Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 169 insertions, 118 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4dbd9d99f9..0b7adf3bc5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,9 +92,12 @@
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
 
-struct kvm_caps kvm_caps __read_mostly = {
-	.supported_mce_cap = MCG_CTL_P | MCG_SER_P,
-};
+/*
+ * Note, kvm_caps fields should *never* have default values, all fields must be
+ * recomputed from scratch during vendor module load, e.g. to account for a
+ * vendor module being reloaded with different module parameters.
+ */
+struct kvm_caps kvm_caps __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_caps);
 
 #define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
@@ -161,15 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, 0644);
 
-/*
- * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
- * adaptive tuning starting from default advancement of 1000ns.  '0' disables
- * advancement entirely.  Any other value is used as-is and disables adaptive
- * tuning, i.e. allows privileged userspace to set an exact advancement time.
- */
-static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, int, 0644);
-
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, 0444);
 
@@ -2230,16 +2224,13 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	/*
 	 * Disallow writes to immutable feature MSRs after KVM_RUN.  KVM does
 	 * not support modifying the guest vCPU model on the fly, e.g. changing
-	 * the nVMX capabilities while L2 is running is nonsensical.  Ignore
+	 * the nVMX capabilities while L2 is running is nonsensical.  Allow
 	 * writes of the same value, e.g. to allow userspace to blindly stuff
 	 * all MSRs when emulating RESET.
 	 */
-	if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) {
-		if (do_get_msr(vcpu, index, &val) || *data != val)
-			return -EINVAL;
-
-		return 0;
-	}
+	if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) &&
+	    (do_get_msr(vcpu, index, &val) || *data != val))
+		return -EINVAL;
 
 	return kvm_set_msr_ignored_check(vcpu, index, *data, true);
 }
@@ -4629,9 +4620,7 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 
 static bool kvm_is_vm_type_supported(unsigned long type)
 {
-	return type == KVM_X86_DEFAULT_VM ||
-	       (type == KVM_X86_SW_PROTECTED_VM &&
-		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
+	return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -4832,9 +4821,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_caps.has_notify_vmexit;
 		break;
 	case KVM_CAP_VM_TYPES:
-		r = BIT(KVM_X86_DEFAULT_VM);
-		if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
-			r |= BIT(KVM_X86_SW_PROTECTED_VM);
+		r = kvm_caps.supported_vm_types;
 		break;
 	default:
 		break;
@@ -4842,46 +4829,44 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	return r;
 }
 
-static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr)
+static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val)
 {
-	void __user *uaddr = (void __user*)(unsigned long)attr->addr;
-
-	if ((u64)(unsigned long)uaddr != attr->addr)
-		return ERR_PTR_USR(-EFAULT);
-	return uaddr;
-}
-
-static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
-{
-	u64 __user *uaddr = kvm_get_attr_addr(attr);
-
-	if (attr->group)
+	if (attr->group) {
+		if (kvm_x86_ops.dev_get_attr)
+			return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val);
 		return -ENXIO;
-
-	if (IS_ERR(uaddr))
-		return PTR_ERR(uaddr);
+	}
 
 	switch (attr->attr) {
 	case KVM_X86_XCOMP_GUEST_SUPP:
-		if (put_user(kvm_caps.supported_xcr0, uaddr))
-			return -EFAULT;
+		*val = kvm_caps.supported_xcr0;
 		return 0;
 	default:
 		return -ENXIO;
 	}
 }
 
+static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
+{
+	u64 __user *uaddr = u64_to_user_ptr(attr->addr);
+	int r;
+	u64 val;
+
+	r = __kvm_x86_dev_get_attr(attr, &val);
+	if (r < 0)
+		return r;
+
+	if (put_user(val, uaddr))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr)
 {
-	if (attr->group)
-		return -ENXIO;
+	u64 val;
 
-	switch (attr->attr) {
-	case KVM_X86_XCOMP_GUEST_SUPP:
-		return 0;
-	default:
-		return -ENXIO;
-	}
+	return __kvm_x86_dev_get_attr(attr, &val);
 }
 
 long kvm_arch_dev_ioctl(struct file *filp,
@@ -5557,11 +5542,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
-					     struct kvm_debugregs *dbgregs)
+static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
+					    struct kvm_debugregs *dbgregs)
 {
 	unsigned int i;
 
