1 files changed, 102 insertions, 25 deletions
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7640a84e554a..d5d0c5c3300b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,6 +607,9 @@ static void svm_disable_virtualization_cpu(void)
 	kvm_cpu_svm_disable();
 
 	amd_pmu_disable_virt();
+
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
 }
 
 static int svm_enable_virtualization_cpu(void)
@@ -684,6 +687,9 @@ static int svm_enable_virtualization_cpu(void)
 		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
 	}
 
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+
 	return 0;
 }
 
@@ -1297,8 +1303,12 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm_set_intercept(svm, INTERCEPT_MWAIT);
 	}
 
-	if (!kvm_hlt_in_guest(vcpu->kvm))
-		svm_set_intercept(svm, INTERCEPT_HLT);
+	if (!kvm_hlt_in_guest(vcpu->kvm)) {
+		if (cpu_feature_enabled(X86_FEATURE_IDLE_HLT))
+			svm_set_intercept(svm, INTERCEPT_IDLE_HLT);
+		else
+			svm_set_intercept(svm, INTERCEPT_HLT);
+	}
 
 	control->iopm_base_pa = iopm_base;
 	control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
@@ -1559,7 +1569,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 
-		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT))
+		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
+		    static_branch_likely(&switch_vcpu_ibpb))
 			indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
@@ -1932,7 +1943,7 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
 
 	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 }
 
 static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -1991,11 +2002,11 @@ 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)) {
@@ -2973,11 +2984,7 @@ static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
 	if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb))
 		return kvm_complete_insn_gp(vcpu, err);
 
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb,
-				X86_TRAP_GP |
-				SVM_EVTINJ_TYPE_EXEPT |
-				SVM_EVTINJ_VALID);
+	svm_vmgexit_inject_exception(svm, X86_TRAP_GP);
 	return 1;
 }
 
@@ -3165,6 +3172,27 @@ 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;
 
@@ -3272,6 +3300,17 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	type = svm->vmcb->control.exit_info_2;
 	gva = svm->vmcb->control.exit_info_1;
 
+	/*
+	 * FIXME: Perform segment checks for 32-bit mode, and inject #SS if the
+	 *        stack segment is used.  The intercept takes priority over all
+	 *        #GP checks except CPL>0, but somehow still generates a linear
+	 *        address?  The APM is sorely lacking.
+	 */
+	if (is_noncanonical_address(gva, vcpu, 0)) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
+
 	return kvm_handle_invpcid(vcpu, type, gva);
 }
 
@@ -3342,6 +3381,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_CR4_WRITE_TRAP]		= cr_trap,
 	[SVM_EXIT_CR8_WRITE_TRAP]		= cr_trap,
 	[SVM_EXIT_INVPCID]                      = invpcid_interception,
+	[SVM_EXIT_IDLE_HLT]			= kvm_emulate_halt,
 	[SVM_EXIT_NPF]				= npf_interception,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
@@ -3504,7 +3544,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 		return interrupt_window_interception(vcpu);
 	else if (exit_code == SVM_EXIT_INTR)
 		return intr_interception(vcpu);
-	else if (exit_code == SVM_EXIT_HLT)
+	else if (exit_code == SVM_EXIT_HLT || exit_code == SVM_EXIT_IDLE_HLT)
 		return kvm_emulate_halt(vcpu);
 	else if (exit_code == SVM_EXIT_NPF)
 		return npf_interception(vcpu);
@@ -3587,7 +3627,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	return svm_invoke_exit_handler(vcpu, exit_code);
 }
 
-static void pre_svm_run(struct kvm_vcpu *vcpu)
+static int pre_svm_run(struct kvm_vcpu *vcpu)
 {
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3609,6 +3649,8 @@ static void pre_svm_run(struct kvm_vcpu *vcpu)
 	/* FIXME: handle wraparound of asid_generation */
 	if (svm->current_vmcb->asid_generation != sd->asid_generation)
 		new_asid(svm, sd);
+
+	return 0;
 }
 
 static void svm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -4116,20 +4158,23 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 		vcpu->arch.nmi_injected = true;
 		svm->nmi_l1_to_l2 = nmi_l1_to_l2;
 		break;
-	case SVM_EXITINTINFO_TYPE_EXEPT:
+	case SVM_EXITINTINFO_TYPE_EXEPT: {
+		u32 error_code = 0;
+
 		/*
 		 * Never re-inject a #VC exception.
 		 */
 		if (vector == X86_TRAP_VC)
 			break;
 
-		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
-			u32 err = svm->vmcb->control.exit_int_info_err;
-			kvm_requeue_exception_e(vcpu, vector, err);
+		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR)
+			error_code = svm->vmcb->control.exit_int_info_err;
 
-		} else
-			kvm_requeue_exception(vcpu, vector);
+		kvm_requeue_exception(vcpu, vector,
+				      exitintinfo & SVM_EXITINTINFO_VALID_ERR,
+				      error_code);
 		break;
+	}
 	case SVM_EXITINTINFO_TYPE_INTR:
 		kvm_queue_interrupt(vcpu, vector, false);
 		break;
@@ -4189,6 +4234,18 @@ 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))
@@ -4197,6 +4254,8 @@ 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();
 }
 
@@ -4231,7 +4290,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (force_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
-	pre_svm_run(vcpu);
+	if (pre_svm_run(vcpu)) {
+		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		vcpu->run->fail_entry.hardware_entry_failure_reason = SVM_EXIT_ERR;
+		vcpu->run->fail_entry.cpu = vcpu->cpu;
+		return EXIT_FASTPATH_EXIT_USERSPACE;
+	}
 
 	sync_lapic_to_cr8(vcpu);
 
@@ -4247,14 +4311,22 @@ 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);
 
 	/*
@@ -4282,6 +4354,10 @@ 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();
 
@@ -5043,6 +5119,7 @@ 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,