forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
smbdirect.c
2610 lines (2240 loc) · 73.7 KB
/
smbdirect.c
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
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (C) 2017, Microsoft Corporation.
*
* Author(s): Long Li <[email protected]>
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU General Public License for more details.
*/
#include <linux/module.h>
#include <linux/highmem.h>
#include "smbdirect.h"
#include "cifs_debug.h"
static struct smbd_response *get_empty_queue_buffer(
struct smbd_connection *info);
static struct smbd_response *get_receive_buffer(
struct smbd_connection *info);
static void put_receive_buffer(
struct smbd_connection *info,
struct smbd_response *response);
static int allocate_receive_buffers(struct smbd_connection *info, int num_buf);
static void destroy_receive_buffers(struct smbd_connection *info);
static void put_empty_packet(
struct smbd_connection *info, struct smbd_response *response);
static void enqueue_reassembly(
struct smbd_connection *info,
struct smbd_response *response, int data_length);
static struct smbd_response *_get_first_reassembly(
struct smbd_connection *info);
static int smbd_post_recv(
struct smbd_connection *info,
struct smbd_response *response);
static int smbd_post_send_empty(struct smbd_connection *info);
static int smbd_post_send_data(
struct smbd_connection *info,
struct kvec *iov, int n_vec, int remaining_data_length);
static int smbd_post_send_page(struct smbd_connection *info,
struct page *page, unsigned long offset,
size_t size, int remaining_data_length);
static void destroy_mr_list(struct smbd_connection *info);
static int allocate_mr_list(struct smbd_connection *info);
/* SMBD version number */
#define SMBD_V1 0x0100
/* Port numbers for SMBD transport */
#define SMB_PORT 445
#define SMBD_PORT 5445
/* Address lookup and resolve timeout in ms */
#define RDMA_RESOLVE_TIMEOUT 5000
/* SMBD negotiation timeout in seconds */
#define SMBD_NEGOTIATE_TIMEOUT 120
/* SMBD minimum receive size and fragmented sized defined in [MS-SMBD] */
#define SMBD_MIN_RECEIVE_SIZE 128
#define SMBD_MIN_FRAGMENTED_SIZE 131072
/*
* Default maximum number of RDMA read/write outstanding on this connection
* This value is possibly decreased during QP creation on hardware limit
*/
#define SMBD_CM_RESPONDER_RESOURCES 32
/* Maximum number of retries on data transfer operations */
#define SMBD_CM_RETRY 6
/* No need to retry on Receiver Not Ready since SMBD manages credits */
#define SMBD_CM_RNR_RETRY 0
/*
* User configurable initial values per SMBD transport connection
* as defined in [MS-SMBD] 3.1.1.1
* Those may change after a SMBD negotiation
*/
/* The local peer's maximum number of credits to grant to the peer */
int smbd_receive_credit_max = 255;
/* The remote peer's credit request of local peer */
int smbd_send_credit_target = 255;
/* The maximum single message size can be sent to remote peer */
int smbd_max_send_size = 1364;
/* The maximum fragmented upper-layer payload receive size supported */
int smbd_max_fragmented_recv_size = 1024 * 1024;
/* The maximum single-message size which can be received */
int smbd_max_receive_size = 8192;
/* The timeout to initiate send of a keepalive message on idle */
int smbd_keep_alive_interval = 120;
/*
* User configurable initial values for RDMA transport
* The actual values used may be lower and are limited to hardware capabilities
