KVM 代码详解

struct kvm {
	struct mutex lock; /* protects the vcpus array and APIC accesses */
	spinlock_t mmu_lock;
	struct rw_semaphore slots_lock;
	struct mm_struct *mm; /* userspace tied to this vm */
	int nmemslots;
	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
					KVM_PRIVATE_MEM_SLOTS];
	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
	struct list_head vm_list;
	struct file *filp;
	struct kvm_io_bus mmio_bus;
	struct kvm_io_bus pio_bus;
	struct kvm_vm_stat stat;
	struct kvm_arch arch;
};

struct kvm_vcpu {
	struct kvm *kvm;
	struct preempt_notifier preempt_notifier;
	int vcpu_id;
	struct mutex mutex;
	int   cpu;
	struct kvm_run *run;
	int guest_mode;
	unsigned long requests;
	struct kvm_guest_debug guest_debug;
	int fpu_active;
	int guest_fpu_loaded;
	wait_queue_head_t wq;
	int sigset_active;
	sigset_t sigset;
	struct kvm_vcpu_stat stat;

#ifdef CONFIG_HAS_IOMEM
	int mmio_needed;
	int mmio_read_completed;
	int mmio_is_write;
	int mmio_size;
	unsigned char mmio_data[8];
	gpa_t mmio_phys_addr;
#endif

	struct kvm_vcpu_arch arch;
};

 

struct kvm_vcpu_arch {
	u64 host_tsc;
	int interrupt_window_open;
	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
	unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */
	unsigned long rip;      /* needs vcpu_load_rsp_rip() */

	unsigned long cr0;
	unsigned long cr2;
	unsigned long cr3;
	unsigned long cr4;
	unsigned long cr8;
	u64 pdptrs[4]; /* pae */
	u64 shadow_efer;
	u64 apic_base;
	struct kvm_lapic *apic;    /* kernel irqchip context */
#define VCPU_MP_STATE_RUNNABLE          0
#define VCPU_MP_STATE_UNINITIALIZED     1
#define VCPU_MP_STATE_INIT_RECEIVED     2
#define VCPU_MP_STATE_SIPI_RECEIVED     3
#define VCPU_MP_STATE_HALTED            4
	int mp_state;
	int sipi_vector;
	u64 ia32_misc_enable_msr;
	bool tpr_access_reporting;

	struct kvm_mmu mmu;

	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
	struct kvm_mmu_memory_cache mmu_page_cache;
	struct kvm_mmu_memory_cache mmu_page_header_cache;

	gfn_t last_pt_write_gfn;
	int   last_pt_write_count;
	u64  *last_pte_updated;

	struct {
		gfn_t gfn;          /* presumed gfn during guest pte update */
		struct page *page;  /* page corresponding to that gfn */
	} update_pte;

	struct i387_fxsave_struct host_fx_image;
	struct i387_fxsave_struct guest_fx_image;

	gva_t mmio_fault_cr2;
	struct kvm_pio_request pio;
	void *pio_data;

	struct kvm_queued_exception {
		bool pending;
		bool has_error_code;
		u8 nr;
		u32 error_code;
	} exception;

	struct {
		int active;
		u8 save_iopl;
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
		} tr, es, ds, fs, gs;
	} rmode;
	int halt_request; /* real mode on Intel only */

	int cpuid_nent;
	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
	/* emulate context */

	struct x86_emulate_ctxt emulate_ctxt;
};

 

 

1.创建虚拟机

vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0)；

static int kvm_dev_ioctl_create_vm(void)
{
	int fd, r;
	struct inode *inode;
	struct file *file;
	struct kvm *kvm;

	kvm = kvm_create_vm();
	if (IS_ERR(kvm))
		return PTR_ERR(kvm);
	r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm);
	if (r) {
		kvm_destroy_vm(kvm);
		return r;
	}

	kvm->filp = file;

	return fd;
}

这个kvm_vm_fops有个mmap的地址，估计和用户态的fd有关。

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);
	spin_lock(&kvm_lock);
	list_add(&kvm->vm_list, &vm_list);
	spin_unlock(&kvm_lock);
out:
	return kvm;
}

create下面有一些list，估计和vm的组织有关，暂先不关。

struct  kvm *kvm_arch_create_vm(void)
{
	struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);

	if (!kvm)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);

	return kvm;
}

这段代码更简单，就是个list的初始化。

 

创建vm的过程围绕struct  kvm *kvm = kvm_create_vm();

2.设置虚拟机内存

struct kvm_userspace_memory_region region={

.slot = 0,

.guest_phys_addr = 0,

.memory_size = ram_size,

.userspace_addr = (u64)ram_start

};

ioctl(vm_fd, KVM_SET_USER_MEMORY_REGION, &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);
}

 

 

 

 

