static bool __read_mostly nested = 0;
module_param(nested, bool, S_IRUGO);
+static bool __read_mostly nested_early_check = 0;
+module_param(nested_early_check, bool, S_IRUGO);
+
static u64 __read_mostly host_xss;
static bool __read_mostly enable_pml = 1;
module_param(ple_window_max, uint, 0444);
extern const ulong vmx_return;
+extern const ulong vmx_early_consistency_check_return;
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
return -1;
}
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
{
struct {
u64 vpid : 16;
BUG_ON(error);
}
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
{
struct {
u64 eptp, gpa;
u64 guest_val, u64 host_val)
{
vmcs_write64(guest_val_vmcs, guest_val);
- vmcs_write64(host_val_vmcs, host_val);
+ if (host_val_vmcs != HOST_IA32_EFER)
+ vmcs_write64(host_val_vmcs, host_val);
vm_entry_controls_setbit(vmx, entry);
vm_exit_controls_setbit(vmx, exit);
}
bool invalidate_gpa)
{
if (enable_ept && (invalidate_gpa || !enable_vpid)) {
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
+ ept_sync_context(construct_eptp(vcpu,
+ vcpu->arch.mmu->root_hpa));
} else {
vpid_sync_context(vpid);
}
rdmsr(MSR_IA32_CR_PAT, low32, high32);
vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
}
+
+ if (cpu_has_load_ia32_efer)
+ vmcs_write64(HOST_IA32_EFER, host_efer);
}
static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
/*
* The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
+ * set the success or error code of an emulated VMX instruction (as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
+ * instruction.
*/
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
| X86_EFLAGS_CF);
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
- u32 vm_instruction_error)
+static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
+ u32 vm_instruction_error)
{
- if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
- /*
- * failValid writes the error number to the current VMCS, which
- * can't be done there isn't a current VMCS.
- */
- nested_vmx_failInvalid(vcpu);
- return;
- }
+ /*
+ * failValid writes the error number to the current VMCS, which
+ * can't be done if there isn't a current VMCS.
+ */
+ if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
+
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
* We don't need to force a shadow sync because
* VM_INSTRUCTION_ERROR is not shadowed
*/
+ return kvm_skip_emulated_instruction(vcpu);
}
static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
return 1;
}
- if (vmx->nested.vmxon) {
- nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmx->nested.vmxon)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
* Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
* which replaces physical address width with 32
*/
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failInvalid(vcpu);
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
if (*(u32 *)kmap(page) != VMCS12_REVISION) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_failInvalid(vcpu);
}
kunmap(page);
kvm_release_page_clean(page);
if (ret)
return ret;
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/*
vmcs_write64(VMCS_LINK_POINTER, -1ull);
}
-static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
+static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (vmx->nested.current_vmptr == -1ull)
return;
vmx->nested.posted_intr_nv = -1;
/* Flush VMCS12 to guest memory */
- kvm_vcpu_write_guest_page(&vmx->vcpu,
+ kvm_vcpu_write_guest_page(vcpu,
vmx->nested.current_vmptr >> PAGE_SHIFT,
vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
vmx->nested.current_vmptr = -1ull;
}
* Free whatever needs to be freed from vmx->nested when L1 goes down, or
* just stops using VMX.
*/
-static void free_nested(struct vcpu_vmx *vmx)
+static void free_nested(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
vmx->nested.pi_desc = NULL;
}
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
free_loaded_vmcs(&vmx->nested.vmcs02);
}
{
if (!nested_vmx_check_permission(vcpu))
return 1;
- free_nested(to_vmx(vcpu));
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ free_nested(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the VMCLEAR instruction */
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_VMXON_POINTER);
if (vmptr == vmx->nested.current_vmptr)
- nested_release_vmcs12(vmx);
+ nested_release_vmcs12(vcpu);
kvm_vcpu_write_guest(vcpu,
vmptr + offsetof(struct vmcs12, launch_state),
&zero, sizeof(zero));
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
vmcs_load(vmx->loaded_vmcs->vmcs);
}
-/*
- * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was
- * used before) all generate the same failure when it is missing.
