kvm_main.c

来自「linux 内核源代码」· C语言 代码 · 共 2,825 行 · 第 1/5 页

	mutex_lock(&vcpu->kvm->lock);
	/*
	 * Does the new cr3 value map to physical memory? (Note, we
	 * catch an invalid cr3 even in real-mode, because it would
	 * cause trouble later on when we turn on paging anyway.)
	 *
	 * A real CPU would silently accept an invalid cr3 and would
	 * attempt to use it - with largely undefined (and often hard
	 * to debug) behavior on the guest side.
	 */
	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
		inject_gp(vcpu);
	else {
		vcpu->cr3 = cr3;
		vcpu->mmu.new_cr3(vcpu);
	}
	mutex_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr3);

void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	if (cr8 & CR8_RESERVED_BITS) {
		printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
		inject_gp(vcpu);
		return;
	}
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_tpr(vcpu, cr8);
	else
		vcpu->cr8 = cr8;
}
EXPORT_SYMBOL_GPL(set_cr8);

unsigned long get_cr8(struct kvm_vcpu *vcpu)
{
	if (irqchip_in_kernel(vcpu->kvm))
		return kvm_lapic_get_cr8(vcpu);
	else
		return vcpu->cr8;
}
EXPORT_SYMBOL_GPL(get_cr8);

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
	if (irqchip_in_kernel(vcpu->kvm))
		return vcpu->apic_base;
	else
		return vcpu->apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);

void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
	/* TODO: reserve bits check */
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_base(vcpu, data);
	else
		vcpu->apic_base = data;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

void fx_init(struct kvm_vcpu *vcpu)
{
	unsigned after_mxcsr_mask;

	/* Initialize guest FPU by resetting ours and saving into guest's */
	preempt_disable();
	fx_save(&vcpu->host_fx_image);
	fpu_init();
	fx_save(&vcpu->guest_fx_image);
	fx_restore(&vcpu->host_fx_image);
	preempt_enable();

	vcpu->cr0 |= X86_CR0_ET;
	after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
	vcpu->guest_fx_image.mxcsr = 0x1f80;
	memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask,
	       0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
}
EXPORT_SYMBOL_GPL(fx_init);

/*
 * Allocate some memory and give it an address in the guest physical address
 * space.
 *
 * Discontiguous memory is allowed, mostly for framebuffers.
 */
static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
					  struct kvm_memory_region *mem)
{
	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)
		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;

	mutex_lock(&kvm->lock);

	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_unlock;

	/* 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_unlock;
	}

	/* Deallocate if slot is being removed */
	if (!npages)
		new.phys_mem = NULL;

	/* 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 */
	if (npages && !new.phys_mem) {
		new.phys_mem = vmalloc(npages * sizeof(struct page *));

		if (!new.phys_mem)
			goto out_unlock;

		memset(new.phys_mem, 0, npages * sizeof(struct page *));
		for (i = 0; i < npages; ++i) {
			new.phys_mem[i] = alloc_page(GFP_HIGHUSER
						     | __GFP_ZERO);
			if (!new.phys_mem[i])
				goto out_unlock;
			set_page_private(new.phys_mem[i],0);
		}
	}

	/* 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_unlock;
		memset(new.dirty_bitmap, 0, dirty_bytes);
	}

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

	*memslot = new;

	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
	kvm_flush_remote_tlbs(kvm);

	mutex_unlock(&kvm->lock);

	kvm_free_physmem_slot(&old, &new);
	return 0;

out_unlock:
	mutex_unlock(&kvm->lock);
	kvm_free_physmem_slot(&new, &old);
out:
	return r;
}

/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				      struct kvm_dirty_log *log)
{
	struct kvm_memory_slot *memslot;
	int r, i;
	int n;
	unsigned long any = 0;

	mutex_lock(&kvm->lock);

	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 nothing is dirty, don't bother messing with page tables. */
	if (any) {
		kvm_mmu_slot_remove_write_access(kvm, log->slot);
		kvm_flush_remote_tlbs(kvm);
		memset(memslot->dirty_bitmap, 0, n);
	}

	r = 0;

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

/*
 * Set a new alias region.  Aliases map a portion of physical memory into
 * another portion.  This is useful for memory windows, for example the PC
 * VGA region.
 */
static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
					 struct kvm_memory_alias *alias)
{
	int r, n;
	struct kvm_mem_alias *p;

	r = -EINVAL;
	/* General sanity checks */
	if (alias->memory_size & (PAGE_SIZE - 1))
		goto out;
	if (alias->guest_phys_addr & (PAGE_SIZE - 1))
		goto out;
	if (alias->slot >= KVM_ALIAS_SLOTS)
		goto out;
	if (alias->guest_phys_addr + alias->memory_size
	    < alias->guest_phys_addr)
		goto out;
	if (alias->target_phys_addr + alias->memory_size
	    < alias->target_phys_addr)
		goto out;

	mutex_lock(&kvm->lock);

	p = &kvm->aliases[alias->slot];
	p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
	p->npages = alias->memory_size >> PAGE_SHIFT;
	p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;

	for (n = KVM_ALIAS_SLOTS; n > 0; --n)
		if (kvm->aliases[n - 1].npages)
			break;
	kvm->naliases = n;

	kvm_mmu_zap_all(kvm);

	mutex_unlock(&kvm->lock);

	return 0;

out:
	return r;
}

static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		memcpy (&chip->chip.pic,
			&pic_irqchip(kvm)->pics[0],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		memcpy (&chip->chip.pic,
			&pic_irqchip(kvm)->pics[1],
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_IOAPIC:
		memcpy (&chip->chip.ioapic,
			ioapic_irqchip(kvm),
			sizeof(struct kvm_ioapic_state));
		break;
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
	int r;

