vmx.c

来自「linux 内核源代码」· C语言 代码 · 共 2,567 行 · 第 1/5 页

}

static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	skip_emulated_instruction(vcpu);
	return kvm_hypercall(vcpu, kvm_run);
}

/*
 * The exit handlers return 1 if the exit was handled fully and guest execution
 * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
 * to be done to userspace and return 0.
 */
static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
				      struct kvm_run *kvm_run) = {
	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
	[EXIT_REASON_CR_ACCESS]               = handle_cr,
	[EXIT_REASON_DR_ACCESS]               = handle_dr,
	[EXIT_REASON_CPUID]                   = handle_cpuid,
	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
	[EXIT_REASON_HLT]                     = handle_halt,
	[EXIT_REASON_VMCALL]                  = handle_vmcall,
	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold
};

static const int kvm_vmx_max_exit_handlers =
	ARRAY_SIZE(kvm_vmx_exit_handlers);

/*
 * The guest has exited.  See if we can fix it or if we need userspace
 * assistance.
 */
static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	u32 vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
	u32 exit_reason = vmcs_read32(VM_EXIT_REASON);
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (unlikely(vmx->fail)) {
		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		kvm_run->fail_entry.hardware_entry_failure_reason
			= vmcs_read32(VM_INSTRUCTION_ERROR);
		return 0;
	}

	if ( (vectoring_info & VECTORING_INFO_VALID_MASK) &&
				exit_reason != EXIT_REASON_EXCEPTION_NMI )
		printk(KERN_WARNING "%s: unexpected, valid vectoring info and "
		       "exit reason is 0x%x\n", __FUNCTION__, exit_reason);
	if (exit_reason < kvm_vmx_max_exit_handlers
	    && kvm_vmx_exit_handlers[exit_reason])
		return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
	else {
		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
		kvm_run->hw.hardware_exit_reason = exit_reason;
	}
	return 0;
}

static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
}

static void update_tpr_threshold(struct kvm_vcpu *vcpu)
{
	int max_irr, tpr;

	if (!vm_need_tpr_shadow(vcpu->kvm))
		return;

	if (!kvm_lapic_enabled(vcpu) ||
	    ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) {
		vmcs_write32(TPR_THRESHOLD, 0);
		return;
	}

	tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4;
	vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4);
}

static void enable_irq_window(struct kvm_vcpu *vcpu)
{
	u32 cpu_based_vm_exec_control;

	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
	cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
}

static void vmx_intr_assist(struct kvm_vcpu *vcpu)
{
	u32 idtv_info_field, intr_info_field;
	int has_ext_irq, interrupt_window_open;
	int vector;

	kvm_inject_pending_timer_irqs(vcpu);
	update_tpr_threshold(vcpu);

	has_ext_irq = kvm_cpu_has_interrupt(vcpu);
	intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD);
	idtv_info_field = vmcs_read32(IDT_VECTORING_INFO_FIELD);
	if (intr_info_field & INTR_INFO_VALID_MASK) {
		if (idtv_info_field & INTR_INFO_VALID_MASK) {
			/* TODO: fault when IDT_Vectoring */
			printk(KERN_ERR "Fault when IDT_Vectoring\n");
		}
		if (has_ext_irq)
			enable_irq_window(vcpu);
		return;
	}
	if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) {
		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field);
		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
				vmcs_read32(VM_EXIT_INSTRUCTION_LEN));

		if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK))
			vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
				vmcs_read32(IDT_VECTORING_ERROR_CODE));
		if (unlikely(has_ext_irq))
			enable_irq_window(vcpu);
		return;
	}
	if (!has_ext_irq)
		return;
	interrupt_window_open =
		((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
		 (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0);
	if (interrupt_window_open) {
		vector = kvm_cpu_get_interrupt(vcpu);
		vmx_inject_irq(vcpu, vector);
		kvm_timer_intr_post(vcpu, vector);
	} else
		enable_irq_window(vcpu);
}

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 %%rax; push %%rbx; push %%rdx;"
		"push %%rsi; push %%rdi; push %%rbp;"
		"push %%r8;  push %%r9;  push %%r10; push %%r11;"
		"push %%r12; push %%r13; push %%r14; push %%r15;"
		"push %%rcx \n\t"
		ASM_VMX_VMWRITE_RSP_RDX "\n\t"
#else
		"pusha; push %%ecx \n\t"
		ASM_VMX_VMWRITE_RSP_RDX "\n\t"
#endif
		/* Check if vmlaunch of vmresume is needed */
		"cmp $0, %1 \n\t"
		/* Load guest registers.  Don't clobber flags. */
#ifdef CONFIG_X86_64
		"mov %c[cr2](%3), %%rax \n\t"
		"mov %%rax, %%cr2 \n\t"
		"mov %c[rax](%3), %%rax \n\t"
		"mov %c[rbx](%3), %%rbx \n\t"
		"mov %c[rdx](%3), %%rdx \n\t"
		"mov %c[rsi](%3), %%rsi \n\t"
		"mov %c[rdi](%3), %%rdi \n\t"
		"mov %c[rbp](%3), %%rbp \n\t"
		"mov %c[r8](%3),  %%r8  \n\t"
		"mov %c[r9](%3),  %%r9  \n\t"
		"mov %c[r10](%3), %%r10 \n\t"
		"mov %c[r11](%3), %%r11 \n\t"
		"mov %c[r12](%3), %%r12 \n\t"
		"mov %c[r13](%3), %%r13 \n\t"
		"mov %c[r14](%3), %%r14 \n\t"
		"mov %c[r15](%3), %%r15 \n\t"
		"mov %c[rcx](%3), %%rcx \n\t" /* kills %3 (rcx) */
#else
		"mov %c[cr2](%3), %%eax \n\t"
		"mov %%eax,   %%cr2 \n\t"
		"mov %c[rax](%3), %%eax \n\t"
		"mov %c[rbx](%3), %%ebx \n\t"
		"mov %c[rdx](%3), %%edx \n\t"
		"mov %c[rsi](%3), %%esi \n\t"
		"mov %c[rdi](%3), %%edi \n\t"
		"mov %c[rbp](%3), %%ebp \n\t"
		"mov %c[rcx](%3), %%ecx \n\t" /* kills %3 (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 %3,     (%%rsp) \n\t"
		"mov %%rax, %c[rax](%3) \n\t"
		"mov %%rbx, %c[rbx](%3) \n\t"
		"pushq (%%rsp); popq %c[rcx](%3) \n\t"
		"mov %%rdx, %c[rdx](%3) \n\t"
		"mov %%rsi, %c[rsi](%3) \n\t"
		"mov %%rdi, %c[rdi](%3) \n\t"
		"mov %%rbp, %c[rbp](%3) \n\t"
		"mov %%r8,  %c[r8](%3) \n\t"
		"mov %%r9,  %c[r9](%3) \n\t"
		"mov %%r10, %c[r10](%3) \n\t"
		"mov %%r11, %c[r11](%3) \n\t"
		"mov %%r12, %c[r12](%3) \n\t"
		"mov %%r13, %c[r13](%3) \n\t"
		"mov %%r14, %c[r14](%3) \n\t"
		"mov %%r15, %c[r15](%3) \n\t"
		"mov %%cr2, %%rax   \n\t"
		"mov %%rax, %c[cr2](%3) \n\t"
		"mov (%%rsp), %3 \n\t"

		"pop  %%rcx; pop  %%r15; pop  %%r14; pop  %%r13; pop  %%r12;"
		"pop  %%r11; pop  %%r10; pop  %%r9;  pop  %%r8;"
		"pop  %%rbp; pop  %%rdi; pop  %%rsi;"
		"pop  %%rdx; pop  %%rbx; pop  %%rax \n\t"
#else
		"xchg %3, (%%esp) \n\t"
		"mov %%eax, %c[rax](%3) \n\t"
		"mov %%ebx, %c[rbx](%3) \n\t"
		"pushl (%%esp); popl %c[rcx](%3) \n\t"
		"mov %%edx, %c[rdx](%3) \n\t"
		"mov %%esi, %c[rsi](%3) \n\t"
		"mov %%edi, %c[rdi](%3) \n\t"
		"mov %%ebp, %c[rbp](%3) \n\t"
		"mov %%cr2, %%eax  \n\t"
		"mov %%eax, %c[cr2](%3) \n\t"
		"mov (%%esp), %3 \n\t"

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

	vcpu->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");
}

static void vmx_inject_page_fault(struct kvm_vcpu *vcpu,
				  unsigned long addr,
				  u32 err_code)
{
	u32 vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);

	++vcpu->stat.pf_guest;

	if (is_page_fault(vect_info)) {
		printk(KERN_DEBUG "inject_page_fault: "
		       "double fault 0x%lx @ 0x%lx\n",
		       addr, vmcs_readl(GUEST_RIP));
		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, 0);
		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
			     DF_VECTOR |
			     INTR_TYPE_EXCEPTION |
			     INTR_INFO_DELIEVER_CODE_MASK |
			     INTR_INFO_VALID_MASK);
		return;
	}
	vcpu->cr2 = addr;
	vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, err_code);
	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
		     PF_VECTOR |
		     INTR_TYPE_EXCEPTION |
		     INTR_INFO_DELIEVER_CODE_MASK |
		     INTR_INFO_VALID_MASK);

}

static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (vmx->vmcs) {
		on_each_cpu(__vcpu_clear, vmx, 0, 1);
		free_vmcs(vmx->vmcs);
		vmx->vmcs = NULL;
	}
}

static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	vmx_free_vmcs(vcpu);
	kfree(vmx->host_msrs);
	kfree(vmx->guest_msrs);
	kvm_vcpu_uninit(vcpu);
	kmem_cache_free(kvm_vcpu_cache, vmx);
}

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;

	if (irqchip_in_kernel(kvm)) {
		err = kvm_create_lapic(&vmx->vcpu);
		if (err < 0)
			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;

	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);
}

static void __init vmx_check_processor_compat(void *rtn)
{
	struct vmcs_config vmcs_conf;

	*(int *)rtn = 0;
	if (setup_vmcs_config(&vmcs_conf) < 0)
		*(int *)rtn = -EIO;
	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
				smp_processor_id());
		*(int *)rtn = -EIO;
	}
}

static struct kvm_x86_ops vmx_x86_ops = {
	.cpu_has_kvm_support = cpu_has_kvm_support,
	.disabled_by_bios = vmx_disabled_by_bios,
	.hardware_setup = hardware_setup,
	.hardware_unsetup = hardware_unsetup,
	.check_processor_compatibility = vmx_check_processor_compat,
	.hardware_enable = hardware_enable,
	.hardware_disable = hardware_disable,

	.vcpu_create = vmx_create_vcpu,
	.vcpu_free = vmx_free_vcpu,
	.vcpu_reset = vmx_vcpu_reset,

	.prepare_guest_switch = vmx_save_host_state,
	.vcpu_load = vmx_vcpu_load,
	.vcpu_put = vmx_vcpu_put,
	.vcpu_decache = vmx_vcpu_decache,

	.set_guest_debug = set_guest_debug,
	.guest_debug_pre = kvm_guest_debug_pre,
	.get_msr = vmx_get_msr,
	.set_msr = vmx_set_msr,
	.get_segment_base = vmx_get_segment_base,
	.get_segment = vmx_get_segment,
	.set_segment = vmx_set_segment,
	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
	.set_cr0 = vmx_set_cr0,
	.set_cr3 = vmx_set_cr3,
	.set_cr4 = vmx_set_cr4,
#ifdef CONFIG_X86_64
	.set_efer = vmx_set_efer,
#endif
	.get_idt = vmx_get_idt,
	.set_idt = vmx_set_idt,
	.get_gdt = vmx_get_gdt,
	.set_gdt = vmx_set_gdt,
	.cache_regs = vcpu_load_rsp_rip,
	.decache_regs = vcpu_put_rsp_rip,
	.get_rflags = vmx_get_rflags,
	.set_rflags = vmx_set_rflags,

	.tlb_flush = vmx_flush_tlb,
	.inject_page_fault = vmx_inject_page_fault,

	.inject_gp = vmx_inject_gp,

	.run = vmx_vcpu_run,
	.handle_exit = kvm_handle_exit,
	.skip_emulated_instruction = skip_emulated_instruction,
	.patch_hypercall = vmx_patch_hypercall,
	.get_irq = vmx_get_irq,
	.set_irq = vmx_inject_irq,
	.inject_pending_irq = vmx_intr_assist,
	.inject_pending_vectors = do_interrupt_requests,
};

static int __init vmx_init(void)
{
	void *iova;
	int r;

	vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
	if (!vmx_io_bitmap_a)
		return -ENOMEM;

	vmx_io_bitmap_b = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
	if (!vmx_io_bitmap_b) {
		r = -ENOMEM;
		goto out;
	}

	/*
	 * Allow direct access to the PC debug port (it is often used for I/O
	 * delays, but the vmexits simply slow things down).
	 */
	iova = kmap(vmx_io_bitmap_a);
	memset(iova, 0xff, PAGE_SIZE);
	clear_bit(0x80, iova);
	kunmap(vmx_io_bitmap_a);

	iova = kmap(vmx_io_bitmap_b);
	memset(iova, 0xff, PAGE_SIZE);
	kunmap(vmx_io_bitmap_b);

	r = kvm_init_x86(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
	if (r)
		goto out1;

	return 0;

out1:
	__free_page(vmx_io_bitmap_b);
out:
	__free_page(vmx_io_bitmap_a);
	return r;
}

static void __exit vmx_exit(void)
{
	__free_page(vmx_io_bitmap_b);
	__free_page(vmx_io_bitmap_a);

	kvm_exit_x86();
}

module_init(vmx_init)
module_exit(vmx_exit)