Merge commit 'origin/master' into next

Conflicts:
	include/linux/kvm.h

6 files changed, 1167 insertions, 930 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
new file mode 100644
index 00000000000..fd9c097b760
--- /dev/null
+++ b/virt/kvm/assigned-dev.c
@@ -0,0 +1,818 @@
+/*
+ * Kernel-based Virtual Machine - device assignment support
+ *
+ * Copyright (C) 2006-9 Red Hat, Inc
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include "irq.h"
+
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+						      int assigned_dev_id)
+{
+	struct list_head *ptr;
+	struct kvm_assigned_dev_kernel *match;
+
+	list_for_each(ptr, head) {
+		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+		if (match->assigned_dev_id == assigned_dev_id)
+			return match;
+	}
+	return NULL;
+}
+
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+				    *assigned_dev, int irq)
+{
+	int i, index;
+	struct msix_entry *host_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+
+	index = -1;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (irq == host_msix_entries[i].vector) {
+			index = i;
+			break;
+		}
+	if (index < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+		return 0;
+	}
+
+	return index;
+}
+
+static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev;
+	struct kvm *kvm;
+	int i;
+
+	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
+				    interrupt_work);
+	kvm = assigned_dev->kvm;
+
+	spin_lock_irq(&assigned_dev->assigned_dev_lock);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		struct kvm_guest_msix_entry *guest_entries =
+			assigned_dev->guest_msix_entries;
+		for (i = 0; i < assigned_dev->entries_nr; i++) {
+			if (!(guest_entries[i].flags &
+					KVM_ASSIGNED_MSIX_PENDING))
+				continue;
+			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+			kvm_set_irq(assigned_dev->kvm,
+				    assigned_dev->irq_source_id,
+				    guest_entries[i].vector, 1);
+		}
+	} else
+		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+			    assigned_dev->guest_irq, 1);
+
+	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
+}
+
+static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
+{
+	unsigned long flags;
+	struct kvm_assigned_dev_kernel *assigned_dev =
+		(struct kvm_assigned_dev_kernel *) dev_id;
+
+	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int index = find_index_from_host_irq(assigned_dev, irq);
+		if (index < 0)
+			goto out;
+		assigned_dev->guest_msix_entries[index].flags |=
+			KVM_ASSIGNED_MSIX_PENDING;
+	}
+
+	schedule_work(&assigned_dev->interrupt_work);
+
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
+		disable_irq_nosync(irq);
+		assigned_dev->host_irq_disabled = true;
+	}
+
+out:
+	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
+	return IRQ_HANDLED;
+}
+
+/* Ack the irq line for an assigned device */
+static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+	struct kvm_assigned_dev_kernel *dev;
+	unsigned long flags;
+
+	if (kian->gsi == -1)
+		return;
+
+	dev = container_of(kian, struct kvm_assigned_dev_kernel,
+			   ack_notifier);
+
+	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
+
+	/* The guest irq may be shared so this ack may be
+	 * from another device.
+	 */
+	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
+	if (dev->host_irq_disabled) {
+		enable_irq(dev->host_irq);
+		dev->host_irq_disabled = false;
+	}
+	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
+}
+
+static void deassign_guest_irq(struct kvm *kvm,
+			       struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
+	assigned_dev->ack_notifier.gsi = -1;
+
+	if (assigned_dev->irq_source_id != -1)
+		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+	assigned_dev->irq_source_id = -1;
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
+
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+			      struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	/*
+	 * In kvm_free_device_irq, cancel_work_sync return true if:
+	 * 1. work is scheduled, and then cancelled.
+	 * 2. work callback is executed.
+	 *
+	 * The first one ensured that the irq is disabled and no more events
+	 * would happen. But for the second one, the irq may be enabled (e.g.
+	 * for MSI). So we disable irq here to prevent further events.
+	 *
+	 * Notice this maybe result in nested disable if the interrupt type is
+	 * INTx, but it's OK for we are going to free it.
+	 *
+	 * If this function is a part of VM destroy, please ensure that till
+	 * now, the kvm state is still legal for probably we also have to wait
+	 * interrupt_work done.
+	 */
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int i;
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			disable_irq_nosync(assigned_dev->
+					   host_msix_entries[i].vector);
+
+		cancel_work_sync(&assigned_dev->interrupt_work);
+
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			free_irq(assigned_dev->host_msix_entries[i].vector,
+				 (void *)assigned_dev);
+
+		assigned_dev->entries_nr = 0;
+		kfree(assigned_dev->host_msix_entries);
+		kfree(assigned_dev->guest_msix_entries);
+		pci_disable_msix(assigned_dev->dev);
+	} else {
+		/* Deal with MSI and INTx */
+		disable_irq_nosync(assigned_dev->host_irq);
+		cancel_work_sync(&assigned_dev->interrupt_work);
+
+		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+
+		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
+			pci_disable_msi(assigned_dev->dev);
+	}
+
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
+}
+
+static int kvm_deassign_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *assigned_dev,
+			    unsigned long irq_requested_type)
+{
+	unsigned long guest_irq_type, host_irq_type;
+
+	if (!irqchip_in_kernel(kvm))
+		return -EINVAL;
+	/* no irq assignment to deassign */
+	if (!assigned_dev->irq_requested_type)
+		return -ENXIO;
+
+	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+	if (host_irq_type)
+		deassign_host_irq(kvm, assigned_dev);
+	if (guest_irq_type)
+		deassign_guest_irq(kvm, assigned_dev);
+
+	return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+				  struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
+
+static void kvm_free_assigned_device(struct kvm *kvm,
+				     struct kvm_assigned_dev_kernel
+				     *assigned_dev)
+{
+	kvm_free_assigned_irq(kvm, assigned_dev);
+
+	pci_reset_function(assigned_dev->dev);
+
+	pci_release_regions(assigned_dev->dev);
+	pci_disable_device(assigned_dev->dev);
+	pci_dev_put(assigned_dev->dev);
+
+	list_del(&assigned_dev->list);
+	kfree(assigned_dev);
+}
+
+void kvm_free_all_assigned_devices(struct kvm *kvm)
+{
+	struct list_head *ptr, *ptr2;
+	struct kvm_assigned_dev_kernel *assigned_dev;
+
+	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
+		assigned_dev = list_entry(ptr,
+					  struct kvm_assigned_dev_kernel,
+					  list);
+
+		kvm_free_assigned_device(kvm, assigned_dev);
+	}
+}
+
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
+{
+	dev->host_irq = dev->dev->irq;
+	/* Even though this is PCI, we don't want to use shared
+	 * interrupts. Sharing host devices with guest-assigned devices
+	 * on the same interrupt line is not a happy situation: there
+	 * are going to be long delays in accepting, acking, etc.
+	 */
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
+			0, "kvm_assigned_intx_device", (void *)dev))
+		return -EIO;
+	return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+					   struct kvm_assigned_dev_kernel *dev)
+{
+	int r;
+
+	if (!dev->dev->msi_enabled) {
+		r = pci_enable_msi(dev->dev);
+		if (r)
+			return r;
+	}
+
+	dev->host_irq = dev->dev->irq;
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
+			"kvm_assigned_msi_device", (void *)dev)) {
+		pci_disable_msi(dev->dev);
+		return -EIO;
+	}
+
+	return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
+{
+	int i, r = -EINVAL;
+
+	/* host_msix_entries and guest_msix_entries should have been
+	 * initialized */
+	if (dev->entries_nr == 0)
+		return r;
+
+	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+	if (r)
+		return r;
+
+	for (i = 0; i < dev->entries_nr; i++) {
+		r = request_irq(dev->host_msix_entries[i].vector,
+				kvm_assigned_dev_intr, 0,
+				"kvm_assigned_msix_device",
+				(void *)dev);
