perf bpf_counter: Fix opening of "any"(-1) CPU events

The bperf BPF counter code doesn't handle "any"(-1) CPU events, always
wanting to aggregate a count against a CPU, which avoids the need for
atomics so let's not change that. Force evsels used for BPF counters
to require a CPU when not in system-wide mode so that the "any"(-1)
value isn't used during map propagation and evsel's CPU map matches
that of the PMU.

Fixes: b91917c0c6fa ("perf bpf_counter: Fix handling of cpumap fixing hybrid")
Signed-off-by: Ian Rogers <[e-mail]>
Signed-off-by: Namhyung Kim <[e-mail]>

tools/perf/builtin-stat.c

···
 	unsigned int interval, timeout;
 	const char * const stat_subcommands[] = { "record", "report" };
 	char errbuf[BUFSIZ];
+	struct evsel *counter;
 
 	setlocale(LC_ALL, "");
 
···
 	}
 
 	evlist__warn_user_requested_cpus(evsel_list, target.cpu_list);
+
+	evlist__for_each_entry(evsel_list, counter) {
+		/*
+		 * Setup BPF counters to require CPUs as any(-1) isn't
+		 * supported. evlist__create_maps below will propagate this
+		 * information to the evsels. Note, evsel__is_bperf isn't yet
+		 * set up, and this change must happen early, so directly use
+		 * the bpf_counter variable and target information.
+		 */
+		if ((counter->bpf_counter || target.use_bpf) && !target__has_cpu(&target))
+			counter->core.requires_cpu = true;
+	}
 
 	if (evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {

tools/perf/util/bpf_counter.c

···
 	struct bperf_leader_bpf *skel = bperf_leader_bpf__open();
 	int link_fd, diff_map_fd, err;
 	struct bpf_link *link = NULL;
+	struct perf_thread_map *threads;
 
 	if (!skel) {
 		pr_err("Failed to open leader skeleton\n");
···
 	 * following evsel__open_per_cpu call
 	 */
 	evsel->leader_skel = skel;
-	evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
+	assert(!perf_cpu_map__has_any_cpu_or_is_empty(evsel->core.cpus));
+	/* Always open system wide. */
+	threads = thread_map__new_by_tid(-1);
+	evsel__open(evsel, evsel->core.cpus, threads);
+	perf_thread_map__put(threads);
 
 out:
 	bperf_leader_bpf__destroy(skel);