rcu: Fix bug in rcu_barrier() torture test
The child threads in the rcu_torture_barrier_cbs() are improperly
synchronized, which can cause the rcu_barrier() tests to hang. The
failure mode is as follows:
1. CPU 0 running in rcu_torture_barrier() sets barrier_cbs_count
to n_barrier_cbs.
2. CPU 1 running in rcu_torture_barrier_cbs() wakes up, posts
its RCU callback, and atomically decrements barrier_cbs_count.
Because barrier_cbs_count is not zero, it does not do the wake_up().
3. CPU 2 running in rcu_torture_barrier_cbs() wakes up, but
finds that barrier_cbs_count is not equal to n_barrier_cbs,
and so returns to sleep.
4. The value of barrier_cbs_count therefore never reaches zero,
which causes the test to hang.
This commit therefore uses a phase variable to coordinate the test,
preventing this scenario from occurring.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 7b6935e..f7fe73e 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -206,6 +206,7 @@
DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
/* and boost task create/destroy. */
static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */
+static bool barrier_phase; /* Test phase. */
static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */
static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
@@ -1642,6 +1643,7 @@
static int rcu_torture_barrier_cbs(void *arg)
{
long myid = (long)arg;
+ bool lastphase = 0;
struct rcu_head rcu;
init_rcu_head_on_stack(&rcu);
@@ -1649,9 +1651,11 @@
set_user_nice(current, 19);
do {
wait_event(barrier_cbs_wq[myid],
- atomic_read(&barrier_cbs_count) == n_barrier_cbs ||
+ barrier_phase != lastphase ||
kthread_should_stop() ||
fullstop != FULLSTOP_DONTSTOP);
+ lastphase = barrier_phase;
+ smp_mb(); /* ensure barrier_phase load before ->call(). */
if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
break;
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
@@ -1676,7 +1680,8 @@
do {
atomic_set(&barrier_cbs_invoked, 0);
atomic_set(&barrier_cbs_count, n_barrier_cbs);
- /* wake_up() path contains the required barriers. */
+ smp_mb(); /* Ensure barrier_phase after prior assignments. */
+ barrier_phase = !barrier_phase;
for (i = 0; i < n_barrier_cbs; i++)
wake_up(&barrier_cbs_wq[i]);
wait_event(barrier_wq,
