summaryrefslogtreecommitdiff
path: root/tools/perf/util/stat-shadow.c
blob: 8ad32763cffff718751f374e2eeb4f07a43bad6f (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
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include "evsel.h"
#include "stat.h"
#include "color.h"
#include "pmu.h"
#include "rblist.h"
#include "evlist.h"
#include "expr.h"
#include "metricgroup.h"

/*
 * AGGR_GLOBAL: Use CPU 0
 * AGGR_SOCKET: Use first CPU of socket
 * AGGR_CORE: Use first CPU of core
 * AGGR_NONE: Use matching CPU
 * AGGR_THREAD: Not supported?
 */
static bool have_frontend_stalled;

struct runtime_stat rt_stat;
struct stats walltime_nsecs_stats;

struct saved_value {
	struct rb_node rb_node;
	struct perf_evsel *evsel;
	enum stat_type type;
	int ctx;
	int cpu;
	struct runtime_stat *stat;
	struct stats stats;
};

static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
{
	struct saved_value *a = container_of(rb_node,
					     struct saved_value,
					     rb_node);
	const struct saved_value *b = entry;

	if (a->cpu != b->cpu)
		return a->cpu - b->cpu;

	/*
	 * Previously the rbtree was used to link generic metrics.
	 * The keys were evsel/cpu. Now the rbtree is extended to support
	 * per-thread shadow stats. For shadow stats case, the keys
	 * are cpu/type/ctx/stat (evsel is NULL). For generic metrics
	 * case, the keys are still evsel/cpu (type/ctx/stat are 0 or NULL).
	 */
	if (a->type != b->type)
		return a->type - b->type;

	if (a->ctx != b->ctx)
		return a->ctx - b->ctx;

	if (a->evsel == NULL && b->evsel == NULL) {
		if (a->stat == b->stat)
			return 0;

		if ((char *)a->stat < (char *)b->stat)
			return -1;

		return 1;
	}

	if (a->evsel == b->evsel)
		return 0;
	if ((char *)a->evsel < (char *)b->evsel)
		return -1;
	return +1;
}

static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
				     const void *entry)
{
	struct saved_value *nd = malloc(sizeof(struct saved_value));

	if (!nd)
		return NULL;
	memcpy(nd, entry, sizeof(struct saved_value));
	return &nd->rb_node;
}

static void saved_value_delete(struct rblist *rblist __maybe_unused,
			       struct rb_node *rb_node)
{
	struct saved_value *v;

	BUG_ON(!rb_node);
	v = container_of(rb_node, struct saved_value, rb_node);
	free(v);
}

static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
					      int cpu,
					      bool create,
					      enum stat_type type,
					      int ctx,
					      struct runtime_stat *st)
{
	struct rblist *rblist;
	struct rb_node *nd;
	struct saved_value dm = {
		.cpu = cpu,
		.evsel = evsel,
		.type = type,
		.ctx = ctx,
		.stat = st,
	};

	rblist = &st->value_list;

	nd = rblist__find(rblist, &dm);
	if (nd)
		return container_of(nd, struct saved_value, rb_node);
	if (create) {
		rblist__add_node(rblist, &dm);
		nd = rblist__find(rblist, &dm);
		if (nd)
			return container_of(nd, struct saved_value, rb_node);
	}
	return NULL;
}

void runtime_stat__init(struct runtime_stat *st)
{
	struct rblist *rblist = &st->value_list;

	rblist__init(rblist);
	rblist->node_cmp = saved_value_cmp;
	rblist->node_new = saved_value_new;
	rblist->node_delete = saved_value_delete;
}

void runtime_stat__exit(struct runtime_stat *st)
{
	rblist__exit(&st->value_list);
}

void perf_stat__init_shadow_stats(void)
{
	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
	runtime_stat__init(&rt_stat);
}

static int evsel_context(struct perf_evsel *evsel)
{
	int ctx = 0;

	if (evsel->attr.exclude_kernel)
		ctx |= CTX_BIT_KERNEL;
	if (evsel->attr.exclude_user)
		ctx |= CTX_BIT_USER;
	if (evsel->attr.exclude_hv)
		ctx |= CTX_BIT_HV;
	if (evsel->attr.exclude_host)
		ctx |= CTX_BIT_HOST;
	if (evsel->attr.exclude_idle)
		ctx |= CTX_BIT_IDLE;