	r = 0;
	switch (chip->chip_id) {
	case KVM_IRQCHIP_PIC_MASTER:
		memcpy (&pic_irqchip(kvm)->pics[0],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_PIC_SLAVE:
		memcpy (&pic_irqchip(kvm)->pics[1],
			&chip->chip.pic,
			sizeof(struct kvm_pic_state));
		break;
	case KVM_IRQCHIP_IOAPIC:
		memcpy (ioapic_irqchip(kvm),
			&chip->chip.ioapic,
			sizeof(struct kvm_ioapic_state));
		break;
	default:
		r = -EINVAL;
		break;
	}
	kvm_pic_update_irq(pic_irqchip(kvm));
	return r;
}

static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
	int i;
	struct kvm_mem_alias *alias;

	for (i = 0; i < kvm->naliases; ++i) {
		alias = &kvm->aliases[i];
		if (gfn >= alias->base_gfn
		    && gfn < alias->base_gfn + alias->npages)
			return alias->target_gfn + gfn - alias->base_gfn;
	}
	return gfn;
}

static struct kvm_memory_slot *__gfn_to_memslot(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;
}

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

struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *slot;

	gfn = unalias_gfn(kvm, gfn);
	slot = __gfn_to_memslot(kvm, gfn);
	if (!slot)
		return NULL;
	return slot->phys_mem[gfn - slot->base_gfn];
}
EXPORT_SYMBOL_GPL(gfn_to_page);

/* WARNING: Does not work on aliased pages. */
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *memslot;

	memslot = __gfn_to_memslot(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);
	}
}

int emulator_read_std(unsigned long addr,
			     void *val,
			     unsigned int bytes,
			     struct kvm_vcpu *vcpu)
{
	void *data = val;

	while (bytes) {
		gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
		unsigned offset = addr & (PAGE_SIZE-1);
		unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
		unsigned long pfn;
		struct page *page;
		void *page_virt;

		if (gpa == UNMAPPED_GVA)
			return X86EMUL_PROPAGATE_FAULT;
		pfn = gpa >> PAGE_SHIFT;
		page = gfn_to_page(vcpu->kvm, pfn);
		if (!page)
			return X86EMUL_UNHANDLEABLE;
		page_virt = kmap_atomic(page, KM_USER0);

		memcpy(data, page_virt + offset, tocopy);

		kunmap_atomic(page_virt, KM_USER0);

		bytes -= tocopy;
		data += tocopy;
		addr += tocopy;
	}

	return X86EMUL_CONTINUE;
}
EXPORT_SYMBOL_GPL(emulator_read_std);

static int emulator_write_std(unsigned long addr,
			      const void *val,
			      unsigned int bytes,
			      struct kvm_vcpu *vcpu)
{
	pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes);
	return X86EMUL_UNHANDLEABLE;
}

/*
 * Only apic need an MMIO device hook, so shortcut now..
 */
static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
						gpa_t addr)
{
	struct kvm_io_device *dev;

	if (vcpu->apic) {
		dev = &vcpu->apic->dev;
		if (dev->in_range(dev, addr))
			return dev;
	}
	return NULL;
}

static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
						gpa_t addr)
{
	struct kvm_io_device *dev;

	dev = vcpu_find_pervcpu_dev(vcpu, addr);
	if (dev == NULL)
		dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
	return dev;
}

static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
					       gpa_t addr)
{
	return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr);
}

static int emulator_read_emulated(unsigned long addr,
				  void *val,
				  unsigned int bytes,
				  struct kvm_vcpu *vcpu)
{
	struct kvm_io_device *mmio_dev;
	gpa_t                 gpa;

	if (vcpu->mmio_read_completed) {
		memcpy(val, vcpu->mmio_data, bytes);
		vcpu->mmio_read_completed = 0;
		return X86EMUL_CONTINUE;
	} else if (emulator_read_std(addr, val, bytes, vcpu)
		   == X86EMUL_CONTINUE)
		return X86EMUL_CONTINUE;

	gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
	if (gpa == UNMAPPED_GVA)
		return X86EMUL_PROPAGATE_FAULT;

	/*
	 * Is this MMIO handled locally?
	 */
	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
	if (mmio_dev) {
		kvm_iodevice_read(mmio_dev, gpa, bytes, val);
		return X86EMUL_CONTINUE;
	}

	vcpu->mmio_needed = 1;
	vcpu->mmio_phys_addr = gpa;
	vcpu->mmio_size = bytes;
	vcpu->mmio_is_write = 0;

	return X86EMUL_UNHANDLEABLE;
}

static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
			       const void *val, int bytes)
{
	struct page *page;
	void *virt;

	if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
		return 0;
	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
	if (!page)
		return 0;
	mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
	virt = kmap_atomic(page, KM_USER0);
	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
	memcpy(virt + offset_in_page(gpa), val, bytes);
	kunmap_atomic(virt, KM_USER0);
	return 1;
}

static int emulator_write_emulated_onepage(unsigned long addr,
					   const void *val,
					   unsigned int bytes,
					   struct kvm_vcpu *vcpu)
{
	struct kvm_io_device *mmio_dev;
	gpa_t                 gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);

	if (gpa == UNMAPPED_GVA) {
		kvm_x86_ops->inject_page_fault(vcpu, addr, 2);
		return X86EMUL_PROPAGATE_FAULT;
	}

	if (emulator_write_phys(vcpu, gpa, val, bytes))
		return X86EMUL_CONTINUE;

	/*
	 * Is this MMIO handled locally?
	 */
	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
	if (mmio_dev) {
		kvm_iodevice_write(mmio_dev, gpa, bytes, val);