Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.1

  The most interesting bit here is irqfd/ioeventfd support for ARM and
  ARM64.

  Summary:

  ARM/ARM64:
     fixes for live migration, irqfd and ioeventfd support (enabling
     vhost, too), page aging

  s390:
     interrupt handling rework, allowing to inject all local interrupts
     via new ioctl and to get/set the full local irq state for migration
     and introspection.  New ioctls to access memory by virtual address,
     and to get/set the guest storage keys.  SIMD support.

  MIPS:
     FPU and MIPS SIMD Architecture (MSA) support.  Includes some
     patches from Ralf Baechle's MIPS tree.

  x86:
     bugfixes (notably for pvclock, the others are small) and cleanups.
     Another small latency improvement for the TSC deadline timer"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  KVM: use slowpath for cross page cached accesses
  kvm: mmu: lazy collapse small sptes into large sptes
  KVM: x86: Clear CR2 on VCPU reset
  KVM: x86: DR0-DR3 are not clear on reset
  KVM: x86: BSP in MSR_IA32_APICBASE is writable
  KVM: x86: simplify kvm_apic_map
  KVM: x86: avoid logical_map when it is invalid
  KVM: x86: fix mixed APIC mode broadcast
  KVM: x86: use MDA for interrupt matching
  kvm/ppc/mpic: drop unused IRQ_testbit
  KVM: nVMX: remove unnecessary double caching of MAXPHYADDR
  KVM: nVMX: checks for address bits beyond MAXPHYADDR on VM-entry
  KVM: x86: cache maxphyaddr CPUID leaf in struct kvm_vcpu
  KVM: vmx: pass error code with internal error #2
  x86: vdso: fix pvclock races with task migration
  KVM: remove kvm_read_hva and kvm_read_hva_atomic
  KVM: x86: optimize delivery of TSC deadline timer interrupt
  KVM: x86: extract blocking logic from __vcpu_run
  kvm: x86: fix x86 eflags fixed bit
  KVM: s390: migrate vcpu interrupt state
  ...

13 files changed, 258 insertions, 146 deletions

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 816db0bf2dd8..d995821f1698 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -185,6 +185,7 @@
 #define HSR_COND	(0xfU << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
+#define FSC_ACCESS	(0x08)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 41008cd7c53f..d71607c16601 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -27,6 +27,8 @@
 #include <asm/fpstate.h>
 #include <kvm/arm_arch_timer.h>
 
+#define __KVM_HAVE_ARCH_INTC_INITIALIZED
+
 #if defined(CONFIG_KVM_ARM_MAX_VCPUS)
 #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
 #else
@@ -165,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 
 /* We do not have shadow page tables, hence the empty hooks */
-static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
-{
-	return 0;
-}
-
-static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	return 0;
-}
-
 static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 							 unsigned long address)
 {
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
index 3f83db2f6cf0..d8e90c8cb5fa 100644
--- a/arch/arm/include/asm/kvm_mmio.h
+++ b/arch/arm/include/asm/kvm_mmio.h
@@ -28,28 +28,6 @@ struct kvm_decode {
 	bool sign_extend;
 };
 
-/*
- * The in-kernel MMIO emulation code wants to use a copy of run->mmio,
- * which is an anonymous type. Use our own type instead.
- */
-struct kvm_exit_mmio {
-	phys_addr_t	phys_addr;
-	u8		data[8];
-	u32		len;
-	bool		is_write;
-	void		*private;
-};
-
-static inline void kvm_prepare_mmio(struct kvm_run *run,
-				    struct kvm_exit_mmio *mmio)
-{
-	run->mmio.phys_addr	= mmio->phys_addr;
-	run->mmio.len		= mmio->len;
-	run->mmio.is_write	= mmio->is_write;
-	memcpy(run->mmio.data, mmio->data, mmio->len);
-	run->exit_reason	= KVM_EXIT_MMIO;
-}
-
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa);
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 0db25bc32864..2499867dd0d8 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -198,6 +198,9 @@ struct kvm_arch_memory_slot {
 /* Highest supported SPI, from VGIC_NR_IRQS */
 #define KVM_ARM_IRQ_GIC_MAX		127
 
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
 /* PSCI interface */
 #define KVM_PSCI_FN_BASE		0x95c1ba5e
 #define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 2d2d6087b9b1..488eaac56028 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -190,7 +190,6 @@ int main(void)
   DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
   DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
   DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
-#ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
   DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
@@ -200,14 +199,11 @@ int main(void)
   DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
   DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-#ifdef CONFIG_KVM_ARM_TIMER
   DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
   DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
   DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
   DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-#endif
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
-#endif
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
 #endif
   return 0; 
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 338ace78ed18..f1f79d104309 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -18,6 +18,7 @@ if VIRTUALIZATION
 
