UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/x86/kvm/vmx.c

4453 lines
113 KiB
C
Raw Blame History

/*
* 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.
* Copyright 2010 Red Hat, Inc. and/or its affilates.
*
* 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 "irq.h"
#include "mmu.h"
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/ftrace_event.h>
#include <linux/slab.h>
#include <linux/tboot.h>
#include "kvm_cache_regs.h"
#include "x86.h"
#include <asm/io.h>
#include <asm/desc.h>
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>
#include "trace.h"
#define __ex(x) __kvm_handle_fault_on_reboot(x)
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
static int __read_mostly bypass_guest_pf = 1;
module_param(bypass_guest_pf, bool, S_IRUGO);
static int __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
static int __read_mostly flexpriority_enabled = 1;
module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
static int __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);
static int __read_mostly enable_unrestricted_guest = 1;
module_param_named(unrestricted_guest,
enable_unrestricted_guest, bool, S_IRUGO);
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
static int __read_mostly vmm_exclusive = 1;
module_param(vmm_exclusive, bool, S_IRUGO);
#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
#define KVM_GUEST_CR0_MASK \
(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
(X86_CR0_WP | X86_CR0_NE)
#define KVM_VM_CR0_ALWAYS_ON \
(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_CR4_GUEST_OWNED_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
| X86_CR4_OSXMMEXCPT)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* ple_gap: upper bound on the amount of time between two successive
* executions of PAUSE in a loop. Also indicate if ple enabled.
* According to test, this time is usually small than 41 cycles.
* ple_window: upper bound on the amount of time a guest is allowed to execute
* in a PAUSE loop. Tests indicate that most spinlocks are held for
* less than 2^12 cycles
* Time is measured based on a counter that runs at the same rate as the TSC,
* refer SDM volume 3b section 21.6.13 & 22.1.3.
*/
#define KVM_VMX_DEFAULT_PLE_GAP 41
#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
module_param(ple_gap, int, S_IRUGO);
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
#define NR_AUTOLOAD_MSRS 1
struct vmcs {
u32 revision_id;
u32 abort;
char data[0];
};
struct shared_msr_entry {
unsigned index;
u64 data;
u64 mask;
};
struct vcpu_vmx {
struct kvm_vcpu vcpu;
struct list_head local_vcpus_link;
unsigned long host_rsp;
int launched;
u8 fail;
u32 idt_vectoring_info;
struct shared_msr_entry *guest_msrs;
int nmsrs;
int save_nmsrs;
#ifdef CONFIG_X86_64
u64 msr_host_kernel_gs_base;
u64 msr_guest_kernel_gs_base;
#endif
struct vmcs *vmcs;
struct msr_autoload {
unsigned nr;
struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
} msr_autoload;
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
int gs_ldt_reload_needed;
int fs_reload_needed;
} host_state;
struct {
int vm86_active;
ulong save_rflags;
struct kvm_save_segment {
u16 selector;
unsigned long base;
u32 limit;
u32 ar;
} tr, es, ds, fs, gs;
struct {
bool pending;
u8 vector;
unsigned rip;
} irq;
} rmode;
int vpid;
bool emulation_required;
/* Support for vnmi-less CPUs */
int soft_vnmi_blocked;
ktime_t entry_time;
s64 vnmi_blocked_time;
u32 exit_reason;
bool rdtscp_enabled;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
{
return container_of(vcpu, struct vcpu_vmx, vcpu);
}
static int init_rmode(struct kvm *kvm);
static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
static unsigned long *vmx_io_bitmap_a;
static unsigned long *vmx_io_bitmap_b;
static unsigned long *vmx_msr_bitmap_legacy;
static unsigned long *vmx_msr_bitmap_longmode;
static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);
static struct vmcs_config {
int size;
int order;
u32 revision_id;
u32 pin_based_exec_ctrl;
u32 cpu_based_exec_ctrl;
u32 cpu_based_2nd_exec_ctrl;
u32 vmexit_ctrl;
u32 vmentry_ctrl;
} vmcs_config;
static struct vmx_capability {
u32 ept;
u32 vpid;
} vmx_capability;
#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 u64 host_efer;
static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
/*
* Keep MSR_STAR at the end, as setup_msrs() will try to optimize it
* away by decrementing the array size.
*/
static const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
static inline bool is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}
static inline bool is_no_device(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
static inline bool is_invalid_opcode(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
}
static inline bool 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 inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}
static inline bool cpu_has_vmx_tpr_shadow(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}
static inline bool vm_need_tpr_shadow(struct kvm *kvm)
{
return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
}
static inline bool cpu_has_secondary_exec_ctrls(void)
{
return vmcs_config.cpu_based_exec_ctrl &
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
}
static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
}
static inline bool cpu_has_vmx_flexpriority(void)
{
return cpu_has_vmx_tpr_shadow() &&
cpu_has_vmx_virtualize_apic_accesses();
}
static inline bool cpu_has_vmx_ept_execute_only(void)
{
return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}
static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
return vmx_capability.ept & VMX_EPTP_UC_BIT;
}
static inline bool cpu_has_vmx_eptp_writeback(void)
{
return vmx_capability.ept & VMX_EPTP_WB_BIT;
}
static inline bool cpu_has_vmx_ept_2m_page(void)
{
return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
}
static inline bool cpu_has_vmx_ept_1g_page(void)
{
return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
}
static inline bool cpu_has_vmx_ept_4levels(void)
{
return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
}
static inline bool cpu_has_vmx_invept_individual_addr(void)
{
return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
}
static inline bool cpu_has_vmx_invept_context(void)
{
return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}
static inline bool cpu_has_vmx_invept_global(void)
{
return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
static inline bool cpu_has_vmx_invvpid_single(void)
{
return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
}
static inline bool cpu_has_vmx_invvpid_global(void)
{
return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}
static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_EPT;
}
static inline bool cpu_has_vmx_unrestricted_guest(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_UNRESTRICTED_GUEST;
}
static inline bool cpu_has_vmx_ple(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled && irqchip_in_kernel(kvm);
}
static inline bool cpu_has_vmx_vpid(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_VPID;
}
static inline bool cpu_has_vmx_rdtscp(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_RDTSCP;
}
static inline bool cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}
static inline bool cpu_has_vmx_wbinvd_exit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_WBINVD_EXITING;
}
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
}
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
int i;
for (i = 0; i < vmx->nmsrs; ++i)
if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
return i;
return -1;
}
static inline void __invvpid(int ext, u16 vpid, gva_t gva)
{
struct {
u64 vpid : 16;
u64 rsvd : 48;
u64 gva;
} operand = { vpid, 0, gva };
asm volatile (__ex(ASM_VMX_INVVPID)
/* CF==1 or ZF==1 --> rc = -1 */
"; ja 1f ; ud2 ; 1:"
: : "a"(&operand), "c"(ext) : "cc", "memory");
}
static inline void __invept(int ext, u64 eptp, gpa_t gpa)
{
struct {
u64 eptp, gpa;
} operand = {eptp, gpa};
asm volatile (__ex(ASM_VMX_INVEPT)
/* CF==1 or ZF==1 --> rc = -1 */
"; ja 1f ; ud2 ; 1:\n"
: : "a" (&operand), "c" (ext) : "cc", "memory");
}
static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
int i;
i = __find_msr_index(vmx, msr);
if (i >= 0)
return &vmx->guest_msrs[i];
return NULL;
}
static void vmcs_clear(struct vmcs *vmcs)
{
u64 phys_addr = __pa(vmcs);
u8 error;
asm volatile (__ex(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 vmcs_load(struct vmcs *vmcs)
{
u64 phys_addr = __pa(vmcs);
u8 error;
asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0"
: "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
: "cc", "memory");
if (error)
printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
vmcs, phys_addr);
}
static void __vcpu_clear(void *arg)
{
struct vcpu_vmx *vmx = arg;
int cpu = raw_smp_processor_id();
if (vmx->vcpu.cpu == cpu)
vmcs_clear(vmx->vmcs);
if (per_cpu(current_vmcs, cpu) == vmx->vmcs)
per_cpu(current_vmcs, cpu) = NULL;
rdtscll(vmx->vcpu.arch.host_tsc);
list_del(&vmx->local_vcpus_link);
vmx->vcpu.cpu = -1;
vmx->launched = 0;
}
static void vcpu_clear(struct vcpu_vmx *vmx)
{
if (vmx->vcpu.cpu == -1)
return;
smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1);
}
static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx)
{
if (vmx->vpid == 0)
return;
if (cpu_has_vmx_invvpid_single())
__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
}
static inline void vpid_sync_vcpu_global(void)
{
if (cpu_has_vmx_invvpid_global())
__invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
}
static inline void vpid_sync_context(struct vcpu_vmx *vmx)
{
if (cpu_has_vmx_invvpid_single())
vpid_sync_vcpu_single(vmx);
else
vpid_sync_vcpu_global();
}
static inline void ept_sync_global(void)
{
if (cpu_has_vmx_invept_global())
__invept(VMX_EPT_EXTENT_GLOBAL, 0, 0);
}
static inline void ept_sync_context(u64 eptp)
{
if (enable_ept) {
if (cpu_has_vmx_invept_context())
__invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0);
else
ept_sync_global();
}
}
static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa)
{
if (enable_ept) {
if (cpu_has_vmx_invept_individual_addr())
__invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR,
eptp, gpa);
else
ept_sync_context(eptp);
}
}
static unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
asm volatile (__ex(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)
{
#ifdef CONFIG_X86_64
return vmcs_readl(field);
#else
return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32);
#endif
}
static noinline void vmwrite_error(unsigned long field, unsigned long value)
{
printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
dump_stack();
}
static void vmcs_writel(unsigned long field, unsigned long value)
{
u8 error;
asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) "; setna %0"
: "=q"(error) : "a"(value), "d"(field) : "cc");
if (unlikely(error))
vmwrite_error(field, value);
}
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)
{
vmcs_writel(field, value);
#ifndef CONFIG_X86_64
asm volatile ("");
vmcs_writel(field+1, value >> 32);
#endif
}
static void vmcs_clear_bits(unsigned long field, u32 mask)
{
vmcs_writel(field, vmcs_readl(field) & ~mask);
}
static void vmcs_set_bits(unsigned long field, u32 mask)
{
vmcs_writel(field, vmcs_readl(field) | mask);
}
static void update_exception_bitmap(struct kvm_vcpu *vcpu)
{
u32 eb;
eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
(1u << NM_VECTOR) | (1u << DB_VECTOR);
if ((vcpu->guest_debug &
(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
eb |= 1u << BP_VECTOR;
if (to_vmx(vcpu)->rmode.vm86_active)
eb = ~0;
if (enable_ept)
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
if (vcpu->fpu_active)
eb &= ~(1u << NM_VECTOR);
vmcs_write32(EXCEPTION_BITMAP, eb);
}
static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
for (i = 0; i < m->nr; ++i)
if (m->guest[i].index == msr)
break;
if (i == m->nr)
return;
--m->nr;
m->guest[i] = m->guest[m->nr];
m->host[i] = m->host[m->nr];
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}
static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
u64 guest_val, u64 host_val)
{
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
for (i = 0; i < m->nr; ++i)
if (m->guest[i].index == msr)
break;
if (i == m->nr) {
++m->nr;
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}
m->guest[i].index = msr;
m->guest[i].value = guest_val;
m->host[i].index = msr;
m->host[i].value = host_val;
}
static void reload_tss(void)
{
/*
* VT restores TR but not its size. Useless.
