel->core.attr.exclude_host;
attr.exclude_guest = evsel->core.attr.exclude_guest;
attr.sample_id_all = evsel->core.attr.sample_id_all;
attr.read_format = evsel->core.attr.read_format;
/* create new id val to be a fixed offset from evsel id */
id = evsel->core.id[0] + 1000000000;
if (!id)
id = 1;
if (etm->synth_opts.branches) {
attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
attr.sample_period = 1;
attr.sample_type |= PERF_SAMPLE_ADDR;
err = cs_etm__synth_event(session, &attr, id);
if (err)
return err;
etm->sample_branches = true;
etm->branches_sample_type = attr.sample_type;
etm->branches_id = id;
id += 1;
attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
}
if (etm->synth_opts.last_branch)
attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
if (etm->synth_opts.instructions) {
attr.config = PERF_COUNT_HW_INSTRUCTIONS;
attr.sample_period = etm->synth_opts.period;
etm->instructions_sample_period = attr.sample_period;
err = cs_etm__synth_event(session, &attr, id);
if (err)
return err;
etm->sample_instructions = true;
etm->instructions_sample_type = attr.sample_type;
etm->instructions_id = id;
id += 1;
}
return 0;
}
static int cs_etm__sample(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
int ret;
u8 trace_chan_id = tidq->trace_chan_id;
u64 instrs_executed = tidq->packet->instr_count;
tidq->period_instructions += instrs_executed;
/*
* Record a branch when the last instruction in
* PREV_PACKET is a branch.
*/
if (etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE &&
tidq->prev_packet->last_instr_taken_branch)
cs_etm__update_last_branch_rb(etmq, tidq);
if (etm->sample_instructions &&
tidq->period_instructions >= etm->instructions_sample_period) {
/*
* Emit instruction sample periodically
* TODO: allow period to be defined in cycles and clock time
*/
/* Get number of instructions executed after the sample point */
u64 instrs_over = tidq->period_instructions -
etm->instructions_sample_period;
/*
* Calculate the address of the sampled instruction (-1 as
* sample is reported as though instruction has just been
* executed, but PC has not advanced to next instruction)
*/
u64 offset = (instrs_executed - instrs_over - 1);
u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
tidq->packet, offset);
ret = cs_etm__synth_instruction_sample(
etmq, tidq, addr, etm->instructions_sample_period);
if (ret)
return ret;
/* Carry remaining instructions into next sample period */
tidq->period_instructions = instrs_over;
}
if (etm->sample_branches) {
bool generate_sample = false;
/* Generate sample for tracing on packet */
if (tidq->prev_packet->sample_type == CS_ETM_DISCONTINUITY)
generate_sample = true;
/* Generate sample for branch taken packet */
if (tidq->prev_packet->sample_type == CS_ETM_RANGE &&
tidq->prev_packet->last_instr_taken_branch)
generate_sample = true;
if (generate_sample) {
ret = cs_etm__synth_branch_sample(etmq, tidq);
if (ret)
return ret;
}
}
if (etm->sample_branches || etm->synth_opts.last_branch) {
/*
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
*/
tmp = tidq->packet;
tidq->packet = tidq->prev_packet;
tidq->prev_packet = tmp;
}
return 0;
}
static int cs_etm__exception(struct cs_etm_traceid_queue *tidq)
{
/*
* When the exception packet is inserted, whether the last instruction
* in previous range packet is taken branch or not, we need to force
* to set 'prev_packet->last_instr_taken_branch' to true. This ensures
* to generate branch sample for the instruction range before the
* exception is trapped to kernel or before the exception returning.
*
* The exception packet includes the dummy address values, so don't
* swap PACKET with PREV_PACKET. This keeps PREV_PACKET to be useful
* for generating instruction and branch samples.
*/
if (tidq->prev_packet->sample_type == CS_ETM_RANGE)
tidq->prev_packet->last_instr_taken_branch = true;
return 0;
}
static int cs_etm__flush(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
int err = 0;
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
/* Handle start tracing packet */
if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
goto swap_packet;
if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
/*
* Generate a last branch event for the branches left in the
* circular buffer at the end of the trace.
*
* Use the address of the end of the last reported execution
* range
*/
u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
tidq->period_instructions);
if (err)
return err;
tidq->period_instructions = 0;
}
if (etm->sample_branches &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
err = cs_etm__synth_branch_sample(etmq, tidq);
if (err)
return err;
}
swap_packet:
if (etm->sample_branches || etm->synth_opts.last_branch) {
/*
* Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
* the next incoming packet.
