perf stat: Take cgroups into account for shadow stats

As of now it doesn't consider cgroups when collecting shadow stats and
metrics so counter values from different cgroups will be saved in a same
slot. This resulted in incorrect numbers when those cgroups have
different workloads.

For example, let's look at the scenario below: cgroups A and C runs same
workload which burns a cpu while cgroup B runs a light workload.

$ perf stat -a -e cycles,instructions --for-each-cgroup A,B,C sleep 1

Performance counter stats for 'system wide':

3,958,116,522 cycles A
6,722,650,929 instructions A # 2.53 insn per cycle
1,132,741 cycles B
571,743 instructions B # 0.00 insn per cycle
4,007,799,935 cycles C
6,793,181,523 instructions C # 2.56 insn per cycle

1.001050869 seconds time elapsed

When I run 'perf stat' with single workload, it usually shows IPC around
1.7. We can verify it (6,722,650,929.0 / 3,958,116,522 = 1.698) for cgroup A.

But in this case, since cgroups are ignored, cycles are averaged so it
used the lower value for IPC calculation and resulted in around 2.5.

avg cycle: (3958116522 + 1132741 + 4007799935) / 3 = 2655683066
IPC (A) : 6722650929 / 2655683066 = 2.531
IPC (B) : 571743 / 2655683066 = 0.0002
IPC (C) : 6793181523 / 2655683066 = 2.557

We can simply compare cgroup pointers in the evsel and it'll be NULL
when cgroups are not specified. With this patch, I can see correct
numbers like below:

$ perf stat -a -e cycles,instructions --for-each-cgroup A,B,C sleep 1

Performance counter stats for 'system wide':

4,171,051,687 cycles A
7,219,793,922 instructions A # 1.73 insn per cycle
1,051,189 cycles B
583,102 instructions B # 0.55 insn per cycle
4,171,124,710 cycles C
7,192,944,580 instructions C # 1.72 insn per cycle

1.007909814 seconds time elapsed

Signed-off-by: Namhyung Kim <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Jin Yao <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/stat-shadow.c

···
 #include "evlist.h"
 #include "expr.h"
 #include "metricgroup.h"
+#include "cgroup.h"
 #include <linux/zalloc.h>
 
 /*
···
 	enum stat_type type;
 	int ctx;
 	int cpu;
+	struct cgroup *cgrp;
 	struct runtime_stat *stat;
 	struct stats stats;
 	u64 metric_total;
···
 
 	if (a->ctx != b->ctx)
 		return a->ctx - b->ctx;
+
+	if (a->cgrp != b->cgrp)
+		return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
 
 	if (a->evsel == NULL && b->evsel == NULL) {
 		if (a->stat == b->stat)
···
 					      bool create,
 					      enum stat_type type,
 					      int ctx,
-					      struct runtime_stat *st)
+					      struct runtime_stat *st,
+					      struct cgroup *cgrp)
 {
 	struct rblist *rblist;
 	struct rb_node *nd;
···
 		.type = type,
 		.ctx = ctx,
 		.stat = st,
+		.cgrp = cgrp,
 	};
 
 	rblist = &st->value_list;
···
 
 struct runtime_stat_data {
 	int ctx;
+	struct cgroup *cgrp;
 };
 
 static void update_runtime_stat(struct runtime_stat *st,
···
 				struct runtime_stat_data *rsd)
 {
 	struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
-						   rsd->ctx, st);
+						   rsd->ctx, st, rsd->cgrp);
 
 	if (v)
 		update_stats(&v->stats, count);
···
 	struct saved_value *v;
 	struct runtime_stat_data rsd = {
 		.ctx = evsel_context(counter),
+		.cgrp = counter->cgrp,
 	};
 
 	count *= counter->scale;
···
 		update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
 
 	if (counter->collect_stat) {
-		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+				       rsd.cgrp);
 		update_stats(&v->stats, count);
 		if (counter->metric_leader)
 			v->metric_total += count;
 	} else if (counter->metric_leader) {
 		v = saved_value_lookup(counter->metric_leader,
-				       cpu, true, STAT_NONE, 0, st);
+				       cpu, true, STAT_NONE, 0, st, rsd.cgrp);
 		v->metric_total += count;
 		v->metric_other++;
 	}
···
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
···
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
···
 			scale = 1e-9;
 		} else {
 			v = saved_value_lookup(metric_events[i], cpu, false,
-					       STAT_NONE, 0, st);
+					       STAT_NONE, 0, st,
+					       metric_events[i]->cgrp);
 			if (!v)
 				break;
 			stats = &v->stats;
···
 	const char *color = NULL;
 	struct runtime_stat_data rsd = {
 		.ctx = evsel_context(evsel),
+		.cgrp = evsel->cgrp,
 	};
 	struct metric_event *me;
 	int num = 1;