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
  ...

10 files changed, 661 insertions, 453 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 6e54f3542126..98c95f2fcba4 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -85,13 +85,22 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+/*
+ * Work function for handling the backup timer that we schedule when a vcpu is
+ * no longer running, but had a timer programmed to fire in the future.
+ */
 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);
+
+	/*
+	 * If the vcpu is blocked we want to wake it up so that it will see
+	 * the timer has expired when entering the guest.
+	 */
+	kvm_vcpu_kick(vcpu);
 }
 
 static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
@@ -102,6 +111,21 @@ static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
 	return HRTIMER_NORESTART;
 }
 
+bool kvm_timer_should_fire(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	cycle_t cval, now;
+
+	if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
+		!(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE))
+		return false;
+
+	cval = timer->cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+	return cval <= now;
+}
+
 /**
  * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
  * @vcpu: The vcpu pointer
@@ -119,6 +143,13 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * populate the CPU timer again.
 	 */
 	timer_disarm(timer);
+
+	/*
+	 * If the timer expired while we were not scheduled, now is the time
+	 * to inject it.
+	 */
+	if (kvm_timer_should_fire(vcpu))
+		kvm_timer_inject_irq(vcpu);
 }
 
 /**
@@ -134,16 +165,9 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 	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) {
+	if (kvm_timer_should_fire(vcpu)) {
 		/*
 		 * Timer has already expired while we were not
 		 * looking. Inject the interrupt and carry on.
@@ -152,6 +176,9 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 		return;
 	}
 
+	cval = timer->cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
 	ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask,
 				 &timecounter->frac);
 	timer_arm(timer, ns);
diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c
index 19c6210f02cf..13907970d11c 100644
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ b/virt/kvm/arm/vgic-v2-emul.c
@@ -107,6 +107,22 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
 					     vcpu->vcpu_id);
 }
 
+static bool handle_mmio_set_active_reg(struct kvm_vcpu *vcpu,
+				       struct kvm_exit_mmio *mmio,
+				       phys_addr_t offset)
+{
+	return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
+					  vcpu->vcpu_id);
+}
+
+static bool handle_mmio_clear_active_reg(struct kvm_vcpu *vcpu,
+					 struct kvm_exit_mmio *mmio,
+					 phys_addr_t offset)
+{
+	return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
+					    vcpu->vcpu_id);
+}
+
 static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
 				     struct kvm_exit_mmio *mmio,
 				     phys_addr_t offset)
@@ -303,7 +319,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
 }
 
-static const struct kvm_mmio_range vgic_dist_ranges[] = {
+static const struct vgic_io_range vgic_dist_ranges[] = {
 	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
@@ -344,13 +360,13 @@ static const struct kvm_mmio_range vgic_dist_ranges[] = {
 		.base		= GIC_DIST_ACTIVE_SET,
 		.len		= VGIC_MAX_IRQS / 8,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_set_active_reg,
 	},
 	{
 		.base		= GIC_DIST_ACTIVE_CLEAR,
 		.len		= VGIC_MAX_IRQS / 8,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_clear_active_reg,
 	},
 	{
 		.base		= GIC_DIST_PRI,
@@ -388,24 +404,6 @@ static const struct kvm_mmio_range vgic_dist_ranges[] = {
 	{}
 };
 
-static bool vgic_v2_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
-				struct kvm_exit_mmio *mmio)
-{
-	unsigned long base = vcpu->kvm->arch.vgic.vgic_dist_base;
-
-	if (!is_in_range(mmio->phys_addr, mmio->len, base,
-			 KVM_VGIC_V2_DIST_SIZE))
-		return false;
-
-	/* GICv2 does not support accesses wider than 32 bits */
-	if (mmio->len > 4) {
-		kvm_inject_dabt(vcpu, mmio->phys_addr);
-		return true;
-	}
-
-	return vgic_handle_mmio_range(vcpu, run, mmio, vgic_dist_ranges, base);
-}
-
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -490,6 +488,7 @@ static bool vgic_v2_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 static int vgic_v2_map_resources(struct kvm *kvm,
 				 const struct vgic_params *params)
 {
+	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
 	if (!irqchip_in_kernel(kvm))
@@ -500,13 +499,17 @@ static int vgic_v2_map_resources(struct kvm *kvm,
 	if (vgic_ready(kvm))
 		goto out;
 
-	if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
-	    IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) {
+	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
+	    IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
 		kvm_err("Need to set vgic cpu and dist addresses first\n");
 		ret = -ENXIO;
 		goto out;
 	}
 
+	vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
+				 KVM_VGIC_V2_DIST_SIZE,
+				 vgic_dist_ranges, -1, &dist->dist_iodev);
+
 	/*
 	 * Initialize the vgic if this hasn't already been done on demand by
 	 * accessing the vgic state from userspace.
@@ -514,18 +517,23 @@ static int vgic_v2_map_resources(struct kvm *kvm,
 	ret = vgic_init(kvm);
 	if (ret) {
 		kvm_err("Unable to allocate maps\n");
-		goto out;
+		goto out_unregister;
 	}
 
-	ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
+	ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base,
 				    params->vcpu_base, KVM_VGIC_V2_CPU_SIZE,
 				    true);
 	if (ret) {
 		kvm_err("Unable to remap VGIC CPU to VCPU\n");
-		goto out;
+		goto out_unregister;
 	}
 
-	kvm->arch.vgic.ready = true;
+	dist->ready = true;
+	goto out;
+
+out_unregister:
+	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
+
 out:
 	if (ret)
 		kvm_vgic_destroy(kvm);
@@ -554,7 +562,6 @@ void vgic_v2_init_emulation(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	dist->vm_ops.handle_mmio = vgic_v2_handle_mmio;
 	dist->vm_ops.queue_sgi = vgic_v2_queue_sgi;
 	dist->vm_ops.add_sgi_source = vgic_v2_add_sgi_source;
 	dist->vm_ops.init_model = vgic_v2_init_model;
@@ -631,7 +638,7 @@ static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
  * CPU Interface Register accesses - these are not accessed by the VM, but by
  * user space for saving and restoring VGIC state.
  */
-static const struct kvm_mmio_range vgic_cpu_ranges[] = {
+static const struct vgic_io_range vgic_cpu_ranges[] = {
 	{
 		.base		= GIC_CPU_CTRL,
 		.len		= 12,
@@ -658,12 +665,13 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 				 struct kvm_device_attr *attr,
 				 u32 *reg, bool is_write)
 {
-	const struct kvm_mmio_range *r = NULL, *ranges;
+	const struct vgic_io_range *r = NULL, *ranges;
 	phys_addr_t offset;
 	int ret, cpuid, c;
 	struct kvm_vcpu *vcpu, *tmp_vcpu;
 	struct vgic_dist *vgic;
 	struct kvm_exit_mmio mmio;
+	u32 data;
 
 	offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
 	cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
@@ -685,6 +693,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 
 	mmio.len = 4;
 	mmio.is_write = is_write;
+	mmio.data = &data;
 	if (is_write)
 		mmio_data_write(&mmio, ~0, *reg);
 	switch (attr->group) {
@@ -699,7 +708,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 	default:
 		BUG();
 	}
-	r = vgic_find_range(ranges, &mmio, offset);
+	r = vgic_find_range(ranges, 4, offset);
 
 	if (unlikely(!r || !r->handle_mmio)) {
 		ret = -ENXIO;
diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c
index b3f154631515..e9c3a7a83833 100644
--- a/virt/kvm/arm/vgic-v3-emul.c
+++ b/virt/kvm/arm/vgic-v3-emul.c
@@ -340,7 +340,7 @@ static bool handle_mmio_idregs(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-static const struct kvm_mmio_range vgic_v3_dist_ranges[] = {
+static const struct vgic_io_range vgic_v3_dist_ranges[] = {
 	{
 		.base           = GICD_CTLR,
 		.len            = 0x04,
@@ -502,6 +502,43 @@ static const struct kvm_mmio_range vgic_v3_dist_ranges[] = {
 	{},
 };
 
