[PATCH v4 0/5] barrier: Add smp_cond_load_*_timewait()

[Ankur Arora]

Catalin Marinas <catalin.marinas at arm.com> writes:

> On Fri, Aug 29, 2025 at 01:07:30AM -0700, Ankur Arora wrote:
>> Ankur Arora (5):
>>   asm-generic: barrier: Add smp_cond_load_relaxed_timewait()
>>   arm64: barrier: Add smp_cond_load_relaxed_timewait()
>>   arm64: rqspinlock: Remove private copy of
>>     smp_cond_load_acquire_timewait
>>   asm-generic: barrier: Add smp_cond_load_acquire_timewait()
>>   rqspinlock: use smp_cond_load_acquire_timewait()
>
> Can you have a go at poll_idle() to see how it would look like using
> this API? It doesn't necessarily mean we have to merge them all at once
> but it gives us a better idea of the suitability of the interface.

So, I've been testing with some version of the following:

diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index 9b6d90a72601..361879396d0c 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -8,35 +8,25 @@
 #include <linux/sched/clock.h>
 #include <linux/sched/idle.h>

-#define POLL_IDLE_RELAX_COUNT	200
-
 static int __cpuidle poll_idle(struct cpuidle_device *dev,
 			       struct cpuidle_driver *drv, int index)
 {
-	u64 time_start;
-
-	time_start = local_clock_noinstr();
+	unsigned long flags;

 	dev->poll_time_limit = false;

 	raw_local_irq_enable();
 	if (!current_set_polling_and_test()) {
-		unsigned int loop_count = 0;
-		u64 limit;
+		u64 limit, time_end;

 		limit = cpuidle_poll_time(drv, dev);
+		time_end = local_clock_noinstr() + limit;

-		while (!need_resched()) {
-			cpu_relax();
-			if (loop_count++ < POLL_IDLE_RELAX_COUNT)
-				continue;
+		flags = smp_cond_load_relaxed_timewait(&current_thread_info()->flags,
+						       VAL & _TIF_NEED_RESCHED,
+						       (local_clock_noinstr() >= time_end));

-			loop_count = 0;
-			if (local_clock_noinstr() - time_start > limit) {
-				dev->poll_time_limit = true;
-				break;
-			}
-		}
+		dev->poll_time_limit = (local_clock_noinstr() >= time_end);
 	}
 	raw_local_irq_disable();

With that, poll_idle() is:

  static int __cpuidle poll_idle(struct cpuidle_device *dev,
			       struct cpuidle_driver *drv, int index)
  {
	unsigned long flags;

	dev->poll_time_limit = false;

	raw_local_irq_enable();
	if (!current_set_polling_and_test()) {
		u64 limit, time_end;

		limit = cpuidle_poll_time(drv, dev);
		time_end = local_clock_noinstr() + limit;

		flags = smp_cond_load_relaxed_timewait(&current_thread_info()->flags,
						       VAL & _TIF_NEED_RESCHED,
						       (local_clock_noinstr() >= time_end));

		dev->poll_time_limit = (local_clock_noinstr() >= time_end);
	}
	raw_local_irq_disable();

	current_clr_polling();

	return index;
  }

--
ankur