vmx.c 50.0 KB
Newer Older
A
Avi Kivity 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "kvm.h"
#include "vmx.h"
#include "kvm_vmx.h"
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <asm/io.h>
A
Anthony Liguori 已提交
25
#include <asm/desc.h>
A
Avi Kivity 已提交
26 27 28 29 30 31 32 33 34 35 36

#include "segment_descriptor.h"

#define MSR_IA32_FEATURE_CONTROL 		0x03a

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);

37
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73
#define HOST_IS_64 1
#else
#define HOST_IS_64 0
#endif

static struct vmcs_descriptor {
	int size;
	int order;
	u32 revision_id;
} vmcs_descriptor;

#define VMX_SEGMENT_FIELD(seg)					\
	[VCPU_SREG_##seg] = {                                   \
		.selector = GUEST_##seg##_SELECTOR,		\
		.base = GUEST_##seg##_BASE,		   	\
		.limit = GUEST_##seg##_LIMIT,		   	\
		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
	}

static struct kvm_vmx_segment_field {
	unsigned selector;
	unsigned base;
	unsigned limit;
	unsigned ar_bytes;
} kvm_vmx_segment_fields[] = {
	VMX_SEGMENT_FIELD(CS),
	VMX_SEGMENT_FIELD(DS),
	VMX_SEGMENT_FIELD(ES),
	VMX_SEGMENT_FIELD(FS),
	VMX_SEGMENT_FIELD(GS),
	VMX_SEGMENT_FIELD(SS),
	VMX_SEGMENT_FIELD(TR),
	VMX_SEGMENT_FIELD(LDTR),
};

static const u32 vmx_msr_index[] = {
74
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE,
#endif
	MSR_EFER, MSR_K6_STAR,
};
#define NR_VMX_MSR (sizeof(vmx_msr_index) / sizeof(*vmx_msr_index))

struct vmx_msr_entry *find_msr_entry(struct kvm_vcpu *vcpu, u32 msr);

static inline int is_page_fault(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
			     INTR_INFO_VALID_MASK)) ==
		(INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}

static inline int is_external_interrupt(u32 intr_info)
{
	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}

static void vmcs_clear(struct vmcs *vmcs)
{
	u64 phys_addr = __pa(vmcs);
	u8 error;

	asm volatile (ASM_VMX_VMCLEAR_RAX "; setna %0"
		      : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
		      : "cc", "memory");
	if (error)
		printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
		       vmcs, phys_addr);
}

static void __vcpu_clear(void *arg)
{
	struct kvm_vcpu *vcpu = arg;
	int cpu = smp_processor_id();

	if (vcpu->cpu == cpu)
		vmcs_clear(vcpu->vmcs);
	if (per_cpu(current_vmcs, cpu) == vcpu->vmcs)
		per_cpu(current_vmcs, cpu) = NULL;
}

static unsigned long vmcs_readl(unsigned long field)
{
	unsigned long value;

	asm volatile (ASM_VMX_VMREAD_RDX_RAX
		      : "=a"(value) : "d"(field) : "cc");
	return value;
}

static u16 vmcs_read16(unsigned long field)
{
	return vmcs_readl(field);
}

static u32 vmcs_read32(unsigned long field)
{
	return vmcs_readl(field);
}

static u64 vmcs_read64(unsigned long field)
{
141
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
	return vmcs_readl(field);
#else
	return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32);
#endif
}

static void vmcs_writel(unsigned long field, unsigned long value)
{
	u8 error;

	asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0"
		       : "=q"(error) : "a"(value), "d"(field) : "cc" );
	if (error)
		printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
		       field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
}

static void vmcs_write16(unsigned long field, u16 value)
{
	vmcs_writel(field, value);
}

static void vmcs_write32(unsigned long field, u32 value)
{
	vmcs_writel(field, value);
}

static void vmcs_write64(unsigned long field, u64 value)
{
171
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299
	vmcs_writel(field, value);
#else
	vmcs_writel(field, value);
	asm volatile ("");
	vmcs_writel(field+1, value >> 32);
#endif
}

/*
 * Switches to specified vcpu, until a matching vcpu_put(), but assumes
 * vcpu mutex is already taken.
 */
static struct kvm_vcpu *vmx_vcpu_load(struct kvm_vcpu *vcpu)
{
	u64 phys_addr = __pa(vcpu->vmcs);
	int cpu;

	cpu = get_cpu();

	if (vcpu->cpu != cpu) {
		smp_call_function(__vcpu_clear, vcpu, 0, 1);
		vcpu->launched = 0;
	}

	if (per_cpu(current_vmcs, cpu) != vcpu->vmcs) {
		u8 error;

		per_cpu(current_vmcs, cpu) = vcpu->vmcs;
		asm volatile (ASM_VMX_VMPTRLD_RAX "; setna %0"
			      : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
			      : "cc");
		if (error)
			printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
			       vcpu->vmcs, phys_addr);
	}

	if (vcpu->cpu != cpu) {
		struct descriptor_table dt;
		unsigned long sysenter_esp;

		vcpu->cpu = cpu;
		/*
		 * Linux uses per-cpu TSS and GDT, so set these when switching
		 * processors.
		 */
		vmcs_writel(HOST_TR_BASE, read_tr_base()); /* 22.2.4 */
		get_gdt(&dt);
		vmcs_writel(HOST_GDTR_BASE, dt.base);   /* 22.2.4 */

		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
	}
	return vcpu;
}

static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
	put_cpu();
}

static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
	return vmcs_readl(GUEST_RFLAGS);
}

static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
	vmcs_writel(GUEST_RFLAGS, rflags);
}

static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
	unsigned long rip;
	u32 interruptibility;

	rip = vmcs_readl(GUEST_RIP);
	rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
	vmcs_writel(GUEST_RIP, rip);

	/*
	 * We emulated an instruction, so temporary interrupt blocking
	 * should be removed, if set.
	 */
	interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
	if (interruptibility & 3)
		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
			     interruptibility & ~3);
}

static void vmx_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code)
{
	printk(KERN_DEBUG "inject_general_protection: rip 0x%lx\n",
	       vmcs_readl(GUEST_RIP));
	vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
		     GP_VECTOR |
		     INTR_TYPE_EXCEPTION |
		     INTR_INFO_DELIEVER_CODE_MASK |
		     INTR_INFO_VALID_MASK);
}

