KVM: Extract core of kvm_flush_remote_tlbs/kvm_reload_remote_mmus

[deliverable/linux.git] / virt / kvm / kvm_main.c

/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "iodev.h"

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
#include <linux/kvm_para.h>
#include <linux/pagemap.h>
#include <linux/mman.h>
#include <linux/swap.h>

#include <asm/processor.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>

#ifdef CONFIG_X86
#include <asm/msidef.h>
#endif

#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
#include "coalesced_mmio.h"
#endif

#ifdef KVM_CAP_DEVICE_ASSIGNMENT
#include <linux/pci.h>
#include <linux/interrupt.h>
#include "irq.h"
#endif

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

static int msi2intx = 1;
module_param(msi2intx, bool, 0);

DEFINE_SPINLOCK(kvm_lock);
LIST_HEAD(vm_list);

static cpumask_t cpus_hardware_enabled;

struct kmem_cache *kvm_vcpu_cache;
EXPORT_SYMBOL_GPL(kvm_vcpu_cache);

static __read_mostly struct preempt_ops kvm_preempt_ops;

struct dentry *kvm_debugfs_dir;

static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
                           unsigned long arg);

static bool kvm_rebooting;

#ifdef KVM_CAP_DEVICE_ASSIGNMENT

#ifdef CONFIG_X86
static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev)
{
        int vcpu_id;
        struct kvm_vcpu *vcpu;
        struct kvm_ioapic *ioapic = ioapic_irqchip(dev->kvm);
        int dest_id = (dev->guest_msi.address_lo & MSI_ADDR_DEST_ID_MASK)
                        >> MSI_ADDR_DEST_ID_SHIFT;
        int vector = (dev->guest_msi.data & MSI_DATA_VECTOR_MASK)
                        >> MSI_DATA_VECTOR_SHIFT;
        int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT,
                                (unsigned long *)&dev->guest_msi.address_lo);
        int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT,
                                (unsigned long *)&dev->guest_msi.data);
        int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT,
                                (unsigned long *)&dev->guest_msi.data);
        u32 deliver_bitmask;

        BUG_ON(!ioapic);

        deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic,
                                dest_id, dest_mode);
        /* IOAPIC delivery mode value is the same as MSI here */
        switch (delivery_mode) {
        case IOAPIC_LOWEST_PRIORITY:
                vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
                                deliver_bitmask);
                if (vcpu != NULL)
                        kvm_apic_set_irq(vcpu, vector, trig_mode);
                else
                        printk(KERN_INFO "kvm: null lowest priority vcpu!\n");
                break;
        case IOAPIC_FIXED:
                for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
                        if (!(deliver_bitmask & (1 << vcpu_id)))
                                continue;
                        deliver_bitmask &= ~(1 << vcpu_id);
                        vcpu = ioapic->kvm->vcpus[vcpu_id];
                        if (vcpu)
                                kvm_apic_set_irq(vcpu, vector, trig_mode);
                }
                break;
        default:
                printk(KERN_INFO "kvm: unsupported MSI delivery mode\n");
        }
}
#else
static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev) {}
#endif

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 void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
{
        struct kvm_assigned_dev_kernel *assigned_dev;

        assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
                                    interrupt_work);

        /* This is taken to safely inject irq inside the guest. When
         * the interrupt injection (or the ioapic code) uses a
         * finer-grained lock, update this
         */
        mutex_lock(&assigned_dev->kvm->lock);
        if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_INTX)
                kvm_set_irq(assigned_dev->kvm,
                            assigned_dev->irq_source_id,
                            assigned_dev->guest_irq, 1);
        else if (assigned_dev->irq_requested_type &
                                KVM_ASSIGNED_DEV_GUEST_MSI) {
                assigned_device_msi_dispatch(assigned_dev);
                enable_irq(assigned_dev->host_irq);
        }
        mutex_unlock(&assigned_dev->kvm->lock);
        kvm_put_kvm(assigned_dev->kvm);
}

static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
{
        struct kvm_assigned_dev_kernel *assigned_dev =
                (struct kvm_assigned_dev_kernel *) dev_id;

        kvm_get_kvm(assigned_dev->kvm);
        schedule_work(&assigned_dev->interrupt_work);
        disable_irq_nosync(irq);
        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;

        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);
        enable_irq(dev->host_irq);
}

static void kvm_free_assigned_irq(struct kvm *kvm,
                                  struct kvm_assigned_dev_kernel *assigned_dev)
{
        if (!irqchip_in_kernel(kvm))
                return;

        kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);

        if (assigned_dev->irq_source_id != -1)
                kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
        assigned_dev->irq_source_id = -1;

        if (!assigned_dev->irq_requested_type)
                return;

        if (cancel_work_sync(&assigned_dev->interrupt_work))
                /* We had pending work. That means we will have to take
                 * care of kvm_put_kvm.
                 */
                kvm_put_kvm(kvm);

        free_irq(assigned_dev->host_irq, (void *)assigned_dev);

        if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
                pci_disable_msi(assigned_dev->dev);

        assigned_dev->irq_requested_type = 0;
}


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_update_intx(struct kvm *kvm,
                        struct kvm_assigned_dev_kernel *adev,
                        struct kvm_assigned_irq *airq)
{
        adev->guest_irq = airq->guest_irq;
        adev->ack_notifier.gsi = airq->guest_irq;

        if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX)
                return 0;

        if (irqchip_in_kernel(kvm)) {
                if (!msi2intx &&
                    adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) {
                        free_irq(adev->host_irq, (void *)kvm);
                        pci_disable_msi(adev->dev);
                }

                if (!capable(CAP_SYS_RAWIO))
                        return -EPERM;

                if (airq->host_irq)
                        adev->host_irq = airq->host_irq;
                else
                        adev->host_irq = adev->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(adev->host_irq, kvm_assigned_dev_intr,
                                0, "kvm_assigned_intx_device", (void *)adev))
                        return -EIO;
        }

        adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX |
                                   KVM_ASSIGNED_DEV_HOST_INTX;
        return 0;
}

#ifdef CONFIG_X86
static int assigned_device_update_msi(struct kvm *kvm,
                        struct kvm_assigned_dev_kernel *adev,
                        struct kvm_assigned_irq *airq)
{
        int r;

        if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
                /* x86 don't care upper address of guest msi message addr */
                adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI;
                adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX;
                adev->guest_msi.address_lo = airq->guest_msi.addr_lo;
                adev->guest_msi.data = airq->guest_msi.data;
                adev->ack_notifier.gsi = -1;
        } else if (msi2intx) {
                adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX;
                adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI;
                adev->guest_irq = airq->guest_irq;
                adev->ack_notifier.gsi = airq->guest_irq;
        }

        if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
                return 0;

        if (irqchip_in_kernel(kvm)) {
                if (!msi2intx) {
                        if (adev->irq_requested_type &
                                        KVM_ASSIGNED_DEV_HOST_INTX)
                                free_irq(adev->host_irq, (void *)adev);

