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
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
|
#ifndef _RDS_RDS_H
#define _RDS_RDS_H
#include <net/sock.h>
#include <linux/scatterlist.h>
#include <linux/highmem.h>
#include <rdma/rdma_cm.h>
#include <linux/mutex.h>
#include <linux/rds.h>
#include "info.h"
/*
* RDS Network protocol version
*/
#define RDS_PROTOCOL_3_0 0x0300
#define RDS_PROTOCOL_3_1 0x0301
#define RDS_PROTOCOL_VERSION RDS_PROTOCOL_3_1
#define RDS_PROTOCOL_MAJOR(v) ((v) >> 8)
#define RDS_PROTOCOL_MINOR(v) ((v) & 255)
#define RDS_PROTOCOL(maj, min) (((maj) << 8) | min)
/*
* XXX randomly chosen, but at least seems to be unused:
* # 18464-18768 Unassigned
* We should do better. We want a reserved port to discourage unpriv'ed
* userspace from listening.
*/
#define RDS_PORT 18634
#ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64
#endif
#ifdef DEBUG
#define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
#else
/* sigh, pr_debug() causes unused variable warnings */
static inline void __attribute__ ((format (printf, 1, 2)))
rdsdebug(char *fmt, ...)
{
}
#endif
/* XXX is there one of these somewhere? */
#define ceil(x, y) \
({ unsigned long __x = (x), __y = (y); (__x + __y - 1) / __y; })
#define RDS_FRAG_SHIFT 12
#define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT))
#define RDS_CONG_MAP_BYTES (65536 / 8)
#define RDS_CONG_MAP_LONGS (RDS_CONG_MAP_BYTES / sizeof(unsigned long))
#define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE)
#define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8)
struct rds_cong_map {
struct rb_node m_rb_node;
__be32 m_addr;
wait_queue_head_t m_waitq;
struct list_head m_conn_list;
unsigned long m_page_addrs[RDS_CONG_MAP_PAGES];
};
/*
* This is how we will track the connection state:
* A connection is always in one of the following
* states. Updates to the state are atomic and imply
* a memory barrier.
*/
enum {
RDS_CONN_DOWN = 0,
RDS_CONN_CONNECTING,
RDS_CONN_DISCONNECTING,
RDS_CONN_UP,
RDS_CONN_ERROR,
};
/* Bits for c_flags */
#define RDS_LL_SEND_FULL 0
#define RDS_RECONNECT_PENDING 1
#define RDS_IN_XMIT 2
struct rds_connection {
struct hlist_node c_hash_node;
__be32 c_laddr;
__be32 c_faddr;
unsigned int c_loopback:1;
struct rds_connection *c_passive;
struct rds_cong_map *c_lcong;
struct rds_cong_map *c_fcong;
struct rds_message *c_xmit_rm;
unsigned long c_xmit_sg;
unsigned int c_xmit_hdr_off;
unsigned int c_xmit_data_off;
unsigned int c_xmit_atomic_sent;
unsigned int c_xmit_rdma_sent;
unsigned int c_xmit_data_sent;
spinlock_t c_lock; /* protect msg queues */
u64 c_next_tx_seq;
struct list_head c_send_queue;
struct list_head c_retrans;
u64 c_next_rx_seq;
struct rds_transport *c_trans;
void *c_transport_data;
atomic_t c_state;
unsigned long c_flags;
unsigned long c_reconnect_jiffies;
struct delayed_work c_send_w;
struct delayed_work c_recv_w;
struct delayed_work c_conn_w;
struct work_struct c_down_w;
struct mutex c_cm_lock; /* protect conn state & cm */
wait_queue_head_t c_waitq;
struct list_head c_map_item;
unsigned long c_map_queued;
unsigned int c_unacked_packets;
unsigned int c_unacked_bytes;
/* Protocol version */
unsigned int c_version;
};
#define RDS_FLAG_CONG_BITMAP 0x01
#define RDS_FLAG_ACK_REQUIRED 0x02
#define RDS_FLAG_RETRANSMITTED 0x04
#define RDS_MAX_ADV_CREDIT 255
/*
* Maximum space available for extension headers.
*/
#define RDS_HEADER_EXT_SPACE 16
struct rds_header {
__be64 h_sequence;
__be64 h_ack;
__be32 h_len;
__be16 h_sport;
__be16 h_dport;
u8 h_flags;
u8 h_credit;
u8 h_padding[4];
__sum16 h_csum;
u8 h_exthdr[RDS_HEADER_EXT_SPACE];
};
/*
* Reserved - indicates end of extensions
*/
#define RDS_EXTHDR_NONE 0
/*
* This extension header is included in the very
* first message that is sent on a new connection,
* and identifies the protocol level. This will help
* rolling updates if a future change requires breaking
* the protocol.