+static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu,
+				    struct kvm_exit_mmio *mmio,
+				    phys_addr_t offset)
+{
+	/* since we don't support LPIs, this register is zero for now */
+	vgic_reg_access(mmio, NULL, offset,
+			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+	return false;
+}
+
+static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu,
+				     struct kvm_exit_mmio *mmio,
+				     phys_addr_t offset)
+{
+	u32 reg;
+	u64 mpidr;
+	struct kvm_vcpu *redist_vcpu = mmio->private;
+	int target_vcpu_id = redist_vcpu->vcpu_id;
+
+	/* the upper 32 bits contain the affinity value */
+	if ((offset & ~3) == 4) {
+		mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu);
+		reg = compress_mpidr(mpidr);
+
+		vgic_reg_access(mmio, &reg, offset,
+				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
+		return false;
+	}
+
+	reg = redist_vcpu->vcpu_id << 8;
+	if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
+		reg |= GICR_TYPER_LAST;
+	vgic_reg_access(mmio, &reg, offset,
+			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
+	return false;
+}
+
 static bool handle_mmio_set_enable_reg_redist(struct kvm_vcpu *vcpu,
 					      struct kvm_exit_mmio *mmio,
 					      phys_addr_t offset)
@@ -570,186 +607,107 @@ static bool handle_mmio_cfg_reg_redist(struct kvm_vcpu *vcpu,
 	return vgic_handle_cfg_reg(reg, mmio, offset);
 }
 
-static const struct kvm_mmio_range vgic_redist_sgi_ranges[] = {
+#define SGI_base(x) ((x) + SZ_64K)
+
+static const struct vgic_io_range vgic_redist_ranges[] = {
+	{
+		.base           = GICR_CTLR,
+		.len            = 0x04,
+		.bits_per_irq   = 0,
+		.handle_mmio    = handle_mmio_ctlr_redist,
+	},
+	{
+		.base           = GICR_TYPER,
+		.len            = 0x08,
+		.bits_per_irq   = 0,
+		.handle_mmio    = handle_mmio_typer_redist,
+	},
+	{
+		.base           = GICR_IIDR,
+		.len            = 0x04,
+		.bits_per_irq   = 0,
+		.handle_mmio    = handle_mmio_iidr,
+	},
+	{
+		.base           = GICR_WAKER,
+		.len            = 0x04,
+		.bits_per_irq   = 0,
+		.handle_mmio    = handle_mmio_raz_wi,
+	},
 	{
-		.base		= GICR_IGROUPR0,
+		.base           = GICR_IDREGS,
+		.len            = 0x30,
+		.bits_per_irq   = 0,
+		.handle_mmio    = handle_mmio_idregs,
+	},
+	{
+		.base		= SGI_base(GICR_IGROUPR0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_rao_wi,
 	},
 	{
-		.base		= GICR_ISENABLER0,
+		.base		= SGI_base(GICR_ISENABLER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_enable_reg_redist,
 	},
 	{
-		.base		= GICR_ICENABLER0,
+		.base		= SGI_base(GICR_ICENABLER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_enable_reg_redist,
 	},
 	{
-		.base		= GICR_ISPENDR0,
+		.base		= SGI_base(GICR_ISPENDR0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_pending_reg_redist,
 	},
 	{
-		.base		= GICR_ICPENDR0,
+		.base		= SGI_base(GICR_ICPENDR0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_pending_reg_redist,
 	},
 	{
-		.base		= GICR_ISACTIVER0,
+		.base		= SGI_base(GICR_ISACTIVER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
-		.base		= GICR_ICACTIVER0,
+		.base		= SGI_base(GICR_ICACTIVER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
-		.base		= GICR_IPRIORITYR0,
+		.base		= SGI_base(GICR_IPRIORITYR0),
 		.len		= 0x20,
 		.bits_per_irq	= 8,
 		.handle_mmio	= handle_mmio_priority_reg_redist,
 	},
 	{
-		.base		= GICR_ICFGR0,
+		.base		= SGI_base(GICR_ICFGR0),
 		.len		= 0x08,
 		.bits_per_irq	= 2,
 		.handle_mmio	= handle_mmio_cfg_reg_redist,
 	},
 	{
-		.base		= GICR_IGRPMODR0,
+		.base		= SGI_base(GICR_IGRPMODR0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
-		.base		= GICR_NSACR,
+		.base		= SGI_base(GICR_NSACR),
 		.len		= 0x04,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{},
 };
 
-static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu,
-				    struct kvm_exit_mmio *mmio,
-				    phys_addr_t offset)
-{
-	/* since we don't support LPIs, this register is zero for now */
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu,
-				     struct kvm_exit_mmio *mmio,
-				     phys_addr_t offset)
-{
-	u32 reg;
-	u64 mpidr;
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-	int target_vcpu_id = redist_vcpu->vcpu_id;
-
-	/* the upper 32 bits contain the affinity value */
-	if ((offset & ~3) == 4) {
-		mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu);
-		reg = compress_mpidr(mpidr);
-
-		vgic_reg_access(mmio, &reg, offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	reg = redist_vcpu->vcpu_id << 8;
-	if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
-		reg |= GICR_TYPER_LAST;
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static const struct kvm_mmio_range vgic_redist_ranges[] = {
-	{
-		.base           = GICR_CTLR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_ctlr_redist,
-	},
-	{
-		.base           = GICR_TYPER,
-		.len            = 0x08,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_typer_redist,
-	},
-	{
-		.base           = GICR_IIDR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_iidr,
-	},
-	{
-		.base           = GICR_WAKER,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_raz_wi,
-	},
-	{
-		.base           = GICR_IDREGS,
-		.len            = 0x30,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_idregs,
-	},
-	{},
-};
-
-/*
- * This function splits accesses between the distributor and the two
- * redistributor parts (private/SPI). As each redistributor is accessible
- * from any CPU, we have to determine the affected VCPU by taking the faulting
- * address into account. We then pass this VCPU to the handler function via
- * the private parameter.
- */
-#define SGI_BASE_OFFSET SZ_64K
-static bool vgic_v3_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
-				struct kvm_exit_mmio *mmio)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long dbase = dist->vgic_dist_base;
-	unsigned long rdbase = dist->vgic_redist_base;
-	int nrcpus = atomic_read(&vcpu->kvm->online_vcpus);
-	int vcpu_id;
-	const struct kvm_mmio_range *mmio_range;
-
-	if (is_in_range(mmio->phys_addr, mmio->len, dbase, GIC_V3_DIST_SIZE)) {
-		return vgic_handle_mmio_range(vcpu, run, mmio,
-					      vgic_v3_dist_ranges, dbase);
-	}
-
-	if (!is_in_range(mmio->phys_addr, mmio->len, rdbase,
-	    GIC_V3_REDIST_SIZE * nrcpus))
-		return false;
-
-	vcpu_id = (mmio->phys_addr - rdbase) / GIC_V3_REDIST_SIZE;
-	rdbase += (vcpu_id * GIC_V3_REDIST_SIZE);
-	mmio->private = kvm_get_vcpu(vcpu->kvm, vcpu_id);
-
-	if (mmio->phys_addr >= rdbase + SGI_BASE_OFFSET) {
-		rdbase += SGI_BASE_OFFSET;
-		mmio_range = vgic_redist_sgi_ranges;
-	} else {
-		mmio_range = vgic_redist_ranges;
-	}
-	return vgic_handle_mmio_range(vcpu, run, mmio, mmio_range, rdbase);
-}
-
 static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 {
 	if (vgic_queue_irq(vcpu, 0, irq)) {
@@ -766,6 +724,9 @@ static int vgic_v3_map_resources(struct kvm *kvm,
 {
 	int ret = 0;
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	gpa_t rdbase = dist->vgic_redist_base;
+	struct vgic_io_device *iodevs = NULL;
+	int i;
 
 	if (!irqchip_in_kernel(kvm))
 		return 0;
@@ -791,7 +752,41 @@ static int vgic_v3_map_resources(struct kvm *kvm,
 		goto out;
 	}
 