                        r = pci_enable_msi(adev->dev);
                        if (r)
                                return r;
                }

                adev->host_irq = adev->dev->irq;
                if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0,
                                "kvm_assigned_msi_device", (void *)adev))
                        return -EIO;
        }

        if (!msi2intx)
                adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI;

        adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI;
        return 0;
}
#endif

static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
                                   struct kvm_assigned_irq
                                   *assigned_irq)
{
        int r = 0;
        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) {
                mutex_unlock(&kvm->lock);
                return -EINVAL;
        }

        if (!match->irq_requested_type) {
                INIT_WORK(&match->interrupt_work,
                                kvm_assigned_dev_interrupt_work_handler);
                if (irqchip_in_kernel(kvm)) {
                        /* Register ack nofitier */
                        match->ack_notifier.gsi = -1;
                        match->ack_notifier.irq_acked =
                                        kvm_assigned_dev_ack_irq;
                        kvm_register_irq_ack_notifier(kvm,
                                        &match->ack_notifier);

                        /* Request IRQ source ID */
                        r = kvm_request_irq_source_id(kvm);
                        if (r < 0)
                                goto out_release;
                        else
                                match->irq_source_id = r;

#ifdef CONFIG_X86
                        /* Determine host device irq type, we can know the
                         * result from dev->msi_enabled */
                        if (msi2intx)
                                pci_enable_msi(match->dev);
#endif
                }
        }

        if ((!msi2intx &&
             (assigned_irq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI)) ||
            (msi2intx && match->dev->msi_enabled)) {
#ifdef CONFIG_X86
                r = assigned_device_update_msi(kvm, match, assigned_irq);
                if (r) {
                        printk(KERN_WARNING "kvm: failed to enable "
                                        "MSI device!\n");
                        goto out_release;
                }
#else
                r = -ENOTTY;
#endif
        } else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) {
                /* Host device IRQ 0 means don't support INTx */
                if (!msi2intx) {
                        printk(KERN_WARNING
                               "kvm: wait device to enable MSI!\n");
                        r = 0;
                } else {
                        printk(KERN_WARNING
                               "kvm: failed to enable MSI device!\n");
                        r = -ENOTTY;
                        goto out_release;
                }
        } else {
                /* Non-sharing INTx mode */
                r = assigned_device_update_intx(kvm, match, assigned_irq);
                if (r) {
                        printk(KERN_WARNING "kvm: failed to enable "
                                        "INTx device!\n");
                        goto out_release;
                }
        }

        mutex_unlock(&kvm->lock);
        return r;
out_release:
        mutex_unlock(&kvm->lock);
        kvm_free_assigned_device(kvm, match);
        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;

        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 = -EINVAL;
                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->dev = dev;
        match->irq_source_id = -1;
        match->kvm = kvm;

        list_add(&match->list, &kvm->arch.assigned_dev_head);

        if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
                r = kvm_iommu_map_guest(kvm, match);
                if (r)
                        goto out_list_del;
        }

out:
        mutex_unlock(&kvm->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);
        return r;
}
#endif

static inline int valid_vcpu(int n)
{
        return likely(n >= 0 && n < KVM_MAX_VCPUS);
}

inline int kvm_is_mmio_pfn(pfn_t pfn)
{
        if (pfn_valid(pfn))
                return PageReserved(pfn_to_page(pfn));

        return true;
}

/*
 * Switches to specified vcpu, until a matching vcpu_put()
 */
void vcpu_load(struct kvm_vcpu *vcpu)
{
        int cpu;

        mutex_lock(&vcpu->mutex);
        cpu = get_cpu();
        preempt_notifier_register(&vcpu->preempt_notifier);
        kvm_arch_vcpu_load(vcpu, cpu);
        put_cpu();
}

void vcpu_put(struct kvm_vcpu *vcpu)
{
        preempt_disable();
        kvm_arch_vcpu_put(vcpu);
        preempt_notifier_unregister(&vcpu->preempt_notifier);
        preempt_enable();
        mutex_unlock(&vcpu->mutex);
}

static void ack_flush(void *_completed)
{
}

static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
        int i, cpu, me;
        cpumask_t cpus;
        bool called = false;
        struct kvm_vcpu *vcpu;

        me = get_cpu();
        cpus_clear(cpus);
        for (i = 0; i < KVM_MAX_VCPUS; ++i) {
                vcpu = kvm->vcpus[i];
                if (!vcpu)
                        continue;
                if (test_and_set_bit(req, &vcpu->requests))
                        continue;
                cpu = vcpu->cpu;
                if (cpu != -1 && cpu != me)
                        cpu_set(cpu, cpus);
        }
        if (!cpus_empty(cpus)) {
                smp_call_function_mask(cpus, ack_flush, NULL, 1);
                called = true;
        }
        put_cpu();
        return called;
}

void kvm_flush_remote_tlbs(struct kvm *kvm)
{
        if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
                ++kvm->stat.remote_tlb_flush;
}

void kvm_reload_remote_mmus(struct kvm *kvm)
{
        make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
}

int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
        struct page *page;
        int r;

        mutex_init(&vcpu->mutex);
        vcpu->cpu = -1;
        vcpu->kvm = kvm;
        vcpu->vcpu_id = id;
        init_waitqueue_head(&vcpu->wq);

        page = alloc_page(GFP_KERNEL | __GFP_ZERO);
        if (!page) {
                r = -ENOMEM;
                goto fail;
        }
        vcpu->run = page_address(page);

        r = kvm_arch_vcpu_init(vcpu);
        if (r < 0)
                goto fail_free_run;
        return 0;

fail_free_run:
        free_page((unsigned long)vcpu->run);
fail:
        return r;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_init);

void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
{
        kvm_arch_vcpu_uninit(vcpu);
        free_page((unsigned long)vcpu->run);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);

#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
{
        return container_of(mn, struct kvm, mmu_notifier);
}

static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
                                             struct mm_struct *mm,
                                             unsigned long address)
{
        struct kvm *kvm = mmu_notifier_to_kvm(mn);
        int need_tlb_flush;

