[PATCH 1/6] tuntap: move socket to tun_file

From: Jason Wang <jasowang@redhat.com>
To: mst@redhat.com, akong@redhat.com, habanero@linux.vnet.ibm.com,
	tahm@linux.vnet.ibm.com, haixiao@juniper.net,
	jwhan@filewood.snu.ac.kr, ernesto.martin@viasat.com,
	mashirle@us.ibm.com, davem@davemloft.net, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org, krkumar2@in.ibm.com
Cc: shemminger@vyatta.com, edumazet@google.com,
	Jason Wang <jasowang@redhat.com>
Subject: [PATCH 1/6] tuntap: move socket to tun_file
Date: Mon, 25 Jun 2012 19:59:18 +0800	[thread overview]
Message-ID: <1340625563-9300-2-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <20120625060830.6765.27584.stgit@amd-6168-8-1.englab.nay.redhat.com>

This patch moves socket structure from tun_device and to tun_file in order to
let it possbile for multiple sockets to be attached to tun/tap device. The
reference between tap device and socket was setup during TUNSETIFF as
usual.

After this patch, we can go further towards multiqueue tun/tap support by
storing an array of pointers of tun_file in tun_device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/tun.c |  352 +++++++++++++++++++++++++++--------------------------
 1 files changed, 181 insertions(+), 171 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 987aeef..1f27789 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -108,9 +108,16 @@ struct tap_filter {
 };
 
 struct tun_file {
+	struct sock sk;
+	struct socket socket;
+	struct socket_wq wq;
+	int vnet_hdr_sz;
+	struct tap_filter txflt;
 	atomic_t count;
 	struct tun_struct *tun;
 	struct net *net;
+	struct fasync_struct *fasync;
+	unsigned int flags;
 };
 
 struct tun_sock;
@@ -125,29 +132,12 @@ struct tun_struct {
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
 			  NETIF_F_TSO6|NETIF_F_UFO)
-	struct fasync_struct	*fasync;
-
-	struct tap_filter       txflt;
-	struct socket		socket;
-	struct socket_wq	wq;
-
-	int			vnet_hdr_sz;
 
 #ifdef TUN_DEBUG
 	int debug;
 #endif
 };
 
-struct tun_sock {
-	struct sock		sk;
-	struct tun_struct	*tun;
-};
-
-static inline struct tun_sock *tun_sk(struct sock *sk)
-{
-	return container_of(sk, struct tun_sock, sk);
-}
-
 static int tun_attach(struct tun_struct *tun, struct file *file)
 {
 	struct tun_file *tfile = file->private_data;
@@ -168,10 +158,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
 	err = 0;
 	tfile->tun = tun;
 	tun->tfile = tfile;
-	tun->socket.file = file;
 	netif_carrier_on(tun->dev);
 	dev_hold(tun->dev);
-	sock_hold(tun->socket.sk);
+	sock_hold(&tfile->sk);
 	atomic_inc(&tfile->count);
 
 out:
@@ -181,15 +170,15 @@ out:
 
 static void __tun_detach(struct tun_struct *tun)
 {
+	struct tun_file *tfile = tun->tfile;
 	/* Detach from net device */
 	netif_tx_lock_bh(tun->dev);
 	netif_carrier_off(tun->dev);
 	tun->tfile = NULL;
-	tun->socket.file = NULL;
 	netif_tx_unlock_bh(tun->dev);
 
 	/* Drop read queue */
-	skb_queue_purge(&tun->socket.sk->sk_receive_queue);
+	skb_queue_purge(&tfile->socket.sk->sk_receive_queue);
 
 	/* Drop the extra count on the net device */
 	dev_put(tun->dev);
@@ -348,19 +337,12 @@ static void tun_net_uninit(struct net_device *dev)
 	/* Inform the methods they need to stop using the dev.
 	 */
 	if (tfile) {
-		wake_up_all(&tun->wq.wait);
+		wake_up_all(&tfile->wq.wait);
 		if (atomic_dec_and_test(&tfile->count))
 			__tun_detach(tun);
 	}
 }
 
-static void tun_free_netdev(struct net_device *dev)
-{
-	struct tun_struct *tun = netdev_priv(dev);
-
-	sk_release_kernel(tun->socket.sk);
-}
-
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
@@ -379,24 +361,26 @@ static int tun_net_close(struct net_device *dev)
 static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
+	struct tun_file *tfile = tun->tfile;
 
 	tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
 
 	/* Drop packet if interface is not attached */
-	if (!tun->tfile)
+	if (!tfile)
 		goto drop;
 