3.新建虚拟CPU

vcpu->vcpu_fd = ioctl(kvm->vm_fd, KVM_CREATE_VCPU, i);

/*
 * 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)
		goto vcpu_destroy;

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

创建虚拟cpu就是填充kvm_vcpu结构体的过程。过程如下vmx_create_vcpu:

这里有个vmx用来保存cpu的各种状态，恢复cpu的运行。但最后只返回了vcpu。

static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
{
	int err;
	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
	int cpu;

	if (!vmx)
		return ERR_PTR(-ENOMEM);

	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
	if (err)
		goto free_vcpu;

	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!vmx->guest_msrs) {
		err = -ENOMEM;
		goto uninit_vcpu;
	}

	vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!vmx->host_msrs)
		goto free_guest_msrs;

	vmx->vmcs = alloc_vmcs();
	if (!vmx->vmcs)
		goto free_msrs;

	vmcs_clear(vmx->vmcs);

	cpu = get_cpu();
	vmx_vcpu_load(&vmx->vcpu, cpu);
	err = vmx_vcpu_setup(vmx);
	vmx_vcpu_put(&vmx->vcpu);
	put_cpu();
	if (err)
		goto free_vmcs;
	if (vm_need_virtualize_apic_accesses(kvm))
		if (alloc_apic_access_page(kvm) != 0)
			goto free_vmcs;

	return &vmx->vcpu;

free_vmcs:
	free_vmcs(vmx->vmcs);
free_msrs:
	kfree(vmx->host_msrs);
free_guest_msrs:
	kfree(vmx->guest_msrs);
uninit_vcpu:
	kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
	kmem_cache_free(kvm_vcpu_cache, vmx);
	return ERR_PTR(err);
}

struct vcpu_vmx {
	struct kvm_vcpu       vcpu;
	int                   launched;
	u8                    fail;
	u32                   idt_vectoring_info;
	struct kvm_msr_entry *guest_msrs;
	struct kvm_msr_entry *host_msrs;
	int                   nmsrs;
	int                   save_nmsrs;
	int                   msr_offset_efer;
#ifdef CONFIG_X86_64
	int                   msr_offset_kernel_gs_base;
#endif
	struct vmcs          *vmcs;
	struct {
		int           loaded;
		u16           fs_sel, gs_sel, ldt_sel;
		int           gs_ldt_reload_needed;
		int           fs_reload_needed;
		int           guest_efer_loaded;
	} host_state;
	struct {
		struct {
			bool pending;
			u8 vector;
			unsigned rip;
		} irq;
	} rmode;
};

 

接下来这个kvm_vcpu_init 把kvm_vpcu的run成员复制为页的地址。

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);

	vcpu->run = page_address(page);

	r = kvm_arch_vcpu_init(vcpu);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_init);

这里还是对struct kvm_vcpu 结构的arch成员进行赋值。

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
	struct page *page;
	struct kvm *kvm;
	int r;

	kvm = vcpu->kvm;

	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
	if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
		vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
	else
		vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED;

	page = alloc_page(GFP_KERNEL | __GFP_ZERO);

	vcpu->arch.pio_data = page_address(page);

	r = kvm_mmu_create(vcpu);

	if (irqchip_in_kernel(kvm)) {
		r = kvm_create_lapic(vcpu);
		if (r < 0)
			goto fail_mmu_destroy;
	}

	return 0;

}

再看下kvm_arch_vcpu_setup

int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
	int r;

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

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

	return 0;
free_vcpu:
	kvm_x86_ops->vcpu_free(vcpu);
	return r;
}

vmx和kvm_vcpu可以相互转化

static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u64 msr;
	int ret;

	if (!init_rmode_tss(vmx->vcpu.kvm)) {
		ret = -ENOMEM;
		goto out;
	}

	vmx->vcpu.arch.rmode.active = 0;

	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
	set_cr8(&vmx->vcpu, 0);
	msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
	if (vmx->vcpu.vcpu_id == 0)
		msr |= MSR_IA32_APICBASE_BSP;
	kvm_set_apic_base(&vmx->vcpu, msr);

	fx_init(&vmx->vcpu);

	/*
	 * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
	 * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4.  Sigh.
	 */
	if (vmx->vcpu.vcpu_id == 0) {
		vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
		vmcs_writel(GUEST_CS_BASE, 0x000f0000);
	} else {
		vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8);
		vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12);
	}
	vmcs_write32(GUEST_CS_LIMIT, 0xffff);
	vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);

	seg_setup(VCPU_SREG_DS);
	seg_setup(VCPU_SREG_ES);
	seg_setup(VCPU_SREG_FS);
	seg_setup(VCPU_SREG_GS);
	seg_setup(VCPU_SREG_SS);

	vmcs_write16(GUEST_TR_SELECTOR, 0);
	vmcs_writel(GUEST_TR_BASE, 0);
	vmcs_write32(GUEST_TR_LIMIT, 0xffff);
	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);

