@@ -4528,6 +4528,7 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
{
unsigned long flags;
int ret = 0;
+ int event_cpu;
/*
* Disabling interrupts avoids all counter scheduling (context
@@ -4551,15 +4552,19 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
goto out;
}
+ /* Allow reading a per-package perf-event from local CPU also */
+ event_cpu = READ_ONCE(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_cpu != smp_processor_id()) {
ret = -EBUSY;
goto out;
}
@@ -4569,7 +4574,7 @@ 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_cpu == smp_processor_id())
event->pmu->read(event);
*value = local64_read(&event->count);
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> --- kernel/events/core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)