perf/core: Allow reading package events from perf_event_read_local

Per-package perf events are typically registered with a single CPU only,
however they can be read across all the CPUs within the package.
Currently perf_event_read maps the event CPU according to the topology
information to avoid an unnecessary SMP call, however
perf_event_read_local deals with hard values and rejects a read with a
failure if the CPU is not the one exactly registered. Allow similar
mapping within the perf_event_read_local if the perf event in question
can support this.

This allows users like BPF code to read the package perf events properly
across different CPUs within a package.
Signed-off-by: Tero Kristo <tero.kristo@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230913125956.3652667-1-tero.kristo@linux.intel.com

kernel/events/core.c

@@ -4425,6 +4425,9 @@ static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
 	u16 local_pkg, event_pkg;
 
+	if ((unsigned)event_cpu >= nr_cpu_ids)
+		return event_cpu;
+
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
 		int local_cpu = smp_processor_id();
 
@@ -4527,6 +4530,8 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 			  u64 *enabled, u64 *running)
 {
 	unsigned long flags;
+	int event_oncpu;
+	int event_cpu;
 	int ret = 0;
 
 	/*
@@ -4551,15 +4556,22 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 		goto out;
 	}
 
+	/*
+	 * Get the event CPU numbers, and adjust them to local if the event is
+	 * a per-package event that can be read locally
+	 */
+	event_oncpu = __perf_event_read_cpu(event, event->oncpu);
+	event_cpu = __perf_event_read_cpu(event, event->cpu);
+
 	/* If this is a per-CPU event, it must be for this CPU */
 	if (!(event->attach_state & PERF_ATTACH_TASK) &&
-	    event->cpu != smp_processor_id()) {
+	    event_cpu != smp_processor_id()) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* If this is a pinned event it must be running on this CPU */
-	if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+	if (event->attr.pinned && event_oncpu != smp_processor_id()) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -4569,7 +4581,7 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
 	 * oncpu == -1).
 	 */
-	if (event->oncpu == smp_processor_id())
+	if (event_oncpu == smp_processor_id())
 		event->pmu->read(event);
 
 	*value = local64_read(&event->count);