        /*
         * When ->invalidate_page runs, the linux pte has been zapped
         * already but the page is still allocated until
         * ->invalidate_page returns. So if we increase the sequence
         * here the kvm page fault will notice if the spte can't be
         * established because the page is going to be freed. If
         * instead the kvm page fault establishes the spte before
         * ->invalidate_page runs, kvm_unmap_hva will release it
         * before returning.
         *
         * The sequence increase only need to be seen at spin_unlock
         * time, and not at spin_lock time.
         *
         * Increasing the sequence after the spin_unlock would be
         * unsafe because the kvm page fault could then establish the
         * pte after kvm_unmap_hva returned, without noticing the page
         * is going to be freed.
         */
        spin_lock(&kvm->mmu_lock);
        kvm->mmu_notifier_seq++;
        need_tlb_flush = kvm_unmap_hva(kvm, address);
        spin_unlock(&kvm->mmu_lock);

        /* we've to flush the tlb before the pages can be freed */
        if (need_tlb_flush)
                kvm_flush_remote_tlbs(kvm);

}

static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
                                                    struct mm_struct *mm,
                                                    unsigned long start,
                                                    unsigned long end)
{
        struct kvm *kvm = mmu_notifier_to_kvm(mn);
        int need_tlb_flush = 0;

        spin_lock(&kvm->mmu_lock);
        /*
         * The count increase must become visible at unlock time as no
         * spte can be established without taking the mmu_lock and
         * count is also read inside the mmu_lock critical section.
         */
        kvm->mmu_notifier_count++;
        for (; start < end; start += PAGE_SIZE)
                need_tlb_flush |= kvm_unmap_hva(kvm, start);
        spin_unlock(&kvm->mmu_lock);

        /* we've to flush the tlb before the pages can be freed */
        if (need_tlb_flush)
                kvm_flush_remote_tlbs(kvm);
}

static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
                                                  struct mm_struct *mm,
                                                  unsigned long start,
                                                  unsigned long end)
{
        struct kvm *kvm = mmu_notifier_to_kvm(mn);

        spin_lock(&kvm->mmu_lock);
        /*
         * This sequence increase will notify the kvm page fault that
         * the page that is going to be mapped in the spte could have
         * been freed.
         */
        kvm->mmu_notifier_seq++;
        /*
         * The above sequence increase must be visible before the
         * below count decrease but both values are read by the kvm
         * page fault under mmu_lock spinlock so we don't need to add
         * a smb_wmb() here in between the two.
         */
        kvm->mmu_notifier_count--;
        spin_unlock(&kvm->mmu_lock);

        BUG_ON(kvm->mmu_notifier_count < 0);
}

static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
                                              struct mm_struct *mm,
                                              unsigned long address)
{
        struct kvm *kvm = mmu_notifier_to_kvm(mn);
        int young;

        spin_lock(&kvm->mmu_lock);
        young = kvm_age_hva(kvm, address);
        spin_unlock(&kvm->mmu_lock);

        if (young)
                kvm_flush_remote_tlbs(kvm);

        return young;
}

static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
        .invalidate_page        = kvm_mmu_notifier_invalidate_page,
        .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
        .invalidate_range_end   = kvm_mmu_notifier_invalidate_range_end,
        .clear_flush_young      = kvm_mmu_notifier_clear_flush_young,
};
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */

static struct kvm *kvm_create_vm(void)
{
        struct kvm *kvm = kvm_arch_create_vm();
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        struct page *page;
#endif

        if (IS_ERR(kvm))
                goto out;

#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        page = alloc_page(GFP_KERNEL | __GFP_ZERO);
        if (!page) {
                kfree(kvm);
                return ERR_PTR(-ENOMEM);
        }
        kvm->coalesced_mmio_ring =
                        (struct kvm_coalesced_mmio_ring *)page_address(page);
#endif

#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) {
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
                        put_page(page);
#endif
                        kfree(kvm);
                        return ERR_PTR(err);
                }
        }
#endif

        kvm->mm = current->mm;
        atomic_inc(&kvm->mm->mm_count);
        spin_lock_init(&kvm->mmu_lock);
        kvm_io_bus_init(&kvm->pio_bus);
        mutex_init(&kvm->lock);
        kvm_io_bus_init(&kvm->mmio_bus);
        init_rwsem(&kvm->slots_lock);
        atomic_set(&kvm->users_count, 1);
        spin_lock(&kvm_lock);
        list_add(&kvm->vm_list, &vm_list);
        spin_unlock(&kvm_lock);
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        kvm_coalesced_mmio_init(kvm);
#endif
out:
        return kvm;
}

/*
 * Free any memory in @free but not in @dont.
 */
static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
                                  struct kvm_memory_slot *dont)
{
        if (!dont || free->rmap != dont->rmap)
                vfree(free->rmap);

        if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
                vfree(free->dirty_bitmap);

        if (!dont || free->lpage_info != dont->lpage_info)
                vfree(free->lpage_info);

        free->npages = 0;
        free->dirty_bitmap = NULL;
        free->rmap = NULL;
        free->lpage_info = NULL;
}

void kvm_free_physmem(struct kvm *kvm)
{
        int i;

        for (i = 0; i < kvm->nmemslots; ++i)
                kvm_free_physmem_slot(&kvm->memslots[i], NULL);
}

static void kvm_destroy_vm(struct kvm *kvm)
{
        struct mm_struct *mm = kvm->mm;

        spin_lock(&kvm_lock);
        list_del(&kvm->vm_list);
        spin_unlock(&kvm_lock);
        kvm_io_bus_destroy(&kvm->pio_bus);
        kvm_io_bus_destroy(&kvm->mmio_bus);
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        if (kvm->coalesced_mmio_ring != NULL)
                free_page((unsigned long)kvm->coalesced_mmio_ring);
#endif
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
        mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
#endif
        kvm_arch_destroy_vm(kvm);
        mmdrop(mm);
}

void kvm_get_kvm(struct kvm *kvm)
{
        atomic_inc(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm);

void kvm_put_kvm(struct kvm *kvm)
{
        if (atomic_dec_and_test(&kvm->users_count))
                kvm_destroy_vm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_put_kvm);


static int kvm_vm_release(struct inode *inode, struct file *filp)
{
        struct kvm *kvm = filp->private_data;

        kvm_put_kvm(kvm);
        return 0;
}

/*
 * Allocate some memory and give it an address in the guest physical address
 * space.
 *
 * Discontiguous memory is allowed, mostly for framebuffers.
 *
 * Must be called holding mmap_sem for write.
 */
int __kvm_set_memory_region(struct kvm *kvm,
                            struct kvm_userspace_memory_region *mem,
                            int user_alloc)
{
        int r;
        gfn_t base_gfn;
        unsigned long npages;
        unsigned long i;
        struct kvm_memory_slot *memslot;
        struct kvm_memory_slot old, new;

        r = -EINVAL;
        /* General sanity checks */
        if (mem->memory_size & (PAGE_SIZE - 1))
                goto out;
        if (mem->guest_phys_addr & (PAGE_SIZE - 1))
                goto out;
        if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1)))
                goto out;
        if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
                goto out;
        if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
                goto out;

        memslot = &kvm->memslots[mem->slot];
        base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
        npages = mem->memory_size >> PAGE_SHIFT;

        if (!npages)
                mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;

        new = old = *memslot;

        new.base_gfn = base_gfn;
        new.npages = npages;
        new.flags = mem->flags;