-	kvm->arch.vgic.ready = true;
+	ret = vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
+				       GIC_V3_DIST_SIZE, vgic_v3_dist_ranges,
+				       -1, &dist->dist_iodev);
+	if (ret)
+		goto out;
+
+	iodevs = kcalloc(dist->nr_cpus, sizeof(iodevs[0]), GFP_KERNEL);
+	if (!iodevs) {
+		ret = -ENOMEM;
+		goto out_unregister;
+	}
+
+	for (i = 0; i < dist->nr_cpus; i++) {
+		ret = vgic_register_kvm_io_dev(kvm, rdbase,
+					       SZ_128K, vgic_redist_ranges,
+					       i, &iodevs[i]);
+		if (ret)
+			goto out_unregister;
+		rdbase += GIC_V3_REDIST_SIZE;
+	}
+
+	dist->redist_iodevs = iodevs;
+	dist->ready = true;
+	goto out;
+
+out_unregister:
+	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
+	if (iodevs) {
+		for (i = 0; i < dist->nr_cpus; i++) {
+			if (iodevs[i].dev.ops)
+				kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+							  &iodevs[i].dev);
+		}
+	}
+
 out:
 	if (ret)
 		kvm_vgic_destroy(kvm);
@@ -832,7 +827,6 @@ void vgic_v3_init_emulation(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	dist->vm_ops.handle_mmio = vgic_v3_handle_mmio;
 	dist->vm_ops.queue_sgi = vgic_v3_queue_sgi;
 	dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source;
 	dist->vm_ops.init_model = vgic_v3_init_model;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index c9f60f524588..8d550ff14700 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -31,6 +31,9 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
+#include <trace/events/kvm.h>
+#include <asm/kvm.h>
+#include <kvm/iodev.h>
 
 /*
  * How the whole thing works (courtesy of Christoffer Dall):
@@ -263,6 +266,13 @@ static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
 	return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
 }
 
+static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
+}
+
 static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
@@ -277,6 +287,20 @@ static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
 	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
 }
 
+static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
+}
+
 static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
@@ -520,6 +544,44 @@ bool vgic_handle_clear_pending_reg(struct kvm *kvm,
 	return false;
 }
 
+bool vgic_handle_set_active_reg(struct kvm *kvm,
+				struct kvm_exit_mmio *mmio,
+				phys_addr_t offset, int vcpu_id)
+{
+	u32 *reg;
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
+	vgic_reg_access(mmio, reg, offset,
+			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+
+	if (mmio->is_write) {
+		vgic_update_state(kvm);
+		return true;
+	}
+
+	return false;
+}
+
+bool vgic_handle_clear_active_reg(struct kvm *kvm,
+				  struct kvm_exit_mmio *mmio,
+				  phys_addr_t offset, int vcpu_id)
+{
+	u32 *reg;
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
+	vgic_reg_access(mmio, reg, offset,
+			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+
+	if (mmio->is_write) {
+		vgic_update_state(kvm);
+		return true;
+	}
+
+	return false;
+}
+
 static u32 vgic_cfg_expand(u16 val)
 {
 	u32 res = 0;
@@ -588,16 +650,12 @@ bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
 }
 
 /**
- * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
+ * vgic_unqueue_irqs - move pending/active IRQs from LRs to the distributor
  * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
  *
- * Move any pending IRQs that have already been assigned to LRs back to the
+ * Move any IRQs that have already been assigned to LRs back to the
  * emulated distributor state so that the complete emulated state can be read
  * from the main emulation structures without investigating the LRs.
- *
- * Note that IRQs in the active state in the LRs get their pending state moved
- * to the distributor but the active state stays in the LRs, because we don't
- * track the active state on the distributor side.
  */
 void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 {
@@ -613,12 +671,22 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 * 01: pending
 		 * 10: active
 		 * 11: pending and active
-		 *
-		 * If the LR holds only an active interrupt (not pending) then
-		 * just leave it alone.
 		 */
-		if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE)
-			continue;
+		BUG_ON(!(lr.state & LR_STATE_MASK));
+
+		/* Reestablish SGI source for pending and active IRQs */
+		if (lr.irq < VGIC_NR_SGIS)
+			add_sgi_source(vcpu, lr.irq, lr.source);
+
+		/*
+		 * If the LR holds an active (10) or a pending and active (11)
+		 * interrupt then move the active state to the
+		 * distributor tracking bit.
+		 */
+		if (lr.state & LR_STATE_ACTIVE) {
+			vgic_irq_set_active(vcpu, lr.irq);
+			lr.state &= ~LR_STATE_ACTIVE;
+		}
 
 		/*
 		 * Reestablish the pending state on the distributor and the
@@ -626,21 +694,19 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 * is fine, then we are only setting a few bits that were
 		 * already set.
 		 */
-		vgic_dist_irq_set_pending(vcpu, lr.irq);
-		if (lr.irq < VGIC_NR_SGIS)
-			add_sgi_source(vcpu, lr.irq, lr.source);
-		lr.state &= ~LR_STATE_PENDING;
+		if (lr.state & LR_STATE_PENDING) {
+			vgic_dist_irq_set_pending(vcpu, lr.irq);
+			lr.state &= ~LR_STATE_PENDING;
+		}
+
 		vgic_set_lr(vcpu, i, lr);
 
 		/*
-		 * If there's no state left on the LR (it could still be
-		 * active), then the LR does not hold any useful info and can
-		 * be marked as free for other use.
+		 * Mark the LR as free for other use.
 		 */
-		if (!(lr.state & LR_STATE_MASK)) {
-			vgic_retire_lr(i, lr.irq, vcpu);
-			vgic_irq_clear_queued(vcpu, lr.irq);
-		}
+		BUG_ON(lr.state & LR_STATE_MASK);
+		vgic_retire_lr(i, lr.irq, vcpu);
+		vgic_irq_clear_queued(vcpu, lr.irq);
 
 		/* Finally update the VGIC state. */
 		vgic_update_state(vcpu->kvm);
@@ -648,24 +714,21 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 }
 
 const
-struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
-{
-	const struct kvm_mmio_range *r = ranges;
-
-	while (r->len) {
-		if (offset >= r->base &&
-		    (offset + mmio->len) <= (r->base + r->len))
-			return r;
-		r++;
+struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
+				      int len, gpa_t offset)
+{
+	while (ranges->len) {
+		if (offset >= ranges->base &&
+		    (offset + len) <= (ranges->base + ranges->len))
+			return ranges;
+		ranges++;
 	}
 
 	return NULL;
 }
 
 static bool vgic_validate_access(const struct vgic_dist *dist,
-				 const struct kvm_mmio_range *range,
+				 const struct vgic_io_range *range,
 				 unsigned long offset)
 {
 	int irq;
@@ -693,9 +756,8 @@ static bool vgic_validate_access(const struct vgic_dist *dist,
 static bool call_range_handler(struct kvm_vcpu *vcpu,
 			       struct kvm_exit_mmio *mmio,
 			       unsigned long offset,
-			       const struct kvm_mmio_range *range)
+			       const struct vgic_io_range *range)
 {
-	u32 *data32 = (void *)mmio->data;
 	struct kvm_exit_mmio mmio32;
 	bool ret;
 
