From: Yang Weijiang <weijiang.yang@intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
pbonzini@redhat.com, sean.j.christopherson@intel.com
Cc: jmattson@google.com, yu.c.zhang@linux.intel.com,
yu-cheng.yu@intel.com, Yang Weijiang <weijiang.yang@intel.com>
Subject: [PATCH v8 3/7] KVM: VMX: Pass through CET related MSRs
Date: Fri, 1 Nov 2019 16:52:18 +0800 [thread overview]
Message-ID: <20191101085222.27997-4-weijiang.yang@intel.com> (raw)
In-Reply-To: <20191101085222.27997-1-weijiang.yang@intel.com>
CET MSRs pass through Guest directly to enhance performance.
CET runtime control settings are stored in MSR_IA32_{U,S}_CET,
Shadow Stack Pointer(SSP) are stored in MSR_IA32_PL{0,1,2,3}_SSP,
SSP table base address is stored in MSR_IA32_INT_SSP_TAB,
these MSRs are defined in kernel and re-used here.
MSR_IA32_U_CET and MSR_IA32_PL3_SSP are used for user mode protection,
the contents could differ from process to process, therefore,
kernel needs to save/restore them during context switch, it makes
sense to pass through them so that the guest kernel can
use xsaves/xrstors to operate them efficiently. Other MSRs are used
for non-user mode protection. See CET spec for detailed info.
The difference between CET VMCS state fields and xsave components is that,
the former used for CET state storage during VMEnter/VMExit,
whereas the latter used for state retention between Guest task/process
switch.
Co-developed-by: Zhang Yi Z <yi.z.zhang@linux.intel.com>
Signed-off-by: Zhang Yi Z <yi.z.zhang@linux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
---
arch/x86/kvm/cpuid.c | 4 +--
arch/x86/kvm/cpuid.h | 2 ++
arch/x86/kvm/vmx/vmx.c | 65 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 69 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dd387a785c1e..4166c4fcad1e 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -371,13 +371,13 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
- F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B);
+ F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | F(SHSTK);
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
- F(MD_CLEAR);
+ F(MD_CLEAR) | F(IBT);
/* cpuid 7.1.eax */
const u32 kvm_cpuid_7_1_eax_x86_features =
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d78a61408243..1d77b880084d 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -27,6 +27,8 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
+u64 kvm_supported_xss(void);
+
static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
{
return vcpu->arch.maxphyaddr;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a84198cff397..db03d9dc1297 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2918,6 +2918,24 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
vmcs_writel(GUEST_CR3, guest_cr3);
}
+static bool guest_cet_allowed(struct kvm_vcpu *vcpu, u32 feature, u32 mode)
+{
+ u64 kvm_xss = kvm_supported_xss();
+
+ /*
+ * Sanity check for guest CET dependencies, guest_cpu_has(SHSTK|IBT) has
+ * implied corresponding host CET status check.
+ */
+ if (feature == X86_FEATURE_SHSTK)
+ return guest_cpuid_has(vcpu, X86_FEATURE_SHSTK) &&
+ (kvm_xss & mode);
+ else if (feature == X86_FEATURE_IBT)
+ return guest_cpuid_has(vcpu, X86_FEATURE_IBT) &&
+ (kvm_xss & mode);
+
+ return false;
+}
+
int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7001,6 +7019,50 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
}
+static void vmx_pass_cet_msrs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+
+ /*
+ * U_CET is required for USER CET, per CET spec., meanwhile U_CET and
+ * PL3_SPP are a bundle for USER CET xsaves.
+ */
+ if (guest_cet_allowed(vcpu, X86_FEATURE_SHSTK, XFEATURE_MASK_CET_USER) ||
+ guest_cet_allowed(vcpu, X86_FEATURE_IBT, XFEATURE_MASK_CET_USER)) {
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_U_CET, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_PL3_SSP, MSR_TYPE_RW);
+ } else {
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_U_CET, MSR_TYPE_RW, true);
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_PL3_SSP, MSR_TYPE_RW, true);
+ }
+ /*
+ * S_CET is required for KERNEL CET, meanwhile PL0_SSP ... PL2_SSP are a bundle
+ * for CET KERNEL xsaves.
+ */
+ if (guest_cet_allowed(vcpu, X86_FEATURE_SHSTK, XFEATURE_MASK_CET_KERNEL) ||
+ guest_cet_allowed(vcpu, X86_FEATURE_IBT, XFEATURE_MASK_CET_KERNEL)) {
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_S_CET, 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_PL1_SSP, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_PL2_SSP, MSR_TYPE_RW);
+
+ /* SSP_TAB only available for KERNEL SHSTK.*/
+ if (guest_cpuid_has(vcpu, X86_FEATURE_SHSTK))
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_INT_SSP_TAB,
+ MSR_TYPE_RW);
+ else
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_INT_SSP_TAB,
+ MSR_TYPE_RW, true);
+ } else {
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_S_CET, MSR_TYPE_RW, true);
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_PL0_SSP, MSR_TYPE_RW, true);
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_PL1_SSP, MSR_TYPE_RW, true);
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_PL2_SSP, MSR_TYPE_RW, true);
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_INT_SSP_TAB, MSR_TYPE_RW, true);
+ }
+}
+
static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7025,6 +7087,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
update_intel_pt_cfg(vcpu);
+
+ if (!is_guest_mode(vcpu))
+ vmx_pass_cet_msrs(vcpu);
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
--
2.17.2
next prev parent reply other threads:[~2019-11-01 8:49 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-01 8:52 [PATCH v8 0/7] Introduce support for guest CET feature Yang Weijiang
2019-11-01 8:52 ` [PATCH v8 1/7] KVM: CPUID: Fix IA32_XSS support in CPUID(0xd,i) enumeration Yang Weijiang
2019-11-01 8:52 ` [PATCH v8 2/7] KVM: VMX: Define CET VMCS fields and #CP flag Yang Weijiang
2019-12-10 21:00 ` Sean Christopherson
2019-12-11 1:45 ` Yang Weijiang
2019-11-01 8:52 ` Yang Weijiang [this message]
2019-12-10 21:18 ` [PATCH v8 3/7] KVM: VMX: Pass through CET related MSRs Sean Christopherson
2019-12-11 1:32 ` Yang Weijiang
2019-12-11 1:50 ` Sean Christopherson
2019-12-11 2:27 ` Yang Weijiang
2019-12-16 2:18 ` Yang Weijiang
2019-12-18 0:34 ` Sean Christopherson
2019-12-18 13:55 ` Yang Weijiang
2019-12-18 16:02 ` Sean Christopherson
2019-11-01 8:52 ` [PATCH v8 4/7] KVM: VMX: Load CET states on vmentry/vmexit Yang Weijiang
2019-12-10 21:23 ` Sean Christopherson
2019-12-11 1:54 ` Yang Weijiang
2019-12-11 16:35 ` Sean Christopherson
2019-12-12 1:04 ` Yang Weijiang
2019-12-18 0:30 ` Sean Christopherson
2019-12-18 13:20 ` Yang Weijiang
2019-11-01 8:52 ` [PATCH v8 5/7] KVM: X86: Enable CET bits update in IA32_XSS Yang Weijiang
2019-11-01 8:52 ` [PATCH v8 6/7] KVM: X86: Load guest fpu state when accessing MSRs managed by XSAVES Yang Weijiang
2019-12-10 21:27 ` Sean Christopherson
2019-12-11 2:03 ` Yang Weijiang
2019-11-01 8:52 ` [PATCH v8 7/7] KVM: X86: Add user-space access interface for CET MSRs Yang Weijiang
2019-12-10 21:58 ` Sean Christopherson
2019-12-11 2:19 ` Yang Weijiang
2019-12-11 16:27 ` Sean Christopherson
2019-12-12 0:42 ` Yang Weijiang
2019-12-12 16:03 ` [PATCH v8 0/7] Introduce support for guest CET feature Konrad Rzeszutek Wilk
2019-12-13 0:44 ` Yang Weijiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191101085222.27997-4-weijiang.yang@intel.com \
--to=weijiang.yang@intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=yu-cheng.yu@intel.com \
--cc=yu.c.zhang@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).