/*
 * reads and returns guest's timestamp counter "register"
 * guest_tsc = host_tsc + tsc_offset    -- 21.3
 */
static u64 guest_read_tsc(void)
{
	u64 host_tsc, tsc_offset;

	rdtscll(host_tsc);
	tsc_offset = vmcs_read64(TSC_OFFSET);
	return host_tsc + tsc_offset;
}

/*
 * writes 'guest_tsc' into guest's timestamp counter "register"
 * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc
 */
static void guest_write_tsc(u64 guest_tsc)
{
	u64 host_tsc;

	rdtscll(host_tsc);
	vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc);
}

static void reload_tss(void)
{
300
#ifndef CONFIG_X86_64
A
Avi Kivity 已提交
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330

	/*
	 * VT restores TR but not its size.  Useless.
	 */
	struct descriptor_table gdt;
	struct segment_descriptor *descs;

	get_gdt(&gdt);
	descs = (void *)gdt.base;
	descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
	load_TR_desc();
#endif
}

/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
	u64 data;
	struct vmx_msr_entry *msr;

	if (!pdata) {
		printk(KERN_ERR "BUG: get_msr called with NULL pdata\n");
		return -EINVAL;
	}

	switch (msr_index) {
331
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
	case MSR_FS_BASE:
		data = vmcs_readl(GUEST_FS_BASE);
		break;
	case MSR_GS_BASE:
		data = vmcs_readl(GUEST_GS_BASE);
		break;
	case MSR_EFER:
		data = vcpu->shadow_efer;
		break;
#endif
	case MSR_IA32_TIME_STAMP_COUNTER:
		data = guest_read_tsc();
		break;
	case MSR_IA32_SYSENTER_CS:
		data = vmcs_read32(GUEST_SYSENTER_CS);
		break;
	case MSR_IA32_SYSENTER_EIP:
		data = vmcs_read32(GUEST_SYSENTER_EIP);
		break;
	case MSR_IA32_SYSENTER_ESP:
		data = vmcs_read32(GUEST_SYSENTER_ESP);
		break;
	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:
		/* MTRR registers */
	case 0xfe:
	case 0x200 ... 0x2ff:
		data = 0;
		break;
	case MSR_IA32_APICBASE:
		data = vcpu->apic_base;
		break;
	default:
		msr = find_msr_entry(vcpu, msr_index);
		if (!msr) {
			printk(KERN_ERR "kvm: unhandled rdmsr: %x\n", msr_index);
			return 1;
		}
		data = msr->data;
		break;
	}

	*pdata = data;
	return 0;
}

/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
	struct vmx_msr_entry *msr;
	switch (msr_index) {
394
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
	case MSR_FS_BASE:
		vmcs_writel(GUEST_FS_BASE, data);
		break;
	case MSR_GS_BASE:
		vmcs_writel(GUEST_GS_BASE, data);
		break;
#endif
	case MSR_IA32_SYSENTER_CS:
		vmcs_write32(GUEST_SYSENTER_CS, data);
		break;
	case MSR_IA32_SYSENTER_EIP:
		vmcs_write32(GUEST_SYSENTER_EIP, data);
		break;
	case MSR_IA32_SYSENTER_ESP:
		vmcs_write32(GUEST_SYSENTER_ESP, data);
		break;
#ifdef __x86_64
	case MSR_EFER:
		set_efer(vcpu, data);
		break;
	case MSR_IA32_MC0_STATUS:
		printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n"
			    , __FUNCTION__, data);
		break;
#endif
	case MSR_IA32_TIME_STAMP_COUNTER: {
		guest_write_tsc(data);
		break;
	}
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_UCODE_WRITE:
	case 0x200 ... 0x2ff: /* MTRRs */
		break;
	case MSR_IA32_APICBASE:
		vcpu->apic_base = data;
		break;
	default:
		msr = find_msr_entry(vcpu, msr_index);
		if (!msr) {
			printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr_index);
			return 1;
		}
		msr->data = data;
		break;
	}

	return 0;
}

/*
 * Sync the rsp and rip registers into the vcpu structure.  This allows
 * registers to be accessed by indexing vcpu->regs.
 */
static void vcpu_load_rsp_rip(struct kvm_vcpu *vcpu)
{
	vcpu->regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
	vcpu->rip = vmcs_readl(GUEST_RIP);
}

/*
 * Syncs rsp and rip back into the vmcs.  Should be called after possible
 * modification.
 */
static void vcpu_put_rsp_rip(struct kvm_vcpu *vcpu)
{
	vmcs_writel(GUEST_RSP, vcpu->regs[VCPU_REGS_RSP]);
	vmcs_writel(GUEST_RIP, vcpu->rip);
}

static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
{
	unsigned long dr7 = 0x400;
	u32 exception_bitmap;
	int old_singlestep;

	exception_bitmap = vmcs_read32(EXCEPTION_BITMAP);
	old_singlestep = vcpu->guest_debug.singlestep;

	vcpu->guest_debug.enabled = dbg->enabled;
	if (vcpu->guest_debug.enabled) {
		int i;

		dr7 |= 0x200;  /* exact */
		for (i = 0; i < 4; ++i) {
			if (!dbg->breakpoints[i].enabled)
				continue;
			vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
			dr7 |= 2 << (i*2);    /* global enable */
			dr7 |= 0 << (i*4+16); /* execution breakpoint */
		}

		exception_bitmap |= (1u << 1);  /* Trap debug exceptions */

		vcpu->guest_debug.singlestep = dbg->singlestep;
	} else {
		exception_bitmap &= ~(1u << 1); /* Ignore debug exceptions */
		vcpu->guest_debug.singlestep = 0;
	}

	if (old_singlestep && !vcpu->guest_debug.singlestep) {
		unsigned long flags;

		flags = vmcs_readl(GUEST_RFLAGS);
		flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
		vmcs_writel(GUEST_RFLAGS, flags);
	}

	vmcs_write32(EXCEPTION_BITMAP, exception_bitmap);
	vmcs_writel(GUEST_DR7, dr7);

	return 0;
}

static __init int cpu_has_kvm_support(void)
{
	unsigned long ecx = cpuid_ecx(1);
	return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
}

static __init int vmx_disabled_by_bios(void)
{
	u64 msr;

	rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
	return (msr & 5) == 1; /* locked but not enabled */
}

static __init void hardware_enable(void *garbage)
{
	int cpu = raw_smp_processor_id();
	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
	u64 old;