- */
-static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (vmx->nested.current_vmptr == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return 0;
- }
- return 1;
-}
-
static int handle_vmread(struct kvm_vcpu *vcpu)
{
unsigned long field;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
* When vmcs->vmcs_link_pointer is -1ull, any VMREAD
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
}
/* Decode instruction info and find the field to read */
field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
/* Read the field, zero-extended to a u64 field_value */
- if (vmcs12_read_any(vmcs12, field, &field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_read_any(vmcs12, field, &field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
/*
* Now copy part of this value to register or memory, as requested.
* Note that the number of bits actually copied is 32 or 64 depending
(is_long_mode(vcpu) ? 8 : 4), NULL);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (vmx_instruction_info & (1u << 10))
field_value = kvm_register_readl(vcpu,
* VMCS," then the "read-only" fields are actually read/write.
*/
if (vmcs_field_readonly(field) &&
- !nested_cpu_has_vmwrite_any_field(vcpu)) {
- nested_vmx_failValid(vcpu,
+ !nested_cpu_has_vmwrite_any_field(vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
* When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
-
}
- if (vmcs12_write_any(vmcs12, field, field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_write_any(vmcs12, field, field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
/*
* Do not track vmcs12 dirty-state if in guest-mode
}
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_VMXON_POINTER);
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
new_vmcs12 = kmap(page);
if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
(new_vmcs12->hdr.shadow_vmcs &&
!nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failValid(vcpu,
+ return nested_vmx_failValid(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
- return kvm_skip_emulated_instruction(vcpu);
}
- nested_release_vmcs12(vmx);
+ nested_release_vmcs12(vcpu);
+
/*
* Load VMCS12 from guest memory since it is not already
* cached.
set_current_vmptr(vmx, vmptr);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the VMPTRST instruction */
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the INVEPT instruction */
types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* According to the Intel VMX instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
case VMX_EPT_EXTENT_CONTEXT:
kvm_mmu_sync_roots(vcpu);
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- nested_vmx_succeed(vcpu);
break;
default:
BUG_ON(1);
break;
}
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
types = (vmx->nested.msrs.vpid_caps &
VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* according to the intel vmx instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- if (operand.vpid >> 16) {
- nested_vmx_failValid(vcpu,
+ if (operand.vpid >> 16)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
vpid02 = nested_get_vpid02(vcpu);
switch (type) {
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
if (!operand.vpid ||
- is_noncanonical_address(operand.gla, vcpu)) {
- nested_vmx_failValid(vcpu,
+ is_noncanonical_address(operand.gla, vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
if (cpu_has_vmx_invvpid_individual_addr()) {
__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
vpid02, operand.gla);
break;
case VMX_VPID_EXTENT_SINGLE_CONTEXT:
case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
- if (!operand.vpid) {
- nested_vmx_failValid(vcpu,
+ if (!operand.vpid)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
__vmx_flush_tlb(vcpu, vpid02, false);
break;
case VMX_VPID_EXTENT_ALL_CONTEXT:
return kvm_skip_emulated_instruction(vcpu);
}
- nested_vmx_succeed(vcpu);
-
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int handle_invpcid(struct kvm_vcpu *vcpu)
}
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3)
+ if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
== operand.pcid)
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
- kvm_mmu_free_roots(vcpu, roots_to_free);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
/*
* If neither the current cr3 nor any of the prev_roots use the
* given PCID, then nothing needs to be done here because a
kvm_mmu_unload(vcpu);
mmu->ept_ad = accessed_dirty;
- mmu->base_role.ad_disabled = !accessed_dirty;
+ mmu->mmu_role.base.ad_disabled = !accessed_dirty;
vmcs12->ept_pointer = address;
/*
* TODO: Check what's the correct approach in case
*/
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- vcpu_load(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- free_nested(vmx);
- vcpu_put(vcpu);
+ vcpu_load(vcpu);
+ vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
+ free_nested(vcpu);
+ vcpu_put(vcpu);
}
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
+ vcpu->arch.mmu = &vcpu->arch.guest_mmu;
kvm_init_shadow_ept_mmu(vcpu,
to_vmx(vcpu)->nested.msrs.ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
nested_ept_ad_enabled(vcpu),
nested_ept_get_cr3(vcpu));
- vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
- vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
- vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->set_cr3 = vmx_set_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3;
+ vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->get_pdptr = kvm_pdptr_read;
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
return;
vmx->nested.vmcs02_initialized = true;
+ /*
+ * We don't care what the EPTP value is we just need to guarantee
+ * it's valid so we don't get a false positive when doing early
+ * consistency checks.
