Initial commit; kernel source import

arch/arm/kvm/Kconfig

@@ -0,0 +1,72 @@
+#
+# 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"
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	select KVM_MMIO
+	select KVM_ARM_HOST
+	depends on ARM_VIRT_EXT && ARM_LPAE
+	---help---
+	  Support hosting virtualized guest machines. You will also
+	  need to select one or more of the processor modules below.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_ARM_HOST
+	bool "KVM host support for ARM cpus."
+	depends on KVM
+	depends on MMU
+	select	MMU_NOTIFIER
+	---help---
+	  Provides host support for ARM processors.
+
+config KVM_ARM_MAX_VCPUS
+	int "Number maximum supported virtual CPUs per VM" if KVM_ARM_HOST
+	default 4 if KVM_ARM_HOST
+	default 0
+	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.
+
+config KVM_ARM_VGIC
+	bool "KVM support for Virtual GIC"
+	depends on KVM_ARM_HOST && OF
+	select HAVE_KVM_IRQCHIP
+	default y
+	---help---
+	  Adds support for a hardware assisted, in-kernel GIC emulation.
+
+config KVM_ARM_TIMER
+	bool "KVM support for Architected Timers"
+	depends on KVM_ARM_VGIC && ARM_ARCH_TIMER
+	select HAVE_KVM_IRQCHIP
+	default y
+	---help---
+	  Adds support for the Architected Timers in virtual machines
+
+source drivers/virtio/Kconfig
+
+endif # VIRTUALIZATION

arch/arm/kvm/Makefile

@@ -0,0 +1,23 @@
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+plus_virt := $(call as-instr,.arch_extension virt,+virt)
+ifeq ($(plus_virt),+virt)
+	plus_virt_def := -DREQUIRES_VIRT=1
+endif
+
+ccflags-y += -Ivirt/kvm -Iarch/arm/kvm
+CFLAGS_arm.o := -I. $(plus_virt_def)
+CFLAGS_mmu.o := -I.
+
+AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
+AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
+
+kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
+
+obj-y += kvm-arm.o init.o interrupts.o
+obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
+obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o
+obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o
+obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o

arch/arm/kvm/arch_timer.c

@@ -0,0 +1,272 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/cpu.h>
+#include <linux/of_irq.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+
+#include <clocksource/arm_arch_timer.h>
+#include <asm/arch_timer.h>
+
+#include <asm/kvm_vgic.h>
+#include <asm/kvm_arch_timer.h>
+
+static struct timecounter *timecounter;
+static struct workqueue_struct *wqueue;
+static struct kvm_irq_level timer_irq = {
+	.level	= 1,
+};
+
+static cycle_t kvm_phys_timer_read(void)
+{
+	return timecounter->cc->read(timecounter->cc);
+}
+
+static bool timer_is_armed(struct arch_timer_cpu *timer)
+{
+	return timer->armed;
+}
+
+/* timer_arm: as in "arm the timer", not as in ARM the company */
+static void timer_arm(struct arch_timer_cpu *timer, u64 ns)
+{
+	timer->armed = true;
+	hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns),
+		      HRTIMER_MODE_ABS);
+}
+
+static void timer_disarm(struct arch_timer_cpu *timer)
+{
+	if (timer_is_armed(timer)) {
+		hrtimer_cancel(&timer->timer);
+		cancel_work_sync(&timer->expired);
+		timer->armed = false;
+	}
+}
+
+static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+			    vcpu->arch.timer_cpu.irq->irq,
+			    vcpu->arch.timer_cpu.irq->level);
+}
+
+static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
+{
+	struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
+
+	/*
+	 * We disable the timer in the world switch and let it be
+	 * handled by kvm_timer_sync_hwstate(). Getting a timer
+	 * interrupt at this point is a sure sign of some major
+	 * breakage.
+	 */
+	pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu);
+	return IRQ_HANDLED;
+}
+
+static void kvm_timer_inject_irq_work(struct work_struct *work)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
+	vcpu->arch.timer_cpu.armed = false;
+	kvm_timer_inject_irq(vcpu);
+}
+
+static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
+{
+	struct arch_timer_cpu *timer;
+	timer = container_of(hrt, struct arch_timer_cpu, timer);
+	queue_work(wqueue, &timer->expired);
+	return HRTIMER_NORESTART;
+}
+
+/**
+ * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Disarm any pending soft timers, since the world-switch code will write the
+ * virtual timer state back to the physical CPU.
+ */
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	/*
+	 * We're about to run this vcpu again, so there is no need to
+	 * keep the background timer running, as we're about to
+	 * populate the CPU timer again.
+	 */
+	timer_disarm(timer);
+}
+
+/**
+ * kvm_timer_sync_hwstate - sync timer state from cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the virtual timer was armed and either schedule a corresponding
+ * soft timer or inject directly if already expired.
+ */
+void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	cycle_t cval, now;
+	u64 ns;
+
+	if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
+		!(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE))
+		return;
+
+	cval = timer->cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+	BUG_ON(timer_is_armed(timer));
+
+	if (cval <= now) {
+		/*
+		 * Timer has already expired while we were not
+		 * looking. Inject the interrupt and carry on.
+		 */
+		kvm_timer_inject_irq(vcpu);
+		return;
+	}
+
+	ns = cyclecounter_cyc2ns(timecounter->cc, cval - now);
+	timer_arm(timer, ns);
+}
+
+void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
+	hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	timer->timer.function = kvm_timer_expire;
+	timer->irq = &timer_irq;
+}
+
+static void kvm_timer_init_interrupt(void *info)
+{
+	enable_percpu_irq(timer_irq.irq, 0);
+}
+
+
+static int kvm_timer_cpu_notify(struct notifier_block *self,
+				unsigned long action, void *cpu)
+{
+	switch (action) {
+	case CPU_STARTING:
+	case CPU_STARTING_FROZEN:
+		kvm_timer_init_interrupt(NULL);
+		break;
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		disable_percpu_irq(timer_irq.irq);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_timer_cpu_nb = {
+	.notifier_call = kvm_timer_cpu_notify,
+};
+
+static const struct of_device_id arch_timer_of_match[] = {
+	{ .compatible	= "arm,armv7-timer",	},
+	{},
+};
+
+int kvm_timer_hyp_init(void)
+{
+	struct device_node *np;
+	unsigned int ppi;
+	int err;
+
+	timecounter = arch_timer_get_timecounter();
+	if (!timecounter)
+		return -ENODEV;
+
+	np = of_find_matching_node(NULL, arch_timer_of_match);
+	if (!np) {
+		kvm_err("kvm_arch_timer: can't find DT node\n");
+		return -ENODEV;
+	}
+
+	ppi = irq_of_parse_and_map(np, 2);
+	if (!ppi) {
+		kvm_err("kvm_arch_timer: no virtual timer interrupt\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = request_percpu_irq(ppi, kvm_arch_timer_handler,
+				 "kvm guest timer", kvm_get_running_vcpus());
+	if (err) {
+		kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n",
+			ppi, err);
+		goto out;
+	}
+
+	timer_irq.irq = ppi;
+
+	err = register_cpu_notifier(&kvm_timer_cpu_nb);
+	if (err) {
+		kvm_err("Cannot register timer CPU notifier\n");
+		goto out_free;
+	}
+
+	wqueue = create_singlethread_workqueue("kvm_arch_timer");
+	if (!wqueue) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	kvm_info("%s IRQ%d\n", np->name, ppi);
+	on_each_cpu(kvm_timer_init_interrupt, NULL, 1);
+
+	goto out;
+out_free:
+	free_percpu_irq(ppi, kvm_get_running_vcpus());
+out:
+	of_node_put(np);
+	return err;
+}
+
+void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	timer_disarm(timer);
+}
+
+int kvm_timer_init(struct kvm *kvm)
+{
+	if (timecounter && wqueue) {
+		kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+		kvm->arch.timer.enabled = 1;
+	}
+
+	return 0;
+}

arch/arm/kvm/coproc.h

@@ -0,0 +1,156 @@
+/*
+ * 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, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_COPROC_LOCAL_H__
+#define __ARM_KVM_COPROC_LOCAL_H__
+
+struct coproc_params {
+	unsigned long CRn;
+	unsigned long CRm;
+	unsigned long Op1;
+	unsigned long Op2;
+	unsigned long Rt1;
+	unsigned long Rt2;
+	bool is_64bit;
+	bool is_write;
+};
+
+struct coproc_reg {
+	/* MRC/MCR/MRRC/MCRR instruction which accesses it. */
+	unsigned long CRn;
+	unsigned long CRm;
+	unsigned long Op1;
+	unsigned long Op2;
+
+	bool is_64;
+
+	/* Trapped access from guest, if non-NULL. */
+	bool (*access)(struct kvm_vcpu *,
+		       const struct coproc_params *,
+		       const struct coproc_reg *);
+
+	/* Initialization for vcpu. */
+	void (*reset)(struct kvm_vcpu *, const struct coproc_reg *);
+
+	/* Index into vcpu->arch.cp15[], or 0 if we don't need to save it. */
+	unsigned long reg;
+
+	/* Value (usually reset value) */
+	u64 val;
+};
+
+static inline void print_cp_instr(const struct coproc_params *p)
+{
+	/* Look, we even formatted it for you to paste into the table! */
+	if (p->is_64bit) {
+		kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
+			      p->CRm, p->Op1, p->is_write ? "write" : "read");
+	} else {
+		kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
+			      " func_%s },\n",
+			      p->CRn, p->CRm, p->Op1, p->Op2,
+			      p->is_write ? "write" : "read");
+	}
+}
+
+static inline bool ignore_write(struct kvm_vcpu *vcpu,
+				const struct coproc_params *p)
+{
+	return true;
+}
+
+static inline bool read_zero(struct kvm_vcpu *vcpu,
+			     const struct coproc_params *p)
+{
+	*vcpu_reg(vcpu, p->Rt1) = 0;
+	return true;
+}
+
+static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
+				      const struct coproc_params *params)
+{
+	kvm_debug("CP15 write to read-only register at: %08lx\n",
+		  *vcpu_pc(vcpu));
+	print_cp_instr(params);
+	return false;
+}
+
+static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
+					const struct coproc_params *params)
+{
+	kvm_debug("CP15 read to write-only register at: %08lx\n",
+		  *vcpu_pc(vcpu));
+	print_cp_instr(params);
+	return false;
+}
+
+/* Reset functions */
+static inline void reset_unknown(struct kvm_vcpu *vcpu,
+				 const struct coproc_reg *r)
+{
+	BUG_ON(!r->reg);
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
+	vcpu->arch.cp15[r->reg] = 0xdecafbad;
+}
+
+static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	BUG_ON(!r->reg);
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
+	vcpu->arch.cp15[r->reg] = r->val;
+}
+
+static inline void reset_unknown64(struct kvm_vcpu *vcpu,
+				   const struct coproc_reg *r)
+{
+	BUG_ON(!r->reg);
+	BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.cp15));
+
+	vcpu->arch.cp15[r->reg] = 0xdecafbad;
+	vcpu->arch.cp15[r->reg+1] = 0xd0c0ffee;
+}
+
+static inline int cmp_reg(const struct coproc_reg *i1,
+			  const struct coproc_reg *i2)
+{
+	BUG_ON(i1 == i2);
+	if (!i1)
+		return 1;
+	else if (!i2)
+		return -1;
+	if (i1->CRn != i2->CRn)
+		return i1->CRn - i2->CRn;
+	if (i1->is_64 != i2->is_64)
+		return i2->is_64 - i1->is_64;
+	if (i1->CRm != i2->CRm)
+		return i1->CRm - i2->CRm;
+	if (i1->Op1 != i2->Op1)
+		return i1->Op1 - i2->Op1;
+	return i1->Op2 - i2->Op2;
+}
+
+
+#define CRn(_x)		.CRn = _x
+#define CRm(_x) 	.CRm = _x
+#define CRm64(_x)       .CRn = _x, .CRm = 0
+#define Op1(_x) 	.Op1 = _x
+#define Op2(_x) 	.Op2 = _x
+#define is64		.is_64 = true
+#define is32		.is_64 = false
+
+#endif /* __ARM_KVM_COPROC_LOCAL_H__ */

