1 files changed, 228 insertions, 69 deletions

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 25b28b1434f5..adcba1b7bf74 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -117,12 +117,14 @@
 static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
 static void vsock_sk_destruct(struct sock *sk);
 static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+static void vsock_close(struct sock *sk, long timeout);
 
 /* Protocol family. */
 struct proto vsock_proto = {
 	.name = "AF_VSOCK",
 	.owner = THIS_MODULE,
 	.obj_size = sizeof(struct vsock_sock),
+	.close = vsock_close,
 #ifdef CONFIG_BPF_SYSCALL
 	.psock_update_sk_prot = vsock_bpf_update_proto,
 #endif
@@ -335,7 +337,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
 
 void vsock_remove_sock(struct vsock_sock *vsk)
 {
-	vsock_remove_bound(vsk);
+	/* Transport reassignment must not remove the binding. */
+	if (sock_flag(sk_vsock(vsk), SOCK_DEAD))
+		vsock_remove_bound(vsk);
+
 	vsock_remove_connected(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_remove_sock);
@@ -402,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
 
 static bool vsock_use_local_transport(unsigned int remote_cid)
 {
+	lockdep_assert_held(&vsock_register_mutex);
+
 	if (!transport_local)
 		return false;
 
@@ -459,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 
 	remote_flags = vsk->remote_addr.svm_flags;
 
+	mutex_lock(&vsock_register_mutex);
+
 	switch (sk->sk_type) {
 	case SOCK_DGRAM:
 		new_transport = transport_dgram;
@@ -474,13 +483,30 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			new_transport = transport_h2g;
 		break;
 	default:
-		return -ESOCKTNOSUPPORT;
+		ret = -ESOCKTNOSUPPORT;
+		goto err;
 	}
 
-	if (vsk->transport) {
-		if (vsk->transport == new_transport)
-			return 0;
+	if (vsk->transport && vsk->transport == new_transport) {
+		ret = 0;
+		goto err;
+	}
+
+	/* We increase the module refcnt to prevent the transport unloading
+	 * while there are open sockets assigned to it.
+	 */
+	if (!new_transport || !try_module_get(new_transport->module)) {
+		ret = -ENODEV;
+		goto err;
+	}
 
+	/* It's safe to release the mutex after a successful try_module_get().
+	 * Whichever transport `new_transport` points at, it won't go away until
+	 * the last module_put() below or in vsock_deassign_transport().
+	 */
+	mutex_unlock(&vsock_register_mutex);
+
+	if (vsk->transport) {
 		/* transport->release() must be called with sock lock acquired.
 		 * This path can only be taken during vsock_connect(), where we
 		 * have already held the sock lock. In the other cases, this
@@ -489,13 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 		 */
 		vsk->transport->release(vsk);
 		vsock_deassign_transport(vsk);
-	}
 
-	/* We increase the module refcnt to prevent the transport unloading
-	 * while there are open sockets assigned to it.
-	 */
-	if (!new_transport || !try_module_get(new_transport->module))
-		return -ENODEV;
+		/* transport's release() and destruct() can touch some socket
+		 * state, since we are reassigning the socket to a new transport
+		 * during vsock_connect(), let's reset these fields to have a
+		 * clean state.
+		 */
+		sock_reset_flag(sk, SOCK_DONE);
+		sk->sk_state = TCP_CLOSE;
+		vsk->peer_shutdown = 0;
+	}
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		if (!new_transport->seqpacket_allow ||
@@ -514,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	vsk->transport = new_transport;
 
 	return 0;
+err:
+	mutex_unlock(&vsock_register_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vsock_assign_transport);
 