+		/* FIXME: free requested_irq's on failure */
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+				struct kvm_assigned_dev_kernel *dev,
+				struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = irq->guest_irq;
+	return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
+	return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
+	return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+			   struct kvm_assigned_dev_kernel *dev,
+			   __u32 host_irq_type)
+{
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+		return r;
+
+	switch (host_irq_type) {
+	case KVM_DEV_IRQ_HOST_INTX:
+		r = assigned_device_enable_host_intx(kvm, dev);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_HOST_MSI:
+		r = assigned_device_enable_host_msi(kvm, dev);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_HOST_MSIX:
+		r = assigned_device_enable_host_msix(kvm, dev);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+
+	if (!r)
+		dev->irq_requested_type |= host_irq_type;
+
+	return r;
+}
+
+static int assign_guest_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *dev,
+			    struct kvm_assigned_irq *irq,
+			    unsigned long guest_irq_type)
+{
+	int id;
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+		return r;
+
+	id = kvm_request_irq_source_id(kvm);
+	if (id < 0)
+		return id;
+
+	dev->irq_source_id = id;
+
+	switch (guest_irq_type) {
+	case KVM_DEV_IRQ_GUEST_INTX:
+		r = assigned_device_enable_guest_intx(kvm, dev, irq);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_GUEST_MSI:
+		r = assigned_device_enable_guest_msi(kvm, dev, irq);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_GUEST_MSIX:
+		r = assigned_device_enable_guest_msix(kvm, dev, irq);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+
+	if (!r) {
+		dev->irq_requested_type |= guest_irq_type;
+		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+	} else
+		kvm_free_irq_source_id(kvm, dev->irq_source_id);
+
+	return r;
+}
+
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+				   struct kvm_assigned_irq *assigned_irq)
+{
+	int r = -EINVAL;
+	struct kvm_assigned_dev_kernel *match;
+	unsigned long host_irq_type, guest_irq_type;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (!irqchip_in_kernel(kvm))
+		return r;
+
+	mutex_lock(&kvm->lock);
+	r = -ENODEV;
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
+
+	r = -EINVAL;
+	/* can only assign one type at a time */
+	if (hweight_long(host_irq_type) > 1)
+		goto out;
+	if (hweight_long(guest_irq_type) > 1)
+		goto out;
+	if (host_irq_type == 0 && guest_irq_type == 0)
+		goto out;
+
+	r = 0;
+	if (host_irq_type)
+		r = assign_host_irq(kvm, match, host_irq_type);
+	if (r)
+		goto out;
+
+	if (guest_irq_type)
+		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+					 struct kvm_assigned_irq
+					 *assigned_irq)
+{
+	int r = -ENODEV;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
+				      struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+	struct pci_dev *dev;
+
+	down_read(&kvm->slots_lock);
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (match) {
+		/* device already assigned */
+		r = -EEXIST;
+		goto out;
+	}
+
+	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
+	if (match == NULL) {
+		printk(KERN_INFO "%s: Couldn't allocate memory\n",
+		       __func__);
+		r = -ENOMEM;
+		goto out;
+	}
+	dev = pci_get_bus_and_slot(assigned_dev->busnr,
+				   assigned_dev->devfn);
+	if (!dev) {
+		printk(KERN_INFO "%s: host device not found\n", __func__);
+		r = -EINVAL;
+		goto out_free;
+	}
+	if (pci_enable_device(dev)) {
+		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
+		r = -EBUSY;
+		goto out_put;
+	}
+	r = pci_request_regions(dev, "kvm_assigned_device");
+	if (r) {
+		printk(KERN_INFO "%s: Could not get access to device regions\n",
+		       __func__);
+		goto out_disable;
+	}
+
+	pci_reset_function(dev);
+
+	match->assigned_dev_id = assigned_dev->assigned_dev_id;
+	match->host_busnr = assigned_dev->busnr;
+	match->host_devfn = assigned_dev->devfn;
+	match->flags = assigned_dev->flags;
+	match->dev = dev;
+	spin_lock_init(&match->assigned_dev_lock);
+	match->irq_source_id = -1;
+	match->kvm = kvm;
+	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+	INIT_WORK(&match->interrupt_work,
+		  kvm_assigned_dev_interrupt_work_handler);
+
+	list_add(&match->list, &kvm->arch.assigned_dev_head);
+
+	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
+		if (!kvm->arch.iommu_domain) {
+			r = kvm_iommu_map_guest(kvm);
+			if (r)
+				goto out_list_del;
+		}
+		r = kvm_assign_device(kvm, match);
+		if (r)
+			goto out_list_del;
+	}
+
+out:
+	mutex_unlock(&kvm->lock);
+	up_read(&kvm->slots_lock);
+	return r;
+out_list_del:
+	list_del(&match->list);
+	pci_release_regions(dev);
+out_disable:
+	pci_disable_device(dev);
+out_put:
+	pci_dev_put(dev);
+out_free:
+	kfree(match);
+	mutex_unlock(&kvm->lock);
+	up_read(&kvm->slots_lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
+		struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (!match) {
+		printk(KERN_INFO "%s: device hasn't been assigned before, "
+		  "so cannot be deassigned\n", __func__);
+		r = -EINVAL;
+		goto out;
+	}
+
+	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
+		kvm_deassign_device(kvm, match);
+
+	kvm_free_assigned_device(kvm, match);
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+				    struct kvm_assigned_msix_nr *entry_nr)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry_nr->assigned_dev_id);
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_nr_out;
+	}
+
+	if (adev->entries_nr == 0) {
+		adev->entries_nr = entry_nr->entry_nr;
+		if (adev->entries_nr == 0 ||
+		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+			r = -EINVAL;
+			goto msix_nr_out;
+		}
+
+		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+						entry_nr->entry_nr,
+						GFP_KERNEL);
+		if (!adev->host_msix_entries) {
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+		adev->guest_msix_entries = kzalloc(
+				sizeof(struct kvm_guest_msix_entry) *
+				entry_nr->entry_nr, GFP_KERNEL);
+		if (!adev->guest_msix_entries) {
+			kfree(adev->host_msix_entries);
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+	} else /* Not allowed set MSI-X number twice */
+		r = -EINVAL;
+msix_nr_out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+				       struct kvm_assigned_msix_entry *entry)
+{
+	int r = 0, i;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry->assigned_dev_id);
+
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_entry_out;
+	}
+
+	for (i = 0; i < adev->entries_nr; i++)
+		if (adev->guest_msix_entries[i].vector == 0 ||
+		    adev->guest_msix_entries[i].entry == entry->entry) {
+			adev->guest_msix_entries[i].entry = entry->entry;
+			adev->guest_msix_entries[i].vector = entry->gsi;
+			adev->host_msix_entries[i].entry = entry->entry;
+			break;
+		}
+	if (i == adev->entries_nr) {
+		r = -ENOSPC;
+		goto msix_entry_out;
+	}
+
+msix_entry_out:
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+#endif
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+				  unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	int r = -ENOTTY;
+
+	switch (ioctl) {
+	case KVM_ASSIGN_PCI_DEVICE: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_IRQ: {
+		r = -EOPNOTSUPP;
+		break;
+	}
+#ifdef KVM_CAP_ASSIGN_DEV_IRQ
+	case KVM_ASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_DEASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
+#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
+	case KVM_DEASSIGN_PCI_DEVICE: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
+#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;
+		r = -EFAULT;
+		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_SET_MSIX_ENTRY: {
+		struct kvm_assigned_msix_entry entry;
+		r = -EFAULT;
+		if (copy_from_user(&entry, argp, sizeof entry))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
+	}
+out:
+	return r;
+}
+
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index bb4ebd89b9f..30f70fd511c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -61,10 +61,8 @@ irqfd_inject(struct work_struct *work)
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
 	struct kvm *kvm = irqfd->kvm;
 