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
+	depends on MMU && OF
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -26,10 +27,12 @@ config KVM
 	select KVM_ARM_HOST
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
-	depends on ARM_VIRT_EXT && ARM_LPAE
+	select MMU_NOTIFIER
+	select HAVE_KVM_EVENTFD
+	select HAVE_KVM_IRQFD
+	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
 	---help---
-	  Support hosting virtualized guest machines. You will also
-	  need to select one or more of the processor modules below.
+	  Support hosting virtualized guest machines.
 
 	  This module provides access to the hardware capabilities through
 	  a character device node named /dev/kvm.
@@ -37,10 +40,7 @@ config 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
+	bool
 	---help---
 	  Provides host support for ARM processors.
 
@@ -55,20 +55,4 @@ config KVM_ARM_MAX_VCPUS
 	  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
-
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 443b8bea43e9..139e46c08b6e 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt)
 	plus_virt_def := -DREQUIRES_VIRT=1
 endif
 
-ccflags-y += -Ivirt/kvm -Iarch/arm/kvm
+ccflags-y += -Iarch/arm/kvm
 CFLAGS_arm.o := -I. $(plus_virt_def)
 CFLAGS_mmu.o := -I.
 
@@ -15,12 +15,12 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 
 KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.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 coproc_a7.o mmio.o psci.o perf.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
-obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o
-obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
+obj-y += $(KVM)/arm/vgic.o
+obj-y += $(KVM)/arm/vgic-v2.o
+obj-y += $(KVM)/arm/vgic-v2-emul.o
+obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 5560f74f9eee..6f536451ab78 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -61,8 +61,6 @@ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
 static u8 kvm_next_vmid;
 static DEFINE_SPINLOCK(kvm_vmid_lock);
 
-static bool vgic_present;
-
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
@@ -173,8 +171,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-		r = vgic_present;
-		break;
+	case KVM_CAP_IRQFD:
+	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
@@ -183,6 +181,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_PSCI:
 	case KVM_CAP_ARM_PSCI_0_2:
 	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_MP_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -268,7 +267,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return 0;
+	return kvm_timer_should_fire(vcpu);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -313,13 +312,29 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	if (vcpu->arch.pause)
+		mp_state->mp_state = KVM_MP_STATE_STOPPED;
+	else
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+
+	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL;
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_RUNNABLE:
+		vcpu->arch.pause = false;
+		break;
+	case KVM_MP_STATE_STOPPED:
+		vcpu->arch.pause = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 /**
@@ -452,6 +467,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+bool kvm_arch_intc_initialized(struct kvm *kvm)
+{
+	return vgic_initialized(kvm);
+}
+
 static void vcpu_pause(struct kvm_vcpu *vcpu)
 {
 	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
@@ -831,8 +851,6 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 
 	switch (dev_id) {
 	case KVM_ARM_DEVICE_VGIC_V2:
-		if (!vgic_present)
-			return -ENXIO;
 		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
 	default:
 		return -ENODEV;
@@ -847,10 +865,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
-		if (vgic_present)
-			return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
-		else
-			return -ENXIO;
+		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
 		struct kvm_arm_device_addr dev_addr;
@@ -1035,10 +1050,6 @@ static int init_hyp_mode(void)
 	if (err)
 		goto out_free_context;
 
-#ifdef CONFIG_KVM_ARM_VGIC
-		vgic_present = true;
-#endif
-
 	/*
 	 * Init HYP architected timer support
 	 */
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 384bab67c462..d503fbb787d3 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -109,22 +109,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return -EINVAL;
 }
 
-#ifndef CONFIG_KVM_ARM_TIMER
-
-#define NUM_TIMER_REGS 0
-
-static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
-{
-	return 0;
-}
-
-static bool is_timer_reg(u64 index)
-{
-	return false;
-}
-
-#else
-
 #define NUM_TIMER_REGS 3
 
 static bool is_timer_reg(u64 index)
@@ -152,8 +136,6 @@ static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	return 0;
 }
 
-#endif
-
 static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	void __user *uaddr = (void __user *)(long)reg->addr;
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 14d488388480..35e4a3a0c476 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -402,7 +402,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
  * 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]
@@ -460,7 +459,6 @@ ARM_BE8(rev	r6, r6	)
 	subs	r4, r4, #1
 	bne	1b
 2:
-#endif
 .endm
 
