@@ -191,6 +191,7 @@ int set_tsc_mode(unsigned int val)
}
DEFINE_PER_CPU(u64, msr_misc_features_shadow);
+EXPORT_PER_CPU_SYMBOL_GPL(msr_misc_features_shadow);
static void set_cpuid_faulting(bool on)
{
@@ -1064,6 +1064,9 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
vmx->loaded_cpu_state = vmx->loaded_vmcs;
host_state = &vmx->loaded_cpu_state->host_state;
+ if (this_cpu_read(msr_misc_features_shadow))
+ wrmsrl(MSR_MISC_FEATURES_ENABLES, 0ULL);
+
/*
* Set host fs and gs selectors. Unfortunately, 22.2.3 does not
* allow segment selectors with cpl > 0 or ti == 1.
@@ -1123,6 +1126,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
{
struct vmcs_host_state *host_state;
+ u64 msrval;
if (!vmx->loaded_cpu_state)
return;
@@ -1133,6 +1137,10 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
++vmx->vcpu.stat.host_state_reload;
vmx->loaded_cpu_state = NULL;
+ msrval = this_cpu_read(msr_misc_features_shadow);
+ if (msrval)
+ wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
+
#ifdef CONFIG_X86_64
rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
There are two defined bits in MSR_MISC_FEATURES_ENABLES, bit 0 for cpuid faulting and bit 1 for ring3mwait. == cpuid Faulting == cpuid faulting is a feature about CPUID instruction. When cpuid faulting is enabled, all execution of the CPUID instruction outside system-management mode (SMM) cause a general-protection (#GP) if the CPL > 0. About this feature, detailed information can be found at https://www.intel.com/content/dam/www/public/us/en/documents/application-notes/virtualization-technology-flexmigration-application-note.pdf Current KVM provides software emulation of this feature for guest. However, because cpuid faulting takes higher priority over CPUID vm exit (Intel SDM vol3.25.1.1), there is a risk of leaking cpuid faulting to guest when host enables it. If host enables cpuid faulting by setting the bit 0 of MSR_MISC_FEATURES_ENABLES, it will pass to guest since there is no switch of MSR_MISC_FEATURES_ENABLES yet. As a result, when guest calls CPUID instruction in CPL > 0, it will generate a #GP instead of CPUID vm eixt. This issue will cause guest boot failure when guest uses *modprobe* to load modules. *modprobe* calls CPUID instruction, thus causing #GP in guest. Since there is no handling of cpuid faulting in #GP handler, guest fails boot. == ring3mwait == Ring3mwait is a Xeon-Phi Product Family x200 series specific feature, which allows the MONITOR and MWAIT instructions to be executed in rings other than ring 0. The feature can be enabled by setting bit 1 in MSR_MISC_FEATURES_ENABLES. The register can also be read to determine whether the instructions are enabled at other than ring 0. About this feature, description can be found at https://software.intel.com/en-us/blogs/2016/10/06/intel-xeon-phi-product-family-x200-knl-user-mode-ring-3-monitor-and-mwait Current kvm doesn't expose feature ring3mwait to guest. However, there is also a risk of leaking ring3mwait to guest if host enables it since there is no switch of MSR_MISC_FEATURES_ENABLES. == solution == From above analysis, both cpuid faulting and ring3mwait can be leaked to guest. To fix this issue, MSR_MISC_FEATURES_ENABLES should be switched between host and guest. Since MSR_MISC_FEATURES_ENABLES is intel-specific, this patch implement the switching only in vmx. For the reason that kvm provides the software emulation of cpuid faulting and kvm doesn't expose ring3mwait to guest. MSR_MISC_FEATURES_ENABLES can be just cleared to zero for guest when any of the features is enabled in host. Signed-off-by: Xiaoyao Li <xiaoyao.li@linux.intel.com> --- arch/x86/kernel/process.c | 1 + arch/x86/kvm/vmx/vmx.c | 8 ++++++++ 2 files changed, 9 insertions(+)