3 files changed, 115 insertions, 121 deletions

diff --git a/kernel/net/vmw_vsock/af_vsock.c b/kernel/net/vmw_vsock/af_vsock.c
index 2ec86e652..7fd1220fb 100644
--- a/kernel/net/vmw_vsock/af_vsock.c
+++ b/kernel/net/vmw_vsock/af_vsock.c
@@ -36,19 +36,20 @@
  * not support simultaneous connects (two "client" sockets connecting).
  *
  * - "Server" sockets are referred to as listener sockets throughout this
- * implementation because they are in the SS_LISTEN state.  When a connection
- * request is received (the second kind of socket mentioned above), we create a
- * new socket and refer to it as a pending socket.  These pending sockets are
- * placed on the pending connection list of the listener socket.  When future
- * packets are received for the address the listener socket is bound to, we
- * check if the source of the packet is from one that has an existing pending
- * connection.  If it does, we process the packet for the pending socket.  When
- * that socket reaches the connected state, it is removed from the listener
- * socket's pending list and enqueued in the listener socket's accept queue.
- * Callers of accept(2) will accept connected sockets from the listener socket's
- * accept queue.  If the socket cannot be accepted for some reason then it is
- * marked rejected.  Once the connection is accepted, it is owned by the user
- * process and the responsibility for cleanup falls with that user process.
+ * implementation because they are in the VSOCK_SS_LISTEN state.  When a
+ * connection request is received (the second kind of socket mentioned above),
+ * we create a new socket and refer to it as a pending socket.  These pending
+ * sockets are placed on the pending connection list of the listener socket.
+ * When future packets are received for the address the listener socket is
+ * bound to, we check if the source of the packet is from one that has an
+ * existing pending connection.  If it does, we process the packet for the
+ * pending socket.  When that socket reaches the connected state, it is removed
+ * from the listener socket's pending list and enqueued in the listener
+ * socket's accept queue.  Callers of accept(2) will accept connected sockets
+ * from the listener socket's accept queue.  If the socket cannot be accepted
+ * for some reason then it is marked rejected.  Once the connection is
+ * accepted, it is owned by the user process and the responsibility for cleanup
+ * falls with that user process.
  *
  * - It is possible that these pending sockets will never reach the connected
  * state; in fact, we may never receive another packet after the connection
@@ -114,8 +115,6 @@ static struct proto vsock_proto = {
  */
 #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ)
 
-#define SS_LISTEN 255
-
 static const struct vsock_transport *transport;
 static DEFINE_MUTEX(vsock_register_mutex);
 
@@ -581,13 +580,14 @@ struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
 			    gfp_t priority,
-			    unsigned short type)
+			    unsigned short type,
+			    int kern)
 {
 	struct sock *sk;
 	struct vsock_sock *psk;
 	struct vsock_sock *vsk;
 
-	sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto);
+	sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern);
 	if (!sk)
 		return NULL;
 
@@ -886,7 +886,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		/* Listening sockets that have connections in their accept
 		 * queue can be read.
 		 */
-		if (sk->sk_state == SS_LISTEN
+		if (sk->sk_state == VSOCK_SS_LISTEN
 		    && !vsock_is_accept_queue_empty(sk))
 			mask |= POLLIN | POLLRDNORM;
 
@@ -1143,7 +1143,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		err = -EALREADY;
 		break;
 	default:
-		if ((sk->sk_state == SS_LISTEN) ||
+		if ((sk->sk_state == VSOCK_SS_LISTEN) ||
 		    vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
 			err = -EINVAL;
 			goto out;
@@ -1255,7 +1255,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
 		goto out;
 	}
 
-	if (listener->sk_state != SS_LISTEN) {
+	if (listener->sk_state != VSOCK_SS_LISTEN) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -1347,7 +1347,7 @@ static int vsock_listen(struct socket *sock, int backlog)
 	}
 
 	sk->sk_max_ack_backlog = backlog;
-	sk->sk_state = SS_LISTEN;
+	sk->sk_state = VSOCK_SS_LISTEN;
 
 	err = 0;
 