	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
	if ((old & 5) == 0)
		/* enable and lock */
		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | 5);
	write_cr4(read_cr4() | CR4_VMXE); /* FIXME: not cpu hotplug safe */
	asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr)
		      : "memory", "cc");
}

static void hardware_disable(void *garbage)
{
	asm volatile (ASM_VMX_VMXOFF : : : "cc");
}

static __init void setup_vmcs_descriptor(void)
{
	u32 vmx_msr_low, vmx_msr_high;

	rdmsr(MSR_IA32_VMX_BASIC_MSR, vmx_msr_low, vmx_msr_high);
	vmcs_descriptor.size = vmx_msr_high & 0x1fff;
	vmcs_descriptor.order = get_order(vmcs_descriptor.size);
	vmcs_descriptor.revision_id = vmx_msr_low;
};

static struct vmcs *alloc_vmcs_cpu(int cpu)
{
	int node = cpu_to_node(cpu);
	struct page *pages;
	struct vmcs *vmcs;

	pages = alloc_pages_node(node, GFP_KERNEL, vmcs_descriptor.order);
	if (!pages)
		return NULL;
	vmcs = page_address(pages);
	memset(vmcs, 0, vmcs_descriptor.size);
	vmcs->revision_id = vmcs_descriptor.revision_id; /* vmcs revision id */
	return vmcs;
}

static struct vmcs *alloc_vmcs(void)
{
	return alloc_vmcs_cpu(smp_processor_id());
}

static void free_vmcs(struct vmcs *vmcs)
{
	free_pages((unsigned long)vmcs, vmcs_descriptor.order);
}

static __exit void free_kvm_area(void)
{
	int cpu;

	for_each_online_cpu(cpu)
		free_vmcs(per_cpu(vmxarea, cpu));
}

extern struct vmcs *alloc_vmcs_cpu(int cpu);

static __init int alloc_kvm_area(void)
{
	int cpu;

	for_each_online_cpu(cpu) {
		struct vmcs *vmcs;

		vmcs = alloc_vmcs_cpu(cpu);
		if (!vmcs) {
			free_kvm_area();
			return -ENOMEM;
		}

		per_cpu(vmxarea, cpu) = vmcs;
	}
	return 0;
}

static __init int hardware_setup(void)
{
	setup_vmcs_descriptor();
	return alloc_kvm_area();
}

static __exit void hardware_unsetup(void)
{
	free_kvm_area();
}

static void update_exception_bitmap(struct kvm_vcpu *vcpu)
{
	if (vcpu->rmode.active)
		vmcs_write32(EXCEPTION_BITMAP, ~0);
	else
		vmcs_write32(EXCEPTION_BITMAP, 1 << PF_VECTOR);
}

static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save)
{
	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];

	if (vmcs_readl(sf->base) == save->base) {
		vmcs_write16(sf->selector, save->selector);
		vmcs_writel(sf->base, save->base);
		vmcs_write32(sf->limit, save->limit);
		vmcs_write32(sf->ar_bytes, save->ar);
	} else {
		u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK)
			<< AR_DPL_SHIFT;
		vmcs_write32(sf->ar_bytes, 0x93 | dpl);
	}
}

static void enter_pmode(struct kvm_vcpu *vcpu)
{
	unsigned long flags;

	vcpu->rmode.active = 0;

	vmcs_writel(GUEST_TR_BASE, vcpu->rmode.tr.base);
	vmcs_write32(GUEST_TR_LIMIT, vcpu->rmode.tr.limit);
	vmcs_write32(GUEST_TR_AR_BYTES, vcpu->rmode.tr.ar);

	flags = vmcs_readl(GUEST_RFLAGS);
	flags &= ~(IOPL_MASK | X86_EFLAGS_VM);
	flags |= (vcpu->rmode.save_iopl << IOPL_SHIFT);
	vmcs_writel(GUEST_RFLAGS, flags);

	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~CR4_VME_MASK) |
			(vmcs_readl(CR4_READ_SHADOW) & CR4_VME_MASK));

	update_exception_bitmap(vcpu);

	fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->rmode.es);
	fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->rmode.ds);
	fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->rmode.gs);
	fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->rmode.fs);

	vmcs_write16(GUEST_SS_SELECTOR, 0);
	vmcs_write32(GUEST_SS_AR_BYTES, 0x93);

	vmcs_write16(GUEST_CS_SELECTOR,
		     vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK);
	vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);
}

static int rmode_tss_base(struct kvm* kvm)
{
	gfn_t base_gfn = kvm->memslots[0].base_gfn + kvm->memslots[0].npages - 3;
	return base_gfn << PAGE_SHIFT;
}

static void fix_rmode_seg(int seg, struct kvm_save_segment *save)
{
	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];

	save->selector = vmcs_read16(sf->selector);
	save->base = vmcs_readl(sf->base);
	save->limit = vmcs_read32(sf->limit);
	save->ar = vmcs_read32(sf->ar_bytes);
	vmcs_write16(sf->selector, vmcs_readl(sf->base) >> 4);
	vmcs_write32(sf->limit, 0xffff);
	vmcs_write32(sf->ar_bytes, 0xf3);
}

static void enter_rmode(struct kvm_vcpu *vcpu)
{
	unsigned long flags;

	vcpu->rmode.active = 1;

	vcpu->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
	vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));

	vcpu->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);

	vcpu->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);

	flags = vmcs_readl(GUEST_RFLAGS);
	vcpu->rmode.save_iopl = (flags & IOPL_MASK) >> IOPL_SHIFT;

	flags |= IOPL_MASK | X86_EFLAGS_VM;

	vmcs_writel(GUEST_RFLAGS, flags);
	vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | CR4_VME_MASK);
	update_exception_bitmap(vcpu);

	vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4);
	vmcs_write32(GUEST_SS_LIMIT, 0xffff);
	vmcs_write32(GUEST_SS_AR_BYTES, 0xf3);

	vmcs_write32(GUEST_CS_AR_BYTES, 0xf3);
	vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);

	fix_rmode_seg(VCPU_SREG_ES, &vcpu->rmode.es);
	fix_rmode_seg(VCPU_SREG_DS, &vcpu->rmode.ds);
	fix_rmode_seg(VCPU_SREG_GS, &vcpu->rmode.gs);
	fix_rmode_seg(VCPU_SREG_FS, &vcpu->rmode.fs);
}

729
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770

static void enter_lmode(struct kvm_vcpu *vcpu)
{
	u32 guest_tr_ar;

