diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index e426d1b..e07241a 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -4,6 +4,7 @@ comment "NVIDIA Tegra options"
 
 config ARCH_TEGRA_2x_SOC
 	bool "Enable support for Tegra20 family"
+	select ARCH_NEEDS_CPU_IDLE_COUPLED
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_ERRATA_720789
 	select ARM_ERRATA_742230
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index 9371a00..02b2cf7 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -37,9 +37,10 @@
 #include "flowctrl.h"
 
 #ifdef CONFIG_PM_SLEEP
-static int tegra20_idle_lp2(struct cpuidle_device *dev,
-			    struct cpuidle_driver *drv,
-			    int index);
+static atomic_t abort_barrier;
+static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev,
+				    struct cpuidle_driver *drv,
+				    int index);
 #endif
 
 static struct cpuidle_driver tegra_idle_driver = {
@@ -55,11 +56,12 @@ static struct cpuidle_driver tegra_idle_driver = {
 		[0] = ARM_CPUIDLE_WFI_STATE_PWR(600),
 #ifdef CONFIG_PM_SLEEP
 		[1] = {
-			.enter			= tegra20_idle_lp2,
+			.enter			= tegra20_idle_lp2_coupled,
 			.exit_latency		= 5000,
 			.target_residency	= 10000,
 			.power_usage		= 0,
-			.flags			= CPUIDLE_FLAG_TIME_VALID,
+			.flags			= CPUIDLE_FLAG_TIME_VALID |
+						  CPUIDLE_FLAG_COUPLED,
 			.name			= "powered-down",
 			.desc			= "CPU power gated",
 		},
@@ -204,28 +206,24 @@ static inline bool tegra20_idle_enter_lp2_cpu_1(struct cpuidle_device *dev,
 }
 #endif
 
-static int __cpuinit tegra20_idle_lp2(struct cpuidle_device *dev,
-				      struct cpuidle_driver *drv,
-				      int index)
+static int __cpuinit tegra20_idle_lp2_coupled(struct cpuidle_device *dev,
+					      struct cpuidle_driver *drv,
+					      int index)
 {
 	u32 cpu = is_smp() ? cpu_logical_map(dev->cpu) : dev->cpu;
 	bool entered_lp2 = false;
-	bool last_cpu;
+
+	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
 
 	local_fiq_disable();
 
-	last_cpu =  tegra_set_cpu_in_lp2(cpu);
+	tegra_set_cpu_in_lp2(cpu);
 	cpu_pm_enter();
 
-	if (cpu == 0) {
-		if (last_cpu)
-			entered_lp2 = tegra20_cpu_cluster_power_down(dev, drv,
-								     index);
-		else
-			cpu_do_idle();
-	} else {
+	if (cpu == 0)
+		entered_lp2 = tegra20_cpu_cluster_power_down(dev, drv, index);
+	else
 		entered_lp2 = tegra20_idle_enter_lp2_cpu_1(dev, drv, index);
-	}
 
 	cpu_pm_exit();
 	tegra_clear_cpu_in_lp2(cpu);
@@ -258,6 +256,9 @@ int __init tegra20_cpuidle_init(void)
 	for_each_possible_cpu(cpu) {
 		dev = &per_cpu(tegra_idle_device, cpu);
 		dev->cpu = cpu;
+#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
+		dev->coupled_cpus = *cpu_online_mask;
+#endif
 
 		dev->state_count = drv->state_count;
 		ret = cpuidle_register_device(dev);