linux-kernel - [PATCH v2 5/7] KVM:VMX: Pass through host CET related MSRs to Guest.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 23 Jan 2019 04:59:07 +0800
From:   Yang Weijiang <weijiang.yang@...el.com>
To:     pbonzini@...hat.com, rkrcmar@...hat.com,
        sean.j.christopherson@...el.com, jmattson@...gle.com,
        linux-kernel@...r.kernel.org, kvm@...r.kernel.org, mst@...hat.com,
        yu-cheng.yu@...el.com, yi.z.zhang@...el.com, hjl.tools@...il.com
Cc:     weijiang.yang@...el.com, Zhang Yi Z <yi.z.zhang@...ux.intel.com>
Subject: [PATCH v2 5/7] KVM:VMX: Pass through host CET related MSRs to Guest.

The CET runtime settings, i.e., CET state control bits(IA32_U_CET/
IA32_S_CET), CET SSP(IA32_PL3_SSP/IA32_PL0_SSP) and SSP table address
(IA32_INTERRUPT_SSP_TABLE_ADDR) are task/thread specific, therefore,
OS needs to save/restore the states properly during context switch,
e.g., task/thread switching, interrupt/exception handling, it uses
xsaves/xrstors to achieve that.

The difference between VMCS CET area fields and xsave CET area, is that
the former is for state retention during Guest/Host context
switch while the latter is for state retention during OS execution.

Linux currently doesn't support CPL1 and CPL2, so SSPs for these level
are skipped here.

Signed-off-by: Zhang Yi Z <yi.z.zhang@...ux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@...el.com>
---
 arch/x86/kvm/vmx.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7bbb8b26e901..68c0e5e41cb1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11531,6 +11531,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+
 	vmx->msr_bitmap_mode = 0;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
@@ -11769,6 +11770,8 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_cpuid_entry2 *best;
+	unsigned long *msr_bitmap;
 
 	if (cpu_has_secondary_exec_ctrls()) {
 		vmx_compute_secondary_exec_control(vmx);
@@ -11786,6 +11789,19 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		nested_vmx_cr_fixed1_bits_update(vcpu);
 		nested_vmx_entry_exit_ctls_update(vcpu);
 	}
+
+	msr_bitmap = vmx->vmcs01.msr_bitmap;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if ((best && best->function == 0x7) &&
+	    ((best->ecx & bit(X86_FEATURE_SHSTK)) |
+	    (best->edx & bit(X86_FEATURE_IBT)))) {
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_U_CET, MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_S_CET, MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_INT_SSP_TAB, MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_PL0_SSP, MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_PL3_SSP, MSR_TYPE_RW);
+	}
+
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
-- 
2.17.1