	return ctx;
}

static void reset_stat(struct runtime_stat *st)
{
	struct rblist *rblist;
	struct rb_node *pos, *next;

	rblist = &st->value_list;
	next = rb_first(&rblist->entries);
	while (next) {
		pos = next;
		next = rb_next(pos);
		memset(&container_of(pos, struct saved_value, rb_node)->stats,
		       0,
		       sizeof(struct stats));
	}
}

void perf_stat__reset_shadow_stats(void)
{
	reset_stat(&rt_stat);
	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
}

void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
{
	reset_stat(st);
}

static void update_runtime_stat(struct runtime_stat *st,
				enum stat_type type,
				int ctx, int cpu, u64 count)
{
	struct saved_value *v = saved_value_lookup(NULL, cpu, true,
						   type, ctx, st);

	if (v)
		update_stats(&v->stats, count);
}

/*
 * Update various tracking values we maintain to print
 * more semantic information such as miss/hit ratios,
 * instruction rates, etc:
 */
void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
				    int cpu, struct runtime_stat *st)
{
	int ctx = evsel_context(counter);

	count *= counter->scale;

	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
		update_runtime_stat(st, STAT_NSECS, 0, cpu, count);
	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
		update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
		update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, ELISION_START))
		update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
		update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
				    ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
				    ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
				    ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
		update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
				    ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
				    ctx, cpu, count);
	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
				    ctx, cpu, count);
	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
		update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
				    ctx, cpu, count);
	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
		update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
		update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
		update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
		update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
		update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
		update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
		update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, SMI_NUM))
		update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
	else if (perf_stat_evsel__is(counter, APERF))
		update_runtime_stat(st, STAT_APERF, ctx, cpu, count);

	if (counter->collect_stat) {
		struct saved_value *v = saved_value_lookup(counter, cpu, true,
							   STAT_NONE, 0, st);
		update_stats(&v->stats, count);
	}
}

/* used for get_ratio_color() */
enum grc_type {
	GRC_STALLED_CYCLES_FE,
	GRC_STALLED_CYCLES_BE,
	GRC_CACHE_MISSES,
	GRC_MAX_NR
};

static const char *get_ratio_color(enum grc_type type, double ratio)
{
	static const double grc_table[GRC_MAX_NR][3] = {
		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
	};
	const char *color = PERF_COLOR_NORMAL;

	if (ratio > grc_table[type][0])
		color = PERF_COLOR_RED;
	else if (ratio > grc_table[type][1])
		color = PERF_COLOR_MAGENTA;
	else if (ratio > grc_table[type][2])
		color = PERF_COLOR_YELLOW;

	return color;
}

static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
						const char *name)
{
	struct perf_evsel *c2;

	evlist__for_each_entry (evsel_list, c2) {
		if (!strcasecmp(c2->name, name))
			return c2;
	}
	return NULL;
}

/* Mark MetricExpr target events and link events using them to them. */
void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
{
	struct perf_evsel *counter, *leader, **metric_events, *oc;
	bool found;
	const char **metric_names;
	int i;
	int num_metric_names;

	evlist__for_each_entry(evsel_list, counter) {
		bool invalid = false;

		leader = counter->leader;
		if (!counter->metric_expr)
			continue;
		metric_events = counter->metric_events;
		if (!metric_events) {
			if (expr__find_other(counter->metric_expr, counter->name,
						&metric_names, &num_metric_names) < 0)
				continue;

			metric_events = calloc(sizeof(struct perf_evsel *),
					       num_metric_names + 1);
			if (!metric_events)
				return;
			counter->metric_events = metric_events;
		}

		for (i = 0; i < num_metric_names; i++) {
			found = false;
			if (leader) {
				/* Search in group */
				for_each_group_member (oc, leader) {
					if (!strcasecmp(oc->name, metric_names[i])) {
						found = true;
						break;
					}
				}
			}
			if (!found) {
				/* Search ignoring groups */
				oc = perf_stat__find_event(evsel_list, metric_names[i]);
			}
			if (!oc) {
				/* Deduping one is good enough to handle duplicated PMUs. */
				static char *printed;

