1 files changed, 101 insertions, 135 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 3a9fe0a8b78c..153c12dbf3eb 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -158,14 +158,6 @@ module_param(lbrv, int, 0444);
 static int tsc_scaling = true;
 module_param(tsc_scaling, int, 0444);
 
-/*
- * enable / disable AVIC.  Because the defaults differ for APICv
- * support between VMX and SVM we cannot use module_param_named.
- */
-static bool avic;
-module_param(avic, bool, 0444);
-module_param(enable_ipiv, bool, 0444);
-
 module_param(enable_device_posted_irqs, bool, 0444);
 
 bool __read_mostly dump_invalid_vmcb;
@@ -195,7 +187,7 @@ static DEFINE_MUTEX(vmcb_dump_mutex);
  * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to
  * defer the restoration of TSC_AUX until the CPU returns to userspace.
  */
-static int tsc_aux_uret_slot __read_mostly = -1;
+int tsc_aux_uret_slot __ro_after_init = -1;
 
 static int get_npt_level(void)
 {
@@ -577,18 +569,6 @@ static int svm_enable_virtualization_cpu(void)
 
 	amd_pmu_enable_virt();
 
-	/*
-	 * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
-	 * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
-	 * Since Linux does not change the value of TSC_AUX once set, prime the
-	 * TSC_AUX field now to avoid a RDMSR on every vCPU run.
-	 */
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
-		u32 __maybe_unused msr_hi;
-
-		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
-	}
-
 	return 0;
 }
 
@@ -736,55 +716,6 @@ static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu)
 		svm_set_intercept_for_msr(vcpu, MSR_IA32_DEBUGCTLMSR, MSR_TYPE_RW, intercept);
 }
 
-void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
-{
-	static const u32 x2avic_passthrough_msrs[] = {
-		X2APIC_MSR(APIC_ID),
-		X2APIC_MSR(APIC_LVR),
-		X2APIC_MSR(APIC_TASKPRI),
-		X2APIC_MSR(APIC_ARBPRI),
-		X2APIC_MSR(APIC_PROCPRI),
-		X2APIC_MSR(APIC_EOI),
-		X2APIC_MSR(APIC_RRR),
-		X2APIC_MSR(APIC_LDR),
-		X2APIC_MSR(APIC_DFR),
-		X2APIC_MSR(APIC_SPIV),
-		X2APIC_MSR(APIC_ISR),
-		X2APIC_MSR(APIC_TMR),
-		X2APIC_MSR(APIC_IRR),
-		X2APIC_MSR(APIC_ESR),
-		X2APIC_MSR(APIC_ICR),
-		X2APIC_MSR(APIC_ICR2),
-
-		/*
-		 * Note!  Always intercept LVTT, as TSC-deadline timer mode
-		 * isn't virtualized by hardware, and the CPU will generate a
-		 * #GP instead of a #VMEXIT.
-		 */
-		X2APIC_MSR(APIC_LVTTHMR),
-		X2APIC_MSR(APIC_LVTPC),
-		X2APIC_MSR(APIC_LVT0),
-		X2APIC_MSR(APIC_LVT1),
-		X2APIC_MSR(APIC_LVTERR),
-		X2APIC_MSR(APIC_TMICT),
-		X2APIC_MSR(APIC_TMCCT),
-		X2APIC_MSR(APIC_TDCR),
-	};
-	int i;
-
-	if (intercept == svm->x2avic_msrs_intercepted)
-		return;
-
-	if (!x2avic_enabled)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(x2avic_passthrough_msrs); i++)
-		svm_set_intercept_for_msr(&svm->vcpu, x2avic_passthrough_msrs[i],
-					  MSR_TYPE_RW, intercept);
-
-	svm->x2avic_msrs_intercepted = intercept;
-}
-
 void svm_vcpu_free_msrpm(void *msrpm)
 {
 	__free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE));
@@ -844,6 +775,17 @@ static void svm_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 		svm_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R);
 	}
 
+	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) {
+		bool shstk_enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK);
+
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, !shstk_enabled);
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, !shstk_enabled);
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, !shstk_enabled);
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, !shstk_enabled);
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, !shstk_enabled);
+		svm_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, !shstk_enabled);
+	}
+
 	if (sev_es_guest(vcpu->kvm))
 		sev_es_recalc_msr_intercepts(vcpu);
 
@@ -1077,13 +1019,13 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void svm_recalc_intercepts_after_set_cpuid(struct kvm_vcpu *vcpu)
+static void svm_recalc_intercepts(struct kvm_vcpu *vcpu)
 {
 	svm_recalc_instruction_intercepts(vcpu);
 	svm_recalc_msr_intercepts(vcpu);
 }
 
-static void init_vmcb(struct kvm_vcpu *vcpu)
+static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -1221,11 +1163,11 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm_set_intercept(svm, INTERCEPT_BUSLOCK);
 
 	if (sev_guest(vcpu->kvm))
-		sev_init_vmcb(svm);
+		sev_init_vmcb(svm, init_event);
 
 	svm_hv_init_vmcb(vmcb);
 
-	svm_recalc_intercepts_after_set_cpuid(vcpu);
+	kvm_make_request(KVM_REQ_RECALC_INTERCEPTS, vcpu);
 
 	vmcb_mark_all_dirty(vmcb);
 
@@ -1244,9 +1186,6 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	svm->nmi_masked = false;
 	svm->awaiting_iret_completion = false;
-
-	if (sev_es_guest(vcpu->kvm))
-		sev_es_vcpu_reset(svm);
 }
 
 static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -1256,10 +1195,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	svm->spec_ctrl = 0;
 	svm->virt_spec_ctrl = 0;
 
-	if (init_event)
-		sev_snp_init_protected_guest_state(vcpu);
-
-	init_vmcb(vcpu);
+	init_vmcb(vcpu, init_event);
 
 	if (!init_event)
 		__svm_vcpu_reset(vcpu);
@@ -1275,7 +1211,6 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
 	struct page *vmcb01_page;
-	struct page *vmsa_page = NULL;
 	int err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
@@ -1286,24 +1221,18 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 	if (!vmcb01_page)
 		goto out;
 
-	if (sev_es_guest(vcpu->kvm)) {
-		/*
-		 * SEV-ES guests require a separate VMSA page used to contain
-		 * the encrypted register state of the guest.
-		 */
-		vmsa_page = snp_safe_alloc_page();
-		if (!vmsa_page)
-			goto error_free_vmcb_page;
-	}
+	err = sev_vcpu_create(vcpu);
+	if (err)
+		goto error_free_vmcb_page;
 
 	err = avic_init_vcpu(svm);
 	if (err)
-		goto error_free_vmsa_page;
+		goto error_free_sev;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm) {
 		err = -ENOMEM;
-		goto error_free_vmsa_page;
+		goto error_free_sev;
 	}
 
 	svm->x2avic_msrs_intercepted = true;
@@ -1312,16 +1241,12 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 	svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
 	svm_switch_vmcb(svm, &svm->vmcb01);
 
-	if (vmsa_page)
-		svm->sev_es.vmsa = page_address(vmsa_page);
-
 	svm->guest_state_loaded = false;
 
 	return 0;
 
-error_free_vmsa_page:
-	if (vmsa_page)
-		__free_page(vmsa_page);
+error_free_sev:
+	sev_free_vcpu(vcpu);
 error_free_vmcb_page:
 	__free_page(vmcb01_page);
 out:
@@ -1423,10 +1348,10 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
 	/*
-	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
-	 * available. The user return MSR support is not required in this case
-	 * because TSC_AUX is restored on #VMEXIT from the host save area
-	 * (which has been initialized in svm_enable_virtualization_cpu()).
+	 * TSC_AUX is always virtualized (context switched by hardware) for
+	 * SEV-ES guests when the feature is available.  For non-SEV-ES guests,
+	 * context switch TSC_AUX via the user_return MSR infrastructure (not
+	 * all CPUs support TSC_AUX virtualization).
 	 */
 	if (likely(tsc_aux_uret_slot >= 0) &&
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
@@ -2727,8 +2652,8 @@ static int svm_get_feature_msr(u32 msr, u64 *data)
 static bool sev_es_prevent_msr_access(struct kvm_vcpu *vcpu,
 				      struct msr_data *msr_info)
 {
-	return sev_es_guest(vcpu->kvm) &&
-	       vcpu->arch.guest_state_protected &&
+	return sev_es_guest(vcpu->kvm) && vcpu->arch.guest_state_protected &&
+	       msr_info->index != MSR_IA32_XSS &&
 	       !msr_write_intercepted(vcpu, msr_info->index);
 }
 
@@ -2784,6 +2709,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (guest_cpuid_is_intel_compatible(vcpu))
 			msr_info->data |= (u64)svm->sysenter_esp_hi << 32;
 		break;
+	case MSR_IA32_S_CET:
+		msr_info->data = svm->vmcb->save.s_cet;
+		break;
+	case MSR_IA32_INT_SSP_TAB:
+		msr_info->data = svm->vmcb->save.isst_addr;
+		break;
+	case MSR_KVM_INTERNAL_GUEST_SSP:
+		msr_info->data = svm->vmcb->save.ssp;
+		break;
 	case MSR_TSC_AUX:
 		msr_info->data = svm->tsc_aux;
 		break;
@@ -3016,13 +2950,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb01.ptr->save.sysenter_esp = (u32)data;
 		svm->sysenter_esp_hi = guest_cpuid_is_intel_compatible(vcpu) ? (data >> 32) : 0;
 		break;
+	case MSR_IA32_S_CET:
+		svm->vmcb->save.s_cet = data;
+		vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET);
+		break;
+	case MSR_IA32_INT_SSP_TAB:
+		svm->vmcb->save.isst_addr = data;
+		vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET);
+		break;
+	case MSR_KVM_INTERNAL_GUEST_SSP:
+		svm->vmcb->save.ssp = data;
+		vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET);
+		break;
 	case MSR_TSC_AUX:
 		/*
 		 * TSC_AUX is always virtualized for SEV-ES guests when the
 		 * feature is available. The user return MSR support is not
 		 * required in this case because TSC_AUX is restored on #VMEXIT
-		 * from the host save area (which has been initialized in
-		 * svm_enable_virtualization_cpu()).
+		 * from the host save area.
 		 */
 		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
 			break;
@@ -3407,6 +3352,10 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-15s %016llx %-13s %016llx\n",
 	       "rsp:", save->rsp, "rax:", save->rax);
 	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "s_cet:", save->s_cet, "ssp:", save->ssp);
+	pr_err("%-15s %016llx\n",
+	       "isst_addr:", save->isst_addr);
+	pr_err("%-15s %016llx %-13s %016llx\n",
 	       "star:", save01->star, "lstar:", save01->lstar);
 	pr_err("%-15s %016llx %-13s %016llx\n",
 	       "cstar:", save01->cstar, "sfmask:", save01->sfmask);
@@ -3431,6 +3380,13 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 		       "sev_features", vmsa->sev_features);
 
 		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "pl0_ssp:", vmsa->pl0_ssp, "pl1_ssp:", vmsa->pl1_ssp);
+		pr_err("%-15s %016llx %-13s %016llx\n",
+		       "pl2_ssp:", vmsa->pl2_ssp, "pl3_ssp:", vmsa->pl3_ssp);
+		pr_err("%-15s %016llx\n",
+		       "u_cet:", vmsa->u_cet);
+
+		pr_err("%-15s %016llx %-13s %016llx\n",
 		       "rax:", vmsa->rax, "rbx:", vmsa->rbx);
 		pr_err("%-15s %016llx %-13s %016llx\n",
 		       "rcx:", vmsa->rcx, "rdx:", vmsa->rdx);
@@ -4180,17 +4136,27 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb_control_area *control = &svm->vmcb->control;
+
+	/*
+	 * Next RIP must be provided as IRQs are disabled, and accessing guest
+	 * memory to decode the instruction might fault, i.e. might sleep.
+	 */
+	if (!nrips || !control->next_rip)
+		return EXIT_FASTPATH_NONE;
 
 	if (is_guest_mode(vcpu))
 		return EXIT_FASTPATH_NONE;
 
