Merge tag 'armsoc-soc' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc

Pull ARM SoC platform updates from Olof Johansson:
 "Our SoC branch usually contains expanded support for new SoCs and
  other core platform code.  In this case, that includes:

   - support for the new Annapurna Labs "Alpine" platform

   - a rework greatly simplifying adding new platform support to the
     MCPM subsystem (Multi-cluster power management)

   - cpuidle and PM improvements for Exynos3250

   - misc updates for Renesas, OMAP, Meson, i.MX.  Some of these could
     have gone in other branches but ended up here for various reasons"

* tag 'armsoc-soc' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (53 commits)
  ARM: alpine: add support for generic pci
  ARM: Exynos: migrate DCSCB to the new MCPM backend abstraction
  ARM: vexpress: migrate DCSCB to the new MCPM backend abstraction
  ARM: vexpress: DCSCB: tighten CPU validity assertion
  ARM: vexpress: migrate TC2 to the new MCPM backend abstraction
  ARM: MCPM: move the algorithmic complexity to the core code
  ARM: EXYNOS: allow cpuidle driver usage on Exynos3250 SoC
  ARM: EXYNOS: add AFTR mode support for Exynos3250
  ARM: EXYNOS: add code for setting/clearing boot flag
  ARM: EXYNOS: fix CPU1 hotplug on Exynos3250
  ARM: S3C64XX: Use fixed IRQ bases to avoid conflicts on Cragganmore
  ARM: cygnus: fix const declaration bcm_cygnus_dt_compat
  ARM: DRA7: hwmod: Fix the hwmod class for GPTimer4
  ARM: DRA7: hwmod: Add data for GPTimers 13 through 16
  ARM: EXYNOS: Remove left over 'extra_save'
  ARM: EXYNOS: Constify exynos_pm_data array
  ARM: EXYNOS: use static in suspend.c
  ARM: EXYNOS: Use platform device name as power domain name
  ARM: EXYNOS: add support for async-bridge clocks for pm_domains
  ARM: omap-device: add missed callback for suspend-to-disk
  ...

47 files changed, 1390 insertions, 618 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c8baa96ed748..d74c9ea6eb06 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -839,6 +839,8 @@ config ARCH_VIRT
 #
 source "arch/arm/mach-mvebu/Kconfig"
 
+source "arch/arm/mach-alpine/Kconfig"
+
 source "arch/arm/mach-asm9260/Kconfig"
 
 source "arch/arm/mach-at91/Kconfig"
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 4cfb4b8fc2dd..771d5185a397 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -93,6 +93,14 @@ choice
 	prompt "Kernel low-level debugging port"
 	depends on DEBUG_LL
 
+	config DEBUG_ALPINE_UART0
+		bool "Kernel low-level debugging messages via Alpine UART0"
+		depends on ARCH_ALPINE
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Alpine based platforms.
+
 	config DEBUG_ASM9260_UART
 		bool "Kernel low-level debugging via asm9260 UART"
 		depends on MACH_ASM9260
@@ -1397,6 +1405,7 @@ config DEBUG_UART_PHYS
 	default 0xf8b00000 if DEBUG_HIX5HD2_UART
 	default 0xf991e000 if DEBUG_QCOM_UARTDM
 	default 0xfcb00000 if DEBUG_HI3620_UART
+	default 0xfd883000 if DEBUG_ALPINE_UART0
 	default 0xfe800000 if ARCH_IOP32X
 	default 0xff690000 if DEBUG_RK32_UART2
 	default 0xffc02000 if DEBUG_SOCFPGA_UART
@@ -1462,6 +1471,7 @@ config DEBUG_UART_VIRT
 	default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
 	default 0xfd000000 if ARCH_SPEAR13XX
 	default 0xfd012000 if ARCH_MV78XX0
+	default 0xfd883000 if DEBUG_ALPINE_UART0
 	default 0xfde12000 if ARCH_DOVE
 	default 0xfe012000 if ARCH_ORION5X
 	default 0xf31004c0 if DEBUG_MESON_UARTAO
@@ -1522,7 +1532,7 @@ config DEBUG_UART_8250_WORD
 	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
 	depends on DEBUG_UART_8250_SHIFT >= 2
 	default y if DEBUG_PICOXCELL_UART || DEBUG_SOCFPGA_UART || \
-		ARCH_KEYSTONE || \
+		ARCH_KEYSTONE || DEBUG_ALPINE_UART0 || \
 		DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \
 		DEBUG_DAVINCI_DA8XX_UART2 || \
 		DEBUG_BCM_KONA_UART || DEBUG_RK32_UART2 || \
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index cced41d40ce2..985227cbbd1b 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -142,6 +142,7 @@ textofs-$(CONFIG_ARCH_AXXIA) := 0x00308000
 
 # Machine directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.
+machine-$(CONFIG_ARCH_ALPINE)		+= alpine
 machine-$(CONFIG_ARCH_AT91)		+= at91
 machine-$(CONFIG_ARCH_AXXIA)		+= axxia
 machine-$(CONFIG_ARCH_BCM)		+= bcm
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 0c3b6783b72a..2a0f895c48d0 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -513,9 +513,27 @@
 	pinctrl-0 = <&iic3_pins>;
 	status = "okay";
 
+	pmic@58 {
+		compatible = "dlg,da9063";
+		reg = <0x58>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+
+		rtc {
+			compatible = "dlg,da9063-rtc";
+		};
+
+		wdt {
+			compatible = "dlg,da9063-watchdog";
+		};
+	};
+
 	vdd_dvfs: regulator@68 {
 		compatible = "dlg,da9210";
 		reg = <0x68>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 
 		regulator-min-microvolt = <1000000>;
 		regulator-max-microvolt = <1000000>;
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index a3c27807f6c5..b2dcf640d583 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -517,9 +517,27 @@
 	status = "okay";
 	clock-frequency = <100000>;
 
+	pmic@58 {
+		compatible = "dlg,da9063";
+		reg = <0x58>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+
+		rtc {
+			compatible = "dlg,da9063-rtc";
+		};
+
+		wdt {
+			compatible = "dlg,da9063-watchdog";
+		};
+	};
+
 	vdd_dvfs: regulator@68 {
 		compatible = "dlg,da9210";
 		reg = <0x68>;
+		interrupt-parent = <&irqc0>;
+		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 
 		regulator-min-microvolt = <1000000>;
 		regulator-max-microvolt = <1000000>;
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 3c165fc2dce2..5f8a52ac7edf 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -55,22 +55,81 @@ bool mcpm_is_available(void)
 	return (platform_ops) ? true : false;
 }
 
+/*
+ * 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 mcpm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static int mcpm_cpu_use_count[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
+
+static inline bool mcpm_cluster_unused(unsigned int cluster)
+{
+	int i, cnt;
+	for (i = 0, cnt = 0; i < MAX_CPUS_PER_CLUSTER; i++)
+		cnt |= mcpm_cpu_use_count[cluster][i];
+	return !cnt;
+}
+
 int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
 {
+	bool cpu_is_down, cluster_is_down;
+	int ret = 0;
+
 	if (!platform_ops)
 		return -EUNATCH; /* try not to shadow power_up errors */
 	might_sleep();
-	return platform_ops->power_up(cpu, cluster);
+
+	/* backward compatibility callback */
+	if (platform_ops->power_up)
+		return platform_ops->power_up(cpu, cluster);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+
+	/*
+	 * 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(&mcpm_lock);
+
+	cpu_is_down = !mcpm_cpu_use_count[cluster][cpu];
+	cluster_is_down = mcpm_cluster_unused(cluster);
+
+	mcpm_cpu_use_count[cluster][cpu]++;
+	/*
+	 * 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_ON(mcpm_cpu_use_count[cluster][cpu] != 1 &&
+	       mcpm_cpu_use_count[cluster][cpu] != 2);
+
+	if (cluster_is_down)
+		ret = platform_ops->cluster_powerup(cluster);
+	if (cpu_is_down && !ret)
+		ret = platform_ops->cpu_powerup(cpu, cluster);
+
+	arch_spin_unlock(&mcpm_lock);
+	local_irq_enable();
+	return ret;
 }
 
 typedef void (*phys_reset_t)(unsigned long);
 
 void mcpm_cpu_power_down(void)
 {
+	unsigned int mpidr, cpu, cluster;
+	bool cpu_going_down, last_man;
 	phys_reset_t phys_reset;
 
-	if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down))
-		return;
+	if (WARN_ON_ONCE(!platform_ops))
+	       return;
 	BUG_ON(!irqs_disabled());
 
 	/*
@@ -79,28 +138,65 @@ void mcpm_cpu_power_down(void)
 	 */
 	setup_mm_for_reboot();
 
-	platform_ops->power_down();
+	/* backward compatibility callback */
+	if (platform_ops->power_down) {
+		platform_ops->power_down();
+		goto not_dead;
+	}
+
+	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);
+
+	__mcpm_cpu_going_down(cpu, cluster);
 
+	arch_spin_lock(&mcpm_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+
+	mcpm_cpu_use_count[cluster][cpu]--;
+	BUG_ON(mcpm_cpu_use_count[cluster][cpu] != 0 &&
+	       mcpm_cpu_use_count[cluster][cpu] != 1);
+	cpu_going_down = !mcpm_cpu_use_count[cluster][cpu];
+	last_man = mcpm_cluster_unused(cluster);
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		platform_ops->cpu_powerdown_prepare(cpu, cluster);
+		platform_ops->cluster_powerdown_prepare(cluster);
+		arch_spin_unlock(&mcpm_lock);
+		platform_ops->cluster_cache_disable();
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		if (cpu_going_down)
+			platform_ops->cpu_powerdown_prepare(cpu, cluster);
+		arch_spin_unlock(&mcpm_lock);
+		/*
+		 * If cpu_going_down is false here, that means a power_up
+		 * request raced ahead of us.  Even if we do not want to
+		 * shut this CPU down, the caller still expects execution
+		 * to return through the system resume entry path, like
+		 * when the WFI is aborted due to a new IRQ or the like..
+		 * So let's continue with cache cleaning in all cases.
+		 */
+		platform_ops->cpu_cache_disable();
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	if (cpu_going_down)
+		wfi();
+
+not_dead:
 	/*
 	 * It is possible for a power_up request to happen concurrently
 	 * with a power_down request for the same CPU. In this case the
-	 * power_down method might not be able to actually enter a
-	 * powered down state with the WFI instruction if the power_up
-	 * method has removed the required reset condition.  The
-	 * power_down method is then allowed to return. We must perform
-	 * a re-entry in the kernel as if the power_up method just had
-	 * deasserted reset on the CPU.
-	 *
-	 * To simplify race issues, the platform specific implementation
-	 * must accommodate for the possibility of unordered calls to
-	 * power_down and power_up with a usage count. Therefore, if a
-	 * call to power_up is issued for a CPU that is not down, then
-	 * the next call to power_down must not attempt a full shutdown
-	 * but only do the minimum (normally disabling L1 cache and CPU
-	 * coherency) and return just as if a concurrent power_up request
-	 * had happened as described above.
+	 * CPU might not be able to actually enter a powered down state
+	 * with the WFI instruction if the power_up request has removed
+	 * the required reset condition.  We must perform a re-entry in
+	 * the kernel as if the power_up method just had deasserted reset
+	 * on the CPU.
 	 */
-
 	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
 	phys_reset(virt_to_phys(mcpm_entry_point));
 
@@ -125,26 +221,66 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 
 void mcpm_cpu_suspend(u64 expected_residency)
 {
-	phys_reset_t phys_reset;
-
-	if (WARN_ON_ONCE(!platform_ops || !platform_ops->suspend))
+	if (WARN_ON_ONCE(!platform_ops))
 		return;
-	BUG_ON(!irqs_disabled());
 
-	/* Very similar to mcpm_cpu_power_down() */
-	setup_mm_for_reboot();
-	platform_ops->suspend(expected_residency);
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
-	phys_reset(virt_to_phys(mcpm_entry_point));
-	BUG();
+	/* backward compatibility callback */
+	if (platform_ops->suspend) {
+		phys_reset_t phys_reset;
+		BUG_ON(!irqs_disabled());
+		setup_mm_for_reboot();
+		platform_ops->suspend(expected_residency);
+		phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+		phys_reset(virt_to_phys(mcpm_entry_point));
+		BUG();
+	}
+
+	/* Some platforms might have to enable special resume modes, etc. */
+	if (platform_ops->cpu_suspend_prepare) {
+		unsigned int mpidr = read_cpuid_mpidr();
+		unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+		unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); 
+		arch_spin_lock(&mcpm_lock);
+		platform_ops->cpu_suspend_prepare(cpu, cluster);
+		arch_spin_unlock(&mcpm_lock);
+	}
+	mcpm_cpu_power_down();
 }
 
 int mcpm_cpu_powered_up(void)
 {
+	unsigned int mpidr, cpu, cluster;
+	bool cpu_was_down, first_man;
+	unsigned long flags;
+
 	if (!platform_ops)
 		return -EUNATCH;
-	if (platform_ops->powered_up)
+
+	/* backward compatibility callback */
+	if (platform_ops->powered_up) {
 		platform_ops->powered_up();
+		return 0;
+	}
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	local_irq_save(flags);
+	arch_spin_lock(&mcpm_lock);
+
+	cpu_was_down = !mcpm_cpu_use_count[cluster][cpu];
+	first_man = mcpm_cluster_unused(cluster);
+
+	if (first_man && platform_ops->cluster_is_up)
+		platform_ops->cluster_is_up(cluster);
+	if (cpu_was_down)
+		mcpm_cpu_use_count[cluster][cpu] = 1;
+	if (platform_ops->cpu_is_up)
+		platform_ops->cpu_is_up(cpu, cluster);
+
+	arch_spin_unlock(&mcpm_lock);
+	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -334,8 +470,10 @@ int __init mcpm_sync_init(
 	}
 	mpidr = read_cpuid_mpidr();
 	this_cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-	for_each_online_cpu(i)
+	for_each_online_cpu(i) {
+		mcpm_cpu_use_count[this_cluster][i] = 1;
 		mcpm_sync.clusters[this_cluster].cpus[i].cpu = CPU_UP;
+	}
 	mcpm_sync.clusters[this_cluster].cluster = CLUSTER_UP;
 	sync_cache_w(&mcpm_sync);
 