	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
	if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
		printk(KERN_DEBUG "%s: tss fixup for long mode. \n",
		       __FUNCTION__);
		vmcs_write32(GUEST_TR_AR_BYTES,
			     (guest_tr_ar & ~AR_TYPE_MASK)
			     | AR_TYPE_BUSY_64_TSS);
	}

	vcpu->shadow_efer |= EFER_LMA;

	find_msr_entry(vcpu, MSR_EFER)->data |= EFER_LMA | EFER_LME;
	vmcs_write32(VM_ENTRY_CONTROLS,
		     vmcs_read32(VM_ENTRY_CONTROLS)
		     | VM_ENTRY_CONTROLS_IA32E_MASK);
}

static void exit_lmode(struct kvm_vcpu *vcpu)
{
	vcpu->shadow_efer &= ~EFER_LMA;

	vmcs_write32(VM_ENTRY_CONTROLS,
		     vmcs_read32(VM_ENTRY_CONTROLS)
		     & ~VM_ENTRY_CONTROLS_IA32E_MASK);
}

#endif

static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	if (vcpu->rmode.active && (cr0 & CR0_PE_MASK))
		enter_pmode(vcpu);

	if (!vcpu->rmode.active && !(cr0 & CR0_PE_MASK))
		enter_rmode(vcpu);

771
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811
	if (vcpu->shadow_efer & EFER_LME) {
		if (!is_paging(vcpu) && (cr0 & CR0_PG_MASK))
			enter_lmode(vcpu);
		if (is_paging(vcpu) && !(cr0 & CR0_PG_MASK))
			exit_lmode(vcpu);
	}
#endif

	vmcs_writel(CR0_READ_SHADOW, cr0);
	vmcs_writel(GUEST_CR0,
		    (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON);
	vcpu->cr0 = cr0;
}

/*
 * Used when restoring the VM to avoid corrupting segment registers
 */
static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	vcpu->rmode.active = ((cr0 & CR0_PE_MASK) == 0);
	update_exception_bitmap(vcpu);
	vmcs_writel(CR0_READ_SHADOW, cr0);
	vmcs_writel(GUEST_CR0,
		    (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON);
	vcpu->cr0 = cr0;
}

static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	vmcs_writel(GUEST_CR3, cr3);
}

static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	vmcs_writel(CR4_READ_SHADOW, cr4);
	vmcs_writel(GUEST_CR4, cr4 | (vcpu->rmode.active ?
		    KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON));
	vcpu->cr4 = cr4;
}

812
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098

static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	struct vmx_msr_entry *msr = find_msr_entry(vcpu, MSR_EFER);

	vcpu->shadow_efer = efer;
	if (efer & EFER_LMA) {
		vmcs_write32(VM_ENTRY_CONTROLS,
				     vmcs_read32(VM_ENTRY_CONTROLS) |
				     VM_ENTRY_CONTROLS_IA32E_MASK);
		msr->data = efer;

	} else {
		vmcs_write32(VM_ENTRY_CONTROLS,
				     vmcs_read32(VM_ENTRY_CONTROLS) &
				     ~VM_ENTRY_CONTROLS_IA32E_MASK);

		msr->data = efer & ~EFER_LME;
	}
}

#endif

static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];

	return vmcs_readl(sf->base);
}

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

	var->base = vmcs_readl(sf->base);
	var->limit = vmcs_read32(sf->limit);
	var->selector = vmcs_read16(sf->selector);
	ar = vmcs_read32(sf->ar_bytes);
	if (ar & AR_UNUSABLE_MASK)
		ar = 0;
	var->type = ar & 15;
	var->s = (ar >> 4) & 1;
	var->dpl = (ar >> 5) & 3;
	var->present = (ar >> 7) & 1;
	var->avl = (ar >> 12) & 1;
	var->l = (ar >> 13) & 1;
	var->db = (ar >> 14) & 1;
	var->g = (ar >> 15) & 1;
	var->unusable = (ar >> 16) & 1;
}

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;

	vmcs_writel(sf->base, var->base);
	vmcs_write32(sf->limit, var->limit);
	vmcs_write16(sf->selector, var->selector);
	if (var->unusable)
		ar = 1 << 16;
	else {
		ar = var->type & 15;
		ar |= (var->s & 1) << 4;
		ar |= (var->dpl & 3) << 5;
		ar |= (var->present & 1) << 7;
		ar |= (var->avl & 1) << 12;
		ar |= (var->l & 1) << 13;
		ar |= (var->db & 1) << 14;
		ar |= (var->g & 1) << 15;
	}
	vmcs_write32(sf->ar_bytes, ar);
}

static int vmx_is_long_mode(struct kvm_vcpu *vcpu)
{
	return vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_CONTROLS_IA32E_MASK;
}

static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
	u32 ar = vmcs_read32(GUEST_CS_AR_BYTES);

	*db = (ar >> 14) & 1;
	*l = (ar >> 13) & 1;
}

static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
	dt->limit = vmcs_read32(GUEST_IDTR_LIMIT);
	dt->base = vmcs_readl(GUEST_IDTR_BASE);
}

static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
	vmcs_write32(GUEST_IDTR_LIMIT, dt->limit);
	vmcs_writel(GUEST_IDTR_BASE, dt->base);
}

static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
	dt->limit = vmcs_read32(GUEST_GDTR_LIMIT);
	dt->base = vmcs_readl(GUEST_GDTR_BASE);
}

static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
	vmcs_write32(GUEST_GDTR_LIMIT, dt->limit);
	vmcs_writel(GUEST_GDTR_BASE, dt->base);
}

static int init_rmode_tss(struct kvm* kvm)
{
	struct page *p1, *p2, *p3;
	gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT;
	char *page;

	p1 = _gfn_to_page(kvm, fn++);
	p2 = _gfn_to_page(kvm, fn++);
	p3 = _gfn_to_page(kvm, fn);

	if (!p1 || !p2 || !p3) {
		kvm_printf(kvm,"%s: gfn_to_page failed\n", __FUNCTION__);
		return 0;
	}

	page = kmap_atomic(p1, KM_USER0);
	memset(page, 0, PAGE_SIZE);
	*(u16*)(page + 0x66) = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
	kunmap_atomic(page, KM_USER0);

	page = kmap_atomic(p2, KM_USER0);
	memset(page, 0, PAGE_SIZE);
	kunmap_atomic(page, KM_USER0);

	page = kmap_atomic(p3, KM_USER0);
	memset(page, 0, PAGE_SIZE);
	*(page + RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1) = ~0;
	kunmap_atomic(page, KM_USER0);

	return 1;
}

static void vmcs_write32_fixedbits(u32 msr, u32 vmcs_field, u32 val)
{
	u32 msr_high, msr_low;

	rdmsr(msr, msr_low, msr_high);

	val &= msr_high;
	val |= msr_low;
	vmcs_write32(vmcs_field, val);
}

static void seg_setup(int seg)
{
	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];

	vmcs_write16(sf->selector, 0);
	vmcs_writel(sf->base, 0);
	vmcs_write32(sf->limit, 0xffff);
	vmcs_write32(sf->ar_bytes, 0x93);
}