-	switch (svm->vmcb->control.exit_code) {
+	switch (control->exit_code) {
 	case SVM_EXIT_MSR:
-		if (!svm->vmcb->control.exit_info_1)
+		if (!control->exit_info_1)
 			break;
-		return handle_fastpath_set_msr_irqoff(vcpu);
+		return handle_fastpath_wrmsr(vcpu);
 	case SVM_EXIT_HLT:
 		return handle_fastpath_hlt(vcpu);
+	case SVM_EXIT_INVD:
+		return handle_fastpath_invd(vcpu);
 	default:
 		break;
 	}
@@ -4467,8 +4433,6 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	if (sev_guest(vcpu->kvm))
 		sev_vcpu_after_set_cpuid(svm);
-
-	svm_recalc_intercepts_after_set_cpuid(vcpu);
 }
 
 static bool svm_has_wbinvd_exit(void)
@@ -5041,7 +5005,7 @@ static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
 	return page_address(page);
 }
 
-static struct kvm_x86_ops svm_x86_ops __initdata = {
+struct kvm_x86_ops svm_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
 	.check_processor_compatibility = svm_check_processor_compat,
@@ -5170,7 +5134,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 
-	.recalc_msr_intercepts = svm_recalc_msr_intercepts,
+	.recalc_intercepts = svm_recalc_intercepts,
 	.complete_emulated_msr = svm_complete_emulated_msr,
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
@@ -5228,7 +5192,8 @@ static __init void svm_set_cpu_caps(void)
 	kvm_set_cpu_caps();
 
 	kvm_caps.supported_perf_cap = 0;
-	kvm_caps.supported_xss = 0;
+
+	kvm_cpu_cap_clear(X86_FEATURE_IBT);
 
 	/* CPUID 0x80000001 and 0x8000000A (SVM features) */
 	if (nested) {
@@ -5300,8 +5265,12 @@ static __init void svm_set_cpu_caps(void)
 	/* CPUID 0x8000001F (SME/SEV features) */
 	sev_set_cpu_caps();
 
-	/* Don't advertise Bus Lock Detect to guest if SVM support is absent */
+	/*
+	 * Clear capabilities that are automatically configured by common code,
+	 * but that require explicit SVM support (that isn't yet implemented).
+	 */
 	kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT);
+	kvm_cpu_cap_clear(X86_FEATURE_MSR_IMM);
 }
 
 static __init int svm_hardware_setup(void)
@@ -5374,6 +5343,21 @@ static __init int svm_hardware_setup(void)
 			  get_npt_level(), PG_LEVEL_1G);
 	pr_info("Nested Paging %s\n", str_enabled_disabled(npt_enabled));
 
+	/*
+	 * It seems that on AMD processors PTE's accessed bit is
+	 * being set by the CPU hardware before the NPF vmexit.
+	 * This is not expected behaviour and our tests fail because
+	 * of it.
+	 * A workaround here is to disable support for
+	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
+	 * In this case userspace can know if there is support using
+	 * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
+	 * it
+	 * If future AMD CPU models change the behaviour described above,
+	 * this variable can be changed accordingly
+	 */
+	allow_smaller_maxphyaddr = !npt_enabled;
+
 	/* Setup shadow_me_value and shadow_me_mask */
 	kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask);
 
@@ -5408,15 +5392,12 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	enable_apicv = avic = avic && avic_hardware_setup();
-
+	enable_apicv = avic_hardware_setup();
 	if (!enable_apicv) {
 		enable_ipiv = false;
 		svm_x86_ops.vcpu_blocking = NULL;
 		svm_x86_ops.vcpu_unblocking = NULL;
 		svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
-	} else if (!x2avic_enabled) {
-		svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true;
 	}
 
 	if (vls) {
@@ -5453,21 +5434,6 @@ static __init int svm_hardware_setup(void)
 
 	svm_set_cpu_caps();
 
-	/*
-	 * It seems that on AMD processors PTE's accessed bit is
-	 * being set by the CPU hardware before the NPF vmexit.
-	 * This is not expected behaviour and our tests fail because
-	 * of it.
-	 * A workaround here is to disable support for
-	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
-	 * In this case userspace can know if there is support using
-	 * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
-	 * it
-	 * If future AMD CPU models change the behaviour described above,
-	 * this variable can be changed accordingly
-	 */
-	allow_smaller_maxphyaddr = !npt_enabled;
-
 	kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED;
 	return 0;