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 3446f6a1d9fa..50b378f59e08 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -171,12 +171,73 @@ void mcpm_cpu_suspend(u64 expected_residency);
 int mcpm_cpu_powered_up(void);
 
 /*
- * Platform specific methods used in the implementation of the above API.
+ * Platform specific callbacks used in the implementation of the above API.
+ *
+ * cpu_powerup:
+ * Make given CPU runable. Called with MCPM lock held and IRQs disabled.
+ * The given cluster is assumed to be set up (cluster_powerup would have
+ * been called beforehand). Must return 0 for success or negative error code.
+ *
+ * cluster_powerup:
+ * Set up power for given cluster. Called with MCPM lock held and IRQs
+ * disabled. Called before first cpu_powerup when cluster is down. Must
+ * return 0 for success or negative error code.
+ *
+ * cpu_suspend_prepare:
+ * Special suspend configuration. Called on target CPU with MCPM lock held
+ * and IRQs disabled. This callback is optional. If provided, it is called
+ * before cpu_powerdown_prepare.
+ *
+ * cpu_powerdown_prepare:
+ * Configure given CPU for power down. Called on target CPU with MCPM lock
+ * held and IRQs disabled. Power down must be effective only at the next WFI instruction.
+ *
+ * cluster_powerdown_prepare:
+ * Configure given cluster for power down. Called on one CPU from target
+ * cluster with MCPM lock held and IRQs disabled. A cpu_powerdown_prepare
+ * for each CPU in the cluster has happened when this occurs.
+ *
+ * cpu_cache_disable:
+ * Clean and disable CPU level cache for the calling CPU. Called on with IRQs
+ * disabled only. The CPU is no longer cache coherent with the rest of the
+ * system when this returns.
+ *
+ * cluster_cache_disable:
+ * Clean and disable the cluster wide cache as well as the CPU level cache
+ * for the calling CPU. No call to cpu_cache_disable will happen for this
+ * CPU. Called with IRQs disabled and only when all the other CPUs are done
+ * with their own cpu_cache_disable. The cluster is no longer cache coherent
+ * with the rest of the system when this returns.
+ *
+ * cpu_is_up:
+ * Called on given CPU after it has been powered up or resumed. The MCPM lock
+ * is held and IRQs disabled. This callback is optional.
+ *
+ * cluster_is_up:
+ * Called by the first CPU to be powered up or resumed in given cluster.
+ * The MCPM lock is held and IRQs disabled. This callback is optional. If
+ * provided, it is called before cpu_is_up for that CPU.
+ *
+ * wait_for_powerdown:
+ * Wait until given CPU is powered down. This is called in sleeping context.
+ * Some reasonable timeout must be considered. Must return 0 for success or
+ * negative error code.
  */
 struct mcpm_platform_ops {
+	int (*cpu_powerup)(unsigned int cpu, unsigned int cluster);
+	int (*cluster_powerup)(unsigned int cluster);
+	void (*cpu_suspend_prepare)(unsigned int cpu, unsigned int cluster);
+	void (*cpu_powerdown_prepare)(unsigned int cpu, unsigned int cluster);
+	void (*cluster_powerdown_prepare)(unsigned int cluster);
+	void (*cpu_cache_disable)(void);
+	void (*cluster_cache_disable)(void);
+	void (*cpu_is_up)(unsigned int cpu, unsigned int cluster);
+	void (*cluster_is_up)(unsigned int cluster);
+	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
+
+	/* deprecated callbacks */
 	int (*power_up)(unsigned int cpu, unsigned int cluster);
 	void (*power_down)(void);
-	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
 	void (*suspend)(u64);
 	void (*powered_up)(void);
 };
diff --git a/arch/arm/mach-alpine/Kconfig b/arch/arm/mach-alpine/Kconfig
new file mode 100644
index 000000000000..2c44b930505a
--- /dev/null
+++ b/arch/arm/mach-alpine/Kconfig
@@ -0,0 +1,12 @@
+config ARCH_ALPINE
+	bool "Annapurna Labs Alpine platform" if ARCH_MULTI_V7
+	select ARM_AMBA
+	select ARM_GIC
+	select GENERIC_IRQ_CHIP
+	select HAVE_ARM_ARCH_TIMER
+	select HAVE_SMP
+	select MFD_SYSCON
+	select PCI
+	select PCI_HOST_GENERIC
+	help
+	  This enables support for the Annapurna Labs Alpine V1 boards.
diff --git a/arch/arm/mach-alpine/Makefile b/arch/arm/mach-alpine/Makefile
new file mode 100644
index 000000000000..b6674890be71
--- /dev/null
+++ b/arch/arm/mach-alpine/Makefile
@@ -0,0 +1,2 @@
+obj-y				+= alpine_machine.o
+obj-$(CONFIG_SMP)		+= platsmp.o alpine_cpu_pm.o
diff --git a/arch/arm/mach-alpine/alpine_cpu_pm.c b/arch/arm/mach-alpine/alpine_cpu_pm.c
new file mode 100644
index 000000000000..121c77c4b53c
--- /dev/null
+++ b/arch/arm/mach-alpine/alpine_cpu_pm.c
@@ -0,0 +1,70 @@
+/*
+ * Low-level power-management support for Alpine platform.
+ *
+ * Copyright (C) 2015 Annapurna Labs Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+
+#include "alpine_cpu_pm.h"
+#include "alpine_cpu_resume.h"
+
+/* NB registers */
+#define AL_SYSFAB_POWER_CONTROL(cpu)	(0x2000 + (cpu)*0x100 + 0x20)
+
+static struct regmap *al_sysfabric;
+static struct al_cpu_resume_regs __iomem *al_cpu_resume_regs;
+static int wakeup_supported;
+
+int alpine_cpu_wakeup(unsigned int phys_cpu, uint32_t phys_resume_addr)
+{
+	if (!wakeup_supported)
+		return -ENOSYS;
+
+	/*
+	 * Set CPU resume address -
+	 * secure firmware running on boot will jump to this address
+	 * after setting proper CPU mode, and initialiing e.g. secure
+	 * regs (the same mode all CPUs are booted to - usually HYP)
+	 */
+	writel(phys_resume_addr,
+	       &al_cpu_resume_regs->per_cpu[phys_cpu].resume_addr);
+
+	/* Power-up the CPU */
+	regmap_write(al_sysfabric, AL_SYSFAB_POWER_CONTROL(phys_cpu), 0);
+
+	return 0;
+}
+
+void __init alpine_cpu_pm_init(void)
+{
+	struct device_node *np;
+	uint32_t watermark;
+
+	al_sysfabric = syscon_regmap_lookup_by_compatible("al,alpine-sysfabric-service");
+
+	np = of_find_compatible_node(NULL, NULL, "al,alpine-cpu-resume");
+	al_cpu_resume_regs = of_iomap(np, 0);
+
+	wakeup_supported = !IS_ERR(al_sysfabric) && al_cpu_resume_regs;
+
+	if (wakeup_supported) {
+		watermark = readl(&al_cpu_resume_regs->watermark);
+		wakeup_supported = (watermark & AL_CPU_RESUME_MAGIC_NUM_MASK)
+				    == AL_CPU_RESUME_MAGIC_NUM;
+	}
+}
diff --git a/arch/arm/mach-alpine/alpine_cpu_pm.h b/arch/arm/mach-alpine/alpine_cpu_pm.h
new file mode 100644
index 000000000000..5179e697c492
--- /dev/null
+++ b/arch/arm/mach-alpine/alpine_cpu_pm.h
@@ -0,0 +1,26 @@
+/*
+ * Low-level power-management support for Alpine platform.
+ *
+ * Copyright (C) 2015 Annapurna Labs Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ALPINE_CPU_PM_H__
+#define __ALPINE_CPU_PM_H__
+
+/* Alpine CPU Power Management Services Initialization */
+void alpine_cpu_pm_init(void);
+
+/* Wake-up a CPU */
+int alpine_cpu_wakeup(unsigned int phys_cpu, uint32_t phys_resume_addr);
+
+#endif /* __ALPINE_CPU_PM_H__ */
diff --git a/arch/arm/mach-alpine/alpine_cpu_resume.h b/arch/arm/mach-alpine/alpine_cpu_resume.h
new file mode 100644
index 000000000000..c80150c0d2d8
--- /dev/null
+++ b/arch/arm/mach-alpine/alpine_cpu_resume.h
@@ -0,0 +1,38 @@
+/*
+ * Annapurna labs cpu-resume register structure.
+ *
+ * Copyright (C) 2015 Annapurna Labs Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef ALPINE_CPU_RESUME_H_
+#define ALPINE_CPU_RESUME_H_
+
+/* Per-cpu regs */
+struct al_cpu_resume_regs_per_cpu {
+	uint32_t	flags;
+	uint32_t	resume_addr;
+};
+
+/* general regs */
+struct al_cpu_resume_regs {
+	/* Watermark for validating the CPU resume struct */
+	uint32_t watermark;
+	uint32_t flags;
+	struct al_cpu_resume_regs_per_cpu per_cpu[];
+};
+
+/* The expected magic number for validating the resume addresses */
+#define AL_CPU_RESUME_MAGIC_NUM		0xf0e1d200
+#define AL_CPU_RESUME_MAGIC_NUM_MASK	0xffffff00
+
+#endif /* ALPINE_CPU_RESUME_H_ */
diff --git a/arch/arm/mach-alpine/alpine_machine.c b/arch/arm/mach-alpine/alpine_machine.c
new file mode 100644
index 000000000000..b8e2145e962b
--- /dev/null
+++ b/arch/arm/mach-alpine/alpine_machine.c
@@ -0,0 +1,28 @@
+/*
+ * Machine declaration for Alpine platforms.
+ *
+ * Copyright (C) 2015 Annapurna Labs Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of_platform.h>
+
+#include <asm/mach/arch.h>
+
+static const char * const al_match[] __initconst = {
+	"al,alpine",
+	NULL,
+};
+
+DT_MACHINE_START(AL_DT, "Annapurna Labs Alpine")
+	.dt_compat	= al_match,
+MACHINE_END
diff --git a/arch/arm/mach-alpine/platsmp.c b/arch/arm/mach-alpine/platsmp.c
new file mode 100644
index 000000000000..f78429f48bd6
--- /dev/null
+++ b/arch/arm/mach-alpine/platsmp.c
@@ -0,0 +1,49 @@
+/*
+ * SMP operations for Alpine platform.
+ *
+ * Copyright (C) 2015 Annapurna Labs Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <asm/smp_plat.h>
+
+#include "alpine_cpu_pm.h"
+
+static int alpine_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	phys_addr_t addr;
+
+	addr = virt_to_phys(secondary_startup);
+
+	if (addr > (phys_addr_t)(uint32_t)(-1)) {
+		pr_err("FAIL: resume address over 32bit (%pa)", &addr);
+		return -EINVAL;
+	}
+
+	return alpine_cpu_wakeup(cpu_logical_map(cpu), (uint32_t)addr);
+}
+
+static void __init alpine_smp_prepare_cpus(unsigned int max_cpus)
+{
+	alpine_cpu_pm_init();
+}
+
+static struct smp_operations alpine_smp_ops __initdata = {
+	.smp_prepare_cpus	= alpine_smp_prepare_cpus,
+	.smp_boot_secondary	= alpine_boot_secondary,
+};
+CPU_METHOD_OF_DECLARE(alpine_smp, "al,alpine-smp", &alpine_smp_ops);
diff --git a/arch/arm/mach-bcm/bcm_cygnus.c b/arch/arm/mach-bcm/bcm_cygnus.c
index 30dc58be51b8..7ae894c7849b 100644
--- a/arch/arm/mach-bcm/bcm_cygnus.c
+++ b/arch/arm/mach-bcm/bcm_cygnus.c
@@ -13,7 +13,7 @@
 
 #include <asm/mach/arch.h>
 
-static const char const *bcm_cygnus_dt_compat[] = {
+static const char * const bcm_cygnus_dt_compat[] __initconst = {
 	"brcm,cygnus",
 	NULL,
 };
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index f70eca7ee705..acd5b560b728 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -126,6 +126,12 @@ enum {
 
 void exynos_firmware_init(void);
 
