2013-06-18 08:49:56 +08:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2013 Nicira, Inc.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
|
|
* License as published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful, but
|
|
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
|
|
|
|
* 02110-1301, USA
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <linux/netdevice.h>
|
|
|
|
#include <linux/in.h>
|
|
|
|
#include <linux/if_arp.h>
|
|
|
|
#include <linux/mroute.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/in6.h>
|
|
|
|
#include <linux/inetdevice.h>
|
|
|
|
#include <linux/netfilter_ipv4.h>
|
|
|
|
#include <linux/etherdevice.h>
|
|
|
|
#include <linux/if_ether.h>
|
|
|
|
#include <linux/if_vlan.h>
|
|
|
|
|
|
|
|
#include <net/ip.h>
|
|
|
|
#include <net/icmp.h>
|
|
|
|
#include <net/protocol.h>
|
|
|
|
#include <net/ip_tunnels.h>
|
|
|
|
#include <net/arp.h>
|
|
|
|
#include <net/checksum.h>
|
|
|
|
#include <net/dsfield.h>
|
|
|
|
#include <net/inet_ecn.h>
|
|
|
|
#include <net/xfrm.h>
|
|
|
|
#include <net/net_namespace.h>
|
|
|
|
#include <net/netns/generic.h>
|
|
|
|
#include <net/rtnetlink.h>
|
|
|
|
|
2014-04-16 01:47:15 +08:00
|
|
|
int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
|
2013-06-18 08:49:56 +08:00
|
|
|
__be32 src, __be32 dst, __u8 proto,
|
2013-09-02 21:34:57 +08:00
|
|
|
__u8 tos, __u8 ttl, __be16 df, bool xnet)
|
2013-06-18 08:49:56 +08:00
|
|
|
{
|
|
|
|
int pkt_len = skb->len;
|
|
|
|
struct iphdr *iph;
|
|
|
|
int err;
|
|
|
|
|
2013-09-02 21:34:57 +08:00
|
|
|
skb_scrub_packet(skb, xnet);
|
|
|
|
|
2013-12-16 14:12:18 +08:00
|
|
|
skb_clear_hash(skb);
|
2013-06-18 08:49:56 +08:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
|
|
|
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
|
|
|
|
|
|
|
|
/* Push down and install the IP header. */
|
2013-10-01 17:35:51 +08:00
|
|
|
skb_push(skb, sizeof(struct iphdr));
|
2013-06-18 08:49:56 +08:00
|
|
|
skb_reset_network_header(skb);
|
|
|
|
|
|
|
|
iph = ip_hdr(skb);
|
|
|
|
|
|
|
|
iph->version = 4;
|
|
|
|
iph->ihl = sizeof(struct iphdr) >> 2;
|
|
|
|
iph->frag_off = df;
|
|
|
|
iph->protocol = proto;
|
|
|
|
iph->tos = tos;
|
|
|
|
iph->daddr = dst;
|
|
|
|
iph->saddr = src;
|
|
|
|
iph->ttl = ttl;
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 20:26:03 +08:00
|
|
|
__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
|
2013-06-18 08:49:56 +08:00
|
|
|
|
2014-04-16 01:47:15 +08:00
|
|
|
err = ip_local_out_sk(sk, skb);
|
2013-06-18 08:49:56 +08:00
|
|
|
if (unlikely(net_xmit_eval(err)))
|
|
|
|
pkt_len = 0;
|
|
|
|
return pkt_len;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(iptunnel_xmit);
|
2013-06-18 08:50:02 +08:00
|
|
|
|
|
|
|
int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
|
|
|
|
{
|
|
|
|
if (unlikely(!pskb_may_pull(skb, hdr_len)))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
skb_pull_rcsum(skb, hdr_len);
|
|
|
|
|
|
|
|
if (inner_proto == htons(ETH_P_TEB)) {
|
|
|
|
struct ethhdr *eh = (struct ethhdr *)skb->data;
|
|
|
|
|
|
|
|
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN))
|
|
|
|
skb->protocol = eh->h_proto;
|
|
|
|
else
|
|
|
|
skb->protocol = htons(ETH_P_802_2);
