diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a5a050af8e7dbca2e474d3f2907b4bc5f5cebbae..3eeef339c787bdb414a0faba3e31d02a6efa2a02 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,6 +41,7 @@ static int			raw_samples			= 0;
 static int			system_wide			= 0;
 static int			profile_cpu			= -1;
 static pid_t			target_pid			= -1;
+static pid_t			child_pid			= -1;
 static int			inherit				= 1;
 static int			force				= 0;
 static int			append_file			= 0;
@@ -184,6 +185,9 @@ static void sig_handler(int sig)
 
 static void sig_atexit(void)
 {
+	if (child_pid != -1)
+		kill(child_pid, SIGTERM);
+
 	if (signr == -1)
 		return;
 
@@ -610,6 +614,8 @@ static int __cmd_record(int argc, const char **argv)
 				exit(-1);
 			}
 		}
+
+		child_pid = pid;
 	}
 
 	if (realtime_prio) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e5f6ece65a1386f51b21f8b537a43fc9833275ea..3db31e7bf1737a438cc93e4648e987ec0073aeb1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -69,7 +69,8 @@ static int			run_idx				=  0;
 static int			run_count			=  1;
 static int			inherit				=  1;
 static int			scale				=  1;
-static int			target_pid			= -1;
+static pid_t			target_pid			= -1;
+static pid_t			child_pid			= -1;
 static int			null_run			=  0;
 
 static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -285,6 +286,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 		exit(-1);
 	}
 
+	child_pid = pid;
+
 	/*
 	 * Wait for the child to be ready to exec.
 	 */
@@ -433,6 +436,9 @@ static void skip_signal(int signo)
 
 static void sig_atexit(void)
 {
+	if (child_pid != -1)
+		kill(child_pid, SIGTERM);
+
 	if (signr == -1)
 		return;