	vmcs_write16(GUEST_LDTR_SELECTOR, 0);
	vmcs_writel(GUEST_LDTR_BASE, 0);
	vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
	vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);

	vmcs_write32(GUEST_SYSENTER_CS, 0);
	vmcs_writel(GUEST_SYSENTER_ESP, 0);
	vmcs_writel(GUEST_SYSENTER_EIP, 0);

	vmcs_writel(GUEST_RFLAGS, 0x02);
	if (vmx->vcpu.vcpu_id == 0)
		vmcs_writel(GUEST_RIP, 0xfff0);
	else
		vmcs_writel(GUEST_RIP, 0);
	vmcs_writel(GUEST_RSP, 0);

	/* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */
	vmcs_writel(GUEST_DR7, 0x400);

	vmcs_writel(GUEST_GDTR_BASE, 0);
	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);

	vmcs_writel(GUEST_IDTR_BASE, 0);
	vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);

	vmcs_write32(GUEST_ACTIVITY_STATE, 0);
	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
	vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);

	guest_write_tsc(0);

	/* Special registers */
	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);

	setup_msrs(vmx);

	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */

	if (cpu_has_vmx_tpr_shadow()) {
		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
		if (vm_need_tpr_shadow(vmx->vcpu.kvm))
			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
				page_to_phys(vmx->vcpu.arch.apic->regs_page));
		vmcs_write32(TPR_THRESHOLD, 0);
	}

	if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
		vmcs_write64(APIC_ACCESS_ADDR,
			     page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));

	vmx->vcpu.arch.cr0 = 0x60000010;
	vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
	vmx_set_cr4(&vmx->vcpu, 0);
#ifdef CONFIG_X86_64
	vmx_set_efer(&vmx->vcpu, 0);
#endif
	vmx_fpu_activate(&vmx->vcpu);
	update_exception_bitmap(&vmx->vcpu);

	return 0;

out:
	return ret;
}

static int init_kvm_mmu(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

	if (!is_paging(vcpu))
		return nonpaging_init_context(vcpu);
	else if (is_long_mode(vcpu))
		return paging64_init_context(vcpu);
	else if (is_pae(vcpu))
		return paging32E_init_context(vcpu);
	else
		return paging32_init_context(vcpu);
}

4.设置运行模式

static void vmx_set_segment(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg)
{
	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
	u32 ar;

	if (vcpu->arch.rmode.active && seg == VCPU_SREG_TR) {
		vcpu->arch.rmode.tr.selector = var->selector;
		vcpu->arch.rmode.tr.base = var->base;
		vcpu->arch.rmode.tr.limit = var->limit;
		vcpu->arch.rmode.tr.ar = vmx_segment_access_rights(var);
		return;
	}
	vmcs_writel(sf->base, var->base);
	vmcs_write32(sf->limit, var->limit);
	vmcs_write16(sf->selector, var->selector);
	if (vcpu->arch.rmode.active && var->s) {
		/*
		 * Hack real-mode segments into vm86 compatibility.
		 */
		if (var->base == 0xffff0000 && var->selector == 0xf000)
			vmcs_writel(sf->base, 0xf0000);
		ar = 0xf3;
	} else
		ar = vmx_segment_access_rights(var);
	vmcs_write32(sf->ar_bytes, ar);
}

 

5.运行虚拟机

ioctl(vcpu->fd, KVM_RUN, 0) < 0)

static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);
	u32 intr_info;

	/*
	 * Loading guest fpu may have cleared host cr0.ts
	 */
	vmcs_writel(HOST_CR0, read_cr0());

