kvm_main.c

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

		return X86EMUL_CONTINUE;
	}

	vcpu->mmio_needed = 1;
	vcpu->mmio_phys_addr = gpa;
	vcpu->mmio_size = bytes;
	vcpu->mmio_is_write = 1;
	memcpy(vcpu->mmio_data, val, bytes);

	return X86EMUL_CONTINUE;
}

int emulator_write_emulated(unsigned long addr,
				   const void *val,
				   unsigned int bytes,
				   struct kvm_vcpu *vcpu)
{
	/* Crossing a page boundary? */
	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
		int rc, now;

		now = -addr & ~PAGE_MASK;
		rc = emulator_write_emulated_onepage(addr, val, now, vcpu);
		if (rc != X86EMUL_CONTINUE)
			return rc;
		addr += now;
		val += now;
		bytes -= now;
	}
	return emulator_write_emulated_onepage(addr, val, bytes, vcpu);
}
EXPORT_SYMBOL_GPL(emulator_write_emulated);

static int emulator_cmpxchg_emulated(unsigned long addr,
				     const void *old,
				     const void *new,
				     unsigned int bytes,
				     struct kvm_vcpu *vcpu)
{
	static int reported;

	if (!reported) {
		reported = 1;
		printk(KERN_WARNING "kvm: emulating exchange as write\n");
	}
	return emulator_write_emulated(addr, new, bytes, vcpu);
}

static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
	return kvm_x86_ops->get_segment_base(vcpu, seg);
}

int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
{
	return X86EMUL_CONTINUE;
}

int emulate_clts(struct kvm_vcpu *vcpu)
{
	kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS);
	return X86EMUL_CONTINUE;
}

int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr, unsigned long *dest)
{
	struct kvm_vcpu *vcpu = ctxt->vcpu;

	switch (dr) {
	case 0 ... 3:
		*dest = kvm_x86_ops->get_dr(vcpu, dr);
		return X86EMUL_CONTINUE;
	default:
		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr);
		return X86EMUL_UNHANDLEABLE;
	}
}

int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
{
	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
	int exception;

	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
	if (exception) {
		/* FIXME: better handling */
		return X86EMUL_UNHANDLEABLE;
	}
	return X86EMUL_CONTINUE;
}

void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
{
	static int reported;
	u8 opcodes[4];
	unsigned long rip = vcpu->rip;
	unsigned long rip_linear;

	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);

	if (reported)
		return;

	emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu);

	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
	reported = 1;
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);

struct x86_emulate_ops emulate_ops = {
	.read_std            = emulator_read_std,
	.write_std           = emulator_write_std,
	.read_emulated       = emulator_read_emulated,
	.write_emulated      = emulator_write_emulated,
	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
};

int emulate_instruction(struct kvm_vcpu *vcpu,
			struct kvm_run *run,
			unsigned long cr2,
			u16 error_code)
{
	struct x86_emulate_ctxt emulate_ctxt;
	int r;
	int cs_db, cs_l;

	vcpu->mmio_fault_cr2 = cr2;
	kvm_x86_ops->cache_regs(vcpu);

	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);

	emulate_ctxt.vcpu = vcpu;
	emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
	emulate_ctxt.cr2 = cr2;
	emulate_ctxt.mode = (emulate_ctxt.eflags & X86_EFLAGS_VM)
		? X86EMUL_MODE_REAL : cs_l
		? X86EMUL_MODE_PROT64 :	cs_db
		? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;

	if (emulate_ctxt.mode == X86EMUL_MODE_PROT64) {
		emulate_ctxt.cs_base = 0;
		emulate_ctxt.ds_base = 0;
		emulate_ctxt.es_base = 0;
		emulate_ctxt.ss_base = 0;
	} else {
		emulate_ctxt.cs_base = get_segment_base(vcpu, VCPU_SREG_CS);
		emulate_ctxt.ds_base = get_segment_base(vcpu, VCPU_SREG_DS);
		emulate_ctxt.es_base = get_segment_base(vcpu, VCPU_SREG_ES);
		emulate_ctxt.ss_base = get_segment_base(vcpu, VCPU_SREG_SS);
	}

	emulate_ctxt.gs_base = get_segment_base(vcpu, VCPU_SREG_GS);
	emulate_ctxt.fs_base = get_segment_base(vcpu, VCPU_SREG_FS);

	vcpu->mmio_is_write = 0;
	vcpu->pio.string = 0;
	r = x86_emulate_memop(&emulate_ctxt, &emulate_ops);
	if (vcpu->pio.string)
		return EMULATE_DO_MMIO;

	if ((r || vcpu->mmio_is_write) && run) {
		run->exit_reason = KVM_EXIT_MMIO;
		run->mmio.phys_addr = vcpu->mmio_phys_addr;
		memcpy(run->mmio.data, vcpu->mmio_data, 8);
		run->mmio.len = vcpu->mmio_size;
		run->mmio.is_write = vcpu->mmio_is_write;
	}

	if (r) {
		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
			return EMULATE_DONE;
		if (!vcpu->mmio_needed) {
			kvm_report_emulation_failure(vcpu, "mmio");
			return EMULATE_FAIL;
		}
		return EMULATE_DO_MMIO;
	}

	kvm_x86_ops->decache_regs(vcpu);
	kvm_x86_ops->set_rflags(vcpu, emulate_ctxt.eflags);

	if (vcpu->mmio_is_write) {
		vcpu->mmio_needed = 0;
		return EMULATE_DO_MMIO;
	}

	return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);

