cpuidle: poll_state: Add time limit to poll_idle()

If poll_idle() is allowed to spin until need_resched() returns 'true',
it may actually spin for a much longer time than expected by the idle
governor, since set_tsk_need_resched() is not always called by the
timer interrupt handler.  If that happens, the CPU may spend much
more time than anticipated in the "polling" state.

To prevent that from happening, limit the time of the spinning loop
in poll_idle().

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Doug Smythies <dsmythies@telus.net>

1 files changed, 10 insertions, 1 deletions

diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index 7416b16287de..68cdc506524b 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -6,15 +6,24 @@
 
 #include <linux/cpuidle.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/idle.h>
 
+#define POLL_IDLE_TIME_LIMIT	(TICK_NSEC / 16)
+
 static int __cpuidle poll_idle(struct cpuidle_device *dev,
 			       struct cpuidle_driver *drv, int index)
 {
+	u64 time_start = local_clock();
+
 	local_irq_enable();
 	if (!current_set_polling_and_test()) {
-		while (!need_resched())
+		while (!need_resched()) {
 			cpu_relax();
+
+			if (local_clock() - time_start > POLL_IDLE_TIME_LIMIT)
+				break;
+		}
 	}
 	current_clr_polling();