19 files changed, 433 insertions, 677 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5bbec7b8183..5f3338eacad 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -82,5 +82,6 @@ obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
+obj-$(CONFIG_ARM_PSCI)		+= psci.o
 
 extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index c8ef20747ee..d957a51435d 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -9,516 +9,53 @@
  * published by the Free Software Foundation.
  */
 #include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <linux/smp.h>
-#include <linux/cpu.h>
-#include <linux/jiffies.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/errno.h>
 
-#include <asm/cputype.h>
 #include <asm/delay.h>
-#include <asm/localtimer.h>
-#include <asm/arch_timer.h>
-#include <asm/system_info.h>
 #include <asm/sched_clock.h>
 
-static unsigned long arch_timer_rate;
+#include <clocksource/arm_arch_timer.h>
 
-enum ppi_nr {
-	PHYS_SECURE_PPI,
-	PHYS_NONSECURE_PPI,
-	VIRT_PPI,
-	HYP_PPI,
-	MAX_TIMER_PPI
-};
-
-static int arch_timer_ppi[MAX_TIMER_PPI];
-
-static struct clock_event_device __percpu **arch_timer_evt;
-static struct delay_timer arch_delay_timer;
-
-static bool arch_timer_use_virtual = true;
-
-/*
- * Architected system timer support.
- */
-
-#define ARCH_TIMER_CTRL_ENABLE		(1 << 0)
-#define ARCH_TIMER_CTRL_IT_MASK		(1 << 1)
-#define ARCH_TIMER_CTRL_IT_STAT		(1 << 2)
-
-#define ARCH_TIMER_REG_CTRL		0
-#define ARCH_TIMER_REG_FREQ		1
-#define ARCH_TIMER_REG_TVAL		2
-
-#define ARCH_TIMER_PHYS_ACCESS		0
-#define ARCH_TIMER_VIRT_ACCESS		1
-
-/*
- * These register accessors are marked inline so the compiler can
- * nicely work out which register we want, and chuck away the rest of
- * the code. At least it does so with a recent GCC (4.6.3).
- */
-static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
-{
-	if (access == ARCH_TIMER_PHYS_ACCESS) {
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
-			break;
-		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
-			break;
-		}
-	}
-
-	isb();
-}
-
-static inline u32 arch_timer_reg_read(const int access, const int reg)
-{
-	u32 val = 0;
-
-	if (access == ARCH_TIMER_PHYS_ACCESS) {
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
-			break;
-		case ARCH_TIMER_REG_FREQ:
-			asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val));
-			break;
-		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
-		switch (reg) {
-		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
-			break;
-		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
-			break;
-		}
-	}
-
-	return val;
-}
-
-static inline cycle_t arch_timer_counter_read(const int access)
-{
-	cycle_t cval = 0;
-
-	if (access == ARCH_TIMER_PHYS_ACCESS)
-		asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
-
-	if (access == ARCH_TIMER_VIRT_ACCESS)
-		asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (cval));
-
-	return cval;
-}
-
-static inline cycle_t arch_counter_get_cntpct(void)
-{
-	return arch_timer_counter_read(ARCH_TIMER_PHYS_ACCESS);
-}
-
-static inline cycle_t arch_counter_get_cntvct(void)
-{
-	return arch_timer_counter_read(ARCH_TIMER_VIRT_ACCESS);
-}
-
-static irqreturn_t inline timer_handler(const int access,
-					struct clock_event_device *evt)
-{
-	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
-	if (ctrl & ARCH_TIMER_CTRL_IT_STAT) {
-		ctrl |= ARCH_TIMER_CTRL_IT_MASK;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
-		evt->event_handler(evt);
-		return IRQ_HANDLED;
-	}
-
-	return IRQ_NONE;
-}
-
-static irqreturn_t arch_timer_handler_virt(int irq, void *dev_id)
-{
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
-
-	return timer_handler(ARCH_TIMER_VIRT_ACCESS, evt);
-}
-
-static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id)
-{
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
-
-	return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt);
-}
-
-static inline void timer_set_mode(const int access, int mode)
-{
-	unsigned long ctrl;
-	switch (mode) {
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
-		ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
-		break;
-	default:
-		break;
-	}
-}
-
-static void arch_timer_set_mode_virt(enum clock_event_mode mode,
-				     struct clock_event_device *clk)
-{
-	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode);
-}
-
-static void arch_timer_set_mode_phys(enum clock_event_mode mode,
-				     struct clock_event_device *clk)
-{
-	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode);
-}
-
-static inline void set_next_event(const int access, unsigned long evt)
-{
-	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
-	ctrl |= ARCH_TIMER_CTRL_ENABLE;
-	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt);
-	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
-}
-
-static int arch_timer_set_next_event_virt(unsigned long evt,
-					  struct clock_event_device *unused)
-{
-	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt);
-	return 0;
-}
-
-static int arch_timer_set_next_event_phys(unsigned long evt,
-					  struct clock_event_device *unused)
-{
-	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt);
-	return 0;
-}
-
-static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
-{
-	clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
-	clk->name = "arch_sys_timer";
-	clk->rating = 450;
-	if (arch_timer_use_virtual) {
-		clk->irq = arch_timer_ppi[VIRT_PPI];
-		clk->set_mode = arch_timer_set_mode_virt;
-		clk->set_next_event = arch_timer_set_next_event_virt;
-	} else {
-		clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
-		clk->set_mode = arch_timer_set_mode_phys;
-		clk->set_next_event = arch_timer_set_next_event_phys;
-	}
-
-	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, NULL);
-
-	clockevents_config_and_register(clk, arch_timer_rate,
-					0xf, 0x7fffffff);
-
-	*__this_cpu_ptr(arch_timer_evt) = clk;
-
-	if (arch_timer_use_virtual)
-		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
-	else {
-		enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
-	}
-
-	return 0;
-}
-
-/* Is the optional system timer available? */
-static int local_timer_is_architected(void)
-{
-	return (cpu_architecture() >= CPU_ARCH_ARMv7) &&
-	       ((read_cpuid_ext(CPUID_EXT_PFR1) >> 16) & 0xf) == 1;
-}
-
-static int arch_timer_available(void)
-{
-	unsigned long freq;
-
-	if (!local_timer_is_architected())
-		return -ENXIO;
-
-	if (arch_timer_rate == 0) {
-		freq = arch_timer_reg_read(ARCH_TIMER_PHYS_ACCESS,
-					   ARCH_TIMER_REG_FREQ);
-
-		/* Check the timer frequency. */
-		if (freq == 0) {
-			pr_warn("Architected timer frequency not available\n");
-			return -EINVAL;
-		}
-
-		arch_timer_rate = freq;
-	}
-
-	pr_info_once("Architected local timer running at %lu.%02luMHz (%s).\n",
-		     arch_timer_rate / 1000000, (arch_timer_rate / 10000) % 100,
-		     arch_timer_use_virtual ? "virt" : "phys");
-	return 0;
-}
-
-static u32 notrace arch_counter_get_cntpct32(void)
-{
-	cycle_t cnt = arch_counter_get_cntpct();
-
-	/*
-	 * The sched_clock infrastructure only knows about counters
-	 * with at most 32bits. Forget about the upper 24 bits for the
-	 * time being...
-	 */
-	return (u32)cnt;
-}
-
-static u32 notrace arch_counter_get_cntvct32(void)
-{
-	cycle_t cnt = arch_counter_get_cntvct();
-
-	/*
-	 * The sched_clock infrastructure only knows about counters
-	 * with at most 32bits. Forget about the upper 24 bits for the
-	 * time being...
-	 */
-	return (u32)cnt;
-}
-
-static cycle_t arch_counter_read(struct clocksource *cs)
-{
-	/*
-	 * Always use the physical counter for the clocksource.
-	 * CNTHCTL.PL1PCTEN must be set to 1.
-	 */
-	return arch_counter_get_cntpct();
-}
-
-static unsigned long arch_timer_read_current_timer(void)
+static unsigned long arch_timer_read_counter_long(void)
 {
-	return arch_counter_get_cntpct();
+	return arch_timer_read_counter();
 }
 
