kvm_main.c

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

		       sizeof sregs->interrupt_bitmap);
		pending_vec = kvm_x86_ops->get_irq(vcpu);
		if (pending_vec >= 0)
			set_bit(pending_vec, (unsigned long *)sregs->interrupt_bitmap);
	} else
		memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
		       sizeof sregs->interrupt_bitmap);

	vcpu_put(vcpu);

	return 0;
}

static void set_segment(struct kvm_vcpu *vcpu,
			struct kvm_segment *var, int seg)
{
	return kvm_x86_ops->set_segment(vcpu, var, seg);
}

static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				    struct kvm_sregs *sregs)
{
	int mmu_reset_needed = 0;
	int i, pending_vec, max_bits;
	struct descriptor_table dt;

	vcpu_load(vcpu);

	dt.limit = sregs->idt.limit;
	dt.base = sregs->idt.base;
	kvm_x86_ops->set_idt(vcpu, &dt);
	dt.limit = sregs->gdt.limit;
	dt.base = sregs->gdt.base;
	kvm_x86_ops->set_gdt(vcpu, &dt);

	vcpu->cr2 = sregs->cr2;
	mmu_reset_needed |= vcpu->cr3 != sregs->cr3;
	vcpu->cr3 = sregs->cr3;

	set_cr8(vcpu, sregs->cr8);

	mmu_reset_needed |= vcpu->shadow_efer != sregs->efer;
#ifdef CONFIG_X86_64
	kvm_x86_ops->set_efer(vcpu, sregs->efer);
#endif
	kvm_set_apic_base(vcpu, sregs->apic_base);

	kvm_x86_ops->decache_cr4_guest_bits(vcpu);

	mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
	vcpu->cr0 = sregs->cr0;
	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);

	mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
	if (!is_long_mode(vcpu) && is_pae(vcpu))
		load_pdptrs(vcpu, vcpu->cr3);

	if (mmu_reset_needed)
		kvm_mmu_reset_context(vcpu);

	if (!irqchip_in_kernel(vcpu->kvm)) {
		memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
		       sizeof vcpu->irq_pending);
		vcpu->irq_summary = 0;
		for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
			if (vcpu->irq_pending[i])
				__set_bit(i, &vcpu->irq_summary);
	} else {
		max_bits = (sizeof sregs->interrupt_bitmap) << 3;
		pending_vec = find_first_bit(
			(const unsigned long *)sregs->interrupt_bitmap,
			max_bits);
		/* Only pending external irq is handled here */
		if (pending_vec < max_bits) {
			kvm_x86_ops->set_irq(vcpu, pending_vec);
			printk("Set back pending irq %d\n", pending_vec);
		}
	}

	set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
	set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
	set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
	set_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
	set_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
	set_segment(vcpu, &sregs->ss, VCPU_SREG_SS);

	set_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
	set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);

	vcpu_put(vcpu);

	return 0;
}

void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
	struct kvm_segment cs;

	get_segment(vcpu, &cs, VCPU_SREG_CS);
	*db = cs.db;
	*l = cs.l;
}
EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * This list is modified at module load time to reflect the
 * capabilities of the host cpu.
 */
static u32 msrs_to_save[] = {
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_K6_STAR,
#ifdef CONFIG_X86_64
	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
	MSR_IA32_TIME_STAMP_COUNTER,
};

static unsigned num_msrs_to_save;

static u32 emulated_msrs[] = {
	MSR_IA32_MISC_ENABLE,
};

static __init void kvm_init_msr_list(void)
{
	u32 dummy[2];
	unsigned i, j;

	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
			continue;
		if (j < i)
			msrs_to_save[j] = msrs_to_save[i];
		j++;
	}
	num_msrs_to_save = j;
}

/*
 * Adapt set_msr() to msr_io()'s calling convention
 */
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_set_msr(vcpu, index, *data);
}

