Merge tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Gleb Natapov:
 "Highlights of the updates are:

  general:
   - new emulated device API
   - legacy device assignment is now optional
   - irqfd interface is more generic and can be shared between arches

  x86:
   - VMCS shadow support and other nested VMX improvements
   - APIC virtualization and Posted Interrupt hardware support
   - Optimize mmio spte zapping

  ppc:
    - BookE: in-kernel MPIC emulation with irqfd support
    - Book3S: in-kernel XICS emulation (incomplete)
    - Book3S: HV: migration fixes
    - BookE: more debug support preparation
    - BookE: e6500 support

  ARM:
   - reworking of Hyp idmaps

  s390:
   - ioeventfd for virtio-ccw

  And many other bug fixes, cleanups and improvements"

* tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  kvm: Add compat_ioctl for device control API
  KVM: x86: Account for failing enable_irq_window for NMI window request
  KVM: PPC: Book3S: Add API for in-kernel XICS emulation
  kvm/ppc/mpic: fix missing unlock in set_base_addr()
  kvm/ppc: Hold srcu lock when calling kvm_io_bus_read/write
  kvm/ppc/mpic: remove users
  kvm/ppc/mpic: fix mmio region lists when multiple guests used
  kvm/ppc/mpic: remove default routes from documentation
  kvm: KVM_CAP_IOMMU only available with device assignment
  ARM: KVM: iterate over all CPUs for CPU compatibility check
  KVM: ARM: Fix spelling in error message
  ARM: KVM: define KVM_ARM_MAX_VCPUS unconditionally
  KVM: ARM: Fix API documentation for ONE_REG encoding
  ARM: KVM: promote vfp_host pointer to generic host cpu context
  ARM: KVM: add architecture specific hook for capabilities
  ARM: KVM: perform HYP initilization for hotplugged CPUs
  ARM: KVM: switch to a dual-step HYP init code
  ARM: KVM: rework HYP page table freeing
  ARM: KVM: enforce maximum size for identity mapped code
  ARM: KVM: move to a KVM provided HYP idmap
  ...

8 files changed, 659 insertions, 340 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index d01b24b72c61..779262f59e25 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -6,6 +6,9 @@ config HAVE_KVM
 config HAVE_KVM_IRQCHIP
        bool
 
+config HAVE_KVM_IRQ_ROUTING
+       bool
+
 config HAVE_KVM_EVENTFD
        bool
        select EVENTFD
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 3642239252b0..8db43701016f 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -80,11 +80,12 @@ kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
 		spin_lock(&assigned_dev->intx_mask_lock);
 		if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
 			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id, vector, 1);
+				    assigned_dev->irq_source_id, vector, 1,
+				    false);
 		spin_unlock(&assigned_dev->intx_mask_lock);
 	} else
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-			    vector, 1);
+			    vector, 1, false);
 }
 
 static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
@@ -165,7 +166,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 		container_of(kian, struct kvm_assigned_dev_kernel,
 			     ack_notifier);
 
-	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
+	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false);
 
 	spin_lock(&dev->intx_mask_lock);
 
@@ -188,7 +189,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 
 		if (reassert)
 			kvm_set_irq(dev->kvm, dev->irq_source_id,
-				    dev->guest_irq, 1);
+				    dev->guest_irq, 1, false);
 	}
 
 	spin_unlock(&dev->intx_mask_lock);
@@ -202,7 +203,7 @@ static void deassign_guest_irq(struct kvm *kvm,
 						&assigned_dev->ack_notifier);
 
 	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-		    assigned_dev->guest_irq, 0);
+		    assigned_dev->guest_irq, 0, false);
 
