perf tool_pmu: Allow num_cpus(_online) to be specific to a cpumask

For hybrid metrics it is useful to know the number of p-core or e-core
CPUs. If a cpumask is specified for the num_cpus or num_cpus_online
tool events, compute the value relative to the given mask rather than
for the full system.

```
$ sudo /tmp/perf/perf stat -e 'tool/num_cpus/,tool/num_cpus,cpu=cpu_core/,
  tool/num_cpus,cpu=cpu_atom/,tool/num_cpus_online/,tool/num_cpus_online,
  cpu=cpu_core/,tool/num_cpus_online,cpu=cpu_atom/' true

 Performance counter stats for 'true':

                28      tool/num_cpus/
                16      tool/num_cpus,cpu=cpu_core/
                12      tool/num_cpus,cpu=cpu_atom/
                28      tool/num_cpus_online/
                16      tool/num_cpus_online,cpu=cpu_core/
                12      tool/num_cpus_online,cpu=cpu_atom/

       0.000767205 seconds time elapsed

       0.000938000 seconds user
       0.000000000 seconds sys
```

Reviewed-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20250719030517.1990983-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

tools/perf/util/expr.c

@@ -401,7 +401,7 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
 	if (ev != TOOL_PMU__EVENT_NONE) {
 		u64 count;
 
-		if (tool_pmu__read_event(ev, &count))
+		if (tool_pmu__read_event(ev, /*evsel=*/NULL, &count))
 			result = count;
 		else
 			pr_err("Failure to read '%s'", literal);

tools/perf/util/tool_pmu.c

@@ -332,7 +332,7 @@ static bool has_pmem(void)
 	return has_pmem;
 }
 
-bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result)
+bool tool_pmu__read_event(enum tool_pmu_event ev, struct evsel *evsel, u64 *result)
 {
 	const struct cpu_topology *topology;
 
@@ -347,18 +347,60 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result)
 		return true;
 
 	case TOOL_PMU__EVENT_NUM_CPUS:
-		*result = cpu__max_present_cpu().cpu;
+		if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) {
+			/* No evsel to be specific to. */
+			*result = cpu__max_present_cpu().cpu;
+		} else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) {
+			/* Evsel just has specific CPUs. */
+			*result = perf_cpu_map__nr(evsel->core.cpus);
+		} else {
+			/*
+			 * "Any CPU" event that can be scheduled on any CPU in
+			 * the PMU's cpumask. The PMU cpumask should be saved in
+			 * own_cpus. If not present fall back to max.
+			 */
+			if (!perf_cpu_map__is_empty(evsel->core.own_cpus))
+				*result = perf_cpu_map__nr(evsel->core.own_cpus);
+			else
+				*result = cpu__max_present_cpu().cpu;
+		}
 		return true;
 
 	case TOOL_PMU__EVENT_NUM_CPUS_ONLINE: {
 		struct perf_cpu_map *online = cpu_map__online();
 
-		if (online) {
+		if (!online)
+			return false;
+
+		if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) {
+			/* No evsel to be specific to. */
 			*result = perf_cpu_map__nr(online);
-			perf_cpu_map__put(online);
-			return true;
+		} else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) {
+			/* Evsel just has specific CPUs. */
+			struct perf_cpu_map *tmp =
+				perf_cpu_map__intersect(online, evsel->core.cpus);
+
+			*result = perf_cpu_map__nr(tmp);
+			perf_cpu_map__put(tmp);
+		} else {
+			/*
+			 * "Any CPU" event that can be scheduled on any CPU in
+			 * the PMU's cpumask. The PMU cpumask should be saved in
+			 * own_cpus, if not present then just the online cpu
+			 * mask.
+			 */
+			if (!perf_cpu_map__is_empty(evsel->core.own_cpus)) {
+				struct perf_cpu_map *tmp =
+					perf_cpu_map__intersect(online, evsel->core.own_cpus);
+
+				*result = perf_cpu_map__nr(tmp);
+				perf_cpu_map__put(tmp);
+			} else {
+				*result = perf_cpu_map__nr(online);
+			}
 		}
-		return false;
+		perf_cpu_map__put(online);
+		return true;
 	}
 	case TOOL_PMU__EVENT_NUM_DIES:
 		topology = online_topology();
@@ -417,7 +459,7 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 			old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
 		val = 0;
 		if (cpu_map_idx == 0 && thread == 0) {
-			if (!tool_pmu__read_event(ev, &val)) {
+			if (!tool_pmu__read_event(ev, evsel, &val)) {
 				count->lost++;
 				val = 0;
 			}

tools/perf/util/tool_pmu.h

@@ -34,7 +34,7 @@ enum tool_pmu_event tool_pmu__str_to_event(const char *str);
 bool tool_pmu__skip_event(const char *name);
 int tool_pmu__num_skip_events(void);
 
-bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result);
+bool tool_pmu__read_event(enum tool_pmu_event ev, struct evsel *evsel, u64 *result);
 
 u64 tool_pmu__cpu_slots_per_cycle(void);