Fixes a race between parent and child threads in futex_requeue.

Similar to commit fbf4dec70277 ("selftests/futex: Order calls to
futex_lock_pi"), which fixed a flake in futex_lock_pi due to racing
between the parent and child threads.

The same issue can occur in the futex_requeue test, because it expects
waiterfn to make progress to futex_wait before the parent starts to
requeue. This is mitigated by the parent sleeping for WAKE_WAIT_US, but
it still fails occasionally. This can be reproduced by adding a sleep in
the waiterfn before futex_wait:

TAP version 13
1..2
not ok 1 futex_requeue simple returned: 0
not ok 2 futex_requeue simple returned: 0
not ok 3 futex_requeue many returned: 0
not ok 4 futex_requeue many returned: 0

This issue can be resolved by checking whether the child thread is in a
sleeping state. This is because when the child thread goes to sleep, it
indicates that it is waiting for the futex lock.

Fixes: 7cb5dd8e2c8c ("selftests: futex: Add futex compare requeue test")
Signed-off-by: Yuwen Chen <ywen.chen@foxmail.com>
Co-developed-by: Edward Liaw <edliaw@google.com>
Signed-off-by: Edward Liaw <edliaw@google.com>
---
 .../futex/functional/futex_requeue.c          | 58 ++++++++++++++++---
 1 file changed, 51 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c
index 7a22458c7fc96..994295fac6972 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue.c
@@ -7,6 +7,7 @@
 
 #include <pthread.h>
 #include <limits.h>
+#include <linux/compiler.h>
 
 #include "futextest.h"
 #include "../../kselftest_harness.h"
@@ -15,6 +16,7 @@
 #define WAKE_WAIT_US 10000
 
 volatile futex_t *f1;
+static pthread_barrier_t barrier;
 
 void *waiterfn(void *arg)
 {
@@ -23,28 +25,59 @@ void *waiterfn(void *arg)
 	to.tv_sec = 0;
 	to.tv_nsec = timeout_ns;
 
+	WRITE_ONCE(*((pid_t *)arg), gettid());
+	pthread_barrier_wait(&barrier);
+
 	if (futex_wait(f1, *f1, &to, 0))
 		printf("waiter failed errno %d\n", errno);
 
 	return NULL;
 }
 
+static int get_thread_state(pid_t pid)
+{
+	FILE *fp;
+	char buf[80], tag[80];
+	char val = 0;
+
+	snprintf(buf, sizeof(buf), "/proc/%d/status", pid);
+	fp = fopen(buf, "r");
+	if (!fp)
+		return -1;
+
+	while (fgets(buf, sizeof(buf), fp))
+		if (fscanf(fp, "%s %c\n", tag, &val) == 2 && !strcmp(tag, "State:"))
+			break;
+
+	fclose(fp);
+	return val;
+}
+
 TEST(requeue_single)
 {
 	volatile futex_t _f1 = 0;
 	volatile futex_t f2 = 0;
 	pthread_t waiter;
-	int res;
+	pid_t tids;
+	int res, state;
 
 	f1 = &_f1;
+	pthread_barrier_init(&barrier, NULL, 2);
 
 	/*
 	 * Requeue a waiter from f1 to f2, and wake f2.
 	 */
-	if (pthread_create(&waiter, NULL, waiterfn, NULL))
+	if (pthread_create(&waiter, NULL, waiterfn, &tids))
 		ksft_exit_fail_msg("pthread_create failed\n");
 
-	usleep(WAKE_WAIT_US);
+	pthread_barrier_wait(&barrier);
+	pthread_barrier_destroy(&barrier);
+	while ((state = get_thread_state(READ_ONCE(tids))) != 'S') {
+		usleep(WAKE_WAIT_US);
+
+		if (state < 0)
+			break;
+	}
 
 	ksft_print_dbg_msg("Requeuing 1 futex from f1 to f2\n");
 	res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0);
@@ -71,7 +104,8 @@ TEST(requeue_multiple)
 	volatile futex_t _f1 = 0;
 	volatile futex_t f2 = 0;
 	pthread_t waiter[10];
-	int res, i;
+	pid_t tids[10];
+	int res, i, state;
 
 	f1 = &_f1;
 
@@ -80,11 +114,21 @@ TEST(requeue_multiple)
 	 * At futex_wake, wake INT_MAX (should be exactly 7).
 	 */
 	for (i = 0; i < 10; i++) {
-		if (pthread_create(&waiter[i], NULL, waiterfn, NULL))
+		pthread_barrier_init(&barrier, NULL, 2);
+
+		if (pthread_create(&waiter[i], NULL, waiterfn, &tids[i]))
 			ksft_exit_fail_msg("pthread_create failed\n");
-	}
 
-	usleep(WAKE_WAIT_US);
+		pthread_barrier_wait(&barrier);
+		pthread_barrier_destroy(&barrier);
+
+		while ((state = get_thread_state(READ_ONCE(tids[i]))) != 'S') {
+			usleep(WAKE_WAIT_US);
+
+			if (state < 0)
+				break;
+		}
+	}
 
 	ksft_print_dbg_msg("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n");
 	res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0);
-- 
2.34.1