+/* CPU BOOT mode flag for Exynos3250 SoC bootloader */
+#define C2_STATE	(1 << 3)
+
+void exynos_set_boot_flag(unsigned int cpu, unsigned int mode);
+void exynos_clear_boot_flag(unsigned int cpu, unsigned int mode);
+
 extern u32 exynos_get_eint_wake_mask(void);
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 8576a9f734bd..bcde0dd668df 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -214,6 +214,7 @@ static void __init exynos_dt_machine_init(void)
 	    of_machine_is_compatible("samsung,exynos4212") ||
 	    (of_machine_is_compatible("samsung,exynos4412") &&
 	     of_machine_is_compatible("samsung,trats2")) ||
+	    of_machine_is_compatible("samsung,exynos3250") ||
 	    of_machine_is_compatible("samsung,exynos5250"))
 		platform_device_register(&exynos_cpuidle);
 
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index 4791a3cc00f9..1bd35763f12e 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -48,7 +48,13 @@ static int exynos_do_idle(unsigned long mode)
 		__raw_writel(virt_to_phys(exynos_cpu_resume_ns),
 			     sysram_ns_base_addr + 0x24);
 		__raw_writel(EXYNOS_AFTR_MAGIC, sysram_ns_base_addr + 0x20);
-		exynos_smc(SMC_CMD_CPU0AFTR, 0, 0, 0);
+		if (soc_is_exynos3250()) {
+			exynos_smc(SMC_CMD_SAVE, OP_TYPE_CORE,
+				   SMC_POWERSTATE_IDLE, 0);
+			exynos_smc(SMC_CMD_SHUTDOWN, OP_TYPE_CLUSTER,
+				   SMC_POWERSTATE_IDLE, 0);
+		} else
+			exynos_smc(SMC_CMD_CPU0AFTR, 0, 0, 0);
 		break;
 	case FW_DO_IDLE_SLEEP:
 		exynos_smc(SMC_CMD_SLEEP, 0, 0, 0);
@@ -206,3 +212,28 @@ void __init exynos_firmware_init(void)
 		outer_cache.configure = exynos_l2_configure;
 	}
 }
+
+#define REG_CPU_STATE_ADDR	(sysram_ns_base_addr + 0x28)
+#define BOOT_MODE_MASK		0x1f
+
+void exynos_set_boot_flag(unsigned int cpu, unsigned int mode)
+{
+	unsigned int tmp;
+
+	tmp = __raw_readl(REG_CPU_STATE_ADDR + cpu * 4);
+
+	if (mode & BOOT_MODE_MASK)
+		tmp &= ~BOOT_MODE_MASK;
+
+	tmp |= mode;
+	__raw_writel(tmp, REG_CPU_STATE_ADDR + cpu * 4);
+}
+
+void exynos_clear_boot_flag(unsigned int cpu, unsigned int mode)
+{
+	unsigned int tmp;
+
+	tmp = __raw_readl(REG_CPU_STATE_ADDR + cpu * 4);
+	tmp &= ~mode;
+	__raw_writel(tmp, REG_CPU_STATE_ADDR + cpu * 4);
+}
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index b0d3c2e876fb..9bdf54795f05 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -61,25 +61,7 @@ static void __iomem *ns_sram_base_addr;
 	: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", \
 	  "r9", "r10", "lr", "memory")
 
-/*
- * 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 exynos_mcpm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-static int
-cpu_use_count[EXYNOS5420_CPUS_PER_CLUSTER][EXYNOS5420_NR_CLUSTERS];
-
-#define exynos_cluster_usecnt(cluster) \
-	(cpu_use_count[0][cluster] +   \
-	 cpu_use_count[1][cluster] +   \
-	 cpu_use_count[2][cluster] +   \
-	 cpu_use_count[3][cluster])
-
-#define exynos_cluster_unused(cluster) !exynos_cluster_usecnt(cluster)
-
-static int exynos_power_up(unsigned int cpu, unsigned int cluster)
+static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster)
 {
 	unsigned int cpunr = cpu + (cluster * EXYNOS5420_CPUS_PER_CLUSTER);
 
@@ -88,127 +70,65 @@ static int exynos_power_up(unsigned int cpu, unsigned int cluster)
 		cluster >= EXYNOS5420_NR_CLUSTERS)
 		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(&exynos_mcpm_lock);
-
-	cpu_use_count[cpu][cluster]++;
-	if (cpu_use_count[cpu][cluster] == 1) {
-		bool was_cluster_down =
-			(exynos_cluster_usecnt(cluster) == 1);
-
-		/*
-		 * Turn on the cluster (L2/COMMON) and then power on the
-		 * cores.
-		 */
-		if (was_cluster_down)
-			exynos_cluster_power_up(cluster);
-
-		exynos_cpu_power_up(cpunr);
-	} else if (cpu_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();
-	}
+	exynos_cpu_power_up(cpunr);
+	return 0;
+}
 
-	arch_spin_unlock(&exynos_mcpm_lock);
-	local_irq_enable();
+static int exynos_cluster_powerup(unsigned int cluster)
+{
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	if (cluster >= EXYNOS5420_NR_CLUSTERS)
+		return -EINVAL;
 
+	exynos_cluster_power_up(cluster);
 	return 0;
 }
 
-/*
- * NOTE: This function requires the stack data to be visible through power down
- * and can only be executed on processors like A15 and A7 that hit the cache
- * with the C bit clear in the SCTLR register.
- */
-static void exynos_power_down(void)
+static void exynos_cpu_powerdown_prepare(unsigned int cpu, unsigned int cluster)
 {
-	unsigned int mpidr, cpu, cluster;
-	bool last_man = false, skip_wfi = false;
-	unsigned int cpunr;
-
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-	cpunr =  cpu + (cluster * EXYNOS5420_CPUS_PER_CLUSTER);
+	unsigned int cpunr = cpu + (cluster * EXYNOS5420_CPUS_PER_CLUSTER);
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	BUG_ON(cpu >= EXYNOS5420_CPUS_PER_CLUSTER ||
 			cluster >= EXYNOS5420_NR_CLUSTERS);
+	exynos_cpu_power_down(cpunr);
+}
 
-	__mcpm_cpu_going_down(cpu, cluster);
-
-	arch_spin_lock(&exynos_mcpm_lock);
-	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
-	cpu_use_count[cpu][cluster]--;
-	if (cpu_use_count[cpu][cluster] == 0) {
-		exynos_cpu_power_down(cpunr);
-
-		if (exynos_cluster_unused(cluster)) {
-			exynos_cluster_power_down(cluster);
-			last_man = true;
-		}
-	} else if (cpu_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();
-	}
-
-	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
-		arch_spin_unlock(&exynos_mcpm_lock);
-
-		if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
-			/*
-			 * On the Cortex-A15 we need to disable
-			 * L2 prefetching before flushing the cache.
-			 */
-			asm volatile(
-			"mcr	p15, 1, %0, c15, c0, 3\n\t"
-			"isb\n\t"
-			"dsb"
-			: : "r" (0x400));
-		}
+static void exynos_cluster_powerdown_prepare(unsigned int cluster)
+{
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	BUG_ON(cluster >= EXYNOS5420_NR_CLUSTERS);
+	exynos_cluster_power_down(cluster);
+}
 
-		/* Flush all cache levels for this cluster. */
-		exynos_v7_exit_coherency_flush(all);
+static void exynos_cpu_cache_disable(void)
+{
+	/* Disable and flush the local CPU cache. */
+	exynos_v7_exit_coherency_flush(louis);
+}
 
+static void exynos_cluster_cache_disable(void)
+{
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
 		/*
-		 * Disable cluster-level coherency by masking
-		 * incoming snoops and DVM messages:
+		 * On the Cortex-A15 we need to disable
+		 * L2 prefetching before flushing the cache.
 		 */
-		cci_disable_port_by_cpu(mpidr);
-
-		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
-	} else {
-		arch_spin_unlock(&exynos_mcpm_lock);
-
-		/* Disable and flush the local CPU cache. */
-		exynos_v7_exit_coherency_flush(louis);
+		asm volatile(
+		"mcr	p15, 1, %0, c15, c0, 3\n\t"
+		"isb\n\t"
+		"dsb"
+		: : "r" (0x400));
 	}
 
-	__mcpm_cpu_down(cpu, cluster);
-
-	/* Now we are prepared for power-down, do it: */
-	if (!skip_wfi)
-		wfi();
+	/* Flush all cache levels for this cluster. */
+	exynos_v7_exit_coherency_flush(all);
 
-	/* Not dead at this point?  Let our caller cope. */
+	/*
+	 * Disable cluster-level coherency by masking
+	 * incoming snoops and DVM messages:
+	 */
+	cci_disable_port_by_cpu(read_cpuid_mpidr());
 }
 
 static int exynos_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
@@ -222,10 +142,8 @@ static int exynos_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
 
 	/* Wait for the core state to be OFF */
 	while (tries--) {
-		if (ACCESS_ONCE(cpu_use_count[cpu][cluster]) == 0) {
-			if ((exynos_cpu_power_state(cpunr) == 0))
-				return 0; /* success: the CPU is halted */
-		}
+		if ((exynos_cpu_power_state(cpunr) == 0))
+			return 0; /* success: the CPU is halted */
 
 		/* Otherwise, wait and retry: */
 		msleep(1);
@@ -234,63 +152,23 @@ static int exynos_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
 	return -ETIMEDOUT; /* timeout */
 }
 
-static void exynos_powered_up(void)
-{
-	unsigned int mpidr, cpu, cluster;
-
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-
-	arch_spin_lock(&exynos_mcpm_lock);
-	if (cpu_use_count[cpu][cluster] == 0)
-		cpu_use_count[cpu][cluster] = 1;
-	arch_spin_unlock(&exynos_mcpm_lock);
-}
-
-static void exynos_suspend(u64 residency)
+static void exynos_cpu_is_up(unsigned int cpu, unsigned int cluster)
 {
-	unsigned int mpidr, cpunr;
-
-	exynos_power_down();
-
-	/*
-	 * Execution reaches here only if cpu did not power down.
-	 * Hence roll back the changes done in exynos_power_down function.
-	 *
-	 * CAUTION: "This function requires the stack data to be visible through
-	 * power down and can only be executed on processors like A15 and A7
-	 * that hit the cache with the C bit clear in the SCTLR register."
-	*/
-	mpidr = read_cpuid_mpidr();
-	cpunr = exynos_pmu_cpunr(mpidr);
-
-	exynos_cpu_power_up(cpunr);
+	/* especially when resuming: make sure power control is set */
+	exynos_cpu_powerup(cpu, cluster);
 }
 
 static const struct mcpm_platform_ops exynos_power_ops = {
-	.power_up		= exynos_power_up,
-	.power_down		= exynos_power_down,
+	.cpu_powerup		= exynos_cpu_powerup,
+	.cluster_powerup	= exynos_cluster_powerup,
+	.cpu_powerdown_prepare	= exynos_cpu_powerdown_prepare,
+	.cluster_powerdown_prepare = exynos_cluster_powerdown_prepare,
+	.cpu_cache_disable	= exynos_cpu_cache_disable,
+	.cluster_cache_disable	= exynos_cluster_cache_disable,
 	.wait_for_powerdown	= exynos_wait_for_powerdown,
-	.suspend		= exynos_suspend,
-	.powered_up		= exynos_powered_up,
+	.cpu_is_up		= exynos_cpu_is_up,
 };
 
-static void __init exynos_mcpm_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 >= EXYNOS5420_CPUS_PER_CLUSTER  ||
-			cluster >= EXYNOS5420_NR_CLUSTERS);
-
-	cpu_use_count[cpu][cluster] = 1;
-}
-
 /*
  * Enable cluster-level coherency, in preparation for turning on the MMU.
  */
@@ -302,19 +180,6 @@ static void __naked exynos_pm_power_up_setup(unsigned int affinity_level)
 	"b	cci_enable_port_for_self");
 }
 
-static void __init exynos_cache_off(void)
-{
-	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
-		/* disable L2 prefetching on the Cortex-A15 */
-		asm volatile(
-		"mcr	p15, 1, %0, c15, c0, 3\n\t"
-		"isb\n\t"
-		"dsb"
-		: : "r" (0x400));
-	}
-	exynos_v7_exit_coherency_flush(all);
-}
-
 static const struct of_device_id exynos_dt_mcpm_match[] = {
 	{ .compatible = "samsung,exynos5420" },
 	{ .compatible = "samsung,exynos5800" },
@@ -370,13 +235,11 @@ static int __init exynos_mcpm_init(void)
 	 */
 	pmu_raw_writel(EXYNOS5420_SWRESET_KFC_SEL, S5P_PMU_SPARE3);
 
