[PATCH v2 2/3] KVM: X86: Provide a capability to disable cstate msr read intercepts

[Wanpeng Li]

From: Wanpeng Li <wanpengli@xxxxxxxxxxx>

Allow guest reads CORE cstate when exposing host CPU power management capabilities 
to the guest. PKG cstate is restricted to avoid a guest to get the whole package 
information in multi-tenant scenario.

Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Cc: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Cc: Liran Alon <liran.alon@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
v1 -> v2:
 * use a separate bit for KVM_CAP_X86_DISABLE_EXITS

 Documentation/virtual/kvm/api.txt | 1 +
 arch/x86/include/asm/kvm_host.h   | 1 +
 arch/x86/kvm/vmx/vmx.c            | 6 ++++++
 arch/x86/kvm/x86.c                | 5 ++++-
 arch/x86/kvm/x86.h                | 5 +++++
 include/uapi/linux/kvm.h          | 4 +++-
 tools/include/uapi/linux/kvm.h    | 4 +++-
 7 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 33cd92d..91fd86f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4894,6 +4894,7 @@ Valid bits in args[0] are
 #define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE            (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE           (1 << 3)
 
 Enabling this capability on a VM provides userspace with a way to no
 longer intercept some instructions for improved latency in some
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d5457c7..1ce8289 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -882,6 +882,7 @@ struct kvm_arch {
 	bool mwait_in_guest;
 	bool hlt_in_guest;
 	bool pause_in_guest;
+	bool cstate_in_guest;
 
 	unsigned long irq_sources_bitmap;
 	s64 kvmclock_offset;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0861c71..da24f18 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6637,6 +6637,12 @@ 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);
+	if (kvm_cstate_in_guest(kvm)) {
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+	}
 	vmx->msr_bitmap_mode = 0;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 202048e..765fe59 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3098,7 +3098,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
-		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE;
+		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
+		      KVM_X86_DISABLE_EXITS_CSTATE;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -4612,6 +4613,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			kvm->arch.hlt_in_guest = true;
 		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
 			kvm->arch.pause_in_guest = true;
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
+			kvm->arch.cstate_in_guest = true;
 		r = 0;
 		break;
 	case KVM_CAP_MSR_PLATFORM_INFO:
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a470ff0..275b3b6 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -333,6 +333,11 @@ static inline bool kvm_pause_in_guest(struct kvm *kvm)
 	return kvm->arch.pause_in_guest;
 }
 
+static inline bool kvm_cstate_in_guest(struct kvm *kvm)
+{
+	return kvm->arch.cstate_in_guest;
+}
+
 DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
 
 static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2fe12b4..c2152f3 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -696,9 +696,11 @@ struct kvm_ioeventfd {
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE         (1 << 3)
 #define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
                                               KVM_X86_DISABLE_EXITS_HLT | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
+                                              KVM_X86_DISABLE_EXITS_PAUSE | \
+                                              KVM_X86_DISABLE_EXITS_CSTATE)
 
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6d4ea4b..ef3303f 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -696,9 +696,11 @@ struct kvm_ioeventfd {
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE         (1 << 3)
 #define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
                                               KVM_X86_DISABLE_EXITS_HLT | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
+                                              KVM_X86_DISABLE_EXITS_PAUSE | \
+                                              KVM_X86_DISABLE_EXITS_CSTATE)
 
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
-- 
2.7.4