*/
tmp = tidq->packet;
tidq->packet = tidq->prev_packet;
tidq->prev_packet = tmp;
}
return err;
}
static int cs_etm__end_block(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
int err;
/*
* It has no new packet coming and 'etmq->packet' contains the stale
* packet which was set at the previous time with packets swapping;
* so skip to generate branch sample to avoid stale packet.
*
* For this case only flush branch stack and generate a last branch
* event for the branches left in the circular buffer at the end of
* the trace.
*/
if (etmq->etm->synth_opts.last_branch &&
tidq->prev_packet->sample_type == CS_ETM_RANGE) {
/*
* Use the address of the end of the last reported execution
* range.
*/
u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
err = cs_etm__synth_instruction_sample(
etmq, tidq, addr,
tidq->period_instructions);
if (err)
return err;
tidq->period_instructions = 0;
}
return 0;
}
/*
* cs_etm__get_data_block: Fetch a block from the auxtrace_buffer queue
* if need be.
* Returns: < 0 if error
* = 0 if no more auxtrace_buffer to read
* > 0 if the current buffer isn't empty yet
*/
static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
{
int ret;
if (!etmq->buf_len) {
ret = cs_etm__get_trace(etmq);
if (ret <= 0)
return ret;
/*
* We cannot assume consecutive blocks in the data file
* are contiguous, reset the decoder to force re-sync.
*/
ret = cs_etm_decoder__reset(etmq->decoder);
if (ret)
return ret;
}
return etmq->buf_len;
}
static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id,
struct cs_etm_packet *packet,
u64 end_addr)
{
/* Initialise to keep compiler happy */
u16 instr16 = 0;
u32 instr32 = 0;
u64 addr;
switch (packet->isa) {
case CS_ETM_ISA_T32:
/*
* The SVC of T32 is defined in ARM DDI 0487D.a, F5.1.247:
*
* b'15 b'8
* +-----------------+--------+
* | 1 1 0 1 1 1 1 1 | imm8 |
* +-----------------+--------+
*
* According to the specifiction, it only defines SVC for T32
* with 16 bits instruction and has no definition for 32bits;
* so below only read 2 bytes as instruction size for T32.
*/
addr = end_addr - 2;
cs_etm__mem_access(etmq, trace_chan_id, addr,
sizeof(instr16), (u8 *)&instr16);
if ((instr16 & 0xFF00) == 0xDF00)
return true;
break;
case CS_ETM_ISA_A32:
/*
* The SVC of A32 is defined in ARM DDI 0487D.a, F5.1.247:
*
* b'31 b'28 b'27 b'24
* +---------+---------+-------------------------+
* | !1111 | 1 1 1 1 | imm24 |
* +---------+---------+-------------------------+
*/
addr = end_addr - 4;
cs_etm__mem_access(etmq, trace_chan_id, addr,
sizeof(instr32), (u8 *)&instr32);
if ((instr32 & 0x0F000000) == 0x0F000000 &&
(instr32 & 0xF0000000) != 0xF0000000)
return true;
break;
case CS_ETM_ISA_A64:
/*
* The SVC of A64 is defined in ARM DDI 0487D.a, C6.2.294:
*
* b'31 b'21 b'4 b'0
* +-----------------------+---------+-----------+
* | 1 1 0 1 0 1 0 0 0 0 0 | imm16 | 0 0 0 0 1 |
* +-----------------------+---------+-----------+
*/
addr = end_addr - 4;
cs_etm__mem_access(etmq, trace_chan_id, addr,
sizeof(instr32), (u8 *)&instr32);
if ((instr32 & 0xFFE0001F) == 0xd4000001)
return true;
break;
case CS_ETM_ISA_UNKNOWN:
default:
break;
}
return false;
}
static bool cs_etm__is_syscall(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq, u64 magic)
{
u8 trace_chan_id = tidq->trace_chan_id;
struct cs_etm_packet *packet = tidq->packet;
struct cs_etm_packet *prev_packet = tidq->prev_packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_SVC)
return true;
/*
* ETMv4 exception type CS_ETMV4_EXC_CALL covers SVC, SMC and
* HVC cases; need to check if it's SVC instruction based on
* packet address.