@@ -712,91 +774,142 @@ static bool call_range_handler(struct kvm_vcpu *vcpu,
 	mmio32.private = mmio->private;
 
 	mmio32.phys_addr = mmio->phys_addr + 4;
-	if (mmio->is_write)
-		*(u32 *)mmio32.data = data32[1];
+	mmio32.data = &((u32 *)mmio->data)[1];
 	ret = range->handle_mmio(vcpu, &mmio32, offset + 4);
-	if (!mmio->is_write)
-		data32[1] = *(u32 *)mmio32.data;
 
 	mmio32.phys_addr = mmio->phys_addr;
-	if (mmio->is_write)
-		*(u32 *)mmio32.data = data32[0];
+	mmio32.data = &((u32 *)mmio->data)[0];
 	ret |= range->handle_mmio(vcpu, &mmio32, offset);
-	if (!mmio->is_write)
-		data32[0] = *(u32 *)mmio32.data;
 
 	return ret;
 }
 
 /**
- * vgic_handle_mmio_range - handle an in-kernel MMIO access
+ * vgic_handle_mmio_access - handle an in-kernel MMIO access
+ * This is called by the read/write KVM IO device wrappers below.
  * @vcpu:	pointer to the vcpu performing the access
- * @run:	pointer to the kvm_run structure
- * @mmio:	pointer to the data describing the access
- * @ranges:	array of MMIO ranges in a given region
- * @mmio_base:	base address of that region
+ * @this:	pointer to the KVM IO device in charge
+ * @addr:	guest physical address of the access
+ * @len:	size of the access
+ * @val:	pointer to the data region
+ * @is_write:	read or write access
  *
  * returns true if the MMIO access could be performed
  */
-bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
-			    struct kvm_exit_mmio *mmio,
-			    const struct kvm_mmio_range *ranges,
-			    unsigned long mmio_base)
+static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu,
+				   struct kvm_io_device *this, gpa_t addr,
+				   int len, void *val, bool is_write)
 {
-	const struct kvm_mmio_range *range;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	struct vgic_io_device *iodev = container_of(this,
+						    struct vgic_io_device, dev);
+	struct kvm_run *run = vcpu->run;
+	const struct vgic_io_range *range;
+	struct kvm_exit_mmio mmio;
 	bool updated_state;
-	unsigned long offset;
+	gpa_t offset;
 
-	offset = mmio->phys_addr - mmio_base;
-	range = vgic_find_range(ranges, mmio, offset);
+	offset = addr - iodev->addr;
+	range = vgic_find_range(iodev->reg_ranges, len, offset);
 	if (unlikely(!range || !range->handle_mmio)) {
-		pr_warn("Unhandled access %d %08llx %d\n",
-			mmio->is_write, mmio->phys_addr, mmio->len);
-		return false;
+		pr_warn("Unhandled access %d %08llx %d\n", is_write, addr, len);
+		return -ENXIO;
 	}
 
-	spin_lock(&vcpu->kvm->arch.vgic.lock);
+	mmio.phys_addr = addr;
+	mmio.len = len;
+	mmio.is_write = is_write;
+	mmio.data = val;
+	mmio.private = iodev->redist_vcpu;
+
+	spin_lock(&dist->lock);
 	offset -= range->base;
 	if (vgic_validate_access(dist, range, offset)) {
-		updated_state = call_range_handler(vcpu, mmio, offset, range);
+		updated_state = call_range_handler(vcpu, &mmio, offset, range);
 	} else {
-		if (!mmio->is_write)
-			memset(mmio->data, 0, mmio->len);
+		if (!is_write)
+			memset(val, 0, len);
 		updated_state = false;
 	}
-	spin_unlock(&vcpu->kvm->arch.vgic.lock);
-	kvm_prepare_mmio(run, mmio);
+	spin_unlock(&dist->lock);
+	run->mmio.is_write	= is_write;
+	run->mmio.len		= len;
+	run->mmio.phys_addr	= addr;
+	memcpy(run->mmio.data, val, len);
+
 	kvm_handle_mmio_return(vcpu, run);
 
 	if (updated_state)
 		vgic_kick_vcpus(vcpu->kvm);
 
-	return true;
+	return 0;
+}
+
+static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu,
+				 struct kvm_io_device *this,
+				 gpa_t addr, int len, void *val)
+{
+	return vgic_handle_mmio_access(vcpu, this, addr, len, val, false);
 }
 
+static int vgic_handle_mmio_write(struct kvm_vcpu *vcpu,
+				  struct kvm_io_device *this,
+				  gpa_t addr, int len, const void *val)
+{
+	return vgic_handle_mmio_access(vcpu, this, addr, len, (void *)val,
+				       true);
+}
+
+struct kvm_io_device_ops vgic_io_ops = {
+	.read	= vgic_handle_mmio_read,
+	.write	= vgic_handle_mmio_write,
+};
+
 /**
- * vgic_handle_mmio - handle an in-kernel MMIO access for the GIC emulation
- * @vcpu:      pointer to the vcpu performing the access
- * @run:       pointer to the kvm_run structure
- * @mmio:      pointer to the data describing the access
+ * vgic_register_kvm_io_dev - register VGIC register frame on the KVM I/O bus
+ * @kvm:            The VM structure pointer
+ * @base:           The (guest) base address for the register frame
+ * @len:            Length of the register frame window
+ * @ranges:         Describing the handler functions for each register
+ * @redist_vcpu_id: The VCPU ID to pass on to the handlers on call
+ * @iodev:          Points to memory to be passed on to the handler
  *
- * returns true if the MMIO access has been performed in kernel space,
- * and false if it needs to be emulated in user space.
- * Calls the actual handling routine for the selected VGIC model.
+ * @iodev stores the parameters of this function to be usable by the handler
+ * respectively the dispatcher function (since the KVM I/O bus framework lacks
+ * an opaque parameter). Initialization is done in this function, but the
+ * reference should be valid and unique for the whole VGIC lifetime.
+ * If the register frame is not mapped for a specific VCPU, pass -1 to
+ * @redist_vcpu_id.
  */
-bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		      struct kvm_exit_mmio *mmio)
+int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
+			     const struct vgic_io_range *ranges,
+			     int redist_vcpu_id,
+			     struct vgic_io_device *iodev)
 {
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return false;
+	struct kvm_vcpu *vcpu = NULL;
+	int ret;
 
-	/*
-	 * This will currently call either vgic_v2_handle_mmio() or
-	 * vgic_v3_handle_mmio(), which in turn will call
-	 * vgic_handle_mmio_range() defined above.
-	 */
-	return vcpu->kvm->arch.vgic.vm_ops.handle_mmio(vcpu, run, mmio);
+	if (redist_vcpu_id >= 0)
+		vcpu = kvm_get_vcpu(kvm, redist_vcpu_id);
+
+	iodev->addr		= base;
+	iodev->len		= len;
+	iodev->reg_ranges	= ranges;
+	iodev->redist_vcpu	= vcpu;
+
+	kvm_iodevice_init(&iodev->dev, &vgic_io_ops);
+
+	mutex_lock(&kvm->slots_lock);
+
+	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, base, len,
+				      &iodev->dev);
+	mutex_unlock(&kvm->slots_lock);
+
+	/* Mark the iodev as invalid if registration fails. */
+	if (ret)
+		iodev->dev.ops = NULL;
+
+	return ret;
 }
 
 static int vgic_nr_shared_irqs(struct vgic_dist *dist)
@@ -804,6 +917,36 @@ static int vgic_nr_shared_irqs(struct vgic_dist *dist)
 	return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
 }
 
+static int compute_active_for_cpu(struct kvm_vcpu *vcpu)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	unsigned long *active, *enabled, *act_percpu, *act_shared;
+	unsigned long active_private, active_shared;
+	int nr_shared = vgic_nr_shared_irqs(dist);
+	int vcpu_id;
+
+	vcpu_id = vcpu->vcpu_id;
+	act_percpu = vcpu->arch.vgic_cpu.active_percpu;
+	act_shared = vcpu->arch.vgic_cpu.active_shared;
+
+	active = vgic_bitmap_get_cpu_map(&dist->irq_active, vcpu_id);
+	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
+	bitmap_and(act_percpu, active, enabled, VGIC_NR_PRIVATE_IRQS);
+
+	active = vgic_bitmap_get_shared_map(&dist->irq_active);
+	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
+	bitmap_and(act_shared, active, enabled, nr_shared);
+	bitmap_and(act_shared, act_shared,
+		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
+		   nr_shared);
+
+	active_private = find_first_bit(act_percpu, VGIC_NR_PRIVATE_IRQS);
+	active_shared = find_first_bit(act_shared, nr_shared);
+
+	return (active_private < VGIC_NR_PRIVATE_IRQS ||
+		active_shared < nr_shared);
+}
+
 static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
@@ -835,7 +978,7 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 
 /*
  * Update the interrupt state and determine which CPUs have pending
- * interrupts. Must be called with distributor lock held.
+ * or active interrupts. Must be called with distributor lock held.
  */
 void vgic_update_state(struct kvm *kvm)
 {
@@ -849,10 +992,13 @@ void vgic_update_state(struct kvm *kvm)
 	}
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
-		if (compute_pending_for_cpu(vcpu)) {
-			pr_debug("CPU%d has pending interrupts\n", c);
+		if (compute_pending_for_cpu(vcpu))
 			set_bit(c, dist->irq_pending_on_cpu);
-		}
+
+		if (compute_active_for_cpu(vcpu))
+			set_bit(c, dist->irq_active_on_cpu);
+		else
+			clear_bit(c, dist->irq_active_on_cpu);
 	}
 }
 