-	exynos_mcpm_usage_count_init();
-
 	ret = mcpm_platform_register(&exynos_power_ops);
 	if (!ret)
 		ret = mcpm_sync_init(exynos_pm_power_up_setup);
 	if (!ret)
-		ret = mcpm_loopback(exynos_cache_off); /* turn on the CCI */
+		ret = mcpm_loopback(exynos_cluster_cache_disable); /* turn on the CCI */
 	if (ret) {
 		iounmap(ns_sram_base_addr);
 		return ret;
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index d2e9f12d12f1..ebd135bb0995 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -126,6 +126,8 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
  */
 void exynos_cpu_power_down(int cpu)
 {
+	u32 core_conf;
+
 	if (cpu == 0 && (soc_is_exynos5420() || soc_is_exynos5800())) {
 		/*
 		 * Bypass power down for CPU0 during suspend. Check for
@@ -137,7 +139,10 @@ void exynos_cpu_power_down(int cpu)
 		if (!(val & S5P_CORE_LOCAL_PWR_EN))
 			return;
 	}
-	pmu_raw_writel(0, EXYNOS_ARM_CORE_CONFIGURATION(cpu));
+
+	core_conf = pmu_raw_readl(EXYNOS_ARM_CORE_CONFIGURATION(cpu));
+	core_conf &= ~S5P_CORE_LOCAL_PWR_EN;
+	pmu_raw_writel(core_conf, EXYNOS_ARM_CORE_CONFIGURATION(cpu));
 }
 
 /**
@@ -148,7 +153,12 @@ void exynos_cpu_power_down(int cpu)
  */
 void exynos_cpu_power_up(int cpu)
 {
-	pmu_raw_writel(S5P_CORE_LOCAL_PWR_EN,
+	u32 core_conf = S5P_CORE_LOCAL_PWR_EN;
+
+	if (soc_is_exynos3250())
+		core_conf |= S5P_CORE_AUTOWAKEUP_EN;
+
+	pmu_raw_writel(core_conf,
 			EXYNOS_ARM_CORE_CONFIGURATION(cpu));
 }
 
@@ -226,6 +236,10 @@ static void exynos_core_restart(u32 core_id)
 	if (!of_machine_is_compatible("samsung,exynos3250"))
 		return;
 
+	while (!pmu_raw_readl(S5P_PMU_SPARE2))
+		udelay(10);
+	udelay(10);
+
 	val = pmu_raw_readl(EXYNOS_ARM_CORE_STATUS(core_id));
 	val |= S5P_CORE_WAKEUP_FROM_LOCAL_CFG;
 	pmu_raw_writel(val, EXYNOS_ARM_CORE_STATUS(core_id));
@@ -346,7 +360,10 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 		call_firmware_op(cpu_boot, core_id);
 
-		arch_send_wakeup_ipi_mask(cpumask_of(cpu));
+		if (soc_is_exynos3250())
+			dsb_sev();
+		else
+			arch_send_wakeup_ipi_mask(cpumask_of(cpu));
 
 		if (pen_release == -1)
 			break;
diff --git a/arch/arm/mach-exynos/pm.c b/arch/arm/mach-exynos/pm.c
index 5685250693fd..cc75ab448be3 100644
--- a/arch/arm/mach-exynos/pm.c
+++ b/arch/arm/mach-exynos/pm.c
@@ -127,6 +127,8 @@ int exynos_pm_central_resume(void)
 static void exynos_set_wakeupmask(long mask)
 {
 	pmu_raw_writel(mask, S5P_WAKEUP_MASK);
+	if (soc_is_exynos3250())
+		pmu_raw_writel(0x0, S5P_WAKEUP_MASK2);
 }
 
 static void exynos_cpu_set_boot_vector(long flags)
@@ -140,7 +142,7 @@ static int exynos_aftr_finisher(unsigned long flags)
 {
 	int ret;
 
-	exynos_set_wakeupmask(0x0000ff3e);
+	exynos_set_wakeupmask(soc_is_exynos3250() ? 0x40003ffe : 0x0000ff3e);
 	/* Set value of power down register for aftr mode */
 	exynos_sys_powerdown_conf(SYS_AFTR);
 
@@ -157,8 +159,13 @@ static int exynos_aftr_finisher(unsigned long flags)
 
 void exynos_enter_aftr(void)
 {
+	unsigned int cpuid = smp_processor_id();
+
 	cpu_pm_enter();
 
+	if (soc_is_exynos3250())
+		exynos_set_boot_flag(cpuid, C2_STATE);
+
 	exynos_pm_central_suspend();
 
 	if (of_machine_is_compatible("samsung,exynos4212") ||
@@ -178,6 +185,9 @@ void exynos_enter_aftr(void)
 
 	exynos_pm_central_resume();
 
+	if (soc_is_exynos3250())
+		exynos_clear_boot_flag(cpuid, C2_STATE);
+
 	cpu_pm_exit();
 }
 
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 37266a826437..cbe56b35aea0 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -37,6 +37,7 @@ struct exynos_pm_domain {
 	struct clk *oscclk;
 	struct clk *clk[MAX_CLK_PER_DOMAIN];
 	struct clk *pclk[MAX_CLK_PER_DOMAIN];
+	struct clk *asb_clk[MAX_CLK_PER_DOMAIN];
 };
 
 static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
@@ -45,14 +46,19 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 	void __iomem *base;
 	u32 timeout, pwr;
 	char *op;
+	int i;
 
 	pd = container_of(domain, struct exynos_pm_domain, pd);
 	base = pd->base;
 
+	for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+		if (IS_ERR(pd->asb_clk[i]))
+			break;
+		clk_prepare_enable(pd->asb_clk[i]);
+	}
+
 	/* Set oscclk before powering off a domain*/
 	if (!power_on) {
-		int i;
-
 		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
 			if (IS_ERR(pd->clk[i]))
 				break;
@@ -81,8 +87,6 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 
 	/* Restore clocks after powering on a domain*/
 	if (power_on) {
-		int i;
-
 		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
 			if (IS_ERR(pd->clk[i]))
 				break;
@@ -92,6 +96,12 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 		}
 	}
 
+	for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+		if (IS_ERR(pd->asb_clk[i]))
+			break;
+		clk_disable_unprepare(pd->asb_clk[i]);
+	}
+
 	return 0;
 }
 
@@ -125,12 +135,21 @@ static __init int exynos4_pm_init_power_domain(void)
 			return -ENOMEM;
 		}
 
-		pd->pd.name = kstrdup(np->name, GFP_KERNEL);
+		pd->pd.name = kstrdup(dev_name(dev), GFP_KERNEL);
 		pd->name = pd->pd.name;
 		pd->base = of_iomap(np, 0);
 		pd->pd.power_off = exynos_pd_power_off;
 		pd->pd.power_on = exynos_pd_power_on;
 
+		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+			char clk_name[8];
+
+			snprintf(clk_name, sizeof(clk_name), "asb%d", i);
+			pd->asb_clk[i] = clk_get(dev, clk_name);
+			if (IS_ERR(pd->asb_clk[i]))
+				break;
+		}
+
 		pd->oscclk = clk_get(dev, "oscclk");
 		if (IS_ERR(pd->oscclk))
 			goto no_clk;
diff --git a/arch/arm/mach-exynos/regs-pmu.h b/arch/arm/mach-exynos/regs-pmu.h
index eb461e1c325a..b7614333d296 100644
--- a/arch/arm/mach-exynos/regs-pmu.h
+++ b/arch/arm/mach-exynos/regs-pmu.h
@@ -43,12 +43,14 @@
 #define S5P_WAKEUP_STAT				0x0600
 #define S5P_EINT_WAKEUP_MASK			0x0604
 #define S5P_WAKEUP_MASK				0x0608
+#define S5P_WAKEUP_MASK2				0x0614
 
 #define S5P_INFORM0				0x0800
 #define S5P_INFORM1				0x0804
 #define S5P_INFORM5				0x0814
 #define S5P_INFORM6				0x0818
 #define S5P_INFORM7				0x081C
+#define S5P_PMU_SPARE2				0x0908
 #define S5P_PMU_SPARE3				0x090C
 
 #define EXYNOS_IROM_DATA2			0x0988
@@ -182,6 +184,7 @@
 
 #define S5P_CORE_LOCAL_PWR_EN			0x3
 #define S5P_CORE_WAKEUP_FROM_LOCAL_CFG		(0x3 << 8)
+#define S5P_CORE_AUTOWAKEUP_EN			(1 << 31)
 
 /* Only for EXYNOS4210 */
 #define S5P_CMU_CLKSTOP_LCD1_LOWPWR	0x1154
diff --git a/arch/arm/mach-exynos/smc.h b/arch/arm/mach-exynos/smc.h
index f7b82f9c1e21..c2845717bc8f 100644
--- a/arch/arm/mach-exynos/smc.h
+++ b/arch/arm/mach-exynos/smc.h
@@ -17,6 +17,8 @@
 #define SMC_CMD_SLEEP		(-3)
 #define SMC_CMD_CPU1BOOT	(-4)
 #define SMC_CMD_CPU0AFTR	(-5)
+#define SMC_CMD_SAVE		(-6)
+#define SMC_CMD_SHUTDOWN	(-7)
 /* For CP15 Access */
 #define SMC_CMD_C15RESUME	(-11)
 /* For L2 Cache Access */
@@ -32,4 +34,11 @@ extern void exynos_smc(u32 cmd, u32 arg1, u32 arg2, u32 arg3);
 
 #endif /* __ASSEMBLY__ */
 
+/* op type for SMC_CMD_SAVE and SMC_CMD_SHUTDOWN */
+#define OP_TYPE_CORE		0x0
+#define OP_TYPE_CLUSTER		0x1
+
+/* Power State required for SMC_CMD_SAVE and SMC_CMD_SHUTDOWN */
+#define SMC_POWERSTATE_IDLE	0x1
+
 #endif
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 2146d918aedd..3e6aea7f83af 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -65,8 +65,6 @@ static struct sleep_save exynos_core_save[] = {
 
 struct exynos_pm_data {
 	const struct exynos_wkup_irq *wkup_irq;
-	struct sleep_save *extra_save;
-	int num_extra_save;
 	unsigned int wake_disable_mask;
 	unsigned int *release_ret_regs;
 
@@ -77,7 +75,7 @@ struct exynos_pm_data {
 	int (*cpu_suspend)(unsigned long);
 };
 
-struct exynos_pm_data *pm_data;
+static const struct exynos_pm_data *pm_data;
 
 static int exynos5420_cpu_state;
 static unsigned int exynos_pmu_spare3;
@@ -106,7 +104,7 @@ static const struct exynos_wkup_irq exynos5250_wkup_irq[] = {
 	{ /* sentinel */ },
 };
 
-unsigned int exynos_release_ret_regs[] = {
+static unsigned int exynos_release_ret_regs[] = {
 	S5P_PAD_RET_MAUDIO_OPTION,
 	S5P_PAD_RET_GPIO_OPTION,
 	S5P_PAD_RET_UART_OPTION,
@@ -117,7 +115,7 @@ unsigned int exynos_release_ret_regs[] = {
 	REG_TABLE_END,
 };
 
-unsigned int exynos3250_release_ret_regs[] = {
+static unsigned int exynos3250_release_ret_regs[] = {
 	S5P_PAD_RET_MAUDIO_OPTION,
 	S5P_PAD_RET_GPIO_OPTION,
 	S5P_PAD_RET_UART_OPTION,
@@ -130,7 +128,7 @@ unsigned int exynos3250_release_ret_regs[] = {
 	REG_TABLE_END,
 };
 
-unsigned int exynos5420_release_ret_regs[] = {
+static unsigned int exynos5420_release_ret_regs[] = {
 	EXYNOS_PAD_RET_DRAM_OPTION,
 	EXYNOS_PAD_RET_MAUDIO_OPTION,
 	EXYNOS_PAD_RET_JTAG_OPTION,
@@ -349,10 +347,6 @@ static void exynos_pm_prepare(void)
 
 	s3c_pm_do_save(exynos_core_save, ARRAY_SIZE(exynos_core_save));
 
-	 if (pm_data->extra_save)
-		s3c_pm_do_save(pm_data->extra_save,
-				pm_data->num_extra_save);
-
 	exynos_pm_enter_sleep_mode();
 
 	/* ensure at least INFORM0 has the resume address */
@@ -475,10 +469,6 @@ static void exynos_pm_resume(void)
 	/* For release retention */
 	exynos_pm_release_retention();
 
-	if (pm_data->extra_save)
-		s3c_pm_do_restore_core(pm_data->extra_save,
-					pm_data->num_extra_save);
-
 	s3c_pm_do_restore_core(exynos_core_save, ARRAY_SIZE(exynos_core_save));
 
 	if (cpuid == ARM_CPU_PART_CORTEX_A9)
@@ -685,7 +675,7 @@ static const struct exynos_pm_data exynos5250_pm_data = {
 	.cpu_suspend	= exynos_cpu_suspend,
 };
 
-static struct exynos_pm_data exynos5420_pm_data = {
+static const struct exynos_pm_data exynos5420_pm_data = {
 	.wkup_irq	= exynos5250_wkup_irq,
 	.wake_disable_mask = (0x7F << 7) | (0x1F << 1),
 	.release_ret_regs = exynos5420_release_ret_regs,
@@ -736,7 +726,7 @@ void __init exynos_pm_init(void)
 	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL)))
 		pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
 
-	pm_data = (struct exynos_pm_data *) match->data;
+	pm_data = (const struct exynos_pm_data *) match->data;
 