*/
if (magic == __perf_cs_etmv4_magic) {
if (packet->exception_number == CS_ETMV4_EXC_CALL &&
cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
prev_packet->end_addr))
return true;
}
return false;
}
static bool cs_etm__is_async_exception(struct cs_etm_traceid_queue *tidq,
u64 magic)
{
struct cs_etm_packet *packet = tidq->packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_DEBUG_HALT ||
packet->exception_number == CS_ETMV3_EXC_ASYNC_DATA_ABORT ||
packet->exception_number == CS_ETMV3_EXC_PE_RESET ||
packet->exception_number == CS_ETMV3_EXC_IRQ ||
packet->exception_number == CS_ETMV3_EXC_FIQ)
return true;
if (magic == __perf_cs_etmv4_magic)
if (packet->exception_number == CS_ETMV4_EXC_RESET ||
packet->exception_number == CS_ETMV4_EXC_DEBUG_HALT ||
packet->exception_number == CS_ETMV4_EXC_SYSTEM_ERROR ||
packet->exception_number == CS_ETMV4_EXC_INST_DEBUG ||
packet->exception_number == CS_ETMV4_EXC_DATA_DEBUG ||
packet->exception_number == CS_ETMV4_EXC_IRQ ||
packet->exception_number == CS_ETMV4_EXC_FIQ)
return true;
return false;
}
static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq,
u64 magic)
{
u8 trace_chan_id = tidq->trace_chan_id;
struct cs_etm_packet *packet = tidq->packet;
struct cs_etm_packet *prev_packet = tidq->prev_packet;
if (magic == __perf_cs_etmv3_magic)
if (packet->exception_number == CS_ETMV3_EXC_SMC ||
packet->exception_number == CS_ETMV3_EXC_HYP ||
packet->exception_number == CS_ETMV3_EXC_JAZELLE_THUMBEE ||
packet->exception_number == CS_ETMV3_EXC_UNDEFINED_INSTR ||
packet->exception_number == CS_ETMV3_EXC_PREFETCH_ABORT ||
packet->exception_number == CS_ETMV3_EXC_DATA_FAULT ||
packet->exception_number == CS_ETMV3_EXC_GENERIC)
return true;
if (magic == __perf_cs_etmv4_magic) {
if (packet->exception_number == CS_ETMV4_EXC_TRAP ||
packet->exception_number == CS_ETMV4_EXC_ALIGNMENT ||
packet->exception_number == CS_ETMV4_EXC_INST_FAULT ||
packet->exception_number == CS_ETMV4_EXC_DATA_FAULT)
return true;
/*
* For CS_ETMV4_EXC_CALL, except SVC other instructions
* (SMC, HVC) are taken as sync exceptions.
*/
if (packet->exception_number == CS_ETMV4_EXC_CALL &&
!cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
prev_packet->end_addr))
return true;
/*
* ETMv4 has 5 bits for exception number; if the numbers
* are in the range ( CS_ETMV4_EXC_FIQ, CS_ETMV4_EXC_END ]
* they are implementation defined exceptions.
*
* For this case, simply take it as sync exception.
*/
if (packet->exception_number > CS_ETMV4_EXC_FIQ &&
packet->exception_number <= CS_ETMV4_EXC_END)
return true;
}
return false;
}
static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
struct cs_etm_packet *packet = tidq->packet;
struct cs_etm_packet *prev_packet = tidq->prev_packet;
u8 trace_chan_id = tidq->trace_chan_id;
u64 magic;
int ret;
switch (packet->sample_type) {
case CS_ETM_RANGE:
/*
* Immediate branch instruction without neither link nor
* return flag, it's normal branch instruction within
* the function.
*/
if (packet->last_instr_type == OCSD_INSTR_BR &&
packet->last_instr_subtype == OCSD_S_INSTR_NONE) {
packet->flags = PERF_IP_FLAG_BRANCH;
if (packet->last_instr_cond)
packet->flags |= PERF_IP_FLAG_CONDITIONAL;
}
/*
* Immediate branch instruction with link (e.g. BL), this is
* branch instruction for function call.
*/
if (packet->last_instr_type == OCSD_INSTR_BR &&
packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL;
/*
* Indirect branch instruction with link (e.g. BLR), this is
* branch instruction for function call.
*/
if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL;
/*
* Indirect branch instruction with subtype of
* OCSD_S_INSTR_V7_IMPLIED_RET, this is explicit hint for
* function return for A32/T32.
*/
if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
packet->last_instr_subtype == OCSD_S_INSTR_V7_IMPLIED_RET)
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN;
/*
* Indirect branch instruction without link (e.g. BR), usually
* this is used for function return, especially for functions
* within dynamic link lib.