@@ -955,6 +1101,26 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq,
+				 int lr_nr, struct vgic_lr vlr)
+{
+	if (vgic_irq_is_active(vcpu, irq)) {
+		vlr.state |= LR_STATE_ACTIVE;
+		kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state);
+		vgic_irq_clear_active(vcpu, irq);
+		vgic_update_state(vcpu->kvm);
+	} else if (vgic_dist_irq_is_pending(vcpu, irq)) {
+		vlr.state |= LR_STATE_PENDING;
+		kvm_debug("Set pending: 0x%x\n", vlr.state);
+	}
+
+	if (!vgic_irq_is_edge(vcpu, irq))
+		vlr.state |= LR_EOI_INT;
+
+	vgic_set_lr(vcpu, lr_nr, vlr);
+	vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
+}
+
 /*
  * Queue an interrupt to a CPU virtual interface. Return true on success,
  * or false if it wasn't possible to queue it.
@@ -982,9 +1148,7 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 		if (vlr.source == sgi_source_id) {
 			kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
 			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
-			vlr.state |= LR_STATE_PENDING;
-			vgic_set_lr(vcpu, lr, vlr);
-			vgic_sync_lr_elrsr(vcpu, lr, vlr);
+			vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
 			return true;
 		}
 	}
@@ -1001,12 +1165,8 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 
 	vlr.irq = irq;
 	vlr.source = sgi_source_id;
-	vlr.state = LR_STATE_PENDING;
-	if (!vgic_irq_is_edge(vcpu, irq))
-		vlr.state |= LR_EOI_INT;
-
-	vgic_set_lr(vcpu, lr, vlr);
-	vgic_sync_lr_elrsr(vcpu, lr, vlr);
+	vlr.state = 0;
+	vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
 
 	return true;
 }
@@ -1038,39 +1198,49 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	unsigned long *pa_percpu, *pa_shared;
 	int i, vcpu_id;
 	int overflow = 0;
+	int nr_shared = vgic_nr_shared_irqs(dist);
 
 	vcpu_id = vcpu->vcpu_id;
 
+	pa_percpu = vcpu->arch.vgic_cpu.pend_act_percpu;
+	pa_shared = vcpu->arch.vgic_cpu.pend_act_shared;
+
+	bitmap_or(pa_percpu, vgic_cpu->pending_percpu, vgic_cpu->active_percpu,
+		  VGIC_NR_PRIVATE_IRQS);
+	bitmap_or(pa_shared, vgic_cpu->pending_shared, vgic_cpu->active_shared,
+		  nr_shared);
 	/*
 	 * We may not have any pending interrupt, or the interrupts
 	 * may have been serviced from another vcpu. In all cases,
 	 * move along.
 	 */
-	if (!kvm_vgic_vcpu_pending_irq(vcpu)) {
-		pr_debug("CPU%d has no pending interrupt\n", vcpu_id);
+	if (!kvm_vgic_vcpu_pending_irq(vcpu) && !kvm_vgic_vcpu_active_irq(vcpu))
 		goto epilog;
-	}
 
 	/* SGIs */
-	for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) {
+	for_each_set_bit(i, pa_percpu, VGIC_NR_SGIS) {
 		if (!queue_sgi(vcpu, i))
 			overflow = 1;
 	}
 
 	/* PPIs */
-	for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) {
+	for_each_set_bit_from(i, pa_percpu, VGIC_NR_PRIVATE_IRQS) {
 		if (!vgic_queue_hwirq(vcpu, i))
 			overflow = 1;
 	}
 
 	/* SPIs */
-	for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
+	for_each_set_bit(i, pa_shared, nr_shared) {
 		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
 			overflow = 1;
 	}
 
+
+
+
 epilog:
 	if (overflow) {
 		vgic_enable_underflow(vcpu);
@@ -1089,7 +1259,9 @@ epilog:
 static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 {
 	u32 status = vgic_get_interrupt_status(vcpu);
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	bool level_pending = false;
+	struct kvm *kvm = vcpu->kvm;
 
 	kvm_debug("STATUS = %08x\n", status);
 
@@ -1106,6 +1278,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
 			WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
 
+			spin_lock(&dist->lock);
 			vgic_irq_clear_queued(vcpu, vlr.irq);
 			WARN_ON(vlr.state & LR_STATE_MASK);
 			vlr.state = 0;
@@ -1124,6 +1297,17 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 			 */
 			vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
 
+			/*
+			 * kvm_notify_acked_irq calls kvm_set_irq()
+			 * to reset the IRQ level. Need to release the
+			 * lock for kvm_set_irq to grab it.
+			 */
+			spin_unlock(&dist->lock);
+
+			kvm_notify_acked_irq(kvm, 0,
+					     vlr.irq - VGIC_NR_PRIVATE_IRQS);
+			spin_lock(&dist->lock);
+
 			/* Any additional pending interrupt? */
 			if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
 				vgic_cpu_irq_set(vcpu, vlr.irq);
@@ -1133,6 +1317,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 				vgic_cpu_irq_clear(vcpu, vlr.irq);
 			}
 
+			spin_unlock(&dist->lock);
+
 			/*
 			 * Despite being EOIed, the LR may not have
 			 * been marked as empty.
@@ -1155,10 +1341,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 	return level_pending;
 }
 
-/*
- * Sync back the VGIC state after a guest run. The distributor lock is
- * needed so we don't get preempted in the middle of the state processing.
- */
+/* Sync back the VGIC state after a guest run */
 static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
@@ -1205,14 +1388,10 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return;
 
-	spin_lock(&dist->lock);
 	__kvm_vgic_sync_hwstate(vcpu);
-	spin_unlock(&dist->lock);
 }
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
@@ -1225,6 +1404,17 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
+int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return 0;
+
+	return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
+}
+
+
 void vgic_kick_vcpus(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
@@ -1397,8 +1587,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
 	kfree(vgic_cpu->pending_shared);
+	kfree(vgic_cpu->active_shared);
+	kfree(vgic_cpu->pend_act_shared);
 	kfree(vgic_cpu->vgic_irq_lr_map);
 	vgic_cpu->pending_shared = NULL;
+	vgic_cpu->active_shared = NULL;
+	vgic_cpu->pend_act_shared = NULL;
 	vgic_cpu->vgic_irq_lr_map = NULL;
 }
 
@@ -1408,9 +1602,14 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 
 	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
 	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
+	vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
+	vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
 	vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);
 
-	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
+	if (!vgic_cpu->pending_shared
+		|| !vgic_cpu->active_shared
+		|| !vgic_cpu->pend_act_shared
+		|| !vgic_cpu->vgic_irq_lr_map) {
 		kvm_vgic_vcpu_destroy(vcpu);
 		return -ENOMEM;
 	}
@@ -1463,10 +1662,12 @@ void kvm_vgic_destroy(struct kvm *kvm)
 	kfree(dist->irq_spi_mpidr);
 	kfree(dist->irq_spi_target);
 	kfree(dist->irq_pending_on_cpu);
+	kfree(dist->irq_active_on_cpu);
 	dist->irq_sgi_sources = NULL;
 	dist->irq_spi_cpu = NULL;
 	dist->irq_spi_target = NULL;
 	dist->irq_pending_on_cpu = NULL;
+	dist->irq_active_on_cpu = NULL;
 	dist->nr_cpus = 0;
 }
 
