diff mbox series

[v3,23/25] KVM: nVMX: Use sanitized allowed-1 bits for VMX control MSRs

Message ID 20220708144223.610080-24-vkuznets@redhat.com (mailing list archive)
State New, archived
Headers show
Series KVM: VMX: Support updated eVMCSv1 revision + use vmcs_config for L1 VMX MSRs | expand

Commit Message

Vitaly Kuznetsov July 8, 2022, 2:42 p.m. UTC 
Using raw host MSR values for setting up nested VMX control MSRs is
incorrect as some features need to disabled, e.g. when KVM runs as
a nested hypervisor on Hyper-V and uses Enlightened VMCS or when a
workaround for IA32_PERF_GLOBAL_CTRL is applied. For non-nested VMX, this
is done in setup_vmcs_config() and the result is stored in vmcs_config.
Use it for setting up allowed-1 bits in nested VMX MSRs too.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 30 ++++++++++++------------------
 arch/x86/kvm/vmx/nested.h |  2 +-
 arch/x86/kvm/vmx/vmx.c    |  5 ++---
 3 files changed, 15 insertions(+), 22 deletions(-)

Comments

Maxim Levitsky July 12, 2022, 12:11 p.m. UTC | #1 
On Fri, 2022-07-08 at 16:42 +0200, Vitaly Kuznetsov wrote:
> Using raw host MSR values for setting up nested VMX control MSRs is
> incorrect as some features need to disabled, e.g. when KVM runs as
> a nested hypervisor on Hyper-V and uses Enlightened VMCS or when a
> workaround for IA32_PERF_GLOBAL_CTRL is applied. For non-nested VMX, this
> is done in setup_vmcs_config() and the result is stored in vmcs_config.
> Use it for setting up allowed-1 bits in nested VMX MSRs too.
> 
> Suggested-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> ---
>  arch/x86/kvm/vmx/nested.c | 30 ++++++++++++------------------
>  arch/x86/kvm/vmx/nested.h |  2 +-
>  arch/x86/kvm/vmx/vmx.c    |  5 ++---
>  3 files changed, 15 insertions(+), 22 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index 09654d5c2144..3d386c663fac 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -6565,8 +6565,10 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void)
>   * bit in the high half is on if the corresponding bit in the control field
>   * may be on. See also vmx_control_verify().
>   */
> -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
> +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps)
>  {
> +       struct nested_vmx_msrs *msrs = &vmcs_conf->nested;
> +
>         /*
>          * Note that as a general rule, the high half of the MSRs (bits in
>          * the control fields which may be 1) should be initialized by the
> @@ -6583,11 +6585,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
>          */
>  
>         /* pin-based controls */
> -       rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
> -               msrs->pinbased_ctls_low,
> -               msrs->pinbased_ctls_high);
>         msrs->pinbased_ctls_low =
>                 PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
> +
> +       msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl;
>         msrs->pinbased_ctls_high &=
>                 PIN_BASED_EXT_INTR_MASK |
>                 PIN_BASED_NMI_EXITING |
> @@ -6598,12 +6599,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
>                 PIN_BASED_VMX_PREEMPTION_TIMER;
>  
>         /* exit controls */
> -       rdmsr(MSR_IA32_VMX_EXIT_CTLS,
> -               msrs->exit_ctls_low,
> -               msrs->exit_ctls_high);
>         msrs->exit_ctls_low =
>                 VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
>  
> +       msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl;
>         msrs->exit_ctls_high &=
>  #ifdef CONFIG_X86_64
>                 VM_EXIT_HOST_ADDR_SPACE_SIZE |
> @@ -6619,11 +6618,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
>         msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
>  
>         /* entry controls */
> -       rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
> -               msrs->entry_ctls_low,
> -               msrs->entry_ctls_high);
>         msrs->entry_ctls_low =
>                 VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
> +
> +       msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl;
>         msrs->entry_ctls_high &=
>  #ifdef CONFIG_X86_64
>                 VM_ENTRY_IA32E_MODE |
> @@ -6637,11 +6635,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
>         msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
>  
>         /* cpu-based controls */
> -       rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
> -               msrs->procbased_ctls_low,
> -               msrs->procbased_ctls_high);
>         msrs->procbased_ctls_low =
>                 CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
> +
> +       msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl;
>         msrs->procbased_ctls_high &=
>                 CPU_BASED_INTR_WINDOW_EXITING |
>                 CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
> @@ -6675,12 +6672,9 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
>          * depend on CPUID bits, they are added later by
>          * vmx_vcpu_after_set_cpuid.
>          */
> -       if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
> -               rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
> -                     msrs->secondary_ctls_low,
> -                     msrs->secondary_ctls_high);
> -
>         msrs->secondary_ctls_low = 0;
> +
> +       msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl;
>         msrs->secondary_ctls_high &=
>                 SECONDARY_EXEC_DESC |
>                 SECONDARY_EXEC_ENABLE_RDTSCP |
> diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
> index c92cea0b8ccc..fae047c6204b 100644
> --- a/arch/x86/kvm/vmx/nested.h
> +++ b/arch/x86/kvm/vmx/nested.h
> @@ -17,7 +17,7 @@ enum nvmx_vmentry_status {
>  };
>  
>  void vmx_leave_nested(struct kvm_vcpu *vcpu);
> -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
> +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps);
>  void nested_vmx_hardware_unsetup(void);
>  __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
>  void nested_vmx_set_vmcs_shadowing_bitmap(void);
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index e462e5b9c0a1..35285109856f 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -7306,7 +7306,7 @@ static int __init vmx_check_processor_compat(void)
>         if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
>                 return -EIO;
>         if (nested)
> -               nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
> +               nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept);
>         if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
>                 printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
>                                 smp_processor_id());
> @@ -8281,8 +8281,7 @@ static __init int hardware_setup(void)
>         setup_default_sgx_lepubkeyhash();
>  
>         if (nested) {
> -               nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
> -                                          vmx_capability.ept);
> +               nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept);
>  
>                 r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
>                 if (r)


Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>

Best regards,
	Maxim Levitsky
diff mbox series

Patch

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 09654d5c2144..3d386c663fac 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6565,8 +6565,10 @@  static u64 nested_vmx_calc_vmcs_enum_msr(void)
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
+void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps)
 {
+	struct nested_vmx_msrs *msrs = &vmcs_conf->nested;
+
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in
 	 * the control fields which may be 1) should be initialized by the
@@ -6583,11 +6585,10 @@  void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	 */
 
 	/* pin-based controls */
-	rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
-		msrs->pinbased_ctls_low,
-		msrs->pinbased_ctls_high);
 	msrs->pinbased_ctls_low =
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+
+	msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl;
 	msrs->pinbased_ctls_high &=
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
@@ -6598,12 +6599,10 @@  void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 		PIN_BASED_VMX_PREEMPTION_TIMER;
 
 	/* exit controls */
-	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
-		msrs->exit_ctls_low,
-		msrs->exit_ctls_high);
 	msrs->exit_ctls_low =
 		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
 
+	msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl;
 	msrs->exit_ctls_high &=
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
@@ -6619,11 +6618,10 @@  void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
 
 	/* entry controls */
-	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
-		msrs->entry_ctls_low,
-		msrs->entry_ctls_high);
 	msrs->entry_ctls_low =
 		VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+
+	msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl;
 	msrs->entry_ctls_high &=
 #ifdef CONFIG_X86_64
 		VM_ENTRY_IA32E_MODE |
@@ -6637,11 +6635,10 @@  void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
 
 	/* cpu-based controls */
-	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
-		msrs->procbased_ctls_low,
-		msrs->procbased_ctls_high);
 	msrs->procbased_ctls_low =
 		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+
+	msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl;
 	msrs->procbased_ctls_high &=
 		CPU_BASED_INTR_WINDOW_EXITING |
 		CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
@@ -6675,12 +6672,9 @@  void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	 * depend on CPUID bits, they are added later by
 	 * vmx_vcpu_after_set_cpuid.
 	 */
-	if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
-		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
-		      msrs->secondary_ctls_low,
-		      msrs->secondary_ctls_high);
-
 	msrs->secondary_ctls_low = 0;
+
+	msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl;
 	msrs->secondary_ctls_high &=
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_ENABLE_RDTSCP |
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index c92cea0b8ccc..fae047c6204b 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -17,7 +17,7 @@  enum nvmx_vmentry_status {
 };
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
+void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e462e5b9c0a1..35285109856f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7306,7 +7306,7 @@  static int __init vmx_check_processor_compat(void)
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -8281,8 +8281,7 @@  static __init int hardware_setup(void)
 	setup_default_sgx_lepubkeyhash();
 
 	if (nested) {
-		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept);
+		nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)