1 files changed, 130 insertions, 39 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index bfabe180053e..3d4c24572ecd 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>
@@ -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;
 };
 
@@ -463,7 +465,7 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
 	rcu_read_lock();
 	numqueues = ACCESS_ONCE(tun->numqueues);
 
-	txq = skb_get_hash(skb);
+	txq = __skb_get_hash_symmetric(skb);
 	if (txq) {
 		e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
 		if (e) {
@@ -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;
 }
 
@@ -853,7 +867,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		 */
 		__u32 rxhash;
 
-		rxhash = skb_get_hash(skb);
+		rxhash = __skb_get_hash_symmetric(skb);
 		if (rxhash) {
 			struct tun_flow_entry *e;
 			e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)],
@@ -953,7 +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;
@@ -987,7 +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 = {
@@ -1101,9 +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)
@@ -1140,10 +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;
@@ -1284,11 +1334,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb, 0);
 
-	rxhash = skb_get_hash(skb);
+	rxhash = __skb_get_hash_symmetric(skb);
 #ifndef CONFIG_4KSTACKS
-	local_bh_disable();
-	netif_receive_skb(skb);
-	local_bh_enable();
+	tun_rx_batched(tun, tfile, skb, more);
 #else
 	netif_rx_ni(skb);
 #endif
@@ -1314,7 +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;
@@ -1461,9 +1510,8 @@ out:
 
 static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 			   struct iov_iter *to,
-			   int noblock)
+			   int noblock, struct sk_buff *skb)
 {
-	struct sk_buff *skb;
 	ssize_t ret;
 	int err;
 
@@ -1472,10 +1520,12 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	/* Read frames from ring */
-	skb = tun_ring_recv(tfile, noblock, &err);
-	if (!skb)
-		return err;
+	if (!skb) {
+		/* Read frames from ring */
+		skb = tun_ring_recv(tfile, noblock, &err);
+		if (!skb)
+			return err;
+	}
 
 	ret = tun_put_user(tun, tfile, skb, to);
 	if (unlikely(ret < 0))
@@ -1495,7 +1545,7 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	if (!tun)
 		return -EBADFD;
-	ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK);
+	ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL);
 	ret = min_t(ssize_t, ret, len);
 	if (ret > 0)
 		iocb->ki_pos = ret;
@@ -1511,7 +1561,6 @@ static void tun_free_netdev(struct net_device *dev)
 	free_percpu(tun->pcpu_stats);
 	tun_flow_uninit(tun);
 	security_tun_dev_free_security(tun->security);
-	free_netdev(dev);
 }
 
 static void tun_setup(struct net_device *dev)
@@ -1522,7 +1571,8 @@ static void tun_setup(struct net_device *dev)
 	tun->group = INVALID_GID;
 
 	dev->ethtool_ops = &tun_ethtool_ops;
-	dev->destructor = tun_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = tun_free_netdev;
 	/* We prefer our own queue length */
 	dev->tx_queue_len = TUN_READQ_SIZE;
 }
@@ -1530,7 +1580,8 @@ static void tun_setup(struct net_device *dev)
 /* Trivial set of netlink ops to allow deleting tun or tap
  * device with netlink.
  */
-static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
+static int tun_validate(struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
 {
 	return -EINVAL;
 }
@@ -1572,7 +1623,8 @@ 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;
 }
@@ -1596,7 +1648,8 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 					 SOL_PACKET, TUN_TX_TIMESTAMP);
 		goto out;
 	}
-	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT);
+	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT,
+			  m->msg_control);
 	if (ret > (ssize_t)total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
@@ -1773,6 +1826,7 @@ 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) {
@@ -1880,6 +1934,8 @@ 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;
@@ -2391,18 +2447,16 @@ static struct miscdevice tun_miscdev = {
 
 /* ethtool interface */
 
-static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	cmd->supported		= 0;
-	cmd->advertising	= 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex		= DUPLEX_FULL;
-	cmd->port		= PORT_TP;
-	cmd->phy_address	= 0;
-	cmd->transceiver	= XCVR_INTERNAL;
-	cmd->autoneg		= AUTONEG_DISABLE;
-	cmd->maxtxpkt		= 0;
-	cmd->maxrxpkt		= 0;
+static int tun_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	cmd->base.speed		= SPEED_10;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.phy_address	= 0;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -2441,13 +2495,38 @@ 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,
 	.get_msglevel	= tun_get_msglevel,
 	.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,
+	.get_link_ksettings = tun_get_link_ksettings,
 };
 
 static int tun_queue_resize(struct tun_struct *tun)
@@ -2506,7 +2585,6 @@ 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) {
@@ -2551,6 +2629,19 @@ struct socket *tun_get_socket(struct file *file)
 }
 EXPORT_SYMBOL_GPL(tun_get_socket);
 
+struct skb_array *tun_get_skb_array(struct file *file)
+{
+	struct tun_file *tfile;
+
+	if (file->f_op != &tun_fops)
+		return ERR_PTR(-EINVAL);
+	tfile = file->private_data;
+	if (!tfile)
+		return ERR_PTR(-EBADFD);
+	return &tfile->tx_array;
+}
+EXPORT_SYMBOL_GPL(tun_get_skb_array);
+
 module_init(tun_init);
 module_exit(tun_cleanup);
 MODULE_DESCRIPTION(DRV_DESCRIPTION);