 	if (assigned_dev->irq_source_id != -1)
 		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
@@ -901,7 +902,7 @@ static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
 	if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
 		if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) {
 			kvm_set_irq(match->kvm, match->irq_source_id,
-				    match->guest_irq, 0);
+				    match->guest_irq, 0, false);
 			/*
 			 * Masking at hardware-level is performed on demand,
 			 * i.e. when an IRQ actually arrives at the host.
@@ -982,36 +983,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#ifdef KVM_CAP_IRQ_ROUTING
-	case KVM_SET_GSI_ROUTING: {
-		struct kvm_irq_routing routing;
-		struct kvm_irq_routing __user *urouting;
-		struct kvm_irq_routing_entry *entries;
-
-		r = -EFAULT;
-		if (copy_from_user(&routing, argp, sizeof(routing)))
-			goto out;
-		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
-			goto out;
-		if (routing.flags)
-			goto out;
-		r = -ENOMEM;
-		entries = vmalloc(routing.nr * sizeof(*entries));
-		if (!entries)
-			goto out;
-		r = -EFAULT;
-		urouting = argp;
-		if (copy_from_user(entries, urouting->entries,
-				   routing.nr * sizeof(*entries)))
-			goto out_free_irq_routing;
-		r = kvm_set_irq_routing(kvm, entries, routing.nr,
-					routing.flags);
-	out_free_irq_routing:
-		vfree(entries);
-		break;
-	}
-#endif /* KVM_CAP_IRQ_ROUTING */
 #ifdef __KVM_HAVE_MSIX
 	case KVM_ASSIGN_SET_MSIX_NR: {
 		struct kvm_assigned_msix_nr entry_nr;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index adb17f266b28..64ee720b75c7 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -35,7 +35,7 @@
 
 #include "iodev.h"
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -100,11 +100,13 @@ irqfd_inject(struct work_struct *work)
 	struct kvm *kvm = irqfd->kvm;
 
 	if (!irqfd->resampler) {
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
-		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1,
+				false);
+		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0,
+				false);
 	} else
 		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-			    irqfd->gsi, 1);
+			    irqfd->gsi, 1, false);
 }
 
 /*
@@ -121,7 +123,7 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
 	resampler = container_of(kian, struct _irqfd_resampler, notifier);
 
 	kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-		    resampler->notifier.gsi, 0);
+		    resampler->notifier.gsi, 0, false);
 
 	rcu_read_lock();
 
@@ -146,7 +148,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd)
 		list_del(&resampler->link);
 		kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
 		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-			    resampler->notifier.gsi, 0);
+			    resampler->notifier.gsi, 0, false);
 		kfree(resampler);
 	}
 
@@ -225,7 +227,8 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 		irq = rcu_dereference(irqfd->irq_entry);
 		/* An event has been signaled, inject an interrupt */
 		if (irq)
-			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+					false);
 		else
 			schedule_work(&irqfd->inject);
 		rcu_read_unlock();
@@ -430,7 +433,7 @@ fail:
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -439,7 +442,7 @@ kvm_eventfd_init(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -543,7 +546,7 @@ void kvm_irq_routing_update(struct kvm *kvm,
  * aggregated from all vm* instances. We need our own isolated single-thread
  * queue to prevent deadlock against flushing the normal work-queue.
  */
-static int __init irqfd_module_init(void)
+int kvm_irqfd_init(void)
 {
 	irqfd_cleanup_wq = create_singlethread_workqueue("kvm-irqfd-cleanup");
 	if (!irqfd_cleanup_wq)
@@ -552,13 +555,10 @@ static int __init irqfd_module_init(void)
 	return 0;
 }
 
-static void __exit irqfd_module_exit(void)
+void kvm_irqfd_exit(void)
 {
 	destroy_workqueue(irqfd_cleanup_wq);
 }
-
-module_init(irqfd_module_init);
-module_exit(irqfd_module_exit);
 #endif
 
 /*
@@ -577,6 +577,7 @@ struct _ioeventfd {
 	struct eventfd_ctx  *eventfd;
 	u64                  datamatch;
 	struct kvm_io_device dev;
+	u8                   bus_idx;
 	bool                 wildcard;
 };
 
@@ -669,7 +670,8 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
 	struct _ioeventfd *_p;
 
 	list_for_each_entry(_p, &kvm->ioeventfds, list)
-		if (_p->addr == p->addr && _p->length == p->length &&
+		if (_p->bus_idx == p->bus_idx &&
+		    _p->addr == p->addr && _p->length == p->length &&
 		    (_p->wildcard || p->wildcard ||
 		     _p->datamatch == p->datamatch))
 			return true;
@@ -677,15 +679,24 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
 	return false;
 }
 
+static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags)
+{
+	if (flags & KVM_IOEVENTFD_FLAG_PIO)
+		return KVM_PIO_BUS;
+	if (flags & KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY)
+		return KVM_VIRTIO_CCW_NOTIFY_BUS;
+	return KVM_MMIO_BUS;
+}
+
 static int
 kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
-	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
-	enum kvm_bus              bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS;
+	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p;
 	struct eventfd_ctx       *eventfd;
 	int                       ret;
 
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	/* must be natural-word sized */
 	switch (args->len) {
 	case 1:
@@ -717,6 +728,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	INIT_LIST_HEAD(&p->list);
 	p->addr    = args->addr;
+	p->bus_idx = bus_idx;
 	p->length  = args->len;
 	p->eventfd = eventfd;
 