*/
if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
packet->last_instr_subtype == OCSD_S_INSTR_NONE)
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN;
/* Return instruction for function return. */
if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
packet->last_instr_subtype == OCSD_S_INSTR_V8_RET)
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN;
/*
* Decoder might insert a discontinuity in the middle of
* instruction packets, fixup prev_packet with flag
* PERF_IP_FLAG_TRACE_BEGIN to indicate restarting trace.
*/
if (prev_packet->sample_type == CS_ETM_DISCONTINUITY)
prev_packet->flags |= PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_TRACE_BEGIN;
/*
* If the previous packet is an exception return packet
* and the return address just follows SVC instuction,
* it needs to calibrate the previous packet sample flags
* as PERF_IP_FLAG_SYSCALLRET.
*/
if (prev_packet->flags == (PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_INTERRUPT) &&
cs_etm__is_svc_instr(etmq, trace_chan_id,
packet, packet->start_addr))
prev_packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_SYSCALLRET;
break;
case CS_ETM_DISCONTINUITY:
/*
* The trace is discontinuous, if the previous packet is
* instruction packet, set flag PERF_IP_FLAG_TRACE_END
* for previous packet.
*/
if (prev_packet->sample_type == CS_ETM_RANGE)
prev_packet->flags |= PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_TRACE_END;
break;
case CS_ETM_EXCEPTION:
ret = cs_etm__get_magic(packet->trace_chan_id, &magic);
if (ret)
return ret;
/* The exception is for system call. */
if (cs_etm__is_syscall(etmq, tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_SYSCALLRET;
/*
* The exceptions are triggered by external signals from bus,
* interrupt controller, debug module, PE reset or halt.
*/
else if (cs_etm__is_async_exception(tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_ASYNC |
PERF_IP_FLAG_INTERRUPT;
/*
* Otherwise, exception is caused by trap, instruction &
* data fault, or alignment errors.
*/
else if (cs_etm__is_sync_exception(etmq, tidq, magic))
packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_CALL |
PERF_IP_FLAG_INTERRUPT;
/*
* When the exception packet is inserted, since exception
* packet is not used standalone for generating samples
* and it's affiliation to the previous instruction range
* packet; so set previous range packet flags to tell perf
* it is an exception taken branch.
*/
if (prev_packet->sample_type == CS_ETM_RANGE)
prev_packet->flags = packet->flags;
break;
case CS_ETM_EXCEPTION_RET:
/*
* When the exception return packet is inserted, since
* exception return packet is not used standalone for
* generating samples and it's affiliation to the previous
* instruction range packet; so set previous range packet
* flags to tell perf it is an exception return branch.
*
* The exception return can be for either system call or
* other exception types; unfortunately the packet doesn't
* contain exception type related info so we cannot decide
* the exception type purely based on exception return packet.
* If we record the exception number from exception packet and
* reuse it for excpetion return packet, this is not reliable
* due the trace can be discontinuity or the interrupt can
* be nested, thus the recorded exception number cannot be
* used for exception return packet for these two cases.
*
* For exception return packet, we only need to distinguish the
* packet is for system call or for other types. Thus the
* decision can be deferred when receive the next packet which
* contains the return address, based on the return address we
* can read out the previous instruction and check if it's a
* system call instruction and then calibrate the sample flag
* as needed.
*/
if (prev_packet->sample_type == CS_ETM_RANGE)
prev_packet->flags = PERF_IP_FLAG_BRANCH |
PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_INTERRUPT;
break;
case CS_ETM_EMPTY:
default:
break;
}
return 0;
}
static int cs_etm__decode_data_block(struct cs_etm_queue *etmq)
{
int ret = 0;
size_t processed = 0;
/*
* Packets are decoded and added to the decoder's packet queue
* until the decoder packet processing callback has requested that
* processing stops or there is nothing left in the buffer. Normal
* operations that stop processing are a timestamp packet or a full
* decoder buffer queue.
*/
ret = cs_etm_decoder__process_data_block(etmq->decoder,
etmq->offset,
&etmq->buf[etmq->buf_used],
etmq->buf_len,
&processed);
if (ret)
goto out;
etmq->offset += processed;
etmq->buf_used += processed;
etmq->buf_len -= processed;
out:
return ret;
}
static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
int ret;
struct cs_etm_packet_queue *packet_queue;
packet_queue = &tidq->packet_queue;
/* Process each packet in this chunk */
while (1) {
ret = cs_etm_decoder__get_packet(packet_queue,
tidq->packet);
if (ret <= 0)
/*
* Stop processing this chunk on
* end of data or error
*/
break;
/*
* Since packet addresses are swapped in packet
* handling within below switch() statements,
* thus setting sample flags must be called
* prior to switch() statement to use address
* information before packets swapping.
