diff -ur strace-5.5/delay.h strace-5.5.y/delay.h
--- strace-5.5/delay.h	2019-08-06 15:38:20.000000000 +0200
+++ strace-5.5.y/delay.h	2020-02-29 12:39:51.563110827 +0100
@@ -14,5 +14,6 @@
 void delay_timer_expired(void);
 void arm_delay_timer(const struct tcb *);
 void delay_tcb(struct tcb *, uint16_t delay_idx, bool isenter);
+int my_waitpid(int, int*, int);
 
 #endif /* !STRACE_DELAY_H */
diff -ur strace-5.5/filter_seccomp.c strace-5.5.y/filter_seccomp.c
--- strace-5.5/filter_seccomp.c	2020-02-06 16:16:17.000000000 +0100
+++ strace-5.5.y/filter_seccomp.c	2020-02-29 12:42:43.184120263 +0100
@@ -19,6 +19,7 @@
 #include "number_set.h"
 #include "syscall.h"
 #include "scno.h"
+#include "delay.h"
 
 bool seccomp_filtering;
 bool seccomp_before_sysentry;
@@ -136,7 +137,7 @@
 		int status;
 
 		for (;;) {
-			long rc = waitpid(pid, &status, 0);
+			long rc = my_waitpid(pid, &status, 0);
 			if (rc < 0 && errno == EINTR)
 				continue;
 			if (rc == pid)
@@ -272,7 +273,7 @@
 	if (pid) {
 		kill(pid, SIGKILL);
 		for (;;) {
-			long rc = waitpid(pid, NULL, 0);
+			long rc = my_waitpid(pid, NULL, 0);
 			if (rc < 0 && errno == EINTR)
 				continue;
 			break;
diff -ur strace-5.5/Makefile.am strace-5.5.y/Makefile.am
--- strace-5.5/Makefile.am	2020-02-06 16:16:17.000000000 +0100
+++ strace-5.5.y/Makefile.am	2020-02-29 10:28:04.515676065 +0100
@@ -45,7 +45,7 @@
 strace_CPPFLAGS = $(AM_CPPFLAGS)
 strace_CFLAGS = $(AM_CFLAGS)
 strace_LDFLAGS =
-strace_LDADD = libstrace.a $(clock_LIBS) $(timer_LIBS)
+strace_LDADD = libstrace.a -lpthread $(clock_LIBS) $(timer_LIBS)
 noinst_LIBRARIES = libstrace.a
 
 libstrace_a_CPPFLAGS = $(strace_CPPFLAGS)
diff -ur strace-5.5/Makefile.in strace-5.5.y/Makefile.in
--- strace-5.5/Makefile.in	2020-02-06 17:23:35.000000000 +0100
+++ strace-5.5.y/Makefile.in	2020-02-29 10:28:28.833677402 +0100
@@ -1631,7 +1631,7 @@
 	$(am__append_11) $(CODE_COVERAGE_CPPFLAGS)
 strace_CFLAGS = $(AM_CFLAGS) $(am__append_4) $(CODE_COVERAGE_CFLAGS)
 strace_LDFLAGS = $(am__append_5) $(am__append_9) $(am__append_12)
-strace_LDADD = libstrace.a $(clock_LIBS) $(timer_LIBS) $(am__append_6) \
+strace_LDADD = libstrace.a -lpthread $(clock_LIBS) $(timer_LIBS) $(am__append_6) \
 	$(am__append_10) $(am__append_13) $(CODE_COVERAGE_LIBS) \
 	$(am__append_14) $(am__append_18)
 noinst_LIBRARIES = libstrace.a $(am__append_15) $(am__append_19)
diff -ur strace-5.5/strace.c strace-5.5.y/strace.c
--- strace-5.5/strace.c	2020-02-06 16:16:17.000000000 +0100
+++ strace-5.5.y/strace.c	2020-03-01 07:59:55.586429063 +0100
@@ -15,6 +15,8 @@
 #include <fcntl.h>
 #include "ptrace.h"
 #include <signal.h>
+#include <semaphore.h>
+#include <pthread.h>
 #include <sys/resource.h>
 #include <sys/stat.h>
 #ifdef HAVE_PATHS_H
@@ -69,7 +71,7 @@
 cflag_t cflag = CFLAG_NONE;
 unsigned int followfork;
 unsigned int ptrace_setoptions = PTRACE_O_TRACESYSGOOD | PTRACE_O_TRACEEXEC
-				 | PTRACE_O_TRACEEXIT;
+				 ;//| PTRACE_O_TRACEEXIT;
 unsigned int xflag;
 bool debug_flag;
 bool Tflag;
@@ -1002,7 +1004,7 @@
 	 */
 	for (;;) {
 		unsigned int sig;
-		if (waitpid(tcp->pid, &status, __WALL) < 0) {
+		if (my_waitpid(tcp->pid, &status, __WALL) < 0) {
 			if (errno == EINTR)
 				continue;
 			/*
@@ -1663,6 +1665,83 @@
 	sigaction(signo, &sa, oldact);
 }
 
