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
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
|
/*
* 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.
*
* 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.
*/
#ifndef _INET_HASHTABLES_H
#define _INET_HASHTABLES_H
#include <linux/interrupt.h>
#include <linux/ipv6.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <net/inet_connection_sock.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
/* This is for all connections with a full identity, no wildcards.
* One chain is dedicated to TIME_WAIT sockets.
* I'll experiment with dynamic table growth later.
*/
struct inet_ehash_bucket {
struct hlist_head chain;
struct hlist_head twchain;
};
/* There are a few simple rules, which allow for local port reuse by
* an application. In essence:
*
* 1) Sockets bound to different interfaces may share a local port.
* Failing that, goto test 2.
* 2) If all sockets have sk->sk_reuse set, and none of them are in
* TCP_LISTEN state, the port may be shared.
* Failing that, goto test 3.
* 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
* address, and none of them are the same, the port may be
* shared.
* Failing this, the port cannot be shared.
*
* The interesting point, is test #2. This is what an FTP server does
* all day. To optimize this case we use a specific flag bit defined
* below. As we add sockets to a bind bucket list, we perform a
* check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
* As long as all sockets added to a bind bucket pass this test,
* the flag bit will be set.
* The resulting situation is that tcp_v[46]_verify_bind() can just check
* for this flag bit, if it is set and the socket trying to bind has
* sk->sk_reuse set, we don't even have to walk the owners list at all,
* we return that it is ok to bind this socket to the requested local port.
*
* Sounds like a lot of work, but it is worth it. In a more naive
* implementation (ie. current FreeBSD etc.) the entire list of ports
* must be walked for each data port opened by an ftp server. Needless
* to say, this does not scale at all. With a couple thousand FTP
* users logged onto your box, isn't it nice to know that new data
* ports are created in O(1) time? I thought so. ;-) -DaveM
*/
struct inet_bind_bucket {
unsigned short port;
signed short fastreuse;
struct hlist_node node;
struct hlist_head owners;
};
#define inet_bind_bucket_for_each(tb, node, head) \
hlist_for_each_entry(tb, node, head, node)
struct inet_bind_hashbucket {
spinlock_t lock;
struct hlist_head chain;
};
/* This is for listening sockets, thus all sockets which possess wildcards. */
#define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */
struct inet_hashinfo {
/* This is for sockets with full identity only. Sockets here will
* always be without wildcards and will have the following invariant:
*
* TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
*
* TIME_WAIT sockets use a separate chain (twchain).
*/
struct inet_ehash_bucket *ehash;
rwlock_t *ehash_locks;
unsigned int ehash_size;
unsigned int ehash_locks_mask;
/* Ok, let's try this, I give up, we do need a local binding
* TCP hash as well as the others for fast bind/connect.
*/
struct inet_bind_hashbucket *bhash;
unsigned int bhash_size;
/* Note : 4 bytes padding on 64 bit arches */
/* All sockets in TCP_LISTEN state will be in here. This is the only
* table where wildcard'd TCP sockets can exist. Hash function here
* is just local port number.
*/
struct hlist_head listening_hash[INET_LHTABLE_SIZE];
/* All the above members are written once at bootup and
* never written again _or_ are predominantly read-access.
*
* Now align to a new cache line as all the following members
* are often dirty.
*/
rwlock_t lhash_lock ____cacheline_aligned;
atomic_t lhash_users;
wait_queue_head_t lhash_wait;
struct kmem_cache *bind_bucket_cachep;
};
static inline struct inet_ehash_bucket *inet_ehash_bucket(
struct inet_hashinfo *hashinfo,
unsigned int hash)
{
return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)];
}
static inline rwlock_t *inet_ehash_lockp(
struct inet_hashinfo *hashinfo,
unsigned int hash)
{
return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask];
}
static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
unsigned int i, size = 256;
#if defined(CONFIG_PROVE_LOCKING)
unsigned int nr_pcpus = 2;
#else
unsigned int nr_pcpus = num_possible_cpus();
#endif
if (nr_pcpus >= 4)
size = 512;
if (nr_pcpus >= 8)
size = 1024;
if (nr_pcpus >= 16)
size = 2048;
if (nr_pcpus >= 32)
size = 4096;
if (sizeof(rwlock_t) != 0) {
#ifdef CONFIG_NUMA
if (size * sizeof(rwlock_t) > PAGE_SIZE)
hashinfo->ehash_locks = vmalloc(size * sizeof(rwlock_t));
else
#endif
hashinfo->ehash_locks = kmalloc(size * sizeof(rwlock_t),
GFP_KERNEL);
if (!hashinfo->ehash_locks)
return ENOMEM;
for (i = 0; i < size; i++)
rwlock_init(&hashinfo->ehash_locks[i]);
}
hashinfo->ehash_locks_mask = size - 1;
return 0;
}
static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
{
if (hashinfo->ehash_locks) {
#ifdef CONFIG_NUMA
unsigned int size = (hashinfo->ehash_locks_mask + 1) *
sizeof(rwlock_t);
if (size > PAGE_SIZE)
vfree(hashinfo->ehash_locks);
else
#else
kfree(hashinfo->ehash_locks);
#endif
hashinfo->ehash_locks = NULL;
}
}
extern struct inet_bind_bucket *
inet_bind_bucket_create(struct kmem_cache *cachep,
struct inet_bind_hashbucket *head,
const unsigned short snum);
extern void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
static inline int inet_bhashfn(const __u16 lport, const int bhash_size)
{
return lport & (bhash_size - 1);
}
extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum);
/* These can have wildcards, don't try too hard. */
static inline int inet_lhashfn(const unsigned short num)
{
return num & (INET_LHTABLE_SIZE - 1);
}
static inline int inet_sk_listen_hashfn(const struct sock *sk)
{
return inet_lhashfn(inet_sk(sk)->num);
}
/* Caller must disable local BH processing. */
static inline void __inet_inherit_port(struct inet_hashinfo *table,
struct sock *sk, struct sock *child)
{
const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
sk_add_bind_node(child, &tb->owners);
inet_csk(child)->icsk_bind_hash = tb;
spin_unlock(&head->lock);
}
static inline void inet_inherit_port(struct inet_hashinfo *table,
struct sock *sk, struct sock *child)
{
local_bh_disable();
__inet_inherit_port(table, sk, child);
local_bh_enable();
}
extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk);
extern void inet_listen_wlock(struct inet_hashinfo *hashinfo);
/*
* - We may sleep inside this lock.
* - If sleeping is not required (or called from BH),
* use plain read_(un)lock(&inet_hashinfo.lhash_lock).
*/
static inline void inet_listen_lock(struct inet_hashinfo *hashinfo)
{
/* read_lock synchronizes to candidates to writers */
read_lock(&hashinfo->lhash_lock);
atomic_inc(&hashinfo->lhash_users);
read_unlock(&hashinfo->lhash_lock);
}
static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo)
{
if (atomic_dec_and_test(&hashinfo->lhash_users))
wake_up(&hashinfo->lhash_wait);
}
static inline void __inet_hash(struct inet_hashinfo *hashinfo,
struct sock *sk, const int listen_possible)
{
struct hlist_head *list;
rwlock_t *lock;
BUG_TRAP(sk_unhashed(sk));
if (listen_possible && sk->sk_state == TCP_LISTEN) {
list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
lock = &hashinfo->lhash_lock;
inet_listen_wlock(hashinfo);
} else {
struct inet_ehash_bucket *head;
sk->sk_hash = inet_sk_ehashfn(sk);
head = inet_ehash_bucket(hashinfo, sk->sk_hash);
list = &head->chain;
<
|