sched: idle: Respect the CPU system wakeup QoS limit for s2idle

A CPU system wakeup QoS limit may have been requested by user space. To
avoid breaking this constraint when entering a low power state during
s2idle, let's start to take into account the QoS limit.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dhruva Gole <d-gole@ti.com>
Reviewed-by: Kevin Hilman (TI) <khilman@baylibre.com>
Tested-by: Kevin Hilman (TI) <khilman@baylibre.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/20251125112650.329269-5-ulf.hansson@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Author: Ulf Hansson

drivers/cpuidle/cpuidle.c

@@ -184,20 +184,22 @@ static noinstr void enter_s2idle_proper(struct cpuidle_driver *drv,
  * cpuidle_enter_s2idle - Enter an idle state suitable for suspend-to-idle.
  * @drv: cpuidle driver for the given CPU.
  * @dev: cpuidle device for the given CPU.
+ * @latency_limit_ns: Idle state exit latency limit
  *
  * If there are states with the ->enter_s2idle callback, find the deepest of
  * them and enter it with frozen tick.
  */
-int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+			 u64 latency_limit_ns)
 {
 	int index;
 
 	/*
-	 * Find the deepest state with ->enter_s2idle present, which guarantees
-	 * that interrupts won't be enabled when it exits and allows the tick to
-	 * be frozen safely.
+	 * Find the deepest state with ->enter_s2idle present that meets the
+	 * specified latency limit, which guarantees that interrupts won't be
+	 * enabled when it exits and allows the tick to be frozen safely.
 	 */
-	index = find_deepest_state(drv, dev, U64_MAX, 0, true);
+	index = find_deepest_state(drv, dev, latency_limit_ns, 0, true);
 	if (index > 0) {
 		enter_s2idle_proper(drv, dev, index);
 		local_irq_enable();

include/linux/cpuidle.h

@@ -248,15 +248,17 @@ extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 				      struct cpuidle_device *dev,
 				      u64 latency_limit_ns);
 extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
-				struct cpuidle_device *dev);
+				struct cpuidle_device *dev,
+				u64 latency_limit_ns);
 extern void cpuidle_use_deepest_state(u64 latency_limit_ns);
 #else
 static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 					     struct cpuidle_device *dev,
 					     u64 latency_limit_ns)
 {return -ENODEV; }
 static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
-				       struct cpuidle_device *dev)
+				       struct cpuidle_device *dev,
+				       u64 latency_limit_ns)
 {return -ENODEV; }
 static inline void cpuidle_use_deepest_state(u64 latency_limit_ns)
 {

kernel/sched/idle.c

@@ -131,12 +131,13 @@ void __cpuidle default_idle_call(void)
 }
 
 static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
-			       struct cpuidle_device *dev)
+			       struct cpuidle_device *dev,
+			       u64 max_latency_ns)
 {
 	if (current_clr_polling_and_test())
 		return -EBUSY;
 
-	return cpuidle_enter_s2idle(drv, dev);
+	return cpuidle_enter_s2idle(drv, dev, max_latency_ns);
 }
 
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
@@ -205,12 +206,13 @@ static void cpuidle_idle_call(void)
 		u64 max_latency_ns;
 
 		if (idle_should_enter_s2idle()) {
+			max_latency_ns = cpu_wakeup_latency_qos_limit() *
+					 NSEC_PER_USEC;
 
-			entered_state = call_cpuidle_s2idle(drv, dev);
+			entered_state = call_cpuidle_s2idle(drv, dev,
+							    max_latency_ns);
 			if (entered_state > 0)
 				goto exit_idle;
-
-			max_latency_ns = U64_MAX;
 		} else {
 			max_latency_ns = dev->forced_idle_latency_limit_ns;
 		}