diff options
| -rw-r--r-- | Documentation/virtual/kvm/mmu.txt | 3 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx.c | 36 |
2 files changed, 25 insertions, 14 deletions
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index c59bd9bc41ef..4176ab076f1c 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -352,7 +352,8 @@ In the first case there are two additional complications: - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and - spte.nx=gpte.nx back. + spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when + shadow paging is in use. - if CR4.SMAP is disabled: since the page has been changed to a kernel page, it can not be reused when CR4.SMAP is enabled. We set CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 81cf77d2d5cf..917148620f49 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1718,26 +1718,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1748,16 +1753,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) |