summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_forward.c
blob: 98d7e53d2afde4e68585631e0f20b193ee2ecd3c (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
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The IP forwarding functionality.
 *
 * Authors:	see ip.c
 *
 * Fixes:
 *		Many		:	Split from ip.c , see ip_input.c for
 *					history.
 *		Dave Gregorich	:	NULL ip_rt_put fix for multicast
 *					routing.
 *		Jos Vos		:	Add call_out_firewall before sending,
 *					use output device for accounting.
 *		Jos Vos		:	Call forward firewall after routing
 *					(always use output device).
 *		Mike McLagan	:	Routing by source
 */

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/netfilter_ipv4.h>
#include <net/checksum.h>
#include <linux/route.h>
#include <net/route.h>
#include <net/xfrm.h>

static bool ip_may_fragment(const struct sk_buff *skb)
{
	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
	       !skb->local_df;
}

static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
	if (skb->len <= mtu || skb->local_df)
		return false;

	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
		return false;

	return true;
}

static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
{
	unsigned int mtu;

	if (skb->local_df || !skb_is_gso(skb))
		return false;

	mtu = dst_mtu(skb_dst(skb));

	/* if seglen > mtu, do software segmentation for IP fragmentation on
	 * output.  DF bit cannot be set since ip_forward would have sent
	 * icmp error.
	 */
	return skb_gso_network_seglen(skb) > mtu;
}

/* called if GSO skb needs to be fragmented on forward */
static int ip_forward_finish_gso(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	netdev_features_t features;
	struct sk_buff *segs;
	int ret = 0;

	features = netif_skb_dev_features(skb, dst->dev);
	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
	if (IS_ERR(segs)) {
		kfree_skb(skb);
		return -ENOMEM;
	}

	consume_skb(skb);

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

		segs->next = NULL;
		err = dst_output(segs);

		if (err && ret == 0)
			ret = err;
		segs = nskb;
	} while (segs);

	return ret;
}

static int ip_forward_finish(struct sk_buff *skb)
{
	struct ip_options *opt	= &(IPCB(skb)->opt);

	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
	IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);

	if (unlikely(opt->optlen))
		ip_forward_options(skb);

	if (ip_gso_exceeds_dst_mtu(skb))
		return ip_forward_finish_gso(skb);

	return dst_output(skb);
}

int ip_forward(struct sk_buff *skb)
{
	struct iphdr *iph;	/* Our header */
	struct rtable *rt;	/* Route we use */
	struct ip_options *opt	= &(IPCB(skb)->opt);

	if (skb_warn_if_lro(skb))
		goto drop;

	if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
		goto drop;

	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
		return NET_RX_SUCCESS;

	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	skb_forward_csum(skb);

	/*
	 *	According to the RFC, we must first decrease the TTL field. If
	 *	that reaches zero, we must reply an ICMP control message telling
	 *	that the packet's lifetime expired.
	 */
	if (ip_hdr(skb)->ttl <= 1)
		goto too_many_hops;

	if (!xfrm4_route_forward(skb))
		goto drop;

	rt = skb_rtable(skb);

	if (opt->is_strictroute && rt->rt_uses_gateway)
		goto sr_failed;

	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			  htonl(dst_mtu(&rt->dst)));
		goto drop;
	}

	/* We are about to mangle packet. Copy it! */
	if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len))
		goto drop;
	iph = ip_hdr(skb);

	/* Decrease ttl after skb cow done */
	ip_decrease_ttl(iph);

	/*
	 *	We now generate an ICMP HOST REDIRECT giving the route
	 *	we calculated.
	 */
	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
		ip_rt_send_redirect(skb);

	skb->priority = rt_tos2priority(iph->tos);

	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev,
		       rt->dst.dev, ip_forward_finish);

sr_failed:
	/*
	 *	Strict routing permits no gatewaying
	 */
	 icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
	 goto drop;

too_many_hops:
	/* Tell the sender its packet died... */
	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
	icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}