diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 26f83ad477260..8482440946260 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -748,7 +748,7 @@ void x86_pmu_enable_all(int added)
 	}
 }
 
-static inline int is_x86_event(struct perf_event *event)
+int is_x86_event(struct perf_event *event)
 {
 	int i;
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b3020243080e9..bc54741516d63 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4002,8 +4002,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 			x86_pmu.pebs_aliases(event);
 	}
 
-	if (needs_branch_stack(event) && is_sampling_event(event))
-		event->hw.flags  |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+	if (needs_branch_stack(event)) {
+		/* Avoid branch stack setup for counting events in SAMPLE READ */
+		if (is_sampling_event(event) ||
+		    !(event->attr.sample_type & PERF_SAMPLE_READ))
+			event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+	}
 
 	if (branch_sample_counters(event)) {
 		struct perf_event *leader, *sibling;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 79ed3ef2dda1e..6e40b55f68da1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,9 +110,16 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+	return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
 static inline bool is_branch_counters_group(struct perf_event *event)
 {
-	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
 }
 
 struct amd_nb {