Merge branch 'tracking-armlt-tc2-pm' into lsk-3.9-vexpress

Conflicts:
	arch/arm/mach-vexpress/Kconfig
	arch/arm/mach-vexpress/Makefile

11 files changed, 602 insertions, 8 deletions

diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index f9f8c15baa9..ec20bd48fb0 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -15,7 +15,7 @@
 	model = "V2P-CA15_CA7";
 	arm,hbi = <0x249>;
 	arm,vexpress,site = <0xf>;
-	compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress";
+	compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic";
 	interrupt-parent = <&gic>;
 	#address-cells = <2>;
 	#size-cells = <2>;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 166e427ed2b..3f0d5e969ef 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -260,6 +260,19 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 	int aliasing_icache;
 	unsigned int id_reg, num_sets, line_size;
 
+#ifdef CONFIG_BIG_LITTLE
+	/*
+	 * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+	 * A7 = VIPT aliasing I-cache
+	 * A15 = PIPT (non-aliasing) I-cache
+	 * To cater for this discrepancy, let's assume aliasing I-cache
+	 * all the time.  This means unneeded extra work on the A15 but
+	 * only ptrace is affected which is not performance critical.
+	 */
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+		return 1;
+#endif
+
 	/* PIPT caches never alias. */
 	if (icache_is_pipt())
 		return 0;
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 987dcf33415..b5c1e636ed8 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,6 +4,7 @@
 #include <asm/assembler.h>
 #include <asm/glue-cache.h>
 #include <asm/glue-proc.h>
+#include "entry-header.S"
 	.text
 
 /*
@@ -30,9 +31,8 @@ ENTRY(__cpu_suspend)
 	mov	r2, r5			@ virtual SP
 	ldr	r3, =sleep_save_sp
 #ifdef CONFIG_SMP
-	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
-	ALT_UP(mov lr, #0)
-	and	lr, lr, #15
+	get_thread_info	r5
+	ldr	lr, [r5, #TI_CPU] 	@ cpu logical index
 	add	r3, r3, lr, lsl #2
 #endif
 	bl	__cpu_suspend_save
@@ -82,10 +82,13 @@ ENDPROC(cpu_resume_after_mmu)
 	.align
 ENTRY(cpu_resume)
 #ifdef CONFIG_SMP
+	mov	r1, #0			@ fall-back logical index for UP
+	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
+	ALT_UP_B(1f)
+	bic	r0, #0xff000000
+	bl	cpu_logical_index 	@ return logical index in r1
+1:
 	adr	r0, sleep_save_sp
-	ALT_SMP(mrc p15, 0, r1, c0, c0, 5)
-	ALT_UP(mov r1, #0)
-	and	r1, r1, #15
 	ldr	r0, [r0, r1, lsl #2]	@ stack phys addr
 #else
 	ldr	r0, sleep_save_sp	@ stack phys addr
@@ -102,3 +105,20 @@ sleep_save_sp:
 	.rept	CONFIG_NR_CPUS
 	.long	0				@ preserve stack phys ptr here
 	.endr
+
+#ifdef CONFIG_SMP
+cpu_logical_index:
+	adr	r3, cpu_map_ptr
+	ldr	r2, [r3]
+	add	r3, r3, r2		@ virt_to_phys(__cpu_logical_map)
+	mov	r1, #0
+1:
+	ldr	r2, [r3, r1, lsl #2]
+	cmp	r2, r0
+	moveq	pc, lr
+	add	r1, r1, #1
+	b	1b
+
+cpu_map_ptr:
+	.long __cpu_logical_map - .
+#endif
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 49e97ef3933..8aac82faa67 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -60,5 +60,13 @@ config ARCH_VEXPRESS_DCSCB
 	  Support for the Dual Cluster System Configuration Block (DCSCB).
 	  This is needed to provide CPU and cluster power management
 	  on RTSM.
+	  
+config ARCH_VEXPRESS_TC2
+	bool "TC2 cluster management"
+	depends on MCPM
+	select ARM_SPC
+	select ARM_CCI
+	help
+	  Support for CPU and cluster power management on TC2.
