Add the rt linux 4.1.3-rt3 as base

Import the rt linux 4.1.3-rt3 as OPNFV kvm base.

It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:

commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date:   Sat Jul 25 12:13:34 2015 +0200

    Prepare v4.1.3-rt3

    Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.

Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>

16 files changed, 4871 insertions, 0 deletions

diff --git a/kernel/arch/arm64/kvm/Kconfig b/kernel/arch/arm64/kvm/Kconfig
new file mode 100644
index 000000000..5105e297e
--- /dev/null
+++ b/kernel/arch/arm64/kvm/Kconfig
@@ -0,0 +1,54 @@
+#
+# KVM configuration
+#
+
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	---help---
+	  Say Y here to get to see options for using your Linux host to run
+	  other operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and
+	  disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	bool "Kernel-based Virtual Machine (KVM) support"
+	depends on OF
+	select MMU_NOTIFIER
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
+	select KVM_MMIO
+	select KVM_ARM_HOST
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+	select SRCU
+	select HAVE_KVM_EVENTFD
+	select HAVE_KVM_IRQFD
+	---help---
+	  Support hosting virtualized guest machines.
+
+	  If unsure, say N.
+
+config KVM_ARM_HOST
+	bool
+	---help---
+	  Provides host support for ARM processors.
+
+config KVM_ARM_MAX_VCPUS
+	int "Number maximum supported virtual CPUs per VM"
+	depends on KVM_ARM_HOST
+	default 4
+	help
+	  Static number of max supported virtual CPUs per VM.
+
+	  If you choose a high number, the vcpu structures will be quite
+	  large, so only choose a reasonable number that you expect to
+	  actually use.
+
+endif # VIRTUALIZATION
diff --git a/kernel/arch/arm64/kvm/Makefile b/kernel/arch/arm64/kvm/Makefile
new file mode 100644
index 000000000..d5904f876
--- /dev/null
+++ b/kernel/arch/arm64/kvm/Makefile
@@ -0,0 +1,29 @@
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+ccflags-y += -Iarch/arm64/kvm
+CFLAGS_arm.o := -I.
+CFLAGS_mmu.o := -I.
+
+KVM=../../../virt/kvm
+ARM=../../../arch/arm/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
+
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
+
+kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
+kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
+kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
+
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
+kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
+kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
diff --git a/kernel/arch/arm64/kvm/emulate.c b/kernel/arch/arm64/kvm/emulate.c
new file mode 100644
index 000000000..f87d8fbaa
--- /dev/null
+++ b/kernel/arch/arm64/kvm/emulate.c
@@ -0,0 +1,159 @@
+/*
+ * (not much of an) Emulation layer for 32bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * based on arch/arm/kvm/emulate.c
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/esr.h>
+#include <asm/kvm_emulate.h>
+
+/*
+ * stolen from arch/arm/kernel/opcodes.c
+ *
+ * condition code lookup table
+ * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
+ *
+ * bit position in short is condition code: NZCV
+ */
+static const unsigned short cc_map[16] = {
+	0xF0F0,			/* EQ == Z set            */
+	0x0F0F,			/* NE                     */
+	0xCCCC,			/* CS == C set            */
+	0x3333,			/* CC                     */
+	0xFF00,			/* MI == N set            */
+	0x00FF,			/* PL                     */
+	0xAAAA,			/* VS == V set            */
+	0x5555,			/* VC                     */
+	0x0C0C,			/* HI == C set && Z clear */
+	0xF3F3,			/* LS == C clear || Z set */
+	0xAA55,			/* GE == (N==V)           */
+	0x55AA,			/* LT == (N!=V)           */
+	0x0A05,			/* GT == (!Z && (N==V))   */
+	0xF5FA,			/* LE == (Z || (N!=V))    */
+	0xFFFF,			/* AL always              */
+	0			/* NV                     */
+};
+
+static int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
+{
+	u32 esr = kvm_vcpu_get_hsr(vcpu);
+
+	if (esr & ESR_ELx_CV)
+		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
+
+	return -1;
+}
+
+/*
+ * Check if a trapped instruction should have been executed or not.
+ */
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr;
+	u32 cpsr_cond;
+	int cond;
+
+	/* Top two bits non-zero?  Unconditional. */
+	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+		return true;
+
+	/* Is condition field valid? */
+	cond = kvm_vcpu_get_condition(vcpu);
+	if (cond == 0xE)
+		return true;
+
+	cpsr = *vcpu_cpsr(vcpu);
+
+	if (cond < 0) {
+		/* This can happen in Thumb mode: examine IT state. */
+		unsigned long it;
+
+		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
+
+		/* it == 0 => unconditional. */
+		if (it == 0)
+			return true;
+
+		/* The cond for this insn works out as the top 4 bits. */
+		cond = (it >> 4);
+	}
+
+	cpsr_cond = cpsr >> 28;
+
+	if (!((cc_map[cond] >> cpsr_cond) & 1))
+		return false;
+
+	return true;
+}
+
+/**
+ * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
+ * @vcpu:	The VCPU pointer
+ *
+ * When exceptions occur while instructions are executed in Thumb IF-THEN
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
+ * to do this little bit of work manually. The fields map like this:
+ *
+ * IT[7:0] -> CPSR[26:25],CPSR[15:10]
+ */
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+{
+	unsigned long itbits, cond;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	bool is_arm = !(cpsr & COMPAT_PSR_T_BIT);
+
+	BUG_ON(is_arm && (cpsr & COMPAT_PSR_IT_MASK));
+
+	if (!(cpsr & COMPAT_PSR_IT_MASK))
+		return;
+
+	cond = (cpsr & 0xe000) >> 13;
+	itbits = (cpsr & 0x1c00) >> (10 - 2);
+	itbits |= (cpsr & (0x3 << 25)) >> 25;
+
+	/* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */
+	if ((itbits & 0x7) == 0)
+		itbits = cond = 0;
+	else
+		itbits = (itbits << 1) & 0x1f;
+
+	cpsr &= ~COMPAT_PSR_IT_MASK;
+	cpsr |= cond << 13;
+	cpsr |= (itbits & 0x1c) << (10 - 2);
+	cpsr |= (itbits & 0x3) << 25;
+	*vcpu_cpsr(vcpu) = cpsr;
+}
+
+/**
+ * kvm_skip_instr - skip a trapped instruction and proceed to the next
+ * @vcpu: The vcpu pointer
+ */
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+	bool is_thumb;
+
+	is_thumb = !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_T_BIT);
+	if (is_thumb && !is_wide_instr)
+		*vcpu_pc(vcpu) += 2;
+	else
+		*vcpu_pc(vcpu) += 4;
+	kvm_adjust_itstate(vcpu);
+}
diff --git a/kernel/arch/arm64/kvm/guest.c b/kernel/arch/arm64/kvm/guest.c
new file mode 100644
index 000000000..9535bd555
--- /dev/null
+++ b/kernel/arch/arm64/kvm/guest.c
@@ -0,0 +1,333 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/guest.c:
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputype.h>
+#include <asm/uaccess.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ NULL }
+};
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static u64 core_reg_offset_from_id(u64 id)
+{
+	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
+}
+
+static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	/*
+	 * Because the kvm_regs structure is a mix of 32, 64 and
+	 * 128bit fields, we index it as if it was a 32bit
+	 * array. Hence below, nr_regs is the number of entries, and
+	 * off the index in the "array".
+	 */
+	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
+	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
+	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	u32 off;
+
+	/* Our ID is an index into the kvm_regs struct. */
+	off = core_reg_offset_from_id(reg->id);
+	if (off >= nr_regs ||
+	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
+		return -ENOENT;
+
+	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
+	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
+	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	__uint128_t tmp;
+	void *valp = &tmp;
+	u64 off;
+	int err = 0;
+
+	/* Our ID is an index into the kvm_regs struct. */
+	off = core_reg_offset_from_id(reg->id);
+	if (off >= nr_regs ||
+	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
+		return -ENOENT;
+
+	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
+		return -EINVAL;
+
+	if (copy_from_user(valp, uaddr, KVM_REG_SIZE(reg->id))) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
+		u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK;
+		switch (mode) {
+		case COMPAT_PSR_MODE_USR:
+		case COMPAT_PSR_MODE_FIQ:
+		case COMPAT_PSR_MODE_IRQ:
+		case COMPAT_PSR_MODE_SVC:
+		case COMPAT_PSR_MODE_ABT:
+		case COMPAT_PSR_MODE_UND:
+		case PSR_MODE_EL0t:
+		case PSR_MODE_EL1t:
+		case PSR_MODE_EL1h:
+			break;
+		default:
+			err = -EINVAL;
+			goto out;
+		}
+	}
+
+	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+out:
+	return err;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	return -EINVAL;
+}
+
+static unsigned long num_core_regs(void)
+{
+	return sizeof(struct kvm_regs) / sizeof(__u32);
+}
+
+/**
+ * ARM64 versions of the TIMER registers, always available on arm64
+ */
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+	switch (index) {
+	case KVM_REG_ARM_TIMER_CTL:
+	case KVM_REG_ARM_TIMER_CNT:
+	case KVM_REG_ARM_TIMER_CVAL:
+		return true;
+	}
+	return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int ret;
+
+	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+	if (ret != 0)
+		return -EFAULT;
+
+	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+
+	val = kvm_arm_timer_get_reg(vcpu, reg->id);
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
+/**
+ * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
+ *
+ * This is for all registers.
+ */
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
+{
+	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
+                + NUM_TIMER_REGS;
+}
+
+/**
+ * kvm_arm_copy_reg_indices - get indices of all registers.
+ *
+ * We do core registers right here, then we apppend system regs.
+ */
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	unsigned int i;
+	const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
+	int ret;
+
+	for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
+		if (put_user(core_reg | i, uindices))
+			return -EFAULT;
+		uindices++;
+	}
+
+	ret = copy_timer_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += NUM_TIMER_REGS;
+
+	return kvm_arm_copy_sys_reg_indices(vcpu, uindices);
+}
+
+int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	/* We currently use nothing arch-specific in upper 32 bits */
+	if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
+		return -EINVAL;
+
+	/* Register group 16 means we want a core register. */
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
+		return get_core_reg(vcpu, reg);
+
+	if (is_timer_reg(reg->id))
+		return get_timer_reg(vcpu, reg);
+
+	return kvm_arm_sys_reg_get_reg(vcpu, reg);
+}
+
+int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	/* We currently use nothing arch-specific in upper 32 bits */
+	if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
+		return -EINVAL;
+
+	/* Register group 16 means we set a core register. */
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
+		return set_core_reg(vcpu, reg);
+
+	if (is_timer_reg(reg->id))
+		return set_timer_reg(vcpu, reg);
+
+	return kvm_arm_sys_reg_set_reg(vcpu, reg);
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+}
+
+int __attribute_const__ kvm_target_cpu(void)
+{
+	unsigned long implementor = read_cpuid_implementor();
+	unsigned long part_number = read_cpuid_part_number();
+
+	switch (implementor) {
+	case ARM_CPU_IMP_ARM:
+		switch (part_number) {
+		case ARM_CPU_PART_AEM_V8:
+			return KVM_ARM_TARGET_AEM_V8;
+		case ARM_CPU_PART_FOUNDATION:
+			return KVM_ARM_TARGET_FOUNDATION_V8;
+		case ARM_CPU_PART_CORTEX_A53:
+			return KVM_ARM_TARGET_CORTEX_A53;
+		case ARM_CPU_PART_CORTEX_A57:
+			return KVM_ARM_TARGET_CORTEX_A57;
+		};
+		break;
+	case ARM_CPU_IMP_APM:
+		switch (part_number) {
+		case APM_CPU_PART_POTENZA:
+			return KVM_ARM_TARGET_XGENE_POTENZA;
+		};
+		break;
+	};
+
+	return -EINVAL;
+}
+
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
+{
+	int target = kvm_target_cpu();
+
+	if (target < 0)
+		return -ENODEV;
+
+	memset(init, 0, sizeof(*init));
+
+	/*
+	 * For now, we don't return any features.
+	 * In future, we might use features to return target
+	 * specific features available for the preferred
+	 * target type.
+	 */
+	init->target = (__u32)target;
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				  struct kvm_translation *tr)
+{
+	return -EINVAL;
+}
diff --git a/kernel/arch/arm64/kvm/handle_exit.c b/kernel/arch/arm64/kvm/handle_exit.c
new file mode 100644
index 000000000..524fa2567
--- /dev/null
+++ b/kernel/arch/arm64/kvm/handle_exit.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/handle_exit.c:
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+#include <asm/esr.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_psci.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+
+static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int ret;
+
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+			    kvm_vcpu_hvc_get_imm(vcpu));
+
+	ret = kvm_psci_call(vcpu);
+	if (ret < 0) {
+		kvm_inject_undefined(vcpu);
+		return 1;
+	}
+
+	return ret;
+}
+
+static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+/**
+ * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
+ *		    instruction executed by a guest
+ *
+ * @vcpu:	the vcpu pointer
+ *
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
+ * world-switches and schedule other host processes until there is an
+ * incoming IRQ or FIQ to the VM.
+ */
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
+		kvm_vcpu_on_spin(vcpu);
+	} else {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
+		kvm_vcpu_block(vcpu);
+	}
+
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
+	return 1;
+}
+
+static exit_handle_fn arm_exit_handlers[] = {
+	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
+	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
+	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
+	[ESR_ELx_EC_CP14_MR]	= kvm_handle_cp14_32,
+	[ESR_ELx_EC_CP14_LS]	= kvm_handle_cp14_load_store,
+	[ESR_ELx_EC_CP14_64]	= kvm_handle_cp14_64,
+	[ESR_ELx_EC_HVC32]	= handle_hvc,
+	[ESR_ELx_EC_SMC32]	= handle_smc,
+	[ESR_ELx_EC_HVC64]	= handle_hvc,
+	[ESR_ELx_EC_SMC64]	= handle_smc,
+	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
+	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
+	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
+};
+
+static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u8 hsr_ec = hsr >> ESR_ELx_EC_SHIFT;
+
+	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
+	    !arm_exit_handlers[hsr_ec]) {
+		kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
+			hsr, esr_get_class_string(hsr));
+		BUG();
+	}
+
+	return arm_exit_handlers[hsr_ec];
+}
+
+/*
+ * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
+ * proper exit to userspace.
