1 files changed, 117 insertions, 49 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index db6acecabeaa..cc88cd7856f5 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -44,6 +44,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/major.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
@@ -73,7 +74,7 @@
 #include <linux/uio.h>
 #include <linux/skb_array.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Uncomment to enable debugging */
 /* #define TUN_DEBUG 1 */
@@ -218,6 +219,7 @@ struct tun_struct {
 	struct list_head disabled;
 	void *security;
 	u32 flow_count;
+	u32 rx_batched;
 	struct tun_pcpu_stats __percpu *pcpu_stats;
 };
 
@@ -522,6 +524,7 @@ static void tun_queue_purge(struct tun_file *tfile)
 	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
 		kfree_skb(skb);
 
+	skb_queue_purge(&tfile->sk.sk_write_queue);
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
@@ -819,7 +822,18 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
@@ -878,13 +892,6 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	    sk_filter(tfile->socket.sk, skb))
 		goto drop;
 
-	/* Limit the number of packets queued by dividing txq length with the
-	 * number of queues.
-	 */
-	if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) * numqueues
-			  >= dev->tx_queue_len)
-		goto drop;
-
 	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
 
@@ -925,18 +932,6 @@ static void tun_net_mclist(struct net_device *dev)
 	 */
 }
 
-#define MIN_MTU 68
-#define MAX_MTU 65535
-
-static int
-tun_net_change_mtu(struct net_device *dev, int new_mtu)
-{
-	if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
-		return -EINVAL;
-	dev->mtu = new_mtu;
-	return 0;
-}
-
 static netdev_features_t tun_net_fix_features(struct net_device *dev,
 	netdev_features_t features)
 {
@@ -972,7 +967,7 @@ static void tun_set_headroom(struct net_device *dev, int new_hr)
 	tun->align = new_hr;
 }
 
-static struct rtnl_link_stats64 *
+static void
 tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	u32 rx_dropped = 0, tx_dropped = 0, rx_frame_errors = 0;
@@ -1006,7 +1001,6 @@ tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->rx_dropped  = rx_dropped;
 	stats->rx_frame_errors = rx_frame_errors;
 	stats->tx_dropped = tx_dropped;
-	return stats;
 }
 
 static const struct net_device_ops tun_netdev_ops = {
@@ -1014,7 +1008,6 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_open		= tun_net_open,
 	.ndo_stop		= tun_net_close,
 	.ndo_start_xmit		= tun_net_xmit,
-	.ndo_change_mtu		= tun_net_change_mtu,
 	.ndo_fix_features	= tun_net_fix_features,
 	.ndo_select_queue	= tun_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1029,7 +1022,6 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_open		= tun_net_open,
 	.ndo_stop		= tun_net_close,
 	.ndo_start_xmit		= tun_net_xmit,
-	.ndo_change_mtu		= tun_net_change_mtu,
 	.ndo_fix_features	= tun_net_fix_features,
 	.ndo_set_rx_mode	= tun_net_mclist,
 	.ndo_set_mac_address	= eth_mac_addr,
@@ -1062,6 +1054,9 @@ static void tun_flow_uninit(struct tun_struct *tun)
 	tun_flow_flush(tun);
 }
 
+#define MIN_MTU 68
+#define MAX_MTU 65535
+
 /* Initialize net device. */
 static void tun_net_init(struct net_device *dev)
 {
@@ -1092,6 +1087,9 @@ static void tun_net_init(struct net_device *dev)
 
 		break;
 	}
+
+	dev->min_mtu = MIN_MTU;
+	dev->max_mtu = MAX_MTU - dev->hard_header_len;
 }
 
 /* Character device part */
@@ -1116,9 +1114,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
@@ -1155,10 +1154,46 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	return skb;
 }
 
+static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
+			   struct sk_buff *skb, int more)
+{
+	struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+	struct sk_buff_head process_queue;
+	u32 rx_batched = tun->rx_batched;
+	bool rcv = false;
+
+	if (!rx_batched || (!more && skb_queue_empty(queue))) {
+		local_bh_disable();
+		netif_receive_skb(skb);
+		local_bh_enable();
+		return;
+	}
+
+	spin_lock(&queue->lock);
+	if (!more || skb_queue_len(queue) == rx_batched) {
+		__skb_queue_head_init(&process_queue);
+		skb_queue_splice_tail_init(queue, &process_queue);
+		rcv = true;
+	} else {
+		__skb_queue_tail(queue, skb);
+	}
+	spin_unlock(&queue->lock);
+
+	if (rcv) {
+		struct sk_buff *nskb;
+
+		local_bh_disable();
+		while ((nskb = __skb_dequeue(&process_queue)))
+			netif_receive_skb(nskb);
+		netif_receive_skb(skb);
+		local_bh_enable();
+	}
+}
+
 /* Get packet from user space buffer */
 static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			    void *msg_control, struct iov_iter *from,
-			    int noblock)
+			    int noblock, bool more)
 {
 	struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
 	struct sk_buff *skb;
@@ -1171,7 +1206,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	bool zerocopy = false;
 	int err;
 	u32 rxhash;
-	ssize_t n;
 
 	if (!(tun->dev->flags & IFF_UP))
 		return -EIO;
@@ -1181,18 +1215,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			return -EINVAL;
 		len -= sizeof(pi);
 