	asm(
		/* Store host registers */
#ifdef CONFIG_X86_64
		"push %%rdx; push %%rbp;"
		"push %%rcx \n\t"
#else
		"push %%edx; push %%ebp;"
		"push %%ecx \n\t"
#endif
		ASM_VMX_VMWRITE_RSP_RDX "\n\t"
		/* Check if vmlaunch of vmresume is needed */
		"cmpl $0, %c[launched](%0) \n\t"
		/* Load guest registers.  Don't clobber flags. */
#ifdef CONFIG_X86_64
		"mov %c[cr2](%0), %%rax \n\t"       //rax = vmx->cr2;
		"mov %%rax, %%cr2 \n\t"
		"mov %c[rax](%0), %%rax \n\t"
		"mov %c[rbx](%0), %%rbx \n\t"
		"mov %c[rdx](%0), %%rdx \n\t"
		"mov %c[rsi](%0), %%rsi \n\t"     
		"mov %c[rdi](%0), %%rdi \n\t"
		"mov %c[rbp](%0), %%rbp \n\t"
		"mov %c[r8](%0),  %%r8  \n\t"
		"mov %c[r9](%0),  %%r9  \n\t"
		"mov %c[r10](%0), %%r10 \n\t"
		"mov %c[r11](%0), %%r11 \n\t"
		"mov %c[r12](%0), %%r12 \n\t"
		"mov %c[r13](%0), %%r13 \n\t"
		"mov %c[r14](%0), %%r14 \n\t"
		"mov %c[r15](%0), %%r15 \n\t"
		"mov %c[rcx](%0), %%rcx \n\t" /* kills %0 (rcx) */
#else
		"mov %c[cr2](%0), %%eax \n\t"
		"mov %%eax,   %%cr2 \n\t"
		"mov %c[rax](%0), %%eax \n\t"
		"mov %c[rbx](%0), %%ebx \n\t"
		"mov %c[rdx](%0), %%edx \n\t"
		"mov %c[rsi](%0), %%esi \n\t"
		"mov %c[rdi](%0), %%edi \n\t"
		"mov %c[rbp](%0), %%ebp \n\t"
		"mov %c[rcx](%0), %%ecx \n\t" /* kills %0 (ecx) */
#endif
		/* Enter guest mode */
		"jne .Llaunched \n\t"
		ASM_VMX_VMLAUNCH "\n\t"
		"jmp .Lkvm_vmx_return \n\t"
		".Llaunched: " ASM_VMX_VMRESUME "\n\t"
		".Lkvm_vmx_return: "
		/* Save guest registers, load host registers, keep flags */
#ifdef CONFIG_X86_64
		"xchg %0,     (%%rsp) \n\t"
		"mov %%rax, %c[rax](%0) \n\t"
		"mov %%rbx, %c[rbx](%0) \n\t"
		"pushq (%%rsp); popq %c[rcx](%0) \n\t"
		"mov %%rdx, %c[rdx](%0) \n\t"
		"mov %%rsi, %c[rsi](%0) \n\t"
		"mov %%rdi, %c[rdi](%0) \n\t"
		"mov %%rbp, %c[rbp](%0) \n\t"
		"mov %%r8,  %c[r8](%0) \n\t"
		"mov %%r9,  %c[r9](%0) \n\t"
		"mov %%r10, %c[r10](%0) \n\t"
		"mov %%r11, %c[r11](%0) \n\t"
		"mov %%r12, %c[r12](%0) \n\t"
		"mov %%r13, %c[r13](%0) \n\t"
		"mov %%r14, %c[r14](%0) \n\t"
		"mov %%r15, %c[r15](%0) \n\t"
		"mov %%cr2, %%rax   \n\t"
		"mov %%rax, %c[cr2](%0) \n\t"

		"pop  %%rbp; pop  %%rbp; pop  %%rdx \n\t"
#else
		"xchg %0, (%%esp) \n\t"
		"mov %%eax, %c[rax](%0) \n\t"
		"mov %%ebx, %c[rbx](%0) \n\t"
		"pushl (%%esp); popl %c[rcx](%0) \n\t"
		"mov %%edx, %c[rdx](%0) \n\t"
		"mov %%esi, %c[rsi](%0) \n\t"
		"mov %%edi, %c[rdi](%0) \n\t"
		"mov %%ebp, %c[rbp](%0) \n\t"
		"mov %%cr2, %%eax  \n\t"
		"mov %%eax, %c[cr2](%0) \n\t"

		"pop %%ebp; pop %%ebp; pop %%edx \n\t"
#endif
		"setbe %c[fail](%0) \n\t"
	      : : "c"(vmx), "d"((unsigned long)HOST_RSP),
		[launched]"i"(offsetof(struct vcpu_vmx, launched)),
		[fail]"i"(offsetof(struct vcpu_vmx, fail)),
		[rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])),
		[rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])),
		[rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])),
		[rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])),
		[rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])),
		[rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])),
		[rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])),
#ifdef CONFIG_X86_64
		[r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])),
		[r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])),
		[r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])),
		[r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])),
		[r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])),
		[r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])),
		[r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])),
		[r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])),
#endif
		[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2))
	      : "cc", "memory"
#ifdef CONFIG_X86_64
		, "rbx", "rdi", "rsi"
		, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
#else
		, "ebx", "edi", "rsi"
#endif
	      );

	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
	if (vmx->rmode.irq.pending)
		fixup_rmode_irq(vmx);

	vcpu->arch.interrupt_window_open =
		(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;

	asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
	vmx->launched = 1;

	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);

	/* We need to handle NMIs before interrupts are enabled */
	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
		asm("int $2");
}

5.接管中断和其他异常

 

6.小结

最终VMM通过VMX 管理VMCS来实现虚拟机的执行管理。但我感觉核心还是在vmx_vcpu_run中，其他就是VMCS的状态初始化。我们预先要实现的状态要初始化到VMCS状态里，通过run函数把虚拟机跑起来。

一下是kvm中的一些关键结构，做了些简化：