1 files changed, 98 insertions, 42 deletions
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 21dacd312779..e67de787fc71 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -28,6 +28,7 @@
 #include <linux/rwsem.h>
 #include <linux/cc_platform.h>
 #include <linux/smp.h>
+#include <linux/string_choices.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
@@ -284,8 +285,6 @@ u32 svm_msrpm_offset(u32 msr)
 	return MSR_INVALID;
 }
 
-static void svm_flush_tlb_current(struct kvm_vcpu *vcpu);
-
 static int get_npt_level(void)
 {
 #ifdef CONFIG_X86_64
@@ -1049,7 +1048,7 @@ void svm_update_lbrv(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK;
 	bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) ||
-			    (is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV) &&
+			    (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
 			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
 	if (enable_lbrv == current_enable_lbrv)
@@ -1187,14 +1186,14 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 	 */
 	if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
 		if (!npt_enabled ||
-		    !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID))
+		    !guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_INVPCID))
 			svm_set_intercept(svm, INTERCEPT_INVPCID);
 		else
 			svm_clr_intercept(svm, INTERCEPT_INVPCID);
 	}
 
 	if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) {
-		if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP))
 			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
 		else
 			svm_set_intercept(svm, INTERCEPT_RDTSCP);
@@ -1921,9 +1920,6 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
 	unsigned long old_cr4 = vcpu->arch.cr4;
 
-	if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
-		svm_flush_tlb_current(vcpu);
-
 	vcpu->arch.cr4 = cr4;
 	if (!npt_enabled) {
 		cr4 |= X86_CR4_PAE;
@@ -1995,11 +1991,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 	svm->asid = sd->next_asid++;
 }
 
-static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
+static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
 {
-	struct vmcb *vmcb = svm->vmcb;
+	struct vmcb *vmcb = to_svm(vcpu)->vmcb;
 
-	if (svm->vcpu.arch.guest_state_protected)
+	if (vcpu->arch.guest_state_protected)
 		return;
 
 	if (unlikely(value != vmcb->save.dr6)) {
@@ -2864,7 +2860,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	switch (msr_info->index) {
 	case MSR_AMD64_TSC_RATIO:
 		if (!msr_info->host_initiated &&
-		    !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR))
+		    !guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR))
 			return 1;
 		msr_info->data = svm->tsc_ratio_msr;
 		break;
@@ -2940,7 +2936,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+		    !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD))
 			return 1;
 
 		msr_info->data = svm->virt_spec_ctrl;
@@ -3024,7 +3020,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:
 
-		if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) {
+		if (!guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR)) {
 
 			if (!msr->host_initiated)
 				return 1;
@@ -3046,7 +3042,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 		svm->tsc_ratio_msr = data;
 
-		if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) &&
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) &&
 		    is_guest_mode(vcpu))
 			nested_svm_update_tsc_ratio_msr(vcpu);
 
@@ -3091,7 +3087,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+		    !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD))
 			return 1;
 
 		if (data & ~SPEC_CTRL_SSBD)
@@ -3169,6 +3165,27 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 			break;
 		}
+
+		/*
+		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
+		 * without BusLockTrap, bits 5:2 control "external pins", but
+		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
+		 * the guest to set bits 5:2 despite not actually virtualizing
+		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
+		 * 5:2 for backwards compatibility.
+		 */
+		data &= ~GENMASK(5, 2);
+
+		/*
+		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+		 * way to communicate lack of support to the guest.
+		 */
+		if (data & DEBUGCTLMSR_BTF) {
+			kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+			data &= ~DEBUGCTLMSR_BTF;
+		}
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
@@ -3263,7 +3280,7 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	unsigned long type;
 	gva_t gva;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -3533,6 +3550,21 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 		*error_code = 0;
 }
 
+static void svm_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info,
+			       u32 *error_code)
+{
+	struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;
+
+	*intr_info = control->event_inj;
+
+	if ((*intr_info & SVM_EXITINTINFO_VALID) &&
+	    (*intr_info & SVM_EXITINTINFO_VALID_ERR))
+		*error_code = control->event_inj_err;
+	else
+		*error_code = 0;
+
+}
+
 static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4178,6 +4210,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	/*
+	 * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+	 * VMRUN controls whether or not physical IRQs are masked (KVM always
+	 * runs with V_INTR_MASKING_MASK).  Toggle RFLAGS.IF here to avoid the
+	 * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+	 * into guest state if delivery of an event during VMRUN triggers a
+	 * #VMEXIT, and the guest_state transitions already tell lockdep that
+	 * IRQs are being enabled/disabled.  Note!  GIF=0 for the entirety of
+	 * this path, so IRQs aren't actually unmasked while running host code.
+	 */
+	raw_local_irq_enable();
+
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
@@ -4186,6 +4230,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
+	raw_local_irq_disable();
+
 	guest_state_exit_irqoff();
 }
 