@@ -1866,7 +1866,7 @@ static int vsock_create(struct net *net, struct socket *sock,
 
 	sock->state = SS_UNCONNECTED;
 
-	return __vsock_create(net, sock, NULL, GFP_KERNEL, 0) ? 0 : -ENOMEM;
+	return __vsock_create(net, sock, NULL, GFP_KERNEL, 0, kern) ? 0 : -ENOMEM;
 }
 
 static const struct net_proto_family vsock_family_ops = {
@@ -1947,13 +1947,13 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 	err = misc_register(&vsock_device);
 	if (err) {
 		pr_err("Failed to register misc device\n");
-		return -ENOENT;
+		goto err_reset_transport;
 	}
 
 	err = proto_register(&vsock_proto, 1);	/* we want our slab */
 	if (err) {
 		pr_err("Cannot register vsock protocol\n");
-		goto err_misc_deregister;
+		goto err_deregister_misc;
 	}
 
 	err = sock_register(&vsock_family_ops);
@@ -1968,8 +1968,9 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 
 err_unregister_proto:
 	proto_unregister(&vsock_proto);
-err_misc_deregister:
+err_deregister_misc:
 	misc_deregister(&vsock_device);
+err_reset_transport:
 	transport = NULL;
 err_busy:
 	mutex_unlock(&vsock_register_mutex);
diff --git a/kernel/net/vmw_vsock/vmci_transport.c b/kernel/net/vmw_vsock/vmci_transport.c
index c294da095..0a369bb44 100644
--- a/kernel/net/vmw_vsock/vmci_transport.c
+++ b/kernel/net/vmw_vsock/vmci_transport.c
@@ -40,13 +40,11 @@
 
 static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg);
 static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg);
-static void vmci_transport_peer_attach_cb(u32 sub_id,
-					  const struct vmci_event_data *ed,
-					  void *client_data);
 static void vmci_transport_peer_detach_cb(u32 sub_id,
 					  const struct vmci_event_data *ed,
 					  void *client_data);
 static void vmci_transport_recv_pkt_work(struct work_struct *work);
+static void vmci_transport_cleanup(struct work_struct *work);
 static int vmci_transport_recv_listen(struct sock *sk,
 				      struct vmci_transport_packet *pkt);
 static int vmci_transport_recv_connecting_server(
@@ -75,6 +73,10 @@ struct vmci_transport_recv_pkt_info {
 	struct vmci_transport_packet pkt;
 };
 
+static LIST_HEAD(vmci_transport_cleanup_list);
+static DEFINE_SPINLOCK(vmci_transport_cleanup_lock);
+static DECLARE_WORK(vmci_transport_cleanup_work, vmci_transport_cleanup);
+
 static struct vmci_handle vmci_transport_stream_handle = { VMCI_INVALID_ID,
 							   VMCI_INVALID_ID };
 static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID;
@@ -90,8 +92,6 @@ static int PROTOCOL_OVERRIDE = -1;
  */
 #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ)
 
-#define SS_LISTEN 255
-
 /* Helper function to convert from a VMCI error code to a VSock error code. */
 
 static s32 vmci_transport_error_to_vsock_error(s32 vmci_error)
@@ -791,44 +791,6 @@ out:
 	return err;
 }
 