*/
ret = cs_etm__set_sample_flags(etmq, tidq);
if (ret < 0)
break;
switch (tidq->packet->sample_type) {
case CS_ETM_RANGE:
/*
* If the packet contains an instruction
* range, generate instruction sequence
* events.
*/
cs_etm__sample(etmq, tidq);
break;
case CS_ETM_EXCEPTION:
case CS_ETM_EXCEPTION_RET:
/*
* If the exception packet is coming,
* make sure the previous instruction
* range packet to be handled properly.
*/
cs_etm__exception(tidq);
break;
case CS_ETM_DISCONTINUITY:
/*
* Discontinuity in trace, flush
* previous branch stack
*/
cs_etm__flush(etmq, tidq);
break;
case CS_ETM_EMPTY:
/*
* Should not receive empty packet,
* report error.
*/
pr_err("CS ETM Trace: empty packet\n");
return -EINVAL;
default:
break;
}
}
return ret;
}
static void cs_etm__clear_all_traceid_queues(struct cs_etm_queue *etmq)
{
int idx;
struct int_node *inode;
struct cs_etm_traceid_queue *tidq;
struct intlist *traceid_queues_list = etmq->traceid_queues_list;
intlist__for_each_entry(inode, traceid_queues_list) {
idx = (int)(intptr_t)inode->priv;
tidq = etmq->traceid_queues[idx];
/* Ignore return value */
cs_etm__process_traceid_queue(etmq, tidq);
/*
* Generate an instruction sample with the remaining
* branchstack entries.
*/
cs_etm__flush(etmq, tidq);
}
}
static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
{
int err = 0;
struct cs_etm_traceid_queue *tidq;
tidq = cs_etm__etmq_get_traceid_queue(etmq, CS_ETM_PER_THREAD_TRACEID);
if (!tidq)
return -EINVAL;
/* Go through each buffer in the queue and decode them one by one */
while (1) {
err = cs_etm__get_data_block(etmq);
if (err <= 0)
return err;
/* Run trace decoder until buffer consumed or end of trace */
do {
err = cs_etm__decode_data_block(etmq);
if (err)
return err;
/*
* Process each packet in this chunk, nothing to do if
* an error occurs other than hoping the next one will
* be better.
*/
err = cs_etm__process_traceid_queue(etmq, tidq);
} while (etmq->buf_len);
if (err == 0)
/* Flush any remaining branch stack entries */
err = cs_etm__end_block(etmq, tidq);
}
return err;
}
static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
pid_t tid)
{
unsigned int i;
struct auxtrace_queues *queues = &etm->queues;
for (i = 0; i < queues->nr_queues; i++) {
struct auxtrace_queue *queue = &etm->queues.queue_array[i];
struct cs_etm_queue *etmq = queue->priv;
struct cs_etm_traceid_queue *tidq;
if (!etmq)
continue;
tidq = cs_etm__etmq_get_traceid_queue(etmq,
CS_ETM_PER_THREAD_TRACEID);
if (!tidq)
continue;
if ((tid == -1) || (tidq->tid == tid)) {
cs_etm__set_pid_tid_cpu(etm, tidq);
cs_etm__run_decoder(etmq);
}
}
return 0;
}
static int cs_etm__process_queues(struct cs_etm_auxtrace *etm)
{
int ret = 0;
unsigned int cs_queue_nr, queue_nr;
u8 trace_chan_id;
u64 timestamp;
struct auxtrace_queue *queue;
struct cs_etm_queue *etmq;
struct cs_etm_traceid_queue *tidq;
while (1) {
if (!etm->heap.heap_cnt)
goto out;
/* Take the entry at the top of the min heap */
cs_queue_nr = etm->heap.heap_array[0].queue_nr;
queue_nr = TO_QUEUE_NR(cs_queue_nr);
trace_chan_id = TO_TRACE_CHAN_ID(cs_queue_nr);
queue = &etm->queues.queue_array[queue_nr];
etmq = queue->priv;
/*
* Remove the top entry from the heap since we are about
* to process it.
*/
auxtrace_heap__pop(&etm->heap);
tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
if (!tidq) {
/*
* No traceID queue has been allocated for this traceID,
* which means something somewhere went very wrong. No
* other choice than simply exit.
*/
ret = -EINVAL;
goto out;
}
/*
* Packets associated with this timestamp are already in
* the etmq's traceID queue, so process them.