 
 endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index f5b78d49246..fb3799e5d22 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -8,5 +8,7 @@ obj-y					:= v2m.o reset.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 CFLAGS_REMOVE_dcscb.o			= -pg
+obj-$(CONFIG_ARCH_VEXPRESS_TC2)		+= tc2_pm.o tc2_pm_setup.o
+CFLAGS_REMOVE_tc2_pm.o			= -pg
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
new file mode 100644
index 00000000000..54757301ca5
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -0,0 +1,258 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
+ *
+ * Created by:	Nicolas Pitre, October 2012
+ * Copyright:	(C) 2012  Linaro Limited
+ *
+ * Some portions of this file were originally written by Achin Gupta
+ * Copyright:   (C) 2012  ARM Limited
+ *
+ * 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/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() after its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static int tc2_pm_use_count[3][2];
+
+static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+{
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cluster >= 2 || cpu >= vexpress_spc_get_nb_cpus(cluster))
+		return -EINVAL;
+
+	/*
+	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+	 * variant exists, we need to disable IRQs manually here.
+	 */
+	local_irq_disable();
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (!tc2_pm_use_count[0][cluster] &&
+	    !tc2_pm_use_count[1][cluster] &&
+	    !tc2_pm_use_count[2][cluster])
+		vexpress_spc_powerdown_enable(cluster, 0);
+
+	tc2_pm_use_count[cpu][cluster]++;
+	if (tc2_pm_use_count[cpu][cluster] == 1) {
+		vexpress_spc_write_bxaddr_reg(cluster, cpu,
+					      virt_to_phys(mcpm_entry_point));
+		vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+	} else if (tc2_pm_use_count[cpu][cluster] != 2) {
+		/*
+		 * The only possible values are:
+		 * 0 = CPU down
+		 * 1 = CPU (still) up
+		 * 2 = CPU requested to be up before it had a chance
+		 *     to actually make itself down.
+		 * Any other value is a bug.
+		 */
+		BUG();
+	}
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void tc2_pm_down(u64 residency)
+{
+	unsigned int mpidr, cpu, cluster;
+	bool last_man = false, skip_wfi = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= 2 || cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	arch_spin_lock(&tc2_pm_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	tc2_pm_use_count[cpu][cluster]--;
+	if (tc2_pm_use_count[cpu][cluster] == 0) {
+		vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+		if (!tc2_pm_use_count[0][cluster] &&
+		    !tc2_pm_use_count[1][cluster] &&
+		    !tc2_pm_use_count[2][cluster] &&
+		    (!residency || residency > 5000)) {
+			vexpress_spc_powerdown_enable(cluster, 1);
+			vexpress_spc_set_global_wakeup_intr(1);
+			last_man = true;
+		}
+	} else if (tc2_pm_use_count[cpu][cluster] == 1) {
+		/*
+		 * A power_up request went ahead of us.
+		 * Even if we do not want to shut this CPU down,
+		 * the caller expects a certain state as if the WFI
+		 * was aborted.  So let's continue with cache cleaning.
+		 */
+		skip_wfi = true;
+	} else
+		BUG();
+
+	gic_cpu_if_down();
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		arch_spin_unlock(&tc2_pm_lock);
+
+		set_cr(get_cr() & ~CR_C);
+		flush_cache_all();
+		asm volatile ("clrex");
+		set_auxcr(get_auxcr() & ~(1 << 6));
+
+		disable_cci(cluster);
+
+		/*
+		 * Ensure that both C & I bits are disabled in the SCTLR
+		 * before disabling ACE snoops. This ensures that no
+		 * coherency traffic will originate from this cpu after
+		 * ACE snoops are turned off.
+		 */
+		cpu_proc_fin();
+
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		/*
+		 * If last man then undo any setup done previously.
