| Message ID | 20210409064345.31497-2-weijiang.yang@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | CET fix patches for nested guest | expand |
On Fri, Apr 09, 2021, Yang Weijiang wrote: > These fields are rarely updated by L1 QEMU/KVM, sync them when L1 is trying to > read/write them and after they're changed. If CET guest entry-load bit is not > set by L1 guest, migrate them to L2 manaully. > > Opportunistically remove one blank line in previous patch. > > Suggested-by: Sean Christopherson <seanjc@google.com> > Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> > --- > arch/x86/kvm/cpuid.c | 1 - > arch/x86/kvm/vmx/nested.c | 30 ++++++++++++++++++++++++++++++ > arch/x86/kvm/vmx/vmx.h | 3 +++ > 3 files changed, 33 insertions(+), 1 deletion(-) > > diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c > index d191de769093..8692f53b8cd0 100644 > --- a/arch/x86/kvm/cpuid.c > +++ b/arch/x86/kvm/cpuid.c > @@ -143,7 +143,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) > } > vcpu->arch.guest_supported_xss = > (((u64)best->edx << 32) | best->ecx) & supported_xss; > - > } else { > vcpu->arch.guest_supported_xss = 0; > } > diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c > index 9728efd529a1..87beb1c034e1 100644 > --- a/arch/x86/kvm/vmx/nested.c > +++ b/arch/x86/kvm/vmx/nested.c > @@ -2516,6 +2516,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) > vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); > > set_cr4_guest_host_mask(vmx); > + > + if (kvm_cet_supported() && vmx->nested.nested_run_pending && > + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) { > + vmcs_writel(GUEST_SSP, vmcs12->guest_ssp); > + vmcs_writel(GUEST_S_CET, vmcs12->guest_s_cet); > + vmcs_writel(GUEST_INTR_SSP_TABLE, vmcs12->guest_ssp_tbl); > + } > } > > /* > @@ -2556,6 +2563,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, > if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || > !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) > vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); > + > + if (kvm_cet_supported() && (!vmx->nested.nested_run_pending || > + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE))) { > + vmcs_writel(GUEST_SSP, vmx->nested.vmcs01_guest_ssp); > + vmcs_writel(GUEST_S_CET, vmx->nested.vmcs01_guest_s_cet); > + vmcs_writel(GUEST_INTR_SSP_TABLE, > + vmx->nested.vmcs01_guest_ssp_tbl); > + } > + > vmx_set_rflags(vcpu, vmcs12->guest_rflags); > > /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the > @@ -3375,6 +3391,11 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, > if (kvm_mpx_supported() && > !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) > vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); > + if (kvm_cet_supported() && !vmx->nested.nested_run_pending) { This needs to be: if (kvm_cet_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE))) otherwise the vmcs01_* members will be stale when emulating VM-Enter with vcmc12.vm_entry_controls.LOAD_CET_STATE=0. > + vmx->nested.vmcs01_guest_ssp = vmcs_readl(GUEST_SSP); > + vmx->nested.vmcs01_guest_s_cet = vmcs_readl(GUEST_S_CET); > + vmx->nested.vmcs01_guest_ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); > + }
On Tue, Apr 20, 2021 at 05:35:01PM +0000, Sean Christopherson wrote: > On Fri, Apr 09, 2021, Yang Weijiang wrote: > > These fields are rarely updated by L1 QEMU/KVM, sync them when L1 is trying to > > read/write them and after they're changed. If CET guest entry-load bit is not > > set by L1 guest, migrate them to L2 manaully. > > > > Opportunistically remove one blank line in previous patch. > > > > Suggested-by: Sean Christopherson <seanjc@google.com> > > Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> > > --- > > arch/x86/kvm/cpuid.c | 1 - > > arch/x86/kvm/vmx/nested.c | 30 ++++++++++++++++++++++++++++++ > > arch/x86/kvm/vmx/vmx.h | 3 +++ > > 3 files changed, 33 insertions(+), 1 deletion(-) > > > > vmx_set_rflags(vcpu, vmcs12->guest_rflags); > > > > /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the > > @@ -3375,6 +3391,11 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, > > if (kvm_mpx_supported() && > > !