xref: /kernel/linux/linux-6.6/include/net/route.h (revision 62306a36)
1/* SPDX-License-Identifier: GPL-2.0-or-later */
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 *		Definitions for the IP router.
8 *
9 * Version:	@(#)route.h	1.0.4	05/27/93
10 *
11 * Authors:	Ross Biro
12 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
13 * Fixes:
14 *		Alan Cox	:	Reformatted. Added ip_rt_local()
15 *		Alan Cox	:	Support for TCP parameters.
16 *		Alexey Kuznetsov:	Major changes for new routing code.
17 *		Mike McLagan    :	Routing by source
18 *		Robert Olsson   :	Added rt_cache statistics
19 */
20#ifndef _ROUTE_H
21#define _ROUTE_H
22
23#include <net/dst.h>
24#include <net/inetpeer.h>
25#include <net/flow.h>
26#include <net/inet_sock.h>
27#include <net/ip_fib.h>
28#include <net/arp.h>
29#include <net/ndisc.h>
30#include <linux/in_route.h>
31#include <linux/rtnetlink.h>
32#include <linux/rcupdate.h>
33#include <linux/route.h>
34#include <linux/ip.h>
35#include <linux/cache.h>
36#include <linux/security.h>
37
38#define RTO_ONLINK	0x01
39
40#define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
41#define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
42
43static inline __u8 ip_sock_rt_scope(const struct sock *sk)
44{
45	if (sock_flag(sk, SOCK_LOCALROUTE))
46		return RT_SCOPE_LINK;
47
48	return RT_SCOPE_UNIVERSE;
49}
50
51static inline __u8 ip_sock_rt_tos(const struct sock *sk)
52{
53	return RT_TOS(inet_sk(sk)->tos);
54}
55
56struct ip_tunnel_info;
57struct fib_nh;
58struct fib_info;
59struct uncached_list;
60struct rtable {
61	struct dst_entry	dst;
62
63	int			rt_genid;
64	unsigned int		rt_flags;
65	__u16			rt_type;
66	__u8			rt_is_input;
67	__u8			rt_uses_gateway;
68
69	int			rt_iif;
70
71	u8			rt_gw_family;
72	/* Info on neighbour */
73	union {
74		__be32		rt_gw4;
75		struct in6_addr	rt_gw6;
76	};
77
78	/* Miscellaneous cached information */
79	u32			rt_mtu_locked:1,
80				rt_pmtu:31;
81};
82
83static inline bool rt_is_input_route(const struct rtable *rt)
84{
85	return rt->rt_is_input != 0;
86}
87
88static inline bool rt_is_output_route(const struct rtable *rt)
89{
90	return rt->rt_is_input == 0;
91}
92
93static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
94{
95	if (rt->rt_gw_family == AF_INET)
96		return rt->rt_gw4;
97	return daddr;
98}
99
100struct ip_rt_acct {
101	__u32 	o_bytes;
102	__u32 	o_packets;
103	__u32 	i_bytes;
104	__u32 	i_packets;
105};
106
107struct rt_cache_stat {
108        unsigned int in_slow_tot;
109        unsigned int in_slow_mc;
110        unsigned int in_no_route;
111        unsigned int in_brd;
112        unsigned int in_martian_dst;
113        unsigned int in_martian_src;
114        unsigned int out_slow_tot;
115        unsigned int out_slow_mc;
116};
117
118extern struct ip_rt_acct __percpu *ip_rt_acct;
119
120struct in_device;
121
122int ip_rt_init(void);
123void rt_cache_flush(struct net *net);
124void rt_flush_dev(struct net_device *dev);
125struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
126					const struct sk_buff *skb);
127struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
128					    struct fib_result *res,
129					    const struct sk_buff *skb);
130
131static inline struct rtable *__ip_route_output_key(struct net *net,
132						   struct flowi4 *flp)
133{
134	return ip_route_output_key_hash(net, flp, NULL);
135}
136
137struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
138				    const struct sock *sk);
139struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
140				      struct net_device *dev,
141				      struct net *net, __be32 *saddr,
142				      const struct ip_tunnel_info *info,
143				      u8 protocol, bool use_cache);
144
145struct dst_entry *ipv4_blackhole_route(struct net *net,
146				       struct dst_entry *dst_orig);
147
148static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp)
149{
150	return ip_route_output_flow(net, flp, NULL);
151}
152
153static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