*/
/* Default maximum number of SGEs in a RDMA write/read */
int smbd_max_frmr_depth = 2048;
/* If payload is less than this byte, use RDMA send/recv not read/write */
int rdma_readwrite_threshold = 4096;
/* Transport logging functions
* Logging are defined as classes. They can be OR'ed to define the actual
* logging level via module parameter smbd_logging_class
* e.g. cifs.smbd_logging_class=0xa0 will log all log_rdma_recv() and
* log_rdma_event()
*/
#define LOG_OUTGOING 0x1
#define LOG_INCOMING 0x2
#define LOG_READ 0x4
#define LOG_WRITE 0x8
#define LOG_RDMA_SEND 0x10
#define LOG_RDMA_RECV 0x20
#define LOG_KEEP_ALIVE 0x40
#define LOG_RDMA_EVENT 0x80
#define LOG_RDMA_MR 0x100
static unsigned int smbd_logging_class;
module_param(smbd_logging_class, uint, 0644);
MODULE_PARM_DESC(smbd_logging_class,
"Logging class for SMBD transport 0x0 to 0x100");
#define ERR 0x0
#define INFO 0x1
static unsigned int smbd_logging_level = ERR;
module_param(smbd_logging_level, uint, 0644);
MODULE_PARM_DESC(smbd_logging_level,
"Logging level for SMBD transport, 0 (default): error, 1: info");
#define log_rdma(level, class, fmt, args...) \
do { \
if (level <= smbd_logging_level || class & smbd_logging_class) \
cifs_dbg(VFS, "%s:%d " fmt, __func__, __LINE__, ##args);\
} while (0)
#define log_outgoing(level, fmt, args...) \
log_rdma(level, LOG_OUTGOING, fmt, ##args)
#define log_incoming(level, fmt, args...) \
log_rdma(level, LOG_INCOMING, fmt, ##args)
#define log_read(level, fmt, args...) log_rdma(level, LOG_READ, fmt, ##args)
#define log_write(level, fmt, args...) log_rdma(level, LOG_WRITE, fmt, ##args)
#define log_rdma_send(level, fmt, args...) \
log_rdma(level, LOG_RDMA_SEND, fmt, ##args)
#define log_rdma_recv(level, fmt, args...) \
log_rdma(level, LOG_RDMA_RECV, fmt, ##args)
#define log_keep_alive(level, fmt, args...) \
log_rdma(level, LOG_KEEP_ALIVE, fmt, ##args)
#define log_rdma_event(level, fmt, args...) \
log_rdma(level, LOG_RDMA_EVENT, fmt, ##args)
#define log_rdma_mr(level, fmt, args...) \
log_rdma(level, LOG_RDMA_MR, fmt, ##args)
/*
* Destroy the transport and related RDMA and memory resources
* Need to go through all the pending counters and make sure on one is using
* the transport while it is destroyed
*/
static void smbd_destroy_rdma_work(struct work_struct *work)
{
struct smbd_response *response;
struct smbd_connection *info =
container_of(work, struct smbd_connection, destroy_work);
unsigned long flags;
log_rdma_event(INFO, "destroying qp\n");
ib_drain_qp(info->id->qp);
rdma_destroy_qp(info->id);
/* Unblock all I/O waiting on the send queue */
wake_up_interruptible_all(&info->wait_send_queue);
log_rdma_event(INFO, "cancelling idle timer\n");
cancel_delayed_work_sync(&info->idle_timer_work);
log_rdma_event(INFO, "cancelling send immediate work\n");
cancel_delayed_work_sync(&info->send_immediate_work);
log_rdma_event(INFO, "wait for all send to finish\n");
wait_event(info->wait_smbd_send_pending,
info->smbd_send_pending == 0);
log_rdma_event(INFO, "wait for all recv to finish\n");
wake_up_interruptible(&info->wait_reassembly_queue);
wait_event(info->wait_smbd_recv_pending,
info->smbd_recv_pending == 0);
log_rdma_event(INFO, "wait for all send posted to IB to finish\n");
wait_event(info->wait_send_pending,
atomic_read(&info->send_pending) == 0);
wait_event(info->wait_send_payload_pending,
atomic_read(&info->send_payload_pending) == 0);
log_rdma_event(INFO, "freeing mr list\n");
