@@ -2165,8 +2165,9 @@ static void perf_group_detach(struct perf_event *event)
 	 * If this is a sibling, remove it from its group.
 	 */
 	if (leader != event) {
+		leader->nr_siblings--;
 		list_del_init(&event->sibling_list);
-		event->group_leader->nr_siblings--;
+		event->group_leader = event;
 		goto out;
 	}
 

@@ -2180,8 +2181,9 @@ static void perf_group_detach(struct perf_event *event)
 		if (sibling->event_caps & PERF_EV_CAP_SIBLING)
 			perf_remove_sibling_event(sibling);
 
-		sibling->group_leader = sibling;
+		leader->nr_siblings--;
 		list_del_init(&sibling->sibling_list);
+		sibling->group_leader = sibling;
 
 		/* Inherit group flags from the previous leader */
 		sibling->group_caps = event->group_caps;

@@ -2358,10 +2360,19 @@ __perf_remove_from_context(struct perf_event *event,
 static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
 {
 	struct perf_event_context *ctx = event->ctx;
+	bool remove;
 
 	lockdep_assert_held(&ctx->mutex);
 
-	event_function_call(event, __perf_remove_from_context, (void *)flags);
+	/*
+	 * There is concurrency vs remove_on_exec().
+	 */
+	raw_spin_lock_irq(&ctx->lock);
+	remove = (event->attach_state & PERF_ATTACH_CONTEXT);
+	raw_spin_unlock_irq(&ctx->lock);
+
+	if (remove)
+		event_function_call(event, __perf_remove_from_context, (void *)flags);
 
 	/*
 	 * The above event_function_call() can NO-OP when it hits

@@ -4198,41 +4209,68 @@ static void perf_event_enable_on_exec(int ctxn)
 static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *child_event,
 				  struct perf_event_context *child_ctx,
-				  struct task_struct *child);
+				  struct task_struct *child,
+				  bool removed);
 
 /*
  * Removes all events from the current task that have been marked
  * remove-on-exec, and feeds their values back to parent events.
  */
-static void perf_event_remove_on_exec(void)
+static void perf_event_remove_on_exec(int ctxn)
 {
-	int ctxn;
+	struct perf_event_context *ctx, *clone_ctx = NULL;
+	struct perf_event *event, *next;
+	LIST_HEAD(free_list);
+	unsigned long flags;
+	bool modified = false;
 
-	for_each_task_context_nr(ctxn) {
-		struct perf_event_context *ctx;
-		struct perf_event *event, *next;
+	ctx = perf_pin_task_context(current, ctxn);
+	if (!ctx)
+		return;
 
-		ctx = perf_pin_task_context(current, ctxn);
-		if (!ctx)
+	mutex_lock(&ctx->mutex);
+
+	if (WARN_ON_ONCE(ctx->task != current))
+		goto unlock;
+
+	list_for_each_entry_safe(event, next, &ctx->event_list, event_entry) {
+		struct perf_event *parent_event = event->parent;
+
+		if (!event->attr.remove_on_exec)
 			continue;
-		mutex_lock(&ctx->mutex);
 
-		list_for_each_entry_safe(event, next, &ctx->event_list, event_entry) {
-			if (!event->attr.remove_on_exec)
-				continue;
+		if (!is_kernel_event(event))
+			perf_remove_from_owner(event);
 
-			if (!is_kernel_event(event))
-				perf_remove_from_owner(event);
-			perf_remove_from_context(event, DETACH_GROUP);
+		modified = true;
+
+		if (parent_event) {
 			/*
-			 * Remove the event and feed back its values to the
-			 * parent event.
+			 * Remove event from parent, to avoid race where the
+			 * parent concurrently iterates through its children to
+			 * enable, disable, or otherwise modify an event.
 			 */
-			perf_event_exit_event(event, ctx, current);
+			mutex_lock(&parent_event->child_mutex);
+			list_del_init(&event->child_list);
+			mutex_unlock(&parent_event->child_mutex);
 		}
-		mutex_unlock(&ctx->mutex);
-		put_ctx(ctx);
+
+		perf_remove_from_context(event, !!event->parent * DETACH_GROUP);
+		perf_event_exit_event(event, ctx, current, true);
 	}
+
+	raw_spin_lock_irqsave(&ctx->lock, flags);
+	if (modified)
+		clone_ctx = unclone_ctx(ctx);
+	--ctx->pin_count;
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
+unlock:
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+	if (clone_ctx)
+		put_ctx(clone_ctx);
 }
 
 struct perf_read_data {

@@ -7581,20 +7619,18 @@ void perf_event_exec(void)
 	struct perf_event_context *ctx;
 	int ctxn;
 
-	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
-		ctx = current->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
 		perf_event_enable_on_exec(ctxn);
+		perf_event_remove_on_exec(ctxn);
 
-		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL,
-				   true);
+		rcu_read_lock();
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx) {
+			perf_iterate_ctx(ctx, perf_event_addr_filters_exec,
+					 NULL, true);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	perf_event_remove_on_exec();
 }
 
 struct remote_output {

@@ -12472,7 +12508,7 @@ static void sync_child_event(struct perf_event *child_event,
 static void
 perf_event_exit_event(struct perf_event *child_event,
 		      struct perf_event_context *child_ctx,
-		      struct task_struct *child)
+		      struct task_struct *child, bool removed)
 {
 	struct perf_event *parent_event = child_event->parent;
 

@@ -12489,12 +12525,15 @@ perf_event_exit_event(struct perf_event *child_event,
 	 * and being thorough is better.
 	 */
 	raw_spin_lock_irq(&child_ctx->lock);
-	WARN_ON_ONCE(child_ctx->is_active);
+	if (!removed) {
+		WARN_ON_ONCE(child_ctx->is_active);
 
-	if (parent_event)
-		perf_group_detach(child_event);
-	list_del_event(child_event, child_ctx);
-	perf_event_set_state(child_event, PERF_EVENT_STATE_EXIT); /* is_event_hup() */
+		if (parent_event)
+			perf_group_detach(child_event);
+		list_del_event(child_event, child_ctx);
+	}
+	if (child_event->state >= PERF_EVENT_STATE_EXIT)
+		perf_event_set_state(child_event, PERF_EVENT_STATE_EXIT); /* is_event_hup() */
 	raw_spin_unlock_irq(&child_ctx->lock);
 
 	/*

@@ -12580,7 +12619,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	perf_event_task(child, child_ctx, 0);
 
 	list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, child_ctx, child);
+		perf_event_exit_event(child_event, child_ctx, child, false);
 
 	mutex_unlock(&child_ctx->mutex);