-	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
-	mutex_unlock(&kvm->irq_lock);
 }
 
 /*
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 9fe140bb38e..38a2d20b89d 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -182,6 +182,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
+	mutex_lock(&ioapic->lock);
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
 		entry = ioapic->redirtbl[irq];
 		level ^= entry.fields.polarity;
@@ -198,34 +199,51 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 		}
 		trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	}
+	mutex_unlock(&ioapic->lock);
+
 	return ret;
 }
 
-static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin,
-				    int trigger_mode)
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
+				     int trigger_mode)
 {
-	union kvm_ioapic_redirect_entry *ent;
+	int i;
+
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
 
-	ent = &ioapic->redirtbl[pin];
+		if (ent->fields.vector != vector)
+			continue;
 
-	kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin);
+		/*
+		 * We are dropping lock while calling ack notifiers because ack
+		 * notifier callbacks for assigned devices call into IOAPIC
+		 * recursively. Since remote_irr is cleared only after call
+		 * to notifiers if the same vector will be delivered while lock
+		 * is dropped it will be put into irr and will be delivered
+		 * after ack notifier returns.
+		 */
+		mutex_unlock(&ioapic->lock);
+		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
+		mutex_lock(&ioapic->lock);
+
+		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+			continue;
 
-	if (trigger_mode == IOAPIC_LEVEL_TRIG) {
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
-		if (!ent->fields.mask && (ioapic->irr & (1 << pin)))
-			ioapic_service(ioapic, pin);
+		if (!ent->fields.mask && (ioapic->irr & (1 << i)))
+			ioapic_service(ioapic, i);
 	}
 }
 
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	int i;
 
-	for (i = 0; i < IOAPIC_NUM_PINS; i++)
-		if (ioapic->redirtbl[i].fields.vector == vector)
-			__kvm_ioapic_update_eoi(ioapic, i, trigger_mode);
+	mutex_lock(&ioapic->lock);
+	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
+	mutex_unlock(&ioapic->lock);
 }
 
 static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
@@ -250,8 +268,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
-	mutex_lock(&ioapic->kvm->irq_lock);
 	addr &= 0xff;
+	mutex_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		result = ioapic->ioregsel;
@@ -265,6 +283,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 		result = 0;
 		break;
 	}
+	mutex_unlock(&ioapic->lock);
+
 	switch (len) {
 	case 8:
 		*(u64 *) val = result;
@@ -277,7 +297,6 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
 	}
-	mutex_unlock(&ioapic->kvm->irq_lock);
 	return 0;
 }
 
@@ -293,15 +312,15 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
-	mutex_lock(&ioapic->kvm->irq_lock);
 	if (len == 4 || len == 8)
 		data = *(u32 *) val;
 	else {
 		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
-		goto unlock;
+		return 0;
 	}
 
 	addr &= 0xff;
+	mutex_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		ioapic->ioregsel = data;
@@ -312,15 +331,14 @@ 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->kvm, data, IOAPIC_LEVEL_TRIG);
+		__kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG);
 		break;
 #endif
 
 	default:
 		break;
 	}
-unlock:
-	mutex_unlock(&ioapic->kvm->irq_lock);
+	mutex_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -349,6 +367,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
 	if (!ioapic)
 		return -ENOMEM;
+	mutex_init(&ioapic->lock);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -360,3 +379,26 @@ int kvm_ioapic_init(struct kvm *kvm)
 	return ret;
 }
 
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	mutex_lock(&ioapic->lock);
+	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
+	mutex_unlock(&ioapic->lock);
+	return 0;
+}
+
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	mutex_lock(&ioapic->lock);
+	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
+	mutex_unlock(&ioapic->lock);
+	return 0;
+}
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 7080b713c16..419c43b667a 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -41,9 +41,11 @@ struct kvm_ioapic {
 	u32 irr;
 	u32 pad;
 	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
+	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
+	struct mutex lock;
 };
 
 #ifdef DEBUG
@@ -73,4 +75,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
 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);
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+
 #endif
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 001663ff401..9b077342ab5 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -31,20 +31,39 @@
 
 #include "ioapic.h"
 
+static inline int kvm_irq_line_state(unsigned long *irq_state,
+				     int irq_source_id, int level)
+{
+	/* Logical OR for level trig interrupt */
+	if (level)
+		set_bit(irq_source_id, irq_state);
+	else
+		clear_bit(irq_source_id, irq_state);
+
+	return !!(*irq_state);
+}
+
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
-			   struct kvm *kvm, int level)
+			   struct kvm *kvm, int irq_source_id, int level)
 {
 #ifdef CONFIG_X86
-	return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level);
+	struct kvm_pic *pic = pic_irqchip(kvm);
+	level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
+				   irq_source_id, level);
+	return kvm_pic_set_irq(pic, e->irqchip.pin, level);
 #else
 	return -1;
 #endif
 }
 
 static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
-			      struct kvm *kvm, int level)
+			      struct kvm *kvm, int irq_source_id, int level)
 {
-	return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
+				   irq_source_id, level);
+
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -63,8 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_is_dm_lowest_prio(irq))
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
@@ -96,10 +113,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 }
 
 static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		       struct kvm *kvm, int level)
+		       struct kvm *kvm, int irq_source_id, int level)
 {
 	struct kvm_lapic_irq irq;
 