*/
struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
struct desc_struct *descs;
descs = (void *)gdt->address;
descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
load_TR_desc();
}
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
u64 guest_efer;
u64 ignore_bits;
guest_efer = vmx->vcpu.arch.efer;
/*
* NX is emulated; LMA and LME handled by hardware; SCE meaninless
* outside long mode
*/
ignore_bits = EFER_NX | EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
guest_efer &= ~ignore_bits;
guest_efer |= host_efer & ignore_bits;
vmx->guest_msrs[efer_offset].data = guest_efer;
vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
/* On ept, can't emulate nx, and must switch nx atomically */
if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
return false;
}
return true;
}
static unsigned long segment_base(u16 selector)
{
struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
struct desc_struct *d;
unsigned long table_base;
unsigned long v;
if (!(selector & ~3))
return 0;
table_base = gdt->address;
if (selector & 4) { /* from ldt */
u16 ldt_selector = kvm_read_ldt();
if (!(ldt_selector & ~3))
return 0;
table_base = segment_base(ldt_selector);
}
d = (struct desc_struct *)(table_base + (selector & ~7));
v = get_desc_base(d);
#ifdef CONFIG_X86_64
if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
#endif
return v;
}
static inline unsigned long kvm_read_tr_base(void)
{
u16 tr;
asm("str %0" : "=g"(tr));
return segment_base(tr);
}
static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int i;
if (vmx->host_state.loaded)
return;
vmx->host_state.loaded = 1;
/*
* Set host fs and gs selectors. Unfortunately, 22.2.3 does not
* allow segment selectors with cpl > 0 or ti == 1.
*/
vmx->host_state.ldt_sel = kvm_read_ldt();
vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
savesegment(fs, vmx->host_state.fs_sel);
if (!(vmx->host_state.fs_sel & 7)) {
vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
vmx->host_state.fs_reload_needed = 0;
} else {
vmcs_write16(HOST_FS_SELECTOR, 0);
vmx->host_state.fs_reload_needed = 1;
}
savesegment(gs, vmx->host_state.gs_sel);
if (!(vmx->host_state.gs_sel & 7))
vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel);
else {
vmcs_write16(HOST_GS_SELECTOR, 0);
vmx->host_state.gs_ldt_reload_needed = 1;
}
#ifdef CONFIG_X86_64
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(vmx->host_state.fs_sel));
vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel));
#endif
#ifdef CONFIG_X86_64
if (is_long_mode(&vmx->vcpu)) {
rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
}
#endif
for (i = 0; i < vmx->save_nmsrs; ++i)
kvm_set_shared_msr(vmx->guest_msrs[i].index,
vmx->guest_msrs[i].data,
vmx->guest_msrs[i].mask);
}
static void __vmx_load_host_state(struct vcpu_vmx *vmx)
{
if (!vmx->host_state.loaded)
return;
++vmx->vcpu.stat.host_state_reload;
vmx->host_state.loaded = 0;
if (vmx->host_state.fs_reload_needed)
loadsegment(fs, vmx->host_state.fs_sel);
if (vmx->host_state.gs_ldt_reload_needed) {
kvm_load_ldt(vmx->host_state.ldt_sel);
#ifdef CONFIG_X86_64
load_gs_index(vmx->host_state.gs_sel);
wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
#else
loadsegment(gs, vmx->host_state.gs_sel);
#endif
}
reload_tss();
#ifdef CONFIG_X86_64
if (is_long_mode(&vmx->vcpu)) {
rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
}
#endif
if (current_thread_info()->status & TS_USEDFPU)
clts();
load_gdt(&__get_cpu_var(host_gdt));
}
static void vmx_load_host_state(struct vcpu_vmx *vmx)
{
preempt_disable();
__vmx_load_host_state(vmx);
preempt_enable();
}
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
*/
static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 tsc_this, delta, new_offset;
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
if (!vmm_exclusive)
kvm_cpu_vmxon(phys_addr);
else if (vcpu->cpu != cpu)
vcpu_clear(vmx);
if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
per_cpu(current_vmcs, cpu) = vmx->vmcs;
vmcs_load(vmx->vmcs);
}
if (vcpu->cpu != cpu) {
struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
unsigned long sysenter_esp;
kvm_migrate_timers(vcpu);
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
local_irq_disable();
list_add(&vmx->local_vcpus_link,
&per_cpu(vcpus_on_cpu, cpu));
local_irq_enable();
vcpu->cpu = cpu;
/*
* Linux uses per-cpu TSS and GDT, so set these when switching
* processors.
*/
vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */
vmcs_writel(HOST_GDTR_BASE, gdt->address); /* 22.2.4 */
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
/*
* Make sure the time stamp counter is monotonous.
*/
rdtscll(tsc_this);
if (tsc_this < vcpu->arch.host_tsc) {
delta = vcpu->arch.host_tsc - tsc_this;
new_offset = vmcs_read64(TSC_OFFSET) + delta;
vmcs_write64(TSC_OFFSET, new_offset);
}
}
}
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
__vmx_load_host_state(to_vmx(vcpu));
if (!vmm_exclusive) {
__vcpu_clear(to_vmx(vcpu));
kvm_cpu_vmxoff();
}
}
static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
{
ulong cr0;
if (vcpu->fpu_active)
return;
vcpu->fpu_active = 1;
cr0 = vmcs_readl(GUEST_CR0);
cr0 &= ~(X86_CR0_TS | X86_CR0_MP);
cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP);
vmcs_writel(GUEST_CR0, cr0);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
{
vmx_decache_cr0_guest_bits(vcpu);
vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = 0;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
}
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
unsigned long rflags, save_rflags;
rflags = vmcs_readl(GUEST_RFLAGS);
if (to_vmx(vcpu)->rmode.vm86_active) {
rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
save_rflags = to_vmx(vcpu)->rmode.save_rflags;
rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
}
return rflags;
}
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
if (to_vmx(vcpu)->rmode.vm86_active) {
to_vmx(vcpu)->rmode.save_rflags = rflags;
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
}
vmcs_writel(GUEST_RFLAGS, rflags);
}
static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
int ret = 0;
if (interruptibility & GUEST_INTR_STATE_STI)
ret |= KVM_X86_SHADOW_INT_STI;
if (interruptibility & GUEST_INTR_STATE_MOV_SS)
ret |= KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
u32 interruptibility = interruptibility_old;
interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
if (mask & KVM_X86_SHADOW_INT_MOV_SS)
interruptibility |= GUEST_INTR_STATE_MOV_SS;
else if (mask & KVM_X86_SHADOW_INT_STI)
interruptibility |= GUEST_INTR_STATE_STI;
if ((interruptibility != interruptibility_old))
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
}
static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
unsigned long rip;
rip = kvm_rip_read(vcpu);
rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
kvm_rip_write(vcpu, rip);
/* skipping an emulated instruction also counts */
vmx_set_interrupt_shadow(vcpu, 0);
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
bool has_error_code, u32 error_code,
bool reinject)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info = nr | INTR_INFO_VALID_MASK;
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
}
if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = nr;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
if (kvm_exception_is_soft(nr))
vmx->rmode.irq.rip +=
vmx->vcpu.arch.event_exit_inst_len;
intr_info |= INTR_TYPE_SOFT_INTR;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
return;
}
if (kvm_exception_is_soft(nr)) {
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmx->vcpu.arch.event_exit_inst_len);
intr_info |= INTR_TYPE_SOFT_EXCEPTION;
} else
intr_info |= INTR_TYPE_HARD_EXCEPTION;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
}
static bool vmx_rdtscp_supported(void)
{
return cpu_has_vmx_rdtscp();
}
/*
* Swap MSR entry in host/guest MSR entry array.
*/
static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
{
struct shared_msr_entry tmp;
tmp = vmx->guest_msrs[to];
vmx->guest_msrs[to] = vmx->guest_msrs[from];
vmx->guest_msrs[from] = tmp;
}
/*
* Set up the vmcs to automatically save and restore system
* msrs. Don't touch the 64-bit msrs if the guest is in legacy
* mode, as fiddling with msrs is very expensive.
*/
static void setup_msrs(struct vcpu_vmx *vmx)
{
int save_nmsrs, index;
unsigned long *msr_bitmap;
vmx_load_host_state(vmx);
save_nmsrs = 0;
#ifdef CONFIG_X86_64
if (is_long_mode(&vmx->vcpu)) {
index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
index = __find_msr_index(vmx, MSR_LSTAR);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
index = __find_msr_index(vmx, MSR_CSTAR);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
index = __find_msr_index(vmx, MSR_TSC_AUX);
if (index >= 0 && vmx->rdtscp_enabled)
move_msr_up(vmx, index, save_nmsrs++);
/*
* MSR_STAR is only needed on long mode guests, and only
* if efer.sce is enabled.