/*
 * Sets up the vmcs for emulated real mode.
 */
static int vmx_vcpu_setup(struct kvm_vcpu *vcpu)
{
	u32 host_sysenter_cs;
	u32 junk;
	unsigned long a;
	struct descriptor_table dt;
	int i;
	int ret = 0;
	int nr_good_msrs;
	extern asmlinkage void kvm_vmx_return(void);

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

	memset(vcpu->regs, 0, sizeof(vcpu->regs));
	vcpu->regs[VCPU_REGS_RDX] = get_rdx_init_val();
	vcpu->cr8 = 0;
	vcpu->apic_base = 0xfee00000 |
			/*for vcpu 0*/ MSR_IA32_APICBASE_BSP |
			MSR_IA32_APICBASE_ENABLE;

	fx_init(vcpu);

	/*
	 * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
	 * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4.  Sigh.
	 */
	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
	vmcs_writel(GUEST_CS_BASE, 0x000f0000);
	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);
	vmcs_writel(GUEST_RIP, 0xfff0);
	vmcs_writel(GUEST_RSP, 0);

	vmcs_writel(GUEST_CR3, 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);

	/* I/O */
	vmcs_write64(IO_BITMAP_A, 0);
	vmcs_write64(IO_BITMAP_B, 0);

	guest_write_tsc(0);

	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */

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

	/* Control */
	vmcs_write32_fixedbits(MSR_IA32_VMX_PINBASED_CTLS_MSR,
			       PIN_BASED_VM_EXEC_CONTROL,
			       PIN_BASED_EXT_INTR_MASK   /* 20.6.1 */
			       | PIN_BASED_NMI_EXITING   /* 20.6.1 */
			);
	vmcs_write32_fixedbits(MSR_IA32_VMX_PROCBASED_CTLS_MSR,
			       CPU_BASED_VM_EXEC_CONTROL,
			       CPU_BASED_HLT_EXITING         /* 20.6.2 */
			       | CPU_BASED_CR8_LOAD_EXITING    /* 20.6.2 */
			       | CPU_BASED_CR8_STORE_EXITING   /* 20.6.2 */
			       | CPU_BASED_UNCOND_IO_EXITING   /* 20.6.2 */
			       | CPU_BASED_INVDPG_EXITING
			       | CPU_BASED_MOV_DR_EXITING
			       | CPU_BASED_USE_TSC_OFFSETING   /* 21.3 */
			);

	vmcs_write32(EXCEPTION_BITMAP, 1 << PF_VECTOR);
	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */

	vmcs_writel(HOST_CR0, read_cr0());  /* 22.2.3 */
	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */

	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
	vmcs_write16(HOST_FS_SELECTOR, read_fs());    /* 22.2.4 */
	vmcs_write16(HOST_GS_SELECTOR, read_gs());    /* 22.2.4 */
	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
1099
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
	rdmsrl(MSR_FS_BASE, a);
	vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */
	rdmsrl(MSR_GS_BASE, a);
	vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */
#else
	vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
	vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
#endif

	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */

	get_idt(&dt);
	vmcs_writel(HOST_IDTR_BASE, dt.base);   /* 22.2.4 */


	vmcs_writel(HOST_RIP, (unsigned long)kvm_vmx_return); /* 22.2.5 */

	rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
	vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
	rdmsrl(MSR_IA32_SYSENTER_ESP, a);
	vmcs_writel(HOST_IA32_SYSENTER_ESP, a);   /* 22.2.3 */
	rdmsrl(MSR_IA32_SYSENTER_EIP, a);
	vmcs_writel(HOST_IA32_SYSENTER_EIP, a);   /* 22.2.3 */

	ret = -ENOMEM;
	vcpu->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!vcpu->guest_msrs)
		goto out;
	vcpu->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!vcpu->host_msrs)
		goto out_free_guest_msrs;

	for (i = 0; i < NR_VMX_MSR; ++i) {
		u32 index = vmx_msr_index[i];
		u32 data_low, data_high;
		u64 data;
		int j = vcpu->nmsrs;

		if (rdmsr_safe(index, &data_low, &data_high) < 0)
			continue;
		data = data_low | ((u64)data_high << 32);
		vcpu->host_msrs[j].index = index;
		vcpu->host_msrs[j].reserved = 0;
		vcpu->host_msrs[j].data = data;
		vcpu->guest_msrs[j] = vcpu->host_msrs[j];
		++vcpu->nmsrs;
	}
	printk(KERN_DEBUG "kvm: msrs: %d\n", vcpu->nmsrs);

	nr_good_msrs = vcpu->nmsrs - NR_BAD_MSRS;
	vmcs_writel(VM_ENTRY_MSR_LOAD_ADDR,
		    virt_to_phys(vcpu->guest_msrs + NR_BAD_MSRS));
	vmcs_writel(VM_EXIT_MSR_STORE_ADDR,
		    virt_to_phys(vcpu->guest_msrs + NR_BAD_MSRS));
	vmcs_writel(VM_EXIT_MSR_LOAD_ADDR,
		    virt_to_phys(vcpu->host_msrs + NR_BAD_MSRS));
	vmcs_write32_fixedbits(MSR_IA32_VMX_EXIT_CTLS_MSR, VM_EXIT_CONTROLS,
		     	       (HOST_IS_64 << 9));  /* 22.2,1, 20.7.1 */
	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, nr_good_msrs); /* 22.2.2 */
	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, nr_good_msrs);  /* 22.2.2 */
	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */


	/* 22.2.1, 20.8.1 */
	vmcs_write32_fixedbits(MSR_IA32_VMX_ENTRY_CTLS_MSR,
                               VM_ENTRY_CONTROLS, 0);
	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */

	vmcs_writel(VIRTUAL_APIC_PAGE_ADDR, 0);
	vmcs_writel(TPR_THRESHOLD, 0);

	vmcs_writel(CR0_GUEST_HOST_MASK, KVM_GUEST_CR0_MASK);
	vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);

	vcpu->cr0 = 0x60000010;
	vmx_set_cr0(vcpu, vcpu->cr0); // enter rmode
	vmx_set_cr4(vcpu, 0);
1177
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692
	vmx_set_efer(vcpu, 0);
#endif

	return 0;

out_free_guest_msrs:
	kfree(vcpu->guest_msrs);
out:
	return ret;
}

static void inject_rmode_irq(struct kvm_vcpu *vcpu, int irq)
{
	u16 ent[2];
	u16 cs;
	u16 ip;
	unsigned long flags;
	unsigned long ss_base = vmcs_readl(GUEST_SS_BASE);
	u16 sp =  vmcs_readl(GUEST_RSP);
	u32 ss_limit = vmcs_read32(GUEST_SS_LIMIT);

	if (sp > ss_limit || sp - 6 > sp) {
		vcpu_printf(vcpu, "%s: #SS, rsp 0x%lx ss 0x%lx limit 0x%x\n",
			    __FUNCTION__,
			    vmcs_readl(GUEST_RSP),
			    vmcs_readl(GUEST_SS_BASE),
			    vmcs_read32(GUEST_SS_LIMIT));
		return;
	}

	if (kvm_read_guest(vcpu, irq * sizeof(ent), sizeof(ent), &ent) !=
								sizeof(ent)) {
		vcpu_printf(vcpu, "%s: read guest err\n", __FUNCTION__);
		return;
	}

	flags =  vmcs_readl(GUEST_RFLAGS);
	cs =  vmcs_readl(GUEST_CS_BASE) >> 4;
	ip =  vmcs_readl(GUEST_RIP);


	if (kvm_write_guest(vcpu, ss_base + sp - 2, 2, &flags) != 2 ||
	    kvm_write_guest(vcpu, ss_base + sp - 4, 2, &cs) != 2 ||
	    kvm_write_guest(vcpu, ss_base + sp - 6, 2, &ip) != 2) {
		vcpu_printf(vcpu, "%s: write guest err\n", __FUNCTION__);
		return;
	}

	vmcs_writel(GUEST_RFLAGS, flags &
		    ~( X86_EFLAGS_IF | X86_EFLAGS_AC | X86_EFLAGS_TF));
	vmcs_write16(GUEST_CS_SELECTOR, ent[1]) ;
	vmcs_writel(GUEST_CS_BASE, ent[1] << 4);
	vmcs_writel(GUEST_RIP, ent[0]);
	vmcs_writel(GUEST_RSP, (vmcs_readl(GUEST_RSP) & ~0xffff) | (sp - 6));
}

static void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
{
	int word_index = __ffs(vcpu->irq_summary);
	int bit_index = __ffs(vcpu->irq_pending[word_index]);
	int irq = word_index * BITS_PER_LONG + bit_index;

	clear_bit(bit_index, &vcpu->irq_pending[word_index]);
	if (!vcpu->irq_pending[word_index])
		clear_bit(word_index, &vcpu->irq_summary);

	if (vcpu->rmode.active) {
		inject_rmode_irq(vcpu, irq);
		return;
	}
	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
			irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}

static void kvm_try_inject_irq(struct kvm_vcpu *vcpu)
{
	if ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF)
	    && (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0)
		/*
		 * Interrupts enabled, and not blocked by sti or mov ss. Good.
		 */
		kvm_do_inject_irq(vcpu);
	else
		/*
		 * Interrupts blocked.  Wait for unblock.
		 */
		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
			     | CPU_BASED_VIRTUAL_INTR_PENDING);
}

static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
{
	struct kvm_guest_debug *dbg = &vcpu->guest_debug;

	set_debugreg(dbg->bp[0], 0);
	set_debugreg(dbg->bp[1], 1);
	set_debugreg(dbg->bp[2], 2);
	set_debugreg(dbg->bp[3], 3);

	if (dbg->singlestep) {
		unsigned long flags;

		flags = vmcs_readl(GUEST_RFLAGS);
		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
		vmcs_writel(GUEST_RFLAGS, flags);
	}
}

static int handle_rmode_exception(struct kvm_vcpu *vcpu,
				  int vec, u32 err_code)
{
	if (!vcpu->rmode.active)
		return 0;

	if (vec == GP_VECTOR && err_code == 0)
		if (emulate_instruction(vcpu, NULL, 0, 0) == EMULATE_DONE)
			return 1;
	return 0;
}

static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u32 intr_info, error_code;
	unsigned long cr2, rip;
	u32 vect_info;
	enum emulation_result er;

	vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);

	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
						!is_page_fault(intr_info)) {
		printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
		       "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info);
	}

	if (is_external_interrupt(vect_info)) {
		int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
		set_bit(irq, vcpu->irq_pending);
		set_bit(irq / BITS_PER_LONG, &vcpu->irq_summary);
	}

	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */
		asm ("int $2");
		return 1;
	}
	error_code = 0;
	rip = vmcs_readl(GUEST_RIP);
	if (intr_info & INTR_INFO_DELIEVER_CODE_MASK)
		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
	if (is_page_fault(intr_info)) {
		cr2 = vmcs_readl(EXIT_QUALIFICATION);

		spin_lock(&vcpu->kvm->lock);
		if (!vcpu->mmu.page_fault(vcpu, cr2, error_code)) {
			spin_unlock(&vcpu->kvm->lock);
			return 1;
		}

		er = emulate_instruction(vcpu, kvm_run, cr2, error_code);
		spin_unlock(&vcpu->kvm->lock);

		switch (er) {
		case EMULATE_DONE:
			return 1;
		case EMULATE_DO_MMIO:
			++kvm_stat.mmio_exits;
			kvm_run->exit_reason = KVM_EXIT_MMIO;
			return 0;
		 case EMULATE_FAIL:
			vcpu_printf(vcpu, "%s: emulate fail\n", __FUNCTION__);
			break;
		default:
			BUG();
		}
	}

	if (vcpu->rmode.active &&
	    handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK,
								error_code))
		return 1;

	if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == (INTR_TYPE_EXCEPTION | 1)) {
		kvm_run->exit_reason = KVM_EXIT_DEBUG;
		return 0;
	}
	kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
	kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
	kvm_run->ex.error_code = error_code;
	return 0;
}

static int handle_external_interrupt(struct kvm_vcpu *vcpu,
				     struct kvm_run *kvm_run)
{
	++kvm_stat.irq_exits;
	return 1;
}


static int get_io_count(struct kvm_vcpu *vcpu, u64 *count)
{
	u64 inst;
	gva_t rip;
	int countr_size;
	int i, n;

	if ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_VM)) {
		countr_size = 2;
	} else {
		u32 cs_ar = vmcs_read32(GUEST_CS_AR_BYTES);

