Merge tag 'kvm-arm-for-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into 'kvm-next'

KVM/ARM changes for v4.1:

- fixes for live migration
- irqfd support
- kvm-io-bus & vgic rework to enable ioeventfd
- page ageing for stage-2 translation
- various cleanups
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 6e54f35..98c95f2 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -85,13 +85,22 @@
 	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 @@
 	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 @@
 	 * 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 @@
 	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 @@
 		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 19c6210..1390797 100644
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ b/virt/kvm/arm/vgic-v2-emul.c
@@ -107,6 +107,22 @@
 					     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 @@
 		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 @@
 		.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 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 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 @@
 	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 @@
 	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 @@
 {
 	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 @@
  * 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 @@
 				 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 @@
 
 	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 @@
 	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 b3f1546..e9c3a7a 100644
--- a/virt/kvm/arm/vgic-v3-emul.c
+++ b/virt/kvm/arm/vgic-v3-emul.c
@@ -340,7 +340,7 @@
 	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 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)
@@ -570,113 +607,9 @@
 	return vgic_handle_cfg_reg(reg, mmio, offset);
 }
 
-static const struct kvm_mmio_range vgic_redist_sgi_ranges[] = {
-	{
-		.base		= GICR_IGROUPR0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_rao_wi,
-	},
-	{
-		.base		= GICR_ISENABLER0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_enable_reg_redist,
-	},
-	{
-		.base		= GICR_ICENABLER0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_enable_reg_redist,
-	},
-	{
-		.base		= GICR_ISPENDR0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_pending_reg_redist,
-	},
-	{
-		.base		= GICR_ICPENDR0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_pending_reg_redist,
-	},
-	{
-		.base		= GICR_ISACTIVER0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICR_ICACTIVER0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICR_IPRIORITYR0,
-		.len		= 0x20,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_priority_reg_redist,
-	},
-	{
-		.base		= GICR_ICFGR0,
-		.len		= 0x08,
-		.bits_per_irq	= 2,
-		.handle_mmio	= handle_mmio_cfg_reg_redist,
-	},
-	{
-		.base		= GICR_IGRPMODR0,
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICR_NSACR,
-		.len		= 0x04,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{},
-};
+#define SGI_base(x) ((x) + SZ_64K)
 
-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[] = {
+static const struct vgic_io_range vgic_redist_ranges[] = {
 	{
 		.base           = GICR_CTLR,
 		.len            = 0x04,
@@ -707,49 +640,74 @@
 		.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		= SGI_base(GICR_ISENABLER0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_set_enable_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_ICENABLER0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_clear_enable_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_ISPENDR0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_set_pending_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_ICPENDR0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_clear_pending_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_ISACTIVER0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_raz_wi,
+	},
+	{
+		.base		= SGI_base(GICR_ICACTIVER0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_raz_wi,
+	},
+	{
+		.base		= SGI_base(GICR_IPRIORITYR0),
+		.len		= 0x20,
+		.bits_per_irq	= 8,
+		.handle_mmio	= handle_mmio_priority_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_ICFGR0),
+		.len		= 0x08,
+		.bits_per_irq	= 2,
+		.handle_mmio	= handle_mmio_cfg_reg_redist,
+	},
+	{
+		.base		= SGI_base(GICR_IGRPMODR0),
+		.len		= 0x04,
+		.bits_per_irq	= 1,
+		.handle_mmio	= handle_mmio_raz_wi,
+	},
+	{
+		.base		= SGI_base(GICR_NSACR),
+		.len		= 0x04,
+		.handle_mmio	= handle_mmio_raz_wi,
+	},
 	{},
 };
 
-/*
- * 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 @@
 {
 	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 @@
 		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 @@
 {
 	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 c9f60f5..8d550ff 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 @@
 	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 @@
 	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 @@
 	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 @@
 }
 
 /**
- * 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 @@
 		 * 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 @@
 		 * 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 @@
 }
 
 const
-struct kvm_mmio_range *vgic_find_range(const struct kvm_mmio_range *ranges,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
+struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
+				      int len, gpa_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++;
+	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 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 @@
 	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;
 }
 
-/**
- * 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
- *
- * 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.
- */
-bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		      struct kvm_exit_mmio *mmio)
+static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu,
+				 struct kvm_io_device *this,
+				 gpa_t addr, int len, void *val)
 {
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return false;
+	return vgic_handle_mmio_access(vcpu, this, addr, len, val, false);
+}
 
-	/*
-	 * 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);
+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_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
+ *
+ * @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.
+ */
+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)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int ret;
+
+	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 @@
 	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 @@
 
 /*
  * 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 @@
 	}
 
 	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_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 @@
 		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 @@
 
 	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 @@
 {
 	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 @@
 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 @@
 			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 @@
 			 */
 			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 @@
 				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 @@
 	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_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 @@
 	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 @@
 	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 @@
 
 	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 @@
 	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 @@
 	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 @@
 				       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 @@
 	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 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 @@
 	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 1e83bdf..0df74cb 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 @@
 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 @@
 	*((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 @@
 			    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 @@
 }
 
 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_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);