@@ -1502,6 +1703,7 @@ int vgic_init(struct kvm *kvm)
 	ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
 	ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
 	ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_active, nr_cpus, nr_irqs);
 	ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
 	ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
 
@@ -1514,10 +1716,13 @@ int vgic_init(struct kvm *kvm)
 				       GFP_KERNEL);
 	dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
 					   GFP_KERNEL);
+	dist->irq_active_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
+					   GFP_KERNEL);
 	if (!dist->irq_sgi_sources ||
 	    !dist->irq_spi_cpu ||
 	    !dist->irq_spi_target ||
-	    !dist->irq_pending_on_cpu) {
+	    !dist->irq_pending_on_cpu ||
+	    !dist->irq_active_on_cpu) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1845,12 +2050,9 @@ int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return r;
 }
 
-int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset)
+int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset)
 {
-	struct kvm_exit_mmio dev_attr_mmio;
-
-	dev_attr_mmio.len = 4;
-	if (vgic_find_range(ranges, &dev_attr_mmio, offset))
+	if (vgic_find_range(ranges, 4, offset))
 		return 0;
 	else
 		return -ENXIO;
@@ -1883,8 +2085,10 @@ static struct notifier_block vgic_cpu_nb = {
 };
 
 static const struct of_device_id vgic_ids[] = {
-	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
-	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+	{ .compatible = "arm,cortex-a15-gic",	.data = vgic_v2_probe, },
+	{ .compatible = "arm,cortex-a7-gic",	.data = vgic_v2_probe, },
+	{ .compatible = "arm,gic-400",		.data = vgic_v2_probe, },
+	{ .compatible = "arm,gic-v3",		.data = vgic_v3_probe, },
 	{},
 };
 
@@ -1932,3 +2136,38 @@ out_free_irq:
 	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
 	return ret;
 }
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries,
+		    int gsi)
+{
+	return gsi;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+	return pin;
+}
+
+int kvm_set_irq(struct kvm *kvm, int irq_source_id,
+		u32 irq, int level, bool line_status)
+{
+	unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	BUG_ON(!vgic_initialized(kvm));
+
+	if (spi > kvm->arch.vgic.nr_irqs)
+		return -EINVAL;
+	return kvm_vgic_inject_irq(kvm, 0, spi, level);
+
+}
+
+/* MSI not implemented yet */
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id,
+		int level, bool line_status)
+{
+	return 0;
+}
diff --git a/virt/kvm/arm/vgic.h b/virt/kvm/arm/vgic.h
index 1e83bdf5f499..0df74cbb6200 100644
--- a/virt/kvm/arm/vgic.h
+++ b/virt/kvm/arm/vgic.h
@@ -20,6 +20,8 @@
 #ifndef __KVM_VGIC_H__
 #define __KVM_VGIC_H__
 
+#include <kvm/iodev.h>
+
 #define VGIC_ADDR_UNDEF		(-1)
 #define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)
 
@@ -57,6 +59,14 @@ void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq);
 void vgic_unqueue_irqs(struct kvm_vcpu *vcpu);
 
+struct kvm_exit_mmio {
+	phys_addr_t	phys_addr;
+	void		*data;
+	u32		len;
+	bool		is_write;
+	void		*private;
+};
+
 void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
 		     phys_addr_t offset, int mode);
 bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
@@ -74,7 +84,7 @@ void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
 	*((u32 *)mmio->data) = cpu_to_le32(value) & mask;
 }
 
-struct kvm_mmio_range {
+struct vgic_io_range {
 	phys_addr_t base;
 	unsigned long len;
 	int bits_per_irq;
@@ -82,6 +92,11 @@ struct kvm_mmio_range {
 			    phys_addr_t offset);
 };
 
+int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
+			     const struct vgic_io_range *ranges,
+			     int redist_id,
+			     struct vgic_io_device *iodev);
+
 static inline bool is_in_range(phys_addr_t addr, unsigned long len,
 			       phys_addr_t baseaddr, unsigned long size)
 {
@@ -89,14 +104,8 @@ static inline bool is_in_range(phys_addr_t addr, unsigned long len,
 }
 
 const
-struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset);
-
-bool vgic_handle_mmio_range(struct kvm_vcpu *vcpu, struct kvm_run *run,
-			    struct kvm_exit_mmio *mmio,
-			    const struct kvm_mmio_range *ranges,
-			    unsigned long mmio_base);
+struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
+				      int len, gpa_t offset);
 
 bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
 			    phys_addr_t offset, int vcpu_id, int access);
@@ -107,12 +116,20 @@ bool vgic_handle_set_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
 bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
 				   phys_addr_t offset, int vcpu_id);
 
+bool vgic_handle_set_active_reg(struct kvm *kvm,
+				struct kvm_exit_mmio *mmio,
+				phys_addr_t offset, int vcpu_id);
+
+bool vgic_handle_clear_active_reg(struct kvm *kvm,
+				  struct kvm_exit_mmio *mmio,
+				  phys_addr_t offset, int vcpu_id);
+
 bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
 			 phys_addr_t offset);
 
 void vgic_kick_vcpus(struct kvm *kvm);
 
-int vgic_has_attr_regs(const struct kvm_mmio_range *ranges, phys_addr_t offset);
+int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset);
 int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
 int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
 
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 00d86427af0f..571c1ce37d15 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -8,7 +8,7 @@
  *
  */
 
-#include "iodev.h"
+#include <kvm/iodev.h>
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
@@ -60,8 +60,9 @@ static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev)
 	return 1;
 }
 
-static int coalesced_mmio_write(struct kvm_io_device *this,
-				gpa_t addr, int len, const void *val)
+static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
+				struct kvm_io_device *this, gpa_t addr,
+				int len, const void *val)
 {
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 148b2392c762..9ff4193dfa49 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -36,7 +36,7 @@
 #include <linux/seqlock.h>
 #include <trace/events/kvm.h>
 
-#include "iodev.h"
+#include <kvm/iodev.h>
 
 #ifdef CONFIG_HAVE_KVM_IRQFD
 /*
@@ -311,6 +311,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	unsigned int events;
 	int idx;
 
+	if (!kvm_arch_intc_initialized(kvm))
+		return -EAGAIN;
+
 	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
 	if (!irqfd)
 		return -ENOMEM;
@@ -712,8 +715,8 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
 
 /* MMIO/PIO writes trigger an event if the addr/val match */
 static int
-ioeventfd_write(struct kvm_io_device *this, gpa_t addr, int len,
-		const void *val)
+ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr,
+		int len, const void *val)
 {
 	struct _ioeventfd *p = to_ioeventfd(this);
 
diff --git a/virt/kvm/iodev.h b/virt/kvm/iodev.h
deleted file mode 100644
index 12fd3caffd2b..000000000000
--- a/virt/kvm/iodev.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * 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 __KVM_IODEV_H__
-#define __KVM_IODEV_H__
-
-#include <linux/kvm_types.h>
-#include <asm/errno.h>
-
-struct kvm_io_device;
-
-/**
- * kvm_io_device_ops are called under kvm slots_lock.
- * read and write handlers return 0 if the transaction has been handled,
- * or non-zero to have it passed to the next device.
- **/
-struct kvm_io_device_ops {
-	int (*read)(struct kvm_io_device *this,
-		    gpa_t addr,
-		    int len,
-		    void *val);
-	int (*write)(struct kvm_io_device *this,
-		     gpa_t addr,
-		     int len,
-		     const void *val);
-	void (*destructor)(struct kvm_io_device *this);
-};
-
-
-struct kvm_io_device {
-	const struct kvm_io_device_ops *ops;
-};
-
-static inline void kvm_iodevice_init(struct kvm_io_device *dev,
-				     const struct kvm_io_device_ops *ops)
-{
-	dev->ops = ops;
-}
-
-static inline int kvm_iodevice_read(struct kvm_io_device *dev,
-				    gpa_t addr, int l, void *v)
-{
-	return dev->ops->read ? dev->ops->read(dev, addr, l, v) : -EOPNOTSUPP;
-}
-
-static inline int kvm_iodevice_write(struct kvm_io_device *dev,
-				     gpa_t addr, int l, const void *v)
-{
-	return dev->ops->write ? dev->ops->write(dev, addr, l, v) : -EOPNOTSUPP;
-}
-
-static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
-{
-	if (dev->ops->destructor)
-		dev->ops->destructor(dev);
-}
-
-#endif /* __KVM_IODEV_H__ */
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 7f256f31df10..1d56a901e791 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -105,7 +105,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 	i = kvm_irq_map_gsi(kvm, irq_set, irq);
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 
-	while(i--) {
+	while (i--) {
 		int r;
 		r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level,
 				   line_status);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cc6a25d95fbf..d3fc9399062a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -16,7 +16,7 @@
  *
  */
 
