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 *		Generic INET6 transport hashtables
8 *
9 * Authors:	Lotsa people, from code originally in tcp, generalised here
10 *		by Arnaldo Carvalho de Melo <acme@mandriva.com>
11 */
12
13#include <linux/module.h>
14#include <linux/random.h>
15
16#include <net/addrconf.h>
17#include <net/inet_connection_sock.h>
18#include <net/inet_hashtables.h>
19#include <net/inet6_hashtables.h>
20#include <net/secure_seq.h>
21#include <net/ip.h>
22#include <net/sock_reuseport.h>
23
24u32 inet6_ehashfn(const struct net *net,
25		  const struct in6_addr *laddr, const u16 lport,
26		  const struct in6_addr *faddr, const __be16 fport)
27{
28	static u32 inet6_ehash_secret __read_mostly;
29	static u32 ipv6_hash_secret __read_mostly;
30
31	u32 lhash, fhash;
32
33	net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret));
34	net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
35
36	lhash = (__force u32)laddr->s6_addr32[3];
37	fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
38
39	return __inet6_ehashfn(lhash, lport, fhash, fport,
40			       inet6_ehash_secret + net_hash_mix(net));
41}
42EXPORT_SYMBOL_GPL(inet6_ehashfn);
43
44/*
45 * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
46 * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
47 *
48 * The sockhash lock must be held as a reader here.
49 */
50struct sock *__inet6_lookup_established(struct net *net,
51					struct inet_hashinfo *hashinfo,
52					   const struct in6_addr *saddr,
53					   const __be16 sport,
54					   const struct in6_addr *daddr,
55					   const u16 hnum,
56					   const int dif, const int sdif)
57{
58	struct sock *sk;
59	const struct hlist_nulls_node *node;
60	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
61	/* Optimize here for direct hit, only listening connections can
62	 * have wildcards anyways.
63	 */
64	unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
65	unsigned int slot = hash & hashinfo->ehash_mask;
66	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
67
68
69begin:
70	sk_nulls_for_each_rcu(sk, node, &head->chain) {
71		if (sk->sk_hash != hash)
72			continue;
73		if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
74			continue;
75		if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
76			goto out;
77
78		if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) {
79			sock_gen_put(sk);
80			goto begin;
81		}
82		goto found;
83	}
84	if (get_nulls_value(node) != slot)
85		goto begin;
86out:
87	sk = NULL;
88found:
89	return sk;
90}
91EXPORT_SYMBOL(__inet6_lookup_established);
92
93static inline int compute_score(struct sock *sk, struct net *net,
94				const unsigned short hnum,
95				const struct in6_addr *daddr,
96				const int dif, const int sdif)
97{
98	int score = -1;
99
100	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
101	    sk->sk_family == PF_INET6) {
102		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
103			return -1;
104
105		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
106			return -1;
107
108		score =  sk->sk_bound_dev_if ? 2 : 1;
109		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
110			score++;
111	}
112	return score;
113}
114
115/**
116 * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
117 * @net: network namespace.
118 * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
119 * @skb: context for a potential SK_REUSEPORT program.
120 * @doff: header offset.
121 * @saddr: source address.
122 * @sport: source port.
123 * @daddr: destination address.
124 * @hnum: destination port in host byte order.
125 * @ehashfn: hash function used to generate the fallback hash.
126 *
127 * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
128 *         the selected sock or an error.
129 */
130struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
131				    struct sk_buff *skb, int doff,
132				    const struct in6_addr *saddr,
133				    __be16 sport,
134				    const struct in6_addr *daddr,
135				    unsigned short hnum,
136				    inet6_ehashfn_t *ehashfn)
137{
138	struct sock *reuse_sk = NULL;
139	u32 phash;
140
141	if (sk->sk_reuseport) {
142		phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
143					   net, daddr, hnum, saddr, sport);
144		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
145	}
146	return reuse_sk;
147}
148EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
149
150/* called with rcu_read_lock() */
151static struct sock *inet6_lhash2_lookup(struct net *net,
152		struct inet_listen_hashbucket *ilb2,
153		struct sk_buff *skb, int doff,
154		const struct in6_addr *saddr,
155		const __be16 sport, const struct in6_addr *daddr,
156		const unsigned short hnum, const int dif, const int sdif)
157{
158	struct sock *sk, *result = NULL;
159	struct hlist_nulls_node *node;
160	int score, hiscore = 0;
161
162	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
163		score = compute_score(sk, net, hnum, daddr, dif, sdif);
164		if (score > hiscore) {
165			result = inet6_lookup_reuseport(net, sk, skb, doff,
166							saddr, sport, daddr, hnum, inet6_ehashfn);
167			if (result)
168				return result;
169
170			result = sk;
171			hiscore = score;
172		}
173	}
174
175	return result;
176}
177
178struct sock *inet6_lookup_run_sk_lookup(struct net *net,
179					int protocol,
180					struct sk_buff *skb, int doff,
181					const struct in6_addr *saddr,
