linux/drivers/net/veth.c
Flavio Leitner b69bbddfa1 veth: add vlan features
The veth device doesn't provide the vlan features,
so TSO for example is disabled and that causes
performance issues when using tagged traffic.

The test topology looks like this:

    br0                     br1
  /   \                  /     \
vnet  veth0.10 ----- veth1.10   vnet
VM                               VM

The netperf results with current veth driver:
MIGRATED TCP STREAM TEST from 192.168.1.1 ()
port 0 AF_INET to 192.168.1.2 () port 0 AF_INET
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.01    2210.22

Now after applying the proposed patch:
MIGRATED TCP STREAM TEST from 192.168.1.1 ()
port 0 AF_INET to 192.168.1.2 () port 0 AF_INET
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    13067.47

Signed-off-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-19 17:36:03 -07:00

468 lines
10 KiB
C

/*
* drivers/net/veth.c
*
* Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
*
* Author: Pavel Emelianov <xemul@openvz.org>
* Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com>
*
*/
#include <linux/netdevice.h>
#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 pcpu_vstats {
u64 packets;
u64 bytes;
struct u64_stats_sync syncp;
};
struct veth_priv {
struct net_device __rcu *peer;
atomic64_t dropped;
};
/*
* ethtool interface
*/
static struct {
const char string[ETH_GSTRING_LEN];
} ethtool_stats_keys[] = {
{ "peer_ifindex" },
};
static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
cmd->supported = 0;
cmd->advertising = 0;
ethtool_cmd_speed_set(cmd, SPEED_10000);
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;
return 0;
}
static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
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)
{
switch(stringset) {
case ETH_SS_STATS:
memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
break;
}
}
static int veth_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(ethtool_stats_keys);
default:
return -EOPNOTSUPP;
}
}
static void veth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
data[0] = peer ? peer->ifindex : 0;
}
static const struct ethtool_ops veth_ethtool_ops = {
.get_settings = veth_get_settings,
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_strings = veth_get_strings,
.get_sset_count = veth_get_sset_count,
.get_ethtool_stats = veth_get_ethtool_stats,
};
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
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
*/
if (skb->ip_summed == CHECKSUM_NONE &&
rcv->features & NETIF_F_RXCSUM)
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
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 u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int cpu;
result->packets = 0;
result->bytes = 0;
for_each_possible_cpu(cpu) {
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;
}
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 = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
if (!peer)
return -ENOTCONN;
if (peer->flags & IFF_UP) {
netif_carrier_on(dev);
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);
if (peer)
netif_carrier_off(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)
{
dev->vstats = alloc_percpu(struct pcpu_vstats);
if (!dev->vstats)
return -ENOMEM;
return 0;
}
static void veth_dev_free(struct net_device *dev)
{
free_percpu(dev->vstats);
free_netdev(dev);
}
static const struct net_device_ops veth_netdev_ops = {
.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_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->vlan_features = dev->features;
dev->destructor = veth_dev_free;
dev->hw_features = VETH_FEATURES;
}
/*
* netlink interface
*/
static int veth_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
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 *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
int err;
struct net_device *peer;
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
*/
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),
ifla_policy);
if (err < 0)
return err;
err = veth_validate(peer_tb, NULL);
if (err < 0)
return err;
tbp = peer_tb;
} else {
ifmp = NULL;
tbp = tb;
}
if (tbp[IFLA_IFNAME])
nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
net = rtnl_link_get_net(src_net, tbp);
if (IS_ERR(net))
return PTR_ERR(net);
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)
eth_hw_addr_random(peer);
if (ifmp && (dev->ifindex != 0))
peer->ifindex = ifmp->ifi_index;
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
*
* note, that since we've registered new device the dev's name
* should be re-allocated
*/
if (tb[IFLA_ADDRESS] == NULL)
eth_hw_addr_random(dev);
if (tb[IFLA_IFNAME])
nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
err = register_netdevice(dev);
if (err < 0)
goto err_register_dev;
netif_carrier_off(dev);
/*
* tie the deviced together
*/
priv = netdev_priv(dev);
rcu_assign_pointer(priv->peer, peer);
priv = netdev_priv(peer);
rcu_assign_pointer(priv->peer, dev);
return 0;
err_register_dev:
/* nothing to do */
err_configure_peer:
unregister_netdevice(peer);
return err;
err_register_peer:
free_netdev(peer);
return err;
}
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 = 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);
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] = {
[VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
};
static struct rtnl_link_ops veth_link_ops = {
.kind = DRV_NAME,
.priv_size = sizeof(struct veth_priv),
.setup = veth_setup,
.validate = veth_validate,
.newlink = veth_newlink,
.dellink = veth_dellink,
.policy = veth_policy,
.maxtype = VETH_INFO_MAX,
};
/*
* init/fini
*/
static __init int veth_init(void)
{
return rtnl_link_register(&veth_link_ops);
}
static __exit void veth_exit(void)
{
rtnl_link_unregister(&veth_link_ops);
}
module_init(veth_init);
module_exit(veth_exit);
MODULE_DESCRIPTION("Virtual Ethernet Tunnel");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);