perf stat: Use affinity for enabling/disabling events

Restructure event enabling/disabling to use affinity, which
minimizes the number of IPIs needed.

Before on a large test case with 94 CPUs:

  % time     seconds  usecs/call     calls    errors syscall
  ------ ----------- ----------- --------- --------- ----------------
   54.65    1.899986          22     84812       660 ioctl

after:

   39.21    0.930451          10     84796       644 ioctl
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-13-andi@firstfloor.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/evlist.c

@@ -378,11 +378,28 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
 void evlist__disable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	int cpu, i;
+
+	if (affinity__setup(&affinity) < 0)
+		return;
+
+	evlist__for_each_cpu(evlist, i, cpu) {
+		affinity__set(&affinity, cpu);
 
+		evlist__for_each_entry(evlist, pos) {
+			if (evsel__cpu_iter_skip(pos, cpu))
+				continue;
+			if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__disable_cpu(pos, pos->cpu_iter - 1);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
-		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__disable(pos);
+		pos->disabled = true;
 	}
 
 	evlist->enabled = false;
@@ -391,11 +408,28 @@ void evlist__disable(struct evlist *evlist)
 void evlist__enable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	int cpu, i;
 
+	if (affinity__setup(&affinity) < 0)
+		return;
+
+	evlist__for_each_cpu(evlist, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evlist, pos) {
+			if (evsel__cpu_iter_skip(pos, cpu))
+				continue;
+			if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__enable_cpu(pos, pos->cpu_iter - 1);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__enable(pos);
+		pos->disabled = false;
 	}
 
 	evlist->enabled = true;