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) > > vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); > > + if (kvm_cet_supported() && !vmx->nested.nested_run_pending) { > > This needs to be: > > if (kvm_cet_supported() && (!vmx->nested.nested_run_pending || > !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE))) > > otherwise the vmcs01_* members will be stale when emulating VM-Enter with > vcmc12.vm_entry_controls.LOAD_CET_STATE=0. > Thanks Sean! Change is included in v6 patch series. > > + vmx->nested.vmcs01_guest_ssp = vmcs_readl(GUEST_SSP); > > + vmx->nested.vmcs01_guest_s_cet = vmcs_readl(GUEST_S_CET); > > + vmx->nested.vmcs01_guest_ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); > > + }
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d191de769093..8692f53b8cd0 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -143,7 +143,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) } vcpu->arch.guest_supported_xss = (((u64)best->edx << 32) | best->ecx) & supported_xss; - } else { vcpu->arch.guest_supported_xss = 0; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9728efd529a1..87beb1c034e1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2516,6 +2516,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); set_cr4_guest_host_mask(vmx); + + if (kvm_cet_supported() && vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) { + vmcs_writel(GUEST_SSP, vmcs12->guest_ssp); + vmcs_writel(GUEST_S_CET, vmcs12->guest_s_cet); + vmcs_writel(GUEST_INTR_SSP_TABLE, vmcs12->guest_ssp_tbl); + } } /* @@ -2556,6 +2563,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); + + if (kvm_cet_supported() && (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE))) { + vmcs_writel(GUEST_SSP, vmx->nested.vmcs01_guest_ssp); + vmcs_writel(GUEST_S_CET, vmx->nested.vmcs01_guest_s_cet); + vmcs_writel(GUEST_INTR_SSP_TABLE, + vmx->nested.vmcs01_guest_ssp_tbl); + } + vmx_set_rflags(vcpu, vmcs12->guest_rflags); /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the @@ -3375,6 +3391,11 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (kvm_mpx_supported() && !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + if (kvm_cet_supported() && !vmx->nested.nested_run_pending) { + vmx->nested.vmcs01_guest_ssp = vmcs_readl(GUEST_SSP); + vmx->nested.vmcs01_guest_s_cet = vmcs_readl(GUEST_S_CET); + vmx->nested.vmcs01_guest_ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); + } /* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4022,9 @@ static bool is_vmcs12_ext_field(unsigned long field) case GUEST_IDTR_BASE: case GUEST_PENDING_DBG_EXCEPTIONS: case GUEST_BNDCFGS: + case GUEST_SSP: + case GUEST_INTR_SSP_TABLE: + case GUEST_S_CET: return true; default: break; @@ -4052,6 +4076,12 @@ static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); if (kvm_mpx_supported()) vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + if (kvm_cet_supported() && (guest_cpuid_has(vcpu, X86_FEATURE_SHSTK) || + guest_cpuid_has(vcpu, X86_FEATURE_IBT))) { + vmcs12->guest_ssp = vmcs_readl(GUEST_SSP); + vmcs12->guest_s_cet = vmcs_readl(GUEST_S_CET); + vmcs12->guest_ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); + } vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9d3a557949ac..36dc4fdb0909 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -155,6 +155,9 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; u64 vmcs01_guest_bndcfgs; + u64 vmcs01_guest_ssp; + u64 vmcs01_guest_s_cet; + u64 vmcs01_guest_ssp_tbl; /* to migrate it to L1 if L2 writes to L1's CR8 directly */ int l1_tpr_threshold;
These fields are rarely updated by L1 QEMU/KVM, sync them when L1 is trying to read/write them and after they're changed. If CET guest entry-load bit is not set by L1 guest, migrate them to L2 manaully. Opportunistically remove one blank line in previous patch. Suggested-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Yang Weijiang <weijiang.yang@intel.com> --- arch/x86/kvm/cpuid.c | 1 - arch/x86/kvm/vmx/nested.c | 30 ++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/vmx.h | 3 +++ 3 files changed, 33 insertions(+), 1 deletion(-)