|
|
|
|
|
|
|
|
} else {
|
|
|
|
skb->protocol = inner_proto;
|
|
|
|
}
|
|
|
|
|
|
|
|
nf_reset(skb);
|
|
|
|
secpath_reset(skb);
|
2013-12-16 14:12:18 +08:00
|
|
|
skb_clear_hash_if_not_l4(skb);
|
2014-03-24 13:06:36 +08:00
|
|
|
skb_dst_drop(skb);
|
2013-06-18 08:50:02 +08:00
|
|
|
skb->vlan_tci = 0;
|
|
|
|
skb_set_queue_mapping(skb, 0);
|
|
|
|
skb->pkt_type = PACKET_HOST;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(iptunnel_pull_header);
|
2013-10-20 02:42:55 +08:00
|
|
|
|
|
|
|
struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
|
|
|
|
bool csum_help,
|
|
|
|
int gso_type_mask)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (likely(!skb->encapsulation)) {
|
|
|
|
skb_reset_inner_headers(skb);
|
|
|
|
skb->encapsulation = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (skb_is_gso(skb)) {
|
|
|
|
err = skb_unclone(skb, GFP_ATOMIC);
|
|
|
|
if (unlikely(err))
|
|
|
|
goto error;
|
|
|
|
skb_shinfo(skb)->gso_type |= gso_type_mask;
|
|
|
|
return skb;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) {
|
|
|
|
err = skb_checksum_help(skb);
|
|
|
|
if (unlikely(err))
|
|
|
|
goto error;
|
|
|
|
} else if (skb->ip_summed != CHECKSUM_PARTIAL)
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
|
|
|
|
return skb;
|
|
|
|
error:
|
|
|
|
kfree_skb(skb);
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
|
2014-02-20 15:14:23 +08:00
|
|
|
|
|
|
|
/* Often modified stats are per cpu, other are shared (netdev->stats) */
|
|
|
|
struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
|
|
|
|
struct rtnl_link_stats64 *tot)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_possible_cpu(i) {
|
|
|
|
const struct pcpu_sw_netstats *tstats =
|
|
|
|
per_cpu_ptr(dev->tstats, i);
|
|
|
|
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
|
|
|
|
unsigned int start;
|
|
|
|
|
|
|
|
do {
|
2014-03-14 12:26:42 +08:00
|
|
|
start = u64_stats_fetch_begin_irq(&tstats->syncp);
|
2014-02-20 15:14:23 +08:00
|
|
|
rx_packets = tstats->rx_packets;
|
|
|
|
tx_packets = tstats->tx_packets;
|
|
|
|
rx_bytes = tstats->rx_bytes;
|
|
|
|
tx_bytes = tstats->tx_bytes;
|
2014-03-14 12:26:42 +08:00
|
|
|
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
|
2014-02-20 15:14:23 +08:00
|
|
|
|
|
|
|
tot->rx_packets += rx_packets;
|
|
|
|
tot->tx_packets += tx_packets;
|
|
|
|
tot->rx_bytes += rx_bytes;
|
|
|
|
tot->tx_bytes += tx_bytes;
|
|
|
|
}
|
|
|
|
|
|
|
|
tot->multicast = dev->stats.multicast;
|
|
|
|
|
|
|
|
tot->rx_crc_errors = dev->stats.rx_crc_errors;
|
|
|
|
tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
|
|
|
|
tot->rx_length_errors = dev->stats.rx_length_errors;
|
|
|
|
tot->rx_frame_errors = dev->stats.rx_frame_errors;
|
|
|
|
tot->rx_errors = dev->stats.rx_errors;
|
|
|
|
|
|
|
|
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
|
|
|
|
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
|
|
|
|
tot->tx_dropped = dev->stats.tx_dropped;
|
|
|
|
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
|
|
|
|
tot->tx_errors = dev->stats.tx_errors;
|
|
|
|
|
|
|
|
tot->collisions = dev->stats.collisions;
|
|
|
|
|
|
|
|
return tot;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
|