Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more kvm fixes from Paolo Bonzini:

 - Static analysis fix

 - New SEV-ES protocol for communicating invalid VMGEXIT requests

 - Ensure APICv is considered inactive if there is no APIC

 - Fix reserved bits for AMD PerfEvtSeln register

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: SVM: Do not terminate SEV-ES guests on GHCB validation failure
  KVM: SEV: Fall back to vmalloc for SEV-ES scratch area if necessary
  KVM: SEV: Return appropriate error codes if SEV-ES scratch setup fails
  KVM: x86/mmu: Retry page fault if root is invalidated by memslot update
  KVM: VMX: Set failure code in prepare_vmcs02()
  KVM: ensure APICv is considered inactive if there is no APIC
  KVM: x86/pmu: Fix reserved bits for AMD PerfEvtSeln register

10 files changed, 106 insertions, 51 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6ac61f85e07b..860ed500580c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1036,6 +1036,7 @@ struct kvm_x86_msr_filter {
 #define APICV_INHIBIT_REASON_PIT_REINJ  4
 #define APICV_INHIBIT_REASON_X2APIC	5
 #define APICV_INHIBIT_REASON_BLOCKIRQ	6
+#define APICV_INHIBIT_REASON_ABSENT	7
 
 struct kvm_arch {
 	unsigned long n_used_mmu_pages;
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 2cef6c5a52c2..6acaf5af0a3d 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -73,4 +73,15 @@
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
+/*
+ * Error codes related to GHCB input that can be communicated back to the guest
+ * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2.
+ */
+#define GHCB_ERR_NOT_REGISTERED		1
+#define GHCB_ERR_INVALID_USAGE		2
+#define GHCB_ERR_INVALID_SCRATCH_AREA	3
+#define GHCB_ERR_MISSING_INPUT		4
+#define GHCB_ERR_INVALID_INPUT		5
+#define GHCB_ERR_INVALID_EVENT		6
+
 #endif
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 6354297e92ae..e2e1d012df22 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { }
 
 static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	return sp->role.invalid ||
+	if (sp->role.invalid)
+		return true;
+
+	/* TDP MMU pages due not use the MMU generation. */
+	return !sp->tdp_mmu_page &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
@@ -3976,6 +3980,20 @@ out_retry:
 	return true;
 }
 
+/*
+ * Returns true if the page fault is stale and needs to be retried, i.e. if the
+ * root was invalidated by a memslot update or a relevant mmu_notifier fired.
+ */
+static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
+				struct kvm_page_fault *fault, int mmu_seq)
+{
+	if (is_obsolete_sp(vcpu->kvm, to_shadow_page(vcpu->arch.mmu->root_hpa)))
+		return true;
+
+	return fault->slot &&
+	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+}
+
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
@@ -4013,8 +4031,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
+
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f87d36898c44..708a5d297fe1 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 9d6066eb7c10..8f9af7b7dbbe 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -900,6 +900,7 @@ out:
 bool svm_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 871c426ec389..b4095dfeeee6 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -281,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->reserved_bits = 0xfffffff000280000ull;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 59727a966f90..7656a2c5662a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2260,7 +2260,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
 	if (svm->sev_es.ghcb_sa_free)
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 }
 
 static void dump_ghcb(struct vcpu_svm *svm)
@@ -2352,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+static bool sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu;
 	struct ghcb *ghcb;
-	u64 exit_code = 0;
+	u64 exit_code;
+	u64 reason;
 
 	ghcb = svm->sev_es.ghcb;
 
-	/* Only GHCB Usage code 0 is supported */
-	if (ghcb->ghcb_usage)
-		goto vmgexit_err;
-
 	/*
-	 * Retrieve the exit code now even though is may not be marked valid
+	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage) {
+		reason = GHCB_ERR_INVALID_USAGE;
+		goto vmgexit_err;
+	}
+
+	reason = GHCB_ERR_MISSING_INPUT;
+
 	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_2_is_valid(ghcb))
@@ -2448,30 +2453,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		break;
 	default:
+		reason = GHCB_ERR_INVALID_EVENT;
 		goto vmgexit_err;
 	}
 
-	return 0;
+	return true;
 
 vmgexit_err:
 	vcpu = &svm->vcpu;
 
-	if (ghcb->ghcb_usage) {
+	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    ghcb->ghcb_usage);
+	} else if (reason == GHCB_ERR_INVALID_EVENT) {
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
+			    exit_code);
 	} else {
-		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
 			    exit_code);
 		dump_ghcb(svm);
 	}
 
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-	vcpu->run->internal.ndata = 2;
-	vcpu->run->internal.data[0] = exit_code;
-	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+	/* Clear the valid entries fields */
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, reason);
 
