1 files changed, 121 insertions, 124 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5cdcf92eb310..a639de8401f8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -60,6 +60,7 @@
 #include <linux/if_arp.h>
 #include <linux/if_ether.h>
 #include <linux/if_tun.h>
+#include <linux/if_vlan.h>
 #include <linux/crc32.h>
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
@@ -137,7 +138,10 @@ struct tun_file {
 	struct fasync_struct *fasync;
 	/* only used for fasnyc */
 	unsigned int flags;
-	u16 queue_index;
+	union {
+		u16 queue_index;
+		unsigned int ifindex;
+	};
 	struct list_head next;
 	struct tun_struct *detached;
 };
@@ -405,6 +409,12 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
 	return tun;
 }
 
+static void tun_queue_purge(struct tun_file *tfile)
+{
+	skb_queue_purge(&tfile->sk.sk_receive_queue);
+	skb_queue_purge(&tfile->sk.sk_error_queue);
+}
+
 static void __tun_detach(struct tun_file *tfile, bool clean)
 {
 	struct tun_file *ntfile;
@@ -431,7 +441,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		synchronize_net();
 		tun_flow_delete_by_queue(tun, tun->numqueues + 1);
 		/* Drop read queue */
-		skb_queue_purge(&tfile->sk.sk_receive_queue);
+		tun_queue_purge(tfile);
 		tun_set_real_num_queues(tun);
 	} else if (tfile->detached && clean) {
 		tun = tun_enable_queue(tfile);
@@ -483,12 +493,12 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		/* Drop read queue */
-		skb_queue_purge(&tfile->sk.sk_receive_queue);
+		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
 		tun_enable_queue(tfile);
-		skb_queue_purge(&tfile->sk.sk_receive_queue);
+		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
 	}
 	BUG_ON(tun->numdisabled != 0);
@@ -497,7 +507,7 @@ static void tun_detach_all(struct net_device *dev)
 		module_put(THIS_MODULE);
 }
 
-static int tun_attach(struct tun_struct *tun, struct file *file)
+static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
 {
 	struct tun_file *tfile = file->private_data;
 	int err;
@@ -522,7 +532,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
 	err = 0;
 
 	/* Re-attach the filter to presist device */
-	if (tun->filter_attached == true) {
+	if (!skip_filter && (tun->filter_attached == true)) {
 		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
 		if (!err)
 			goto out;
@@ -739,10 +749,17 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 			  >= dev->tx_queue_len / tun->numqueues)
 		goto drop;
 
-	/* Orphan the skb - required as we might hang on to it
-	 * for indefinite time. */
 	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
+
+	if (skb->sk) {
+		sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags);
+		sw_tx_timestamp(skb);
+	}
+
+	/* Orphan the skb - required as we might hang on to it
+	 * for indefinite time.
+	 */
 	skb_orphan(skb);
 
 	nf_reset(skb);
@@ -943,7 +960,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 		linear = len;
 
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   &err);
+				   &err, 0);
 	if (!skb)
 		return ERR_PTR(err);
 
@@ -955,86 +972,6 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	return skb;
 }
 
-/* set skb frags from iovec, this can move to core network code for reuse */
-static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
-				  int offset, size_t count)
-{
-	int len = iov_length(from, count) - offset;
-	int copy = skb_headlen(skb);
-	int size, offset1 = 0;
-	int i = 0;
-
-	/* Skip over from offset */
-	while (count && (offset >= from->iov_len)) {
-		offset -= from->iov_len;
-		++from;
-		--count;
-	}
-
-	/* copy up to skb headlen */
-	while (count && (copy > 0)) {
-		size = min_t(unsigned int, copy, from->iov_len - offset);
-		if (copy_from_user(skb->data + offset1, from->iov_base + offset,
-				   size))
-			return -EFAULT;
-		if (copy > size) {
-			++from;
-			--count;
-			offset = 0;
-		} else
-			offset += size;
-		copy -= size;
-		offset1 += size;
-	}
-
-	if (len == offset1)
-		return 0;
-
-	while (count--) {
-		struct page *page[MAX_SKB_FRAGS];
-		int num_pages;
-		unsigned long base;
-		unsigned long truesize;
-
-		len = from->iov_len - offset;
-		if (!len) {
-			offset = 0;
-			++from;
-			continue;
-		}
-		base = (unsigned long)from->iov_base + offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		if (i + size > MAX_SKB_FRAGS)
-			return -EMSGSIZE;
-		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
-		if (num_pages != size) {
-			int j;
-
-			for (j = 0; j < num_pages; j++)
-				put_page(page[i + j]);
-			return -EFAULT;
-		}
-		truesize = size * PAGE_SIZE;
-		skb->data_len += len;
-		skb->len += len;
-		skb->truesize += truesize;
-		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
-		while (len) {
-			int off = base & ~PAGE_MASK;
-			int size = min_t(int, len, PAGE_SIZE - off);
-			__skb_fill_page_desc(skb, i, page[i], off, size);
-			skb_shinfo(skb)->nr_frags++;
-			/* increase sk_wmem_alloc */
-			base += size;
-			len -= size;
-			i++;
-		}
-		offset = 0;
-		++from;
-	}
-	return 0;
-}
-
 /* Get packet from user space buffer */
 static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			    void *msg_control, const struct iovec *iv,
@@ -1051,8 +988,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	u32 rxhash;
 
