rcu-tasks: Use order_base_2() instead of ilog2()

The ilog2() function can be used to generate a shift count, but it will
generate the same count for a power of two as for one greater than a power
of two.  This results in shift counts that are larger than necessary for
systems with a power-of-two number of CPUs because the CPUs are numbered
from zero, so that the maximum CPU number is one less than that power
of two.

This commit therefore substitutes order_base_2(), which appears to have
been designed for exactly this use case.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index d64f0b1d8cd3ba17202c97b519aa24e712710a35..670c75cbcb98dab80bfa358d2667048f46b74eb6 100644 (file)
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -123,7 +123,7 @@ static struct rcu_tasks rt_name =                                                   \
        .call_func = call,                                                              \
        .rtpcpu = &rt_name ## __percpu,                                                 \
        .name = n,                                                                      \
-       .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS) + 1,                              \
+       .percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS),                           \
        .percpu_enqueue_lim = 1,                                                        \
        .percpu_dequeue_lim = 1,                                                        \
        .barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex),                \
@@ -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, ilog2(nr_cpu_ids) + 1);
+                       WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids));
                        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);
@@ -417,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
        if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) {
                raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
                if (rtp->percpu_enqueue_lim > 1) {
-                       WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1);
+                       WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids));
                        smp_store_release(&rtp->percpu_enqueue_lim, 1);
                        rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu();
                        pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name);