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
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
|
/*
* Copyright (c) 2006 Oracle. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
*/
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/gfp.h>
#include <linux/in.h>
#include <linux/poll.h>
#include <net/sock.h>
#include "rds.h"
/* this is just used for stats gathering :/ */
static DEFINE_SPINLOCK(rds_sock_lock);
static unsigned long rds_sock_count;
static LIST_HEAD(rds_sock_list);
DECLARE_WAIT_QUEUE_HEAD(rds_poll_waitq);
/*
* This is called as the final descriptor referencing this socket is closed.
* We have to unbind the socket so that another socket can be bound to the
* address it was using.
*
* We have to be careful about racing with the incoming path. sock_orphan()
* sets SOCK_DEAD and we use that as an indicator to the rx path that new
* messages shouldn't be queued.
*/
static int rds_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct rds_sock *rs;
if (!sk)
goto out;
rs = rds_sk_to_rs(sk);
sock_orphan(sk);
/* Note - rds_clear_recv_queue grabs rs_recv_lock, so
* that ensures the recv path has completed messing
* with the socket. */
rds_clear_recv_queue(rs);
rds_cong_remove_socket(rs);
rds_remove_bound(rs);
rds_send_drop_to(rs, NULL);
rds_rdma_drop_keys(rs);
rds_notify_queue_get(rs, NULL);
spin_lock_bh(&rds_sock_lock);
list_del_init(&rs->rs_item);
rds_sock_count--;
spin_unlock_bh(&rds_sock_lock);
rds_trans_put(rs->rs_transport);
sock->sk = NULL;
sock_put(sk);
out:
return 0;
}
/*
* Careful not to race with rds_release -> sock_orphan which clears sk_sleep.
* _bh() isn't OK here, we're called from interrupt handlers. It's probably OK
* to wake the waitqueue after sk_sleep is clear as we hold a sock ref, but
* this seems more conservative.
* NB - normally, one would use sk_callback_lock for this, but we can
* get here from interrupts, whereas the network code grabs sk_callback_lock
* with _lock_bh only - so relying on sk_callback_lock introduces livelocks.
*/
void rds_wake_sk_sleep(struct rds_sock *rs)
{
unsigned long flags;
read_lock_irqsave(&rs->rs_recv_lock, flags);
__rds_wake_sk_sleep(rds_rs_to_sk(rs));
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
}
static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
struct rds_sock *rs = rds_sk_to_rs(sock->sk);
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
/* racey, don't care */
if (peer) {
if (!rs->rs_conn_addr)
return -ENOTCONN;
sin->sin_port = rs->rs_conn_port;
sin->sin_addr.s_addr = rs->rs_conn_addr;
} else {
sin->sin_port = rs->rs_bound_port;
sin->sin_addr.s_addr = rs->rs_bound_addr;
}
sin->sin_family = AF_INET;
*uaddr_len = sizeof(*sin);
return 0;
}
/*
* RDS' poll is without a doubt the least intuitive part of the interface,
* as POLLIN and POLLOUT do not behave entirely as you would expect from
* a network protocol.
*
* POLLIN is asserted if
* - there is data on the receive queue.
* - to signal that a previously congested destination may have become
* uncongested
* - A notification has been queued to the socket (this can be a congestion
* update, or a RDMA completion).
*
* POLLOUT is asserted if there is room on the send queue. This does not mean
* however, that the next sendmsg() call will succeed. If the application tries
* to send to a congested destination, the system call may still fail (and
* return ENOBUFS).
*/
static __poll_t rds_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
struct sock *sk = sock->sk;
struct rds_sock *rs = rds_sk_to_rs(sk);
__poll_t mask = 0;
unsigned long flags;
poll_wait(file, sk_sleep(sk), wait);
if (rs->rs_seen_congestion)
poll_wait(file, &rds_poll_waitq, wait);
read_lock_irqsave(&rs->rs_recv_lock, flags);
if (!rs->rs_cong_monitor) {
/* When a congestion map was updated, we signal POLLIN for
* "historical" reasons. Applications can also poll for
* WRBAND instead. */
if (rds_cong_updated_since(&rs->rs_cong_track))
mask |= (POLLIN | POLLRDNORM | POLLWRBAND);
} else {
spin_lock(&rs->rs_lock);
if (rs->rs_cong_notify)
mask |= (POLLIN | POLLRDNORM);
spin_unlock(&rs->rs_lock);
}
if (!list_empty(&rs->rs_recv_queue) ||
!list_empty(&rs->rs_notify_queue))
mask |= (POLLIN | POLLRDNORM);
if (rs->rs_snd_bytes < rds_sk_sndbuf(rs))
mask |= (POLLOUT | POLLWRNORM);
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
/* clear state any time we wake a seen-congested socket */
if (mask)
rs->rs_seen_congestion = 0;
return mask;
}
static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
return -ENOIOCTLCMD;
}
static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
int len)
{
struct sockaddr_in sin;
int ret = 0;
/* racing with another thread binding seems ok here */
if (rs->rs_bound_addr == 0) {
ret = -ENOTCONN; /* XXX not a great errno */
goto out;
}
if (len < sizeof(struct sockaddr_in)) {
ret = -EINVAL;
goto out;
}
if (copy_from_user(&sin, optval, sizeof(sin))) {
ret = -EFAULT;
goto out;
}
rds_send_drop_to(rs, &sin);
out:
return ret;
}
static int rds_set_bool_option(unsigned char *optvar, char __user *optval,
int optlen)
{
int value;
if (optlen < sizeof(int))
return -EINVAL;
if (get_user(value, (int __user *) optval))
return -EFAULT;
*optvar = !!value;
return 0;
}
static int rds_cong_monitor(struct rds_sock *rs, char __user *optval,
int optlen)
{
int ret;
ret
|