*/
ret = cs_etm__process_traceid_queue(etmq, tidq);
if (ret < 0)
goto out;
/*
* Packets for this timestamp have been processed, time to
* move on to the next timestamp, fetching a new auxtrace_buffer
* if need be.
*/
refetch:
ret = cs_etm__get_data_block(etmq);
if (ret < 0)
goto out;
/*
* No more auxtrace_buffers to process in this etmq, simply
* move on to another entry in the auxtrace_heap.
*/
if (!ret)
continue;
ret = cs_etm__decode_data_block(etmq);
if (ret)
goto out;
timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
if (!timestamp) {
/*
* Function cs_etm__decode_data_block() returns when
* there is no more traces to decode in the current
* auxtrace_buffer OR when a timestamp has been
* encountered on any of the traceID queues. Since we
* did not get a timestamp, there is no more traces to
* process in this auxtrace_buffer. As such empty and
* flush all traceID queues.
*/
cs_etm__clear_all_traceid_queues(etmq);
/* Fetch another auxtrace_buffer for this etmq */
goto refetch;
}
/*
* Add to the min heap the timestamp for packets that have
* just been decoded. They will be processed and synthesized
* during the next call to cs_etm__process_traceid_queue() for
* this queue/traceID.
*/
cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id);
ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
}
out:
return ret;
}
static int cs_etm__process_itrace_start(struct cs_etm_auxtrace *etm,
union perf_event *event)
{
struct thread *th;
if (etm->timeless_decoding)
return 0;
/*
* Add the tid/pid to the log so that we can get a match when
* we get a contextID from the decoder.
*/
th = machine__findnew_thread(etm->machine,
event->itrace_start.pid,
event->itrace_start.tid);
if (!th)
return -ENOMEM;
thread__put(th);
return 0;
}
static int cs_etm__process_switch_cpu_wide(struct cs_etm_auxtrace *etm,
union perf_event *event)
{
struct thread *th;
bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
/*
* Context switch in per-thread mode are irrelevant since perf
* will start/stop tracing as the process is scheduled.
*/
if (etm->timeless_decoding)
return 0;
/*
* SWITCH_IN events carry the next process to be switched out while
* SWITCH_OUT events carry the process to be switched in. As such
* we don't care about IN events.
*/
if (!out)
return 0;
/*
* Add the tid/pid to the log so that we can get a match when
* we get a contextID from the decoder.
*/
th = machine__findnew_thread(etm->machine,
event->context_switch.next_prev_pid,
event->context_switch.next_prev_tid);
if (!th)
return -ENOMEM;
thread__put(th);
return 0;
}
static int cs_etm__process_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
struct perf_tool *tool)
{
int err = 0;
u64 timestamp;
struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
struct cs_etm_auxtrace,
auxtrace);
if (dump_trace)
return 0;
if (!tool->ordered_events) {
pr_err("CoreSight ETM Trace requires ordered events\n");
return -EINVAL;
}
if (sample->time && (sample->time != (u64) -1))
timestamp = sample->time;
else
timestamp = 0;
if (timestamp || etm->timeless_decoding) {
err = cs_etm__update_queues(etm);
if (err)
return err;
}
if (etm->timeless_decoding &&
event->header.type == PERF_RECORD_EXIT)
return cs_etm__process_timeless_queues(etm,
event->fork.tid);
if (event->header.type == PERF_RECORD_ITRACE_START)
return cs_etm__process_itrace_start(etm, event);
else if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
return cs_etm__process_switch_cpu_wide(etm, event);
if (!etm->timeless_decoding &&
event->header.type == PERF_RECORD_AUX)
return cs_etm__process_queues(etm);
return 0;
}
static int cs_etm__process_auxtrace_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool __maybe_unused)
{
struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
struct cs_etm_auxtrace,
auxtrace);
if (!etm->data_queued) {
struct auxtrace_buffer *buffer;
off_t data_offset;
int fd = perf_data__fd(session->data);
bool is_pipe = perf_data__is_pipe(session->data);
int err;
if (is_pipe)
data_offset = 0;
else {
data_offset = lseek(fd, 0, SEEK_CUR);
if (data_offset == -1)
return -errno;
}
err = auxtrace_queues__add_event(&etm->queues, session,
event, data_offset, &buffer);
if (err)
return err;
if (dump_trace)
if (auxtrace_buffer__get_data(buffer, fd)) {
cs_etm__dump_event(etm, buffer);
auxtrace_buffer__put_data(buffer);
}
}
return 0;
}
static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm)
{
struct evsel *evsel;
struct evlist *evlist = etm->session->evlist;
bool timeless_decoding = true;
/*
* Circle through the list of event and complain if we find one
* with the time bit set.