arch/arm/kvm/coproc_a15.c

@@ -0,0 +1,166 @@
+/*
+ * 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, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include <linux/kvm_host.h>
+#include <asm/cputype.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <linux/init.h>
+
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	/*
+	 * Compute guest MPIDR:
+	 * (Even if we present only one VCPU to the guest on an SMP
+	 * host we don't set the U bit in the MPIDR, or vice versa, as
+	 * revealing the underlying hardware properties is likely to
+	 * be the best choice).
+	 */
+	vcpu->arch.cp15[c0_MPIDR] = (read_cpuid_mpidr() & ~MPIDR_LEVEL_MASK)
+		| (vcpu->vcpu_id & MPIDR_LEVEL_MASK);
+}
+
+#include "coproc.h"
+
+/* A15 TRM 4.3.28: RO WI */
+static bool access_actlr(struct kvm_vcpu *vcpu,
+			 const struct coproc_params *p,
+			 const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
+	return true;
+}
+
+/* A15 TRM 4.3.60: R/O. */
+static bool access_cbar(struct kvm_vcpu *vcpu,
+			const struct coproc_params *p,
+			const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p);
+	return read_zero(vcpu, p);
+}
+
+/* A15 TRM 4.3.48: R/O WI. */
+static bool access_l2ctlr(struct kvm_vcpu *vcpu,
+			  const struct coproc_params *p,
+			  const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
+	return true;
+}
+
+static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	u32 l2ctlr, ncores;
+
+	asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
+	l2ctlr &= ~(3 << 24);
+	ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
+	l2ctlr |= (ncores & 3) << 24;
+
+	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
+}
+
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+	u32 actlr;
+
+	/* ACTLR contains SMP bit: make sure you create all cpus first! */
+	asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr));
+	/* Make the SMP bit consistent with the guest configuration */
+	if (atomic_read(&vcpu->kvm->online_vcpus) > 1)
+		actlr |= 1U << 6;
+	else
+		actlr &= ~(1U << 6);
+
+	vcpu->arch.cp15[c1_ACTLR] = actlr;
+}
+
+/* A15 TRM 4.3.49: R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). */
+static bool access_l2ectlr(struct kvm_vcpu *vcpu,
+			   const struct coproc_params *p,
+			   const struct coproc_reg *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	*vcpu_reg(vcpu, p->Rt1) = 0;
+	return true;
+}
+
+/*
+ * A15-specific CP15 registers.
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ *            registers preceding 32-bit ones.
+ */
+static const struct coproc_reg a15_regs[] = {
+	/* MPIDR: we use VMPIDR for guest access. */
+	{ CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32,
+			NULL, reset_mpidr, c0_MPIDR },
+
+	/* SCTLR: swapped by interrupt.S. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
+			NULL, reset_val, c1_SCTLR, 0x00C50078 },
+	/* ACTLR: trapped by HCR.TAC bit. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
+			access_actlr, reset_actlr, c1_ACTLR },
+	/* CPACR: swapped by interrupt.S. */
+	{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
+			NULL, reset_val, c1_CPACR, 0x00000000 },
+
+	/*
+	 * L2CTLR access (guest wants to know #CPUs).
+	 */
+	{ CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32,
+			access_l2ctlr, reset_l2ctlr, c9_L2CTLR },
+	{ CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr},
+
+	/* The Configuration Base Address Register. */
+	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
+};
+
+static struct kvm_coproc_target_table a15_target_table = {
+	.target = KVM_ARM_TARGET_CORTEX_A15,
+	.table = a15_regs,
+	.num = ARRAY_SIZE(a15_regs),
+};
+
+static int __init coproc_a15_init(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(a15_regs); i++)
+		BUG_ON(cmp_reg(&a15_regs[i-1],
+			       &a15_regs[i]) >= 0);
+
+	kvm_register_target_coproc_table(&a15_target_table);
+	return 0;
+}
+late_initcall(coproc_a15_init);

arch/arm/kvm/emulate.c

@@ -0,0 +1,402 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/mm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/opcodes.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+#define VCPU_NR_MODES		6
+#define VCPU_REG_OFFSET_USR	0
+#define VCPU_REG_OFFSET_FIQ	1
+#define VCPU_REG_OFFSET_IRQ	2
+#define VCPU_REG_OFFSET_SVC	3
+#define VCPU_REG_OFFSET_ABT	4
+#define VCPU_REG_OFFSET_UND	5
+#define REG_OFFSET(_reg) \
+	(offsetof(struct kvm_regs, _reg) / sizeof(u32))
+
+#define USR_REG_OFFSET(_num) REG_OFFSET(usr_regs.uregs[_num])
+
+static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = {
+	/* USR/SYS Registers */
+	[VCPU_REG_OFFSET_USR] = {
+		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),
+	},
+
+	/* FIQ Registers */
+	[VCPU_REG_OFFSET_FIQ] = {
+		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(fiq_regs[0]), /* r8 */
+		REG_OFFSET(fiq_regs[1]), /* r9 */
+		REG_OFFSET(fiq_regs[2]), /* r10 */
+		REG_OFFSET(fiq_regs[3]), /* r11 */
+		REG_OFFSET(fiq_regs[4]), /* r12 */
+		REG_OFFSET(fiq_regs[5]), /* r13 */
+		REG_OFFSET(fiq_regs[6]), /* r14 */
+	},
+
+	/* IRQ Registers */
+	[VCPU_REG_OFFSET_IRQ] = {
+		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(irq_regs[0]), /* r13 */
+		REG_OFFSET(irq_regs[1]), /* r14 */
+	},
+
+	/* SVC Registers */
+	[VCPU_REG_OFFSET_SVC] = {
+		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(svc_regs[0]), /* r13 */
+		REG_OFFSET(svc_regs[1]), /* r14 */
+	},
+
+	/* ABT Registers */
+	[VCPU_REG_OFFSET_ABT] = {
+		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(abt_regs[0]), /* r13 */
+		REG_OFFSET(abt_regs[1]), /* r14 */
+	},
+
+	/* UND Registers */
+	[VCPU_REG_OFFSET_UND] = {
+		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(und_regs[0]), /* r13 */
+		REG_OFFSET(und_regs[1]), /* r14 */
+	},
+};
+
+/*
+ * Return a pointer to the register number valid in the current mode of
+ * the virtual CPU.
+ */
+unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
+{
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs;
+	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
+
+	switch (mode) {
+	case USR_MODE...SVC_MODE:
+		mode &= ~MODE32_BIT; /* 0 ... 3 */
+		break;
+
+	case ABT_MODE:
+		mode = VCPU_REG_OFFSET_ABT;
+		break;
+
+	case UND_MODE:
+		mode = VCPU_REG_OFFSET_UND;
+		break;
+
+	case SYSTEM_MODE:
+		mode = VCPU_REG_OFFSET_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_spsr(struct kvm_vcpu *vcpu)
+{
+	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
+	switch (mode) {
+	case SVC_MODE:
+		return &vcpu->arch.regs.KVM_ARM_SVC_spsr;
+	case ABT_MODE:
+		return &vcpu->arch.regs.KVM_ARM_ABT_spsr;
+	case UND_MODE:
+		return &vcpu->arch.regs.KVM_ARM_UND_spsr;
+	case IRQ_MODE:
+		return &vcpu->arch.regs.KVM_ARM_IRQ_spsr;
+	case FIQ_MODE:
+		return &vcpu->arch.regs.KVM_ARM_FIQ_spsr;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A conditional instruction is allowed to trap, even though it
+ * wouldn't be executed.  So let's re-implement the hardware, in
+ * software!
+ */
+bool kvm_condition_valid(struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr, cond, insn;
+
+	/*
+	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
+	 * catch undefined instructions, and then we won't get past
+	 * the arm_exit_handlers test anyway.
+	 */
+	BUG_ON(!kvm_vcpu_trap_get_class(vcpu));
+
+	/* Top two bits non-zero?  Unconditional. */
+	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+		return true;
+
+	cpsr = *vcpu_cpsr(vcpu);
+
+	/* Is condition field valid? */
+	if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT)
+		cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT;
+	else {
+		/* 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);
+	}
+
+	/* Shift makes it look like an ARM-mode instruction */
+	insn = cond << 28;
+	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
+}
+
+/**
+ * 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 advanved (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 & PSR_T_BIT);
+
+	BUG_ON(is_arm && (cpsr & PSR_IT_MASK));
+
+	if (!(cpsr & PSR_IT_MASK))
+		return;
+
+	cond = (cpsr & 0xe000) >> 13;
+	itbits = (cpsr & 0x1c00) >> (10 - 2);
+	itbits |= (cpsr & (0x3 << 25)) >> 25;
+
+	/* Perform ITAdvance (see page A-52 in ARM DDI 0406C) */
+	if ((itbits & 0x7) == 0)
+		itbits = cond = 0;
+	else
+		itbits = (itbits << 1) & 0x1f;
+
+	cpsr &= ~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_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+	bool is_thumb;
+
+	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_T_BIT);
+	if (is_thumb && !is_wide_instr)
+		*vcpu_pc(vcpu) += 2;
+	else
+		*vcpu_pc(vcpu) += 4;
+	kvm_adjust_itstate(vcpu);
+}
+
+
+/******************************************************************************
+ * Inject exceptions into the guest
+ */
+
+static u32 exc_vector_base(struct kvm_vcpu *vcpu)
+{
+	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+	u32 vbar = vcpu->arch.cp15[c12_VBAR];
+
+	if (sctlr & SCTLR_V)
+		return 0xffff0000;
+	else /* always have security exceptions */
+		return vbar;
+}
+
+/**
+ * kvm_inject_undefined - inject an undefined exception into the guest
+ * @vcpu: The VCPU to receive the undefined exception
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ *
+ * Modelled after TakeUndefInstrException() pseudocode.
+ */
+void kvm_inject_undefined(struct kvm_vcpu *vcpu)
+{
+	unsigned long new_lr_value;
+	unsigned long new_spsr_value;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+	bool is_thumb = (cpsr & PSR_T_BIT);
+	u32 vect_offset = 4;
+	u32 return_offset = (is_thumb) ? 2 : 4;
+
+	new_spsr_value = cpsr;
+	new_lr_value = *vcpu_pc(vcpu) - return_offset;
+
+	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | UND_MODE;
+	*vcpu_cpsr(vcpu) |= PSR_I_BIT;
+	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
+
+	if (sctlr & SCTLR_TE)
+		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
+	if (sctlr & SCTLR_EE)
+		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+
+	/* Note: These now point to UND banked copies */
+	*vcpu_spsr(vcpu) = cpsr;
+	*vcpu_reg(vcpu, 14) = new_lr_value;
+
+	/* Branch to exception vector */
+	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
+}
+
+/*
+ * Modelled after TakeDataAbortException() and TakePrefetchAbortException
+ * pseudocode.
+ */
+static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
+{
+	unsigned long new_lr_value;
+	unsigned long new_spsr_value;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+	bool is_thumb = (cpsr & PSR_T_BIT);
+	u32 vect_offset;
+	u32 return_offset = (is_thumb) ? 4 : 0;
+	bool is_lpae;
+
+	new_spsr_value = cpsr;
+	new_lr_value = *vcpu_pc(vcpu) + return_offset;
+
+	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | ABT_MODE;
+	*vcpu_cpsr(vcpu) |= PSR_I_BIT | PSR_A_BIT;
+	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
+
+	if (sctlr & SCTLR_TE)
+		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
+	if (sctlr & SCTLR_EE)
+		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+
+	/* Note: These now point to ABT banked copies */
+	*vcpu_spsr(vcpu) = cpsr;
+	*vcpu_reg(vcpu, 14) = new_lr_value;
+
+	if (is_pabt)
+		vect_offset = 12;
+	else
+		vect_offset = 16;
+
+	/* Branch to exception vector */
+	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
+
+	if (is_pabt) {
+		/* Set DFAR and DFSR */
+		vcpu->arch.cp15[c6_IFAR] = addr;
+		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		/* Always give debug fault for now - should give guest a clue */
+		if (is_lpae)
+			vcpu->arch.cp15[c5_IFSR] = 1 << 9 | 0x22;
+		else
+			vcpu->arch.cp15[c5_IFSR] = 2;
+	} else { /* !iabt */
+		/* Set DFAR and DFSR */
+		vcpu->arch.cp15[c6_DFAR] = addr;
+		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		/* Always give debug fault for now - should give guest a clue */
+		if (is_lpae)
+			vcpu->arch.cp15[c5_DFSR] = 1 << 9 | 0x22;
+		else
+			vcpu->arch.cp15[c5_DFSR] = 2;
+	}
+
+}
+
+/**
+ * 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)
+{
+	inject_abt(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)
+{
+	inject_abt(vcpu, true, addr);
+}