+ */
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       int exception_index)
+{
+	exit_handle_fn exit_handler;
+
+	switch (exception_index) {
+	case ARM_EXCEPTION_IRQ:
+		return 1;
+	case ARM_EXCEPTION_TRAP:
+		/*
+		 * See ARM ARM B1.14.1: "Hyp traps on instructions
+		 * that fail their condition code check"
+		 */
+		if (!kvm_condition_valid(vcpu)) {
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			return 1;
+		}
+
+		exit_handler = kvm_get_exit_handler(vcpu);
+
+		return exit_handler(vcpu, run);
+	default:
+		kvm_pr_unimpl("Unsupported exception type: %d",
+			      exception_index);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		return 0;
+	}
+}
diff --git a/kernel/arch/arm64/kvm/hyp-init.S b/kernel/arch/arm64/kvm/hyp-init.S
new file mode 100644
index 000000000..178ba2248
--- /dev/null
+++ b/kernel/arch/arm64/kvm/hyp-init.S
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2012,2013 - 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/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/pgtable-hwdef.h>
+
+	.text
+	.pushsection	.hyp.idmap.text, "ax"
+
+	.align	11
+
+ENTRY(__kvm_hyp_init)
+	ventry	__invalid		// Synchronous EL2t
+	ventry	__invalid		// IRQ EL2t
+	ventry	__invalid		// FIQ EL2t
+	ventry	__invalid		// Error EL2t
+
+	ventry	__invalid		// Synchronous EL2h
+	ventry	__invalid		// IRQ EL2h
+	ventry	__invalid		// FIQ EL2h
+	ventry	__invalid		// Error EL2h
+
+	ventry	__do_hyp_init		// Synchronous 64-bit EL1
+	ventry	__invalid		// IRQ 64-bit EL1
+	ventry	__invalid		// FIQ 64-bit EL1
+	ventry	__invalid		// Error 64-bit EL1
+
+	ventry	__invalid		// Synchronous 32-bit EL1
+	ventry	__invalid		// IRQ 32-bit EL1
+	ventry	__invalid		// FIQ 32-bit EL1
+	ventry	__invalid		// Error 32-bit EL1
+
+__invalid:
+	b	.
+
+	/*
+	 * x0: HYP boot pgd
+	 * x1: HYP pgd
+	 * x2: HYP stack
+	 * x3: HYP vectors
+	 */
+__do_hyp_init:
+
+	msr	ttbr0_el2, x0
+
+	mrs	x4, tcr_el1
+	ldr	x5, =TCR_EL2_MASK
+	and	x4, x4, x5
+	ldr	x5, =TCR_EL2_FLAGS
+	orr	x4, x4, x5
+
+#ifndef CONFIG_ARM64_VA_BITS_48
+	/*
+	 * If we are running with VA_BITS < 48, we may be running with an extra
+	 * level of translation in the ID map. This is only the case if system
+	 * RAM is out of range for the currently configured page size and number
+	 * of translation levels, in which case we will also need the extra
+	 * level for the HYP ID map, or we won't be able to enable the EL2 MMU.
+	 *
+	 * However, at EL2, there is only one TTBR register, and we can't switch
+	 * between translation tables *and* update TCR_EL2.T0SZ at the same
+	 * time. Bottom line: we need the extra level in *both* our translation
+	 * tables.
+	 *
+	 * So use the same T0SZ value we use for the ID map.
+	 */
+	ldr_l	x5, idmap_t0sz
+	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+#endif
+	msr	tcr_el2, x4
+
+	ldr	x4, =VTCR_EL2_FLAGS
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
+	 * VTCR_EL2.
+	 */
+	mrs	x5, ID_AA64MMFR0_EL1
+	bfi	x4, x5, #16, #3
+	msr	vtcr_el2, x4
+
+	mrs	x4, mair_el1
+	msr	mair_el2, x4
+	isb
+
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi	alle2
+	dsb	sy
+
+	mrs	x4, sctlr_el2
+	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
+	ldr	x5, =SCTLR_EL2_FLAGS
+	orr	x4, x4, x5
+	msr	sctlr_el2, x4
+	isb
+
+	/* Skip the trampoline dance if we merged the boot and runtime PGDs */
+	cmp	x0, x1
+	b.eq	merged
+
+	/* MMU is now enabled. Get ready for the trampoline dance */
+	ldr	x4, =TRAMPOLINE_VA
+	adr	x5, target
+	bfi	x4, x5, #0, #PAGE_SHIFT
+	br	x4
+
+target: /* We're now in the trampoline code, switch page tables */
+	msr	ttbr0_el2, x1
+	isb
+
+	/* Invalidate the old TLBs */
+	tlbi	alle2
+	dsb	sy
+
+merged:
+	/* Set the stack and new vectors */
+	kern_hyp_va	x2
+	mov	sp, x2
+	kern_hyp_va	x3
+	msr	vbar_el2, x3
+
+	/* Hello, World! */
+	eret
+ENDPROC(__kvm_hyp_init)
+
+	.ltorg
+
+	.popsection
diff --git a/kernel/arch/arm64/kvm/hyp.S b/kernel/arch/arm64/kvm/hyp.S
new file mode 100644
index 000000000..5befd010e
--- /dev/null
+++ b/kernel/arch/arm64/kvm/hyp.S
@@ -0,0 +1,1298 @@
+/*
+ * Copyright (C) 2012,2013 - 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/linkage.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+#include <asm/debug-monitors.h>
+#include <asm/esr.h>
+#include <asm/fpsimdmacros.h>
+#include <asm/kvm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/memory.h>
+
+#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
+#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_SPSR_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_SPSR + 8*x)
+#define CPU_SYSREG_OFFSET(x)	(CPU_SYSREGS + 8*x)
+
+	.text
+	.pushsection	.hyp.text, "ax"
+	.align	PAGE_SHIFT
+
+.macro save_common_regs
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	add	x3, x2, #CPU_XREG_OFFSET(19)
+	stp	x19, x20, [x3]
+	stp	x21, x22, [x3, #16]
+	stp	x23, x24, [x3, #32]
+	stp	x25, x26, [x3, #48]
+	stp	x27, x28, [x3, #64]
+	stp	x29, lr, [x3, #80]
+
+	mrs	x19, sp_el0
+	mrs	x20, elr_el2		// EL1 PC
+	mrs	x21, spsr_el2		// EL1 pstate
+
+	stp	x19, x20, [x3, #96]
+	str	x21, [x3, #112]
+
+	mrs	x22, sp_el1
+	mrs	x23, elr_el1
+	mrs	x24, spsr_el1
+
+	str	x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
+	str	x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
+	str	x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
+.endm
+
+.macro restore_common_regs
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	ldr	x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
+	ldr	x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
+	ldr	x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
+
+	msr	sp_el1, x22
+	msr	elr_el1, x23
+	msr	spsr_el1, x24
+
+	add	x3, x2, #CPU_XREG_OFFSET(31)    // SP_EL0
+	ldp	x19, x20, [x3]
+	ldr	x21, [x3, #16]
+
+	msr	sp_el0, x19
+	msr	elr_el2, x20 				// EL1 PC
+	msr	spsr_el2, x21 				// EL1 pstate
+
+	add	x3, x2, #CPU_XREG_OFFSET(19)
+	ldp	x19, x20, [x3]
+	ldp	x21, x22, [x3, #16]
+	ldp	x23, x24, [x3, #32]
+	ldp	x25, x26, [x3, #48]
+	ldp	x27, x28, [x3, #64]
+	ldp	x29, lr, [x3, #80]
+.endm
+
+.macro save_host_regs
+	save_common_regs
+.endm
+
+.macro restore_host_regs
+	restore_common_regs
+.endm
+
+.macro save_fpsimd
+	// x2: cpu context address
+	// x3, x4: tmp regs
+	add	x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+	fpsimd_save x3, 4
+.endm
+
+.macro restore_fpsimd
+	// x2: cpu context address
+	// x3, x4: tmp regs
+	add	x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+	fpsimd_restore x3, 4
+.endm
+
+.macro save_guest_regs
+	// x0 is the vcpu address
+	// x1 is the return code, do not corrupt!
+	// x2 is the cpu context
+	// x3 is a tmp register
+	// Guest's x0-x3 are on the stack
+
+	// Compute base to save registers
+	add	x3, x2, #CPU_XREG_OFFSET(4)
+	stp	x4, x5, [x3]
+	stp	x6, x7, [x3, #16]
+	stp	x8, x9, [x3, #32]
+	stp	x10, x11, [x3, #48]
+	stp	x12, x13, [x3, #64]
+	stp	x14, x15, [x3, #80]
+	stp	x16, x17, [x3, #96]
+	str	x18, [x3, #112]
+
+	pop	x6, x7			// x2, x3
+	pop	x4, x5			// x0, x1
+
+	add	x3, x2, #CPU_XREG_OFFSET(0)
+	stp	x4, x5, [x3]
+	stp	x6, x7, [x3, #16]
+
+	save_common_regs
+.endm
+
+.macro restore_guest_regs
+	// x0 is the vcpu address.
+	// x2 is the cpu context
+	// x3 is a tmp register
+
+	// Prepare x0-x3 for later restore
+	add	x3, x2, #CPU_XREG_OFFSET(0)
+	ldp	x4, x5, [x3]
+	ldp	x6, x7, [x3, #16]
+	push	x4, x5		// Push x0-x3 on the stack
+	push	x6, x7
+
+	// x4-x18
+	ldp	x4, x5, [x3, #32]
+	ldp	x6, x7, [x3, #48]
+	ldp	x8, x9, [x3, #64]
+	ldp	x10, x11, [x3, #80]
+	ldp	x12, x13, [x3, #96]
+	ldp	x14, x15, [x3, #112]
+	ldp	x16, x17, [x3, #128]
+	ldr	x18, [x3, #144]
+
+	// x19-x29, lr, sp*, elr*, spsr*
+	restore_common_regs
+
+	// Last bits of the 64bit state
+	pop	x2, x3
+	pop	x0, x1
+
+	// Do not touch any register after this!
+.endm
+
+/*
+ * Macros to perform system register save/restore.
+ *
+ * Ordering here is absolutely critical, and must be kept consistent
+ * in {save,restore}_sysregs, {save,restore}_guest_32bit_state,
+ * and in kvm_asm.h.
+ *
+ * In other words, don't touch any of these unless you know what
+ * you are doing.
+ */
+.macro save_sysregs
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
+
+	mrs	x4,	vmpidr_el2
+	mrs	x5,	csselr_el1
+	mrs	x6,	sctlr_el1
+	mrs	x7,	actlr_el1
+	mrs	x8,	cpacr_el1
+	mrs	x9,	ttbr0_el1
+	mrs	x10,	ttbr1_el1
+	mrs	x11,	tcr_el1
+	mrs	x12,	esr_el1
+	mrs	x13, 	afsr0_el1
+	mrs	x14,	afsr1_el1
+	mrs	x15,	far_el1
+	mrs	x16,	mair_el1
+	mrs	x17,	vbar_el1
+	mrs	x18,	contextidr_el1
+	mrs	x19,	tpidr_el0
+	mrs	x20,	tpidrro_el0
+	mrs	x21,	tpidr_el1
+	mrs	x22, 	amair_el1
+	mrs	x23, 	cntkctl_el1
+	mrs	x24,	par_el1
+	mrs	x25,	mdscr_el1
+
+	stp	x4, x5, [x3]
+	stp	x6, x7, [x3, #16]
+	stp	x8, x9, [x3, #32]
+	stp	x10, x11, [x3, #48]
+	stp	x12, x13, [x3, #64]
+	stp	x14, x15, [x3, #80]
+	stp	x16, x17, [x3, #96]
+	stp	x18, x19, [x3, #112]
+	stp	x20, x21, [x3, #128]
+	stp	x22, x23, [x3, #144]
+	stp	x24, x25, [x3, #160]
+.endm
+
+.macro save_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbcr15_el1
+	mrs	x19, dbgbcr14_el1
+	mrs	x18, dbgbcr13_el1
+	mrs	x17, dbgbcr12_el1
+	mrs	x16, dbgbcr11_el1
+	mrs	x15, dbgbcr10_el1
+	mrs	x14, dbgbcr9_el1
+	mrs	x13, dbgbcr8_el1
+	mrs	x12, dbgbcr7_el1
+	mrs	x11, dbgbcr6_el1
+	mrs	x10, dbgbcr5_el1
+	mrs	x9, dbgbcr4_el1
+	mrs	x8, dbgbcr3_el1
+	mrs	x7, dbgbcr2_el1
+	mrs	x6, dbgbcr1_el1
+	mrs	x5, dbgbcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbvr15_el1
+	mrs	x19, dbgbvr14_el1
+	mrs	x18, dbgbvr13_el1
+	mrs	x17, dbgbvr12_el1
+	mrs	x16, dbgbvr11_el1
+	mrs	x15, dbgbvr10_el1
+	mrs	x14, dbgbvr9_el1
+	mrs	x13, dbgbvr8_el1
+	mrs	x12, dbgbvr7_el1
+	mrs	x11, dbgbvr6_el1
+	mrs	x10, dbgbvr5_el1
+	mrs	x9, dbgbvr4_el1
+	mrs	x8, dbgbvr3_el1
+	mrs	x7, dbgbvr2_el1
+	mrs	x6, dbgbvr1_el1
+	mrs	x5, dbgbvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwcr15_el1
+	mrs	x19, dbgwcr14_el1
+	mrs	x18, dbgwcr13_el1
+	mrs	x17, dbgwcr12_el1
+	mrs	x16, dbgwcr11_el1
+	mrs	x15, dbgwcr10_el1
+	mrs	x14, dbgwcr9_el1
+	mrs	x13, dbgwcr8_el1
+	mrs	x12, dbgwcr7_el1
+	mrs	x11, dbgwcr6_el1
+	mrs	x10, dbgwcr5_el1
+	mrs	x9, dbgwcr4_el1
+	mrs	x8, dbgwcr3_el1
+	mrs	x7, dbgwcr2_el1
+	mrs	x6, dbgwcr1_el1
+	mrs	x5, dbgwcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwvr15_el1
+	mrs	x19, dbgwvr14_el1
