};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+static bool __read_mostly nosmt;
+module_param(nosmt, bool, S_IRUGO);
+
static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
extern const ulong vmx_return;
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+
+/* These MUST be in sync with vmentry_l1d_param order. */
+enum vmx_l1d_flush_state {
+ VMENTER_L1D_FLUSH_NEVER,
+ VMENTER_L1D_FLUSH_COND,
+ VMENTER_L1D_FLUSH_ALWAYS,
+};
+
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
+
+static const struct {
+ const char *option;
+ enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+ {"never", VMENTER_L1D_FLUSH_NEVER},
+ {"cond", VMENTER_L1D_FLUSH_COND},
+ {"always", VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+ unsigned int i;
+
+ if (!s)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+ if (!strcmp(s, vmentry_l1d_param[i].option)) {
+ vmentry_l1d_flush = vmentry_l1d_param[i].cmd;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+ return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+ .set = vmentry_l1d_flush_set,
+ .get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO);
+
struct kvm_vmx {
struct kvm kvm;
* underlying hardware which will be used to run L2.
* This structure is packed to ensure that its layout is identical across
* machines (necessary for live migration).
- * If there are changes in this struct, VMCS12_REVISION must be changed.
+ *
+ * IMPORTANT: Changing the layout of existing fields in this structure
+ * will break save/restore compatibility with older kvm releases. When
+ * adding new fields, either use space in the reserved padding* arrays
+ * or add the new fields to the end of the structure.
*/
typedef u64 natural_width;
struct __packed vmcs12 {
u64 virtual_apic_page_addr;
u64 apic_access_addr;
u64 posted_intr_desc_addr;
- u64 vm_function_control;
u64 ept_pointer;
u64 eoi_exit_bitmap0;
u64 eoi_exit_bitmap1;
u64 eoi_exit_bitmap2;
u64 eoi_exit_bitmap3;
- u64 eptp_list_address;
u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
- u64 pml_address;
u64 guest_ia32_debugctl;
u64 guest_ia32_pat;
u64 guest_ia32_efer;
u64 host_ia32_pat;
u64 host_ia32_efer;
u64 host_ia32_perf_global_ctrl;
- u64 padding64[8]; /* room for future expansion */
+ u64 vmread_bitmap;
+ u64 vmwrite_bitmap;
+ u64 vm_function_control;
+ u64 eptp_list_address;
+ u64 pml_address;
+ u64 padding64[3]; /* room for future expansion */
/*
* To allow migration of L1 (complete with its L2 guests) between
* machines of different natural widths (32 or 64 bit), we cannot have
u16 guest_ldtr_selector;
u16 guest_tr_selector;
u16 guest_intr_status;
- u16 guest_pml_index;
u16 host_es_selector;
u16 host_cs_selector;
u16 host_ss_selector;
u16 host_fs_selector;
u16 host_gs_selector;
u16 host_tr_selector;
+ u16 guest_pml_index;
};
+/*
+ * For save/restore compatibility, the vmcs12 field offsets must not change.
+ */
+#define CHECK_OFFSET(field, loc) \
+ BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \
+ "Offset of " #field " in struct vmcs12 has changed.")
+