-static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
+static u32 arch_timer_read_counter_u32(void)
 {
-	/*
-	 * Always use the physical counter for the clocksource.
-	 * CNTHCTL.PL1PCTEN must be set to 1.
-	 */
-	return arch_counter_get_cntpct();
+	return arch_timer_read_counter();
 }
 
-static struct clocksource clocksource_counter = {
-	.name	= "arch_sys_counter",
-	.rating	= 400,
-	.read	= arch_counter_read,
-	.mask	= CLOCKSOURCE_MASK(56),
-	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static struct cyclecounter cyclecounter = {
-	.read	= arch_counter_read_cc,
-	.mask	= CLOCKSOURCE_MASK(56),
-};
-
-static struct timecounter timecounter;
-
-struct timecounter *arch_timer_get_timecounter(void)
-{
-	return &timecounter;
-}
-
-static void __cpuinit arch_timer_stop(struct clock_event_device *clk)
-{
-	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
-		 clk->irq, smp_processor_id());
-
-	if (arch_timer_use_virtual)
-		disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
-	else {
-		disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
-	}
-
-	clk->set_mode(CLOCK_EVT_MODE_UNUSED, clk);
-}
-
-static struct local_timer_ops arch_timer_ops __cpuinitdata = {
-	.setup	= arch_timer_setup,
-	.stop	= arch_timer_stop,
-};
-
-static struct clock_event_device arch_timer_global_evt;
+static struct delay_timer arch_delay_timer;
 
-static int __init arch_timer_register(void)
+static void __init arch_timer_delay_timer_register(void)
 {
-	int err;
-	int ppi;
-
-	err = arch_timer_available();
-	if (err)
-		goto out;
-
-	arch_timer_evt = alloc_percpu(struct clock_event_device *);
-	if (!arch_timer_evt) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
-	cyclecounter.mult = clocksource_counter.mult;
-	cyclecounter.shift = clocksource_counter.shift;
-	timecounter_init(&timecounter, &cyclecounter,
-			 arch_counter_get_cntpct());
-
-	if (arch_timer_use_virtual) {
-		ppi = arch_timer_ppi[VIRT_PPI];
-		err = request_percpu_irq(ppi, arch_timer_handler_virt,
-					 "arch_timer", arch_timer_evt);
-	} else {
-		ppi = arch_timer_ppi[PHYS_SECURE_PPI];
-		err = request_percpu_irq(ppi, arch_timer_handler_phys,
-					 "arch_timer", arch_timer_evt);
-		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
-			ppi = arch_timer_ppi[PHYS_NONSECURE_PPI];
-			err = request_percpu_irq(ppi, arch_timer_handler_phys,
-						 "arch_timer", arch_timer_evt);
-			if (err)
-				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
-						arch_timer_evt);
-		}
-	}
-
-	if (err) {
-		pr_err("arch_timer: can't register interrupt %d (%d)\n",
-		       ppi, err);
-		goto out_free;
-	}
-
-	err = local_timer_register(&arch_timer_ops);
-	if (err) {
-		/*
-		 * We couldn't register as a local timer (could be
-		 * because we're on a UP platform, or because some
-		 * other local timer is already present...). Try as a
-		 * global timer instead.
-		 */
-		arch_timer_global_evt.cpumask = cpumask_of(0);
-		err = arch_timer_setup(&arch_timer_global_evt);
-	}
-	if (err)
-		goto out_free_irq;
-
 	/* Use the architected timer for the delay loop. */
-	arch_delay_timer.read_current_timer = &arch_timer_read_current_timer;
-	arch_delay_timer.freq = arch_timer_rate;
+	arch_delay_timer.read_current_timer = arch_timer_read_counter_long;
+	arch_delay_timer.freq = arch_timer_get_rate();
 	register_current_timer_delay(&arch_delay_timer);
-	return 0;
-
-out_free_irq:
-	if (arch_timer_use_virtual)
-		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
-	else {
-		free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
-				arch_timer_evt);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
-					arch_timer_evt);
-	}
-
-out_free:
-	free_percpu(arch_timer_evt);
-out:
-	return err;
 }
 
