diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 19c29d5..58de1f6 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -25,11 +25,13 @@
 obj-$(CONFIG_SMP)			+= omap-smp.o omap-headsmp.o
 obj-$(CONFIG_LOCAL_TIMERS)		+= timer-mpu.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= omap-hotplug.o
-obj-$(CONFIG_ARCH_OMAP4)		+= omap4-common.o omap-wakeupgen.o
+obj-$(CONFIG_ARCH_OMAP4)		+= omap4-common.o omap-wakeupgen.o \
+					   sleep44xx.o
 
 plus_sec := $(call as-instr,.arch_extension sec,+sec)
 AFLAGS_omap-headsmp.o			:=-Wa,-march=armv7-a$(plus_sec)
 AFLAGS_omap-smc.o			:=-Wa,-march=armv7-a$(plus_sec)
+AFLAGS_sleep44xx.o			:=-Wa,-march=armv7-a$(plus_sec)
 
 # Functions loaded to SRAM
 obj-$(CONFIG_SOC_OMAP2420)		+= sram242x.o
@@ -63,7 +65,7 @@
 obj-$(CONFIG_ARCH_OMAP2)		+= sleep24xx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= pm34xx.o sleep34xx.o \
 					   cpuidle34xx.o
-obj-$(CONFIG_ARCH_OMAP4)		+= pm44xx.o
+obj-$(CONFIG_ARCH_OMAP4)		+= pm44xx.o omap-mpuss-lowpower.o
 obj-$(CONFIG_PM_DEBUG)			+= pm-debug.o
 obj-$(CONFIG_OMAP_SMARTREFLEX)          += sr_device.o smartreflex.o
 obj-$(CONFIG_OMAP_SMARTREFLEX_CLASS3)	+= smartreflex-class3.o
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index 7ebcb6a..36cdba7 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -24,9 +24,11 @@
 
 #ifndef __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H
 #define __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H
+#ifndef __ASSEMBLER__
 
 #include <linux/delay.h>
 #include <plat/common.h>
+#include <asm/proc-fns.h>
 
 #ifdef CONFIG_SOC_OMAP2420
 extern void omap242x_map_common_io(void);
@@ -183,6 +185,7 @@
 extern void __init gic_init_irq(void);
 extern void omap_smc1(u32 fn, u32 arg);
 extern void __iomem *omap4_get_sar_ram_base(void);
+extern void omap_do_wfi(void);
 
 #ifdef CONFIG_SMP
 /* Needed for secondary core boot */
@@ -192,4 +195,31 @@
 extern u32 omap_read_auxcoreboot0(void);
 #endif
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PM)
+extern int omap4_mpuss_init(void);
+extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
+extern int omap4_finish_suspend(unsigned long cpu_state);
+extern void omap4_cpu_resume(void);
+#else
+static inline int omap4_enter_lowpower(unsigned int cpu,
+					unsigned int power_state)
+{
+	cpu_do_idle();
+	return 0;
+}
+
+static inline int omap4_mpuss_init(void)
+{
+	return 0;
+}
+
+static inline int omap4_finish_suspend(unsigned long cpu_state)
+{
+	return 0;
+}
+
+static inline void omap4_cpu_resume(void)
+{}
+#endif
+#endif /* __ASSEMBLER__ */
 #endif /* __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H */
diff --git a/arch/arm/mach-omap2/include/mach/omap-secure.h b/arch/arm/mach-omap2/include/mach/omap-secure.h
index 29f60ca..5f0763d 100644
--- a/arch/arm/mach-omap2/include/mach/omap-secure.h
+++ b/arch/arm/mach-omap2/include/mach/omap-secure.h
@@ -35,9 +35,18 @@
 #define OMAP4_HAL_SAVEALL_INDEX		0x1c
 #define OMAP4_HAL_SAVEGIC_INDEX		0x1d
 
+/* Secure Monitor mode APIs */
+#define OMAP4_MON_SCU_PWR_INDEX		0x108
+
+/* Secure PPA(Primary Protected Application) APIs */
+#define OMAP4_PPA_CPU_ACTRL_SMP_INDEX	0x25
+
+#ifndef __ASSEMBLER__
+
 extern u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs,
 				u32 arg1, u32 arg2, u32 arg3, u32 arg4);
 extern u32 omap_smc2(u32 id, u32 falg, u32 pargs);
 extern phys_addr_t omap_secure_ram_mempool_base(void);
 