+static inline void vmx_check_vmcs12_offsets(void) {
+ CHECK_OFFSET(revision_id, 0);
+ CHECK_OFFSET(abort, 4);
+ CHECK_OFFSET(launch_state, 8);
+ CHECK_OFFSET(io_bitmap_a, 40);
+ CHECK_OFFSET(io_bitmap_b, 48);
+ CHECK_OFFSET(msr_bitmap, 56);
+ CHECK_OFFSET(vm_exit_msr_store_addr, 64);
+ CHECK_OFFSET(vm_exit_msr_load_addr, 72);
+ CHECK_OFFSET(vm_entry_msr_load_addr, 80);
+ CHECK_OFFSET(tsc_offset, 88);
+ CHECK_OFFSET(virtual_apic_page_addr, 96);
+ CHECK_OFFSET(apic_access_addr, 104);
+ CHECK_OFFSET(posted_intr_desc_addr, 112);
+ CHECK_OFFSET(ept_pointer, 120);
+ CHECK_OFFSET(eoi_exit_bitmap0, 128);
+ CHECK_OFFSET(eoi_exit_bitmap1, 136);
+ CHECK_OFFSET(eoi_exit_bitmap2, 144);
+ CHECK_OFFSET(eoi_exit_bitmap3, 152);
+ CHECK_OFFSET(xss_exit_bitmap, 160);
+ CHECK_OFFSET(guest_physical_address, 168);
+ CHECK_OFFSET(vmcs_link_pointer, 176);
+ CHECK_OFFSET(guest_ia32_debugctl, 184);
+ CHECK_OFFSET(guest_ia32_pat, 192);
+ CHECK_OFFSET(guest_ia32_efer, 200);
+ CHECK_OFFSET(guest_ia32_perf_global_ctrl, 208);
+ CHECK_OFFSET(guest_pdptr0, 216);
+ CHECK_OFFSET(guest_pdptr1, 224);
+ CHECK_OFFSET(guest_pdptr2, 232);
+ CHECK_OFFSET(guest_pdptr3, 240);
+ CHECK_OFFSET(guest_bndcfgs, 248);
+ CHECK_OFFSET(host_ia32_pat, 256);
+ CHECK_OFFSET(host_ia32_efer, 264);
+ CHECK_OFFSET(host_ia32_perf_global_ctrl, 272);
+ CHECK_OFFSET(vmread_bitmap, 280);
+ CHECK_OFFSET(vmwrite_bitmap, 288);
+ CHECK_OFFSET(vm_function_control, 296);
+ CHECK_OFFSET(eptp_list_address, 304);
+ CHECK_OFFSET(pml_address, 312);
+ CHECK_OFFSET(cr0_guest_host_mask, 344);
+ CHECK_OFFSET(cr4_guest_host_mask, 352);
+ CHECK_OFFSET(cr0_read_shadow, 360);
+ CHECK_OFFSET(cr4_read_shadow, 368);
+ CHECK_OFFSET(cr3_target_value0, 376);
+ CHECK_OFFSET(cr3_target_value1, 384);
+ CHECK_OFFSET(cr3_target_value2, 392);
+ CHECK_OFFSET(cr3_target_value3, 400);
+ CHECK_OFFSET(exit_qualification, 408);
+ CHECK_OFFSET(guest_linear_address, 416);
+ CHECK_OFFSET(guest_cr0, 424);
+ CHECK_OFFSET(guest_cr3, 432);
+ CHECK_OFFSET(guest_cr4, 440);
+ CHECK_OFFSET(guest_es_base, 448);
+ CHECK_OFFSET(guest_cs_base, 456);
+ CHECK_OFFSET(guest_ss_base, 464);
+ CHECK_OFFSET(guest_ds_base, 472);
+ CHECK_OFFSET(guest_fs_base, 480);
+ CHECK_OFFSET(guest_gs_base, 488);
+ CHECK_OFFSET(guest_ldtr_base, 496);
+ CHECK_OFFSET(guest_tr_base, 504);
+ CHECK_OFFSET(guest_gdtr_base, 512);
+ CHECK_OFFSET(guest_idtr_base, 520);
+ CHECK_OFFSET(guest_dr7, 528);
+ CHECK_OFFSET(guest_rsp, 536);
+ CHECK_OFFSET(guest_rip, 544);
+ CHECK_OFFSET(guest_rflags, 552);
+ CHECK_OFFSET(guest_pending_dbg_exceptions, 560);
+ CHECK_OFFSET(guest_sysenter_esp, 568);
+ CHECK_OFFSET(guest_sysenter_eip, 576);
+ CHECK_OFFSET(host_cr0, 584);
+ CHECK_OFFSET(host_cr3, 592);
+ CHECK_OFFSET(host_cr4, 600);
+ CHECK_OFFSET(host_fs_base, 608);
+ CHECK_OFFSET(host_gs_base, 616);
+ CHECK_OFFSET(host_tr_base, 624);
+ CHECK_OFFSET(host_gdtr_base, 632);
+ CHECK_OFFSET(host_idtr_base, 640);
+ CHECK_OFFSET(host_ia32_sysenter_esp, 648);
+ CHECK_OFFSET(host_ia32_sysenter_eip, 656);
+ CHECK_OFFSET(host_rsp, 664);
+ CHECK_OFFSET(host_rip, 672);
