Merge tag 'kvm-arm-for-v4.12-round2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

Second round of KVM/ARM Changes for v4.12.

Changes include:
 - A fix related to the 32-bit idmap stub
 - A fix to the bitmask used to deode the operands of an AArch32 CP
   instruction
 - We have moved the files shared between arch/arm/kvm and
   arch/arm64/kvm to virt/kvm/arm
 - We add support for saving/restoring the virtual ITS state to
   userspace

16 files changed, 5725 insertions, 277 deletions

diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
new file mode 100644
index 000000000000..3417e184c8e1
--- /dev/null
+++ b/virt/kvm/arm/arm.c
@@ -0,0 +1,1480 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/cpu_pm.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/mman.h>
+#include <linux/sched.h>
+#include <linux/kvm.h>
+#include <trace/events/kvm.h>
+#include <kvm/arm_pmu.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/mman.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/virt.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_psci.h>
+#include <asm/sections.h>
+
+#ifdef REQUIRES_VIRT
+__asm__(".arch_extension	virt");
+#endif
+
+static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
+static kvm_cpu_context_t __percpu *kvm_host_cpu_state;
+
+/* Per-CPU variable containing the currently running vcpu. */
+static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
+
+/* The VMID used in the VTTBR */
+static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
+static u32 kvm_next_vmid;
+static unsigned int kvm_vmid_bits __read_mostly;
+static DEFINE_SPINLOCK(kvm_vmid_lock);
+
+static bool vgic_present;
+
+static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
+
+static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(preemptible());
+	__this_cpu_write(kvm_arm_running_vcpu, vcpu);
+}
+
+/**
+ * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU.
+ * Must be called from non-preemptible context
+ */
+struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
+{
+	BUG_ON(preemptible());
+	return __this_cpu_read(kvm_arm_running_vcpu);
+}
+
+/**
+ * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
+ */
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
+{
+	return &kvm_arm_running_vcpu;
+}
+
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
+}
+
+int kvm_arch_hardware_setup(void)
+{
+	return 0;
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+	*(int *)rtn = 0;
+}
+
+
+/**
+ * kvm_arch_init_vm - initializes a VM data structure
+ * @kvm:	pointer to the KVM struct
+ */
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
+{
+	int ret, cpu;
+
+	if (type)
+		return -EINVAL;
+
+	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
+	if (!kvm->arch.last_vcpu_ran)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
+
+	ret = kvm_alloc_stage2_pgd(kvm);
+	if (ret)
+		goto out_fail_alloc;
+
+	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
+	if (ret)
+		goto out_free_stage2_pgd;
+
+	kvm_vgic_early_init(kvm);
+
+	/* Mark the initial VMID generation invalid */
+	kvm->arch.vmid_gen = 0;
+
+	/* The maximum number of VCPUs is limited by the host's GIC model */
+	kvm->arch.max_vcpus = vgic_present ?
+				kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
+
+	return ret;
+out_free_stage2_pgd:
+	kvm_free_stage2_pgd(kvm);
+out_fail_alloc:
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
+	return ret;
+}
+
+bool kvm_arch_has_vcpu_debugfs(void)
+{
+	return false;
+}
+
+int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+
+/**
+ * kvm_arch_destroy_vm - destroy the VM data structure
+ * @kvm:	pointer to the KVM struct
+ */
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	int i;
+
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
+
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		if (kvm->vcpus[i]) {
+			kvm_arch_vcpu_free(kvm->vcpus[i]);
+			kvm->vcpus[i] = NULL;
+		}
+	}
+
+	kvm_vgic_destroy(kvm);
+}
+
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
+{
+	int r;
+	switch (ext) {
+	case KVM_CAP_IRQCHIP:
+		r = vgic_present;
+		break;
+	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_DEVICE_CTRL:
+	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_SYNC_MMU:
+	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+	case KVM_CAP_ONE_REG:
+	case KVM_CAP_ARM_PSCI:
+	case KVM_CAP_ARM_PSCI_0_2:
+	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_MP_STATE:
+	case KVM_CAP_IMMEDIATE_EXIT:
+		r = 1;
+		break;
+	case KVM_CAP_ARM_SET_DEVICE_ADDR:
+		r = 1;
+		break;
+	case KVM_CAP_NR_VCPUS:
+		r = num_online_cpus();
+		break;
+	case KVM_CAP_MAX_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
+	case KVM_CAP_MSI_DEVID:
+		if (!kvm)
+			r = -EINVAL;
+		else
+			r = kvm->arch.vgic.msis_require_devid;
+		break;
+	case KVM_CAP_ARM_USER_IRQ:
+		/*
+		 * 1: EL1_VTIMER, EL1_PTIMER, and PMU.
+		 * (bump this number if adding more devices)
+		 */
+		r = 1;
+		break;
+	default:
+		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
+		break;
+	}
+	return r;
+}
+
+long kvm_arch_dev_ioctl(struct file *filp,
+			unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	int err;
+	struct kvm_vcpu *vcpu;
+
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	if (id >= kvm->arch.max_vcpus) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
+	if (err)
+		goto vcpu_uninit;
+
+	return vcpu;
+vcpu_uninit:
+	kvm_vcpu_uninit(vcpu);
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
+out:
+	return ERR_PTR(err);
+}
+
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	kvm_vgic_vcpu_early_init(vcpu);
+}
+
+void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	kvm_mmu_free_memory_caches(vcpu);
+	kvm_timer_vcpu_terminate(vcpu);
+	kvm_vgic_vcpu_destroy(vcpu);
+	kvm_pmu_vcpu_destroy(vcpu);
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvm_arch_vcpu_free(vcpu);
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return kvm_timer_should_fire(vcpu_vtimer(vcpu)) ||
+	       kvm_timer_should_fire(vcpu_ptimer(vcpu));
+}
+
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_schedule(vcpu);
+}
+
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_unschedule(vcpu);
+}
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	/* Force users to call KVM_ARM_VCPU_INIT */
+	vcpu->arch.target = -1;
+	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+
+	/* Set up the timer */
+	kvm_timer_vcpu_init(vcpu);
+
+	kvm_arm_reset_debug_ptr(vcpu);
+
+	return kvm_vgic_vcpu_init(vcpu);
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	int *last_ran;
+
+	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+
+	/*
+	 * We might get preempted before the vCPU actually runs, but
+	 * over-invalidation doesn't affect correctness.
+	 */
+	if (*last_ran != vcpu->vcpu_id) {
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		*last_ran = vcpu->vcpu_id;
+	}
+
+	vcpu->cpu = cpu;
+	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
+
+	kvm_arm_set_running_vcpu(vcpu);
+
+	kvm_vgic_load(vcpu);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	kvm_vgic_put(vcpu);
+
+	vcpu->cpu = -1;
+
+	kvm_arm_set_running_vcpu(NULL);
+	kvm_timer_vcpu_put(vcpu);
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	if (vcpu->arch.power_off)
+		mp_state->mp_state = KVM_MP_STATE_STOPPED;
+	else
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_RUNNABLE:
+		vcpu->arch.power_off = false;
+		break;
+	case KVM_MP_STATE_STOPPED:
+		vcpu->arch.power_off = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled
+ * @v:		The VCPU pointer
+ *
+ * If the guest CPU is not waiting for interrupts or an interrupt line is
+ * asserted, the CPU is by definition runnable.
+ */
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
+{
+	return ((!!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v))
+		&& !v->arch.power_off && !v->arch.pause);
+}
+
+/* Just ensure a guest exit from a particular CPU */
+static void exit_vm_noop(void *info)
+{
+}
+
+void force_vm_exit(const cpumask_t *mask)
+{
+	preempt_disable();
+	smp_call_function_many(mask, exit_vm_noop, NULL, true);
+	preempt_enable();
+}
+
+/**
+ * need_new_vmid_gen - check that the VMID is still valid
+ * @kvm: The VM's VMID to check
+ *
+ * return true if there is a new generation of VMIDs being used
+ *
+ * The hardware supports only 256 values with the value zero reserved for the
+ * host, so we check if an assigned value belongs to a previous generation,
+ * which which requires us to assign a new value. If we're the first to use a
+ * VMID for the new generation, we must flush necessary caches and TLBs on all
+ * CPUs.
+ */
+static bool need_new_vmid_gen(struct kvm *kvm)
+{
+	return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
+}
+
+/**
+ * update_vttbr - Update the VTTBR with a valid VMID before the guest runs
+ * @kvm	The guest that we are about to run
+ *
+ * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the
+ * VM has a valid VMID, otherwise assigns a new one and flushes corresponding
+ * caches and TLBs.
+ */
+static void update_vttbr(struct kvm *kvm)
+{
+	phys_addr_t pgd_phys;
+	u64 vmid;
+
+	if (!need_new_vmid_gen(kvm))
+		return;
+
+	spin_lock(&kvm_vmid_lock);
+
+	/*
+	 * We need to re-check the vmid_gen here to ensure that if another vcpu
+	 * already allocated a valid vmid for this vm, then this vcpu should
+	 * use the same vmid.
+	 */
+	if (!need_new_vmid_gen(kvm)) {
+		spin_unlock(&kvm_vmid_lock);
+		return;
+	}
+
+	/* First user of a new VMID generation? */
+	if (unlikely(kvm_next_vmid == 0)) {
+		atomic64_inc(&kvm_vmid_gen);
+		kvm_next_vmid = 1;
+
+		/*
+		 * On SMP we know no other CPUs can use this CPU's or each
+		 * other's VMID after force_vm_exit returns since the
+		 * kvm_vmid_lock blocks them from reentry to the guest.
+		 */
+		force_vm_exit(cpu_all_mask);
+		/*
+		 * Now broadcast TLB + ICACHE invalidation over the inner
+		 * shareable domain to make sure all data structures are
+		 * clean.
+		 */
+		kvm_call_hyp(__kvm_flush_vm_context);
+	}
+
+	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
+	kvm->arch.vmid = kvm_next_vmid;
+	kvm_next_vmid++;
+	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
+
+	/* update vttbr to be used with the new vmid */
+	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
+	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
+	kvm->arch.vttbr = pgd_phys | vmid;
+
+	spin_unlock(&kvm_vmid_lock);
+}
+
+static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret = 0;
+
+	if (likely(vcpu->arch.has_run_once))
+		return 0;
+
+	vcpu->arch.has_run_once = true;
+
+	/*
+	 * Map the VGIC hardware resources before running a vcpu the first
+	 * time on this VM.
+	 */
+	if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) {
+		ret = kvm_vgic_map_resources(kvm);
+		if (ret)
+			return ret;
+	}
+
+	ret = kvm_timer_enable(vcpu);
+
+	return ret;
+}
+
+bool kvm_arch_intc_initialized(struct kvm *kvm)
+{
+	return vgic_initialized(kvm);
+}
+
+void kvm_arm_halt_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		vcpu->arch.pause = true;
+	kvm_make_all_cpus_request(kvm, KVM_REQ_VCPU_EXIT);
+}
+
+void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pause = true;
+	kvm_vcpu_kick(vcpu);
+}
+
+void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
+	vcpu->arch.pause = false;
+	swake_up(wq);
+}
+
+void kvm_arm_resume_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arm_resume_vcpu(vcpu);
+}
+
+static void vcpu_sleep(struct kvm_vcpu *vcpu)
+{
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
+	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+				       (!vcpu->arch.pause)));
+}
+
+static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.target >= 0;
+}
+
+/**
+ * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
+ * @vcpu:	The VCPU pointer
+ * @run:	The kvm_run structure pointer used for userspace state exchange
+ *
+ * This function is called through the VCPU_RUN ioctl called from user space. It
+ * will execute VM code in a loop until the time slice for the process is used
+ * or some emulation is needed from user space in which case the function will
+ * return with return value 0 and with the kvm_run structure filled in with the
+ * required data for the requested emulation.
+ */
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int ret;
+	sigset_t sigsaved;
+
+	if (unlikely(!kvm_vcpu_initialized(vcpu)))
+		return -ENOEXEC;
+
+	ret = kvm_vcpu_first_run_init(vcpu);
+	if (ret)
+		return ret;
+
+	if (run->exit_reason == KVM_EXIT_MMIO) {
+		ret = kvm_handle_mmio_return(vcpu, vcpu->run);
+		if (ret)
+			return ret;
+	}
+
+	if (run->immediate_exit)
+		return -EINTR;
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	ret = 1;
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	while (ret > 0) {
+		/*
+		 * Check conditions before entering the guest
+		 */
+		cond_resched();
+
+		update_vttbr(vcpu->kvm);
+
+		if (vcpu->arch.power_off || vcpu->arch.pause)
+			vcpu_sleep(vcpu);
+
+		/*
+		 * Preparing the interrupts to be injected also
+		 * involves poking the GIC, which must be done in a
+		 * non-preemptible context.
+		 */
+		preempt_disable();
+
+		kvm_pmu_flush_hwstate(vcpu);
+
+		kvm_timer_flush_hwstate(vcpu);
+		kvm_vgic_flush_hwstate(vcpu);
+
+		local_irq_disable();
+
+		/*
+		 * If we have a singal pending, or need to notify a userspace
+		 * irqchip about timer or PMU level changes, then we exit (and
+		 * update the timer level state in kvm_timer_update_run
+		 * below).
+		 */
+		if (signal_pending(current) ||
+		    kvm_timer_should_notify_user(vcpu) ||
+		    kvm_pmu_should_notify_user(vcpu)) {
+			ret = -EINTR;
+			run->exit_reason = KVM_EXIT_INTR;
+		}
+
+		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
+			vcpu->arch.power_off || vcpu->arch.pause) {
+			local_irq_enable();
+			kvm_pmu_sync_hwstate(vcpu);
+			kvm_timer_sync_hwstate(vcpu);
+			kvm_vgic_sync_hwstate(vcpu);
+			preempt_enable();
+			continue;
+		}
+
+		kvm_arm_setup_debug(vcpu);
+
+		/**************************************************************
+		 * Enter the guest
+		 */
+		trace_kvm_entry(*vcpu_pc(vcpu));
+		guest_enter_irqoff();
+		vcpu->mode = IN_GUEST_MODE;
+
+		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
+
+		vcpu->mode = OUTSIDE_GUEST_MODE;
+		vcpu->stat.exits++;
+		/*
+		 * Back from guest
+		 *************************************************************/
+
+		kvm_arm_clear_debug(vcpu);
+
+		/*
+		 * We may have taken a host interrupt in HYP mode (ie
+		 * while executing the guest). This interrupt is still
+		 * pending, as we haven't serviced it yet!
+		 *
+		 * We're now back in SVC mode, with interrupts
+		 * disabled.  Enabling the interrupts now will have
+		 * the effect of taking the interrupt again, in SVC
+		 * mode this time.
+		 */
+		local_irq_enable();
+
+		/*
+		 * We do local_irq_enable() before calling guest_exit() so
+		 * that if a timer interrupt hits while running the guest we
+		 * account that tick as being spent in the guest.  We enable
+		 * preemption after calling guest_exit() so that if we get
+		 * preempted we make sure ticks after that is not counted as
+		 * guest time.
+		 */
+		guest_exit();
+		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+
+		/*
+		 * We must sync the PMU and timer state before the vgic state so
+		 * that the vgic can properly sample the updated state of the
+		 * interrupt line.
+		 */
+		kvm_pmu_sync_hwstate(vcpu);
+		kvm_timer_sync_hwstate(vcpu);
+
+		kvm_vgic_sync_hwstate(vcpu);
+
+		preempt_enable();
+
+		ret = handle_exit(vcpu, run, ret);
+	}
+
+	/* Tell userspace about in-kernel device output levels */
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
+		kvm_timer_update_run(vcpu);
+		kvm_pmu_update_run(vcpu);
+	}
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	return ret;
+}
+
+static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
+{
+	int bit_index;
+	bool set;
+	unsigned long *ptr;
+
+	if (number == KVM_ARM_IRQ_CPU_IRQ)
+		bit_index = __ffs(HCR_VI);
+	else /* KVM_ARM_IRQ_CPU_FIQ */
+		bit_index = __ffs(HCR_VF);
+
+	ptr = (unsigned long *)&vcpu->arch.irq_lines;
+	if (level)
+		set = test_and_set_bit(bit_index, ptr);
+	else
+		set = test_and_clear_bit(bit_index, ptr);
+
+	/*
+	 * If we didn't change anything, no need to wake up or kick other CPUs
+	 */
+	if (set == level)
+		return 0;
+
+	/*
+	 * The vcpu irq_lines field was updated, wake up sleeping VCPUs and
+	 * trigger a world-switch round on the running physical CPU to set the
+	 * virtual IRQ/FIQ fields in the HCR appropriately.
+	 */
+	kvm_vcpu_kick(vcpu);
+
+	return 0;
+}
+
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
+			  bool line_status)
+{
+	u32 irq = irq_level->irq;
+	unsigned int irq_type, vcpu_idx, irq_num;
+	int nrcpus = atomic_read(&kvm->online_vcpus);
+	struct kvm_vcpu *vcpu = NULL;
+	bool level = irq_level->level;
+
+	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
+	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
+	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;
+
+	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);
+
+	switch (irq_type) {
+	case KVM_ARM_IRQ_TYPE_CPU:
+		if (irqchip_in_kernel(kvm))
+			return -ENXIO;
+
+		if (vcpu_idx >= nrcpus)
+			return -EINVAL;
+
+		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		if (!vcpu)
+			return -EINVAL;
+
+		if (irq_num > KVM_ARM_IRQ_CPU_FIQ)
+			return -EINVAL;
+
+		return vcpu_interrupt_line(vcpu, irq_num, level);
+	case KVM_ARM_IRQ_TYPE_PPI:
+		if (!irqchip_in_kernel(kvm))
+			return -ENXIO;
+
+		if (vcpu_idx >= nrcpus)
+			return -EINVAL;
+
+		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		if (!vcpu)
+			return -EINVAL;
+
+		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
+			return -EINVAL;
+
+		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level);
+	case KVM_ARM_IRQ_TYPE_SPI:
+		if (!irqchip_in_kernel(kvm))
+			return -ENXIO;
+
+		if (irq_num < VGIC_NR_PRIVATE_IRQS)
+			return -EINVAL;
+
+		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
+	}
+
+	return -EINVAL;
+}
+
+static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+			       const struct kvm_vcpu_init *init)
+{
+	unsigned int i;
+	int phys_target = kvm_target_cpu();
+
+	if (init->target != phys_target)
+		return -EINVAL;
+
+	/*
+	 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
+	 * use the same target.
+	 */
+	if (vcpu->arch.target != -1 && vcpu->arch.target != init->target)
+		return -EINVAL;
+
+	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
+	for (i = 0; i < sizeof(init->features) * 8; i++) {
+		bool set = (init->features[i / 32] & (1 << (i % 32)));
+
+		if (set && i >= KVM_VCPU_MAX_FEATURES)
+			return -ENOENT;
+
+		/*
+		 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
+		 * use the same feature set.
+		 */
+		if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES &&
+		    test_bit(i, vcpu->arch.features) != set)
+			return -EINVAL;
+
+		if (set)
+			set_bit(i, vcpu->arch.features);
+	}
+
+	vcpu->arch.target = phys_target;
+
+	/* Now we know what it is, we can reset it. */
+	return kvm_reset_vcpu(vcpu);
+}
+
+
+static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
+					 struct kvm_vcpu_init *init)
+{
+	int ret;
+
+	ret = kvm_vcpu_set_target(vcpu, init);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure a rebooted VM will fault in RAM pages and detect if the
+	 * guest MMU is turned off and flush the caches as needed.
+	 */
+	if (vcpu->arch.has_run_once)
+		stage2_unmap_vm(vcpu->kvm);
+
+	vcpu_reset_hcr(vcpu);
+
+	/*
+	 * Handle the "start in power-off" case.
+	 */
+	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+		vcpu->arch.power_off = true;
+	else
+		vcpu->arch.power_off = false;
+
+	return 0;
+}
+
+static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+			 unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	struct kvm_device_attr attr;
+
+	switch (ioctl) {
+	case KVM_ARM_VCPU_INIT: {
+		struct kvm_vcpu_init init;
+
+		if (copy_from_user(&init, argp, sizeof(init)))
+			return -EFAULT;
+
+		return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
+	}
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			return -EFAULT;
+		if (ioctl == KVM_SET_ONE_REG)
+			return kvm_arm_set_reg(vcpu, &reg);
+		else
+			return kvm_arm_get_reg(vcpu, &reg);
+	}
+	case KVM_GET_REG_LIST: {
+		struct kvm_reg_list __user *user_list = argp;
+		struct kvm_reg_list reg_list;
+		unsigned n;
+
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
+		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
+			return -EFAULT;
+		n = reg_list.n;
+		reg_list.n = kvm_arm_num_regs(vcpu);
+		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
+			return -EFAULT;
+		if (n < reg_list.n)
+			return -E2BIG;
+		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
+	}
+	case KVM_SET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_set_attr(vcpu, &attr);
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_get_attr(vcpu, &attr);
+	}
+	case KVM_HAS_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_has_attr(vcpu, &attr);
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
+ *
+ * Steps 1-4 below provide general overview of dirty page logging. See
+ * kvm_get_dirty_log_protect() function description for additional details.
+ *
+ * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
+ * always flush the TLB (step 4) even if previous step failed  and the dirty
+ * bitmap may be corrupt. Regardless of previous outcome the KVM logging API
+ * does not preclude user space subsequent dirty log read. Flushing TLB ensures
+ * writes will be marked dirty for next log read.
+ *
+ *   1. Take a snapshot of the bit and clear it if needed.
+ *   2. Write protect the corresponding page.
+ *   3. Copy the snapshot to the userspace.
+ *   4. Flush TLB's if needed.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	bool is_dirty = false;
+	int r;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log_protect(kvm, log, &is_dirty);
+
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
+
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
+					struct kvm_arm_device_addr *dev_addr)
+{
+	unsigned long dev_id, type;
+
+	dev_id = (dev_addr->id & KVM_ARM_DEVICE_ID_MASK) >>
+		KVM_ARM_DEVICE_ID_SHIFT;
+	type = (dev_addr->id & KVM_ARM_DEVICE_TYPE_MASK) >>
+		KVM_ARM_DEVICE_TYPE_SHIFT;
+
+	switch (dev_id) {
+	case KVM_ARM_DEVICE_VGIC_V2:
+		if (!vgic_present)
+			return -ENXIO;
+		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
+	default:
+		return -ENODEV;
+	}