 	if (!(tun->flags & TUN_NO_PI)) {
-		if ((len -= sizeof(pi)) > total_len)
+		if (len < sizeof(pi))
 			return -EINVAL;
+		len -= sizeof(pi);
 
 		if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
 			return -EFAULT;
@@ -1060,8 +998,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & TUN_VNET_HDR) {
-		if ((len -= tun->vnet_hdr_sz) > total_len)
+		if (len < tun->vnet_hdr_sz)
 			return -EINVAL;
+		len -= tun->vnet_hdr_sz;
 
 		if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
 			return -EFAULT;
@@ -1082,32 +1021,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			return -EINVAL;
 	}
 
-	if (msg_control)
-		zerocopy = true;
-
-	if (zerocopy) {
-		/* Userspace may produce vectors with count greater than
-		 * MAX_SKB_FRAGS, so we need to linearize parts of the skb
-		 * to let the rest of data to be fit in the frags.
-		 */
-		if (count > MAX_SKB_FRAGS) {
-			copylen = iov_length(iv, count - MAX_SKB_FRAGS);
-			if (copylen < offset)
-				copylen = 0;
-			else
-				copylen -= offset;
-		} else
-				copylen = 0;
-		/* There are 256 bytes to be copied in skb, so there is enough
-		 * room for skb expand head in case it is used.
+	if (msg_control) {
+		/* There are 256 bytes to be copied in skb, so there is
+		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
-		if (copylen < gso.hdr_len)
-			copylen = gso.hdr_len;
-		if (!copylen)
-			copylen = GOODCOPY_LEN;
+		copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
 		linear = copylen;
-	} else {
+		if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
+			zerocopy = true;
+	}
+
+	if (!zerocopy) {
 		copylen = len;
 		linear = gso.hdr_len;
 	}
@@ -1121,8 +1046,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (zerocopy)
 		err = zerocopy_sg_from_iovec(skb, iv, offset, count);
-	else
+	else {
 		err = skb_copy_datagram_from_iovec(skb, 0, iv, offset, len);
+		if (!err && msg_control) {
+			struct ubuf_info *uarg = msg_control;
+			uarg->callback(uarg, false);
+		}
+	}
 
 	if (err) {
 		tun->dev->stats.rx_dropped++;
@@ -1246,6 +1176,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 {
 	struct tun_pi pi = { 0, skb->protocol };
 	ssize_t total = 0;
+	int vlan_offset = 0;
 
 	if (!(tun->flags & TUN_NO_PI)) {
 		if ((len -= sizeof(pi)) < 0)
@@ -1309,11 +1240,40 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		total += tun->vnet_hdr_sz;
 	}
 
-	len = min_t(int, skb->len, len);
+	if (!vlan_tx_tag_present(skb)) {
+		len = min_t(int, skb->len, len);
+	} else {
+		int copy, ret;
+		struct {
+			__be16 h_vlan_proto;
+			__be16 h_vlan_TCI;
+		} veth;
+
+		veth.h_vlan_proto = skb->vlan_proto;
+		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
+
+		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
+		len = min_t(int, skb->len + VLAN_HLEN, len);
+
+		copy = min_t(int, vlan_offset, len);
+		ret = skb_copy_datagram_const_iovec(skb, 0, iv, total, copy);
+		len -= copy;
+		total += copy;
+		if (ret || !len)
+			goto done;
 
-	skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
-	total += skb->len;
+		copy = min_t(int, sizeof(veth), len);
+		ret = memcpy_toiovecend(iv, (void *)&veth, total, copy);
+		len -= copy;
+		total += copy;
+		if (ret || !len)
+			goto done;
+	}
 