/*
 * Read or write a bunch of msrs. All parameters are kernel addresses.
 *
 * @return number of msrs set successfully.
 */
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
		    struct kvm_msr_entry *entries,
		    int (*do_msr)(struct kvm_vcpu *vcpu,
				  unsigned index, u64 *data))
{
	int i;

	vcpu_load(vcpu);

	for (i = 0; i < msrs->nmsrs; ++i)
		if (do_msr(vcpu, entries[i].index, &entries[i].data))
			break;

	vcpu_put(vcpu);

	return i;
}

/*
 * Read or write a bunch of msrs. Parameters are user addresses.
 *
 * @return number of msrs set successfully.
 */
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
		  int (*do_msr)(struct kvm_vcpu *vcpu,
				unsigned index, u64 *data),
		  int writeback)
{
	struct kvm_msrs msrs;
	struct kvm_msr_entry *entries;
	int r, n;
	unsigned size;

	r = -EFAULT;
	if (copy_from_user(&msrs, user_msrs, sizeof msrs))
		goto out;

	r = -E2BIG;
	if (msrs.nmsrs >= MAX_IO_MSRS)
		goto out;

	r = -ENOMEM;
	size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
	entries = vmalloc(size);
	if (!entries)
		goto out;

	r = -EFAULT;
	if (copy_from_user(entries, user_msrs->entries, size))
		goto out_free;

	r = n = __msr_io(vcpu, &msrs, entries, do_msr);
	if (r < 0)
		goto out_free;

	r = -EFAULT;
	if (writeback && copy_to_user(user_msrs->entries, entries, size))
		goto out_free;

	r = n;

out_free:
	vfree(entries);
out:
	return r;
}

/*
 * Translate a guest virtual address to a guest physical address.
 */
static int kvm_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				    struct kvm_translation *tr)
{
	unsigned long vaddr = tr->linear_address;
	gpa_t gpa;

	vcpu_load(vcpu);
	mutex_lock(&vcpu->kvm->lock);
	gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
	tr->physical_address = gpa;
	tr->valid = gpa != UNMAPPED_GVA;
	tr->writeable = 1;
	tr->usermode = 0;
	mutex_unlock(&vcpu->kvm->lock);
	vcpu_put(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
				    struct kvm_interrupt *irq)
{
	if (irq->irq < 0 || irq->irq >= 256)
		return -EINVAL;
	if (irqchip_in_kernel(vcpu->kvm))
		return -ENXIO;
	vcpu_load(vcpu);

	set_bit(irq->irq, vcpu->irq_pending);
	set_bit(irq->irq / BITS_PER_LONG, &vcpu->irq_summary);

	vcpu_put(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
				      struct kvm_debug_guest *dbg)
{
	int r;

	vcpu_load(vcpu);

	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);

	vcpu_put(vcpu);

	return r;
}

static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma,
				    unsigned long address,
				    int *type)
{
	struct kvm_vcpu *vcpu = vma->vm_file->private_data;
	unsigned long pgoff;
	struct page *page;

	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	if (pgoff == 0)
		page = virt_to_page(vcpu->run);
	else if (pgoff == KVM_PIO_PAGE_OFFSET)
		page = virt_to_page(vcpu->pio_data);
	else
		return NOPAGE_SIGBUS;
	get_page(page);
	if (type != NULL)
		*type = VM_FAULT_MINOR;

	return page;
}

static struct vm_operations_struct kvm_vcpu_vm_ops = {
	.nopage = kvm_vcpu_nopage,
};

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;

	fput(vcpu->kvm->filp);
	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, r;
	struct inode *inode;
	struct file *file;

	r = anon_inode_getfd(&fd, &inode, &file,
			     "kvm-vcpu", &kvm_vcpu_fops, vcpu);
	if (r)
		return r;
	atomic_inc(&vcpu->kvm->filp->f_count);
	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_x86_ops->vcpu_create(kvm, n);
	if (IS_ERR(vcpu))
		return PTR_ERR(vcpu);

