CET fix patches for nested guest
v3 cover CET fix patches for nested guest
This patch series is to fix a few issues found during nested guest testing on Linux, also including a patch to explictly disable CET support in nested guest over Hyper-V(s).
Yang Weijiang (3):
KVM: nVMX: Sync L2 guest CET states between L1/L2
KVM: nVMX: Set X86_CR4_CET in cr4_fixed1_bits if CET IBT is enabled
KVM: nVMX: Add CET entry/exit load bits to evmcs unsupported list
arch/x86/kvm/cpuid.c | 1 - arch/x86/kvm/vmx/evmcs.c | 4 ++-- arch/x86/kvm/vmx/evmcs.h | 6 ++++-- arch/x86/kvm/vmx/nested.c | 30 ++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/vmx.c | 1 + arch/x86/kvm/vmx/vmx.h | 3 +++ 6 files changed, 40 insertions(+), 5 deletions(-)
Signature · 1 line
2.26.2
PATCH v3 1/3 KVM: nVMX: Sync L2 guest CET states between L1/L2
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.
--- 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(-)
arch/x86/kvm/cpuid.c +0 -1
@@ -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 ; }
arch/x86/kvm/vmx/nested.c +30 -0
@@ -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 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) { + 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 +4023,9 @@ 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 +4077,11 @@ 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 ()) { + 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; }
arch/x86/kvm/vmx/vmx.h +3 -0
@@ -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;
Signature · 1 line
2.26.2
Re: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
Quoted 17 lines · Yang Weijiang
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.
Suggested-by Sean Christopherson <[email protected]>Signed-off-by Yang Weijiang <[email protected]>--- 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(-)arch/x86/kvm/cpuid.c +0
-0
arch/x86/kvm/cpuid.c void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) · line 146
Quoted 4 lines
arch/x86/kvm/cpuid.c +0
-1@@ -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; -
Nitpick: stray change?
Quoted 86 lines
arch/x86/kvm/cpuid.c +0
-0}else { vcpu->arch.guest_supported_xss =0 ; }arch/x86/kvm/vmx/nested.c +30
-0@@ -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 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) { + 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 +4023,9 @@ 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 +4077,11 @@ 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 ()) { + 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;
Signature · 1 line
Vitaly
Re: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
Quoted 14 lines · Vitaly Kuznetsov
Quoted 12 lines · Yang Weijiang
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.
Suggested-by Sean Christopherson <[email protected]>Signed-off-by Yang Weijiang <[email protected]>--- 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(-)
Quoted 11 lines
arch/x86/kvm/cpuid.c void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) · line 146
Quoted 9 lines
arch/x86/kvm/cpuid.c +0
-1@@ -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; -Nitpick: stray change?
Yes, I should keep the change log in V2 :-)
Quoted 90 lines
Quoted 87 lines
arch/x86/kvm/cpuid.c +0
-0}else { vcpu->arch.guest_supported_xss =0 ; }arch/x86/kvm/vmx/nested.c +30
-0@@ -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 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) { + 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 +4023,9 @@ 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 +4077,11 @@ 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 ()) { + 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
Vitaly
Sean Christopherson
maintainerRe: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
In reply to Yang Weijiangarch/x86/kvm/vmx/nested.c enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, · line 3395
Quoted 6 lines · Yang Weijiang
arch/x86/kvm/vmx/nested.c +2
-0@@ -3375,6 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) {
Alignment.
Quoted 18 lines
arch/x86/kvm/vmx/nested.c +7
-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 ); + }/* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4023,9 @@ 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 ;
arch/x86/kvm/vmx/nested.c static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, · line 4080
Quoted 4 lines
arch/x86/kvm/vmx/nested.c +1
-0@@ -4052,6 +4077,11 @@ 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 ()) {
Isn't the existing kvm_mpx_supported() check wrong in the sense that KVM only needs to sync to vmcs12 if KVM and the guest both support MPX? Same would apply to CET. Not sure it'd be a net positive in terms of performance since guest_cpuid_has() can be quite slow, but overwriting vmcs12 fields that technically don't exist feels wrong.