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	memset(dbgregs, 0, sizeof(*dbgregs));
 
 	BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db));
@@ -5570,6 +5559,7 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
 
 	dbgregs->dr6 = vcpu->arch.dr6;
 	dbgregs->dr7 = vcpu->arch.dr7;
+	return 0;
 }
 
 static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
@@ -5577,6 +5567,10 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 {
 	unsigned int i;
 
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	if (dbgregs->flags)
 		return -EINVAL;
 
@@ -5597,8 +5591,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 }
 
 
-static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
-					  u8 *state, unsigned int size)
+static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
+					 u8 *state, unsigned int size)
 {
 	/*
 	 * Only copy state for features that are enabled for the guest.  The
@@ -5616,24 +5610,25 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
 			     XFEATURE_MASK_FPSSE;
 
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
-		return;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
 	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
 				       supported_xcr0, vcpu->arch.pkru);
+	return 0;
 }
 
-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
-					 struct kvm_xsave *guest_xsave)
+static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+					struct kvm_xsave *guest_xsave)
 {
-	kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
-				      sizeof(guest_xsave->region));
+	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+					     sizeof(guest_xsave->region));
 }
 
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
-		return 0;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
 	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
 					      guest_xsave->region,
@@ -5641,18 +5636,23 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					      &vcpu->arch.pkru);
 }
 
-static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
-					struct kvm_xcrs *guest_xcrs)
+static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
+				       struct kvm_xcrs *guest_xcrs)
 {
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
 		guest_xcrs->nr_xcrs = 0;
-		return;
+		return 0;
 	}
 
 	guest_xcrs->nr_xcrs = 1;
 	guest_xcrs->flags = 0;
 	guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
 	guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
+	return 0;
 }
 
 static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
@@ -5660,6 +5660,10 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 {
 	int i, r = 0;
 
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -EINVAL;
 
@@ -5712,12 +5716,9 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu,
 static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
 				 struct kvm_device_attr *attr)
 {
-	u64 __user *uaddr = kvm_get_attr_addr(attr);
+	u64 __user *uaddr = u64_to_user_ptr(attr->addr);
 	int r;
 
-	if (IS_ERR(uaddr))
-		return PTR_ERR(uaddr);
-
 	switch (attr->attr) {
 	case KVM_VCPU_TSC_OFFSET:
 		r = -EFAULT;
@@ -5735,13 +5736,10 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
 static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
 				 struct kvm_device_attr *attr)
 {
-	u64 __user *uaddr = kvm_get_attr_addr(attr);
+	u64 __user *uaddr = u64_to_user_ptr(attr->addr);
 	struct kvm *kvm = vcpu->kvm;
 	int r;
 
-	if (IS_ERR(uaddr))
-		return PTR_ERR(uaddr);
-
 	switch (attr->attr) {
 	case KVM_VCPU_TSC_OFFSET: {
 		u64 offset, tsc, ns;
@@ -6048,7 +6046,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_GET_DEBUGREGS: {
 		struct kvm_debugregs dbgregs;
 
-		kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+		r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+		if (r < 0)
+			break;
 
 		r = -EFAULT;
 		if (copy_to_user(argp, &dbgregs,
@@ -6078,7 +6078,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (!u.xsave)
 			break;
 
-		kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);
+		r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);
+		if (r < 0)
+			break;
 
 		r = -EFAULT;
 		if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave)))
@@ -6107,7 +6109,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (!u.xsave)
 			break;
 
-		kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size);
+		r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size);
+		if (r < 0)
+			break;
 
 		r = -EFAULT;
 		if (copy_to_user(argp, u.xsave, size))
@@ -6123,7 +6127,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (!u.xcrs)
 			break;
 
-		kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);
+		r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);
+		if (r < 0)
+			break;
 
 		r = -EFAULT;
 		if (copy_to_user(argp, u.xcrs,
@@ -6267,6 +6273,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 #endif
 	case KVM_GET_SREGS2: {
+		r = -EINVAL;
+		if (vcpu->kvm->arch.has_protected_state &&
+		    vcpu->arch.guest_state_protected)
+			goto out;
+
 		u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL);
 		r = -ENOMEM;
 		if (!u.sregs2)
@@ -6279,6 +6290,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_SET_SREGS2: {
+		r = -EINVAL;
+		if (vcpu->kvm->arch.has_protected_state &&
+		    vcpu->arch.guest_state_protected)
+			goto out;
+
 		u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2));
 		if (IS_ERR(u.sregs2)) {
 			r = PTR_ERR(u.sregs2);
@@ -9732,6 +9748,8 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 		return -EIO;
 	}
 
+	memset(&kvm_caps, 0, sizeof(kvm_caps));
+
 	x86_emulator_cache = kvm_alloc_emulator_cache();
 	if (!x86_emulator_cache) {
 		pr_err("failed to allocate cache for x86 emulator\n");
@@ -9750,6 +9768,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	if (r)
 		goto out_free_percpu;
 
+	kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM);
+	kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P;
+
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 		kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
@@ -9795,6 +9816,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 
 	kvm_register_perf_callbacks(ops->handle_intel_pt_intr);
 
+	if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled)
+		kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM);
+
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		kvm_caps.supported_xss = 0;
 
@@ -9995,15 +10019,12 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
 
 static void kvm_apicv_init(struct kvm *kvm)
 {
-	unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons;
+	enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT :
+						       APICV_INHIBIT_REASON_DISABLE;
 
-	init_rwsem(&kvm->arch.apicv_update_lock);
-
-	set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true);
+	set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true);
 
-	if (!enable_apicv)
-		set_or_clear_apicv_inhibit(inhibits,
-					   APICV_INHIBIT_REASON_DISABLE, true);
+	init_rwsem(&kvm->arch.apicv_update_lock);
 }
 
 static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
@@ -10051,26 +10072,15 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
-int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
+unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
+				      unsigned long a0, unsigned long a1,
+				      unsigned long a2, unsigned long a3,
+				      int op_64_bit, int cpl)
 {
-	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit;
-
-	if (kvm_xen_hypercall_enabled(vcpu->kvm))
-		return kvm_xen_hypercall(vcpu);
-
-	if (kvm_hv_hypercall_enabled(vcpu))
-		return kvm_hv_hypercall(vcpu);
-
-	nr = kvm_rax_read(vcpu);
-	a0 = kvm_rbx_read(vcpu);
-	a1 = kvm_rcx_read(vcpu);
-	a2 = kvm_rdx_read(vcpu);
-	a3 = kvm_rsi_read(vcpu);
+	unsigned long ret;
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
-	op_64_bit = is_64_bit_hypercall(vcpu);
 	if (!op_64_bit) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
@@ -10079,7 +10089,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		a3 &= 0xFFFFFFFF;
 	}
 
-	if (static_call(kvm_x86_get_cpl)(vcpu) != 0) {
+	if (cpl) {
 		ret = -KVM_EPERM;
 		goto out;
 	}
@@ -10140,18 +10150,49 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 		WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ);
 		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
+		/* stat is incremented on completion. */
 		return 0;
 	}
 	default:
 		ret = -KVM_ENOSYS;
 		break;
 	}
+
 out:
+	++vcpu->stat.hypercalls;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall);
+
+int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
+{
+	unsigned long nr, a0, a1, a2, a3, ret;
+	int op_64_bit;
+	int cpl;
+
+	if (kvm_xen_hypercall_enabled(vcpu->kvm))
+		return kvm_xen_hypercall(vcpu);
+
+	if (kvm_hv_hypercall_enabled(vcpu))
+		return kvm_hv_hypercall(vcpu);
+
+	nr = kvm_rax_read(vcpu);
+	a0 = kvm_rbx_read(vcpu);
+	a1 = kvm_rcx_read(vcpu);
+	a2 = kvm_rdx_read(vcpu);
+	a3 = kvm_rsi_read(vcpu);
+	op_64_bit = is_64_bit_hypercall(vcpu);
+	cpl = static_call(kvm_x86_get_cpl)(vcpu);
+
+	ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl);
+	if (nr == KVM_HC_MAP_GPA_RANGE && !ret)
+		/* MAP_GPA tosses the request to the user space. */
+		return 0;
+
 	if (!op_64_bit)
 		ret = (u32)ret;
 	kvm_rax_write(vcpu, ret);
 