+	mrs	x18, dbgwvr13_el1
+	mrs	x17, dbgwvr12_el1
+	mrs	x16, dbgwvr11_el1
+	mrs	x15, dbgwvr10_el1
+	mrs	x14, dbgwvr9_el1
+	mrs	x13, dbgwvr8_el1
+	mrs	x12, dbgwvr7_el1
+	mrs	x11, dbgwvr6_el1
+	mrs	x10, dbgwvr5_el1
+	mrs	x9, dbgwvr4_el1
+	mrs	x8, dbgwvr3_el1
+	mrs	x7, dbgwvr2_el1
+	mrs	x6, dbgwvr1_el1
+	mrs	x5, dbgwvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	mrs	x21, mdccint_el1
+	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+.endm
+
+.macro restore_sysregs
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
+
+	ldp	x4, x5, [x3]
+	ldp	x6, x7, [x3, #16]
+	ldp	x8, x9, [x3, #32]
+	ldp	x10, x11, [x3, #48]
+	ldp	x12, x13, [x3, #64]
+	ldp	x14, x15, [x3, #80]
+	ldp	x16, x17, [x3, #96]
+	ldp	x18, x19, [x3, #112]
+	ldp	x20, x21, [x3, #128]
+	ldp	x22, x23, [x3, #144]
+	ldp	x24, x25, [x3, #160]
+
+	msr	vmpidr_el2,	x4
+	msr	csselr_el1,	x5
+	msr	sctlr_el1,	x6
+	msr	actlr_el1,	x7
+	msr	cpacr_el1,	x8
+	msr	ttbr0_el1,	x9
+	msr	ttbr1_el1,	x10
+	msr	tcr_el1,	x11
+	msr	esr_el1,	x12
+	msr	afsr0_el1,	x13
+	msr	afsr1_el1,	x14
+	msr	far_el1,	x15
+	msr	mair_el1,	x16
+	msr	vbar_el1,	x17
+	msr	contextidr_el1,	x18
+	msr	tpidr_el0,	x19
+	msr	tpidrro_el0,	x20
+	msr	tpidr_el1,	x21
+	msr	amair_el1,	x22
+	msr	cntkctl_el1,	x23
+	msr	par_el1,	x24
+	msr	mdscr_el1,	x25
+.endm
+
+.macro restore_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbcr15_el1, x20
+	msr	dbgbcr14_el1, x19
+	msr	dbgbcr13_el1, x18
+	msr	dbgbcr12_el1, x17
+	msr	dbgbcr11_el1, x16
+	msr	dbgbcr10_el1, x15
+	msr	dbgbcr9_el1, x14
+	msr	dbgbcr8_el1, x13
+	msr	dbgbcr7_el1, x12
+	msr	dbgbcr6_el1, x11
+	msr	dbgbcr5_el1, x10
+	msr	dbgbcr4_el1, x9
+	msr	dbgbcr3_el1, x8
+	msr	dbgbcr2_el1, x7
+	msr	dbgbcr1_el1, x6
+	msr	dbgbcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbvr15_el1, x20
+	msr	dbgbvr14_el1, x19
+	msr	dbgbvr13_el1, x18
+	msr	dbgbvr12_el1, x17
+	msr	dbgbvr11_el1, x16
+	msr	dbgbvr10_el1, x15
+	msr	dbgbvr9_el1, x14
+	msr	dbgbvr8_el1, x13
+	msr	dbgbvr7_el1, x12
+	msr	dbgbvr6_el1, x11
+	msr	dbgbvr5_el1, x10
+	msr	dbgbvr4_el1, x9
+	msr	dbgbvr3_el1, x8
+	msr	dbgbvr2_el1, x7
+	msr	dbgbvr1_el1, x6
+	msr	dbgbvr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwcr15_el1, x20
+	msr	dbgwcr14_el1, x19
+	msr	dbgwcr13_el1, x18
+	msr	dbgwcr12_el1, x17
+	msr	dbgwcr11_el1, x16
+	msr	dbgwcr10_el1, x15
+	msr	dbgwcr9_el1, x14
+	msr	dbgwcr8_el1, x13
+	msr	dbgwcr7_el1, x12
+	msr	dbgwcr6_el1, x11
+	msr	dbgwcr5_el1, x10
+	msr	dbgwcr4_el1, x9
+	msr	dbgwcr3_el1, x8
+	msr	dbgwcr2_el1, x7
+	msr	dbgwcr1_el1, x6
+	msr	dbgwcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwvr15_el1, x20
+	msr	dbgwvr14_el1, x19
+	msr	dbgwvr13_el1, x18
+	msr	dbgwvr12_el1, x17
+	msr	dbgwvr11_el1, x16
+	msr	dbgwvr10_el1, x15
+	msr	dbgwvr9_el1, x14
+	msr	dbgwvr8_el1, x13
+	msr	dbgwvr7_el1, x12
+	msr	dbgwvr6_el1, x11
+	msr	dbgwvr5_el1, x10
+	msr	dbgwvr4_el1, x9
+	msr	dbgwvr3_el1, x8
+	msr	dbgwvr2_el1, x7
+	msr	dbgwvr1_el1, x6
+	msr	dbgwvr0_el1, x5
+
+	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+	msr	mdccint_el1, x21
+.endm
+
+.macro skip_32bit_state tmp, target
+	// Skip 32bit state if not needed
+	mrs	\tmp, hcr_el2
+	tbnz	\tmp, #HCR_RW_SHIFT, \target
+.endm
+
+.macro skip_tee_state tmp, target
+	// Skip ThumbEE state if not needed
+	mrs	\tmp, id_pfr0_el1
+	tbz	\tmp, #12, \target
+.endm
+
+.macro skip_debug_state tmp, target
+	ldr	\tmp, [x0, #VCPU_DEBUG_FLAGS]
+	tbz	\tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
+.endm
+
+.macro compute_debug_state target
+	// Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
+	// is set, we do a full save/restore cycle and disable trapping.
+	add	x25, x0, #VCPU_CONTEXT
+
+	// Check the state of MDSCR_EL1
+	ldr	x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
+	and	x26, x25, #DBG_MDSCR_KDE
+	and	x25, x25, #DBG_MDSCR_MDE
+	adds	xzr, x25, x26
+	b.eq	9998f		// Nothing to see there
+
+	// If any interesting bits was set, we must set the flag
+	mov	x26, #KVM_ARM64_DEBUG_DIRTY
+	str	x26, [x0, #VCPU_DEBUG_FLAGS]
+	b	9999f		// Don't skip restore
+
+9998:
+	// Otherwise load the flags from memory in case we recently
+	// trapped
+	skip_debug_state x25, \target
+9999:
+.endm
+
+.macro save_guest_32bit_state
+	skip_32bit_state x3, 1f
+
+	add	x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
+	mrs	x4, spsr_abt
+	mrs	x5, spsr_und
+	mrs	x6, spsr_irq
+	mrs	x7, spsr_fiq
+	stp	x4, x5, [x3]
+	stp	x6, x7, [x3, #16]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
+	mrs	x4, dacr32_el2
+	mrs	x5, ifsr32_el2
+	mrs	x6, fpexc32_el2
+	stp	x4, x5, [x3]
+	str	x6, [x3, #16]
+
+	skip_debug_state x8, 2f
+	mrs	x7, dbgvcr32_el2
+	str	x7, [x3, #24]
+2:
+	skip_tee_state x8, 1f
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
+	mrs	x4, teecr32_el1
+	mrs	x5, teehbr32_el1
+	stp	x4, x5, [x3]
+1:
+.endm
+
+.macro restore_guest_32bit_state
+	skip_32bit_state x3, 1f
+
+	add	x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
+	ldp	x4, x5, [x3]
+	ldp	x6, x7, [x3, #16]
+	msr	spsr_abt, x4
+	msr	spsr_und, x5
+	msr	spsr_irq, x6
+	msr	spsr_fiq, x7
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
+	ldp	x4, x5, [x3]
+	ldr	x6, [x3, #16]
+	msr	dacr32_el2, x4
+	msr	ifsr32_el2, x5
+	msr	fpexc32_el2, x6
+
+	skip_debug_state x8, 2f
+	ldr	x7, [x3, #24]
+	msr	dbgvcr32_el2, x7
+2:
+	skip_tee_state x8, 1f
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
+	ldp	x4, x5, [x3]
+	msr	teecr32_el1, x4
+	msr	teehbr32_el1, x5
+1:
+.endm
+
+.macro activate_traps
+	ldr     x2, [x0, #VCPU_HCR_EL2]
+	msr     hcr_el2, x2
+	mov	x2, #CPTR_EL2_TTA
+	msr	cptr_el2, x2
+
+	mov	x2, #(1 << 15)	// Trap CP15 Cr=15
+	msr	hstr_el2, x2
+
+	mrs	x2, mdcr_el2
+	and	x2, x2, #MDCR_EL2_HPMN_MASK
+	orr	x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
+	orr	x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
+
+	// Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
+	// if not dirty.
+	ldr	x3, [x0, #VCPU_DEBUG_FLAGS]
+	tbnz	x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
+	orr	x2, x2,  #MDCR_EL2_TDA
+1:
+	msr	mdcr_el2, x2
+.endm
+
+.macro deactivate_traps
+	mov	x2, #HCR_RW
+	msr	hcr_el2, x2
+	msr	cptr_el2, xzr
+	msr	hstr_el2, xzr
+
+	mrs	x2, mdcr_el2
+	and	x2, x2, #MDCR_EL2_HPMN_MASK
+	msr	mdcr_el2, x2
+.endm
+
+.macro activate_vm
+	ldr	x1, [x0, #VCPU_KVM]
+	kern_hyp_va	x1
+	ldr	x2, [x1, #KVM_VTTBR]
+	msr	vttbr_el2, x2
+.endm
+
+.macro deactivate_vm
+	msr	vttbr_el2, xzr
+.endm
+
+/*
+ * Call into the vgic backend for state saving
+ */
+.macro save_vgic_state
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, VGIC_SAVE_FN]
+	kern_hyp_va	x24
+	blr	x24
+	mrs	x24, hcr_el2
+	mov	x25, #HCR_INT_OVERRIDE
+	neg	x25, x25
+	and	x24, x24, x25
+	msr	hcr_el2, x24
+.endm
+
+/*
+ * Call into the vgic backend for state restoring
+ */
+.macro restore_vgic_state
+	mrs	x24, hcr_el2
+	ldr	x25, [x0, #VCPU_IRQ_LINES]
+	orr	x24, x24, #HCR_INT_OVERRIDE
+	orr	x24, x24, x25
+	msr	hcr_el2, x24
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, #VGIC_RESTORE_FN]
+	kern_hyp_va	x24
+	blr	x24
+.endm
+
+.macro save_timer_state
+	// x0: vcpu pointer
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va x2
+	ldr	w3, [x2, #KVM_TIMER_ENABLED]
+	cbz	w3, 1f
+
+	mrs	x3, cntv_ctl_el0
+	and	x3, x3, #3
+	str	w3, [x0, #VCPU_TIMER_CNTV_CTL]
+	bic	x3, x3, #1		// Clear Enable
+	msr	cntv_ctl_el0, x3
+
+	isb
+
+	mrs	x3, cntv_cval_el0
+	str	x3, [x0, #VCPU_TIMER_CNTV_CVAL]
+
+1:
+	// Allow physical timer/counter access for the host
+	mrs	x2, cnthctl_el2
+	orr	x2, x2, #3
+	msr	cnthctl_el2, x2
+
+	// Clear cntvoff for the host
+	msr	cntvoff_el2, xzr
+.endm
+
+.macro restore_timer_state
+	// x0: vcpu pointer
+	// Disallow physical timer access for the guest
+	// Physical counter access is allowed
+	mrs	x2, cnthctl_el2
+	orr	x2, x2, #1
+	bic	x2, x2, #2
+	msr	cnthctl_el2, x2
+
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va x2
+	ldr	w3, [x2, #KVM_TIMER_ENABLED]
+	cbz	w3, 1f
+
+	ldr	x3, [x2, #KVM_TIMER_CNTVOFF]
+	msr	cntvoff_el2, x3
+	ldr	x2, [x0, #VCPU_TIMER_CNTV_CVAL]
+	msr	cntv_cval_el0, x2
+	isb
+
+	ldr	w2, [x0, #VCPU_TIMER_CNTV_CTL]
+	and	x2, x2, #3
+	msr	cntv_ctl_el0, x2
+1:
+.endm
+
+__save_sysregs:
+	save_sysregs
+	ret
+
+__restore_sysregs:
+	restore_sysregs
+	ret
+
+__save_debug:
+	save_debug
+	ret
+
+__restore_debug:
+	restore_debug
+	ret
+
+__save_fpsimd:
+	save_fpsimd
+	ret
+
+__restore_fpsimd:
+	restore_fpsimd
+	ret
+
+/*
+ * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+ *
+ * This is the world switch. The first half of the function
+ * deals with entering the guest, and anything from __kvm_vcpu_return
+ * to the end of the function deals with reentering the host.
+ * On the enter path, only x0 (vcpu pointer) must be preserved until
+ * the last moment. On the exit path, x0 (vcpu pointer) and x1 (exception
+ * code) must both be preserved until the epilogue.
+ * In both cases, x2 points to the CPU context we're saving/restoring from/to.
+ */
+ENTRY(__kvm_vcpu_run)
+	kern_hyp_va	x0
+	msr	tpidr_el2, x0	// Save the vcpu register
+
+	// Host context
+	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
+	kern_hyp_va x2
+
+	save_host_regs
+	bl __save_fpsimd
+	bl __save_sysregs
+
+	compute_debug_state 1f
+	bl	__save_debug
+1:
+	activate_traps
+	activate_vm
+
+	restore_vgic_state
+	restore_timer_state
+
+	// Guest context
+	add	x2, x0, #VCPU_CONTEXT
+
+	bl __restore_sysregs
+	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	bl	__restore_debug
+1:
+	restore_guest_32bit_state
+	restore_guest_regs
+
+	// That's it, no more messing around.
+	eret
+
+__kvm_vcpu_return:
+	// Assume x0 is the vcpu pointer, x1 the return code
+	// Guest's x0-x3 are on the stack
+
+	// Guest context
+	add	x2, x0, #VCPU_CONTEXT
+
+	save_guest_regs
+	bl __save_fpsimd
+	bl __save_sysregs
+
+	skip_debug_state x3, 1f
+	bl	__save_debug
+1:
+	save_guest_32bit_state
+
+	save_timer_state
+	save_vgic_state
+
+	deactivate_traps
+	deactivate_vm
+
+	// Host context
+	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
+	kern_hyp_va x2
+
+	bl __restore_sysregs
+	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	// Clear the dirty flag for the next run, as all the state has
+	// already been saved. Note that we nuke the whole 64bit word.
+	// If we ever add more flags, we'll have to be more careful...