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+		       unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	void __user *argp = (void __user *)arg;
+
+	switch (ioctl) {
+	case KVM_CREATE_IRQCHIP: {
+		int ret;
+		if (!vgic_present)
+			return -ENXIO;
+		mutex_lock(&kvm->lock);
+		ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_unlock(&kvm->lock);
+		return ret;
+	}
+	case KVM_ARM_SET_DEVICE_ADDR: {
+		struct kvm_arm_device_addr dev_addr;
+
+		if (copy_from_user(&dev_addr, argp, sizeof(dev_addr)))
+			return -EFAULT;
+		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
+	}
+	case KVM_ARM_PREFERRED_TARGET: {
+		int err;
+		struct kvm_vcpu_init init;
+
+		err = kvm_vcpu_preferred_target(&init);
+		if (err)
+			return err;
+
+		if (copy_to_user(argp, &init, sizeof(init)))
+			return -EFAULT;
+
+		return 0;
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+static void cpu_init_hyp_mode(void *dummy)
+{
+	phys_addr_t pgd_ptr;
+	unsigned long hyp_stack_ptr;
+	unsigned long stack_page;
+	unsigned long vector_ptr;
+
+	/* Switch from the HYP stub to our own HYP init vector */
+	__hyp_set_vectors(kvm_get_idmap_vector());
+
+	pgd_ptr = kvm_mmu_get_httbr();
+	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
+	hyp_stack_ptr = stack_page + PAGE_SIZE;
+	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
+
+	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_stage2();
+
+	if (is_kernel_in_hyp_mode())
+		kvm_timer_init_vhe();
+
+	kvm_arm_init_debug();
+}
+
+static void cpu_hyp_reset(void)
+{
+	if (!is_kernel_in_hyp_mode())
+		__hyp_reset_vectors();
+}
+
+static void cpu_hyp_reinit(void)
+{
+	cpu_hyp_reset();
+
+	if (is_kernel_in_hyp_mode()) {
+		/*
+		 * __cpu_init_stage2() is safe to call even if the PM
+		 * event was cancelled before the CPU was reset.
+		 */
+		__cpu_init_stage2();
+	} else {
+		cpu_init_hyp_mode(NULL);
+	}
+
+	if (vgic_present)
+		kvm_vgic_init_cpu_hardware();
+}
+
+static void _kvm_arch_hardware_enable(void *discard)
+{
+	if (!__this_cpu_read(kvm_arm_hardware_enabled)) {
+		cpu_hyp_reinit();
+		__this_cpu_write(kvm_arm_hardware_enabled, 1);
+	}
+}
+
+int kvm_arch_hardware_enable(void)
+{
+	_kvm_arch_hardware_enable(NULL);
+	return 0;
+}
+
+static void _kvm_arch_hardware_disable(void *discard)
+{
+	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
+		cpu_hyp_reset();
+		__this_cpu_write(kvm_arm_hardware_enabled, 0);
+	}
+}
+
+void kvm_arch_hardware_disable(void)
+{
+	_kvm_arch_hardware_disable(NULL);
+}
+
+#ifdef CONFIG_CPU_PM
+static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
+				    unsigned long cmd,
+				    void *v)
+{
+	/*
+	 * kvm_arm_hardware_enabled is left with its old value over
+	 * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should
+	 * re-enable hyp.
+	 */
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		if (__this_cpu_read(kvm_arm_hardware_enabled))
+			/*
+			 * don't update kvm_arm_hardware_enabled here
+			 * so that the hardware will be re-enabled
+			 * when we resume. See below.
+			 */
+			cpu_hyp_reset();
+
+		return NOTIFY_OK;
+	case CPU_PM_EXIT:
+		if (__this_cpu_read(kvm_arm_hardware_enabled))
+			/* The hardware was enabled before suspend. */
+			cpu_hyp_reinit();
+
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block hyp_init_cpu_pm_nb = {
+	.notifier_call = hyp_init_cpu_pm_notifier,
+};
+
+static void __init hyp_cpu_pm_init(void)
+{
+	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
+}
+static void __init hyp_cpu_pm_exit(void)
+{
+	cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
+}
+#else
+static inline void hyp_cpu_pm_init(void)
+{
+}
+static inline void hyp_cpu_pm_exit(void)
+{
+}
+#endif
+
+static void teardown_common_resources(void)
+{
+	free_percpu(kvm_host_cpu_state);
+}
+
+static int init_common_resources(void)
+{
+	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+	if (!kvm_host_cpu_state) {
+		kvm_err("Cannot allocate host CPU state\n");
+		return -ENOMEM;
+	}
+
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
+	return 0;
+}
+
+static int init_subsystems(void)
+{
+	int err = 0;
+
+	/*
+	 * Enable hardware so that subsystem initialisation can access EL2.
+	 */
+	on_each_cpu(_kvm_arch_hardware_enable, NULL, 1);
+
+	/*
+	 * Register CPU lower-power notifier
+	 */
+	hyp_cpu_pm_init();
+
+	/*
+	 * Init HYP view of VGIC
+	 */
+	err = kvm_vgic_hyp_init();
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		err = 0;
+		break;
+	default:
+		goto out;
+	}
+
+	/*
+	 * Init HYP architected timer support
+	 */
+	err = kvm_timer_hyp_init();
+	if (err)
+		goto out;
+
+	kvm_perf_init();
+	kvm_coproc_table_init();
+
+out:
+	on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
+
+	return err;
+}
+
+static void teardown_hyp_mode(void)
+{
+	int cpu;
+
+	if (is_kernel_in_hyp_mode())
+		return;
+
+	free_hyp_pgds();
+	for_each_possible_cpu(cpu)
+		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+	hyp_cpu_pm_exit();
+}
+
+static int init_vhe_mode(void)
+{
+	kvm_info("VHE mode initialized successfully\n");
+	return 0;
+}
+
+/**
+ * Inits Hyp-mode on all online CPUs
+ */
+static int init_hyp_mode(void)
+{
+	int cpu;
+	int err = 0;
+
+	/*
+	 * Allocate Hyp PGD and setup Hyp identity mapping
+	 */
+	err = kvm_mmu_init();
+	if (err)
+		goto out_err;
+
+	/*
+	 * Allocate stack pages for Hypervisor-mode
+	 */
+	for_each_possible_cpu(cpu) {
+		unsigned long stack_page;
+
+		stack_page = __get_free_page(GFP_KERNEL);
+		if (!stack_page) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
+	}
+
+	/*
+	 * Map the Hyp-code called directly from the host
+	 */
+	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
+				  kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
+	if (err) {
+		kvm_err("Cannot map world-switch code\n");
+		goto out_err;
+	}
+
+	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
+				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
+	if (err) {
+		kvm_err("Cannot map rodata section\n");
+		goto out_err;
+	}
+
+	err = create_hyp_mappings(kvm_ksym_ref(__bss_start),
+				  kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+	if (err) {
+		kvm_err("Cannot map bss section\n");
+		goto out_err;
+	}
+
+	/*
+	 * Map the Hyp stack pages
+	 */
+	for_each_possible_cpu(cpu) {
+		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
+		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
+					  PAGE_HYP);
+
+		if (err) {
+			kvm_err("Cannot map hyp stack\n");
+			goto out_err;
+		}
+	}
+
+	for_each_possible_cpu(cpu) {
+		kvm_cpu_context_t *cpu_ctxt;
+
+		cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
+		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
+
+		if (err) {
+			kvm_err("Cannot map host CPU state: %d\n", err);
+			goto out_err;
+		}
+	}
+
+	kvm_info("Hyp mode initialized successfully\n");
+
+	return 0;
+
+out_err:
+	teardown_hyp_mode();
+	kvm_err("error initializing Hyp mode: %d\n", err);
+	return err;
+}
+
+static void check_kvm_target_cpu(void *ret)
+{
+	*(int *)ret = kvm_target_cpu();
+}
+
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	mpidr &= MPIDR_HWID_BITMASK;
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
+			return vcpu;
+	}
+	return NULL;
+}
+
+/**
+ * Initialize Hyp-mode and memory mappings on all CPUs.
+ */
+int kvm_arch_init(void *opaque)
+{
+	int err;
+	int ret, cpu;
+
+	if (!is_hyp_mode_available()) {
+		kvm_err("HYP mode not available\n");
+		return -ENODEV;
+	}
+
+	for_each_online_cpu(cpu) {
+		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
+		if (ret < 0) {
+			kvm_err("Error, CPU %d not supported!\n", cpu);
+			return -ENODEV;
+		}
+	}
+
+	err = init_common_resources();
+	if (err)
+		return err;
+
+	if (is_kernel_in_hyp_mode())
+		err = init_vhe_mode();
+	else
+		err = init_hyp_mode();
+	if (err)
+		goto out_err;
+
+	err = init_subsystems();
+	if (err)
+		goto out_hyp;
+
+	return 0;
+
+out_hyp:
+	teardown_hyp_mode();
+out_err:
+	teardown_common_resources();
+	return err;
+}
+
+/* NOP: Compiling as a module not supported */
+void kvm_arch_exit(void)
+{
+	kvm_perf_teardown();
+}
+
+static int arm_init(void)
+{
+	int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	return rc;
+}
+
+module_init(arm_init);
diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c
new file mode 100644
index 000000000000..b6e715fd3c90
--- /dev/null
+++ b/virt/kvm/arm/mmio.c
@@ -0,0 +1,217 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmio.h>
+#include <asm/kvm_emulate.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data)
+{
+	void *datap = NULL;
+	union {
+		u8	byte;
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		tmp.byte	= data;
+		datap		= &tmp.byte;
+		break;
+	case 2:
+		tmp.hword	= data;
+		datap		= &tmp.hword;
+		break;
+	case 4:
+		tmp.word	= data;
+		datap		= &tmp.word;
+		break;
+	case 8:
+		tmp.dword	= data;
+		datap		= &tmp.dword;
+		break;
+	}
+
+	memcpy(buf, datap, len);
+}
+
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len)
+{
+	unsigned long data = 0;
+	union {
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		data = *(u8 *)buf;
+		break;
+	case 2:
+		memcpy(&tmp.hword, buf, len);
+		data = tmp.hword;
+		break;
+	case 4:
+		memcpy(&tmp.word, buf, len);
+		data = tmp.word;
+		break;
+	case 8:
+		memcpy(&tmp.dword, buf, len);
+		data = tmp.dword;
+		break;
+	}
+
+	return data;
+}
+
+/**
+ * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
+ *			     or in-kernel IO emulation
+ *
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ */
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	unsigned long data;
+	unsigned int len;
+	int mask;
+
+	if (!run->mmio.is_write) {
+		len = run->mmio.len;
+		if (len > sizeof(unsigned long))
+			return -EINVAL;
+
+		data = kvm_mmio_read_buf(run->mmio.data, len);
+
+		if (vcpu->arch.mmio_decode.sign_extend &&
+		    len < sizeof(unsigned long)) {
+			mask = 1U << ((len * 8) - 1);
+			data = (data ^ mask) - mask;
+		}
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+			       data);
+		data = vcpu_data_host_to_guest(vcpu, data, len);
+		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
+	}
+
+	return 0;
+}
+
+static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
+{
+	unsigned long rt;
+	int access_size;
+	bool sign_extend;
+
+	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		/* page table accesses IO mem: tell guest to fix its TTBR */
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		return 1;
+	}
+
+	access_size = kvm_vcpu_dabt_get_as(vcpu);
+	if (unlikely(access_size < 0))
+		return access_size;
+
+	*is_write = kvm_vcpu_dabt_iswrite(vcpu);
+	sign_extend = kvm_vcpu_dabt_issext(vcpu);
+	rt = kvm_vcpu_dabt_get_rd(vcpu);
+
+	*len = access_size;
+	vcpu->arch.mmio_decode.sign_extend = sign_extend;
+	vcpu->arch.mmio_decode.rt = rt;
+
+	/*
+	 * The MMIO instruction is emulated and should not be re-executed
+	 * in the guest.
+	 */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 0;
+}
+
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa)
+{
+	unsigned long data;
+	unsigned long rt;
+	int ret;
+	bool is_write;
+	int len;
+	u8 data_buf[8];
+
+	/*
+	 * Prepare MMIO operation. First decode the syndrome data we get
+	 * from the CPU. Then try if some in-kernel emulation feels
+	 * responsible, otherwise let user space do its magic.
+	 */
+	if (kvm_vcpu_dabt_isvalid(vcpu)) {
+		ret = decode_hsr(vcpu, &is_write, &len);
+		if (ret)
+			return ret;
+	} else {
+		kvm_err("load/store instruction decoding not implemented\n");
+		return -ENOSYS;
+	}
+
+	rt = vcpu->arch.mmio_decode.rt;
+
+	if (is_write) {
+		data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
+					       len);
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
+		kvm_mmio_write_buf(data_buf, len, data);
+
+		ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len,
+				       data_buf);
+	} else {
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len,
+			       fault_ipa, 0);
+
+		ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len,
+				      data_buf);
+	}
+
+	/* Now prepare kvm_run for the potential return to userland. */
+	run->mmio.is_write	= is_write;
+	run->mmio.phys_addr	= fault_ipa;
+	run->mmio.len		= len;
+
+	if (!ret) {
+		/* We handled the access successfully in the kernel. */
+		if (!is_write)
+			memcpy(run->mmio.data, data_buf, len);
+		vcpu->stat.mmio_exit_kernel++;
+		kvm_handle_mmio_return(vcpu, run);
+		return 1;
+	}
+
+	if (is_write)
+		memcpy(run->mmio.data, data_buf, len);
+	vcpu->stat.mmio_exit_user++;
+	run->exit_reason	= KVM_EXIT_MMIO;
+	return 0;
+}
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
new file mode 100644
index 000000000000..313ee646480f
--- /dev/null
+++ b/virt/kvm/arm/mmu.c
@@ -0,0 +1,1975 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/mman.h>
+#include <linux/kvm_host.h>
+#include <linux/io.h>
+#include <linux/hugetlb.h>
+#include <trace/events/kvm.h>
+#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_mmio.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/virt.h>
+
+#include "trace.h"
+
+static pgd_t *boot_hyp_pgd;
+static pgd_t *hyp_pgd;
+static pgd_t *merged_hyp_pgd;
+static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
+
+static unsigned long hyp_idmap_start;
+static unsigned long hyp_idmap_end;
+static phys_addr_t hyp_idmap_vector;
+
+#define S2_PGD_SIZE	(PTRS_PER_S2_PGD * sizeof(pgd_t))
+#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
+#define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
+#define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)
+
+static bool memslot_is_logging(struct kvm_memory_slot *memslot)
+{
+	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
+}
+
+/**
+ * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8
+ * @kvm:	pointer to kvm structure.
+ *
+ * Interface to HYP function to flush all VM TLB entries
+ */
+void kvm_flush_remote_tlbs(struct kvm *kvm)
+{
+	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+}
+
+static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+}
+
+/*
+ * D-Cache management functions. They take the page table entries by
+ * value, as they are flushing the cache using the kernel mapping (or
+ * kmap on 32bit).
+ */
+static void kvm_flush_dcache_pte(pte_t pte)
+{
+	__kvm_flush_dcache_pte(pte);
+}
+
+static void kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	__kvm_flush_dcache_pmd(pmd);
+}
+
+static void kvm_flush_dcache_pud(pud_t pud)
+{
+	__kvm_flush_dcache_pud(pud);
+}
+
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
+/**
+ * stage2_dissolve_pmd() - clear and flush huge PMD entry
+ * @kvm:	pointer to kvm structure.
+ * @addr:	IPA
+ * @pmd:	pmd pointer for IPA
+ *
+ * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all
+ * pages in the range dirty.
+ */
+static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+{
+	if (!pmd_thp_or_huge(*pmd))
+		return;
+
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	put_page(virt_to_page(pmd));
+}
+
+static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
+				  int min, int max)
+{
+	void *page;
+
+	BUG_ON(max > KVM_NR_MEM_OBJS);
+	if (cache->nobjs >= min)
+		return 0;
+	while (cache->nobjs < max) {
+		page = (void *)__get_free_page(PGALLOC_GFP);
+		if (!page)
+			return -ENOMEM;
+		cache->objects[cache->nobjs++] = page;
+	}
+	return 0;
+}
+
+static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
+{
+	while (mc->nobjs)
+		free_page((unsigned long)mc->objects[--mc->nobjs]);
+}
+
+static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
+{
+	void *p;
+
+	BUG_ON(!mc || !mc->nobjs);
+	p = mc->objects[--mc->nobjs];
+	return p;
+}
+
+static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+{
+	pud_t *pud_table __maybe_unused = stage2_pud_offset(pgd, 0UL);
+	stage2_pgd_clear(pgd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	stage2_pud_free(pud_table);
+	put_page(virt_to_page(pgd));
+}
+
+static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+{
+	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(pud, 0);
+	VM_BUG_ON(stage2_pud_huge(*pud));
+	stage2_pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	stage2_pmd_free(pmd_table);
+	put_page(virt_to_page(pud));
+}
+
+static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+{
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(pmd_thp_or_huge(*pmd));
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pte_free_kernel(NULL, pte_table);
+	put_page(virt_to_page(pmd));
+}
+
+/*
+ * Unmapping vs dcache management:
+ *
+ * If a guest maps certain memory pages as uncached, all writes will
+ * bypass the data cache and go directly to RAM.  However, the CPUs
+ * can still speculate reads (not writes) and fill cache lines with
+ * data.
+ *
+ * Those cache lines will be *clean* cache lines though, so a
+ * clean+invalidate operation is equivalent to an invalidate
+ * operation, because no cache lines are marked dirty.
+ *
+ * Those clean cache lines could be filled prior to an uncached write
+ * by the guest, and the cache coherent IO subsystem would therefore
+ * end up writing old data to disk.
+ *
+ * This is why right after unmapping a page/section and invalidating
+ * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
+ * the IO subsystem will never hit in the cache.
+ */
+static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t start_addr = addr;
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			pte_t old_pte = *pte;
+
+			kvm_set_pte(pte, __pte(0));
+			kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+			/* No need to invalidate the cache for device mappings */
+			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
+				kvm_flush_dcache_pte(old_pte);
+
+			put_page(virt_to_page(pte));
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (stage2_pte_table_empty(start_pte))
+		clear_stage2_pmd_entry(kvm, pmd, start_addr);
+}
+
+static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pmd_t *pmd, *start_pmd;
+
+	start_pmd = pmd = stage2_pmd_offset(pud, addr);
+	do {
+		next = stage2_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (pmd_thp_or_huge(*pmd)) {
+				pmd_t old_pmd = *pmd;
+
+				pmd_clear(pmd);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+				kvm_flush_dcache_pmd(old_pmd);
+
+				put_page(virt_to_page(pmd));
+			} else {
+				unmap_stage2_ptes(kvm, pmd, addr, next);
+			}
+		}
+	} while (pmd++, addr = next, addr != end);
+
+	if (stage2_pmd_table_empty(start_pmd))
+		clear_stage2_pud_entry(kvm, pud, start_addr);
+}
+
+static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pud_t *pud, *start_pud;
+
+	start_pud = pud = stage2_pud_offset(pgd, addr);
+	do {
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
+			if (stage2_pud_huge(*pud)) {
+				pud_t old_pud = *pud;
+
+				stage2_pud_clear(pud);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_flush_dcache_pud(old_pud);
+				put_page(virt_to_page(pud));
+			} else {
+				unmap_stage2_pmds(kvm, pud, addr, next);
+			}
+		}
+	} while (pud++, addr = next, addr != end);
+
+	if (stage2_pud_table_empty(start_pud))
+		clear_stage2_pgd_entry(kvm, pgd, start_addr);
+}
+
+/**
+ * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * @kvm:   The VM pointer
+ * @start: The intermediate physical base address of the range to unmap
+ * @size:  The size of the area to unmap
+ *
+ * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
+ * be called while holding mmu_lock (unless for freeing the stage2 pgd before
+ * destroying the VM), otherwise another faulting VCPU may come in and mess
+ * with things behind our backs.
+ */
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+{
+	pgd_t *pgd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	assert_spin_locked(&kvm->mmu_lock);
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+	do {
+		next = stage2_pgd_addr_end(addr, end);
+		if (!stage2_pgd_none(*pgd))
+			unmap_stage2_puds(kvm, pgd, addr, next);
+		/*
+		 * If the range is too large, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector warnings.
+		 */
+		if (next != end)
+			cond_resched_lock(&kvm->mmu_lock);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
+			kvm_flush_dcache_pte(*pte);
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = stage2_pmd_offset(pud, addr);
+	do {
+		next = stage2_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (pmd_thp_or_huge(*pmd))
+				kvm_flush_dcache_pmd(*pmd);
+			else
+				stage2_flush_ptes(kvm, pmd, addr, next);
+		}
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = stage2_pud_offset(pgd, addr);
+	do {
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
+			if (stage2_pud_huge(*pud))
+				kvm_flush_dcache_pud(*pud);
+			else
+				stage2_flush_pmds(kvm, pud, addr, next);
+		}
+	} while (pud++, addr = next, addr != end);
+}
+
+static void stage2_flush_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	phys_addr_t next;
+	pgd_t *pgd;
+
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+	do {
+		next = stage2_pgd_addr_end(addr, end);
+		stage2_flush_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+static void stage2_flush_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_flush_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
+static void clear_hyp_pgd_entry(pgd_t *pgd)
+{
+	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0UL);
+	pgd_clear(pgd);
+	pud_free(NULL, pud_table);
+	put_page(virt_to_page(pgd));
+}
+
+static void clear_hyp_pud_entry(pud_t *pud)
+{
+	pmd_t *pmd_table __maybe_unused = pmd_offset(pud, 0);
+	VM_BUG_ON(pud_huge(*pud));
+	pud_clear(pud);
+	pmd_free(NULL, pmd_table);
+	put_page(virt_to_page(pud));
+}
+
+static void clear_hyp_pmd_entry(pmd_t *pmd)
+{
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(pmd_thp_or_huge(*pmd));
+	pmd_clear(pmd);
+	pte_free_kernel(NULL, pte_table);
+	put_page(virt_to_page(pmd));
+}
+
+static void unmap_hyp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			kvm_set_pte(pte, __pte(0));
+			put_page(virt_to_page(pte));
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (hyp_pte_table_empty(start_pte))
+		clear_hyp_pmd_entry(pmd);
+}
+
+static void unmap_hyp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next;
+	pmd_t *pmd, *start_pmd;
+
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		/* Hyp doesn't use huge pmds */
+		if (!pmd_none(*pmd))
+			unmap_hyp_ptes(pmd, addr, next);
+	} while (pmd++, addr = next, addr != end);
+
+	if (hyp_pmd_table_empty(start_pmd))
+		clear_hyp_pud_entry(pud);
+}
+
+static void unmap_hyp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next;
+	pud_t *pud, *start_pud;
+
