summaryrefslogtreecommitdiff
path: root/net/ipv6/ioam6_iptunnel.c
blob: 5d03101724b9a660b14054cf8e3d9f7c1b85b819 (plain)
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
// SPDX-License-Identifier: GPL-2.0+
/*
 *  IPv6 IOAM Lightweight Tunnel implementation
 *
 *  Author:
 *  Justin Iurman <justin.iurman@uliege.be>
 */

#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/ioam6.h>
#include <linux/ioam6_iptunnel.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/lwtunnel.h>
#include <net/ioam6.h>
#include <net/netlink.h>

#define IOAM6_MASK_SHORT_FIELDS 0xff100000
#define IOAM6_MASK_WIDE_FIELDS 0xe00000

struct ioam6_lwt_encap {
	struct ipv6_hopopt_hdr eh;
	u8 pad[2];			/* 2-octet padding for 4n-alignment */
	struct ioam6_hdr ioamh;
	struct ioam6_trace_hdr traceh;
} __packed;

struct ioam6_lwt {
	struct ioam6_lwt_encap	tuninfo;
};

static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt)
{
	return (struct ioam6_lwt *)lwt->data;
}

static struct ioam6_lwt_encap *ioam6_lwt_info(struct lwtunnel_state *lwt)
{
	return &ioam6_lwt_state(lwt)->tuninfo;
}

static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt)
{
	return &(ioam6_lwt_state(lwt)->tuninfo.traceh);
}

static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = {
	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)),
};

static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace)
{
	u32 fields;

	if (!trace->type_be32 || !trace->remlen ||
	    trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4)
		return false;

	trace->nodelen = 0;
	fields = be32_to_cpu(trace->type_be32);

	trace->nodelen += hweight32(fields & IOAM6_MASK_SHORT_FIELDS)
				* (sizeof(__be32) / 4);
	trace->nodelen += hweight32(fields & IOAM6_MASK_WIDE_FIELDS)
				* (sizeof(__be64) / 4);

	return true;
}

static int ioam6_build_state(struct net *net, struct nlattr *nla,
			     unsigned int family, const void *cfg,
			     struct lwtunnel_state **ts,
			     struct netlink_ext_ack *extack)
{
	struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1];
	struct ioam6_lwt_encap *tuninfo;
	struct ioam6_trace_hdr *trace;
	struct lwtunnel_state *s;
	int len_aligned;
	int len, err;

	if (family != AF_INET6)
		return -EINVAL;

	err = nla_parse_nested(tb, IOAM6_IPTUNNEL_MAX, nla,
			       ioam6_iptunnel_policy, extack);
	if (err < 0)
		return err;

	if (!tb[IOAM6_IPTUNNEL_TRACE]) {
		NL_SET_ERR_MSG(extack, "missing trace");
		return -EINVAL;
	}

	trace = nla_data(tb[IOAM6_IPTUNNEL_TRACE]);
	if (!ioam6_validate_trace_hdr(trace)) {
		NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_TRACE],
				    "invalid trace validation");
		return -EINVAL;
	}

	len = sizeof(*tuninfo) + trace->remlen * 4;
	len_aligned = ALIGN(len, 8);

	s = lwtunnel_state_alloc(len_aligned);
	if (!s)
		return -ENOMEM;

	tuninfo = ioam6_lwt_info(s);
	tuninfo->eh.hdrlen = (len_aligned >> 3) - 1;
	tuninfo->pad[0] = IPV6_TLV_PADN;
	tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC;
	tuninfo->ioamh.opt_type = IPV6_TLV_IOAM;
	tuninfo->ioamh.opt_len = sizeof(tuninfo->ioamh) - 2 + sizeof(*trace)
					+ trace->remlen * 4;

	memcpy(&tuninfo->traceh, trace, sizeof(*trace));

	len = len_aligned - len;
	if (len == 1) {
		tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1;
	} else if (len > 0) {
		tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN;
		tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2;
	}

	s->type = LWTUNNEL_ENCAP_IOAM6;
	s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;

	*ts = s;

	return 0;
}

static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo)
{
	struct ioam6_trace_hdr *trace;
	struct ipv6hdr *oldhdr, *hdr;
	struct ioam6_namespace *ns;
	int hdrlen, err;

	hdrlen = (tuninfo->eh.hdrlen + 1) << 3;

	err = skb_cow_head(skb, hdrlen + skb->mac_len);
	if (unlikely(err))
		return err;

	oldhdr = ipv6_hdr(skb);
	skb_pull(skb, sizeof(*oldhdr));
	skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(*oldhdr));

	skb_push(skb, sizeof(*oldhdr) + hdrlen);
	skb_reset_network_header(skb);
	skb_mac_header_rebuild(skb);

	hdr = ipv6_hdr(skb);
	memmove(hdr, oldhdr, sizeof(*oldhdr));
	tuninfo->eh.nexthdr = hdr->nexthdr;

	skb_set_transport_header(skb, sizeof(*hdr));
	skb_postpush_rcsum(skb, hdr, sizeof(*hdr) + hdrlen);

	memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen);

	hdr->nexthdr = NEXTHDR_HOP;
	hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr));

	trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb)
					   + sizeof(struct ipv6_hopopt_hdr) + 2
					   + sizeof(struct ioam6_hdr));

	ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id);
	if (ns)
		ioam6_fill_trace_data(skb, ns, trace);

	return 0;
}

static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate;
	int err = -EINVAL;

	if (skb->protocol != htons(ETH_P_IPV6))
		goto drop;

	/* Only for packets we send and
	 * that do not contain a Hop-by-Hop yet
	 */
	if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
		goto out;

	err = ioam6_do_inline(skb, ioam6_lwt_info(lwt));
	if (unlikely(err))
		goto drop;

	err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev));
	if (unlikely(err))
		goto drop;

out:
	return lwt->orig_output(net, sk, skb);

drop:
	kfree_skb(skb);
	return err;
}

static int ioam6_fill_encap_info(struct sk_buff *skb,
				 struct lwtunnel_state *lwtstate)
{
	struct ioam6_trace_hdr *trace;
	int err;

	trace = ioam6_lwt_trace(lwtstate);

	err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(*trace), trace);
	if (err)
		return err;

	return 0;
}

static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate)
{
	struct ioam6_trace_hdr *trace = ioam6_lwt_trace(lwtstate);

	return nla_total_size(sizeof(*trace));
}

static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
	struct ioam6_trace_hdr *a_hdr = ioam6_lwt_trace(a);
	struct ioam6_trace_hdr *b_hdr = ioam6_lwt_trace(b);

	return (a_hdr->namespace_id != b_hdr->namespace_id);
}

static const struct lwtunnel_encap_ops ioam6_iptun_ops = {
	.build_state		= ioam6_build_state,
	.output		= ioam6_output,
	.fill_encap		= ioam6_fill_encap_info,
	.get_encap_size	= ioam6_encap_nlsize,
	.cmp_encap		= ioam6_encap_cmp,
	.owner			= THIS_MODULE,
};

int __init ioam6_iptunnel_init(void)
{
	return lwtunnel_encap_add_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
}

void ioam6_iptunnel_exit(void)
{
	lwtunnel_encap_del_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
}