arch/arm/kvm/guest.c

@@ -0,0 +1,239 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/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>
+
+#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM }
+#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
+
+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)
+{
+	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
+	struct kvm_regs *regs = &vcpu->arch.regs;
+	u64 off;
+
+	if (KVM_REG_SIZE(reg->id) != 4)
+		return -ENOENT;
+
+	/* Our ID is an index into the kvm_regs struct. */
+	off = core_reg_offset_from_id(reg->id);
+	if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id))
+		return -ENOENT;
+
+	return put_user(((u32 *)regs)[off], uaddr);
+}
+
+static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
+	struct kvm_regs *regs = &vcpu->arch.regs;
+	u64 off, val;
+
+	if (KVM_REG_SIZE(reg->id) != 4)
+		return -ENOENT;
+
+	/* Our ID is an index into the kvm_regs struct. */
+	off = core_reg_offset_from_id(reg->id);
+	if (off >= sizeof(*regs) / KVM_REG_SIZE(reg->id))
+		return -ENOENT;
+
+	if (get_user(val, uaddr) != 0)
+		return -EFAULT;
+
+	if (off == KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr)) {
+		unsigned long mode = val & MODE_MASK;
+		switch (mode) {
+		case USR_MODE:
+		case FIQ_MODE:
+		case IRQ_MODE:
+		case SVC_MODE:
+		case ABT_MODE:
+		case UND_MODE:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	((u32 *)regs)[off] = val;
+	return 0;
+}
+
+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);
+}
+
+/**
+ * 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_coproc_regs(vcpu);
+}
+
+/**
+ * kvm_arm_copy_reg_indices - get indices of all registers.
+ *
+ * We do core registers right here, then we apppend coproc regs.
+ */
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	unsigned int i;
+	const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE;
+
+	for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) {
+		if (put_user(core_reg | i, uindices))
+			return -EFAULT;
+		uindices++;
+	}
+
+	return kvm_arm_copy_coproc_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_ARM >> 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);
+
+	return kvm_arm_coproc_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_ARM >> 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);
+
+	return kvm_arm_coproc_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();
+
+	if (implementor != ARM_CPU_IMP_ARM)
+		return -EINVAL;
+
+	switch (part_number) {
+	case ARM_CPU_PART_CORTEX_A15:
+		return KVM_ARM_TARGET_CORTEX_A15;
+	default:
+		return -EINVAL;
+	}
+}
+
+int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+			const struct kvm_vcpu_init *init)
+{
+	unsigned int i;
+
+	/* We can only do a cortex A15 for now. */
+	if (init->target != kvm_target_cpu())
+		return -EINVAL;
+
+	vcpu->arch.target = init->target;
+	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+
+	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
+	for (i = 0; i < sizeof(init->features) * 8; i++) {
+		if (test_bit(i, (void *)init->features)) {
+			if (i >= KVM_VCPU_MAX_FEATURES)
+				return -ENOENT;
+			set_bit(i, vcpu->arch.features);
+		}
+	}
+
+	/* Now we know what it is, we can reset it. */
+	return kvm_reset_vcpu(vcpu);
+}
+
+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;
+}

arch/arm/kvm/handle_exit.c

@@ -0,0 +1,164 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_psci.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+#include "trace.h"
+
+typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+
+static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* SVC called from Hyp mode should never get here */
+	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
+	BUG();
+	return -EINVAL; /* Squash warning */
+}
+
+static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+		      kvm_vcpu_hvc_get_imm(vcpu));
+
+	if (kvm_psci_call(vcpu))
+		return 1;
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (kvm_psci_call(vcpu))
+		return 1;
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* The hypervisor should never cause aborts */
+	kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
+		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
+	return -EFAULT;
+}
+
+static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* This is either an error in the ws. code or an external abort */
+	kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
+		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
+	return -EFAULT;
+}
+
+/**
+ * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * @vcpu:	the vcpu pointer
+ * @run:	the kvm_run structure pointer
+ *
+ * Simply sets the wait_for_interrupts flag on the vcpu structure, 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_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	trace_kvm_wfi(*vcpu_pc(vcpu));
+	kvm_vcpu_block(vcpu);
+	return 1;
+}
+
+static exit_handle_fn arm_exit_handlers[] = {
+	[HSR_EC_WFI]		= kvm_handle_wfi,
+	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
+	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
+	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
+	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
+	[HSR_EC_HVC]		= handle_hvc,
+	[HSR_EC_SMC]		= handle_smc,
+	[HSR_EC_IABT]		= kvm_handle_guest_abort,
+	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
+	[HSR_EC_DABT]		= kvm_handle_guest_abort,
+	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
+};
+
+static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
+{
+	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+
+	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
+	    !arm_exit_handlers[hsr_ec]) {
+		kvm_err("Unknown exception class: hsr: %#08x\n",
+			(unsigned int)kvm_vcpu_get_hsr(vcpu));
+		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_UNDEFINED:
+		kvm_err("Undefined exception in Hyp mode at: %#08lx\n",
+			kvm_vcpu_get_hyp_pc(vcpu));
+		BUG();
+		panic("KVM: Hypervisor undefined exception!\n");
+	case ARM_EXCEPTION_DATA_ABORT:
+	case ARM_EXCEPTION_PREF_ABORT:
+	case ARM_EXCEPTION_HVC:
+		/*
+		 * 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;
+	}
+}

arch/arm/kvm/init.S

@@ -0,0 +1,154 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unified.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+/********************************************************************
+ * Hypervisor initialization
+ *   - should be called with:
+ *       r0 = top of Hyp stack (kernel VA)
+ *       r1 = pointer to hyp vectors
+ *       r2,r3 = Hypervisor pgd pointer
+ *
+ * The init scenario is:
+ * - We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd,
+ *   runtime stack, runtime vectors
+ * - Enable the MMU with the boot pgd
+ * - Jump to a target into the trampoline page (remember, this is the same
+ *   physical page!)
+ * - Now switch to the runtime pgd (same VA, and still the same physical
+ *   page!)
+ * - Invalidate TLBs
+ * - Set stack and vectors
+ * - Profit! (or eret, if you only care about the code).
+ *
+ * As we only have four registers available to pass parameters (and we
+ * need six), we split the init in two phases:
+ * - Phase 1: r0 = 0, r1 = 0, r2,r3 contain the boot PGD.
+ *   Provides the basic HYP init, and enable the MMU.
+ * - Phase 2: r0 = ToS, r1 = vectors, r2,r3 contain the runtime PGD.
+ *   Switches to the runtime PGD, set stack and vectors.
+ */
+
+	.text
+	.pushsection    .hyp.idmap.text,"ax"
+	.align 5
+__kvm_hyp_init:
+	.globl __kvm_hyp_init
+
+	@ Hyp-mode exception vector
+	W(b)	.
+	W(b)	.
+	W(b)	.
+	W(b)	.
+	W(b)	.
+	W(b)	__do_hyp_init
+	W(b)	.
+	W(b)	.
+
+__do_hyp_init:
+	cmp	r0, #0			@ We have a SP?
+	bne	phase2			@ Yes, second stage init
+
+	@ Set the HTTBR to point to the hypervisor PGD pointer passed
+	mcrr	p15, 4, r2, r3, c2
+
+	@ Set the HTCR and VTCR to the same shareability and cacheability
+	@ settings as the non-secure TTBCR and with T0SZ == 0.
+	mrc	p15, 4, r0, c2, c0, 2	@ HTCR
+	ldr	r2, =HTCR_MASK
+	bic	r0, r0, r2
+	mrc	p15, 0, r1, c2, c0, 2	@ TTBCR
+	and	r1, r1, #(HTCR_MASK & ~TTBCR_T0SZ)
+	orr	r0, r0, r1
+	mcr	p15, 4, r0, c2, c0, 2	@ HTCR
+
+	mrc	p15, 4, r1, c2, c1, 2	@ VTCR
+	ldr	r2, =VTCR_MASK
+	bic	r1, r1, r2
+	bic	r0, r0, #(~VTCR_HTCR_SH)	@ clear non-reusable HTCR bits
+	orr	r1, r0, r1
+	orr	r1, r1, #(KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S)
+	mcr	p15, 4, r1, c2, c1, 2	@ VTCR
+
+	@ Use the same memory attributes for hyp. accesses as the kernel
+	@ (copy MAIRx ro HMAIRx).
+	mrc	p15, 0, r0, c10, c2, 0
+	mcr	p15, 4, r0, c10, c2, 0
+	mrc	p15, 0, r0, c10, c2, 1
+	mcr	p15, 4, r0, c10, c2, 1
+
+	@ Set the HSCTLR to:
+	@  - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel)
+	@  - Endianness: Kernel config
+	@  - Fast Interrupt Features: Kernel config
+	@  - Write permission implies XN: disabled
+	@  - Instruction cache: enabled
+	@  - Data/Unified cache: enabled
+	@  - Memory alignment checks: enabled
+	@  - MMU: enabled (this code must be run from an identity mapping)
+	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
+	ldr	r2, =HSCTLR_MASK
+	bic	r0, r0, r2
+	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
+	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
+	and	r1, r1, r2
+ ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+	orr	r1, r1, r2
+	orr	r0, r0, r1
+	isb
+	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
+
+	@ End of init phase-1
+	eret
+
+phase2:
+	@ Set stack pointer
+	mov	sp, r0
+
+	@ Set HVBAR to point to the HYP vectors
+	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
+
+	@ Jump to the trampoline page
+	ldr	r0, =TRAMPOLINE_VA
+	adr	r1, target
+	bfi	r0, r1, #0, #PAGE_SHIFT
+	mov	pc, r0
+
+target:	@ We're now in the trampoline code, switch page tables
+	mcrr	p15, 4, r2, r3, c2
+	isb
+
+	@ Invalidate the old TLBs
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb
+
+	eret
+
+	.ltorg
+
+	.globl __kvm_hyp_init_end
+__kvm_hyp_init_end:
+
+	.popsection

