Merge v7.1.5linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

5 files changed, 49 insertions, 43 deletions

diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 9519fec09ee6..c5c2f778c669 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -488,8 +488,10 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 
 	if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) {
 		ret = kvm_pi_update_irte(irqfd, &irqfd->irq_entry);
-		if (ret)
+		if (ret) {
 			kvm->arch.nr_possible_bypass_irqs--;
+			irqfd->producer = NULL;
+		}
 	}
 	spin_unlock_irq(&kvm->irqfds.lock);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 92a1e69c5962..d806abaeda3d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -3371,6 +3371,12 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
 					struct kvm_lapic *apic)
 {
 	int vector;
+
+	if (unlikely(!pv_eoi_enabled(vcpu))) {
+		__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
+		return;
+	}
+
 	/*
 	 * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host
 	 * and KVM_PV_EOI_ENABLED in guest memory as follows:
@@ -3382,8 +3388,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
 	 * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset:
 	 * 	-> host enabled PV EOI, guest executed EOI.
 	 */
-	BUG_ON(!pv_eoi_enabled(vcpu));
-
 	if (pv_eoi_test_and_clr_pending(vcpu))
 		return;
 	vector = apic_set_eoi(apic);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index d90f5a41e340..996f398a577f 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2142,8 +2142,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	if (ret)
 		return ret;
 
+	/* Do not allow SNP VM migration until additional state transfer is implemented  */
 	if (kvm->arch.vm_type != source_kvm->arch.vm_type ||
-	    sev_guest(kvm) || !sev_guest(source_kvm)) {
+	    sev_guest(kvm) || !sev_guest(source_kvm) || sev_snp_guest(source_kvm)) {
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -2865,8 +2866,9 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	 * disallow out-of-band SEV/SEV-ES init if the target is already an
 	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
 	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 * Also do not allow SNP VM mirroring until additional state transfer is implemented.
 	 */
-	if (sev_guest(kvm) || !sev_guest(source_kvm) ||
+	if (sev_guest(kvm) || !sev_guest(source_kvm) || sev_snp_guest(source_kvm) ||
 	    is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
 		goto e_unlock;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 3fe88f29be7a..52ab52b0e1cc 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -553,6 +553,9 @@ static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
 						struct vmcs12 *vmcs12)
 {
+	gpa_t vtpr_gpa = vmcs12->virtual_apic_page_addr + APIC_TASKPRI;
+	u32 vtpr;
+
 	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
 		return 0;
 
@@ -562,6 +565,32 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
 	if (CC(!nested_cpu_has_vid(vmcs12) && vmcs12->tpr_threshold >> 4))
 		return -EINVAL;
 
+	/*
+	 * Do the illegal vTPR vs. TPR Threshold consistency check if and only
+	 * if KVM is configured to WARN on missed consistency checks, otherwise
+	 * it's a waste of time.  KVM needs to rely on hardware to fully detect
+	 * an illegal combination due to the vTPR being writable by L1 at all
+	 * times (it's an in-memory value, not a VMCS field).  I.e. even if the
+	 * check passes now, it might fail at the actual VM-Enter.
+	 *
+	 * If reading guest memory fails, skip the check as KVM's de facto ABI
+	 * for VMX instruction accesses to non-existent memory is to provide
+	 * PCI Bus Error semantics (reads return 0xFFs), in which case the vTPR
+	 * is guaranteed to greater than or equal to the threshold.
+	 *
+	 * Note!  Deliberately use the VM-scoped API when reading guest memory,
+	 * to ensure the read doesn't hit SMRAM when restoring L2 state on RSM,
+	 * and only perform the check when in KVM_RUN, to avoid a false failure
+	 * if userspace hasn't yet configured memslots during state restore.
+	 */
+	if (warn_on_missed_cc && vcpu->wants_to_run &&
+	    nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) &&
+	    !nested_cpu_has_vid(vmcs12) &&
+	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !kvm_read_guest(vcpu->kvm, vtpr_gpa, &vtpr, sizeof(vtpr)) &&
+	    CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > ((vtpr >> 4) & GENMASK(3, 0))))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -3085,38 +3114,6 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static int nested_vmx_check_controls_late(struct kvm_vcpu *vcpu,
-					  struct vmcs12 *vmcs12)
-{
-	void *vapic = to_vmx(vcpu)->nested.virtual_apic_map.hva;
-	u32 vtpr = vapic ? (*(u32 *)(vapic + APIC_TASKPRI)) >> 4 : 0;
-
-	/*
-	 * Don't bother with the consistency checks if KVM isn't configured to
-	 * WARN on missed consistency checks, as KVM needs to rely on hardware
-	 * to fully detect an illegal vTPR vs. TRP Threshold combination due to
-	 * the vTPR being writable by L1 at all times (it's an in-memory value,
-	 * not a VMCS field).  I.e. even if the check passes now, it might fail
-	 * at the actual VM-Enter.
-	 *
-	 * Keying off the module param also allows treating an invalid vAPIC
-	 * mapping as a consistency check failure without increasing the risk
-	 * of breaking a "real" VM.
-	 */
-	if (!warn_on_missed_cc)
-		return 0;
-
-	if ((exec_controls_get(to_vmx(vcpu)) & CPU_BASED_TPR_SHADOW) &&
-	    nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) &&
-	    !nested_cpu_has_vid(vmcs12) &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
-	    (CC(!vapic) ||
-	     CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > (vtpr & GENMASK(3, 0)))))
-		return -EINVAL;
-
-	return 0;
-}
-
 static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -3666,11 +3663,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
 		}
 
-		if (nested_vmx_check_controls_late(vcpu, vmcs12)) {
-			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-			return NVMX_VMENTRY_VMFAIL;
-		}
-
 		if (nested_vmx_check_guest_state(vcpu, vmcs12,
 						 &entry_failure_code)) {
 			exit_reason.basic = EXIT_REASON_INVALID_STATE;
@@ -3755,6 +3747,8 @@ vmentry_fail_vmexit:
 	if (!from_vmentry)
 		return NVMX_VMENTRY_VMEXIT;
 
+	nested_put_vmcs12_pages(vcpu);
+
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason.full;
 	if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index ec29a2db1adc..556bf9fe1f5d 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -2725,7 +2725,11 @@ static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
 		goto out;
 	}
 
-	if (init_vm->cpuid.padding) {
+	/*
+	 * Reject the request if userspace changes cpuid.nent between the
+	 * initial read and the subsequent copy.
+	 */
+	if (init_vm->cpuid.padding || init_vm->cpuid.nent != nr_user_entries) {
 		ret = -EINVAL;
 		goto out;
 	}