[PATCH 11/13] powerpc/64s: cpuidle no memory barrier after break from idle

[Nicholas Piggin]

A memory barrier is not required after the task wakes up,
only if we clear the polling flag before waking. The case
where we have work to do is the important one, so optimise
for it.

Reviewed-by: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 drivers/cpuidle/cpuidle-powernv.c | 11 +++++++++--
 drivers/cpuidle/cpuidle-pseries.c | 11 +++++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 9d03326ac05e..37b0698b7193 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -59,14 +59,21 @@ static int snooze_loop(struct cpuidle_device *dev,
 	ppc64_runlatch_off();
 	HMT_very_low();
 	while (!need_resched()) {
-		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time)
+		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
+			/*
+			 * Task has not woken up but we are exiting the polling
+			 * loop anyway. Require a barrier after polling is
+			 * cleared to order subsequent test of need_resched().
+			 */
+			clear_thread_flag(TIF_POLLING_NRFLAG);
+			smp_mb();
 			break;
+		}
 	}
 
 	HMT_medium();
 	ppc64_runlatch_on();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
-	smp_mb();
 
 	return index;
 }
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index a404f352d284..e9b3853d93ea 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -71,13 +71,20 @@ static int snooze_loop(struct cpuidle_device *dev,
 	while (!need_resched()) {
 		HMT_low();
 		HMT_very_low();
-		if (snooze_timeout_en && get_tb() > snooze_exit_time)
+		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
+			/*
+			 * Task has not woken up but we are exiting the polling
+			 * loop anyway. Require a barrier after polling is
+			 * cleared to order subsequent test of need_resched().
+			 */
+			clear_thread_flag(TIF_POLLING_NRFLAG);
+			smp_mb();
 			break;
+		}
 	}
 
 	HMT_medium();
 	clear_thread_flag(TIF_POLLING_NRFLAG);
-	smp_mb();
 
 	idle_loop_epilog(in_purr);
 
-- 
2.11.0