summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/cs-etm.c
blob: 1b0d422373be5e8dce853cd15a312b22355147ce (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
/*
 * 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 <stdlib.h>

#include "auxtrace.h"
#include "color.h"
#include "cs-etm.h"
#include "cs-etm-decoder/cs-etm-decoder.h"
#include "debug.h"
#include "evlist.h"
#include "intlist.h"
#include "machine.h"
#include "map.h"
#include "perf.h"
#include "thread.h"
#include "thread_map.h"
#include "thread-stack.h"
#include "util.h"

#define MAX_TIMESTAMP (~0ULL)

/*
 * A64 instructions are always 4 bytes
 *
 * Only A64 is supported, so can use this constant for converting between
 * addresses and instruction counts, calculting offsets etc
 */
#define A64_INSTR_SIZE 4

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_queue {
	struct cs_etm_auxtrace *etm;
	struct thread *thread;
	struct cs_etm_decoder *decoder;
	struct auxtrace_buffer *buffer;
	const struct cs_etm_state *state;
	union perf_event *event_buf;
	unsigned int queue_nr;
	pid_t pid, tid;
	int cpu;
	u64 time;
	u64 timestamp;
	u64 offset;
	u64 period_instructions;
	struct branch_stack *last_branch;
	struct branch_stack *last_branch_rb;
	size_t last_branch_pos;
	struct cs_etm_packet *prev_packet;
	struct cs_etm_packet *packet;
};

static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
					   pid_t tid, u64 time_);

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__dump_event(struct cs_etm_auxtrace *etm,
			       struct auxtrace_buffer *buffer)
{
	int i, 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);
	for (i = 0; i < etm->num_cpu; i++) {
		t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
		t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
		t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
		t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
		t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
		t_params[i].etmv4.reg_configr =
					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
		t_params[i].etmv4.reg_traceidr =
					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
	}

	/* Set decoder parameters to simply print the trace packets */
	d_params.packet_printer = cs_etm__packet_dump;
	d_params.operation = CS_ETM_OPERATION_PRINT;
	d_params.formatted = true;
	d_params.fsyncs = false;
	d_params.hsyncs = false;
	d_params.frame_aligned = true;

	decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);

	zfree(&t_params);

	if (!decoder)
		return;
	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);
}

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;

	if (!etm->timeless_decoding)
		return -EINVAL;

	ret = cs_etm__update_queues(etm);

	if (ret < 0)
		return ret;

	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
}

static void cs_etm__free_queue(void *priv)
{
	struct cs_etm_queue *etmq = priv;

	if (!etmq)
		return;

	thread__zput(etmq->thread);
	cs_etm_decoder__free(etmq->decoder);
	zfree(&etmq->event_buf);
	zfree(&etmq->last_branch);
	zfree(&etmq->last_branch_rb);
	zfree(&etmq->prev_packet);
	zfree(&etmq->packet);
	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/CPU# 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]);

	zfree(&aux->metadata);
	zfree(&aux);
}

static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
			      size_t size, u8 *buffer)
{
	u8  cpumode;
	u64 offset;
	int len;
	struct	 thread *thread;
	struct	 machine *machine;
	struct	 addr_location al;

	if (!etmq)
		return -1;

	machine = etmq->etm->machine;
	if (address >= etmq->etm->kernel_start)
		cpumode = PERF_RECORD_MISC_KERNEL;
	else
		cpumode = PERF_RECORD_MISC_USER;

	thread = etmq->thread;
	if (!thread) {
		if (cpumode != PERF_RECORD_MISC_KERNEL)
			return -EINVAL;
		thread = etmq->etm->unknown_thread;
	}

	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);

	if (!al.map || !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,
						unsigned int queue_nr)
{
	int i;
	struct cs_etm_decoder_params d_params;
	struct cs_etm_trace_params  *t_params;
	struct cs_etm_queue *etmq;
	size_t szp = sizeof(struct cs_etm_packet);

	etmq = zalloc(sizeof(*etmq));
	if (!etmq)
		return NULL;

	etmq->packet = zalloc(szp);
	if (!etmq->packet)
		goto out_free;

	if (etm->synth_opts.last_branch || etm->sample_branches) {
		etmq->prev_packet = zalloc(szp);
		if (!etmq->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);
		etmq->last_branch = zalloc(sz);
		if (!etmq->last_branch)
			goto out_free;
		etmq->last_branch_rb = zalloc(sz);
		if (!etmq->last_branch_rb)
			goto out_free;
	}