 	/* Drop if the filter does not like it.
 	 * This is a noop if the filter is disabled.
 	 * Filter can be enabled only for the TAP devices. */
-	if (!check_filter(&tun->txflt, skb))
+	if (!check_filter(&tfile->txflt, skb))
 		goto drop;
 
-	if (tun->socket.sk->sk_filter &&
-	    sk_filter(tun->socket.sk, skb))
+	if (tfile->socket.sk->sk_filter &&
+	    sk_filter(tfile->socket.sk, skb))
 		goto drop;
 
-	if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
+	if (skb_queue_len(&tfile->socket.sk->sk_receive_queue)
+	    >= dev->tx_queue_len) {
 		if (!(tun->flags & TUN_ONE_QUEUE)) {
 			/* Normal queueing mode. */
 			/* Packet scheduler handles dropping of further packets. */
@@ -417,12 +401,12 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_orphan(skb);
 
 	/* Enqueue packet */
-	skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
+	skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
 
 	/* Notify and wake up reader process */
-	if (tun->flags & TUN_FASYNC)
-		kill_fasync(&tun->fasync, SIGIO, POLL_IN);
-	wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
+	if (tfile->flags & TUN_FASYNC)
+		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
+	wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
 				   POLLRDNORM | POLLRDBAND);
 	return NETDEV_TX_OK;
 
@@ -550,11 +534,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
 	if (!tun)
 		return POLLERR;
 
-	sk = tun->socket.sk;
+	sk = tfile->socket.sk;
 
 	tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
 
-	poll_wait(file, &tun->wq.wait, wait);
+	poll_wait(file, &tfile->wq.wait, wait);
 
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
@@ -573,11 +557,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
 
 /* prepad is the amount to reserve at front.  len is length after that.
  * linear is a hint as to how much to copy (usually headers). */
-static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
+static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 				     size_t prepad, size_t len,
 				     size_t linear, int noblock)
 {
-	struct sock *sk = tun->socket.sk;
+	struct sock *sk = tfile->socket.sk;
 	struct sk_buff *skb;
 	int err;
 
@@ -601,7 +585,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
 }
 
 /* Get packet from user space buffer */
-static ssize_t tun_get_user(struct tun_struct *tun,
+static ssize_t tun_get_user(struct tun_file *tfile,
 			    const struct iovec *iv, size_t count,
 			    int noblock)
 {
@@ -610,8 +594,10 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 	size_t len = count, align = NET_SKB_PAD;
 	struct virtio_net_hdr gso = { 0 };
 	int offset = 0;
+	struct tun_struct *tun = NULL;
+	bool drop = false, error = false;
 
-	if (!(tun->flags & TUN_NO_PI)) {
+	if (!(tfile->flags & TUN_NO_PI)) {
 		if ((len -= sizeof(pi)) > count)
 			return -EINVAL;
 
@@ -620,8 +606,9 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 		offset += sizeof(pi);
 	}
 
-	if (tun->flags & TUN_VNET_HDR) {
-		if ((len -= tun->vnet_hdr_sz) > count)
+	if (tfile->flags & TUN_VNET_HDR) {
+		len -= tfile->vnet_hdr_sz;
+		if (len > count)
 			return -EINVAL;
 
 		if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
@@ -633,41 +620,43 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 
 		if (gso.hdr_len > len)
 			return -EINVAL;
-		offset += tun->vnet_hdr_sz;
+		offset += tfile->vnet_hdr_sz;
 	}
 
-	if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
+	if ((tfile->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
 		align += NET_IP_ALIGN;
 		if (unlikely(len < ETH_HLEN ||
 			     (gso.hdr_len && gso.hdr_len < ETH_HLEN)))
 			return -EINVAL;
 	}
 
-	skb = tun_alloc_skb(tun, align, len, gso.hdr_len, noblock);
+	skb = tun_alloc_skb(tfile, align, len, gso.hdr_len, noblock);
+
 	if (IS_ERR(skb)) {
 		if (PTR_ERR(skb) != -EAGAIN)
-			tun->dev->stats.rx_dropped++;
-		return PTR_ERR(skb);
+			drop = true;
+		count = PTR_ERR(skb);
+		goto err;
 	}
 
 	if (skb_copy_datagram_from_iovec(skb, 0, iv, offset, len)) {
-		tun->dev->stats.rx_dropped++;
+		drop = true;
 		kfree_skb(skb);
-		return -EFAULT;
+		count = -EFAULT;
+		goto err;
 	}
 
 	if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
 		if (!skb_partial_csum_set(skb, gso.csum_start,
 					  gso.csum_offset)) {
-			tun->dev->stats.rx_frame_errors++;
-			kfree_skb(skb);
-			return -EINVAL;
+			error = true;
+			goto err_free;
 		}
 	}
 