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+	u32 cid = VMADDR_CID_ANY;
+
+	mutex_lock(&vsock_register_mutex);
+	if (*transport)
+		cid = (*transport)->get_local_cid();
+	mutex_unlock(&vsock_register_mutex);
+
+	return cid;
+}
+
 bool vsock_find_cid(unsigned int cid)
 {
-	if (transport_g2h && cid == transport_g2h->get_local_cid())
+	if (cid == vsock_registered_transport_cid(&transport_g2h))
 		return true;
 
 	if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -641,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
 		unsigned int i;
 
 		for (i = 0; i < MAX_PORT_RETRIES; i++) {
-			if (port <= LAST_RESERVED_PORT)
+			if (port == VMADDR_PORT_ANY ||
+			    port <= LAST_RESERVED_PORT)
 				port = LAST_RESERVED_PORT + 1;
 
 			new_addr.svm_port = port++;
@@ -797,39 +846,44 @@ static bool sock_type_connectible(u16 type)
 
 static void __vsock_release(struct sock *sk, int level)
 {
-	if (sk) {
-		struct sock *pending;
-		struct vsock_sock *vsk;
+	struct vsock_sock *vsk;
+	struct sock *pending;
 
-		vsk = vsock_sk(sk);
-		pending = NULL;	/* Compiler warning. */
+	vsk = vsock_sk(sk);
+	pending = NULL;	/* Compiler warning. */
 
-		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
-		 * version to avoid the warning "possible recursive locking
-		 * detected". When "level" is 0, lock_sock_nested(sk, level)
-		 * is the same as lock_sock(sk).
-		 */
-		lock_sock_nested(sk, level);
+	/* When "level" is SINGLE_DEPTH_NESTING, use the nested
+	 * version to avoid the warning "possible recursive locking
+	 * detected". When "level" is 0, lock_sock_nested(sk, level)
+	 * is the same as lock_sock(sk).
+	 */
+	lock_sock_nested(sk, level);
 
-		if (vsk->transport)
-			vsk->transport->release(vsk);
-		else if (sock_type_connectible(sk->sk_type))
-			vsock_remove_sock(vsk);
+	/* Indicate to vsock_remove_sock() that the socket is being released and
+	 * can be removed from the bound_table. Unlike transport reassignment
+	 * case, where the socket must remain bound despite vsock_remove_sock()
+	 * being called from the transport release() callback.
+	 */
+	sock_set_flag(sk, SOCK_DEAD);
 
-		sock_orphan(sk);
-		sk->sk_shutdown = SHUTDOWN_MASK;
+	if (vsk->transport)
+		vsk->transport->release(vsk);
+	else if (sock_type_connectible(sk->sk_type))
+		vsock_remove_sock(vsk);
 
-		skb_queue_purge(&sk->sk_receive_queue);
+	sock_orphan(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
-		/* Clean up any sockets that never were accepted. */
-		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
-			__vsock_release(pending, SINGLE_DEPTH_NESTING);
-			sock_put(pending);
-		}
+	skb_queue_purge(&sk->sk_receive_queue);
 
-		release_sock(sk);
-		sock_put(sk);
+	/* Clean up any sockets that never were accepted. */
+	while ((pending = vsock_dequeue_accept(sk)) != NULL) {
+		__vsock_release(pending, SINGLE_DEPTH_NESTING);
+		sock_put(pending);
 	}
+
+	release_sock(sk);
+	sock_put(sk);
 }
 
 static void vsock_sk_destruct(struct sock *sk)
@@ -870,6 +924,9 @@ EXPORT_SYMBOL_GPL(vsock_create_connected);
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk)
 {
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	return vsk->transport->stream_has_data(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_stream_has_data);
@@ -878,6 +935,9 @@ s64 vsock_connectible_has_data(struct vsock_sock *vsk)
 {
 	struct sock *sk = sk_vsock(vsk);
 
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	if (sk->sk_type == SOCK_SEQPACKET)
 		return vsk->transport->seqpacket_has_data(vsk);
 	else
@@ -887,6 +947,9 @@ EXPORT_SYMBOL_GPL(vsock_connectible_has_data);
 
 s64 vsock_stream_has_space(struct vsock_sock *vsk)
 {
+	if (WARN_ON(!vsk->transport))
+		return 0;
+
 	return vsk->transport->stream_has_space(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_stream_has_space);
@@ -901,9 +964,22 @@ void vsock_data_ready(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(vsock_data_ready);
 