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		/* Hyp doesn't use huge puds */
+		if (!pud_none(*pud))
+			unmap_hyp_pmds(pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+
+	if (hyp_pud_table_empty(start_pud))
+		clear_hyp_pgd_entry(pgd);
+}
+
+static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
+{
+	pgd_t *pgd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	/*
+	 * We don't unmap anything from HYP, except at the hyp tear down.
+	 * Hence, we don't have to invalidate the TLBs here.
+	 */
+	pgd = pgdp + pgd_index(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (!pgd_none(*pgd))
+			unmap_hyp_puds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * free_hyp_pgds - free Hyp-mode page tables
+ *
+ * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
+ * therefore contains either mappings in the kernel memory area (above
+ * PAGE_OFFSET), or device mappings in the vmalloc range (from
+ * VMALLOC_START to VMALLOC_END).
+ *
+ * boot_hyp_pgd should only map two pages for the init code.
+ */
+void free_hyp_pgds(void)
+{
+	unsigned long addr;
+
+	mutex_lock(&kvm_hyp_pgd_mutex);
+
+	if (boot_hyp_pgd) {
+		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
+		boot_hyp_pgd = NULL;
+	}
+
+	if (hyp_pgd) {
+		unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
+		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
+
+		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
+		hyp_pgd = NULL;
+	}
+	if (merged_hyp_pgd) {
+		clear_page(merged_hyp_pgd);
+		free_page((unsigned long)merged_hyp_pgd);
+		merged_hyp_pgd = NULL;
+	}
+
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+}
+
+static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
+				    unsigned long end, unsigned long pfn,
+				    pgprot_t prot)
+{
+	pte_t *pte;
+	unsigned long addr;
+
+	addr = start;
+	do {
+		pte = pte_offset_kernel(pmd, addr);
+		kvm_set_pte(pte, pfn_pte(pfn, prot));
+		get_page(virt_to_page(pte));
+		kvm_flush_dcache_to_poc(pte, sizeof(*pte));
+		pfn++;
+	} while (addr += PAGE_SIZE, addr != end);
+}
+
+static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
+				   unsigned long end, unsigned long pfn,
+				   pgprot_t prot)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long addr, next;
+
+	addr = start;
+	do {
+		pmd = pmd_offset(pud, addr);
+
+		BUG_ON(pmd_sect(*pmd));
+
+		if (pmd_none(*pmd)) {
+			pte = pte_alloc_one_kernel(NULL, addr);
+			if (!pte) {
+				kvm_err("Cannot allocate Hyp pte\n");
+				return -ENOMEM;
+			}
+			pmd_populate_kernel(NULL, pmd, pte);
+			get_page(virt_to_page(pmd));
+			kvm_flush_dcache_to_poc(pmd, sizeof(*pmd));
+		}
+
+		next = pmd_addr_end(addr, end);
+
+		create_hyp_pte_mappings(pmd, addr, next, pfn, prot);
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
+static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
+				   unsigned long end, unsigned long pfn,
+				   pgprot_t prot)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr, next;
+	int ret;
+
+	addr = start;
+	do {
+		pud = pud_offset(pgd, addr);
+
+		if (pud_none_or_clear_bad(pud)) {
+			pmd = pmd_alloc_one(NULL, addr);
+			if (!pmd) {
+				kvm_err("Cannot allocate Hyp pmd\n");
+				return -ENOMEM;
+			}
+			pud_populate(NULL, pud, pmd);
+			get_page(virt_to_page(pud));
+			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+		}
+
+		next = pud_addr_end(addr, end);
+		ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		if (ret)
+			return ret;
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
+static int __create_hyp_mappings(pgd_t *pgdp,
+				 unsigned long start, unsigned long end,
+				 unsigned long pfn, pgprot_t prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	unsigned long addr, next;
+	int err = 0;
+
+	mutex_lock(&kvm_hyp_pgd_mutex);
+	addr = start & PAGE_MASK;
+	end = PAGE_ALIGN(end);
+	do {
+		pgd = pgdp + pgd_index(addr);
+
+		if (pgd_none(*pgd)) {
+			pud = pud_alloc_one(NULL, addr);
+			if (!pud) {
+				kvm_err("Cannot allocate Hyp pud\n");
+				err = -ENOMEM;
+				goto out;
+			}
+			pgd_populate(NULL, pgd, pud);
+			get_page(virt_to_page(pgd));
+			kvm_flush_dcache_to_poc(pgd, sizeof(*pgd));
+		}
+
+		next = pgd_addr_end(addr, end);
+		err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot);
+		if (err)
+			goto out;
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+out:
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+	return err;
+}
+
+static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
+{
+	if (!is_vmalloc_addr(kaddr)) {
+		BUG_ON(!virt_addr_valid(kaddr));
+		return __pa(kaddr);
+	} else {
+		return page_to_phys(vmalloc_to_page(kaddr)) +
+		       offset_in_page(kaddr);
+	}
+}
+
+/**
+ * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
+ * @from:	The virtual kernel start address of the range
+ * @to:		The virtual kernel end address of the range (exclusive)
+ * @prot:	The protection to be applied to this range
+ *
+ * The same virtual address as the kernel virtual address is also used
+ * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
+ * physical pages.
+ */
+int create_hyp_mappings(void *from, void *to, pgprot_t prot)
+{
+	phys_addr_t phys_addr;
+	unsigned long virt_addr;
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
+
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
+	start = start & PAGE_MASK;
+	end = PAGE_ALIGN(end);
+
+	for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+		int err;
+
+		phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
+		err = __create_hyp_mappings(hyp_pgd, virt_addr,
+					    virt_addr + PAGE_SIZE,
+					    __phys_to_pfn(phys_addr),
+					    prot);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode
+ * @from:	The kernel start VA of the range
+ * @to:		The kernel end VA of the range (exclusive)
+ * @phys_addr:	The physical start address which gets mapped
+ *
+ * The resulting HYP VA is the same as the kernel VA, modulo
+ * HYP_PAGE_OFFSET.
+ */
+int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
+{
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
+
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
+	/* Check for a valid kernel IO mapping */
+	if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
+		return -EINVAL;
+
+	return __create_hyp_mappings(hyp_pgd, start, end,
+				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
+}
+
+/**
+ * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
+ * @kvm:	The KVM struct pointer for the VM.
+ *
+ * Allocates only the stage-2 HW PGD level table(s) (can support either full
+ * 40-bit input addresses or limited to 32-bit input addresses). Clears the
+ * allocated pages.
+ *
+ * Note we don't need locking here as this is only called when the VM is
+ * created, which can only be done once.
+ */
+int kvm_alloc_stage2_pgd(struct kvm *kvm)
+{
+	pgd_t *pgd;
+
+	if (kvm->arch.pgd != NULL) {
+		kvm_err("kvm_arch already initialized?\n");
+		return -EINVAL;
+	}
+
+	/* Allocate the HW PGD, making sure that each page gets its own refcount */
+	pgd = alloc_pages_exact(S2_PGD_SIZE, GFP_KERNEL | __GFP_ZERO);
+	if (!pgd)
+		return -ENOMEM;
+
+	kvm->arch.pgd = pgd;
+	return 0;
+}
+
+static void stage2_unmap_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	hva_t hva = memslot->userspace_addr;
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = PAGE_SIZE * memslot->npages;
+	hva_t reg_end = hva + size;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we should
+	 * unmap any of them.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (!(vma->vm_flags & VM_PFNMAP)) {
+			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+}
+
+/**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+void stage2_unmap_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	down_read(&current->mm->mmap_sem);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_unmap_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	up_read(&current->mm->mmap_sem);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
+/**
+ * kvm_free_stage2_pgd - free all stage-2 tables
+ * @kvm:	The KVM struct pointer for the VM.
+ *
+ * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
+ * underlying level-2 and level-3 tables before freeing the actual level-1 table
+ * and setting the struct pointer to NULL.
+ *
+ * Note we don't need locking here as this is only called when the VM is
+ * destroyed, which can only be done once.
+ */
+void kvm_free_stage2_pgd(struct kvm *kvm)
+{
+	if (kvm->arch.pgd == NULL)
+		return;
+
+	spin_lock(&kvm->mmu_lock);
+	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	spin_unlock(&kvm->mmu_lock);
+
+	/* Free the HW pgd, one page at a time */
+	free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
+	kvm->arch.pgd = NULL;
+}
+
+static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			     phys_addr_t addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+	if (WARN_ON(stage2_pgd_none(*pgd))) {
+		if (!cache)
+			return NULL;
+		pud = mmu_memory_cache_alloc(cache);
+		stage2_pgd_populate(pgd, pud);
+		get_page(virt_to_page(pgd));
+	}
+
+	return stage2_pud_offset(pgd, addr);
+}
+
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			     phys_addr_t addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = stage2_get_pud(kvm, cache, addr);
+	if (stage2_pud_none(*pud)) {
+		if (!cache)
+			return NULL;
+		pmd = mmu_memory_cache_alloc(cache);
+		stage2_pud_populate(pud, pmd);
+		get_page(virt_to_page(pud));
+	}
+
+	return stage2_pmd_offset(pud, addr);
+}
+
+static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
+			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
+{
+	pmd_t *pmd, old_pmd;
+
+	pmd = stage2_get_pmd(kvm, cache, addr);
+	VM_BUG_ON(!pmd);
+
+	/*
+	 * Mapping in huge pages should only happen through a fault.  If a
+	 * page is merged into a transparent huge page, the individual
+	 * subpages of that huge page should be unmapped through MMU
+	 * notifiers before we get here.
+	 *
+	 * Merging of CompoundPages is not supported; they should become
+	 * splitting first, unmapped, merged, and mapped back in on-demand.
+	 */
+	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
+
+	old_pmd = *pmd;
+	if (pmd_present(old_pmd)) {
+		pmd_clear(pmd);
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	} else {
+		get_page(virt_to_page(pmd));
+	}
+
+	kvm_set_pmd(pmd, *new_pmd);
+	return 0;
+}
+
+static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			  phys_addr_t addr, const pte_t *new_pte,
+			  unsigned long flags)
+{
+	pmd_t *pmd;
+	pte_t *pte, old_pte;
+	bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
+	bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE;
+
+	VM_BUG_ON(logging_active && !cache);
+
+	/* Create stage-2 page table mapping - Levels 0 and 1 */
+	pmd = stage2_get_pmd(kvm, cache, addr);
+	if (!pmd) {
+		/*
+		 * Ignore calls from kvm_set_spte_hva for unallocated
+		 * address ranges.
+		 */
+		return 0;
+	}
+
+	/*
+	 * While dirty page logging - dissolve huge PMD, then continue on to
+	 * allocate page.
+	 */
+	if (logging_active)
+		stage2_dissolve_pmd(kvm, addr, pmd);
+
+	/* Create stage-2 page mappings - Level 2 */
+	if (pmd_none(*pmd)) {
+		if (!cache)
+			return 0; /* ignore calls from kvm_set_spte_hva */
+		pte = mmu_memory_cache_alloc(cache);
+		pmd_populate_kernel(NULL, pmd, pte);
+		get_page(virt_to_page(pmd));
+	}
+
+	pte = pte_offset_kernel(pmd, addr);
+
+	if (iomap && pte_present(*pte))
+		return -EFAULT;
+
+	/* Create 2nd stage page table mapping - Level 3 */
+	old_pte = *pte;
+	if (pte_present(old_pte)) {
+		kvm_set_pte(pte, __pte(0));
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	} else {
+		get_page(virt_to_page(pte));
+	}
+
+	kvm_set_pte(pte, *new_pte);
+	return 0;
+}
+
+#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static int stage2_ptep_test_and_clear_young(pte_t *pte)
+{
+	if (pte_young(*pte)) {
+		*pte = pte_mkold(*pte);
+		return 1;
+	}
+	return 0;
+}
+#else
+static int stage2_ptep_test_and_clear_young(pte_t *pte)
+{
+	return __ptep_test_and_clear_young(pte);
+}
+#endif
+
+static int stage2_pmdp_test_and_clear_young(pmd_t *pmd)
+{
+	return stage2_ptep_test_and_clear_young((pte_t *)pmd);
+}
+
+/**
+ * kvm_phys_addr_ioremap - map a device range to guest IPA
+ *
+ * @kvm:	The KVM pointer
+ * @guest_ipa:	The IPA at which to insert the mapping
+ * @pa:		The physical address of the device
+ * @size:	The size of the mapping
+ */
+int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
+			  phys_addr_t pa, unsigned long size, bool writable)
+{
+	phys_addr_t addr, end;
+	int ret = 0;
+	unsigned long pfn;
+	struct kvm_mmu_memory_cache cache = { 0, };
+
+	end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK;
+	pfn = __phys_to_pfn(pa);
+
+	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
+		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
+
+		if (writable)
+			pte = kvm_s2pte_mkwrite(pte);
+
+		ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
+						KVM_NR_MEM_OBJS);
+		if (ret)
+			goto out;
+		spin_lock(&kvm->mmu_lock);
+		ret = stage2_set_pte(kvm, &cache, addr, &pte,
+						KVM_S2PTE_FLAG_IS_IOMAP);
+		spin_unlock(&kvm->mmu_lock);
+		if (ret)
+			goto out;
+
+		pfn++;
+	}
+
+out:
+	mmu_free_memory_cache(&cache);
+	return ret;
+}
+
+static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
+{
+	kvm_pfn_t pfn = *pfnp;
+	gfn_t gfn = *ipap >> PAGE_SHIFT;
+
+	if (PageTransCompoundMap(pfn_to_page(pfn))) {
+		unsigned long mask;
+		/*
+		 * The address we faulted on is backed by a transparent huge
+		 * page.  However, because we map the compound huge page and
+		 * not the individual tail page, we need to transfer the
+		 * refcount to the head page.  We have to be careful that the
+		 * THP doesn't start to split while we are adjusting the
+		 * refcounts.
+		 *
+		 * We are sure this doesn't happen, because mmu_notifier_retry
+		 * was successful and we are holding the mmu_lock, so if this
+		 * THP is trying to split, it will be blocked in the mmu
+		 * notifier before touching any of the pages, specifically
+		 * before being able to call __split_huge_page_refcount().
+		 *
+		 * We can therefore safely transfer the refcount from PG_tail
+		 * to PG_head and switch the pfn from a tail page to the head
+		 * page accordingly.
+		 */
+		mask = PTRS_PER_PMD - 1;
+		VM_BUG_ON((gfn & mask) != (pfn & mask));
+		if (pfn & mask) {
+			*ipap &= PMD_MASK;
+			kvm_release_pfn_clean(pfn);
+			pfn &= ~mask;
+			kvm_get_pfn(pfn);
+			*pfnp = pfn;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
+/**
+ * stage2_wp_ptes - write protect PMD range
+ * @pmd:	pointer to pmd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			if (!kvm_s2pte_readonly(pte))
+				kvm_set_s2pte_readonly(pte);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+/**
+ * stage2_wp_pmds - write protect PUD range
+ * @pud:	pointer to pud entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = stage2_pmd_offset(pud, addr);
+
+	do {
+		next = stage2_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (pmd_thp_or_huge(*pmd)) {
+				if (!kvm_s2pmd_readonly(pmd))
+					kvm_set_s2pmd_readonly(pmd);
+			} else {
+				stage2_wp_ptes(pmd, addr, next);
+			}
+		}
+	} while (pmd++, addr = next, addr != end);
+}
+
+/**
+  * stage2_wp_puds - write protect PGD range
+  * @pgd:	pointer to pgd entry
+  * @addr:	range start address
+  * @end:	range end address
+  *
+  * Process PUD entries, for a huge PUD we cause a panic.
+  */
+static void  stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = stage2_pud_offset(pgd, addr);
+	do {
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
+			/* TODO:PUD not supported, revisit later if supported */
+			BUG_ON(stage2_pud_huge(*pud));
+			stage2_wp_pmds(pud, addr, next);
+		}
+	} while (pud++, addr = next, addr != end);
+}
+
+/**
+ * stage2_wp_range() - write protect stage2 memory region range
+ * @kvm:	The KVM pointer
+ * @addr:	Start address of range
+ * @end:	End address of range
+ */
+static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+	pgd_t *pgd;
+	phys_addr_t next;
+
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+	do {
+		/*
+		 * Release kvm_mmu_lock periodically if the memory region is
+		 * large. Otherwise, we may see kernel panics with
+		 * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
+		 * CONFIG_LOCKDEP. Additionally, holding the lock too long
+		 * will also starve other vCPUs.
+		 */
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock))
+			cond_resched_lock(&kvm->mmu_lock);
+
+		next = stage2_pgd_addr_end(addr, end);
+		if (stage2_pgd_present(*pgd))
+			stage2_wp_puds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot to write protect
+ *
+ * Called to start logging dirty pages after memory region
+ * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
+ * all present PMD and PTEs are write protected in the memory region.
+ * Afterwards read of dirty page log can be called.
+ *
+ * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
+ */
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
+	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_wp_range(kvm, start, end);
+	spin_unlock(&kvm->mmu_lock);
+	kvm_flush_remote_tlbs(kvm);
+}
+
+/**
+ * kvm_mmu_write_protect_pt_masked() - write protect dirty pages
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot associated with mask
+ * @gfn_offset:	The gfn offset in memory slot
+ * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
+ *		slot to be write protected
+ *
+ * Walks bits set in mask write protects the associated pte's. Caller must
+ * acquire kvm_mmu_lock.
+ */
+static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+		struct kvm_memory_slot *slot,
+		gfn_t gfn_offset, unsigned long mask)
+{
+	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
+	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
+	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+
+	stage2_wp_range(kvm, start, end);
+}
+
+/*
+ * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
+ * dirty pages.
+ *
+ * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
+ * enable dirty logging for them.
+ */
+void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
+		struct kvm_memory_slot *slot,
+		gfn_t gfn_offset, unsigned long mask)
+{
+	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+}
+
+static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
+				      unsigned long size)
+{
+	__coherent_cache_guest_page(vcpu, pfn, size);
+}
+
+static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+			  struct kvm_memory_slot *memslot, unsigned long hva,
+			  unsigned long fault_status)
+{
+	int ret;
+	bool write_fault, writable, hugetlb = false, force_pte = false;
+	unsigned long mmu_seq;
+	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+	struct vm_area_struct *vma;
+	kvm_pfn_t pfn;
+	pgprot_t mem_type = PAGE_S2;
+	bool logging_active = memslot_is_logging(memslot);
+	unsigned long flags = 0;
+
+	write_fault = kvm_is_write_fault(vcpu);
+	if (fault_status == FSC_PERM && !write_fault) {
+		kvm_err("Unexpected L2 read permission error\n");
+		return -EFAULT;
+	}
+
+	/* Let's check if we will get back a huge page backed by hugetlbfs */
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		up_read(&current->mm->mmap_sem);
+		return -EFAULT;
+	}
+
+	if (is_vm_hugetlb_page(vma) && !logging_active) {
+		hugetlb = true;
+		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
+	} else {
+		/*
+		 * Pages belonging to memslots that don't have the same
+		 * alignment for userspace and IPA cannot be mapped using
+		 * block descriptors even if the pages belong to a THP for
+		 * the process, because the stage-2 block descriptor will
+		 * cover more than a single THP and we loose atomicity for
+		 * unmapping, updates, and splits of the THP or other pages
+		 * in the stage-2 block range.
+		 */
+		if ((memslot->userspace_addr & ~PMD_MASK) !=
+		    ((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK))
+			force_pte = true;
+	}
+	up_read(&current->mm->mmap_sem);
+
+	/* We need minimum second+third level pages */
+	ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
+				     KVM_NR_MEM_OBJS);
+	if (ret)
+		return ret;
+
+	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	/*
+	 * Ensure the read of mmu_notifier_seq happens before we call
+	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
+	 * the page we just got a reference to gets unmapped before we have a
+	 * chance to grab the mmu_lock, which ensure that if the page gets
+	 * unmapped afterwards, the call to kvm_unmap_hva will take it away
+	 * from us again properly. This smp_rmb() interacts with the smp_wmb()
+	 * in kvm_mmu_notifier_invalidate_<page|range_end>.
+	 */
+	smp_rmb();
+
+	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
+	if (is_error_noslot_pfn(pfn))
+		return -EFAULT;
+
+	if (kvm_is_device_pfn(pfn)) {
+		mem_type = PAGE_S2_DEVICE;
+		flags |= KVM_S2PTE_FLAG_IS_IOMAP;
+	} else if (logging_active) {
+		/*
+		 * Faults on pages in a memslot with logging enabled
+		 * should not be mapped with huge pages (it introduces churn
+		 * and performance degradation), so force a pte mapping.
+		 */
+		force_pte = true;
+		flags |= KVM_S2_FLAG_LOGGING_ACTIVE;
+
+		/*
+		 * Only actually map the page as writable if this was a write
+		 * fault.
+		 */
+		if (!write_fault)
+			writable = false;
+	}
+
+	spin_lock(&kvm->mmu_lock);
+	if (mmu_notifier_retry(kvm, mmu_seq))
+		goto out_unlock;
+
+	if (!hugetlb && !force_pte)
+		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
+
+	if (hugetlb) {
+		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
+		new_pmd = pmd_mkhuge(new_pmd);
+		if (writable) {
+			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
+			kvm_set_pfn_dirty(pfn);
+		}
+		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE);
+		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+	} else {
+		pte_t new_pte = pfn_pte(pfn, mem_type);
+
+		if (writable) {
+			new_pte = kvm_s2pte_mkwrite(new_pte);
+			kvm_set_pfn_dirty(pfn);
+			mark_page_dirty(kvm, gfn);
+		}
+		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE);
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
+	}
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
+	kvm_set_pfn_accessed(pfn);
+	kvm_release_pfn_clean(pfn);
+	return ret;
+}
+
+/*
+ * Resolve the access fault by making the page young again.
+ * Note that because the faulting entry is guaranteed not to be
+ * cached in the TLB, we don't need to invalidate anything.
