1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
|
/*
* 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 <linux/static_key.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>
int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
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;
__ip_select_ident(dev_net(rt->dst.dev), iph,
skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out_sk(sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);
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;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
} else {
skb->protocol = inner_proto;
}
nf_reset(skb);
secpath_reset(skb);
skb_clear_hash_if_not_l4(skb);
skb_dst_drop(skb);
skb->vlan_tci = 0;
skb_set_queue_mapping(skb, 0);
skb->pkt_type = PACKET_HOST;
return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_pull_header);
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 packet is not gso and we are resolving any partial checksum,
* clear encapsulation flag. This allows setting CHECKSUM_PARTIAL
* on the outer header without confusing devices that implement
* NETIF_F_IP_CSUM with encapsulation.
*/
if (csum_help)
skb->encapsulation = 0;
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);
/* 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;
netdev_stats_to_stats64(tot, &dev->stats);
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 {
start = u64_stats_fetch_begin_irq(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
return tot;
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static const struct nla_policy ip_tun_policy[IP_TUN_MAX + 1] = {
[IP_TUN_ID] = { .type = NLA_U64 },
[IP_TUN_DST] = { .type = NLA_U32 },
[IP_TUN_SRC] = { .type = NLA_U32 },
[IP_TUN_TTL] = { .type = NLA_U8 },
[IP_TUN_TOS] = { .type = NLA_U8 },
[IP_TUN_SPORT] = { .type = NLA_U16 },
[IP_TUN_DPORT] = { .type = NLA_U16 },
[IP_TUN_FLAGS] = { .type = NLA_U16 },
};
static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr,
struct lwtunnel_state **ts)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[IP_TUN_MAX + 1];
int err;
err = nla_parse_nested(tb, IP_TUN_MAX, attr, ip_tun_policy);
if (err < 0)
return err;
new_state = lwtunnel_state_alloc(sizeof(*tun_info));
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP;
tun_info = lwt_tun_info(new_state);
if (tb[IP_TUN_ID])
tun_info->key.tun_id = nla_get_u64(tb[IP_TUN_ID]);
if (tb[IP_TUN_DST])
tun_info->key.ipv4_dst = nla_get_be32(tb[IP_TUN_DST]);
if (tb[IP_TUN_SRC])
tun_info->key.ipv4_src = nla_get_be32(tb[IP_TUN_SRC]);
if (tb[IP_TUN_TTL])
tun_info->key.ipv4_ttl = nla_get_u8(tb[IP_TUN_TTL]);
if (tb[IP_TUN_TOS])
tun_info->key.ipv4_tos = nla_get_u8(tb[IP_TUN_TOS]);
if (tb[IP_TUN_SPORT])
tun_info->key.tp_src = nla_get_be16(tb[IP_TUN_SPORT]);
if (tb[IP_TUN_DPORT])
tun_info->key.tp_dst = nla_get_be16(tb[IP_TUN_DPORT]);
if (tb[IP_TUN_FLAGS])
tun_info->key.tun_flags = nla_get_u16(tb[IP_TUN_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->options = NULL;
tun_info->options_len = 0;
*ts = new_state;
return 0;
}
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_u64(skb, IP_TUN_ID, tun_info->key.tun_id) ||
nla_put_be32(skb, IP_TUN_DST, tun_info->key.ipv4_dst) ||
nla_put_be32(skb, IP_TUN_SRC, tun_info->key.ipv4_src) ||
nla_put_u8(skb, IP_TUN_TOS, tun_info->key.ipv4_tos) ||
nla_put_u8(skb, IP_TUN_TTL, tun_info->key.ipv4_ttl) ||
nla_put_u16(skb, IP_TUN_SPORT, tun_info->key.tp_src) ||
nla_put_u16(skb, IP_TUN_DPORT, tun_info->key.tp_dst) ||
nla_put_u16(skb, IP_TUN_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
return 0;
}
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size(8) /* IP_TUN_ID */
+ nla_total_size(4) /* IP_TUN_DST */
+ nla_total_size(4) /* IP_TUN_SRC */
+ nla_total_size(1) /* IP_TUN_TOS */
+ nla_total_size(1) /* IP_TUN_TTL */
+ nla_total_size(2) /* IP_TUN_SPORT */
+ nla_total_size(2) /* IP_TUN_DPORT */
+ nla_total_size(2); /* IP_TUN_FLAGS */
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
.build_state = ip_tun_build_state,
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
};
void __init ip_tunnel_core_init(void)
{
lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
}
struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE;
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
static_key_slow_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
static_key_slow_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
|