+/* Dummy callback required by sockmap.
+ * See unconditional call of saved_close() in sock_map_close().
+ */
+static void vsock_close(struct sock *sk, long timeout)
+{
+}
+
 static int vsock_release(struct socket *sock)
 {
-	__vsock_release(sock->sk, 0);
+	struct sock *sk = sock->sk;
+
+	if (!sk)
+		return 0;
+
+	sk->sk_prot->close(sk, 0);
+	__vsock_release(sk, 0);
 	sock->sk = NULL;
 	sock->state = SS_FREE;
 
@@ -911,7 +987,7 @@ static int vsock_release(struct socket *sock)
 }
 
 static int
-vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+vsock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len)
 {
 	int err;
 	struct sock *sk;
@@ -953,17 +1029,7 @@ static int vsock_getname(struct socket *sock,
 		vm_addr = &vsk->local_addr;
 	}
 
-	if (!vm_addr) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	/* sys_getsockname() and sys_getpeername() pass us a
-	 * MAX_SOCK_ADDR-sized buffer and don't set addr_len.  Unfortunately
-	 * that macro is defined in socket.c instead of .h, so we hardcode its
-	 * value here.
-	 */
-	BUILD_BUG_ON(sizeof(*vm_addr) > 128);
+	BUILD_BUG_ON(sizeof(*vm_addr) > sizeof(struct sockaddr_storage));
 	memcpy(addr, vm_addr, sizeof(*vm_addr));
 	err = sizeof(*vm_addr);
 
@@ -972,6 +1038,39 @@ out:
 	return err;
 }
 
+void vsock_linger(struct sock *sk)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	ssize_t (*unsent)(struct vsock_sock *vsk);
+	struct vsock_sock *vsk = vsock_sk(sk);
+	long timeout;
+
+	if (!sock_flag(sk, SOCK_LINGER))
+		return;
+
+	timeout = sk->sk_lingertime;
+	if (!timeout)
+		return;
+
+	/* Transports must implement `unsent_bytes` if they want to support
+	 * SOCK_LINGER through `vsock_linger()` since we use it to check when
+	 * the socket can be closed.
+	 */
+	unsent = vsk->transport->unsent_bytes;
+	if (!unsent)
+		return;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+
+	do {
+		if (sk_wait_event(sk, &timeout, unsent(vsk) == 0, &wait))
+			break;
+	} while (!signal_pending(current) && timeout);
+
+	remove_wait_queue(sk_sleep(sk), &wait);
+}
+EXPORT_SYMBOL_GPL(vsock_linger);
+
 static int vsock_shutdown(struct socket *sock, int mode)
 {
 	int err;
@@ -1054,6 +1153,9 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLRDHUP;
 	}
 
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
+
 	if (sock->type == SOCK_DGRAM) {
 		/* For datagram sockets we can read if there is something in
 		 * the queue and write as long as the socket isn't shutdown for
@@ -1145,6 +1247,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor)
 {
 	struct vsock_sock *vsk = vsock_sk(sk);
 
+	if (WARN_ON_ONCE(!vsk->transport))
+		return -ENODEV;
+
 	return vsk->transport->read_skb(vsk, read_actor);
 }
 
@@ -1223,7 +1328,7 @@ out:
 }
 
 static int vsock_dgram_connect(struct socket *sock,
-			       struct sockaddr *addr, int addr_len, int flags)
+			       struct sockaddr_unsized *addr, int addr_len, int flags)
 {
 	int err;
 	struct sock *sk;
@@ -1309,6 +1414,28 @@ static int vsock_do_ioctl(struct socket *sock, unsigned int cmd,
 	vsk = vsock_sk(sk);
 
 	switch (cmd) {
+	case SIOCINQ: {
+		ssize_t n_bytes;
+
+		if (!vsk->transport) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (sock_type_connectible(sk->sk_type) &&
+		    sk->sk_state == TCP_LISTEN) {
+			ret = -EINVAL;
+			break;
+		}
+
+		n_bytes = vsock_stream_has_data(vsk);
+		if (n_bytes < 0) {
+			ret = n_bytes;
+			break;
+		}
+		ret = put_user(n_bytes, arg);
+		break;
+	}
 	case SIOCOUTQ: {
 		ssize_t n_bytes;
 
