summaryrefslogtreecommitdiff
path: root/net/ipv4/netfilter.c
blob: 4f47e064e262c2f24e7cb13eacfcebff0fad86a3 (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
/* IPv4 specific functions of netfilter core */
#include <linux/kernel.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/ip.h>
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/netfilter/nf_queue.h>

/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt;
	struct flowi4 fl4 = {};
	__be32 saddr = iph->saddr;
	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
	unsigned int hh_len;

	if (addr_type == RTN_UNSPEC)
		addr_type = inet_addr_type(net, saddr);
	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
		flags |= FLOWI_FLAG_ANYSRC;
	else
		saddr = 0;

	/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
	 * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
	 */
	fl4.daddr = iph->daddr;
	fl4.saddr = saddr;
	fl4.flowi4_tos = RT_TOS(iph->tos);
	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
	fl4.flowi4_mark = skb->mark;
	fl4.flowi4_flags = flags;
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt))
		return -1;

	/* Drop old route. */
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	if (skb_dst(skb)->error)
		return -1;

#ifdef CONFIG_XFRM
	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
		struct dst_entry *dst = skb_dst(skb);
		skb_dst_set(skb, NULL);
		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
		if (IS_ERR(dst))
			return -1;
		skb_dst_set(skb, dst);
	}
#endif

	/* Change in oif may mean change in hh_len. */
	hh_len = skb_dst(skb)->dev->hard_header_len;
	if (skb_headroom(skb) < hh_len &&
	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
				0, GFP_ATOMIC))
		return -1;

	return 0;
}
EXPORT_SYMBOL(ip_route_me_harder);

#ifdef CONFIG_XFRM
int ip_xfrm_me_harder(struct sk_buff *skb)
{
	struct flowi fl;
	unsigned int hh_len;
	struct dst_entry *dst;

	if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
		return 0;
	if (xfrm_decode_session(skb, &fl, AF_INET) < 0)
		return -1;

	dst = skb_dst(skb);
	if (dst->xfrm)
		dst = ((struct xfrm_dst *)dst)->route;
	dst_hold(dst);

	dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0);
	if (IS_ERR(dst))
		return -1;

	skb_dst_drop(skb);
	skb_dst_set(skb, dst);

	/* Change in oif may mean change in hh_len. */
	hh_len = skb_dst(skb)->dev->hard_header_len;
	if (skb_headroom(skb) < hh_len &&
	    pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
		return -1;
	return 0;
}
EXPORT_SYMBOL(ip_xfrm_me_harder);
#endif

void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
EXPORT_SYMBOL(ip_nat_decode_session);

/*
 * Extra routing may needed on local out, as the QUEUE target never
 * returns control to the table.
 */

struct ip_rt_info {
	__be32 daddr;
	__be32 saddr;
	u_int8_t tos;
	u_int32_t mark;
};

static void nf_ip_saveroute(const struct sk_buff *skb,
			    struct nf_queue_entry *entry)
{
	struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->hook == NF_INET_LOCAL_OUT) {
		const struct iphdr *iph = ip_hdr(skb);

		rt_info->tos = iph->tos;
		rt_info->daddr = iph->daddr;
		rt_info->saddr = iph->saddr;
		rt_info->mark = skb->mark;
	}
}

static int nf_ip_reroute(struct sk_buff *skb,
			 const struct nf_queue_entry *entry)
{
	const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->hook == NF_INET_LOCAL_OUT) {
		const struct iphdr *iph = ip_hdr(skb);

		if (!(iph->tos == rt_info->tos &&
		      skb->mark == rt_info->mark &&
		      iph->daddr == rt_info->daddr &&
		      iph->saddr == rt_info->saddr))
			return ip_route_me_harder(skb, RTN_UNSPEC);
	}
	return 0;
}

__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
			    unsigned int dataoff, u_int8_t protocol)
{
	const struct iphdr *iph = ip_hdr(skb);
	__sum16 csum = 0;

	switch (skb->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
			break;
		if ((protocol == 0 && !csum_fold(skb->csum)) ||
		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
				       skb->len - dataoff, protocol,
				       skb->csum)) {
			skb->ip_summed = CHECKSUM_UNNECESSARY;
			break;
		}
		/* fall through */
	case CHECKSUM_NONE:
		if (protocol == 0)
			skb->csum = 0;
		else
			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
						       skb->len - dataoff,
						       protocol, 0);
		csum = __skb_checksum_complete(skb);
	}
	return csum;
}
EXPORT_SYMBOL(nf_ip_checksum);

static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
				      unsigned int dataoff, unsigned int len,
				      u_int8_t protocol)
{
	const struct iphdr *iph = ip_hdr(skb);
	__sum16 csum = 0;

	switch (skb->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (len == skb->len - dataoff)
			return nf_ip_checksum(skb, hook, dataoff, protocol);
		/* fall through */
	case CHECKSUM_NONE:
		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol,
					       skb->len - dataoff, 0);
		skb->ip_summed = CHECKSUM_NONE;
		return __skb_checksum_complete_head(skb, dataoff + len);
	}
	return csum;
}

static int nf_ip_route(struct net *net, struct dst_entry **dst,
		       struct flowi *fl, bool strict __always_unused)
{
	struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
	if (IS_ERR(rt))
		return PTR_ERR(rt);
	*dst = &rt->dst;
	return 0;
}

static const struct nf_afinfo nf_ip_afinfo = {
	.family			= AF_INET,
	.checksum		= nf_ip_checksum,
	.checksum_partial	= nf_ip_checksum_partial,
	.route			= nf_ip_route,
	.saveroute		= nf_ip_saveroute,
	.reroute		= nf_ip_reroute,
	.route_key_size		= sizeof(struct ip_rt_info),
};

static int ipv4_netfilter_init(void)
{
	return nf_register_afinfo(&nf_ip_afinfo);
}

static void ipv4_netfilter_fini(void)
{
	nf_unregister_afinfo(&nf_ip_afinfo);
}

module_init(ipv4_netfilter_init);
module_exit(ipv4_netfilter_fini);

#ifdef CONFIG_SYSCTL
struct ctl_path nf_net_ipv4_netfilter_sysctl_path[] = {
	{ .procname = "net", },
	{ .procname = "ipv4", },
	{ .procname = "netfilter", },
	{ }
};
EXPORT_SYMBOL_GPL(nf_net_ipv4_netfilter_sysctl_path);
#endif /* CONFIG_SYSCTL */