xref: /kernel/linux/linux-5.10/net/ipv4/ip_forward.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0
2/*
3 * INET		An implementation of the TCP/IP protocol suite for the LINUX
4 *		operating system.  INET is implemented using the  BSD Socket
5 *		interface as the means of communication with the user level.
6 *
7 *		The IP forwarding functionality.
8 *
9 * Authors:	see ip.c
10 *
11 * Fixes:
12 *		Many		:	Split from ip.c , see ip_input.c for
13 *					history.
14 *		Dave Gregorich	:	NULL ip_rt_put fix for multicast
15 *					routing.
16 *		Jos Vos		:	Add call_out_firewall before sending,
17 *					use output device for accounting.
18 *		Jos Vos		:	Call forward firewall after routing
19 *					(always use output device).
20 *		Mike McLagan	:	Routing by source
21 */
22
23#include <linux/types.h>
24#include <linux/mm.h>
25#include <linux/skbuff.h>
26#include <linux/ip.h>
27#include <linux/icmp.h>
28#include <linux/netdevice.h>
29#include <linux/slab.h>
30#include <net/sock.h>
31#include <net/ip.h>
32#include <net/tcp.h>
33#include <net/udp.h>
34#include <net/icmp.h>
35#include <linux/tcp.h>
36#include <linux/udp.h>
37#include <linux/netfilter_ipv4.h>
38#include <net/checksum.h>
39#include <linux/route.h>
40#include <net/route.h>
41#include <net/xfrm.h>
42
43static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
44{
45	if (skb->len <= mtu)
46		return false;
47
48	if (unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0))
49		return false;
50
51	/* original fragment exceeds mtu and DF is set */
52	if (unlikely(IPCB(skb)->frag_max_size > mtu))
53		return true;
54
55	if (skb->ignore_df)
56		return false;
57
58	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
59		return false;
60
61	return true;
62}
63
64
65static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
66{
67	struct ip_options *opt	= &(IPCB(skb)->opt);
68
69	__IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS);
70	__IP_ADD_STATS(net, IPSTATS_MIB_OUTOCTETS, skb->len);
71
72#ifdef CONFIG_NET_SWITCHDEV
73	if (skb->offload_l3_fwd_mark) {
74		consume_skb(skb);
75		return 0;
76	}
77#endif
78
79	if (unlikely(opt->optlen))
80		ip_forward_options(skb);
81
82	skb->tstamp = 0;
83	return dst_output(net, sk, skb);
84}
85
86int ip_forward(struct sk_buff *skb)
87{
88	u32 mtu;
89	struct iphdr *iph;	/* Our header */
90	struct rtable *rt;	/* Route we use */
91	struct ip_options *opt	= &(IPCB(skb)->opt);
92	struct net *net;
93
94	/* that should never happen */
95	if (skb->pkt_type != PACKET_HOST)
96		goto drop;
97
98	if (unlikely(skb->sk))
99		goto drop;
100
101	if (skb_warn_if_lro(skb))
102		goto drop;
103
104	if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
105		goto drop;
106
107	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
108		return NET_RX_SUCCESS;
109
110	skb_forward_csum(skb);
111	net = dev_net(skb->dev);
112
113	/*
114	 *	According to the RFC, we must first decrease the TTL field. If
115	 *	that reaches zero, we must reply an ICMP control message telling
116	 *	that the packet's lifetime expired.
117	 */
118	if (ip_hdr(skb)->ttl <= 1)
119		goto too_many_hops;
120
121	if (!xfrm4_route_forward(skb))
122		goto drop;
123
124	rt = skb_rtable(skb);
125
126	if (opt->is_strictroute && rt->rt_uses_gateway)
127		goto sr_failed;
128
129	IPCB(skb)->flags |= IPSKB_FORWARDED;
130	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
131	if (ip_exceeds_mtu(skb, mtu)) {
132		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
133		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
134			  htonl(mtu));
135		goto drop;
136	}
137
138	/* We are about to mangle packet. Copy it! */
139	if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len))
140		goto drop;
141	iph = ip_hdr(skb);
142
143	/* Decrease ttl after skb cow done */
144	ip_decrease_ttl(iph);
145
146	/*
147	 *	We now generate an ICMP HOST REDIRECT giving the route
148	 *	we calculated.
149	 */
150	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
151	    !skb_sec_path(skb))
152		ip_rt_send_redirect(skb);
153
154	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority))
155		skb->priority = rt_tos2priority(iph->tos);
156
157	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
158		       net, NULL, skb, skb->dev, rt->dst.dev,
159		       ip_forward_finish);
160
161sr_failed:
162	/*
163	 *	Strict routing permits no gatewaying
164	 */
165	 icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
166	 goto drop;
167
168too_many_hops:
169	/* Tell the sender its packet died... */
170	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
171	icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
172drop:
173	kfree_skb(skb);
174	return NET_RX_DROP;
175}
176