+ CHECK_OFFSET(pin_based_vm_exec_control, 744);
+ CHECK_OFFSET(cpu_based_vm_exec_control, 748);
+ CHECK_OFFSET(exception_bitmap, 752);
+ CHECK_OFFSET(page_fault_error_code_mask, 756);
+ CHECK_OFFSET(page_fault_error_code_match, 760);
+ CHECK_OFFSET(cr3_target_count, 764);
+ CHECK_OFFSET(vm_exit_controls, 768);
+ CHECK_OFFSET(vm_exit_msr_store_count, 772);
+ CHECK_OFFSET(vm_exit_msr_load_count, 776);
+ CHECK_OFFSET(vm_entry_controls, 780);
+ CHECK_OFFSET(vm_entry_msr_load_count, 784);
+ CHECK_OFFSET(vm_entry_intr_info_field, 788);
+ CHECK_OFFSET(vm_entry_exception_error_code, 792);
+ CHECK_OFFSET(vm_entry_instruction_len, 796);
+ CHECK_OFFSET(tpr_threshold, 800);
+ CHECK_OFFSET(secondary_vm_exec_control, 804);
+ CHECK_OFFSET(vm_instruction_error, 808);
+ CHECK_OFFSET(vm_exit_reason, 812);
+ CHECK_OFFSET(vm_exit_intr_info, 816);
+ CHECK_OFFSET(vm_exit_intr_error_code, 820);
+ CHECK_OFFSET(idt_vectoring_info_field, 824);
+ CHECK_OFFSET(idt_vectoring_error_code, 828);
+ CHECK_OFFSET(vm_exit_instruction_len, 832);
+ CHECK_OFFSET(vmx_instruction_info, 836);
+ CHECK_OFFSET(guest_es_limit, 840);
+ CHECK_OFFSET(guest_cs_limit, 844);
+ CHECK_OFFSET(guest_ss_limit, 848);
+ CHECK_OFFSET(guest_ds_limit, 852);
+ CHECK_OFFSET(guest_fs_limit, 856);
+ CHECK_OFFSET(guest_gs_limit, 860);
+ CHECK_OFFSET(guest_ldtr_limit, 864);
+ CHECK_OFFSET(guest_tr_limit, 868);
+ CHECK_OFFSET(guest_gdtr_limit, 872);
+ CHECK_OFFSET(guest_idtr_limit, 876);
+ CHECK_OFFSET(guest_es_ar_bytes, 880);
+ CHECK_OFFSET(guest_cs_ar_bytes, 884);
+ CHECK_OFFSET(guest_ss_ar_bytes, 888);
+ CHECK_OFFSET(guest_ds_ar_bytes, 892);
+ CHECK_OFFSET(guest_fs_ar_bytes, 896);
+ CHECK_OFFSET(guest_gs_ar_bytes, 900);
+ CHECK_OFFSET(guest_ldtr_ar_bytes, 904);
+ CHECK_OFFSET(guest_tr_ar_bytes, 908);
+ CHECK_OFFSET(guest_interruptibility_info, 912);
+ CHECK_OFFSET(guest_activity_state, 916);
+ CHECK_OFFSET(guest_sysenter_cs, 920);
+ CHECK_OFFSET(host_ia32_sysenter_cs, 924);
+ CHECK_OFFSET(vmx_preemption_timer_value, 928);
+ CHECK_OFFSET(virtual_processor_id, 960);
+ CHECK_OFFSET(posted_intr_nv, 962);
+ CHECK_OFFSET(guest_es_selector, 964);
+ CHECK_OFFSET(guest_cs_selector, 966);
+ CHECK_OFFSET(guest_ss_selector, 968);
+ CHECK_OFFSET(guest_ds_selector, 970);
+ CHECK_OFFSET(guest_fs_selector, 972);
+ CHECK_OFFSET(guest_gs_selector, 974);
+ CHECK_OFFSET(guest_ldtr_selector, 976);
+ CHECK_OFFSET(guest_tr_selector, 978);
+ CHECK_OFFSET(guest_intr_status, 980);
+ CHECK_OFFSET(host_es_selector, 982);
+ CHECK_OFFSET(host_cs_selector, 984);
+ CHECK_OFFSET(host_ss_selector, 986);
+ CHECK_OFFSET(host_ds_selector, 988);
+ CHECK_OFFSET(host_fs_selector, 990);
+ CHECK_OFFSET(host_gs_selector, 992);
+ CHECK_OFFSET(host_tr_selector, 994);
+ CHECK_OFFSET(guest_pml_index, 996);
+}
+
/*
* VMCS12_REVISION is an arbitrary id that should be changed if the content or
* layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
* VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
+ *
+ * IMPORTANT: Changing this value will break save/restore compatibility with
+ * older kvm releases.