				/*
				 * Adding events automatically would be difficult, because
				 * it would risk creating groups that are not schedulable.
				 * perf stat doesn't understand all the scheduling constraints
				 * of events. So we ask the user instead to add the missing
				 * events.
				 */
				if (!printed || strcasecmp(printed, metric_names[i])) {
					fprintf(stderr,
						"Add %s event to groups to get metric expression for %s\n",
						metric_names[i],
						counter->name);
					printed = strdup(metric_names[i]);
				}
				invalid = true;
				continue;
			}
			metric_events[i] = oc;
			oc->collect_stat = true;
		}
		metric_events[i] = NULL;
		free(metric_names);
		if (invalid) {
			free(metric_events);
			counter->metric_events = NULL;
			counter->metric_expr = NULL;
		}
	}
}

static double runtime_stat_avg(struct runtime_stat *st,
			       enum stat_type type, int ctx, int cpu)
{
	struct saved_value *v;

	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
	if (!v)
		return 0.0;

	return avg_stats(&v->stats);
}

static double runtime_stat_n(struct runtime_stat *st,
			     enum stat_type type, int ctx, int cpu)
{
	struct saved_value *v;

	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
	if (!v)
		return 0.0;

	return v->stats.n;
}

static void print_stalled_cycles_frontend(struct perf_stat_config *config,
					  int cpu,
					  struct perf_evsel *evsel, double avg,
					  struct perf_stat_output_ctx *out,
					  struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);

	if (ratio)
		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
				  ratio);
	else
		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
}

static void print_stalled_cycles_backend(struct perf_stat_config *config,
					 int cpu,
					 struct perf_evsel *evsel, double avg,
					 struct perf_stat_output_ctx *out,
					 struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);

	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
}

static void print_branch_misses(struct perf_stat_config *config,
				int cpu,
				struct perf_evsel *evsel,
				double avg,
				struct perf_stat_output_ctx *out,
				struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);

	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
}

static void print_l1_dcache_misses(struct perf_stat_config *config,
				   int cpu,
				   struct perf_evsel *evsel,
				   double avg,
				   struct perf_stat_output_ctx *out,
				   struct runtime_stat *st)

{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);

	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
}

static void print_l1_icache_misses(struct perf_stat_config *config,
				   int cpu,
				   struct perf_evsel *evsel,
				   double avg,
				   struct perf_stat_output_ctx *out,
				   struct runtime_stat *st)

{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
}

static void print_dtlb_cache_misses(struct perf_stat_config *config,
				    int cpu,
				    struct perf_evsel *evsel,
				    double avg,
				    struct perf_stat_output_ctx *out,
				    struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
}

static void print_itlb_cache_misses(struct perf_stat_config *config,
				    int cpu,
				    struct perf_evsel *evsel,
				    double avg,
				    struct perf_stat_output_ctx *out,
				    struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
}

static void print_ll_cache_misses(struct perf_stat_config *config,
				  int cpu,
				  struct perf_evsel *evsel,
				  double avg,
				  struct perf_stat_output_ctx *out,
				  struct runtime_stat *st)
{
	double total, ratio = 0.0;
	const char *color;
	int ctx = evsel_context(evsel);

	total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);

	if (total)
		ratio = avg / total * 100.0;

	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
}

/*
 * High level "TopDown" CPU core pipe line bottleneck break down.
 *
 * Basic concept following
 * Yasin, A Top Down Method for Performance analysis and Counter architecture
 * ISPASS14
 *
 * The CPU pipeline is divided into 4 areas that can be bottlenecks:
 *
 * Frontend -> Backend -> Retiring
 * BadSpeculation in addition means out of order execution that is thrown away
 * (for example branch mispredictions)
 * Frontend is instruction decoding.
 * Backend is execution, like computation and accessing data in memory
 * Retiring is good execution that is not directly bottlenecked
 *
 * The formulas are computed in slots.
 * A slot is an entry in the pipeline each for the pipeline width
 * (for example a 4-wide pipeline has 4 slots for each cycle)
 *
 * Formulas:
 * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) /
 *			TotalSlots
 * Retiring = SlotsRetired / TotalSlots
 * FrontendBound = FetchBubbles / TotalSlots
 * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound
 *
 * The kernel provides the mapping to the low level CPU events and any scaling
 * needed for the CPU pipeline width, for example:
 *
 * TotalSlots = Cycles * 4
 *
 * The scaling factor is communicated in the sysfs unit.
 *
 * In some cases the CPU may not be able to measure all the formulas due to
 * missing events. In this case multiple formulas are combined, as possible.
 *
 * Full TopDown supports more levels to sub-divide each area: for example
 * BackendBound into computing bound and memory bound. For now we only
 * support Level 1 TopDown.
 */

static double sanitize_val(double x)
{
	if (x < 0 && x >= -0.02)
		return 0.0;
	return x;
}

static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
{
	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
}

static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
{
	double bad_spec = 0;
	double total_slots;
	double total;