*/
evlist__for_each_entry(evlist, evsel) {
if ((evsel->core.attr.sample_type & PERF_SAMPLE_TIME))
timeless_decoding = false;
}
return timeless_decoding;
}
static const char * const cs_etm_global_header_fmts[] = {
[CS_HEADER_VERSION_0] = " Header version %llx\n",
[CS_PMU_TYPE_CPUS] = " PMU type/num cpus %llx\n",
[CS_ETM_SNAPSHOT] = " Snapshot %llx\n",
};
static const char * const cs_etm_priv_fmts[] = {
[CS_ETM_MAGIC] = " Magic number %llx\n",
[CS_ETM_CPU] = " CPU %lld\n",
[CS_ETM_ETMCR] = " ETMCR %llx\n",
[CS_ETM_ETMTRACEIDR] = " ETMTRACEIDR %llx\n",
[CS_ETM_ETMCCER] = " ETMCCER %llx\n",
[CS_ETM_ETMIDR] = " ETMIDR %llx\n",
};
static const char * const cs_etmv4_priv_fmts[] = {
[CS_ETM_MAGIC] = " Magic number %llx\n",
[CS_ETM_CPU] = " CPU %lld\n",
[CS_ETMV4_TRCCONFIGR] = " TRCCONFIGR %llx\n",
[CS_ETMV4_TRCTRACEIDR] = " TRCTRACEIDR %llx\n",
[CS_ETMV4_TRCIDR0] = " TRCIDR0 %llx\n",
[CS_ETMV4_TRCIDR1] = " TRCIDR1 %llx\n",
[CS_ETMV4_TRCIDR2] = " TRCIDR2 %llx\n",
[CS_ETMV4_TRCIDR8] = " TRCIDR8 %llx\n",
[CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n",
};
static void cs_etm__print_auxtrace_info(__u64 *val, int num)
{
int i, j, cpu = 0;
for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
fprintf(stdout, cs_etm_global_header_fmts[i], val[i]);
for (i = CS_HEADER_VERSION_0_MAX; cpu < num; cpu++) {
if (val[i] == __perf_cs_etmv3_magic)
for (j = 0; j < CS_ETM_PRIV_MAX; j++, i++)
fprintf(stdout, cs_etm_priv_fmts[j], val[i]);
else if (val[i] == __perf_cs_etmv4_magic)
for (j = 0; j < CS_ETMV4_PRIV_MAX; j++, i++)
fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]);
else
/* failure.. return */
return;
}
}
int cs_etm__process_auxtrace_info(union perf_event *event,
struct perf_session *session)
{
struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
struct cs_etm_auxtrace *etm = NULL;
struct int_node *inode;
unsigned int pmu_type;
int event_header_size = sizeof(struct perf_event_header);
int info_header_size;
int total_size = auxtrace_info->header.size;
int priv_size = 0;
int num_cpu;
int err = 0, idx = -1;
int i, j, k;
u64 *ptr, *hdr = NULL;
u64 **metadata = NULL;
/*
* sizeof(auxtrace_info_event::type) +
* sizeof(auxtrace_info_event::reserved) == 8
*/
info_header_size = 8;
if (total_size < (event_header_size + info_header_size))
return -EINVAL;
priv_size = total_size - event_header_size - info_header_size;
/* First the global part */
ptr = (u64 *) auxtrace_info->priv;
/* Look for version '0' of the header */
if (ptr[0] != 0)
return -EINVAL;
hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_0_MAX);
if (!hdr)
return -ENOMEM;
/* Extract header information - see cs-etm.h for format */
for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
hdr[i] = ptr[i];
num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff;
pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) &
0xffffffff);
/*
* Create an RB tree for traceID-metadata tuple. Since the conversion
* has to be made for each packet that gets decoded, optimizing access
* in anything other than a sequential array is worth doing.
*/
traceid_list = intlist__new(NULL);
if (!traceid_list) {
err = -ENOMEM;
goto err_free_hdr;
}
metadata = zalloc(sizeof(*metadata) * num_cpu);
if (!metadata) {
err = -ENOMEM;
goto err_free_traceid_list;
}
/*
* The metadata is stored in the auxtrace_info section and encodes
* the configuration of the ARM embedded trace macrocell which is
* required by the trace decoder to properly decode the trace due
* to its highly compressed nature.
