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

Pull KVM fixes from Paolo Bonzini:

 - fix for module unload vs deferred jump labels (note: there might be
   other buggy modules!)

 - two NULL pointer dereferences from syzkaller

 - also syzkaller: fix emulation of fxsave/fxrstor/sgdt/sidt, problem
   made worse during this merge window, "just" kernel memory leak on
   releases

 - fix emulation of "mov ss" - somewhat serious on AMD, less so on Intel

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: fix emulation of "MOV SS, null selector"
  KVM: x86: fix NULL deref in vcpu_scan_ioapic
  KVM: eventfd: fix NULL deref irqbypass consumer
  KVM: x86: Introduce segmented_write_std
  KVM: x86: flush pending lapic jump label updates on module unload
  jump_labels: API for flushing deferred jump label updates

arch/x86/kvm/emulate.c

@@ -818,6 +818,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
 }
 
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+			       struct segmented_address addr,
+			       void *data,
+			       unsigned int size)
+{
+	int rc;
+	ulong linear;
+
+	rc = linearize(ctxt, addr, size, true, &linear);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
 /*
  * Prefetch the remaining bytes of the instruction without crossing page
  * boundary if they are not in fetch_cache yet.
@@ -1571,7 +1585,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				    &ctxt->exception);
 }
 
-/* Does not support long mode */
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, int seg, u8 cpl,
 				     enum x86_transfer_type transfer,
@@ -1608,20 +1621,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 	rpl = selector & 3;
 
-	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
-	if ((seg == VCPU_SREG_CS
-	     || (seg == VCPU_SREG_SS
-		 && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
-	     || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
-
 	/* TR should be in GDT only */
 	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
 		goto exception;
 
-	if (null_selector) /* for NULL selector skip all following checks */
+	/* NULL selector is not valid for TR, CS and (except for long mode) SS */
+	if (null_selector) {
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+			goto exception;
+
+		if (seg == VCPU_SREG_SS) {
+			if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+				goto exception;
+
+			/*
+			 * ctxt->ops->set_segment expects the CPL to be in
+			 * SS.DPL, so fake an expand-up 32-bit data segment.
+			 */
+			seg_desc.type = 3;
+			seg_desc.p = 1;
+			seg_desc.s = 1;
+			seg_desc.dpl = cpl;
+			seg_desc.d = 1;
+			seg_desc.g = 1;
+		}
+
+		/* Skip all following checks */
 		goto load;
+	}
 
 	ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
 	if (ret != X86EMUL_CONTINUE)
@@ -1737,6 +1764,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				   u16 selector, int seg)
 {
 	u8 cpl = ctxt->ops->cpl(ctxt);
+
+	/*
+	 * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+	 * they can load it at CPL<3 (Intel's manual says only LSS can,
+	 * but it's wrong).
+	 *
+	 * However, the Intel manual says that putting IST=1/DPL=3 in
+	 * an interrupt gate will result in SS=3 (the AMD manual instead
+	 * says it doesn't), so allow SS=3 in __load_segment_descriptor
+	 * and only forbid it here.
+	 */
+	if (seg == VCPU_SREG_SS && selector == 3 &&
+	    ctxt->mode == X86EMUL_MODE_PROT64)
+		return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
 	return __load_segment_descriptor(ctxt, selector, seg, cpl,
 					 X86_TRANSFER_NONE, NULL);
 }
@@ -3685,8 +3727,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt,
 	}
 	/* Disable writeback. */
 	ctxt->dst.type = OP_NONE;
-	return segmented_write(ctxt, ctxt->dst.addr.mem,
-			       &desc_ptr, 2 + ctxt->op_bytes);
+	return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+				   &desc_ptr, 2 + ctxt->op_bytes);
 }
 
 static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3932,7 +3974,7 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	else
 		size = offsetof(struct fxregs_state, xmm_space[0]);
 
-	return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
 }
 
 static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
@@ -3974,7 +4016,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 

arch/x86/kvm/lapic.c

@@ -2426,3 +2426,9 @@ void kvm_lapic_init(void)
 	jump_label_rate_limit(&apic_hw_disabled, HZ);
 	jump_label_rate_limit(&apic_sw_disabled, HZ);
 }
+
+void kvm_lapic_exit(void)
+{
+	static_key_deferred_flush(&apic_hw_disabled);
+	static_key_deferred_flush(&apic_sw_disabled);
+}

arch/x86/kvm/lapic.h

@@ -110,6 +110,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
 void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
 
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)

arch/x86/kvm/x86.c

@@ -3342,6 +3342,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 	switch (cap->cap) {
 	case KVM_CAP_HYPERV_SYNIC:
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
 		return kvm_hv_activate_synic(vcpu);
 	default:
 		return -EINVAL;
@@ -6045,6 +6047,7 @@ int kvm_arch_init(void *opaque)
 
 void kvm_arch_exit(void)
 {
+	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))

include/linux/jump_label_ratelimit.h

@@ -14,6 +14,7 @@ struct static_key_deferred {
 
 #ifdef HAVE_JUMP_LABEL
 extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
+extern void static_key_deferred_flush(struct static_key_deferred *key);
 extern void
 jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
 
@@ -26,6 +27,10 @@ static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 	STATIC_KEY_CHECK_USE();
 	static_key_slow_dec(&key->key);
 }
+static inline void static_key_deferred_flush(struct static_key_deferred *key)
+{
+	STATIC_KEY_CHECK_USE();
+}
 static inline void
 jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)

kernel/jump_label.c

@@ -182,6 +182,13 @@ void static_key_slow_dec_deferred(struct static_key_deferred *key)
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
 
+void static_key_deferred_flush(struct static_key_deferred *key)
+{
+	STATIC_KEY_CHECK_USE();
+	flush_delayed_work(&key->work);
+}
+EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {

virt/lib/irqbypass.c

@@ -195,7 +195,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->token == consumer->token) {
+		if (tmp->token == consumer->token || tmp == consumer) {
 			mutex_unlock(&lock);
 			module_put(THIS_MODULE);
 			return -EBUSY;
@@ -245,7 +245,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->token != consumer->token)
+		if (tmp != consumer)
 			continue;
 
 		list_for_each_entry(producer, &producers, node) {