-	switch (tun->flags & TUN_TYPE_MASK) {
+	switch (tfile->flags & TUN_TYPE_MASK) {
 	case TUN_TUN_DEV:
-		if (tun->flags & TUN_NO_PI) {
+		if (tfile->flags & TUN_NO_PI) {
 			switch (skb->data[0] & 0xf0) {
 			case 0x40:
 				pi.proto = htons(ETH_P_IP);
@@ -676,18 +665,15 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
-				tun->dev->stats.rx_dropped++;
-				kfree_skb(skb);
-				return -EINVAL;
+				drop = true;
+				goto err_free;
 			}
 		}
 
 		skb_reset_mac_header(skb);
 		skb->protocol = pi.proto;
-		skb->dev = tun->dev;
 		break;
 	case TUN_TAP_DEV:
-		skb->protocol = eth_type_trans(skb, tun->dev);
 		break;
 	}
 
@@ -704,9 +690,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 			break;
 		default:
-			tun->dev->stats.rx_frame_errors++;
-			kfree_skb(skb);
-			return -EINVAL;
+			error = true;
+			goto err_free;
 		}
 
 		if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
@@ -714,9 +699,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 
 		skb_shinfo(skb)->gso_size = gso.gso_size;
 		if (skb_shinfo(skb)->gso_size == 0) {
-			tun->dev->stats.rx_frame_errors++;
-			kfree_skb(skb);
-			return -EINVAL;
+			error = true;
+			goto err_free;
 		}
 
 		/* Header must be checked, and gso_segs computed. */
@@ -724,11 +708,38 @@ static ssize_t tun_get_user(struct tun_struct *tun,
 		skb_shinfo(skb)->gso_segs = 0;
 	}
 
-	netif_rx_ni(skb);
+	tun = __tun_get(tfile);
+	if (!tun)
+		return -EBADFD;
 
+	switch (tfile->flags & TUN_TYPE_MASK) {
+	case TUN_TUN_DEV:
+		skb->dev = tun->dev;
+		break;
+	case TUN_TAP_DEV:
+		skb->protocol = eth_type_trans(skb, tun->dev);
+		break;
+	}
+
+	netif_rx_ni(skb);
 	tun->dev->stats.rx_packets++;
 	tun->dev->stats.rx_bytes += len;
+	tun_put(tun);
+	return count;
+
+err_free:
+	count = -EINVAL;
+	kfree_skb(skb);
+err:
+	tun = __tun_get(tfile);
+	if (!tun)
+		return -EBADFD;
 
+	if (drop)
+		tun->dev->stats.rx_dropped++;
+	if (error)
+		tun->dev->stats.rx_frame_errors++;
+	tun_put(tun);
 	return count;
 }
 
@@ -736,30 +747,25 @@ static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
 			      unsigned long count, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
-	struct tun_struct *tun = tun_get(file);
+	struct tun_file *tfile = file->private_data;
 	ssize_t result;
 
-	if (!tun)
-		return -EBADFD;
-
-	tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count);
-
-	result = tun_get_user(tun, iv, iov_length(iv, count),
+	result = tun_get_user(tfile, iv, iov_length(iv, count),
 			      file->f_flags & O_NONBLOCK);
 
-	tun_put(tun);
 	return result;
 }
 
 /* Put packet to the user space buffer */
-static ssize_t tun_put_user(struct tun_struct *tun,
+static ssize_t tun_put_user(struct tun_file *tfile,
 			    struct sk_buff *skb,
 			    const struct iovec *iv, int len)
 {
+	struct tun_struct *tun = NULL;
 	struct tun_pi pi = { 0, skb->protocol };
 	ssize_t total = 0;
 
-	if (!(tun->flags & TUN_NO_PI)) {
+	if (!(tfile->flags & TUN_NO_PI)) {
 		if ((len -= sizeof(pi)) < 0)
 			return -EINVAL;
 
@@ -773,9 +779,10 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		total += sizeof(pi);
 	}
 