+	if (!level)
+		return -1;
+
 	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
 
 	irq.dest_id = (e->msi.address_lo &
@@ -116,78 +136,67 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
-/* This should be called with the kvm->irq_lock mutex held
+/*
  * 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, int irq, int level)
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 {
-	struct kvm_kernel_irq_routing_entry *e;
-	unsigned long *irq_state, sig_level;
-	int ret = -1;
+	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
+	int ret = -1, i = 0;
+	struct kvm_irq_routing_table *irq_rt;
+	struct hlist_node *n;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
-	if (irq < KVM_IOAPIC_NUM_PINS) {
-		irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
-
-		/* Logical OR for level trig interrupt */
-		if (level)
-			set_bit(irq_source_id, irq_state);
-		else
-			clear_bit(irq_source_id, irq_state);
-		sig_level = !!(*irq_state);
-	} else if (!level)
-		return ret;
-	else /* Deal with MSI/MSI-X */
-		sig_level = 1;
-
 	/* 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.
 	 */
-	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->gsi == irq) {
-			int r = e->set(e, kvm, sig_level);
-			if (r < 0)
-				continue;
+	rcu_read_lock();
+	irq_rt = rcu_dereference(kvm->irq_routing);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, n, &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);
+	}
 
-			ret = r + ((ret < 0) ? 0 : ret);
-		}
 	return ret;
 }
 
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
-	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_ack_notifier *kian;
 	struct hlist_node *n;
-	unsigned gsi = pin;
+	int gsi;
 
 	trace_kvm_ack_irq(irqchip, pin);
 
-	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->type == KVM_IRQ_ROUTING_IRQCHIP &&
-		    e->irqchip.irqchip == irqchip &&
-		    e->irqchip.pin == pin) {
-			gsi = e->gsi;
-			break;
-		}
-
-	hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
-		if (kian->gsi == gsi)
-			kian->irq_acked(kian);
+	rcu_read_lock();
+	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kian, n, &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(&kian->link, &kvm->arch.irq_ack_notifier_list);
+	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -195,8 +204,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 				    struct kvm_irq_ack_notifier *kian)
 {
 	mutex_lock(&kvm->irq_lock);
-	hlist_del_init(&kian->link);
+	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -205,16 +215,17 @@ int kvm_request_irq_source_id(struct kvm *kvm)
 	int irq_source_id;
 
 	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap,
-				sizeof(kvm->arch.irq_sources_bitmap));
+	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
 
-	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	if (irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
-		return -EFAULT;
+		irq_source_id = -EFAULT;
+		goto unlock;
 	}
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 	set_bit(irq_source_id, bitmap);
+unlock:
 	mutex_unlock(&kvm->irq_lock);
 
 	return irq_source_id;
@@ -228,13 +239,23 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 
 	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
-	    irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	    irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
-		return;
+		goto unlock;
 	}
-	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
-		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	if (!irqchip_in_kernel(kvm))
+		goto unlock;
+
+	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
+		clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
+		if (i >= 16)
+			continue;
+#ifdef CONFIG_X86
+		clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
+#endif
+	}
+unlock:
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -243,7 +264,7 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 {
 	mutex_lock(&kvm->irq_lock);
 	kimn->irq = irq;
-	hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+	hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -251,8 +272,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn)
 {
 	mutex_lock(&kvm->irq_lock);
-	hlist_del(&kimn->link);
+	hlist_del_rcu(&kimn->link);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
@@ -260,33 +282,37 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
 	struct kvm_irq_mask_notifier *kimn;
 	struct hlist_node *n;
 
-	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
-
-	hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link)
 		if (kimn->irq == irq)
 			kimn->func(kimn, mask);
-}
-
-static void __kvm_free_irq_routing(struct list_head *irq_routing)
-{
-	struct kvm_kernel_irq_routing_entry *e, *n;
-
-	list_for_each_entry_safe(e, n, irq_routing, link)
-		kfree(e);
+	rcu_read_unlock();
 }
 
 void kvm_free_irq_routing(struct kvm *kvm)
 {
-	mutex_lock(&kvm->irq_lock);
-	__kvm_free_irq_routing(&kvm->irq_routing);
-	mutex_unlock(&kvm->irq_lock);
+	/* Called only during vm destruction. Nobody can use the pointer
+	   at this stage */
+	kfree(kvm->irq_routing);
 }
 
-static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+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 r = -EINVAL;
 	int delta;
+	struct kvm_kernel_irq_routing_entry *ei;
+	struct hlist_node *n;
+
+	/*
+	 * 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, n, &rt->map[ue->gsi], link)
+		if (ei->type == KVM_IRQ_ROUTING_MSI ||
+		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
+			return r;
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
@@ -309,6 +335,9 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 		}
 		e->irqchip.irqchip = ue->u.irqchip.irqchip;
 		e->irqchip.pin = ue->u.irqchip.pin + delta;
+		if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS)
+			goto out;
+		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
 		break;
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
@@ -319,6 +348,8 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 	default:
 		goto out;
 	}
+
+	hlist_add_head(&e->link, &rt->map[e->gsi]);
 	r = 0;
 out:
 	return r;
@@ -330,43 +361,53 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			unsigned nr,
 			unsigned flags)
 {
-	struct list_head irq_list = LIST_HEAD_INIT(irq_list);
-	struct list_head tmp = LIST_HEAD_INIT(tmp);
-	struct kvm_kernel_irq_routing_entry *e = NULL;
-	unsigned i;
+	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->gsi >= KVM_MAX_IRQ_ROUTES)
-			goto out;
 		if (ue->flags)
 			goto out;
-		r = -ENOMEM;
-		e = kzalloc(sizeof(*e), GFP_KERNEL);
-		if (!e)
-			goto out;
-		r = setup_routing_entry(e, ue);
+		r = setup_routing_entry(new, &new->rt_entries[i], ue);
 		if (r)
 			goto out;
 		++ue;
-		list_add(&e->link, &irq_list);
-		e = NULL;
 	}
 
 	mutex_lock(&kvm->irq_lock);
-	list_splice(&kvm->irq_routing, &tmp);
-	INIT_LIST_HEAD(&kvm->irq_routing);
-	list_splice(&irq_list, &kvm->irq_routing);
-	INIT_LIST_HEAD(&irq_list);
-	list_splice(&tmp, &irq_list);
+	old = kvm->irq_routing;
+	rcu_assign_pointer(kvm->irq_routing, new);
 	mutex_unlock(&kvm->irq_lock);
+	synchronize_rcu();
 
+	new = old;
 	r = 0;
 
 out:
-	kfree(e);
-	__kvm_free_irq_routing(&irq_list);
+	kfree(new);
 	return r;
 }
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cdca63917e7..e1f2bf8d7b1 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -43,6 +43,7 @@
 #include <linux/swap.h>
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
+#include <linux/compat.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -54,12 +55,6 @@
 #include "coalesced_mmio.h"
 #endif
 
-#ifdef KVM_CAP_DEVICE_ASSIGNMENT
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include "irq.h"
-#endif
-
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
@@ -76,6 +71,8 @@ DEFINE_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 
 static cpumask_var_t cpus_hardware_enabled;
+static int kvm_usage_count = 0;
+static atomic_t hardware_enable_failed;
 
 struct kmem_cache *kvm_vcpu_cache;
 EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
@@ -86,615 +83,13 @@ struct dentry *kvm_debugfs_dir;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
+static int hardware_enable_all(void);
+static void hardware_disable_all(void);
 
 static bool kvm_rebooting;
 
 static bool largepages_enabled = true;
 
-#ifdef KVM_CAP_DEVICE_ASSIGNMENT
-static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
-						      int assigned_dev_id)
-{
-	struct list_head *ptr;
-	struct kvm_assigned_dev_kernel *match;
-
-	list_for_each(ptr, head) {
-		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
-		if (match->assigned_dev_id == assigned_dev_id)
-			return match;
-	}
-	return NULL;
-}
-
-static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
-				    *assigned_dev, int irq)
-{
-	int i, index;
-	struct msix_entry *host_msix_entries;
-
-	host_msix_entries = assigned_dev->host_msix_entries;
-
-	index = -1;
-	for (i = 0; i < assigned_dev->entries_nr; i++)
-		if (irq == host_msix_entries[i].vector) {
-			index = i;
-			break;
-		}
-	if (index < 0) {
-		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
-		return 0;
-	}
-
-	return index;
-}
-
-static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev;
-	struct kvm *kvm;
-	int i;
-
-	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
-				    interrupt_work);
-	kvm = assigned_dev->kvm;
-
-	mutex_lock(&kvm->irq_lock);
-	spin_lock_irq(&assigned_dev->assigned_dev_lock);
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		struct kvm_guest_msix_entry *guest_entries =
-			assigned_dev->guest_msix_entries;
-		for (i = 0; i < assigned_dev->entries_nr; i++) {
-			if (!(guest_entries[i].flags &
-					KVM_ASSIGNED_MSIX_PENDING))
-				continue;
-			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
-			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id,
-				    guest_entries[i].vector, 1);
-		}
-	} else
-		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-			    assigned_dev->guest_irq, 1);
-
-	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
-	mutex_unlock(&assigned_dev->kvm->irq_lock);
-}
-
-static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
-{
-	unsigned long flags;
-	struct kvm_assigned_dev_kernel *assigned_dev =
-		(struct kvm_assigned_dev_kernel *) dev_id;
-
-	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		int index = find_index_from_host_irq(assigned_dev, irq);
-		if (index < 0)
-			goto out;
-		assigned_dev->guest_msix_entries[index].flags |=
-			KVM_ASSIGNED_MSIX_PENDING;
-	}
-
-	schedule_work(&assigned_dev->interrupt_work);
-
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
-		disable_irq_nosync(irq);
-		assigned_dev->host_irq_disabled = true;
-	}
-
-out:
-	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
-	return IRQ_HANDLED;
-}
-
-/* Ack the irq line for an assigned device */
-static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
-{
-	struct kvm_assigned_dev_kernel *dev;
-	unsigned long flags;
-
-	if (kian->gsi == -1)
-		return;
-
-	dev = container_of(kian, struct kvm_assigned_dev_kernel,
-			   ack_notifier);
-
-	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
-
-	/* The guest irq may be shared so this ack may be
-	 * from another device.
-	 */
-	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
-	if (dev->host_irq_disabled) {
-		enable_irq(dev->host_irq);
-		dev->host_irq_disabled = false;
-	}
-	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
-}
-
-static void deassign_guest_irq(struct kvm *kvm,
-			       struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
-	assigned_dev->ack_notifier.gsi = -1;
-
-	if (assigned_dev->irq_source_id != -1)
-		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
-	assigned_dev->irq_source_id = -1;
-	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
-}
-
-/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
-static void deassign_host_irq(struct kvm *kvm,
-			      struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	/*
-	 * In kvm_free_device_irq, cancel_work_sync return true if:
-	 * 1. work is scheduled, and then cancelled.
-	 * 2. work callback is executed.
-	 *
-	 * The first one ensured that the irq is disabled and no more events
-	 * would happen. But for the second one, the irq may be enabled (e.g.
-	 * for MSI). So we disable irq here to prevent further events.
-	 *
-	 * Notice this maybe result in nested disable if the interrupt type is
-	 * INTx, but it's OK for we are going to free it.
-	 *
-	 * If this function is a part of VM destroy, please ensure that till
-	 * now, the kvm state is still legal for probably we also have to wait
-	 * interrupt_work done.
-	 */
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		int i;
-		for (i = 0; i < assigned_dev->entries_nr; i++)
-			disable_irq_nosync(assigned_dev->
-					   host_msix_entries[i].vector);
-
-		cancel_work_sync(&assigned_dev->interrupt_work);
-
-		for (i = 0; i < assigned_dev->entries_nr; i++)
-			free_irq(assigned_dev->host_msix_entries[i].vector,
-				 (void *)assigned_dev);
-
-		assigned_dev->entries_nr = 0;
-		kfree(assigned_dev->host_msix_entries);
-		kfree(assigned_dev->guest_msix_entries);
-		pci_disable_msix(assigned_dev->dev);
-	} else {
-		/* Deal with MSI and INTx */
-		disable_irq_nosync(assigned_dev->host_irq);
-		cancel_work_sync(&assigned_dev->interrupt_work);
-
-		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
-
-		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
-			pci_disable_msi(assigned_dev->dev);
-	}
-
-	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
-}
-
-static int kvm_deassign_irq(struct kvm *kvm,
-			    struct kvm_assigned_dev_kernel *assigned_dev,
-			    unsigned long irq_requested_type)
-{
-	unsigned long guest_irq_type, host_irq_type;
-
-	if (!irqchip_in_kernel(kvm))
-		return -EINVAL;
-	/* no irq assignment to deassign */
-	if (!assigned_dev->irq_requested_type)
-		return -ENXIO;
-
-	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
-	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
-
-	if (host_irq_type)
-		deassign_host_irq(kvm, assigned_dev);
-	if (guest_irq_type)
-		deassign_guest_irq(kvm, assigned_dev);
-
-	return 0;
-}
-
-static void kvm_free_assigned_irq(struct kvm *kvm,
-				  struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
-}
-
-static void kvm_free_assigned_device(struct kvm *kvm,
-				     struct kvm_assigned_dev_kernel
-				     *assigned_dev)
-{
-	kvm_free_assigned_irq(kvm, assigned_dev);
-
-	pci_reset_function(assigned_dev->dev);
-
-	pci_release_regions(assigned_dev->dev);
-	pci_disable_device(assigned_dev->dev);
-	pci_dev_put(assigned_dev->dev);
-
-	list_del(&assigned_dev->list);
-	kfree(assigned_dev);
-}
-
-void kvm_free_all_assigned_devices(struct kvm *kvm)
-{
-	struct list_head *ptr, *ptr2;
-	struct kvm_assigned_dev_kernel *assigned_dev;
-
-	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
-		assigned_dev = list_entry(ptr,
-					  struct kvm_assigned_dev_kernel,
-					  list);
-
-		kvm_free_assigned_device(kvm, assigned_dev);
-	}
-}
-
-static int assigned_device_enable_host_intx(struct kvm *kvm,
-					    struct kvm_assigned_dev_kernel *dev)
-{
-	dev->host_irq = dev->dev->irq;
-	/* Even though this is PCI, we don't want to use shared