+ */
+ if (enable_ept && nested_early_check)
+ vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
+
/* All VMFUNCs are currently emulated through L0 vmexits. */
if (cpu_has_vmx_vmfunc())
vmcs_write64(VM_FUNCTION_CONTROL, 0);
* entry, but only if the current (host) sp changed from the value
* we wrote last (vmx->host_rsp). This cache is no longer relevant
* if we switch vmcs, and rather than hold a separate cache per vmcs,
- * here we just force the write to happen on entry.
+ * here we just force the write to happen on entry. host_rsp will
+ * also be written unconditionally by nested_vmx_check_vmentry_hw()
+ * if we are doing early consistency checks via hardware.
*/
vmx->host_rsp = 0;
return 0;
}
+static int __noclone nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long cr3, cr4;
+
+ if (!nested_early_check)
+ return 0;
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+
+ preempt_disable();
+
+ vmx_prepare_switch_to_guest(vcpu);
+
+ /*
+ * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
+ * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to
+ * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
+ * there is no need to preserve other bits or save/restore the field.
+ */
+ vmcs_writel(GUEST_RFLAGS, 0);
+
+ vmcs_writel(HOST_RIP, vmx_early_consistency_check_return);
+
+ cr3 = __get_current_cr3_fast();
+ if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+ vmcs_writel(HOST_CR3, cr3);
+ vmx->loaded_vmcs->host_state.cr3 = cr3;
+ }
+
+ cr4 = cr4_read_shadow();
+ if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->loaded_vmcs->host_state.cr4 = cr4;
+ }
+
+ vmx->__launched = vmx->loaded_vmcs->launched;
+
+ asm(
+ /* Set HOST_RSP */
+ __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
+ "mov %%" _ASM_SP ", %c[host_rsp](%0)\n\t"
+
+ /* Check if vmlaunch of vmresume is needed */
+ "cmpl $0, %c[launched](%0)\n\t"
+ "je 1f\n\t"
+ __ex(ASM_VMX_VMRESUME) "\n\t"
+ "jmp 2f\n\t"
+ "1: " __ex(ASM_VMX_VMLAUNCH) "\n\t"
+ "jmp 2f\n\t"
+ "2: "
+
+ /* Set vmx->fail accordingly */
+ "setbe %c[fail](%0)\n\t"
+
+ ".pushsection .rodata\n\t"
+ ".global vmx_early_consistency_check_return\n\t"
+ "vmx_early_consistency_check_return: " _ASM_PTR " 2b\n\t"
+ ".popsection"
+ :
+ : "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", "cc", "memory"
+ );
+
+ vmcs_writel(HOST_RIP, vmx_return);
+
+ preempt_enable();
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+ if (vmx->fail) {
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ vmx->fail = 0;
+ return 1;
+ }
+
+ /*
+ * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
+ */
+ local_irq_enable();
+ if (hw_breakpoint_active())
+ set_debugreg(__this_cpu_read(cpu_dr7), 7);
+
+ /*
+ * A non-failing VMEntry means we somehow entered guest mode with
+ * an illegal RIP, and that's just the tip of the iceberg. There
+ * is no telling what memory has been modified or what state has
+ * been exposed to unknown code. Hitting this all but guarantees
+ * a (very critical) hardware issue.