-	if (tun->flags & TUN_VNET_HDR) {
+	if (tfile->flags & TUN_VNET_HDR) {
 		struct virtio_net_hdr gso = { 0 }; /* no info leak */
-		if ((len -= tun->vnet_hdr_sz) < 0)
+		len -= tfile->vnet_hdr_sz;
+		if (len < 0)
 			return -EINVAL;
 
 		if (skb_is_gso(skb)) {
@@ -818,7 +825,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
 					       sizeof(gso))))
 			return -EFAULT;
-		total += tun->vnet_hdr_sz;
+		total += tfile->vnet_hdr_sz;
 	}
 
 	len = min_t(int, skb->len, len);
@@ -826,29 +833,33 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
 	total += skb->len;
 
-	tun->dev->stats.tx_packets++;
-	tun->dev->stats.tx_bytes += len;
+	tun = __tun_get(tfile);
+	if (tun) {
+		tun->dev->stats.tx_packets++;
+		tun->dev->stats.tx_bytes += len;
+		tun_put(tun);
+	}
 
 	return total;
 }
 
-static ssize_t tun_do_read(struct tun_struct *tun,
+static ssize_t tun_do_read(struct tun_file *tfile,
 			   struct kiocb *iocb, const struct iovec *iv,
 			   ssize_t len, int noblock)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sk_buff *skb;
 	ssize_t ret = 0;
-
-	tun_debug(KERN_INFO, tun, "tun_chr_read\n");
+	struct tun_struct *tun = NULL;
 
 	if (unlikely(!noblock))
-		add_wait_queue(&tun->wq.wait, &wait);
+		add_wait_queue(&tfile->wq.wait, &wait);
 	while (len) {
 		current->state = TASK_INTERRUPTIBLE;
 
+		skb = skb_dequeue(&tfile->socket.sk->sk_receive_queue);
 		/* Read frames from the queue */
-		if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
+		if (!skb) {
 			if (noblock) {
 				ret = -EAGAIN;
 				break;
@@ -857,25 +868,38 @@ static ssize_t tun_do_read(struct tun_struct *tun,
 				ret = -ERESTARTSYS;
 				break;
 			}
+
+			tun = __tun_get(tfile);
+			if (!tun) {
+				ret = -EIO;
+				break;
+			}
 			if (tun->dev->reg_state != NETREG_REGISTERED) {
 				ret = -EIO;
+				tun_put(tun);
 				break;
 			}
+			tun_put(tun);
 
 			/* Nothing to read, let's sleep */
 			schedule();
 			continue;
 		}
-		netif_wake_queue(tun->dev);
 
-		ret = tun_put_user(tun, skb, iv, len);
+		tun = __tun_get(tfile);
+		if (tun) {
+			netif_wake_queue(tun->dev);
+			tun_put(tun);
+		}
+
+		ret = tun_put_user(tfile, skb, iv, len);
 		kfree_skb(skb);
 		break;
 	}
 
 	current->state = TASK_RUNNING;
 	if (unlikely(!noblock))
-		remove_wait_queue(&tun->wq.wait, &wait);
+		remove_wait_queue(&tfile->wq.wait, &wait);
 
 	return ret;
 }
@@ -885,21 +909,17 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
 {
 	struct file *file = iocb->ki_filp;
 	struct tun_file *tfile = file->private_data;
-	struct tun_struct *tun = __tun_get(tfile);
 	ssize_t len, ret;
 
-	if (!tun)
-		return -EBADFD;
 	len = iov_length(iv, count);
 	if (len < 0) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+	ret = tun_do_read(tfile, iocb, iv, len, file->f_flags & O_NONBLOCK);
 	ret = min_t(ssize_t, ret, len);
 out:
-	tun_put(tun);
 	return ret;
 }
 
@@ -911,7 +931,7 @@ static void tun_setup(struct net_device *dev)
 	tun->group = -1;
 
 	dev->ethtool_ops = &tun_ethtool_ops;
-	dev->destructor = tun_free_netdev;
+	dev->destructor = free_netdev;
 }
 