-	 * interrupts. Sharing host devices with guest-assigned devices
-	 * on the same interrupt line is not a happy situation: there
-	 * are going to be long delays in accepting, acking, etc.
-	 */
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
-			0, "kvm_assigned_intx_device", (void *)dev))
-		return -EIO;
-	return 0;
-}
-
-#ifdef __KVM_HAVE_MSI
-static int assigned_device_enable_host_msi(struct kvm *kvm,
-					   struct kvm_assigned_dev_kernel *dev)
-{
-	int r;
-
-	if (!dev->dev->msi_enabled) {
-		r = pci_enable_msi(dev->dev);
-		if (r)
-			return r;
-	}
-
-	dev->host_irq = dev->dev->irq;
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
-			"kvm_assigned_msi_device", (void *)dev)) {
-		pci_disable_msi(dev->dev);
-		return -EIO;
-	}
-
-	return 0;
-}
-#endif
-
-#ifdef __KVM_HAVE_MSIX
-static int assigned_device_enable_host_msix(struct kvm *kvm,
-					    struct kvm_assigned_dev_kernel *dev)
-{
-	int i, r = -EINVAL;
-
-	/* host_msix_entries and guest_msix_entries should have been
-	 * initialized */
-	if (dev->entries_nr == 0)
-		return r;
-
-	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
-	if (r)
-		return r;
-
-	for (i = 0; i < dev->entries_nr; i++) {
-		r = request_irq(dev->host_msix_entries[i].vector,
-				kvm_assigned_dev_intr, 0,
-				"kvm_assigned_msix_device",
-				(void *)dev);
-		/* FIXME: free requested_irq's on failure */
-		if (r)
-			return r;
-	}
-
-	return 0;
-}
-
-#endif
-
-static int assigned_device_enable_guest_intx(struct kvm *kvm,
-				struct kvm_assigned_dev_kernel *dev,
-				struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = irq->guest_irq;
-	return 0;
-}
-
-#ifdef __KVM_HAVE_MSI
-static int assigned_device_enable_guest_msi(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *dev,
-			struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = -1;
-	dev->host_irq_disabled = false;
-	return 0;
-}
-#endif
-#ifdef __KVM_HAVE_MSIX
-static int assigned_device_enable_guest_msix(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *dev,
-			struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = -1;
-	dev->host_irq_disabled = false;
-	return 0;
-}
-#endif
-
-static int assign_host_irq(struct kvm *kvm,
-			   struct kvm_assigned_dev_kernel *dev,
-			   __u32 host_irq_type)
-{
-	int r = -EEXIST;
-
-	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
-		return r;
-
-	switch (host_irq_type) {
-	case KVM_DEV_IRQ_HOST_INTX:
-		r = assigned_device_enable_host_intx(kvm, dev);
-		break;
-#ifdef __KVM_HAVE_MSI
-	case KVM_DEV_IRQ_HOST_MSI:
-		r = assigned_device_enable_host_msi(kvm, dev);
-		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
-	case KVM_DEV_IRQ_HOST_MSIX:
-		r = assigned_device_enable_host_msix(kvm, dev);
-		break;
-#endif
-	default:
-		r = -EINVAL;
-	}
-
-	if (!r)
-		dev->irq_requested_type |= host_irq_type;
-
-	return r;
-}
-
-static int assign_guest_irq(struct kvm *kvm,
-			    struct kvm_assigned_dev_kernel *dev,
-			    struct kvm_assigned_irq *irq,
-			    unsigned long guest_irq_type)
-{
-	int id;
-	int r = -EEXIST;
-
-	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
-		return r;
-
-	id = kvm_request_irq_source_id(kvm);
-	if (id < 0)
-		return id;
-
-	dev->irq_source_id = id;
-
-	switch (guest_irq_type) {
-	case KVM_DEV_IRQ_GUEST_INTX:
-		r = assigned_device_enable_guest_intx(kvm, dev, irq);
-		break;
-#ifdef __KVM_HAVE_MSI
-	case KVM_DEV_IRQ_GUEST_MSI:
-		r = assigned_device_enable_guest_msi(kvm, dev, irq);
-		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
-	case KVM_DEV_IRQ_GUEST_MSIX:
-		r = assigned_device_enable_guest_msix(kvm, dev, irq);
-		break;
-#endif
-	default:
-		r = -EINVAL;
-	}
-
-	if (!r) {
-		dev->irq_requested_type |= guest_irq_type;
-		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
-	} else
-		kvm_free_irq_source_id(kvm, dev->irq_source_id);
-
-	return r;
-}
-
-/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
-static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
-				   struct kvm_assigned_irq *assigned_irq)
-{
-	int r = -EINVAL;
-	struct kvm_assigned_dev_kernel *match;
-	unsigned long host_irq_type, guest_irq_type;
-
-	if (!capable(CAP_SYS_RAWIO))
-		return -EPERM;
-
-	if (!irqchip_in_kernel(kvm))
-		return r;
-
-	mutex_lock(&kvm->lock);
-	r = -ENODEV;
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_irq->assigned_dev_id);
-	if (!match)
-		goto out;
-
-	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
-	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
-
-	r = -EINVAL;
-	/* can only assign one type at a time */
-	if (hweight_long(host_irq_type) > 1)
-		goto out;
-	if (hweight_long(guest_irq_type) > 1)
-		goto out;
-	if (host_irq_type == 0 && guest_irq_type == 0)
-		goto out;
-
-	r = 0;
-	if (host_irq_type)
-		r = assign_host_irq(kvm, match, host_irq_type);
-	if (r)
-		goto out;
-
-	if (guest_irq_type)
-		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
-					 struct kvm_assigned_irq
-					 *assigned_irq)
-{
-	int r = -ENODEV;
-	struct kvm_assigned_dev_kernel *match;
-
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_irq->assigned_dev_id);
-	if (!match)
-		goto out;
-
-	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
-				      struct kvm_assigned_pci_dev *assigned_dev)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *match;
-	struct pci_dev *dev;
-
-	down_read(&kvm->slots_lock);
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_dev->assigned_dev_id);
-	if (match) {
-		/* device already assigned */
-		r = -EEXIST;
-		goto out;
-	}
-
-	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
-	if (match == NULL) {
-		printk(KERN_INFO "%s: Couldn't allocate memory\n",
-		       __func__);
-		r = -ENOMEM;
-		goto out;
-	}
-	dev = pci_get_bus_and_slot(assigned_dev->busnr,
-				   assigned_dev->devfn);
-	if (!dev) {
-		printk(KERN_INFO "%s: host device not found\n", __func__);
-		r = -EINVAL;
-		goto out_free;
-	}
-	if (pci_enable_device(dev)) {
-		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
-		r = -EBUSY;
-		goto out_put;
-	}
-	r = pci_request_regions(dev, "kvm_assigned_device");
-	if (r) {
-		printk(KERN_INFO "%s: Could not get access to device regions\n",
-		       __func__);
-		goto out_disable;
-	}
-
-	pci_reset_function(dev);
-
-	match->assigned_dev_id = assigned_dev->assigned_dev_id;
-	match->host_busnr = assigned_dev->busnr;
-	match->host_devfn = assigned_dev->devfn;
-	match->flags = assigned_dev->flags;
-	match->dev = dev;
-	spin_lock_init(&match->assigned_dev_lock);
-	match->irq_source_id = -1;
-	match->kvm = kvm;
-	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
-	INIT_WORK(&match->interrupt_work,
-		  kvm_assigned_dev_interrupt_work_handler);
-
-	list_add(&match->list, &kvm->arch.assigned_dev_head);
-
-	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
-		if (!kvm->arch.iommu_domain) {
-			r = kvm_iommu_map_guest(kvm);
-			if (r)
-				goto out_list_del;
-		}
-		r = kvm_assign_device(kvm, match);
-		if (r)
-			goto out_list_del;
-	}
-
-out:
-	mutex_unlock(&kvm->lock);
-	up_read(&kvm->slots_lock);
-	return r;
-out_list_del:
-	list_del(&match->list);
-	pci_release_regions(dev);
-out_disable:
-	pci_disable_device(dev);
-out_put:
-	pci_dev_put(dev);
-out_free:
-	kfree(match);
-	mutex_unlock(&kvm->lock);
-	up_read(&kvm->slots_lock);
-	return r;
-}
-#endif
-
-#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
-static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
-		struct kvm_assigned_pci_dev *assigned_dev)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *match;
-
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_dev->assigned_dev_id);
-	if (!match) {
-		printk(KERN_INFO "%s: device hasn't been assigned before, "
-		  "so cannot be deassigned\n", __func__);
-		r = -EINVAL;
-		goto out;
-	}
-
-	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
-		kvm_deassign_device(kvm, match);
-
-	kvm_free_assigned_device(kvm, match);
-
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-#endif
-
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
@@ -950,6 +345,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
 