+ * Only the HW Access Flag updates are supported for Stage 2 (no DBM),
+ * so there is no need for atomic (pte|pmd)_mkyoung operations.
+ */
+static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+	kvm_pfn_t pfn;
+	bool pfn_valid = false;
+
+	trace_kvm_access_fault(fault_ipa);
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		goto out;
+
+	if (pmd_thp_or_huge(*pmd)) {	/* THP, HugeTLB */
+		*pmd = pmd_mkyoung(*pmd);
+		pfn = pmd_pfn(*pmd);
+		pfn_valid = true;
+		goto out;
+	}
+
+	pte = pte_offset_kernel(pmd, fault_ipa);
+	if (pte_none(*pte))		/* Nothing there either */
+		goto out;
+
+	*pte = pte_mkyoung(*pte);	/* Just a page... */
+	pfn = pte_pfn(*pte);
+	pfn_valid = true;
+out:
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	if (pfn_valid)
+		kvm_set_pfn_accessed(pfn);
+}
+
+/**
+ * kvm_handle_guest_abort - handles all 2nd stage aborts
+ * @vcpu:	the VCPU pointer
+ * @run:	the kvm_run structure
+ *
+ * Any abort that gets to the host is almost guaranteed to be caused by a
+ * missing second stage translation table entry, which can mean that either the
+ * guest simply needs more memory and we must allocate an appropriate page or it
+ * can mean that the guest tried to access I/O memory, which is emulated by user
+ * space. The distinction is based on the IPA causing the fault and whether this
+ * memory region has been registered as standard RAM by user space.
+ */
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	unsigned long fault_status;
+	phys_addr_t fault_ipa;
+	struct kvm_memory_slot *memslot;
+	unsigned long hva;
+	bool is_iabt, write_fault, writable;
+	gfn_t gfn;
+	int ret, idx;
+
+	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+	if (unlikely(!is_iabt && kvm_vcpu_dabt_isextabt(vcpu))) {
+		kvm_inject_vabt(vcpu);
+		return 1;
+	}
+
+	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
+			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
+
+	/* Check the stage-2 fault is trans. fault or write fault */
+	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
+	    fault_status != FSC_ACCESS) {
+		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+			kvm_vcpu_trap_get_class(vcpu),
+			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+			(unsigned long)kvm_vcpu_get_hsr(vcpu));
+		return -EFAULT;
+	}
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	gfn = fault_ipa >> PAGE_SHIFT;
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+	write_fault = kvm_is_write_fault(vcpu);
+	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+		if (is_iabt) {
+			/* Prefetch Abort on I/O address */
+			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
+		/*
+		 * Check for a cache maintenance operation. Since we
+		 * ended-up here, we know it is outside of any memory
+		 * slot. But we can't find out if that is for a device,
+		 * or if the guest is just being stupid. The only thing
+		 * we know for sure is that this range cannot be cached.
+		 *
+		 * So let's assume that the guest is just being
+		 * cautious, and skip the instruction.
+		 */
+		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
+		/*
+		 * The IPA is reported as [MAX:12], so we need to
+		 * complement it with the bottom 12 bits from the
+		 * faulting VA. This is always 12 bits, irrespective
+		 * of the page size.
+		 */
+		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
+		ret = io_mem_abort(vcpu, run, fault_ipa);
+		goto out_unlock;
+	}
+
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+
+	if (fault_status == FSC_ACCESS) {
+		handle_access_fault(vcpu, fault_ipa);
+		ret = 1;
+		goto out_unlock;
+	}
+
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+	if (ret == 0)
+		ret = 1;
+out_unlock:
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	return ret;
+}
+
+static int handle_hva_to_gpa(struct kvm *kvm,
+			     unsigned long start,
+			     unsigned long end,
+			     int (*handler)(struct kvm *kvm,
+					    gpa_t gpa, u64 size,
+					    void *data),
+			     void *data)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int ret = 0;
+
+	slots = kvm_memslots(kvm);
+
+	/* we only care about the pages that the guest sees */
+	kvm_for_each_memslot(memslot, slots) {
+		unsigned long hva_start, hva_end;
+		gfn_t gpa;
+
+		hva_start = max(start, memslot->userspace_addr);
+		hva_end = min(end, memslot->userspace_addr +
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+
+		gpa = hva_to_gfn_memslot(hva_start, memslot) << PAGE_SHIFT;
+		ret |= handler(kvm, gpa, (u64)(hva_end - hva_start), data);
+	}
+
+	return ret;
+}
+
+static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
+{
+	unmap_stage2_range(kvm, gpa, size);
+	return 0;
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	unsigned long end = hva + PAGE_SIZE;
+
+	if (!kvm->arch.pgd)
+		return 0;
+
+	trace_kvm_unmap_hva(hva);
+	handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL);
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm,
+			unsigned long start, unsigned long end)
+{
+	if (!kvm->arch.pgd)
+		return 0;
+
+	trace_kvm_unmap_hva_range(start, end);
+	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+	return 0;
+}
+
+static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
+{
+	pte_t *pte = (pte_t *)data;
+
+	WARN_ON(size != PAGE_SIZE);
+	/*
+	 * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE
+	 * flag clear because MMU notifiers will have unmapped a huge PMD before
+	 * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and
+	 * therefore stage2_set_pte() never needs to clear out a huge PMD
+	 * through this calling path.
+	 */
+	stage2_set_pte(kvm, NULL, gpa, pte, 0);
+	return 0;
+}
+
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	unsigned long end = hva + PAGE_SIZE;
+	pte_t stage2_pte;
+
+	if (!kvm->arch.pgd)
+		return;
+
+	trace_kvm_set_spte_hva(hva);
+	stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2);
+	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
+}
+
+static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (pmd_thp_or_huge(*pmd))	/* THP, HugeTLB */
+		return stage2_pmdp_test_and_clear_young(pmd);
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (pte_none(*pte))
+		return 0;
+
+	return stage2_ptep_test_and_clear_young(pte);
+}
+
+static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (pmd_thp_or_huge(*pmd))		/* THP, HugeTLB */
+		return pmd_young(*pmd);
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (!pte_none(*pte))		/* Just a page... */
+		return pte_young(*pte);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	trace_kvm_age_hva(start, end);
+	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_test_age_hva(hva);
+	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+}
+
+void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
+{
+	mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+}
+
+phys_addr_t kvm_mmu_get_httbr(void)
+{
+	if (__kvm_cpu_uses_extended_idmap())
+		return virt_to_phys(merged_hyp_pgd);
+	else
+		return virt_to_phys(hyp_pgd);
+}
+
+phys_addr_t kvm_get_idmap_vector(void)
+{
+	return hyp_idmap_vector;
+}
+
+static int kvm_map_idmap_text(pgd_t *pgd)
+{
+	int err;
+
+	/* Create the idmap in the boot page tables */
+	err = 	__create_hyp_mappings(pgd,
+				      hyp_idmap_start, hyp_idmap_end,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP_EXEC);
+	if (err)
+		kvm_err("Failed to idmap %lx-%lx\n",
+			hyp_idmap_start, hyp_idmap_end);
+
+	return err;
+}
+
+int kvm_mmu_init(void)
+{
+	int err;
+
+	hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
+	hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
+	hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);
+
+	/*
+	 * We rely on the linker script to ensure at build time that the HYP
+	 * init code does not cross a page boundary.
+	 */
+	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
+
+	kvm_info("IDMAP page: %lx\n", hyp_idmap_start);
+	kvm_info("HYP VA range: %lx:%lx\n",
+		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
+
+	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
+	    hyp_idmap_start <  kern_hyp_va(~0UL) &&
+	    hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
+		/*
+		 * The idmap page is intersecting with the VA space,
+		 * it is not safe to continue further.
+		 */
+		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	if (!hyp_pgd) {
+		kvm_err("Hyp mode PGD not allocated\n");
+		err = -ENOMEM;
+		goto out;
+	}
+
+	if (__kvm_cpu_uses_extended_idmap()) {
+		boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+							 hyp_pgd_order);
+		if (!boot_hyp_pgd) {
+			kvm_err("Hyp boot PGD not allocated\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = kvm_map_idmap_text(boot_hyp_pgd);
+		if (err)
+			goto out;
+
+		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		if (!merged_hyp_pgd) {
+			kvm_err("Failed to allocate extra HYP pgd\n");
+			goto out;
+		}
+		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
+				    hyp_idmap_start);
+	} else {
+		err = kvm_map_idmap_text(hyp_pgd);
+		if (err)
+			goto out;
+	}
+
+	return 0;
+out:
+	free_hyp_pgds();
+	return err;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				   const struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
+				   enum kvm_mr_change change)
+{
+	/*
+	 * At this point memslot has been committed and there is an
+	 * allocated dirty_bitmap[], dirty pages will be be tracked while the
+	 * memory slot is write protected.
+	 */
+	if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES)
+		kvm_mmu_wp_memory_region(kvm, mem->slot);
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   const struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
+{
+	hva_t hva = mem->userspace_addr;
+	hva_t reg_end = hva + mem->memory_size;
+	bool writable = !(mem->flags & KVM_MEM_READONLY);
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
+			change != KVM_MR_FLAGS_ONLY)
+		return 0;
+
+	/*
+	 * Prevent userspace from creating a memory region outside of the IPA
+	 * space addressable by the KVM guest IPA space.
+	 */
+	if (memslot->base_gfn + memslot->npages >=
+	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
+		return -EFAULT;
+
+	down_read(&current->mm->mmap_sem);
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we can map
+	 * any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = mem->guest_phys_addr +
+				    (vm_start - mem->userspace_addr);
+			phys_addr_t pa;
+
+			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+			pa += vm_start - vma->vm_start;
+
+			/* IO region dirty page logging not allowed */
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
+						    vm_end - vm_start,
+						    writable);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (change == KVM_MR_FLAGS_ONLY)
+		goto out;
+
+	spin_lock(&kvm->mmu_lock);
+	if (ret)
+		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+	else
+		stage2_flush_memslot(kvm, memslot);
+	spin_unlock(&kvm->mmu_lock);
+out:
+	up_read(&current->mm->mmap_sem);
+	return ret;
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
+{
+	return 0;
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_free_stage2_pgd(kvm);
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	unmap_stage2_range(kvm, gpa, size);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+/*
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
+ *
+ * Main problems:
+ * - S/W ops are local to a CPU (not broadcast)
+ * - We have line migration behind our back (speculation)
+ * - System caches don't support S/W at all (damn!)
+ *
+ * In the face of the above, the best we can do is to try and convert
+ * S/W ops to VA ops. Because the guest is not allowed to infer the
+ * S/W to PA mapping, it can only use S/W to nuke the whole cache,
+ * which is a rather good thing for us.
+ *
+ * Also, it is only used when turning caches on/off ("The expected
+ * usage of the cache maintenance instructions that operate by set/way
+ * is associated with the cache maintenance instructions associated
+ * with the powerdown and powerup of caches, if this is required by
+ * the implementation.").
+ *
+ * We use the following policy:
+ *
+ * - If we trap a S/W operation, we enable VM trapping to detect
+ *   caches being turned on/off, and do a full clean.
+ *
+ * - We flush the caches on both caches being turned on and off.
+ *
+ * - Once the caches are enabled, we stop trapping VM ops.
+ */
+void kvm_set_way_flush(struct kvm_vcpu *vcpu)
+{
+	unsigned long hcr = vcpu_get_hcr(vcpu);
+
+	/*
+	 * If this is the first time we do a S/W operation
+	 * (i.e. HCR_TVM not set) flush the whole memory, and set the
+	 * VM trapping.
+	 *
+	 * Otherwise, rely on the VM trapping to wait for the MMU +
+	 * Caches to be turned off. At that point, we'll be able to
+	 * clean the caches again.
+	 */
+	if (!(hcr & HCR_TVM)) {
+		trace_kvm_set_way_flush(*vcpu_pc(vcpu),
+					vcpu_has_cache_enabled(vcpu));
+		stage2_flush_vm(vcpu->kvm);
+		vcpu_set_hcr(vcpu, hcr | HCR_TVM);
+	}
+}
+
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
+{
+	bool now_enabled = vcpu_has_cache_enabled(vcpu);
+
+	/*
+	 * If switching the MMU+caches on, need to invalidate the caches.
+	 * If switching it off, need to clean the caches.
+	 * Clean + invalidate does the trick always.
+	 */
+	if (now_enabled != was_enabled)
+		stage2_flush_vm(vcpu->kvm);
+
+	/* Caches are now on, stop trapping VM ops (until a S/W op) */
+	if (now_enabled)
+		vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM);
+
+	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
+}
diff --git a/virt/kvm/arm/perf.c b/virt/kvm/arm/perf.c
new file mode 100644
index 000000000000..1a3849da0b4b
--- /dev/null
+++ b/virt/kvm/arm/perf.c
@@ -0,0 +1,68 @@
+/*
+ * Based on the x86 implementation.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+static int kvm_is_in_guest(void)
+{
+        return kvm_arm_get_running_vcpu() != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return !vcpu_mode_priv(vcpu);
+
+	return 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return *vcpu_pc(vcpu);
+
+	return 0;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+	.is_in_guest	= kvm_is_in_guest,
+	.is_user_mode	= kvm_is_user_mode,
+	.get_guest_ip	= kvm_get_guest_ip,
+};
+
+int kvm_perf_init(void)
+{
+	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
+}
+
+int kvm_perf_teardown(void)
+{
+	return perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+}
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
new file mode 100644
index 000000000000..a08d7a93aebb
--- /dev/null
+++ b/virt/kvm/arm/psci.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (C) 2012 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/preempt.h>
+#include <linux/kvm_host.h>
+#include <linux/wait.h>
+
+#include <asm/cputype.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_psci.h>
+#include <asm/kvm_host.h>
+
+#include <uapi/linux/psci.h>
+
+/*
+ * This is an implementation of the Power State Coordination Interface
+ * as described in ARM document number ARM DEN 0022A.
+ */
+
+#define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+
+static unsigned long psci_affinity_mask(unsigned long affinity_level)
+{
+	if (affinity_level <= 3)
+		return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
+
+	return 0;
+}
+
+static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * NOTE: For simplicity, we make VCPU suspend emulation to be
+	 * same-as WFI (Wait-for-interrupt) emulation.
+	 *
+	 * This means for KVM the wakeup events are interrupts and
+	 * this is consistent with intended use of StateID as described
+	 * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
+	 *
+	 * Further, we also treat power-down request to be same as
+	 * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
+	 * specification (ARM DEN 0022A). This means all suspend states
+	 * for KVM will preserve the register state.
+	 */
+	kvm_vcpu_block(vcpu);
+
+	return PSCI_RET_SUCCESS;
+}
+
+static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = true;
+}
+
+static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
+{
+	struct kvm *kvm = source_vcpu->kvm;
+	struct kvm_vcpu *vcpu = NULL;
+	struct swait_queue_head *wq;
+	unsigned long cpu_id;
+	unsigned long context_id;
+	phys_addr_t target_pc;
+
+	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	if (vcpu_mode_is_32bit(source_vcpu))
+		cpu_id &= ~((u32) 0);
+
+	vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
+
+	/*
+	 * Make sure the caller requested a valid CPU and that the CPU is
+	 * turned off.
+	 */
+	if (!vcpu)
+		return PSCI_RET_INVALID_PARAMS;
+	if (!vcpu->arch.power_off) {
+		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+			return PSCI_RET_ALREADY_ON;
+		else
+			return PSCI_RET_INVALID_PARAMS;
+	}
+
+	target_pc = vcpu_get_reg(source_vcpu, 2);
+	context_id = vcpu_get_reg(source_vcpu, 3);
+
+	kvm_reset_vcpu(vcpu);
+
+	/* Gracefully handle Thumb2 entry point */
+	if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
+		target_pc &= ~((phys_addr_t) 1);
+		vcpu_set_thumb(vcpu);
+	}
+
+	/* Propagate caller endianness */
+	if (kvm_vcpu_is_be(source_vcpu))
+		kvm_vcpu_set_be(vcpu);
+
+	*vcpu_pc(vcpu) = target_pc;
+	/*
+	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
+	 * the general puspose registers are undefined upon CPU_ON.
+	 */
+	vcpu_set_reg(vcpu, 0, context_id);
+	vcpu->arch.power_off = false;
+	smp_mb();		/* Make sure the above is visible */
+
+	wq = kvm_arch_vcpu_wq(vcpu);
+	swake_up(wq);
+
+	return PSCI_RET_SUCCESS;
+}
+
+static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
+{
+	int i, matching_cpus = 0;
+	unsigned long mpidr;
+	unsigned long target_affinity;
+	unsigned long target_affinity_mask;
+	unsigned long lowest_affinity_level;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tmp;
+
+	target_affinity = vcpu_get_reg(vcpu, 1);
+	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
+
+	/* Determine target affinity mask */
+	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+	if (!target_affinity_mask)
+		return PSCI_RET_INVALID_PARAMS;
+
+	/* Ignore other bits of target affinity */
+	target_affinity &= target_affinity_mask;
+
+	/*
+	 * If one or more VCPU matching target affinity are running
+	 * then ON else OFF
+	 */
+	kvm_for_each_vcpu(i, tmp, kvm) {
+		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
+		if ((mpidr & target_affinity_mask) == target_affinity) {
+			matching_cpus++;
+			if (!tmp->arch.power_off)
+				return PSCI_0_2_AFFINITY_LEVEL_ON;
+		}
+	}
+
+	if (!matching_cpus)
+		return PSCI_RET_INVALID_PARAMS;
+
+	return PSCI_0_2_AFFINITY_LEVEL_OFF;
+}
+
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+{
+	int i;
+	struct kvm_vcpu *tmp;
+
+	/*
+	 * The KVM ABI specifies that a system event exit may call KVM_RUN
+	 * again and may perform shutdown/reboot at a later time that when the
+	 * actual request is made.  Since we are implementing PSCI and a
+	 * caller of PSCI reboot and shutdown expects that the system shuts
+	 * down or reboots immediately, let's make sure that VCPUs are not run
+	 * after this call is handled and before the VCPUs have been
+	 * re-initialized.
+	 */
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		tmp->arch.power_off = true;
+		kvm_vcpu_kick(tmp);
+	}
+
+	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+	vcpu->run->system_event.type = type;
+	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+}
+
+static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+}
+
+int kvm_psci_version(struct kvm_vcpu *vcpu)
+{
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+		return KVM_ARM_PSCI_0_2;
+
+	return KVM_ARM_PSCI_0_1;
+}
+
+static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long val;
+	int ret = 1;
+
+	switch (psci_fn) {
+	case PSCI_0_2_FN_PSCI_VERSION:
+		/*
+		 * Bits[31:16] = Major Version = 0
+		 * Bits[15:0] = Minor Version = 2
+		 */
+		val = 2;
+		break;
+	case PSCI_0_2_FN_CPU_SUSPEND:
+	case PSCI_0_2_FN64_CPU_SUSPEND:
+		val = kvm_psci_vcpu_suspend(vcpu);
+		break;
+	case PSCI_0_2_FN_CPU_OFF:
+		kvm_psci_vcpu_off(vcpu);
+		val = PSCI_RET_SUCCESS;
+		break;
+	case PSCI_0_2_FN_CPU_ON:
+	case PSCI_0_2_FN64_CPU_ON:
+		mutex_lock(&kvm->lock);
+		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
+		break;
+	case PSCI_0_2_FN_AFFINITY_INFO:
+	case PSCI_0_2_FN64_AFFINITY_INFO:
+		val = kvm_psci_vcpu_affinity_info(vcpu);
+		break;
+	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+		/*
+		 * Trusted OS is MP hence does not require migration
+	         * or
+		 * Trusted OS is not present
+		 */
+		val = PSCI_0_2_TOS_MP;
+		break;
+	case PSCI_0_2_FN_SYSTEM_OFF:
+		kvm_psci_system_off(vcpu);
+		/*
+		 * We should'nt be going back to guest VCPU after
+		 * receiving SYSTEM_OFF request.
+		 *
+		 * If user space accidently/deliberately resumes
+		 * guest VCPU after SYSTEM_OFF request then guest
+		 * VCPU should see internal failure from PSCI return
+		 * value. To achieve this, we preload r0 (or x0) with
+		 * PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	case PSCI_0_2_FN_SYSTEM_RESET:
+		kvm_psci_system_reset(vcpu);
+		/*
+		 * Same reason as SYSTEM_OFF for preloading r0 (or x0)
+		 * with PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	default:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	}
+
+	vcpu_set_reg(vcpu, 0, val);
+	return ret;
+}
+
+static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long val;
+
+	switch (psci_fn) {
+	case KVM_PSCI_FN_CPU_OFF:
+		kvm_psci_vcpu_off(vcpu);
+		val = PSCI_RET_SUCCESS;
+		break;
+	case KVM_PSCI_FN_CPU_ON:
+		mutex_lock(&kvm->lock);
+		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
+		break;
+	default:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	}
+
+	vcpu_set_reg(vcpu, 0, val);
+	return 1;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC instructions.
+ * The calling convention is similar to SMC calls to the secure world
+ * where the function number is placed in r0.
+ *
+ * This function returns: > 0 (success), 0 (success but exit to user
+ * space), and < 0 (errors)
+ *
+ * Errors:
+ * -EINVAL: Unrecognized PSCI function
+ */
+int kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+	switch (kvm_psci_version(vcpu)) {
+	case KVM_ARM_PSCI_0_2:
+		return kvm_psci_0_2_call(vcpu);
+	case KVM_ARM_PSCI_0_1:
+		return kvm_psci_0_1_call(vcpu);
+	default:
+		return -EINVAL;
+	};
+}
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
index 37d8b98867d5..f7dc5ddd6847 100644
--- a/virt/kvm/arm/trace.h
+++ b/virt/kvm/arm/trace.h
@@ -7,26 +7,250 @@
 #define TRACE_SYSTEM kvm
 