 	/* All wakeup disable */
 	tmp = pmu_raw_readl(S5P_WAKEUP_MASK);
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 0748747b2bc6..3a3d3e9d7bfd 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -21,6 +21,7 @@ config MXC_AVIC
 
 config MXC_DEBUG_BOARD
 	bool "Enable MXC debug board(for 3-stack)"
+	depends on MACH_MX27_3DS || MACH_MX31_3DS || MACH_MX35_3DS
 	help
 	  The debug board is an integral part of the MXC 3-stack(PDK)
 	  platforms, it can be attached or removed from the peripheral
@@ -50,6 +51,7 @@ config HAVE_IMX_ANATOP
 
 config HAVE_IMX_GPC
 	bool
+	select PM_GENERIC_DOMAINS if PM
 
 config HAVE_IMX_MMDC
 	bool
@@ -586,6 +588,7 @@ config SOC_VF610
 	select ARM_GIC
 	select PINCTRL_VF610
 	select PL310_ERRATA_769419 if CACHE_L2X0
+	select SMP_ON_UP if SMP
 
 	help
 	  This enables support for Freescale Vybrid VF610 processor.
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index d04a430607b8..469a150bf98f 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -119,6 +119,7 @@ static unsigned int share_count_asrc;
 static unsigned int share_count_ssi1;
 static unsigned int share_count_ssi2;
 static unsigned int share_count_ssi3;
+static unsigned int share_count_mipi_core_cfg;
 
 static void __init imx6q_clocks_init(struct device_node *ccm_node)
 {
@@ -246,6 +247,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_PLL3_60M]  = imx_clk_fixed_factor("pll3_60m",  "pll3_usb_otg",   1, 8);
 	clk[IMX6QDL_CLK_TWD]       = imx_clk_fixed_factor("twd",       "arm",            1, 2);
 	clk[IMX6QDL_CLK_GPT_3M]    = imx_clk_fixed_factor("gpt_3m",    "osc",            1, 8);
+	clk[IMX6QDL_CLK_VIDEO_27M] = imx_clk_fixed_factor("video_27m", "pll3_pfd1_540m", 1, 20);
 	if (cpu_is_imx6dl()) {
 		clk[IMX6QDL_CLK_GPU2D_AXI] = imx_clk_fixed_factor("gpu2d_axi", "mmdc_ch0_axi_podf", 1, 1);
 		clk[IMX6QDL_CLK_GPU3D_AXI] = imx_clk_fixed_factor("gpu3d_axi", "mmdc_ch0_axi_podf", 1, 1);
@@ -400,7 +402,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		clk[IMX6QDL_CLK_GPU2D_CORE] = imx_clk_gate2("gpu2d_core", "gpu2d_core_podf", base + 0x6c, 24);
 	clk[IMX6QDL_CLK_GPU3D_CORE]   = imx_clk_gate2("gpu3d_core",    "gpu3d_core_podf",   base + 0x6c, 26);
 	clk[IMX6QDL_CLK_HDMI_IAHB]    = imx_clk_gate2("hdmi_iahb",     "ahb",               base + 0x70, 0);
-	clk[IMX6QDL_CLK_HDMI_ISFR]    = imx_clk_gate2("hdmi_isfr",     "pll3_pfd1_540m",    base + 0x70, 4);
+	clk[IMX6QDL_CLK_HDMI_ISFR]    = imx_clk_gate2("hdmi_isfr",     "video_27m",         base + 0x70, 4);
 	clk[IMX6QDL_CLK_I2C1]         = imx_clk_gate2("i2c1",          "ipg_per",           base + 0x70, 6);
 	clk[IMX6QDL_CLK_I2C2]         = imx_clk_gate2("i2c2",          "ipg_per",           base + 0x70, 8);
 	clk[IMX6QDL_CLK_I2C3]         = imx_clk_gate2("i2c3",          "ipg_per",           base + 0x70, 10);
@@ -415,7 +417,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_LDB_DI0]      = imx_clk_gate2("ldb_di0",       "ldb_di0_podf",      base + 0x74, 12);
 	clk[IMX6QDL_CLK_LDB_DI1]      = imx_clk_gate2("ldb_di1",       "ldb_di1_podf",      base + 0x74, 14);
 	clk[IMX6QDL_CLK_IPU2_DI1]     = imx_clk_gate2("ipu2_di1",      "ipu2_di1_sel",      base + 0x74, 10);
-	clk[IMX6QDL_CLK_HSI_TX]       = imx_clk_gate2("hsi_tx",        "hsi_tx_podf",       base + 0x74, 16);
+	clk[IMX6QDL_CLK_HSI_TX]       = imx_clk_gate2_shared("hsi_tx", "hsi_tx_podf",       base + 0x74, 16, &share_count_mipi_core_cfg);
+	clk[IMX6QDL_CLK_MIPI_CORE_CFG] = imx_clk_gate2_shared("mipi_core_cfg", "video_27m", base + 0x74, 16, &share_count_mipi_core_cfg);
+	clk[IMX6QDL_CLK_MIPI_IPG]     = imx_clk_gate2_shared("mipi_ipg", "ipg",             base + 0x74, 16, &share_count_mipi_core_cfg);
 	if (cpu_is_imx6dl())
 		/*
 		 * The multiplexer and divider of the imx6q clock gpu2d get
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 745caa18ab2c..029f59ce2712 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -10,15 +10,25 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
+#include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/regulator/consumer.h>
 #include <linux/irqchip/arm-gic.h>
 #include "common.h"
+#include "hardware.h"
 
+#define GPC_CNTR		0x000
 #define GPC_IMR1		0x008
+#define GPC_PGC_GPU_PDN		0x260
+#define GPC_PGC_GPU_PUPSCR	0x264
+#define GPC_PGC_GPU_PDNSCR	0x268
 #define GPC_PGC_CPU_PDN		0x2a0
 #define GPC_PGC_CPU_PUPSCR	0x2a4
 #define GPC_PGC_CPU_PDNSCR	0x2a8
@@ -27,6 +37,18 @@
 
 #define IMR_NUM			4
 
+#define GPU_VPU_PUP_REQ		BIT(1)
+#define GPU_VPU_PDN_REQ		BIT(0)
+
+#define GPC_CLK_MAX		6
+
+struct pu_domain {
+	struct generic_pm_domain base;
+	struct regulator *reg;
+	struct clk *clk[GPC_CLK_MAX];
+	int num_clks;
+};
+
 static void __iomem *gpc_base;
 static u32 gpc_wake_irqs[IMR_NUM];
 static u32 gpc_saved_imrs[IMR_NUM];
@@ -170,3 +192,194 @@ void __init imx_gpc_init(void)
 	gic_arch_extn.irq_unmask = imx_gpc_irq_unmask;
 	gic_arch_extn.irq_set_wake = imx_gpc_irq_set_wake;
 }
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS
+
+static void _imx6q_pm_pu_power_off(struct generic_pm_domain *genpd)
+{
+	int iso, iso2sw;
+	u32 val;
+
+	/* Read ISO and ISO2SW power down delays */
+	val = readl_relaxed(gpc_base + GPC_PGC_GPU_PDNSCR);
+	iso = val & 0x3f;
+	iso2sw = (val >> 8) & 0x3f;
+
+	/* Gate off PU domain when GPU/VPU when powered down */
+	writel_relaxed(0x1, gpc_base + GPC_PGC_GPU_PDN);
+
+	/* Request GPC to power down GPU/VPU */
+	val = readl_relaxed(gpc_base + GPC_CNTR);
+	val |= GPU_VPU_PDN_REQ;
+	writel_relaxed(val, gpc_base + GPC_CNTR);
+
+	/* Wait ISO + ISO2SW IPG clock cycles */
+	ndelay((iso + iso2sw) * 1000 / 66);
+}
+
+static int imx6q_pm_pu_power_off(struct generic_pm_domain *genpd)
+{
+	struct pu_domain *pu = container_of(genpd, struct pu_domain, base);
+
+	_imx6q_pm_pu_power_off(genpd);
+
+	if (pu->reg)
+		regulator_disable(pu->reg);
+
+	return 0;
+}
+
+static int imx6q_pm_pu_power_on(struct generic_pm_domain *genpd)
+{
+	struct pu_domain *pu = container_of(genpd, struct pu_domain, base);
+	int i, ret, sw, sw2iso;
+	u32 val;
+
+	if (pu->reg)
+		ret = regulator_enable(pu->reg);
+	if (pu->reg && ret) {
+		pr_err("%s: failed to enable regulator: %d\n", __func__, ret);
+		return ret;
+	}
+
+	/* Enable reset clocks for all devices in the PU domain */
+	for (i = 0; i < pu->num_clks; i++)
+		clk_prepare_enable(pu->clk[i]);
+
+	/* Gate off PU domain when GPU/VPU when powered down */
+	writel_relaxed(0x1, gpc_base + GPC_PGC_GPU_PDN);
+
+	/* Read ISO and ISO2SW power down delays */
+	val = readl_relaxed(gpc_base + GPC_PGC_GPU_PUPSCR);
+	sw = val & 0x3f;
+	sw2iso = (val >> 8) & 0x3f;
+
+	/* Request GPC to power up GPU/VPU */
+	val = readl_relaxed(gpc_base + GPC_CNTR);
+	val |= GPU_VPU_PUP_REQ;
+	writel_relaxed(val, gpc_base + GPC_CNTR);
+
+	/* Wait ISO + ISO2SW IPG clock cycles */
+	ndelay((sw + sw2iso) * 1000 / 66);
+
+	/* Disable reset clocks for all devices in the PU domain */
+	for (i = 0; i < pu->num_clks; i++)
+		clk_disable_unprepare(pu->clk[i]);
+
+	return 0;
+}
+
+static struct generic_pm_domain imx6q_arm_domain = {
+	.name = "ARM",
+};
+
+static struct pu_domain imx6q_pu_domain = {
+	.base = {
+		.name = "PU",
+		.power_off = imx6q_pm_pu_power_off,
+		.power_on = imx6q_pm_pu_power_on,
+		.power_off_latency_ns = 25000,
+		.power_on_latency_ns = 2000000,
+	},
+};
+
+static struct generic_pm_domain imx6sl_display_domain = {
+	.name = "DISPLAY",
+};
+
+static struct generic_pm_domain *imx_gpc_domains[] = {
+	&imx6q_arm_domain,
+	&imx6q_pu_domain.base,
+	&imx6sl_display_domain,
+};
+
+static struct genpd_onecell_data imx_gpc_onecell_data = {
+	.domains = imx_gpc_domains,
+	.num_domains = ARRAY_SIZE(imx_gpc_domains),
+};
+
+static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
+{
+	struct clk *clk;
+	bool is_off;
+	int i;
+
+	imx6q_pu_domain.reg = pu_reg;
+
+	for (i = 0; ; i++) {
+		clk = of_clk_get(dev->of_node, i);
+		if (IS_ERR(clk))
+			break;
+		if (i >= GPC_CLK_MAX) {
+			dev_err(dev, "more than %d clocks\n", GPC_CLK_MAX);
+			goto clk_err;
+		}
+		imx6q_pu_domain.clk[i] = clk;
+	}
+	imx6q_pu_domain.num_clks = i;
+
+	is_off = IS_ENABLED(CONFIG_PM);
+	if (is_off) {
+		_imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
+	} else {
+		/*
+		 * Enable power if compiled without CONFIG_PM in case the
+		 * bootloader disabled it.
+		 */
+		imx6q_pm_pu_power_on(&imx6q_pu_domain.base);
+	}
+
+	pm_genpd_init(&imx6q_pu_domain.base, NULL, is_off);
+	return of_genpd_add_provider_onecell(dev->of_node,
+					     &imx_gpc_onecell_data);
+
+clk_err:
+	while (i--)
+		clk_put(imx6q_pu_domain.clk[i]);
+	return -EINVAL;
+}
+
+#else
+static inline int imx_gpc_genpd_init(struct device *dev, struct regulator *reg)
+{
+	return 0;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS */
+
+static int imx_gpc_probe(struct platform_device *pdev)
+{
+	struct regulator *pu_reg;
+	int ret;
+
+	pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
+	if (PTR_ERR(pu_reg) == -ENODEV)
+		pu_reg = NULL;
+	if (IS_ERR(pu_reg)) {
+		ret = PTR_ERR(pu_reg);
+		dev_err(&pdev->dev, "failed to get pu regulator: %d\n", ret);
+		return ret;
+	}
+
+	return imx_gpc_genpd_init(&pdev->dev, pu_reg);
+}
+
+static const struct of_device_id imx_gpc_dt_ids[] = {
+	{ .compatible = "fsl,imx6q-gpc" },
+	{ .compatible = "fsl,imx6sl-gpc" },
+	{ }
+};
+
+static struct platform_driver imx_gpc_driver = {
+	.driver = {
+		.name = "imx-gpc",
+		.owner = THIS_MODULE,
+		.of_match_table = imx_gpc_dt_ids,
+	},
+	.probe = imx_gpc_probe,
+};
+
+static int __init imx_pgc_init(void)
+{
+	return platform_driver_register(&imx_gpc_driver);
+}
+subsys_initcall(imx_pgc_init);
diff --git a/arch/arm/mach-meson/Kconfig b/arch/arm/mach-meson/Kconfig
index 18301dc9d2e7..0743e2059645 100644
--- a/arch/arm/mach-meson/Kconfig
+++ b/arch/arm/mach-meson/Kconfig
@@ -1,8 +1,11 @@
 menuconfig ARCH_MESON
 	bool "Amlogic Meson SoCs" if ARCH_MULTI_V7
+	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select ARM_GIC
 	select CACHE_L2X0
+	select PINCTRL
+	select PINCTRL_MESON
 
 if ARCH_MESON
 
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index c1e4567a5ab3..97473168d6b6 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -64,6 +64,20 @@ config MACH_ARMADA_38X
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 380/385 SoC with device tree.
 