*/
#define VMCS12_REVISION 0x11e57ed0
bool sync_shadow_vmcs;
bool dirty_vmcs12;
- bool change_vmcs01_virtual_x2apic_mode;
+ bool change_vmcs01_virtual_apic_mode;
+
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
(unsigned long *)&pi_desc->control);
}
+struct vmx_msrs {
+ unsigned int nr;
+ struct vmx_msr_entry val[NR_AUTOLOAD_MSRS];
+};
+
struct vcpu_vmx {
struct kvm_vcpu vcpu;
unsigned long host_rsp;
struct loaded_vmcs *loaded_vmcs;
bool __launched; /* temporary, used in vmx_vcpu_run */
struct msr_autoload {
- unsigned nr;
- struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
- struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+ struct vmx_msrs guest;
+ struct vmx_msrs host;
} msr_autoload;
struct {
int loaded;
FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
+ FIELD64(PML_ADDRESS, pml_address),
FIELD64(TSC_OFFSET, tsc_offset),
FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
+ FIELD64(VMREAD_BITMAP, vmread_bitmap),
+ FIELD64(VMWRITE_BITMAP, vmwrite_bitmap),
FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
- FIELD64(PML_ADDRESS, pml_address),
FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
return *(u16 *)((char *)current_evmcs + offset);
}
+static inline void evmcs_touch_msr_bitmap(void)
+{
+ if (unlikely(!current_evmcs))
+ return;
+
+ if (current_evmcs->hv_enlightenments_control.msr_bitmap)
+ current_evmcs->hv_clean_fields &=
+ ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+}
+
static void evmcs_load(u64 phys_addr)
{
struct hv_vp_assist_page *vp_ap =
static inline u16 evmcs_read16(unsigned long field) { return 0; }
static inline void evmcs_load(u64 phys_addr) {}
static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
+static inline void evmcs_touch_msr_bitmap(void) {}
#endif /* IS_ENABLED(CONFIG_HYPERV) */
static inline bool is_exception_n(u32 intr_info, u8 vector)
return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
+static inline bool cpu_has_vmx_invvpid_individual_addr(void)
+{
+ return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT;
+}
+
static inline bool cpu_has_vmx_invvpid_single(void)
{
return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
return vmx_misc_cr3_count(to_vmx(vcpu)->nested.msrs.misc_low);
}
+/*
+ * Do the virtual VMX capability MSRs specify that L1 can use VMWRITE
+ * to modify any valid field of the VMCS, or are the VM-exit
+ * information fields read-only?
+ */
+static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->nested.msrs.misc_low &
+ MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
vm_exit_controls_clearbit(vmx, exit);
}
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+ unsigned int i;
+
+ for (i = 0; i < m->nr; ++i) {
+ if (m->val[i].index == msr)
+ return i;
+ }
+ return -ENOENT;
+}
+
static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
- unsigned i;
+ int i;
struct msr_autoload *m = &vmx->msr_autoload;
switch (msr) {
}
break;
}
+ i = find_msr(&m->guest, msr);
+ if (i < 0)
+ goto skip_guest;
+ --m->guest.nr;
+ m->guest.val[i] = m->guest.val[m->guest.nr];
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
- for (i = 0; i < m->nr; ++i)
- if (m->guest[i].index == msr)
- break;
-
- if (i == m->nr)
+skip_guest:
+ i = find_msr(&m->host, msr);
+ if (i < 0)
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);
+
+ --m->host.nr;
+ m->host.val[i] = m->host.val[m->host.nr];
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
}
static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
}
static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
- u64 guest_val, u64 host_val)
+ u64 guest_val, u64 host_val, bool entry_only)
{
- unsigned i;
+ int i, j = 0;
struct msr_autoload *m = &vmx->msr_autoload;
switch (msr) {
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
- for (i = 0; i < m->nr; ++i)
- if (m->guest[i].index == msr)
- break;
+ i = find_msr(&m->guest, msr);
+ if (!entry_only)
+ j = find_msr(&m->host, msr);
- if (i == NR_AUTOLOAD_MSRS) {
+ if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
printk_once(KERN_WARNING "Not enough msr switch entries. "
"Can't add msr %x\n", msr);
return;
- } else if (i == m->nr) {
- ++m->nr;
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}
+ if (i < 0) {
+ i = m->guest.nr++;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+ }
+ m->guest.val[i].index = msr;
+ m->guest.val[i].value = guest_val;
- m->guest[i].index = msr;
- m->guest[i].value = guest_val;
- m->host[i].index = msr;
- m->host[i].value = host_val;
+ if (entry_only)
+ return;
+
+ if (j < 0) {
+ j = m->host.nr++;
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+ }
+ m->host.val[j].index = msr;
+ m->host.val[j].value = host_val;
}
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
- guest_efer, host_efer);
+ guest_efer, host_efer, false);
return false;
} else {
guest_efer &= ~ignore_bits;
msrs->misc_high);
msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA;
msrs->misc_low |=
+ MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
VMX_MISC_ACTIVITY_HLT;
msrs->misc_high = 0;
vmx->nested.msrs.misc_low = data;
vmx->nested.msrs.misc_high = data >> 32;
+
+ /*
+ * If L1 has read-only VM-exit information fields, use the
+ * less permissive vmx_vmwrite_bitmap to specify write
+ * permissions for the shadow VMCS.
+ */
+ if (enable_shadow_vmcs && !nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
+ vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
+
return 0;
}
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ /*
+ * Don't allow changes to the VMX capability MSRs while the vCPU
+ * is in VMX operation.