-static const struct of_device_id arch_timer_of_match[] __initconst = {
-	{ .compatible	= "arm,armv7-timer",	},
-	{},
-};
-
 int __init arch_timer_of_register(void)
 {
-	struct device_node *np;
-	u32 freq;
-	int i;
-
-	np = of_find_matching_node(NULL, arch_timer_of_match);
-	if (!np) {
-		pr_err("arch_timer: can't find DT node\n");
-		return -ENODEV;
-	}
-
-	/* Try to determine the frequency from the device tree or CNTFRQ */
-	if (!of_property_read_u32(np, "clock-frequency", &freq))
-		arch_timer_rate = freq;
-
-	for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
-		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
+	int ret;
 
-	/*
-	 * If no interrupt provided for virtual timer, we'll have to
-	 * stick to the physical timer. It'd better be accessible...
-	 */
-	if (!arch_timer_ppi[VIRT_PPI]) {
-		arch_timer_use_virtual = false;
+	ret = arch_timer_init();
+	if (ret)
+		return ret;
 
-		if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
-		    !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
-			pr_warn("arch_timer: No interrupt available, giving up\n");
-			return -EINVAL;
-		}
-	}
+	arch_timer_delay_timer_register();
 
-	return arch_timer_register();
+	return 0;
 }
 
 int __init arch_timer_sched_clock_init(void)
 {
-	u32 (*cnt32)(void);
-	int err;
-
-	err = arch_timer_available();
-	if (err)
-		return err;
-
-	if (arch_timer_use_virtual)
-		cnt32 = arch_counter_get_cntvct32;
-	else
-		cnt32 = arch_counter_get_cntpct32;
+	if (arch_timer_get_rate() == 0)
+		return -ENXIO;
 
-	setup_sched_clock(cnt32, 32, arch_timer_rate);
+	setup_sched_clock(arch_timer_read_counter_u32,
+			  32, arch_timer_get_rate());
 	return 0;
 }
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c985b481192..5ce738b4350 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -13,6 +13,9 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
+#ifdef CONFIG_KVM_ARM_HOST
+#include <linux/kvm_host.h>
+#endif
 #include <asm/cacheflush.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
@@ -146,5 +149,45 @@ int main(void)
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
+#ifdef CONFIG_KVM_ARM_HOST
+  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
+  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
+  DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
+  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
+  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.vfp_host));
+  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
+  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
+  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
+  DEFINE(VCPU_ABT_REGS,		offsetof(struct kvm_vcpu, arch.regs.abt_regs));
+  DEFINE(VCPU_UND_REGS,		offsetof(struct kvm_vcpu, arch.regs.und_regs));
+  DEFINE(VCPU_IRQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.irq_regs));
+  DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
+  DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
+  DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
+  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
+  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.hsr));
+  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.hxfar));
+  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.hpfar));
+  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.hyp_pc));
+#ifdef CONFIG_KVM_ARM_VGIC
+  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
+  DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
+  DEFINE(VGIC_CPU_VMCR,		offsetof(struct vgic_cpu, vgic_vmcr));
+  DEFINE(VGIC_CPU_MISR,		offsetof(struct vgic_cpu, vgic_misr));
+  DEFINE(VGIC_CPU_EISR,		offsetof(struct vgic_cpu, vgic_eisr));
+  DEFINE(VGIC_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_elrsr));
+  DEFINE(VGIC_CPU_APR,		offsetof(struct vgic_cpu, vgic_apr));
+  DEFINE(VGIC_CPU_LR,		offsetof(struct vgic_cpu, vgic_lr));
+  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
+#ifdef CONFIG_KVM_ARM_TIMER
+  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
+  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
+  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
+  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
+#endif
+  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
+#endif
+  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
+#endif
   return 0; 
 }
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 379cf329239..a1f73b502ef 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -413,7 +413,7 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
-static int __init pcibios_init_resources(int busnr, struct pci_sys_data *sys)
+static int pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 {
 	int ret;
 	struct pci_host_bridge_window *window;
@@ -445,7 +445,7 @@ static int __init pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 	return 0;
 }
 
-static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
+static void pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 {
 	struct pci_sys_data *sys = NULL;
 	int ret;
@@ -464,6 +464,9 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 		sys->map_irq = hw->map_irq;
 		INIT_LIST_HEAD(&sys->resources);
 