 /* Trivial set of netlink ops to allow deleting tun or tap
@@ -931,7 +951,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = {
 
 static void tun_sock_write_space(struct sock *sk)
 {
-	struct tun_struct *tun;
+	struct tun_file *tfile = NULL;
 	wait_queue_head_t *wqueue;
 
 	if (!sock_writeable(sk))
@@ -945,37 +965,38 @@ static void tun_sock_write_space(struct sock *sk)
 		wake_up_interruptible_sync_poll(wqueue, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 
-	tun = tun_sk(sk)->tun;
-	kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
-}
-
-static void tun_sock_destruct(struct sock *sk)
-{
-	free_netdev(tun_sk(sk)->tun->dev);
+	tfile = container_of(sk, struct tun_file, sk);
+	kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
 }
 
 static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
 		       struct msghdr *m, size_t total_len)
 {
-	struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
-	return tun_get_user(tun, m->msg_iov, total_len,
-			    m->msg_flags & MSG_DONTWAIT);
+	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+	ssize_t result;
+
+	result = tun_get_user(tfile, m->msg_iov, total_len,
+			      m->msg_flags & MSG_DONTWAIT);
+	return result;
 }
 
 static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 		       struct msghdr *m, size_t total_len,
 		       int flags)
 {
-	struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	int ret;
+
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
 		return -EINVAL;
-	ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+
+	ret = tun_do_read(tfile, iocb, m->msg_iov, total_len,
 			  flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
 	}
+
 	return ret;
 }
 
@@ -996,7 +1017,7 @@ static const struct proto_ops tun_socket_ops = {
 static struct proto tun_proto = {
 	.name		= "tun",
 	.owner		= THIS_MODULE,
-	.obj_size	= sizeof(struct tun_sock),
+	.obj_size	= sizeof(struct tun_file),
 };
 
 static int tun_flags(struct tun_struct *tun)
@@ -1047,8 +1068,8 @@ static DEVICE_ATTR(group, 0444, tun_show_group, NULL);
 
 static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 {
-	struct sock *sk;
 	struct tun_struct *tun;
+	struct tun_file *tfile = file->private_data;
 	struct net_device *dev;
 	int err;
 
@@ -1069,7 +1090,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		     (tun->group != -1 && !in_egroup_p(tun->group))) &&
 		    !capable(CAP_NET_ADMIN))
 			return -EPERM;
-		err = security_tun_dev_attach(tun->socket.sk);
+		err = security_tun_dev_attach(tfile->socket.sk);
 		if (err < 0)
 			return err;
 
@@ -1113,25 +1134,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		tun = netdev_priv(dev);
 		tun->dev = dev;
 		tun->flags = flags;
-		tun->txflt.count = 0;
-		tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
 
-		err = -ENOMEM;
-		sk = sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL, &tun_proto);
-		if (!sk)
-			goto err_free_dev;
-
-		sk_change_net(sk, net);
-		tun->socket.wq = &tun->wq;
-		init_waitqueue_head(&tun->wq.wait);
-		tun->socket.ops = &tun_socket_ops;
-		sock_init_data(&tun->socket, sk);
-		sk->sk_write_space = tun_sock_write_space;
-		sk->sk_sndbuf = INT_MAX;
-
-		tun_sk(sk)->tun = tun;
-
-		security_tun_dev_post_create(sk);
+		security_tun_dev_post_create(&tfile->sk);
 
 		tun_net_init(dev);
 
@@ -1141,15 +1145,13 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		err = register_netdevice(tun->dev);
 		if (err < 0)
-			goto err_free_sk;
+			goto err_free_dev;
 
 		if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
 		    device_create_file(&tun->dev->dev, &dev_attr_owner) ||
 		    device_create_file(&tun->dev->dev, &dev_attr_group))
 			pr_err("Failed to create tun sysfs files\n");
 
-		sk->sk_destruct = tun_sock_destruct;
-
 		err = tun_attach(tun, file);
 		if (err < 0)
 			goto failed;
@@ -1172,6 +1174,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	else
 		tun->flags &= ~TUN_VNET_HDR;
 
+	/* Cache flags from tun device */
+	tfile->flags = tun->flags;
 	/* Make sure persistent devices do not get stuck in
 	 * xoff state.
 	 */
@@ -1181,11 +1185,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	strcpy(ifr->ifr_name, tun->dev->name);
 	return 0;
 
- err_free_sk:
-	tun_free_netdev(dev);
- err_free_dev:
+err_free_dev:
 	free_netdev(dev);
- failed:
+failed:
 	return err;
 }
 