        /* Disallow changing a memory slot's size. */
        r = -EINVAL;
        if (npages && old.npages && npages != old.npages)
                goto out_free;

        /* Check for overlaps */
        r = -EEXIST;
        for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
                struct kvm_memory_slot *s = &kvm->memslots[i];

                if (s == memslot)
                        continue;
                if (!((base_gfn + npages <= s->base_gfn) ||
                      (base_gfn >= s->base_gfn + s->npages)))
                        goto out_free;
        }

        /* Free page dirty bitmap if unneeded */
        if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
                new.dirty_bitmap = NULL;

        r = -ENOMEM;

        /* Allocate if a slot is being created */
#ifndef CONFIG_S390
        if (npages && !new.rmap) {
                new.rmap = vmalloc(npages * sizeof(struct page *));

                if (!new.rmap)
                        goto out_free;

                memset(new.rmap, 0, npages * sizeof(*new.rmap));

                new.user_alloc = user_alloc;
                /*
                 * hva_to_rmmap() serialzies with the mmu_lock and to be
                 * safe it has to ignore memslots with !user_alloc &&
                 * !userspace_addr.
                 */
                if (user_alloc)
                        new.userspace_addr = mem->userspace_addr;
                else
                        new.userspace_addr = 0;
        }
        if (npages && !new.lpage_info) {
                int largepages = npages / KVM_PAGES_PER_HPAGE;
                if (npages % KVM_PAGES_PER_HPAGE)
                        largepages++;
                if (base_gfn % KVM_PAGES_PER_HPAGE)
                        largepages++;

                new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));

                if (!new.lpage_info)
                        goto out_free;

                memset(new.lpage_info, 0, largepages * sizeof(*new.lpage_info));

                if (base_gfn % KVM_PAGES_PER_HPAGE)
                        new.lpage_info[0].write_count = 1;
                if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
                        new.lpage_info[largepages-1].write_count = 1;
        }

        /* Allocate page dirty bitmap if needed */
        if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
                unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8;

                new.dirty_bitmap = vmalloc(dirty_bytes);
                if (!new.dirty_bitmap)
                        goto out_free;
                memset(new.dirty_bitmap, 0, dirty_bytes);
        }
#endif /* not defined CONFIG_S390 */

        if (!npages)
                kvm_arch_flush_shadow(kvm);

        spin_lock(&kvm->mmu_lock);
        if (mem->slot >= kvm->nmemslots)
                kvm->nmemslots = mem->slot + 1;

        *memslot = new;
        spin_unlock(&kvm->mmu_lock);

        r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc);
        if (r) {
                spin_lock(&kvm->mmu_lock);
                *memslot = old;
                spin_unlock(&kvm->mmu_lock);
                goto out_free;
        }

        kvm_free_physmem_slot(&old, npages ? &new : NULL);
        /* Slot deletion case: we have to update the current slot */
        if (!npages)
                *memslot = old;
#ifdef CONFIG_DMAR
        /* map the pages in iommu page table */
        r = kvm_iommu_map_pages(kvm, base_gfn, npages);
        if (r)
                goto out;
#endif
        return 0;

out_free:
        kvm_free_physmem_slot(&new, &old);
out:
        return r;

}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);

int kvm_set_memory_region(struct kvm *kvm,
                          struct kvm_userspace_memory_region *mem,
                          int user_alloc)
{
        int r;

        down_write(&kvm->slots_lock);
        r = __kvm_set_memory_region(kvm, mem, user_alloc);
        up_write(&kvm->slots_lock);
        return r;
}
EXPORT_SYMBOL_GPL(kvm_set_memory_region);

int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
                                   struct
                                   kvm_userspace_memory_region *mem,
                                   int user_alloc)
{
        if (mem->slot >= KVM_MEMORY_SLOTS)
                return -EINVAL;
        return kvm_set_memory_region(kvm, mem, user_alloc);
}

int kvm_get_dirty_log(struct kvm *kvm,
                        struct kvm_dirty_log *log, int *is_dirty)
{
        struct kvm_memory_slot *memslot;
        int r, i;
        int n;
        unsigned long any = 0;

        r = -EINVAL;
        if (log->slot >= KVM_MEMORY_SLOTS)
                goto out;

        memslot = &kvm->memslots[log->slot];
        r = -ENOENT;
        if (!memslot->dirty_bitmap)
                goto out;

        n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;

        for (i = 0; !any && i < n/sizeof(long); ++i)
                any = memslot->dirty_bitmap[i];

        r = -EFAULT;
        if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
                goto out;

        if (any)
                *is_dirty = 1;

        r = 0;
out:
        return r;
}

int is_error_page(struct page *page)
{
        return page == bad_page;
}
EXPORT_SYMBOL_GPL(is_error_page);

int is_error_pfn(pfn_t pfn)
{
        return pfn == bad_pfn;
}
EXPORT_SYMBOL_GPL(is_error_pfn);

static inline unsigned long bad_hva(void)
{
        return PAGE_OFFSET;
}

int kvm_is_error_hva(unsigned long addr)
{
        return addr == bad_hva();
}
EXPORT_SYMBOL_GPL(kvm_is_error_hva);

struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
{
        int i;

        for (i = 0; i < kvm->nmemslots; ++i) {
                struct kvm_memory_slot *memslot = &kvm->memslots[i];

                if (gfn >= memslot->base_gfn
                    && gfn < memslot->base_gfn + memslot->npages)
                        return memslot;
        }
        return NULL;
}
EXPORT_SYMBOL_GPL(gfn_to_memslot_unaliased);

struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
        gfn = unalias_gfn(kvm, gfn);
        return gfn_to_memslot_unaliased(kvm, gfn);
}

int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
{
        int i;

        gfn = unalias_gfn(kvm, gfn);
        for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
                struct kvm_memory_slot *memslot = &kvm->memslots[i];

                if (gfn >= memslot->base_gfn
                    && gfn < memslot->base_gfn + memslot->npages)
                        return 1;
        }
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);

unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
{
        struct kvm_memory_slot *slot;

        gfn = unalias_gfn(kvm, gfn);
        slot = gfn_to_memslot_unaliased(kvm, gfn);
        if (!slot)
                return bad_hva();
        return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
}
EXPORT_SYMBOL_GPL(gfn_to_hva);

pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
{
        struct page *page[1];
        unsigned long addr;
        int npages;
        pfn_t pfn;

        might_sleep();

