#include <linux/slab.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
+#include <linux/u64_stats_sync.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <linux/veth.h>
+#include <linux/module.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) */
-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 pcpu_vstats {
+ u64 packets;
+ u64 bytes;
+ struct u64_stats_sync syncp;
};
struct veth_priv {
- struct net_device *peer;
- struct veth_net_stats __percpu *stats;
+ struct net_device __rcu *peer;
+ atomic64_t dropped;
};
/*
static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
static void veth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
- struct veth_priv *priv;
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer = rtnl_dereference(priv->peer);
- priv = netdev_priv(dev);
- data[0] = priv->peer->ifindex;
+ data[0] = peer ? peer->ifindex : 0;
}
static const struct ethtool_ops veth_ethtool_ops = {
.get_ethtool_stats = veth_get_ethtool_stats,
};
-/*
- * xmit
- */
-
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, *rcv_stats;
- int length;
-
- priv = netdev_priv(dev);
- rcv = priv->peer;
- rcv_priv = netdev_priv(rcv);
-
- stats = this_cpu_ptr(priv->stats);
- rcv_stats = this_cpu_ptr(rcv_priv->stats);
-
- if (!(rcv->flags & IFF_UP))
- goto tx_drop;
-
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *rcv;
+ int length = skb->len;
+
+ rcu_read_lock();
+ rcv = rcu_dereference(priv->peer);
+ if (unlikely(!rcv)) {
+ kfree_skb(skb);
+ goto drop;
+ }
/* don't change ip_summed == CHECKSUM_PARTIAL, as that
- will cause bad checksum on forwarded packets */
+ * will cause bad checksum on forwarded packets
+ */
if (skb->ip_summed == CHECKSUM_NONE &&
rcv->features & NETIF_F_RXCSUM)
skb->ip_summed = CHECKSUM_UNNECESSARY;
- length = skb->len;
- if (dev_forward_skb(rcv, skb) != NET_RX_SUCCESS)
- goto rx_drop;
-
- stats->tx_bytes += length;
- stats->tx_packets++;
-
- rcv_stats->rx_bytes += length;
- rcv_stats->rx_packets++;
-
- return NETDEV_TX_OK;
-
-tx_drop:
- kfree_skb(skb);
- stats->tx_dropped++;
- return NETDEV_TX_OK;
+ if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
+ struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
-rx_drop:
- rcv_stats->rx_dropped++;
+ u64_stats_update_begin(&stats->syncp);
+ stats->bytes += length;
+ stats->packets++;
+ u64_stats_update_end(&stats->syncp);
+ } else {
+drop:
+ atomic64_inc(&priv->dropped);
+ }
+ rcu_read_unlock();
return NETDEV_TX_OK;
}
* general routines
*/
-static struct net_device_stats *veth_get_stats(struct net_device *dev)
+static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
{
- struct veth_priv *priv;
+ struct veth_priv *priv = netdev_priv(dev);
int cpu;
- struct veth_net_stats *stats, total = {0};
-
- priv = netdev_priv(dev);
+ result->packets = 0;
+ result->bytes = 0;
for_each_possible_cpu(cpu) {
- stats = per_cpu_ptr(priv->stats, cpu);
-
- 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;
+ struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu);
+ u64 packets, bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&stats->syncp);
+ packets = stats->packets;
+ bytes = stats->bytes;
+ } while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+ result->packets += packets;
+ result->bytes += bytes;
}
- 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;
+ return atomic64_read(&priv->dropped);
+}
+
+static struct rtnl_link_stats64 *veth_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer;
+ struct pcpu_vstats one;
+
+ tot->tx_dropped = veth_stats_one(&one, dev);
+ tot->tx_bytes = one.bytes;
+ tot->tx_packets = one.packets;
+
+ rcu_read_lock();
+ peer = rcu_dereference(priv->peer);
+ if (peer) {