-	return -EINVAL;
+	return false;
 }
 
 void sev_es_unmap_ghcb(struct vcpu_svm *svm)
@@ -2493,7 +2502,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 			svm->sev_es.ghcb_sa_sync = false;
 		}
 
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 		svm->sev_es.ghcb_sa = NULL;
 		svm->sev_es.ghcb_sa_free = false;
 	}
@@ -2541,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
-		return false;
+		goto e_scratch;
 	}
 
 	scratch_gpa_end = scratch_gpa_beg + len;
 	if (scratch_gpa_end < scratch_gpa_beg) {
 		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
 		       len, scratch_gpa_beg);
-		return false;
+		goto e_scratch;
 	}
 
 	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
@@ -2566,7 +2575,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		    scratch_gpa_end > ghcb_scratch_end) {
 			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
 			       scratch_gpa_beg, scratch_gpa_end);
-			return false;
+			goto e_scratch;
 		}
 
 		scratch_va = (void *)svm->sev_es.ghcb;
@@ -2579,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		if (len > GHCB_SCRATCH_AREA_LIMIT) {
 			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
 			       len, GHCB_SCRATCH_AREA_LIMIT);
-			return false;
+			goto e_scratch;
 		}
-		scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT);
+		scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT);
 		if (!scratch_va)
-			return false;
+			goto e_scratch;
 
 		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
 			/* Unable to copy scratch area from guest */
 			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
 
-			kfree(scratch_va);
-			return false;
+			kvfree(scratch_va);
+			goto e_scratch;
 		}
 
 		/*
@@ -2607,6 +2616,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	svm->sev_es.ghcb_sa_len = len;
 
 	return true;
+
+e_scratch:
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+
+	return false;
 }
 
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
@@ -2657,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 
 		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID);
 		if (!ret) {
-			ret = -EINVAL;
+			/* Error, keep GHCB MSR value as-is */
 			break;
 		}
 
@@ -2693,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 						GHCB_MSR_TERM_REASON_POS);
 		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
 			reason_set, reason_code);
-		fallthrough;
+
+		ret = -EINVAL;
+		break;
 	}
 	default:
-		ret = -EINVAL;
+		/* Error, keep GHCB MSR value as-is */
+		break;
 	}
 
 	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
@@ -2720,14 +2738,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	if (!ghcb_gpa) {
 		vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n");
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
 		/* Unable to map GHCB from guest */
 		vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
 			    ghcb_gpa);
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
@@ -2737,15 +2759,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
-	ret = sev_es_validate_vmgexit(svm);
-	if (ret)
-		return ret;
+	if (!sev_es_validate_vmgexit(svm))
+		return 1;
 
 	sev_es_sync_from_ghcb(svm);
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	ret = -EINVAL;
+	ret = 1;
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
@@ -2786,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(ghcb, 1);
-			ghcb_set_sw_exit_info_2(ghcb,
-						X86_TRAP_UD |
-						SVM_EVTINJ_TYPE_EXEPT |
-						SVM_EVTINJ_VALID);
+			ghcb_set_sw_exit_info_1(ghcb, 2);
+			ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT);
 		}
 
-		ret = 1;
 		break;
 	}
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
+		ret = -EINVAL;
 		break;
 	default:
 		ret = svm_invoke_exit_handler(vcpu, exit_code);
@@ -2821,7 +2839,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 		return -EINVAL;
 
 	if (!setup_vmgexit_scratch(svm, in, bytes))
-		return -EINVAL;
+		return 1;
 
 	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
 				    count, in);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 64f2828035c2..9c941535f78c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2591,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				     vmcs12->guest_ia32_perf_global_ctrl)))
+				     vmcs12->guest_ia32_perf_global_ctrl))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
+	}
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f90448809690..9453743ce0c4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7525,6 +7525,7 @@ static void hardware_unsetup(void)
 static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0ee1a039b490..e0aa4dd53c7f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5740,6 +5740,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
 		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 		r = 0;
 split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
@@ -6120,6 +6121,7 @@ set_identity_unlock:
 		/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -8818,10 +8820,9 @@ static void kvm_apicv_init(struct kvm *kvm)
 {
 	init_rwsem(&kvm->arch.apicv_update_lock);
 
-	if (enable_apicv)
-		clear_bit(APICV_INHIBIT_REASON_DISABLE,
-			  &kvm->arch.apicv_inhibit_reasons);
-	else
+	set_bit(APICV_INHIBIT_REASON_ABSENT,
+		&kvm->arch.apicv_inhibit_reasons);
+	if (!enable_apicv)
 		set_bit(APICV_INHIBIT_REASON_DISABLE,
 			&kvm->arch.apicv_inhibit_reasons);
 }