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr)) {
                get_page(bad_page);
                return page_to_pfn(bad_page);
        }

        npages = get_user_pages_fast(addr, 1, 1, page);

        if (unlikely(npages != 1)) {
                struct vm_area_struct *vma;

                down_read(&current->mm->mmap_sem);
                vma = find_vma(current->mm, addr);

                if (vma == NULL || addr < vma->vm_start ||
                    !(vma->vm_flags & VM_PFNMAP)) {
                        up_read(&current->mm->mmap_sem);
                        get_page(bad_page);
                        return page_to_pfn(bad_page);
                }

                pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
                up_read(&current->mm->mmap_sem);
                BUG_ON(!kvm_is_mmio_pfn(pfn));
        } else
                pfn = page_to_pfn(page[0]);

        return pfn;
}

EXPORT_SYMBOL_GPL(gfn_to_pfn);

struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
        pfn_t pfn;

        pfn = gfn_to_pfn(kvm, gfn);
        if (!kvm_is_mmio_pfn(pfn))
                return pfn_to_page(pfn);

        WARN_ON(kvm_is_mmio_pfn(pfn));

        get_page(bad_page);
        return bad_page;
}

EXPORT_SYMBOL_GPL(gfn_to_page);

void kvm_release_page_clean(struct page *page)
{
        kvm_release_pfn_clean(page_to_pfn(page));
}
EXPORT_SYMBOL_GPL(kvm_release_page_clean);

void kvm_release_pfn_clean(pfn_t pfn)
{
        if (!kvm_is_mmio_pfn(pfn))
                put_page(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);

void kvm_release_page_dirty(struct page *page)
{
        kvm_release_pfn_dirty(page_to_pfn(page));
}
EXPORT_SYMBOL_GPL(kvm_release_page_dirty);

void kvm_release_pfn_dirty(pfn_t pfn)
{
        kvm_set_pfn_dirty(pfn);
        kvm_release_pfn_clean(pfn);
}
EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);

void kvm_set_page_dirty(struct page *page)
{
        kvm_set_pfn_dirty(page_to_pfn(page));
}
EXPORT_SYMBOL_GPL(kvm_set_page_dirty);

void kvm_set_pfn_dirty(pfn_t pfn)
{
        if (!kvm_is_mmio_pfn(pfn)) {
                struct page *page = pfn_to_page(pfn);
                if (!PageReserved(page))
                        SetPageDirty(page);
        }
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);

void kvm_set_pfn_accessed(pfn_t pfn)
{
        if (!kvm_is_mmio_pfn(pfn))
                mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);

void kvm_get_pfn(pfn_t pfn)
{
        if (!kvm_is_mmio_pfn(pfn))
                get_page(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_get_pfn);

static int next_segment(unsigned long len, int offset)
{
        if (len > PAGE_SIZE - offset)
                return PAGE_SIZE - offset;
        else
                return len;
}

int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
                        int len)
{
        int r;
        unsigned long addr;

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr))
                return -EFAULT;
        r = copy_from_user(data, (void __user *)addr + offset, len);
        if (r)
                return -EFAULT;
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page);

int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len)
{
        gfn_t gfn = gpa >> PAGE_SHIFT;
        int seg;
        int offset = offset_in_page(gpa);
        int ret;

        while ((seg = next_segment(len, offset)) != 0) {
                ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
                if (ret < 0)
                        return ret;
                offset = 0;
                len -= seg;
                data += seg;
                ++gfn;
        }
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest);

int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
                          unsigned long len)
{
        int r;
        unsigned long addr;
        gfn_t gfn = gpa >> PAGE_SHIFT;
        int offset = offset_in_page(gpa);

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr))
                return -EFAULT;
        pagefault_disable();
        r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
        pagefault_enable();
        if (r)
                return -EFAULT;
        return 0;
}
EXPORT_SYMBOL(kvm_read_guest_atomic);

int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
                         int offset, int len)
{
        int r;
        unsigned long addr;

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr))
                return -EFAULT;
        r = copy_to_user((void __user *)addr + offset, data, len);
        if (r)
                return -EFAULT;
        mark_page_dirty(kvm, gfn);
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest_page);

int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
                    unsigned long len)
{
        gfn_t gfn = gpa >> PAGE_SHIFT;
        int seg;
        int offset = offset_in_page(gpa);
        int ret;

        while ((seg = next_segment(len, offset)) != 0) {
                ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
                if (ret < 0)
                        return ret;
                offset = 0;
                len -= seg;
                data += seg;
                ++gfn;
        }
        return 0;
}

int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
{
        return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_clear_guest_page);

int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
{
        gfn_t gfn = gpa >> PAGE_SHIFT;
        int seg;
        int offset = offset_in_page(gpa);
        int ret;

        while ((seg = next_segment(len, offset)) != 0) {
                ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
                if (ret < 0)
                        return ret;
                offset = 0;
                len -= seg;
                ++gfn;
        }
        return 0;
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);

void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
        struct kvm_memory_slot *memslot;

        gfn = unalias_gfn(kvm, gfn);
        memslot = gfn_to_memslot_unaliased(kvm, gfn);
        if (memslot && memslot->dirty_bitmap) {
                unsigned long rel_gfn = gfn - memslot->base_gfn;

                /* avoid RMW */
                if (!test_bit(rel_gfn, memslot->dirty_bitmap))
                        set_bit(rel_gfn, memslot->dirty_bitmap);
        }
}