	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
	if (!etmq->event_buf)
		goto out_free;

	etmq->etm = etm;
	etmq->queue_nr = queue_nr;
	etmq->pid = -1;
	etmq->tid = -1;
	etmq->cpu = -1;

	/* 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;

	for (i = 0; i < etm->num_cpu; i++) {
		t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
		t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
		t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
		t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
		t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
		t_params[i].etmv4.reg_configr =
					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
		t_params[i].etmv4.reg_traceidr =
					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
	}

	/* Set decoder parameters to simply print the trace packets */
	d_params.packet_printer = cs_etm__packet_dump;
	d_params.operation = CS_ETM_OPERATION_DECODE;
	d_params.formatted = true;
	d_params.fsyncs = false;
	d_params.hsyncs = false;
	d_params.frame_aligned = true;
	d_params.data = etmq;

	etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);

	zfree(&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;

	etmq->offset = 0;
	etmq->period_instructions = 0;

	return etmq;

out_free_decoder:
	cs_etm_decoder__free(etmq->decoder);
out_free:
	zfree(&etmq->event_buf);
	zfree(&etmq->last_branch);
	zfree(&etmq->last_branch_rb);
	zfree(&etmq->prev_packet);
	zfree(&etmq->packet);
	free(etmq);

	return NULL;
}

static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
			       struct auxtrace_queue *queue,
			       unsigned int queue_nr)
{
	struct cs_etm_queue *etmq = queue->priv;

	if (list_empty(&queue->head) || etmq)
		return 0;

	etmq = cs_etm__alloc_queue(etm, queue_nr);

	if (!etmq)
		return -ENOMEM;

	queue->priv = etmq;

	if (queue->cpu != -1)
		etmq->cpu = queue->cpu;

	etmq->tid = queue->tid;

	return 0;
}

static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
{
	unsigned int i;
	int ret;

	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 branch_stack *bs_src = etmq->last_branch_rb;
	struct branch_stack *bs_dst = etmq->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 - etmq->last_branch_pos;
	memcpy(&bs_dst->entries[0],
	       &bs_src->entries[etmq->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) * etmq->last_branch_pos);
	}
}

static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
{
	etmq->last_branch_pos = 0;
	etmq->last_branch_rb->nr = 0;
}

static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
{
	/*
	 * The packet records the execution range with an exclusive end address
	 *
	 * A64 instructions are constant size, so the last executed
	 * instruction is A64_INSTR_SIZE before the end address
	 * Will need to do instruction level decode for T32 instructions as
	 * they can be variable size (not yet supported).
	 */
	return packet->end_addr - A64_INSTR_SIZE;
}

static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
{
	/*
	 * Only A64 instructions are currently supported, so can get
	 * instruction count by dividing.
	 * Will need to do instruction level decode for T32 instructions as
	 * they can be variable size (not yet supported).
	 */
	return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE;
}

static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet,
				     u64 offset)
{
	/*
	 * Only A64 instructions are currently supported, so can get
	 * instruction address by muliplying.
	 * Will need to do instruction level decode for T32 instructions as
	 * they can be variable size (not yet supported).
	 */
	return packet->start_addr + offset * A64_INSTR_SIZE;
}

static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
{
	struct branch_stack *bs = etmq->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 (!etmq->last_branch_pos)
		etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;

	etmq->last_branch_pos -= 1;

	be       = &bs->entries[etmq->last_branch_pos];
	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
	be->to	 = etmq->packet->start_addr;
	/* 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_buffer *buff, 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);
		buff->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);

	buff->offset = aux_buffer->offset;
	buff->len = aux_buffer->size;
	buff->buf = aux_buffer->data;

	buff->ref_timestamp = aux_buffer->reference;

	return buff->len;
}

static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
				     struct auxtrace_queue *queue)
{
	struct cs_etm_queue *etmq = queue->priv;