+#endif /* __ASSEMBLER__ */
 #endif /* OMAP_ARCH_OMAP_SECURE_H */
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
new file mode 100644
index 0000000..867fee5
--- /dev/null
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -0,0 +1,248 @@
+/*
+ * OMAP MPUSS low power code
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *	Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * OMAP4430 MPUSS mainly consists of dual Cortex-A9 with per-CPU
+ * Local timer and Watchdog, GIC, SCU, PL310 L2 cache controller,
+ * CPU0 and CPU1 LPRM modules.
+ * CPU0, CPU1 and MPUSS each have there own power domain and
+ * hence multiple low power combinations of MPUSS are possible.
+ *
+ * The CPU0 and CPU1 can't support Closed switch Retention (CSWR)
+ * because the mode is not supported by hw constraints of dormant
+ * mode. While waking up from the dormant mode, a reset  signal
+ * to the Cortex-A9 processor must be asserted by the external
+ * power controller.
+ *
+ * With architectural inputs and hardware recommendations, only
+ * below modes are supported from power gain vs latency point of view.
+ *
+ *	CPU0		CPU1		MPUSS
+ *	----------------------------------------------
+ *	ON		ON		ON
+ *	ON(Inactive)	OFF		ON(Inactive)
+ *	OFF		OFF		CSWR
+ *	OFF		OFF		OSWR (*TBD)
+ *	OFF		OFF		OFF* (*TBD)
+ *	----------------------------------------------
+ *
+ * Note: CPU0 is the master core and it is the last CPU to go down
+ * and first to wake-up when MPUSS low power states are excercised
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/smp_scu.h>
+#include <asm/system.h>
+#include <asm/pgalloc.h>
+#include <asm/suspend.h>
+
+#include <plat/omap44xx.h>
+
+#include "common.h"
+#include "omap4-sar-layout.h"
+#include "pm.h"
+#include "powerdomain.h"
+
+#ifdef CONFIG_SMP
+
+struct omap4_cpu_pm_info {
+	struct powerdomain *pwrdm;
+	void __iomem *scu_sar_addr;
+	void __iomem *wkup_sar_addr;
+};
+
+static DEFINE_PER_CPU(struct omap4_cpu_pm_info, omap4_pm_info);
+
+/*
+ * Program the wakeup routine address for the CPU0 and CPU1
+ * used for OFF or DORMANT wakeup.
+ */
+static inline void set_cpu_wakeup_addr(unsigned int cpu_id, u32 addr)
+{
+	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu_id);
+
+	__raw_writel(addr, pm_info->wkup_sar_addr);
+}
+
+/*
+ * Set the CPUx powerdomain's previous power state
+ */
+static inline void set_cpu_next_pwrst(unsigned int cpu_id,
+				unsigned int power_state)
+{
+	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu_id);
+
+	pwrdm_set_next_pwrst(pm_info->pwrdm, power_state);
+}
+
+/*
+ * Read CPU's previous power state
+ */
+static inline unsigned int read_cpu_prev_pwrst(unsigned int cpu_id)
+{
+	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu_id);
+
+	return pwrdm_read_prev_pwrst(pm_info->pwrdm);
+}
+
+/*
+ * Clear the CPUx powerdomain's previous power state
+ */
+static inline void clear_cpu_prev_pwrst(unsigned int cpu_id)
+{
+	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu_id);
+
+	pwrdm_clear_all_prev_pwrst(pm_info->pwrdm);
+}
+
+/*
+ * Store the SCU power status value to scratchpad memory
+ */
+static void scu_pwrst_prepare(unsigned int cpu_id, unsigned int cpu_state)
+{
+	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu_id);
+	u32 scu_pwr_st;
+
+	switch (cpu_state) {
+	case PWRDM_POWER_RET:
+		scu_pwr_st = SCU_PM_DORMANT;
+		break;
+	case PWRDM_POWER_OFF:
+		scu_pwr_st = SCU_PM_POWEROFF;
+		break;
+	case PWRDM_POWER_ON:
+	case PWRDM_POWER_INACTIVE:
+	default:
+		scu_pwr_st = SCU_PM_NORMAL;
+		break;
+	}
+
+	__raw_writel(scu_pwr_st, pm_info->scu_sar_addr);
+}
+
+/**
+ * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
+ * The purpose of this function is to manage low power programming
+ * of OMAP4 MPUSS subsystem
+ * @cpu : CPU ID
+ * @power_state: Low power state.
+ */
+int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
+{
+	unsigned int save_state = 0;
+	unsigned int wakeup_cpu;
+
+	if (omap_rev() == OMAP4430_REV_ES1_0)
+		return -ENXIO;
+
+	switch (power_state) {
+	case PWRDM_POWER_ON:
+	case PWRDM_POWER_INACTIVE:
+		save_state = 0;
+		break;
+	case PWRDM_POWER_OFF:
+		save_state = 1;
+		break;
+	case PWRDM_POWER_RET:
+	default:
+		/*
+		 * CPUx CSWR is invalid hardware state. Also CPUx OSWR
+		 * doesn't make much scense, since logic is lost and $L1
+		 * needs to be cleaned because of coherency. This makes
+		 * CPUx OSWR equivalent to CPUX OFF and hence not supported
+		 */
+		WARN_ON(1);
+		return -ENXIO;
+	}
+
+	clear_cpu_prev_pwrst(cpu);
+	set_cpu_next_pwrst(cpu, power_state);
+	set_cpu_wakeup_addr(cpu, virt_to_phys(omap4_cpu_resume));
+	scu_pwrst_prepare(cpu, power_state);
+
+	/*
+	 * Call low level function  with targeted low power state.
+	 */
+	cpu_suspend(save_state, omap4_finish_suspend);
+
+	/*
+	 * Restore the CPUx power state to ON otherwise CPUx
+	 * power domain can transitions to programmed low power
+	 * state while doing WFI outside the low powe code. On
+	 * secure devices, CPUx does WFI which can result in
+	 * domain transition
+	 */
+	wakeup_cpu = smp_processor_id();
+	set_cpu_next_pwrst(wakeup_cpu, PWRDM_POWER_ON);
+
+	return 0;
+}
+
+/*
+ * Initialise OMAP4 MPUSS
+ */
+int __init omap4_mpuss_init(void)
+{
+	struct omap4_cpu_pm_info *pm_info;
+	void __iomem *sar_base = omap4_get_sar_ram_base();
+
+	if (omap_rev() == OMAP4430_REV_ES1_0) {
+		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
+		return -ENODEV;
+	}
+
+	/* Initilaise per CPU PM information */
+	pm_info = &per_cpu(omap4_pm_info, 0x0);
+	pm_info->scu_sar_addr = sar_base + SCU_OFFSET0;
+	pm_info->wkup_sar_addr = sar_base + CPU0_WAKEUP_NS_PA_ADDR_OFFSET;
+	pm_info->pwrdm = pwrdm_lookup("cpu0_pwrdm");
+	if (!pm_info->pwrdm) {
+		pr_err("Lookup failed for CPU0 pwrdm\n");
+		return -ENODEV;
+	}
+
+	/* Clear CPU previous power domain state */
+	pwrdm_clear_all_prev_pwrst(pm_info->pwrdm);
+
+	/* Initialise CPU0 power domain state to ON */
+	pwrdm_set_next_pwrst(pm_info->pwrdm, PWRDM_POWER_ON);
+
+	pm_info = &per_cpu(omap4_pm_info, 0x1);
+	pm_info->scu_sar_addr = sar_base + SCU_OFFSET1;
+	pm_info->wkup_sar_addr = sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+	pm_info->pwrdm = pwrdm_lookup("cpu1_pwrdm");
+	if (!pm_info->pwrdm) {
+		pr_err("Lookup failed for CPU1 pwrdm\n");
+		return -ENODEV;
+	}
+
+	/* Clear CPU previous power domain state */
+	pwrdm_clear_all_prev_pwrst(pm_info->pwrdm);
+
+	/* Initialise CPU1 power domain state to ON */
+	pwrdm_set_next_pwrst(pm_info->pwrdm, PWRDM_POWER_ON);
+
+	/* Save device type on scratchpad for low level code to use */
+	if (omap_type() != OMAP2_DEVICE_TYPE_GP)
+		__raw_writel(1, sar_base + OMAP_TYPE_OFFSET);
+	else
+		__raw_writel(0, sar_base + OMAP_TYPE_OFFSET);
+
+	return 0;
+}
+
+#endif
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 74e90b4..ee83808 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -24,6 +24,7 @@
 #include <asm/hardware/gic.h>
 #include <asm/smp_scu.h>
 #include <mach/hardware.h>
+#include <mach/omap-secure.h>
 