/*
 * The vCPU has executed a HLT instruction with in-kernel mode enabled.
 */
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
        DEFINE_WAIT(wait);

        for (;;) {
                prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);

                if (kvm_cpu_has_interrupt(vcpu) ||
                    kvm_cpu_has_pending_timer(vcpu) ||
                    kvm_arch_vcpu_runnable(vcpu)) {
                        set_bit(KVM_REQ_UNHALT, &vcpu->requests);
                        break;
                }
                if (signal_pending(current))
                        break;

                vcpu_put(vcpu);
                schedule();
                vcpu_load(vcpu);
        }

        finish_wait(&vcpu->wq, &wait);
}

void kvm_resched(struct kvm_vcpu *vcpu)
{
        if (!need_resched())
                return;
        cond_resched();
}
EXPORT_SYMBOL_GPL(kvm_resched);

static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
        struct kvm_vcpu *vcpu = vma->vm_file->private_data;
        struct page *page;

        if (vmf->pgoff == 0)
                page = virt_to_page(vcpu->run);
#ifdef CONFIG_X86
        else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
                page = virt_to_page(vcpu->arch.pio_data);
#endif
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
                page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
#endif
        else
                return VM_FAULT_SIGBUS;
        get_page(page);
        vmf->page = page;
        return 0;
}

static struct vm_operations_struct kvm_vcpu_vm_ops = {
        .fault = kvm_vcpu_fault,
};

static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
{
        vma->vm_ops = &kvm_vcpu_vm_ops;
        return 0;
}

static int kvm_vcpu_release(struct inode *inode, struct file *filp)
{
        struct kvm_vcpu *vcpu = filp->private_data;

        kvm_put_kvm(vcpu->kvm);
        return 0;
}

static struct file_operations kvm_vcpu_fops = {
        .release        = kvm_vcpu_release,
        .unlocked_ioctl = kvm_vcpu_ioctl,
        .compat_ioctl   = kvm_vcpu_ioctl,
        .mmap           = kvm_vcpu_mmap,
};

/*
 * Allocates an inode for the vcpu.
 */
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
        int fd = anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, 0);
        if (fd < 0)
                kvm_put_kvm(vcpu->kvm);
        return fd;
}

/*
 * Creates some virtual cpus.  Good luck creating more than one.
 */
static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
{
        int r;
        struct kvm_vcpu *vcpu;

        if (!valid_vcpu(n))
                return -EINVAL;

        vcpu = kvm_arch_vcpu_create(kvm, n);
        if (IS_ERR(vcpu))
                return PTR_ERR(vcpu);

        preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);

        r = kvm_arch_vcpu_setup(vcpu);
        if (r)
                return r;

        mutex_lock(&kvm->lock);
        if (kvm->vcpus[n]) {
                r = -EEXIST;
                goto vcpu_destroy;
        }
        kvm->vcpus[n] = vcpu;
        mutex_unlock(&kvm->lock);

        /* Now it's all set up, let userspace reach it */
        kvm_get_kvm(kvm);
        r = create_vcpu_fd(vcpu);
        if (r < 0)
                goto unlink;
        return r;

unlink:
        mutex_lock(&kvm->lock);
        kvm->vcpus[n] = NULL;
vcpu_destroy:
        mutex_unlock(&kvm->lock);
        kvm_arch_vcpu_destroy(vcpu);
        return r;
}

static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
{
        if (sigset) {
                sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
                vcpu->sigset_active = 1;
                vcpu->sigset = *sigset;
        } else
                vcpu->sigset_active = 0;
        return 0;
}

static long kvm_vcpu_ioctl(struct file *filp,
                           unsigned int ioctl, unsigned long arg)
{
        struct kvm_vcpu *vcpu = filp->private_data;
        void __user *argp = (void __user *)arg;
        int r;
        struct kvm_fpu *fpu = NULL;
        struct kvm_sregs *kvm_sregs = NULL;

        if (vcpu->kvm->mm != current->mm)
                return -EIO;
        switch (ioctl) {
        case KVM_RUN:
                r = -EINVAL;
                if (arg)
                        goto out;
                r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
                break;
        case KVM_GET_REGS: {
                struct kvm_regs *kvm_regs;

                r = -ENOMEM;
                kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
                if (!kvm_regs)
                        goto out;
                r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
                if (r)
                        goto out_free1;
                r = -EFAULT;
                if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
                        goto out_free1;
                r = 0;
out_free1:
                kfree(kvm_regs);
                break;
        }
        case KVM_SET_REGS: {
                struct kvm_regs *kvm_regs;

                r = -ENOMEM;
                kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
                if (!kvm_regs)
                        goto out;
                r = -EFAULT;
                if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs)))
                        goto out_free2;
                r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
                if (r)
                        goto out_free2;
                r = 0;
out_free2:
                kfree(kvm_regs);
                break;
        }
        case KVM_GET_SREGS: {
                kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
                r = -ENOMEM;
                if (!kvm_sregs)
                        goto out;
                r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs)))
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_SREGS: {
                kvm_sregs = kmalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
                r = -ENOMEM;
                if (!kvm_sregs)
                        goto out;
                r = -EFAULT;
                if (copy_from_user(kvm_sregs, argp, sizeof(struct kvm_sregs)))
                        goto out;
                r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_GET_MP_STATE: {
                struct kvm_mp_state mp_state;

                r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, &mp_state, sizeof mp_state))
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_MP_STATE: {
                struct kvm_mp_state mp_state;

                r = -EFAULT;
                if (copy_from_user(&mp_state, argp, sizeof mp_state))
                        goto out;
                r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_TRANSLATE: {
                struct kvm_translation tr;

                r = -EFAULT;
                if (copy_from_user(&tr, argp, sizeof tr))
                        goto out;
                r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, &tr, sizeof tr))
                        goto out;
                r = 0;
                break;
        }
        case KVM_DEBUG_GUEST: {
                struct kvm_debug_guest dbg;

                r = -EFAULT;
                if (copy_from_user(&dbg, argp, sizeof dbg))
                        goto out;
                r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_SIGNAL_MASK: {
                struct kvm_signal_mask __user *sigmask_arg = argp;
                struct kvm_signal_mask kvm_sigmask;
                sigset_t sigset, *p;

                p = NULL;
                if (argp) {
                        r = -EFAULT;
                        if (copy_from_user(&kvm_sigmask, argp,
                                           sizeof kvm_sigmask))
                                goto out;
                        r = -EINVAL;
                        if (kvm_sigmask.len != sizeof sigset)
                                goto out;
                        r = -EFAULT;
                        if (copy_from_user(&sigset, sigmask_arg->sigset,
                                           sizeof sigset))
                                goto out;
                        p = &sigset;
                }
                r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
                break;
        }
        case KVM_GET_FPU: {
                fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
                r = -ENOMEM;
                if (!fpu)
                        goto out;
                r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu);
                if (r)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu)))
                        goto out;
                r = 0;
                break;
        }
        case KVM_SET_FPU: {
                fpu = kmalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
                r = -ENOMEM;
                if (!fpu)
                        goto out;
                r = -EFAULT;
                if (copy_from_user(fpu, argp, sizeof(struct kvm_fpu)))
                        goto out;
                r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        default:
                r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
        }
out:
        kfree(fpu);
        kfree(kvm_sregs);
        return r;
}