Quoted 24 lines
arch/x86/kvm/vmx/nested.c +4
-0+ 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
2.26.2
Re: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
Quoted 27 lines · Sean Christopherson
arch/x86/kvm/vmx/nested.c enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, · line 3395
Quoted 6 lines · Yang Weijiang
arch/x86/kvm/vmx/nested.c +2
-0@@ -3375,6 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) {Alignment.
Quoted 17 lines
arch/x86/kvm/vmx/nested.c +7
-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 ); + }/* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4023,9 @@ 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 ;
Quoted 8 lines
arch/x86/kvm/vmx/nested.c static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, · line 4080
Quoted 5 lines
arch/x86/kvm/vmx/nested.c +1
-0@@ -4052,6 +4077,11 @@ 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 ()) {Isn't the existing
kvm_mpx_supported()check wrong in the sense that KVM only needs to sync to vmcs12 if KVM and the guest both support MPX?
For MPX, if guest_cpuid_has() is not efficent, can it be checked by BNDCFGS EN bit? E.g.:
if (kvm_mpx_supported() && (vmcs12->guest_bndcfgs & 1))
Quoted 3 lines
Same would apply to CET. Not sure it'd be a net positive in terms of performance since
guest_cpuid_has()can be quite slow, but overwriting vmcs12 fields that technically don't exist feels wrong.
For CET, can we get equivalent effect by checking vmcs12->guest_cr4.CET? E.g.:
if (kvm_cet_supported() && (vmcs12->guest_cr4 & X86_CR4_CET))
Quoted 25 lines
Quoted 25 lines
arch/x86/kvm/vmx/nested.c +4
-0+ 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
2.26.2
Re: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
On Mon, Mar 08, 2021 at 04:01:09PM +0800, Yang Weijiang wrote:
Hi, Sean,
Any comments for below change?
Quoted 75 lines · Sean Christopherson
Quoted 27 lines · Yang Weijiang
arch/x86/kvm/vmx/nested.c enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, · line 3395
Quoted 6 lines
arch/x86/kvm/vmx/nested.c +2
-0@@ -3375,6 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) {Alignment.
Quoted 17 lines
arch/x86/kvm/vmx/nested.c +7
-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 ); + }/* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4023,9 @@ 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 ;Quoted 8 lines
arch/x86/kvm/vmx/nested.c static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, · line 4080
Quoted 5 lines
arch/x86/kvm/vmx/nested.c +1
-0@@ -4052,6 +4077,11 @@ 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 ()) {Isn't the existing
kvm_mpx_supported()check wrong in the sense that KVM only needs to sync to vmcs12 if KVM and the guest both support MPX?For MPX, if
guest_cpuid_has()is not efficent, can it be checked by BNDCFGS EN bit? E.g.:if (
kvm_mpx_supported()&& (vmcs12->guest_bndcfgs& 1))Quoted 3 lines
Same would apply to CET. Not sure it'd be a net positive in terms of performance since
guest_cpuid_has()can be quite slow, but overwriting vmcs12 fields that technically don't exist feels wrong.For CET, can we get equivalent effect by checking
vmcs12->guest_cr4.CET? E.g.:
if (kvm_cet_supported()&& (vmcs12->guest_cr4&X86_CR4_CET))Quoted 25 lines
Quoted 25 lines
arch/x86/kvm/vmx/nested.c +4
-0+ 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
2.26.2
Sean Christopherson
maintainerRe: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
In reply to Yang WeijiangQuoted 42 lines · Yang Weijiang
Quoted 27 lines · Sean Christopherson
arch/x86/kvm/vmx/nested.c enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, · line 3395
Quoted 6 lines · Yang Weijiang
arch/x86/kvm/vmx/nested.c +2
-0@@ -3375,6 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) {Alignment.