arch/arm/kvm/interrupts.S

@@ -0,0 +1,501 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/unified.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/vfpmacros.h>
+#include "interrupts_head.S"
+
+	.text
+
+__kvm_hyp_code_start:
+	.globl __kvm_hyp_code_start
+
+/********************************************************************
+ * Flush per-VMID TLBs
+ *
+ * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+ *
+ * We rely on the hardware to broadcast the TLB invalidation to all CPUs
+ * inside the inner-shareable domain (which is the case for all v7
+ * implementations).  If we come across a non-IS SMP implementation, we'll
+ * have to use an IPI based mechanism. Until then, we stick to the simple
+ * hardware assisted version.
+ *
+ * As v7 does not support flushing per IPA, just nuke the whole TLB
+ * instead, ignoring the ipa value.
+ */
+ENTRY(__kvm_tlb_flush_vmid_ipa)
+	push	{r2, r3}
+
+	dsb	ishst
+	add	r0, r0, #KVM_VTTBR
+	ldrd	r2, r3, [r0]
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	isb
+	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
+	dsb
+	isb
+	mov	r2, #0
+	mov	r3, #0
+	mcrr	p15, 6, r2, r3, c2	@ Back to VMID #0
+	isb				@ Not necessary if followed by eret
+
+	pop	{r2, r3}
+	bx	lr
+ENDPROC(__kvm_tlb_flush_vmid_ipa)
+
+/********************************************************************
+ * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
+ * domain, for all VMIDs
+ *
+ * void __kvm_flush_vm_context(void);
+ */
+ENTRY(__kvm_flush_vm_context)
+	mov	r0, #0			@ rn parameter for c15 flushes is SBZ
+
+	/* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */
+	mcr     p15, 4, r0, c8, c3, 4
+	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
+	mcr     p15, 0, r0, c7, c1, 0
+	dsb
+	isb				@ Not necessary if followed by eret
+
+	bx	lr
+ENDPROC(__kvm_flush_vm_context)
+
+
+/********************************************************************
+ *  Hypervisor world-switch code
+ *
+ *
+ * int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+ */
+ENTRY(__kvm_vcpu_run)
+	@ Save the vcpu pointer
+	mcr	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
+
+	save_host_regs
+
+	restore_vgic_state
+	restore_timer_state
+
+	@ Store hardware CP15 state and load guest state
+	read_cp15_state store_to_vcpu = 0
+	write_cp15_state read_from_vcpu = 1
+
+	@ If the host kernel has not been configured with VFPv3 support,
+	@ then it is safer if we deny guests from using it as well.
+#ifdef CONFIG_VFPv3
+	@ Set FPEXC_EN so the guest doesn't trap floating point instructions
+	VFPFMRX r2, FPEXC		@ VMRS
+	push	{r2}
+	orr	r2, r2, #FPEXC_EN
+	VFPFMXR FPEXC, r2		@ VMSR
+#endif
+
+	@ Configure Hyp-role
+	configure_hyp_role vmentry
+
+	@ Trap coprocessor CRx accesses
+	set_hstr vmentry
+	set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hdcr vmentry
+
+	@ Write configured ID register into MIDR alias
+	ldr	r1, [vcpu, #VCPU_MIDR]
+	mcr	p15, 4, r1, c0, c0, 0
+
+	@ Write guest view of MPIDR into VMPIDR
+	ldr	r1, [vcpu, #CP15_OFFSET(c0_MPIDR)]
+	mcr	p15, 4, r1, c0, c0, 5
+
+	@ Set up guest memory translation
+	ldr	r1, [vcpu, #VCPU_KVM]
+	add	r1, r1, #KVM_VTTBR
+	ldrd	r2, r3, [r1]
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+
+	@ We're all done, just restore the GPRs and go to the guest
+	restore_guest_regs
+	clrex				@ Clear exclusive monitor
+	eret
+
+__kvm_vcpu_return:
+	/*
+	 * return convention:
+	 * guest r0, r1, r2 saved on the stack
+	 * r0: vcpu pointer
+	 * r1: exception code
+	 */
+	save_guest_regs
+
+	@ Set VMID == 0
+	mov	r2, #0
+	mov	r3, #0
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+
+	@ Don't trap coprocessor accesses for host kernel
+	set_hstr vmexit
+	set_hdcr vmexit
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+
+#ifdef CONFIG_VFPv3
+	@ Save floating point registers we if let guest use them.
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	bne	after_vfp_restore
+
+	@ Switch VFP/NEON hardware state to the host's
+	add	r7, vcpu, #VCPU_VFP_GUEST
+	store_vfp_state r7
+	add	r7, vcpu, #VCPU_VFP_HOST
+	ldr	r7, [r7]
+	restore_vfp_state r7
+
+after_vfp_restore:
+	@ Restore FPEXC_EN which we clobbered on entry
+	pop	{r2}
+	VFPFMXR FPEXC, r2
+#endif
+
+	@ Reset Hyp-role
+	configure_hyp_role vmexit
+
+	@ Let host read hardware MIDR
+	mrc	p15, 0, r2, c0, c0, 0
+	mcr	p15, 4, r2, c0, c0, 0
+
+	@ Back to hardware MPIDR
+	mrc	p15, 0, r2, c0, c0, 5
+	mcr	p15, 4, r2, c0, c0, 5
+
+	@ Store guest CP15 state and restore host state
+	read_cp15_state store_to_vcpu = 1
+	write_cp15_state read_from_vcpu = 0
+
+	save_timer_state
+	save_vgic_state
+
+	restore_host_regs
+	clrex				@ Clear exclusive monitor
+	mov	r0, r1			@ Return the return code
+	mov	r1, #0			@ Clear upper bits in return value
+	bx	lr			@ return to IOCTL
+
+/********************************************************************
+ *  Call function in Hyp mode
+ *
+ *
+ * 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 r0, r1, and r2 (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.
+ *
+ * The calling convention follows the standard AAPCS:
+ *   r0 - r3: caller save
+ *   r12:     caller save
+ *   rest:    callee save
+ */
+ENTRY(kvm_call_hyp)
+	hvc	#0
+	bx	lr
+
+/********************************************************************
+ * Hypervisor exception vector and handlers
+ *
+ *
+ * The KVM/ARM Hypervisor ABI is defined as follows:
+ *
+ * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
+ * instruction is issued since all traps are disabled when running the host
+ * kernel as per the Hyp-mode initialization at boot time.
+ *
+ * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
+ * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
+ * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
+ * instructions are called from within Hyp-mode.
+ *
+ * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
+ *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
+ *    exception vector code will check that the HVC comes from VMID==0 and if
+ *    so will push the necessary state (SPSR, lr_usr) on the Hyp stack.
+ *    - r0 contains a pointer to a HYP function
+ *    - r1, r2, and r3 contain arguments to the above function.
+ *    - The HYP function will be called with its arguments in r0, r1 and r2.
+ *    On HYP function return, we return directly to SVC.
+ *
+ * Note that the above is used to execute code in Hyp-mode from a host-kernel
+ * point of view, and is a different concept from performing a world-switch and
+ * executing guest code SVC mode (with a VMID != 0).
+ */
+
+/* Handle undef, svc, pabt, or dabt by crashing with a user notice */
+.macro bad_exception exception_code, panic_str
+	push	{r0-r2}
+	mrrc	p15, 6, r0, r1, c2	@ Read VTTBR
+	lsr	r1, r1, #16
+	ands	r1, r1, #0xff
+	beq	99f
+
+	load_vcpu			@ Load VCPU pointer
+	.if \exception_code == ARM_EXCEPTION_DATA_ABORT
+	mrc	p15, 4, r2, c5, c2, 0	@ HSR
+	mrc	p15, 4, r1, c6, c0, 0	@ HDFAR
+	str	r2, [vcpu, #VCPU_HSR]
+	str	r1, [vcpu, #VCPU_HxFAR]
+	.endif
+	.if \exception_code == ARM_EXCEPTION_PREF_ABORT
+	mrc	p15, 4, r2, c5, c2, 0	@ HSR
+	mrc	p15, 4, r1, c6, c0, 2	@ HIFAR
+	str	r2, [vcpu, #VCPU_HSR]
+	str	r1, [vcpu, #VCPU_HxFAR]
+	.endif
+	mov	r1, #\exception_code
+	b	__kvm_vcpu_return
+
+	@ We were in the host already. Let's craft a panic-ing return to SVC.
+99:	mrs	r2, cpsr
+	bic	r2, r2, #MODE_MASK
+	orr	r2, r2, #SVC_MODE
+THUMB(	orr	r2, r2, #PSR_T_BIT	)
+	msr	spsr_cxsf, r2
+	mrs	r1, ELR_hyp
+	ldr	r2, =BSYM(panic)
+	msr	ELR_hyp, r2
+	ldr	r0, =\panic_str
+	clrex				@ Clear exclusive monitor
+	eret
+.endm
+
+	.text
+
+	.align 5
+__kvm_hyp_vector:
+	.globl __kvm_hyp_vector
+
+	@ Hyp-mode exception vector
+	W(b)	hyp_reset
+	W(b)	hyp_undef
+	W(b)	hyp_svc
+	W(b)	hyp_pabt
+	W(b)	hyp_dabt
+	W(b)	hyp_hvc
+	W(b)	hyp_irq
+	W(b)	hyp_fiq
+
+	.align
+hyp_reset:
+	b	hyp_reset
+
+	.align
+hyp_undef:
+	bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str
+
+	.align
+hyp_svc:
+	bad_exception ARM_EXCEPTION_HVC, svc_die_str
+
+	.align
+hyp_pabt:
+	bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str
+
+	.align
+hyp_dabt:
+	bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str
+
+	.align
+hyp_hvc:
+	/*
+	 * Getting here is either becuase of a trap from a guest or from calling
+	 * HVC from the host kernel, which means "switch to Hyp mode".
+	 */
+	push	{r0, r1, r2}
+
+	@ Check syndrome register
+	mrc	p15, 4, r1, c5, c2, 0	@ HSR
+	lsr	r0, r1, #HSR_EC_SHIFT
+#ifdef CONFIG_VFPv3
+	cmp	r0, #HSR_EC_CP_0_13
+	beq	switch_to_guest_vfp
+#endif
+	cmp	r0, #HSR_EC_HVC
+	bne	guest_trap		@ Not HVC instr.
+
+	/*
+	 * Let's check if the HVC came from VMID 0 and allow simple
+	 * switch to Hyp mode
+	 */
+	mrrc    p15, 6, r0, r2, c2
+	lsr     r2, r2, #16
+	and     r2, r2, #0xff
+	cmp     r2, #0
+	bne	guest_trap		@ Guest called HVC
+
+host_switch_to_hyp:
+	pop	{r0, r1, r2}
+
+	push	{lr}
+	mrs	lr, SPSR
+	push	{lr}
+
+	mov	lr, r0
+	mov	r0, r1
+	mov	r1, r2
+	mov	r2, r3
+
+THUMB(	orr	lr, #1)
+	blx	lr			@ Call the HYP function
+
+	pop	{lr}
+	msr	SPSR_csxf, lr
+	pop	{lr}
+	eret
+
+guest_trap:
+	load_vcpu			@ Load VCPU pointer to r0
+	str	r1, [vcpu, #VCPU_HSR]
+
+	@ Check if we need the fault information
+	lsr	r1, r1, #HSR_EC_SHIFT
+	cmp	r1, #HSR_EC_IABT
+	mrceq	p15, 4, r2, c6, c0, 2	@ HIFAR
+	beq	2f
+	cmp	r1, #HSR_EC_DABT
+	bne	1f
+	mrc	p15, 4, r2, c6, c0, 0	@ HDFAR
+
+2:	str	r2, [vcpu, #VCPU_HxFAR]
+
+	/*
+	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
+	 *
+	 * Abort on the stage 2 translation for a memory access from a
+	 * Non-secure PL1 or PL0 mode:
+	 *
+	 * For any Access flag fault or Translation fault, and also for any
+	 * Permission fault on the stage 2 translation of a memory access
+	 * made as part of a translation table walk for a stage 1 translation,
+	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
+	 * is UNKNOWN.
+	 */
+
+	/* Check for permission fault, and S1PTW */
+	mrc	p15, 4, r1, c5, c2, 0	@ HSR
+	and	r0, r1, #HSR_FSC_TYPE
+	cmp	r0, #FSC_PERM
+	tsteq	r1, #(1 << 7)		@ S1PTW
+	mrcne	p15, 4, r2, c6, c0, 4	@ HPFAR
+	bne	3f
+
+	/* Preserve PAR */
+	mrrc	p15, 0, r0, r1, c7	@ PAR
+	push	{r0, r1}
+
+	/* Resolve IPA using the xFAR */
+	mcr	p15, 0, r2, c7, c8, 0	@ ATS1CPR
+	isb
+	mrrc	p15, 0, r0, r1, c7	@ PAR
+	tst	r0, #1
+	bne	4f			@ Failed translation
+	ubfx	r2, r0, #12, #20
+	lsl	r2, r2, #4
+	orr	r2, r2, r1, lsl #24
+
+	/* Restore PAR */
+	pop	{r0, r1}
+	mcrr	p15, 0, r0, r1, c7	@ PAR
+
+3:	load_vcpu			@ Load VCPU pointer to r0
+	str	r2, [r0, #VCPU_HPFAR]
+
+1:	mov	r1, #ARM_EXCEPTION_HVC
+	b	__kvm_vcpu_return
+
+4:	pop	{r0, r1}		@ Failed translation, return to guest
+	mcrr	p15, 0, r0, r1, c7	@ PAR
+	clrex
+	pop	{r0, r1, r2}
+	eret
+
+/*
+ * If VFPv3 support is not available, then we will not switch the VFP
+ * registers; however cp10 and cp11 accesses will still trap and fallback
+ * to the regular coprocessor emulation code, which currently will
+ * inject an undefined exception to the guest.
+ */
+#ifdef CONFIG_VFPv3
+switch_to_guest_vfp:
+	load_vcpu			@ Load VCPU pointer to r0
+	push	{r3-r7}
+
+	@ NEON/VFP used.  Turn on VFP access.
+	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+
+	@ Switch VFP/NEON hardware state to the guest's
+	add	r7, r0, #VCPU_VFP_HOST
+	ldr	r7, [r7]
+	store_vfp_state r7
+	add	r7, r0, #VCPU_VFP_GUEST
+	restore_vfp_state r7
+
+	pop	{r3-r7}
+	pop	{r0-r2}
+	clrex
+	eret
+#endif
+
+	.align
+hyp_irq:
+	push	{r0, r1, r2}
+	mov	r1, #ARM_EXCEPTION_IRQ
+	load_vcpu			@ Load VCPU pointer to r0
+	b	__kvm_vcpu_return
+
+	.align
+hyp_fiq:
+	b	hyp_fiq
+
+	.ltorg
+
+__kvm_hyp_code_end:
+	.globl	__kvm_hyp_code_end
+
+	.section ".rodata"
+
+und_die_str:
+	.ascii	"unexpected undefined exception in Hyp mode at: %#08x"
+pabt_die_str:
+	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x"
+dabt_die_str:
+	.ascii	"unexpected data abort in Hyp mode at: %#08x"
+svc_die_str:
+	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x"