 /*
@@ -469,7 +467,6 @@ ARM_BE8(rev	r6, r6	)
  * 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]
@@ -501,7 +498,6 @@ ARM_BE8(rev	r6, r6  )
 	subs	r4, r4, #1
 	bne	1b
 2:
-#endif
 .endm
 
 #define CNTHCTL_PL1PCTEN	(1 << 0)
@@ -515,7 +511,6 @@ ARM_BE8(rev	r6, r6  )
  * 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
@@ -537,7 +532,6 @@ ARM_BE8(rev	r6, r6  )
 	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
 
 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)
@@ -559,7 +553,6 @@ ARM_BE8(rev	r6, r6  )
 	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
@@ -579,7 +572,6 @@ ARM_BE8(rev	r6, r6  )
 	and	r2, r2, #3
 	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 1:
-#endif
 .endm
 
 .equ vmentry,	0
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 5d3bfc0eb3f0..974b1c606d04 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -121,12 +121,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 0;
 }
 
-static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-		      struct kvm_exit_mmio *mmio)
+static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 {
 	unsigned long rt;
-	int len;
-	bool is_write, sign_extend;
+	int access_size;
+	bool sign_extend;
 
 	if (kvm_vcpu_dabt_isextabt(vcpu)) {
 		/* cache operation on I/O addr, tell guest unsupported */
@@ -140,17 +139,15 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return 1;
 	}
 
-	len = kvm_vcpu_dabt_get_as(vcpu);
-	if (unlikely(len < 0))
-		return len;
+	access_size = kvm_vcpu_dabt_get_as(vcpu);
+	if (unlikely(access_size < 0))
+		return access_size;
 
-	is_write = kvm_vcpu_dabt_iswrite(vcpu);
+	*is_write = kvm_vcpu_dabt_iswrite(vcpu);
 	sign_extend = kvm_vcpu_dabt_issext(vcpu);
 	rt = kvm_vcpu_dabt_get_rd(vcpu);
 
-	mmio->is_write = is_write;
-	mmio->phys_addr = fault_ipa;
-	mmio->len = len;
+	*len = access_size;
 	vcpu->arch.mmio_decode.sign_extend = sign_extend;
 	vcpu->arch.mmio_decode.rt = rt;
 
@@ -165,20 +162,20 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa)
 {
-	struct kvm_exit_mmio mmio;
 	unsigned long data;
 	unsigned long rt;
 	int ret;
+	bool is_write;
+	int len;
+	u8 data_buf[8];
 
 	/*
-	 * 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.
+	 * Prepare MMIO operation. First decode the syndrome data we get
+	 * from the CPU. Then try if some in-kernel emulation feels
+	 * responsible, otherwise let user space do its magic.
 	 */
-
 	if (kvm_vcpu_dabt_isvalid(vcpu)) {
-		ret = decode_hsr(vcpu, fault_ipa, &mmio);
+		ret = decode_hsr(vcpu, &is_write, &len);
 		if (ret)
 			return ret;
 	} else {
@@ -188,21 +185,34 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	rt = vcpu->arch.mmio_decode.rt;
 
-	if (mmio.is_write) {
-		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt),
-					       mmio.len);
+	if (is_write) {
+		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len);
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
+		mmio_write_buf(data_buf, len, data);
 
-		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len,
-			       fault_ipa, data);
-		mmio_write_buf(mmio.data, mmio.len, data);
+		ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len,
+				       data_buf);
 	} else {
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len,
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len,
 			       fault_ipa, 0);
+
+		ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len,
+				      data_buf);
 	}
 
-	if (vgic_handle_mmio(vcpu, run, &mmio))
+	/* Now prepare kvm_run for the potential return to userland. */
+	run->mmio.is_write	= is_write;
+	run->mmio.phys_addr	= fault_ipa;
+	run->mmio.len		= len;
+	memcpy(run->mmio.data, data_buf, len);
+
+	if (!ret) {
+		/* We handled the access successfully in the kernel. */
+		kvm_handle_mmio_return(vcpu, run);
 		return 1;
+	}
 
-	kvm_prepare_mmio(run, &mmio);
+	run->exit_reason	= KVM_EXIT_MMIO;
 	return 0;
 }
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 5656d79c5a44..15b050d46fc9 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1330,10 +1330,51 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 out_unlock:
 	spin_unlock(&kvm->mmu_lock);
+	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret;
 }
 