+		if (hw->private_data)
+			sys->private_data = hw->private_data[nr];
+
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
@@ -493,7 +496,7 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 	}
 }
 
-void __init pci_common_init(struct hw_pci *hw)
+void pci_common_init(struct hw_pci *hw)
 {
 	struct pci_sys_data *sys;
 	LIST_HEAD(head);
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 5ff2e77782b..5eae53e7a2e 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -28,6 +28,7 @@
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/smp.h>
+#include <linux/cpu_pm.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
@@ -35,6 +36,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/kdebug.h>
 #include <asm/traps.h>
+#include <asm/hardware/coresight.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -49,6 +51,9 @@ static int core_num_wrps;
 /* Debug architecture version. */
 static u8 debug_arch;
 
+/* Does debug architecture support OS Save and Restore? */
+static bool has_ossr;
+
 /* Maximum supported watchpoint length. */
 static u8 max_watchpoint_len;
 
@@ -903,6 +908,23 @@ static struct undef_hook debug_reg_hook = {
 	.fn		= debug_reg_trap,
 };
 
+/* Does this core support OS Save and Restore? */
+static bool core_has_os_save_restore(void)
+{
+	u32 oslsr;
+
+	switch (get_debug_arch()) {
+	case ARM_DEBUG_ARCH_V7_1:
+		return true;
+	case ARM_DEBUG_ARCH_V7_ECP14:
+		ARM_DBG_READ(c1, c1, 4, oslsr);
+		if (oslsr & ARM_OSLSR_OSLM0)
+			return true;
+	default:
+		return false;
+	}
+}
+
 static void reset_ctrl_regs(void *unused)
 {
 	int i, raw_num_brps, err = 0, cpu = smp_processor_id();
@@ -930,11 +952,7 @@ static void reset_ctrl_regs(void *unused)
 		if ((val & 0x1) == 0)
 			err = -EPERM;
 
-		/*
-		 * Check whether we implement OS save and restore.
-		 */
-		ARM_DBG_READ(c1, c1, 4, val);
-		if ((val & 0x9) == 0)
+		if (!has_ossr)
 			goto clear_vcr;
 		break;
 	case ARM_DEBUG_ARCH_V7_1:
@@ -955,9 +973,9 @@ static void reset_ctrl_regs(void *unused)
 
 	/*
 	 * Unconditionally clear the OS lock by writing a value
-	 * other than 0xC5ACCE55 to the access register.
+	 * other than CS_LAR_KEY to the access register.
 	 */
-	ARM_DBG_WRITE(c1, c0, 4, 0);
+	ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY);
 	isb();
 
 	/*
@@ -1015,6 +1033,30 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = {
 	.notifier_call = dbg_reset_notify,
 };
 
+#ifdef CONFIG_CPU_PM
+static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action,
+			     void *v)
+{
+	if (action == CPU_PM_EXIT)
+		reset_ctrl_regs(NULL);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = {
+	.notifier_call = dbg_cpu_pm_notify,
+};
+
+static void __init pm_init(void)
+{
+	cpu_pm_register_notifier(&dbg_cpu_pm_nb);
+}
+#else
+static inline void pm_init(void)
+{
+}
+#endif
+
 static int __init arch_hw_breakpoint_init(void)
 {
 	debug_arch = get_debug_arch();
@@ -1024,6 +1066,8 @@ static int __init arch_hw_breakpoint_init(void)
 		return 0;
 	}
 
+	has_ossr = core_has_os_save_restore();
+
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
 	core_num_wrps = get_num_wrps();
@@ -1062,8 +1106,9 @@ static int __init arch_hw_breakpoint_init(void)
 	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
 			TRAP_HWBKPT, "breakpoint debug exception");
 
-	/* Register hotplug notifier. */
+	/* Register hotplug and PM notifiers. */
 	register_cpu_notifier(&dbg_reset_nb);
+	pm_init();
 	return 0;
 }
 arch_initcall(arch_hw_breakpoint_init);
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 896165096d6..8e4ef4c83a7 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -117,6 +117,16 @@ void __init init_IRQ(void)
 	machine_desc->init_irq();
 }
 
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
+{
+	if (handle_arch_irq)
+		return;
+
+	handle_arch_irq = handle_irq;
+}
+#endif
+
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index f9e8657dd24..31e0eb353cd 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -149,12 +149,6 @@ again:
 static void
 armpmu_read(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-
-	/* Don't read disabled counters! */
-	if (hwc->idx < 0)
-		return;
-
 	armpmu_event_update(event);
 }
 
@@ -207,8 +201,6 @@ armpmu_del(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	WARN_ON(idx < 0);
-
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
@@ -358,7 +350,7 @@ __hw_perf_event_init(struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	int mapping, err;
+	int mapping;
 
 	mapping = armpmu->map_event(event);
 
@@ -407,14 +399,12 @@ __hw_perf_event_init(struct perf_event *event)
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
 
-	err = 0;
 	if (event->group_leader != event) {
-		err = validate_group(event);
-		if (err)
+		if (validate_group(event) != 0);
 			return -EINVAL;
 	}
 
-	return err;
+	return 0;
 }
 
 static int armpmu_event_init(struct perf_event *event)
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 5f6620684e2..1f2740e3dbc 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -147,7 +147,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->free_irq	= cpu_pmu_free_irq;
 
 	/* Ensure the PMU has sane values out of reset. */
-	if (cpu_pmu && cpu_pmu->reset)
+	if (cpu_pmu->reset)
 		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
 }
 
@@ -201,48 +201,46 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 static int probe_current_pmu(struct arm_pmu *pmu)
 {
 	int cpu = get_cpu();
-	unsigned long cpuid = read_cpuid_id();
-	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
-	unsigned long part_number = (cpuid & 0xFFF0);
+	unsigned long implementor = read_cpuid_implementor();
+	unsigned long part_number = read_cpuid_part_number();
 	int ret = -ENODEV;
 
 	pr_info("probing PMU on CPU %d\n", cpu);
 
 	/* ARM Ltd CPUs. */
-	if (0x41 == implementor) {
+	if (implementor == ARM_CPU_IMP_ARM) {
 		switch (part_number) {
-		case 0xB360:	/* ARM1136 */
-		case 0xB560:	/* ARM1156 */
-		case 0xB760:	/* ARM1176 */
+		case ARM_CPU_PART_ARM1136:
+		case ARM_CPU_PART_ARM1156:
+		case ARM_CPU_PART_ARM1176:
 			ret = armv6pmu_init(pmu);
 			break;
-		case 0xB020:	/* ARM11mpcore */
+		case ARM_CPU_PART_ARM11MPCORE:
 			ret = armv6mpcore_pmu_init(pmu);
 			break;
-		case 0xC080:	/* Cortex-A8 */
+		case ARM_CPU_PART_CORTEX_A8:
 			ret = armv7_a8_pmu_init(pmu);
 			break;
-		case 0xC090:	/* Cortex-A9 */
+		case ARM_CPU_PART_CORTEX_A9:
 			ret = armv7_a9_pmu_init(pmu);
 			break;
-		case 0xC050:	/* Cortex-A5 */
+		case ARM_CPU_PART_CORTEX_A5:
 			ret = armv7_a5_pmu_init(pmu);
 			break;
-		case 0xC0F0:	/* Cortex-A15 */
+		case ARM_CPU_PART_CORTEX_A15:
 			ret = armv7_a15_pmu_init(pmu);
 			break;
-		case 0xC070:	/* Cortex-A7 */
+		case ARM_CPU_PART_CORTEX_A7:
 			ret = armv7_a7_pmu_init(pmu);
 			break;
 		}
 	/* Intel CPUs [xscale]. */
-	} else if (0x69 == implementor) {
-		part_number = (cpuid >> 13) & 0x7;
-		switch (part_number) {
-		case 1:
+	} else if (implementor == ARM_CPU_IMP_INTEL) {
+		switch (xscale_cpu_arch_version()) {
+		case ARM_CPU_XSCALE_ARCH_V1:
 			ret = xscale1pmu_init(pmu);
 			break;
-		case 2:
+		case ARM_CPU_XSCALE_ARCH_V2:
 			ret = xscale2pmu_init(pmu);
 			break;
 		}
@@ -279,17 +277,22 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (ret) {
-		pr_info("failed to register PMU devices!");
-		kfree(pmu);
-		return ret;
+		pr_info("failed to probe PMU!");
+		goto out_free;
 	}
 
 	cpu_pmu = pmu;
 	cpu_pmu->plat_device = pdev;
 	cpu_pmu_init(cpu_pmu);
-	armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
 
-	return 0;
+	if (!ret)
+		return 0;
+
+out_free:
+	pr_info("failed to register PMU devices!");
+	kfree(pmu);
+	return ret;
 }
 
 static struct platform_driver cpu_pmu_driver = {
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 041d0526a28..03664b0e8fa 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -106,7 +106,7 @@ static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 		},
 		[C(OP_WRITE)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
@@ -259,7 +259,7 @@ static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 		},
 		[C(OP_WRITE)] = {
 			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4fbc757d9cf..8c79a9e70b8 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -157,8 +157,8 @@ static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
 		},
 		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
@@ -282,7 +282,7 @@ static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 		},
 		[C(OP_WRITE)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
@@ -399,8 +399,8 @@ static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
 		},
 		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		/*
 		 * The prefetch counters don't differentiate between the I
@@ -527,8 +527,8 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
 		},
 		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
@@ -651,8 +651,8 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
 		},
 		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 2b0fe30ec12..63990c42fac 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -83,7 +83,7 @@ static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 		},
 		[C(OP_WRITE)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 		[C(OP_PREFETCH)] = {
 			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index c6dec5fc20a..047d3e40e47 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -172,14 +172,9 @@ static void default_idle(void)
 	local_irq_enable();
 }
 
-void (*pm_idle)(void) = default_idle;
-EXPORT_SYMBOL(pm_idle);
-
 /*
- * The idle thread, has rather strange semantics for calling pm_idle,
- * but this is what x86 does and we need to do the same, so that
- * things like cpuidle get called in the same way.  The only difference
- * is that we always respect 'hlt_counter' to prevent low power idle.
+ * The idle thread.
+ * We always respect 'hlt_counter' to prevent low power idle.
  */
 void cpu_idle(void)
 {
@@ -210,10 +205,10 @@ void cpu_idle(void)
 			} else if (!need_resched()) {
 				stop_critical_timings();
 				if (cpuidle_idle_call())
-					pm_idle();
+					default_idle();
 				start_critical_timings();
 				/*
-				 * pm_idle functions must always
+				 * default_idle functions must always
 				 * return with IRQs enabled.
 				 */
 				WARN_ON(irqs_disabled());
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
new file mode 100644
index 00000000000..36531643cc2
--- /dev/null
+++ b/arch/arm/kernel/psci.c
@@ -0,0 +1,211 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt) "psci: " fmt
+
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/compiler.h>
+#include <asm/errno.h>
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+#include <asm/psci.h>
+
+struct psci_operations psci_ops;
+
+static int (*invoke_psci_fn)(u32, u32, u32, u32);
+
+enum psci_function {
+	PSCI_FN_CPU_SUSPEND,
+	PSCI_FN_CPU_ON,
+	PSCI_FN_CPU_OFF,
+	PSCI_FN_MIGRATE,
+	PSCI_FN_MAX,
+};
+
+static u32 psci_function_id[PSCI_FN_MAX];
+
+#define PSCI_RET_SUCCESS		0
+#define PSCI_RET_EOPNOTSUPP		-1
+#define PSCI_RET_EINVAL			-2
+#define PSCI_RET_EPERM			-3
+
+static int psci_to_linux_errno(int errno)
+{
+	switch (errno) {
+	case PSCI_RET_SUCCESS:
+		return 0;
+	case PSCI_RET_EOPNOTSUPP:
+		return -EOPNOTSUPP;
+	case PSCI_RET_EINVAL:
+		return -EINVAL;
+	case PSCI_RET_EPERM:
+		return -EPERM;
+	};
+
+	return -EINVAL;
+}
+
+#define PSCI_POWER_STATE_ID_MASK	0xffff
+#define PSCI_POWER_STATE_ID_SHIFT	0
+#define PSCI_POWER_STATE_TYPE_MASK	0x1
+#define PSCI_POWER_STATE_TYPE_SHIFT	16
+#define PSCI_POWER_STATE_AFFL_MASK	0x3
+#define PSCI_POWER_STATE_AFFL_SHIFT	24
+
+static u32 psci_power_state_pack(struct psci_power_state state)
+{
+	return	((state.id & PSCI_POWER_STATE_ID_MASK)
+			<< PSCI_POWER_STATE_ID_SHIFT)	|
+		((state.type & PSCI_POWER_STATE_TYPE_MASK)
+			<< PSCI_POWER_STATE_TYPE_SHIFT)	|
+		((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
+			<< PSCI_POWER_STATE_AFFL_SHIFT);
+}
+
+/*
+ * The following two functions are invoked via the invoke_psci_fn pointer
+ * and will not be inlined, allowing us to piggyback on the AAPCS.
+ */
+static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1,
+					 u32 arg2)
+{
+	asm volatile(
+			__asmeq("%0", "r0")
+			__asmeq("%1", "r1")
+			__asmeq("%2", "r2")
+			__asmeq("%3", "r3")
+			__HVC(0)
+		: "+r" (function_id)
+		: "r" (arg0), "r" (arg1), "r" (arg2));
+
+	return function_id;
+}
+
+static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
+					 u32 arg2)
+{
+	asm volatile(
+			__asmeq("%0", "r0")
+			__asmeq("%1", "r1")
+			__asmeq("%2", "r2")
+			__asmeq("%3", "r3")
+			__SMC(0)
+		: "+r" (function_id)
+		: "r" (arg0), "r" (arg1), "r" (arg2));
+
+	return function_id;
+}
+
+static int psci_cpu_suspend(struct psci_power_state state,
+			    unsigned long entry_point)
+{
+	int err;
+	u32 fn, power_state;
+
+	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
+	power_state = psci_power_state_pack(state);
+	err = invoke_psci_fn(fn, power_state, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_off(struct psci_power_state state)
+{
+	int err;
+	u32 fn, power_state;
+
+	fn = psci_function_id[PSCI_FN_CPU_OFF];
+	power_state = psci_power_state_pack(state);
+	err = invoke_psci_fn(fn, power_state, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_CPU_ON];
+	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
+	return psci_to_linux_errno(err);
+}
+
+static int psci_migrate(unsigned long cpuid)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_MIGRATE];
+	err = invoke_psci_fn(fn, cpuid, 0, 0);
+	return psci_to_linux_errno(err);
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci",	},
+	{},
+};
+
+static int __init psci_init(void)
+{
+	struct device_node *np;
+	const char *method;
+	u32 id;
+
+	np = of_find_matching_node(NULL, psci_of_match);
+	if (!np)
+		return 0;
+
+	pr_info("probing function IDs from device-tree\n");
+
+	if (of_property_read_string(np, "method", &method)) {
+		pr_warning("missing \"method\" property\n");
+		goto out_put_node;
+	}
+
+	if (!strcmp("hvc", method)) {
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+	} else if (!strcmp("smc", method)) {
+		invoke_psci_fn = __invoke_psci_fn_smc;
+	} else {
+		pr_warning("invalid \"method\" property: %s\n", method);
+		goto out_put_node;
+	}
+
+	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
+		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
+		psci_ops.cpu_suspend = psci_cpu_suspend;
+	}
+
+	if (!of_property_read_u32(np, "cpu_off", &id)) {
+		psci_function_id[PSCI_FN_CPU_OFF] = id;
+		psci_ops.cpu_off = psci_cpu_off;
+	}
+
+	if (!of_property_read_u32(np, "cpu_on", &id)) {
+		psci_function_id[PSCI_FN_CPU_ON] = id;
+		psci_ops.cpu_on = psci_cpu_on;
+	}
+
+	if (!of_property_read_u32(np, "migrate", &id)) {
+		psci_function_id[PSCI_FN_MIGRATE] = id;
+		psci_ops.migrate = psci_migrate;
+	}
+
+out_put_node:
+	of_node_put(np);
+	return 0;
+}
+early_initcall(psci_init);
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index fc6692e2b60..bd6f56b9ec2 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -93,11 +93,11 @@ static void notrace update_sched_clock(void)
 	 * detectable in cyc_to_fixed_sched_clock().
 	 */
 	raw_local_irq_save(flags);
-	cd.epoch_cyc = cyc;
+	cd.epoch_cyc_copy = cyc;
 	smp_wmb();
 	cd.epoch_ns = ns;
 	smp_wmb();
-	cd.epoch_cyc_copy = cyc;
+	cd.epoch_cyc = cyc;
 	raw_local_irq_restore(flags);
 }
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 84f4cbf652e..5f73f7018f5 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -125,18 +125,6 @@ void __init smp_init_cpus(void)
 		smp_ops.smp_init_cpus();
 }
 
-static void __init platform_smp_prepare_cpus(unsigned int max_cpus)
-{
-	if (smp_ops.smp_prepare_cpus)
-		smp_ops.smp_prepare_cpus(max_cpus);
-}
-
-static void __cpuinit platform_secondary_init(unsigned int cpu)
-{
-	if (smp_ops.smp_secondary_init)
-		smp_ops.smp_secondary_init(cpu);
-}
-
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	if (smp_ops.smp_boot_secondary)
@@ -154,12 +142,6 @@ static int platform_cpu_kill(unsigned int cpu)
 	return 1;
 }
 
-static void platform_cpu_die(unsigned int cpu)
-{
-	if (smp_ops.cpu_die)
-		smp_ops.cpu_die(cpu);
-}
-
 static int platform_cpu_disable(unsigned int cpu)
 {
 	if (smp_ops.cpu_disable)
@@ -257,7 +239,8 @@ void __ref cpu_die(void)
 	 * actual CPU shutdown procedure is at least platform (if not
 	 * CPU) specific.
 	 */
-	platform_cpu_die(cpu);
+	if (smp_ops.cpu_die)
+		smp_ops.cpu_die(cpu);
 
 	/*
 	 * Do not return to the idle loop - jump back to the secondary
@@ -324,7 +307,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * Give the platform a chance to do its own initialisation.
 	 */
-	platform_secondary_init(cpu);
+	if (smp_ops.smp_secondary_init)
+		smp_ops.smp_secondary_init(cpu);
 
 	notify_cpu_starting(cpu);
 
@@ -399,8 +383,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		/*
 		 * Initialise the present map, which describes the set of CPUs
 		 * actually populated at the present time. A platform should
-		 * re-initialize the map in platform_smp_prepare_cpus() if
-		 * present != possible (e.g. physical hotplug).
+		 * re-initialize the map in the platforms smp_prepare_cpus()
+		 * if present != possible (e.g. physical hotplug).
 		 */
 		init_cpu_present(cpu_possible_mask);
 
@@ -408,7 +392,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		 * Initialise the SCU if there are more than one CPU
 		 * and let them know where to start.
 		 */
-		platform_smp_prepare_cpus(max_cpus);
+		if (smp_ops.smp_prepare_cpus)
+			smp_ops.smp_prepare_cpus(max_cpus);
 	}
 }
 
@@ -416,7 +401,8 @@ static void (*smp_cross_call)(const struct cpumask *, unsigned int);
 
 void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
 {
-	smp_cross_call = fn;
+	if (!smp_cross_call)
+		smp_cross_call = fn;
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -475,14 +461,8 @@ u64 smp_irq_stat_cpu(unsigned int cpu)
  */
 static DEFINE_PER_CPU(struct clock_event_device, percpu_clockevent);
 
-static void ipi_timer(void)
-{
-	struct clock_event_device *evt = &__get_cpu_var(percpu_clockevent);
-	evt->event_handler(evt);
-}
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-static void smp_timer_broadcast(const struct cpumask *mask)
+void tick_broadcast(const struct cpumask *mask)
 {
 	smp_cross_call(mask, IPI_TIMER);
 }
@@ -530,7 +510,6 @@ static void __cpuinit percpu_timer_setup(void)
 	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
 
 	evt->cpumask = cpumask_of(cpu);
-	evt->broadcast = smp_timer_broadcast;
 
 	if (!lt_ops || lt_ops->setup(evt))
 		broadcast_timer_setup(evt);
@@ -596,11 +575,13 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	case IPI_WAKEUP:
 		break;
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
 		irq_enter();
-		ipi_timer();
+		tick_receive_broadcast();
 		irq_exit();
 		break;
+#endif
 
 	case IPI_RESCHEDULE:
 		scheduler_ipi();
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index b9f015e843d..45eac87ed66 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -75,7 +75,7 @@ void scu_enable(void __iomem *scu_base)
 int scu_power_mode(void __iomem *scu_base, unsigned int mode)
 {
 	unsigned int val;
-	int cpu = cpu_logical_map(smp_processor_id());
+	int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0);
 
 	if (mode > 3 || mode == 1 || cpu > 3)
 		return -EINVAL;
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 49f335d301b..c092115d903 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -24,14 +24,12 @@
 
 #include <asm/smp_twd.h>
 #include <asm/localtimer.h>
-#include <asm/hardware/gic.h>
 
 /* set up by the platform code */
 static void __iomem *twd_base;
 
 static struct clk *twd_clk;
 static unsigned long twd_timer_rate;
-static bool common_setup_called;
 static DEFINE_PER_CPU(bool, percpu_setup_called);
 
 static struct clock_event_device __percpu **twd_evt;
@@ -239,25 +237,28 @@ static irqreturn_t twd_handler(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static struct clk *twd_get_clock(void)
+static void twd_get_clock(struct device_node *np)
 {
-	struct clk *clk;
 	int err;
 
-	clk = clk_get_sys("smp_twd", NULL);
-	if (IS_ERR(clk)) {
-		pr_err("smp_twd: clock not found: %d\n", (int)PTR_ERR(clk));
-		return clk;
+	if (np)
+		twd_clk = of_clk_get(np, 0);
+	else
+		twd_clk = clk_get_sys("smp_twd", NULL);
+
+	if (IS_ERR(twd_clk)) {
+		pr_err("smp_twd: clock not found %d\n", (int) PTR_ERR(twd_clk));
+		return;
 	}
 
-	err = clk_prepare_enable(clk);
+	err = clk_prepare_enable(twd_clk);
 	if (err) {
 		pr_err("smp_twd: clock failed to prepare+enable: %d\n", err);
-		clk_put(clk);
-		return ERR_PTR(err);
+		clk_put(twd_clk);
+		return;
 	}
 
-	return clk;
+	twd_timer_rate = clk_get_rate(twd_clk);
 }
 
 /*
@@ -280,26 +281,7 @@ static int __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	}
 	per_cpu(percpu_setup_called, cpu) = true;
 
-	/*
-	 * This stuff only need to be done once for the entire TWD cluster
-	 * during the runtime of the system.
-	 */
-	if (!common_setup_called) {
-		twd_clk = twd_get_clock();
-
-		/*
-		 * We use IS_ERR_OR_NULL() here, because if the clock stubs
-		 * are active we will get a valid clk reference which is
-		 * however NULL and will return the rate 0. In that case we
-		 * need to calibrate the rate instead.
-		 */
-		if (!IS_ERR_OR_NULL(twd_clk))
-			twd_timer_rate = clk_get_rate(twd_clk);
-		else
-			twd_calibrate_rate();
-
-		common_setup_called = true;
-	}
+	twd_calibrate_rate();
 
 	/*
 	 * The following is done once per CPU the first time .setup() is
@@ -330,7 +312,7 @@ static struct local_timer_ops twd_lt_ops __cpuinitdata = {
 	.stop	= twd_timer_stop,
 };
 
-static int __init twd_local_timer_common_register(void)
+static int __init twd_local_timer_common_register(struct device_node *np)
 {
 	int err;
 
@@ -350,6 +332,8 @@ static int __init twd_local_timer_common_register(void)
 	if (err)
 		goto out_irq;
 
+	twd_get_clock(np);
+
 	return 0;
 
 out_irq:
@@ -373,7 +357,7 @@ int __init twd_local_timer_register(struct twd_local_timer *tlt)
 	if (!twd_base)
 		return -ENOMEM;
 
-	return twd_local_timer_common_register();
+	return twd_local_timer_common_register(NULL);
 }
 
 #ifdef CONFIG_OF
@@ -405,7 +389,7 @@ void __init twd_local_timer_of_register(void)
 		goto out;
 	}
 
-	err = twd_local_timer_common_register();
+	err = twd_local_timer_common_register(np);
 
 out:
 	WARN(err, "twd_local_timer_of_register failed (%d)\n", err);
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 09be0c3c906..955d92d265e 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -21,7 +21,6 @@
 #include <linux/timex.h>
 #include <linux/errno.h>
 #include <linux/profile.h>
-#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 #include <linux/irq.h>
 
@@ -31,11 +30,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
-/*
- * Our system timer.
- */
-static struct sys_timer *system_timer;
-
 #if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) || \
     defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE)
 /* this needs a better home */
@@ -69,16 +63,6 @@ unsigned long profile_pc(struct pt_regs *regs)
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
-u32 arch_gettimeoffset(void)
-{
-	if (system_timer->offset != NULL)
-		return system_timer->offset() * 1000;
-
-	return 0;
-}
-#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
-
 #ifndef CONFIG_GENERIC_CLOCKEVENTS
 /*
  * Kernel system timer support.
@@ -129,43 +113,8 @@ int __init register_persistent_clock(clock_access_fn read_boot,
 	return -EINVAL;
 }
 
-#if defined(CONFIG_PM) && !defined(CONFIG_GENERIC_CLOCKEVENTS)
-static int timer_suspend(void)
-{
-	if (system_timer->suspend)
-		system_timer->suspend();
-
-	return 0;
-}
-
-static void timer_resume(void)
-{
-	if (system_timer->resume)
-		system_timer->resume();
-}
-#else
-#define timer_suspend NULL
-#define timer_resume NULL
-#endif
-
-static struct syscore_ops timer_syscore_ops = {
-	.suspend	= timer_suspend,
-	.resume		= timer_resume,
-};
-
-static int __init timer_init_syscore_ops(void)
-{
-	register_syscore_ops(&timer_syscore_ops);
-
-	return 0;
-}
-
-device_initcall(timer_init_syscore_ops);
-
 void __init time_init(void)
 {
-	system_timer = machine_desc->timer;
-	system_timer->init();
+	machine_desc->init_time();
 	sched_clock_postinit();
 }
-
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 11c1785bf63..b571484e9f0 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -19,7 +19,11 @@
 	ALIGN_FUNCTION();						\
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
 	*(.idmap.text)							\
-	VMLINUX_SYMBOL(__idmap_text_end) = .;
+	VMLINUX_SYMBOL(__idmap_text_end) = .;				\
+	ALIGN_FUNCTION();						\
+	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;			\
+	*(.hyp.idmap.text)						\
+	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
 
 #ifdef CONFIG_HOTPLUG_CPU
 #define ARM_CPU_DISCARD(x)