		countr_size = (cs_ar & AR_L_MASK) ? 8:
			      (cs_ar & AR_DB_MASK) ? 4: 2;
	}

	rip =  vmcs_readl(GUEST_RIP);
	if (countr_size != 8)
		rip += vmcs_readl(GUEST_CS_BASE);

	n = kvm_read_guest(vcpu, rip, sizeof(inst), &inst);

	for (i = 0; i < n; i++) {
		switch (((u8*)&inst)[i]) {
		case 0xf0:
		case 0xf2:
		case 0xf3:
		case 0x2e:
		case 0x36:
		case 0x3e:
		case 0x26:
		case 0x64:
		case 0x65:
		case 0x66:
			break;
		case 0x67:
			countr_size = (countr_size == 2) ? 4: (countr_size >> 1);
		default:
			goto done;
		}
	}
	return 0;
done:
	countr_size *= 8;
	*count = vcpu->regs[VCPU_REGS_RCX] & (~0ULL >> (64 - countr_size));
	return 1;
}

static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u64 exit_qualification;

	++kvm_stat.io_exits;
	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
	kvm_run->exit_reason = KVM_EXIT_IO;
	if (exit_qualification & 8)
		kvm_run->io.direction = KVM_EXIT_IO_IN;
	else
		kvm_run->io.direction = KVM_EXIT_IO_OUT;
	kvm_run->io.size = (exit_qualification & 7) + 1;
	kvm_run->io.string = (exit_qualification & 16) != 0;
	kvm_run->io.string_down
		= (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
	kvm_run->io.rep = (exit_qualification & 32) != 0;
	kvm_run->io.port = exit_qualification >> 16;
	if (kvm_run->io.string) {
		if (!get_io_count(vcpu, &kvm_run->io.count))
			return 1;
		kvm_run->io.address = vmcs_readl(GUEST_LINEAR_ADDRESS);
	} else
		kvm_run->io.value = vcpu->regs[VCPU_REGS_RAX]; /* rax */
	return 0;
}

static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u64 address = vmcs_read64(EXIT_QUALIFICATION);
	int instruction_length = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
	spin_lock(&vcpu->kvm->lock);
	vcpu->mmu.inval_page(vcpu, address);
	spin_unlock(&vcpu->kvm->lock);
	vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP) + instruction_length);
	return 1;
}

static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u64 exit_qualification;
	int cr;
	int reg;

	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
	cr = exit_qualification & 15;
	reg = (exit_qualification >> 8) & 15;
	switch ((exit_qualification >> 4) & 3) {
	case 0: /* mov to cr */
		switch (cr) {
		case 0:
			vcpu_load_rsp_rip(vcpu);
			set_cr0(vcpu, vcpu->regs[reg]);
			skip_emulated_instruction(vcpu);
			return 1;
		case 3:
			vcpu_load_rsp_rip(vcpu);
			set_cr3(vcpu, vcpu->regs[reg]);
			skip_emulated_instruction(vcpu);
			return 1;
		case 4:
			vcpu_load_rsp_rip(vcpu);
			set_cr4(vcpu, vcpu->regs[reg]);
			skip_emulated_instruction(vcpu);
			return 1;
		case 8:
			vcpu_load_rsp_rip(vcpu);
			set_cr8(vcpu, vcpu->regs[reg]);
			skip_emulated_instruction(vcpu);
			return 1;
		};
		break;
	case 1: /*mov from cr*/
		switch (cr) {
		case 3:
			vcpu_load_rsp_rip(vcpu);
			vcpu->regs[reg] = vcpu->cr3;
			vcpu_put_rsp_rip(vcpu);
			skip_emulated_instruction(vcpu);
			return 1;
		case 8:
			printk(KERN_DEBUG "handle_cr: read CR8 "
			       "cpu erratum AA15\n");
			vcpu_load_rsp_rip(vcpu);
			vcpu->regs[reg] = vcpu->cr8;
			vcpu_put_rsp_rip(vcpu);
			skip_emulated_instruction(vcpu);
			return 1;
		}
		break;
	case 3: /* lmsw */
		lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);

		skip_emulated_instruction(vcpu);
		return 1;
	default:
		break;
	}
	kvm_run->exit_reason = 0;
	printk(KERN_ERR "kvm: unhandled control register: op %d cr %d\n",
	       (int)(exit_qualification >> 4) & 3, cr);
	return 0;
}

static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u64 exit_qualification;
	unsigned long val;
	int dr, reg;

	/*
	 * FIXME: this code assumes the host is debugging the guest.
	 *        need to deal with guest debugging itself too.
	 */
	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
	dr = exit_qualification & 7;
	reg = (exit_qualification >> 8) & 15;
	vcpu_load_rsp_rip(vcpu);
	if (exit_qualification & 16) {
		/* mov from dr */
		switch (dr) {
		case 6:
			val = 0xffff0ff0;
			break;
		case 7:
			val = 0x400;
			break;
		default:
			val = 0;
		}
		vcpu->regs[reg] = val;
	} else {
		/* mov to dr */
	}
	vcpu_put_rsp_rip(vcpu);
	skip_emulated_instruction(vcpu);
	return 1;
}

static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	kvm_run->exit_reason = KVM_EXIT_CPUID;
	return 0;
}

static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u32 ecx = vcpu->regs[VCPU_REGS_RCX];
	u64 data;

	if (vmx_get_msr(vcpu, ecx, &data)) {
		vmx_inject_gp(vcpu, 0);
		return 1;
	}

	/* FIXME: handling of bits 32:63 of rax, rdx */
	vcpu->regs[VCPU_REGS_RAX] = data & -1u;
	vcpu->regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
	skip_emulated_instruction(vcpu);
	return 1;
}

static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u32 ecx = vcpu->regs[VCPU_REGS_RCX];
	u64 data = (vcpu->regs[VCPU_REGS_RAX] & -1u)
		| ((u64)(vcpu->regs[VCPU_REGS_RDX] & -1u) << 32);

	if (vmx_set_msr(vcpu, ecx, data) != 0) {
		vmx_inject_gp(vcpu, 0);
		return 1;
	}

	skip_emulated_instruction(vcpu);
	return 1;
}

static int handle_interrupt_window(struct kvm_vcpu *vcpu,
				   struct kvm_run *kvm_run)
{
	/* Turn off interrupt window reporting. */
	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
		     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
		     & ~CPU_BASED_VIRTUAL_INTR_PENDING);
	return 1;
}

static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	skip_emulated_instruction(vcpu);
	if (vcpu->irq_summary && (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF))
		return 1;

	kvm_run->exit_reason = KVM_EXIT_HLT;
	return 0;
}

/*
 * 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_IO_INSTRUCTION]          = handle_io,
	[EXIT_REASON_INVLPG]                  = handle_invlpg,
	[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,
};

static const int kvm_vmx_max_exit_handlers =
	sizeof(kvm_vmx_exit_handlers) / sizeof(*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);

