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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* mpls tunnels An implementation mpls tunnels using the light weight tunnel
* infrastructure
*
* Authors: Roopa Prabhu, <roopa@cumulusnetworks.com>
*/
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/net.h>
#include <linux/module.h>
#include <linux/mpls.h>
#include <linux/vmalloc.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include <net/ip6_fib.h>
#include <net/route.h>
#include <net/mpls_iptunnel.h>
#include <linux/mpls_iptunnel.h>
#include "internal.h"
static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = {
[MPLS_IPTUNNEL_DST] = { .len = sizeof(u32) },
[MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 },
};
static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en)
{
/* The size of the layer 2.5 labels to be added for this route */
return en->labels * sizeof(struct mpls_shim_hdr);
}
static int mpls_xmit(struct sk_buff *skb)
{
struct mpls_iptunnel_encap *tun_encap_info;
struct mpls_shim_hdr *hdr;
struct net_device *out_dev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = NULL;
struct rt6_info *rt6 = NULL;
struct mpls_dev *out_mdev;
struct net *net;
int err = 0;
bool bos;
int i;
unsigned int ttl;
/* Find the output device */
out_dev = dst->dev;
net = dev_net(out_dev);
skb_orphan(skb);
if (!mpls_output_possible(out_dev) ||
!dst->lwtstate || skb_warn_if_lro(skb))
goto drop;
skb_forward_csum(skb);
tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate);
/* Obtain the ttl using the following set of rules.
*
* LWT ttl propagation setting:
* - disabled => use default TTL value from LWT
* - enabled => use TTL value from IPv4/IPv6 header
* - default =>
* Global ttl propagation setting:
* - disabled => use default TTL value from global setting
* - enabled => use TTL value from IPv4/IPv6 header
*/
if (dst->ops->family == AF_INET) {
if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
ttl = tun_encap_info->default_ttl;
else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
!net->mpls.ip_ttl_propagate)
ttl = net->mpls.default_ttl;
else
ttl = ip_hdr(skb)->ttl;
rt = (struct rtable *)dst;
} else if (dst->ops->family == AF_INET6) {
if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
ttl = tun_encap_info->default_ttl;
else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
!net->mpls.ip_ttl_propagate)
ttl = net->mpls.default_ttl;
else
ttl = ipv6_hdr(skb)->hop_limit;
rt6 = (struct rt6_info *)dst;
} else {
goto drop;
}
/* Verify the destination can hold the packet */
new_header_size = mpls_encap_size(tun_encap_info);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
goto drop;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
hh_len = 0;
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
goto drop;
skb_set_inner_protocol(skb, skb->protocol);
skb_reset_inner_network_header(skb);
skb_push(skb, new_header_size);
skb_reset_network_header(skb);
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
/* Push the new labels */
hdr = mpls_hdr(skb);
bos = true;
for (i = tun_encap_info->labels - 1; i >= 0; i--) {
hdr[i] = mpls_entry_encode(tun_encap_info->label[i],
ttl, 0, bos);
bos = false;
}
mpls_stats_inc_outucastpkts(out_dev, skb);
if (rt) {
if (rt->rt_gw_family == AF_INET6)
err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6,
skb);
else
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
skb);
} else if (rt6) {
if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
/* 6PE (RFC 4798) */
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt6->rt6i_gateway.s6_addr32[3],
skb);
} else
err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway,
skb);
}
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
return LWTUNNEL_XMIT_DONE;
drop:
out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
if (out_mdev)
MPLS_INC_STATS(out_mdev, tx_errors);
kfree_skb(skb);
return -EINVAL;
}
static int mpls_build_state(struct net *net, struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct mpls_iptunnel_encap *tun_encap_info;
struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1];
struct lwtunnel_state *newts;
u8 n_labels;
int ret;
ret = nla_parse_nested_deprecated(tb, MPLS_IPTUNNEL_MAX, nla,
mpls_iptunnel_policy, extack);
if (ret < 0)
return ret;
if (!tb[MPLS_IPTUNNEL_DST]) {
NL_SET_ERR_MSG(extack, "MPLS_IPTUNNEL_DST attribute is missing");
return -EINVAL;
}
/* determine number of labels */
if (nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS,
&n_labels, NULL, extack))
return -EINVAL;
newts = lwtunnel_state_alloc(struct_size(tun_encap_info, label,
n_labels));
if (!newts)
return -ENOMEM;
tun_encap_info = mpls_lwtunnel_encap(newts);
ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels,
&tun_encap_info->labels, tun_encap_info->label,
extack);
if (ret)
goto errout;
tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT;
if (tb[MPLS_IPTUNNEL_TTL]) {
tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]);
/* TTL 0 implies propagate from IP header */
tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ?
MPLS_TTL_PROP_DISABLED :
MPLS_TTL_PROP_ENABLED;
}
newts->type = LWTUNNEL_ENCAP_MPLS;
newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
newts->headroom = mpls_encap_size(tun_encap_info);
*ts = newts;
return 0;
errout:
kfree(newts);
*ts = NULL;
return ret;
}
static int mpls_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct mpls_iptunnel_encap *tun_encap_info;
tun_encap_info = mpls_lwtunnel_encap(lwtstate);
if (nla_put_labels(skb, MPLS_IPTUNNEL_DST, tun_encap_info->labels,
tun_encap_info->label))
goto nla_put_failure;
if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT &&
nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate)
{
struct mpls_iptunnel_encap *tun_encap_info;
int nlsize;
tun_encap_info = mpls_lwtunnel_encap(lwtstate);
nlsize = nla_total_size(tun_encap_info->labels * 4);
if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT)
nlsize += nla_total_size(1);
return nlsize;
}
static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
struct mpls_iptunnel_encap *a_hdr = mpls_lwtunnel_encap(a);
struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b);
int l;
if (a_hdr->labels != b_hdr->labels ||
a_hdr->ttl_propagate != b_hdr->ttl_propagate ||
a_hdr->default_ttl != b_hdr->default_ttl)
return 1;
for (l = 0;
|