-#include "iodev.h"
+#include <kvm/iodev.h>
 
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
@@ -66,13 +66,13 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-unsigned int halt_poll_ns = 0;
+static unsigned int halt_poll_ns;
 module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
 
 /*
  * Ordering of locks:
  *
- * 		kvm->lock --> kvm->slots_lock --> kvm->irq_lock
+ *	kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
 DEFINE_SPINLOCK(kvm_lock);
@@ -80,7 +80,7 @@ static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
 static cpumask_var_t cpus_hardware_enabled;
-static int kvm_usage_count = 0;
+static int kvm_usage_count;
 static atomic_t hardware_enable_failed;
 
 struct kmem_cache *kvm_vcpu_cache;
@@ -539,20 +539,12 @@ void *kvm_kvzalloc(unsigned long size)
 		return kzalloc(size, GFP_KERNEL);
 }
 
-void kvm_kvfree(const void *addr)
-{
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
-}
-
 static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
 	if (!memslot->dirty_bitmap)
 		return;
 
-	kvm_kvfree(memslot->dirty_bitmap);
+	kvfree(memslot->dirty_bitmap);
 	memslot->dirty_bitmap = NULL;
 }
 
@@ -888,8 +880,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		 * or moved, memslot will be created.
 		 *
 		 * validation of sp->gfn happens in:
-		 * 	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
-		 * 	- kvm_is_visible_gfn (mmu_check_roots)
+		 *	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
+		 *	- kvm_is_visible_gfn (mmu_check_roots)
 		 */
 		kvm_arch_flush_shadow_memslot(kvm, slot);
 
@@ -1061,9 +1053,11 @@ int kvm_get_dirty_log_protect(struct kvm *kvm,
 		mask = xchg(&dirty_bitmap[i], 0);
 		dirty_bitmap_buffer[i] = mask;
 
-		offset = i * BITS_PER_LONG;
-		kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset,
-								mask);
+		if (mask) {
+			offset = i * BITS_PER_LONG;
+			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
+								offset, mask);
+		}
 	}
 
 	spin_unlock(&kvm->mmu_lock);
@@ -1193,16 +1187,6 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
 	return gfn_to_hva_memslot_prot(slot, gfn, writable);
 }
 
-static int kvm_read_hva(void *data, void __user *hva, int len)
-{
-	return __copy_from_user(data, hva, len);
-}
-
-static int kvm_read_hva_atomic(void *data, void __user *hva, int len)
-{
-	return __copy_from_user_inatomic(data, hva, len);
-}
-
 static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
 	unsigned long start, int write, struct page **page)
 {
@@ -1481,7 +1465,6 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 
 	return kvm_pfn_to_page(pfn);
 }
-
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
@@ -1517,6 +1500,7 @@ void kvm_set_pfn_dirty(pfn_t pfn)
 {
 	if (!kvm_is_reserved_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
+
 		if (!PageReserved(page))
 			SetPageDirty(page);
 	}
@@ -1554,7 +1538,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 	addr = gfn_to_hva_prot(kvm, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = kvm_read_hva(data, (void __user *)addr + offset, len);
+	r = __copy_from_user(data, (void __user *)addr + offset, len);
 	if (r)
 		return -EFAULT;
 	return 0;
@@ -1593,7 +1577,7 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
 	pagefault_disable();
-	r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len);
+	r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
 	pagefault_enable();
 	if (r)
 		return -EFAULT;
@@ -1653,8 +1637,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	ghc->generation = slots->generation;
 	ghc->len = len;
 	ghc->memslot = gfn_to_memslot(kvm, start_gfn);
-	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
-	if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
+	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL);
+	if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) {
 		ghc->hva += offset;
 	} else {
 		/*
@@ -1742,7 +1726,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 	int offset = offset_in_page(gpa);
 	int ret;
 
-        while ((seg = next_segment(len, offset)) != 0) {
+	while ((seg = next_segment(len, offset)) != 0) {
 		ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
 		if (ret < 0)
 			return ret;
@@ -1800,6 +1784,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	start = cur = ktime_get();
 	if (halt_poll_ns) {
 		ktime_t stop = ktime_add_ns(ktime_get(), halt_poll_ns);
+
 		do {
 			/*
 			 * This sets KVM_REQ_UNHALT if an interrupt
@@ -2118,7 +2103,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
 	 * so vcpu_load() would break it.
 	 */
-	if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT)
+	if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT)
 		return kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 #endif
 
@@ -2135,6 +2120,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 			/* The thread running this VCPU changed. */
 			struct pid *oldpid = vcpu->pid;
 			struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
+
 			rcu_assign_pointer(vcpu->pid, newpid);
 			if (oldpid)
 				synchronize_rcu();
@@ -2205,7 +2191,7 @@ out_free1:
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(argp, &mp_state, sizeof mp_state))
+		if (copy_to_user(argp, &mp_state, sizeof(mp_state)))
 			goto out;
 		r = 0;
 		break;
@@ -2214,7 +2200,7 @@ out_free1:
 		struct kvm_mp_state mp_state;
 
 		r = -EFAULT;
-		if (copy_from_user(&mp_state, argp, sizeof mp_state))
+		if (copy_from_user(&mp_state, argp, sizeof(mp_state)))
 			goto out;
 		r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
 		break;
@@ -2223,13 +2209,13 @@ out_free1:
 		struct kvm_translation tr;
 
 		r = -EFAULT;
-		if (copy_from_user(&tr, argp, sizeof tr))
+		if (copy_from_user(&tr, argp, sizeof(tr)))
 			goto out;
 		r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(argp, &tr, sizeof tr))
+		if (copy_to_user(argp, &tr, sizeof(tr)))
 			goto out;
 		r = 0;
 		break;
@@ -2238,7 +2224,7 @@ out_free1:
 		struct kvm_guest_debug dbg;
 
 		r = -EFAULT;
-		if (copy_from_user(&dbg, argp, sizeof dbg))
+		if (copy_from_user(&dbg, argp, sizeof(dbg)))
 			goto out;
 		r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
 		break;
@@ -2252,14 +2238,14 @@ out_free1:
 		if (argp) {
 			r = -EFAULT;
 			if (copy_from_user(&kvm_sigmask, argp,
-					   sizeof kvm_sigmask))
+					   sizeof(kvm_sigmask)))
 				goto out;
 			r = -EINVAL;
-			if (kvm_sigmask.len != sizeof sigset)
+			if (kvm_sigmask.len != sizeof(sigset))
 				goto out;
 			r = -EFAULT;
 			if (copy_from_user(&sigset, sigmask_arg->sigset,
-					   sizeof sigset))
+					   sizeof(sigset)))
 				goto out;
 			p = &sigset;
 		}
@@ -2321,14 +2307,14 @@ static long kvm_vcpu_compat_ioctl(struct file *filp,
 		if (argp) {
 			r = -EFAULT;
 			if (copy_from_user(&kvm_sigmask, argp,
-					   sizeof kvm_sigmask))
+					   sizeof(kvm_sigmask)))
 				goto out;
 			r = -EINVAL;
-			if (kvm_sigmask.len != sizeof csigset)
+			if (kvm_sigmask.len != sizeof(csigset))
 				goto out;
 			r = -EFAULT;
 			if (copy_from_user(&csigset, sigmask_arg->sigset,
-					   sizeof csigset))
+					   sizeof(csigset)))
 				goto out;
 			sigset_from_compat(&sigset, &csigset);
 			r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
@@ -2525,7 +2511,7 @@ static long kvm_vm_ioctl(struct file *filp,
 
 		r = -EFAULT;
 		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof kvm_userspace_mem))
+						sizeof(kvm_userspace_mem)))
 			goto out;
 