+ */
+ if (vmx->nested.vmxon)
+ return -EBUSY;
+
switch (msr_index) {
case MSR_IA32_VMX_BASIC:
return vmx_restore_vmx_basic(vmx, data);
vcpu->arch.ia32_xss = data;
if (vcpu->arch.ia32_xss != host_xss)
add_atomic_switch_msr(vmx, MSR_IA32_XSS,
- vcpu->arch.ia32_xss, host_xss);
+ vcpu->arch.ia32_xss, host_xss, false);
else
clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
break;
if (!loaded_vmcs->msr_bitmap)
goto out_vmcs;
memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+
+ if (IS_ENABLED(CONFIG_HYPERV) &&
+ static_branch_unlikely(&enable_evmcs) &&
+ (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+ struct hv_enlightened_vmcs *evmcs =
+ (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
+
+ evmcs->hv_enlightenments_control.msr_bitmap = 1;
+ }
}
return 0;
if (!cpu_has_vmx_msr_bitmap())
return;
+ if (static_branch_unlikely(&enable_evmcs))
+ evmcs_touch_msr_bitmap();
+
/*
* 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.
if (!cpu_has_vmx_msr_bitmap())
return;
+ if (static_branch_unlikely(&enable_evmcs))
+ evmcs_touch_msr_bitmap();
+
/*
* 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.
VMX_EPT_MISCONFIG_WX_VALUE);
}
+static bool vmx_l1d_use_msr_save_list(void)
+{
+ if (!enable_ept || !boot_cpu_has_bug(X86_BUG_L1TF) ||
+ static_cpu_has(X86_FEATURE_HYPERVISOR) ||
+ !static_cpu_has(X86_FEATURE_FLUSH_L1D))
+ return false;
+
+ return vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+}
+
#define VMX_XSS_EXIT_BITMAP 0
/*
* Sets up the vmcs for emulated real mode.
int i;
if (enable_shadow_vmcs) {
+ /*
+ * At vCPU creation, "VMWRITE to any supported field
+ * in the VMCS" is supported, so use the more
+ * permissive vmx_vmread_bitmap to specify both read
+ * and write permissions for the shadow VMCS.
+ */
vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
- vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
+ vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmread_bitmap));
}
if (cpu_has_vmx_msr_bitmap())
vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
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_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
}
+ /*
+ * If flushing the L1D cache on every VMENTER is enforced and the
+ * MSR is available, use the MSR save list.
+ */
+ if (vmx_l1d_use_msr_save_list())
+ add_atomic_switch_msr(vmx, MSR_IA32_FLUSH_CMD, L1D_FLUSH, 0, true);
}
static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
- sizeof(*vmpointer), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
return 1;
}
+ /* CPL=0 must be checked manually. */
+ if (vmx_get_cpl(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
if (vmx->nested.vmxon) {
nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
return kvm_skip_emulated_instruction(vcpu);
*/
static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
{
+ if (vmx_get_cpl(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
if (!to_vmx(vcpu)->nested.vmxon) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 0;
}
+/*
+ * Copy the writable VMCS shadow fields back to the VMCS12, in case
+ * they have been modified by the L1 guest. Note that the "read-only"
+ * VM-exit information fields are actually writable if the vCPU is
+ * configured to support "VMWRITE to any supported field in the VMCS."
+ */
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
{
- int i;
+ const u16 *fields[] = {
+ shadow_read_write_fields,
+ shadow_read_only_fields
+ };
+ const int max_fields[] = {
+ max_shadow_read_write_fields,
+ max_shadow_read_only_fields
+ };
+ int i, q;
unsigned long field;
u64 field_value;
struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
- const u16 *fields = shadow_read_write_fields;
- const int num_fields = max_shadow_read_write_fields;
preempt_disable();
vmcs_load(shadow_vmcs);
- for (i = 0; i < num_fields; i++) {
- field = fields[i];
- field_value = __vmcs_readl(field);
- vmcs12_write_any(&vmx->vcpu, field, field_value);
+ for (q = 0; q < ARRAY_SIZE(fields); q++) {
+ for (i = 0; i < max_fields[q]; i++) {
+ field = fields[q][i];
+ field_value = __vmcs_readl(field);
+ vmcs12_write_any(&vmx->vcpu, field, field_value);
+ }
+ /*
+ * Skip the VM-exit information fields if they are read-only.