arch/arm/kvm/interrupts_head.S

@@ -0,0 +1,611 @@
+#include <linux/irqchip/arm-gic.h>
+
+#define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
+#define VCPU_USR_SP		(VCPU_USR_REG(13))
+#define VCPU_USR_LR		(VCPU_USR_REG(14))
+#define CP15_OFFSET(_cp15_reg_idx) (VCPU_CP15 + (_cp15_reg_idx * 4))
+
+/*
+ * Many of these macros need to access the VCPU structure, which is always
+ * held in r0. These macros should never clobber r1, as it is used to hold the
+ * exception code on the return path (except of course the macro that switches
+ * all the registers before the final jump to the VM).
+ */
+vcpu	.req	r0		@ vcpu pointer always in r0
+
+/* Clobbers {r2-r6} */
+.macro store_vfp_state vfp_base
+	@ The VFPFMRX and VFPFMXR macros are the VMRS and VMSR instructions
+	VFPFMRX	r2, FPEXC
+	@ Make sure VFP is enabled so we can touch the registers.
+	orr	r6, r2, #FPEXC_EN
+	VFPFMXR	FPEXC, r6
+
+	VFPFMRX	r3, FPSCR
+	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
+	@ we only need to save them if FPEXC_EX is set.
+	VFPFMRX r4, FPINST
+	tst	r2, #FPEXC_FP2V
+	VFPFMRX r5, FPINST2, ne		@ vmrsne
+	bic	r6, r2, #FPEXC_EX	@ FPEXC_EX disable
+	VFPFMXR	FPEXC, r6
+1:
+	VFPFSTMIA \vfp_base, r6		@ Save VFP registers
+	stm	\vfp_base, {r2-r5}	@ Save FPEXC, FPSCR, FPINST, FPINST2
+.endm
+
+/* Assume FPEXC_EN is on and FPEXC_EX is off, clobbers {r2-r6} */
+.macro restore_vfp_state vfp_base
+	VFPFLDMIA \vfp_base, r6		@ Load VFP registers
+	ldm	\vfp_base, {r2-r5}	@ Load FPEXC, FPSCR, FPINST, FPINST2
+
+	VFPFMXR FPSCR, r3
+	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	VFPFMXR FPINST, r4
+	tst	r2, #FPEXC_FP2V
+	VFPFMXR FPINST2, r5, ne
+1:
+	VFPFMXR FPEXC, r2	@ FPEXC	(last, in case !EN)
+.endm
+
+/* These are simply for the macros to work - value don't have meaning */
+.equ usr, 0
+.equ svc, 1
+.equ abt, 2
+.equ und, 3
+.equ irq, 4
+.equ fiq, 5
+
+.macro push_host_regs_mode mode
+	mrs	r2, SP_\mode
+	mrs	r3, LR_\mode
+	mrs	r4, SPSR_\mode
+	push	{r2, r3, r4}
+.endm
+
+/*
+ * Store all host persistent registers on the stack.
+ * Clobbers all registers, in all modes, except r0 and r1.
+ */
+.macro save_host_regs
+	/* Hyp regs. Only ELR_hyp (SPSR_hyp already saved) */
+	mrs	r2, ELR_hyp
+	push	{r2}
+
+	/* usr regs */
+	push	{r4-r12}	@ r0-r3 are always clobbered
+	mrs	r2, SP_usr
+	mov	r3, lr
+	push	{r2, r3}
+
+	push_host_regs_mode svc
+	push_host_regs_mode abt
+	push_host_regs_mode und
+	push_host_regs_mode irq
+
+	/* fiq regs */
+	mrs	r2, r8_fiq
+	mrs	r3, r9_fiq
+	mrs	r4, r10_fiq
+	mrs	r5, r11_fiq
+	mrs	r6, r12_fiq
+	mrs	r7, SP_fiq
+	mrs	r8, LR_fiq
+	mrs	r9, SPSR_fiq
+	push	{r2-r9}
+.endm
+
+.macro pop_host_regs_mode mode
+	pop	{r2, r3, r4}
+	msr	SP_\mode, r2
+	msr	LR_\mode, r3
+	msr	SPSR_\mode, r4
+.endm
+
+/*
+ * Restore all host registers from the stack.
+ * Clobbers all registers, in all modes, except r0 and r1.
+ */
+.macro restore_host_regs
+	pop	{r2-r9}
+	msr	r8_fiq, r2
+	msr	r9_fiq, r3
+	msr	r10_fiq, r4
+	msr	r11_fiq, r5
+	msr	r12_fiq, r6
+	msr	SP_fiq, r7
+	msr	LR_fiq, r8
+	msr	SPSR_fiq, r9
+
+	pop_host_regs_mode irq
+	pop_host_regs_mode und
+	pop_host_regs_mode abt
+	pop_host_regs_mode svc
+
+	pop	{r2, r3}
+	msr	SP_usr, r2
+	mov	lr, r3
+	pop	{r4-r12}
+
+	pop	{r2}
+	msr	ELR_hyp, r2
+.endm
+
+/*
+ * Restore SP, LR and SPSR for a given mode. offset is the offset of
+ * this mode's registers from the VCPU base.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ *
+ * Clobbers r1, r2, r3, r4.
+ */
+.macro restore_guest_regs_mode mode, offset
+	add	r1, vcpu, \offset
+	ldm	r1, {r2, r3, r4}
+	msr	SP_\mode, r2
+	msr	LR_\mode, r3
+	msr	SPSR_\mode, r4
+.endm
+
+/*
+ * Restore all guest registers from the vcpu struct.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ *
+ * Clobbers *all* registers.
+ */
+.macro restore_guest_regs
+	restore_guest_regs_mode svc, #VCPU_SVC_REGS
+	restore_guest_regs_mode abt, #VCPU_ABT_REGS
+	restore_guest_regs_mode und, #VCPU_UND_REGS
+	restore_guest_regs_mode irq, #VCPU_IRQ_REGS
+
+	add	r1, vcpu, #VCPU_FIQ_REGS
+	ldm	r1, {r2-r9}
+	msr	r8_fiq, r2
+	msr	r9_fiq, r3
+	msr	r10_fiq, r4
+	msr	r11_fiq, r5
+	msr	r12_fiq, r6
+	msr	SP_fiq, r7
+	msr	LR_fiq, r8
+	msr	SPSR_fiq, r9
+
+	@ Load return state
+	ldr	r2, [vcpu, #VCPU_PC]
+	ldr	r3, [vcpu, #VCPU_CPSR]
+	msr	ELR_hyp, r2
+	msr	SPSR_cxsf, r3
+
+	@ Load user registers
+	ldr	r2, [vcpu, #VCPU_USR_SP]
+	ldr	r3, [vcpu, #VCPU_USR_LR]
+	msr	SP_usr, r2
+	mov	lr, r3
+	add	vcpu, vcpu, #(VCPU_USR_REGS)
+	ldm	vcpu, {r0-r12}
+.endm
+
+/*
+ * Save SP, LR and SPSR for a given mode. offset is the offset of
+ * this mode's registers from the VCPU base.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ *
+ * Clobbers r2, r3, r4, r5.
+ */
+.macro save_guest_regs_mode mode, offset
+	add	r2, vcpu, \offset
+	mrs	r3, SP_\mode
+	mrs	r4, LR_\mode
+	mrs	r5, SPSR_\mode
+	stm	r2, {r3, r4, r5}
+.endm
+
+/*
+ * Save all guest registers to the vcpu struct
+ * Expects guest's r0, r1, r2 on the stack.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ *
+ * Clobbers r2, r3, r4, r5.
+ */
+.macro save_guest_regs
+	@ Store usr registers
+	add	r2, vcpu, #VCPU_USR_REG(3)
+	stm	r2, {r3-r12}
+	add	r2, vcpu, #VCPU_USR_REG(0)
+	pop	{r3, r4, r5}		@ r0, r1, r2
+	stm	r2, {r3, r4, r5}
+	mrs	r2, SP_usr
+	mov	r3, lr
+	str	r2, [vcpu, #VCPU_USR_SP]
+	str	r3, [vcpu, #VCPU_USR_LR]
+
+	@ Store return state
+	mrs	r2, ELR_hyp
+	mrs	r3, spsr
+	str	r2, [vcpu, #VCPU_PC]
+	str	r3, [vcpu, #VCPU_CPSR]
+
+	@ Store other guest registers
+	save_guest_regs_mode svc, #VCPU_SVC_REGS
+	save_guest_regs_mode abt, #VCPU_ABT_REGS
+	save_guest_regs_mode und, #VCPU_UND_REGS
+	save_guest_regs_mode irq, #VCPU_IRQ_REGS
+.endm
+
+/* Reads cp15 registers from hardware and stores them in memory
+ * @store_to_vcpu: If 0, registers are written in-order to the stack,
+ * 		   otherwise to the VCPU struct pointed to by vcpup
+ *
+ * Assumes vcpu pointer in vcpu reg
+ *
+ * Clobbers r2 - r12
+ */
+.macro read_cp15_state store_to_vcpu
+	mrc	p15, 0, r2, c1, c0, 0	@ SCTLR
+	mrc	p15, 0, r3, c1, c0, 2	@ CPACR
+	mrc	p15, 0, r4, c2, c0, 2	@ TTBCR
+	mrc	p15, 0, r5, c3, c0, 0	@ DACR
+	mrrc	p15, 0, r6, r7, c2	@ TTBR 0
+	mrrc	p15, 1, r8, r9, c2	@ TTBR 1
+	mrc	p15, 0, r10, c10, c2, 0	@ PRRR
+	mrc	p15, 0, r11, c10, c2, 1	@ NMRR
+	mrc	p15, 2, r12, c0, c0, 0	@ CSSELR
+
+	.if \store_to_vcpu == 0
+	push	{r2-r12}		@ Push CP15 registers
+	.else
+	str	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
+	str	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
+	str	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
+	str	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
+	add	r2, vcpu, #CP15_OFFSET(c2_TTBR0)
+	strd	r6, r7, [r2]
+	add	r2, vcpu, #CP15_OFFSET(c2_TTBR1)
+	strd	r8, r9, [r2]
+	str	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
+	str	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
+	str	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
+	.endif
+
+	mrc	p15, 0, r2, c13, c0, 1	@ CID
+	mrc	p15, 0, r3, c13, c0, 2	@ TID_URW
+	mrc	p15, 0, r4, c13, c0, 3	@ TID_URO
+	mrc	p15, 0, r5, c13, c0, 4	@ TID_PRIV
+	mrc	p15, 0, r6, c5, c0, 0	@ DFSR
+	mrc	p15, 0, r7, c5, c0, 1	@ IFSR
+	mrc	p15, 0, r8, c5, c1, 0	@ ADFSR
+	mrc	p15, 0, r9, c5, c1, 1	@ AIFSR
+	mrc	p15, 0, r10, c6, c0, 0	@ DFAR
+	mrc	p15, 0, r11, c6, c0, 2	@ IFAR
+	mrc	p15, 0, r12, c12, c0, 0	@ VBAR
+
+	.if \store_to_vcpu == 0
+	push	{r2-r12}		@ Push CP15 registers
+	.else
+	str	r2, [vcpu, #CP15_OFFSET(c13_CID)]
+	str	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
+	str	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
+	str	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
+	str	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
+	str	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
+	str	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
+	str	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
+	str	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
+	str	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
+	str	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
+	.endif
+
+	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
+	mrrc	p15, 0, r4, r5, c7	@ PAR
+
+	.if \store_to_vcpu == 0
+	push	{r2,r4-r5}
+	.else
+	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
+	strd	r4, r5, [r12]
+	.endif
+.endm
+
+/*
+ * Reads cp15 registers from memory and writes them to hardware
+ * @read_from_vcpu: If 0, registers are read in-order from the stack,
+ *		    otherwise from the VCPU struct pointed to by vcpup
+ *
+ * Assumes vcpu pointer in vcpu reg
+ */
+.macro write_cp15_state read_from_vcpu
+	.if \read_from_vcpu == 0
+	pop	{r2,r4-r5}
+	.else
+	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
+	ldrd	r4, r5, [r12]
+	.endif
+
+	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
+	mcrr	p15, 0, r4, r5, c7	@ PAR
+
+	.if \read_from_vcpu == 0
+	pop	{r2-r12}
+	.else
+	ldr	r2, [vcpu, #CP15_OFFSET(c13_CID)]
+	ldr	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
+	ldr	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
+	ldr	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
+	ldr	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
+	ldr	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
+	ldr	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
+	ldr	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
+	ldr	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
+	ldr	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
+	ldr	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
+	.endif
+
+	mcr	p15, 0, r2, c13, c0, 1	@ CID
+	mcr	p15, 0, r3, c13, c0, 2	@ TID_URW
+	mcr	p15, 0, r4, c13, c0, 3	@ TID_URO
+	mcr	p15, 0, r5, c13, c0, 4	@ TID_PRIV
+	mcr	p15, 0, r6, c5, c0, 0	@ DFSR
+	mcr	p15, 0, r7, c5, c0, 1	@ IFSR
+	mcr	p15, 0, r8, c5, c1, 0	@ ADFSR
+	mcr	p15, 0, r9, c5, c1, 1	@ AIFSR
+	mcr	p15, 0, r10, c6, c0, 0	@ DFAR
+	mcr	p15, 0, r11, c6, c0, 2	@ IFAR
+	mcr	p15, 0, r12, c12, c0, 0	@ VBAR
+
+	.if \read_from_vcpu == 0
+	pop	{r2-r12}
+	.else
+	ldr	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
+	ldr	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
+	ldr	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
+	ldr	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
+	add	r12, vcpu, #CP15_OFFSET(c2_TTBR0)
+	ldrd	r6, r7, [r12]
+	add	r12, vcpu, #CP15_OFFSET(c2_TTBR1)
+	ldrd	r8, r9, [r12]
+	ldr	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
+	ldr	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
+	ldr	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
+	.endif
+
+	mcr	p15, 0, r2, c1, c0, 0	@ SCTLR
+	mcr	p15, 0, r3, c1, c0, 2	@ CPACR
+	mcr	p15, 0, r4, c2, c0, 2	@ TTBCR
+	mcr	p15, 0, r5, c3, c0, 0	@ DACR
+	mcrr	p15, 0, r6, r7, c2	@ TTBR 0
+	mcrr	p15, 1, r8, r9, c2	@ TTBR 1
+	mcr	p15, 0, r10, c10, c2, 0	@ PRRR
+	mcr	p15, 0, r11, c10, c2, 1	@ NMRR
+	mcr	p15, 2, r12, c0, c0, 0	@ CSSELR
+.endm
+
+/*
+ * Save the VGIC CPU state into memory
+ *
+ * Assumes vcpu pointer in vcpu reg
+ */
+.macro save_vgic_state
+#ifdef CONFIG_KVM_ARM_VGIC
+	/* Get VGIC VCTRL base into r2 */
+	ldr	r2, [vcpu, #VCPU_KVM]
+	ldr	r2, [r2, #KVM_VGIC_VCTRL]
+	cmp	r2, #0
+	beq	2f
+
+	/* Compute the address of struct vgic_cpu */
+	add	r11, vcpu, #VCPU_VGIC_CPU
+
+	/* Save all interesting registers */
+	ldr	r3, [r2, #GICH_HCR]
+	ldr	r4, [r2, #GICH_VMCR]
+	ldr	r5, [r2, #GICH_MISR]
+	ldr	r6, [r2, #GICH_EISR0]
+	ldr	r7, [r2, #GICH_EISR1]
+	ldr	r8, [r2, #GICH_ELRSR0]
+	ldr	r9, [r2, #GICH_ELRSR1]
+	ldr	r10, [r2, #GICH_APR]
+
+	str	r3, [r11, #VGIC_CPU_HCR]
+	str	r4, [r11, #VGIC_CPU_VMCR]
+	str	r5, [r11, #VGIC_CPU_MISR]
+	str	r6, [r11, #VGIC_CPU_EISR]
+	str	r7, [r11, #(VGIC_CPU_EISR + 4)]
+	str	r8, [r11, #VGIC_CPU_ELRSR]
+	str	r9, [r11, #(VGIC_CPU_ELRSR + 4)]
+	str	r10, [r11, #VGIC_CPU_APR]
+
+	/* Clear GICH_HCR */
+	mov	r5, #0
+	str	r5, [r2, #GICH_HCR]
+
+	/* Save list registers */
+	add	r2, r2, #GICH_LR0
+	add	r3, r11, #VGIC_CPU_LR
+	ldr	r4, [r11, #VGIC_CPU_NR_LR]
+1:	ldr	r6, [r2], #4
+	str	r6, [r3], #4
+	subs	r4, r4, #1
+	bne	1b
+2:
+#endif
+.endm
+
+/*
+ * Restore the VGIC CPU state from memory
+ *
+ * Assumes vcpu pointer in vcpu reg
+ */
+.macro restore_vgic_state
+#ifdef CONFIG_KVM_ARM_VGIC
+	/* Get VGIC VCTRL base into r2 */
+	ldr	r2, [vcpu, #VCPU_KVM]
+	ldr	r2, [r2, #KVM_VGIC_VCTRL]
+	cmp	r2, #0
+	beq	2f
+
+	/* Compute the address of struct vgic_cpu */
+	add	r11, vcpu, #VCPU_VGIC_CPU
+
+	/* We only restore a minimal set of registers */
+	ldr	r3, [r11, #VGIC_CPU_HCR]
+	ldr	r4, [r11, #VGIC_CPU_VMCR]
+	ldr	r8, [r11, #VGIC_CPU_APR]
+
+	str	r3, [r2, #GICH_HCR]
+	str	r4, [r2, #GICH_VMCR]
+	str	r8, [r2, #GICH_APR]
+
+	/* Restore list registers */
+	add	r2, r2, #GICH_LR0
+	add	r3, r11, #VGIC_CPU_LR
+	ldr	r4, [r11, #VGIC_CPU_NR_LR]
+1:	ldr	r6, [r3], #4
+	str	r6, [r2], #4
+	subs	r4, r4, #1
+	bne	1b
+2:
+#endif
+.endm
+
+#define CNTHCTL_PL1PCTEN	(1 << 0)
+#define CNTHCTL_PL1PCEN		(1 << 1)
+
+/*
+ * Save the timer state onto the VCPU and allow physical timer/counter access
+ * for the host.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ * Clobbers r2-r5
+ */
+.macro save_timer_state
+#ifdef CONFIG_KVM_ARM_TIMER
+	ldr	r4, [vcpu, #VCPU_KVM]
+	ldr	r2, [r4, #KVM_TIMER_ENABLED]
+	cmp	r2, #0
+	beq	1f
+
+	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
+	bic	r2, #1			@ Clear ENABLE
+	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+	isb
+
+	mrrc	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	ldr	r4, =VCPU_TIMER_CNTV_CVAL
+	add	r5, vcpu, r4
+	strd	r2, r3, [r5]
+
+1:
+#endif
+	@ Allow physical timer/counter access for the host
+	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
+	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
+	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
+.endm
+
+/*
+ * Load the timer state from the VCPU and deny physical timer/counter access
+ * for the host.
+ *
+ * Assumes vcpu pointer in vcpu reg
+ * Clobbers r2-r5
+ */
+.macro restore_timer_state
+	@ Disallow physical timer access for the guest
+	@ Physical counter access is allowed
+	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
+	orr	r2, r2, #CNTHCTL_PL1PCTEN
+	bic	r2, r2, #CNTHCTL_PL1PCEN
+	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
+
+#ifdef CONFIG_KVM_ARM_TIMER
+	ldr	r4, [vcpu, #VCPU_KVM]
+	ldr	r2, [r4, #KVM_TIMER_ENABLED]
+	cmp	r2, #0
+	beq	1f
+
+	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
+	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
+	mcrr	p15, 4, r2, r3, c14	@ CNTVOFF
+
+	ldr	r4, =VCPU_TIMER_CNTV_CVAL
+	add	r5, vcpu, r4
+	ldrd	r2, r3, [r5]
+	mcrr	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	isb
+
+	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
+	and	r2, r2, #3
+	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+1:
+#endif
+.endm
+
+.equ vmentry,	0
+.equ vmexit,	1
+
+/* Configures the HSTR (Hyp System Trap Register) on entry/return
+ * (hardware reset value is 0) */
+.macro set_hstr operation
+	mrc	p15, 4, r2, c1, c1, 3
+	ldr	r3, =HSTR_T(15)
+	.if \operation == vmentry
+	orr	r2, r2, r3		@ Trap CR{15}
+	.else
+	bic	r2, r2, r3		@ Don't trap any CRx accesses
+	.endif
+	mcr	p15, 4, r2, c1, c1, 3
+.endm
+
+/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
+ * (hardware reset value is 0). Keep previous value in r2. */
+.macro set_hcptr operation, mask
+	mrc	p15, 4, r2, c1, c1, 2
+	ldr	r3, =\mask
+	.if \operation == vmentry
+	orr	r3, r2, r3		@ Trap coproc-accesses defined in mask
+	.else
+	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
+	.endif
+	mcr	p15, 4, r3, c1, c1, 2
+.endm
+
+/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
+ * (hardware reset value is 0) */
+.macro set_hdcr operation
+	mrc	p15, 4, r2, c1, c1, 1
+	ldr	r3, =(HDCR_TPM|HDCR_TPMCR)
+	.if \operation == vmentry
+	orr	r2, r2, r3		@ Trap some perfmon accesses
+	.else
+	bic	r2, r2, r3		@ Don't trap any perfmon accesses
+	.endif
+	mcr	p15, 4, r2, c1, c1, 1
+.endm
+
+/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
+.macro configure_hyp_role operation
+	mrc	p15, 4, r2, c1, c1, 0	@ HCR
+	bic	r2, r2, #HCR_VIRT_EXCP_MASK
+	ldr	r3, =HCR_GUEST_MASK
+	.if \operation == vmentry
+	orr	r2, r2, r3
+	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
+	orr	r2, r2, r3
+	.else
+	bic	r2, r2, r3
+	.endif
+	mcr	p15, 4, r2, c1, c1, 0
+.endm
+
+.macro load_vcpu
+	mrc	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
+.endm