	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);
	kvm_run->instruction_length = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
	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 int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	u8 fail;
	u16 fs_sel, gs_sel, ldt_sel;
	int fs_gs_ldt_reload_needed;

again:
	/*
	 * Set host fs and gs selectors.  Unfortunately, 22.2.3 does not
	 * allow segment selectors with cpl > 0 or ti == 1.
	 */
	fs_sel = read_fs();
	gs_sel = read_gs();
	ldt_sel = read_ldt();
	fs_gs_ldt_reload_needed = (fs_sel & 7) | (gs_sel & 7) | ldt_sel;
	if (!fs_gs_ldt_reload_needed) {
		vmcs_write16(HOST_FS_SELECTOR, fs_sel);
		vmcs_write16(HOST_GS_SELECTOR, gs_sel);
	} else {
		vmcs_write16(HOST_FS_SELECTOR, 0);
		vmcs_write16(HOST_GS_SELECTOR, 0);
	}

1693
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716
	vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE));
	vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE));
#else
	vmcs_writel(HOST_FS_BASE, segment_base(fs_sel));
	vmcs_writel(HOST_GS_BASE, segment_base(gs_sel));
#endif

	if (vcpu->irq_summary &&
	    !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK))
		kvm_try_inject_irq(vcpu);

	if (vcpu->guest_debug.enabled)
		kvm_guest_debug_pre(vcpu);

	fx_save(vcpu->host_fx_image);
	fx_restore(vcpu->guest_fx_image);

	save_msrs(vcpu->host_msrs, vcpu->nmsrs);
	load_msrs(vcpu->guest_msrs, NR_BAD_MSRS);

	asm (
		/* Store host registers */
		"pushf \n\t"
1717
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
		"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. */
1731
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
		"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 launched \n\t"
		ASM_VMX_VMLAUNCH "\n\t"
		"jmp kvm_vmx_return \n\t"
		"launched: " ASM_VMX_VMRESUME "\n\t"
		".globl kvm_vmx_return \n\t"
		"kvm_vmx_return: "
		/* Save guest registers, load host registers, keep flags */
1768
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819
		"xchg %3,     0(%%rsp) \n\t"
		"mov %%rax, %c[rax](%3) \n\t"
		"mov %%rbx, %c[rbx](%3) \n\t"
		"pushq 0(%%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 0(%%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, 0(%%esp) \n\t"
		"mov %%eax, %c[rax](%3) \n\t"
		"mov %%ebx, %c[rbx](%3) \n\t"
		"pushl 0(%%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 0(%%esp), %3 \n\t"

		"pop %%ecx; popa \n\t"
#endif
		"setbe %0 \n\t"
		"popf \n\t"
	      : "=g" (fail)
	      : "r"(vcpu->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])),
1820
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840
		[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" );

	++kvm_stat.exits;

	save_msrs(vcpu->guest_msrs, NR_BAD_MSRS);
	load_msrs(vcpu->host_msrs, NR_BAD_MSRS);

	fx_save(vcpu->guest_fx_image);
	fx_restore(vcpu->host_fx_image);

1841
#ifndef CONFIG_X86_64
A
Avi Kivity 已提交
1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858
	asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
#endif

	kvm_run->exit_type = 0;
	if (fail) {
		kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY;
		kvm_run->exit_reason = vmcs_read32(VM_INSTRUCTION_ERROR);
	} else {
		if (fs_gs_ldt_reload_needed) {
			load_ldt(ldt_sel);
			load_fs(fs_sel);
			/*
			 * If we have to reload gs, we must take care to
			 * preserve our gs base.
			 */
			local_irq_disable();
			load_gs(gs_sel);
1859
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
			wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE));
#endif
			local_irq_enable();

			reload_tss();
		}
		vcpu->launched = 1;
		kvm_run->exit_type = KVM_EXIT_TYPE_VM_EXIT;
		if (kvm_handle_exit(kvm_run, vcpu)) {
			/* Give scheduler a change to reschedule. */
			if (signal_pending(current)) {
				++kvm_stat.signal_exits;
				return -EINTR;
			}
			kvm_resched(vcpu);
			goto again;
		}
	}
	return 0;
}

static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
	vmcs_writel(GUEST_CR3, vmcs_readl(GUEST_CR3));
}

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);

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

static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
	vmx_free_vmcs(vcpu);
}

static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
{
	struct vmcs *vmcs;

	vmcs = alloc_vmcs();
	if (!vmcs)
		return -ENOMEM;
	vmcs_clear(vmcs);
	vcpu->vmcs = vmcs;
	vcpu->launched = 0;
	return 0;
}

static struct kvm_arch_ops vmx_arch_ops = {
	.cpu_has_kvm_support = cpu_has_kvm_support,
	.disabled_by_bios = vmx_disabled_by_bios,
	.hardware_setup = hardware_setup,
	.hardware_unsetup = hardware_unsetup,
	.hardware_enable = hardware_enable,
	.hardware_disable = hardware_disable,

	.vcpu_create = vmx_create_vcpu,
	.vcpu_free = vmx_free_vcpu,

	.vcpu_load = vmx_vcpu_load,
	.vcpu_put = vmx_vcpu_put,

	.set_guest_debug = set_guest_debug,
	.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,
	.is_long_mode = vmx_is_long_mode,
	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
	.set_cr0 = vmx_set_cr0,
	.set_cr0_no_modeswitch = vmx_set_cr0_no_modeswitch,
	.set_cr3 = vmx_set_cr3,
	.set_cr4 = vmx_set_cr4,
1969
#ifdef CONFIG_X86_64
A
Avi Kivity 已提交
1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
	.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,
	.skip_emulated_instruction = skip_emulated_instruction,
	.vcpu_setup = vmx_vcpu_setup,
};

static int __init vmx_init(void)
{
	kvm_init_arch(&vmx_arch_ops, THIS_MODULE);
	return 0;
}

static void __exit vmx_exit(void)
{
	kvm_exit_arch();
}

module_init(vmx_init)
module_exit(vmx_exit)