+ */
+ if (!nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
+ break;
}
vmcs_clear(shadow_vmcs);
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, true, &gva))
return 1;
- /* _system ok, as hardware has verified cpl=0 */
- kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
- &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
+ /* _system ok, nested_vmx_check_permission has verified cpl=0 */
+ kvm_write_guest_virt_system(vcpu, gva, &field_value,
+ (is_long_mode(vcpu) ? 8 : 4), NULL);
}
nested_vmx_succeed(vcpu);
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
- &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &field_value,
+ (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
- if (vmcs_field_readonly(field)) {
+ /*
+ * If the vCPU supports "VMWRITE to any supported field in the
+ * 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,
VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
return kvm_skip_emulated_instruction(vcpu);
if (get_vmx_mem_address(vcpu, exit_qualification,
vmx_instruction_info, true, &vmcs_gva))
return 1;
- /* ok to use *_system, as hardware has verified cpl=0 */
- if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
- (void *)&to_vmx(vcpu)->nested.current_vmptr,
- sizeof(u64), &e)) {
+ /* *_system ok, nested_vmx_check_permission has verified cpl=0 */
+ if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
+ (void *)&to_vmx(vcpu)->nested.current_vmptr,
+ sizeof(u64), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
- sizeof(operand), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmx_instruction_info, false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
- sizeof(operand), &e)) {
+ if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
switch (type) {
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
- if (is_noncanonical_address(operand.gla, vcpu)) {
+ if (!operand.vpid ||
+ is_noncanonical_address(operand.gla, vcpu)) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
return kvm_skip_emulated_instruction(vcpu);
}
- /* fall through */
+ if (cpu_has_vmx_invvpid_individual_addr() &&
+ vmx->nested.vpid02) {
+ __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
+ vmx->nested.vpid02, operand.gla);
+ } else
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ break;
case VMX_VPID_EXTENT_SINGLE_CONTEXT:
case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
if (!operand.vpid) {
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
return kvm_skip_emulated_instruction(vcpu);
}
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
break;
case VMX_VPID_EXTENT_ALL_CONTEXT:
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
break;
default:
WARN_ON_ONCE(1);
return kvm_skip_emulated_instruction(vcpu);
}
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
case EXIT_REASON_TPR_BELOW_THRESHOLD:
return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
case EXIT_REASON_APIC_ACCESS:
- return nested_cpu_has2(vmcs12,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
case EXIT_REASON_APIC_WRITE:
case EXIT_REASON_EOI_INDUCED:
- /* apic_write and eoi_induced should exit unconditionally. */
+ /*
+ * The controls for "virtualize APIC accesses," "APIC-
+ * register virtualization," and "virtual-interrupt
+ * delivery" only come from vmcs12.
+ */
return true;
case EXIT_REASON_EPT_VIOLATION:
/*
}
}
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
+{
+ int size = PAGE_SIZE << L1D_CACHE_ORDER;
+ bool always;
+
+ /*
+ * This code is only executed when:
+ * - the flush mode is 'cond'
+ * - the flush mode is 'always' and the flush MSR is not
+ * available
+ *
+ * If the CPU has the flush MSR then clear the flush bit because
+ * 'always' mode is handled via the MSR save list.
+ *
+ * If the MSR is not avaibable then act depending on the mitigation
+ * mode: If 'flush always', keep the flush bit set, otherwise clear
+ * it.
+ *
+ * The flush bit gets set again either from vcpu_run() or from one
+ * of the unsafe VMEXIT handlers.
+ */
+ if (static_cpu_has(X86_FEATURE_FLUSH_L1D))
+ always = false;
+ else
+ always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+
+ vcpu->arch.l1tf_flush_l1d = always;
+
+ vcpu->stat.l1d_flush++;
+
+ if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+ wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ return;
+ }
+
+ asm volatile(
+ /* First ensure the pages are in the TLB */
+ "xorl %%eax, %%eax\n"
+ ".Lpopulate_tlb:\n\t"
+ "movzbl (%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+ "addl $4096, %%eax\n\t"
+ "cmpl %%eax, %[size]\n\t"
+ "jne .Lpopulate_tlb\n\t"
+ "xorl %%eax, %%eax\n\t"
+ "cpuid\n\t"
+ /* Now fill the cache */
+ "xorl %%eax, %%eax\n"
+ ".Lfill_cache:\n"
+ "movzbl (%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+ "addl $64, %%eax\n\t"
+ "cmpl %%eax, %[size]\n\t"
+ "jne .Lfill_cache\n\t"
+ "lfence\n"
+ :: [empty_zp] "r" (vmx_l1d_flush_pages),
+ [size] "r" (size)
+ : "eax", "ebx", "ecx", "edx");
+}
+
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
vmcs_write32(TPR_THRESHOLD, irr);
}
-static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
{
u32 sec_exec_control;
+ if (!lapic_in_kernel(vcpu))
+ return;
+
/* Postpone execution until vmcs01 is the current VMCS. */
if (is_guest_mode(vcpu)) {
- to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
return;
}
- if (!cpu_has_vmx_virtualize_x2apic_mode())
- return;
-
if (!cpu_need_tpr_shadow(vcpu))
return;
sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+ sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
- if (set) {
- sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
- } else {
- sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
- sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmx_flush_tlb(vcpu, true);
+ switch (kvm_get_apic_mode(vcpu)) {
+ case LAPIC_MODE_INVALID:
+ WARN_ONCE(true, "Invalid local APIC state");
+ case LAPIC_MODE_DISABLED:
+ break;
+ case LAPIC_MODE_XAPIC:
+ if (flexpriority_enabled) {
+ sec_exec_control |=
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmx_flush_tlb(vcpu, true);
+ }
+ break;
+ case LAPIC_MODE_X2APIC:
+ if (cpu_has_vmx_virtualize_x2apic_mode())
+ sec_exec_control |=
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+ break;
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- /*
- * Currently we do not handle the nested case where L2 has an
- * APIC access page of its own; that page is still pinned.