154					     __be32 saddr, u8 tos, int oif)
155{
156	struct flowi4 fl4 = {
157		.flowi4_oif = oif,
158		.flowi4_tos = tos,
159		.daddr = daddr,
160		.saddr = saddr,
161	};
162	return ip_route_output_key(net, &fl4);
163}
164
165static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
166						   const struct sock *sk,
167						   __be32 daddr, __be32 saddr,
168						   __be16 dport, __be16 sport,
169						   __u8 proto, __u8 tos, int oif)
170{
171	flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos,
172			   RT_SCOPE_UNIVERSE, proto,
173			   sk ? inet_sk_flowi_flags(sk) : 0,
174			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
175	if (sk)
176		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
177	return ip_route_output_flow(net, fl4, sk);
178}
179
180static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4,
181						 __be32 daddr, __be32 saddr,
182						 __be32 gre_key, __u8 tos, int oif)
183{
184	memset(fl4, 0, sizeof(*fl4));
185	fl4->flowi4_oif = oif;
186	fl4->daddr = daddr;
187	fl4->saddr = saddr;
188	fl4->flowi4_tos = tos;
189	fl4->flowi4_proto = IPPROTO_GRE;
190	fl4->fl4_gre_key = gre_key;
191	return ip_route_output_key(net, fl4);
192}
193int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
194			  u8 tos, struct net_device *dev,
195			  struct in_device *in_dev, u32 *itag);
196int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
197			 u8 tos, struct net_device *devin);
198int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
199		      u8 tos, struct net_device *devin,
200		      const struct sk_buff *hint);
201
202static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
203				 u8 tos, struct net_device *devin)
204{
205	int err;
206
207	rcu_read_lock();
208	err = ip_route_input_noref(skb, dst, src, tos, devin);
209	if (!err) {
210		skb_dst_force(skb);
211		if (!skb_dst(skb))
212			err = -EINVAL;
213	}
214	rcu_read_unlock();
215
216	return err;
217}
218
219void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
220		      u8 protocol);
221void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
222void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol);
223void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
224void ip_rt_send_redirect(struct sk_buff *skb);
225
226unsigned int inet_addr_type(struct net *net, __be32 addr);
227unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id);
228unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
229				__be32 addr);
230unsigned int inet_addr_type_dev_table(struct net *net,
231				      const struct net_device *dev,
232				      __be32 addr);
233void ip_rt_multicast_event(struct in_device *);
234int ip_rt_ioctl(struct net *, unsigned int cmd, struct rtentry *rt);
235void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
236struct rtable *rt_dst_alloc(struct net_device *dev,
237			    unsigned int flags, u16 type, bool noxfrm);
238struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt);
239
240struct in_ifaddr;
241void fib_add_ifaddr(struct in_ifaddr *);
242void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
243void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric);
244
245void rt_add_uncached_list(struct rtable *rt);
246void rt_del_uncached_list(struct rtable *rt);
247
248int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
249		       u32 table_id, struct fib_info *fi,
250		       int *fa_index, int fa_start, unsigned int flags);
251
252static inline void ip_rt_put(struct rtable *rt)
253{
254	/* dst_release() accepts a NULL parameter.
255	 * We rely on dst being first structure in struct rtable
256	 */
257	BUILD_BUG_ON(offsetof(struct rtable, dst) != 0);
258	dst_release(&rt->dst);
259}
260
261#define IPTOS_RT_MASK	(IPTOS_TOS_MASK & ~3)
262
263extern const __u8 ip_tos2prio[16];
264
265static inline char rt_tos2priority(u8 tos)
266{
267	return ip_tos2prio[IPTOS_TOS(tos)>>1];
268}
269
270/* ip_route_connect() and ip_route_newports() work in tandem whilst
271 * binding a socket for a new outgoing connection.
