diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 46fe5cfb5163..09915ae06d28 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -424,6 +424,11 @@ struct pmu {
 	 */
 	size_t				task_ctx_size;
 
+	/*
+	 * Kmem cache of PMU specific data
+	 */
+	struct kmem_cache		*task_ctx_cache;
+
 	/*
 	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
 	 * can be synchronized using this function. See Intel LBR callstack support
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 75090403f942..30d9b3182369 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1240,12 +1240,18 @@ static void get_ctx(struct perf_event_context *ctx)
 
 static void *alloc_task_ctx_data(struct pmu *pmu)
 {
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
 	return kzalloc(pmu->task_ctx_size, GFP_KERNEL);
 }
 
 static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
 {
-	kfree(task_ctx_data);
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+	else
+		kfree(task_ctx_data);
 }
 
 static void free_ctx(struct rcu_head *head)