-		n = copy_from_iter(&pi, sizeof(pi), from);
-		if (n != sizeof(pi))
+		if (!copy_from_iter_full(&pi, sizeof(pi), from))
 			return -EFAULT;
 	}
 
 	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))
+		if (!copy_from_iter_full(&gso, sizeof(gso), from))
 			return -EFAULT;
 
 		if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
@@ -1201,7 +1235,7 @@ 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) {
@@ -1255,8 +1289,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		return -EFAULT;
 	}
 
-	err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun));
-	if (err) {
+	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
 		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
 		kfree_skb(skb);
 		return -EINVAL;
@@ -1302,7 +1335,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	skb_probe_transport_header(skb, 0);
 
 	rxhash = skb_get_hash(skb);
+#ifndef CONFIG_4KSTACKS
+	tun_rx_batched(tun, tfile, skb, more);
+#else
 	netif_rx_ni(skb);
+#endif
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
@@ -1325,7 +1362,8 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (!tun)
 		return -EBADFD;
 
-	result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK);
+	result = tun_get_user(tun, tfile, NULL, from,
+			      file->f_flags & O_NONBLOCK, false);
 
 	tun_put(tun);
 	return result;
@@ -1348,7 +1386,7 @@ 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;
 
@@ -1367,15 +1405,13 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	if (vnet_hdr_sz) {
-		struct virtio_net_hdr gso = { 0 }; /* no info leak */
-		int ret;
+		struct virtio_net_hdr gso;
 
 		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
-		ret = virtio_net_hdr_from_skb(skb, &gso,
-					      tun_is_little_endian(tun));
-		if (ret) {
+		if (virtio_net_hdr_from_skb(skb, &gso,
+					    tun_is_little_endian(tun), true)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
 			       "0x%x, gso_size %d, hdr_len %d\n",
@@ -1585,7 +1621,8 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -EBADFD;
 
 	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
-			   m->msg_flags & MSG_DONTWAIT);
+			   m->msg_flags & MSG_DONTWAIT,
+			   m->msg_flags & MSG_MORE);
 	tun_put(tun);
 	return ret;
 }
@@ -1786,6 +1823,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		tun->align = NET_SKB_PAD;
 		tun->filter_attached = false;
 		tun->sndbuf = tfile->socket.sk->sk_sndbuf;
+		tun->rx_batched = 0;
 
 		tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats);
 		if (!tun->pcpu_stats) {
@@ -1893,6 +1931,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 		return -EINVAL;
 
 	tun->set_features = features;
+	tun->dev->wanted_features &= ~TUN_USER_FEATURES;
+	tun->dev->wanted_features |= features;
 	netdev_update_features(tun->dev);
 
 	return 0;
@@ -1991,7 +2031,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	int le;
 	int ret;
 
-	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
+	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) {
 		if (copy_from_user(&ifr, argp, ifreq_len))
 			return -EFAULT;
 	} else {
@@ -2011,7 +2051,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	rtnl_lock();
 
 	tun = __tun_get(tfile);
-	if (cmd == TUNSETIFF && !tun) {
+	if (cmd == TUNSETIFF) {
+		ret = -EEXIST;
+		if (tun)
+			goto unlock;
+
 		ifr.ifr_name[IFNAMSIZ-1] = '\0';
 
 		ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr);
@@ -2450,6 +2494,29 @@ static void tun_set_msglevel(struct net_device *dev, u32 value)
 #endif
 }
 
+static int tun_get_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+
+	ec->rx_max_coalesced_frames = tun->rx_batched;
+
+	return 0;
+}
+
+static int tun_set_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+
+	if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT)
+		tun->rx_batched = NAPI_POLL_WEIGHT;
+	else
+		tun->rx_batched = ec->rx_max_coalesced_frames;
+
+	return 0;
+}
+
 static const struct ethtool_ops tun_ethtool_ops = {
 	.get_settings	= tun_get_settings,
 	.get_drvinfo	= tun_get_drvinfo,
@@ -2457,6 +2524,8 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.set_msglevel	= tun_set_msglevel,
 	.get_link	= ethtool_op_get_link,
 	.get_ts_info	= ethtool_op_get_ts_info,
+	.get_coalesce   = tun_get_coalesce,
+	.set_coalesce   = tun_set_coalesce,
 };
 
 static int tun_queue_resize(struct tun_struct *tun)
@@ -2515,7 +2584,6 @@ static int __init tun_init(void)
 	int ret = 0;
 
 	pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
-	pr_info("%s\n", DRV_COPYRIGHT);
 
 	ret = rtnl_link_register(&tun_link_ops);
 	if (ret) {