perf: Account freq events globally

Freq events may not always be affine to a particular CPU. As such,
account_event_cpu() may crash if we account per cpu a freq event
that has event->cpu == -1.

To solve this, lets account freq events globally. In practice
this doesn't change much the picture because perf tools create
per-task perf events with one event per CPU by default. Profiling a
single CPU is usually a corner case so there is no much point in
optimizing things that way.

Reported-by: Jiri Olsa <[e-mail]>
Suggested-by: Peter Zijlstra <[e-mail]>
Signed-off-by: Frederic Weisbecker <[e-mail]>
Tested-by: Jiri Olsa <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Signed-off-by: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

kernel/events/core.c

···
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
-static DEFINE_PER_CPU(atomic_t, perf_freq_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
+static atomic_t nr_freq_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
···
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, task_ctx);
 
-	if (atomic_read(&__get_cpu_var(perf_freq_events)))
-		tick_nohz_full_kick();
-
 	return 0;
 }
 
···
 #ifdef CONFIG_NO_HZ_FULL
 bool perf_event_can_stop_tick(void)
 {
-	if (atomic_read(&__get_cpu_var(perf_freq_events)) ||
+	if (atomic_read(&nr_freq_events) ||
 	    __this_cpu_read(perf_throttled_count))
 		return false;
 	else
···
 	}
 	if (is_cgroup_event(event))
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
-
-	if (event->attr.freq)
-		atomic_dec(&per_cpu(perf_freq_events, cpu));
 }
 
 static void unaccount_event(struct perf_event *event)
···
 		atomic_dec(&nr_comm_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
+	if (event->attr.freq)
+		atomic_dec(&nr_freq_events);
 	if (is_cgroup_event(event))
 		static_key_slow_dec_deferred(&perf_sched_events);
 	if (has_branch_stack(event))
···
 	}
 	if (is_cgroup_event(event))
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
-
-	if (event->attr.freq)
-		atomic_inc(&per_cpu(perf_freq_events, cpu));
 }
 
 static void account_event(struct perf_event *event)
···
 		atomic_inc(&nr_comm_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
+	if (event->attr.freq) {
+		if (atomic_inc_return(&nr_freq_events) == 1)
+			tick_nohz_full_kick_all();
+	}
 	if (has_branch_stack(event))
 		static_key_slow_inc(&perf_sched_events.key);
 	if (is_cgroup_event(event))