*/
index = __find_msr_index(vmx, MSR_STAR);
if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE))
move_msr_up(vmx, index, save_nmsrs++);
}
#endif
index = __find_msr_index(vmx, MSR_EFER);
if (index >= 0 && update_transition_efer(vmx, index))
move_msr_up(vmx, index, save_nmsrs++);
vmx->save_nmsrs = save_nmsrs;
if (cpu_has_vmx_msr_bitmap()) {
if (is_long_mode(&vmx->vcpu))
msr_bitmap = vmx_msr_bitmap_longmode;
else
msr_bitmap = vmx_msr_bitmap_legacy;
vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
}
}
/*
* 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)
{
vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc);
}
/*
* 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 shared_msr_entry *msr;
if (!pdata) {
printk(KERN_ERR "BUG: get_msr called with NULL pdata\n");
return -EINVAL;
}
switch (msr_index) {
#ifdef CONFIG_X86_64
case MSR_FS_BASE:
data = vmcs_readl(GUEST_FS_BASE);
break;
case MSR_GS_BASE:
data = vmcs_readl(GUEST_GS_BASE);
break;
case MSR_KERNEL_GS_BASE:
vmx_load_host_state(to_vmx(vcpu));
data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
break;
#endif
case MSR_EFER:
return kvm_get_msr_common(vcpu, msr_index, pdata);
case MSR_IA32_TSC:
data = guest_read_tsc();
break;
case MSR_IA32_SYSENTER_CS:
data = vmcs_read32(GUEST_SYSENTER_CS);
break;
case MSR_IA32_SYSENTER_EIP:
data = vmcs_readl(GUEST_SYSENTER_EIP);
break;
case MSR_IA32_SYSENTER_ESP:
data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
case MSR_TSC_AUX:
if (!to_vmx(vcpu)->rdtscp_enabled)
return 1;
/* Otherwise falls through */
default:
vmx_load_host_state(to_vmx(vcpu));
msr = find_msr_entry(to_vmx(vcpu), msr_index);
if (msr) {
vmx_load_host_state(to_vmx(vcpu));
data = msr->data;
break;
}
return kvm_get_msr_common(vcpu, msr_index, pdata);
}
*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 vcpu_vmx *vmx = to_vmx(vcpu);
struct shared_msr_entry *msr;
u64 host_tsc;
int ret = 0;
switch (msr_index) {
case MSR_EFER:
vmx_load_host_state(vmx);
ret = kvm_set_msr_common(vcpu, msr_index, data);
break;
#ifdef CONFIG_X86_64
case MSR_FS_BASE:
vmcs_writel(GUEST_FS_BASE, data);
break;
case MSR_GS_BASE:
vmcs_writel(GUEST_GS_BASE, data);
break;
case MSR_KERNEL_GS_BASE:
vmx_load_host_state(vmx);
vmx->msr_guest_kernel_gs_base = data;
break;
#endif
case MSR_IA32_SYSENTER_CS:
vmcs_write32(GUEST_SYSENTER_CS, data);
break;
case MSR_IA32_SYSENTER_EIP:
vmcs_writel(GUEST_SYSENTER_EIP, data);
break;
case MSR_IA32_SYSENTER_ESP:
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_TSC:
rdtscll(host_tsc);
guest_write_tsc(data, host_tsc);
break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
vmcs_write64(GUEST_IA32_PAT, data);
vcpu->arch.pat = data;
break;
}
ret = kvm_set_msr_common(vcpu, msr_index, data);
break;
case MSR_TSC_AUX:
if (!vmx->rdtscp_enabled)
return 1;
/* Check reserved bit, higher 32 bits should be zero */
if ((data >> 32) != 0)
return 1;
/* Otherwise falls through */
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
vmx_load_host_state(vmx);
msr->data = data;
break;
}
ret = kvm_set_msr_common(vcpu, msr_index, data);
}
return ret;
}
static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
switch (reg) {
case VCPU_REGS_RSP:
vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
break;
case VCPU_REGS_RIP:
vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
break;
case VCPU_EXREG_PDPTR:
if (enable_ept)
ept_save_pdptrs(vcpu);
break;
default:
break;
}
}
static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
else
vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
update_exception_bitmap(vcpu);
}
static __init int cpu_has_kvm_support(void)
{
return cpu_has_vmx();
}
static __init int vmx_disabled_by_bios(void)
{
u64 msr;
rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
if (msr & FEATURE_CONTROL_LOCKED) {
if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
&& tboot_enabled())
return 1;
if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
&& !tboot_enabled())
return 1;
}
return 0;
/* locked but not enabled */
}
static void kvm_cpu_vmxon(u64 addr)
{
asm volatile (ASM_VMX_VMXON_RAX
: : "a"(&addr), "m"(addr)
: "memory", "cc");
}
static int hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
u64 old, test_bits;
if (read_cr4() & X86_CR4_VMXE)
return -EBUSY;
INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
test_bits = FEATURE_CONTROL_LOCKED;
test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
if (tboot_enabled())
test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
if ((old & test_bits) != test_bits) {
/* enable and lock */
wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
}
write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
if (vmm_exclusive) {
kvm_cpu_vmxon(phys_addr);
ept_sync_global();
}
store_gdt(&__get_cpu_var(host_gdt));
return 0;
}
static void vmclear_local_vcpus(void)
{
int cpu = raw_smp_processor_id();
struct vcpu_vmx *vmx, *n;
list_for_each_entry_safe(vmx, n, &per_cpu(vcpus_on_cpu, cpu),
local_vcpus_link)
__vcpu_clear(vmx);
}
/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
* tricks.
*/
static void kvm_cpu_vmxoff(void)
{
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
static void hardware_disable(void *garbage)
{
if (vmm_exclusive) {
vmclear_local_vcpus();
kvm_cpu_vmxoff();
}
write_cr4(read_cr4() & ~X86_CR4_VMXE);
}
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
u32 msr, u32 *result)
{
u32 vmx_msr_low, vmx_msr_high;
u32 ctl = ctl_min | ctl_opt;
rdmsr(msr, vmx_msr_low, vmx_msr_high);
ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */
ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */
/* Ensure minimum (required) set of control bits are supported. */
if (ctl_min & ~ctl)
return -EIO;
*result = ctl;
return 0;
}
static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
{
u32 vmx_msr_low, vmx_msr_high;
u32 min, opt, min2, opt2;
u32 _pin_based_exec_control = 0;
u32 _cpu_based_exec_control = 0;
u32 _cpu_based_2nd_exec_control = 0;
u32 _vmexit_control = 0;
u32 _vmentry_control = 0;
min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
opt = PIN_BASED_VIRTUAL_NMIS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
&_pin_based_exec_control) < 0)
return -EIO;
min = CPU_BASED_HLT_EXITING |
#ifdef CONFIG_X86_64
CPU_BASED_CR8_LOAD_EXITING |
CPU_BASED_CR8_STORE_EXITING |
#endif
CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING |
CPU_BASED_USE_IO_BITMAPS |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING |
CPU_BASED_MWAIT_EXITING |
CPU_BASED_MONITOR_EXITING |
CPU_BASED_INVLPG_EXITING;
opt = CPU_BASED_TPR_SHADOW |
CPU_BASED_USE_MSR_BITMAPS |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
&_cpu_based_exec_control) < 0)
return -EIO;
#ifdef CONFIG_X86_64
if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
_cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
~CPU_BASED_CR8_STORE_EXITING;
#endif
if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
min2 = 0;
opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_WBINVD_EXITING |
SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_ENABLE_EPT |
SECONDARY_EXEC_UNRESTRICTED_GUEST |
SECONDARY_EXEC_PAUSE_LOOP_EXITING |
SECONDARY_EXEC_RDTSCP;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
return -EIO;
}
#ifndef CONFIG_X86_64
if (!(_cpu_based_2nd_exec_control &
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
_cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
#endif
if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
enabled */
_cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING |
CPU_BASED_INVLPG_EXITING);
rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
vmx_capability.ept, vmx_capability.vpid);
}
min = 0;
#ifdef CONFIG_X86_64
min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
#endif
opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
&_vmexit_control) < 0)
return -EIO;
min = 0;
opt = VM_ENTRY_LOAD_IA32_PAT;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
&_vmentry_control) < 0)
return -EIO;
rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);
/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
if ((vmx_msr_high & 0x1fff) > PAGE_SIZE)
return -EIO;
#ifdef CONFIG_X86_64
/* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */
if (vmx_msr_high & (1u<<16))
return -EIO;
#endif
/* Require Write-Back (WB) memory type for VMCS accesses. */
if (((vmx_msr_high >> 18) & 15) != 6)
return -EIO;
vmcs_conf->size = vmx_msr_high & 0x1fff;
vmcs_conf->order = get_order(vmcs_config.size);
vmcs_conf->revision_id = vmx_msr_low;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control;
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
return 0;
}
static struct vmcs *alloc_vmcs_cpu(int cpu)
{
int node = cpu_to_node(cpu);
struct page *pages;
struct vmcs *vmcs;
pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order);
if (!pages)
return NULL;
vmcs = page_address(pages);
memset(vmcs, 0, vmcs_config.size);
vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
return vmcs;
}
static struct vmcs *alloc_vmcs(void)
{
return alloc_vmcs_cpu(raw_smp_processor_id());
}
static void free_vmcs(struct vmcs *vmcs)
{
free_pages((unsigned long)vmcs, vmcs_config.order);
}
static void free_kvm_area(void)
{
int cpu;
for_each_possible_cpu(cpu) {
free_vmcs(per_cpu(vmxarea, cpu));
per_cpu(vmxarea, cpu) = NULL;
}
}
static __init int alloc_kvm_area(void)
{
int cpu;
for_each_possible_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)
{
if (setup_vmcs_config(&vmcs_config) < 0)
return -EIO;
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
if (!cpu_has_vmx_vpid())
enable_vpid = 0;
if (!cpu_has_vmx_ept() ||
!cpu_has_vmx_ept_4levels()) {
enable_ept = 0;
enable_unrestricted_guest = 0;
}
if (!cpu_has_vmx_unrestricted_guest())
enable_unrestricted_guest = 0;
if (!cpu_has_vmx_flexpriority())
flexpriority_enabled = 0;
if (!cpu_has_vmx_tpr_shadow())
kvm_x86_ops->update_cr8_intercept = NULL;
if (enable_ept && !cpu_has_vmx_ept_2m_page())
kvm_disable_largepages();
if (!cpu_has_vmx_ple())
ple_gap = 0;
return alloc_kvm_area();
}
static __exit void hardware_unsetup(void)
{
free_kvm_area();
}
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 && (save->base & AR_S_MASK)) {
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;
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmx->emulation_required = 1;
vmx->rmode.vm86_active = 0;
vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
flags = vmcs_readl(GUEST_RFLAGS);
flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
update_exception_bitmap(vcpu);
if (emulate_invalid_guest_state)
return;
fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es);
fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds);
fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
fix_pmode_dataseg(VCPU_SREG_FS, &vmx->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 gva_t rmode_tss_base(struct kvm *kvm)
{
if (!kvm->arch.tss_addr) {
struct kvm_memslots *slots;
gfn_t base_gfn;
slots = kvm_memslots(kvm);
base_gfn = slots->memslots[0].base_gfn +
kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
}
return kvm->arch.tss_addr;
}
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, save->base >> 4);
vmcs_write32(sf->base, save->base & 0xfffff);
vmcs_write32(sf->limit, 0xffff);
vmcs_write32(sf->ar_bytes, 0xf3);
}
static void enter_rmode(struct kvm_vcpu *vcpu)
{
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (enable_unrestricted_guest)
return;
vmx->emulation_required = 1;
vmx->rmode.vm86_active = 1;
vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
vmx->rmode.save_rflags = flags;
flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
update_exception_bitmap(vcpu);
if (emulate_invalid_guest_state)
goto continue_rmode;
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_write32(GUEST_CS_LIMIT, 0xffff);
if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000)
vmcs_writel(GUEST_CS_BASE, 0xf0000);
vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);
fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
continue_rmode:
kvm_mmu_reset_context(vcpu);
init_rmode(vcpu->kvm);
}
static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
if (!msr)
return;
/*
* Force kernel_gs_base reloading before EFER changes, as control
* of this msr depends on is_long_mode().