	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);

	total_slots = td_total_slots(ctx, cpu, st);
	if (total_slots)
		bad_spec = total / total_slots;
	return sanitize_val(bad_spec);
}

static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
{
	double retiring = 0;
	double total_slots = td_total_slots(ctx, cpu, st);
	double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
					    ctx, cpu);

	if (total_slots)
		retiring = ret_slots / total_slots;
	return retiring;
}

static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
{
	double fe_bound = 0;
	double total_slots = td_total_slots(ctx, cpu, st);
	double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
					    ctx, cpu);

	if (total_slots)
		fe_bound = fetch_bub / total_slots;
	return fe_bound;
}

static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
{
	double sum = (td_fe_bound(ctx, cpu, st) +
		      td_bad_spec(ctx, cpu, st) +
		      td_retiring(ctx, cpu, st));
	if (sum == 0)
		return 0;
	return sanitize_val(1.0 - sum);
}

static void print_smi_cost(struct perf_stat_config *config,
			   int cpu, struct perf_evsel *evsel,
			   struct perf_stat_output_ctx *out,
			   struct runtime_stat *st)
{
	double smi_num, aperf, cycles, cost = 0.0;
	int ctx = evsel_context(evsel);
	const char *color = NULL;

	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
	aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
	cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);

	if ((cycles == 0) || (aperf == 0))
		return;

	if (smi_num)
		cost = (aperf - cycles) / aperf * 100.00;

	if (cost > 10)
		color = PERF_COLOR_RED;
	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
}

static void generic_metric(struct perf_stat_config *config,
			   const char *metric_expr,
			   struct perf_evsel **metric_events,
			   char *name,
			   const char *metric_name,
			   double avg,
			   int cpu,
			   struct perf_stat_output_ctx *out,
			   struct runtime_stat *st)
{
	print_metric_t print_metric = out->print_metric;
	struct parse_ctx pctx;
	double ratio;
	int i;
	void *ctxp = out->ctx;

	expr__ctx_init(&pctx);
	expr__add_id(&pctx, name, avg);
	for (i = 0; metric_events[i]; i++) {
		struct saved_value *v;
		struct stats *stats;
		double scale;

		if (!strcmp(metric_events[i]->name, "duration_time")) {
			stats = &walltime_nsecs_stats;
			scale = 1e-9;
		} else {
			v = saved_value_lookup(metric_events[i], cpu, false,
					       STAT_NONE, 0, st);
			if (!v)
				break;
			stats = &v->stats;
			scale = 1.0;
		}
		expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
	}
	if (!metric_events[i]) {
		const char *p = metric_expr;

		if (expr__parse(&ratio, &pctx, &p) == 0)
			print_metric(config, ctxp, NULL, "%8.1f",
				metric_name ?
				metric_name :
				out->force_header ?  name : "",
				ratio);
		else
			print_metric(config, ctxp, NULL, NULL,
				     out->force_header ?
				     (metric_name ? metric_name : name) : "", 0);
	} else
		print_metric(config, ctxp, NULL, NULL, "", 0);
}

void perf_stat__print_shadow_stats(struct perf_stat_config *config,
				   struct perf_evsel *evsel,
				   double avg, int cpu,
				   struct perf_stat_output_ctx *out,
				   struct rblist *metric_events,
				   struct runtime_stat *st)
{
	void *ctxp = out->ctx;
	print_metric_t print_metric = out->print_metric;
	double total, ratio = 0.0, total2;
	const char *color = NULL;
	int ctx = evsel_context(evsel);
	struct metric_event *me;
	int num = 1;

	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);

		if (total) {
			ratio = avg / total;
			print_metric(config, ctxp, NULL, "%7.2f ",
					"insn per cycle", ratio);
		} else {
			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
		}