@@ -1357,9 +1359,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETTXFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
-		if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+		if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
 			break;
-		ret = update_filter(&tun->txflt, (void __user *)arg);
+		ret = update_filter(&tfile->txflt, (void __user *)arg);
 		break;
 
 	case SIOCGIFHWADDR:
@@ -1379,7 +1381,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		break;
 
 	case TUNGETSNDBUF:
-		sndbuf = tun->socket.sk->sk_sndbuf;
+		sndbuf = tfile->socket.sk->sk_sndbuf;
 		if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
 			ret = -EFAULT;
 		break;
@@ -1390,11 +1392,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			break;
 		}
 
-		tun->socket.sk->sk_sndbuf = sndbuf;
+		tfile->socket.sk->sk_sndbuf = sndbuf;
 		break;
 
 	case TUNGETVNETHDRSZ:
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = tfile->vnet_hdr_sz;
 		if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
 			ret = -EFAULT;
 		break;
@@ -1409,27 +1411,27 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			break;
 		}
 
-		tun->vnet_hdr_sz = vnet_hdr_sz;
+		tfile->vnet_hdr_sz = vnet_hdr_sz;
 		break;
 
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
-		if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+		if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
 			break;
 		ret = -EFAULT;
 		if (copy_from_user(&fprog, argp, sizeof(fprog)))
 			break;
 
-		ret = sk_attach_filter(&fprog, tun->socket.sk);
+		ret = sk_attach_filter(&fprog, tfile->socket.sk);
 		break;
 
 	case TUNDETACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
-		if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+		if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
 			break;
-		ret = sk_detach_filter(tun->socket.sk);
+		ret = sk_detach_filter(tfile->socket.sk);
 		break;
 
 	default:
@@ -1481,43 +1483,50 @@ static long tun_chr_compat_ioctl(struct file *file,
 
 static int tun_chr_fasync(int fd, struct file *file, int on)
 {
-	struct tun_struct *tun = tun_get(file);
-	int ret;
-
-	if (!tun)
-		return -EBADFD;
-
-	tun_debug(KERN_INFO, tun, "tun_chr_fasync %d\n", on);
+	struct tun_file *tfile = file->private_data;
+	int ret = fasync_helper(fd, file, on, &tfile->fasync);
 
-	if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
+	if (ret < 0)
 		goto out;
 
 	if (on) {
 		ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
 		if (ret)
 			goto out;
-		tun->flags |= TUN_FASYNC;
+		tfile->flags |= TUN_FASYNC;
 	} else
-		tun->flags &= ~TUN_FASYNC;
+		tfile->flags &= ~TUN_FASYNC;
 	ret = 0;
 out:
-	tun_put(tun);
 	return ret;
 }
 
 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 = kmalloc(sizeof(*tfile), GFP_KERNEL);
+	tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+					&tun_proto);
 	if (!tfile)
 		return -ENOMEM;
-	atomic_set(&tfile->count, 0);
+
 	tfile->tun = NULL;
-	tfile->net = get_net(current->nsproxy->net_ns);
+	tfile->net = net;
+	tfile->txflt.count = 0;
+	tfile->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
+	tfile->socket.wq = &tfile->wq;
+	init_waitqueue_head(&tfile->wq.wait);
+	tfile->socket.file = file;
+	tfile->socket.ops = &tun_socket_ops;
+	sock_init_data(&tfile->socket, &tfile->sk);
+
+	tfile->sk.sk_write_space = tun_sock_write_space;
+	tfile->sk.sk_sndbuf = INT_MAX;
 	file->private_data = tfile;
+
 	return 0;
 }
 
@@ -1541,14 +1550,14 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 				unregister_netdevice(dev);
 			rtnl_unlock();
 		}
-	}
 
-	tun = tfile->tun;
-	if (tun)
-		sock_put(tun->socket.sk);
+		/* drop the reference that netdevice holds */
+		sock_put(&tfile->sk);
 
-	put_net(tfile->net);
-	kfree(tfile);
+	}
+
+	/* drop the reference that file holds */
+	sock_put(&tfile->sk);
 
 	return 0;
 }
@@ -1676,13 +1685,14 @@ static void tun_cleanup(void)
 struct socket *tun_get_socket(struct file *file)
 {
 	struct tun_struct *tun;
+	struct tun_file *tfile = file->private_data;
 	if (file->f_op != &tun_fops)
 		return ERR_PTR(-EINVAL);
 	tun = tun_get(file);
 	if (!tun)
 		return ERR_PTR(-EBADFD);
 	tun_put(tun);
-	return &tun->socket;
+	return &tfile->socket;
 }
 EXPORT_SYMBOL_GPL(tun_get_socket);
 
-- 
1.7.1