 /*
- * Tracepoints for vgic
+ * Tracepoints for entry/exit to guest
  */
-TRACE_EVENT(vgic_update_irq_pending,
-	TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
-	TP_ARGS(vcpu_id, irq, level),
+TRACE_EVENT(kvm_entry,
+	TP_PROTO(unsigned long vcpu_pc),
+	TP_ARGS(vcpu_pc),
 
 	TP_STRUCT__entry(
-		__field(	unsigned long,	vcpu_id	)
-		__field(	__u32,		irq	)
-		__field(	bool,		level	)
+		__field(	unsigned long,	vcpu_pc		)
 	),
 
 	TP_fast_assign(
-		__entry->vcpu_id	= vcpu_id;
-		__entry->irq		= irq;
+		__entry->vcpu_pc		= vcpu_pc;
+	),
+
+	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
+	TP_ARGS(idx, exit_reason, vcpu_pc),
+
+	TP_STRUCT__entry(
+		__field(	int,		idx		)
+		__field(	unsigned int,	exit_reason	)
+		__field(	unsigned long,	vcpu_pc		)
+	),
+
+	TP_fast_assign(
+		__entry->idx			= idx;
+		__entry->exit_reason		= exit_reason;
+		__entry->vcpu_pc		= vcpu_pc;
+	),
+
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+		  __print_symbolic(__entry->idx, kvm_arm_exception_type),
+		  __entry->exit_reason,
+		  __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
+		  __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_guest_fault,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
+		 unsigned long hxfar,
+		 unsigned long long ipa),
+	TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	hsr		)
+		__field(	unsigned long,	hxfar		)
+		__field(   unsigned long long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->hsr			= hsr;
+		__entry->hxfar			= hxfar;
+		__entry->ipa			= ipa;
+	),
+
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+		  __entry->ipa, __entry->hsr,
+		  __entry->hxfar, __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_access_fault,
+	TP_PROTO(unsigned long ipa),
+	TP_ARGS(ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->ipa		= ipa;
+	),
+
+	TP_printk("IPA: %lx", __entry->ipa)
+);
+
+TRACE_EVENT(kvm_irq_line,
+	TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
+	TP_ARGS(type, vcpu_idx, irq_num, level),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	type		)
+		__field(	int,		vcpu_idx	)
+		__field(	int,		irq_num		)
+		__field(	int,		level		)
+	),
+
+	TP_fast_assign(
+		__entry->type		= type;
+		__entry->vcpu_idx	= vcpu_idx;
+		__entry->irq_num	= irq_num;
 		__entry->level		= level;
 	),
 
-	TP_printk("VCPU: %ld, IRQ %d, level: %d",
-		  __entry->vcpu_id, __entry->irq, __entry->level)
+	TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
+		  (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
+		  (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
+		  (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
+		  __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
+);
+
+TRACE_EVENT(kvm_mmio_emulate,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
+		 unsigned long cpsr),
+	TP_ARGS(vcpu_pc, instr, cpsr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	instr		)
+		__field(	unsigned long,	cpsr		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->instr			= instr;
+		__entry->cpsr			= cpsr;
+	),
+
+	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_unmap_hva_range,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_set_spte_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_age_hva,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_set_way_flush,
+	    TP_PROTO(unsigned long vcpu_pc, bool cache),
+	    TP_ARGS(vcpu_pc, cache),
+
+	    TP_STRUCT__entry(
+		    __field(	unsigned long,	vcpu_pc		)
+		    __field(	bool,		cache		)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->vcpu_pc		= vcpu_pc;
+		    __entry->cache		= cache;
+	    ),
+
+	    TP_printk("S/W flush at 0x%016lx (cache %s)",
+		      __entry->vcpu_pc, __entry->cache ? "on" : "off")
+);
+
+TRACE_EVENT(kvm_toggle_cache,
+	    TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
+	    TP_ARGS(vcpu_pc, was, now),
+
+	    TP_STRUCT__entry(
+		    __field(	unsigned long,	vcpu_pc		)
+		    __field(	bool,		was		)
+		    __field(	bool,		now		)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->vcpu_pc		= vcpu_pc;
+		    __entry->was		= was;
+		    __entry->now		= now;
+	    ),
+
+	    TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
+		      __entry->vcpu_pc, __entry->was ? "on" : "off",
+		      __entry->now ? "on" : "off")
 );
 
 /*
diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h
new file mode 100644
index 000000000000..ed3229282888
--- /dev/null
+++ b/virt/kvm/arm/vgic/trace.h
@@ -0,0 +1,37 @@
+#if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VGIC_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+TRACE_EVENT(vgic_update_irq_pending,
+	TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
+	TP_ARGS(vcpu_id, irq, level),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_id	)
+		__field(	__u32,		irq	)
+		__field(	bool,		level	)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+		__entry->irq		= irq;
+		__entry->level		= level;
+	),
+
+	TP_printk("VCPU: %ld, IRQ %d, level: %d",
+		  __entry->vcpu_id, __entry->irq, __entry->level)
+);
+
+#endif /* _TRACE_VGIC_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 25fd1b942c11..dc68e2e424ab 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -227,10 +227,27 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 }
 
 /**
- * kvm_vgic_vcpu_init() - Enable the VCPU interface
- * @vcpu: the VCPU which's VGIC should be enabled
+ * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs
+ * @vcpu: pointer to the VCPU being created and initialized
  */
-static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	int ret = 0;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return 0;
+
+	/*
+	 * If we are creating a VCPU with a GICv3 we must also register the
+	 * KVM io device for the redistributor that belongs to this VCPU.
+	 */
+	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+		ret = vgic_register_redist_iodev(vcpu);
+	return ret;
+}
+
+static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_enable(vcpu);
@@ -269,7 +286,7 @@ int vgic_init(struct kvm *kvm)
 		dist->msis_require_devid = true;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_init(vcpu);
+		kvm_vgic_vcpu_enable(vcpu);
 
 	ret = kvm_vgic_setup_default_irq_routing(kvm);
 	if (ret)
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 8d1da1af4b09..2dff288b3a66 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/uaccess.h>
+#include <linux/list_sort.h>
 
 #include <linux/irqchip/arm-gic-v3.h>
 
@@ -33,6 +34,12 @@
 #include "vgic.h"
 #include "vgic-mmio.h"
 
+static int vgic_its_save_tables_v0(struct vgic_its *its);
+static int vgic_its_restore_tables_v0(struct vgic_its *its);
+static int vgic_its_commit_v0(struct vgic_its *its);
+static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
+			     struct kvm_vcpu *filter_vcpu);
+
 /*
  * Creates a new (reference to a) struct vgic_irq for a given LPI.
  * If this LPI is already mapped on another ITS, we increase its refcount
@@ -40,10 +47,12 @@
  * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq.
  * This function returns a pointer to the _unlocked_ structure.
  */
-static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
+static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
+				     struct kvm_vcpu *vcpu)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+	int ret;
 
 	/* In this case there is no put, since we keep the reference. */
 	if (irq)
@@ -60,6 +69,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
 	irq->config = VGIC_CONFIG_EDGE;
 	kref_init(&irq->refcount);
 	irq->intid = intid;
+	irq->target_vcpu = vcpu;
 
 	spin_lock(&dist->lpi_list_lock);
 
@@ -91,6 +101,19 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
 out_unlock:
 	spin_unlock(&dist->lpi_list_lock);
 
+	/*
+	 * We "cache" the configuration table entries in our struct vgic_irq's.
+	 * However we only have those structs for mapped IRQs, so we read in
+	 * the respective config data from memory here upon mapping the LPI.
+	 */
+	ret = update_lpi_config(kvm, irq, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ret = vgic_v3_lpi_sync_pending_status(kvm, irq);
+	if (ret)
+		return ERR_PTR(ret);
+
 	return irq;
 }
 
@@ -99,6 +122,8 @@ struct its_device {
 
 	/* the head for the list of ITTEs */
 	struct list_head itt_head;
+	u32 num_eventid_bits;
+	gpa_t itt_addr;
 	u32 device_id;
 };
 
@@ -114,8 +139,8 @@ struct its_collection {
 #define its_is_collection_mapped(coll) ((coll) && \
 				((coll)->target_addr != COLLECTION_NOT_MAPPED))
 
-struct its_itte {
-	struct list_head itte_list;
+struct its_ite {
+	struct list_head ite_list;
 
 	struct vgic_irq *irq;
 	struct its_collection *collection;
@@ -123,6 +148,50 @@ struct its_itte {
 	u32 event_id;
 };
 
+/**
+ * struct vgic_its_abi - ITS abi ops and settings
+ * @cte_esz: collection table entry size
+ * @dte_esz: device table entry size
+ * @ite_esz: interrupt translation table entry size
+ * @save tables: save the ITS tables into guest RAM
+ * @restore_tables: restore the ITS internal structs from tables
+ *  stored in guest RAM
+ * @commit: initialize the registers which expose the ABI settings,
+ *  especially the entry sizes
+ */
+struct vgic_its_abi {
+	int cte_esz;
+	int dte_esz;
+	int ite_esz;
+	int (*save_tables)(struct vgic_its *its);
+	int (*restore_tables)(struct vgic_its *its);
+	int (*commit)(struct vgic_its *its);
+};
+
+static const struct vgic_its_abi its_table_abi_versions[] = {
+	[0] = {.cte_esz = 8, .dte_esz = 8, .ite_esz = 8,
+	 .save_tables = vgic_its_save_tables_v0,
+	 .restore_tables = vgic_its_restore_tables_v0,
+	 .commit = vgic_its_commit_v0,
+	},
+};
+
+#define NR_ITS_ABIS	ARRAY_SIZE(its_table_abi_versions)
+
+inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its)
+{
+	return &its_table_abi_versions[its->abi_rev];
+}
+
+int vgic_its_set_abi(struct vgic_its *its, int rev)
+{
+	const struct vgic_its_abi *abi;
+
+	its->abi_rev = rev;
+	abi = vgic_its_get_abi(its);
+	return abi->commit(its);
+}
+
 /*
  * Find and returns a device in the device table for an ITS.
  * Must be called with the its_lock mutex held.
@@ -143,27 +212,27 @@ static struct its_device *find_its_device(struct vgic_its *its, u32 device_id)
  * Device ID/Event ID pair on an ITS.
  * Must be called with the its_lock mutex held.
  */
-static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
+static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
 				  u32 event_id)
 {
 	struct its_device *device;
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 	device = find_its_device(its, device_id);
 	if (device == NULL)
 		return NULL;
 
-	list_for_each_entry(itte, &device->itt_head, itte_list)
-		if (itte->event_id == event_id)
-			return itte;
+	list_for_each_entry(ite, &device->itt_head, ite_list)
+		if (ite->event_id == event_id)
+			return ite;
 
 	return NULL;
 }
 
 /* To be used as an iterator this macro misses the enclosing parentheses */
-#define for_each_lpi_its(dev, itte, its) \
+#define for_each_lpi_its(dev, ite, its) \
 	list_for_each_entry(dev, &(its)->device_list, dev_list) \
-		list_for_each_entry(itte, &(dev)->itt_head, itte_list)
+		list_for_each_entry(ite, &(dev)->itt_head, ite_list)
 
 /*
  * We only implement 48 bits of PA at the moment, although the ITS
@@ -171,11 +240,14 @@ static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
  */
 #define BASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 16))
 #define CBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 12))
-#define PENDBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 16))
-#define PROPBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 12))
 
 #define GIC_LPI_OFFSET 8192
 
+#define VITS_TYPER_IDBITS 16
+#define VITS_TYPER_DEVBITS 16
+#define VITS_DTE_MAX_DEVID_OFFSET	(BIT(14) - 1)
+#define VITS_ITE_MAX_EVENTID_OFFSET	(BIT(16) - 1)
+
 /*
  * Finds and returns a collection in the ITS collection table.
  * Must be called with the its_lock mutex held.
@@ -204,7 +276,7 @@ static struct its_collection *find_collection(struct vgic_its *its, int coll_id)
 static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 			     struct kvm_vcpu *filter_vcpu)
 {
-	u64 propbase = PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
+	u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
 	u8 prop;
 	int ret;
 
@@ -229,13 +301,13 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 }
 
 /*
- * Create a snapshot of the current LPI list, so that we can enumerate all
- * LPIs without holding any lock.
- * Returns the array length and puts the kmalloc'ed array into intid_ptr.
+ * Create a snapshot of the current LPIs targeting @vcpu, so that we can
+ * enumerate those LPIs without holding any lock.
+ * Returns their number and puts the kmalloc'ed array into intid_ptr.
  */
-static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
+static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
 {
-	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	struct vgic_irq *irq;
 	u32 *intids;
 	int irq_count = dist->lpi_list_count, i = 0;
@@ -254,14 +326,14 @@ static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
 	spin_lock(&dist->lpi_list_lock);
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		/* We don't need to "get" the IRQ, as we hold the list lock. */
-		intids[i] = irq->intid;
-		if (++i == irq_count)
-			break;
+		if (irq->target_vcpu != vcpu)
+			continue;
+		intids[i++] = irq->intid;
 	}
 	spin_unlock(&dist->lpi_list_lock);
 
 	*intid_ptr = intids;
-	return irq_count;
+	return i;
 }
 
 /*
@@ -270,18 +342,18 @@ static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
  * Needs to be called whenever either the collection for a LPIs has
  * changed or the collection itself got retargeted.
  */
-static void update_affinity_itte(struct kvm *kvm, struct its_itte *itte)
+static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite)
 {
 	struct kvm_vcpu *vcpu;
 
-	if (!its_is_collection_mapped(itte->collection))
+	if (!its_is_collection_mapped(ite->collection))
 		return;
 