 static struct kvm *kvm_create_vm(void)
 {
+	int r = 0;
 	struct kvm *kvm = kvm_arch_create_vm();
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	struct page *page;
@@ -957,16 +353,21 @@ static struct kvm *kvm_create_vm(void)
 
 	if (IS_ERR(kvm))
 		goto out;
+
+	r = hardware_enable_all();
+	if (r)
+		goto out_err_nodisable;
+
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-	INIT_LIST_HEAD(&kvm->irq_routing);
 	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page) {
-		kfree(kvm);
-		return ERR_PTR(-ENOMEM);
+		r = -ENOMEM;
+		goto out_err;
 	}
 	kvm->coalesced_mmio_ring =
 			(struct kvm_coalesced_mmio_ring *)page_address(page);
@@ -974,15 +375,13 @@ static struct kvm *kvm_create_vm(void)
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	{
-		int err;
 		kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;
-		err = mmu_notifier_register(&kvm->mmu_notifier, current->mm);
-		if (err) {
+		r = mmu_notifier_register(&kvm->mmu_notifier, current->mm);
+		if (r) {
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 			put_page(page);
 #endif
-			kfree(kvm);
-			return ERR_PTR(err);
+			goto out_err;
 		}
 	}
 #endif
@@ -1006,6 +405,12 @@ static struct kvm *kvm_create_vm(void)
 #endif
 out:
 	return kvm;
+
+out_err:
+	hardware_disable_all();
+out_err_nodisable:
+	kfree(kvm);
+	return ERR_PTR(r);
 }
 
 /*
@@ -1064,6 +469,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_flush_shadow(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
+	hardware_disable_all();
 	mmdrop(mm);
 }
 
@@ -1690,9 +1096,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		if (signal_pending(current))
 			break;
 
-		vcpu_put(vcpu);
 		schedule();
-		vcpu_load(vcpu);
 	}
 
 	finish_wait(&vcpu->wq, &wait);
@@ -1706,6 +1110,21 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
+void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu)
+{
+	ktime_t expires;
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+
+	/* Sleep for 100 us, and hope lock-holder got scheduled */
+	expires = ktime_add_ns(ktime_get(), 100000UL);
+	schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+
+	finish_wait(&vcpu->wq, &wait);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
+
 static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vma->vm_file->private_data;
@@ -1829,88 +1248,6 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
 	return 0;
 }
 
