5 files changed, 58 insertions, 10 deletions

diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 04003b90dc49..74068742cef3 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -674,8 +674,7 @@ have_coupled:
 	coupled->refcnt++;
 
 	csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu);
-	csd->func = cpuidle_coupled_handle_poke;
-	csd->info = (void *)(unsigned long)dev->cpu;
+	INIT_CSD(csd, cpuidle_coupled_handle_poke, (void *)(unsigned long)dev->cpu);
 
 	return 0;
 }
diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c
index 4a031c62f92a..ff2c3f8e4668 100644
--- a/drivers/cpuidle/cpuidle-psci-domain.c
+++ b/drivers/cpuidle/cpuidle-psci-domain.c
@@ -327,6 +327,8 @@ struct device *psci_dt_attach_cpu(int cpu)
 	if (cpu_online(cpu))
 		pm_runtime_get_sync(dev);
 
+	dev_pm_syscore_device(dev, true);
+
 	return dev;
 }
 
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index d928b37718bd..b51b5df08450 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -19,6 +19,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/psci.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -52,8 +53,9 @@ static inline int psci_enter_state(int idx, u32 state)
 	return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, idx, state);
 }
 
-static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
-					struct cpuidle_driver *drv, int idx)
+static int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
+					  struct cpuidle_driver *drv, int idx,
+					  bool s2idle)
 {
 	struct psci_cpuidle_data *data = this_cpu_ptr(&psci_cpuidle_data);
 	u32 *states = data->psci_states;
@@ -66,7 +68,12 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
 		return -1;
 
 	/* Do runtime PM to manage a hierarchical CPU toplogy. */
-	RCU_NONIDLE(pm_runtime_put_sync_suspend(pd_dev));
+	rcu_irq_enter_irqson();
+	if (s2idle)
+		dev_pm_genpd_suspend(pd_dev);
+	else
+		pm_runtime_put_sync_suspend(pd_dev);
+	rcu_irq_exit_irqson();
 
 	state = psci_get_domain_state();
 	if (!state)
@@ -74,7 +81,12 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
 
 	ret = psci_cpu_suspend_enter(state) ? -1 : idx;
 
-	RCU_NONIDLE(pm_runtime_get_sync(pd_dev));
+	rcu_irq_enter_irqson();
+	if (s2idle)
+		dev_pm_genpd_resume(pd_dev);
+	else
+		pm_runtime_get_sync(pd_dev);
+	rcu_irq_exit_irqson();
 
 	cpu_pm_exit();
 
@@ -83,6 +95,19 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
 	return ret;
 }
 
+static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int idx)
+{
+	return __psci_enter_domain_idle_state(dev, drv, idx, false);
+}
+
+static int psci_enter_s2idle_domain_idle_state(struct cpuidle_device *dev,
+					       struct cpuidle_driver *drv,
+					       int idx)
+{
+	return __psci_enter_domain_idle_state(dev, drv, idx, true);
+}
+
 static int psci_idle_cpuhp_up(unsigned int cpu)
 {
 	struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev);
@@ -170,6 +195,7 @@ static int psci_dt_cpu_init_topology(struct cpuidle_driver *drv,
 	 * deeper states.
 	 */
 	drv->states[state_count - 1].enter = psci_enter_domain_idle_state;
+	drv->states[state_count - 1].enter_s2idle = psci_enter_s2idle_domain_idle_state;
 	psci_cpuidle_use_cpuhp = true;
 
 	return 0;
diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index e8956706a291..191966dc8d02 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -189,7 +189,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
 	}
 
 	local_fiq_disable();
-	tegra_pm_set_cpu_in_lp2();
+	RCU_NONIDLE(tegra_pm_set_cpu_in_lp2());
 	cpu_pm_enter();
 
 	switch (index) {
@@ -207,7 +207,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
 	}
 
 	cpu_pm_exit();
-	tegra_pm_clear_cpu_in_lp2();
+	RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2());
 	local_fiq_enable();
 
 	return err ?: index;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 83af15f77f66..ef2ea1b12cd8 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -368,6 +368,19 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index)
 		cpuidle_curr_governor->reflect(dev, index);
 }
 
+/*
+ * Min polling interval of 10usec is a guess. It is assuming that
+ * for most users, the time for a single ping-pong workload like
+ * perf bench pipe would generally complete within 10usec but
+ * this is hardware dependant. Actual time can be estimated with
+ *
+ * perf bench sched pipe -l 10000
+ *
+ * Run multiple times to avoid cpufreq effects.
+ */
+#define CPUIDLE_POLL_MIN 10000
+#define CPUIDLE_POLL_MAX (TICK_NSEC / 16)
+
 /**
  * cpuidle_poll_time - return amount of time to poll for,
  * governors can override dev->poll_limit_ns if necessary
@@ -382,15 +395,23 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv,
 	int i;
 	u64 limit_ns;
 
+	BUILD_BUG_ON(CPUIDLE_POLL_MIN > CPUIDLE_POLL_MAX);
+
 	if (dev->poll_limit_ns)
 		return dev->poll_limit_ns;
 
-	limit_ns = TICK_NSEC;
+	limit_ns = CPUIDLE_POLL_MAX;
 	for (i = 1; i < drv->state_count; i++) {
+		u64 state_limit;
+
 		if (dev->states_usage[i].disable)
 			continue;
 
-		limit_ns = drv->states[i].target_residency_ns;
+		state_limit = drv->states[i].target_residency_ns;
+		if (state_limit < CPUIDLE_POLL_MIN)
+			continue;
+
+		limit_ns = min_t(u64, state_limit, CPUIDLE_POLL_MAX);
 		break;
 	}