272 *
273 * In order to use IPSEC properly, we must, in the end, have a
274 * route that was looked up using all available keys including source
275 * and destination ports.
276 *
277 * However, if a source port needs to be allocated (the user specified
278 * a wildcard source port) we need to obtain addressing information
279 * in order to perform that allocation.
280 *
281 * So ip_route_connect() looks up a route using wildcarded source and
282 * destination ports in the key, simply so that we can get a pair of
283 * addresses to use for port allocation.
284 *
285 * Later, once the ports are allocated, ip_route_newports() will make
286 * another route lookup if needed to make sure we catch any IPSEC
287 * rules keyed on the port information.
288 *
289 * The callers allocate the flow key on their stack, and must pass in
290 * the same flowi4 object to both the ip_route_connect() and the
291 * ip_route_newports() calls.
292 */
293
294static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
295					 __be32 src, int oif, u8 protocol,
296					 __be16 sport, __be16 dport,
297					 const struct sock *sk)
298{
299	__u8 flow_flags = 0;
300
301	if (inet_test_bit(TRANSPARENT, sk))
302		flow_flags |= FLOWI_FLAG_ANYSRC;
303
304	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
305			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
306			   src, dport, sport, sk->sk_uid);
307}
308
309static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
310					      __be32 src, int oif, u8 protocol,
311					      __be16 sport, __be16 dport,
312					      const struct sock *sk)
313{
314	struct net *net = sock_net(sk);
315	struct rtable *rt;
316
317	ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk);
318
319	if (!dst || !src) {
320		rt = __ip_route_output_key(net, fl4);
321		if (IS_ERR(rt))
322			return rt;
323		ip_rt_put(rt);
324		flowi4_update_output(fl4, oif, fl4->daddr, fl4->saddr);
325	}
326	security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
327	return ip_route_output_flow(net, fl4, sk);
328}
329
330static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt,
331					       __be16 orig_sport, __be16 orig_dport,
332					       __be16 sport, __be16 dport,
333					       const struct sock *sk)
334{
335	if (sport != orig_sport || dport != orig_dport) {
336		fl4->fl4_dport = dport;
337		fl4->fl4_sport = sport;
338		ip_rt_put(rt);
339		flowi4_update_output(fl4, sk->sk_bound_dev_if, fl4->daddr,
340				     fl4->saddr);
341		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
342		return ip_route_output_flow(sock_net(sk), fl4, sk);
343	}
344	return rt;
345}
346
347static inline int inet_iif(const struct sk_buff *skb)
348{
349	struct rtable *rt = skb_rtable(skb);
350
351	if (rt && rt->rt_iif)
352		return rt->rt_iif;
353
354	return skb->skb_iif;
355}
356
357static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
358{
359	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
360	struct net *net = dev_net(dst->dev);
361
362	if (hoplimit == 0)
363		hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
364	return hoplimit;
365}
366
367static inline struct neighbour *ip_neigh_gw4(struct net_device *dev,
368					     __be32 daddr)
369{
370	struct neighbour *neigh;
371
372	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr);
373	if (unlikely(!neigh))
374		neigh = __neigh_create(&arp_tbl, &daddr, dev, false);
375
376	return neigh;
377}
378
379static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt,
380						struct sk_buff *skb,
381						bool *is_v6gw)
382{
383	struct net_device *dev = rt->dst.dev;
384	struct neighbour *neigh;
385
386	if (likely(rt->rt_gw_family == AF_INET)) {
387		neigh = ip_neigh_gw4(dev, rt->rt_gw4);
388	} else if (rt->rt_gw_family == AF_INET6) {
389		neigh = ip_neigh_gw6(dev, &rt->rt_gw6);
390		*is_v6gw = true;
391	} else {
392		neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr);
393	}
394	return neigh;
395}
396
397#endif	/* _ROUTE_H */
398