static long kvm_vm_ioctl(struct file *filp,
                           unsigned int ioctl, unsigned long arg)
{
        struct kvm *kvm = filp->private_data;
        void __user *argp = (void __user *)arg;
        int r;

        if (kvm->mm != current->mm)
                return -EIO;
        switch (ioctl) {
        case KVM_CREATE_VCPU:
                r = kvm_vm_ioctl_create_vcpu(kvm, arg);
                if (r < 0)
                        goto out;
                break;
        case KVM_SET_USER_MEMORY_REGION: {
                struct kvm_userspace_memory_region kvm_userspace_mem;

                r = -EFAULT;
                if (copy_from_user(&kvm_userspace_mem, argp,
                                                sizeof kvm_userspace_mem))
                        goto out;

                r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
                if (r)
                        goto out;
                break;
        }
        case KVM_GET_DIRTY_LOG: {
                struct kvm_dirty_log log;

                r = -EFAULT;
                if (copy_from_user(&log, argp, sizeof log))
                        goto out;
                r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
                if (r)
                        goto out;
                break;
        }
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
        case KVM_REGISTER_COALESCED_MMIO: {
                struct kvm_coalesced_mmio_zone zone;
                r = -EFAULT;
                if (copy_from_user(&zone, argp, sizeof zone))
                        goto out;
                r = -ENXIO;
                r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
                if (r)
                        goto out;
                r = 0;
                break;
        }
        case KVM_UNREGISTER_COALESCED_MMIO: {
                struct kvm_coalesced_mmio_zone zone;
                r = -EFAULT;
                if (copy_from_user(&zone, argp, sizeof zone))
                        goto out;
                r = -ENXIO;
                r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
                if (r)
                        goto out;
                r = 0;
                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: {
                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;
        }
#endif
        default:
                r = kvm_arch_vm_ioctl(filp, ioctl, arg);
        }
out:
        return r;
}

static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
        struct page *page[1];
        unsigned long addr;
        int npages;
        gfn_t gfn = vmf->pgoff;
        struct kvm *kvm = vma->vm_file->private_data;

        addr = gfn_to_hva(kvm, gfn);
        if (kvm_is_error_hva(addr))
                return VM_FAULT_SIGBUS;

        npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page,
                                NULL);
        if (unlikely(npages != 1))
                return VM_FAULT_SIGBUS;

        vmf->page = page[0];
        return 0;
}

static struct vm_operations_struct kvm_vm_vm_ops = {
        .fault = kvm_vm_fault,
};

static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
{
        vma->vm_ops = &kvm_vm_vm_ops;
        return 0;
}

static struct file_operations kvm_vm_fops = {
        .release        = kvm_vm_release,
        .unlocked_ioctl = kvm_vm_ioctl,
        .compat_ioctl   = kvm_vm_ioctl,
        .mmap           = kvm_vm_mmap,
};

static int kvm_dev_ioctl_create_vm(void)
{
        int fd;
        struct kvm *kvm;

        kvm = kvm_create_vm();
        if (IS_ERR(kvm))
                return PTR_ERR(kvm);
        fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, 0);
        if (fd < 0)
                kvm_put_kvm(kvm);

        return fd;
}

static long kvm_dev_ioctl(struct file *filp,
                          unsigned int ioctl, unsigned long arg)
{
        long r = -EINVAL;

        switch (ioctl) {
        case KVM_GET_API_VERSION:
                r = -EINVAL;
                if (arg)
                        goto out;
                r = KVM_API_VERSION;
                break;
        case KVM_CREATE_VM:
                r = -EINVAL;
                if (arg)
                        goto out;
                r = kvm_dev_ioctl_create_vm();
                break;
        case KVM_CHECK_EXTENSION:
                r = kvm_dev_ioctl_check_extension(arg);
                break;
        case KVM_GET_VCPU_MMAP_SIZE:
                r = -EINVAL;
                if (arg)
                        goto out;
                r = PAGE_SIZE;     /* struct kvm_run */
#ifdef CONFIG_X86
                r += PAGE_SIZE;    /* pio data page */
#endif
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
                r += PAGE_SIZE;    /* coalesced mmio ring page */
#endif
                break;
        case KVM_TRACE_ENABLE:
        case KVM_TRACE_PAUSE:
        case KVM_TRACE_DISABLE:
                r = kvm_trace_ioctl(ioctl, arg);
                break;
        default:
                return kvm_arch_dev_ioctl(filp, ioctl, arg);
        }
out:
        return r;
}

static struct file_operations kvm_chardev_ops = {
        .unlocked_ioctl = kvm_dev_ioctl,
        .compat_ioctl   = kvm_dev_ioctl,
};

static struct miscdevice kvm_dev = {
        KVM_MINOR,
        "kvm",
        &kvm_chardev_ops,
};

static void hardware_enable(void *junk)
{
        int cpu = raw_smp_processor_id();

        if (cpu_isset(cpu, cpus_hardware_enabled))
                return;
        cpu_set(cpu, cpus_hardware_enabled);
        kvm_arch_hardware_enable(NULL);
}

static void hardware_disable(void *junk)
{
        int cpu = raw_smp_processor_id();

        if (!cpu_isset(cpu, cpus_hardware_enabled))
                return;
        cpu_clear(cpu, cpus_hardware_enabled);
        kvm_arch_hardware_disable(NULL);
}

static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
                           void *v)
{
        int cpu = (long)v;

        val &= ~CPU_TASKS_FROZEN;
        switch (val) {
        case CPU_DYING:
                printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
                       cpu);
                hardware_disable(NULL);
                break;
        case CPU_UP_CANCELED:
                printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
                       cpu);
                smp_call_function_single(cpu, hardware_disable, NULL, 1);
                break;
        case CPU_ONLINE:
                printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
                       cpu);
                smp_call_function_single(cpu, hardware_enable, NULL, 1);
                break;
        }
        return NOTIFY_OK;
}


asmlinkage void kvm_handle_fault_on_reboot(void)
{
        if (kvm_rebooting)
                /* spin while reset goes on */
                while (true)
                        ;
        /* Fault while not rebooting.  We want the trace. */
        BUG();
}
EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);

static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
                      void *v)
{
        if (val == SYS_RESTART) {
                /*
                 * Some (well, at least mine) BIOSes hang on reboot if
                 * in vmx root mode.
                 */
                printk(KERN_INFO "kvm: exiting hardware virtualization\n");
                kvm_rebooting = true;
                on_each_cpu(hardware_disable, NULL, 1);
        }
        return NOTIFY_OK;
}