Quoted 17 lines
arch/x86/kvm/vmx/nested.c +7
-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 ); + }/* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4023,9 @@ 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 ;Quoted 8 lines
arch/x86/kvm/vmx/nested.c static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, · line 4080
Quoted 5 lines
arch/x86/kvm/vmx/nested.c +1
-0@@ -4052,6 +4077,11 @@ 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 ()) {Isn't the existing
kvm_mpx_supported()check wrong in the sense that KVM only needs to sync to vmcs12 if KVM and the guest both support MPX?For MPX, if
guest_cpuid_has()is not efficent, can it be checked by BNDCFGS EN bit? E.g.:if (
kvm_mpx_supported()&& (vmcs12->guest_bndcfgs& 1))
Quoted 7 lines
Quoted 3 lines
Same would apply to CET. Not sure it'd be a net positive in terms of performance since
guest_cpuid_has()can be quite slow, but overwriting vmcs12 fields that technically don't exist feels wrong.For CET, can we get equivalent effect by checking
vmcs12->guest_cr4.CET? E.g.:
if (kvm_cet_supported()&& (vmcs12->guest_cr4&X86_CR4_CET))
No, because the existence of the fields does not depend on them being enabled. E.g. things will go sideways if the values change while L2 is running, L2 disables CET, and then an exit occurs.
This is already a slow path, maybe the guest_cpuid_has() checks are a non-issue.
Quoted 26 lines
Quoted 26 lines
Quoted 26 lines
arch/x86/kvm/vmx/nested.c +4
-0+ 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
2.26.2
Re: [PATCH v3 1/3] KVM: nVMX: Sync L2 guest CET states between L1/L2
Quoted 51 lines · Sean Christopherson
Quoted 42 lines · Yang Weijiang
Quoted 27 lines · Sean Christopherson
arch/x86/kvm/vmx/nested.c enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, · line 3395
Quoted 6 lines · Yang Weijiang
arch/x86/kvm/vmx/nested.c +2
-0@@ -3375,6 +3391,12 @@ 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 () && + !(vmcs12->vm_entry_controls &VM_ENTRY_LOAD_CET_STATE )) {Alignment.
Quoted 17 lines
arch/x86/kvm/vmx/nested.c +7
-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 ); + }/* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* @@ -4001,6 +4023,9 @@ 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 ;Quoted 8 lines
arch/x86/kvm/vmx/nested.c static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, · line 4080
Quoted 5 lines
arch/x86/kvm/vmx/nested.c +1
-0@@ -4052,6 +4077,11 @@ 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 ()) {Isn't the existing
kvm_mpx_supported()check wrong in the sense that KVM only needs to sync to vmcs12 if KVM and the guest both support MPX?For MPX, if
guest_cpuid_has()is not efficent, can it be checked by BNDCFGS EN bit? E.g.:if (
kvm_mpx_supported()&& (vmcs12->guest_bndcfgs& 1))Quoted 7 lines
Quoted 3 lines
Same would apply to CET. Not sure it'd be a net positive in terms of performance since
guest_cpuid_has()can be quite slow, but overwriting vmcs12 fields that technically don't exist feels wrong.For CET, can we get equivalent effect by checking
vmcs12->guest_cr4.CET? E.g.:
if (kvm_cet_supported()&& (vmcs12->guest_cr4&X86_CR4_CET))
Quoted 5 lines
No, because the existence of the fields does not depend on them being enabled. E.g. things will go sideways if the values change while L2 is running, L2 disables CET, and then an exit occurs.
This is already a slow path, maybe the
guest_cpuid_has()checks are a non-issue.
Agree, then will add the check to both MPX and CET. Thanks!
Quoted 28 lines
Quoted 28 lines
Quoted 28 lines
Quoted 28 lines
arch/x86/kvm/vmx/nested.c +4
-0+ 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; }arch/x86/kvm/vmx/vmx.h +3
-0@@ -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;Signature · 1 line
2.26.2
PATCH v3 2/3 KVM: nVMX: Set X86_CR4_CET in cr4_fixed1_bits if CET IBT is enabled
In reply to Yang WeijiangCET SHSTK and IBT are independently controlled by kernel, set X86_CR4_CET bit in cr4_fixed1_bits if either of them is enabled so that nested guest can enjoy the feature.