*/
for (j = 0; j < num_cpu; j++) {
if (ptr[i] == __perf_cs_etmv3_magic) {
metadata[j] = zalloc(sizeof(*metadata[j]) *
CS_ETM_PRIV_MAX);
if (!metadata[j]) {
err = -ENOMEM;
goto err_free_metadata;
}
for (k = 0; k < CS_ETM_PRIV_MAX; k++)
metadata[j][k] = ptr[i + k];
/* The traceID is our handle */
idx = metadata[j][CS_ETM_ETMTRACEIDR];
i += CS_ETM_PRIV_MAX;
} else if (ptr[i] == __perf_cs_etmv4_magic) {
metadata[j] = zalloc(sizeof(*metadata[j]) *
CS_ETMV4_PRIV_MAX);
if (!metadata[j]) {
err = -ENOMEM;
goto err_free_metadata;
}
for (k = 0; k < CS_ETMV4_PRIV_MAX; k++)
metadata[j][k] = ptr[i + k];
/* The traceID is our handle */
idx = metadata[j][CS_ETMV4_TRCTRACEIDR];
i += CS_ETMV4_PRIV_MAX;
}
/* Get an RB node for this CPU */
inode = intlist__findnew(traceid_list, idx);
/* Something went wrong, no need to continue */
if (!inode) {
err = -ENOMEM;
goto err_free_metadata;
}
/*
* The node for that CPU should not be taken.
* Back out if that's the case.
*/
if (inode->priv) {
err = -EINVAL;
goto err_free_metadata;
}
/* All good, associate the traceID with the metadata pointer */
inode->priv = metadata[j];
}
/*
* Each of CS_HEADER_VERSION_0_MAX, CS_ETM_PRIV_MAX and
* CS_ETMV4_PRIV_MAX mark how many double words are in the
* global metadata, and each cpu's metadata respectively.
* The following tests if the correct number of double words was
* present in the auxtrace info section.
*/
if (i * 8 != priv_size) {
err = -EINVAL;
goto err_free_metadata;
}
etm = zalloc(sizeof(*etm));
if (!etm) {
err = -ENOMEM;
goto err_free_metadata;
}
err = auxtrace_queues__init(&etm->queues);
if (err)
goto err_free_etm;
etm->session = session;
etm->machine = &session->machines.host;
etm->num_cpu = num_cpu;
etm->pmu_type = pmu_type;
etm->snapshot_mode = (hdr[CS_ETM_SNAPSHOT] != 0);
etm->metadata = metadata;
etm->auxtrace_type = auxtrace_info->type;
etm->timeless_decoding = cs_etm__is_timeless_decoding(etm);
etm->auxtrace.process_event = cs_etm__process_event;
etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
etm->auxtrace.flush_events = cs_etm__flush_events;
etm->auxtrace.free_events = cs_etm__free_events;
etm->auxtrace.free = cs_etm__free;
session->auxtrace = &etm->auxtrace;
etm->unknown_thread = thread__new(999999999, 999999999);
if (!etm->unknown_thread) {
err = -ENOMEM;
goto err_free_queues;
}
/*
* Initialize list node so that at thread__zput() we can avoid
* segmentation fault at list_del_init().
*/
INIT_LIST_HEAD(&etm->unknown_thread->node);
err = thread__set_comm(etm->unknown_thread, "unknown", 0);
if (err)
goto err_delete_thread;
if (thread__init_map_groups(etm->unknown_thread, etm->machine)) {
err = -ENOMEM;
goto err_delete_thread;
}
if (dump_trace) {
cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
return 0;
}
if (session->itrace_synth_opts->set) {
etm->synth_opts = *session->itrace_synth_opts;
} else {
itrace_synth_opts__set_default(&etm->synth_opts,
session->itrace_synth_opts->default_no_sample);
etm->synth_opts.callchain = false;
}
err = cs_etm__synth_events(etm, session);
if (err)
goto err_delete_thread;
err = auxtrace_queues__process_index(&etm->queues, session);
if (err)
goto err_delete_thread;
etm->data_queued = etm->queues.populated;
return 0;
err_delete_thread:
thread__zput(etm->unknown_thread);
err_free_queues:
auxtrace_queues__free(&etm->queues);
session->auxtrace = NULL;
err_free_etm:
zfree(&etm);
err_free_metadata:
/* No need to check @metadata[j], free(NULL) is supported */
for (j = 0; j < num_cpu; j++)
zfree(&metadata[j]);
zfree(&metadata);
err_free_traceid_list:
intlist__delete(traceid_list);
err_free_hdr:
zfree(&hdr);
return err;
}
|