+	str	xzr, [x0, #VCPU_DEBUG_FLAGS]
+	bl	__restore_debug
+1:
+	restore_host_regs
+
+	mov	x0, x1
+	ret
+END(__kvm_vcpu_run)
+
+// void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+ENTRY(__kvm_tlb_flush_vmid_ipa)
+	dsb	ishst
+
+	kern_hyp_va	x0
+	ldr	x2, [x0, #KVM_VTTBR]
+	msr	vttbr_el2, x2
+	isb
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	lsr	x1, x1, #12
+	tlbi	ipas2e1is, x1
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb	ish
+	tlbi	vmalle1is
+	dsb	ish
+	isb
+
+	msr	vttbr_el2, xzr
+	ret
+ENDPROC(__kvm_tlb_flush_vmid_ipa)
+
+/**
+ * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
+ * @struct kvm *kvm - pointer to kvm structure
+ *
+ * Invalidates all Stage 1 and 2 TLB entries for current VMID.
+ */
+ENTRY(__kvm_tlb_flush_vmid)
+	dsb     ishst
+
+	kern_hyp_va     x0
+	ldr     x2, [x0, #KVM_VTTBR]
+	msr     vttbr_el2, x2
+	isb
+
+	tlbi    vmalls12e1is
+	dsb     ish
+	isb
+
+	msr     vttbr_el2, xzr
+	ret
+ENDPROC(__kvm_tlb_flush_vmid)
+
+ENTRY(__kvm_flush_vm_context)
+	dsb	ishst
+	tlbi	alle1is
+	ic	ialluis
+	dsb	ish
+	ret
+ENDPROC(__kvm_flush_vm_context)
+
+	// struct vgic_sr_vectors __vgi_sr_vectors;
+	.align 3
+ENTRY(__vgic_sr_vectors)
+	.skip	VGIC_SR_VECTOR_SZ
+ENDPROC(__vgic_sr_vectors)
+
+__kvm_hyp_panic:
+	// Guess the context by looking at VTTBR:
+	// If zero, then we're already a host.
+	// Otherwise restore a minimal host context before panicing.
+	mrs	x0, vttbr_el2
+	cbz	x0, 1f
+
+	mrs	x0, tpidr_el2
+
+	deactivate_traps
+	deactivate_vm
+
+	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
+	kern_hyp_va x2
+
+	bl __restore_sysregs
+
+1:	adr	x0, __hyp_panic_str
+	adr	x1, 2f
+	ldp	x2, x3, [x1]
+	sub	x0, x0, x2
+	add	x0, x0, x3
+	mrs	x1, spsr_el2
+	mrs	x2, elr_el2
+	mrs	x3, esr_el2
+	mrs	x4, far_el2
+	mrs	x5, hpfar_el2
+	mrs	x6, par_el1
+	mrs	x7, tpidr_el2
+
+	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
+		      PSR_MODE_EL1h)
+	msr	spsr_el2, lr
+	ldr	lr, =panic
+	msr	elr_el2, lr
+	eret
+
+	.align	3
+2:	.quad	HYP_PAGE_OFFSET
+	.quad	PAGE_OFFSET
+ENDPROC(__kvm_hyp_panic)
+
+__hyp_panic_str:
+	.ascii	"HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+
+	.align	2
+
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
+ENTRY(kvm_call_hyp)
+	hvc	#0
+	ret
+ENDPROC(kvm_call_hyp)
+
+.macro invalid_vector	label, target
+	.align	2
+\label:
+	b \target
+ENDPROC(\label)
+.endm
+
+	/* None of these should ever happen */
+	invalid_vector	el2t_sync_invalid, __kvm_hyp_panic
+	invalid_vector	el2t_irq_invalid, __kvm_hyp_panic
+	invalid_vector	el2t_fiq_invalid, __kvm_hyp_panic
+	invalid_vector	el2t_error_invalid, __kvm_hyp_panic
+	invalid_vector	el2h_sync_invalid, __kvm_hyp_panic
+	invalid_vector	el2h_irq_invalid, __kvm_hyp_panic
+	invalid_vector	el2h_fiq_invalid, __kvm_hyp_panic
+	invalid_vector	el2h_error_invalid, __kvm_hyp_panic
+	invalid_vector	el1_sync_invalid, __kvm_hyp_panic
+	invalid_vector	el1_irq_invalid, __kvm_hyp_panic
+	invalid_vector	el1_fiq_invalid, __kvm_hyp_panic
+	invalid_vector	el1_error_invalid, __kvm_hyp_panic
+
+el1_sync:					// Guest trapped into EL2
+	push	x0, x1
+	push	x2, x3
+
+	mrs	x1, esr_el2
+	lsr	x2, x1, #ESR_ELx_EC_SHIFT
+
+	cmp	x2, #ESR_ELx_EC_HVC64
+	b.ne	el1_trap
+
+	mrs	x3, vttbr_el2			// If vttbr is valid, the 64bit guest
+	cbnz	x3, el1_trap			// called HVC
+
+	/* Here, we're pretty sure the host called HVC. */
+	pop	x2, x3
+	pop	x0, x1
+
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
+
+	/*
+	 * Compute the function address in EL2, and shuffle the parameters.
+	 */
+	kern_hyp_va	x0
+	mov	lr, x0
+	mov	x0, x1
+	mov	x1, x2
+	mov	x2, x3
+	blr	lr
+
+	pop	lr, xzr
+2:	eret
+
+el1_trap:
+	/*
+	 * x1: ESR
+	 * x2: ESR_EC
+	 */
+	cmp	x2, #ESR_ELx_EC_DABT_LOW
+	mov	x0, #ESR_ELx_EC_IABT_LOW
+	ccmp	x2, x0, #4, ne
+	b.ne	1f		// Not an abort we care about
+
+	/* This is an abort. Check for permission fault */
+	and	x2, x1, #ESR_ELx_FSC_TYPE
+	cmp	x2, #FSC_PERM
+	b.ne	1f		// Not a permission fault
+
+	/*
+	 * Check for Stage-1 page table walk, which is guaranteed
+	 * to give a valid HPFAR_EL2.
+	 */
+	tbnz	x1, #7, 1f	// S1PTW is set
+
+	/* Preserve PAR_EL1 */
+	mrs	x3, par_el1
+	push	x3, xzr
+
+	/*
+	 * Permission fault, HPFAR_EL2 is invalid.
+	 * Resolve the IPA the hard way using the guest VA.
+	 * Stage-1 translation already validated the memory access rights.
+	 * As such, we can use the EL1 translation regime, and don't have
+	 * to distinguish between EL0 and EL1 access.
+	 */
+	mrs	x2, far_el2
+	at	s1e1r, x2
+	isb
+
+	/* Read result */
+	mrs	x3, par_el1
+	pop	x0, xzr			// Restore PAR_EL1 from the stack
+	msr	par_el1, x0
+	tbnz	x3, #0, 3f		// Bail out if we failed the translation
+	ubfx	x3, x3, #12, #36	// Extract IPA
+	lsl	x3, x3, #4		// and present it like HPFAR
+	b	2f
+
+1:	mrs	x3, hpfar_el2
+	mrs	x2, far_el2
+
+2:	mrs	x0, tpidr_el2
+	str	w1, [x0, #VCPU_ESR_EL2]
+	str	x2, [x0, #VCPU_FAR_EL2]
+	str	x3, [x0, #VCPU_HPFAR_EL2]
+
+	mov	x1, #ARM_EXCEPTION_TRAP
+	b	__kvm_vcpu_return
+
+	/*
+	 * Translation failed. Just return to the guest and
+	 * let it fault again. Another CPU is probably playing
+	 * behind our back.
+	 */
+3:	pop	x2, x3
+	pop	x0, x1
+
+	eret
+
+el1_irq:
+	push	x0, x1
+	push	x2, x3
+	mrs	x0, tpidr_el2
+	mov	x1, #ARM_EXCEPTION_IRQ
+	b	__kvm_vcpu_return
+
+	.ltorg
+
+	.align 11
+
+ENTRY(__kvm_hyp_vector)
+	ventry	el2t_sync_invalid		// Synchronous EL2t
+	ventry	el2t_irq_invalid		// IRQ EL2t
+	ventry	el2t_fiq_invalid		// FIQ EL2t
+	ventry	el2t_error_invalid		// Error EL2t
+
+	ventry	el2h_sync_invalid		// Synchronous EL2h
+	ventry	el2h_irq_invalid		// IRQ EL2h
+	ventry	el2h_fiq_invalid		// FIQ EL2h
+	ventry	el2h_error_invalid		// Error EL2h
+
+	ventry	el1_sync			// Synchronous 64-bit EL1
+	ventry	el1_irq				// IRQ 64-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 64-bit EL1
+	ventry	el1_error_invalid		// Error 64-bit EL1
+
+	ventry	el1_sync			// Synchronous 32-bit EL1
+	ventry	el1_irq				// IRQ 32-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
+	ventry	el1_error_invalid		// Error 32-bit EL1
+ENDPROC(__kvm_hyp_vector)
+
+	.popsection
diff --git a/kernel/arch/arm64/kvm/inject_fault.c b/kernel/arch/arm64/kvm/inject_fault.c
new file mode 100644
index 000000000..f02530e72
--- /dev/null
+++ b/kernel/arch/arm64/kvm/inject_fault.c
@@ -0,0 +1,203 @@
+/*
+ * Fault injection for both 32 and 64bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Based on arch/arm/kvm/emulate.c
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/esr.h>
+
+#define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
+				 PSR_I_BIT | PSR_D_BIT)
+#define EL1_EXCEPT_SYNC_OFFSET	0x200
+
+static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
+{
+	unsigned long cpsr;
+	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
+	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
+	u32 return_offset = (is_thumb) ? 4 : 0;
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+
+	cpsr = mode | COMPAT_PSR_I_BIT;
+
+	if (sctlr & (1 << 30))
+		cpsr |= COMPAT_PSR_T_BIT;
+	if (sctlr & (1 << 25))
+		cpsr |= COMPAT_PSR_E_BIT;
+
+	*vcpu_cpsr(vcpu) = cpsr;
+
+	/* Note: These now point to the banked copies */
+	*vcpu_spsr(vcpu) = new_spsr_value;
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+
+	/* Branch to exception vector */
+	if (sctlr & (1 << 13))
+		vect_offset += 0xffff0000;
+	else /* always have security exceptions */
+		vect_offset += vcpu_cp15(vcpu, c12_VBAR);
+
+	*vcpu_pc(vcpu) = vect_offset;
+}
+
+static void inject_undef32(struct kvm_vcpu *vcpu)
+{
+	prepare_fault32(vcpu, COMPAT_PSR_MODE_UND, 4);
+}
+
+/*
+ * Modelled after TakeDataAbortException() and TakePrefetchAbortException
+ * pseudocode.
+ */
+static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
+			 unsigned long addr)
+{
+	u32 vect_offset;
+	u32 *far, *fsr;
+	bool is_lpae;
+
+	if (is_pabt) {
+		vect_offset = 12;
+		far = &vcpu_cp15(vcpu, c6_IFAR);
+		fsr = &vcpu_cp15(vcpu, c5_IFSR);
+	} else { /* !iabt */
+		vect_offset = 16;
+		far = &vcpu_cp15(vcpu, c6_DFAR);
+		fsr = &vcpu_cp15(vcpu, c5_DFSR);
+	}
+
+	prepare_fault32(vcpu, COMPAT_PSR_MODE_ABT | COMPAT_PSR_A_BIT, vect_offset);
+
+	*far = addr;
+
+	/* Give the guest an IMPLEMENTATION DEFINED exception */
+	is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
+	if (is_lpae)
+		*fsr = 1 << 9 | 0x34;
+	else
+		*fsr = 0x14;
+}
+
+static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
+{
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	bool is_aarch32;
+	u32 esr = 0;
+
+	is_aarch32 = vcpu_mode_is_32bit(vcpu);
+
+	*vcpu_spsr(vcpu) = cpsr;
+	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+
+	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
+
+	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
+
+	/*
+	 * Build an {i,d}abort, depending on the level and the
+	 * instruction set. Report an external synchronous abort.
+	 */
+	if (kvm_vcpu_trap_il_is32bit(vcpu))
+		esr |= ESR_ELx_IL;
+
+	/*
+	 * Here, the guest runs in AArch64 mode when in EL1. If we get
+	 * an AArch32 fault, it means we managed to trap an EL0 fault.
+	 */
+	if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t)
+		esr |= (ESR_ELx_EC_IABT_LOW << ESR_ELx_EC_SHIFT);
+	else
+		esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
+
+	if (!is_iabt)
+		esr |= ESR_ELx_EC_DABT_LOW;
+
+	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
+}
+
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+
+	*vcpu_spsr(vcpu) = cpsr;
+	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+
+	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
+
+	/*
+	 * Build an unknown exception, depending on the instruction
+	 * set.
+	 */
+	if (kvm_vcpu_trap_il_is32bit(vcpu))
+		esr |= ESR_ELx_IL;
+
+	vcpu_sys_reg(vcpu, ESR_EL1) = esr;
+}
+
+/**
+ * kvm_inject_dabt - inject a data abort into the guest
+ * @vcpu: The VCPU to receive the undefined exception
+ * @addr: The address to report in the DFAR
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+		inject_abt32(vcpu, false, addr);
+
+	inject_abt64(vcpu, false, addr);
+}
+
+/**
+ * kvm_inject_pabt - inject a prefetch abort into the guest
+ * @vcpu: The VCPU to receive the undefined exception
+ * @addr: The address to report in the DFAR
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+		inject_abt32(vcpu, true, addr);
+
+	inject_abt64(vcpu, true, addr);
+}
+
+/**
+ * kvm_inject_undefined - inject an undefined instruction into the guest
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_undefined(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+		inject_undef32(vcpu);
+
+	inject_undef64(vcpu);
+}
diff --git a/kernel/arch/arm64/kvm/regmap.c b/kernel/arch/arm64/kvm/regmap.c
new file mode 100644
index 000000000..bbc6ae32e
--- /dev/null
+++ b/kernel/arch/arm64/kvm/regmap.c
@@ -0,0 +1,168 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/emulate.c:
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/ptrace.h>
+
+#define VCPU_NR_MODES 6
+#define REG_OFFSET(_reg) \
+	(offsetof(struct user_pt_regs, _reg) / sizeof(unsigned long))
+
+#define USR_REG_OFFSET(R) REG_OFFSET(compat_usr(R))
+
+static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
+	/* USR Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+		USR_REG_OFFSET(12), USR_REG_OFFSET(13),	USR_REG_OFFSET(14),
+		REG_OFFSET(pc)
+	},
+
+	/* FIQ Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7),
+		REG_OFFSET(compat_r8_fiq),  /* r8 */
+		REG_OFFSET(compat_r9_fiq),  /* r9 */
+		REG_OFFSET(compat_r10_fiq), /* r10 */
+		REG_OFFSET(compat_r11_fiq), /* r11 */
+		REG_OFFSET(compat_r12_fiq), /* r12 */
+		REG_OFFSET(compat_sp_fiq),  /* r13 */
+		REG_OFFSET(compat_lr_fiq),  /* r14 */
+		REG_OFFSET(pc)
+	},
+
+	/* IRQ Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+		USR_REG_OFFSET(12),
+		REG_OFFSET(compat_sp_irq), /* r13 */
+		REG_OFFSET(compat_lr_irq), /* r14 */
+		REG_OFFSET(pc)
+	},
+
+	/* SVC Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+		USR_REG_OFFSET(12),
+		REG_OFFSET(compat_sp_svc), /* r13 */
+		REG_OFFSET(compat_lr_svc), /* r14 */
+		REG_OFFSET(pc)
+	},
+
+	/* ABT Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+		USR_REG_OFFSET(12),
+		REG_OFFSET(compat_sp_abt), /* r13 */
+		REG_OFFSET(compat_lr_abt), /* r14 */
+		REG_OFFSET(pc)
+	},
+
+	/* UND Registers */
+	{
+		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+		USR_REG_OFFSET(12),
+		REG_OFFSET(compat_sp_und), /* r13 */
+		REG_OFFSET(compat_lr_und), /* r14 */
+		REG_OFFSET(pc)
+	},
+};
+
+/*
+ * Return a pointer to the register number valid in the current mode of
+ * the virtual CPU.
+ */
+unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
+{
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
+	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+
+	switch (mode) {
+	case COMPAT_PSR_MODE_USR ... COMPAT_PSR_MODE_SVC:
+		mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */
+		break;
+
+	case COMPAT_PSR_MODE_ABT:
+		mode = 4;
+		break;
+
+	case COMPAT_PSR_MODE_UND:
+		mode = 5;
+		break;
+
+	case COMPAT_PSR_MODE_SYS:
+		mode = 0;	/* SYS maps to USR */
+		break;
+
+	default:
+		BUG();
+	}
+
+	return reg_array + vcpu_reg_offsets[mode][reg_num];
+}
+
+/*
+ * Return the SPSR for the current mode of the virtual CPU.
+ */
+unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu)
+{
+	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+	switch (mode) {
+	case COMPAT_PSR_MODE_SVC:
+		mode = KVM_SPSR_SVC;
+		break;
+	case COMPAT_PSR_MODE_ABT:
+		mode = KVM_SPSR_ABT;
+		break;
+	case COMPAT_PSR_MODE_UND:
+		mode = KVM_SPSR_UND;
+		break;
+	case COMPAT_PSR_MODE_IRQ:
+		mode = KVM_SPSR_IRQ;
+		break;
+	case COMPAT_PSR_MODE_FIQ:
+		mode = KVM_SPSR_FIQ;
+		break;
+	default:
+		BUG();
+	}
+
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[mode];
+}
diff --git a/kernel/arch/arm64/kvm/reset.c b/kernel/arch/arm64/kvm/reset.c
new file mode 100644
index 000000000..0b4326578
--- /dev/null
+++ b/kernel/arch/arm64/kvm/reset.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/reset.c
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/errno.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+
+#include <kvm/arm_arch_timer.h>
+
+#include <asm/cputype.h>
+#include <asm/ptrace.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_coproc.h>
+
+/*
+ * ARMv8 Reset Values
+ */
+static const struct kvm_regs default_regs_reset = {
+	.regs.pstate = (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT |
+			PSR_F_BIT | PSR_D_BIT),
+};
+
+static const struct kvm_regs default_regs_reset32 = {
+	.regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT |
+			COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT),
+};
+
+static const struct kvm_irq_level default_vtimer_irq = {
+	.irq	= 27,
+	.level	= 1,
+};
+
+static bool cpu_has_32bit_el1(void)
+{
+	u64 pfr0;
+
+	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+	return !!(pfr0 & 0x20);
+}
+
+int kvm_arch_dev_ioctl_check_extension(long ext)
+{
+	int r;
+
+	switch (ext) {
+	case KVM_CAP_ARM_EL1_32BIT:
+		r = cpu_has_32bit_el1();
+		break;
+	default:
+		r = 0;
+	}
+
+	return r;
+}
+
+/**
+ * kvm_reset_vcpu - sets core registers and sys_regs to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on
+ * the virtual CPU struct to their architectually defined reset
+ * values.
+ */
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
+{
+	const struct kvm_irq_level *cpu_vtimer_irq;
+	const struct kvm_regs *cpu_reset;
+
+	switch (vcpu->arch.target) {
+	default:
+		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
+			if (!cpu_has_32bit_el1())
+				return -EINVAL;
+			cpu_reset = &default_regs_reset32;
+		} else {
+			cpu_reset = &default_regs_reset;
+		}
+
+		cpu_vtimer_irq = &default_vtimer_irq;
+		break;
+	}
+
+	/* Reset core registers */
+	memcpy(vcpu_gp_regs(vcpu), cpu_reset, sizeof(*cpu_reset));
+
+	/* Reset system registers */
+	kvm_reset_sys_regs(vcpu);
+
+	/* Reset timer */
+	kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
+
+	return 0;
+}
diff --git a/kernel/arch/arm64/kvm/sys_regs.c b/kernel/arch/arm64/kvm/sys_regs.c
new file mode 100644
index 000000000..c370b4014
--- /dev/null
+++ b/kernel/arch/arm64/kvm/sys_regs.c
@@ -0,0 +1,1521 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/coproc.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: Rusty Russell <rusty@rustcorp.com.au>
+ *          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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/debug-monitors.h>
+#include <asm/esr.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_mmu.h>
+
+#include <trace/events/kvm.h>
+
+#include "sys_regs.h"
+
+/*
+ * All of this file is extremly similar to the ARM coproc.c, but the
+ * types are different. My gut feeling is that it should be pretty
+ * easy to merge, but that would be an ABI breakage -- again. VFP
+ * would also need to be abstracted.
+ *
+ * For AArch32, we only take care of what is being trapped. Anything
+ * that has to do with init and userspace access has to go via the
+ * 64bit interface.
+ */
+
+/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
+static u32 cache_levels;
+
+/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
+#define CSSELR_MAX 12
+
+/* Which cache CCSIDR represents depends on CSSELR value. */
+static u32 get_ccsidr(u32 csselr)
+{
+	u32 ccsidr;
+
+	/* Make sure noone else changes CSSELR during this! */
+	local_irq_disable();
+	/* Put value into CSSELR */
+	asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+	isb();
+	/* Read result out of CCSIDR */
+	asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
+	local_irq_enable();
+
+	return ccsidr;
+}
+
+/*
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
+ */
+static bool access_dcsw(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
+	kvm_set_way_flush(vcpu);
+	return true;
+}
+
+/*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set. If the guest enables the MMU, we stop trapping the VM
+ * sys_regs and leave it in complete control of the caches.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	unsigned long val;
+	bool was_enabled = vcpu_has_cache_enabled(vcpu);
+
+	BUG_ON(!p->is_write);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	if (!p->is_aarch32) {
+		vcpu_sys_reg(vcpu, r->reg) = val;
+	} else {
+		if (!p->is_32bit)
+			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
+		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+	}
+
+	kvm_toggle_cache(vcpu, was_enabled);
+	return true;
+}
+
+/*
+ * Trap handler for the GICv3 SGI generation system register.
+ * Forward the request to the VGIC emulation.
+ * The cp15_64 code makes sure this automatically works
+ * for both AArch64 and AArch32 accesses.
+ */
+static bool access_gic_sgi(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 val;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	vgic_v3_dispatch_sgi(vcpu, val);
+
+	return true;
+}
+
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+	else
+		return read_zero(vcpu, p);
+}
+
+static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		return true;
+	}
+}
+
+static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
+				   const struct sys_reg_params *p,
+				   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u32 val;
+		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
+		*vcpu_reg(vcpu, p->Rt) = val;
+		return true;
+	}
+}
+
+/*
+ * We want to avoid world-switching all the DBG registers all the
+ * time:
+ * 
+ * - If we've touched any debug register, it is likely that we're
+ *   going to touch more of them. It then makes sense to disable the
+ *   traps and start doing the save/restore dance
+ * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
+ *   then mandatory to save/restore the registers, as the guest
+ *   depends on them.
+ * 
+ * For this, we use a DIRTY bit, indicating the guest has modified the
+ * debug registers, used as follow:
+ *
+ * On guest entry:
+ * - If the dirty bit is set (because we're coming back from trapping),
+ *   disable the traps, save host registers, restore guest registers.
+ * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
+ *   set the dirty bit, disable the traps, save host registers,
+ *   restore guest registers.
+ * - Otherwise, enable the traps
+ *
+ * On guest exit:
+ * - If the dirty bit is set, save guest registers, restore host
+ *   registers and clear the dirty bit. This ensure that the host can
+ *   now use the debug registers.
+ */
+static bool trap_debug_regs(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+	}
+
+	return true;
+}
+
+static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 amair;
+
+	asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
+	vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
+}
+
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 mpidr;
+
+	/*
+	 * Map the vcpu_id into the first three affinity level fields of
+	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
+	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
+	 * of the GICv3 to be able to address each CPU directly when
+	 * sending IPIs.
+	 */
+	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
+	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
+	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
+	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
+}
+
+/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
+#define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
+	/* DBGBVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100),	\
+	  trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 },		\
+	/* DBGBCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101),	\
+	  trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 },		\
+	/* DBGWVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110),	\
+	  trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 },		\
+	/* DBGWCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
+	  trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
+
+/*
+ * Architected system registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * We could trap ID_DFR0 and tell the guest we don't support performance
+ * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
+ * NAKed, so it will read the PMCR anyway.
+ *
+ * Therefore we tell the guest we have 0 counters.  Unfortunately, we
+ * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
+ * all PM registers, which doesn't crash the guest kernel at least.
+ *
+ * Debug handling: We do trap most, if not all debug related system
+ * registers. The implementation is good enough to ensure that a guest
+ * can use these with minimal performance degradation. The drawback is
+ * that we don't implement any of the external debug, none of the
+ * OSlock protocol. This should be revisited if we ever encounter a
+ * more demanding guest...
+ */
+static const struct sys_reg_desc sys_reg_descs[] = {
+	/* DC ISW */
+	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010),
+	  access_dcsw },
+	/* DC CSW */
+	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010),
+	  access_dcsw },
+	/* DC CISW */
+	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
+	  access_dcsw },
+
+	DBG_BCR_BVR_WCR_WVR_EL1(0),
+	DBG_BCR_BVR_WCR_WVR_EL1(1),
+	/* MDCCINT_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+	  trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+	/* MDSCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+	  trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+	DBG_BCR_BVR_WCR_WVR_EL1(2),
+	DBG_BCR_BVR_WCR_WVR_EL1(3),
+	DBG_BCR_BVR_WCR_WVR_EL1(4),
+	DBG_BCR_BVR_WCR_WVR_EL1(5),
+	DBG_BCR_BVR_WCR_WVR_EL1(6),
+	DBG_BCR_BVR_WCR_WVR_EL1(7),
+	DBG_BCR_BVR_WCR_WVR_EL1(8),
+	DBG_BCR_BVR_WCR_WVR_EL1(9),
+	DBG_BCR_BVR_WCR_WVR_EL1(10),
+	DBG_BCR_BVR_WCR_WVR_EL1(11),
+	DBG_BCR_BVR_WCR_WVR_EL1(12),
+	DBG_BCR_BVR_WCR_WVR_EL1(13),
+	DBG_BCR_BVR_WCR_WVR_EL1(14),
+	DBG_BCR_BVR_WCR_WVR_EL1(15),
+
+	/* MDRAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+	  trap_raz_wi },
+	/* OSLAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
+	  trap_raz_wi },
+	/* OSLSR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
+	  trap_oslsr_el1 },
+	/* OSDLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGPRCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGCLAIMSET_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGCLAIMCLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGAUTHSTATUS_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
+	  trap_dbgauthstatus_el1 },
+
+	/* TEECR32_EL1 */
+	{ Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
+	  NULL, reset_val, TEECR32_EL1, 0 },
+	/* TEEHBR32_EL1 */
+	{ Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
+	  NULL, reset_val, TEEHBR32_EL1, 0 },
+
+	/* MDCCSR_EL1 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR[TR]X_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
+	  trap_raz_wi },
+
+	/* DBGVCR32_EL2 */
+	{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
+	  NULL, reset_val, DBGVCR32_EL2, 0 },
+
+	/* MPIDR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101),
+	  NULL, reset_mpidr, MPIDR_EL1 },
+	/* SCTLR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+	  access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+	/* CPACR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
+	  NULL, reset_val, CPACR_EL1, 0 },
+	/* TTBR0_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
+	  access_vm_reg, reset_unknown, TTBR0_EL1 },
+	/* TTBR1_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
+	  access_vm_reg, reset_unknown, TTBR1_EL1 },
+	/* TCR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
+	  access_vm_reg, reset_val, TCR_EL1, 0 },
+
+	/* AFSR0_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
+	  access_vm_reg, reset_unknown, AFSR0_EL1 },
+	/* AFSR1_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
+	  access_vm_reg, reset_unknown, AFSR1_EL1 },
+	/* ESR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
+	  access_vm_reg, reset_unknown, ESR_EL1 },
+	/* FAR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
+	  access_vm_reg, reset_unknown, FAR_EL1 },
+	/* PAR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
+	  NULL, reset_unknown, PAR_EL1 },
+
+	/* PMINTENSET_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
+	  trap_raz_wi },
+	/* PMINTENCLR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
+	  trap_raz_wi },
+
+	/* MAIR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
+	  access_vm_reg, reset_unknown, MAIR_EL1 },
+	/* AMAIR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
+	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
+
+	/* VBAR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
+	  NULL, reset_val, VBAR_EL1, 0 },
+
+	/* ICC_SGI1R_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
+	  access_gic_sgi },
+	/* ICC_SRE_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
+	  trap_raz_wi },
+
+	/* CONTEXTIDR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
+	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
+	/* TPIDR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
+	  NULL, reset_unknown, TPIDR_EL1 },
+
+	/* CNTKCTL_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000),
+	  NULL, reset_val, CNTKCTL_EL1, 0},
+
+	/* CSSELR_EL1 */
+	{ Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
+	  NULL, reset_unknown, CSSELR_EL1 },
+
+	/* PMCR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
+	  trap_raz_wi },
+	/* PMCNTENSET_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
+	  trap_raz_wi },
+	/* PMCNTENCLR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
+	  trap_raz_wi },
+	/* PMOVSCLR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
+	  trap_raz_wi },
+	/* PMSWINC_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
+	  trap_raz_wi },
+	/* PMSELR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
+	  trap_raz_wi },
+	/* PMCEID0_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
+	  trap_raz_wi },
+	/* PMCEID1_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
+	  trap_raz_wi },
+	/* PMCCNTR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
+	  trap_raz_wi },
+	/* PMXEVTYPER_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
+	  trap_raz_wi },
+	/* PMXEVCNTR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
+	  trap_raz_wi },
+	/* PMUSERENR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
+	  trap_raz_wi },
+	/* PMOVSSET_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
+	  trap_raz_wi },
+
+	/* TPIDR_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
+	  NULL, reset_unknown, TPIDR_EL0 },
+	/* TPIDRRO_EL0 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
+	  NULL, reset_unknown, TPIDRRO_EL0 },
+
+	/* DACR32_EL2 */
+	{ Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
+	  NULL, reset_unknown, DACR32_EL2 },
+	/* IFSR32_EL2 */
+	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0000), Op2(0b001),
+	  NULL, reset_unknown, IFSR32_EL2 },
+	/* FPEXC32_EL2 */
+	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0011), Op2(0b000),
+	  NULL, reset_val, FPEXC32_EL2, 0x70 },
+};
+
+static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
+		u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
+		u32 el3 = !!((pfr >> 12) & 0xf);
+
+		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
+					  (((dfr >> 12) & 0xf) << 24) |
+					  (((dfr >> 28) & 0xf) << 20) |
+					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		return true;
+	}
+}
+
+static bool trap_debug32(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+	}
+
+	return true;
+}
+
+#define DBG_BCR_BVR_WCR_WVR(n)					\
+	/* DBGBVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32,	\
+	  NULL, (cp14_DBGBVR0 + (n) * 2) },			\
+	/* DBGBCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32,	\
+	  NULL, (cp14_DBGBCR0 + (n) * 2) },			\
+	/* DBGWVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32,	\
+	  NULL, (cp14_DBGWVR0 + (n) * 2) },			\
+	/* DBGWCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32,	\
+	  NULL, (cp14_DBGWCR0 + (n) * 2) }
+
+#define DBGBXVR(n)						\
+	{ Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32,	\
+	  NULL, cp14_DBGBXVR0 + n * 2 }
+
+/*
+ * Trapped cp14 registers. We generally ignore most of the external
+ * debug, on the principle that they don't really make sense to a
+ * guest. Revisit this one day, whould this principle change.
