1 files changed, 164 insertions, 51 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 17d334ef5430..200045f71df0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -62,8 +62,6 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
 #define SEG_TYPE_LDT 2
 #define SEG_TYPE_BUSY_TSS16 3
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
-
 static bool erratum_383_found __read_mostly;
 
 u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
@@ -101,6 +99,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_EFER,				.always = false },
 	{ .index = MSR_IA32_CR_PAT,			.always = false },
 	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
+	{ .index = MSR_TSC_AUX,				.always = false },
 	{ .index = MSR_INVALID,				.always = false },
 };
 
@@ -172,7 +171,7 @@ static int vls = true;
 module_param(vls, int, 0444);
 
 /* enable/disable Virtual GIF */
-static int vgif = true;
+int vgif = true;
 module_param(vgif, int, 0444);
 
 /* enable/disable LBR virtualization */
@@ -189,6 +188,9 @@ module_param(tsc_scaling, int, 0444);
 static bool avic;
 module_param(avic, bool, 0444);
 
+static bool force_avic;
+module_param_unsafe(force_avic, bool, 0444);
+
 bool __read_mostly dump_invalid_vmcb;
 module_param(dump_invalid_vmcb, bool, 0644);
 
@@ -790,6 +792,17 @@ static void init_msrpm_offsets(void)
 	}
 }
 
+void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
+{
+	to_vmcb->save.dbgctl		= from_vmcb->save.dbgctl;
+	to_vmcb->save.br_from		= from_vmcb->save.br_from;
+	to_vmcb->save.br_to		= from_vmcb->save.br_to;
+	to_vmcb->save.last_excp_from	= from_vmcb->save.last_excp_from;
+	to_vmcb->save.last_excp_to	= from_vmcb->save.last_excp_to;
+
+	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
+}
+
 static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -799,6 +812,10 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+
+	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
+	if (is_guest_mode(vcpu))
+		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
 }
 
 static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
@@ -810,6 +827,67 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+
+	/*
+	 * Move the LBR msrs back to the vmcb01 to avoid copying them
+	 * on nested guest entries.
+	 */
+	if (is_guest_mode(vcpu))
+		svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
+}
+
+static int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index)
+{
+	/*
+	 * If the LBR virtualization is disabled, the LBR msrs are always
+	 * kept in the vmcb01 to avoid copying them on nested guest entries.
+	 *
+	 * If nested, and the LBR virtualization is enabled/disabled, the msrs
+	 * are moved between the vmcb01 and vmcb02 as needed.
+	 */
+	struct vmcb *vmcb =
+		(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ?
+			svm->vmcb : svm->vmcb01.ptr;
+
+	switch (index) {
+	case MSR_IA32_DEBUGCTLMSR:
+		return vmcb->save.dbgctl;
+	case MSR_IA32_LASTBRANCHFROMIP:
+		return vmcb->save.br_from;
+	case MSR_IA32_LASTBRANCHTOIP:
+		return vmcb->save.br_to;
+	case MSR_IA32_LASTINTFROMIP:
+		return vmcb->save.last_excp_from;
+	case MSR_IA32_LASTINTTOIP:
+		return vmcb->save.last_excp_to;
+	default:
+		KVM_BUG(false, svm->vcpu.kvm,
+			"%s: Unknown MSR 0x%x", __func__, index);
+		return 0;
+	}
+}
+
+void svm_update_lbrv(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) &
+					   DEBUGCTLMSR_LBR;
+
+	bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext &
+				      LBR_CTL_ENABLE_MASK);
+
+	if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled))
+		if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))
+			enable_lbrv = true;
+
+	if (enable_lbrv == current_enable_lbrv)
+		return;
+
+	if (enable_lbrv)
+		svm_enable_lbrv(vcpu);
+	else
+		svm_disable_lbrv(vcpu);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)
@@ -831,6 +909,9 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;
 
+	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+		return;
+
 	control->pause_filter_count = __grow_ple_window(old,
 							pause_filter_count,
 							pause_filter_count_grow,
@@ -849,6 +930,9 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;
 
+	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+		return;
+
 	control->pause_filter_count =
 				__shrink_ple_window(old,
 						    pause_filter_count,
@@ -960,6 +1044,8 @@ 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
@@ -979,8 +1065,9 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
 static void init_vmcb(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb_control_area *control = &svm->vmcb->control;
-	struct vmcb_save_area *save = &svm->vmcb->save;
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+	struct vmcb_control_area *control = &vmcb->control;
+	struct vmcb_save_area *save = &vmcb->save;
 
 	svm_set_intercept(svm, INTERCEPT_CR0_READ);
 	svm_set_intercept(svm, INTERCEPT_CR3_READ);
@@ -1104,7 +1191,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
 
 	if (kvm_vcpu_apicv_active(vcpu))
-		avic_init_vmcb(svm);
+		avic_init_vmcb(svm, vmcb);
 
 	if (vgif) {
 		svm_clr_intercept(svm, INTERCEPT_STGI);
@@ -1122,10 +1209,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	svm_hv_init_vmcb(svm->vmcb);
+	svm_hv_init_vmcb(vmcb);
 	init_vmcb_after_set_cpuid(vcpu);
 