static struct notifier_block kvm_reboot_notifier = {
        .notifier_call = kvm_reboot,
        .priority = 0,
};

void kvm_io_bus_init(struct kvm_io_bus *bus)
{
        memset(bus, 0, sizeof(*bus));
}

void kvm_io_bus_destroy(struct kvm_io_bus *bus)
{
        int i;

        for (i = 0; i < bus->dev_count; i++) {
                struct kvm_io_device *pos = bus->devs[i];

                kvm_iodevice_destructor(pos);
        }
}

struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
                                          gpa_t addr, int len, int is_write)
{
        int i;

        for (i = 0; i < bus->dev_count; i++) {
                struct kvm_io_device *pos = bus->devs[i];

                if (pos->in_range(pos, addr, len, is_write))
                        return pos;
        }

        return NULL;
}

void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev)
{
        BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1));

        bus->devs[bus->dev_count++] = dev;
}

static struct notifier_block kvm_cpu_notifier = {
        .notifier_call = kvm_cpu_hotplug,
        .priority = 20, /* must be > scheduler priority */
};

static int vm_stat_get(void *_offset, u64 *val)
{
        unsigned offset = (long)_offset;
        struct kvm *kvm;

        *val = 0;
        spin_lock(&kvm_lock);
        list_for_each_entry(kvm, &vm_list, vm_list)
                *val += *(u32 *)((void *)kvm + offset);
        spin_unlock(&kvm_lock);
        return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n");

static int vcpu_stat_get(void *_offset, u64 *val)
{
        unsigned offset = (long)_offset;
        struct kvm *kvm;
        struct kvm_vcpu *vcpu;
        int i;

        *val = 0;
        spin_lock(&kvm_lock);
        list_for_each_entry(kvm, &vm_list, vm_list)
                for (i = 0; i < KVM_MAX_VCPUS; ++i) {
                        vcpu = kvm->vcpus[i];
                        if (vcpu)
                                *val += *(u32 *)((void *)vcpu + offset);
                }
        spin_unlock(&kvm_lock);
        return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n");

static struct file_operations *stat_fops[] = {
        [KVM_STAT_VCPU] = &vcpu_stat_fops,
        [KVM_STAT_VM]   = &vm_stat_fops,
};

static void kvm_init_debug(void)
{
        struct kvm_stats_debugfs_item *p;

        kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
        for (p = debugfs_entries; p->name; ++p)
                p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
                                                (void *)(long)p->offset,
                                                stat_fops[p->kind]);
}

static void kvm_exit_debug(void)
{
        struct kvm_stats_debugfs_item *p;

        for (p = debugfs_entries; p->name; ++p)
                debugfs_remove(p->dentry);
        debugfs_remove(kvm_debugfs_dir);
}

static int kvm_suspend(struct sys_device *dev, pm_message_t state)
{
        hardware_disable(NULL);
        return 0;
}

static int kvm_resume(struct sys_device *dev)
{
        hardware_enable(NULL);
        return 0;
}

static struct sysdev_class kvm_sysdev_class = {
        .name = "kvm",
        .suspend = kvm_suspend,
        .resume = kvm_resume,
};

static struct sys_device kvm_sysdev = {
        .id = 0,
        .cls = &kvm_sysdev_class,
};

struct page *bad_page;
pfn_t bad_pfn;

static inline
struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
{
        return container_of(pn, struct kvm_vcpu, preempt_notifier);
}

static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
{
        struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);

        kvm_arch_vcpu_load(vcpu, cpu);
}

static void kvm_sched_out(struct preempt_notifier *pn,
                          struct task_struct *next)
{
        struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);

        kvm_arch_vcpu_put(vcpu);
}

int kvm_init(void *opaque, unsigned int vcpu_size,
                  struct module *module)
{
        int r;
        int cpu;

        kvm_init_debug();

        r = kvm_arch_init(opaque);
        if (r)
                goto out_fail;

        bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO);

        if (bad_page == NULL) {
                r = -ENOMEM;
                goto out;
        }

        bad_pfn = page_to_pfn(bad_page);

        r = kvm_arch_hardware_setup();
        if (r < 0)
                goto out_free_0;

        for_each_online_cpu(cpu) {
                smp_call_function_single(cpu,
                                kvm_arch_check_processor_compat,
                                &r, 1);
                if (r < 0)
                        goto out_free_1;
        }

        on_each_cpu(hardware_enable, NULL, 1);
        r = register_cpu_notifier(&kvm_cpu_notifier);
        if (r)
                goto out_free_2;
        register_reboot_notifier(&kvm_reboot_notifier);

        r = sysdev_class_register(&kvm_sysdev_class);
        if (r)
                goto out_free_3;

        r = sysdev_register(&kvm_sysdev);
        if (r)
                goto out_free_4;

        /* A kmem cache lets us meet the alignment requirements of fx_save. */
        kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size,
                                           __alignof__(struct kvm_vcpu),
                                           0, NULL);
        if (!kvm_vcpu_cache) {
                r = -ENOMEM;
                goto out_free_5;
        }

        kvm_chardev_ops.owner = module;
        kvm_vm_fops.owner = module;
        kvm_vcpu_fops.owner = module;

        r = misc_register(&kvm_dev);
        if (r) {
                printk(KERN_ERR "kvm: misc device register failed\n");
                goto out_free;
        }

        kvm_preempt_ops.sched_in = kvm_sched_in;
        kvm_preempt_ops.sched_out = kvm_sched_out;
#ifndef CONFIG_X86
        msi2intx = 0;
#endif

        return 0;

out_free:
        kmem_cache_destroy(kvm_vcpu_cache);
out_free_5:
        sysdev_unregister(&kvm_sysdev);
out_free_4:
        sysdev_class_unregister(&kvm_sysdev_class);
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_0:
        __free_page(bad_page);
out:
        kvm_arch_exit();
        kvm_exit_debug();
out_fail:
        return r;
}
EXPORT_SYMBOL_GPL(kvm_init);

void kvm_exit(void)
{
        kvm_trace_cleanup();
        misc_deregister(&kvm_dev);
        kmem_cache_destroy(kvm_vcpu_cache);
        sysdev_unregister(&kvm_sysdev);
        sysdev_class_unregister(&kvm_sysdev_class);
        unregister_reboot_notifier(&kvm_reboot_notifier);
        unregister_cpu_notifier(&kvm_cpu_notifier);
        on_each_cpu(hardware_disable, NULL, 1);
        kvm_arch_hardware_unsetup();
        kvm_arch_exit();
        kvm_exit_debug();
        __free_page(bad_page);
}
EXPORT_SYMBOL_GPL(kvm_exit);