+ */
+static const struct sys_reg_desc cp14_regs[] = {
+	/* DBGIDR */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+	/* DBGDTRRXext */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
+
+	DBG_BCR_BVR_WCR_WVR(0),
+	/* DBGDSCRint */
+	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(1),
+	/* DBGDCCINT */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+	/* DBGDSCRext */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(2),
+	/* DBGDTR[RT]Xint */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
+	/* DBGDTR[RT]Xext */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(3),
+	DBG_BCR_BVR_WCR_WVR(4),
+	DBG_BCR_BVR_WCR_WVR(5),
+	/* DBGWFAR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
+	/* DBGOSECCR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(6),
+	/* DBGVCR */
+	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(7),
+	DBG_BCR_BVR_WCR_WVR(8),
+	DBG_BCR_BVR_WCR_WVR(9),
+	DBG_BCR_BVR_WCR_WVR(10),
+	DBG_BCR_BVR_WCR_WVR(11),
+	DBG_BCR_BVR_WCR_WVR(12),
+	DBG_BCR_BVR_WCR_WVR(13),
+	DBG_BCR_BVR_WCR_WVR(14),
+	DBG_BCR_BVR_WCR_WVR(15),
+
+	/* DBGDRAR (32bit) */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
+
+	DBGBXVR(0),
+	/* DBGOSLAR */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+	DBGBXVR(1),
+	/* DBGOSLSR */
+	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+	DBGBXVR(2),
+	DBGBXVR(3),
+	/* DBGOSDLR */
+	{ Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
+	DBGBXVR(4),
+	/* DBGPRCR */
+	{ Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
+	DBGBXVR(5),
+	DBGBXVR(6),
+	DBGBXVR(7),
+	DBGBXVR(8),
+	DBGBXVR(9),
+	DBGBXVR(10),
+	DBGBXVR(11),
+	DBGBXVR(12),
+	DBGBXVR(13),
+	DBGBXVR(14),
+	DBGBXVR(15),
+
+	/* DBGDSAR (32bit) */
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
+
+	/* DBGDEVID2 */
+	{ Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
+	/* DBGDEVID1 */
+	{ Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
+	/* DBGDEVID */
+	{ Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
+	/* DBGCLAIMSET */
+	{ Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
+	/* DBGCLAIMCLR */
+	{ Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
+	/* DBGAUTHSTATUS */
+	{ Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
+};
+
+/* Trapped cp14 64bit registers */
+static const struct sys_reg_desc cp14_64_regs[] = {
+	/* DBGDRAR (64bit) */
+	{ Op1( 0), CRm( 1), .access = trap_raz_wi },
+
+	/* DBGDSAR (64bit) */
+	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
+};
+
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
+static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
+
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
+	/*
+	 * DC{C,I,CI}SW operations:
+	 */
+	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
+	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
+	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
+
+	/* PMU */
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
+
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+
+	/* ICC_SRE */
+	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
+
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+};
+
+static const struct sys_reg_desc cp15_64_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
+};
+
+/* Target specific emulation tables */
+static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];
+
+void kvm_register_target_sys_reg_table(unsigned int target,
+				       struct kvm_sys_reg_target_table *table)
+{
+	target_tables[target] = table;
+}
+
+/* Get specific register table for this target. */
+static const struct sys_reg_desc *get_target_table(unsigned target,
+						   bool mode_is_64,
+						   size_t *num)
+{
+	struct kvm_sys_reg_target_table *table;
+
+	table = target_tables[target];
+	if (mode_is_64) {
+		*num = table->table64.num;
+		return table->table64.table;
+	} else {
+		*num = table->table32.num;
+		return table->table32.table;
+	}
+}
+
+static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
+					 const struct sys_reg_desc table[],
+					 unsigned int num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++) {
+		const struct sys_reg_desc *r = &table[i];
+
+		if (params->Op0 != r->Op0)
+			continue;
+		if (params->Op1 != r->Op1)
+			continue;
+		if (params->CRn != r->CRn)
+			continue;
+		if (params->CRm != r->CRm)
+			continue;
+		if (params->Op2 != r->Op2)
+			continue;
+
+		return r;
+	}
+	return NULL;
+}
+
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+/*
+ * emulate_cp --  tries to match a sys_reg access in a handling table, and
+ *                call the corresponding trap handler.
+ *
+ * @params: pointer to the descriptor of the access
+ * @table: array of trap descriptors
+ * @num: size of the trap descriptor array
+ *
+ * Return 0 if the access has been handled, and -1 if not.
+ */
+static int emulate_cp(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_params *params,
+		      const struct sys_reg_desc *table,
+		      size_t num)
+{
+	const struct sys_reg_desc *r;
+
+	if (!table)
+		return -1;	/* Not handled */
+
+	r = find_reg(params, table, num);
+
+	if (r) {
+		/*
+		 * Not having an accessor means that we have
+		 * configured a trap that we don't know how to
+		 * handle. This certainly qualifies as a gross bug
+		 * that should be fixed right away.
+		 */
+		BUG_ON(!r->access);
+
+		if (likely(r->access(vcpu, params, r))) {
+			/* Skip instruction, since it was emulated */
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		}
+
+		/* Handled */
+		return 0;
+	}
+
+	/* Not handled */
+	return -1;
+}
+
+static void unhandled_cp_access(struct kvm_vcpu *vcpu,
+				struct sys_reg_params *params)
+{
+	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	int cp;
+
+	switch(hsr_ec) {
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+		cp = 15;
+		break;
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_64:
+		cp = 14;
+		break;
+	default:
+		WARN_ON((cp = -1));
+	}
+
+	kvm_err("Unsupported guest CP%d access at: %08lx\n",
+		cp, *vcpu_pc(vcpu));
+	print_sys_reg_instr(params);
+	kvm_inject_undefined(vcpu);
+}
+
+/**
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
+{
+	struct sys_reg_params params;
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt2 = (hsr >> 10) & 0xf;
+
+	params.is_aarch32 = true;
+	params.is_32bit = false;
+	params.CRm = (hsr >> 1) & 0xf;
+	params.Rt = (hsr >> 5) & 0xf;
+	params.is_write = ((hsr & 1) == 0);
+
+	params.Op0 = 0;
+	params.Op1 = (hsr >> 16) & 0xf;
+	params.Op2 = 0;
+	params.CRn = 0;
+
+	/*
+	 * Massive hack here. Store Rt2 in the top 32bits so we only
+	 * have one register to deal with. As we use the same trap
+	 * backends between AArch32 and AArch64, we get away with it.
+	 */
+	if (params.is_write) {
+		u64 val = *vcpu_reg(vcpu, params.Rt);
+		val &= 0xffffffff;
+		val |= *vcpu_reg(vcpu, Rt2) << 32;
+		*vcpu_reg(vcpu, params.Rt) = val;
+	}
+
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		goto out;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		goto out;
+
+	unhandled_cp_access(vcpu, &params);
+
+out:
+	/* Do the opposite hack for the read side */
+	if (!params.is_write) {
+		u64 val = *vcpu_reg(vcpu, params.Rt);
+		val >>= 32;
+		*vcpu_reg(vcpu, Rt2) = val;
+	}
+
+	return 1;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
+{
+	struct sys_reg_params params;
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	params.is_aarch32 = true;
+	params.is_32bit = true;
+	params.CRm = (hsr >> 1) & 0xf;
+	params.Rt  = (hsr >> 5) & 0xf;
+	params.is_write = ((hsr & 1) == 0);
+	params.CRn = (hsr >> 10) & 0xf;
+	params.Op0 = 0;
+	params.Op1 = (hsr >> 14) & 0x7;
+	params.Op2 = (hsr >> 17) & 0x7;
+
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		return 1;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		return 1;
+
+	unhandled_cp_access(vcpu, &params);
+	return 1;
+}
+
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_64(vcpu,
+				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_32(vcpu,
+				cp15_regs, ARRAY_SIZE(cp15_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_64(vcpu,
+				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
+				NULL, 0);
+}
+
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_32(vcpu,
+				cp14_regs, ARRAY_SIZE(cp14_regs),
+				NULL, 0);
+}
+
+static int emulate_sys_reg(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *params)
+{
+	size_t num;
+	const struct sys_reg_desc *table, *r;
+
+	table = get_target_table(vcpu->arch.target, true, &num);
+
+	/* Search target-specific then generic table. */
+	r = find_reg(params, table, num);
+	if (!r)
+		r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+	if (likely(r)) {
+		/*
+		 * Not having an accessor means that we have
+		 * configured a trap that we don't know how to
+		 * handle. This certainly qualifies as a gross bug
+		 * that should be fixed right away.
+		 */
+		BUG_ON(!r->access);
+
+		if (likely(r->access(vcpu, params, r))) {
+			/* Skip instruction, since it was emulated */
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			return 1;
+		}
+		/* If access function fails, it should complain. */
+	} else {
+		kvm_err("Unsupported guest sys_reg access at: %lx\n",
+			*vcpu_pc(vcpu));
+		print_sys_reg_instr(params);
+	}
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
+			      const struct sys_reg_desc *table, size_t num)
+{
+	unsigned long i;
+
+	for (i = 0; i < num; i++)
+		if (table[i].reset)
+			table[i].reset(vcpu, &table[i]);
+}
+
+/**
+ * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct sys_reg_params params;
+	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+
+	params.is_aarch32 = false;
+	params.is_32bit = false;
+	params.Op0 = (esr >> 20) & 3;
+	params.Op1 = (esr >> 14) & 0x7;
+	params.CRn = (esr >> 10) & 0xf;
+	params.CRm = (esr >> 1) & 0xf;
+	params.Op2 = (esr >> 17) & 0x7;
+	params.Rt = (esr >> 5) & 0x1f;
+	params.is_write = !(esr & 1);
+
+	return emulate_sys_reg(vcpu, &params);
+}
+
+/******************************************************************************
+ * Userspace API
+ *****************************************************************************/
+
+static bool index_to_params(u64 id, struct sys_reg_params *params)
+{
+	switch (id & KVM_REG_SIZE_MASK) {
+	case KVM_REG_SIZE_U64:
+		/* Any unused index bits means it's not valid. */
+		if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK
+			      | KVM_REG_ARM_COPROC_MASK
+			      | KVM_REG_ARM64_SYSREG_OP0_MASK
+			      | KVM_REG_ARM64_SYSREG_OP1_MASK
+			      | KVM_REG_ARM64_SYSREG_CRN_MASK
+			      | KVM_REG_ARM64_SYSREG_CRM_MASK
+			      | KVM_REG_ARM64_SYSREG_OP2_MASK))
+			return false;
+		params->Op0 = ((id & KVM_REG_ARM64_SYSREG_OP0_MASK)
+			       >> KVM_REG_ARM64_SYSREG_OP0_SHIFT);
+		params->Op1 = ((id & KVM_REG_ARM64_SYSREG_OP1_MASK)
+			       >> KVM_REG_ARM64_SYSREG_OP1_SHIFT);
+		params->CRn = ((id & KVM_REG_ARM64_SYSREG_CRN_MASK)
+			       >> KVM_REG_ARM64_SYSREG_CRN_SHIFT);
+		params->CRm = ((id & KVM_REG_ARM64_SYSREG_CRM_MASK)
+			       >> KVM_REG_ARM64_SYSREG_CRM_SHIFT);
+		params->Op2 = ((id & KVM_REG_ARM64_SYSREG_OP2_MASK)
+			       >> KVM_REG_ARM64_SYSREG_OP2_SHIFT);
+		return true;
+	default:
+		return false;
+	}
+}
+
+/* Decode an index value, and find the sys_reg_desc entry. */
+static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
+						    u64 id)
+{
+	size_t num;
+	const struct sys_reg_desc *table, *r;
+	struct sys_reg_params params;
+
+	/* We only do sys_reg for now. */
+	if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG)
+		return NULL;
+
+	if (!index_to_params(id, &params))
+		return NULL;
+
+	table = get_target_table(vcpu->arch.target, true, &num);
+	r = find_reg(&params, table, num);
+	if (!r)
+		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+	/* Not saved in the sys_reg array? */
+	if (r && !r->reg)
+		r = NULL;
+
+	return r;
+}
+
+/*
+ * These are the invariant sys_reg registers: we let the guest see the
+ * host versions of these, so they're part of the guest state.
+ *
+ * A future CPU may provide a mechanism to present different values to
+ * the guest, or a future kvm may trap them.