-	vmcb_mark_all_dirty(svm->vmcb);
+	vmcb_mark_all_dirty(vmcb);
 
 	enable_gif(svm);
 }
@@ -1380,7 +1467,7 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 	/*
 	 * The following fields are ignored when AVIC is enabled
 	 */
-	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+	WARN_ON(kvm_vcpu_apicv_activated(&svm->vcpu));
 
 	svm_set_intercept(svm, INTERCEPT_VINTR);
 
@@ -2142,7 +2229,7 @@ void svm_set_gif(struct vcpu_svm *svm, bool value)
 		 * Likewise, clear the VINTR intercept, we will set it
 		 * again while processing KVM_REQ_EVENT if needed.
 		 */
-		if (vgif_enabled(svm))
+		if (vgif)
 			svm_clr_intercept(svm, INTERCEPT_STGI);
 		if (svm_is_intercept(svm, INTERCEPT_VINTR))
 			svm_clear_vintr(svm);
@@ -2160,7 +2247,7 @@ void svm_set_gif(struct vcpu_svm *svm, bool value)
 		 * in use, we still rely on the VINTR intercept (rather than
 		 * STGI) to detect an open interrupt window.
 		*/
-		if (!vgif_enabled(svm))
+		if (!vgif)
 			svm_clear_vintr(svm);
 	}
 }
@@ -2575,25 +2662,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_TSC_AUX:
 		msr_info->data = svm->tsc_aux;
 		break;
-	/*
-	 * Nobody will change the following 5 values in the VMCB so we can
-	 * safely return them on rdmsr. They will always be 0 until LBRV is
-	 * implemented.
-	 */
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = svm->vmcb->save.dbgctl;
-		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
-		msr_info->data = svm->vmcb->save.br_from;
-		break;
 	case MSR_IA32_LASTBRANCHTOIP:
-		msr_info->data = svm->vmcb->save.br_to;
-		break;
 	case MSR_IA32_LASTINTFROMIP:
-		msr_info->data = svm->vmcb->save.last_excp_from;
-		break;
 	case MSR_IA32_LASTINTTOIP:
-		msr_info->data = svm->vmcb->save.last_excp_to;
+		msr_info->data = svm_get_lbr_msr(svm, msr_info->index);
 		break;
 	case MSR_VM_HSAVE_PA:
 		msr_info->data = svm->nested.hsave_msr;
@@ -2839,12 +2913,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
-		svm->vmcb->save.dbgctl = data;
-		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
-		if (data & (1ULL<<0))
-			svm_enable_lbrv(vcpu);
+		if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK)
+			svm->vmcb->save.dbgctl = data;
 		else
-			svm_disable_lbrv(vcpu);
+			svm->vmcb01.ptr->save.dbgctl = data;
+
+		svm_update_lbrv(vcpu);
+
 		break;
 	case MSR_VM_HSAVE_PA:
 		/*
@@ -2901,9 +2976,16 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu)
 	svm_clear_vintr(to_svm(vcpu));
 
 	/*
-	 * For AVIC, the only reason to end up here is ExtINTs.
+	 * If not running nested, for AVIC, the only reason to end up here is ExtINTs.
 	 * In this case AVIC was temporarily disabled for
 	 * requesting the IRQ window and we have to re-enable it.
+	 *
+	 * If running nested, still remove the VM wide AVIC inhibit to
+	 * support case in which the interrupt window was requested when the
+	 * vCPU was not running nested.
+
+	 * All vCPUs which run still run nested, will remain to have their
+	 * AVIC still inhibited due to per-cpu AVIC inhibition.
 	 */
 	kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
 
@@ -2914,7 +2996,6 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu)
 static int pause_interception(struct kvm_vcpu *vcpu)
 {
 	bool in_kernel;
-
 	/*
 	 * CPL is not made available for an SEV-ES guest, therefore
 	 * vcpu->arch.preempted_in_kernel can never be true.  Just
@@ -2922,8 +3003,7 @@ static int pause_interception(struct kvm_vcpu *vcpu)
 	 */
 	in_kernel = !sev_es_guest(vcpu->kvm) && svm_get_cpl(vcpu) == 0;
 