 #include "common.h"
 
@@ -40,6 +41,18 @@
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
 	/*
+	 * Configure ACTRL and enable NS SMP bit access on CPU1 on HS device.
+	 * OMAP44XX EMU/HS devices - CPU0 SMP bit access is enabled in PPA
+	 * init and for CPU1, a secure PPA API provided. CPU0 must be ON
+	 * while executing NS_SMP API on CPU1 and PPA version must be 1.4.0+.
+	 * OMAP443X GP devices- SMP bit isn't accessible.
+	 * OMAP446X GP devices - SMP bit access is enabled on both CPUs.
+	 */
+	if (cpu_is_omap443x() && (omap_type() != OMAP2_DEVICE_TYPE_GP))
+		omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX,
+							4, 0, 0, 0, 0, 0);
+
+	/*
 	 * If any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
 	 * for us: do so
diff --git a/arch/arm/mach-omap2/omap4-sar-layout.h b/arch/arm/mach-omap2/omap4-sar-layout.h
index 7781ea4..970a2ee 100644
--- a/arch/arm/mach-omap2/omap4-sar-layout.h
+++ b/arch/arm/mach-omap2/omap4-sar-layout.h
@@ -19,4 +19,13 @@
 #define SAR_BANK3_OFFSET		0x2000
 #define SAR_BANK4_OFFSET		0x3000
 
+/* Scratch pad memory offsets from SAR_BANK1 */
+#define SCU_OFFSET0				0xd00
+#define SCU_OFFSET1				0xd04
+#define OMAP_TYPE_OFFSET			0xd10
+
+/* CPUx Wakeup Non-Secure Physical Address offsets in SAR_BANK3 */
+#define CPU0_WAKEUP_NS_PA_ADDR_OFFSET		0xa04
+#define CPU1_WAKEUP_NS_PA_ADDR_OFFSET		0xa08
+
 #endif
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index c34139d..781aadf 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -163,6 +163,12 @@
 		goto err2;
 	}
 