+config MACH_ARMADA_39X
+	bool "Marvell Armada 39x boards" if ARCH_MULTI_V7
+	select ARM_GIC
+	select ARMADA_39X_CLK
+	select CACHE_L2X0
+	select HAVE_ARM_SCU
+	select HAVE_ARM_TWD if SMP
+	select HAVE_SMP
+	select MACH_MVEBU_V7
+	select PINCTRL_ARMADA_39X
+	help
+	  Say 'Y' here if you want your kernel to support boards based
+	  on the Marvell Armada 39x SoC with device tree.
+
 config MACH_ARMADA_XP
 	bool "Marvell Armada XP boards" if ARCH_MULTI_V7
 	select ARMADA_XP_CLK
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index 31b66f26e029..afee9083ad92 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -232,3 +232,17 @@ DT_MACHINE_START(ARMADA_38X_DT, "Marvell Armada 380/385 (Device Tree)")
 	.restart	= mvebu_restart,
 	.dt_compat	= armada_38x_dt_compat,
 MACHINE_END
+
+static const char * const armada_39x_dt_compat[] __initconst = {
+	"marvell,armada390",
+	"marvell,armada398",
+	NULL,
+};
+
+DT_MACHINE_START(ARMADA_39X_DT, "Marvell Armada 39x (Device Tree)")
+	.l2c_aux_val	= 0,
+	.l2c_aux_mask	= ~0,
+	.init_irq       = mvebu_init_irq,
+	.restart	= mvebu_restart,
+	.dt_compat	= armada_39x_dt_compat,
+MACHINE_END
diff --git a/arch/arm/mach-mvebu/platsmp-a9.c b/arch/arm/mach-mvebu/platsmp-a9.c
index 2ec1a42b4321..df0a9cc5da59 100644
--- a/arch/arm/mach-mvebu/platsmp-a9.c
+++ b/arch/arm/mach-mvebu/platsmp-a9.c
@@ -110,3 +110,5 @@ CPU_METHOD_OF_DECLARE(mvebu_armada_375_smp, "marvell,armada-375-smp",
 		      &mvebu_cortex_a9_smp_ops);
 CPU_METHOD_OF_DECLARE(mvebu_armada_380_smp, "marvell,armada-380-smp",
 		      &armada_38x_smp_ops);
+CPU_METHOD_OF_DECLARE(mvebu_armada_390_smp, "marvell,armada-390-smp",
+		      &armada_38x_smp_ops);
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index be9541e18650..166b18f515a2 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -690,6 +690,9 @@ struct dev_pm_domain omap_device_pm_domain = {
 		USE_PLATFORM_PM_SLEEP_OPS
 		.suspend_noirq = _od_suspend_noirq,
 		.resume_noirq = _od_resume_noirq,
+		.freeze_noirq = _od_suspend_noirq,
+		.thaw_noirq = _od_resume_noirq,
+		.restore_noirq = _od_resume_noirq,
 	}
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
index 8eb85925e444..e2223148ba4d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
@@ -20,6 +20,7 @@
 #include "omap_hwmod_33xx_43xx_common_data.h"
 #include "prcm43xx.h"
 #include "omap_hwmod_common_data.h"
+#include "hdq1w.h"
 
 
 /* IP blocks */
@@ -516,6 +517,33 @@ static struct omap_hwmod am43xx_dss_rfbi_hwmod = {
 	.parent_hwmod	= &am43xx_dss_core_hwmod,
 };
 
+/* HDQ1W */
+static struct omap_hwmod_class_sysconfig am43xx_hdq1w_sysc = {
+	.rev_offs       = 0x0000,
+	.sysc_offs      = 0x0014,
+	.syss_offs      = 0x0018,
+	.sysc_flags     = (SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE),
+	.sysc_fields    = &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class am43xx_hdq1w_hwmod_class = {
+	.name   = "hdq1w",
+	.sysc   = &am43xx_hdq1w_sysc,
+	.reset	= &omap_hdq1w_reset,
+};
+
+static struct omap_hwmod am43xx_hdq1w_hwmod = {
+	.name           = "hdq1w",
+	.class          = &am43xx_hdq1w_hwmod_class,
+	.clkdm_name     = "l4ls_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = AM43XX_CM_PER_HDQ1W_CLKCTRL_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
 /* Interfaces */
 static struct omap_hwmod_ocp_if am43xx_l3_main__l4_hs = {
 	.master		= &am33xx_l3_main_hwmod,
@@ -790,6 +818,13 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__dss_rfbi = {
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+static struct omap_hwmod_ocp_if am43xx_l4_ls__hdq1w = {
+	.master         = &am33xx_l4_ls_hwmod,
+	.slave          = &am43xx_hdq1w_hwmod,
+	.clk            = "l4ls_gclk",
+	.user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am33xx_l4_wkup__synctimer,
 	&am43xx_l4_ls__timer8,
@@ -889,6 +924,7 @@ static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am43xx_l4_ls__dss,
 	&am43xx_l4_ls__dss_dispc,
 	&am43xx_l4_ls__dss_rfbi,
+	&am43xx_l4_ls__hdq1w,
 	NULL,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 16fe7a1b7a35..0e64c2fac0b5 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1726,21 +1726,6 @@ static struct omap_hwmod_class dra7xx_timer_1ms_hwmod_class = {
 	.sysc	= &dra7xx_timer_1ms_sysc,
 };
 
-static struct omap_hwmod_class_sysconfig dra7xx_timer_secure_sysc = {
-	.rev_offs	= 0x0000,
-	.sysc_offs	= 0x0010,
-	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_RESET_STATUS |
-			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
-	.sysc_fields	= &omap_hwmod_sysc_type2,
-};
-
-static struct omap_hwmod_class dra7xx_timer_secure_hwmod_class = {
-	.name	= "timer",
-	.sysc	= &dra7xx_timer_secure_sysc,
-};
-
 static struct omap_hwmod_class_sysconfig dra7xx_timer_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
@@ -1804,7 +1789,7 @@ static struct omap_hwmod dra7xx_timer3_hwmod = {
 /* timer4 */
 static struct omap_hwmod dra7xx_timer4_hwmod = {
 	.name		= "timer4",
-	.class		= &dra7xx_timer_secure_hwmod_class,
+	.class		= &dra7xx_timer_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
 	.main_clk	= "timer4_gfclk_mux",
 	.prcm = {
@@ -1921,6 +1906,66 @@ static struct omap_hwmod dra7xx_timer11_hwmod = {
 	},
 };
 
+/* timer13 */
+static struct omap_hwmod dra7xx_timer13_hwmod = {
+	.name		= "timer13",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per3_clkdm",
+	.main_clk	= "timer13_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER3_TIMER13_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER3_TIMER13_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer14 */
+static struct omap_hwmod dra7xx_timer14_hwmod = {
+	.name		= "timer14",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per3_clkdm",
+	.main_clk	= "timer14_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER3_TIMER14_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER3_TIMER14_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer15 */
+static struct omap_hwmod dra7xx_timer15_hwmod = {
+	.name		= "timer15",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per3_clkdm",
+	.main_clk	= "timer15_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER3_TIMER15_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER3_TIMER15_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer16 */
+static struct omap_hwmod dra7xx_timer16_hwmod = {
+	.name		= "timer16",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per3_clkdm",
+	.main_clk	= "timer16_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER3_TIMER16_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER3_TIMER16_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
 /*
  * 'uart' class
  *
@@ -3059,6 +3104,38 @@ static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer11 = {
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l4_per3 -> timer13 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer13 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer13_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer14 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer14 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer14_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer15 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer15 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer15_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer16 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer16 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer16_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 /* l4_per1 -> uart1 */
 static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart1 = {
 	.master		= &dra7xx_l4_per1_hwmod,
@@ -3295,6 +3372,10 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per1__timer9,
 	&dra7xx_l4_per1__timer10,
 	&dra7xx_l4_per1__timer11,
+	&dra7xx_l4_per3__timer13,
+	&dra7xx_l4_per3__timer14,
+	&dra7xx_l4_per3__timer15,
+	&dra7xx_l4_per3__timer16,
 	&dra7xx_l4_per1__uart1,
 	&dra7xx_l4_per1__uart2,
 	&dra7xx_l4_per1__uart3,
diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h
index ad7b3e9977f8..48df3b55057e 100644
--- a/arch/arm/mach-omap2/prcm43xx.h
+++ b/arch/arm/mach-omap2/prcm43xx.h
@@ -143,5 +143,6 @@
 #define AM43XX_CM_PER_USB_OTG_SS1_CLKCTRL_OFFSET        0x0268
 #define AM43XX_CM_PER_USBPHYOCP2SCP1_CLKCTRL_OFFSET	0x05C0
 #define AM43XX_CM_PER_DSS_CLKCTRL_OFFSET		0x0a20
+#define AM43XX_CM_PER_HDQ1W_CLKCTRL_OFFSET		0x04a0
 
 #endif
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index f26fcdca2445..5b4ca3c3c879 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -55,7 +55,7 @@ static int pmu_power_domain_is_on(int pd)
 	return !(val & BIT(pd));
 }
 
-struct reset_control *rockchip_get_core_reset(int cpu)
+static struct reset_control *rockchip_get_core_reset(int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
 	struct device_node *np;
@@ -201,7 +201,7 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node)
 	return 0;
 }
 
-static struct regmap_config rockchip_pmu_regmap_config = {
+static const struct regmap_config rockchip_pmu_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c
index 50cb781aaa36..b07d88602073 100644
--- a/arch/arm/mach-rockchip/pm.c
+++ b/arch/arm/mach-rockchip/pm.c
@@ -75,9 +75,13 @@ static void rk3288_slp_mode_set(int level)
 	regmap_read(pmu_regmap, RK3288_PMU_PWRMODE_CON,
 		    &rk3288_pmu_pwr_mode_con);
 
-	/* set bit 8 so that system will resume to FAST_BOOT_ADDR */
+	/*
+	 * SGRF_FAST_BOOT_EN - system to boot from FAST_BOOT_ADDR
+	 * PCLK_WDT_GATE - disable WDT during suspend.
+	 */
 	regmap_write(sgrf_regmap, RK3288_SGRF_SOC_CON0,
-		     SGRF_FAST_BOOT_EN | SGRF_FAST_BOOT_EN_WRITE);
+		     SGRF_PCLK_WDT_GATE | SGRF_FAST_BOOT_EN
+		     | SGRF_PCLK_WDT_GATE_WRITE | SGRF_FAST_BOOT_EN_WRITE);
 
 	/* booting address of resuming system is from this register value */
 	regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR,
@@ -122,7 +126,8 @@ static void rk3288_slp_mode_set_resume(void)
 		     rk3288_pmu_pwr_mode_con);
 
 	regmap_write(sgrf_regmap, RK3288_SGRF_SOC_CON0,
-		     rk3288_sgrf_soc_con0 | SGRF_FAST_BOOT_EN_WRITE);
+		     rk3288_sgrf_soc_con0 | SGRF_PCLK_WDT_GATE_WRITE
+		     | SGRF_FAST_BOOT_EN_WRITE);
 }
 
 static int rockchip_lpmode_enter(unsigned long arg)
@@ -209,6 +214,9 @@ static int rk3288_suspend_init(struct device_node *np)
 	memcpy(rk3288_bootram_base, rockchip_slp_cpu_resume,
 	       rk3288_bootram_sz);
 
+	regmap_write(pmu_regmap, RK3288_PMU_OSC_CNT, OSC_STABL_CNT_THRESH);
+	regmap_write(pmu_regmap, RK3288_PMU_STABL_CNT, PMU_STABL_CNT_THRESH);
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-rockchip/pm.h b/arch/arm/mach-rockchip/pm.h
index 7c889c04604b..03ff31d8282d 100644
--- a/arch/arm/mach-rockchip/pm.h
+++ b/arch/arm/mach-rockchip/pm.h
@@ -50,6 +50,8 @@ static inline void rockchip_suspend_init(void)
 
 #define RK3288_SGRF_SOC_CON0		(0x0000)
 #define RK3288_SGRF_FAST_BOOT_ADDR	(0x0120)
+#define SGRF_PCLK_WDT_GATE		BIT(6)
+#define SGRF_PCLK_WDT_GATE_WRITE	BIT(22)
 #define SGRF_FAST_BOOT_EN		BIT(8)
 #define SGRF_FAST_BOOT_EN_WRITE		BIT(24)
 
@@ -63,6 +65,10 @@ static inline void rockchip_suspend_init(void)
 /* PMU_WAKEUP_CFG1 bits */
 #define PMU_ARMINT_WAKEUP_EN		BIT(0)
 