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		grow_ple_window(vcpu);
+	grow_ple_window(vcpu);
 
 	kvm_vcpu_on_spin(vcpu, in_kernel);
 	return kvm_skip_emulated_instruction(vcpu);
@@ -3496,14 +3576,20 @@ static void svm_enable_irq_window(struct kvm_vcpu *vcpu)
 	 * enabled, the STGI interception will not occur. Enable the irq
 	 * window under the assumption that the hardware will set the GIF.
 	 */
-	if (vgif_enabled(svm) || gif_set(svm)) {
+	if (vgif || gif_set(svm)) {
 		/*
 		 * IRQ window is not needed when AVIC is enabled,
 		 * unless we have pending ExtINT since it cannot be injected
-		 * via AVIC. In such case, we need to temporarily disable AVIC,
+		 * via AVIC. In such case, KVM needs to temporarily disable AVIC,
 		 * and fallback to injecting IRQ via V_IRQ.
+		 *
+		 * If running nested, AVIC is already locally inhibited
+		 * on this vCPU, therefore there is no need to request
+		 * the VM wide AVIC inhibition.
 		 */
-		kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
+		if (!is_guest_mode(vcpu))
+			kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
+
 		svm_set_vintr(svm);
 	}
 }
@@ -3516,7 +3602,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 		return; /* IRET will cause a vm exit */
 
 	if (!gif_set(svm)) {
-		if (vgif_enabled(svm))
+		if (vgif)
 			svm_set_intercept(svm, INTERCEPT_STGI);
 		return; /* STGI will cause a vm exit */
 	}
@@ -3865,7 +3951,7 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 		hv_track_root_tdp(vcpu, root_hpa);
 
 		cr3 = vcpu->arch.cr3;
-	} else if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
+	} else if (vcpu->arch.mmu->root_role.level >= PT64_ROOT_4LEVEL) {
 		cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu);
 	} else {
 		/* PCID in the guest should be impossible with a 32-bit MMU. */
@@ -3946,6 +4032,17 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 			     guest_cpuid_has(vcpu, X86_FEATURE_NRIPS);
 
 	svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR);
+	svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV);
+
+	svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
+
+	svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) &&
+			guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER);
+
+	svm->pause_threshold_enabled = kvm_cpu_cap_has(X86_FEATURE_PFTHRESHOLD) &&
+			guest_cpuid_has(vcpu, X86_FEATURE_PFTHRESHOLD);
+
+	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
 
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
@@ -3963,13 +4060,6 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		 */
 		if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC))
 			kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC);
-
-		/*
-		 * Currently, AVIC does not work with nested virtualization.
-		 * So, we disable AVIC when cpuid for SVM is set in the L1 guest.
-		 */
-		if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-			kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_NESTED);
 	}
 	init_vmcb_after_set_cpuid(vcpu);
 }
@@ -4224,7 +4314,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
 	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
 
-	ret = nested_svm_vmexit(svm);
+	ret = nested_svm_simple_vmexit(svm, SVM_EXIT_SW);
 	if (ret)
 		return ret;
 
@@ -4321,7 +4411,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!gif_set(svm)) {
-		if (vgif_enabled(svm))
+		if (vgif)
 			svm_set_intercept(svm, INTERCEPT_STGI);
 		/* STGI will cause a vm exit */
 	} else {
@@ -4605,7 +4695,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.sched_in = svm_sched_in,
 
-	.pmu_ops = &amd_pmu_ops,
 	.nested_ops = &svm_nested_ops,
 
 	.deliver_interrupt = svm_deliver_interrupt,
@@ -4633,6 +4722,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.complete_emulated_msr = svm_complete_emulated_msr,
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
+	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
 };
 
 /*
@@ -4696,6 +4786,20 @@ 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);
+		if (lbrv)
+			kvm_cpu_cap_set(X86_FEATURE_LBRV);
+
+		if (boot_cpu_has(X86_FEATURE_PAUSEFILTER))
+			kvm_cpu_cap_set(X86_FEATURE_PAUSEFILTER);
+
+		if (boot_cpu_has(X86_FEATURE_PFTHRESHOLD))
+			kvm_cpu_cap_set(X86_FEATURE_PFTHRESHOLD);
+
+		if (vgif)
+			kvm_cpu_cap_set(X86_FEATURE_VGIF);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}
@@ -4789,6 +4893,9 @@ static __init int svm_hardware_setup(void)
 			  get_npt_level(), PG_LEVEL_1G);
 	pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
 
+	/* Setup shadow_me_value and shadow_me_mask */
+	kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask);
+
 	/* Note, SEV setup consumes npt_enabled. */
 	sev_hardware_setup();
 
@@ -4807,15 +4914,20 @@ static __init int svm_hardware_setup(void)
 			nrips = false;
 	}
 
-	enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC);
+	enable_apicv = avic = avic && npt_enabled && (boot_cpu_has(X86_FEATURE_AVIC) || force_avic);
 
 	if (enable_apicv) {
-		pr_info("AVIC enabled\n");
+		if (!boot_cpu_has(X86_FEATURE_AVIC)) {
+			pr_warn("AVIC is not supported in CPUID but force enabled");
+			pr_warn("Your system might crash and burn");
+		} else
+			pr_info("AVIC enabled\n");
 
 		amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
 	} else {
 		svm_x86_ops.vcpu_blocking = NULL;
 		svm_x86_ops.vcpu_unblocking = NULL;
+		svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
 	}
 
 	if (vls) {
@@ -4880,6 +4992,7 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = {
 	.check_processor_compatibility = svm_check_processor_compat,
 
 	.runtime_ops = &svm_x86_ops,
+	.pmu_ops = &amd_pmu_ops,
 };
 
 static int __init svm_init(void)