arch/arm/kvm/mmio.c

@@ -0,0 +1,146 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmio.h>
+#include <asm/kvm_emulate.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+/**
+ * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
+ * @vcpu: The VCPU pointer
+ * @run:  The VCPU run struct containing the mmio data
+ *
+ * This should only be called after returning from userspace for MMIO load
+ * emulation.
+ */
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	unsigned long *dest;
+	unsigned int len;
+	int mask;
+
+	if (!run->mmio.is_write) {
+		dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
+		*dest = 0;
+
+		len = run->mmio.len;
+		if (len > sizeof(unsigned long))
+			return -EINVAL;
+
+		memcpy(dest, run->mmio.data, len);
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+				*((u64 *)run->mmio.data));
+
+		if (vcpu->arch.mmio_decode.sign_extend &&
+		    len < sizeof(unsigned long)) {
+			mask = 1U << ((len * 8) - 1);
+			*dest = (*dest ^ mask) - mask;
+		}
+	}
+
+	return 0;
+}
+
+static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+		      struct kvm_exit_mmio *mmio)
+{
+	unsigned long rt, len;
+	bool is_write, sign_extend;
+
+	if (kvm_vcpu_dabt_isextabt(vcpu)) {
+		/* cache operation on I/O addr, tell guest unsupported */
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		return 1;
+	}
+
+	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		/* page table accesses IO mem: tell guest to fix its TTBR */
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		return 1;
+	}
+
+	len = kvm_vcpu_dabt_get_as(vcpu);
+	if (unlikely(len < 0))
+		return len;
+
+	is_write = kvm_vcpu_dabt_iswrite(vcpu);
+	sign_extend = kvm_vcpu_dabt_issext(vcpu);
+	rt = kvm_vcpu_dabt_get_rd(vcpu);
+
+	if (kvm_vcpu_reg_is_pc(vcpu, rt)) {
+		/* IO memory trying to read/write pc */
+		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		return 1;
+	}
+
+	mmio->is_write = is_write;
+	mmio->phys_addr = fault_ipa;
+	mmio->len = len;
+	vcpu->arch.mmio_decode.sign_extend = sign_extend;
+	vcpu->arch.mmio_decode.rt = rt;
+
+	/*
+	 * The MMIO instruction is emulated and should not be re-executed
+	 * in the guest.
+	 */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 0;
+}
+
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa)
+{
+	struct kvm_exit_mmio mmio;
+	unsigned long rt;
+	int ret;
+
+	/*
+	 * Prepare MMIO operation. First stash it in a private
+	 * structure that we can use for in-kernel emulation. If the
+	 * kernel can't handle it, copy it into run->mmio and let user
+	 * space do its magic.
+	 */
+
+	if (kvm_vcpu_dabt_isvalid(vcpu)) {
+		ret = decode_hsr(vcpu, fault_ipa, &mmio);
+		if (ret)
+			return ret;
+	} else {
+		kvm_err("load/store instruction decoding not implemented\n");
+		return -ENOSYS;
+	}
+
+	rt = vcpu->arch.mmio_decode.rt;
+	trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
+					 KVM_TRACE_MMIO_READ_UNSATISFIED,
+			mmio.len, fault_ipa,
+			(mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0);
+
+	if (mmio.is_write)
+		memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len);
+
+	if (vgic_handle_mmio(vcpu, run, &mmio))
+		return 1;
+
+	kvm_prepare_mmio(run, &mmio);
+	return 0;
+}