+#define MAX_WAITIDX 65536
+static unsigned short in_idx = 0, out_idx = 0;
+static sem_t wait_sem;
+static pthread_t wait_thread;
+static int wait_pid[MAX_WAITIDX];
+static int wait_status[MAX_WAITIDX];
+static struct rusage wait_rusage[MAX_WAITIDX];
+
+static void*
+child_sighandler(void *arg)
+{
+	int status;
+	struct rusage ru;
+	int pid;
+	for (;;) {
+		pid = wait4(-1, &status, __WALL, (cflag ? &ru : NULL));
+		if (pid < 0 && errno == EINTR)
+			continue;
+
+		if (pid < 0)
+			pid = -errno;
+
+		if (pid > 0 && WIFSTOPPED(status) && (status >> 16) == PTRACE_EVENT_EXIT) {
+			int i = ptrace(PTRACE_SYSCALL, pid, 0L, 0L);
+			fprintf(stderr, "in thread: ptrace(PTRACE_SYSCALL, %d, 0L, 0L)=%d errno=%d\n", pid, i, errno);
+		}
+		wait_pid[in_idx] = pid;
+		wait_status[in_idx] = status;
+		if (cflag)
+			wait_rusage[in_idx] = ru;
+		in_idx++;
+		if (in_idx == out_idx || sem_post(&wait_sem) == -1)
+			error_msg_and_die("fatal error in child_sighandler"); 
+		if (pid < 0)
+			break;
+	}
+
+	return NULL;
+}
+
+int my_waitpid(int pid, int *status, int options)
+{
+	int skip = 0;
+	unsigned short idx = out_idx;
+	for (;;) {
+		while (sem_wait(&wait_sem) == -1 && errno == EINTR)
+			;
+		if (wait_pid[idx] < 0) {
+			while (skip-- >= 0)
+				sem_post(&wait_sem);
+			errno = -wait_pid[idx];
+			return -1;
+		}
+		if (wait_pid[idx] == pid)
+			break;
+		idx++;
+		skip++;
+	}
+	*status = wait_status[idx];
+	while (skip > 0) {
+		unsigned short idx1 = idx;
+		idx1--;
+		wait_status[idx] = wait_status[idx1];
+		wait_pid[idx] = wait_pid[idx1];
+		if (cflag)
+			wait_rusage[idx] = wait_rusage[idx1];
+		if (sem_post(&wait_sem) == -1)
+			error_msg_and_die("fatal error in my_waitpid"); 
+		skip--;
+		idx--;
+	}
+	out_idx++;
+	if (pid < 0)
+		errno = -pid;
+	return pid < 0 ? -1 : pid;
+}
+
 /*
  * Initialization part of main() was eating much stack (~0.5k),
  * which was unused after init.
@@ -2124,6 +2203,9 @@
 		startup_child(argv);
 	}
 
