[PATCH 3/4] perf: Check the supported CPU of an event

[kan.liang@linux.intel.com]

From: Kan Liang <kan.liang@linux.intel.com>

All architectures, which support the filter_match callback, check
whether an event is schedulable on the current CPU. Since the
supported_cpus is moved to struct pmu, the check can be done in the
generic code. The filter_match callback can be avoided for some
architecture, e.g., x86.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 kernel/events/core.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b172f54..7140f40 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2225,9 +2225,19 @@ static bool is_orphaned_event(struct perf_event *event)
 	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
+static __always_inline bool pmu_can_sched_on_this_cpu(struct pmu *pmu)
+{
+	return cpumask_empty(&pmu->supported_cpus) ||
+	       cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus);
+}
+
 static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
+
+	if (!pmu_can_sched_on_this_cpu(pmu))
+		return 0;
+
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
@@ -3825,7 +3835,7 @@ static inline void perf_event_context_update_hybrid(struct perf_event_context *c
 {
 	struct pmu *pmu = ctx->pmu;
 
-	if (cpumask_empty(&pmu->supported_cpus) || cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus))
+	if (pmu_can_sched_on_this_cpu(pmu))
 		return;
 
 	rcu_read_lock();
-- 
2.7.4