diff --git a/kernel/events/core.c b/kernel/events/core.c
index 479c9e672ec4371219d89cf35d16cb9470a9bc4c..76c754e45d012a4a8cfbe53dfdb38b936186aaec 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2462,7 +2462,11 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
 	 * event_function_call() user.
 	 */
 	raw_spin_lock_irq(&ctx->lock);
-	if (!ctx->is_active) {
+	/*
+	 * Cgroup events are per-cpu events, and must IPI because of
+	 * cgrp_cpuctx_list.
+	 */
+	if (!ctx->is_active && !is_cgroup_event(event)) {
 		__perf_remove_from_context(event, __get_cpu_context(ctx),
 					   ctx, (void *)flags);
 		raw_spin_unlock_irq(&ctx->lock);
@@ -2895,11 +2899,14 @@ perf_install_in_context(struct perf_event_context *ctx,
 	 * perf_event_attr::disabled events will not run and can be initialized
 	 * without IPI. Except when this is the first event for the context, in
 	 * that case we need the magic of the IPI to set ctx->is_active.
+	 * Similarly, cgroup events for the context also needs the IPI to
+	 * manipulate the cgrp_cpuctx_list.
 	 *
 	 * The IOC_ENABLE that is sure to follow the creation of a disabled
 	 * event will issue the IPI and reprogram the hardware.
 	 */
-	if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && ctx->nr_events) {
+	if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF &&
+	    ctx->nr_events && !is_cgroup_event(event)) {
 		raw_spin_lock_irq(&ctx->lock);
 		if (ctx->task == TASK_TOMBSTONE) {
 			raw_spin_unlock_irq(&ctx->lock);
@@ -5985,6 +5992,8 @@ static void ring_buffer_attach(struct perf_event *event,
 	struct perf_buffer *old_rb = NULL;
 	unsigned long flags;
 
+	WARN_ON_ONCE(event->parent);
+
 	if (event->rb) {
 		/*
 		 * Should be impossible, we set this when removing
@@ -6042,6 +6051,9 @@ static void ring_buffer_wakeup(struct perf_event *event)
 {
 	struct perf_buffer *rb;
 
+	if (event->parent)
+		event = event->parent;
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
 	if (rb) {
@@ -6055,6 +6067,9 @@ struct perf_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct perf_buffer *rb;
 
+	if (event->parent)
+		event = event->parent;
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
 	if (rb) {
@@ -6763,7 +6778,7 @@ static unsigned long perf_prepare_sample_aux(struct perf_event *event,
 	if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id()))
 		goto out;
 
-	rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler);
+	rb = ring_buffer_get(sampler);
 	if (!rb)
 		goto out;
 
@@ -6829,7 +6844,7 @@ static void perf_aux_sample_output(struct perf_event *event,
 	if (WARN_ON_ONCE(!sampler || !data->aux_size))
 		return;
 
-	rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler);
+	rb = ring_buffer_get(sampler);
 	if (!rb)
 		return;