*/
vmx_load_host_state(to_vmx(vcpu));
vcpu->arch.efer = efer;
if (efer & EFER_LMA) {
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS) |
VM_ENTRY_IA32E_MODE);
msr->data = efer;
} else {
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS) &
~VM_ENTRY_IA32E_MODE);
msr->data = efer & ~EFER_LME;
}
setup_msrs(vmx);
}
#ifdef CONFIG_X86_64
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",
__func__);
vmcs_write32(GUEST_TR_AR_BYTES,
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
}
static void exit_lmode(struct kvm_vcpu *vcpu)
{
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS)
& ~VM_ENTRY_IA32E_MODE);
vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
}
#endif
static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
vpid_sync_context(to_vmx(vcpu));
if (enable_ept) {
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
}
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
}
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
}
static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
{
if (!test_bit(VCPU_EXREG_PDPTR,
(unsigned long *)&vcpu->arch.regs_dirty))
return;
if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]);
vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]);
vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]);
vmcs_write64(GUEST_PDPTR3, vcpu->arch.pdptrs[3]);
}
}
static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
{
if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
vcpu->arch.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
vcpu->arch.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
}
__set_bit(VCPU_EXREG_PDPTR,
(unsigned long *)&vcpu->arch.regs_avail);
__set_bit(VCPU_EXREG_PDPTR,
(unsigned long *)&vcpu->arch.regs_dirty);
}
static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
unsigned long cr0,
struct kvm_vcpu *vcpu)
{
if (!(cr0 & X86_CR0_PG)) {
/* From paging/starting to nonpaging */
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) |
(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
} else if (!is_paging(vcpu)) {
/* From nonpaging to paging */
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
~(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
}
if (!(cr0 & X86_CR0_WP))
*hw_cr0 &= ~X86_CR0_WP;
}
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long hw_cr0;
if (enable_unrestricted_guest)
hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST)
| KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
else
hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
enter_pmode(vcpu);
if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
enter_rmode(vcpu);
#ifdef CONFIG_X86_64
if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
enter_lmode(vcpu);
if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
exit_lmode(vcpu);
}
#endif
if (enable_ept)
ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
if (!vcpu->fpu_active)
hw_cr0 |= X86_CR0_TS | X86_CR0_MP;
vmcs_writel(CR0_READ_SHADOW, cr0);
vmcs_writel(GUEST_CR0, hw_cr0);
vcpu->arch.cr0 = cr0;
}
static u64 construct_eptp(unsigned long root_hpa)
{
u64 eptp;
/* TODO write the value reading from MSR */
eptp = VMX_EPT_DEFAULT_MT |
VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT;
eptp |= (root_hpa & PAGE_MASK);
return eptp;
}
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
unsigned long guest_cr3;
u64 eptp;
guest_cr3 = cr3;
if (enable_ept) {
eptp = construct_eptp(cr3);
vmcs_write64(EPT_POINTER, eptp);
guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
vcpu->kvm->arch.ept_identity_map_addr;
ept_load_pdptrs(vcpu);
}
vmx_flush_tlb(vcpu);
vmcs_writel(GUEST_CR3, guest_cr3);
}
static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
vcpu->arch.cr4 = cr4;
if (enable_ept) {
if (!is_paging(vcpu)) {
hw_cr4 &= ~X86_CR4_PAE;
hw_cr4 |= X86_CR4_PSE;
} else if (!(cr4 & X86_CR4_PAE)) {
hw_cr4 &= ~X86_CR4_PAE;
}
}
vmcs_writel(CR4_READ_SHADOW, cr4);
vmcs_writel(GUEST_CR4, hw_cr4);
}
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) && !emulate_invalid_guest_state)
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 int vmx_get_cpl(struct kvm_vcpu *vcpu)
{
if (!is_protmode(vcpu))
return 0;
if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
return 3;
return vmcs_read16(GUEST_CS_SELECTOR) & 3;
}
static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
u32 ar;
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;
}
if (ar == 0) /* a 0 value means unusable */
ar = AR_UNUSABLE_MASK;
return ar;
}
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
u32 ar;
if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
vmx->rmode.tr.selector = var->selector;
vmx->rmode.tr.base = var->base;
vmx->rmode.tr.limit = var->limit;
vmx->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 (vmx->rmode.vm86_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);
/*
* Fix the "Accessed" bit in AR field of segment registers for older
* qemu binaries.
* IA32 arch specifies that at the time of processor reset the
* "Accessed" bit in the AR field of segment registers is 1. And qemu
* is setting it to 0 in the usedland code. This causes invalid guest
* state vmexit when "unrestricted guest" mode is turned on.
* Fix for this setup issue in cpu_reset is being pushed in the qemu
* tree. Newer qemu binaries with that qemu fix would not need this
* kvm hack.
*/
if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
ar |= 0x1; /* Accessed */
vmcs_write32(sf->ar_bytes, ar);
}
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 desc_ptr *dt)
{
dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
dt->address = vmcs_readl(GUEST_IDTR_BASE);
}
static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
vmcs_writel(GUEST_IDTR_BASE, dt->address);
}
static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
dt->address = vmcs_readl(GUEST_GDTR_BASE);
}
static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
vmcs_writel(GUEST_GDTR_BASE, dt->address);
}
static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_segment var;
u32 ar;
vmx_get_segment(vcpu, &var, seg);
ar = vmx_segment_access_rights(&var);
if (var.base != (var.selector << 4))
return false;
if (var.limit != 0xffff)
return false;
if (ar != 0xf3)
return false;
return true;
}
static bool code_segment_valid(struct kvm_vcpu *vcpu)
{
struct kvm_segment cs;
unsigned int cs_rpl;
vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
cs_rpl = cs.selector & SELECTOR_RPL_MASK;
if (cs.unusable)
return false;
if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
return false;
if (!cs.s)
return false;
if (cs.type & AR_TYPE_WRITEABLE_MASK) {
if (cs.dpl > cs_rpl)
return false;
} else {
if (cs.dpl != cs_rpl)
return false;
}
if (!cs.present)
return false;
/* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */
return true;
}
static bool stack_segment_valid(struct kvm_vcpu *vcpu)
{
struct kvm_segment ss;
unsigned int ss_rpl;
vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
ss_rpl = ss.selector & SELECTOR_RPL_MASK;
if (ss.unusable)
return true;
if (ss.type != 3 && ss.type != 7)
return false;
if (!ss.s)
return false;
if (ss.dpl != ss_rpl) /* DPL != RPL */
return false;
if (!ss.present)
return false;
return true;
}
static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_segment var;
unsigned int rpl;
vmx_get_segment(vcpu, &var, seg);
rpl = var.selector & SELECTOR_RPL_MASK;
if (var.unusable)
return true;
if (!var.s)
return false;
if (!var.present)
return false;
if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) {
if (var.dpl < rpl) /* DPL < RPL */
return false;
}
/* TODO: Add other members to kvm_segment_field to allow checking for other access
* rights flags
*/
return true;
}
static bool tr_valid(struct kvm_vcpu *vcpu)
{
struct kvm_segment tr;
vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
if (tr.unusable)
return false;
if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */
return false;
if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
return false;
if (!tr.present)
return false;
return true;
}
static bool ldtr_valid(struct kvm_vcpu *vcpu)
{
struct kvm_segment ldtr;
vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
if (ldtr.unusable)
return true;
if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */
return false;
if (ldtr.type != 2)
return false;
if (!ldtr.present)
return false;
return true;
}
static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
{
struct kvm_segment cs, ss;
vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
return ((cs.selector & SELECTOR_RPL_MASK) ==
(ss.selector & SELECTOR_RPL_MASK));
}
/*
* Check if guest state is valid. Returns true if valid, false if
* not.
* We assume that registers are always usable
*/
static bool guest_state_valid(struct kvm_vcpu *vcpu)
{
/* real mode guest state checks */
if (!is_protmode(vcpu)) {
if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_DS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_ES))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_FS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_GS))
return false;
} else {
/* protected mode guest state checks */
if (!cs_ss_rpl_check(vcpu))
return false;
if (!code_segment_valid(vcpu))
return false;
if (!stack_segment_valid(vcpu))
return false;
if (!data_segment_valid(vcpu, VCPU_SREG_DS))
return false;
if (!data_segment_valid(vcpu, VCPU_SREG_ES))
return false;
if (!data_segment_valid(vcpu, VCPU_SREG_FS))
return false;
if (!data_segment_valid(vcpu, VCPU_SREG_GS))
return false;
if (!tr_valid(vcpu))
return false;
if (!ldtr_valid(vcpu))
return false;
}
/* TODO:
* - Add checks on RIP
* - Add checks on RFLAGS
*/
return true;
}
static int init_rmode_tss(struct kvm *kvm)
{
gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT;
u16 data = 0;
int ret = 0;
int r;
r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
if (r < 0)
goto out;
data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
r = kvm_write_guest_page(kvm, fn++, &data,
TSS_IOPB_BASE_OFFSET, sizeof(u16));
if (r < 0)
goto out;
r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
if (r < 0)
goto out;
r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
if (r < 0)
goto out;
data = ~0;
r = kvm_write_guest_page(kvm, fn, &data,
RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
sizeof(u8));
if (r < 0)
goto out;
ret = 1;
out:
return ret;
}
static int init_rmode_identity_map(struct kvm *kvm)
{
int i, r, ret;
pfn_t identity_map_pfn;
u32 tmp;
if (!enable_ept)
return 1;
if (unlikely(!kvm->arch.ept_identity_pagetable)) {
printk(KERN_ERR "EPT: identity-mapping pagetable "
"haven't been allocated!\n");
return 0;
}
if (likely(kvm->arch.ept_identity_pagetable_done))
return 1;
ret = 0;
identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;
r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
if (r < 0)
goto out;
/* Set up identity-mapping pagetable for EPT in real mode */
for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
r = kvm_write_guest_page(kvm, identity_map_pfn,
&tmp, i * sizeof(tmp), sizeof(tmp));
if (r < 0)
goto out;
}
kvm->arch.ept_identity_pagetable_done = true;
ret = 1;
out:
return ret;
}
static void seg_setup(int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
unsigned int ar;
vmcs_write16(sf->selector, 0);
vmcs_writel(sf->base, 0);
vmcs_write32(sf->limit, 0xffff);
if (enable_unrestricted_guest) {
ar = 0x93;
if (seg == VCPU_SREG_CS)
ar |= 0x08; /* code segment */
} else
ar = 0xf3;
vmcs_write32(sf->ar_bytes, ar);
}
static int alloc_apic_access_page(struct kvm *kvm)
{
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
mutex_lock(&kvm->slots_lock);
if (kvm->arch.apic_access_page)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
if (r)
goto out;
kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
out:
mutex_unlock(&kvm->slots_lock);
return r;
}
static int alloc_identity_pagetable(struct kvm *kvm)
{
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
mutex_lock(&kvm->slots_lock);
if (kvm->arch.ept_identity_pagetable)
goto out;
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr =
kvm->arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
if (r)
goto out;
kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
out:
mutex_unlock(&kvm->slots_lock);
return r;
}
static void allocate_vpid(struct vcpu_vmx *vmx)
{
int vpid;
vmx->vpid = 0;
if (!enable_vpid)
return;
spin_lock(&vmx_vpid_lock);
vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
if (vpid < VMX_NR_VPIDS) {
vmx->vpid = vpid;
__set_bit(vpid, vmx_vpid_bitmap);
}
spin_unlock(&vmx_vpid_lock);
}
static void free_vpid(struct vcpu_vmx *vmx)
{
if (!enable_vpid)
return;
spin_lock(&vmx_vpid_lock);
if (vmx->vpid != 0)
__clear_bit(vmx->vpid, vmx_vpid_bitmap);
spin_unlock(&vmx_vpid_lock);
}
static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
{
int f = sizeof(unsigned long);
if (!cpu_has_vmx_msr_bitmap())
return;
/*
* See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
* have the write-low and read-high bitmap offsets the wrong way round.
* We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
*/
if (msr <= 0x1fff) {
__clear_bit(msr, msr_bitmap + 0x000 / f); /* read-low */
__clear_bit(msr, msr_bitmap + 0x800 / f); /* write-low */
} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
msr &= 0x1fff;
__clear_bit(msr, msr_bitmap + 0x400 / f); /* read-high */
__clear_bit(msr, msr_bitmap + 0xc00 / f); /* write-high */
}
}
static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
{
if (!longmode_only)
__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr);
__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr);
}
/*
* Sets up the vmcs for emulated real mode.
*/
static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
u32 host_sysenter_cs, msr_low, msr_high;
u32 junk;
u64 host_pat, tsc_this, tsc_base;
unsigned long a;
struct desc_ptr dt;
int i;
unsigned long kvm_vmx_return;
u32 exec_control;
/* I/O */
vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a));
vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));
if (cpu_has_vmx_msr_bitmap())
vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
/* Control */
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
vmcs_config.pin_based_exec_ctrl);
exec_control = vmcs_config.cpu_based_exec_ctrl;
if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) {
exec_control &= ~CPU_BASED_TPR_SHADOW;
#ifdef CONFIG_X86_64
exec_control |= CPU_BASED_CR8_STORE_EXITING |
CPU_BASED_CR8_LOAD_EXITING;
#endif
}
if (!enable_ept)
exec_control |= CPU_BASED_CR3_STORE_EXITING |
CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_INVLPG_EXITING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
exec_control &=
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
if (!enable_ept) {
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
enable_unrestricted_guest = 0;
}
if (!enable_unrestricted_guest)
exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (!ple_gap)
exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
if (ple_gap) {
vmcs_write32(PLE_GAP, ple_gap);
vmcs_write32(PLE_WINDOW, ple_window);
}
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 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, 0); /* 22.2.4 */
vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */
vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
#ifdef CONFIG_X86_64
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 */
native_store_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
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 */
if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
host_pat = msr_low | ((u64) msr_high << 32);
vmcs_write64(HOST_IA32_PAT, host_pat);
}
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
host_pat = msr_low | ((u64) msr_high << 32);
/* Write the default value follow host pat */
vmcs_write64(GUEST_IA32_PAT, host_pat);
/* Keep arch.pat sync with GUEST_IA32_PAT */
vmx->vcpu.arch.pat = host_pat;
}
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
int j = vmx->nmsrs;
if (rdmsr_safe(index, &data_low, &data_high) < 0)
continue;
if (wrmsr_safe(index, data_low, data_high) < 0)
continue;
vmx->guest_msrs[j].index = i;
vmx->guest_msrs[j].data = 0;
vmx->guest_msrs[j].mask = -1ull;
++vmx->nmsrs;
}
vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
/* 22.2.1, 20.8.1 */
vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl);
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
rdtscll(tsc_this);
if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc)
tsc_base = tsc_this;
guest_write_tsc(0, tsc_base);
return 0;
}
static int init_rmode(struct kvm *kvm)
{
int idx, ret = 0;
idx = srcu_read_lock(&kvm->srcu);
if (!init_rmode_tss(kvm))
goto exit;
if (!init_rmode_identity_map(kvm))
goto exit;
ret = 1;
exit:
srcu_read_unlock(&kvm->srcu, idx);
return ret;
}
static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 msr;
int ret;
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
if (!init_rmode(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
}
vmx->rmode.vm86_active = 0;
vmx->soft_vnmi_blocked = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&vmx->vcpu))
msr |= MSR_IA32_APICBASE_BSP;
kvm_set_apic_base(&vmx->vcpu, msr);
ret = fx_init(&vmx->vcpu);
if (ret != 0)
goto out;
seg_setup(VCPU_SREG_CS);
/*
* GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
* insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh.
*/
if (kvm_vcpu_is_bsp(&vmx->vcpu)) {
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);
}
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 (kvm_vcpu_is_bsp(&vmx->vcpu))
kvm_rip_write(vcpu, 0xfff0);
else
kvm_rip_write(vcpu, 0);
kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
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);
/* 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));
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
vmx_set_efer(&vmx->vcpu, 0);
vmx_fpu_activate(&vmx->vcpu);
update_exception_bitmap(&vmx->vcpu);
vpid_sync_context(vmx);
ret = 0;
/* HACK: Don't enable emulation on guest boot/reset */
vmx->emulation_required = 0;
out:
return ret;
}
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 enable_nmi_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
if (!cpu_has_virtual_nmis()) {
enable_irq_window(vcpu);
return;
}
cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
}
static void vmx_inject_irq(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
uint32_t intr;
int irq = vcpu->arch.interrupt.nr;
trace_kvm_inj_virq(irq);
++vcpu->stat.irq_injections;
if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = irq;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
if (vcpu->arch.interrupt.soft)
vmx->rmode.irq.rip +=
vmx->vcpu.arch.event_exit_inst_len;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
return;
}
intr = irq | INTR_INFO_VALID_MASK;
if (vcpu->arch.interrupt.soft) {
intr |= INTR_TYPE_SOFT_INTR;
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmx->vcpu.arch.event_exit_inst_len);
} else
intr |= INTR_TYPE_EXT_INTR;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
}
static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (!cpu_has_virtual_nmis()) {
/*
* Tracking the NMI-blocked state in software is built upon
* finding the next open IRQ window. This, in turn, depends on
* well-behaving guests: They have to keep IRQs disabled at
* least as long as the NMI handler runs. Otherwise we may
* cause NMI nesting, maybe breaking the guest. But as this is
* highly unlikely, we can live with the residual risk.
*/
vmx->soft_vnmi_blocked = 1;
vmx->vnmi_blocked_time = 0;
}
++vcpu->stat.nmi_injections;
if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = NMI_VECTOR;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
NMI_VECTOR | INTR_TYPE_SOFT_INTR |
INTR_INFO_VALID_MASK);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
return;
}
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
}
static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
{
if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked)
return 0;
return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
(GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_NMI));
}
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
{
if (!cpu_has_virtual_nmis())
return to_vmx(vcpu)->soft_vnmi_blocked;
return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
}
static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (!cpu_has_virtual_nmis()) {
if (vmx->soft_vnmi_blocked != masked) {
vmx->soft_vnmi_blocked = masked;
vmx->vnmi_blocked_time = 0;
}
} else {
if (masked)
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
else
vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
}
}
static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
{
return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
}
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
{
int ret;
struct kvm_userspace_memory_region tss_mem = {
.slot = TSS_PRIVATE_MEMSLOT,
.guest_phys_addr = addr,
.memory_size = PAGE_SIZE * 3,
.flags = 0,
};
ret = kvm_set_memory_region(kvm, &tss_mem, 0);
if (ret)
return ret;
kvm->arch.tss_addr = addr;
return 0;
}
static int handle_rmode_exception(struct kvm_vcpu *vcpu,
int vec, u32 err_code)
{
/*
* Instruction with address size override prefix opcode 0x67
* Cause the #SS fault with 0 error code in VM86 mode.
*/
if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0)
if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE)
return 1;
/*
* Forward all other exceptions that are valid in real mode.
* FIXME: Breaks guest debugging in real mode, needs to be fixed with
* the required debugging infrastructure rework.
*/
switch (vec) {
case DB_VECTOR:
if (vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
return 0;
kvm_queue_exception(vcpu, vec);
return 1;
case BP_VECTOR:
/*
* Update instruction length as we may reinject the exception
* from user space while in guest debugging mode.
*/
to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
return 0;
/* fall through */
case DE_VECTOR:
case OF_VECTOR:
case BR_VECTOR:
case UD_VECTOR:
case DF_VECTOR:
case SS_VECTOR:
case GP_VECTOR:
case MF_VECTOR:
kvm_queue_exception(vcpu, vec);
return 1;
}
return 0;
}
/*
* Trigger machine check on the host. We assume all the MSRs are already set up
* by the CPU and that we still run on the same CPU as the MCE occurred on.
* We pass a fake environment to the machine check handler because we want
* the guest to be always treated like user space, no matter what context
* it used internally.
*/
static void kvm_machine_check(void)
{
#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
struct pt_regs regs = {
.cs = 3, /* Fake ring 3 no matter what the guest ran on */
.flags = X86_EFLAGS_IF,
};
do_machine_check(&regs, 0);
#endif
}
static int handle_machine_check(struct kvm_vcpu *vcpu)
{
/* already handled by vcpu_run */
return 1;
}
static int handle_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct kvm_run *kvm_run = vcpu->run;
u32 intr_info, ex_no, error_code;
unsigned long cr2, rip, dr6;
u32 vect_info;
enum emulation_result er;
vect_info = vmx->idt_vectoring_info;
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
if (is_machine_check(intr_info))
return handle_machine_check(vcpu);
if ((vect_info & VECTORING_INFO_VALID_MASK) &&
!is_page_fault(intr_info)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
vcpu->run->internal.ndata = 2;
vcpu->run->internal.data[0] = vect_info;
vcpu->run->internal.data[1] = intr_info;
return 0;
}
if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
return 1; /* already handled by vmx_vcpu_run() */
if (is_no_device(intr_info)) {
vmx_fpu_activate(vcpu);
return 1;
}
if (is_invalid_opcode(intr_info)) {
er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
error_code = 0;
rip = kvm_rip_read(vcpu);
if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
if (is_page_fault(intr_info)) {
/* EPT won't cause page fault directly */
if (enable_ept)
BUG();
cr2 = vmcs_readl(EXIT_QUALIFICATION);
trace_kvm_page_fault(cr2, error_code);
if (kvm_event_needs_reinjection(vcpu))
kvm_mmu_unprotect_page_virt(vcpu, cr2);
return kvm_mmu_page_fault(vcpu, cr2, error_code);
}
if (vmx->rmode.vm86_active &&
handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK,
error_code)) {
if (vcpu->arch.halt_request) {
vcpu->arch.halt_request = 0;
return kvm_emulate_halt(vcpu);
}
return 1;
}
ex_no = intr_info & INTR_INFO_VECTOR_MASK;
switch (ex_no) {
case DB_VECTOR:
dr6 = vmcs_readl(EXIT_QUALIFICATION);
if (!(vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
vcpu->arch.dr6 = dr6 | DR6_FIXED_1;
kvm_queue_exception(vcpu, DB_VECTOR);
return 1;
}
kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
/* fall through */
case BP_VECTOR:
/*
* Update instruction length as we may reinject #BP from
* user space while in guest debugging mode. Reading it for
* #DB as well causes no harm, it is not used in that case.
*/
vmx->vcpu.arch.event_exit_inst_len =
vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
kvm_run->debug.arch.exception = ex_no;
break;
default:
kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
kvm_run->ex.exception = ex_no;
kvm_run->ex.error_code = error_code;
break;
}
return 0;
}
static int handle_external_interrupt(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
return 1;
}
static int handle_triple_fault(struct kvm_vcpu *vcpu)
{
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
}
static int handle_io(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
int size, in, string;
unsigned port;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
string = (exit_qualification & 16) != 0;
in = (exit_qualification & 8) != 0;
++vcpu->stat.io_exits;
if (string || in)
return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
port = exit_qualification >> 16;
size = (exit_qualification & 7) + 1;
skip_emulated_instruction(vcpu);
return kvm_fast_pio_out(vcpu, size, port);
}
static void
vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
{
/*
* Patch in the VMCALL instruction:
*/
hypercall[0] = 0x0f;
hypercall[1] = 0x01;
hypercall[2] = 0xc1;
}
static void complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
if (err)
kvm_inject_gp(vcpu, 0);
else
skip_emulated_instruction(vcpu);
}
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
int cr;
int reg;
int err;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
cr = exit_qualification & 15;
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
val = kvm_register_read(vcpu, reg);
trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
err = kvm_set_cr0(vcpu, val);
complete_insn_gp(vcpu, err);
return 1;
case 3:
err = kvm_set_cr3(vcpu, val);
complete_insn_gp(vcpu, err);
return 1;
case 4:
err = kvm_set_cr4(vcpu, val);
complete_insn_gp(vcpu, err);
return 1;
case 8: {
u8 cr8_prev = kvm_get_cr8(vcpu);
u8 cr8 = kvm_register_read(vcpu, reg);
kvm_set_cr8(vcpu, cr8);
skip_emulated_instruction(vcpu);
if (irqchip_in_kernel(vcpu->kvm))
return 1;
if (cr8_prev <= cr8)
return 1;
vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
return 0;
}
};
break;
case 2: /* clts */
vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
skip_emulated_instruction(vcpu);
vmx_fpu_activate(vcpu);
return 1;
case 1: /*mov from cr*/
switch (cr) {
case 3:
kvm_register_write(vcpu, reg, vcpu->arch.cr3);
trace_kvm_cr_read(cr, vcpu->arch.cr3);
skip_emulated_instruction(vcpu);
return 1;
case 8:
val = kvm_get_cr8(vcpu);
kvm_register_write(vcpu, reg, val);
trace_kvm_cr_read(cr, val);
skip_emulated_instruction(vcpu);
return 1;
}
break;
case 3: /* lmsw */
val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
kvm_lmsw(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
default:
break;
}
vcpu->run->exit_reason = 0;
pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n",
(int)(exit_qualification >> 4) & 3, cr);
return 0;
}
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
int dr, reg;
/* Do not handle if the CPL > 0, will trigger GP on re-entry */
if (!kvm_require_cpl(vcpu, 0))
return 1;
dr = vmcs_readl(GUEST_DR7);
if (dr & DR7_GD) {
/*
* As the vm-exit takes precedence over the debug trap, we
* need to emulate the latter, either for the host or the
* guest debugging itself.
*/
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
vcpu->run->debug.arch.dr7 = dr;
vcpu->run->debug.arch.pc =
vmcs_readl(GUEST_CS_BASE) +
vmcs_readl(GUEST_RIP);
vcpu->run->debug.arch.exception = DB_VECTOR;
vcpu->run->exit_reason = KVM_EXIT_DEBUG;
return 0;
} else {
vcpu->arch.dr7 &= ~DR7_GD;
vcpu->arch.dr6 |= DR6_BD;
vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
kvm_queue_exception(vcpu, DB_VECTOR);
return 1;
}
}
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
reg = DEBUG_REG_ACCESS_REG(exit_qualification);
if (exit_qualification & TYPE_MOV_FROM_DR) {
unsigned long val;
if (!kvm_get_dr(vcpu, dr, &val))
kvm_register_write(vcpu, reg, val);
} else
kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
}
static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
{
vmcs_writel(GUEST_DR7, val);
}
static int handle_cpuid(struct kvm_vcpu *vcpu)
{
kvm_emulate_cpuid(vcpu);
return 1;
}
static int handle_rdmsr(struct kvm_vcpu *vcpu)
{
u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
u64 data;
if (vmx_get_msr(vcpu, ecx, &data)) {
trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(vcpu, 0);
return 1;
}
trace_kvm_msr_read(ecx, data);
/* FIXME: handling of bits 32:63 of rax, rdx */
vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
skip_emulated_instruction(vcpu);
return 1;
}
static int handle_wrmsr(struct kvm_vcpu *vcpu)
{
u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
if (vmx_set_msr(vcpu, ecx, data) != 0) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(vcpu, 0);
return 1;
}
trace_kvm_msr_write(ecx, data);
skip_emulated_instruction(vcpu);
return 1;
}
static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
{
return 1;
}
static int handle_interrupt_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
/* clear pending irq */
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);
++vcpu->stat.irq_window_exits;
/*
* If the user space waits to inject interrupts, exit as soon as
* possible
*/
if (!irqchip_in_kernel(vcpu->kvm) &&
vcpu->run->request_interrupt_window &&
!kvm_cpu_has_interrupt(vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
return 0;
}
return 1;
}
static int handle_halt(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
return kvm_emulate_halt(vcpu);
}
static int handle_vmcall(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
kvm_emulate_hypercall(vcpu);
return 1;
}
static int handle_vmx_insn(struct kvm_vcpu *vcpu)
{
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
static int handle_invlpg(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
kvm_mmu_invlpg(vcpu, exit_qualification);
skip_emulated_instruction(vcpu);
return 1;
}
static int handle_wbinvd(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
kvm_emulate_wbinvd(vcpu);
return 1;
}
static int handle_xsetbv(struct kvm_vcpu *vcpu)
{
u64 new_bv = kvm_read_edx_eax(vcpu);
u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
if (kvm_set_xcr(vcpu, index, new_bv) == 0)
skip_emulated_instruction(vcpu);
return 1;
}
static int handle_apic_access(struct kvm_vcpu *vcpu)
{
return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
}
static int handle_task_switch(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification;
bool has_error_code = false;
u32 error_code = 0;
u16 tss_selector;
int reason, type, idt_v;
idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
reason = (u32)exit_qualification >> 30;
if (reason == TASK_SWITCH_GATE && idt_v) {
switch (type) {
case INTR_TYPE_NMI_INTR:
vcpu->arch.nmi_injected = false;
if (cpu_has_virtual_nmis())
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
break;
case INTR_TYPE_EXT_INTR:
case INTR_TYPE_SOFT_INTR:
kvm_clear_interrupt_queue(vcpu);
break;
case INTR_TYPE_HARD_EXCEPTION:
if (vmx->idt_vectoring_info &
VECTORING_INFO_DELIVER_CODE_MASK) {
has_error_code = true;
error_code =
vmcs_read32(IDT_VECTORING_ERROR_CODE);
}
/* fall through */
case INTR_TYPE_SOFT_EXCEPTION:
kvm_clear_exception_queue(vcpu);
break;
default:
break;
}
}
tss_selector = exit_qualification;
if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
type != INTR_TYPE_EXT_INTR &&
type != INTR_TYPE_NMI_INTR))
skip_emulated_instruction(vcpu);
if (kvm_task_switch(vcpu, tss_selector, reason,
has_error_code, error_code) == EMULATE_FAIL) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
return 0;
}
/* clear all local breakpoint enable flags */
vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
/*
* TODO: What about debug traps on tss switch?