- * Hence, we skip the case where the VCPU is in guest mode _and_
- * L1 prepared an APIC access page for L2.
- *
- * For the case where L1 and L2 share the same APIC access page
- * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear
- * in the vmcs12), this function will only update either the vmcs01
- * or the vmcs02. If the former, the vmcs02 will be updated by
- * prepare_vmcs02. If the latter, the vmcs01 will be updated in
- * the next L2->L1 exit.
- */
- if (!is_guest_mode(vcpu) ||
- !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ if (!is_guest_mode(vcpu)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
vmx_flush_tlb(vcpu, true);
}
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
+ vcpu->arch.l1tf_flush_l1d = true;
}
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
clear_atomic_switch_msr(vmx, msrs[i].msr);
else
add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
- msrs[i].host);
+ msrs[i].host, false);
}
static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
(unsigned long)¤t_evmcs->host_rsp : 0;
+ if (static_branch_unlikely(&vmx_l1d_should_flush)) {
+ if (vcpu->arch.l1tf_flush_l1d)
+ vmx_l1d_flush(vcpu);
+ }
+
asm(
/* Store host registers */
"push %%" _ASM_DX "; push %%" _ASM_BP ";"
static struct kvm *vmx_vm_alloc(void)
{
- struct kvm_vmx *kvm_vmx = kzalloc(sizeof(struct kvm_vmx), GFP_KERNEL);
+ struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx));
return &kvm_vmx->kvm;
}
static void vmx_vm_free(struct kvm *kvm)
{
- kfree(to_kvm_vmx(kvm));
+ vfree(to_kvm_vmx(kvm));
}
static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
return ERR_PTR(err);
}
+#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+
static int vmx_vm_init(struct kvm *kvm)
{
if (!ple_gap)
kvm->arch.pause_in_guest = true;
+
+ if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
+ if (nosmt) {
+ pr_err(L1TF_MSG);
+ return -EOPNOTSUPP;
+ }
+ pr_warn(L1TF_MSG);
+ }
return 0;
}
vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
}
- } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) &&
- cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
- vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
- kvm_vcpu_reload_apic_access_page(vcpu);
}
if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
return 0;
}
-static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- bool from_vmentry)
+static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
* Set the MSR load/store lists to match L0's settings.
*/
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
set_cr4_guest_host_mask(vmx);
* is assigned to entry_failure_code on failure.
*/
static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- bool from_vmentry, u32 *entry_failure_code)
+ u32 *entry_failure_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control, vmcs12_exec_ctrl;
if (vmx->nested.dirty_vmcs12) {
- prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
+ prepare_vmcs02_full(vcpu, vmcs12);
vmx->nested.dirty_vmcs12 = false;
}
* HOST_FS_BASE, HOST_GS_BASE.
*/
- if (from_vmentry &&
+ if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
}
- if (from_vmentry) {
+ if (vmx->nested.nested_run_pending) {
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
vmcs12->vm_entry_intr_info_field);
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
~VM_ENTRY_IA32E_MODE) |
(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
- if (from_vmentry &&
+ if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
vcpu->arch.pat = vmcs12->guest_ia32_pat;
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
}
} else {
vmx_flush_tlb(vcpu, true);
vmx_set_cr4(vcpu, vmcs12->guest_cr4);
vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
- if (from_vmentry &&
+ if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
vcpu->arch.efer = vmcs12->guest_ia32_efer;
else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
return 0;
}
-static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
+static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
vcpu->arch.tsc_offset += vmcs12->tsc_offset;
r = EXIT_REASON_INVALID_STATE;
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+ if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
goto fail;
nested_get_vmcs12_pages(vcpu, vmcs12);
* the nested entry.
