X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fdrivers%2Fnet%2Ftun.c;h=c31d8e74f131ed5da2e7cad82e655096d7126996;hb=4bfeded9ee7ddc1cf05f6bd2c388894a7d736291;hp=e470ae59d40536fe7530774cb473ebe57000f9a8;hpb=9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00;p=kvmfornfv.git

diff --git a/kernel/drivers/net/tun.c b/kernel/drivers/net/tun.c
index e470ae59d..c31d8e74f 100644
--- a/kernel/drivers/net/tun.c
+++ b/kernel/drivers/net/tun.c
@@ -111,6 +111,7 @@ do {								\
 #define TUN_FASYNC	IFF_ATTACH_QUEUE
 /* High bits in flags field are unused. */
 #define TUN_VNET_LE     0x80000000
+#define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
 		      IFF_MULTI_QUEUE)
@@ -146,7 +147,6 @@ struct tun_file {
 	struct socket socket;
 	struct socket_wq wq;
 	struct tun_struct __rcu *tun;
-	struct net *net;
 	struct fasync_struct *fasync;
 	/* only used for fasnyc */
 	unsigned int flags;
@@ -206,14 +206,68 @@ struct tun_struct {
 	u32 flow_count;
 };
 
+#ifdef CONFIG_TUN_VNET_CROSS_LE
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_BE ? false :
+		virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be = !!(tun->flags & TUN_VNET_BE);
+
+	if (put_user(be, argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be;
+
+	if (get_user(be, argp))
+		return -EFAULT;
+
+	if (be)
+		tun->flags |= TUN_VNET_BE;
+	else
+		tun->flags &= ~TUN_VNET_BE;
+
+	return 0;
+}
+#else
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+static inline bool tun_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_LE ||
+		tun_legacy_is_little_endian(tun);
+}
+
 static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
 {
-	return __virtio16_to_cpu(tun->flags & TUN_VNET_LE, val);
+	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
 }
 
 static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
 {
-	return __cpu_to_virtio16(tun->flags & TUN_VNET_LE, val);
+	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
 }
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -493,10 +547,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
-
-		BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
-				 &tfile->socket.flags));
-		sk_release_kernel(&tfile->sk);
+		sock_put(&tfile->sk);
 	}
 }
 
@@ -516,11 +567,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -570,11 +623,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 
 	/* Re-attach the filter to persist device */
 	if (!skip_filter && (tun->filter_attached == true)) {
-		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		err = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (!err)
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -807,7 +862,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
 
-	if (skb->sk) {
+	if (skb->sk && sk_fullsock(skb->sk)) {
 		sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags);
 		sw_tx_timestamp(skb);
 	}
@@ -910,6 +965,7 @@ static const struct net_device_ops tap_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= tun_poll_controller,
 #endif
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void tun_flow_init(struct tun_struct *tun)
@@ -948,7 +1004,6 @@ static void tun_net_init(struct net_device *dev)
 		/* Zero header length */
 		dev->type = ARPHRD_NONE;
 		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 
 	case IFF_TAP:
@@ -960,7 +1015,6 @@ static void tun_net_init(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 	}
 }
@@ -988,7 +1042,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
 	     sock_writeable(sk)))
 		mask |= POLLOUT | POLLWRNORM;
 
@@ -1054,9 +1108,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		n = copy_from_iter(&gso, sizeof(gso), from);
 		if (n != sizeof(gso))
@@ -1068,7 +1124,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1247,7 +1303,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 
@@ -1357,9 +1413,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
@@ -1411,6 +1464,8 @@ static void tun_setup(struct net_device *dev)
 
 	dev->ethtool_ops = &tun_ethtool_ops;
 	dev->destructor = tun_free_netdev;
+	/* We prefer our own queue length */
+	dev->tx_queue_len = TUN_READQ_SIZE;
 }
 
 /* Trivial set of netlink ops to allow deleting tun or tap
@@ -1436,7 +1491,7 @@ static void tun_sock_write_space(struct sock *sk)
 	if (!sock_writeable(sk))
 		return;
 
-	if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+	if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
 	wqueue = sk_sleep(sk);
@@ -1492,18 +1547,10 @@ out:
 	return ret;
 }
 
-static int tun_release(struct socket *sock)
-{
-	if (sock->sk)
-		sock_put(sock->sk);
-	return 0;
-}
-
 /* Ops structure to mimic raw sockets with tun */
 static const struct proto_ops tun_socket_ops = {
 	.sendmsg = tun_sendmsg,
 	.recvmsg = tun_recvmsg,
-	.release = tun_release,
 };
 
 static struct proto tun_proto = {
@@ -1760,7 +1807,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n)
 
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		sk_detach_filter(tfile->socket.sk);
+		__sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held());
 	}
 
 	tun->filter_attached = false;
@@ -1773,7 +1820,8 @@ static int tun_attach_filter(struct tun_struct *tun)
 
 	for (i = 0; i < tun->numqueues; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (ret) {
 			tun_detach_filter(tun, i);
 			return ret;
@@ -1865,7 +1913,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	if (cmd == TUNSETIFF && !tun) {
 		ifr.ifr_name[IFNAMSIZ-1] = '\0';
 
-		ret = tun_set_iff(tfile->net, file, &ifr);
+		ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr);
 
 		if (ret)
 			goto unlock;
@@ -2056,6 +2104,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			tun->flags &= ~TUN_VNET_LE;
 		break;
 
+	case TUNGETVNETBE:
+		ret = tun_get_vnet_be(tun, argp);
+		break;
+
+	case TUNSETVNETBE:
+		ret = tun_set_vnet_be(tun, argp);
+		break;
+
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
@@ -2154,16 +2210,16 @@ out:
 
 static int tun_chr_open(struct inode *inode, struct file * file)
 {
+	struct net *net = current->nsproxy->net_ns;
 	struct tun_file *tfile;
 
 	DBG1(KERN_INFO, "tunX: tun_chr_open\n");
 
-	tfile = (struct tun_file *)sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL,
-					    &tun_proto);
+	tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+					    &tun_proto, 0);
 	if (!tfile)
 		return -ENOMEM;
 	RCU_INIT_POINTER(tfile->tun, NULL);
-	tfile->net = get_net(current->nsproxy->net_ns);
 	tfile->flags = 0;
 	tfile->ifindex = 0;
 
@@ -2174,13 +2230,11 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 	tfile->socket.ops = &tun_socket_ops;
 
 	sock_init_data(&tfile->socket, &tfile->sk);
-	sk_change_net(&tfile->sk, tfile->net);
 
 	tfile->sk.sk_write_space = tun_sock_write_space;
 	tfile->sk.sk_sndbuf = INT_MAX;
 
 	file->private_data = tfile;
-	set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags);
 	INIT_LIST_HEAD(&tfile->next);
 
 	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
@@ -2191,10 +2245,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 static int tun_chr_close(struct inode *inode, struct file *file)
 {
 	struct tun_file *tfile = file->private_data;
-	struct net *net = tfile->net;
 
 	tun_detach(tfile, true);
-	put_net(net);
 
 	return 0;
 }