Enlightened VMCS v1 got updated and now includes the required fields
for TSC scaling and loading PERF_GLOBAL_CTRL upon VMENTER/VMEXIT
features. For Hyper-V on KVM enablement, KVM can just observe VMX control
MSRs and use the features (with or without eVMCS) when
possible. Hyper-V on KVM case is trickier because of live migration:
the new features require explicit enablement from VMM to not break
it. Luckily, the updated eVMCS revision comes with a feature bit in
CPUID.0x4000000A.EBX.
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
arch/x86/kvm/hyperv.c | 2 +-
arch/x86/kvm/vmx/evmcs.c | 88 +++++++++++++++++++++++++++++++--------
arch/x86/kvm/vmx/evmcs.h | 17 ++------
arch/x86/kvm/vmx/nested.c | 2 +-
arch/x86/kvm/vmx/vmx.c | 2 +-
5 files changed, 78 insertions(+), 33 deletions(-)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 1098915360ae..8a2b24f9bbf6 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2552,7 +2552,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_NESTED_FEATURES:
ent->eax = evmcs_ver;
ent->eax |= HV_X64_NESTED_MSR_BITMAP;
-
+ ent->ebx |= HV_X64_NESTED_EVMCS1_2022_UPDATE;
break;
case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 8bea5dea0341..e8497f9854a1 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -368,7 +368,60 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
return 0;
}
-void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
+enum evmcs_revision {
+ EVMCSv1_2016,
+ EVMCSv1_2022,
+ EVMCS_REVISION_MAX,
+};
+
+enum evmcs_unsupported_ctrl_type {
+ EVMCS_EXIT_CTLS,
+ EVMCS_ENTRY_CTLS,
+ EVMCS_2NDEXEC,
+ EVMCS_PINCTRL,
+ EVMCS_VMFUNC,
+ EVMCS_CTRL_MAX,
+};
+
+static u32 evmcs_unsupported_ctls[EVMCS_CTRL_MAX][EVMCS_REVISION_MAX] = {
+ [EVMCS_EXIT_CTLS] = {
+ [EVMCSv1_2016] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
+ [EVMCSv1_2022] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL,
+ },
+ [EVMCS_ENTRY_CTLS] = {
+ [EVMCSv1_2016] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL | VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+ [EVMCSv1_2022] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL,
+ },
+ [EVMCS_2NDEXEC] = {
+ [EVMCSv1_2016] = EVMCS1_UNSUPPORTED_2NDEXEC | SECONDARY_EXEC_TSC_SCALING,
+ [EVMCSv1_2022] = EVMCS1_UNSUPPORTED_2NDEXEC,
+ },
+ [EVMCS_PINCTRL] = {
+ [EVMCSv1_2016] = EVMCS1_UNSUPPORTED_PINCTRL,
+ [EVMCSv1_2022] = EVMCS1_UNSUPPORTED_PINCTRL,
+ },
+ [EVMCS_VMFUNC] = {
+ [EVMCSv1_2016] = EVMCS1_UNSUPPORTED_VMFUNC,
+ [EVMCSv1_2022] = EVMCS1_UNSUPPORTED_VMFUNC,
+ },
+};
+
+static u32 evmcs_get_unsupported_ctls(struct kvm_vcpu *vcpu,
+ enum evmcs_unsupported_ctrl_type ctrl_type)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ enum evmcs_revision evmcs_rev = EVMCSv1_2016;
+
+ if (!hv_vcpu)
+ return 0;
+
+ if (hv_vcpu->cpuid_cache.nested_ebx & HV_X64_NESTED_EVMCS1_2022_UPDATE)
+ evmcs_rev = EVMCSv1_2022;
+
+ return evmcs_unsupported_ctls[ctrl_type][evmcs_rev];
+}
+
+void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
u32 ctl_low = (u32)*pdata;
u32 ctl_high = (u32)(*pdata >> 32);
@@ -380,72 +433,73 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
switch (msr_index) {
case MSR_IA32_VMX_EXIT_CTLS:
case MSR_IA32_VMX_TRUE_EXIT_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ ctl_high &= ~evmcs_get_unsupported_ctls(vcpu, EVMCS_EXIT_CTLS);
break;
case MSR_IA32_VMX_ENTRY_CTLS:
case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+ ctl_high &= ~evmcs_get_unsupported_ctls(vcpu, EVMCS_ENTRY_CTLS);
break;
case MSR_IA32_VMX_PROCBASED_CTLS2:
- ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+ ctl_high &= ~evmcs_get_unsupported_ctls(vcpu, EVMCS_2NDEXEC);
break;
case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
case MSR_IA32_VMX_PINBASED_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ ctl_high &= ~evmcs_get_unsupported_ctls(vcpu, EVMCS_PINCTRL);
break;
case MSR_IA32_VMX_VMFUNC:
- ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
+ ctl_low &= ~evmcs_get_unsupported_ctls(vcpu, EVMCS_VMFUNC);
break;
}
*pdata = ctl_low | ((u64)ctl_high << 32);
}
-int nested_evmcs_check_controls(struct vmcs12 *vmcs12)
+int nested_evmcs_check_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
int ret = 0;
u32 unsupp_ctl;
