perf stat: Support metrics with hybrid events

One metric such as 'Kernel_Utilization' may be from different PMUs and
consists of different events.

For core,
Kernel_Utilization = cpu_clk_unhalted.thread:k / cpu_clk_unhalted.thread

For atom,
Kernel_Utilization = cpu_clk_unhalted.core:k / cpu_clk_unhalted.core

The metric group string for core is:
'{cpu_clk_unhalted.thread/metric-id=cpu_clk_unhalted.thread:k/k,cpu_clk_unhalted.thread/metric-id=cpu_clk_unhalted.thread/}:W'
It's internally expanded to:
'{cpu_clk_unhalted.thread_p/metric-id=cpu_clk_unhalted.thread_p:k/k,cpu_clk_unhalted.thread/metric-id=cpu_clk_unhalted.thread/}:W#cpu_core'

The metric group string for atom is:
'{cpu_clk_unhalted.core/metric-id=cpu_clk_unhalted.core:k/k,cpu_clk_unhalted.core/metric-id=cpu_clk_unhalted.core/}:W'
It's internally expanded to:
'{cpu_clk_unhalted.core/metric-id=cpu_clk_unhalted.core:k/k,cpu_clk_unhalted.core/metric-id=cpu_clk_unhalted.core/}:W#cpu_atom'

That means the group "{cpu_clk_unhalted.thread:k,cpu_clk_unhalted.thread}:W"
is from cpu_core PMU and the group "{cpu_clk_unhalted.core:k,cpu_clk_unhalted.core}"
is from cpu_atom PMU. And then next, check if the events in the group are
valid on that PMU. If one event is not valid on that PMU, the associated
group would be removed internally.

In this example, cpu_clk_unhalted.thread is valid on cpu_core and
cpu_clk_unhalted.core is valid on cpu_atom. So the checks for these two
groups are passed.

Before:

  # ./perf stat -M Kernel_Utilization -a sleep 1
WARNING: events in group from different hybrid PMUs!
WARNING: grouped events cpus do not match, disabling group:
  anon group { CPU_CLK_UNHALTED.THREAD_P:k, CPU_CLK_UNHALTED.THREAD_P:k, CPU_CLK_UNHALTED.THREAD, CPU_CLK_UNHALTED.THREAD }

 Performance counter stats for 'system wide':

        17,639,501      cpu_atom/CPU_CLK_UNHALTED.CORE/ #     1.00 Kernel_Utilization
        17,578,757      cpu_atom/CPU_CLK_UNHALTED.CORE:k/
     1,005,350,226 ns   duration_time
        43,012,352      cpu_core/CPU_CLK_UNHALTED.THREAD_P:k/ #     0.99 Kernel_Utilization
        17,608,010      cpu_atom/CPU_CLK_UNHALTED.THREAD_P:k/
        43,608,755      cpu_core/CPU_CLK_UNHALTED.THREAD/
        17,630,838      cpu_atom/CPU_CLK_UNHALTED.THREAD/
     1,005,350,226 ns   duration_time

       1.005350226 seconds time elapsed

After:

  # ./perf stat -M Kernel_Utilization -a sleep 1

 Performance counter stats for 'system wide':

        17,981,895      CPU_CLK_UNHALTED.CORE [cpu_atom] #     1.00 Kernel_Utilization
        17,925,405      CPU_CLK_UNHALTED.CORE:k [cpu_atom]
     1,004,811,366 ns   duration_time
        41,246,425      CPU_CLK_UNHALTED.THREAD_P:k [cpu_core] #     0.99 Kernel_Utilization
        41,819,129      CPU_CLK_UNHALTED.THREAD [cpu_core]
     1,004,811,366 ns   duration_time

       1.004811366 seconds time elapsed
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220422065635.767648-1-zhengjun.xing@linux.intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/stat-display.c

@@ -539,7 +539,8 @@ static void aggr_update_shadow(struct perf_stat_config *config,
 	}
 }
 
-static void uniquify_event_name(struct evsel *counter)
+static void uniquify_event_name(struct evsel *counter,
+				struct perf_stat_config *stat_config)
 {
 	char *new_name;
 	char *config;
@@ -558,7 +559,8 @@ static void uniquify_event_name(struct evsel *counter)
 			counter->name = new_name;
 		}
 	} else {
-		if (perf_pmu__has_hybrid()) {
+		if (perf_pmu__has_hybrid() &&
+		    stat_config->metric_events.nr_entries == 0) {
 			ret = asprintf(&new_name, "%s/%s/",
 				       counter->pmu_name, counter->name);
 		} else {
@@ -619,7 +621,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 		return false;
 	cb(config, counter, data, true);
 	if (config->no_merge || hybrid_uniquify(counter))
-		uniquify_event_name(counter);
+		uniquify_event_name(counter, config);
 	else if (counter->auto_merge_stats)
 		collect_all_aliases(config, counter, cb, data);
 	return true;