		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
					 ctx, cpu);

		total = max(total, runtime_stat_avg(st,
						    STAT_STALLED_CYCLES_BACK,
						    ctx, cpu));

		if (total && avg) {
			out->new_line(config, ctxp);
			ratio = total / avg;
			print_metric(config, ctxp, NULL, "%7.2f ",
					"stalled cycles per insn",
					ratio);
		} else if (have_frontend_stalled) {
			print_metric(config, ctxp, NULL, NULL,
				     "stalled cycles per insn", 0);
		}
	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
			print_branch_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
	} else if (
		evsel->attr.type == PERF_TYPE_HW_CACHE &&
		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {

		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
	} else if (
		evsel->attr.type == PERF_TYPE_HW_CACHE &&
		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {

		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
	} else if (
		evsel->attr.type == PERF_TYPE_HW_CACHE &&
		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {

		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
	} else if (
		evsel->attr.type == PERF_TYPE_HW_CACHE &&
		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {

		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
	} else if (
		evsel->attr.type == PERF_TYPE_HW_CACHE &&
		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {

		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
		else
			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);

		if (total)
			ratio = avg * 100 / total;

		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
			print_metric(config, ctxp, NULL, "%8.3f %%",
				     "of all cache refs", ratio);
		else
			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);

		if (total) {
			ratio = avg / total;
			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
		} else {
			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
		}
	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);

		if (total)
			print_metric(config, ctxp, NULL,
					"%7.2f%%", "transactional cycles",
					100.0 * (avg / total));
		else
			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
				     0);
	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);

		if (total2 < avg)
			total2 = avg;
		if (total)
			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
				100.0 * ((total2-avg) / total));
		else
			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
					 ctx, cpu);

		if (avg)
			ratio = total / avg;

		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
			print_metric(config, ctxp, NULL, "%8.0f",
				     "cycles / transaction", ratio);
		else
			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
				      0);
	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
					 ctx, cpu);

		if (avg)
			ratio = total / avg;

		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
	} else if (perf_evsel__is_clock(evsel)) {
		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
				     avg / (ratio * evsel->scale));
		else
			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
		double fe_bound = td_fe_bound(ctx, cpu, st);

		if (fe_bound > 0.2)
			color = PERF_COLOR_RED;
		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
				fe_bound * 100.);
	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
		double retiring = td_retiring(ctx, cpu, st);

		if (retiring > 0.7)
			color = PERF_COLOR_GREEN;
		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
				retiring * 100.);
	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
		double bad_spec = td_bad_spec(ctx, cpu, st);

		if (bad_spec > 0.1)
			color = PERF_COLOR_RED;
		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
				bad_spec * 100.);
	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
		double be_bound = td_be_bound(ctx, cpu, st);
		const char *name = "backend bound";
		static int have_recovery_bubbles = -1;

		/* In case the CPU does not support topdown-recovery-bubbles */
		if (have_recovery_bubbles < 0)
			have_recovery_bubbles = pmu_have_event("cpu",
					"topdown-recovery-bubbles");
		if (!have_recovery_bubbles)
			name = "backend bound/bad spec";

		if (be_bound > 0.2)
			color = PERF_COLOR_RED;
		if (td_total_slots(ctx, cpu, st) > 0)
			print_metric(config, ctxp, color, "%8.1f%%", name,
					be_bound * 100.);
		else
			print_metric(config, ctxp, NULL, NULL, name, 0);
	} else if (evsel->metric_expr) {
		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
				evsel->metric_name, avg, cpu, out, st);
	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
		char unit = 'M';
		char unit_buf[10];

		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);

		if (total)
			ratio = 1000.0 * avg / total;
		if (ratio < 0.001) {
			ratio *= 1000;
			unit = 'K';
		}
		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
		print_smi_cost(config, cpu, evsel, out, st);
	} else {
		num = 0;
	}

	if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
		struct metric_expr *mexp;

		list_for_each_entry (mexp, &me->head, nd) {
			if (num++ > 0)
				out->new_line(config, ctxp);
			generic_metric(config, mexp->metric_expr, mexp->metric_events,
					evsel->name, mexp->metric_name,
					avg, cpu, out, st);
		}
	}
	if (num == 0)
		print_metric(config, ctxp, NULL, NULL, NULL, 0);
}