+	skb_copy_datagram_const_iovec(skb, vlan_offset, iv, total, len);
+	total += len;
+
+done:
 	tun->dev->stats.tx_packets++;
 	tun->dev->stats.tx_bytes += len;
 
@@ -1462,7 +1422,6 @@ static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
 	return ret;
 }
 
-
 static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 		       struct msghdr *m, size_t total_len,
 		       int flags)
@@ -1474,10 +1433,15 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!tun)
 		return -EBADFD;
 
-	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) {
+	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
 		ret = -EINVAL;
 		goto out;
 	}
+	if (flags & MSG_ERRQUEUE) {
+		ret = sock_recv_errqueue(sock->sk, m, total_len,
+					 SOL_PACKET, TUN_TX_TIMESTAMP);
+		goto out;
+	}
 	ret = tun_do_read(tun, tfile, iocb, m->msg_iov, total_len,
 			  flags & MSG_DONTWAIT);
 	if (ret > total_len) {
@@ -1601,7 +1565,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (err < 0)
 			return err;
 
-		err = tun_attach(tun, file);
+		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER);
 		if (err < 0)
 			return err;
 
@@ -1648,6 +1612,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		dev_net_set(dev, net);
 		dev->rtnl_link_ops = &tun_link_ops;
+		dev->ifindex = tfile->ifindex;
 
 		tun = netdev_priv(dev);
 		tun->dev = dev;
@@ -1668,12 +1633,13 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		tun_flow_init(tun);
 
 		dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
-			TUN_USER_FEATURES;
+				   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+				   NETIF_F_HW_VLAN_STAG_TX;
 		dev->features = dev->hw_features;
 		dev->vlan_features = dev->features;
 
 		INIT_LIST_HEAD(&tun->disabled);
-		err = tun_attach(tun, file);
+		err = tun_attach(tun, file, false);
 		if (err < 0)
 			goto err_free_dev;
 
@@ -1837,7 +1803,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 		ret = security_tun_dev_attach_queue(tun->security);
 		if (ret < 0)
 			goto unlock;
-		ret = tun_attach(tun, file);
+		ret = tun_attach(tun, file, false);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached)
@@ -1863,6 +1829,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	kgid_t group;
 	int sndbuf;
 	int vnet_hdr_sz;
+	unsigned int ifindex;
 	int ret;
 
 	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
@@ -1897,6 +1864,19 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EFAULT;
 		goto unlock;
 	}
+	if (cmd == TUNSETIFINDEX) {
+		ret = -EPERM;
+		if (tun)
+			goto unlock;
+
+		ret = -EFAULT;
+		if (copy_from_user(&ifindex, argp, sizeof(ifindex)))
+			goto unlock;
+
+		ret = 0;
+		tfile->ifindex = ifindex;
+		goto unlock;
+	}
 
 	ret = -EBADFD;
 	if (!tun)
@@ -1909,6 +1889,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	case TUNGETIFF:
 		tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
 
+		if (tfile->detached)
+			ifr.ifr_flags |= IFF_DETACH_QUEUE;
+		if (!tfile->socket.sk->sk_filter)
+			ifr.ifr_flags |= IFF_NOFILTER;
+
 		if (copy_to_user(argp, &ifr, ifreq_len))
 			ret = -EFAULT;
 		break;
@@ -2065,6 +2050,16 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		tun_detach_filter(tun, tun->numqueues);
 		break;
 
+	case TUNGETFILTER:
+		ret = -EINVAL;
+		if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+			break;
+		ret = -EFAULT;
+		if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog)))
+			break;
+		ret = 0;
+		break;
+
 	default:
 		ret = -EINVAL;
 		break;
@@ -2145,6 +2140,7 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 	rcu_assign_pointer(tfile->tun, NULL);
 	tfile->net = get_net(current->nsproxy->net_ns);
 	tfile->flags = 0;
+	tfile->ifindex = 0;
 
 	rcu_assign_pointer(tfile->socket.wq, &tfile->wq);
 	init_waitqueue_head(&tfile->wq.wait);
@@ -2260,6 +2256,7 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.get_msglevel	= tun_get_msglevel,
 	.set_msglevel	= tun_set_msglevel,
 	.get_link	= ethtool_op_get_link,
+	.get_ts_info	= ethtool_op_get_ts_info,
 };