* Are we supposed to inject them and update dr6?
*/
return 1;
}
static int handle_ept_violation(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
gpa_t gpa;
int gla_validity;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
if (exit_qualification & (1 << 6)) {
printk(KERN_ERR "EPT: GPA exceeds GAW!\n");
return -EINVAL;
}
gla_validity = (exit_qualification >> 7) & 0x3;
if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) {
printk(KERN_ERR "EPT: Handling EPT violation failed!\n");
printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
(long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
vmcs_readl(GUEST_LINEAR_ADDRESS));
printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
(long unsigned int)exit_qualification);
vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION;
return 0;
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
}
static u64 ept_rsvd_mask(u64 spte, int level)
{
int i;
u64 mask = 0;
for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
mask |= (1ULL << i);
if (level > 2)
/* bits 7:3 reserved */
mask |= 0xf8;
else if (level == 2) {
if (spte & (1ULL << 7))
/* 2MB ref, bits 20:12 reserved */
mask |= 0x1ff000;
else
/* bits 6:3 reserved */
mask |= 0x78;
}
return mask;
}
static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
int level)
{
printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
/* 010b (write-only) */
WARN_ON((spte & 0x7) == 0x2);
/* 110b (write/execute) */
WARN_ON((spte & 0x7) == 0x6);
/* 100b (execute-only) and value not supported by logical processor */
if (!cpu_has_vmx_ept_execute_only())
WARN_ON((spte & 0x7) == 0x4);
/* not 000b */
if ((spte & 0x7)) {
u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
if (rsvd_bits != 0) {
printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
__func__, rsvd_bits);
WARN_ON(1);
}
if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
u64 ept_mem_type = (spte & 0x38) >> 3;
if (ept_mem_type == 2 || ept_mem_type == 3 ||
ept_mem_type == 7) {
printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
__func__, ept_mem_type);
WARN_ON(1);
}
}
}
}
static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
{
u64 sptes[4];
int nr_sptes, i;
gpa_t gpa;
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
printk(KERN_ERR "EPT: Misconfiguration.\n");
printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
return 0;
}
static int handle_nmi_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
/* clear pending NMI */
cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
++vcpu->stat.nmi_window_exits;
return 1;
}
static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
enum emulation_result err = EMULATE_DONE;
int ret = 1;
while (!guest_state_valid(vcpu)) {
err = emulate_instruction(vcpu, 0, 0, 0);
if (err == EMULATE_DO_MMIO) {
ret = 0;
goto out;
}
if (err != EMULATE_DONE)
return 0;
if (signal_pending(current))
goto out;
if (need_resched())
schedule();
}
vmx->emulation_required = 0;
out:
return ret;
}
/*
* Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
* exiting, so only get here on cpu with PAUSE-Loop-Exiting.
*/
static int handle_pause(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
kvm_vcpu_on_spin(vcpu);
return 1;
}
static int handle_invalid_op(struct kvm_vcpu *vcpu)
{
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
/*
* 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) = {
[EXIT_REASON_EXCEPTION_NMI] = handle_exception,
[EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
[EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault,
[EXIT_REASON_NMI_WINDOW] = handle_nmi_window,
[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_INVLPG] = handle_invlpg,
[EXIT_REASON_VMCALL] = handle_vmcall,
[EXIT_REASON_VMCLEAR] = handle_vmx_insn,
[EXIT_REASON_VMLAUNCH] = handle_vmx_insn,
[EXIT_REASON_VMPTRLD] = handle_vmx_insn,
[EXIT_REASON_VMPTRST] = handle_vmx_insn,
[EXIT_REASON_VMREAD] = handle_vmx_insn,
[EXIT_REASON_VMRESUME] = handle_vmx_insn,
[EXIT_REASON_VMWRITE] = handle_vmx_insn,
[EXIT_REASON_VMOFF] = handle_vmx_insn,
[EXIT_REASON_VMON] = handle_vmx_insn,
[EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
[EXIT_REASON_XSETBV] = handle_xsetbv,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
};
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 vmx_handle_exit(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
trace_kvm_exit(exit_reason, vcpu);
/* If guest state is invalid, start emulating */
if (vmx->emulation_required && emulate_invalid_guest_state)
return handle_invalid_guest_state(vcpu);
/* Access CR3 don't cause VMExit in paging mode, so we need
* to sync with guest real CR3. */
if (enable_ept && is_paging(vcpu))
vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
= exit_reason;
return 0;
}
if (unlikely(vmx->fail)) {
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->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 &&
exit_reason != EXIT_REASON_EPT_VIOLATION &&
exit_reason != EXIT_REASON_TASK_SWITCH))
printk(KERN_WARNING "%s: unexpected, valid vectoring info "
"(0x%x) and exit reason is 0x%x\n",
__func__, vectoring_info, exit_reason);
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) {
if (vmx_interrupt_allowed(vcpu)) {
vmx->soft_vnmi_blocked = 0;
} else if (vmx->vnmi_blocked_time > 1000000000LL &&
vcpu->arch.nmi_pending) {
/*
* This CPU don't support us in finding the end of an
* NMI-blocked window if the guest runs with IRQs
* disabled. So we pull the trigger after 1 s of
* futile waiting, but inform the user about this.
*/
printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
"state on VCPU %d after 1 s timeout\n",
__func__, vcpu->vcpu_id);
vmx->soft_vnmi_blocked = 0;
}
}
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
vcpu->run->hw.hardware_exit_reason = exit_reason;
}
return 0;
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
if (irr == -1 || tpr < irr) {
vmcs_write32(TPR_THRESHOLD, 0);
return;
}
vmcs_write32(TPR_THRESHOLD, irr);
}
static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
u32 idt_vectoring_info = vmx->idt_vectoring_info;
bool unblock_nmi;
u8 vector;
int type;
bool idtv_info_valid;
exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
/* Handle machine checks before interrupts are enabled */
if ((vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
|| (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI
&& is_machine_check(exit_intr_info)))
kvm_machine_check();
/* We need to handle NMIs before interrupts are enabled */
if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
(exit_intr_info & INTR_INFO_VALID_MASK)) {
kvm_before_handle_nmi(&vmx->vcpu);
asm("int $2");
kvm_after_handle_nmi(&vmx->vcpu);
}
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
if (cpu_has_virtual_nmis()) {
unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
/*
* SDM 3: 27.7.1.2 (September 2008)
* Re-set bit "block by NMI" before VM entry if vmexit caused by
* a guest IRET fault.
* SDM 3: 23.2.2 (September 2008)
* Bit 12 is undefined in any of the following cases:
* If the VM exit sets the valid bit in the IDT-vectoring
* information field.
* If the VM exit is due to a double fault.
*/
if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
vector != DF_VECTOR && !idtv_info_valid)
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
} else if (unlikely(vmx->soft_vnmi_blocked))
vmx->vnmi_blocked_time +=
ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time));
vmx->vcpu.arch.nmi_injected = false;
kvm_clear_exception_queue(&vmx->vcpu);
kvm_clear_interrupt_queue(&vmx->vcpu);
if (!idtv_info_valid)
return;
vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
switch (type) {
case INTR_TYPE_NMI_INTR:
vmx->vcpu.arch.nmi_injected = true;
/*
* SDM 3: 27.7.1.2 (September 2008)
* Clear bit "block by NMI" before VM entry if a NMI
* delivery faulted.
*/
vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
break;
case INTR_TYPE_SOFT_EXCEPTION:
vmx->vcpu.arch.event_exit_inst_len =
vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
/* fall through */
case INTR_TYPE_HARD_EXCEPTION:
if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
u32 err = vmcs_read32(IDT_VECTORING_ERROR_CODE);
kvm_queue_exception_e(&vmx->vcpu, vector, err);
} else
kvm_queue_exception(&vmx->vcpu, vector);
break;
case INTR_TYPE_SOFT_INTR:
vmx->vcpu.arch.event_exit_inst_len =
vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
/* fall through */
case INTR_TYPE_EXT_INTR:
kvm_queue_interrupt(&vmx->vcpu, vector,
type == INTR_TYPE_SOFT_INTR);
break;
default:
break;
}
}
/*
* Failure to inject an interrupt should give us the information
* in IDT_VECTORING_INFO_FIELD. However, if the failure occurs
* when fetching the interrupt redirection bitmap in the real-mode
* tss, this doesn't happen. So we do it ourselves.