arch/arm/kvm/mmu.c

@@ -0,0 +1,844 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/mman.h>
+#include <linux/kvm_host.h>
+#include <linux/io.h>
+#include <trace/events/kvm.h>
+#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_mmio.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+
+#include "trace.h"
+
+extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+
+static pgd_t *boot_hyp_pgd;
+static pgd_t *hyp_pgd;
+static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
+
+static void *init_bounce_page;
+static unsigned long hyp_idmap_start;
+static unsigned long hyp_idmap_end;
+static phys_addr_t hyp_idmap_vector;
+
+static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	/*
+	 * This function also gets called when dealing with HYP page
+	 * tables. As HYP doesn't have an associated struct kvm (and
+	 * the HYP page tables are fairly static), we don't do
+	 * anything there.
+	 */
+	if (kvm)
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+}
+
+static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
+				  int min, int max)
+{
+	void *page;
+
+	BUG_ON(max > KVM_NR_MEM_OBJS);
+	if (cache->nobjs >= min)
+		return 0;
+	while (cache->nobjs < max) {
+		page = (void *)__get_free_page(PGALLOC_GFP);
+		if (!page)
+			return -ENOMEM;
+		cache->objects[cache->nobjs++] = page;
+	}
+	return 0;
+}
+
+static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
+{
+	while (mc->nobjs)
+		free_page((unsigned long)mc->objects[--mc->nobjs]);
+}
+
+static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
+{
+	void *p;
+
+	BUG_ON(!mc || !mc->nobjs);
+	p = mc->objects[--mc->nobjs];
+	return p;
+}
+
+static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+{
+	pmd_t *pmd_table = pmd_offset(pud, 0);
+	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pmd_free(NULL, pmd_table);
+	put_page(virt_to_page(pud));
+}
+
+static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+{
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pte_free_kernel(NULL, pte_table);
+	put_page(virt_to_page(pmd));
+}
+
+static bool pmd_empty(pmd_t *pmd)
+{
+	struct page *pmd_page = virt_to_page(pmd);
+	return page_count(pmd_page) == 1;
+}
+
+static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
+{
+	if (pte_present(*pte)) {
+		kvm_set_pte(pte, __pte(0));
+		put_page(virt_to_page(pte));
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	}
+}
+
+static bool pte_empty(pte_t *pte)
+{
+	struct page *pte_page = virt_to_page(pte);
+	return page_count(pte_page) == 1;
+}
+
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+			unsigned long long start, u64 size)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long long addr = start, end = start + size;
+	u64 range;
+
+	while (addr < end) {
+		pgd = pgdp + pgd_index(addr);
+		pud = pud_offset(pgd, addr);
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
+			continue;
+		}
+
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
+			continue;
+		}
+
+		pte = pte_offset_kernel(pmd, addr);
+		clear_pte_entry(kvm, pte, addr);
+		range = PAGE_SIZE;
+
+		/* If we emptied the pte, walk back up the ladder */
+		if (pte_empty(pte)) {
+			clear_pmd_entry(kvm, pmd, addr);
+			range = PMD_SIZE;
+			if (pmd_empty(pmd)) {
+				clear_pud_entry(kvm, pud, addr);
+				range = PUD_SIZE;
+			}
+		}
+
+		addr += range;
+	}
+}
+
+/**
+ * free_boot_hyp_pgd - free HYP boot page tables
+ *
+ * Free the HYP boot page tables. The bounce page is also freed.
+ */
+void free_boot_hyp_pgd(void)
+{
+	mutex_lock(&kvm_hyp_pgd_mutex);
+
+	if (boot_hyp_pgd) {
+		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		kfree(boot_hyp_pgd);
+		boot_hyp_pgd = NULL;
+	}
+
+	if (hyp_pgd)
+		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+
+	kfree(init_bounce_page);
+	init_bounce_page = NULL;
+
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+}
+
+/**
+ * free_hyp_pgds - free Hyp-mode page tables
+ *
+ * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
+ * therefore contains either mappings in the kernel memory area (above
+ * PAGE_OFFSET), or device mappings in the vmalloc range (from
+ * VMALLOC_START to VMALLOC_END).
+ *
+ * boot_hyp_pgd should only map two pages for the init code.
+ */
+void free_hyp_pgds(void)
+{
+	unsigned long addr;
+
+	free_boot_hyp_pgd();
+
+	mutex_lock(&kvm_hyp_pgd_mutex);
+
+	if (hyp_pgd) {
+		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+
+		kfree(hyp_pgd);
+		hyp_pgd = NULL;
+	}
+
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+}
+
+static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
+				    unsigned long end, unsigned long pfn,
+				    pgprot_t prot)
+{
+	pte_t *pte;
+	unsigned long addr;
+
+	addr = start;
+	do {
+		pte = pte_offset_kernel(pmd, addr);
+		kvm_set_pte(pte, pfn_pte(pfn, prot));
+		get_page(virt_to_page(pte));
+		kvm_flush_dcache_to_poc(pte, sizeof(*pte));
+		pfn++;
+	} while (addr += PAGE_SIZE, addr != end);
+}
+
+static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
+				   unsigned long end, unsigned long pfn,
+				   pgprot_t prot)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long addr, next;
+
+	addr = start;
+	do {
+		pmd = pmd_offset(pud, addr);
+
+		BUG_ON(pmd_sect(*pmd));
+
+		if (pmd_none(*pmd)) {
+			pte = pte_alloc_one_kernel(NULL, addr);
+			if (!pte) {
+				kvm_err("Cannot allocate Hyp pte\n");
+				return -ENOMEM;
+			}
+			pmd_populate_kernel(NULL, pmd, pte);
+			get_page(virt_to_page(pmd));
+			kvm_flush_dcache_to_poc(pmd, sizeof(*pmd));
+		}
+
+		next = pmd_addr_end(addr, end);
+
+		create_hyp_pte_mappings(pmd, addr, next, pfn, prot);
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
+static int __create_hyp_mappings(pgd_t *pgdp,
+				 unsigned long start, unsigned long end,
+				 unsigned long pfn, pgprot_t prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr, next;
+	int err = 0;
+
+	mutex_lock(&kvm_hyp_pgd_mutex);
+	addr = start & PAGE_MASK;
+	end = PAGE_ALIGN(end);
+	do {
+		pgd = pgdp + pgd_index(addr);
+		pud = pud_offset(pgd, addr);
+
+		if (pud_none_or_clear_bad(pud)) {
+			pmd = pmd_alloc_one(NULL, addr);
+			if (!pmd) {
+				kvm_err("Cannot allocate Hyp pmd\n");
+				err = -ENOMEM;
+				goto out;
+			}
+			pud_populate(NULL, pud, pmd);
+			get_page(virt_to_page(pud));
+			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+		}
+
+		next = pgd_addr_end(addr, end);
+		err = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		if (err)
+			goto out;
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+out:
+	mutex_unlock(&kvm_hyp_pgd_mutex);
+	return err;
+}
+
+/**
+ * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
+ * @from:	The virtual kernel start address of the range
+ * @to:		The virtual kernel end address of the range (exclusive)
+ *
+ * The same virtual address as the kernel virtual address is also used
+ * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
+ * physical pages.
+ */
+int create_hyp_mappings(void *from, void *to)
+{
+	unsigned long phys_addr = virt_to_phys(from);
+	unsigned long start = KERN_TO_HYP((unsigned long)from);
+	unsigned long end = KERN_TO_HYP((unsigned long)to);
+
+	/* Check for a valid kernel memory mapping */
+	if (!virt_addr_valid(from) || !virt_addr_valid(to - 1))
+		return -EINVAL;
+
+	return __create_hyp_mappings(hyp_pgd, start, end,
+				     __phys_to_pfn(phys_addr), PAGE_HYP);
+}
+
+/**
+ * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode
+ * @from:	The kernel start VA of the range
+ * @to:		The kernel end VA of the range (exclusive)
+ * @phys_addr:	The physical start address which gets mapped
+ *
+ * The resulting HYP VA is the same as the kernel VA, modulo
+ * HYP_PAGE_OFFSET.
+ */
+int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
+{
+	unsigned long start = KERN_TO_HYP((unsigned long)from);
+	unsigned long end = KERN_TO_HYP((unsigned long)to);
+
+	/* Check for a valid kernel IO mapping */
+	if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
+		return -EINVAL;
+
+	return __create_hyp_mappings(hyp_pgd, start, end,
+				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
+}
+
+/**
+ * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
+ * @kvm:	The KVM struct pointer for the VM.
+ *
+ * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can
+ * support either full 40-bit input addresses or limited to 32-bit input
+ * addresses). Clears the allocated pages.
+ *
+ * Note we don't need locking here as this is only called when the VM is
+ * created, which can only be done once.
+ */
+int kvm_alloc_stage2_pgd(struct kvm *kvm)
+{
+	pgd_t *pgd;
+
+	if (kvm->arch.pgd != NULL) {
+		kvm_err("kvm_arch already initialized?\n");
+		return -EINVAL;
+	}
+
+	pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, S2_PGD_ORDER);
+	if (!pgd)
+		return -ENOMEM;
+
+	/* stage-2 pgd must be aligned to its size */
+	VM_BUG_ON((unsigned long)pgd & (S2_PGD_SIZE - 1));
+
+	memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t));
+	kvm_clean_pgd(pgd);
+	kvm->arch.pgd = pgd;
+
+	return 0;
+}
+
+/**
+ * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * @kvm:   The VM pointer
+ * @start: The intermediate physical base address of the range to unmap
+ * @size:  The size of the area to unmap
+ *
+ * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
+ * be called while holding mmu_lock (unless for freeing the stage2 pgd before
+ * destroying the VM), otherwise another faulting VCPU may come in and mess
+ * with things behind our backs.
+ */
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+{
+	unmap_range(kvm, kvm->arch.pgd, start, size);
+}
+
+/**
+ * kvm_free_stage2_pgd - free all stage-2 tables
+ * @kvm:	The KVM struct pointer for the VM.
+ *
+ * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
+ * underlying level-2 and level-3 tables before freeing the actual level-1 table
+ * and setting the struct pointer to NULL.
+ *
+ * Note we don't need locking here as this is only called when the VM is
+ * destroyed, which can only be done once.
+ */
+void kvm_free_stage2_pgd(struct kvm *kvm)
+{
+	if (kvm->arch.pgd == NULL)
+		return;
+
+	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+	kvm->arch.pgd = NULL;
+}
+
+
+static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			  phys_addr_t addr, const pte_t *new_pte, bool iomap)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte, old_pte;
+
+	/* Create 2nd stage page table mapping - Level 1 */
+	pgd = kvm->arch.pgd + pgd_index(addr);
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud)) {
+		if (!cache)
+			return 0; /* ignore calls from kvm_set_spte_hva */
+		pmd = mmu_memory_cache_alloc(cache);
+		pud_populate(NULL, pud, pmd);
+		get_page(virt_to_page(pud));
+	}
+
+	pmd = pmd_offset(pud, addr);
+
+	/* Create 2nd stage page table mapping - Level 2 */
+	if (pmd_none(*pmd)) {
+		if (!cache)
+			return 0; /* ignore calls from kvm_set_spte_hva */
+		pte = mmu_memory_cache_alloc(cache);
+		kvm_clean_pte(pte);
+		pmd_populate_kernel(NULL, pmd, pte);
+		get_page(virt_to_page(pmd));
+	}
+
+	pte = pte_offset_kernel(pmd, addr);
+
+	if (iomap && pte_present(*pte))
+		return -EFAULT;
+
+	/* Create 2nd stage page table mapping - Level 3 */
+	old_pte = *pte;
+	kvm_set_pte(pte, *new_pte);
+	if (pte_present(old_pte))
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
+	else
+		get_page(virt_to_page(pte));
+
+	return 0;
+}
+
+/**
+ * kvm_phys_addr_ioremap - map a device range to guest IPA
+ *
+ * @kvm:	The KVM pointer
+ * @guest_ipa:	The IPA at which to insert the mapping
+ * @pa:		The physical address of the device
+ * @size:	The size of the mapping
+ */
+int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
+			  phys_addr_t pa, unsigned long size)
+{
+	phys_addr_t addr, end;
+	int ret = 0;
+	unsigned long pfn;
+	struct kvm_mmu_memory_cache cache = { 0, };
+
+	end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK;
+	pfn = __phys_to_pfn(pa);
+
+	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
+		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
+		kvm_set_s2pte_writable(&pte);
+
+		ret = mmu_topup_memory_cache(&cache, 2, 2);
+		if (ret)
+			goto out;
+		spin_lock(&kvm->mmu_lock);
+		ret = stage2_set_pte(kvm, &cache, addr, &pte, true);
+		spin_unlock(&kvm->mmu_lock);
+		if (ret)
+			goto out;
+
+		pfn++;
+	}
+
+out:
+	mmu_free_memory_cache(&cache);
+	return ret;
+}
+
+static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+			  gfn_t gfn, struct kvm_memory_slot *memslot,
+			  unsigned long fault_status)
+{
+	pte_t new_pte;
+	pfn_t pfn;
+	int ret;
+	bool write_fault, writable;
+	unsigned long mmu_seq;
+	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+
+	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	if (fault_status == FSC_PERM && !write_fault) {
+		kvm_err("Unexpected L2 read permission error\n");
+		return -EFAULT;
+	}
+
+	/* We need minimum second+third level pages */
+	ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
+	if (ret)
+		return ret;
+
+	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	/*
+	 * Ensure the read of mmu_notifier_seq happens before we call
+	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
+	 * the page we just got a reference to gets unmapped before we have a
+	 * chance to grab the mmu_lock, which ensure that if the page gets
+	 * unmapped afterwards, the call to kvm_unmap_hva will take it away
+	 * from us again properly. This smp_rmb() interacts with the smp_wmb()
+	 * in kvm_mmu_notifier_invalidate_<page|range_end>.
+	 */
+	smp_rmb();
+
+	pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write_fault, &writable);
+	if (is_error_pfn(pfn))
+		return -EFAULT;
+
+	new_pte = pfn_pte(pfn, PAGE_S2);
+	coherent_icache_guest_page(vcpu->kvm, gfn);
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+		goto out_unlock;
+	if (writable) {
+		kvm_set_s2pte_writable(&new_pte);
+		kvm_set_pfn_dirty(pfn);
+	}
+	stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false);
+
+out_unlock:
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	kvm_release_pfn_clean(pfn);
+	return 0;
+}
+
+/**
+ * kvm_handle_guest_abort - handles all 2nd stage aborts
+ * @vcpu:	the VCPU pointer
+ * @run:	the kvm_run structure
+ *
+ * Any abort that gets to the host is almost guaranteed to be caused by a
+ * missing second stage translation table entry, which can mean that either the
+ * guest simply needs more memory and we must allocate an appropriate page or it
+ * can mean that the guest tried to access I/O memory, which is emulated by user
+ * space. The distinction is based on the IPA causing the fault and whether this
+ * memory region has been registered as standard RAM by user space.
+ */
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	unsigned long fault_status;
+	phys_addr_t fault_ipa;
+	struct kvm_memory_slot *memslot;
+	bool is_iabt;
+	gfn_t gfn;
+	int ret, idx;
+
+	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
+			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
+
+	/* Check the stage-2 fault is trans. fault or write fault */
+	fault_status = kvm_vcpu_trap_get_fault(vcpu);
+	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
+		kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n",
+			kvm_vcpu_trap_get_class(vcpu), fault_status);
+		return -EFAULT;
+	}
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	gfn = fault_ipa >> PAGE_SHIFT;
+	if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+		if (is_iabt) {
+			/* Prefetch Abort on I/O address */
+			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
+		if (fault_status != FSC_FAULT) {
+			kvm_err("Unsupported fault status on io memory: %#lx\n",
+				fault_status);
+			ret = -EFAULT;
+			goto out_unlock;
+		}
+
+		/*
+		 * The IPA is reported as [MAX:12], so we need to
+		 * complement it with the bottom 12 bits from the
+		 * faulting VA. This is always 12 bits, irrespective
+		 * of the page size.
+		 */
+		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
+		ret = io_mem_abort(vcpu, run, fault_ipa);
+		goto out_unlock;
+	}
+
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+
+	ret = user_mem_abort(vcpu, fault_ipa, gfn, memslot, fault_status);
+	if (ret == 0)
+		ret = 1;
+out_unlock:
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	return ret;
+}
+
+static void handle_hva_to_gpa(struct kvm *kvm,
+			      unsigned long start,
+			      unsigned long end,
+			      void (*handler)(struct kvm *kvm,
+					      gpa_t gpa, void *data),
+			      void *data)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	slots = kvm_memslots(kvm);
+
+	/* we only care about the pages that the guest sees */
+	kvm_for_each_memslot(memslot, slots) {
+		unsigned long hva_start, hva_end;
+		gfn_t gfn, gfn_end;
+
+		hva_start = max(start, memslot->userspace_addr);
+		hva_end = min(end, memslot->userspace_addr +
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+		 */
+		gfn = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+
+		for (; gfn < gfn_end; ++gfn) {
+			gpa_t gpa = gfn << PAGE_SHIFT;
+			handler(kvm, gpa, data);
+		}
+	}
+}
+
+static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	unsigned long end = hva + PAGE_SIZE;
+
+	if (!kvm->arch.pgd)
+		return 0;
+
+	trace_kvm_unmap_hva(hva);
+	handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL);
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm,
+			unsigned long start, unsigned long end)
+{
+	if (!kvm->arch.pgd)
+		return 0;
+
+	trace_kvm_unmap_hva_range(start, end);
+	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+	return 0;
+}
+
+static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	pte_t *pte = (pte_t *)data;
+
+	stage2_set_pte(kvm, NULL, gpa, pte, false);
+}
+
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	unsigned long end = hva + PAGE_SIZE;
+	pte_t stage2_pte;
+
+	if (!kvm->arch.pgd)
+		return;
+
+	trace_kvm_set_spte_hva(hva);
+	stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2);
+	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
+}
+
+void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
+{
+	mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+}
+
+phys_addr_t kvm_mmu_get_httbr(void)
+{
+	return virt_to_phys(hyp_pgd);
+}
+
+phys_addr_t kvm_mmu_get_boot_httbr(void)
+{
+	return virt_to_phys(boot_hyp_pgd);
+}
+
+phys_addr_t kvm_get_idmap_vector(void)
+{
+	return hyp_idmap_vector;
+}
+
+int kvm_mmu_init(void)
+{
+	int err;
+
+	hyp_idmap_start = virt_to_phys(__hyp_idmap_text_start);
+	hyp_idmap_end = virt_to_phys(__hyp_idmap_text_end);
+	hyp_idmap_vector = virt_to_phys(__kvm_hyp_init);
+
+	if ((hyp_idmap_start ^ hyp_idmap_end) & PAGE_MASK) {
+		/*
+		 * Our init code is crossing a page boundary. Allocate
+		 * a bounce page, copy the code over and use that.
+		 */
+		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
+		phys_addr_t phys_base;
+
+		init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!init_bounce_page) {
+			kvm_err("Couldn't allocate HYP init bounce page\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(init_bounce_page, __hyp_idmap_text_start, len);
+		/*
+		 * Warning: the code we just copied to the bounce page
+		 * must be flushed to the point of coherency.
+		 * Otherwise, the data may be sitting in L2, and HYP
+		 * mode won't be able to observe it as it runs with
+		 * caches off at that point.
+		 */
+		kvm_flush_dcache_to_poc(init_bounce_page, len);
+
+		phys_base = virt_to_phys(init_bounce_page);
+		hyp_idmap_vector += phys_base - hyp_idmap_start;
+		hyp_idmap_start = phys_base;
+		hyp_idmap_end = phys_base + len;
+
+		kvm_info("Using HYP init bounce page @%lx\n",
+			 (unsigned long)phys_base);
+	}
+
+	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	if (!hyp_pgd || !boot_hyp_pgd) {
+		kvm_err("Hyp mode PGD not allocated\n");
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Create the idmap in the boot page tables */
+	err = 	__create_hyp_mappings(boot_hyp_pgd,
+				      hyp_idmap_start, hyp_idmap_end,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP);
+
+	if (err) {
+		kvm_err("Failed to idmap %lx-%lx\n",
+			hyp_idmap_start, hyp_idmap_end);
+		goto out;
+	}
+
+	/* Map the very same page at the trampoline VA */
+	err = 	__create_hyp_mappings(boot_hyp_pgd,
+				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP);
+	if (err) {
+		kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n",
+			TRAMPOLINE_VA);
+		goto out;
+	}
+
+	/* Map the same page again into the runtime page tables */
+	err = 	__create_hyp_mappings(hyp_pgd,
+				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP);
+	if (err) {
+		kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n",
+			TRAMPOLINE_VA);
+		goto out;
+	}
+
+	return 0;
+out:
+	free_hyp_pgds();
+	return err;
+}