unsupp_ctl = vmcs12->pin_based_vm_exec_control &
- EVMCS1_UNSUPPORTED_PINCTRL;
+ evmcs_get_unsupported_ctls(vcpu, EVMCS_PINCTRL);
if (unsupp_ctl) {
trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported pin-based VM-execution controls",
+ "eVMCS: unsupported pin-based VM-execution controls: ",
unsupp_ctl);
ret = -EINVAL;
}
unsupp_ctl = vmcs12->secondary_vm_exec_control &
- EVMCS1_UNSUPPORTED_2NDEXEC;
+ evmcs_get_unsupported_ctls(vcpu, EVMCS_2NDEXEC);
if (unsupp_ctl) {
trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported secondary VM-execution controls",
+ "eVMCS: unsupported secondary VM-execution controls: ",
unsupp_ctl);
ret = -EINVAL;
}
unsupp_ctl = vmcs12->vm_exit_controls &
- EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ evmcs_get_unsupported_ctls(vcpu, EVMCS_EXIT_CTLS);
if (unsupp_ctl) {
trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-exit controls",
+ "eVMCS: unsupported VM-exit controls: ",
unsupp_ctl);
ret = -EINVAL;
}
unsupp_ctl = vmcs12->vm_entry_controls &
- EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+ evmcs_get_unsupported_ctls(vcpu, EVMCS_ENTRY_CTLS);
if (unsupp_ctl) {
trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-entry controls",
+ "eVMCS: unsupported VM-entry controls: ",
unsupp_ctl);
ret = -EINVAL;
}
- unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC;
+ unsupp_ctl = vmcs12->vm_function_control &
+ evmcs_get_unsupported_ctls(vcpu, EVMCS_VMFUNC);
if (unsupp_ctl) {
trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-function controls",
+ "eVMCS: unsupported VM-function controls: ",
unsupp_ctl);
ret = -EINVAL;
}
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index f886a8ff0342..4b809c79ae63 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -37,16 +37,9 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);
* EPTP_LIST_ADDRESS = 0x00002024,
* VMREAD_BITMAP = 0x00002026,
* VMWRITE_BITMAP = 0x00002028,
- *
- * TSC_MULTIPLIER = 0x00002032,
* PLE_GAP = 0x00004020,
* PLE_WINDOW = 0x00004022,
* VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
- * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
- * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
- *
- * Currently unsupported in KVM:
- * GUEST_IA32_RTIT_CTL = 0x00002814,
*/
#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \
PIN_BASED_VMX_PREEMPTION_TIMER)
@@ -58,12 +51,10 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);
SECONDARY_EXEC_ENABLE_PML | \
SECONDARY_EXEC_ENABLE_VMFUNC | \
SECONDARY_EXEC_SHADOW_VMCS | \
- SECONDARY_EXEC_TSC_SCALING | \
SECONDARY_EXEC_PAUSE_LOOP_EXITING)
#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \
- (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \
- VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
-#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
+#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0)
#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
struct evmcs_field {
@@ -243,7 +234,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa);
uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
-void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata);
-int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
+void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+int nested_evmcs_check_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12);
#endif /* __KVM_X86_VMX_EVMCS_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 270a1d8e4a6e..edb2f9c74d71 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2895,7 +2895,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
return -EINVAL;
if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled)
- return nested_evmcs_check_controls(vmcs12);
+ return nested_evmcs_check_controls(vcpu, vmcs12);
return 0;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d7f8331d6f7e..bd6f8552102a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1933,7 +1933,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
*/
if (!msr_info->host_initiated &&
vmx->nested.enlightened_vmcs_enabled)
- nested_evmcs_filter_control_msr(msr_info->index,
+ nested_evmcs_filter_control_msr(vcpu, msr_info->index,
&msr_info->data);
break;
case MSR_IA32_RTIT_CTL:
--
2.35.3
