Mathieu Poirier [off-list ref] writes:

+static void etm_event_destroy(struct perf_event *event)
+{
+	/* switching off the source will also tear down the path */
+	etm_event_power_sources(event->cpu, false);
+}
+
+static int etm_event_init(struct perf_event *event)
+{
+	int ret;
+
+	if (event->attr.type != etm_pmu.type)
+		return -ENOENT;
+
+	if (event->cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	/* only one session at a time */
+	if (etm_event_source_enabled(event->cpu))
+		return -EBUSY;

Why is this the case? If you were to configure the event in pmu::add()
and deconfigure it in pmu::del(), like you already do with the buffer
part, you could handle as many sessions as you want.

+
+	/*
+	 * Make sure CPUs don't disappear between the
+	 * power up sequence and configuration.
+	 */
+	get_online_cpus();
+	ret = etm_event_power_sources(event->cpu, true);
+	if (ret)
+		goto out;
+
+	ret = etm_event_config_sources(event->cpu);

This can be done in pmu::add(), if you can call directly into
etm_configure_cpu() or etm_config_enable() so that there's no cross-cpu
calling in between.

One general comment -- it would be slightly easier at least for me if
all the pmu related bits were in one patch.

Thanks,
--
Alex