path: root/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>

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

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

/*
 * 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)
{
}

void kvm_flush_remote_tlbs(struct kvm *kvm)
{
	int i, cpu;
	cpumask_t cpus;
	struct kvm_vcpu *vcpu;

	cpus_clear(cpus);
	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
		vcpu = kvm->vcpus[i];
		if (!vcpu)
			continue;
		if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
			continue;
		cpu = vcpu->cpu;
		if (cpu != -1 && cpu != raw_smp_processor_id())
			cpu_set(cpu, cpus);
	}
	if (cpus_empty(cpus))
		return;
	++kvm->stat.remote_tlb_flush;
	smp_call_function_mask(cpus, ack_flush, NULL, 1);
}

void kvm_reload_remote_mmus(struct kvm *kvm)
{
	int i, cpu;
	cpumask_t cpus;
	struct kvm_vcpu *vcpu;

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


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);

static struct kvm *kvm_create_vm(void)
{
	struct kvm *kvm = kvm_arch_create_vm();

	if (IS_ERR(kvm))
		goto out;

	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);
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);
	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 (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_