 		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
@@ -2535,7 +2521,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		struct kvm_dirty_log log;
 
 		r = -EFAULT;
-		if (copy_from_user(&log, argp, sizeof log))
+		if (copy_from_user(&log, argp, sizeof(log)))
 			goto out;
 		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
 		break;
@@ -2543,16 +2529,18 @@ static long kvm_vm_ioctl(struct file *filp,
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	case KVM_REGISTER_COALESCED_MMIO: {
 		struct kvm_coalesced_mmio_zone zone;
+
 		r = -EFAULT;
-		if (copy_from_user(&zone, argp, sizeof zone))
+		if (copy_from_user(&zone, argp, sizeof(zone)))
 			goto out;
 		r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
 		break;
 	}
 	case KVM_UNREGISTER_COALESCED_MMIO: {
 		struct kvm_coalesced_mmio_zone zone;
+
 		r = -EFAULT;
-		if (copy_from_user(&zone, argp, sizeof zone))
+		if (copy_from_user(&zone, argp, sizeof(zone)))
 			goto out;
 		r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
 		break;
@@ -2562,7 +2550,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		struct kvm_irqfd data;
 
 		r = -EFAULT;
-		if (copy_from_user(&data, argp, sizeof data))
+		if (copy_from_user(&data, argp, sizeof(data)))
 			goto out;
 		r = kvm_irqfd(kvm, &data);
 		break;
@@ -2571,7 +2559,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		struct kvm_ioeventfd data;
 
 		r = -EFAULT;
-		if (copy_from_user(&data, argp, sizeof data))
+		if (copy_from_user(&data, argp, sizeof(data)))
 			goto out;
 		r = kvm_ioeventfd(kvm, &data);
 		break;
@@ -2592,7 +2580,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		struct kvm_msi msi;
 
 		r = -EFAULT;
-		if (copy_from_user(&msi, argp, sizeof msi))
+		if (copy_from_user(&msi, argp, sizeof(msi)))
 			goto out;
 		r = kvm_send_userspace_msi(kvm, &msi);
 		break;
@@ -2604,7 +2592,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		struct kvm_irq_level irq_event;
 
 		r = -EFAULT;
-		if (copy_from_user(&irq_event, argp, sizeof irq_event))
+		if (copy_from_user(&irq_event, argp, sizeof(irq_event)))
 			goto out;
 
 		r = kvm_vm_ioctl_irq_line(kvm, &irq_event,
@@ -2614,7 +2602,7 @@ static long kvm_vm_ioctl(struct file *filp,
 
 		r = -EFAULT;
 		if (ioctl == KVM_IRQ_LINE_STATUS) {
-			if (copy_to_user(argp, &irq_event, sizeof irq_event))
+			if (copy_to_user(argp, &irq_event, sizeof(irq_event)))
 				goto out;
 		}
 
@@ -2647,7 +2635,7 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out_free_irq_routing;
 		r = kvm_set_irq_routing(kvm, entries, routing.nr,
 					routing.flags);
-	out_free_irq_routing:
+out_free_irq_routing:
 		vfree(entries);
 		break;
 	}
@@ -2822,8 +2810,7 @@ static void hardware_enable_nolock(void *junk)
 	if (r) {
 		cpumask_clear_cpu(cpu, cpus_hardware_enabled);
 		atomic_inc(&hardware_enable_failed);
-		printk(KERN_INFO "kvm: enabling virtualization on "
-				 "CPU%d failed\n", cpu);
+		pr_info("kvm: enabling virtualization on CPU%d failed\n", cpu);
 	}
 }
 
@@ -2899,12 +2886,12 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	val &= ~CPU_TASKS_FROZEN;
 	switch (val) {
 	case CPU_DYING:
-		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
+		pr_info("kvm: disabling virtualization on CPU%d\n",
 		       cpu);
 		hardware_disable();
 		break;
 	case CPU_STARTING:
-		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
+		pr_info("kvm: enabling virtualization on CPU%d\n",
 		       cpu);
 		hardware_enable();
 		break;
@@ -2921,7 +2908,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 	 *
 	 * And Intel TXT required VMX off for all cpu when system shutdown.
 	 */
-	printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+	pr_info("kvm: exiting hardware virtualization\n");
 	kvm_rebooting = true;
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	return NOTIFY_OK;
@@ -2945,7 +2932,7 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 }
 
 static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
-                                 const struct kvm_io_range *r2)
+				 const struct kvm_io_range *r2)
 {
 	if (r1->addr < r2->addr)
 		return -1;
@@ -2998,7 +2985,7 @@ static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 	return off;
 }
 
-static int __kvm_io_bus_write(struct kvm_io_bus *bus,
+static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
 			      struct kvm_io_range *range, const void *val)
 {
 	int idx;
@@ -3009,7 +2996,7 @@ static int __kvm_io_bus_write(struct kvm_io_bus *bus,
 
 	while (idx < bus->dev_count &&
 		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_write(bus->range[idx].dev, range->addr,
+		if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr,
 					range->len, val))
 			return idx;
 		idx++;
@@ -3019,7 +3006,7 @@ static int __kvm_io_bus_write(struct kvm_io_bus *bus,
 }
 
 /* kvm_io_bus_write - called under kvm->slots_lock */
-int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
 	struct kvm_io_bus *bus;
@@ -3031,14 +3018,14 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		.len = len,
 	};
 
-	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	r = __kvm_io_bus_write(bus, &range, val);
+	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	r = __kvm_io_bus_write(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
 
 /* kvm_io_bus_write_cookie - called under kvm->slots_lock */
-int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
-			    int len, const void *val, long cookie)
+int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
+			    gpa_t addr, int len, const void *val, long cookie)
 {
 	struct kvm_io_bus *bus;
 	struct kvm_io_range range;
@@ -3048,12 +3035,12 @@ int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		.len = len,
 	};
 
-	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
 
 	/* First try the device referenced by cookie. */
 	if ((cookie >= 0) && (cookie < bus->dev_count) &&
 	    (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
-		if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len,
+		if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len,
 					val))
 			return cookie;
 
@@ -3061,11 +3048,11 @@ int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	 * cookie contained garbage; fall back to search and return the
 	 * correct cookie value.
 	 */
-	return __kvm_io_bus_write(bus, &range, val);
+	return __kvm_io_bus_write(vcpu, bus, &range, val);
 }
 
-static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
-			     void *val)
+static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
+			     struct kvm_io_range *range, void *val)
 {
 	int idx;
 
@@ -3075,7 +3062,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
 
 	while (idx < bus->dev_count &&
 		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_read(bus->range[idx].dev, range->addr,
+		if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr,
 				       range->len, val))
 			return idx;
 		idx++;
@@ -3086,7 +3073,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
 EXPORT_SYMBOL_GPL(kvm_io_bus_write);
 
 /* kvm_io_bus_read - called under kvm->slots_lock */
-int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val)
 {
 	struct kvm_io_bus *bus;
@@ -3098,8 +3085,8 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		.len = len,
 	};
 
-	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	r = __kvm_io_bus_read(bus, &range, val);
+	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	r = __kvm_io_bus_read(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
 
@@ -3269,6 +3256,7 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
 static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
 	if (vcpu->preempted)
 		vcpu->preempted = false;
 
@@ -3350,7 +3338,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	r = misc_register(&kvm_dev);
 	if (r) {
-		printk(KERN_ERR "kvm: misc device register failed\n");
+		pr_err("kvm: misc device register failed\n");
 		goto out_unreg;
 	}
 
@@ -3361,7 +3349,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	r = kvm_init_debug();
 	if (r) {
-		printk(KERN_ERR "kvm: create debugfs files failed\n");
+		pr_err("kvm: create debugfs files failed\n");
 		goto out_undebugfs;
 	}