-	vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+	vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
 
-	spin_lock(&itte->irq->irq_lock);
-	itte->irq->target_vcpu = vcpu;
-	spin_unlock(&itte->irq->irq_lock);
+	spin_lock(&ite->irq->irq_lock);
+	ite->irq->target_vcpu = vcpu;
+	spin_unlock(&ite->irq->irq_lock);
 }
 
 /*
@@ -292,13 +364,13 @@ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its,
 				       struct its_collection *coll)
 {
 	struct its_device *device;
-	struct its_itte *itte;
+	struct its_ite *ite;
 
-	for_each_lpi_its(device, itte, its) {
-		if (!itte->collection || coll != itte->collection)
+	for_each_lpi_its(device, ite, its) {
+		if (!ite->collection || coll != ite->collection)
 			continue;
 
-		update_affinity_itte(kvm, itte);
+		update_affinity_ite(kvm, ite);
 	}
 }
 
@@ -310,20 +382,20 @@ static u32 max_lpis_propbaser(u64 propbaser)
 }
 
 /*
- * Scan the whole LPI pending table and sync the pending bit in there
+ * Sync the pending table pending bit of LPIs targeting @vcpu
  * with our own data structures. This relies on the LPI being
  * mapped before.
  */
 static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 {
-	gpa_t pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+	gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
 	struct vgic_irq *irq;
 	int last_byte_offset = -1;
 	int ret = 0;
 	u32 *intids;
 	int nr_irqs, i;
 
-	nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
+	nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
 	if (nr_irqs < 0)
 		return nr_irqs;
 
@@ -364,6 +436,7 @@ static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
 					      struct vgic_its *its,
 					      gpa_t addr, unsigned int len)
 {
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
 	u64 reg = GITS_TYPER_PLPIS;
 
 	/*
@@ -374,8 +447,9 @@ static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
 	 * To avoid memory waste in the guest, we keep the number of IDBits and
 	 * DevBits low - as least for the time being.
 	 */
-	reg |= 0x0f << GITS_TYPER_DEVBITS_SHIFT;
-	reg |= 0x0f << GITS_TYPER_IDBITS_SHIFT;
+	reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT;
+	reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT;
+	reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT;
 
 	return extract_bytes(reg, addr & 7, len);
 }
@@ -384,7 +458,23 @@ static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm,
 					     struct vgic_its *its,
 					     gpa_t addr, unsigned int len)
 {
-	return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+	u32 val;
+
+	val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK;
+	val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM;
+	return val;
+}
+
+static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm,
+					    struct vgic_its *its,
+					    gpa_t addr, unsigned int len,
+					    unsigned long val)
+{
+	u32 rev = GITS_IIDR_REV(val);
+
+	if (rev >= NR_ITS_ABIS)
+		return -EINVAL;
+	return vgic_its_set_abi(its, rev);
 }
 
 static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
@@ -425,25 +515,25 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
 				u32 devid, u32 eventid)
 {
 	struct kvm_vcpu *vcpu;
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 	if (!its->enabled)
 		return -EBUSY;
 
-	itte = find_itte(its, devid, eventid);
-	if (!itte || !its_is_collection_mapped(itte->collection))
+	ite = find_ite(its, devid, eventid);
+	if (!ite || !its_is_collection_mapped(ite->collection))
 		return E_ITS_INT_UNMAPPED_INTERRUPT;
 
-	vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+	vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
 	if (!vcpu)
 		return E_ITS_INT_UNMAPPED_INTERRUPT;
 
 	if (!vcpu->arch.vgic_cpu.lpis_enabled)
 		return -EBUSY;
 
-	spin_lock(&itte->irq->irq_lock);
-	itte->irq->pending_latch = true;
-	vgic_queue_irq_unlock(kvm, itte->irq);
+	spin_lock(&ite->irq->irq_lock);
+	ite->irq->pending_latch = true;
+	vgic_queue_irq_unlock(kvm, ite->irq);
 
 	return 0;
 }
@@ -511,15 +601,15 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
 }
 
 /* Requires the its_lock to be held. */
-static void its_free_itte(struct kvm *kvm, struct its_itte *itte)
+static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
 {
-	list_del(&itte->itte_list);
+	list_del(&ite->ite_list);
 
 	/* This put matches the get in vgic_add_lpi. */
-	if (itte->irq)
-		vgic_put_irq(kvm, itte->irq);
+	if (ite->irq)
+		vgic_put_irq(kvm, ite->irq);
 
-	kfree(itte);
+	kfree(ite);
 }
 
 static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
@@ -529,9 +619,11 @@ static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
 
 #define its_cmd_get_command(cmd)	its_cmd_mask_field(cmd, 0,  0,  8)
 #define its_cmd_get_deviceid(cmd)	its_cmd_mask_field(cmd, 0, 32, 32)
+#define its_cmd_get_size(cmd)		(its_cmd_mask_field(cmd, 1,  0,  5) + 1)
 #define its_cmd_get_id(cmd)		its_cmd_mask_field(cmd, 1,  0, 32)
 #define its_cmd_get_physical_id(cmd)	its_cmd_mask_field(cmd, 1, 32, 32)
 #define its_cmd_get_collection(cmd)	its_cmd_mask_field(cmd, 2,  0, 16)
+#define its_cmd_get_ittaddr(cmd)	(its_cmd_mask_field(cmd, 2,  8, 44) << 8)
 #define its_cmd_get_target_addr(cmd)	its_cmd_mask_field(cmd, 2, 16, 32)
 #define its_cmd_get_validbit(cmd)	its_cmd_mask_field(cmd, 2, 63,  1)
 
@@ -544,17 +636,17 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
 {
 	u32 device_id = its_cmd_get_deviceid(its_cmd);
 	u32 event_id = its_cmd_get_id(its_cmd);
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 
-	itte = find_itte(its, device_id, event_id);
-	if (itte && itte->collection) {
+	ite = find_ite(its, device_id, event_id);
+	if (ite && ite->collection) {
 		/*
 		 * Though the spec talks about removing the pending state, we
 		 * don't bother here since we clear the ITTE anyway and the
 		 * pending state is a property of the ITTE struct.
 		 */
-		its_free_itte(kvm, itte);
+		its_free_ite(kvm, ite);
 		return 0;
 	}
 
@@ -572,26 +664,26 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
 	u32 event_id = its_cmd_get_id(its_cmd);
 	u32 coll_id = its_cmd_get_collection(its_cmd);
 	struct kvm_vcpu *vcpu;
-	struct its_itte *itte;
+	struct its_ite *ite;
 	struct its_collection *collection;
 
-	itte = find_itte(its, device_id, event_id);
-	if (!itte)
+	ite = find_ite(its, device_id, event_id);
+	if (!ite)
 		return E_ITS_MOVI_UNMAPPED_INTERRUPT;
 
-	if (!its_is_collection_mapped(itte->collection))
+	if (!its_is_collection_mapped(ite->collection))
 		return E_ITS_MOVI_UNMAPPED_COLLECTION;
 
 	collection = find_collection(its, coll_id);
 	if (!its_is_collection_mapped(collection))
 		return E_ITS_MOVI_UNMAPPED_COLLECTION;
 
-	itte->collection = collection;
+	ite->collection = collection;
 	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
 
-	spin_lock(&itte->irq->irq_lock);
-	itte->irq->target_vcpu = vcpu;
-	spin_unlock(&itte->irq->irq_lock);
+	spin_lock(&ite->irq->irq_lock);
+	ite->irq->target_vcpu = vcpu;
+	spin_unlock(&ite->irq->irq_lock);
 
 	return 0;
 }
@@ -600,16 +692,31 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
  * Check whether an ID can be stored into the corresponding guest table.
  * For a direct table this is pretty easy, but gets a bit nasty for
  * indirect tables. We check whether the resulting guest physical address
- * is actually valid (covered by a memslot and guest accessbible).
+ * is actually valid (covered by a memslot and guest accessible).
  * For this we have to read the respective first level entry.
  */
-static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
+static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
+			      gpa_t *eaddr)
 {
 	int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+	u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
+	int esz = GITS_BASER_ENTRY_SIZE(baser);
 	int index;
-	u64 indirect_ptr;
 	gfn_t gfn;
-	int esz = GITS_BASER_ENTRY_SIZE(baser);
+
+	switch (type) {
+	case GITS_BASER_TYPE_DEVICE:
+		if (id >= BIT_ULL(VITS_TYPER_DEVBITS))
+			return false;
+		break;
+	case GITS_BASER_TYPE_COLLECTION:
+		/* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */
+		if (id >= BIT_ULL(16))
+			return false;
+		break;
+	default:
+		return false;
+	}
 
 	if (!(baser & GITS_BASER_INDIRECT)) {
 		phys_addr_t addr;
@@ -620,6 +727,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 		addr = BASER_ADDRESS(baser) + id * esz;
 		gfn = addr >> PAGE_SHIFT;
 
+		if (eaddr)
+			*eaddr = addr;
 		return kvm_is_visible_gfn(its->dev->kvm, gfn);
 	}
 
@@ -652,6 +761,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 	indirect_ptr += index * esz;
 	gfn = indirect_ptr >> PAGE_SHIFT;
 
+	if (eaddr)
+		*eaddr = indirect_ptr;
 	return kvm_is_visible_gfn(its->dev->kvm, gfn);
 }
 
@@ -661,7 +772,7 @@ static int vgic_its_alloc_collection(struct vgic_its *its,
 {
 	struct its_collection *collection;
 
-	if (!vgic_its_check_id(its, its->baser_coll_table, coll_id))
+	if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL))
 		return E_ITS_MAPC_COLLECTION_OOR;
 
 	collection = kzalloc(sizeof(*collection), GFP_KERNEL);
@@ -679,7 +790,7 @@ static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
 {
 	struct its_collection *collection;
 	struct its_device *device;
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 	/*
 	 * Clearing the mapping for that collection ID removes the
@@ -690,15 +801,34 @@ static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
 	if (!collection)
 		return;
 
-	for_each_lpi_its(device, itte, its)
-		if (itte->collection &&
-		    itte->collection->collection_id == coll_id)
-			itte->collection = NULL;
+	for_each_lpi_its(device, ite, its)
+		if (ite->collection &&
+		    ite->collection->collection_id == coll_id)
+			ite->collection = NULL;
 
 	list_del(&collection->coll_list);
 	kfree(collection);
 }
 
+/* Must be called with its_lock mutex held */
+static struct its_ite *vgic_its_alloc_ite(struct its_device *device,
+					  struct its_collection *collection,
+					  u32 lpi_id, u32 event_id)
+{
+	struct its_ite *ite;
+
+	ite = kzalloc(sizeof(*ite), GFP_KERNEL);
+	if (!ite)
+		return ERR_PTR(-ENOMEM);
+
+	ite->event_id	= event_id;
+	ite->collection = collection;
+	ite->lpi = lpi_id;
+
+	list_add_tail(&ite->ite_list, &device->itt_head);
+	return ite;
+}
+
 /*
  * The MAPTI and MAPI commands map LPIs to ITTEs.
  * Must be called with its_lock mutex held.
@@ -709,16 +839,20 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
 	u32 device_id = its_cmd_get_deviceid(its_cmd);
 	u32 event_id = its_cmd_get_id(its_cmd);
 	u32 coll_id = its_cmd_get_collection(its_cmd);
-	struct its_itte *itte;
+	struct its_ite *ite;
+	struct kvm_vcpu *vcpu = NULL;
 	struct its_device *device;
 	struct its_collection *collection, *new_coll = NULL;
-	int lpi_nr;
 	struct vgic_irq *irq;
+	int lpi_nr;
 
 	device = find_its_device(its, device_id);
 	if (!device)
 		return E_ITS_MAPTI_UNMAPPED_DEVICE;
 
+	if (event_id >= BIT_ULL(device->num_eventid_bits))
+		return E_ITS_MAPTI_ID_OOR;
+
 	if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI)
 		lpi_nr = its_cmd_get_physical_id(its_cmd);
 	else
@@ -728,7 +862,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
 		return E_ITS_MAPTI_PHYSICALID_OOR;
 
 	/* If there is an existing mapping, behavior is UNPREDICTABLE. */
-	if (find_itte(its, device_id, event_id))
+	if (find_ite(its, device_id, event_id))
 		return 0;
 
 	collection = find_collection(its, coll_id);
@@ -739,36 +873,24 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
 		new_coll = collection;
 	}
 
-	itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
-	if (!itte) {
+	ite = vgic_its_alloc_ite(device, collection, lpi_nr, event_id);
+	if (IS_ERR(ite)) {
 		if (new_coll)
 			vgic_its_free_collection(its, coll_id);
-		return -ENOMEM;
+		return PTR_ERR(ite);
 	}
 
-	itte->event_id	= event_id;
-	list_add_tail(&itte->itte_list, &device->itt_head);
-
-	itte->collection = collection;
-	itte->lpi = lpi_nr;
+	if (its_is_collection_mapped(collection))
+		vcpu = kvm_get_vcpu(kvm, collection->target_addr);
 
-	irq = vgic_add_lpi(kvm, lpi_nr);
+	irq = vgic_add_lpi(kvm, lpi_nr, vcpu);
 	if (IS_ERR(irq)) {
 		if (new_coll)
 			vgic_its_free_collection(its, coll_id);
-		its_free_itte(kvm, itte);
+		its_free_ite(kvm, ite);
 		return PTR_ERR(irq);
 	}
-	itte->irq = irq;
-
-	update_affinity_itte(kvm, itte);
-
-	/*
-	 * We "cache" the configuration table entries in out struct vgic_irq's.
-	 * However we only have those structs for mapped IRQs, so we read in
-	 * the respective config data from memory here upon mapping the LPI.
-	 */
-	update_lpi_config(kvm, itte->irq, NULL);
+	ite->irq = irq;
 
 	return 0;
 }
@@ -776,20 +898,40 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
 /* Requires the its_lock to be held. */
 static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
 {
-	struct its_itte *itte, *temp;
+	struct its_ite *ite, *temp;
 
 	/*
 	 * The spec says that unmapping a device with still valid
 	 * ITTEs associated is UNPREDICTABLE. We remove all ITTEs,
 	 * since we cannot leave the memory unreferenced.
 	 */
-	list_for_each_entry_safe(itte, temp, &device->itt_head, itte_list)
-		its_free_itte(kvm, itte);
+	list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
+		its_free_ite(kvm, ite);
 
 	list_del(&device->dev_list);
 	kfree(device);
 }
 
+/* Must be called with its_lock mutex held */
+static struct its_device *vgic_its_alloc_device(struct vgic_its *its,
+						u32 device_id, gpa_t itt_addr,
+						u8 num_eventid_bits)
+{
+	struct its_device *device;
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return ERR_PTR(-ENOMEM);
+
+	device->device_id = device_id;
+	device->itt_addr = itt_addr;
+	device->num_eventid_bits = num_eventid_bits;
+	INIT_LIST_HEAD(&device->itt_head);
+
+	list_add_tail(&device->dev_list, &its->device_list);
+	return device;
+}
+
 /*
  * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs).
  * Must be called with the its_lock mutex held.
@@ -799,11 +941,16 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
 {
 	u32 device_id = its_cmd_get_deviceid(its_cmd);
 	bool valid = its_cmd_get_validbit(its_cmd);
+	u8 num_eventid_bits = its_cmd_get_size(its_cmd);
+	gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd);
 	struct its_device *device;
 
-	if (!vgic_its_check_id(its, its->baser_device_table, device_id))
+	if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL))
 		return E_ITS_MAPD_DEVICE_OOR;
 
+	if (valid && num_eventid_bits > VITS_TYPER_IDBITS)
+		return E_ITS_MAPD_ITTSIZE_OOR;
+
 	device = find_its_device(its, device_id);
 
 	/*
@@ -821,14 +968,10 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
 	if (!valid)
 		return 0;
 
-	device = kzalloc(sizeof(struct its_device), GFP_KERNEL);
-	if (!device)
-		return -ENOMEM;
-
-	device->device_id = device_id;
-	INIT_LIST_HEAD(&device->itt_head);
-
-	list_add_tail(&device->dev_list, &its->device_list);
+	device = vgic_its_alloc_device(its, device_id, itt_addr,
+				       num_eventid_bits);
+	if (IS_ERR(device))
+		return PTR_ERR(device);
 
 	return 0;
 }
@@ -883,14 +1026,14 @@ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
 {
 	u32 device_id = its_cmd_get_deviceid(its_cmd);
 	u32 event_id = its_cmd_get_id(its_cmd);
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 
-	itte = find_itte(its, device_id, event_id);
-	if (!itte)
+	ite = find_ite(its, device_id, event_id);
+	if (!ite)
 		return E_ITS_CLEAR_UNMAPPED_INTERRUPT;
 
-	itte->irq->pending_latch = false;
+	ite->irq->pending_latch = false;
 
 	return 0;
 }
@@ -904,14 +1047,14 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
 {
 	u32 device_id = its_cmd_get_deviceid(its_cmd);
 	u32 event_id = its_cmd_get_id(its_cmd);
-	struct its_itte *itte;
+	struct its_ite *ite;
 
 
-	itte = find_itte(its, device_id, event_id);
-	if (!itte)
+	ite = find_ite(its, device_id, event_id);
+	if (!ite)
 		return E_ITS_INV_UNMAPPED_INTERRUPT;
 
-	return update_lpi_config(kvm, itte->irq, NULL);
+	return update_lpi_config(kvm, ite->irq, NULL);
 }
 
 /*
@@ -938,7 +1081,7 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
 
 	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
 
-	irq_count = vgic_copy_lpi_list(kvm, &intids);
+	irq_count = vgic_copy_lpi_list(vcpu, &intids);
 	if (irq_count < 0)
 		return irq_count;
 
@@ -1213,6 +1356,33 @@ static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm,
 	return extract_bytes(its->creadr, addr & 0x7, len);
 }
 
+static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm,
+					      struct vgic_its *its,
+					      gpa_t addr, unsigned int len,
+					      unsigned long val)
+{
+	u32 cmd_offset;
+	int ret = 0;
+
+	mutex_lock(&its->cmd_lock);
+
+	if (its->enabled) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	cmd_offset = ITS_CMD_OFFSET(val);
+	if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	its->creadr = cmd_offset;
+out:
+	mutex_unlock(&its->cmd_lock);
+	return ret;
+}
+
 #define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7)
 static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm,
 					      struct vgic_its *its,
@@ -1241,6 +1411,7 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 				      gpa_t addr, unsigned int len,
 				      unsigned long val)
 {
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
 	u64 entry_size, device_type;
 	u64 reg, *regptr, clearbits = 0;
 
@@ -1251,12 +1422,12 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 	switch (BASER_INDEX(addr)) {
 	case 0:
 		regptr = &its->baser_device_table;
-		entry_size = 8;
+		entry_size = abi->dte_esz;
 		device_type = GITS_BASER_TYPE_DEVICE;
 		break;
 	case 1:
 		regptr = &its->baser_coll_table;
-		entry_size = 8;
+		entry_size = abi->cte_esz;
 		device_type = GITS_BASER_TYPE_COLLECTION;
 		clearbits = GITS_BASER_INDIRECT;
 		break;
@@ -1317,6 +1488,16 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
 	.its_write = wr,					\
 }
 
+#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\
+{								\
+	.reg_offset = off,					\
+	.len = length,						\
+	.access_flags = acc,					\
+	.its_read = rd,						\
+	.its_write = wr,					\
+	.uaccess_its_write = uwr,				\
+}
+
 static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its,
 			      gpa_t addr, unsigned int len, unsigned long val)
 {
@@ -1327,8 +1508,9 @@ static struct vgic_register_region its_registers[] = {
 	REGISTER_ITS_DESC(GITS_CTLR,
 		vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4,
 		VGIC_ACCESS_32bit),
-	REGISTER_ITS_DESC(GITS_IIDR,
-		vgic_mmio_read_its_iidr, its_mmio_write_wi, 4,
+	REGISTER_ITS_DESC_UACCESS(GITS_IIDR,
+		vgic_mmio_read_its_iidr, its_mmio_write_wi,
+		vgic_mmio_uaccess_write_its_iidr, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_ITS_DESC(GITS_TYPER,
 		vgic_mmio_read_its_typer, its_mmio_write_wi, 8,
@@ -1339,8 +1521,9 @@ static struct vgic_register_region its_registers[] = {
 	REGISTER_ITS_DESC(GITS_CWRITER,
 		vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
-	REGISTER_ITS_DESC(GITS_CREADR,
-		vgic_mmio_read_its_creadr, its_mmio_write_wi, 8,
+	REGISTER_ITS_DESC_UACCESS(GITS_CREADR,
+		vgic_mmio_read_its_creadr, its_mmio_write_wi,
+		vgic_mmio_uaccess_write_its_creadr, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
 	REGISTER_ITS_DESC(GITS_BASER,
 		vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40,
@@ -1357,17 +1540,19 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu)
 		its_sync_lpi_pending_table(vcpu);
 }
 