+		 */
+		if (last_man) {
+			vexpress_spc_powerdown_enable(cluster, 0);
+			vexpress_spc_set_global_wakeup_intr(0);
+		}
+
+		arch_spin_unlock(&tc2_pm_lock);
+
+		set_cr(get_cr() & ~CR_C);
+		flush_cache_louis();
+		asm volatile ("clrex");
+		set_auxcr(get_auxcr() & ~(1 << 6));
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	if (!skip_wfi)
+		wfi();
+
+	/* Not dead at this point?  Let our caller cope. */
+}
+
+static void tc2_pm_power_down(void)
+{
+	tc2_pm_down(0);
+}
+
+static void tc2_pm_suspend(u64 residency)
+{
+	extern void tc2_resume(void);
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	vexpress_spc_write_bxaddr_reg(cluster, cpu,
+				      virt_to_phys(tc2_resume));
+
+	tc2_pm_down(residency);
+}
+
+static void tc2_pm_powered_up(void)
+{
+	unsigned int mpidr, cpu, cluster;
+	unsigned long flags;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= 2 || cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+	local_irq_save(flags);
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (!tc2_pm_use_count[0][cluster] &&
+	    !tc2_pm_use_count[1][cluster] &&
+	    !tc2_pm_use_count[2][cluster]) {
+		vexpress_spc_powerdown_enable(cluster, 0);
+		vexpress_spc_set_global_wakeup_intr(0);
+	}
+
+	if (!tc2_pm_use_count[cpu][cluster])
+		tc2_pm_use_count[cpu][cluster] = 1;
+
+	vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0);
+	vexpress_spc_write_bxaddr_reg(cluster, cpu, 0);
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_restore(flags);
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up	= tc2_pm_power_up,
+	.power_down	= tc2_pm_power_down,
+	.suspend	= tc2_pm_suspend,
+	.powered_up	= tc2_pm_powered_up,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cpu >= 3 || cluster >= 2);
+	tc2_pm_use_count[cpu][cluster] = 1;
+}
+
+extern void tc2_pm_power_up_setup(unsigned int affinity_level);
+
+static int __init tc2_pm_init(void)
+{
+	int ret;
+
+	if (!vexpress_spc_check_loaded())
+		return -ENODEV;
+
+	tc2_pm_usage_count_init();
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(tc2_pm_power_up_setup);
+	if (!ret)
+		pr_info("TC2 power management initialized\n");
+	return ret;
+}
+
+early_initcall(tc2_pm_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S
new file mode 100644
index 00000000000..4728f83731a
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_setup.S
@@ -0,0 +1,102 @@
+/*
+ * arch/arm/include/asm/tc2_pm_setup.S
+ *
+ * Created by: Nicolas Pitre, October 2012
+ (             (based on dcscb_setup.S by Dave Martin)
+ * Copyright:  (C) 2012  Linaro Limited
+ *
+ * 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/mcpm.h>
+
+
+#define SPC_PHYS_BASE		0x7FFF0000
+#define SPC_WAKE_INT_STAT	0xb2c
+
+#define SNOOP_CTL_A15		0x404
+#define SNOOP_CTL_A7		0x504
+
+#define A15_SNOOP_MASK		(0x3 << 7)
+#define A7_SNOOP_MASK		(0x1 << 13)
+
+#define A15_BX_ADDR0		0xB68
+
+
+#define CCI_PHYS_BASE		0x2c090000
+
+#define SLAVE_SNOOPCTL_OFFSET	0
+#define SNOOPCTL_SNOOP_ENABLE	(1 << 0)
+#define SNOOPCTL_DVM_ENABLE	(1 << 1)
+
+#define CCI_STATUS_OFFSET	0xc
+#define STATUS_CHANGE_PENDING	(1 << 0)
+
+#define CCI_SLAVE_OFFSET(n)	(0x1000 + 0x1000 * (n))
+#define CCI_SLAVE_A15		3
+#define CCI_SLAVE_A7		4
+#define CCI_A15_OFFSET		CCI_SLAVE_OFFSET(CCI_SLAVE_A15)
+#define CCI_A7_OFFSET		CCI_SLAVE_OFFSET(CCI_SLAVE_A7)
+
+
+ENTRY(tc2_resume)
+	mrc	p15, 0, r0, c0, c0, 5
+	ubfx	r1, r0, #0, #4		@ r1 = cpu
+	ubfx	r2, r0, #8, #4		@ r2 = cluster
+	add	r1, r1, r2, lsl #2	@ r1 = index of CPU in WAKE_INT_STAT
+	ldr	r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT
+	ldr	r3, [r3]
+	lsr	r3, r1
+	tst	r3, #1
+	wfieq				@ if no pending IRQ reenters wfi
+	b	mcpm_entry_point
+ENDPROC(tc2_resume)
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ */
+
+ENTRY(tc2_pm_power_up_setup)
+
+	cmp	r0, #0
+	beq	2f
+
+	@ Enable CCI snoops
+	mrc	p15, 0, r0, c0, c0, 5	@ MPIDR
+	ubfx	r0, r0, #8, #4		@ cluster
+	ldr	r3, =CCI_PHYS_BASE + CCI_A15_OFFSET
+	cmp	r0, #0		@ A15 cluster?
+	addne	r3, r3, #CCI_A7_OFFSET - CCI_A15_OFFSET
+
+	@ r3 now points to the correct CCI slave register block
+	ldr	r0, [r3, #SLAVE_SNOOPCTL_OFFSET]
+	orr	r0, r0, #SNOOPCTL_SNOOP_ENABLE | SNOOPCTL_DVM_ENABLE
+	str	r0, [r3, #SLAVE_SNOOPCTL_OFFSET]	@ enable CCI snoops
+
+	@ Wait for snoop control change to complete:
+	ldr	r3, =CCI_PHYS_BASE
+1:	ldr	r0, [r3, #CCI_STATUS_OFFSET]
+	tst	r0, #STATUS_CHANGE_PENDING
+	bne	1b
+
+	bx	lr
+
+2:	@ Clear the BX addr register
+	ldr	r3, =SPC_PHYS_BASE + A15_BX_ADDR0
+	mrc	p15, 0, r0, c0, c0, 5	@ MPIDR
+	ubfx	r1, r0, #8, #4		@ cluster
+	ubfx	r0, r0, #0, #4		@ cpu
+	add	r3, r3, r1, lsl #4
+	mov	r1, #0
+	str	r1, [r3, r0, lsl #2]
+	dsb
+
+	bx	lr
+
+ENDPROC(tc2_pm_power_up_setup)
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 24c6e7d945e..6a7e6a9beff 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -4,6 +4,6 @@
 
 obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
-
+obj-$(CONFIG_BIG_LITTLE) += arm_big_little.o
 obj-$(CONFIG_CPU_IDLE_CALXEDA) += cpuidle-calxeda.o
 obj-$(CONFIG_CPU_IDLE_KIRKWOOD) += cpuidle-kirkwood.o
diff --git a/drivers/cpuidle/arm_big_little.c b/drivers/cpuidle/arm_big_little.c
new file mode 100644
index 00000000000..a430800d4a7
--- /dev/null
+++ b/drivers/cpuidle/arm_big_little.c
@@ -0,0 +1,183 @@
+/*
+ * big.LITTLE CPU idle driver.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.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/arm-cci.h>
+#include <linux/bitmap.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/clockchips.h>
+#include <linux/debugfs.h>
+#include <linux/hrtimer.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/tick.h>
+#include <linux/vexpress.h>
+#include <asm/mcpm.h>
+#include <asm/cpuidle.h>
+#include <asm/cputype.h>
+#include <asm/idmap.h>
+#include <asm/proc-fns.h>
+#include <asm/suspend.h>
+#include <linux/of.h>
+
+static int bl_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
+{
+	ktime_t time_start, time_end;
+	s64 diff;
+
+	time_start = ktime_get();
+
+	cpu_do_idle();
+
+	time_end = ktime_get();
+
+	local_irq_enable();
+
+	diff = ktime_to_us(ktime_sub(time_end, time_start));
+	if (diff > INT_MAX)
+		diff = INT_MAX;
+
+	dev->last_residency = (int) diff;
+
+	return index;
+}
+
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int idx);
+
+static struct cpuidle_state bl_cpuidle_set[] __initdata = {
+	[0] = {
+		.enter                  = bl_cpuidle_simple_enter,
+		.exit_latency           = 1,
+		.target_residency       = 1,
+		.power_usage		= UINT_MAX,
+		.flags                  = CPUIDLE_FLAG_TIME_VALID,
+		.name                   = "WFI",
+		.desc                   = "ARM WFI",
+	},
+	[1] = {
+		.enter			= bl_enter_powerdown,
+		.exit_latency		= 300,
+		.target_residency	= 1000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID,
+		.name			= "C1",
+		.desc			= "ARM power down",
+	},
+};
+
+struct cpuidle_driver bl_idle_driver = {
+	.name = "bl_idle",
+	.owner = THIS_MODULE,
+	.safe_state_index = 0
+};
+
+static DEFINE_PER_CPU(struct cpuidle_device, bl_idle_dev);
+
+static int notrace bl_powerdown_finisher(unsigned long arg)
+{