182					const __be16 sport,
183					const struct in6_addr *daddr,
184					const u16 hnum, const int dif,
185					inet6_ehashfn_t *ehashfn)
186{
187	struct sock *sk, *reuse_sk;
188	bool no_reuseport;
189
190	no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
191					    daddr, hnum, dif, &sk);
192	if (no_reuseport || IS_ERR_OR_NULL(sk))
193		return sk;
194
195	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
196					  saddr, sport, daddr, hnum, ehashfn);
197	if (reuse_sk)
198		sk = reuse_sk;
199	return sk;
200}
201EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
202
203struct sock *inet6_lookup_listener(struct net *net,
204		struct inet_hashinfo *hashinfo,
205		struct sk_buff *skb, int doff,
206		const struct in6_addr *saddr,
207		const __be16 sport, const struct in6_addr *daddr,
208		const unsigned short hnum, const int dif, const int sdif)
209{
210	struct inet_listen_hashbucket *ilb2;
211	struct sock *result = NULL;
212	unsigned int hash2;
213
214	/* Lookup redirect from BPF */
215	if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
216	    hashinfo == net->ipv4.tcp_death_row.hashinfo) {
217		result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
218						    saddr, sport, daddr, hnum, dif,
219						    inet6_ehashfn);
220		if (result)
221			goto done;
222	}
223
224	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
225	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
226
227	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
228				     saddr, sport, daddr, hnum,
229				     dif, sdif);
230	if (result)
231		goto done;
232
233	/* Lookup lhash2 with in6addr_any */
234	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
235	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
236
237	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
238				     saddr, sport, &in6addr_any, hnum,
239				     dif, sdif);
240done:
241	if (IS_ERR(result))
242		return NULL;
243	return result;
244}
245EXPORT_SYMBOL_GPL(inet6_lookup_listener);
246
247struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
248			  struct sk_buff *skb, int doff,
249			  const struct in6_addr *saddr, const __be16 sport,
250			  const struct in6_addr *daddr, const __be16 dport,
251			  const int dif)
252{
253	struct sock *sk;
254	bool refcounted;
255
256	sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
257			    ntohs(dport), dif, 0, &refcounted);
258	if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
259		sk = NULL;
260	return sk;
261}
262EXPORT_SYMBOL_GPL(inet6_lookup);
263
264static int __inet6_check_established(struct inet_timewait_death_row *death_row,
265				     struct sock *sk, const __u16 lport,
266				     struct inet_timewait_sock **twp)
267{
268	struct inet_hashinfo *hinfo = death_row->hashinfo;
269	struct inet_sock *inet = inet_sk(sk);
270	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
271	const struct in6_addr *saddr = &sk->sk_v6_daddr;
272	const int dif = sk->sk_bound_dev_if;
273	struct net *net = sock_net(sk);
274	const int sdif = l3mdev_master_ifindex_by_index(net, dif);
275	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
276	const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
277						inet->inet_dport);
278	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
279	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
280	struct sock *sk2;
281	const struct hlist_nulls_node *node;
282	struct inet_timewait_sock *tw = NULL;
283
284	spin_lock(lock);
285
286	sk_nulls_for_each(sk2, node, &head->chain) {
287		if (sk2->sk_hash != hash)
288			continue;
289
290		if (likely(inet6_match(net, sk2, saddr, daddr, ports,
291				       dif, sdif))) {
292			if (sk2->sk_state == TCP_TIME_WAIT) {
293				tw = inet_twsk(sk2);
294				if (twsk_unique(sk, sk2, twp))
295					break;
296			}
297			goto not_unique;
298		}
299	}
300
301	/* Must record num and sport now. Otherwise we will see
302	 * in hash table socket with a funny identity.
303	 */
304	inet->inet_num = lport;
305	inet->inet_sport = htons(lport);
306	sk->sk_hash = hash;
307	WARN_ON(!sk_unhashed(sk));
308	__sk_nulls_add_node_rcu(sk, &head->chain);
309	if (tw) {
310		sk_nulls_del_node_init_rcu((struct sock *)tw);
311		__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
312	}
313	spin_unlock(lock);
314	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
315
316	if (twp) {
317		*twp = tw;
318	} else if (tw) {
319		/* Silly. Should hash-dance instead... */
320		inet_twsk_deschedule_put(tw);
321	}
322	return 0;
323
324not_unique:
325	spin_unlock(lock);
326	return -EADDRNOTAVAIL;
327}
328
329static u64 inet6_sk_port_offset(const struct sock *sk)
330{
331	const struct inet_sock *inet = inet_sk(sk);
332
333	return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32,
334					  sk->sk_v6_daddr.s6_addr32,
335					  inet->inet_dport);
336}
337
338int inet6_hash_connect(struct inet_timewait_death_row *death_row,
339		       struct sock *sk)
340{
341	u64 port_offset = 0;
342
343	if (!inet_sk(sk)->inet_num)
344		port_offset = inet6_sk_port_offset(sk);
345	return __inet_hash_connect(death_row, sk, port_offset,
346				   __inet6_check_established);
347}
348EXPORT_SYMBOL_GPL(inet6_hash_connect);
349
350int inet6_hash(struct sock *sk)
351{
352	int err = 0;
353
354	if (sk->sk_state != TCP_CLOSE)
355		err = __inet_hash(sk, NULL);
356
357	return err;
358}
359EXPORT_SYMBOL_GPL(inet6_hash);
360