-static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its,
+				   u64 addr)
 {
 	struct vgic_io_device *iodev = &its->iodev;
 	int ret;
 
-	if (!its->initialized)
-		return -EBUSY;
-
-	if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
-		return -ENXIO;
+	mutex_lock(&kvm->slots_lock);
+	if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+		ret = -EBUSY;
+		goto out;
+	}
 
+	its->vgic_its_base = addr;
 	iodev->regions = its_registers;
 	iodev->nr_regions = ARRAY_SIZE(its_registers);
 	kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops);
@@ -1375,9 +1560,9 @@ static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
 	iodev->base_addr = its->vgic_its_base;
 	iodev->iodev_type = IODEV_ITS;
 	iodev->its = its;
-	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr,
 				      KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
+out:
 	mutex_unlock(&kvm->slots_lock);
 
 	return ret;
@@ -1387,7 +1572,6 @@ static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
 	(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb)		| \
 	 GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner)		| \
 	 GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)		| \
-	 ((8ULL - 1) << GITS_BASER_ENTRY_SIZE_SHIFT)			| \
 	 GITS_BASER_PAGE_SIZE_64K)
 
 #define INITIAL_PROPBASER_VALUE						  \
@@ -1415,7 +1599,6 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
 	INIT_LIST_HEAD(&its->collection_list);
 
 	dev->kvm->arch.vgic.has_its = true;
-	its->initialized = false;
 	its->enabled = false;
 	its->dev = dev;
 
@@ -1427,16 +1610,23 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
 
 	dev->private = its;
 
-	return 0;
+	return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
+}
+
+static void vgic_its_free_device(struct kvm *kvm, struct its_device *dev)
+{
+	struct its_ite *ite, *tmp;
+
+	list_for_each_entry_safe(ite, tmp, &dev->itt_head, ite_list)
+		its_free_ite(kvm, ite);
+	list_del(&dev->dev_list);
+	kfree(dev);
 }
 
 static void vgic_its_destroy(struct kvm_device *kvm_dev)
 {
 	struct kvm *kvm = kvm_dev->kvm;
 	struct vgic_its *its = kvm_dev->private;
-	struct its_device *dev;
-	struct its_itte *itte;
-	struct list_head *dev_cur, *dev_temp;
 	struct list_head *cur, *temp;
 
 	/*
@@ -1447,25 +1637,710 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
 		return;
 
 	mutex_lock(&its->its_lock);
-	list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
-		dev = container_of(dev_cur, struct its_device, dev_list);
-		list_for_each_safe(cur, temp, &dev->itt_head) {
-			itte = (container_of(cur, struct its_itte, itte_list));
-			its_free_itte(kvm, itte);
-		}
-		list_del(dev_cur);
-		kfree(dev);
+	list_for_each_safe(cur, temp, &its->device_list) {
+		struct its_device *dev;
+
+		dev = list_entry(cur, struct its_device, dev_list);
+		vgic_its_free_device(kvm, dev);
 	}
 
 	list_for_each_safe(cur, temp, &its->collection_list) {
+		struct its_collection *coll;
+
+		coll = list_entry(cur, struct its_collection, coll_list);
 		list_del(cur);
-		kfree(container_of(cur, struct its_collection, coll_list));
+		kfree(coll);
 	}
 	mutex_unlock(&its->its_lock);
 
 	kfree(its);
 }
 
+int vgic_its_has_attr_regs(struct kvm_device *dev,
+			   struct kvm_device_attr *attr)
+{
+	const struct vgic_register_region *region;
+	gpa_t offset = attr->attr;
+	int align;
+
+	align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7;
+
+	if (offset & align)
+		return -EINVAL;
+
+	region = vgic_find_mmio_region(its_registers,
+				       ARRAY_SIZE(its_registers),
+				       offset);
+	if (!region)
+		return -ENXIO;
+
+	return 0;
+}
+
+int vgic_its_attr_regs_access(struct kvm_device *dev,
+			      struct kvm_device_attr *attr,
+			      u64 *reg, bool is_write)
+{
+	const struct vgic_register_region *region;
+	struct vgic_its *its;
+	gpa_t addr, offset;
+	unsigned int len;
+	int align, ret = 0;
+
+	its = dev->private;
+	offset = attr->attr;
+
+	/*
+	 * Although the spec supports upper/lower 32-bit accesses to
+	 * 64-bit ITS registers, the userspace ABI requires 64-bit
+	 * accesses to all 64-bit wide registers. We therefore only
+	 * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID
+	 * registers
+	 */
+	if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4))
+		align = 0x3;
+	else
+		align = 0x7;
+
+	if (offset & align)
+		return -EINVAL;
+
+	mutex_lock(&dev->kvm->lock);
+
+	if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+	region = vgic_find_mmio_region(its_registers,
+				       ARRAY_SIZE(its_registers),
+				       offset);
+	if (!region) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (!lock_all_vcpus(dev->kvm)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	addr = its->vgic_its_base + offset;
+
+	len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4;
+
+	if (is_write) {
+		if (region->uaccess_its_write)
+			ret = region->uaccess_its_write(dev->kvm, its, addr,
+							len, *reg);
+		else
+			region->its_write(dev->kvm, its, addr, len, *reg);
+	} else {
+		*reg = region->its_read(dev->kvm, its, addr, len);
+	}
+	unlock_all_vcpus(dev->kvm);
+out:
+	mutex_unlock(&dev->kvm->lock);
+	return ret;
+}
+
+static u32 compute_next_devid_offset(struct list_head *h,
+				     struct its_device *dev)
+{
+	struct its_device *next;
+	u32 next_offset;
+
+	if (list_is_last(&dev->dev_list, h))
+		return 0;
+	next = list_next_entry(dev, dev_list);
+	next_offset = next->device_id - dev->device_id;
+
+	return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET);
+}
+
+static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
+{
+	struct its_ite *next;
+	u32 next_offset;
+
+	if (list_is_last(&ite->ite_list, h))
+		return 0;
+	next = list_next_entry(ite, ite_list);
+	next_offset = next->event_id - ite->event_id;
+
+	return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET);
+}
+
+/**
+ * entry_fn_t - Callback called on a table entry restore path
+ * @its: its handle
+ * @id: id of the entry
+ * @entry: pointer to the entry
+ * @opaque: pointer to an opaque data
+ *
+ * Return: < 0 on error, 0 if last element was identified, id offset to next
+ * element otherwise
+ */
+typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
+			  void *opaque);
+
+/**
+ * scan_its_table - Scan a contiguous table in guest RAM and applies a function
+ * to each entry
+ *
+ * @its: its handle
+ * @base: base gpa of the table
+ * @size: size of the table in bytes
+ * @esz: entry size in bytes
+ * @start_id: the ID of the first entry in the table
+ * (non zero for 2d level tables)
+ * @fn: function to apply on each entry
+ *
+ * Return: < 0 on error, 0 if last element was identified, 1 otherwise
+ * (the last element may not be found on second level tables)
+ */
+static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
+			  int start_id, entry_fn_t fn, void *opaque)
+{
+	void *entry = kzalloc(esz, GFP_KERNEL);
+	struct kvm *kvm = its->dev->kvm;
+	unsigned long len = size;
+	int id = start_id;
+	gpa_t gpa = base;
+	int ret;
+
+	while (len > 0) {
+		int next_offset;
+		size_t byte_offset;
+
+		ret = kvm_read_guest(kvm, gpa, entry, esz);
+		if (ret)
+			goto out;
+
+		next_offset = fn(its, id, entry, opaque);
+		if (next_offset <= 0) {
+			ret = next_offset;
+			goto out;
+		}
+
+		byte_offset = next_offset * esz;
+		id += next_offset;
+		gpa += byte_offset;
+		len -= byte_offset;
+	}
+	ret =  1;
+
+out:
+	kfree(entry);
+	return ret;
+}
+
+/**
+ * vgic_its_save_ite - Save an interrupt translation entry at @gpa
+ */
+static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
+			      struct its_ite *ite, gpa_t gpa, int ite_esz)
+{
+	struct kvm *kvm = its->dev->kvm;
+	u32 next_offset;
+	u64 val;
+
+	next_offset = compute_next_eventid_offset(&dev->itt_head, ite);
+	val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) |
+	       ((u64)ite->lpi << KVM_ITS_ITE_PINTID_SHIFT) |
+		ite->collection->collection_id;
+	val = cpu_to_le64(val);
+	return kvm_write_guest(kvm, gpa, &val, ite_esz);
+}
+
+/**
+ * vgic_its_restore_ite - restore an interrupt translation entry
+ * @event_id: id used for indexing
+ * @ptr: pointer to the ITE entry
+ * @opaque: pointer to the its_device
+ */
+static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id,
+				void *ptr, void *opaque)
+{
+	struct its_device *dev = (struct its_device *)opaque;
+	struct its_collection *collection;
+	struct kvm *kvm = its->dev->kvm;
+	struct kvm_vcpu *vcpu = NULL;
+	u64 val;
+	u64 *p = (u64 *)ptr;
+	struct vgic_irq *irq;
+	u32 coll_id, lpi_id;
+	struct its_ite *ite;
+	u32 offset;
+
+	val = *p;
+
+	val = le64_to_cpu(val);
+
+	coll_id = val & KVM_ITS_ITE_ICID_MASK;
+	lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT;
+
+	if (!lpi_id)
+		return 1; /* invalid entry, no choice but to scan next entry */
+
+	if (lpi_id < VGIC_MIN_LPI)
+		return -EINVAL;
+
+	offset = val >> KVM_ITS_ITE_NEXT_SHIFT;
+	if (event_id + offset >= BIT_ULL(dev->num_eventid_bits))
+		return -EINVAL;
+
+	collection = find_collection(its, coll_id);
+	if (!collection)
+		return -EINVAL;
+
+	ite = vgic_its_alloc_ite(dev, collection, lpi_id, event_id);
+	if (IS_ERR(ite))
+		return PTR_ERR(ite);
+
+	if (its_is_collection_mapped(collection))
+		vcpu = kvm_get_vcpu(kvm, collection->target_addr);
+
+	irq = vgic_add_lpi(kvm, lpi_id, vcpu);
+	if (IS_ERR(irq))
+		return PTR_ERR(irq);
+	ite->irq = irq;
+
+	return offset;
+}
+
+static int vgic_its_ite_cmp(void *priv, struct list_head *a,
+			    struct list_head *b)
+{
+	struct its_ite *itea = container_of(a, struct its_ite, ite_list);
+	struct its_ite *iteb = container_of(b, struct its_ite, ite_list);
+
+	if (itea->event_id < iteb->event_id)
+		return -1;
+	else
+		return 1;
+}
+
+static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	gpa_t base = device->itt_addr;
+	struct its_ite *ite;
+	int ret;
+	int ite_esz = abi->ite_esz;
+
+	list_sort(NULL, &device->itt_head, vgic_its_ite_cmp);
+
+	list_for_each_entry(ite, &device->itt_head, ite_list) {
+		gpa_t gpa = base + ite->event_id * ite_esz;
+
+		ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	gpa_t base = dev->itt_addr;
+	int ret;
+	int ite_esz = abi->ite_esz;
+	size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz;
+
+	ret = scan_its_table(its, base, max_size, ite_esz, 0,
+			     vgic_its_restore_ite, dev);
+
+	return ret;
+}
+
+/**
+ * vgic_its_save_dte - Save a device table entry at a given GPA
+ *
+ * @its: ITS handle
+ * @dev: ITS device
+ * @ptr: GPA
+ */
+static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
+			     gpa_t ptr, int dte_esz)
+{
+	struct kvm *kvm = its->dev->kvm;
+	u64 val, itt_addr_field;
+	u32 next_offset;
+
+	itt_addr_field = dev->itt_addr >> 8;
+	next_offset = compute_next_devid_offset(&its->device_list, dev);
+	val = (1ULL << KVM_ITS_DTE_VALID_SHIFT |
+	       ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) |
+	       (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
+		(dev->num_eventid_bits - 1));
+	val = cpu_to_le64(val);
+	return kvm_write_guest(kvm, ptr, &val, dte_esz);
+}
+
+/**
+ * vgic_its_restore_dte - restore a device table entry
+ *
+ * @its: its handle
+ * @id: device id the DTE corresponds to
+ * @ptr: kernel VA where the 8 byte DTE is located
+ * @opaque: unused
+ *
+ * Return: < 0 on error, 0 if the dte is the last one, id offset to the
+ * next dte otherwise
+ */
+static int vgic_its_restore_dte(struct vgic_its *its, u32 id,
+				void *ptr, void *opaque)
+{
+	struct its_device *dev;
+	gpa_t itt_addr;
+	u8 num_eventid_bits;
+	u64 entry = *(u64 *)ptr;
+	bool valid;
+	u32 offset;
+	int ret;
+
+	entry = le64_to_cpu(entry);
+
+	valid = entry >> KVM_ITS_DTE_VALID_SHIFT;
+	num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1;
+	itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK)
+			>> KVM_ITS_DTE_ITTADDR_SHIFT) << 8;
+
+	if (!valid)
+		return 1;
+
+	/* dte entry is valid */
+	offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT;
+
+	dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	ret = vgic_its_restore_itt(its, dev);
+	if (ret) {
+		vgic_its_free_device(its->dev->kvm, dev);
+		return ret;
+	}
+
+	return offset;
+}
+
+static int vgic_its_device_cmp(void *priv, struct list_head *a,
+			       struct list_head *b)
+{
+	struct its_device *deva = container_of(a, struct its_device, dev_list);
+	struct its_device *devb = container_of(b, struct its_device, dev_list);
+
+	if (deva->device_id < devb->device_id)
+		return -1;
+	else
+		return 1;
+}
+
+/**
+ * vgic_its_save_device_tables - Save the device table and all ITT
+ * into guest RAM
+ *
+ * L1/L2 handling is hidden by vgic_its_check_id() helper which directly
+ * returns the GPA of the device entry
+ */
+static int vgic_its_save_device_tables(struct vgic_its *its)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	struct its_device *dev;
+	int dte_esz = abi->dte_esz;
+	u64 baser;
+
+	baser = its->baser_device_table;
+
+	list_sort(NULL, &its->device_list, vgic_its_device_cmp);
+
+	list_for_each_entry(dev, &its->device_list, dev_list) {
+		int ret;
+		gpa_t eaddr;
+
+		if (!vgic_its_check_id(its, baser,
+				       dev->device_id, &eaddr))
+			return -EINVAL;
+
+		ret = vgic_its_save_itt(its, dev);
+		if (ret)
+			return ret;
+
+		ret = vgic_its_save_dte(its, dev, eaddr, dte_esz);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/**
+ * handle_l1_dte - callback used for L1 device table entries (2 stage case)
+ *
+ * @its: its handle
+ * @id: index of the entry in the L1 table
+ * @addr: kernel VA
+ * @opaque: unused
+ *
+ * L1 table entries are scanned by steps of 1 entry
+ * Return < 0 if error, 0 if last dte was found when scanning the L2
+ * table, +1 otherwise (meaning next L1 entry must be scanned)
+ */
+static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
+			 void *opaque)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	int l2_start_id = id * (SZ_64K / abi->dte_esz);
+	u64 entry = *(u64 *)addr;
+	int dte_esz = abi->dte_esz;
+	gpa_t gpa;
+	int ret;
+
+	entry = le64_to_cpu(entry);
+
+	if (!(entry & KVM_ITS_L1E_VALID_MASK))
+		return 1;
+
+	gpa = entry & KVM_ITS_L1E_ADDR_MASK;
+
+	ret = scan_its_table(its, gpa, SZ_64K, dte_esz,
+			     l2_start_id, vgic_its_restore_dte, NULL);
+
+	if (ret <= 0)
+		return ret;
+
+	return 1;
+}
+
+/**
+ * vgic_its_restore_device_tables - Restore the device table and all ITT
+ * from guest RAM to internal data structs
+ */
+static int vgic_its_restore_device_tables(struct vgic_its *its)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	u64 baser = its->baser_device_table;
+	int l1_esz, ret;
+	int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+	gpa_t l1_gpa;
+
+	if (!(baser & GITS_BASER_VALID))
+		return 0;
+
+	l1_gpa = BASER_ADDRESS(baser);
+
+	if (baser & GITS_BASER_INDIRECT) {
+		l1_esz = GITS_LVL1_ENTRY_SIZE;
+		ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+				     handle_l1_dte, NULL);
+	} else {
+		l1_esz = abi->dte_esz;
+		ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+				     vgic_its_restore_dte, NULL);
+	}
+
+	if (ret > 0)
+		ret = -EINVAL;
+
+	return ret;
+}
+
+static int vgic_its_save_cte(struct vgic_its *its,
+			     struct its_collection *collection,
+			     gpa_t gpa, int esz)
+{
+	u64 val;
+
+	val = (1ULL << KVM_ITS_CTE_VALID_SHIFT |
+	       ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
+	       collection->collection_id);
+	val = cpu_to_le64(val);
+	return kvm_write_guest(its->dev->kvm, gpa, &val, esz);
+}
+
+static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
+{
+	struct its_collection *collection;
+	struct kvm *kvm = its->dev->kvm;
+	u32 target_addr, coll_id;
+	u64 val;
+	int ret;
+
+	BUG_ON(esz > sizeof(val));
+	ret = kvm_read_guest(kvm, gpa, &val, esz);
+	if (ret)
+		return ret;
+	val = le64_to_cpu(val);
+	if (!(val & KVM_ITS_CTE_VALID_MASK))
+		return 0;
+
+	target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT);
+	coll_id = val & KVM_ITS_CTE_ICID_MASK;
+
+	if (target_addr >= atomic_read(&kvm->online_vcpus))
+		return -EINVAL;
+
+	collection = find_collection(its, coll_id);
+	if (collection)
+		return -EEXIST;
+	ret = vgic_its_alloc_collection(its, &collection, coll_id);
+	if (ret)
+		return ret;
+	collection->target_addr = target_addr;
+	return 1;
+}
+
+/**
+ * vgic_its_save_collection_table - Save the collection table into
+ * guest RAM
+ */
+static int vgic_its_save_collection_table(struct vgic_its *its)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	struct its_collection *collection;
+	u64 val;
+	gpa_t gpa;
+	size_t max_size, filled = 0;
+	int ret, cte_esz = abi->cte_esz;
+
+	gpa = BASER_ADDRESS(its->baser_coll_table);
+	if (!gpa)
+		return 0;
+
+	max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+	list_for_each_entry(collection, &its->collection_list, coll_list) {
+		ret = vgic_its_save_cte(its, collection, gpa, cte_esz);
+		if (ret)
+			return ret;
+		gpa += cte_esz;
+		filled += cte_esz;
+	}
+
+	if (filled == max_size)
+		return 0;
+
+	/*
+	 * table is not fully filled, add a last dummy element
+	 * with valid bit unset
+	 */
+	val = 0;
+	BUG_ON(cte_esz > sizeof(val));
+	ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz);
+	return ret;
+}
+
+/**
+ * vgic_its_restore_collection_table - reads the collection table
+ * in guest memory and restores the ITS internal state. Requires the
+ * BASER registers to be restored before.
+ */
+static int vgic_its_restore_collection_table(struct vgic_its *its)
+{
+	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	int cte_esz = abi->cte_esz;
+	size_t max_size, read = 0;
+	gpa_t gpa;
+	int ret;
+
+	if (!(its->baser_coll_table & GITS_BASER_VALID))
+		return 0;
+
+	gpa = BASER_ADDRESS(its->baser_coll_table);
+
+	max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+	while (read < max_size) {
+		ret = vgic_its_restore_cte(its, gpa, cte_esz);
+		if (ret <= 0)
+			break;
+		gpa += cte_esz;
+		read += cte_esz;
+	}
+	return ret;
+}
+
+/**
+ * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
+ * according to v0 ABI
+ */
+static int vgic_its_save_tables_v0(struct vgic_its *its)
+{
+	struct kvm *kvm = its->dev->kvm;
+	int ret;
+
+	mutex_lock(&kvm->lock);
+	mutex_lock(&its->its_lock);
+
+	if (!lock_all_vcpus(kvm)) {
+		mutex_unlock(&its->its_lock);
+		mutex_unlock(&kvm->lock);
+		return -EBUSY;
+	}
+
+	ret = vgic_its_save_device_tables(its);
+	if (ret)
+		goto out;
+
+	ret = vgic_its_save_collection_table(its);
+
+out:
+	unlock_all_vcpus(kvm);
+	mutex_unlock(&its->its_lock);
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
+/**
+ * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
+ * to internal data structs according to V0 ABI
+ *
+ */
+static int vgic_its_restore_tables_v0(struct vgic_its *its)
+{
+	struct kvm *kvm = its->dev->kvm;
+	int ret;
+
+	mutex_lock(&kvm->lock);
+	mutex_lock(&its->its_lock);
+
+	if (!lock_all_vcpus(kvm)) {
+		mutex_unlock(&its->its_lock);
+		mutex_unlock(&kvm->lock);
+		return -EBUSY;
+	}
+
+	ret = vgic_its_restore_collection_table(its);
+	if (ret)
+		goto out;
+
+	ret = vgic_its_restore_device_tables(its);
+out:
+	unlock_all_vcpus(kvm);
+	mutex_unlock(&its->its_lock);
+	mutex_unlock(&kvm->lock);
+
+	return ret;
+}
+
+static int vgic_its_commit_v0(struct vgic_its *its)
+{
+	const struct vgic_its_abi *abi;
+
+	abi = vgic_its_get_abi(its);
+	its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+	its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+
+	its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5)
+					<< GITS_BASER_ENTRY_SIZE_SHIFT);
+
+	its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5)
+					<< GITS_BASER_ENTRY_SIZE_SHIFT);
+	return 0;
+}
+
 static int vgic_its_has_attr(struct kvm_device *dev,
 			     struct kvm_device_attr *attr)
 {
@@ -1480,8 +2355,14 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_ARM_VGIC_CTRL_INIT:
 			return 0;
+		case KVM_DEV_ARM_ITS_SAVE_TABLES:
+			return 0;
+		case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+			return 0;
 		}
 		break;
+	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS:
+		return vgic_its_has_attr_regs(dev, attr);
 	}
 	return -ENXIO;
 }
@@ -1509,18 +2390,30 @@ static int vgic_its_set_attr(struct kvm_device *dev,
 		if (ret)
 			return ret;
 
