xen: fixes for 5.0-rc3

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQRTLbB6QfY48x44uB6AXGG7T9hjvgUCXEGhYwAKCRCAXGG7T9hj
 vu/qAP4ljV1QwAicTP2IosIpmSojJV4BkkJOs36dgF1u4DscPAEA7YhvTzGYcZr6
 7rmBIbGve6Yb24Uh4aL3ir4w+LUvSAg=
 =Jm9L
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-5.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - Several fixes for the Xen pvcalls drivers (1 fix for the backend and
   8 for the frontend).

 - A fix for a rather longstanding bug in the Xen sched_clock()
   interface which led to weird time jumps when migrating the system.

 - A fix for avoiding accesses to x2apic MSRs in Xen PV guests.

* tag 'for-linus-5.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: Fix x86 sched_clock() interface for xen
  pvcalls-front: fix potential null dereference
  always clear the X2APIC_ENABLE bit for PV guest
  pvcalls-front: Avoid get_free_pages(GFP_KERNEL) under spinlock
  xen/pvcalls: remove set but not used variable 'intf'
  pvcalls-back: set -ENOTCONN in pvcalls_conn_back_read
  pvcalls-front: don't return error when the ring is full
  pvcalls-front: properly allocate sk
  pvcalls-front: don't try to free unallocated rings
  pvcalls-front: read all data before closing the connection

arch/x86/xen/enlighten_pv.c

@@ -898,10 +898,7 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 	val = native_read_msr_safe(msr, err);
 	switch (msr) {
 	case MSR_IA32_APICBASE:
-#ifdef CONFIG_X86_X2APIC
+		val &= ~X2APIC_ENABLE;
-		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
-#endif
-			val &= ~X2APIC_ENABLE;
 		break;
 	}
 	return val;

arch/x86/xen/time.c

@@ -361,8 +361,6 @@ void xen_timer_resume(void)
 {
 	int cpu;
 
-	pvclock_resume();
-
 	if (xen_clockevent != &xen_vcpuop_clockevent)
 		return;
 
@@ -379,12 +377,15 @@ static const struct pv_time_ops xen_time_ops __initconst = {
 };
 
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
+static u64 xen_clock_value_saved;
 
 void xen_save_time_memory_area(void)
 {
 	struct vcpu_register_time_memory_area t;
 	int ret;
 
+	xen_clock_value_saved = xen_clocksource_read() - xen_sched_clock_offset;
+
 	if (!xen_clock)
 		return;
 
@@ -404,7 +405,7 @@ void xen_restore_time_memory_area(void)
 	int ret;
 
 	if (!xen_clock)
-		return;
+		goto out;
 
 	t.addr.v = &xen_clock->pvti;
 
@@ -421,6 +422,11 @@ void xen_restore_time_memory_area(void)
 	if (ret != 0)
 		pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
 			  ret);
+
+out:
+	/* Need pvclock_resume() before using xen_clocksource_read(). */
+	pvclock_resume();
+	xen_sched_clock_offset = xen_clocksource_read() - xen_clock_value_saved;
 }
 
 static void xen_setup_vsyscall_time_info(void)

drivers/xen/events/events_base.c

@@ -1650,7 +1650,7 @@ void xen_callback_vector(void)
 			xen_have_vector_callback = 0;
 			return;
 		}
-		pr_info("Xen HVM callback vector for event delivery is enabled\n");
+		pr_info_once("Xen HVM callback vector for event delivery is enabled\n");
 		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
 				xen_hvm_callback_vector);
 	}

drivers/xen/pvcalls-back.c

@@ -160,9 +160,10 @@ static void pvcalls_conn_back_read(void *opaque)
 
 	/* write the data, then modify the indexes */
 	virt_wmb();
-	if (ret < 0)
+	if (ret < 0) {
+		atomic_set(&map->read, 0);
 		intf->in_error = ret;
-	else
+	} else
 		intf->in_prod = prod + ret;
 	/* update the indexes, then notify the other end */
 	virt_wmb();
@@ -282,13 +283,11 @@ static int pvcalls_back_socket(struct xenbus_device *dev,
 static void pvcalls_sk_state_change(struct sock *sock)
 {
 	struct sock_mapping *map = sock->sk_user_data;
-	struct pvcalls_data_intf *intf;
 
 	if (map == NULL)
 		return;
 
-	intf = map->ring;
+	atomic_inc(&map->read);
-	intf->in_error = -ENOTCONN;
 	notify_remote_via_irq(map->irq);
 }
 

drivers/xen/pvcalls-front.c

@@ -31,6 +31,12 @@
 #define PVCALLS_NR_RSP_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
 #define PVCALLS_FRONT_MAX_SPIN 5000
 
+static struct proto pvcalls_proto = {
+	.name	= "PVCalls",
+	.owner	= THIS_MODULE,
+	.obj_size = sizeof(struct sock),
+};
+
 struct pvcalls_bedata {
 	struct xen_pvcalls_front_ring ring;
 	grant_ref_t ref;
@@ -335,6 +341,42 @@ int pvcalls_front_socket(struct socket *sock)
 	return ret;
 }
 
+static void free_active_ring(struct sock_mapping *map)
+{
+	if (!map->active.ring)
+		return;
+
+	free_pages((unsigned long)map->active.data.in,
+			map->active.ring->ring_order);
+	free_page((unsigned long)map->active.ring);
+}
+
+static int alloc_active_ring(struct sock_mapping *map)
+{
+	void *bytes;
+
+	map->active.ring = (struct pvcalls_data_intf *)
+		get_zeroed_page(GFP_KERNEL);
+	if (!map->active.ring)
+		goto out;
+
+	map->active.ring->ring_order = PVCALLS_RING_ORDER;
+	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					PVCALLS_RING_ORDER);
+	if (!bytes)
+		goto out;
+
+	map->active.data.in = bytes;
+	map->active.data.out = bytes +
+		XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+
+	return 0;
+
+out:
+	free_active_ring(map);
+	return -ENOMEM;
+}
+
 static int create_active(struct sock_mapping *map, int *evtchn)
 {
 	void *bytes;
@@ -343,15 +385,7 @@ static int create_active(struct sock_mapping *map, int *evtchn)
 	*evtchn = -1;
 	init_waitqueue_head(&map->active.inflight_conn_req);
 
-	map->active.ring = (struct pvcalls_data_intf *)
+	bytes = map->active.data.in;
-		__get_free_page(GFP_KERNEL | __GFP_ZERO);
-	if (map->active.ring == NULL)
-		goto out_error;
-	map->active.ring->ring_order = PVCALLS_RING_ORDER;
-	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-					PVCALLS_RING_ORDER);
-	if (bytes == NULL)
-		goto out_error;
 	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
 		map->active.ring->ref[i] = gnttab_grant_foreign_access(
 			pvcalls_front_dev->otherend_id,
@@ -361,10 +395,6 @@ static int create_active(struct sock_mapping *map, int *evtchn)
 		pvcalls_front_dev->otherend_id,
 		pfn_to_gfn(virt_to_pfn((void *)map->active.ring)), 0);
 
-	map->active.data.in = bytes;
-	map->active.data.out = bytes +
-		XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
-
 	ret = xenbus_alloc_evtchn(pvcalls_front_dev, evtchn);
 	if (ret)
 		goto out_error;
@@ -385,8 +415,6 @@ static int create_active(struct sock_mapping *map, int *evtchn)
 out_error:
 	if (*evtchn >= 0)
 		xenbus_free_evtchn(pvcalls_front_dev, *evtchn);
-	free_pages((unsigned long)map->active.data.in, PVCALLS_RING_ORDER);
-	free_page((unsigned long)map->active.ring);
 	return ret;
 }
 
@@ -406,17 +434,24 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 		return PTR_ERR(map);
 
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+	ret = alloc_active_ring(map);
+	if (ret < 0) {
+		pvcalls_exit_sock(sock);
+		return ret;
+	}
 
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
+		free_active_ring(map);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	ret = create_active(map, &evtchn);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
+		free_active_ring(map);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
@@ -469,8 +504,10 @@ static int __write_ring(struct pvcalls_data_intf *intf,
 	virt_mb();
 
 	size = pvcalls_queued(prod, cons, array_size);
-	if (size >= array_size)
+	if (size > array_size)
 		return -EINVAL;
+	if (size == array_size)
+		return 0;
 	if (len > array_size - size)
 		len = array_size - size;
 
@@ -560,15 +597,13 @@ static int __read_ring(struct pvcalls_data_intf *intf,
 	error = intf->in_error;
 	/* get pointers before reading from the ring */
 	virt_rmb();
-	if (error < 0)
-		return error;
 
 	size = pvcalls_queued(prod, cons, array_size);
 	masked_prod = pvcalls_mask(prod, array_size);
 	masked_cons = pvcalls_mask(cons, array_size);
 
 	if (size == 0)
-		return 0;
+		return error ?: size;
 
 	if (len > size)
 		len = size;
@@ -780,25 +815,36 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		}
 	}
 
+	map2 = kzalloc(sizeof(*map2), GFP_KERNEL);
+	if (map2 == NULL) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		pvcalls_exit_sock(sock);
+		return -ENOMEM;
+	}
+	ret = alloc_active_ring(map2);
+	if (ret < 0) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+				(void *)&map->passive.flags);
+		kfree(map2);
+		pvcalls_exit_sock(sock);
+		return ret;
+	}
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
+		free_active_ring(map2);
+		kfree(map2);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
-	map2 = kzalloc(sizeof(*map2), GFP_ATOMIC);
+
-	if (map2 == NULL) {
-		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
-			  (void *)&map->passive.flags);
-		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit_sock(sock);
-		return -ENOMEM;
-	}
 	ret = create_active(map2, &evtchn);
 	if (ret < 0) {
+		free_active_ring(map2);
 		kfree(map2);
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
@@ -839,7 +885,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 
 received:
 	map2->sock = newsock;
-	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
+	newsock->sk = sk_alloc(sock_net(sock->sk), PF_INET, GFP_KERNEL, &pvcalls_proto, false);
 	if (!newsock->sk) {
 		bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
 		map->passive.inflight_req_id = PVCALLS_INVALID_ID;
@@ -1032,8 +1078,8 @@ int pvcalls_front_release(struct socket *sock)
 		spin_lock(&bedata->socket_lock);
 		list_del(&map->list);
 		spin_unlock(&bedata->socket_lock);
-		if (READ_ONCE(map->passive.inflight_req_id) !=
+		if (READ_ONCE(map->passive.inflight_req_id) != PVCALLS_INVALID_ID &&
-		    PVCALLS_INVALID_ID) {
+			READ_ONCE(map->passive.inflight_req_id) != 0) {
 			pvcalls_front_free_map(bedata,
 					       map->passive.accept_map);
 		}