+	unsigned int mpidr = read_cpuid_mpidr();
+	unsigned int cluster = (mpidr >> 8) & 0xf;
+	unsigned int cpu = mpidr & 0xf;
+
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	mcpm_cpu_suspend(0);  /* 0 should be replaced with better value here */
+	return 1;
+}
+
+/*
+ * bl_enter_powerdown - Programs CPU to enter the specified state
+ * @dev: cpuidle device
+ * @drv: The target state to be programmed
+ * @idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int idx)
+{
+	struct timespec ts_preidle, ts_postidle, ts_idle;
+	int ret;
+
+	/* Used to keep track of the total time in idle */
+	getnstimeofday(&ts_preidle);
+
+	BUG_ON(!irqs_disabled());
+
+	cpu_pm_enter();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+
+	ret = cpu_suspend((unsigned long) dev, bl_powerdown_finisher);
+	if (ret)
+		BUG();
+
+	mcpm_cpu_powered_up();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	cpu_pm_exit();
+
+	getnstimeofday(&ts_postidle);
+	local_irq_enable();
+	ts_idle = timespec_sub(ts_postidle, ts_preidle);
+
+	dev->last_residency = ts_idle.tv_nsec / NSEC_PER_USEC +
+					ts_idle.tv_sec * USEC_PER_SEC;
+	return idx;
+}
+
+/*
+ * bl_idle_init
+ *
+ * Registers the bl specific cpuidle driver with the cpuidle
+ * framework with the valid set of states.
+ */
+int __init bl_idle_init(void)
+{
+	struct cpuidle_device *dev;
+	int i, cpu_id;
+	struct cpuidle_driver *drv = &bl_idle_driver;
+
+	if (!of_find_compatible_node(NULL, NULL, "arm,generic")) {
+		pr_info("%s: No compatible node found\n", __func__);
+		return -ENODEV;
+	}
+
+	drv->state_count = (sizeof(bl_cpuidle_set) /
+				       sizeof(struct cpuidle_state));
+
+	for (i = 0; i < drv->state_count; i++) {
+		memcpy(&drv->states[i], &bl_cpuidle_set[i],
+				sizeof(struct cpuidle_state));
+	}
+
+	cpuidle_register_driver(drv);
+
+	for_each_cpu(cpu_id, cpu_online_mask) {
+		pr_err("CPUidle for CPU%d registered\n", cpu_id);
+		dev = &per_cpu(bl_idle_dev, cpu_id);
+		dev->cpu = cpu_id;
+
+		dev->state_count = drv->state_count;
+
+		if (cpuidle_register_device(dev)) {
+			printk(KERN_ERR "%s: Cpuidle register device failed\n",
+			       __func__);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+late_initcall(bl_idle_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 487caf473b6..e2931de32e6 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -453,6 +453,12 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
+void gic_cpu_if_down(void)
+{
+	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
+	writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+}
+
 #ifdef CONFIG_CPU_PM
 /*
  * Saves the GIC distributor registers during suspend or idle.  Must be called
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 3e203eb23cc..b5696108c06 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -67,6 +67,8 @@ void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
 		    u32 offset, struct device_node *);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 
+void gic_cpu_if_down(void);
+
 static inline void gic_init(unsigned int nr, int start,
 			    void __iomem *dist , void __iomem *cpu)
 {