-static void vmci_transport_peer_attach_cb(u32 sub_id,
-					  const struct vmci_event_data *e_data,
-					  void *client_data)
-{
-	struct sock *sk = client_data;
-	const struct vmci_event_payload_qp *e_payload;
-	struct vsock_sock *vsk;
-
-	e_payload = vmci_event_data_const_payload(e_data);
-
-	vsk = vsock_sk(sk);
-
-	/* We don't ask for delayed CBs when we subscribe to this event (we
-	 * pass 0 as flags to vmci_event_subscribe()).  VMCI makes no
-	 * guarantees in that case about what context we might be running in,
-	 * so it could be BH or process, blockable or non-blockable.  So we
-	 * need to account for all possible contexts here.
-	 */
-	local_bh_disable();
-	bh_lock_sock(sk);
-
-	/* XXX This is lame, we should provide a way to lookup sockets by
-	 * qp_handle.
-	 */
-	if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle,
-				 e_payload->handle)) {
-		/* XXX This doesn't do anything, but in the future we may want
-		 * to set a flag here to verify the attach really did occur and
-		 * we weren't just sent a datagram claiming it was.
-		 */
-		goto out;
-	}
-
-out:
-	bh_unlock_sock(sk);
-	local_bh_enable();
-}
-
 static void vmci_transport_handle_detach(struct sock *sk)
 {
 	struct vsock_sock *vsk;
@@ -871,28 +833,38 @@ static void vmci_transport_peer_detach_cb(u32 sub_id,
 					  const struct vmci_event_data *e_data,
 					  void *client_data)
 {
-	struct sock *sk = client_data;
+	struct vmci_transport *trans = client_data;
 	const struct vmci_event_payload_qp *e_payload;
-	struct vsock_sock *vsk;
 
 	e_payload = vmci_event_data_const_payload(e_data);
-	vsk = vsock_sk(sk);
-	if (vmci_handle_is_invalid(e_payload->handle))
-		return;
-
-	/* Same rules for locking as for peer_attach_cb(). */
-	local_bh_disable();
-	bh_lock_sock(sk);
 
 	/* XXX This is lame, we should provide a way to lookup sockets by
 	 * qp_handle.
 	 */
-	if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle,
-				 e_payload->handle))
-		vmci_transport_handle_detach(sk);
+	if (vmci_handle_is_invalid(e_payload->handle) ||
+	    vmci_handle_is_equal(trans->qp_handle, e_payload->handle))
+		return;
 
-	bh_unlock_sock(sk);
-	local_bh_enable();
+	/* We don't ask for delayed CBs when we subscribe to this event (we
+	 * pass 0 as flags to vmci_event_subscribe()).  VMCI makes no
+	 * guarantees in that case about what context we might be running in,
+	 * so it could be BH or process, blockable or non-blockable.  So we
+	 * need to account for all possible contexts here.
+	 */
+	spin_lock_bh(&trans->lock);
+	if (!trans->sk)
+		goto out;
+
+	/* Apart from here, trans->lock is only grabbed as part of sk destruct,
+	 * where trans->sk isn't locked.
+	 */
+	bh_lock_sock(trans->sk);
+
+	vmci_transport_handle_detach(trans->sk);
+
+	bh_unlock_sock(trans->sk);
+ out:
+	spin_unlock_bh(&trans->lock);
 }
 
 static void vmci_transport_qp_resumed_cb(u32 sub_id,
@@ -919,7 +891,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work)
 	vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context;
 
 	switch (sk->sk_state) {
-	case SS_LISTEN:
+	case VSOCK_SS_LISTEN:
 		vmci_transport_recv_listen(sk, pkt);
 		break;
 	case SS_CONNECTING:
@@ -1022,7 +994,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	}
 
 	pending = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
-				 sk->sk_type);
+				 sk->sk_type, 0);
 	if (!pending) {
 		vmci_transport_send_reset(sk, pkt);
 		return -ENOMEM;
@@ -1181,7 +1153,7 @@ vmci_transport_recv_connecting_server(struct sock *listener,
 	 */
 	err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH,
 				   vmci_transport_peer_detach_cb,
-				   pending, &detach_sub_id);
+				   vmci_trans(vpending), &detach_sub_id);
 	if (err < VMCI_SUCCESS) {
 		vmci_transport_send_reset(pending, pkt);
 		err = vmci_transport_error_to_vsock_error(err);
@@ -1262,7 +1234,7 @@ vmci_transport_recv_connecting_server(struct sock *listener,
 	/* Callers of accept() will be be waiting on the listening socket, not
 	 * the pending socket.
 	 */
-	listener->sk_state_change(listener);
+	listener->sk_data_ready(listener);
 
 	return 0;
 
