*/
#include <linux/netdevice.h>
+#include <linux/slab.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#define DRV_NAME "veth"
#define DRV_VERSION "1.0"
+#define MIN_MTU 68 /* Min L3 MTU */
+#define MAX_MTU 65535 /* Max L3 MTU (arbitrary) */
+#define MTU_PAD (ETH_HLEN + 4) /* Max difference between L2 and L3 size MTU */
+
struct veth_net_stats {
unsigned long rx_packets;
unsigned long tx_packets;
unsigned long rx_bytes;
unsigned long tx_bytes;
unsigned long tx_dropped;
+ unsigned long rx_dropped;
};
struct veth_priv {
struct net_device *peer;
- struct veth_net_stats *stats;
+ struct veth_net_stats __percpu *stats;
unsigned ip_summed;
};
return 0;
}
-static struct ethtool_ops veth_ethtool_ops = {
+static const struct ethtool_ops veth_ethtool_ops = {
.get_settings = veth_get_settings,
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
* xmit
*/
-static int veth_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct net_device *rcv = NULL;
struct veth_priv *priv, *rcv_priv;
- struct veth_net_stats *stats;
- int length, cpu;
-
- skb_orphan(skb);
+ struct veth_net_stats *stats, *rcv_stats;
+ int length;
priv = netdev_priv(dev);
rcv = priv->peer;
rcv_priv = netdev_priv(rcv);
- cpu = smp_processor_id();
- stats = per_cpu_ptr(priv->stats, cpu);
+ stats = this_cpu_ptr(priv->stats);
+ rcv_stats = this_cpu_ptr(rcv_priv->stats);
if (!(rcv->flags & IFF_UP))
- goto outf;
+ goto tx_drop;
- skb->pkt_type = PACKET_HOST;
- skb->protocol = eth_type_trans(skb, rcv);
if (dev->features & NETIF_F_NO_CSUM)
skb->ip_summed = rcv_priv->ip_summed;
- dst_release(skb->dst);
- skb->dst = NULL;
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
-
- length = skb->len;
+ length = skb->len + ETH_HLEN;
+ if (dev_forward_skb(rcv, skb) != NET_RX_SUCCESS)
+ goto rx_drop;
stats->tx_bytes += length;
stats->tx_packets++;
- stats = per_cpu_ptr(rcv_priv->stats, cpu);
- stats->rx_bytes += length;
- stats->rx_packets++;
+ rcv_stats->rx_bytes += length;
+ rcv_stats->rx_packets++;
- netif_rx(skb);
- return 0;
+ return NETDEV_TX_OK;
-outf:
+tx_drop:
kfree_skb(skb);
stats->tx_dropped++;
- return 0;
+ return NETDEV_TX_OK;
+
+rx_drop:
+ kfree_skb(skb);
+ rcv_stats->rx_dropped++;
+ return NETDEV_TX_OK;
}
/*
static struct net_device_stats *veth_get_stats(struct net_device *dev)
{
struct veth_priv *priv;
- struct net_device_stats *dev_stats;
int cpu;
- struct veth_net_stats *stats;
+ struct veth_net_stats *stats, total = {0};
priv = netdev_priv(dev);
- dev_stats = &dev->stats;
- dev_stats->rx_packets = 0;
- dev_stats->tx_packets = 0;
- dev_stats->rx_bytes = 0;
- dev_stats->tx_bytes = 0;
- dev_stats->tx_dropped = 0;
-
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
stats = per_cpu_ptr(priv->stats, cpu);
- dev_stats->rx_packets += stats->rx_packets;
- dev_stats->tx_packets += stats->tx_packets;
- dev_stats->rx_bytes += stats->rx_bytes;
- dev_stats->tx_bytes += stats->tx_bytes;
- dev_stats->tx_dropped += stats->tx_dropped;
+ total.rx_packets += stats->rx_packets;
+ total.tx_packets += stats->tx_packets;
+ total.rx_bytes += stats->rx_bytes;
+ total.tx_bytes += stats->tx_bytes;
+ total.tx_dropped += stats->tx_dropped;
+ total.rx_dropped += stats->rx_dropped;
}
-
- return dev_stats;
+ dev->stats.rx_packets = total.rx_packets;
+ dev->stats.tx_packets = total.tx_packets;
+ dev->stats.rx_bytes = total.rx_bytes;
+ dev->stats.tx_bytes = total.tx_bytes;
+ dev->stats.tx_dropped = total.tx_dropped;
+ dev->stats.rx_dropped = total.rx_dropped;
+
+ return &dev->stats;
}
static int veth_open(struct net_device *dev)
return 0;
}
+static int veth_close(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+
+ netif_carrier_off(dev);
+ netif_carrier_off(priv->peer);
+
+ return 0;
+}
+
+static int is_valid_veth_mtu(int new_mtu)
+{
+ return (new_mtu >= MIN_MTU && new_mtu <= MAX_MTU);
+}
+
+static int veth_change_mtu(struct net_device *dev, int new_mtu)
+{
+ if (!is_valid_veth_mtu(new_mtu))
+ return -EINVAL;
+ dev->mtu = new_mtu;
+ return 0;
+}
+
