summaryrefslogtreecommitdiffstats
path: root/net/ipv4/xfrm4_input.c
blob: 801404f7d657465c8a5e873a9578a122f2b2e940 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * xfrm4_input.c
 *
 * Changes:
 *	YOSHIFUJI Hideaki @USAGI
 *		Split up af-specific portion
 *	Derek Atkins <derek@ihtfp.com>
 *		Add Encapsulation support
 *
 */

#include <linux/slab.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/protocol.h>
#include <net/gro.h>

static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk,
				   struct sk_buff *skb)
{
	return dst_input(skb);
}

static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
					 struct sk_buff *skb)
{
	if (!skb_dst(skb)) {
		const struct iphdr *iph = ip_hdr(skb);

		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
					 iph->tos, skb->dev))
			goto drop;
	}

	if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2))
		goto drop;

	return 0;
drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}

int xfrm4_transport_finish(struct sk_buff *skb, int async)
{
	struct xfrm_offload *xo = xfrm_offload(skb);
	struct iphdr *iph = ip_hdr(skb);

	iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;

#ifndef CONFIG_NETFILTER
	if (!async)
		return -iph->protocol;
#endif

	__skb_push(skb, skb->data - skb_network_header(skb));
	iph->tot_len = htons(skb->len);
	ip_send_check(iph);

	if (xo && (xo->flags & XFRM_GRO)) {
		/* The full l2 header needs to be preserved so that re-injecting the packet at l2
		 * works correctly in the presence of vlan tags.
		 */
		skb_mac_header_rebuild_full(skb, xo->orig_mac_len);
		skb_reset_network_header(skb);
		skb_reset_transport_header(skb);
		return 0;
	}

	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
		xfrm4_rcv_encap_finish);
	return 0;
}

static int __xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull)
{
	struct udp_sock *up = udp_sk(sk);
	struct udphdr *uh;
	struct iphdr *iph;
	int iphlen, len;
	__u8 *udpdata;
	__be32 *udpdata32;
	u16 encap_type;

	encap_type = READ_ONCE(up->encap_type);
	/* if this is not encapsulated socket, then just return now */
	if (!encap_type)
		return 1;

	/* If this is a paged skb, make sure we pull up
	 * whatever data we need to look at. */
	len = skb->len - sizeof(struct udphdr);
	if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8)))
		return 1;

	/* Now we can get the pointers */
	uh = udp_hdr(skb);
	udpdata = (__u8 *)uh + sizeof(struct udphdr);
	udpdata32 = (__be32 *)udpdata;

	switch (encap_type) {
	default:
	case UDP_ENCAP_ESPINUDP:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return -EINVAL;
		} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) {
			/* ESP Packet without Non-ESP header */
			len = sizeof(struct udphdr);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	case UDP_ENCAP_ESPINUDP_NON_IKE:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return -EINVAL;
		} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
			   udpdata32[0] == 0 && udpdata32[1] == 0) {

			/* ESP Packet with Non-IKE marker */
			len = sizeof(struct udphdr) + 2 * sizeof(u32);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	}

	/* At this point we are sure that this is an ESPinUDP packet,
	 * so we need to remove 'len' bytes from the packet (the UDP
	 * header and optional ESP marker bytes) and then modify the
	 * protocol to ESP, and then call into the transform receiver.
	 */
	if (skb_unclone(skb, GFP_ATOMIC))
		return -EINVAL;

	/* Now we can update and verify the packet length... */
	iph = ip_hdr(skb);
	iphlen = iph->ihl << 2;
	iph->tot_len = htons(ntohs(iph->tot_len) - len);
	if (skb->len < iphlen + len) {
		/* packet is too small!?! */
		return -EINVAL;
	}

	/* pull the data buffer up to the ESP header and set the
	 * transport header to point to ESP.  Keep UDP on the stack
	 * for later.
	 */
	if (pull) {
		__skb_pull(skb, len);
		skb_reset_transport_header(skb);
	} else {
		skb_set_transport_header(skb, len);
	}

	/* process ESP */
	return 0;
}

/* If it's a keepalive packet, then just eat it.
 * If it's an encapsulated packet, then pass it to the
 * IPsec xfrm input.
 * Returns 0 if skb passed to xfrm or was dropped.
 * Returns >0 if skb should be passed to UDP.
 * Returns <0 if skb should be resubmitted (-ret is protocol)
 */
int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
{
	int ret;

	ret = __xfrm4_udp_encap_rcv(sk, skb, true);
	if (!ret)
		return xfrm4_rcv_encap(skb, IPPROTO_ESP, 0,
				       udp_sk(sk)->encap_type);

	if (ret < 0) {
		kfree_skb(skb);
		return 0;
	}

	return ret;
}
EXPORT_SYMBOL(xfrm4_udp_encap_rcv);

struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
					struct sk_buff *skb)
{
	int offset = skb_gro_offset(skb);
	const struct net_offload *ops;
	struct sk_buff *pp = NULL;
	int ret;

	offset = offset - sizeof(struct udphdr);

	if (!pskb_pull(skb, offset))
		return NULL;

	rcu_read_lock();
	ops = rcu_dereference(inet_offloads[IPPROTO_ESP]);
	if (!ops || !ops->callbacks.gro_receive)
		goto out;

	ret = __xfrm4_udp_encap_rcv(sk, skb, false);
	if (ret)
		goto out;

	skb_push(skb, offset);
	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;

	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
	rcu_read_unlock();

	return pp;

out:
	rcu_read_unlock();
	skb_push(skb, offset);
	NAPI_GRO_CB(skb)->same_flow = 0;
	NAPI_GRO_CB(skb)->flush = 1;

	return NULL;
}
EXPORT_SYMBOL(xfrm4_gro_udp_encap_rcv);

int xfrm4_rcv(struct sk_buff *skb)
{
	return xfrm4_rcv_spi(skb, ip_hdr(skb)->protocol, 0);
}
EXPORT_SYMBOL(xfrm4_rcv);