--- arch/x86/kvm/vmx/vmx.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/kvm/vmx/vmx.c +1 -0
@@ -7267,6 +7267,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)cr4_fixed1_update (X86_CR4_UMIP , ecx,feature_bit (UMIP ));cr4_fixed1_update (X86_CR4_LA57 , ecx,feature_bit (LA57 ));cr4_fixed1_update (X86_CR4_CET , ecx,feature_bit (SHSTK )); +cr4_fixed1_update (X86_CR4_CET , edx,feature_bit (IBT ));#undef cr4_fixed1_update }
Signature · 1 line
2.26.2
PATCH v3 3/3 KVM: nVMX: Add CET entry/exit load bits to evmcs unsupported list
In reply to Yang WeijiangNested guest doesn't support CET when KVM is running as an intermediate layer between two Hyper-Vs for now, so mask out related CET entry/exit load bits. Relevant enabling patches will be posted as a separate patch series.
--- arch/x86/kvm/vmx/evmcs.c | 4 ++-- arch/x86/kvm/vmx/evmcs.h | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-)
arch/x86/kvm/vmx/evmcs.c +2 -2
@@ -351,11 +351,11 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)switch (msr_index) {case MSR_IA32_VMX_EXIT_CTLS :case MSR_IA32_VMX_TRUE_EXIT_CTLS : - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL ; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL ;break ;case MSR_IA32_VMX_ENTRY_CTLS :case MSR_IA32_VMX_TRUE_ENTRY_CTLS : - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL ; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL ;break ;case MSR_IA32_VMX_PROCBASED_CTLS2 : ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES ;
arch/x86/kvm/vmx/evmcs.h +4 -2
@@ -59,8 +59,10 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_SHADOW_VMCS | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) +#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_LOAD_CET_STATE) +#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_CET_STATE)#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)#if IS_ENABLED (CONFIG_HYPERV )
Signature · 1 line
2.26.2
Re: [PATCH v3 3/3] KVM: nVMX: Add CET entry/exit load bits to evmcs unsupported list
Quoted 38 lines · Yang Weijiang
Nested guest doesn't support CET when KVM is running as an intermediate layer between two Hyper-Vs for now, so mask out related CET entry/exit load bits. Relevant enabling patches will be posted as a separate patch series.
Suggested-by Paolo Bonzini <[email protected]>Suggested-by Vitaly Kuznetsov <[email protected]>Signed-off-by Yang Weijiang <[email protected]>--- arch/x86/kvm/vmx/evmcs.c | 4 ++-- arch/x86/kvm/vmx/evmcs.h | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-)arch/x86/kvm/vmx/evmcs.c +2
-2@@ -351,11 +351,11 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)switch (msr_index) {case MSR_IA32_VMX_EXIT_CTLS :case MSR_IA32_VMX_TRUE_EXIT_CTLS : - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL ; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL ;break ;case MSR_IA32_VMX_ENTRY_CTLS :case MSR_IA32_VMX_TRUE_ENTRY_CTLS : - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL ; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL ;break ;case MSR_IA32_VMX_PROCBASED_CTLS2 : ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES ;arch/x86/kvm/vmx/evmcs.h +0
-0@@ -59,8 +59,10 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);SECONDARY_EXEC_SHADOW_VMCS | \ SECONDARY_EXEC_TSC_SCALING | \
arch/x86/kvm/vmx/evmcs.h DECLARE_STATIC_KEY_FALSE(enable_evmcs); · line 68
Quoted 10 lines
arch/x86/kvm/vmx/evmcs.h +4
-2SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) +#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_LOAD_CET_STATE) +#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_CET_STATE)#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)#if IS_ENABLED (CONFIG_HYPERV )
Thanks, this should be enough for both KVM on Hyper-V and Hyper-V on KVM using eVMCS.
Signature · 1 line
Vitaly