1// SPDX-License-Identifier: GPL-2.0-only
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 TIME_WAIT sockets functions
8 *
9 *		From code orinally in TCP
10 */
11
12#include <linux/kernel.h>
13#include <linux/slab.h>
14#include <linux/module.h>
15#include <net/inet_hashtables.h>
16#include <net/inet_timewait_sock.h>
17#include <net/ip.h>
18
19
20/**
21 *	inet_twsk_bind_unhash - unhash a timewait socket from bind hash
22 *	@tw: timewait socket
23 *	@hashinfo: hashinfo pointer
24 *
25 *	unhash a timewait socket from bind hash, if hashed.
26 *	bind hash lock must be held by caller.
27 *	Returns 1 if caller should call inet_twsk_put() after lock release.
28 */
29void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
30			  struct inet_hashinfo *hashinfo)
31{
32	struct inet_bind_bucket *tb = tw->tw_tb;
33
34	if (!tb)
35		return;
36
37	__hlist_del(&tw->tw_bind_node);
38	tw->tw_tb = NULL;
39	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
40	__sock_put((struct sock *)tw);
41}
42
43/* Must be called with locally disabled BHs. */
44static void inet_twsk_kill(struct inet_timewait_sock *tw)
45{
46	struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
47	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
48	struct inet_bind_hashbucket *bhead;
49
50	spin_lock(lock);
51	sk_nulls_del_node_init_rcu((struct sock *)tw);
52	spin_unlock(lock);
53
54	/* Disassociate with bind bucket. */
55	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
56			hashinfo->bhash_size)];
57
58	spin_lock(&bhead->lock);
59	inet_twsk_bind_unhash(tw, hashinfo);
60	spin_unlock(&bhead->lock);
61
62	atomic_dec(&tw->tw_dr->tw_count);
63	inet_twsk_put(tw);
64}
65
66void inet_twsk_free(struct inet_timewait_sock *tw)
67{
68	struct module *owner = tw->tw_prot->owner;
69	twsk_destructor((struct sock *)tw);
70#ifdef SOCK_REFCNT_DEBUG
71	pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
72#endif
73	kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
74	module_put(owner);
75}
76
77void inet_twsk_put(struct inet_timewait_sock *tw)
78{
79	if (refcount_dec_and_test(&tw->tw_refcnt))
80		inet_twsk_free(tw);
81}
82EXPORT_SYMBOL_GPL(inet_twsk_put);
83
84static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
85				   struct hlist_nulls_head *list)
86{
87	hlist_nulls_add_head_rcu(&tw->tw_node, list);
88}
89
90static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
91				    struct hlist_head *list)
92{
93	hlist_add_head(&tw->tw_bind_node, list);
94}
95
96/*
97 * Enter the time wait state. This is called with locally disabled BH.
98 * Essentially we whip up a timewait bucket, copy the relevant info into it
99 * from the SK, and mess with hash chains and list linkage.
100 */
101void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
102			   struct inet_hashinfo *hashinfo)
103{
104	const struct inet_sock *inet = inet_sk(sk);
105	const struct inet_connection_sock *icsk = inet_csk(sk);
106	struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
107	spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
108	struct inet_bind_hashbucket *bhead;
109	/* Step 1: Put TW into bind hash. Original socket stays there too.
110	   Note, that any socket with inet->num != 0 MUST be bound in
111	   binding cache, even if it is closed.
112	 */
113	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
114			hashinfo->bhash_size)];
115	spin_lock(&bhead->lock);
116	tw->tw_tb = icsk->icsk_bind_hash;
117	WARN_ON(!icsk->icsk_bind_hash);
118	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
119	spin_unlock(&bhead->lock);
120
121	spin_lock(lock);
122
123	inet_twsk_add_node_rcu(tw, &ehead->chain);
124
125	/* Step 3: Remove SK from hash chain */
126	if (__sk_nulls_del_node_init_rcu(sk))
127		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
128
129	spin_unlock(lock);
130
131	/* tw_refcnt is set to 3 because we have :
132	 * - one reference for bhash chain.
133	 * - one reference for ehash chain.
134	 * - one reference for timer.
135	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
136	 * committed into memory all tw fields.
137	 * Also note that after this point, we lost our implicit reference
138	 * so we are not allowed to use tw anymore.