@@ -760,12 +772,12 @@ fail:
 static int
 kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
-	int                       pio = args->flags & KVM_IOEVENTFD_FLAG_PIO;
-	enum kvm_bus              bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS;
+	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
 	int                       ret = -ENOENT;
 
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
@@ -775,7 +787,8 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
 		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
 
-		if (p->eventfd != eventfd  ||
+		if (p->bus_idx != bus_idx ||
+		    p->eventfd != eventfd  ||
 		    p->addr != args->addr  ||
 		    p->length != args->len ||
 		    p->wildcard != wildcard)
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 5ba005c00e2f..2d682977ce82 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -50,7 +50,8 @@
 #else
 #define ioapic_debug(fmt, arg...)
 #endif
-static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq);
+static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq,
+		bool line_status);
 
 static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 					  unsigned long addr,
@@ -90,7 +91,80 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 	return result;
 }
 
-static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
+static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
+{
+	ioapic->rtc_status.pending_eoi = 0;
+	bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
+}
+
+static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+	bool new_val, old_val;
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	union kvm_ioapic_redirect_entry *e;
+
+	e = &ioapic->redirtbl[RTC_GSI];
+	if (!kvm_apic_match_dest(vcpu, NULL, 0,	e->fields.dest_id,
+				e->fields.dest_mode))
+		return;
+
+	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
+	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+
+	if (new_val == old_val)
+		return;
+
+	if (new_val) {
+		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi++;
+	} else {
+		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi--;
+	}
+
+	WARN_ON(ioapic->rtc_status.pending_eoi < 0);
+}
+
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+
+	spin_lock(&ioapic->lock);
+	__rtc_irq_eoi_tracking_restore_one(vcpu);
+	spin_unlock(&ioapic->lock);
+}
+
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	if (RTC_GSI >= IOAPIC_NUM_PINS)
+		return;
+
+	rtc_irq_eoi_tracking_reset(ioapic);
+	kvm_for_each_vcpu(i, vcpu, ioapic->kvm)
+	    __rtc_irq_eoi_tracking_restore_one(vcpu);
+}
+
+static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
+{
+	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map))
+		--ioapic->rtc_status.pending_eoi;
+
+	WARN_ON(ioapic->rtc_status.pending_eoi < 0);
+}
+
+static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
+{
+	if (ioapic->rtc_status.pending_eoi > 0)
+		return true; /* coalesced */
+
+	return false;
+}
+
+static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx,
+		bool line_status)
 {
 	union kvm_ioapic_redirect_entry *pent;
 	int injected = -1;
@@ -98,7 +172,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
 	pent = &ioapic->redirtbl[idx];
 
 	if (!pent->fields.mask) {
-		injected = ioapic_deliver(ioapic, idx);
+		injected = ioapic_deliver(ioapic, idx, line_status);
 		if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
 			pent->fields.remote_irr = 1;
 	}
@@ -119,41 +193,48 @@ static void update_handled_vectors(struct kvm_ioapic *ioapic)
 	smp_wmb();
 }
 
-void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
-					u64 *eoi_exit_bitmap)
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+			u32 *tmr)
 {
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
 	union kvm_ioapic_redirect_entry *e;
-	struct kvm_lapic_irq irqe;
 	int index;
 
 	spin_lock(&ioapic->lock);
-	/* traverse ioapic entry to set eoi exit bitmap*/
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
 		if (!e->fields.mask &&
 			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
 			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
-				 index))) {
-			irqe.dest_id = e->fields.dest_id;
-			irqe.vector = e->fields.vector;
-			irqe.dest_mode = e->fields.dest_mode;
-			irqe.delivery_mode = e->fields.delivery_mode << 8;
-			kvm_calculate_eoi_exitmap(vcpu, &irqe, eoi_exit_bitmap);
+				 index) || index == RTC_GSI)) {
+			if (kvm_apic_match_dest(vcpu, NULL, 0,
+				e->fields.dest_id, e->fields.dest_mode)) {
+				__set_bit(e->fields.vector,
+					(unsigned long *)eoi_exit_bitmap);
+				if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG)
+					__set_bit(e->fields.vector,
+						(unsigned long *)tmr);
+			}
 		}
 	}
 	spin_unlock(&ioapic->lock);
 }
-EXPORT_SYMBOL_GPL(kvm_ioapic_calculate_eoi_exitmap);
 
