On Thu, Mar 11, 2021 at 01:37:00PM +0100, Frederic Weisbecker wrote:
> Optimize further the check for local full dynticks CPU. Testing directly
> tick_nohz_full_cpu(smp_processor_id()) is suboptimal because the
> compiler first fetches the CPU number and only then processes the
> static key.
>
> It's best to evaluate the static branch before anything.
Or you do tricky things like this ;-)
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff..bd4a6b055b80 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -185,13 +185,12 @@ static inline bool tick_nohz_full_enabled(void)
return tick_nohz_full_running;
}
-static inline bool tick_nohz_full_cpu(int cpu)
-{
- if (!tick_nohz_full_enabled())
- return false;
-
- return cpumask_test_cpu(cpu, tick_nohz_full_mask);
-}
+#define tick_nohz_full_cpu(_cpu) ({ \
+ bool __ret = false; \
+ if (tick_nohz_full_enabled()) \
+ __ret = cpumask_test_cpu((_cpu), tick_nohz_full_mask); \
+ __ret; \
+})
static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)
{