+	if (sem_init(&wait_sem, 0, 0) == -1)
+		perror_msg_and_die("Unable to initialize signal wait sema");
+
 	set_sighandler(SIGTTOU, SIG_IGN, NULL);
 	set_sighandler(SIGTTIN, SIG_IGN, NULL);
 	if (opt_intr != INTR_ANYWHERE) {
@@ -2150,6 +2232,7 @@
 	if (nprocs != 0 || daemonized_tracer)
 		startup_attach();
 
+	pthread_create(&wait_thread, NULL, child_sighandler, NULL);
 	/* Do we want pids printed in our -o OUTFILE?
 	 * -ff: no (every pid has its own file); or
 	 * -f: yes (there can be more pids in the future); or
@@ -2607,10 +2690,28 @@
 	 * then the system call will be interrupted and
 	 * the expiration will be handled by the signal handler.
 	 */
-	int status;
+	int status = 0;
 	struct rusage ru;
-	int pid = wait4(-1, &status, __WALL, (cflag ? &ru : NULL));
-	int wait_errno = errno;
+	int pid = 0;
+	int wait_errno = 0;
+	while (sem_wait(&wait_sem) == -1 && errno == EINTR)
+		;
+
+	if (in_idx == out_idx)
+		error_msg_and_die("wait queue error");
+	pid = wait_pid[out_idx];
+	status = wait_status[out_idx];
+	ru = wait_rusage[out_idx];
+	if (pid > 0 && WIFSTOPPED(status) && (status >> 16) == PTRACE_EVENT_EXIT) {
+		int i = ptrace(PTRACE_SYSCALL, pid, 0L, 0L);
+		fprintf(stderr, "ptrace(PTRACE_SYSCALL, %d, 0L, 0L)=%d errno=%d\n", pid, i, errno);
+	}
+	out_idx++;
+	if (pid < 0) {
+		wait_errno = -pid;
+		out_idx--;
+		sem_post(&wait_sem);
+	}
 
 	/*
 	 * The window of opportunity to handle expirations
@@ -2791,8 +2892,25 @@
 			break;
 
 next_event_wait_next:
-		pid = wait4(-1, &status, __WALL | WNOHANG, (cflag ? &ru : NULL));
-		wait_errno = errno;
+		pid = 0;
+		if (in_idx != out_idx) {
+			while (sem_wait(&wait_sem) == -1 && errno == EINTR)
+				;
+
+			pid = wait_pid[out_idx];
+			status = wait_status[out_idx];
+			ru = wait_rusage[out_idx];
+			if (pid > 0 && WIFSTOPPED(status) && (status >> 16) == PTRACE_EVENT_EXIT) {
+				int i = ptrace(PTRACE_SYSCALL, pid, 0L, 0L);
+				fprintf(stderr, "ptrace(PTRACE_SYSCALL, %d, 0L, 0L)=%d errno=%d\n", pid, i, errno);
+			}
+			out_idx++;
+			if (pid < 0) {
+				wait_errno = -pid;
+				out_idx--;
+				sem_post(&wait_sem);
+			}
+		}
 		wait_nohang = true;
 	}
 
@@ -3019,7 +3137,8 @@
 
 	case TE_STOP_BEFORE_EXIT:
 		print_event_exit(current_tcp);
-		break;
+		//droptcb(current_tcp);
+		return true;
 	}
 
 	/* We handled quick cases, we are permitted to interrupt now. */
@@ -3138,9 +3257,10 @@
 	if (shared_log != stderr)
 		fclose(shared_log);
 	if (popen_pid) {
-		while (waitpid(popen_pid, NULL, 0) < 0 && errno == EINTR)
+		while (my_waitpid(popen_pid, NULL, 0) < 0 && errno == EINTR)
 			;
 	}
+	pthread_join(wait_thread, NULL);
 	if (sig) {
 		exit_code = 0x100 | sig;
 	}