+ */
+
+#define FUNCTION_INVARIANT(reg)						\
+	static void get_##reg(struct kvm_vcpu *v,			\
+			      const struct sys_reg_desc *r)		\
+	{								\
+		u64 val;						\
+									\
+		asm volatile("mrs %0, " __stringify(reg) "\n"		\
+			     : "=r" (val));				\
+		((struct sys_reg_desc *)r)->val = val;			\
+	}
+
+FUNCTION_INVARIANT(midr_el1)
+FUNCTION_INVARIANT(ctr_el0)
+FUNCTION_INVARIANT(revidr_el1)
+FUNCTION_INVARIANT(id_pfr0_el1)
+FUNCTION_INVARIANT(id_pfr1_el1)
+FUNCTION_INVARIANT(id_dfr0_el1)
+FUNCTION_INVARIANT(id_afr0_el1)
+FUNCTION_INVARIANT(id_mmfr0_el1)
+FUNCTION_INVARIANT(id_mmfr1_el1)
+FUNCTION_INVARIANT(id_mmfr2_el1)
+FUNCTION_INVARIANT(id_mmfr3_el1)
+FUNCTION_INVARIANT(id_isar0_el1)
+FUNCTION_INVARIANT(id_isar1_el1)
+FUNCTION_INVARIANT(id_isar2_el1)
+FUNCTION_INVARIANT(id_isar3_el1)
+FUNCTION_INVARIANT(id_isar4_el1)
+FUNCTION_INVARIANT(id_isar5_el1)
+FUNCTION_INVARIANT(clidr_el1)
+FUNCTION_INVARIANT(aidr_el1)
+
+/* ->val is filled in by kvm_sys_reg_table_init() */
+static struct sys_reg_desc invariant_sys_regs[] = {
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000),
+	  NULL, get_midr_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110),
+	  NULL, get_revidr_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000),
+	  NULL, get_id_pfr0_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001),
+	  NULL, get_id_pfr1_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010),
+	  NULL, get_id_dfr0_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011),
+	  NULL, get_id_afr0_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100),
+	  NULL, get_id_mmfr0_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101),
+	  NULL, get_id_mmfr1_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110),
+	  NULL, get_id_mmfr2_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111),
+	  NULL, get_id_mmfr3_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+	  NULL, get_id_isar0_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001),
+	  NULL, get_id_isar1_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+	  NULL, get_id_isar2_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011),
+	  NULL, get_id_isar3_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100),
+	  NULL, get_id_isar4_el1 },
+	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101),
+	  NULL, get_id_isar5_el1 },
+	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001),
+	  NULL, get_clidr_el1 },
+	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111),
+	  NULL, get_aidr_el1 },
+	{ Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001),
+	  NULL, get_ctr_el0 },
+};
+
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)
+{
+	if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
+		return -EFAULT;
+	return 0;
+}
+
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id)
+{
+	if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
+		return -EFAULT;
+	return 0;
+}
+
+static int get_invariant_sys_reg(u64 id, void __user *uaddr)
+{
+	struct sys_reg_params params;
+	const struct sys_reg_desc *r;
+
+	if (!index_to_params(id, &params))
+		return -ENOENT;
+
+	r = find_reg(&params, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
+	if (!r)
+		return -ENOENT;
+
+	return reg_to_user(uaddr, &r->val, id);
+}
+
+static int set_invariant_sys_reg(u64 id, void __user *uaddr)
+{
+	struct sys_reg_params params;
+	const struct sys_reg_desc *r;
+	int err;
+	u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */
+
+	if (!index_to_params(id, &params))
+		return -ENOENT;
+	r = find_reg(&params, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
+	if (!r)
+		return -ENOENT;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/* This is what we mean by invariant: you can't change it. */
+	if (r->val != val)
+		return -EINVAL;
+
+	return 0;
+}
+
+static bool is_valid_cache(u32 val)
+{
+	u32 level, ctype;
+
+	if (val >= CSSELR_MAX)
+		return false;
+
+	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
+	level = (val >> 1);
+	ctype = (cache_levels >> (level * 3)) & 7;
+
+	switch (ctype) {
+	case 0: /* No cache */
+		return false;
+	case 1: /* Instruction cache only */
+		return (val & 1);
+	case 2: /* Data cache only */
+	case 4: /* Unified cache */
+		return !(val & 1);
+	case 3: /* Separate instruction and data caches */
+		return true;
+	default: /* Reserved: we can't know instruction or data. */
+		return false;
+	}
+}
+
+static int demux_c15_get(u64 id, void __user *uaddr)
+{
+	u32 val;
+	u32 __user *uval = uaddr;
+
+	/* Fail if we have unknown bits set. */
+	if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
+		   | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
+		return -ENOENT;
+
+	switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
+	case KVM_REG_ARM_DEMUX_ID_CCSIDR:
+		if (KVM_REG_SIZE(id) != 4)
+			return -ENOENT;
+		val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
+			>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
+		if (!is_valid_cache(val))
+			return -ENOENT;
+
+		return put_user(get_ccsidr(val), uval);
+	default:
+		return -ENOENT;
+	}
+}
+
+static int demux_c15_set(u64 id, void __user *uaddr)
+{
+	u32 val, newval;
+	u32 __user *uval = uaddr;
+
+	/* Fail if we have unknown bits set. */
+	if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
+		   | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
+		return -ENOENT;
+
+	switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
+	case KVM_REG_ARM_DEMUX_ID_CCSIDR:
+		if (KVM_REG_SIZE(id) != 4)
+			return -ENOENT;
+		val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
+			>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
+		if (!is_valid_cache(val))
+			return -ENOENT;
+
+		if (get_user(newval, uval))
+			return -EFAULT;
+
+		/* This is also invariant: you can't change it. */
+		if (newval != get_ccsidr(val))
+			return -EINVAL;
+		return 0;
+	default:
+		return -ENOENT;
+	}
+}
+
+int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	const struct sys_reg_desc *r;
+	void __user *uaddr = (void __user *)(unsigned long)reg->addr;
+
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
+		return demux_c15_get(reg->id, uaddr);
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
+		return -ENOENT;
+
+	r = index_to_sys_reg_desc(vcpu, reg->id);
+	if (!r)
+		return get_invariant_sys_reg(reg->id, uaddr);
+
+	return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id);
+}
+
+int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	const struct sys_reg_desc *r;
+	void __user *uaddr = (void __user *)(unsigned long)reg->addr;
+
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
+		return demux_c15_set(reg->id, uaddr);
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
+		return -ENOENT;
+
+	r = index_to_sys_reg_desc(vcpu, reg->id);
+	if (!r)
+		return set_invariant_sys_reg(reg->id, uaddr);
+
+	return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id);
+}
+
+static unsigned int num_demux_regs(void)
+{
+	unsigned int i, count = 0;
+
+	for (i = 0; i < CSSELR_MAX; i++)
+		if (is_valid_cache(i))
+			count++;
+
+	return count;
+}
+
+static int write_demux_regids(u64 __user *uindices)
+{
+	u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
+	unsigned int i;
+
+	val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
+	for (i = 0; i < CSSELR_MAX; i++) {
+		if (!is_valid_cache(i))
+			continue;
+		if (put_user(val | i, uindices))
+			return -EFAULT;
+		uindices++;
+	}
+	return 0;
+}
+
+static u64 sys_reg_to_index(const struct sys_reg_desc *reg)
+{
+	return (KVM_REG_ARM64 | KVM_REG_SIZE_U64 |
+		KVM_REG_ARM64_SYSREG |
+		(reg->Op0 << KVM_REG_ARM64_SYSREG_OP0_SHIFT) |
+		(reg->Op1 << KVM_REG_ARM64_SYSREG_OP1_SHIFT) |
+		(reg->CRn << KVM_REG_ARM64_SYSREG_CRN_SHIFT) |
+		(reg->CRm << KVM_REG_ARM64_SYSREG_CRM_SHIFT) |
+		(reg->Op2 << KVM_REG_ARM64_SYSREG_OP2_SHIFT));
+}
+
+static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind)
+{
+	if (!*uind)
+		return true;
+
+	if (put_user(sys_reg_to_index(reg), *uind))
+		return false;
+
+	(*uind)++;
+	return true;
+}
+
+/* Assumed ordered tables, see kvm_sys_reg_table_init. */
+static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
+{
+	const struct sys_reg_desc *i1, *i2, *end1, *end2;
+	unsigned int total = 0;
+	size_t num;
+
+	/* We check for duplicates here, to allow arch-specific overrides. */
+	i1 = get_target_table(vcpu->arch.target, true, &num);
+	end1 = i1 + num;
+	i2 = sys_reg_descs;
+	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
+
+	BUG_ON(i1 == end1 || i2 == end2);
+
+	/* Walk carefully, as both tables may refer to the same register. */
+	while (i1 || i2) {
+		int cmp = cmp_sys_reg(i1, i2);
+		/* target-specific overrides generic entry. */
+		if (cmp <= 0) {
+			/* Ignore registers we trap but don't save. */
+			if (i1->reg) {
+				if (!copy_reg_to_user(i1, &uind))
+					return -EFAULT;
+				total++;
+			}
+		} else {
+			/* Ignore registers we trap but don't save. */
+			if (i2->reg) {
+				if (!copy_reg_to_user(i2, &uind))
+					return -EFAULT;
+				total++;
+			}
+		}
+
+		if (cmp <= 0 && ++i1 == end1)
+			i1 = NULL;
+		if (cmp >= 0 && ++i2 == end2)
+			i2 = NULL;
+	}
+	return total;
+}
+
+unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu)
+{
+	return ARRAY_SIZE(invariant_sys_regs)
+		+ num_demux_regs()
+		+ walk_sys_regs(vcpu, (u64 __user *)NULL);
+}
+
+int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	unsigned int i;
+	int err;
+
+	/* Then give them all the invariant registers' indices. */
+	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) {
+		if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices))
+			return -EFAULT;
+		uindices++;
+	}
+
+	err = walk_sys_regs(vcpu, uindices);
+	if (err < 0)
+		return err;
+	uindices += err;
+
+	return write_demux_regids(uindices);
+}
+
+static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
+{
+	unsigned int i;
+
+	for (i = 1; i < n; i++) {
+		if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
+			kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+void kvm_sys_reg_table_init(void)
+{
+	unsigned int i;
+	struct sys_reg_desc clidr;
+
+	/* Make sure tables are unique and in order. */
+	BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
+	BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
+	BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
+	BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+	BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
+	BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
+
+	/* We abuse the reset function to overwrite the table itself. */
+	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
+		invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);
+
+	/*
+	 * CLIDR format is awkward, so clean it up.  See ARM B4.1.20:
+	 *
+	 *   If software reads the Cache Type fields from Ctype1
+	 *   upwards, once it has seen a value of 0b000, no caches
+	 *   exist at further-out levels of the hierarchy. So, for
+	 *   example, if Ctype3 is the first Cache Type field with a
+	 *   value of 0b000, the values of Ctype4 to Ctype7 must be
+	 *   ignored.
+	 */
+	get_clidr_el1(NULL, &clidr); /* Ugly... */
+	cache_levels = clidr.val;
+	for (i = 0; i < 7; i++)
+		if (((cache_levels >> (i*3)) & 7) == 0)
+			break;
+	/* Clear all higher bits. */
+	cache_levels &= (1 << (i*3))-1;
+}
+
+/**
+ * kvm_reset_sys_regs - sets system registers to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on the
+ * virtual CPU struct to their architecturally defined reset values.