+ tot->rx_dropped = veth_stats_one(&one, peer);
+ tot->rx_bytes = one.bytes;
+ tot->rx_packets = one.packets;
+ }
+ rcu_read_unlock();
+
+ return tot;
}
static int veth_open(struct net_device *dev)
{
- struct veth_priv *priv;
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer = rtnl_dereference(priv->peer);
- priv = netdev_priv(dev);
- if (priv->peer == NULL)
+ if (!peer)
return -ENOTCONN;
- if (priv->peer->flags & IFF_UP) {
+ if (peer->flags & IFF_UP) {
netif_carrier_on(dev);
- netif_carrier_on(priv->peer);
+ netif_carrier_on(peer);
}
return 0;
}
static int veth_close(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer = rtnl_dereference(priv->peer);
netif_carrier_off(dev);
- netif_carrier_off(priv->peer);
+ if (peer)
+ netif_carrier_off(peer);
return 0;
}
static int veth_dev_init(struct net_device *dev)
{
- struct veth_net_stats __percpu *stats;
- struct veth_priv *priv;
-
- stats = alloc_percpu(struct veth_net_stats);
- if (stats == NULL)
+ dev->vstats = alloc_percpu(struct pcpu_vstats);
+ if (!dev->vstats)
return -ENOMEM;
- priv = netdev_priv(dev);
- priv->stats = stats;
return 0;
}
static void veth_dev_free(struct net_device *dev)
{
- struct veth_priv *priv;
-
- priv = netdev_priv(dev);
- free_percpu(priv->stats);
+ free_percpu(dev->vstats);
free_netdev(dev);
}
.ndo_stop = veth_close,
.ndo_start_xmit = veth_xmit,
.ndo_change_mtu = veth_change_mtu,
- .ndo_get_stats = veth_get_stats,
+ .ndo_get_stats64 = veth_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
};
+#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_HIGHDMA | \
+ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \
+ NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX )
+
static void veth_setup(struct net_device *dev)
{
ether_setup(dev);
+ dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
dev->netdev_ops = &veth_netdev_ops;
dev->ethtool_ops = &veth_ethtool_ops;
dev->features |= NETIF_F_LLTX;
+ dev->features |= VETH_FEATURES;
dev->destructor = veth_dev_free;
- dev->hw_features = NETIF_F_NO_CSUM | NETIF_F_SG | NETIF_F_RXCSUM;
+ dev->hw_features = VETH_FEATURES;
}
/*
if (IS_ERR(net))
return PTR_ERR(net);
- peer = rtnl_create_link(src_net, net, ifname, &veth_link_ops, tbp);
+ peer = rtnl_create_link(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);
+ eth_hw_addr_random(peer);
+
+ if (ifmp && (dev->ifindex != 0))
+ peer->ifindex = ifmp->ifi_index;
err = register_netdevice(peer);
put_net(net);
*/
if (tb[IFLA_ADDRESS] == NULL)
- random_ether_addr(dev->dev_addr);
+ eth_hw_addr_random(dev);
if (tb[IFLA_IFNAME])
nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
*/
priv = netdev_priv(dev);
- priv->peer = peer;
+ rcu_assign_pointer(priv->peer, peer);
priv = netdev_priv(peer);
- priv->peer = dev;
+ rcu_assign_pointer(priv->peer, dev);
return 0;
err_register_dev:
struct net_device *peer;
priv = netdev_priv(dev);
- peer = priv->peer;
+ peer = rtnl_dereference(priv->peer);
+ /* Note : dellink() is called from default_device_exit_batch(),
+ * before a rcu_synchronize() point. The devices are guaranteed
+ * not being freed before one RCU grace period.
+ */
+ RCU_INIT_POINTER(priv->peer, NULL);
unregister_netdevice_queue(dev, head);
- unregister_netdevice_queue(peer, head);
+
+ if (peer) {
+ priv = netdev_priv(peer);
+ RCU_INIT_POINTER(priv->peer, NULL);
+ unregister_netdevice_queue(peer, head);
+ }
}
-static const struct nla_policy veth_policy[VETH_INFO_MAX + 1];
+static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
+ [VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
+};
static struct rtnl_link_ops veth_link_ops = {
.kind = DRV_NAME,
projects / firefly-linux-kernel-4.4.55.git / blobdiff