*/
static void fixup_rmode_irq(struct vcpu_vmx *vmx)
{
vmx->rmode.irq.pending = 0;
if (kvm_rip_read(&vmx->vcpu) + 1 != vmx->rmode.irq.rip)
return;
kvm_rip_write(&vmx->vcpu, vmx->rmode.irq.rip);
if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) {
vmx->idt_vectoring_info &= ~VECTORING_INFO_TYPE_MASK;
vmx->idt_vectoring_info |= INTR_TYPE_EXT_INTR;
return;
}
vmx->idt_vectoring_info =
VECTORING_INFO_VALID_MASK
| INTR_TYPE_EXT_INTR
| vmx->rmode.irq.vector;
}
#ifdef CONFIG_X86_64
#define R "r"
#define Q "q"
#else
#define R "e"
#define Q "l"
#endif
static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
vmx->entry_time = ktime_get();
/* Don't enter VMX if guest state is invalid, let the exit handler
start emulation until we arrive back to a valid state */
if (vmx->emulation_required && emulate_invalid_guest_state)
return;
if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
/* When single-stepping over STI and MOV SS, we must clear the
* corresponding interruptibility bits in the guest state. Otherwise
* vmentry fails as it then expects bit 14 (BS) in pending debug
* exceptions being set, but that's not correct for the guest debugging
* case. */
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
"push %%"R"cx \n\t"
"cmp %%"R"sp, %c[host_rsp](%0) \n\t"
"je 1f \n\t"
"mov %%"R"sp, %c[host_rsp](%0) \n\t"
__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
"1: \n\t"
/* Reload cr2 if changed */
"mov %c[cr2](%0), %%"R"ax \n\t"
"mov %%cr2, %%"R"dx \n\t"
"cmp %%"R"ax, %%"R"dx \n\t"
"je 2f \n\t"
"mov %%"R"ax, %%cr2 \n\t"
"2: \n\t"
/* Check if vmlaunch of vmresume is needed */
"cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
"mov %c[rax](%0), %%"R"ax \n\t"
"mov %c[rbx](%0), %%"R"bx \n\t"
"mov %c[rdx](%0), %%"R"dx \n\t"
"mov %c[rsi](%0), %%"R"si \n\t"
"mov %c[rdi](%0), %%"R"di \n\t"
"mov %c[rbp](%0), %%"R"bp \n\t"
#ifdef CONFIG_X86_64
"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"
#endif
"mov %c[rcx](%0), %%"R"cx \n\t" /* kills %0 (ecx) */
/* Enter guest mode */
"jne .Llaunched \n\t"
__ex(ASM_VMX_VMLAUNCH) "\n\t"
"jmp .Lkvm_vmx_return \n\t"
".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t"
".Lkvm_vmx_return: "
/* Save guest registers, load host registers, keep flags */
"xchg %0, (%%"R"sp) \n\t"
"mov %%"R"ax, %c[rax](%0) \n\t"
"mov %%"R"bx, %c[rbx](%0) \n\t"
"push"Q" (%%"R"sp); pop"Q" %c[rcx](%0) \n\t"
"mov %%"R"dx, %c[rdx](%0) \n\t"
"mov %%"R"si, %c[rsi](%0) \n\t"
"mov %%"R"di, %c[rdi](%0) \n\t"
"mov %%"R"bp, %c[rbp](%0) \n\t"
#ifdef CONFIG_X86_64
"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"
#endif
"mov %%cr2, %%"R"ax \n\t"
"mov %%"R"ax, %c[cr2](%0) \n\t"
"pop %%"R"bp; pop %%"R"bp; pop %%"R"dx \n\t"
"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)),
[host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)),
[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"
, R"bx", R"di", R"si"
#ifdef CONFIG_X86_64
, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
#endif
);
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_PDPTR));
vcpu->arch.regs_dirty = 0;
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
if (vmx->rmode.irq.pending)
fixup_rmode_irq(vmx);
asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
vmx->launched = 1;
vmx_complete_interrupts(vmx);
}
#undef R
#undef Q
static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (vmx->vmcs) {
vcpu_clear(vmx);
free_vmcs(vmx->vmcs);
vmx->vmcs = NULL;
}
}
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
free_vpid(vmx);
vmx_free_vmcs(vcpu);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
}
static inline void vmcs_init(struct vmcs *vmcs)
{
u64 phys_addr = __pa(per_cpu(vmxarea, raw_smp_processor_id()));
if (!vmm_exclusive)
kvm_cpu_vmxon(phys_addr);
vmcs_clear(vmcs);
if (!vmm_exclusive)
kvm_cpu_vmxoff();
}
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);
allocate_vpid(vmx);
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->vmcs = alloc_vmcs();
if (!vmx->vmcs)
goto free_msrs;
vmcs_init(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;
if (enable_ept) {
if (!kvm->arch.ept_identity_map_addr)
kvm->arch.ept_identity_map_addr =
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
if (alloc_identity_pagetable(kvm) != 0)
goto free_vmcs;
}
return &vmx->vcpu;
free_vmcs:
free_vmcs(vmx->vmcs);
free_msrs:
kfree(vmx->guest_msrs);
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
free_vpid(vmx);
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 int get_ept_level(void)
{
return VMX_EPT_DEFAULT_GAW + 1;
}
static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
u64 ret;
/* For VT-d and EPT combination
* 1. MMIO: always map as UC
* 2. EPT with VT-d:
* a. VT-d without snooping control feature: can't guarantee the
* result, try to trust guest.
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
if (is_mmio)
ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
else if (vcpu->kvm->arch.iommu_domain &&
!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY))
ret = kvm_get_guest_memory_type(vcpu, gfn) <<
VMX_EPT_MT_EPTE_SHIFT;
else
ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
| VMX_EPT_IPAT_BIT;
return ret;
}
#define _ER(x) { EXIT_REASON_##x, #x }
static const struct trace_print_flags vmx_exit_reasons_str[] = {
_ER(EXCEPTION_NMI),
_ER(EXTERNAL_INTERRUPT),
_ER(TRIPLE_FAULT),
_ER(PENDING_INTERRUPT),
_ER(NMI_WINDOW),
_ER(TASK_SWITCH),
_ER(CPUID),
_ER(HLT),
_ER(INVLPG),
_ER(RDPMC),
_ER(RDTSC),
_ER(VMCALL),
_ER(VMCLEAR),
_ER(VMLAUNCH),
_ER(VMPTRLD),
_ER(VMPTRST),
_ER(VMREAD),
_ER(VMRESUME),
_ER(VMWRITE),
_ER(VMOFF),
_ER(VMON),
_ER(CR_ACCESS),
_ER(DR_ACCESS),
_ER(IO_INSTRUCTION),
_ER(MSR_READ),
_ER(MSR_WRITE),
_ER(MWAIT_INSTRUCTION),
_ER(MONITOR_INSTRUCTION),
_ER(PAUSE_INSTRUCTION),
_ER(MCE_DURING_VMENTRY),
_ER(TPR_BELOW_THRESHOLD),
_ER(APIC_ACCESS),
_ER(EPT_VIOLATION),
_ER(EPT_MISCONFIG),
_ER(WBINVD),
{ -1, NULL }
};
#undef _ER
static int vmx_get_lpage_level(void)
{
if (enable_ept && !cpu_has_vmx_ept_1g_page())
return PT_DIRECTORY_LEVEL;
else
/* For shadow and EPT supported 1GB page */
return PT_PDPE_LEVEL;
}
static inline u32 bit(int bitno)
{
return 1 << (bitno & 31);
}
static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control;
vmx->rdtscp_enabled = false;
if (vmx_rdtscp_supported()) {
exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
if (exec_control & SECONDARY_EXEC_RDTSCP) {
best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
if (best && (best->edx & bit(X86_FEATURE_RDTSCP)))
vmx->rdtscp_enabled = true;
else {
exec_control &= ~SECONDARY_EXEC_RDTSCP;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
exec_control);
}
}
}
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
{
}
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,
.cpu_has_accelerated_tpr = report_flexpriority,
.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,
.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,
.get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
.decache_cr0_guest_bits = vmx_decache_cr0_guest_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,
.set_efer = vmx_set_efer,
.get_idt = vmx_get_idt,
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
.set_gdt = vmx_set_gdt,
.set_dr7 = vmx_set_dr7,
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
.fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
.run = vmx_vcpu_run,
.handle_exit = vmx_handle_exit,
.skip_emulated_instruction = skip_emulated_instruction,
.set_interrupt_shadow = vmx_set_interrupt_shadow,
.get_interrupt_shadow = vmx_get_interrupt_shadow,
.patch_hypercall = vmx_patch_hypercall,
.set_irq = vmx_inject_irq,
.set_nmi = vmx_inject_nmi,
.queue_exception = vmx_queue_exception,
.interrupt_allowed = vmx_interrupt_allowed,
.nmi_allowed = vmx_nmi_allowed,
.get_nmi_mask = vmx_get_nmi_mask,
.set_nmi_mask = vmx_set_nmi_mask,
.enable_nmi_window = enable_nmi_window,
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.set_tss_addr = vmx_set_tss_addr,
.get_tdp_level = get_ept_level,
.get_mt_mask = vmx_get_mt_mask,
.exit_reasons_str = vmx_exit_reasons_str,
.get_lpage_level = vmx_get_lpage_level,
.cpuid_update = vmx_cpuid_update,
.rdtscp_supported = vmx_rdtscp_supported,
.set_supported_cpuid = vmx_set_supported_cpuid,
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
};
static int __init vmx_init(void)
{
int r, i;
rdmsrl_safe(MSR_EFER, &host_efer);
for (i = 0; i < NR_VMX_MSR; ++i)
kvm_define_shared_msr(i, vmx_msr_index[i]);
vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_io_bitmap_a)
return -ENOMEM;
vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_io_bitmap_b) {
r = -ENOMEM;
goto out;
}
vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_msr_bitmap_legacy) {
r = -ENOMEM;
goto out1;
}
vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_msr_bitmap_longmode) {
r = -ENOMEM;
goto out2;
}
/*
* Allow direct access to the PC debug port (it is often used for I/O
* delays, but the vmexits simply slow things down).
*/
memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
clear_bit(0x80, vmx_io_bitmap_a);
memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
__alignof__(struct vcpu_vmx), THIS_MODULE);
if (r)
goto out3;
vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
if (enable_ept) {
bypass_guest_pf = 0;
kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
VMX_EPT_WRITABLE_MASK);
kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
VMX_EPT_EXECUTABLE_MASK);
kvm_enable_tdp();
} else
kvm_disable_tdp();
if (bypass_guest_pf)
kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
return 0;
out3:
free_page((unsigned long)vmx_msr_bitmap_longmode);
out2:
free_page((unsigned long)vmx_msr_bitmap_legacy);
out1:
free_page((unsigned long)vmx_io_bitmap_b);
out:
free_page((unsigned long)vmx_io_bitmap_a);
return r;
}
static void __exit vmx_exit(void)
{
free_page((unsigned long)vmx_msr_bitmap_legacy);
free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_b);
free_page((unsigned long)vmx_io_bitmap_a);
kvm_exit();
}
module_init(vmx_init)
module_exit(vmx_exit)
Reference in New Issue View Git Blame Copy Permalink