+	ret = omap4_mpuss_init();
+	if (ret) {
+		pr_err("Failed to initialise OMAP4 MPUSS\n");
+		goto err2;
+	}
+
 	(void) clkdm_for_each(clkdms_setup, NULL);
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
new file mode 100644
index 0000000..e5521945
--- /dev/null
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -0,0 +1,276 @@
+/*
+ * OMAP44xx sleep code.
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ * 	Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software,you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/system.h>
+#include <asm/smp_scu.h>
+#include <asm/memory.h>
+#include <asm/hardware/cache-l2x0.h>
+
+#include <plat/omap44xx.h>
+#include <mach/omap-secure.h>
+
+#include "common.h"
+#include "omap4-sar-layout.h"
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PM)
+
+.macro	DO_SMC
+	dsb
+	smc	#0
+	dsb
+.endm
+
+ppa_zero_params:
+	.word		0x0
+
+/*
+ * =============================
+ * == CPU suspend finisher ==
+ * =============================
+ *
+ * void omap4_finish_suspend(unsigned long cpu_state)
+ *
+ * This function code saves the CPU context and performs the CPU
+ * power down sequence. Calling WFI effectively changes the CPU
+ * power domains states to the desired target power state.
+ *
+ * @cpu_state : contains context save state (r0)
+ *	0 - No context lost
+ * 	1 - CPUx L1 and logic lost: MPUSS CSWR
+ * 	2 - CPUx L1 and logic lost + GIC lost: MPUSS OSWR
+ *	3 - CPUx L1 and logic lost + GIC + L2 lost: MPUSS OFF
+ * @return: This function never returns for CPU OFF and DORMANT power states.
+ * Post WFI, CPU transitions to DORMANT or OFF power state and on wake-up
+ * from this follows a full CPU reset path via ROM code to CPU restore code.
+ * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET.
+ * It returns to the caller for CPU INACTIVE and ON power states or in case
+ * CPU failed to transition to targeted OFF/DORMANT state.
+ */
+ENTRY(omap4_finish_suspend)
+	stmfd	sp!, {lr}
+	cmp	r0, #0x0
+	beq	do_WFI				@ No lowpower state, jump to WFI
+
+	/*
+	 * Flush all data from the L1 data cache before disabling
+	 * SCTLR.C bit.
+	 */
+	bl	omap4_get_sar_ram_base
+	ldr	r9, [r0, #OMAP_TYPE_OFFSET]
+	cmp	r9, #0x1			@ Check for HS device
+	bne	skip_secure_l1_clean
+	mov	r0, #SCU_PM_NORMAL
+	mov	r1, #0xFF			@ clean seucre L1
+	stmfd   r13!, {r4-r12, r14}
+	ldr	r12, =OMAP4_MON_SCU_PWR_INDEX
+	DO_SMC
+	ldmfd   r13!, {r4-r12, r14}
+skip_secure_l1_clean:
+	bl	v7_flush_dcache_all
+
+	/*
+	 * Clear the SCTLR.C bit to prevent further data cache
+	 * allocation. Clearing SCTLR.C would make all the data accesses
+	 * strongly ordered and would not hit the cache.
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	bic	r0, r0, #(1 << 2)		@ Disable the C bit
+	mcr	p15, 0, r0, c1, c0, 0
+	isb
+
+	/*
+	 * Invalidate L1 data cache. Even though only invalidate is
+	 * necessary exported flush API is used here. Doing clean
+	 * on already clean cache would be almost NOP.
+	 */
+	bl	v7_flush_dcache_all
+
+	/*
+	 * Switch the CPU from Symmetric Multiprocessing (SMP) mode
+	 * to AsymmetricMultiprocessing (AMP) mode by programming
+	 * the SCU power status to DORMANT or OFF mode.
+	 * This enables the CPU to be taken out of coherency by
+	 * preventing the CPU from receiving cache, TLB, or BTB
+	 * maintenance operations broadcast by other CPUs in the cluster.
+	 */
+	bl	omap4_get_sar_ram_base
+	mov	r8, r0
+	ldr	r9, [r8, #OMAP_TYPE_OFFSET]
+	cmp	r9, #0x1			@ Check for HS device
+	bne	scu_gp_set
+	mrc	p15, 0, r0, c0, c0, 5		@ Read MPIDR
+	ands	r0, r0, #0x0f
+	ldreq	r0, [r8, #SCU_OFFSET0]
+	ldrne	r0, [r8, #SCU_OFFSET1]
+	mov	r1, #0x00
+	stmfd   r13!, {r4-r12, r14}
+	ldr	r12, =OMAP4_MON_SCU_PWR_INDEX
+	DO_SMC
+	ldmfd   r13!, {r4-r12, r14}
+	b	skip_scu_gp_set
+scu_gp_set:
+	mrc	p15, 0, r0, c0, c0, 5		@ Read MPIDR
+	ands	r0, r0, #0x0f
