1 files changed, 178 insertions, 50 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a713c803a3a3..67fee545d42a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -31,6 +31,7 @@
 #include <linux/string_choices.h>
 
 #include <asm/apic.h>
+#include <asm/msr.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
@@ -475,24 +476,18 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu)
 
 static void svm_init_erratum_383(void)
 {
-	u32 low, high;
-	int err;
 	u64 val;
 
 	if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
 		return;
 
 	/* Use _safe variants to not break nested virtualization */
-	val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
-	if (err)
+	if (native_read_msr_safe(MSR_AMD64_DC_CFG, &val))
 		return;
 
 	val |= (1ULL << 47);
 
-	low  = lower_32_bits(val);
-	high = upper_32_bits(val);
-
-	native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+	native_write_msr_safe(MSR_AMD64_DC_CFG, val);
 
 	erratum_383_found = true;
 }
@@ -566,7 +561,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier)
 	if (multiplier == __this_cpu_read(current_tsc_ratio))
 		return;
 
-	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	wrmsrq(MSR_AMD64_TSC_RATIO, multiplier);
 	__this_cpu_write(current_tsc_ratio, multiplier);
 }
 
@@ -579,15 +574,15 @@ static inline void kvm_cpu_svm_disable(void)
 {
 	uint64_t efer;
 
-	wrmsrl(MSR_VM_HSAVE_PA, 0);
-	rdmsrl(MSR_EFER, efer);
+	wrmsrq(MSR_VM_HSAVE_PA, 0);
+	rdmsrq(MSR_EFER, efer);
 	if (efer & EFER_SVME) {
 		/*
 		 * Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and
 		 * NMI aren't blocked.
 		 */
 		stgi();
-		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+		wrmsrq(MSR_EFER, efer & ~EFER_SVME);
 	}
 }
 
@@ -616,7 +611,7 @@ static int svm_enable_virtualization_cpu(void)
 	uint64_t efer;
 	int me = raw_smp_processor_id();
 
-	rdmsrl(MSR_EFER, efer);
+	rdmsrq(MSR_EFER, efer);
 	if (efer & EFER_SVME)
 		return -EBUSY;
 
@@ -626,9 +621,9 @@ static int svm_enable_virtualization_cpu(void)
 	sd->next_asid = sd->max_asid + 1;
 	sd->min_asid = max_sev_asid + 1;
 
-	wrmsrl(MSR_EFER, efer | EFER_SVME);
+	wrmsrq(MSR_EFER, efer | EFER_SVME);
 
-	wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa);
+	wrmsrq(MSR_VM_HSAVE_PA, sd->save_area_pa);
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		/*
@@ -649,13 +644,12 @@ static int svm_enable_virtualization_cpu(void)
 	 * erratum is present everywhere).
 	 */
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
-		uint64_t len, status = 0;
+		u64 len, status = 0;
 		int err;
 
-		len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
+		err = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &len);
 		if (!err)
-			status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
-						      &err);
+			err = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, &status);
 
 		if (err)
 			osvw_status = osvw_len = 0;
@@ -1297,8 +1291,12 @@ 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));
@@ -1508,6 +1506,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
 }
 
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+	struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+	if (!sd->bp_spec_reduce_set)
+		return;
+
+	msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	if (atomic_dec_return(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	/*
+	 * Verify a new VM didn't come along, acquire the lock, and increment
+	 * the count before this task acquired the lock.
+	 */
+	if (atomic_read(&srso_nr_vms))
+		return;
+
+	on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	/*
+	 * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+	 * transition, i.e. destroying the last VM, is fully complete, e.g. so
+	 * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+	 */
+	if (atomic_inc_not_zero(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
 static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1540,6 +1595,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+	    !sd->bp_spec_reduce_set) {
+		sd->bp_spec_reduce_set = true;
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	}
 	svm->guest_state_loaded = true;
 }
 
@@ -1559,7 +1619,8 @@ 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 +1993,7 @@ 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,
@@ -2138,14 +2199,13 @@ static int ac_interception(struct kvm_vcpu *vcpu)
 
 static bool is_erratum_383(void)
 {
-	int err, i;
+	int i;
 	u64 value;
 
 	if (!erratum_383_found)
 		return false;
 
-	value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
-	if (err)
+	if (native_read_msr_safe(MSR_IA32_MC0_STATUS, &value))
 		return false;
 
 	/* Bit 62 may or may not be set for this mce */
@@ -2156,17 +2216,11 @@ static bool is_erratum_383(void)
 
 	/* Clear MCi_STATUS registers */
 	for (i = 0; i < 6; ++i)
-		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
-
-	value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
-	if (!err) {
-		u32 low, high;
+		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0);
 
+	if (!native_read_msr_safe(MSR_IA32_MCG_STATUS, &value)) {
 		value &= ~(1ULL << 2);
-		low    = lower_32_bits(value);
-		high   = upper_32_bits(value);
-
-		native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+		native_write_msr_safe(MSR_IA32_MCG_STATUS, value);
 	}
 
 	/* Flush tlb to evict multi-match entries */
@@ -2220,6 +2274,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	 */
 	if (!sev_es_guest(vcpu->kvm)) {
 		clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+		if (is_smm(vcpu))
+			kvm_smm_changed(vcpu, false);
+#endif
 		kvm_vcpu_reset(vcpu, true);
 	}
 
@@ -2973,11 +3031,7 @@ 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 +3219,27 @@ 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 +3347,17 @@ 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 +3428,7 @@ 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 +3591,7 @@ 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 +3674,7 @@ 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 +3696,8 @@ 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 +4205,23 @@ 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 +4281,18 @@ 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 +4301,8 @@ 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 +4337,12 @@ 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);
 
@@ -4253,6 +4364,16 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	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);
 
 	/*
@@ -4280,6 +4401,10 @@ 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();
 
@@ -4958,6 +5083,8 @@ static void svm_vm_destroy(struct kvm *kvm)
 {
 	avic_vm_destroy(kvm);
 	sev_vm_destroy(kvm);
+
+	svm_srso_vm_destroy();
 }
 
 static int svm_vm_init(struct kvm *kvm)
@@ -4983,6 +5110,7 @@ static int svm_vm_init(struct kvm *kvm)
 			return ret;
 	}
 
+	svm_srso_vm_init();
 	return 0;
 }
 
@@ -5154,7 +5282,7 @@ static __init void svm_adjust_mmio_mask(void)
 		return;
 
 	/* If memory encryption is not enabled, use existing mask */
-	rdmsrl(MSR_AMD64_SYSCFG, msr);
+	rdmsrq(MSR_AMD64_SYSCFG, msr);
 	if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 		return;