/*
 * The vCPU has executed a HLT instruction with in-kernel mode enabled.
 */
static void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue(&vcpu->wq, &wait);

	/*
	 * We will block until either an interrupt or a signal wakes us up
	 */
	while (!kvm_cpu_has_interrupt(vcpu)
	       && !signal_pending(current)
	       && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE
	       && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) {
		set_current_state(TASK_INTERRUPTIBLE);
		vcpu_put(vcpu);
		schedule();
		vcpu_load(vcpu);
	}

	__set_current_state(TASK_RUNNING);
	remove_wait_queue(&vcpu->wq, &wait);
}

int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
	++vcpu->stat.halt_exits;
	if (irqchip_in_kernel(vcpu->kvm)) {
		vcpu->mp_state = VCPU_MP_STATE_HALTED;
		kvm_vcpu_block(vcpu);
		if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE)
			return -EINTR;
		return 1;
	} else {
		vcpu->run->exit_reason = KVM_EXIT_HLT;
		return 0;
	}
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);

int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	unsigned long nr, a0, a1, a2, a3, a4, a5, ret;

	kvm_x86_ops->cache_regs(vcpu);
	ret = -KVM_EINVAL;
#ifdef CONFIG_X86_64
	if (is_long_mode(vcpu)) {
		nr = vcpu->regs[VCPU_REGS_RAX];
		a0 = vcpu->regs[VCPU_REGS_RDI];
		a1 = vcpu->regs[VCPU_REGS_RSI];
		a2 = vcpu->regs[VCPU_REGS_RDX];
		a3 = vcpu->regs[VCPU_REGS_RCX];
		a4 = vcpu->regs[VCPU_REGS_R8];
		a5 = vcpu->regs[VCPU_REGS_R9];
	} else
#endif
	{
		nr = vcpu->regs[VCPU_REGS_RBX] & -1u;
		a0 = vcpu->regs[VCPU_REGS_RAX] & -1u;
		a1 = vcpu->regs[VCPU_REGS_RCX] & -1u;
		a2 = vcpu->regs[VCPU_REGS_RDX] & -1u;
		a3 = vcpu->regs[VCPU_REGS_RSI] & -1u;
		a4 = vcpu->regs[VCPU_REGS_RDI] & -1u;
		a5 = vcpu->regs[VCPU_REGS_RBP] & -1u;
	}
	switch (nr) {
	default:
		run->hypercall.nr = nr;
		run->hypercall.args[0] = a0;
		run->hypercall.args[1] = a1;
		run->hypercall.args[2] = a2;
		run->hypercall.args[3] = a3;
		run->hypercall.args[4] = a4;
		run->hypercall.args[5] = a5;
		run->hypercall.ret = ret;
		run->hypercall.longmode = is_long_mode(vcpu);
		kvm_x86_ops->decache_regs(vcpu);
		return 0;
	}
	vcpu->regs[VCPU_REGS_RAX] = ret;
	kvm_x86_ops->decache_regs(vcpu);
	return 1;
}
EXPORT_SYMBOL_GPL(kvm_hypercall);

static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
}

void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
	struct descriptor_table dt = { limit, base };

	kvm_x86_ops->set_gdt(vcpu, &dt);
}

void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
	struct descriptor_table dt = { limit, base };

	kvm_x86_ops->set_idt(vcpu, &dt);
}

void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
		   unsigned long *rflags)
{
	lmsw(vcpu, msw);
	*rflags = kvm_x86_ops->get_rflags(vcpu);
}

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
	switch (cr) {
	case 0:
		return vcpu->cr0;
	case 2:
		return vcpu->cr2;
	case 3:
		return vcpu->cr3;
	case 4:
		return vcpu->cr4;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
		return 0;
	}
}

void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
		     unsigned long *rflags)
{
	switch (cr) {
	case 0:
		set_cr0(vcpu, mk_cr_64(vcpu->cr0, val));
		*rflags = kvm_x86_ops->get_rflags(vcpu);
		break;
	case 2:
		vcpu->cr2 = val;
		break;
	case 3:
		set_cr3(vcpu, val);
		break;
	case 4:
		set_cr4(vcpu, mk_cr_64(vcpu->cr4, val));
		break;
	default:
		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
	}
}

/*
 * Register the para guest with the host:
 */
static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
{
	struct kvm_vcpu_para_state *para_state;
	hpa_t para_state_hpa, hypercall_hpa;
	struct page *para_state_page;
	unsigned char *hypercall;
	gpa_t hypercall_gpa;

	printk(KERN_DEBUG "kvm: guest trying to enter paravirtual mode\n");
	printk(KERN_DEBUG ".... para_state_gpa: %08Lx\n", para_state_gpa);