@@ -4236,14 +4282,22 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
 	 * of a #DB.
 	 */
-	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
-		svm_set_dr6(svm, vcpu->arch.dr6);
-	else
-		svm_set_dr6(svm, DR6_ACTIVE_LOW);
+	if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+		svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
 
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
+	/*
+	 * Hardware only context switches DEBUGCTL if LBR virtualization is
+	 * enabled.  Manually load DEBUGCTL if necessary (and restore it after
+	 * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+	 * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+	 */
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(svm->vmcb->save.dbgctl);
+
 	kvm_wait_lapic_expire(vcpu);
 
 	/*
@@ -4271,6 +4325,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
+
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
@@ -4392,27 +4450,17 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * XSS on VM-Enter/VM-Exit.  Failure to do so would effectively give
 	 * the guest read/write access to the host's XSS.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVE) &&
-	    boot_cpu_has(X86_FEATURE_XSAVES) &&
-	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVE))
-		kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES);
-
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS);
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR);
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV);
+	guest_cpu_cap_change(vcpu, X86_FEATURE_XSAVES,
+			     boot_cpu_has(X86_FEATURE_XSAVES) &&
+			     guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE));
 
 	/*
 	 * Intercept VMLOAD if the vCPU model is Intel in order to emulate that
 	 * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing
 	 * SVM on Intel is bonkers and extremely unlikely to work).
 	 */
-	if (!guest_cpuid_is_intel_compatible(vcpu))
-		kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
-
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER);
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD);
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF);
-	kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI);
+	if (guest_cpuid_is_intel_compatible(vcpu))
+		guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
 
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
@@ -4422,7 +4470,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
-				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
+				     !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
 	if (sev_guest(vcpu->kvm))
 		sev_vcpu_after_set_cpuid(svm);
@@ -4673,7 +4721,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
 	 * responsible for ensuring nested SVM and SMIs are mutually exclusive.
 	 */
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		return 1;
 
 	smram->smram64.svm_guest_flag = 1;
@@ -4720,14 +4768,14 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 
 	const struct kvm_smram_state_64 *smram64 = &smram->smram64;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM))
 		return 0;
 
 	/* Non-zero if SMI arrived while vCPU was in guest mode. */
 	if (!smram64->svm_guest_flag)
 		return 0;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SVM))
 		return 1;
 
 	if (!(smram64->efer & EFER_SVME))
@@ -4790,9 +4838,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
 static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 					 void *insn, int insn_len)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
 	bool smep, smap, is_user;
 	u64 error_code;
 
+	/* Check that emulation is possible during event vectoring */
+	if ((svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK) &&
+	    !kvm_can_emulate_event_vectoring(emul_type))
+		return X86EMUL_UNHANDLEABLE_VECTORING;
+
 	/* Emulation is always possible when KVM has access to all guest state. */
 	if (!sev_guest(vcpu->kvm))
 		return X86EMUL_CONTINUE;
@@ -4889,7 +4943,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * In addition, don't apply the erratum workaround if the #NPF occurred
 	 * while translating guest page tables (see below).
 	 */
-	error_code = to_svm(vcpu)->vmcb->control.exit_info_1;
+	error_code = svm->vmcb->control.exit_info_1;
 	if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK))
 		goto resume_guest;
 
@@ -5036,6 +5090,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
+	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
@@ -5077,6 +5132,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS,
 
 	.get_exit_info = svm_get_exit_info,
+	.get_entry_info = svm_get_entry_info,
 
 	.vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid,
 
@@ -5328,7 +5384,7 @@ static __init int svm_hardware_setup(void)
 	/* Force VM NPT level equal to the host's paging level */
 	kvm_configure_mmu(npt_enabled, get_npt_level(),
 			  get_npt_level(), PG_LEVEL_1G);
-	pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
+	pr_info("Nested Paging %s\n", str_enabled_disabled(npt_enabled));
 
 	/* Setup shadow_me_value and shadow_me_mask */
 	kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask);