KVM: vmx: Emulate MSR IA32_UMWAIT_CONTROL

UMWAIT and TPAUSE instructions use 32bit 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/kernel/cpu/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@intel.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 53 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 32b4dc9030aa..c222f283b456 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -17,6 +17,12 @@
  */
 static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
 
+u32 get_umwait_control_msr(void)
+{
+	return umwait_control_cached;
+}
+EXPORT_SYMBOL_GPL(get_umwait_control_msr);
+
 /*
  * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
  * hardware or BIOS before kernel boot.
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bb55f54e29b1..52dd2241b749 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1733,6 +1733,12 @@ 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 (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			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))
@@ -1906,6 +1912,16 @@ 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 (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			return 1;
+
+		/* The reserved bit 1 and non-32 bit [63:32] should be zero */
+		if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32)))
+			return 1;
+
+		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))
@@ -4211,6 +4227,8 @@ 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();
 	vmx->hv_deadline_tsc = -1;
@@ -6384,6 +6402,23 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
+static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
+{
+	u32 host_umwait_control;
+
+	if (!vmx_has_waitpkg(vmx))
+		return;
+
+	host_umwait_control = get_umwait_control_msr();
+
+	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_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6478,6 +6513,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	pt_guest_enter(vmx);
 
 	atomic_switch_perf_msrs(vmx);
+	atomic_switch_umwait_control_msr(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 64d5a4890aa9..bee16687dc0b 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 get_umwait_control_msr(void);
+
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
 #define MSR_TYPE_RW	3
@@ -211,6 +213,7 @@ struct vcpu_vmx {
 #endif
 
 	u64		      spec_ctrl;
+	u32		      msr_ia32_umwait_control;
 
 	u32 secondary_exec_control;
 
@@ -497,6 +500,12 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
 	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
 }
 
+static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
+{
+	return vmx->secondary_exec_control &
+		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+}
+
 void dump_vmcs(void);
 
 #endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c38d247dbffb..977b36348bed 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1145,6 +1145,8 @@ static u32 msrs_to_save[] = {
 	MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
 	MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
 	MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
+	MSR_IA32_UMWAIT_CONTROL,
+
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
 	MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,