@@ -1401,7 +1528,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	sock_put(sk);
 }
 
-static int vsock_connect(struct socket *sock, struct sockaddr *addr,
+static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr,
 			 int addr_len, int flags)
 {
 	int err;
@@ -1485,6 +1612,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 		if (err < 0)
 			goto out;
 
+		/* sk_err might have been set as a result of an earlier
+		 * (failed) connect attempt.
+		 */
+		sk->sk_err = 0;
+
 		/* Mark sock as connecting and set the error code to in
 		 * progress in case this is a non-blocking connect.
 		 */
@@ -1499,7 +1631,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
+	/* If the socket is already closing or it is in an error state, there
+	 * is no point in waiting.
+	 */
+	while (sk->sk_state != TCP_ESTABLISHED &&
+	       sk->sk_state != TCP_CLOSING && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection
@@ -1513,7 +1649,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 			 * reschedule it, then ungrab the socket refcount to
 			 * keep it balanced.
 			 */
-			if (mod_delayed_work(system_wq, &vsk->connect_work,
+			if (mod_delayed_work(system_percpu_wq, &vsk->connect_work,
 					     timeout))
 				sock_put(sk);
 
@@ -1525,18 +1661,40 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 		timeout = schedule_timeout(timeout);
 		lock_sock(sk);
 
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeout);
-			sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE;
-			sock->state = SS_UNCONNECTED;
-			vsock_transport_cancel_pkt(vsk);
-			vsock_remove_connected(vsk);
-			goto out_wait;
-		} else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) {
-			err = -ETIMEDOUT;
+		/* Connection established. Whatever happens to socket once we
+		 * release it, that's not connect()'s concern. No need to go
+		 * into signal and timeout handling. Call it a day.
+		 *
+		 * Note that allowing to "reset" an already established socket
+		 * here is racy and insecure.
+		 */
+		if (sk->sk_state == TCP_ESTABLISHED)
+			break;
+
+		/* If connection was _not_ established and a signal/timeout came
+		 * to be, we want the socket's state reset. User space may want
+		 * to retry.
+		 *
+		 * sk_state != TCP_ESTABLISHED implies that socket is not on
+		 * vsock_connected_table. We keep the binding and the transport
+		 * assigned.
+		 */
+		if (signal_pending(current) || timeout == 0) {
+			err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout);
+
+			/* Listener might have already responded with
+			 * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our
+			 * sk_state == TCP_SYN_SENT, which hereby we break.
+			 * In such case VIRTIO_VSOCK_OP_RST will follow.
+			 */
 			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
+
+			/* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by
+			 * transport->connect().
+			 */
 			vsock_transport_cancel_pkt(vsk);
+
 			goto out_wait;
 		}
 
@@ -2447,18 +2605,19 @@ static long vsock_dev_do_ioctl(struct file *filp,
 			       unsigned int cmd, void __user *ptr)
 {
 	u32 __user *p = ptr;
-	u32 cid = VMADDR_CID_ANY;
 	int retval = 0;
+	u32 cid;
 
 	switch (cmd) {
 	case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
 		/* To be compatible with the VMCI behavior, we prioritize the
 		 * guest CID instead of well-know host CID (VMADDR_CID_HOST).
 		 */
-		if (transport_g2h)
-			cid = transport_g2h->get_local_cid();
-		else if (transport_h2g)
-			cid = transport_h2g->get_local_cid();
+		cid = vsock_registered_transport_cid(&transport_g2h);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_h2g);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_local);
 
 		if (put_user(cid, p) != 0)
 			retval = -EFAULT;