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);
VMX_SEGMENT_FIELD(LDTR),
};
+static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
+
/*
* Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it
* away by decrementing the array size.
SECONDARY_EXEC_ENABLE_EPT;
}
+static inline int cpu_has_vmx_unrestricted_guest(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
+}
+
static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled &&
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;
}
opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_WBINVD_EXITING |
SECONDARY_EXEC_ENABLE_VPID |
- SECONDARY_EXEC_ENABLE_EPT;
+ SECONDARY_EXEC_ENABLE_EPT |
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
if (!cpu_has_vmx_vpid())
enable_vpid = 0;
- if (!cpu_has_vmx_ept())
+ if (!cpu_has_vmx_ept()) {
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;
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (enable_unrestricted_guest)
+ return;
+
vmx->emulation_required = 1;
vcpu->arch.rmode.vm86_active = 1;
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)) {
- if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
- printk(KERN_ERR "EPT: Fail to load pdptrs!\n");
- return;
- }
vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]);
vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]);
vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]);
}
}
+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,
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
vmx_set_cr4(vcpu, vcpu->arch.cr4);
- *hw_cr0 |= X86_CR0_PE | X86_CR0_PG;
*hw_cr0 &= ~X86_CR0_WP;
} else if (!is_paging(vcpu)) {
/* From nonpaging to paging */
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
- unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) |
- KVM_VM_CR0_ALWAYS_ON;
+ 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;
vmx_fpu_deactivate(vcpu);
if (enable_ept) {
eptp = construct_eptp(cr3);
vmcs_write64(EPT_POINTER, eptp);
- ept_sync_context(eptp);
- ept_load_pdptrs(vcpu);
guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
}
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 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);
- vmcs_write32(sf->ar_bytes, 0xf3);
+ 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)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
if (!enable_ept)
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
+ if (!enable_unrestricted_guest)
+ exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
(long unsigned int)exit_qualification);
kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = 0;
- return -ENOTSUPP;
+ kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ return 0;
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
/* Access CR3 don't cause VMExit in paging mode, so we need
* to sync with guest real CR3. */
- if (enable_ept && is_paging(vcpu)) {
+ if (enable_ept && is_paging(vcpu))
vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- ept_load_pdptrs(vcpu);
- }
if (unlikely(vmx->fail)) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (enable_ept && is_paging(vcpu)) {
+ vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
+ ept_load_pdptrs(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();
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);
+
/*
* Loading guest fpu may have cleared host cr0.ts
*/
#endif
);
- vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
+ vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
+ | (1 << VCPU_EXREG_PDPTR));
vcpu->arch.regs_dirty = 0;
get_debugreg(vcpu->arch.dr6, 6);