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

Pull KVM fixes from Paolo Bonzini:
 "Many patches, pretty much all of them small, that accumulated while I
  was on vacation.

  ARM:

   - Remove the last leftovers of the ill-fated FPSIMD host state
     mapping at EL2 stage-1

   - Fix unexpected advertisement to the guest of unimplemented S2 base
     granule sizes

   - Gracefully fail initialising pKVM if the interrupt controller isn't
     GICv3

   - Also gracefully fail initialising pKVM if the carveout allocation
     fails

   - Fix the computing of the minimum MMIO range required for the host
     on stage-2 fault

   - Fix the generation of the GICv3 Maintenance Interrupt in nested
     mode

  x86:

   - Reject SEV{-ES} intra-host migration if one or more vCPUs are
     actively being created, so as not to create a non-SEV{-ES} vCPU in
     an SEV{-ES} VM

   - Use a pre-allocated, per-vCPU buffer for handling de-sparsification
     of vCPU masks in Hyper-V hypercalls; fixes a "stack frame too
     large" issue

   - Allow out-of-range/invalid Xen event channel ports when configuring
     IRQ routing, to avoid dictating a specific ioctl() ordering to
     userspace

   - Conditionally reschedule when setting memory attributes to avoid
     soft lockups when userspace converts huge swaths of memory to/from
     private

   - Add back MWAIT as a required feature for the MONITOR/MWAIT selftest

   - Add a missing field in struct sev_data_snp_launch_start that
     resulted in the guest-visible workarounds field being filled at the
     wrong offset

   - Skip non-canonical address when processing Hyper-V PV TLB flushes
     to avoid VM-Fail on INVVPID

   - Advertise supported TDX TDVMCALLs to userspace

   - Pass SetupEventNotifyInterrupt arguments to userspace

   - Fix TSC frequency underflow"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: avoid underflow when scaling TSC frequency
  KVM: arm64: Remove kvm_arch_vcpu_run_map_fp()
  KVM: arm64: Fix handling of FEAT_GTG for unimplemented granule sizes
  KVM: arm64: Don't free hyp pages with pKVM on GICv2
  KVM: arm64: Fix error path in init_hyp_mode()
  KVM: arm64: Adjust range correctly during host stage-2 faults
  KVM: arm64: nv: Fix MI line level calculation in vgic_v3_nested_update_mi()
  KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush
  KVM: SVM: Add missing member in SNP_LAUNCH_START command structure
  Documentation: KVM: Fix unexpected unindent warnings
  KVM: selftests: Add back the missing check of MONITOR/MWAIT availability
  KVM: Allow CPU to reschedule while setting per-page memory attributes
  KVM: x86/xen: Allow 'out of range' event channel ports in IRQ routing table.
  KVM: x86/hyper-v: Use preallocated per-vCPU buffer for de-sparsified vCPU masks
  KVM: SVM: Initialize vmsa_pa in VMCB to INVALID_PAGE if VMSA page is NULL
  KVM: SVM: Reject SEV{-ES} intra host migration if vCPU creation is in-flight
  KVM: TDX: Report supported optional TDVMCALLs in TDX capabilities
  KVM: TDX: Exit to userspace for SetupEventNotifyInterrupt

5 files changed, 60 insertions, 6 deletions

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..ee27064dd72f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1979,6 +1979,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
+		if (is_noncanonical_invlpg_address(entries[i], vcpu))
+			continue;
+
 		/*
 		 * Lower 12 bits of 'address' encode the number of additional
 		 * pages to flush.
@@ -2001,11 +2004,11 @@ out_flush_all:
 static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
 	u64 *sparse_banks = hv_vcpu->sparse_banks;
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
-	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
 	/*
 	 * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 459c3b791fd4..b201f77fcd49 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
 	struct kvm_vcpu *src_vcpu;
 	unsigned long i;
 
+	if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+	    dst->created_vcpus != atomic_read(&dst->online_vcpus))
+		return -EBUSY;
+
 	if (!sev_es_guest(src))
 		return 0;
 
@@ -4445,8 +4449,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	 * the VMSA will be NULL if this vCPU is the destination for intrahost
 	 * migration, and will be copied later.
 	 */
-	if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
-		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+	if (!svm->sev_es.snp_has_guest_vmsa) {
+		if (svm->sev_es.vmsa)
+			svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+		else
+			svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+	}
 
 	if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
 		svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 1ad20c273f3b..f31ccdeb905b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,6 +173,9 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
 	tdx_clear_unsupported_cpuid(entry);
 }
 
+#define TDVMCALLINFO_GET_QUOTE				BIT(0)
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT	BIT(1)
+
 static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
 			     struct kvm_tdx_capabilities *caps)
 {
@@ -188,6 +191,10 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
 
 	caps->cpuid.nent = td_conf->num_cpuid_config;
 
+	caps->user_tdvmcallinfo_1_r11 =
+		TDVMCALLINFO_GET_QUOTE |
+		TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
 	for (i = 0; i < td_conf->num_cpuid_config; i++)
 		td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
 
@@ -1530,6 +1537,27 @@ static int tdx_get_quote(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 vector = tdx->vp_enter_args.r12;
+
+	if (vector < 32 || vector > 255) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_TDX;
+	vcpu->run->tdx.flags = 0;
+	vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+	vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+	vcpu->run->tdx.setup_event_notify.vector = vector;
+
+	vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+	return 0;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	switch (tdvmcall_leaf(vcpu)) {
@@ -1541,6 +1569,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		return tdx_get_td_vm_call_info(vcpu);
 	case TDVMCALL_GET_QUOTE:
 		return tdx_get_quote(vcpu);
+	case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+		return tdx_setup_event_notify_interrupt(vcpu);
 	default:
 		break;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a9d992d5652f..357b9e3a6cef 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,9 +3258,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* With all the info we got, fill in the values */
 
-	if (kvm_caps.has_tsc_control)
+	if (kvm_caps.has_tsc_control) {
 		tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
 					    v->arch.l1_tsc_scaling_ratio);
+		tgt_tsc_khz = tgt_tsc_khz ? : 1;
+	}
 
 	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9b029bb29a16..5fa2cca43653 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 
-	if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
-		return -EINVAL;
+	/*
+	 * Don't check for the port being within range of max_evtchn_port().
+	 * Userspace can configure what ever targets it likes; events just won't
+	 * be delivered if/while the target is invalid, just like userspace can
+	 * configure MSIs which target non-existent APICs.
+	 *
+	 * This allow on Live Migration and Live Update, the IRQ routing table
+	 * can be restored *independently* of other things like creating vCPUs,
+	 * without imposing an ordering dependency on userspace.  In this
+	 * particular case, the problematic ordering would be with setting the
+	 * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+	 * instead of 1024 event channels.
+	 */
 
 	/* We only support 2 level event channels for now */
 	if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)