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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
|
/*
* 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.
*
* Generic INET transport hashtables
*
* Authors: Lotsa people, from code originally in tcp
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/ip.h>
/*
* Allocate and initialize a new local port bind bucket.
* The bindhash mutex for snum's hash chain must be held here.
*/
struct inet_bind_bucket *inet_bind_bucket_create(kmem_cache_t *cachep,
struct inet_bind_hashbucket *head,
const unsigned short snum)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, SLAB_ATOMIC);
if (tb != NULL) {
tb->port = snum;
tb->fastreuse = 0;
INIT_HLIST_HEAD(&tb->owners);
hlist_add_head(&tb->node, &head->chain);
}
return tb;
}
/*
* Caller must hold hashbucket lock for this tb with local BH disabled
*/
void inet_bind_bucket_destroy(kmem_cache_t *cachep, struct inet_bind_bucket *tb)
{
if (hlist_empty(&tb->owners)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
}
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum)
{
inet_sk(sk)->num = snum;
sk_add_bind_node(sk, &tb->owners);
inet_csk(sk)->icsk_bind_hash = tb;
}
/*
* Get rid of any references to a local port held by the given sock.
*/
static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
{
const int bhash = inet_bhashfn(inet_sk(sk)->num, hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
__sk_del_bind_node(sk);
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->num = 0;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
spin_unlock(&head->lock);
}
void inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
{
local_bh_disable();
__inet_put_port(hashinfo, sk);
local_bh_enable();
}
EXPORT_SYMBOL(inet_put_port);
/*
* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it can be very bad on SMP.
* Look, when several writers sleep and reader wakes them up, all but one
* immediately hit write lock and grab all the cpus. Exclusive sleep solves
* this, _but_ remember, it adds useless work on UP machines (wake up each
* exclusive lock release). It should be ifdefed really.
*/
void inet_listen_wlock(struct inet_hashinfo *hashinfo)
{
write_lock(&hashinfo->lhash_lock);
if (atomic_read(&hashinfo->lhash_users)) {
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait_exclusive(&hashinfo->lhash_wait,
&wait, TASK_UNINTERRUPTIBLE);
if (!atomic_read(&hashinfo->lhash_users))
break;
write_unlock_bh(&hashinfo->lhash_lock);
schedule();
write_lock_bh(&hashinfo->lhash_lock);
}
finish_wait(&hashinfo->lhash_wait, &wait);
}
}
EXPORT_SYMBOL(inet_listen_wlock);
/*
* Don't inline this cruft. Here are some nice properties to exploit here. The
* BSD API does not allow a listening sock to specify the remote port nor the
* remote address for the connection. So always assume those are both
* wildcarded during the search since they can never be otherwise.
*/
static struct sock *__inet_lookup_listener(const struct hlist_head *head,
const u32 daddr,
const unsigned short hnum,
const int dif)
{
struct sock *result = NULL, *sk;
const struct hlist_node *node;
int hiscore = -1;
sk_for_each(sk, node, head) {
const struct inet_sock *inet = inet_sk(sk);
if (inet->num == hnum && !ipv6_only_sock(sk)) {
const __u32 rcv_saddr = inet->rcv_saddr;
int score = sk->sk_family == PF_INET ? 1 : 0;
if (rcv_saddr) {
if (rcv_saddr != daddr)
continue;
score += 2;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
continue;
score += 2;
}
if (score == 5)
return sk;
if (score > hiscore) {
hiscore = score;
result = sk;
}
}
}
return result;
}
/* Optimize the common listener case. */
struct sock *inet_lookup_listener(struct inet_hashinfo *hashinfo,
const u32 daddr, const unsigned short hnum,
const int dif)
{
struct sock *sk = NULL;
const struct hlist_head *head;
read_lock(&hashinfo->lhash_lock);
head = &hashinfo->listening_hash[inet_lhashfn(hnum)];
if (!hlist_empty(head)) {
const struct inet_sock *inet = inet_sk((sk = __sk_head(head)));
if (inet->num == hnum && !sk->sk_node.next &&
(!inet->rcv_saddr || inet->rcv_saddr == daddr) &&
(sk->sk_family == PF_INET || !ipv6_only_sock(sk)) &&
!sk->sk_bound_dev_if)
goto sherry_cache;
sk = __inet_lookup_listener(head, daddr, hnum, dif);
}
if (sk) {
sherry_cache:
sock_hold(sk);
}
read_unlock(&hashinfo->lhash_lock);
return sk;
}
EXPORT_SYMBOL_GPL(inet_lookup_listener);
/* called with local bh disabled */
static int __inet_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, __u16 lport,
struct inet_timewait_sock **twp)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
u32 daddr = inet->rcv_saddr;
u32 saddr = inet->daddr;
int dif = sk->sk_bound_dev_if;
INET_ADDR_COOKIE(acookie, saddr, daddr)
const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport);
unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
struct sock *sk2;
const struct hlist_node *node;
struct inet_timewait_sock *tw;
prefetch(head->chain.first);
write_lock(&head->lock);
/* Check TIME-WAIT sockets first. */
sk_for_each(sk2, node, &(head + hinfo->ehash_size)->chain) {
tw = inet_twsk(sk2);
if (INET_TW_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif)) {
if (twsk_unique(sk, sk2, twp))
goto unique;
else
goto not_unique;
}
}
tw = NULL;
/* And established part... */
sk_for_each(sk2, node, &head->chain) {
if (INET_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif))
goto not_unique;
}
unique:
/* Must record num and sport now. Otherwise we will see
* in hash table socket with a funny identity. */
inet->num = lport;
inet->sport = htons(lport);
sk->sk_hash = hash;
BUG_TRAP(sk_unhashed(sk));
__sk_add_node(sk, &head->chain);
sock_prot_inc_use(sk->sk_prot);
write_unlock(&head->lock);
if (twp) {
*twp = tw;
NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
} else if (tw) {
/* Silly. Should hash-dance instead... */
inet_twsk_deschedule(tw, death_row);
NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
inet_twsk_put(tw);
}
return 0;
not_unique:
write_unlock(&head->lock);
return -EADDRNOTAVAIL;
}
static inline
|