-void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm)
+#ifdef CONFIG_X86
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
-	if (!kvm_apic_vid_enabled(kvm) || !ioapic)
+	if (!ioapic)
 		return;
-	kvm_make_update_eoibitmap_request(kvm);
+	kvm_make_scan_ioapic_request(kvm);
 }
+#else
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
+{
+	return;
+}
+#endif
 
 static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
@@ -195,16 +276,17 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
-			ioapic_service(ioapic, index);
-		kvm_ioapic_make_eoibitmap_request(ioapic->kvm);
+			ioapic_service(ioapic, index, false);
+		kvm_vcpu_request_scan_ioapic(ioapic->kvm);
 		break;
 	}
 }
 
-static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
+static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 {
 	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
 	struct kvm_lapic_irq irqe;
+	int ret;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
@@ -220,11 +302,19 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	irqe.level = 1;
 	irqe.shorthand = 0;
 
-	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
+	if (irq == RTC_GSI && line_status) {
+		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
+				ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi = ret;
+	} else
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+
+	return ret;
 }
 
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
-		       int level)
+		       int level, bool line_status)
 {
 	u32 old_irr;
 	u32 mask = 1 << irq;
@@ -244,13 +334,20 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 		ret = 1;
 	} else {
 		int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+		if (irq == RTC_GSI && line_status &&
+			rtc_irq_check_coalesced(ioapic)) {
+			ret = 0; /* coalesced */
+			goto out;
+		}
 		ioapic->irr |= mask;
 		if ((edge && old_irr != ioapic->irr) ||
 		    (!edge && !entry.fields.remote_irr))
-			ret = ioapic_service(ioapic, irq);
+			ret = ioapic_service(ioapic, irq, line_status);
 		else
 			ret = 0; /* report coalesced interrupt */
 	}
+out:
 	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	spin_unlock(&ioapic->lock);
 
@@ -267,8 +364,8 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
 	spin_unlock(&ioapic->lock);
 }
 
-static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
-				     int trigger_mode)
+static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
+			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
 	int i;
 
@@ -278,6 +375,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 		if (ent->fields.vector != vector)
 			continue;
 
+		if (i == RTC_GSI)
+			rtc_irq_eoi(ioapic, vcpu);
 		/*
 		 * We are dropping lock while calling ack notifiers because ack
 		 * notifier callbacks for assigned devices call into IOAPIC
@@ -296,7 +395,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
 		if (!ent->fields.mask && (ioapic->irr & (1 << i)))
-			ioapic_service(ioapic, i);
+			ioapic_service(ioapic, i, false);
 	}
 }
 
@@ -307,12 +406,12 @@ bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
 	return test_bit(vector, ioapic->handled_vectors);
 }
 
-void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
 {
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
 
 	spin_lock(&ioapic->lock);
-	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
+	__kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode);
 	spin_unlock(&ioapic->lock);
 }
 
@@ -410,7 +509,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 		break;
 #ifdef	CONFIG_IA64
 	case IOAPIC_REG_EOI:
-		__kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG);
+		__kvm_ioapic_update_eoi(NULL, ioapic, data, IOAPIC_LEVEL_TRIG);
 		break;
 #endif
 
@@ -431,6 +530,7 @@ void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->ioregsel = 0;
 	ioapic->irr = 0;
 	ioapic->id = 0;
+	rtc_irq_eoi_tracking_reset(ioapic);
 	update_handled_vectors(ioapic);
 }
 
@@ -496,7 +596,8 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
 	spin_lock(&ioapic->lock);
 	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
 	update_handled_vectors(ioapic);
-	kvm_ioapic_make_eoibitmap_request(kvm);
+	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_rtc_eoi_tracking_restore_all(ioapic);
 	spin_unlock(&ioapic->lock);
 	return 0;
 }
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 0400a466c50c..615d8c995c3c 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -34,6 +34,17 @@ struct kvm_vcpu;
 #define	IOAPIC_INIT			0x5
 #define	IOAPIC_EXTINT			0x7
 
+#ifdef CONFIG_X86
+#define RTC_GSI 8
+#else
+#define RTC_GSI -1U
+#endif
+
+struct rtc_status {
+	int pending_eoi;
+	DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
+};
+
 struct kvm_ioapic {
 	u64 base_address;
 	u32 ioregsel;
@@ -47,6 +58,7 @@ struct kvm_ioapic {
 	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	DECLARE_BITMAP(handled_vectors, 256);
+	struct rtc_status rtc_status;
 };
 
