From: Sean Christopherson seanjc@google.com Sent: Wednesday, January 5, 2022 3:35 AM
On Wed, Dec 29, 2021, Yang Zhong wrote:
From: Jing Liu jing2.liu@intel.com
Disable read emulation of IA32_XFD_ERR MSR if guest cpuid includes XFD. This saves one unnecessary VM-exit in guest #NM handler, given that the MSR is already restored with the guest value before the guest is resumed.
Suggested-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Jing Liu jing2.liu@intel.com Signed-off-by: Yang Zhong yang.zhong@intel.com
arch/x86/kvm/vmx/vmx.c | 6 ++++++ arch/x86/kvm/vmx/vmx.h | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4e51de876085..638665b3e241 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -162,6 +162,7 @@ static u32
vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE,
- MSR_IA32_XFD_ERR,
#endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, @@ -7228,6 +7229,11 @@ static void vmx_vcpu_after_set_cpuid(struct
kvm_vcpu *vcpu)
}}
- if (boot_cpu_has(X86_FEATURE_XFD))
This should be kvm_cpu_cap_has(), not boot_cpu_has(). If 32-bit kernels don't suppress XFD in boot_cpu_data, then using boot_cpus_has() is wrong. And even if XFD is suppressed, using kvm_cpu_cap_has() is still preferable.
Make sense.