summaryrefslogtreecommitdiff
path: root/net/xfrm/xfrm_output.c
blob: 45ba07ab3e4f8d322e564c902774706ec09bcf9c (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
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
/*
 * xfrm_output.c - Common IPsec encapsulation code.
 *
 * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/xfrm.h>

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);

static int xfrm_skb_check_space(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev)
		- skb_headroom(skb);
	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);

	if (nhead <= 0) {
		if (ntail <= 0)
			return 0;
		nhead = 0;
	} else if (ntail < 0)
		ntail = 0;

	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
}

/* Children define the path of the packet through the
 * Linux networking.  Thus, destinations are stackable.
 */

static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
{
	struct dst_entry *child = dst_clone(xfrm_dst_child(skb_dst(skb)));

	skb_dst_drop(skb);
	return child;
}

static int xfrm_output_one(struct sk_buff *skb, int err)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;
	struct net *net = xs_net(x);

	if (err <= 0)
		goto resume;

	do {
		err = xfrm_skb_check_space(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			goto error_nolock;
		}

		skb->mark = xfrm_smark_get(skb->mark, x);

		err = x->outer_mode->output(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
			goto error_nolock;
		}

		spin_lock_bh(&x->lock);

		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
			err = -EINVAL;
			goto error;
		}

		err = xfrm_state_check_expire(x);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
			goto error;
		}

		err = x->repl->overflow(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
			goto error;
		}

		x->curlft.bytes += skb->len;
		x->curlft.packets++;

		spin_unlock_bh(&x->lock);

		skb_dst_force(skb);

		if (xfrm_offload(skb)) {
			x->type_offload->encap(x, skb);
		} else {
			/* Inner headers are invalid now. */
			skb->encapsulation = 0;

			err = x->type->output(x, skb);
			if (err == -EINPROGRESS)
				goto out;
		}

resume:
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			goto error_nolock;
		}

		dst = skb_dst_pop(skb);
		if (!dst) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			err = -EHOSTUNREACH;
			goto error_nolock;
		}
		skb_dst_set(skb, dst);
		x = dst->xfrm;
	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));

	return 0;

error:
	spin_unlock_bh(&x->lock);
error_nolock:
	kfree_skb(skb);
out:
	return err;
}

int xfrm_output_resume(struct sk_buff *skb, int err)
{
	struct net *net = xs_net(skb_dst(skb)->xfrm);

	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
		nf_reset(skb);

		err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
		if (unlikely(err != 1))
			goto out;

		if (!skb_dst(skb)->xfrm)
			return dst_output(net, skb->sk, skb);

		err = nf_hook(skb_dst(skb)->ops->family,
			      NF_INET_POST_ROUTING, net, skb->sk, skb,
			      NULL, skb_dst(skb)->dev, xfrm_output2);
		if (unlikely(err != 1))
			goto out;
	}

	if (err == -EINPROGRESS)
		err = 0;

out:
	return err;
}
EXPORT_SYMBOL_GPL(xfrm_output_resume);

static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return xfrm_output_resume(skb, 1);
}

static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct sk_buff *segs;

	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
	segs = skb_gso_segment(skb, 0);
	kfree_skb(skb);
	if (IS_ERR(segs))
		return PTR_ERR(segs);
	if (segs == NULL)
		return -EINVAL;

	do {
		struct sk_buff *nskb = segs->next;
		int err;

		segs->next = NULL;
		err = xfrm_output2(net, sk, segs);

		if (unlikely(err)) {
			kfree_skb_list(nskb);
			return err;
		}

		segs = nskb;
	} while (segs);

	return 0;
}

int xfrm_output(struct sock *sk, struct sk_buff *skb)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	struct xfrm_state *x = skb_dst(skb)->xfrm;
	int err;

	secpath_reset(skb);

	if (xfrm_dev_offload_ok(skb, x)) {
		struct sec_path *sp;

		sp = secpath_dup(skb->sp);
		if (!sp) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			kfree_skb(skb);
			return -ENOMEM;
		}
		if (skb->sp)
			secpath_put(skb->sp);
		skb->sp = sp;
		skb->encapsulation = 1;

		sp->olen++;
		sp->xvec[skb->sp->len++] = x;
		xfrm_state_hold(x);

		if (skb_is_gso(skb)) {
			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;

			return xfrm_output2(net, sk, skb);
		}

		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
			goto out;
	}

	if (skb_is_gso(skb))
		return xfrm_output_gso(net, sk, skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		err = skb_checksum_help(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			kfree_skb(skb);
			return err;
		}
	}

out:
	return xfrm_output2(net, sk, skb);
}
EXPORT_SYMBOL_GPL(xfrm_output);

int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
	struct xfrm_mode *inner_mode;
	if (x->sel.family == AF_UNSPEC)
		inner_mode = xfrm_ip2inner_mode(x,
				xfrm_af2proto(skb_dst(skb)->ops->family));
	else
		inner_mode = x->inner_mode;

	if (inner_mode == NULL)
		return -EAFNOSUPPORT;
	return inner_mode->afinfo->extract_output(x, skb);
}
EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);

void xfrm_local_error(struct sk_buff *skb, int mtu)
{
	unsigned int proto;
	struct xfrm_state_afinfo *afinfo;

	if (skb->protocol == htons(ETH_P_IP))
		proto = AF_INET;
	else if (skb->protocol == htons(ETH_P_IPV6))
		proto = AF_INET6;
	else
		return;

	afinfo = xfrm_state_get_afinfo(proto);
	if (afinfo) {
		afinfo->local_error(skb, mtu);
		rcu_read_unlock();
	}
}
EXPORT_SYMBOL_GPL(xfrm_local_error);