+/* wait 30ms for OSC stable and 30ms for pmic stable */
+#define OSC_STABL_CNT_THRESH	(32 * 30)
+#define PMU_STABL_CNT_THRESH	(32 * 30)
+
 enum rk3288_pwr_mode_con {
 	PMU_PWR_MODE_EN = 0,
 	PMU_CLK_CORE_SRC_GATE_EN,
diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h
index 7bc66682687e..dcbe17f5e5f8 100644
--- a/arch/arm/mach-s3c64xx/crag6410.h
+++ b/arch/arm/mach-s3c64xx/crag6410.h
@@ -14,6 +14,7 @@
 #include <mach/gpio-samsung.h>
 
 #define GLENFARCLAS_PMIC_IRQ_BASE	IRQ_BOARD_START
+#define BANFF_PMIC_IRQ_BASE		(IRQ_BOARD_START + 64)
 
 #define PCA935X_GPIO_BASE		GPIO_BOARD_START
 #define CODEC_GPIO_BASE			(GPIO_BOARD_START + 8)
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index 10b913baab28..65c426bc45f7 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -554,6 +554,7 @@ static struct wm831x_touch_pdata touch_pdata = {
 
 static struct wm831x_pdata crag_pmic_pdata = {
 	.wm831x_num = 1,
+	.irq_base = BANFF_PMIC_IRQ_BASE,
 	.gpio_base = BANFF_PMIC_GPIO_BASE,
 	.soft_shutdown = true,
 
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 2f36c85eec4b..347b6a58fc3e 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -69,10 +69,12 @@ config ARCH_R8A7779
 config ARCH_R8A7790
 	bool "R-Car H2 (R8A77900)"
 	select ARCH_RCAR_GEN2
+	select I2C
 
 config ARCH_R8A7791
 	bool "R-Car M2-W (R8A77910)"
 	select ARCH_RCAR_GEN2
+	select I2C
 
 config ARCH_R8A7794
 	bool "R-Car E2 (R8A77940)"
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index 03794b0de64b..3631d8b6fc5e 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -35,6 +35,8 @@ cpu-y				:= platsmp.o headsmp.o
 # Shared SoC family objects
 obj-$(CONFIG_ARCH_RCAR_GEN2)	+= setup-rcar-gen2.o platsmp-apmu.o $(cpu-y)
 CFLAGS_setup-rcar-gen2.o	+= -march=armv7-a
+obj-$(CONFIG_ARCH_R8A7790)	+= regulator-quirk-rcar-gen2.o
+obj-$(CONFIG_ARCH_R8A7791)	+= regulator-quirk-rcar-gen2.o
 
 # SMP objects
 smp-y				:= $(cpu-y)
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
new file mode 100644
index 000000000000..384e6e934b87
--- /dev/null
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -0,0 +1,147 @@
+/*
+ * R-Car Generation 2 da9063/da9210 regulator quirk
+ *
+ * The r8a7790/lager and r8a7791/koelsch development boards have da9063 and
+ * da9210 regulators.  Both regulators have their interrupt request lines tied
+ * to the same interrupt pin (IRQ2) on the SoC.
+ *
+ * After cold boot or da9063-induced restart, both the da9063 and da9210 seem
+ * to assert their interrupt request lines.  Hence as soon as one driver
+ * requests this irq, it gets stuck in an interrupt storm, as it only manages
+ * to deassert its own interrupt request line, and the other driver hasn't
+ * installed an interrupt handler yet.
+ *
+ * To handle this, install a quirk that masks the interrupts in both the
+ * da9063 and da9210.  This quirk has to run after the i2c master driver has
+ * been initialized, but before the i2c slave drivers are initialized.
+ *
+ * Copyright (C) 2015 Glider bvba
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/mfd/da9063/registers.h>
+
+
+#define IRQC_BASE		0xe61c0000
+#define IRQC_MONITOR		0x104	/* IRQn Signal Level Monitor Register */
+
+#define REGULATOR_IRQ_MASK	BIT(2)	/* IRQ2, active low */
+
+static void __iomem *irqc;
+
+static const u8 da9063_mask_regs[] = {
+	DA9063_REG_IRQ_MASK_A,
+	DA9063_REG_IRQ_MASK_B,
+	DA9063_REG_IRQ_MASK_C,
+	DA9063_REG_IRQ_MASK_D,
+};
+
+/* DA9210 System Control and Event Registers */
+#define DA9210_REG_MASK_A		0x54
+#define DA9210_REG_MASK_B		0x55
+
+static const u8 da9210_mask_regs[] = {
+	DA9210_REG_MASK_A,
+	DA9210_REG_MASK_B,
+};
+
+static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
+			     unsigned int nregs)
+{
+	unsigned int i;
+
+	dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+
+	for (i = 0; i < nregs; i++) {
+		int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
+		if (error) {
+			dev_err(&client->dev, "i2c error %d\n", error);
+			return;
+		}
+	}
+}
+
+static int regulator_quirk_notify(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct i2c_client *client;
+	u32 mon;
+
+	mon = ioread32(irqc + IRQC_MONITOR);
+	dev_dbg(dev, "%s: %ld, IRQC_MONITOR = 0x%x\n", __func__, action, mon);
+	if (mon & REGULATOR_IRQ_MASK)
+		goto remove;
+
+	if (action != BUS_NOTIFY_ADD_DEVICE || dev->type == &i2c_adapter_type)
+		return 0;
+
+	client = to_i2c_client(dev);
+	dev_dbg(dev, "Detected %s\n", client->name);
+
+	if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
+		da9xxx_mask_irqs(client, da9063_mask_regs,
+				 ARRAY_SIZE(da9063_mask_regs));
+	else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
+		da9xxx_mask_irqs(client, da9210_mask_regs,
+				 ARRAY_SIZE(da9210_mask_regs));
+
+	mon = ioread32(irqc + IRQC_MONITOR);
+	if (mon & REGULATOR_IRQ_MASK)
+		goto remove;
+
+	return 0;
+
+remove:
+	dev_info(dev, "IRQ2 is not asserted, removing quirk\n");
+
+	bus_unregister_notifier(&i2c_bus_type, nb);
+	iounmap(irqc);
+	return 0;
+}
+
+static struct notifier_block regulator_quirk_nb = {
+	.notifier_call = regulator_quirk_notify
+};
+
+static int __init rcar_gen2_regulator_quirk(void)
+{
+	u32 mon;
+
+	if (!of_machine_is_compatible("renesas,koelsch") &&
+	    !of_machine_is_compatible("renesas,lager"))
+		return -ENODEV;
+
+	irqc = ioremap(IRQC_BASE, PAGE_SIZE);
+	if (!irqc)
+		return -ENOMEM;
+
+	mon = ioread32(irqc + IRQC_MONITOR);
+	if (mon & REGULATOR_IRQ_MASK) {
+		pr_debug("%s: IRQ2 is not asserted, not installing quirk\n",
+			 __func__);
+		iounmap(irqc);
+		return 0;
+	}
+
+	pr_info("IRQ2 is asserted, installing da9063/da9210 regulator quirk\n");
+
+	bus_register_notifier(&i2c_bus_type, &regulator_quirk_nb);
+	return 0;
+}
+
+arch_initcall(rcar_gen2_regulator_quirk);
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index 51464cc6d65b..5d13595aa027 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -21,6 +21,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <asm/mach/arch.h>
@@ -195,7 +196,7 @@ void __init rcar_gen2_reserve(void)
 
 	of_scan_flat_dt(rcar_gen2_scan_mem, &mrc);
 #ifdef CONFIG_DMA_CMA
-	if (mrc.size)
+	if (mrc.size && memblock_is_region_memory(mrc.base, mrc.size))
 		dma_contiguous_reserve_area(mrc.size, mrc.base, 0,
 					    &rcar_gen2_dma_contiguous, true);
 #endif
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 30b993399ed7..5cedcf572104 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
-#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/of_address.h>
 #include <linux/vexpress.h>
@@ -36,163 +35,102 @@
 #define KFC_CFG_W	0x2c
 #define DCS_CFG_R	0x30
 
-/*
- * We can't use regular spinlocks. In the switcher case, it is possible
- * for an outbound CPU to call power_down() while its inbound counterpart
- * is already live using the same logical CPU number which trips lockdep
- * debugging.
- */
-static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-
 static void __iomem *dcscb_base;
-static int dcscb_use_count[4][2];
 static int dcscb_allcpus_mask[2];
 
-static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
+static int dcscb_cpu_powerup(unsigned int cpu, unsigned int cluster)
 {
 	unsigned int rst_hold, cpumask = (1 << cpu);
-	unsigned int all_mask;
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
-	if (cpu >= 4 || cluster >= 2)
+	if (cluster >= 2 || !(cpumask & dcscb_allcpus_mask[cluster]))
 		return -EINVAL;
 
-	all_mask = dcscb_allcpus_mask[cluster];
+	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+	rst_hold &= ~(cpumask | (cpumask << 4));
+	writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+	return 0;
+}
 
-	/*
-	 * 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(&dcscb_lock);
-
-	dcscb_use_count[cpu][cluster]++;
-	if (dcscb_use_count[cpu][cluster] == 1) {
-		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
-		if (rst_hold & (1 << 8)) {
-			/* remove cluster reset and add individual CPU's reset */
-			rst_hold &= ~(1 << 8);
-			rst_hold |= all_mask;
-		}
-		rst_hold &= ~(cpumask | (cpumask << 4));
-		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
-	} else if (dcscb_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();
-	}
+static int dcscb_cluster_powerup(unsigned int cluster)
+{
+	unsigned int rst_hold;
 
-	arch_spin_unlock(&dcscb_lock);
-	local_irq_enable();
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	if (cluster >= 2)
+		return -EINVAL;
 
+	/* remove cluster reset and add individual CPU's reset */
+	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+	rst_hold &= ~(1 << 8);
+	rst_hold |= dcscb_allcpus_mask[cluster];
+	writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
 	return 0;
 }
 
-static void dcscb_power_down(void)
+static void dcscb_cpu_powerdown_prepare(unsigned int cpu, unsigned int cluster)
 {
-	unsigned int mpidr, cpu, cluster, rst_hold, cpumask, all_mask;
-	bool last_man = false, skip_wfi = false;
-
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-	cpumask = (1 << cpu);
+	unsigned int rst_hold;
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
-	BUG_ON(cpu >= 4 || cluster >= 2);
-
-	all_mask = dcscb_allcpus_mask[cluster];
-
-	__mcpm_cpu_going_down(cpu, cluster);
-
-	arch_spin_lock(&dcscb_lock);
-	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
-	dcscb_use_count[cpu][cluster]--;
-	if (dcscb_use_count[cpu][cluster] == 0) {
-		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
-		rst_hold |= cpumask;
-		if (((rst_hold | (rst_hold >> 4)) & all_mask) == all_mask) {
-			rst_hold |= (1 << 8);
-			last_man = true;
-		}
-		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
-	} else if (dcscb_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();
-
-	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
-		arch_spin_unlock(&dcscb_lock);
-
-		/* Flush all cache levels for this cluster. */
-		v7_exit_coherency_flush(all);
-
-		/*
-		 * A full outer cache flush could be needed at this point
-		 * on platforms with such a cache, depending on where the
-		 * outer cache sits. In some cases the notion of a "last
-		 * cluster standing" would need to be implemented if the
-		 * outer cache is shared across clusters. In any case, when
-		 * the outer cache needs flushing, there is no concurrent
-		 * access to the cache controller to worry about and no
-		 * special locking besides what is already provided by the
-		 * MCPM state machinery is needed.
-		 */
-
-		/*
-		 * Disable cluster-level coherency by masking
-		 * incoming snoops and DVM messages:
-		 */
-		cci_disable_port_by_cpu(mpidr);
-
-		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
-	} else {
-		arch_spin_unlock(&dcscb_lock);
-
-		/* Disable and flush the local CPU cache. */
-		v7_exit_coherency_flush(louis);
-	}
+	BUG_ON(cluster >= 2 || !((1 << cpu) & dcscb_allcpus_mask[cluster]));
 
-	__mcpm_cpu_down(cpu, cluster);
+	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+	rst_hold |= (1 << cpu);
+	writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+}
 
-	/* Now we are prepared for power-down, do it: */
-	dsb();
-	if (!skip_wfi)
-		wfi();
+static void dcscb_cluster_powerdown_prepare(unsigned int cluster)
+{
+	unsigned int rst_hold;
 
-	/* Not dead at this point?  Let our caller cope. */
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	BUG_ON(cluster >= 2);
+
+	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+	rst_hold |= (1 << 8);
+	writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
 }
 
-static const struct mcpm_platform_ops dcscb_power_ops = {
-	.power_up	= dcscb_power_up,
-	.power_down	= dcscb_power_down,
-};
+static void dcscb_cpu_cache_disable(void)
+{
+	/* Disable and flush the local CPU cache. */
+	v7_exit_coherency_flush(louis);
+}
 
-static void __init dcscb_usage_count_init(void)
+static void dcscb_cluster_cache_disable(void)
 {
-	unsigned int mpidr, cpu, cluster;
+	/* Flush all cache levels for this cluster. */
+	v7_exit_coherency_flush(all);
 