139	 */
140	refcount_set(&tw->tw_refcnt, 3);
141}
142EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
143
144static void tw_timer_handler(struct timer_list *t)
145{
146	struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
147
148	if (tw->tw_kill)
149		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
150	else
151		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED);
152	inet_twsk_kill(tw);
153}
154
155struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
156					   struct inet_timewait_death_row *dr,
157					   const int state)
158{
159	struct inet_timewait_sock *tw;
160
161	if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets)
162		return NULL;
163
164	tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
165			      GFP_ATOMIC);
166	if (tw) {
167		const struct inet_sock *inet = inet_sk(sk);
168
169		tw->tw_dr	    = dr;
170		/* Give us an identity. */
171		tw->tw_daddr	    = inet->inet_daddr;
172		tw->tw_rcv_saddr    = inet->inet_rcv_saddr;
173		tw->tw_bound_dev_if = sk->sk_bound_dev_if;
174		tw->tw_tos	    = inet->tos;
175		tw->tw_num	    = inet->inet_num;
176		tw->tw_state	    = TCP_TIME_WAIT;
177		tw->tw_substate	    = state;
178		tw->tw_sport	    = inet->inet_sport;
179		tw->tw_dport	    = inet->inet_dport;
180		tw->tw_family	    = sk->sk_family;
181		tw->tw_reuse	    = sk->sk_reuse;
182		tw->tw_reuseport    = sk->sk_reuseport;
183		tw->tw_hash	    = sk->sk_hash;
184		tw->tw_ipv6only	    = 0;
185		tw->tw_transparent  = inet->transparent;
186		tw->tw_prot	    = sk->sk_prot_creator;
187		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
188		twsk_net_set(tw, sock_net(sk));
189		timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
190		/*
191		 * Because we use RCU lookups, we should not set tw_refcnt
192		 * to a non null value before everything is setup for this
193		 * timewait socket.
194		 */
195		refcount_set(&tw->tw_refcnt, 0);
196
197		__module_get(tw->tw_prot->owner);
198	}
199
200	return tw;
201}
202EXPORT_SYMBOL_GPL(inet_twsk_alloc);
203
204/* These are always called from BH context.  See callers in
205 * tcp_input.c to verify this.
206 */
207
208/* This is for handling early-kills of TIME_WAIT sockets.
209 * Warning : consume reference.
210 * Caller should not access tw anymore.
211 */
212void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
213{
214	if (del_timer_sync(&tw->tw_timer))
215		inet_twsk_kill(tw);
216	inet_twsk_put(tw);
217}
218EXPORT_SYMBOL(inet_twsk_deschedule_put);
219
220void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
221{
222	/* timeout := RTO * 3.5
223	 *
224	 * 3.5 = 1+2+0.5 to wait for two retransmits.
225	 *
226	 * RATIONALE: if FIN arrived and we entered TIME-WAIT state,
227	 * our ACK acking that FIN can be lost. If N subsequent retransmitted
228	 * FINs (or previous seqments) are lost (probability of such event
229	 * is p^(N+1), where p is probability to lose single packet and
230	 * time to detect the loss is about RTO*(2^N - 1) with exponential
231	 * backoff). Normal timewait length is calculated so, that we
232	 * waited at least for one retransmitted FIN (maximal RTO is 120sec).
233	 * [ BTW Linux. following BSD, violates this requirement waiting
234	 *   only for 60sec, we should wait at least for 240 secs.
235	 *   Well, 240 consumes too much of resources 8)
236	 * ]
237	 * This interval is not reduced to catch old duplicate and
238	 * responces to our wandering segments living for two MSLs.
239	 * However, if we use PAWS to detect
240	 * old duplicates, we can reduce the interval to bounds required
241	 * by RTO, rather than MSL. So, if peer understands PAWS, we
242	 * kill tw bucket after 3.5*RTO (it is important that this number
243	 * is greater than TS tick!) and detect old duplicates with help
244	 * of PAWS.
245	 */
246
247	tw->tw_kill = timeo <= 4*HZ;
248	if (!rearm) {
249		BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo));
250		atomic_inc(&tw->tw_dr->tw_count);
251	} else {
252		mod_timer_pending(&tw->tw_timer, jiffies + timeo);
253	}
254}
255EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
256
257/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
258void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
259{
260	struct hlist_nulls_node *node;
261	unsigned int slot;
262	struct sock *sk;
263
264	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
265		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
266restart_rcu:
267		cond_resched();
268		rcu_read_lock();
269restart:
270		sk_nulls_for_each_rcu(sk, node, &head->chain) {
271			int state = inet_sk_state_load(sk);
272
273			if ((1 << state) & ~(TCPF_TIME_WAIT |
274					     TCPF_NEW_SYN_RECV))
275				continue;
276
277			if (sk->sk_family != family ||
278			    refcount_read(&sock_net(sk)->count))
279				continue;
280
281			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
282				continue;
283
284			if (unlikely(sk->sk_family != family ||
285				     refcount_read(&sock_net(sk)->count))) {
286				sock_gen_put(sk);
287				goto restart;
288			}
289
290			rcu_read_unlock();
291			local_bh_disable();
292			if (state == TCP_TIME_WAIT) {
293				inet_twsk_deschedule_put(inet_twsk(sk));
294			} else {
295				struct request_sock *req = inet_reqsk(sk);
296
297				inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
298								  req);
299			}
300			local_bh_enable();
301			goto restart_rcu;
302		}
303		/* If the nulls value we got at the end of this lookup is
304		 * not the expected one, we must restart lookup.
305		 * We probably met an item that was moved to another chain.
306		 */
307		if (get_nulls_value(node) != slot)
308			goto restart;
309		rcu_read_unlock();
310	}
311}
312EXPORT_SYMBOL_GPL(inet_twsk_purge);
313