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

	/* We do fxsave: this must be aligned. */
	BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF);

	vcpu_load(vcpu);
	r = kvm_mmu_setup(vcpu);
	vcpu_put(vcpu);
	if (r < 0)
		goto free_vcpu;

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

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

unlink:
	mutex_lock(&kvm->lock);
	kvm->vcpus[n] = NULL;
	mutex_unlock(&kvm->lock);

mmu_unload:
	vcpu_load(vcpu);
	kvm_mmu_unload(vcpu);
	vcpu_put(vcpu);

free_vcpu:
	kvm_x86_ops->vcpu_free(vcpu);
	return r;
}

static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
{
	u64 efer;
	int i;
	struct kvm_cpuid_entry *e, *entry;

	rdmsrl(MSR_EFER, efer);
	entry = NULL;
	for (i = 0; i < vcpu->cpuid_nent; ++i) {
		e = &vcpu->cpuid_entries[i];
		if (e->function == 0x80000001) {
			entry = e;
			break;
		}
	}
	if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) {
		entry->edx &= ~(1 << 20);
		printk(KERN_INFO "kvm: guest NX capability removed\n");
	}
}

static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
				    struct kvm_cpuid *cpuid,
				    struct kvm_cpuid_entry __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -EFAULT;
	if (copy_from_user(&vcpu->cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
		goto out;
	vcpu->cpuid_nent = cpuid->nent;
	cpuid_fix_nx_cap(vcpu);
	return 0;

out:
	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;
}

/*
 * fxsave fpu state.  Taken from x86_64/processor.h.  To be killed when
 * we have asm/x86/processor.h
 */
struct fxsave {
	u16	cwd;
	u16	swd;
	u16	twd;
	u16	fop;
	u64	rip;
	u64	rdp;
	u32	mxcsr;
	u32	mxcsr_mask;
	u32	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
#ifdef CONFIG_X86_64
	u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg = 256 bytes */
#else
	u32	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
#endif
};

static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;

	vcpu_load(vcpu);

	memcpy(fpu->fpr, fxsave->st_space, 128);
	fpu->fcw = fxsave->cwd;
	fpu->fsw = fxsave->swd;
	fpu->ftwx = fxsave->twd;
	fpu->last_opcode = fxsave->fop;
	fpu->last_ip = fxsave->rip;
	fpu->last_dp = fxsave->rdp;
	memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);

	vcpu_put(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;

	vcpu_load(vcpu);

	memcpy(fxsave->st_space, fpu->fpr, 128);
	fxsave->cwd = fpu->fcw;
	fxsave->swd = fpu->fsw;
	fxsave->twd = fpu->ftwx;
	fxsave->fop = fpu->last_opcode;
	fxsave->rip = fpu->last_ip;
	fxsave->rdp = fpu->last_dp;
	memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);

	vcpu_put(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	vcpu_load(vcpu);
	memcpy(s->regs, vcpu->apic->regs, sizeof *s);
	vcpu_put(vcpu);

	return 0;
}

static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
				    struct kvm_lapic_state *s)
{
	vcpu_load(vcpu);
	memcpy(vcpu->apic->regs, s->regs, sizeof *s);
	kvm_apic_post_state_restore(vcpu);
	vcpu_put(vcpu);

	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 = -EINVAL;

	switch (ioctl) {
	case KVM_RUN:
		r = -EINVAL;
		if (arg)
			goto out;
		r = kvm_vcpu_ioctl_run(vcpu, vcpu->run);
		break;
	case KVM_GET_REGS: {
		struct kvm_regs kvm_regs;

		memset(&kvm_regs, 0, sizeof kvm_regs);
		r = kvm_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_REGS: {
		struct kvm_regs kvm_regs;

		r = -EFAULT;
		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
			goto out;
		r = kvm_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
		if