[LTP] [PATCH] syscalls/tgkill03: wait for defunct tid to get detached

[Jan Stancek]

Case where defunct tid is used has been observed to sporadically fail:
  tgkill03.c:96: FAIL: Defunct tid should have failed with ESRCH: SUCCESS

glibc __pthread_timedjoin_ex() waits for CLONE_CHILD_CLEARTID to clear tid,
and then resumes. Kernel clears it (glibc pd->tid) at:
  do_exit
    exit_mm
      mm_release
        put_user(0, tsk->clear_child_tid);

but kernel tid is still valid, presumably until:
  release_task
    __exit_signal
      __unhash_process
        detach_pid

To avoid race wait until /proc/<pid>/task/<tid> disappears.

Signed-off-by: Jan Stancek <jstancek@redhat.com>
---
 testcases/kernel/syscalls/tgkill/tgkill03.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/testcases/kernel/syscalls/tgkill/tgkill03.c b/testcases/kernel/syscalls/tgkill/tgkill03.c
index f5bbdc5a8d4e..5ac1d2651f7a 100644
--- a/testcases/kernel/syscalls/tgkill/tgkill03.c
+++ b/testcases/kernel/syscalls/tgkill/tgkill03.c
@@ -7,6 +7,7 @@
 
 #include <pthread.h>
 #include <pwd.h>
+#include <stdio.h>
 #include <sys/types.h>
 
 #include "tst_safe_pthread.h"
@@ -42,6 +43,7 @@ static void setup(void)
 {
 	sigset_t sigusr1;
 	pthread_t defunct_thread;
+	char defunct_tid_path[PATH_MAX];
 
 	sigemptyset(&sigusr1);
 	sigaddset(&sigusr1, SIGUSR1);
@@ -55,8 +57,10 @@ static void setup(void)
 	TST_CHECKPOINT_WAIT(0);
 
 	SAFE_PTHREAD_CREATE(&defunct_thread, NULL, defunct_thread_func, NULL);
-
 	SAFE_PTHREAD_JOIN(defunct_thread, NULL);
+	sprintf(defunct_tid_path, "/proc/%d/task/%d", getpid(), defunct_tid);
+	while (access(defunct_tid_path, R_OK) == 0)
+		usleep(10000);
 }
 
 static void cleanup(void)
-- 
1.8.3.1