arch/arm/kvm/perf.c

@@ -0,0 +1,68 @@
+/*
+ * Based on the x86 implementation.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+static int kvm_is_in_guest(void)
+{
+        return kvm_arm_get_running_vcpu() != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return !vcpu_mode_priv(vcpu);
+
+	return 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return *vcpu_pc(vcpu);
+
+	return 0;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+	.is_in_guest	= kvm_is_in_guest,
+	.is_user_mode	= kvm_is_user_mode,
+	.get_guest_ip	= kvm_get_guest_ip,
+};
+
+int kvm_perf_init(void)
+{
+	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
+}
+
+int kvm_perf_teardown(void)
+{
+	return perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+}

arch/arm/kvm/psci.c

@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2012 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/wait.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_psci.h>
+
+/*
+ * This is an implementation of the Power State Coordination Interface
+ * as described in ARM document number ARM DEN 0022A.
+ */
+
+static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pause = true;
+}
+
+static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
+{
+	struct kvm *kvm = source_vcpu->kvm;
+	struct kvm_vcpu *vcpu;
+	wait_queue_head_t *wq;
+	unsigned long cpu_id;
+	phys_addr_t target_pc;
+
+	cpu_id = *vcpu_reg(source_vcpu, 1);
+	if (vcpu_mode_is_32bit(source_vcpu))
+		cpu_id &= ~((u32) 0);
+
+	if (cpu_id >= atomic_read(&kvm->online_vcpus))
+		return KVM_PSCI_RET_INVAL;
+
+	target_pc = *vcpu_reg(source_vcpu, 2);
+
+	vcpu = kvm_get_vcpu(kvm, cpu_id);
+
+	wq = kvm_arch_vcpu_wq(vcpu);
+	if (!waitqueue_active(wq))
+		return KVM_PSCI_RET_INVAL;
+
+	kvm_reset_vcpu(vcpu);
+
+	/* Gracefully handle Thumb2 entry point */
+	if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
+		target_pc &= ~((phys_addr_t) 1);
+		vcpu_set_thumb(vcpu);
+	}
+
+	*vcpu_pc(vcpu) = target_pc;
+	vcpu->arch.pause = false;
+	smp_mb();		/* Make sure the above is visible */
+
+	wake_up_interruptible(wq);
+
+	return KVM_PSCI_RET_SUCCESS;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC or SMC instructions.
+ * The calling convention is similar to SMC calls to the secure world where
+ * the function number is placed in r0 and this function returns true if the
+ * function number specified in r0 is withing the PSCI range, and false
+ * otherwise.
+ */
+bool kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long val;
+
+	switch (psci_fn) {
+	case KVM_PSCI_FN_CPU_OFF:
+		kvm_psci_vcpu_off(vcpu);
+		val = KVM_PSCI_RET_SUCCESS;
+		break;
+	case KVM_PSCI_FN_CPU_ON:
+		val = kvm_psci_vcpu_on(vcpu);
+		break;
+	case KVM_PSCI_FN_CPU_SUSPEND:
+	case KVM_PSCI_FN_MIGRATE:
+		val = KVM_PSCI_RET_NI;
+		break;
+
+	default:
+		return false;
+	}
+
+	*vcpu_reg(vcpu, 0) = val;
+	return true;
+}

arch/arm/kvm/reset.c

@@ -0,0 +1,74 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+
+#include <asm/unified.h>
+#include <asm/ptrace.h>
+#include <asm/cputype.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_coproc.h>
+
+/******************************************************************************
+ * Cortex-A15 Reset Values
+ */
+
+static const int a15_max_cpu_idx = 3;
+
+static struct kvm_regs a15_regs_reset = {
+	.usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT,
+};
+
+
+/*******************************************************************************
+ * Exported reset function
+ */
+
+/**
+ * kvm_reset_vcpu - sets core registers and cp15 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 architectually defined reset values.
+ */
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_regs *cpu_reset;
+
+	switch (vcpu->arch.target) {
+	case KVM_ARM_TARGET_CORTEX_A15:
+		if (vcpu->vcpu_id > a15_max_cpu_idx)
+			return -EINVAL;
+		cpu_reset = &a15_regs_reset;
+		vcpu->arch.midr = read_cpuid_id();
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	/* Reset core registers */
+	memcpy(&vcpu->arch.regs, cpu_reset, sizeof(vcpu->arch.regs));
+
+	/* Reset CP15 registers */
+	kvm_reset_coprocs(vcpu);
+
+	return 0;
+}

arch/arm/kvm/trace.h

@@ -0,0 +1,235 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+/*
+ * Tracepoints for entry/exit to guest
+ */
+TRACE_EVENT(kvm_entry,
+	TP_PROTO(unsigned long vcpu_pc),
+	TP_ARGS(vcpu_pc),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+	),
+
+	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned long vcpu_pc),
+	TP_ARGS(vcpu_pc),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+	),
+
+	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_guest_fault,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
+		 unsigned long hxfar,
+		 unsigned long long ipa),
+	TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	hsr		)
+		__field(	unsigned long,	hxfar		)
+		__field(   unsigned long long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->hsr			= hsr;
+		__entry->hxfar			= hxfar;
+		__entry->ipa			= ipa;
+	),
+
+	TP_printk("guest fault at PC %#08lx (hxfar %#08lx, "
+		  "ipa %#16llx, hsr %#08lx",
+		  __entry->vcpu_pc, __entry->hxfar,
+		  __entry->ipa, __entry->hsr)
+);
+
+TRACE_EVENT(kvm_irq_line,
+	TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
+	TP_ARGS(type, vcpu_idx, irq_num, level),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	type		)
+		__field(	int,		vcpu_idx	)
+		__field(	int,		irq_num		)
+		__field(	int,		level		)
+	),
+
+	TP_fast_assign(
+		__entry->type		= type;
+		__entry->vcpu_idx	= vcpu_idx;
+		__entry->irq_num	= irq_num;
+		__entry->level		= level;
+	),
+
+	TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
+		  (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
+		  (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
+		  (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
+		  __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
+);
+
+TRACE_EVENT(kvm_mmio_emulate,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
+		 unsigned long cpsr),
+	TP_ARGS(vcpu_pc, instr, cpsr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	instr		)
+		__field(	unsigned long,	cpsr		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->instr			= instr;
+		__entry->cpsr			= cpsr;
+	),
+
+	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
+);
+
+/* Architecturally implementation defined CP15 register access */
+TRACE_EVENT(kvm_emulate_cp15_imp,
+	TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn,
+		 unsigned long CRm, unsigned long Op2, bool is_write),
+	TP_ARGS(Op1, Rt1, CRn, CRm, Op2, is_write),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	Op1		)
+		__field(	unsigned int,	Rt1		)
+		__field(	unsigned int,	CRn		)
+		__field(	unsigned int,	CRm		)
+		__field(	unsigned int,	Op2		)
+		__field(	bool,		is_write	)
+	),
+
+	TP_fast_assign(
+		__entry->is_write		= is_write;
+		__entry->Op1			= Op1;
+		__entry->Rt1			= Rt1;
+		__entry->CRn			= CRn;
+		__entry->CRm			= CRm;
+		__entry->Op2			= Op2;
+	),
+
+	TP_printk("Implementation defined CP15: %s\tp15, %u, r%u, c%u, c%u, %u",
+			(__entry->is_write) ? "mcr" : "mrc",
+			__entry->Op1, __entry->Rt1, __entry->CRn,
+			__entry->CRm, __entry->Op2)
+);
+
+TRACE_EVENT(kvm_wfi,
+	TP_PROTO(unsigned long vcpu_pc),
+	TP_ARGS(vcpu_pc),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+	),
+
+	TP_printk("guest executed wfi at: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_unmap_hva_range,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_set_spte_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_hvc,
+	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_KVM_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH arch/arm/kvm
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>