-		its->vgic_its_base = addr;
-
-		return 0;
+		return vgic_register_its_iodev(dev->kvm, its, addr);
 	}
-	case KVM_DEV_ARM_VGIC_GRP_CTRL:
+	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+		const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+
 		switch (attr->attr) {
 		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			its->initialized = true;
-
+			/* Nothing to do */
 			return 0;
+		case KVM_DEV_ARM_ITS_SAVE_TABLES:
+			return abi->save_tables(its);
+		case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+			return abi->restore_tables(its);
 		}
-		break;
+	}
+	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		u64 reg;
+
+		if (get_user(reg, uaddr))
+			return -EFAULT;
+
+		return vgic_its_attr_regs_access(dev, attr, &reg, true);
+	}
 	}
 	return -ENXIO;
 }
@@ -1541,10 +2434,20 @@ static int vgic_its_get_attr(struct kvm_device *dev,
 		if (copy_to_user(uaddr, &addr, sizeof(addr)))
 			return -EFAULT;
 		break;
+	}
+	case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		u64 reg;
+		int ret;
+
+		ret = vgic_its_attr_regs_access(dev, attr, &reg, false);
+		if (ret)
+			return ret;
+		return put_user(reg, uaddr);
+	}
 	default:
 		return -ENXIO;
 	}
-	}
 
 	return 0;
 }
@@ -1563,30 +2466,3 @@ int kvm_vgic_register_its_device(void)
 	return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
 				       KVM_DEV_TYPE_ARM_VGIC_ITS);
 }
-
-/*
- * Registers all ITSes with the kvm_io_bus framework.
- * To follow the existing VGIC initialization sequence, this has to be
- * done as late as possible, just before the first VCPU runs.
- */
-int vgic_register_its_iodevs(struct kvm *kvm)
-{
-	struct kvm_device *dev;
-	int ret = 0;
-
-	list_for_each_entry(dev, &kvm->devices, vm_node) {
-		if (dev->ops != &kvm_arm_vgic_its_ops)
-			continue;
-
-		ret = vgic_register_its_iodev(kvm, dev->private);
-		if (ret)
-			return ret;
-		/*
-		 * We don't need to care about tearing down previously
-		 * registered ITSes, as the kvm_io_bus framework removes
-		 * them for us if the VM gets destroyed.
-		 */
-	}
-
-	return ret;
-}
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index d181d2baee9c..10ae6f394b71 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -37,6 +37,14 @@ int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
 	return 0;
 }
 
+static int vgic_check_type(struct kvm *kvm, int type_needed)
+{
+	if (kvm->arch.vgic.vgic_model != type_needed)
+		return -ENODEV;
+	else
+		return 0;
+}
+
 /**
  * kvm_vgic_addr - set or get vgic VM base addresses
  * @kvm:   pointer to the vm struct
@@ -57,40 +65,41 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 {
 	int r = 0;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
-	int type_needed;
 	phys_addr_t *addr_ptr, alignment;
 
 	mutex_lock(&kvm->lock);
 	switch (type) {
 	case KVM_VGIC_V2_ADDR_TYPE_DIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 		addr_ptr = &vgic->vgic_dist_base;
 		alignment = SZ_4K;
 		break;
 	case KVM_VGIC_V2_ADDR_TYPE_CPU:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 		addr_ptr = &vgic->vgic_cpu_base;
 		alignment = SZ_4K;
 		break;
 	case KVM_VGIC_V3_ADDR_TYPE_DIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
 		addr_ptr = &vgic->vgic_dist_base;
 		alignment = SZ_64K;
 		break;
 	case KVM_VGIC_V3_ADDR_TYPE_REDIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
+		if (r)
+			break;
+		if (write) {
+			r = vgic_v3_set_redist_base(kvm, *addr);
+			goto out;
+		}
 		addr_ptr = &vgic->vgic_redist_base;
-		alignment = SZ_64K;
 		break;
 	default:
 		r = -ENODEV;
-		goto out;
 	}
 
-	if (vgic->vgic_model != type_needed) {
-		r = -ENODEV;
+	if (r)
 		goto out;
-	}
 
 	if (write) {
 		r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment);
@@ -259,13 +268,13 @@ static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
 	}
 }
 
-static void unlock_all_vcpus(struct kvm *kvm)
+void unlock_all_vcpus(struct kvm *kvm)
 {
 	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
 }
 
 /* Returns true if all vcpus were locked, false otherwise */
-static bool lock_all_vcpus(struct kvm *kvm)
+bool lock_all_vcpus(struct kvm *kvm)
 {
 	struct kvm_vcpu *tmp_vcpu;
 	int c;
@@ -580,6 +589,24 @@ static int vgic_v3_set_attr(struct kvm_device *dev,
 		reg = tmp32;
 		return vgic_v3_attr_regs_access(dev, attr, &reg, true);
 	}
+	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+		int ret;
+
+		switch (attr->attr) {
+		case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+			mutex_lock(&dev->kvm->lock);
+
+			if (!lock_all_vcpus(dev->kvm)) {
+				mutex_unlock(&dev->kvm->lock);
+				return -EBUSY;
+			}
+			ret = vgic_v3_save_pending_tables(dev->kvm);
+			unlock_all_vcpus(dev->kvm);
+			mutex_unlock(&dev->kvm->lock);
+			return ret;
+		}
+		break;
+	}
 	}
 	return -ENXIO;
 }
@@ -658,6 +685,8 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_ARM_VGIC_CTRL_INIT:
 			return 0;
+		case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+			return 0;
 		}
 	}
 	return -ENXIO;
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 6afb3b484886..99da1a207c19 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -556,67 +556,130 @@ unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev)
 	return SZ_64K;
 }
 
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
+/**
+ * vgic_register_redist_iodev - register a single redist iodev
+ * @vcpu:    The VCPU to which the redistributor belongs
+ *
+ * Register a KVM iodev for this VCPU's redistributor using the address
+ * provided.
+ *
+ * Return 0 on success, -ERRNO otherwise.
+ */
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+	struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+	gpa_t rd_base, sgi_base;
+	int ret;
+
+	/*
+	 * We may be creating VCPUs before having set the base address for the
+	 * redistributor region, in which case we will come back to this
+	 * function for all VCPUs when the base address is set.  Just return
+	 * without doing any work for now.
+	 */
+	if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base))
+		return 0;
+
+	if (!vgic_v3_check_base(kvm))
+		return -EINVAL;
+
+	rd_base = vgic->vgic_redist_base + kvm_vcpu_get_idx(vcpu) * SZ_64K * 2;
+	sgi_base = rd_base + SZ_64K;
+
+	kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
+	rd_dev->base_addr = rd_base;
+	rd_dev->iodev_type = IODEV_REDIST;
+	rd_dev->regions = vgic_v3_rdbase_registers;
+	rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
+	rd_dev->redist_vcpu = vcpu;
+
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
+				      SZ_64K, &rd_dev->dev);
+	mutex_unlock(&kvm->slots_lock);
+
+	if (ret)
+		return ret;
+
+	kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
+	sgi_dev->base_addr = sgi_base;
+	sgi_dev->iodev_type = IODEV_REDIST;
+	sgi_dev->regions = vgic_v3_sgibase_registers;
+	sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
+	sgi_dev->redist_vcpu = vcpu;
+
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
+				      SZ_64K, &sgi_dev->dev);
+	mutex_unlock(&kvm->slots_lock);
+	if (ret)
+		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+					  &rd_dev->dev);
+
+	return ret;
+}
+
+static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+{
+	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+	struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+
+	kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev);
+	kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &sgi_dev->dev);
+}
+
+static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	int c, ret = 0;
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
-		gpa_t rd_base = redist_base_address + c * SZ_64K * 2;
-		gpa_t sgi_base = rd_base + SZ_64K;
-		struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
-		struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
-
-		kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
-		rd_dev->base_addr = rd_base;
-		rd_dev->iodev_type = IODEV_REDIST;
-		rd_dev->regions = vgic_v3_rdbase_registers;
-		rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
-		rd_dev->redist_vcpu = vcpu;
-
-		mutex_lock(&kvm->slots_lock);
-		ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
-					      SZ_64K, &rd_dev->dev);
-		mutex_unlock(&kvm->slots_lock);
-
+		ret = vgic_register_redist_iodev(vcpu);
 		if (ret)
 			break;
-
-		kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
-		sgi_dev->base_addr = sgi_base;
-		sgi_dev->iodev_type = IODEV_REDIST;
-		sgi_dev->regions = vgic_v3_sgibase_registers;
-		sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
-		sgi_dev->redist_vcpu = vcpu;
-
-		mutex_lock(&kvm->slots_lock);
-		ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
-					      SZ_64K, &sgi_dev->dev);
-		mutex_unlock(&kvm->slots_lock);
-		if (ret) {
-			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-						  &rd_dev->dev);
-			break;
-		}
 	}
 
 	if (ret) {
 		/* The current c failed, so we start with the previous one. */
 		for (c--; c >= 0; c--) {
-			struct vgic_cpu *vgic_cpu;
-
 			vcpu = kvm_get_vcpu(kvm, c);
-			vgic_cpu = &vcpu->arch.vgic_cpu;
-			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-						  &vgic_cpu->rd_iodev.dev);
-			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-						  &vgic_cpu->sgi_iodev.dev);
+			vgic_unregister_redist_iodev(vcpu);
 		}
 	}
 
 	return ret;
 }
 
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
+{
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	int ret;
+
+	/* vgic_check_ioaddr makes sure we don't do this twice */
+	ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K);
+	if (ret)
+		return ret;
+
+	vgic->vgic_redist_base = addr;
+	if (!vgic_v3_check_base(kvm)) {
+		vgic->vgic_redist_base = VGIC_ADDR_UNDEF;
+		return -EINVAL;
+	}
+
+	/*
+	 * Register iodevs for each existing VCPU.  Adding more VCPUs
+	 * afterwards will register the iodevs when needed.
+	 */
+	ret = vgic_register_all_redist_iodevs(kvm);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
 	const struct vgic_register_region *region;
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 2a5db1352722..1c17b2a2f105 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -446,13 +446,12 @@ static int match_region(const void *key, const void *elt)
 	return 0;
 }
 
-/* Find the proper register handler entry given a certain address offset. */
-static const struct vgic_register_region *
-vgic_find_mmio_region(const struct vgic_register_region *region, int nr_regions,
-		      unsigned int offset)
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+		      int nr_regions, unsigned int offset)
 {
-	return bsearch((void *)(uintptr_t)offset, region, nr_regions,
-		       sizeof(region[0]), match_region);
+	return bsearch((void *)(uintptr_t)offset, regions, nr_regions,
+		       sizeof(regions[0]), match_region);
 }
 
 void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 98bb566b660a..ea4171acdef3 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -36,8 +36,13 @@ struct vgic_register_region {
 	};
 	unsigned long (*uaccess_read)(struct kvm_vcpu *vcpu, gpa_t addr,
 				      unsigned int len);
-	void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
-			      unsigned int len, unsigned long val);
+	union {
+		void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
+				      unsigned int len, unsigned long val);
+		int (*uaccess_its_write)(struct kvm *kvm, struct vgic_its *its,
+					 gpa_t addr, unsigned int len,
+					 unsigned long val);
+	};
 };
 
 extern struct kvm_io_device_ops kvm_io_gic_ops;
@@ -192,4 +197,9 @@ u64 vgic_sanitise_shareability(u64 reg);
 u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
 			u64 (*sanitise_fn)(u64));
 
+/* Find the proper register handler entry given a certain address offset */
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+		      int nr_regions, unsigned int offset);
+
 #endif
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index df1503650300..8fa737edde6f 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -234,19 +234,125 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 	vgic_v3->vgic_hcr = ICH_HCR_EN;
 }
 
-/* check for overlapping regions and for regions crossing the end of memory */
-static bool vgic_v3_check_base(struct kvm *kvm)
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
+{
+	struct kvm_vcpu *vcpu;
+	int byte_offset, bit_nr;
+	gpa_t pendbase, ptr;
+	bool status;
+	u8 val;
+	int ret;
+
+retry:
+	vcpu = irq->target_vcpu;
+	if (!vcpu)
+		return 0;
+
+	pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+	byte_offset = irq->intid / BITS_PER_BYTE;
+	bit_nr = irq->intid % BITS_PER_BYTE;
+	ptr = pendbase + byte_offset;
+
+	ret = kvm_read_guest(kvm, ptr, &val, 1);
+	if (ret)
+		return ret;
+
+	status = val & (1 << bit_nr);
+
+	spin_lock(&irq->irq_lock);
+	if (irq->target_vcpu != vcpu) {
+		spin_unlock(&irq->irq_lock);
+		goto retry;
+	}
+	irq->pending_latch = status;
+	vgic_queue_irq_unlock(vcpu->kvm, irq);
+
+	if (status) {
+		/* clear consumed data */
+		val &= ~(1 << bit_nr);
+		ret = kvm_write_guest(kvm, ptr, &val, 1);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/**
+ * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * kvm lock and all vcpu lock must be held
+ */
+int vgic_v3_save_pending_tables(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	int last_byte_offset = -1;
+	struct vgic_irq *irq;
+	int ret;
+
+	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+		int byte_offset, bit_nr;
+		struct kvm_vcpu *vcpu;
+		gpa_t pendbase, ptr;
+		bool stored;
+		u8 val;
+
+		vcpu = irq->target_vcpu;
+		if (!vcpu)
+			continue;
+
+		pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+		byte_offset = irq->intid / BITS_PER_BYTE;
+		bit_nr = irq->intid % BITS_PER_BYTE;
+		ptr = pendbase + byte_offset;
+
+		if (byte_offset != last_byte_offset) {
+			ret = kvm_read_guest(kvm, ptr, &val, 1);
+			if (ret)
+				return ret;
+			last_byte_offset = byte_offset;
+		}
+
+		stored = val & (1U << bit_nr);
+		if (stored == irq->pending_latch)
+			continue;
+
+		if (irq->pending_latch)
+			val |= 1 << bit_nr;
+		else
+			val &= ~(1 << bit_nr);
+
+		ret = kvm_write_guest(kvm, ptr, &val, 1);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * Check for overlapping regions and for regions crossing the end of memory
+ * for base addresses which have already been set.
+ */
+bool vgic_v3_check_base(struct kvm *kvm)
 {
 	struct vgic_dist *d = &kvm->arch.vgic;
 	gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
 
 	redist_size *= atomic_read(&kvm->online_vcpus);
 
-	if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
+	if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
+	    d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
 		return false;
-	if (d->vgic_redist_base + redist_size < d->vgic_redist_base)
+
+	if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) &&
+	    d->vgic_redist_base + redist_size < d->vgic_redist_base)
 		return false;
 
+	/* Both base addresses must be set to check if they overlap */
+	if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) ||
+	    IS_VGIC_ADDR_UNDEF(d->vgic_redist_base))
+		return true;
+
 	if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
 		return true;
 	if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
@@ -291,20 +397,6 @@ int vgic_v3_map_resources(struct kvm *kvm)
 		goto out;
 	}
 
-	ret = vgic_register_redist_iodevs(kvm, dist->vgic_redist_base);
-	if (ret) {
-		kvm_err("Unable to register VGICv3 redist MMIO regions\n");
-		goto out;
-	}
-
-	if (vgic_has_its(kvm)) {
-		ret = vgic_register_its_iodevs(kvm);
-		if (ret) {
-			kvm_err("Unable to register VGIC ITS MMIO regions\n");
-			goto out;
-		}
-	}
-
 	dist->ready = true;
 
 out:
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 4346bc7d08dc..83b24d20ff8f 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -21,7 +21,7 @@
 #include "vgic.h"
 
 #define CREATE_TRACE_POINTS
-#include "../trace.h"
+#include "trace.h"
 
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 799fd651b260..da83e4caa272 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -73,6 +73,29 @@
 				      KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \
 				      KVM_REG_ARM_VGIC_SYSREG_OP2_MASK)
 
+/*
+ * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt,
+ * below macros are defined for ITS table entry encoding.
+ */
+#define KVM_ITS_CTE_VALID_SHIFT		63
+#define KVM_ITS_CTE_VALID_MASK		BIT_ULL(63)
+#define KVM_ITS_CTE_RDBASE_SHIFT	16
+#define KVM_ITS_CTE_ICID_MASK		GENMASK_ULL(15, 0)
+#define KVM_ITS_ITE_NEXT_SHIFT		48
+#define KVM_ITS_ITE_PINTID_SHIFT	16
+#define KVM_ITS_ITE_PINTID_MASK		GENMASK_ULL(47, 16)
+#define KVM_ITS_ITE_ICID_MASK		GENMASK_ULL(15, 0)
+#define KVM_ITS_DTE_VALID_SHIFT		63
+#define KVM_ITS_DTE_VALID_MASK		BIT_ULL(63)
+#define KVM_ITS_DTE_NEXT_SHIFT		49
+#define KVM_ITS_DTE_NEXT_MASK		GENMASK_ULL(62, 49)
+#define KVM_ITS_DTE_ITTADDR_SHIFT	5
+#define KVM_ITS_DTE_ITTADDR_MASK	GENMASK_ULL(48, 5)
+#define KVM_ITS_DTE_SIZE_MASK		GENMASK_ULL(4, 0)
+#define KVM_ITS_L1E_VALID_MASK		BIT_ULL(63)
+/* we only support 64 kB translation table page size */
+#define KVM_ITS_L1E_ADDR_MASK		GENMASK_ULL(51, 16)
+
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
 	if (irq->config == VGIC_CONFIG_EDGE)
@@ -157,12 +180,15 @@ void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 void vgic_v3_enable(struct kvm_vcpu *vcpu);
 int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
+int vgic_v3_save_pending_tables(struct kvm *kvm);
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+bool vgic_v3_check_base(struct kvm *kvm);
 
 void vgic_v3_load(struct kvm_vcpu *vcpu);
 void vgic_v3_put(struct kvm_vcpu *vcpu);
 
-int vgic_register_its_iodevs(struct kvm *kvm);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
@@ -187,4 +213,7 @@ int vgic_init(struct kvm *kvm);
 int vgic_debug_init(struct kvm *kvm);
 int vgic_debug_destroy(struct kvm *kvm);
 
+bool lock_all_vcpus(struct kvm *kvm);
+void unlock_all_vcpus(struct kvm *kvm);
+
 #endif