-	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -10475,7 +10516,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 
 	if (is_guest_mode(vcpu) &&
 	    kvm_x86_ops.nested_ops->has_events &&
-	    kvm_x86_ops.nested_ops->has_events(vcpu))
+	    kvm_x86_ops.nested_ops->has_events(vcpu, true))
 		*req_immediate_exit = true;
 
 	/*
@@ -11485,6 +11526,10 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 	__get_regs(vcpu, regs);
 	vcpu_put(vcpu);
@@ -11526,6 +11571,10 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 	__set_regs(vcpu, regs);
 	vcpu_put(vcpu);
@@ -11598,6 +11647,10 @@ static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2)
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 	__get_sregs(vcpu, sregs);
 	vcpu_put(vcpu);
@@ -11865,6 +11918,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 {
 	int ret;
 
+	if (vcpu->kvm->arch.has_protected_state &&
+	    vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 	ret = __set_sregs(vcpu, sregs);
 	vcpu_put(vcpu);
@@ -11982,7 +12039,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	struct fxregs_state *fxsave;
 
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
-		return 0;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
 	vcpu_load(vcpu);
 
@@ -12005,7 +12062,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	struct fxregs_state *fxsave;
 
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
-		return 0;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
 	vcpu_load(vcpu);
 
@@ -12102,7 +12159,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		return r;
 
-	r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+	r = kvm_create_lapic(vcpu);
 	if (r < 0)
 		goto fail_mmu_destroy;
 
@@ -12531,6 +12588,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		return -EINVAL;
 
 	kvm->arch.vm_type = type;
+	kvm->arch.has_private_mem =
+		(type == KVM_X86_SW_PROTECTED_VM);
 
 	ret = kvm_page_track_init(kvm);
 	if (ret)
@@ -12730,7 +12789,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot)
 	int i;
 
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.rmap[i]);
+		vfree(slot->arch.rmap[i]);
 		slot->arch.rmap[i] = NULL;
 	}
 }
@@ -12742,7 +12801,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	memslot_rmap_free(slot);
 
 	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.lpage_info[i - 1]);
+		vfree(slot->arch.lpage_info[i - 1]);
 		slot->arch.lpage_info[i - 1] = NULL;
 	}
 
@@ -12834,7 +12893,7 @@ out_free:
 	memslot_rmap_free(slot);
 
 	for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvfree(slot->arch.lpage_info[i - 1]);
+		vfree(slot->arch.lpage_info[i - 1]);
 		slot->arch.lpage_info[i - 1] = NULL;
 	}
 	return -ENOMEM;
@@ -13041,12 +13100,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		kvm_arch_free_memslot(kvm, old);
 }
 
-static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
-	return (is_guest_mode(vcpu) &&
-		static_call(kvm_x86_guest_apic_has_interrupt)(vcpu));
-}
-
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 {
 	if (!list_empty_careful(&vcpu->async_pf.done))
@@ -13077,9 +13130,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	if (kvm_test_request(KVM_REQ_PMI, vcpu))
 		return true;
 
-	if (kvm_arch_interrupt_allowed(vcpu) &&
-	    (kvm_cpu_has_interrupt(vcpu) ||
-	    kvm_guest_apic_has_interrupt(vcpu)))
+	if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu))
 		return true;
 
 	if (kvm_hv_has_stimer_pending(vcpu))
@@ -13087,7 +13138,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 
 	if (is_guest_mode(vcpu) &&
 	    kvm_x86_ops.nested_ops->has_events &&
-	    kvm_x86_ops.nested_ops->has_events(vcpu))
+	    kvm_x86_ops.nested_ops->has_events(vcpu, false))
 		return true;
 
 	if (kvm_xen_has_pending_events(vcpu))