+ */
+ WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
+ VMX_EXIT_REASONS_FAILED_VMENTRY));
+
+ return 0;
+}
+STACK_FRAME_NON_STANDARD(nested_vmx_check_vmentry_hw);
+
static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12);
/*
* If from_vmentry is false, this is being called from state restore (either RSM
* or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume.
++ *
++ * Returns:
++ * 0 - success, i.e. proceed with actual VMEnter
++ * 1 - consistency check VMExit
++ * -1 - consistency check VMFail
*/
static int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
bool from_vmentry)
if (from_vmentry) {
nested_get_vmcs12_pages(vcpu);
+ if (nested_vmx_check_vmentry_hw(vcpu)) {
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ return -1;
+ }
+
if (check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
goto vmentry_fail_vmexit;
}
load_vmcs12_host_state(vcpu, vmcs12);
vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
vmcs12->exit_qualification = exit_qual;
- nested_vmx_succeed(vcpu);
if (enable_shadow_vmcs)
vmx->nested.sync_shadow_vmcs = true;
return 1;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- goto out;
+ if (vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_vmcs12(vcpu);
* rather than RFLAGS.ZF, and no error number is stored to the
* VM-instruction error field.
*/
- if (vmcs12->hdr.shadow_vmcs) {
- nested_vmx_failInvalid(vcpu);
- goto out;
- }
+ if (vmcs12->hdr.shadow_vmcs)
+ return nested_vmx_failInvalid(vcpu);
if (enable_shadow_vmcs)
copy_shadow_to_vmcs12(vmx);
* for misconfigurations which will anyway be caught by the processor
* when using the merged vmcs02.
*/
- if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
- nested_vmx_failValid(vcpu,
- VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- goto out;
- }
+ if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- if (vmcs12->launch_state == launch) {
- nested_vmx_failValid(vcpu,
+ if (vmcs12->launch_state == launch)
+ return nested_vmx_failValid(vcpu,
launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
: VMXERR_VMRESUME_NONLAUNCHED_VMCS);
- goto out;
- }
ret = check_vmentry_prereqs(vcpu, vmcs12);
- if (ret) {
- nested_vmx_failValid(vcpu, ret);
- goto out;
- }
+ if (ret)
+ return nested_vmx_failValid(vcpu, ret);
/*
* We're finally done with prerequisite checking, and can start with
* the nested entry.
*/
-
vmx->nested.nested_run_pending = 1;
ret = nested_vmx_enter_non_root_mode(vcpu, true);
- if (ret) {
- vmx->nested.nested_run_pending = 0;
+ vmx->nested.nested_run_pending = !ret;
+ if (ret > 0)
return 1;
- }
+ else if (ret)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/* Hide L1D cache contents from the nested guest. */
vmx->vcpu.arch.l1tf_flush_l1d = true;
return kvm_vcpu_halt(vcpu);
}
return 1;
-
-out:
- return kvm_skip_emulated_instruction(vcpu);
}
/*
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
- /*
- * The only expected VM-instruction error is "VM entry with
- * invalid control field(s)." Anything else indicates a
- * problem with L0.
- */
- WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
- VMXERR_ENTRY_INVALID_CONTROL_FIELD));
-
leave_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
vmcs12->vm_exit_msr_store_count))
nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+ } else {
+ /*
+ * The only expected VM-instruction error is "VM entry with
+ * invalid control field(s)." Anything else indicates a
+ * problem with L0. And we should never get here with a
+ * VMFail of any type if early consistency checks are enabled.
+ */
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ WARN_ON_ONCE(nested_early_check);
}
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
return;
}
-
+
/*
* After an early L2 VM-entry failure, we're now back
* in L1 which thinks it just finished a VMLAUNCH or
* flag and the VM-instruction error field of the VMCS
* accordingly, and skip the emulated instruction.
*/
- nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-
- kvm_skip_emulated_instruction(vcpu);
+ (void)nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/*
* Restore L1's host state to KVM's software model. We're here
to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
}
- free_nested(to_vmx(vcpu));
+ free_nested(vcpu);
}
static int vmx_check_intercept(struct kvm_vcpu *vcpu,