	/*
	 * Needs to be page aligned:
	 */
	if (para_state_gpa != PAGE_ALIGN(para_state_gpa))
		goto err_gp;

	para_state_hpa = gpa_to_hpa(vcpu, para_state_gpa);
	printk(KERN_DEBUG ".... para_state_hpa: %08Lx\n", para_state_hpa);
	if (is_error_hpa(para_state_hpa))
		goto err_gp;

	mark_page_dirty(vcpu->kvm, para_state_gpa >> PAGE_SHIFT);
	para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
	para_state = kmap(para_state_page);

	printk(KERN_DEBUG "....  guest version: %d\n", para_state->guest_version);
	printk(KERN_DEBUG "....           size: %d\n", para_state->size);

	para_state->host_version = KVM_PARA_API_VERSION;
	/*
	 * We cannot support guests that try to register themselves
	 * with a newer API version than the host supports:
	 */
	if (para_state->guest_version > KVM_PARA_API_VERSION) {
		para_state->ret = -KVM_EINVAL;
		goto err_kunmap_skip;
	}

	hypercall_gpa = para_state->hypercall_gpa;
	hypercall_hpa = gpa_to_hpa(vcpu, hypercall_gpa);
	printk(KERN_DEBUG ".... hypercall_hpa: %08Lx\n", hypercall_hpa);
	if (is_error_hpa(hypercall_hpa)) {
		para_state->ret = -KVM_EINVAL;
		goto err_kunmap_skip;
	}

	printk(KERN_DEBUG "kvm: para guest successfully registered.\n");
	vcpu->para_state_page = para_state_page;
	vcpu->para_state_gpa = para_state_gpa;
	vcpu->hypercall_gpa = hypercall_gpa;

	mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT);
	hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
				KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
	kvm_x86_ops->patch_hypercall(vcpu, hypercall);
	kunmap_atomic(hypercall, KM_USER1);

	para_state->ret = 0;
err_kunmap_skip:
	kunmap(para_state_page);
	return 0;
err_gp:
	return 1;
}

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data;

	switch (msr) {
	case 0xc0010010: /* SYSCFG */
	case 0xc0010015: /* HWCR */
	case MSR_IA32_PLATFORM_ID:
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
	case MSR_IA32_MC0_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MCG_CAP:
	case MSR_IA32_MC0_MISC:
	case MSR_IA32_MC0_MISC+4:
	case MSR_IA32_MC0_MISC+8:
	case MSR_IA32_MC0_MISC+12:
	case MSR_IA32_MC0_MISC+16:
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_PERF_STATUS:
	case MSR_IA32_EBL_CR_POWERON:
		/* MTRR registers */
	case 0xfe:
	case 0x200 ... 0x2ff:
		data = 0;
		break;
	case 0xcd: /* fsb frequency */
		data = 3;
		break;
	case MSR_IA32_APICBASE:
		data = kvm_get_apic_base(vcpu);
		break;
	case MSR_IA32_MISC_ENABLE:
		data = vcpu->ia32_misc_enable_msr;
		break;
#ifdef CONFIG_X86_64
	case MSR_EFER:
		data = vcpu->shadow_efer;
		break;
#endif
	default:
		pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}
	*pdata = data;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);

/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
}

#ifdef CONFIG_X86_64

static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	if (efer & EFER_RESERVED_BITS) {
		printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
		       efer);
		inject_gp(vcpu);
		return;
	}

	if (is_paging(vcpu)
	    && (vcpu->shadow_efer & EFER_LME) != (efer & EFER_LME)) {
		printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
		inject_gp(vcpu);
		return;
	}

	kvm_x86_ops->set_efer(vcpu, efer);

	efer &= ~EFER_LMA;
	efer |= vcpu->shadow_efer & EFER_LMA;

	vcpu->shadow_efer = efer;
}

#endif

int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	switch (msr) {
#ifdef CONFIG_X86_64
	case MSR_EFER:
		set_efer(vcpu, data);
		break;
#endif
	case MSR_IA32_MC0_STATUS:
		pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
		       __FUNCTION__, data);
		break;
	case MSR_IA32_MCG_STATUS:
		pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
			__FUNCTION__, data);
		break;
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_UCODE_WRITE:
	case 0x200 ... 0x2ff: /* MTRRs */
		break;
	case MSR_IA32_APICBASE:
		kvm_set_apic_base(vcpu, data);
		break;
	case MSR_IA32_MISC_ENABLE:
		vcpu->ia32_misc_enable_msr = data;
		break;
	/*
	 * This is the 'probe whether the host is KVM' logic:
	 */
	case MSR_KVM_API_MAGIC:
		return vcpu_register_para(vcpu, data);

	default:
		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);

/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
	return kvm_x86_ops->set_msr(vcpu, msr_index, data);
}

void kvm_resched(struct kvm_vcpu *vcpu)
{
	if (!need_resched())
		return;
	cond_resched();
}
EXPORT_SYMBOL_GPL(kvm_resched);

void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	int i;
	u32 function;
	struct kvm_cpuid_entry *e, *best;