diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index de165a1b9240..20b56eb987f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -521,6 +521,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	/*
+	 * Normally perf_session__new would do this, but it doesn't have the
+	 * evlist.
+	 */
+	if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
+		pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		rec->tool.ordered_events = false;
+	}
+
 	if (!rec->evlist->nr_groups)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
@@ -965,9 +974,11 @@ static struct record record = {
 	.tool = {
 		.sample		= process_sample_event,
 		.fork		= perf_event__process_fork,
+		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
+		.ordered_events	= true,
 	},
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecf319728f25..6135cc07213c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -601,8 +601,8 @@ static void display_sig(int sig __maybe_unused)
 
 static void display_setup_sig(void)
 {
-	signal(SIGSEGV, display_sig);
-	signal(SIGFPE,  display_sig);
+	signal(SIGSEGV, sighandler_dump_stack);
+	signal(SIGFPE, sighandler_dump_stack);
 	signal(SIGINT,  display_sig);
 	signal(SIGQUIT, display_sig);
 	signal(SIGTERM, display_sig);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7ff682770fdb..f1a4c833121e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1387,6 +1387,24 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 							event->fork.ptid);
 	int err = 0;
 
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	/*
+	 * There may be an existing thread that is not actually the parent,
+	 * either because we are processing events out of order, or because the
+	 * (fork) event that would have removed the thread was lost. Assume the
+	 * latter case and continue on as best we can.
+	 */
+	if (parent->pid_ != (pid_t)event->fork.ppid) {
+		dump_printf("removing erroneous parent thread %d/%d\n",
+			    parent->pid_, parent->tid);
+		machine__remove_thread(machine, parent);
+		thread__put(parent);
+		parent = machine__findnew_thread(machine, event->fork.ppid,
+						 event->fork.ptid);
+	}
+
 	/* if a thread currently exists for the thread id remove it */
 	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
@@ -1395,8 +1413,6 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
-	if (dump_trace)
-		perf_event__fprintf_task(event, stdout);
 
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28c4b746baa1..0a9ae8014729 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -191,6 +191,12 @@ static int thread__clone_map_groups(struct thread *thread,
 	if (thread->pid_ == parent->pid_)
 		return 0;
 
+	if (thread->mg == parent->mg) {
+		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
+			 thread->pid_, thread->tid, parent->pid_, parent->tid);
+		return 0;
+	}
+
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		if (map_groups__clone(thread->mg, parent->mg, i) < 0)