	/* CPU-wide tracing isn't supported yet */
	if (queue->tid == -1)
		return;

	if ((!etmq->thread) && (etmq->tid != -1))
		etmq->thread = machine__find_thread(etm->machine, -1,
						    etmq->tid);

	if (etmq->thread) {
		etmq->pid = etmq->thread->pid_;
		if (queue->cpu == -1)
			etmq->cpu = etmq->thread->cpu;
	}
}

static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
					    u64 addr, u64 period)
{
	int ret = 0;
	struct cs_etm_auxtrace *etm = etmq->etm;
	union perf_event *event = etmq->event_buf;
	struct perf_sample sample = {.ip = 0,};

	event->sample.header.type = PERF_RECORD_SAMPLE;
	event->sample.header.misc = PERF_RECORD_MISC_USER;
	event->sample.header.size = sizeof(struct perf_event_header);

	sample.ip = addr;
	sample.pid = etmq->pid;
	sample.tid = etmq->tid;
	sample.id = etmq->etm->instructions_id;
	sample.stream_id = etmq->etm->instructions_id;
	sample.period = period;
	sample.cpu = etmq->packet->cpu;
	sample.flags = 0;
	sample.insn_len = 1;
	sample.cpumode = event->header.misc;

	if (etm->synth_opts.last_branch) {
		cs_etm__copy_last_branch_rb(etmq);
		sample.branch_stack = etmq->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(etmq);

	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)
{
	int ret = 0;
	struct cs_etm_auxtrace *etm = etmq->etm;
	struct perf_sample sample = {.ip = 0,};
	union perf_event *event = etmq->event_buf;
	struct dummy_branch_stack {
		u64			nr;
		struct branch_entry	entries;
	} dummy_bs;

	event->sample.header.type = PERF_RECORD_SAMPLE;
	event->sample.header.misc = PERF_RECORD_MISC_USER;
	event->sample.header.size = sizeof(struct perf_event_header);

	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
	sample.pid = etmq->pid;
	sample.tid = etmq->tid;
	sample.addr = etmq->packet->start_addr;
	sample.id = etmq->etm->branches_id;
	sample.stream_id = etmq->etm->branches_id;
	sample.period = 1;
	sample.cpu = etmq->packet->cpu;
	sample.flags = 0;
	sample.cpumode = PERF_RECORD_MISC_USER;

	/*
	 * 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 perf_evlist *evlist = session->evlist;
	struct perf_evsel *evsel;
	struct perf_event_attr attr;
	bool found = false;
	u64 id;
	int err;

	evlist__for_each_entry(evlist, evsel) {
		if (evsel->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->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->attr.exclude_user;
	attr.exclude_kernel = evsel->attr.exclude_kernel;
	attr.exclude_hv = evsel->attr.exclude_hv;
	attr.exclude_host = evsel->attr.exclude_host;
	attr.exclude_guest = evsel->attr.exclude_guest;
	attr.sample_id_all = evsel->attr.sample_id_all;
	attr.read_format = evsel->attr.read_format;

	/* create new id val to be a fixed offset from evsel id */
	id = evsel->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_auxtrace *etm = etmq->etm;
	struct cs_etm_packet *tmp;
	int ret;
	u64 instrs_executed;

	instrs_executed = cs_etm__instr_count(etmq->packet);
	etmq->period_instructions += instrs_executed;

	/*
	 * Record a branch when the last instruction in
	 * PREV_PACKET is a branch.
	 */
	if (etm->synth_opts.last_branch &&
	    etmq->prev_packet &&
	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
	    etmq->prev_packet->last_instr_taken_branch)
		cs_etm__update_last_branch_rb(etmq);

	if (etm->sample_instructions &&
	    etmq->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 = etmq->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->packet, offset);

		ret = cs_etm__synth_instruction_sample(
			etmq, addr, etm->instructions_sample_period);
		if (ret)
			return ret;