-#ifdef __KVM_HAVE_MSIX
-static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
-				    struct kvm_assigned_msix_nr *entry_nr)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *adev;
-
-	mutex_lock(&kvm->lock);
-
-	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      entry_nr->assigned_dev_id);
-	if (!adev) {
-		r = -EINVAL;
-		goto msix_nr_out;
-	}
-
-	if (adev->entries_nr == 0) {
-		adev->entries_nr = entry_nr->entry_nr;
-		if (adev->entries_nr == 0 ||
-		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
-			r = -EINVAL;
-			goto msix_nr_out;
-		}
-
-		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
-						entry_nr->entry_nr,
-						GFP_KERNEL);
-		if (!adev->host_msix_entries) {
-			r = -ENOMEM;
-			goto msix_nr_out;
-		}
-		adev->guest_msix_entries = kzalloc(
-				sizeof(struct kvm_guest_msix_entry) *
-				entry_nr->entry_nr, GFP_KERNEL);
-		if (!adev->guest_msix_entries) {
-			kfree(adev->host_msix_entries);
-			r = -ENOMEM;
-			goto msix_nr_out;
-		}
-	} else /* Not allowed set MSI-X number twice */
-		r = -EINVAL;
-msix_nr_out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
-				       struct kvm_assigned_msix_entry *entry)
-{
-	int r = 0, i;
-	struct kvm_assigned_dev_kernel *adev;
-
-	mutex_lock(&kvm->lock);
-
-	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      entry->assigned_dev_id);
-
-	if (!adev) {
-		r = -EINVAL;
-		goto msix_entry_out;
-	}
-
-	for (i = 0; i < adev->entries_nr; i++)
-		if (adev->guest_msix_entries[i].vector == 0 ||
-		    adev->guest_msix_entries[i].entry == entry->entry) {
-			adev->guest_msix_entries[i].entry = entry->entry;
-			adev->guest_msix_entries[i].vector = entry->gsi;
-			adev->host_msix_entries[i].entry = entry->entry;
-			break;
-		}
-	if (i == adev->entries_nr) {
-		r = -ENOSPC;
-		goto msix_entry_out;
-	}
-
-msix_entry_out:
-	mutex_unlock(&kvm->lock);
-
-	return r;
-}
-#endif
-
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2169,112 +1506,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
-#ifdef KVM_CAP_DEVICE_ASSIGNMENT
-	case KVM_ASSIGN_PCI_DEVICE: {
-		struct kvm_assigned_pci_dev assigned_dev;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
-			goto out;
-		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_ASSIGN_IRQ: {
-		r = -EOPNOTSUPP;
-		break;
-	}
-#ifdef KVM_CAP_ASSIGN_DEV_IRQ
-	case KVM_ASSIGN_DEV_IRQ: {
-		struct kvm_assigned_irq assigned_irq;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
-			goto out;
-		r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_DEASSIGN_DEV_IRQ: {
-		struct kvm_assigned_irq assigned_irq;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
-			goto out;
-		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
-		if (r)
-			goto out;
-		break;
-	}
-#endif
-#endif
-#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
-	case KVM_DEASSIGN_PCI_DEVICE: {
-		struct kvm_assigned_pci_dev assigned_dev;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
-			goto out;
-		r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-#endif
-#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;
-		r = -EFAULT;
-		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
-			goto out;
-		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_ASSIGN_SET_MSIX_ENTRY: {
-		struct kvm_assigned_msix_entry entry;
-		r = -EFAULT;
-		if (copy_from_user(&entry, argp, sizeof entry))
-			goto out;
-		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
-		if (r)
-			goto out;
-		break;
-	}
-#endif
 	case KVM_IRQFD: {
 		struct kvm_irqfd data;
 
@@ -2306,11 +1537,59 @@ static long kvm_vm_ioctl(struct file *filp,
 #endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
+		if (r == -ENOTTY)
+			r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
 	}
 out:
 	return r;
 }
 
+#ifdef CONFIG_COMPAT
+struct compat_kvm_dirty_log {
+	__u32 slot;
+	__u32 padding1;
+	union {
+		compat_uptr_t dirty_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
+static long kvm_vm_compat_ioctl(struct file *filp,
+			   unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	int r;
+
+	if (kvm->mm != current->mm)
+		return -EIO;
+	switch (ioctl) {
+	case KVM_GET_DIRTY_LOG: {
+		struct compat_kvm_dirty_log compat_log;
+		struct kvm_dirty_log log;
+
+		r = -EFAULT;
+		if (copy_from_user(&compat_log, (void __user *)arg,
+				   sizeof(compat_log)))
+			goto out;
+		log.slot	 = compat_log.slot;
+		log.padding1	 = compat_log.padding1;
+		log.padding2	 = compat_log.padding2;
+		log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
+		if (r)
+			goto out;
+		break;
+	}
+	default:
+		r = kvm_vm_ioctl(filp, ioctl, arg);
+	}
+
+out:
+	return r;
+}
+#endif
+
 static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page[1];
@@ -2345,7 +1624,9 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
 static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
-	.compat_ioctl   = kvm_vm_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = kvm_vm_compat_ioctl,
+#endif
 	.mmap           = kvm_vm_mmap,
 };
 
@@ -2373,6 +1654,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	case KVM_CAP_SET_BOOT_CPU_ID:
 #endif
+	case KVM_CAP_INTERNAL_ERROR_DATA:
 		return 1;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQ_ROUTING:
@@ -2443,11 +1725,21 @@ static struct miscdevice kvm_dev = {
 static void hardware_enable(void *junk)
 {
 	int cpu = raw_smp_processor_id();
+	int r;
 
 	if (cpumask_test_cpu(cpu, cpus_hardware_enabled))
 		return;
+
 	cpumask_set_cpu(cpu, cpus_hardware_enabled);
-	kvm_arch_hardware_enable(NULL);
+
+	r = kvm_arch_hardware_enable(NULL);
+
+	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);
+	}
 }
 
 static void hardware_disable(void *junk)
@@ -2460,11 +1752,52 @@ static void hardware_disable(void *junk)
 	kvm_arch_hardware_disable(NULL);
 }
 
+static void hardware_disable_all_nolock(void)
+{
+	BUG_ON(!kvm_usage_count);
+
+	kvm_usage_count--;
+	if (!kvm_usage_count)
+		on_each_cpu(hardware_disable, NULL, 1);
+}
+
+static void hardware_disable_all(void)
+{
+	spin_lock(&kvm_lock);
+	hardware_disable_all_nolock();
+	spin_unlock(&kvm_lock);
+}
+
+static int hardware_enable_all(void)
+{
+	int r = 0;
+
+	spin_lock(&kvm_lock);
+
+	kvm_usage_count++;
+	if (kvm_usage_count == 1) {
+		atomic_set(&hardware_enable_failed, 0);
+		on_each_cpu(hardware_enable, NULL, 1);
+
+		if (atomic_read(&hardware_enable_failed)) {
+			hardware_disable_all_nolock();
+			r = -EBUSY;
+		}
+	}
+
+	spin_unlock(&kvm_lock);
+
+	return r;
+}
+
 static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 			   void *v)
 {
 	int cpu = (long)v;
 
+	if (!kvm_usage_count)
+		return NOTIFY_OK;
+
 	val &= ~CPU_TASKS_FROZEN;
 	switch (val) {
 	case CPU_DYING:
@@ -2667,13 +2000,15 @@ static void kvm_exit_debug(void)
 
 static int kvm_suspend(struct sys_device *dev, pm_message_t state)
 {
-	hardware_disable(NULL);
+	if (kvm_usage_count)
+		hardware_disable(NULL);
 	return 0;
 }
 
 static int kvm_resume(struct sys_device *dev)
 {
-	hardware_enable(NULL);
+	if (kvm_usage_count)
+		hardware_enable(NULL);
 	return 0;
 }
 
@@ -2748,7 +2083,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 			goto out_free_1;
 	}
 
-	on_each_cpu(hardware_enable, NULL, 1);
 	r = register_cpu_notifier(&kvm_cpu_notifier);
 	if (r)
 		goto out_free_2;
@@ -2798,7 +2132,6 @@ out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 out_free_2:
-	on_each_cpu(hardware_disable, NULL, 1);
 out_free_1:
 	kvm_arch_hardware_unsetup();
 out_free_0a: