KVM: x86: nSVM: implement nested VMLOAD/VMSAVE

This was tested by booting L1,L2,L3 (all Linux) and checking
that no VMLOAD/VMSAVE vmexits happened.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20220301143650.143749-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/svm/nested.c

@@ -121,6 +121,20 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 }
 
+static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm)
+{
+	if (!svm->v_vmload_vmsave_enabled)
+		return true;
+
+	if (!nested_npt_enabled(svm))
+		return true;
+
+	if (!(svm->nested.ctl.virt_ext & VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK))
+		return true;
+
+	return false;
+}
+
 void recalc_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *c, *h;
@@ -162,8 +176,17 @@ void recalc_intercepts(struct vcpu_svm *svm)
 	if (!intercept_smi)
 		vmcb_clr_intercept(c, INTERCEPT_SMI);
 
-	vmcb_set_intercept(c, INTERCEPT_VMLOAD);
-	vmcb_set_intercept(c, INTERCEPT_VMSAVE);
+	if (nested_vmcb_needs_vls_intercept(svm)) {
+		/*
+		 * If the virtual VMLOAD/VMSAVE is not enabled for the L2,
+		 * we must intercept these instructions to correctly
+		 * emulate them in case L1 doesn't intercept them.
+		 */
+		vmcb_set_intercept(c, INTERCEPT_VMLOAD);
+		vmcb_set_intercept(c, INTERCEPT_VMSAVE);
+	} else {
+		WARN_ON(!(c->virt_ext & VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK));
+	}
 }
 
 /*
@@ -454,11 +477,6 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
 	vmcb12->control.exit_int_info = exit_int_info;
 }
 
-static inline bool nested_npt_enabled(struct vcpu_svm *svm)
-{
-	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
-}
-
 static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -621,6 +639,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
 	svm->vmcb->control.event_inj_err       = svm->nested.ctl.event_inj_err;
 
+	if (!nested_vmcb_needs_vls_intercept(svm))
+		svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
+
 	nested_svm_transition_tlb_flush(vcpu);
 
 	/* Enter Guest-Mode */

arch/x86/kvm/svm/svm.c

@@ -960,6 +960,8 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0);
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0);
+
+		svm->v_vmload_vmsave_enabled = false;
 	} else {
 		/*
 		 * If hardware supports Virtual VMLOAD VMSAVE then enable it
@@ -3947,6 +3949,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR);
 
+	svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
+
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
@@ -4695,6 +4699,9 @@ static __init void svm_set_cpu_caps(void)
 		if (tsc_scaling)
 			kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
 
+		if (vls)
+			kvm_cpu_cap_set(X86_FEATURE_V_VMSAVE_VMLOAD);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}

arch/x86/kvm/svm/svm.h

@@ -231,9 +231,10 @@ struct vcpu_svm {
 	unsigned int3_injected;
 	unsigned long int3_rip;
 
-	/* cached guest cpuid flags for faster access */
+	/* optional nested SVM features that are enabled for this guest  */
 	bool nrips_enabled                : 1;
 	bool tsc_scaling_enabled          : 1;
+	bool v_vmload_vmsave_enabled      : 1;
 
 	u32 ldr_reg;
 	u32 dfr_reg;
@@ -481,6 +482,11 @@ static inline bool gif_set(struct vcpu_svm *svm)
 		return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
 }
 
+static inline bool nested_npt_enabled(struct vcpu_svm *svm)
+{
+	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
+}
+
 /* svm.c */
 #define MSR_INVALID				0xffffffffU