		/* Carry remaining instructions into next sample period */
		etmq->period_instructions = instrs_over;
	}

	if (etm->sample_branches &&
	    etmq->prev_packet &&
	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
	    etmq->prev_packet->last_instr_taken_branch) {
		ret = cs_etm__synth_branch_sample(etmq);
		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 = etmq->packet;
		etmq->packet = etmq->prev_packet;
		etmq->prev_packet = tmp;
	}

	return 0;
}

static int cs_etm__flush(struct cs_etm_queue *etmq)
{
	int err = 0;
	struct cs_etm_packet *tmp;

	if (etmq->etm->synth_opts.last_branch &&
	    etmq->prev_packet &&
	    etmq->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(etmq->prev_packet);

		err = cs_etm__synth_instruction_sample(
			etmq, addr,
			etmq->period_instructions);
		etmq->period_instructions = 0;

		/*
		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
		 * the next incoming packet.
		 */
		tmp = etmq->packet;
		etmq->packet = etmq->prev_packet;
		etmq->prev_packet = tmp;
	}

	return err;
}

static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
{
	struct cs_etm_auxtrace *etm = etmq->etm;
	struct cs_etm_buffer buffer;
	size_t buffer_used, processed;
	int err = 0;

	if (!etm->kernel_start)
		etm->kernel_start = machine__kernel_start(etm->machine);

	/* Go through each buffer in the queue and decode them one by one */
	while (1) {
		buffer_used = 0;
		memset(&buffer, 0, sizeof(buffer));
		err = cs_etm__get_trace(&buffer, etmq);
		if (err <= 0)
			return err;
		/*
		 * We cannot assume consecutive blocks in the data file are
		 * contiguous, reset the decoder to force re-sync.
		 */
		err = cs_etm_decoder__reset(etmq->decoder);
		if (err != 0)
			return err;

		/* Run trace decoder until buffer consumed or end of trace */
		do {
			processed = 0;
			err = cs_etm_decoder__process_data_block(
				etmq->decoder,
				etmq->offset,
				&buffer.buf[buffer_used],
				buffer.len - buffer_used,
				&processed);
			if (err)
				return err;

			etmq->offset += processed;
			buffer_used += processed;

			/* Process each packet in this chunk */
			while (1) {
				err = cs_etm_decoder__get_packet(etmq->decoder,
								 etmq->packet);
				if (err <= 0)
					/*
					 * Stop processing this chunk on
					 * end of data or error
					 */
					break;

				switch (etmq->packet->sample_type) {
				case CS_ETM_RANGE:
					/*
					 * If the packet contains an instruction
					 * range, generate instruction sequence
					 * events.
					 */
					cs_etm__sample(etmq);
					break;
				case CS_ETM_TRACE_ON:
					/*
					 * Discontinuity in trace, flush
					 * previous branch stack
					 */
					cs_etm__flush(etmq);
					break;
				default:
					break;
				}
			}
		} while (buffer.len > buffer_used);

		if (err == 0)
			/* Flush any remaining branch stack entries */
			err = cs_etm__flush(etmq);
	}

	return err;
}

static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
					   pid_t tid, u64 time_)
{
	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;

		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
			etmq->time = time_;
			cs_etm__set_pid_tid_cpu(etm, queue);
			cs_etm__run_decoder(etmq);
		}
	}

	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 (!etm->timeless_decoding)
		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 (event->header.type == PERF_RECORD_EXIT)
		return cs_etm__process_timeless_queues(etm,
						       event->fork.tid,
						       sample->time);

	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 perf_evsel *evsel;
	struct perf_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->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 auxtrace_info_event *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-CPU# 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 = PTR_ERR(inode);
			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 CPU# */
		inode->priv = &metadata[j][CS_ETM_CPU];
	}

	/*
	 * 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;

	if (dump_trace) {
		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
		return 0;
	}

	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
		etm->synth_opts = *session->itrace_synth_opts;
	} else {
		itrace_synth_opts__set_default(&etm->synth_opts);
		etm->synth_opts.callchain = false;
	}

	err = cs_etm__synth_events(etm, session);
	if (err)
		goto err_free_queues;

	err = auxtrace_queues__process_index(&etm->queues, session);
	if (err)
		goto err_free_queues;

	etm->data_queued = etm->queues.populated;

	return 0;

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++)
		free(metadata[j]);
	zfree(&metadata);
err_free_traceid_list:
	intlist__delete(traceid_list);
err_free_hdr:
	zfree(&hdr);

	return -EINVAL;
}
OpenPOWER on IntegriCloud