[PATCH RESEND v3 2/3] KVM: vmx: Emulate MSR IA32_UMWAIT_CONTROL

[Tao Xu <tao3.xu@xxxxxxxxx>]

UMWAIT and TPAUSE instructions use IA32_UMWAIT_CONTROL at MSR index E1H
to determines the maximum time in TSC-quanta that the processor can reside
in either C0.1 or C0.2.

This patch emulates MSR IA32_UMWAIT_CONTROL in guest and differentiate
IA32_UMWAIT_CONTROL between host and guest. The variable
mwait_control_cached in arch/x86/power/umwait.c caches the MSR value, so
this patch uses it to avoid frequently rdmsr of IA32_UMWAIT_CONTROL.

Co-developed-by: Jingqi Liu <jingqi.liu@xxxxxxxxx>
Signed-off-by: Jingqi Liu <jingqi.liu@xxxxxxxxx>
Signed-off-by: Tao Xu <tao3.xu@xxxxxxxxx>
---
 arch/x86/kvm/vmx/vmx.c  | 36 ++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/vmx.h  |  3 +++
 arch/x86/power/umwait.c |  3 ++-
 3 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b35bfac30a34..f33a25e82cb8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1679,6 +1679,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!vmx_waitpkg_supported())
+			return 1;
+
+		msr_info->data = vmx->msr_ia32_umwait_control;
+		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -1841,6 +1847,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!vmx_waitpkg_supported())
+			return 1;
+
+		if (!data)
+			break;
+
+		vmx->msr_ia32_umwait_control = data;
+		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -4126,6 +4141,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx->rmode.vm86_active = 0;
 	vmx->spec_ctrl = 0;
 
+	vmx->msr_ia32_umwait_control = 0;
+
 	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	kvm_set_cr8(vcpu, 0);
@@ -6339,6 +6356,23 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
+static void atomic_switch_ia32_umwait_control(struct vcpu_vmx *vmx)
+{
+	u64 host_umwait_control;
+
+	if (!vmx_waitpkg_supported())
+		return;
+
+	host_umwait_control = umwait_control_cached;
+
+	if (vmx->msr_ia32_umwait_control != host_umwait_control)
+		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
+				      vmx->msr_ia32_umwait_control,
+				      host_umwait_control, false);
+	else
+		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
+}
+
 static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
 {
 	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
@@ -6447,6 +6481,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	atomic_switch_perf_msrs(vmx);
 
+	atomic_switch_ia32_umwait_control(vmx);
+
 	vmx_update_hv_timer(vcpu);
 
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 61128b48c503..8485bec7c38a 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -14,6 +14,8 @@
 extern const u32 vmx_msr_index[];
 extern u64 host_efer;
 
+extern u32 umwait_control_cached;
+
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
 #define MSR_TYPE_RW	3
@@ -194,6 +196,7 @@ struct vcpu_vmx {
 #endif
 
 	u64		      spec_ctrl;
+	u64		      msr_ia32_umwait_control;
 
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
diff --git a/arch/x86/power/umwait.c b/arch/x86/power/umwait.c
index 7fa381e3fd4e..2e6ce4cbccb3 100644
--- a/arch/x86/power/umwait.c
+++ b/arch/x86/power/umwait.c
@@ -9,7 +9,8 @@
  * MSR value. By default, umwait max time is 100000 in TSC-quanta and C0.2
  * is enabled
  */
-static u32 umwait_control_cached = 100000;
+u32 umwait_control_cached = 100000;
+EXPORT_SYMBOL_GPL(umwait_control_cached);
 
 /*
  * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR
-- 
2.20.1