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	/*
+	 * A full outer cache flush could be needed at this point
+	 * on platforms with such a cache, depending on where the
+	 * outer cache sits. In some cases the notion of a "last
+	 * cluster standing" would need to be implemented if the
+	 * outer cache is shared across clusters. In any case, when
+	 * the outer cache needs flushing, there is no concurrent
+	 * access to the cache controller to worry about and no
+	 * special locking besides what is already provided by the
+	 * MCPM state machinery is needed.
+	 */
 
-	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
-	BUG_ON(cpu >= 4 || cluster >= 2);
-	dcscb_use_count[cpu][cluster] = 1;
+	/*
+	 * Disable cluster-level coherency by masking
+	 * incoming snoops and DVM messages:
+	 */
+	cci_disable_port_by_cpu(read_cpuid_mpidr());
 }
 
+static const struct mcpm_platform_ops dcscb_power_ops = {
+	.cpu_powerup		= dcscb_cpu_powerup,
+	.cluster_powerup	= dcscb_cluster_powerup,
+	.cpu_powerdown_prepare	= dcscb_cpu_powerdown_prepare,
+	.cluster_powerdown_prepare = dcscb_cluster_powerdown_prepare,
+	.cpu_cache_disable	= dcscb_cpu_cache_disable,
+	.cluster_cache_disable	= dcscb_cluster_cache_disable,
+};
+
 extern void dcscb_power_up_setup(unsigned int affinity_level);
 
 static int __init dcscb_init(void)
@@ -213,7 +151,6 @@ static int __init dcscb_init(void)
 	cfg = readl_relaxed(dcscb_base + DCS_CFG_R);
 	dcscb_allcpus_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1;
 	dcscb_allcpus_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1;
-	dcscb_usage_count_init();
 
 	ret = mcpm_platform_register(&dcscb_power_ops);
 	if (!ret)
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index 2fb78b4648cb..b3328cd46c33 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -18,7 +18,6 @@
 #include <linux/kernel.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/irqchip/arm-gic.h>
 
@@ -44,101 +43,36 @@
 
 static void __iomem *scc;
 
-/*
- * 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;
-
 #define TC2_CLUSTERS			2
 #define TC2_MAX_CPUS_PER_CLUSTER	3
 
 static unsigned int tc2_nr_cpus[TC2_CLUSTERS];
 
-/* Keep per-cpu usage count to cope with unordered up/down requests */
-static int tc2_pm_use_count[TC2_MAX_CPUS_PER_CLUSTER][TC2_CLUSTERS];
-
-#define tc2_cluster_unused(cluster) \
-	(!tc2_pm_use_count[0][cluster] && \
-	 !tc2_pm_use_count[1][cluster] && \
-	 !tc2_pm_use_count[2][cluster])
-
-static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+static int tc2_pm_cpu_powerup(unsigned int cpu, unsigned int cluster)
 {
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_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_cluster_unused(cluster))
-		ve_spc_powerdown(cluster, false);
-
-	tc2_pm_use_count[cpu][cluster]++;
-	if (tc2_pm_use_count[cpu][cluster] == 1) {
-		ve_spc_set_resume_addr(cluster, cpu,
-				       virt_to_phys(mcpm_entry_point));
-		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
-	} 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();
-
+	ve_spc_set_resume_addr(cluster, cpu,
+			       virt_to_phys(mcpm_entry_point));
+	ve_spc_cpu_wakeup_irq(cluster, cpu, true);
 	return 0;
 }
 
-static void tc2_pm_down(u64 residency)
+static int tc2_pm_cluster_powerup(unsigned int cluster)
 {
-	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: cluster %u\n", __func__, cluster);
+	if (cluster >= TC2_CLUSTERS)
+		return -EINVAL;
+	ve_spc_powerdown(cluster, false);
+	return 0;
+}
 
+static void tc2_pm_cpu_powerdown_prepare(unsigned int cpu, unsigned int cluster)
+{
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_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) {
-		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
-		if (tc2_cluster_unused(cluster)) {
-			ve_spc_powerdown(cluster, true);
-			ve_spc_global_wakeup_irq(true);
-			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();
-
+	ve_spc_cpu_wakeup_irq(cluster, cpu, true);
 	/*
 	 * If the CPU is committed to power down, make sure
 	 * the power controller will be in charge of waking it
@@ -146,55 +80,38 @@ static void tc2_pm_down(u64 residency)
 	 * to the CPU by disabling the GIC CPU IF to prevent wfi
 	 * from completing execution behind power controller back
 	 */
-	if (!skip_wfi)
-		gic_cpu_if_down();
-
-	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
-		arch_spin_unlock(&tc2_pm_lock);
-
-		if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
-			/*
-			 * On the Cortex-A15 we need to disable
-			 * L2 prefetching before flushing the cache.
-			 */
-			asm volatile(
-			"mcr	p15, 1, %0, c15, c0, 3 \n\t"
-			"isb	\n\t"
-			"dsb	"
-			: : "r" (0x400) );
-		}
-
-		v7_exit_coherency_flush(all);
-
-		cci_disable_port_by_cpu(mpidr);
-
-		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
-	} else {
-		/*
-		 * If last man then undo any setup done previously.
-		 */
-		if (last_man) {
-			ve_spc_powerdown(cluster, false);
-			ve_spc_global_wakeup_irq(false);
-		}
-
-		arch_spin_unlock(&tc2_pm_lock);
-
-		v7_exit_coherency_flush(louis);
-	}
-
-	__mcpm_cpu_down(cpu, cluster);
+	gic_cpu_if_down();
+}
 
-	/* Now we are prepared for power-down, do it: */
-	if (!skip_wfi)
-		wfi();
+static void tc2_pm_cluster_powerdown_prepare(unsigned int cluster)
+{
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS);
+	ve_spc_powerdown(cluster, true);
+	ve_spc_global_wakeup_irq(true);
+}
 
-	/* Not dead at this point?  Let our caller cope. */
+static void tc2_pm_cpu_cache_disable(void)
+{
+	v7_exit_coherency_flush(louis);
 }
 
-static void tc2_pm_power_down(void)
+static void tc2_pm_cluster_cache_disable(void)
 {
-	tc2_pm_down(0);
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
+		/*
+		 * On the Cortex-A15 we need to disable
+		 * L2 prefetching before flushing the cache.
+		 */
+		asm volatile(
+		"mcr	p15, 1, %0, c15, c0, 3 \n\t"
+		"isb	\n\t"
+		"dsb	"
+		: : "r" (0x400) );
+	}
+
+	v7_exit_coherency_flush(all);
+	cci_disable_port_by_cpu(read_cpuid_mpidr());
 }
 
 static int tc2_core_in_reset(unsigned int cpu, unsigned int cluster)
@@ -217,27 +134,21 @@ static int tc2_pm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
 	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
 
 	for (tries = 0; tries < TIMEOUT_MSEC / POLL_MSEC; ++tries) {
+		pr_debug("%s(cpu=%u, cluster=%u): RESET_CTRL = 0x%08X\n",
+			 __func__, cpu, cluster,
+			 readl_relaxed(scc + RESET_CTRL));
+
 		/*
-		 * Only examine the hardware state if the target CPU has
-		 * caught up at least as far as tc2_pm_down():
+		 * We need the CPU to reach WFI, but the power
+		 * controller may put the cluster in reset and
+		 * power it off as soon as that happens, before
+		 * we have a chance to see STANDBYWFI.
+		 *
+		 * So we need to check for both conditions:
 		 */
-		if (ACCESS_ONCE(tc2_pm_use_count[cpu][cluster]) == 0) {
-			pr_debug("%s(cpu=%u, cluster=%u): RESET_CTRL = 0x%08X\n",
-				 __func__, cpu, cluster,
-				 readl_relaxed(scc + RESET_CTRL));
-
-			/*
-			 * We need the CPU to reach WFI, but the power
-			 * controller may put the cluster in reset and
-			 * power it off as soon as that happens, before
-			 * we have a chance to see STANDBYWFI.
-			 *
-			 * So we need to check for both conditions:
-			 */
-			if (tc2_core_in_reset(cpu, cluster) ||
-			    ve_spc_cpu_in_wfi(cpu, cluster))
-				return 0; /* success: the CPU is halted */
-		}
+		if (tc2_core_in_reset(cpu, cluster) ||
+		    ve_spc_cpu_in_wfi(cpu, cluster))
+			return 0; /* success: the CPU is halted */
 
 		/* Otherwise, wait and retry: */
 		msleep(POLL_MSEC);
@@ -246,72 +157,40 @@ static int tc2_pm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
 	return -ETIMEDOUT; /* timeout */
 }
 
-static void tc2_pm_suspend(u64 residency)
+static void tc2_pm_cpu_suspend_prepare(unsigned int cpu, unsigned int cluster)
 {
-	unsigned int mpidr, cpu, cluster;
-
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 	ve_spc_set_resume_addr(cluster, cpu, virt_to_phys(mcpm_entry_point));
-	tc2_pm_down(residency);
 }
 
-static void tc2_pm_powered_up(void)
+static void tc2_pm_cpu_is_up(unsigned int cpu, unsigned int cluster)
 {
-	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 >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
-
-	local_irq_save(flags);
-	arch_spin_lock(&tc2_pm_lock);
-
-	if (tc2_cluster_unused(cluster)) {
-		ve_spc_powerdown(cluster, false);
-		ve_spc_global_wakeup_irq(false);
-	}
-
-	if (!tc2_pm_use_count[cpu][cluster])
-		tc2_pm_use_count[cpu][cluster] = 1;
-
 	ve_spc_cpu_wakeup_irq(cluster, cpu, false);
 	ve_spc_set_resume_addr(cluster, cpu, 0);
+}
 
-	arch_spin_unlock(&tc2_pm_lock);
-	local_irq_restore(flags);
+static void tc2_pm_cluster_is_up(unsigned int cluster)
+{
+	pr_debug("%s: cluster %u\n", __func__, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS);
+	ve_spc_powerdown(cluster, false);
+	ve_spc_global_wakeup_irq(false);
 }
 
 static const struct mcpm_platform_ops tc2_pm_power_ops = {
-	.power_up		= tc2_pm_power_up,
-	.power_down		= tc2_pm_power_down,
+	.cpu_powerup		= tc2_pm_cpu_powerup,
+	.cluster_powerup	= tc2_pm_cluster_powerup,
+	.cpu_suspend_prepare	= tc2_pm_cpu_suspend_prepare,
+	.cpu_powerdown_prepare	= tc2_pm_cpu_powerdown_prepare,
+	.cluster_powerdown_prepare = tc2_pm_cluster_powerdown_prepare,
+	.cpu_cache_disable	= tc2_pm_cpu_cache_disable,
+	.cluster_cache_disable	= tc2_pm_cluster_cache_disable,
 	.wait_for_powerdown	= tc2_pm_wait_for_powerdown,
-	.suspend		= tc2_pm_suspend,
-	.powered_up		= tc2_pm_powered_up,
+	.cpu_is_up		= tc2_pm_cpu_is_up,
+	.cluster_is_up		= tc2_pm_cluster_is_up,
 };
 
-static bool __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);
-	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster]) {
-		pr_err("%s: boot CPU is out of bound!\n", __func__);
-		return false;
-	}
-	tc2_pm_use_count[cpu][cluster] = 1;
-	return true;
-}
-
 /*
  * Enable cluster-level coherency, in preparation for turning on the MMU.
  */
@@ -323,23 +202,9 @@ static void __naked tc2_pm_power_up_setup(unsigned int affinity_level)
 "	b	cci_enable_port_for_self ");
 }
 
-static void __init tc2_cache_off(void)
-{
-	pr_info("TC2: disabling cache during MCPM loopback test\n");
-	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
-		/* disable L2 prefetching on the Cortex-A15 */
-		asm volatile(
-		"mcr	p15, 1, %0, c15, c0, 3 \n\t"
-		"isb	\n\t"
-		"dsb	"
-		: : "r" (0x400) );
-	}
-	v7_exit_coherency_flush(all);
-	cci_disable_port_by_cpu(read_cpuid_mpidr());
-}
-
 static int __init tc2_pm_init(void)
 {
+	unsigned int mpidr, cpu, cluster;
 	int ret, irq;
 	u32 a15_cluster_id, a7_cluster_id, sys_info;
 	struct device_node *np;
@@ -379,14 +244,20 @@ static int __init tc2_pm_init(void)
 	if (!cci_probed())
 		return -ENODEV;
 
-	if (!tc2_pm_usage_count_init())
+	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);
+	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster]) {
+		pr_err("%s: boot CPU is out of bound!\n", __func__);
 		return -EINVAL;
+	}
 
 	ret = mcpm_platform_register(&tc2_pm_power_ops);
 	if (!ret) {
 		mcpm_sync_init(tc2_pm_power_up_setup);
 		/* test if we can (re)enable the CCI on our own */
-		BUG_ON(mcpm_loopback(tc2_cache_off) != 0);
+		BUG_ON(mcpm_loopback(tc2_pm_cluster_cache_disable) != 0);
 		pr_info("TC2 power management initialized\n");
 	}
 	return ret;