*/
- ret = enter_vmx_non_root_mode(vcpu, true);
- if (ret)
+ vmx->nested.nested_run_pending = 1;
+ ret = enter_vmx_non_root_mode(vcpu);
+ if (ret) {
+ vmx->nested.nested_run_pending = 0;
return ret;
+ }
+
+ /* Hide L1D cache contents from the nested guest. */
+ vmx->vcpu.arch.l1tf_flush_l1d = true;
/*
* If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
* by event injection, halt vcpu.
*/
if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
- !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK))
+ !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) {
+ vmx->nested.nested_run_pending = 0;
return kvm_vcpu_halt(vcpu);
-
- vmx->nested.nested_run_pending = 1;
-
+ }
return 1;
out:
load_vmcs12_mmu_host_state(vcpu, vmcs12);
- if (enable_vpid) {
- /*
- * Trivially support vpid by letting L2s share their parent
- * L1's vpid. TODO: move to a more elaborate solution, giving
- * each L2 its own vpid and exposing the vpid feature to L1.
- */
+ /*
+ * If vmcs01 don't use VPID, CPU flushes TLB on every
+ * VMEntry/VMExit. Thus, no need to flush TLB.
+ *
+ * If vmcs12 uses VPID, TLB entries populated by L2 are
+ * tagged with vmx->nested.vpid02 while L1 entries are tagged
+ * with vmx->vpid. Thus, no need to flush TLB.
+ *
+ * Therefore, flush TLB only in case vmcs01 uses VPID and
+ * vmcs12 don't use VPID as in this case L1 & L2 TLB entries
+ * are both tagged with vmx->vpid.
+ */
+ if (enable_vpid &&
+ !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) {
vmx_flush_tlb(vcpu, true);
}
vmx_segment_cache_clear(vmx);
/* Update any VMCS fields that might have changed while L2 ran */
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
if (vmx->hv_deadline_tsc == -1)
vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
- if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
- vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
- vmx_set_virtual_x2apic_mode(vcpu,
- vcpu->arch.apic_base & X2APIC_ENABLE);
+ if (vmx->nested.change_vmcs01_virtual_apic_mode) {
+ vmx->nested.change_vmcs01_virtual_apic_mode = false;
+ vmx_set_virtual_apic_mode(vcpu);
} else if (!nested_cpu_has_ept(vmcs12) &&
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
struct vcpu_vmx *vmx;
- u64 tscl, guest_tscl, delta_tsc;
+ u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
if (kvm_mwait_in_guest(vcpu->kvm))
return -EOPNOTSUPP;
tscl = rdtsc();
guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+ lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+
+ if (delta_tsc > lapic_timer_advance_cycles)
+ delta_tsc -= lapic_timer_advance_cycles;
+ else
+ delta_tsc = 0;
/* Convert to host delta tsc if tsc scaling is enabled */
if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
if (vmx->nested.smm.guest_mode) {
vcpu->arch.hflags &= ~HF_SMM_MASK;
- ret = enter_vmx_non_root_mode(vcpu, false);
+ ret = enter_vmx_non_root_mode(vcpu);
vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
.enable_nmi_window = enable_nmi_window,
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
- .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+ .set_virtual_apic_mode = vmx_set_virtual_apic_mode,
.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
.get_enable_apicv = vmx_get_enable_apicv,
.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
.enable_smi_window = enable_smi_window,
};
+static int __init vmx_setup_l1d_flush(void)
+{
+ struct page *page;
+
+ if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
+ !boot_cpu_has_bug(X86_BUG_L1TF) ||
+ vmx_l1d_use_msr_save_list())
+ return 0;
+
+ if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+ if (!page)
+ return -ENOMEM;
+ vmx_l1d_flush_pages = page_address(page);
+ }
+
+ static_branch_enable(&vmx_l1d_should_flush);
+ return 0;
+}
+
+static void vmx_free_l1d_flush_pages(void)
+{
+ if (vmx_l1d_flush_pages) {
+ free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+ vmx_l1d_flush_pages = NULL;
+ }
+}
+
static int __init vmx_init(void)
{
int r;
}
#endif
- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
- __alignof__(struct vcpu_vmx), THIS_MODULE);
+ r = vmx_setup_l1d_flush();
if (r)
return r;
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
+ if (r) {
+ vmx_free_l1d_flush_pages();
+ return r;
+ }
+
#ifdef CONFIG_KEXEC_CORE
rcu_assign_pointer(crash_vmclear_loaded_vmcss,
crash_vmclear_local_loaded_vmcss);
#endif
+ vmx_check_vmcs12_offsets();
return 0;
}
static_branch_disable(&enable_evmcs);
}
#endif
+ vmx_free_l1d_flush_pages();
}
module_init(vmx_init)