xen: fixes for 4.16-rc2

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABAgAGBQJah+tbAAoJELDendYovxMvHIYH/38IC3Nd3IWTVsLvHXUCxFrn
 fNPKgSyC5/igLbmwjPQ+kbr7bha6Vi3uZwmovoC/9i03gYfzmuuMhhOvOVByYHXg
 HHC+kqegB7tZ2GFeR2hrIba4UxBz4ZC0R5+qQYHZMx5dRt0/Llby663mkcK7WEWr
 Na8jT32AbIOiCKWHgsmTC7h2ZiSXeY+WVj1B3Re7ovLHMTYoMDQhVi5I7w34bcch
 bgTLx4TokC8Z3kCNotPAwrL0rQggEJ+PR91j2mL52uEWv80Q4hgR+QIFtEwiYXmG
 jDbx4Y+jQUAu4+r6/2z4S/gFTV93lB+dWbXYuHoFv5Mv1A+Ve7Al744RvrNh3gM=
 =UVdB
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-4.16a-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - fixes for the Xen pvcalls frontend driver

 - fix for booting Xen pv domains

 - fix for the xenbus driver user interface

* tag 'for-linus-4.16a-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  pvcalls-front: wait for other operations to return when release passive sockets
  pvcalls-front: introduce a per sock_mapping refcount
  x86/xen: Calculate __max_logical_packages on PV domains
  xenbus: track caller request id

arch/x86/include/asm/smp.h

@@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
+void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);

arch/x86/kernel/smpboot.c

@@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void)
 	cpu_set_state_online(me);
 }
 
-void __init native_smp_cpus_done(unsigned int max_cpus)
+void __init calculate_max_logical_packages(void)
 {
 	int ncpus;
 
-	pr_debug("Boot done\n");
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
@@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
+}
+
+void __init native_smp_cpus_done(unsigned int max_cpus)
+{
+	pr_debug("Boot done\n");
+
+	calculate_max_logical_packages();
 
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);

arch/x86/xen/smp.c

@@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus)
 
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
+	else
+		calculate_max_logical_packages();
 
 	if (xen_have_vcpu_info_placement)
 		return;

drivers/xen/pvcalls-front.c

@@ -60,6 +60,7 @@ struct sock_mapping {
 	bool active_socket;
 	struct list_head list;
 	struct socket *sock;
+	atomic_t refcount;
 	union {
 		struct {
 			int irq;
@@ -93,6 +94,32 @@ struct sock_mapping {
 	};
 };
 
+static inline struct sock_mapping *pvcalls_enter_sock(struct socket *sock)
+{
+	struct sock_mapping *map;
+
+	if (!pvcalls_front_dev ||
+		dev_get_drvdata(&pvcalls_front_dev->dev) == NULL)
+		return ERR_PTR(-ENOTCONN);
+
+	map = (struct sock_mapping *)sock->sk->sk_send_head;
+	if (map == NULL)
+		return ERR_PTR(-ENOTSOCK);
+
+	pvcalls_enter();
+	atomic_inc(&map->refcount);
+	return map;
+}
+
+static inline void pvcalls_exit_sock(struct socket *sock)
+{
+	struct sock_mapping *map;
+
+	map = (struct sock_mapping *)sock->sk->sk_send_head;
+	atomic_dec(&map->refcount);
+	pvcalls_exit();
+}
+
 static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
 {
 	*req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
@@ -369,31 +396,23 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *)sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	ret = create_active(map, &evtchn);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 
@@ -423,7 +442,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	smp_rmb();
 	ret = bedata->rsp[req_id].ret;
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -488,23 +507,15 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	mutex_lock(&map->active.out_mutex);
 	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
 		mutex_unlock(&map->active.out_mutex);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EAGAIN;
 	}
 	if (len > INT_MAX)
@@ -526,7 +537,7 @@ again:
 		tot_sent = sent;
 
 	mutex_unlock(&map->active.out_mutex);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return tot_sent;
 }
 
@@ -591,19 +602,11 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	mutex_lock(&map->active.in_mutex);
 	if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER))
 		len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
@@ -623,7 +626,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		ret = 0;
 
 	mutex_unlock(&map->active.in_mutex);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -637,24 +640,16 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
 		return -EOPNOTSUPP;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (map == NULL) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	req = RING_GET_REQUEST(&bedata->ring, req_id);
@@ -684,7 +679,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
 
 	map->passive.status = PVCALLS_STATUS_BIND;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return 0;
 }
 
@@ -695,21 +690,13 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	struct xen_pvcalls_request *req;
 	int notify, req_id, ret;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	if (map->passive.status != PVCALLS_STATUS_BIND) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EOPNOTSUPP;
 	}
 
@@ -717,7 +704,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	req = RING_GET_REQUEST(&bedata->ring, req_id);
@@ -741,7 +728,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
 
 	map->passive.status = PVCALLS_STATUS_LISTEN;
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -753,21 +740,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct xen_pvcalls_request *req;
 	int notify, req_id, ret, evtchn, nonblock;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
+		return PTR_ERR(map);
-		return -ENOTCONN;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return -ENOTSOCK;
-	}
-
 	if (map->passive.status != PVCALLS_STATUS_LISTEN) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EINVAL;
 	}
 