@@ -1321,7 +1293,6 @@ vmci_transport_recv_connecting_client(struct sock *sk,
 		    || vmci_trans(vsk)->qpair
 		    || vmci_trans(vsk)->produce_size != 0
 		    || vmci_trans(vsk)->consume_size != 0
-		    || vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID
 		    || vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) {
 			skerr = EPROTO;
 			err = -EINVAL;
@@ -1389,7 +1360,6 @@ static int vmci_transport_recv_connecting_client_negotiate(
 	struct vsock_sock *vsk;
 	struct vmci_handle handle;
 	struct vmci_qp *qpair;
-	u32 attach_sub_id;
 	u32 detach_sub_id;
 	bool is_local;
 	u32 flags;
@@ -1399,7 +1369,6 @@ static int vmci_transport_recv_connecting_client_negotiate(
 
 	vsk = vsock_sk(sk);
 	handle = VMCI_INVALID_HANDLE;
-	attach_sub_id = VMCI_INVALID_ID;
 	detach_sub_id = VMCI_INVALID_ID;
 
 	/* If we have gotten here then we should be past the point where old
@@ -1444,23 +1413,15 @@ static int vmci_transport_recv_connecting_client_negotiate(
 		goto destroy;
 	}
 
-	/* Subscribe to attach and detach events first.
+	/* Subscribe to detach events first.
 	 *
 	 * XXX We attach once for each queue pair created for now so it is easy
 	 * to find the socket (it's provided), but later we should only
 	 * subscribe once and add a way to lookup sockets by queue pair handle.
 	 */
-	err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH,
-				   vmci_transport_peer_attach_cb,
-				   sk, &attach_sub_id);
-	if (err < VMCI_SUCCESS) {
-		err = vmci_transport_error_to_vsock_error(err);
-		goto destroy;
-	}
-
 	err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH,
 				   vmci_transport_peer_detach_cb,
-				   sk, &detach_sub_id);
+				   vmci_trans(vsk), &detach_sub_id);
 	if (err < VMCI_SUCCESS) {
 		err = vmci_transport_error_to_vsock_error(err);
 		goto destroy;
@@ -1496,7 +1457,6 @@ static int vmci_transport_recv_connecting_client_negotiate(
 	vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size =
 		pkt->u.size;
 
-	vmci_trans(vsk)->attach_sub_id = attach_sub_id;
 	vmci_trans(vsk)->detach_sub_id = detach_sub_id;
 
 	vmci_trans(vsk)->notify_ops->process_negotiate(sk);
@@ -1504,9 +1464,6 @@ static int vmci_transport_recv_connecting_client_negotiate(
 	return 0;
 
 destroy:
-	if (attach_sub_id != VMCI_INVALID_ID)
-		vmci_event_unsubscribe(attach_sub_id);
-
 	if (detach_sub_id != VMCI_INVALID_ID)
 		vmci_event_unsubscribe(detach_sub_id);
 
@@ -1607,9 +1564,11 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk,
 	vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE;
 	vmci_trans(vsk)->qpair = NULL;
 	vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = 0;
-	vmci_trans(vsk)->attach_sub_id = vmci_trans(vsk)->detach_sub_id =
-		VMCI_INVALID_ID;
+	vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID;
 	vmci_trans(vsk)->notify_ops = NULL;
+	INIT_LIST_HEAD(&vmci_trans(vsk)->elem);
+	vmci_trans(vsk)->sk = &vsk->sk;
+	spin_lock_init(&vmci_trans(vsk)->lock);
 	if (psk) {
 		vmci_trans(vsk)->queue_pair_size =
 			vmci_trans(psk)->queue_pair_size;
@@ -1629,29 +1588,57 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk,
 	return 0;
 }
 
-static void vmci_transport_destruct(struct vsock_sock *vsk)
+static void vmci_transport_free_resources(struct list_head *transport_list)
 {
-	if (vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID) {
-		vmci_event_unsubscribe(vmci_trans(vsk)->attach_sub_id);
-		vmci_trans(vsk)->attach_sub_id = VMCI_INVALID_ID;
-	}
+	while (!list_empty(transport_list)) {
+		struct vmci_transport *transport =
+		    list_first_entry(transport_list, struct vmci_transport,
+				     elem);
+		list_del(&transport->elem);
 