static int veth_dev_init(struct net_device *dev)
{
- struct veth_net_stats *stats;
+ struct veth_net_stats __percpu *stats;
struct veth_priv *priv;
stats = alloc_percpu(struct veth_net_stats);
}
static const struct net_device_ops veth_netdev_ops = {
- .ndo_init = veth_dev_init,
- .ndo_open = veth_open,
- .ndo_start_xmit = veth_xmit,
- .ndo_get_stats = veth_get_stats,
+ .ndo_init = veth_dev_init,
+ .ndo_open = veth_open,
+ .ndo_stop = veth_close,
+ .ndo_start_xmit = veth_xmit,
+ .ndo_change_mtu = veth_change_mtu,
+ .ndo_get_stats = veth_get_stats,
+ .ndo_set_mac_address = eth_mac_addr,
};
static void veth_setup(struct net_device *dev)
dev->destructor = veth_dev_free;
}
-static void veth_change_state(struct net_device *dev)
-{
- struct net_device *peer;
- struct veth_priv *priv;
-
- priv = netdev_priv(dev);
- peer = priv->peer;
-
- if (netif_carrier_ok(peer)) {
- if (!netif_carrier_ok(dev))
- netif_carrier_on(dev);
- } else {
- if (netif_carrier_ok(dev))
- netif_carrier_off(dev);
- }
-}
-
-static int veth_device_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
-{
- struct net_device *dev = ptr;
-
- if (dev->netdev_ops->ndo_open != veth_open)
- goto out;
-
- switch (event) {
- case NETDEV_CHANGE:
- veth_change_state(dev);
- break;
- }
-out:
- return NOTIFY_DONE;
-}
-
-static struct notifier_block veth_notifier_block __read_mostly = {
- .notifier_call = veth_device_event,
-};
-
/*
* netlink interface
*/
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
+ if (tb[IFLA_MTU]) {
+ if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU])))
+ return -EINVAL;
+ }
return 0;
}
static struct rtnl_link_ops veth_link_ops;
-static int veth_newlink(struct net_device *dev,
+static int veth_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
int err;
struct veth_priv *priv;
char ifname[IFNAMSIZ];
struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
+ struct ifinfomsg *ifmp;
+ struct net *net;
/*
* create and register peer first
- *
- * struct ifinfomsg is at the head of VETH_INFO_PEER, but we
- * skip it since no info from it is useful yet
*/
-
if (data != NULL && data[VETH_INFO_PEER] != NULL) {
struct nlattr *nla_peer;
nla_peer = data[VETH_INFO_PEER];
+ ifmp = nla_data(nla_peer);
err = nla_parse(peer_tb, IFLA_MAX,
nla_data(nla_peer) + sizeof(struct ifinfomsg),
nla_len(nla_peer) - sizeof(struct ifinfomsg),
return err;
tbp = peer_tb;
- } else
+ } else {
+ ifmp = NULL;
tbp = tb;
+ }
if (tbp[IFLA_IFNAME])
nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
- peer = rtnl_create_link(dev_net(dev), ifname, &veth_link_ops, tbp);
- if (IS_ERR(peer))
+ net = rtnl_link_get_net(src_net, tbp);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ peer = rtnl_create_link(src_net, net, ifname, &veth_link_ops, tbp);
+ if (IS_ERR(peer)) {
+ put_net(net);
return PTR_ERR(peer);
+ }
if (tbp[IFLA_ADDRESS] == NULL)
random_ether_addr(peer->dev_addr);
err = register_netdevice(peer);
+ put_net(net);
+ net = NULL;
if (err < 0)
goto err_register_peer;
netif_carrier_off(peer);
+ err = rtnl_configure_link(peer, ifmp);
+ if (err < 0)
+ goto err_configure_peer;
+
/*
* register dev last
*
err_register_dev:
/* nothing to do */
err_alloc_name:
+err_configure_peer:
unregister_netdevice(peer);
return err;
return err;
}
-static void veth_dellink(struct net_device *dev)
+static void veth_dellink(struct net_device *dev, struct list_head *head)
{
struct veth_priv *priv;
struct net_device *peer;
priv = netdev_priv(dev);
peer = priv->peer;
- unregister_netdevice(dev);
- unregister_netdevice(peer);
+ unregister_netdevice_queue(dev, head);
+ unregister_netdevice_queue(peer, head);
}
static const struct nla_policy veth_policy[VETH_INFO_MAX + 1];
static __init int veth_init(void)
{
- register_netdevice_notifier(&veth_notifier_block);
return rtnl_link_register(&veth_link_ops);
}
static __exit void veth_exit(void)
{
rtnl_link_unregister(&veth_link_ops);
- unregister_netdevice_notifier(&veth_notifier_block);
}
module_init(veth_init);