@@ -785,13 +764,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 			goto received;
 		}
 		if (nonblock) {
-			pvcalls_exit();
+			pvcalls_exit_sock(sock);
 			return -EAGAIN;
 		}
 		if (wait_event_interruptible(map->passive.inflight_accept_req,
 			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 					  (void *)&map->passive.flags))) {
-			pvcalls_exit();
+			pvcalls_exit_sock(sock);
 			return -EINTR;
 		}
 	}
@@ -802,7 +781,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	map2 = kzalloc(sizeof(*map2), GFP_ATOMIC);
@@ -810,7 +789,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -ENOMEM;
 	}
 	ret = create_active(map2, &evtchn);
@@ -819,7 +798,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	list_add_tail(&map2->list, &bedata->socket_mappings);
@@ -841,13 +820,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 	/* We could check if we have received a response before returning. */
 	if (nonblock) {
 		WRITE_ONCE(map->passive.inflight_req_id, req_id);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EAGAIN;
 	}
 
 	if (wait_event_interruptible(bedata->inflight_req,
 		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -EINTR;
 	}
 	/* read req_id, then the content */
@@ -862,7 +841,7 @@ received:
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		pvcalls_front_free_map(bedata, map2);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return -ENOMEM;
 	}
 	newsock->sk->sk_send_head = (void *)map2;
@@ -874,7 +853,7 @@ received:
 	clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags);
 	wake_up(&map->passive.inflight_accept_req);
 
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -965,23 +944,16 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock,
 	struct sock_mapping *map;
 	__poll_t ret;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map))
-		pvcalls_exit();
 		return EPOLLNVAL;
-	}
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (!map) {
-		pvcalls_exit();
-		return EPOLLNVAL;
-	}
 	if (map->active_socket)
 		ret = pvcalls_front_poll_active(file, bedata, map, wait);
 	else
 		ret = pvcalls_front_poll_passive(file, bedata, map, wait);
-	pvcalls_exit();
+	pvcalls_exit_sock(sock);
 	return ret;
 }
 
@@ -995,25 +967,20 @@ int pvcalls_front_release(struct socket *sock)
 	if (sock->sk == NULL)
 		return 0;
 
-	pvcalls_enter();
+	map = pvcalls_enter_sock(sock);
-	if (!pvcalls_front_dev) {
+	if (IS_ERR(map)) {
-		pvcalls_exit();
+		if (PTR_ERR(map) == -ENOTCONN)
-		return -EIO;
+			return -EIO;
+		else
+			return 0;
 	}
-
 	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
 
-	map = (struct sock_mapping *) sock->sk->sk_send_head;
-	if (map == NULL) {
-		pvcalls_exit();
-		return 0;
-	}
-
 	spin_lock(&bedata->socket_lock);
 	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		pvcalls_exit();
+		pvcalls_exit_sock(sock);
 		return ret;
 	}
 	sock->sk->sk_send_head = NULL;
@@ -1043,14 +1010,20 @@ int pvcalls_front_release(struct socket *sock)
 		/*
 		 * We need to make sure that sendmsg/recvmsg on this socket have
 		 * not started before we've cleared sk_send_head here. The
-		 * easiest (though not optimal) way to guarantee this is to see
+		 * easiest way to guarantee this is to see that no pvcalls
-		 * that no pvcall (other than us) is in progress.
+		 * (other than us) is in progress on this socket.
 		 */
-		while (atomic_read(&pvcalls_refcount) > 1)
+		while (atomic_read(&map->refcount) > 1)
 			cpu_relax();
 
 		pvcalls_front_free_map(bedata, map);
 	} else {
+		wake_up(&bedata->inflight_req);
+		wake_up(&map->passive.inflight_accept_req);
+
+		while (atomic_read(&map->refcount) > 1)
+			cpu_relax();
+
 		spin_lock(&bedata->socket_lock);
 		list_del(&map->list);
 		spin_unlock(&bedata->socket_lock);

drivers/xen/xenbus/xenbus.h

@@ -76,6 +76,7 @@ struct xb_req_data {
 	struct list_head list;
 	wait_queue_head_t wq;
 	struct xsd_sockmsg msg;
+	uint32_t caller_req_id;
 	enum xsd_sockmsg_type type;
 	char *body;
 	const struct kvec *vec;

drivers/xen/xenbus/xenbus_comms.c

@@ -309,6 +309,7 @@ static int process_msg(void)
 			goto out;
 
 		if (req->state == xb_req_state_wait_reply) {
+			req->msg.req_id = req->caller_req_id;
 			req->msg.type = state.msg.type;
 			req->msg.len = state.msg.len;
 			req->body = state.body;

drivers/xen/xenbus/xenbus_xs.c

@@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	req->state = xb_req_state_queued;
 	init_waitqueue_head(&req->wq);
 
+	/* Save the caller req_id and restore it later in the reply */
+	req->caller_req_id = req->msg.req_id;
 	req->msg.req_id = xs_request_enter(req);
 
 	mutex_lock(&xb_write_mutex);
@@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t,
 	req->num_vecs = num_vecs;
 	req->cb = xs_wake_up;
 
+	msg.req_id = 0;
 	msg.tx_id = t.id;
 	msg.type = type;
 	msg.len = 0;