-	if (vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) {
-		vmci_event_unsubscribe(vmci_trans(vsk)->detach_sub_id);
-		vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID;
-	}
+		if (transport->detach_sub_id != VMCI_INVALID_ID) {
+			vmci_event_unsubscribe(transport->detach_sub_id);
+			transport->detach_sub_id = VMCI_INVALID_ID;
+		}
 
-	if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) {
-		vmci_qpair_detach(&vmci_trans(vsk)->qpair);
-		vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE;
-		vmci_trans(vsk)->produce_size = 0;
-		vmci_trans(vsk)->consume_size = 0;
+		if (!vmci_handle_is_invalid(transport->qp_handle)) {
+			vmci_qpair_detach(&transport->qpair);
+			transport->qp_handle = VMCI_INVALID_HANDLE;
+			transport->produce_size = 0;
+			transport->consume_size = 0;
+		}
+
+		kfree(transport);
 	}
+}
+
+static void vmci_transport_cleanup(struct work_struct *work)
+{
+	LIST_HEAD(pending);
+
+	spin_lock_bh(&vmci_transport_cleanup_lock);
+	list_replace_init(&vmci_transport_cleanup_list, &pending);
+	spin_unlock_bh(&vmci_transport_cleanup_lock);
+	vmci_transport_free_resources(&pending);
+}
+
+static void vmci_transport_destruct(struct vsock_sock *vsk)
+{
+	/* Ensure that the detach callback doesn't use the sk/vsk
+	 * we are about to destruct.
+	 */
+	spin_lock_bh(&vmci_trans(vsk)->lock);
+	vmci_trans(vsk)->sk = NULL;
+	spin_unlock_bh(&vmci_trans(vsk)->lock);
 
 	if (vmci_trans(vsk)->notify_ops)
 		vmci_trans(vsk)->notify_ops->socket_destruct(vsk);
 
-	kfree(vsk->trans);
+	spin_lock_bh(&vmci_transport_cleanup_lock);
+	list_add(&vmci_trans(vsk)->elem, &vmci_transport_cleanup_list);
+	spin_unlock_bh(&vmci_transport_cleanup_lock);
+	schedule_work(&vmci_transport_cleanup_work);
+
 	vsk->trans = NULL;
 }
 
@@ -2146,6 +2133,9 @@ module_init(vmci_transport_init);
 
 static void __exit vmci_transport_exit(void)
 {
+	cancel_work_sync(&vmci_transport_cleanup_work);
+	vmci_transport_free_resources(&vmci_transport_cleanup_list);
+
 	if (!vmci_handle_is_invalid(vmci_transport_stream_handle)) {
 		if (vmci_datagram_destroy_handle(
 			vmci_transport_stream_handle) != VMCI_SUCCESS)
@@ -2164,6 +2154,7 @@ module_exit(vmci_transport_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMCI transport for Virtual Sockets");
+MODULE_VERSION("1.0.2.0-k");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("vmware_vsock");
 MODULE_ALIAS_NETPROTO(PF_VSOCK);
diff --git a/kernel/net/vmw_vsock/vmci_transport.h b/kernel/net/vmw_vsock/vmci_transport.h
index ce6c9623d..2ad46f396 100644
--- a/kernel/net/vmw_vsock/vmci_transport.h
+++ b/kernel/net/vmw_vsock/vmci_transport.h
@@ -119,10 +119,12 @@ struct vmci_transport {
 	u64 queue_pair_size;
 	u64 queue_pair_min_size;
 	u64 queue_pair_max_size;
-	u32 attach_sub_id;
 	u32 detach_sub_id;
 	union vmci_transport_notify notify;
 	struct vmci_transport_notify_ops *notify_ops;
+	struct list_head elem;
+	struct sock *sk;
+	spinlock_t lock; /* protects sk. */
 };
 
 int vmci_transport_register(void);