Currently, call_rcu_tasks_generic() sets ->percpu_enqueue_shift to
order_base_2(nr_cpu_ids) upon encountering sufficient contention.
This does not shift to use of non-CPU-0 callback queues as intended, but
rather continues using only CPU 0's queue. Although this does provide
some decrease in contention due to spreading work over multiple locks,
it is not the dramatic decrease that was intended.
This commit therefore makes call_rcu_tasks_generic() set
->percpu_enqueue_shift to 0.
Reported-by: Neeraj Upadhyay <quic_neeraju@xxxxxxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Martin KaFai Lau <kafai@xxxxxx>
Cc: KP Singh <kpsingh@xxxxxxxxxx>
---
kernel/rcu/tasks.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index c0fc3641ef13a..d73e32d803438 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -302,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
if (unlikely(needadjust)) {
raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rtp->percpu_enqueue_lim != nr_cpu_ids) {
- WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids));
+ WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids);
smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids);
pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
--
2.31.1.189.g2e36527f23