+/*
+ * Resolve the access fault by making the page young again.
+ * Note that because the faulting entry is guaranteed not to be
+ * cached in the TLB, we don't need to invalidate anything.
+ */
+static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+	pfn_t pfn;
+	bool pfn_valid = false;
+
+	trace_kvm_access_fault(fault_ipa);
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+
+	pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		goto out;
+
+	if (kvm_pmd_huge(*pmd)) {	/* THP, HugeTLB */
+		*pmd = pmd_mkyoung(*pmd);
+		pfn = pmd_pfn(*pmd);
+		pfn_valid = true;
+		goto out;
+	}
+
+	pte = pte_offset_kernel(pmd, fault_ipa);
+	if (pte_none(*pte))		/* Nothing there either */
+		goto out;
+
+	*pte = pte_mkyoung(*pte);	/* Just a page... */
+	pfn = pte_pfn(*pte);
+	pfn_valid = true;
+out:
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	if (pfn_valid)
+		kvm_set_pfn_accessed(pfn);
+}
+
 /**
  * kvm_handle_guest_abort - handles all 2nd stage aborts
  * @vcpu:	the VCPU pointer
@@ -1364,7 +1405,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	/* Check the stage-2 fault is trans. fault or write fault */
 	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
-	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
+	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
+	    fault_status != FSC_ACCESS) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1400,6 +1442,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
 
+	if (fault_status == FSC_ACCESS) {
+		handle_access_fault(vcpu, fault_ipa);
+		ret = 1;
+		goto out_unlock;
+	}
+
 	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
@@ -1408,15 +1456,16 @@ out_unlock:
 	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)
+static int handle_hva_to_gpa(struct kvm *kvm,
+			     unsigned long start,
+			     unsigned long end,
+			     int (*handler)(struct kvm *kvm,
+					    gpa_t gpa, void *data),
+			     void *data)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
+	int ret = 0;
 
 	slots = kvm_memslots(kvm);
 
@@ -1440,14 +1489,17 @@ static void handle_hva_to_gpa(struct kvm *kvm,
 
 		for (; gfn < gfn_end; ++gfn) {
 			gpa_t gpa = gfn << PAGE_SHIFT;
-			handler(kvm, gpa, data);
+			ret |= handler(kvm, gpa, data);
 		}
 	}
+
+	return ret;
 }
 
-static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 {
 	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
+	return 0;
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
@@ -1473,7 +1525,7 @@ int kvm_unmap_hva_range(struct kvm *kvm,
 	return 0;
 }
 
-static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
 {
 	pte_t *pte = (pte_t *)data;
 
@@ -1485,6 +1537,7 @@ static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
 	 * through this calling path.
 	 */
 	stage2_set_pte(kvm, NULL, gpa, pte, 0);
+	return 0;
 }
 
 
@@ -1501,6 +1554,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
 }
 
+static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (kvm_pmd_huge(*pmd)) {	/* THP, HugeTLB */
+		if (pmd_young(*pmd)) {
+			*pmd = pmd_mkold(*pmd);
+			return 1;
+		}
+
+		return 0;
+	}
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (pte_none(*pte))
+		return 0;
+
+	if (pte_young(*pte)) {
+		*pte = pte_mkold(*pte);	/* Just a page... */
+		return 1;
+	}
+
+	return 0;
+}
+
+static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (kvm_pmd_huge(*pmd))		/* THP, HugeTLB */
+		return pmd_young(*pmd);
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (!pte_none(*pte))		/* Just a page... */
+		return pte_young(*pte);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	trace_kvm_age_hva(start, end);
+	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_test_age_hva(hva);
+	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+}
+
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 {
 	mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 6817664b46b8..0ec35392d208 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -68,6 +68,21 @@ TRACE_EVENT(kvm_guest_fault,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
 
+TRACE_EVENT(kvm_access_fault,
+	TP_PROTO(unsigned long ipa),
+	TP_ARGS(ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->ipa		= ipa;
+	),
+
+	TP_printk("IPA: %lx", __entry->ipa)
+);
+
 TRACE_EVENT(kvm_irq_line,
 	TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
 	TP_ARGS(type, vcpu_idx, irq_num, level),
@@ -210,6 +225,39 @@ TRACE_EVENT(kvm_set_spte_hva,
 	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
 );
 
+TRACE_EVENT(kvm_age_hva,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+);
+
 TRACE_EVENT(kvm_hvc,
 	TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
 	TP_ARGS(vcpu_pc, r0, imm),