+ */
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
+{
+	size_t num;
+	const struct sys_reg_desc *table;
+
+	/* Catch someone adding a register without putting in reset entry. */
+	memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs));
+
+	/* Generic chip reset first (so target could override). */
+	reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+	table = get_target_table(vcpu->arch.target, true, &num);
+	reset_sys_reg_descs(vcpu, table, num);
+
+	for (num = 1; num < NR_SYS_REGS; num++)
+		if (vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
+			panic("Didn't reset vcpu_sys_reg(%zi)", num);
+}
diff --git a/kernel/arch/arm64/kvm/sys_regs.h b/kernel/arch/arm64/kvm/sys_regs.h
new file mode 100644
index 000000000..d411e2514
--- /dev/null
+++ b/kernel/arch/arm64/kvm/sys_regs.h
@@ -0,0 +1,140 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/coproc.h
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__
+#define __ARM64_KVM_SYS_REGS_LOCAL_H__
+
+struct sys_reg_params {
+	u8	Op0;
+	u8	Op1;
+	u8	CRn;
+	u8	CRm;
+	u8	Op2;
+	u8	Rt;
+	bool	is_write;
+	bool	is_aarch32;
+	bool	is_32bit;	/* Only valid if is_aarch32 is true */
+};
+
+struct sys_reg_desc {
+	/* MRS/MSR instruction which accesses it. */
+	u8	Op0;
+	u8	Op1;
+	u8	CRn;
+	u8	CRm;
+	u8	Op2;
+
+	/* Trapped access from guest, if non-NULL. */
+	bool (*access)(struct kvm_vcpu *,
+		       const struct sys_reg_params *,
+		       const struct sys_reg_desc *);
+
+	/* Initialization for vcpu. */
+	void (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *);
+
+	/* Index into sys_reg[], or 0 if we don't need to save it. */
+	int reg;
+
+	/* Value (usually reset value) */
+	u64 val;
+};
+
+static inline void print_sys_reg_instr(const struct sys_reg_params *p)
+{
+	/* Look, we even formatted it for you to paste into the table! */
+	kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n",
+		      p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read");
+}
+
+static inline bool ignore_write(struct kvm_vcpu *vcpu,
+				const struct sys_reg_params *p)
+{
+	return true;
+}
+
+static inline bool read_zero(struct kvm_vcpu *vcpu,
+			     const struct sys_reg_params *p)
+{
+	*vcpu_reg(vcpu, p->Rt) = 0;
+	return true;
+}
+
+static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
+				      const struct sys_reg_params *params)
+{
+	kvm_debug("sys_reg write to read-only register at: %lx\n",
+		  *vcpu_pc(vcpu));
+	print_sys_reg_instr(params);
+	return false;
+}
+
+static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
+					const struct sys_reg_params *params)
+{
+	kvm_debug("sys_reg read to write-only register at: %lx\n",
+		  *vcpu_pc(vcpu));
+	print_sys_reg_instr(params);
+	return false;
+}
+
+/* Reset functions */
+static inline void reset_unknown(struct kvm_vcpu *vcpu,
+				 const struct sys_reg_desc *r)
+{
+	BUG_ON(!r->reg);
+	BUG_ON(r->reg >= NR_SYS_REGS);
+	vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+}
+
+static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	BUG_ON(!r->reg);
+	BUG_ON(r->reg >= NR_SYS_REGS);
+	vcpu_sys_reg(vcpu, r->reg) = r->val;
+}
+
+static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
+			      const struct sys_reg_desc *i2)
+{
+	BUG_ON(i1 == i2);
+	if (!i1)
+		return 1;
+	else if (!i2)
+		return -1;
+	if (i1->Op0 != i2->Op0)
+		return i1->Op0 - i2->Op0;
+	if (i1->Op1 != i2->Op1)
+		return i1->Op1 - i2->Op1;
+	if (i1->CRn != i2->CRn)
+		return i1->CRn - i2->CRn;
+	if (i1->CRm != i2->CRm)
+		return i1->CRm - i2->CRm;
+	return i1->Op2 - i2->Op2;
+}
+
+
+#define Op0(_x) 	.Op0 = _x
+#define Op1(_x) 	.Op1 = _x
+#define CRn(_x)		.CRn = _x
+#define CRm(_x) 	.CRm = _x
+#define Op2(_x) 	.Op2 = _x
+
+#endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/kernel/arch/arm64/kvm/sys_regs_generic_v8.c b/kernel/arch/arm64/kvm/sys_regs_generic_v8.c
new file mode 100644
index 000000000..475fd2929
--- /dev/null
+++ b/kernel/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Based on arch/arm/kvm/coproc_a15.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: Rusty Russell <rusty@rustcorp.au>
+ *          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, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kvm_host.h>
+#include <asm/cputype.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <linux/init.h>
+
+#include "sys_regs.h"
+
+static bool access_actlr(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+	return true;
+}
+
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 actlr;
+
+	asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr));
+	vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr;
+}
+
+/*
+ * Implementation specific sys-reg registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ */
+static const struct sys_reg_desc genericv8_sys_regs[] = {
+	/* ACTLR_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
+	  access_actlr, reset_actlr, ACTLR_EL1 },
+};
+
+static const struct sys_reg_desc genericv8_cp15_regs[] = {
+	/* ACTLR */
+	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
+	  access_actlr },
+};
+
+static struct kvm_sys_reg_target_table genericv8_target_table = {
+	.table64 = {
+		.table = genericv8_sys_regs,
+		.num = ARRAY_SIZE(genericv8_sys_regs),
+	},
+	.table32 = {
+		.table = genericv8_cp15_regs,
+		.num = ARRAY_SIZE(genericv8_cp15_regs),
+	},
+};
+
+static int __init sys_reg_genericv8_init(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++)
+		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
+			       &genericv8_sys_regs[i]) >= 0);
+
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8,
+					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
+					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
+					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
+					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
+					  &genericv8_target_table);
+
+	return 0;
+}
+late_initcall(sys_reg_genericv8_init);
diff --git a/kernel/arch/arm64/kvm/trace.h b/kernel/arch/arm64/kvm/trace.h
new file mode 100644
index 000000000..157416e96
--- /dev/null
+++ b/kernel/arch/arm64/kvm/trace.h
@@ -0,0 +1,55 @@
+#if !defined(_TRACE_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM64_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+TRACE_EVENT(kvm_wfx_arm64,
+	TP_PROTO(unsigned long vcpu_pc, bool is_wfe),
+	TP_ARGS(vcpu_pc, is_wfe),
+
+	TP_STRUCT__entry(
+		__field(unsigned long,	vcpu_pc)
+		__field(bool,		is_wfe)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->is_wfe  = is_wfe;
+	),
+
+	TP_printk("guest executed wf%c at: 0x%08lx",
+		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_hvc_arm64,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
+	TP_ARGS(vcpu_pc, r0, imm),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, vcpu_pc)
+		__field(unsigned long, r0)
+		__field(unsigned long, imm)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->r0 = r0;
+		__entry->imm = imm;
+	),
+
+	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+		  __entry->vcpu_pc, __entry->r0, __entry->imm)
+);
+
+#endif /* _TRACE_ARM64_KVM_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/arch/arm64/kvm/vgic-v2-switch.S b/kernel/arch/arm64/kvm/vgic-v2-switch.S
new file mode 100644
index 000000000..f002fe1c3
--- /dev/null
+++ b/kernel/arch/arm64/kvm/vgic-v2-switch.S
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2012,2013 - 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/linkage.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+ENTRY(__save_vgic_v2_state)
+__save_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* Save all interesting registers */
+	ldr	w4, [x2, #GICH_HCR]
+	ldr	w5, [x2, #GICH_VMCR]
+	ldr	w6, [x2, #GICH_MISR]
+	ldr	w7, [x2, #GICH_EISR0]
+	ldr	w8, [x2, #GICH_EISR1]
+	ldr	w9, [x2, #GICH_ELRSR0]
+	ldr	w10, [x2, #GICH_ELRSR1]
+	ldr	w11, [x2, #GICH_APR]
+CPU_BE(	rev	w4,  w4  )
+CPU_BE(	rev	w5,  w5  )
+CPU_BE(	rev	w6,  w6  )
+CPU_BE(	rev	w7,  w7  )
+CPU_BE(	rev	w8,  w8  )
+CPU_BE(	rev	w9,  w9  )
+CPU_BE(	rev	w10, w10 )
+CPU_BE(	rev	w11, w11 )
+
+	str	w4, [x3, #VGIC_V2_CPU_HCR]
+	str	w5, [x3, #VGIC_V2_CPU_VMCR]
+	str	w6, [x3, #VGIC_V2_CPU_MISR]
+CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
+CPU_LE(	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_LE(	str	w9, [x3, #VGIC_V2_CPU_ELRSR] )
+CPU_LE(	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w7, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_BE(	str	w8, [x3, #VGIC_V2_CPU_EISR] )
+CPU_BE(	str	w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w10, [x3, #VGIC_V2_CPU_ELRSR] )
+	str	w11, [x3, #VGIC_V2_CPU_APR]
+
+	/* Clear GICH_HCR */
+	str	wzr, [x2, #GICH_HCR]
+
+	/* Save list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x2], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x3], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__save_vgic_v2_state)
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+ENTRY(__restore_vgic_v2_state)
+__restore_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* We only restore a minimal set of registers */
+	ldr	w4, [x3, #VGIC_V2_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V2_CPU_VMCR]
+	ldr	w6, [x3, #VGIC_V2_CPU_APR]
+CPU_BE(	rev	w4, w4 )
+CPU_BE(	rev	w5, w5 )
+CPU_BE(	rev	w6, w6 )
+
+	str	w4, [x2, #GICH_HCR]
+	str	w5, [x2, #GICH_VMCR]
+	str	w6, [x2, #GICH_APR]
+
+	/* Restore list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x3], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x2], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__restore_vgic_v2_state)
+
+	.popsection
diff --git a/kernel/arch/arm64/kvm/vgic-v3-switch.S b/kernel/arch/arm64/kvm/vgic-v3-switch.S
new file mode 100644
index 000000000..617a012a0
--- /dev/null
+++ b/kernel/arch/arm64/kvm/vgic-v3-switch.S
@@ -0,0 +1,271 @@
+/*
+ * Copyright (C) 2012,2013 - 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/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * We store LRs in reverse order to let the CPU deal with streaming
+ * access. Use this macro to make it look saner...
+ */
+#define LR_OFFSET(n)	(VGIC_V3_CPU_LR + (15 - n) * 8)
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+.macro	save_vgic_v3_state
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Make sure stores to the GIC via the memory mapped interface
+	// are now visible to the system register interface
+	dsb	st
+
+	// Save all interesting registers
+	mrs_s	x4, ICH_HCR_EL2
+	mrs_s	x5, ICH_VMCR_EL2
+	mrs_s	x6, ICH_MISR_EL2
+	mrs_s	x7, ICH_EISR_EL2
+	mrs_s	x8, ICH_ELSR_EL2
+
+	str	w4, [x3, #VGIC_V3_CPU_HCR]
+	str	w5, [x3, #VGIC_V3_CPU_VMCR]
+	str	w6, [x3, #VGIC_V3_CPU_MISR]
+	str	w7, [x3, #VGIC_V3_CPU_EISR]
+	str	w8, [x3, #VGIC_V3_CPU_ELRSR]
+
+	msr_s	ICH_HCR_EL2, xzr
+
+	mrs_s	x21, ICH_VTR_EL2
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	mrs_s	x20, ICH_LR15_EL2
+	mrs_s	x19, ICH_LR14_EL2
+	mrs_s	x18, ICH_LR13_EL2
+	mrs_s	x17, ICH_LR12_EL2
+	mrs_s	x16, ICH_LR11_EL2
+	mrs_s	x15, ICH_LR10_EL2
+	mrs_s	x14, ICH_LR9_EL2
+	mrs_s	x13, ICH_LR8_EL2
+	mrs_s	x12, ICH_LR7_EL2
+	mrs_s	x11, ICH_LR6_EL2
+	mrs_s	x10, ICH_LR5_EL2
+	mrs_s	x9, ICH_LR4_EL2
+	mrs_s	x8, ICH_LR3_EL2
+	mrs_s	x7, ICH_LR2_EL2
+	mrs_s	x6, ICH_LR1_EL2
+	mrs_s	x5, ICH_LR0_EL2
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	str	x20, [x3, #LR_OFFSET(15)]
+	str	x19, [x3, #LR_OFFSET(14)]
+	str	x18, [x3, #LR_OFFSET(13)]
+	str	x17, [x3, #LR_OFFSET(12)]
+	str	x16, [x3, #LR_OFFSET(11)]
+	str	x15, [x3, #LR_OFFSET(10)]
+	str	x14, [x3, #LR_OFFSET(9)]
+	str	x13, [x3, #LR_OFFSET(8)]
+	str	x12, [x3, #LR_OFFSET(7)]
+	str	x11, [x3, #LR_OFFSET(6)]
+	str	x10, [x3, #LR_OFFSET(5)]
+	str	x9, [x3, #LR_OFFSET(4)]
+	str	x8, [x3, #LR_OFFSET(3)]
+	str	x7, [x3, #LR_OFFSET(2)]
+	str	x6, [x3, #LR_OFFSET(1)]
+	str	x5, [x3, #LR_OFFSET(0)]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP0R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	mrs_s	x19, ICH_AP0R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+6:	mrs_s	x18, ICH_AP0R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+5:	mrs_s	x17, ICH_AP0R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP0R]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP1R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	mrs_s	x19, ICH_AP1R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+6:	mrs_s	x18, ICH_AP1R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+5:	mrs_s	x17, ICH_AP1R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP1R]
+
+	// Restore SRE_EL1 access and re-enable SRE at EL1.
+	mrs_s	x5, ICC_SRE_EL2
+	orr	x5, x5, #ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+	isb
+	mov	x5, #1
+	msr_s	ICC_SRE_EL1, x5
+.endm
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+.macro	restore_vgic_v3_state
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Restore all interesting registers
+	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
+	ldr	w25, [x3, #VGIC_V3_CPU_SRE]
+
+	msr_s	ICC_SRE_EL1, x25
+
+	// make sure SRE is valid before writing the other registers
+	isb
+
+	msr_s	ICH_HCR_EL2, x4
+	msr_s	ICH_VMCR_EL2, x5
+
+	mrs_s	x21, ICH_VTR_EL2
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	msr_s	ICH_AP1R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+	msr_s	ICH_AP1R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+	msr_s	ICH_AP1R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP1R]
+	msr_s	ICH_AP1R0_EL2, x17
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	msr_s	ICH_AP0R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+	msr_s	ICH_AP0R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+	msr_s	ICH_AP0R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP0R]
+	msr_s	ICH_AP0R0_EL2, x17
+
+	and	w22, w21, #0xf
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	ldr	x20, [x3, #LR_OFFSET(15)]
+	ldr	x19, [x3, #LR_OFFSET(14)]
+	ldr	x18, [x3, #LR_OFFSET(13)]
+	ldr	x17, [x3, #LR_OFFSET(12)]
+	ldr	x16, [x3, #LR_OFFSET(11)]
+	ldr	x15, [x3, #LR_OFFSET(10)]
+	ldr	x14, [x3, #LR_OFFSET(9)]
+	ldr	x13, [x3, #LR_OFFSET(8)]
+	ldr	x12, [x3, #LR_OFFSET(7)]
+	ldr	x11, [x3, #LR_OFFSET(6)]
+	ldr	x10, [x3, #LR_OFFSET(5)]
+	ldr	x9, [x3, #LR_OFFSET(4)]
+	ldr	x8, [x3, #LR_OFFSET(3)]
+	ldr	x7, [x3, #LR_OFFSET(2)]
+	ldr	x6, [x3, #LR_OFFSET(1)]
+	ldr	x5, [x3, #LR_OFFSET(0)]
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	msr_s	ICH_LR15_EL2, x20
+	msr_s	ICH_LR14_EL2, x19
+	msr_s	ICH_LR13_EL2, x18
+	msr_s	ICH_LR12_EL2, x17
+	msr_s	ICH_LR11_EL2, x16
+	msr_s	ICH_LR10_EL2, x15
+	msr_s	ICH_LR9_EL2,  x14
+	msr_s	ICH_LR8_EL2,  x13
+	msr_s	ICH_LR7_EL2,  x12
+	msr_s	ICH_LR6_EL2,  x11
+	msr_s	ICH_LR5_EL2,  x10
+	msr_s	ICH_LR4_EL2,   x9
+	msr_s	ICH_LR3_EL2,   x8
+	msr_s	ICH_LR2_EL2,   x7
+	msr_s	ICH_LR1_EL2,   x6
+	msr_s	ICH_LR0_EL2,   x5
+
+	// Ensure that the above will have reached the
+	// (re)distributors. This ensure the guest will read
+	// the correct values from the memory-mapped interface.
+	isb
+	dsb	sy
+
+	// Prevent the guest from touching the GIC system registers
+	// if SRE isn't enabled for GICv3 emulation
+	cbnz	x25, 1f
+	mrs_s	x5, ICC_SRE_EL2
+	and	x5, x5, #~ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+1:
+.endm
+
+ENTRY(__save_vgic_v3_state)
+	save_vgic_v3_state
+	ret
+ENDPROC(__save_vgic_v3_state)
+
+ENTRY(__restore_vgic_v3_state)
+	restore_vgic_v3_state
+	ret
+ENDPROC(__restore_vgic_v3_state)
+
+ENTRY(__vgic_v3_get_ich_vtr_el2)
+	mrs_s	x0, ICH_VTR_EL2
+	ret
+ENDPROC(__vgic_v3_get_ich_vtr_el2)
+
+	.popsection