diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 7f2c10c..c714219 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -54,10 +54,21 @@
 #define BM_CLPCR_MASK_SCU_IDLE		(0x1 << 26)
 #define BM_CLPCR_MASK_L2CC_IDLE		(0x1 << 27)
 
+#define CGPR				0x64
+#define BM_CGPR_CHICKEN_BIT		(0x1 << 17)
+
 static void __iomem *ccm_base;
 
 void __init imx6q_clock_map_io(void) { }
 
+void imx6q_set_chicken_bit(void)
+{
+	u32 val = readl_relaxed(ccm_base + CGPR);
+
+	val |= BM_CGPR_CHICKEN_BIT;
+	writel_relaxed(val, ccm_base + CGPR);
+}
+
 int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode)
 {
 	u32 val = readl_relaxed(ccm_base + CLPCR);
@@ -68,6 +79,7 @@ int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode)
 		break;
 	case WAIT_UNCLOCKED:
 		val |= 0x1 << BP_CLPCR_LPM;
+		val |= BM_CLPCR_ARM_CLK_DIS_ON_LPM;
 		break;
 	case STOP_POWER_ON:
 		val |= 0x2 << BP_CLPCR_LPM;
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 7191ab4..7edd53d 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -127,9 +127,11 @@ extern u32 *pl310_get_save_ptr(void);
 extern void v7_secondary_startup(void);
 extern void imx_scu_map_io(void);
 extern void imx_smp_prepare(void);
+extern void imx_scu_standby_enable(void);
 #else
 static inline void imx_scu_map_io(void) {}
 static inline void imx_smp_prepare(void) {}
+static inline void imx_scu_standby_enable(void) {}
 #endif
 extern void imx_enable_cpu(int cpu, bool enable);
 extern void imx_set_cpu_jump(int cpu, void *jump_addr);
@@ -139,6 +141,7 @@ extern void imx_gpc_init(void);
 extern void imx_gpc_pre_suspend(void);
 extern void imx_gpc_post_resume(void);
 extern int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode);
+extern void imx6q_set_chicken_bit(void);
 extern void imx6q_clock_map_io(void);
 
 extern void imx_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 83facc9..ddc26c2 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -6,21 +6,93 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/clockchips.h>
 #include <linux/cpuidle.h>
 #include <linux/module.h>
 #include <asm/cpuidle.h>
+#include <asm/proc-fns.h>
 
+#include "common.h"
 #include "cpuidle.h"
 
+static atomic_t master = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(master_lock);
+
+static int imx6q_enter_wait(struct cpuidle_device *dev,
+			    struct cpuidle_driver *drv, int index)
+{
+	int cpu = dev->cpu;
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+
+	if (atomic_inc_return(&master) == num_online_cpus()) {
+		/*
+		 * With this lock, we prevent other cpu to exit and enter
+		 * this function again and become the master.
+		 */
+		if (!spin_trylock(&master_lock))
+			goto idle;
+		imx6q_set_lpm(WAIT_UNCLOCKED);
+		cpu_do_idle();
+		imx6q_set_lpm(WAIT_CLOCKED);
+		spin_unlock(&master_lock);
+		goto done;
+	}
+
+idle:
+	cpu_do_idle();
+done:
+	atomic_dec(&master);
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+
+	return index;
+}
+
+/*
+ * For each cpu, setup the broadcast timer because local timer
+ * stops for the states other than WFI.
+ */
+static void imx6q_setup_broadcast_timer(void *arg)
+{
+	int cpu = smp_processor_id();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
 static struct cpuidle_driver imx6q_cpuidle_driver = {
 	.name = "imx6q_cpuidle",
 	.owner = THIS_MODULE,
 	.en_core_tk_irqen = 1,
-	.states[0] = ARM_CPUIDLE_WFI_STATE,
-	.state_count = 1,
+	.states = {
+		/* WFI */
+		ARM_CPUIDLE_WFI_STATE,
+		/* WAIT */
+		{
+			.exit_latency = 50,
+			.target_residency = 75,
+			.flags = CPUIDLE_FLAG_TIME_VALID,
+			.enter = imx6q_enter_wait,
+			.name = "WAIT",
+			.desc = "Clock off",
+		},
+	},
+	.state_count = 2,
+	.safe_state_index = 0,
 };
 
 int __init imx6q_cpuidle_init(void)
 {
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
+	/* Need to enable SCU standby for entering WAIT modes */
+	imx_scu_standby_enable();
+
+	/* Set chicken bit to get a reliable WAIT mode support */
+	imx6q_set_chicken_bit();
+
+	/* Configure the broadcast timer on each cpu */
+	on_each_cpu(imx6q_setup_broadcast_timer, NULL, 1);
+
 	return imx_cpuidle_init(&imx6q_cpuidle_driver);
 }
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 4ea7ad9..cda7622 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -201,7 +201,12 @@ static void __init imx6q_init_machine(void)
 
 static void __init imx6q_init_late(void)
 {
-	imx6q_cpuidle_init();
+	/*
+	 * WAIT mode is broken on TO 1.0 and 1.1, so there is no point
+	 * to run cpuidle on them.
+	 */
+	if (imx6q_revision() > IMX_CHIP_REVISION_1_1)
+		imx6q_cpuidle_init();
 }
 
 static void __init imx6q_map_io(void)
diff --git a/arch/arm/mach-imx/platsmp.c b/arch/arm/mach-imx/platsmp.c
index 3777b80..a70b548 100644
--- a/arch/arm/mach-imx/platsmp.c
+++ b/arch/arm/mach-imx/platsmp.c
@@ -20,6 +20,8 @@
 #include "common.h"
 #include "hardware.h"
 
+#define SCU_STANDBY_ENABLE	(1 << 5)
+
 static void __iomem *scu_base;
 
 static struct map_desc scu_io_desc __initdata = {
@@ -42,6 +44,14 @@ void __init imx_scu_map_io(void)
 	scu_base = IMX_IO_ADDRESS(base);
 }
 
+void imx_scu_standby_enable(void)
+{
+	u32 val = readl_relaxed(scu_base);
+
+	val |= SCU_STANDBY_ENABLE;
+	writel_relaxed(val, scu_base);
+}
+
 static void __cpuinit imx_secondary_init(unsigned int cpu)
 {
 	/*