* NB: This is no longer true for IB, where we do a version
* negotiation during the connection setup phase (protocol
* version information is included in the RDMA CM private data).
*/
#define RDS_EXTHDR_VERSION 1
struct rds_ext_header_version {
__be32 h_version;
};
/*
* This extension header is included in the RDS message
* chasing an RDMA operation.
*/
#define RDS_EXTHDR_RDMA 2
struct rds_ext_header_rdma {
__be32 h_rdma_rkey;
};
/*
* This extension header tells the peer about the
* destination <R_Key,offset> of the requested RDMA
* operation.
*/
#define RDS_EXTHDR_RDMA_DEST 3
struct rds_ext_header_rdma_dest {
__be32 h_rdma_rkey;
__be32 h_rdma_offset;
};
#define __RDS_EXTHDR_MAX 16 /* for now */
struct rds_incoming {
atomic_t i_refcount;
struct list_head i_item;
struct rds_connection *i_conn;
struct rds_header i_hdr;
unsigned long i_rx_jiffies;
__be32 i_saddr;
rds_rdma_cookie_t i_rdma_cookie;
};
struct rds_mr {
struct rb_node r_rb_node;
atomic_t r_refcount;
u32 r_key;
/* A copy of the creation flags */
unsigned int r_use_once:1;
unsigned int r_invalidate:1;
unsigned int r_write:1;
/* This is for RDS_MR_DEAD.
* It would be nice & consistent to make this part of the above
* bit field here, but we need to use test_and_set_bit.
*/
unsigned long r_state;
struct rds_sock *r_sock; /* back pointer to the socket that owns us */
struct rds_transport *r_trans;
void *r_trans_private;
};
/* Flags for mr->r_state */
#define RDS_MR_DEAD 0
static inline rds_rdma_cookie_t rds_rdma_make_cookie(u32 r_key, u32 offset)
{
return r_key | (((u64) offset) << 32);
}
static inline u32 rds_rdma_cookie_key(rds_rdma_cookie_t cookie)
{
return cookie;
}
static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie)
{
return cookie >> 32;
}
/* atomic operation types */
#define RDS_ATOMIC_TYPE_CSWP 0
#define RDS_ATOMIC_TYPE_FADD 1
/*
* m_sock_item and m_conn_item are on lists that are serialized under
* conn->c_lock. m_sock_item has additional meaning in that once it is empty
* the message will not be put back on the retransmit list after being sent.
* messages that are canceled while being sent rely on this.
*
* m_inc is used by loopback so that it can pass an incoming message straight
* back up into the rx path. It embeds a wire header which is also used by
* the send path, which is kind of awkward.
*
* m_sock_item indicates the message's presence on a socket's send or receive
* queue. m_rs will point to that socket.
*
* m_daddr is used by cancellation to prune messages to a given destination.
*
* The RDS_MSG_ON_SOCK and RDS_MSG_ON_CONN flags are used to avoid lock
* nesting. As paths iterate over messages on a sock, or conn, they must
* also lock the conn, or sock, to remove the message from those lists too.
* Testing the flag to determine if the message is still on the lists lets
* us avoid testing the list_head directly. That means each path can use
* the message's list_head to keep it on a local list while juggling locks
* without confusing the other path.
*
* m_ack_seq is an optional field set by transports who need a different
* sequence number range to invalidate. They can use this in a callback
* that they pass to rds_send_drop_acked() to see if each message has been
* acked. The HAS_ACK_SEQ flag can be used to detect messages which haven't
* had ack_seq set yet.
*/
#define RDS_MSG_ON_SOCK 1
#define RDS_MSG_ON_CONN 2
#define RDS_MSG_HAS_ACK_SEQ 3
#define RDS_MSG_ACK_REQUIRED 4
#define RDS_MSG_RETRANSMITTED 5
#define RDS_MSG_MAPPED 6
#define RDS_MSG_PAGEVEC 7
struct rds_message {
atomic_t m_refcount;
struct list_head m_sock_item;
struct list_head m_conn_item;
struct rds_incoming m_inc;
u64 m_ack_seq;
__be32 m_daddr;
unsigned long m_flags;
/* Never access m_rs without holding m_rs_lock.
* Lock nesting is
* rm->m_rs_lock
* -> rs->rs_lock
*/
spinlock_t m_rs_lock;
wait_queue_head_t m_flush_wait;
struct rds_sock *m_rs;
/* cookie to send to remote, in rds header */
rds_rdma_cookie_t m_rdma_cookie;
unsigned int m_used_sgs;
unsigned int m_total_sgs;
void *m_final_op;
struct {
struct rm_atomic_op {
int op_type
|