+	ldreq	r1, [r8, #SCU_OFFSET0]
+	ldrne	r1, [r8, #SCU_OFFSET1]
+	bl	omap4_get_scu_base
+	bl	scu_power_mode
+skip_scu_gp_set:
+	mrc	p15, 0, r0, c1, c1, 2		@ Read NSACR data
+	tst	r0, #(1 << 18)
+	mrcne	p15, 0, r0, c1, c0, 1
+	bicne	r0, r0, #(1 << 6)		@ Disable SMP bit
+	mcrne	p15, 0, r0, c1, c0, 1
+	isb
+	dsb
+
+do_WFI:
+	bl	omap_do_wfi
+
+	/*
+	 * CPU is here when it failed to enter OFF/DORMANT or
+	 * no low power state was attempted.
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	tst	r0, #(1 << 2)			@ Check C bit enabled?
+	orreq	r0, r0, #(1 << 2)		@ Enable the C bit
+	mcreq	p15, 0, r0, c1, c0, 0
+	isb
+
+	/*
+	 * Ensure the CPU power state is set to NORMAL in
+	 * SCU power state so that CPU is back in coherency.
+	 * In non-coherent mode CPU can lock-up and lead to
+	 * system deadlock.
+	 */
+	mrc	p15, 0, r0, c1, c0, 1
+	tst	r0, #(1 << 6)			@ Check SMP bit enabled?
+	orreq	r0, r0, #(1 << 6)
+	mcreq	p15, 0, r0, c1, c0, 1
+	isb
+	bl	omap4_get_sar_ram_base
+	mov	r8, r0
+	ldr	r9, [r8, #OMAP_TYPE_OFFSET]
+	cmp	r9, #0x1			@ Check for HS device
+	bne	scu_gp_clear
+	mov	r0, #SCU_PM_NORMAL
+	mov	r1, #0x00
+	stmfd   r13!, {r4-r12, r14}
+	ldr	r12, =OMAP4_MON_SCU_PWR_INDEX
+	DO_SMC
+	ldmfd   r13!, {r4-r12, r14}
+	b	skip_scu_gp_clear
+scu_gp_clear:
+	bl	omap4_get_scu_base
+	mov	r1, #SCU_PM_NORMAL
+	bl	scu_power_mode
+skip_scu_gp_clear:
+	isb
+	dsb
+	ldmfd	sp!, {pc}
+ENDPROC(omap4_finish_suspend)
+
+/*
+ * ============================
+ * == CPU resume entry point ==
+ * ============================
+ *
+ * void omap4_cpu_resume(void)
+ *
+ * ROM code jumps to this function while waking up from CPU
+ * OFF or DORMANT state. Physical address of the function is
+ * stored in the SAR RAM while entering to OFF or DORMANT mode.
+ * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET.
+ */
+ENTRY(omap4_cpu_resume)
+	/*
+	 * Configure ACTRL and enable NS SMP bit access on CPU1 on HS device.
+	 * OMAP44XX EMU/HS devices - CPU0 SMP bit access is enabled in PPA
+	 * init and for CPU1, a secure PPA API provided. CPU0 must be ON
+	 * while executing NS_SMP API on CPU1 and PPA version must be 1.4.0+.
+	 * OMAP443X GP devices- SMP bit isn't accessible.
+	 * OMAP446X GP devices - SMP bit access is enabled on both CPUs.
+	 */
+	ldr	r8, =OMAP44XX_SAR_RAM_BASE
+	ldr	r9, [r8, #OMAP_TYPE_OFFSET]
+	cmp	r9, #0x1			@ Skip if GP device
+	bne	skip_ns_smp_enable
+	mrc     p15, 0, r0, c0, c0, 5
+	ands    r0, r0, #0x0f
+	beq	skip_ns_smp_enable
+ppa_actrl_retry:
+	mov     r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX
+	adr	r3, ppa_zero_params		@ Pointer to parameters
+	mov	r1, #0x0			@ Process ID
+	mov	r2, #0x4			@ Flag
+	mov	r6, #0xff
+	mov	r12, #0x00			@ Secure Service ID
+	DO_SMC
+	cmp	r0, #0x0			@ API returns 0 on success.
+	beq	enable_smp_bit
+	b	ppa_actrl_retry
+enable_smp_bit:
+	mrc	p15, 0, r0, c1, c0, 1
+	tst	r0, #(1 << 6)			@ Check SMP bit enabled?
+	orreq	r0, r0, #(1 << 6)
+	mcreq	p15, 0, r0, c1, c0, 1
+	isb
+skip_ns_smp_enable:
+
+	b	cpu_resume			@ Jump to generic resume
+ENDPROC(omap4_cpu_resume)
+#endif
+
+ENTRY(omap_do_wfi)
+	stmfd	sp!, {lr}
+
+	/*
+	 * Execute an ISB instruction to ensure that all of the
+	 * CP15 register changes have been committed.
+	 */
+	isb
+
+	/*
+	 * Execute a barrier instruction to ensure that all cache,
+	 * TLB and branch predictor maintenance operations issued
+	 * by any CPU in the cluster have completed.
+	 */
+	dsb
+	dmb
+
+	/*
+	 * Execute a WFI instruction and wait until the
+	 * STANDBYWFI output is asserted to indicate that the
+	 * CPU is in idle and low power state. CPU can specualatively
+	 * prefetch the instructions so add NOPs after WFI. Sixteen
+	 * NOPs as per Cortex-A9 pipeline.
+	 */
+	wfi					@ Wait For Interrupt
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	ldmfd	sp!, {pc}
+ENDPROC(omap_do_wfi)