 #ifdef DEBUG
@@ -67,24 +79,25 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 	return kvm->arch.vioapic;
 }
 
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
 int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 		int short_hand, int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
-void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
+			int trigger_mode);
 bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
 int kvm_ioapic_init(struct kvm *kvm);
 void kvm_ioapic_destroy(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
-		       int level);
+		       int level, bool line_status);
 void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq);
+		struct kvm_lapic_irq *irq, unsigned long *dest_map);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
-void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm);
-void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
-					u64 *eoi_exit_bitmap);
-
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+			u32 *tmr);
 
 #endif
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index e9073cf4d040..e2e6b4473a96 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -35,7 +35,8 @@
 #include "ioapic.h"
 
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
-			   struct kvm *kvm, int irq_source_id, int level)
+			   struct kvm *kvm, int irq_source_id, int level,
+			   bool line_status)
 {
 #ifdef CONFIG_X86
 	struct kvm_pic *pic = pic_irqchip(kvm);
@@ -46,10 +47,12 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 }
 
 static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
-			      struct kvm *kvm, int irq_source_id, int level)
+			      struct kvm *kvm, int irq_source_id, int level,
+			      bool line_status)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level);
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
+				line_status);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -63,7 +66,7 @@ inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
 }
 
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq)
+		struct kvm_lapic_irq *irq, unsigned long *dest_map)
 {
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
@@ -74,7 +77,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		irq->delivery_mode = APIC_DM_FIXED;
 	}
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r))
+	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
 		return r;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -88,7 +91,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		if (!kvm_is_dm_lowest_prio(irq)) {
 			if (r < 0)
 				r = 0;
-			r += kvm_apic_set_irq(vcpu, irq);
+			r += kvm_apic_set_irq(vcpu, irq, dest_map);
 		} else if (kvm_lapic_enabled(vcpu)) {
 			if (!lowest)
 				lowest = vcpu;
@@ -98,7 +101,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	}
 
 	if (lowest)
-		r = kvm_apic_set_irq(lowest, irq);
+		r = kvm_apic_set_irq(lowest, irq, dest_map);
 
 	return r;
 }
@@ -121,7 +124,7 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
 }
 
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		struct kvm *kvm, int irq_source_id, int level)
+		struct kvm *kvm, int irq_source_id, int level, bool line_status)
 {
 	struct kvm_lapic_irq irq;
 
@@ -130,7 +133,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 
 	kvm_set_msi_irq(e, &irq);
 
-	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
 
 
@@ -142,63 +145,12 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
 
 	kvm_set_msi_irq(e, &irq);
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
 		return r;
 	else
 		return -EWOULDBLOCK;
 }
 
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
-{
-	struct kvm_kernel_irq_routing_entry route;
-
-	if (!irqchip_in_kernel(kvm) || msi->flags != 0)
-		return -EINVAL;
-
-	route.msi.address_lo = msi->address_lo;
-	route.msi.address_hi = msi->address_hi;
-	route.msi.data = msi->data;
-
-	return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
-}
-
-/*
- * Return value:
- *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
- *  = 0   Interrupt was coalesced (previous irq is still pending)
- *  > 0   Number of CPUs interrupt was delivered to
- */
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
-{
-	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
-	int ret = -1, i = 0;
-	struct kvm_irq_routing_table *irq_rt;
-
-	trace_kvm_set_irq(irq, level, irq_source_id);
-
-	/* Not possible to detect if the guest uses the PIC or the
-	 * IOAPIC.  So set the bit in both. The guest will ignore
-	 * writes to the unused one.
-	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
-	if (irq < irq_rt->nr_rt_entries)
-		hlist_for_each_entry(e, &irq_rt->map[irq], link)
-			irq_set[i++] = *e;
-	rcu_read_unlock();
-
-	while(i--) {
-		int r;
-		r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level);
-		if (r < 0)
-			continue;
-
-		ret = r + ((ret < 0) ? 0 : ret);
-	}
-
-	return ret;
-}
-
 /*
  * Deliver an IRQ in an atomic context if we can, or return a failure,
  * user can retry in a process context.
@@ -236,63 +188,6 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	return ret;
 }
 
-bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
-	struct kvm_irq_ack_notifier *kian;
-	int gsi;
-
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
-	if (gsi != -1)
-		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
-					 link)
-			if (kian->gsi == gsi) {
-				rcu_read_unlock();
-				return true;
-			}
-
-	rcu_read_unlock();
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
-
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
-	struct kvm_irq_ack_notifier *kian;
-	int gsi;
-
-	trace_kvm_ack_irq(irqchip, pin);
-
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
-	if (gsi != -1)
-		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
-					 link)
-			if (kian->gsi == gsi)
-				kian->irq_acked(kian);
-	rcu_read_unlock();
-}
-
-void kvm_register_irq_ack_notifier(struct kvm *kvm,
-				   struct kvm_irq_ack_notifier *kian)
-{
-	mutex_lock(&kvm->irq_lock);
-	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
-	mutex_unlock(&kvm->irq_lock);
-	kvm_ioapic_make_eoibitmap_request(kvm);
-}
-
-void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
-				    struct kvm_irq_ack_notifier *kian)
-{
-	mutex_lock(&kvm->irq_lock);
-	hlist_del_init_rcu(&kian->link);
-	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
-	kvm_ioapic_make_eoibitmap_request(kvm);
-}
-
 int kvm_request_irq_source_id(struct kvm *kvm)
 {
 	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
@@ -376,34 +271,14 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	rcu_read_unlock();
 }
 
-void kvm_free_irq_routing(struct kvm *kvm)
-{
-	/* Called only during vm destruction. Nobody can use the pointer
-	   at this stage */
-	kfree(kvm->irq_routing);
-}
-
-static int setup_routing_entry(struct kvm_irq_routing_table *rt,
-			       struct kvm_kernel_irq_routing_entry *e,
-			       const struct kvm_irq_routing_entry *ue)
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+			  struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
 	int delta;
 	unsigned max_pin;
-	struct kvm_kernel_irq_routing_entry *ei;
 
-	/*
-	 * Do not allow GSI to be mapped to the same irqchip more than once.
-	 * Allow only one to one mapping between GSI and MSI.
-	 */
-	hlist_for_each_entry(ei, &rt->map[ue->gsi], link)
-		if (ei->type == KVM_IRQ_ROUTING_MSI ||
-		    ue->type == KVM_IRQ_ROUTING_MSI ||
-		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
-			return r;
-
-	e->gsi = ue->gsi;
-	e->type = ue->type;
 	switch (ue->type) {
 	case KVM_IRQ_ROUTING_IRQCHIP:
 		delta = 0;
@@ -440,69 +315,11 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
 		goto out;
 	}
 
-	hlist_add_head(&e->link, &rt->map[e->gsi]);
 	r = 0;
 out:
 	return r;
 }
 
-
-int kvm_set_irq_routing(struct kvm *kvm,
-			const struct kvm_irq_routing_entry *ue,
-			unsigned nr,
-			unsigned flags)
-{
-	struct kvm_irq_routing_table *new, *old;
-	u32 i, j, nr_rt_entries = 0;
-	int r;
-
-	for (i = 0; i < nr; ++i) {
-		if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES)
-			return -EINVAL;
-		nr_rt_entries = max(nr_rt_entries, ue[i].gsi);
-	}
-
-	nr_rt_entries += 1;
-
-	new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head))
-		      + (nr * sizeof(struct kvm_kernel_irq_routing_entry)),
-		      GFP_KERNEL);
-
-	if (!new)
-		return -ENOMEM;
-
-	new->rt_entries = (void *)&new->map[nr_rt_entries];
-
-	new->nr_rt_entries = nr_rt_entries;
-	for (i = 0; i < 3; i++)
-		for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++)
-			new->chip[i][j] = -1;
-
-	for (i = 0; i < nr; ++i) {
-		r = -EINVAL;
-		if (ue->flags)
-			goto out;
-		r = setup_routing_entry(new, &new->rt_entries[i], ue);
-		if (r)
-			goto out;
-		++ue;
-	}
-
-	mutex_lock(&kvm->irq_lock);
-	old = kvm->irq_routing;
-	kvm_irq_routing_update(kvm, new);
-	mutex_unlock(&kvm->irq_lock);
-
-	synchronize_rcu();
-
-	new = old;
-	r = 0;
-
-out:
-	kfree(new);
-	return r;
-}
-
 #define IOAPIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
 	  .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
new file mode 100644
index 000000000000..20dc9e4a8f6c
--- /dev/null
+++ b/virt/kvm/irqchip.c
@@ -0,0 +1,237 @@
+/*
+ * irqchip.c: Common API for in kernel interrupt controllers
+ * Copyright (c) 2007, Intel Corporation.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (c) 2013, Alexander Graf <agraf@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the impl