wake_up_interruptible_all(&info->wait_mr);
wait_event(info->wait_for_mr_cleanup,
atomic_read(&info->mr_used_count) == 0);
destroy_mr_list(info);
/* It's not posssible for upper layer to get to reassembly */
log_rdma_event(INFO, "drain the reassembly queue\n");
do {
spin_lock_irqsave(&info->reassembly_queue_lock, flags);
response = _get_first_reassembly(info);
if (response) {
list_del(&response->list);
spin_unlock_irqrestore(
&info->reassembly_queue_lock, flags);
put_receive_buffer(info, response);
}
} while (response);
spin_unlock_irqrestore(&info->reassembly_queue_lock, flags);
info->reassembly_data_length = 0;
log_rdma_event(INFO, "free receive buffers\n");
wait_event(info->wait_receive_queues,
info->count_receive_queue + info->count_empty_packet_queue
== info->receive_credit_max);
destroy_receive_buffers(info);
ib_free_cq(info->send_cq);
ib_free_cq(info->recv_cq);
ib_dealloc_pd(info->pd);
rdma_destroy_id(info->id);
/* free mempools */
mempool_destroy(info->request_mempool);
kmem_cache_destroy(info->request_cache);
mempool_destroy(info->response_mempool);
kmem_cache_destroy(info->response_cache);
info->transport_status = SMBD_DESTROYED;
wake_up_all(&info->wait_destroy);
}
static int smbd_process_disconnected(struct smbd_connection *info)
{
schedule_work(&info->destroy_work);
return 0;
}
static void smbd_disconnect_rdma_work(struct work_struct *work)
{
struct smbd_connection *info =
container_of(work, struct smbd_connection, disconnect_work);
if (info->transport_status == SMBD_CONNECTED) {
info->transport_status = SMBD_DISCONNECTING;
rdma_disconnect(info->id);
}
}
static void smbd_disconnect_rdma_connection(struct smbd_connection *info)
{
queue_work(info->workqueue, &info->disconnect_work);
}
/* Upcall from RDMA CM */
static int smbd_conn_upcall(
struct rdma_cm_id *id, struct rdma_cm_event *event)
{
struct smbd_connection *info = id->context;
log_rdma_event(INFO, "event=%d status=%d\n",
event->event, event->status);
switch (event->event) {
case RDMA_CM_EVENT_ADDR_RESOLVED:
case RDMA_CM_EVENT_ROUTE_RESOLVED:
info->ri_rc = 0;
complete(&info->ri_done);
break;
case RDMA_CM_EVENT_ADDR_ERROR:
info->ri_rc = -EHOSTUNREACH;
complete(&info->ri_done);
break;
case RDMA_CM_EVENT_ROUTE_ERROR:
info->ri_rc = -ENETUNREACH;
complete(&info->ri_done);
break;
case RDMA_CM_EVENT_ESTABLISHED:
log_rdma_event(INFO, "connected event=%d\n", event->event);
info->transport_status = SMBD_CONNECTED;
wake_up_interruptible(&info->conn_wait);
break;
case RDMA_CM_EVENT_CONNECT_ERROR:
case RDMA_CM_EVENT_UNREACHABLE:
case RDMA_CM_EVENT_REJECTED:
log_rdma_event(INFO, "connecting failed event=%d\n", event->event);
info->transport_status = SMBD_DISCONNECTED;
wake_up_interruptible(&info->conn_wait);
break;
case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_DISCONNECTED:
/* This happenes when we fail the negotiation */
if (info->transport_status == SMBD_NEGOTIATE_FAILED) {
info->transport_status = SMBD_DISCONNECTED;
wake_up(&info->conn_wait);
break;
}
info->transport_status = SMBD_DISCONNECTED;
smbd_process_disconnected(info);
break;
default:
break;
}
return 0;
}
/* Upcall from RDMA QP */
static void
smbd_qp_async_error_upcall(struct ib_event *event, void *context)
{
struct smbd_connection *info = context;
log_rdma_event(ERR, "%s on device %s info %p\n",
ib_event_msg(event->event), event->device->name, info);
switch (event->event) {
case IB_EVENT_CQ_ERR:
case IB_EVENT_QP_FATAL:
smbd_disconnect_rdma_connection(info);
default:
break;
}
}
static inline void *smbd_request_payload(struct smbd_request *request)
{
return (void *)request->packet;
}
static inline void *smbd_response_payload(struct smbd_response *response)
{
return (void *)response->packet;
}
/* Called when a RDMA send is done */
static void send_done(struct ib_cq *cq, struct ib_wc *wc)
{
int i;
struct smbd_request *request =
container_of(wc->wr_cqe, struct smbd_request, cqe);
log_rdma_send(INFO, "smbd_request %p completed wc->status=%d\n",
request, wc->status);
if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) {
log_rdma_send(ERR, "wc->status=%d wc->opcode=%d\n",
wc->status, wc->opcode);
smbd_disconnect_rdma_connection(request->info);
}
for (i = 0; i < request->num_sge; i++)
ib_dma_unmap_single(request->info->id->device,
request->sge[i].addr,
request->sge[i].length,
DMA_TO_DEVICE);
if (request->has_payload) {
if (atomic_dec_and_test(&request->info->send_payload_pending))
wake_up(&request->info->wait_send_payload_pending);
} else {
if (atomic_dec_and_test(&request->info->send_pending))
wake_up(&request->info->wait_send_pending);
}
mempool_free(request, request->info->request_mempool);
}
static void dump_smbd_negotiate_resp(struct smbd_negotiate_resp *resp)
{
log_rdma_event(INFO, "resp message min_version %u max_version %u "
"negotiated_version %u credits_requested %u "
"credits_granted %u status %u max_readwrite_size %u "
"preferred_send_size %u max_receive_size %u "
"max_fragmented_size %u\n",
resp->min_version, resp->max_version, resp->negotiated_version,
resp->credits_requested, resp->credits_granted, resp->status,
resp->max_readwrite_size, resp->preferred_send_size,
resp->max_receive_size, resp->max_fragmented_size);
}
/*
* Process a negotiation response message, according to [MS-SMBD]3.1.5.7
* response, packet_length: the negotiation response message
* return value: true if negotiation is a success, false if failed
*/
static bool process_negotiation_response(
struct smbd_response *response, int packet_length)
{
struct smbd_connection *info = response->info;
struct smbd_negotiate_resp *packet = smbd_response_payload(response);
if (packet_length < sizeof(struct smbd_negotiate_resp)) {
log_rdma_event(ERR,
"error: packet_length=%d\n", packet_length);
return false;
}
if (le16_to_cpu(packet->negotiated_version) != SMBD_V1) {
log_rdma_event(ERR, "error: negotiated_version=%x\n",
le16_to_cpu(packet->negotiated_version));
return false;
}
info->protocol = le16_to_cpu(packet->negotiated_version);
if (packet->credits_requested == 0) {
log_rdma_event(ERR, "error: credits_requested==0\n");
return false;
}
info->receive_credit_target = le16_to_cpu(packet->credits_requested);
if (packet->credits_granted == 0) {
log_rdma_event(ERR, "error: credits_granted==0\n");
return false;
}
atomic_set(&info->send_credits, le16_to_cpu(packet->credits_granted));
atomic_set(&info->receive_credits, 0);
if (le32_to_cpu(packet->preferred_send_size) > info->max_receive_size) {
log_rdma_event(ERR, "error: preferred_send_size=%d\n",
le32_to_cpu(packet->preferred_send_size));
return false;
}
info->max_receive_size = le32_to_cpu(packet->preferred_send_size);
if (le32_to_cpu(packet->max_receive_size) < SMBD_MIN_RECEIVE_SIZE) {
log_rdma_event(ERR, "error: max_receive_size=%d\n",
le32_to_cpu(packet->max_receive_size));
return false;
}
info->max_send_size = min_t(int, info->max_send_size,
le32_to_cpu(packet->max_receive_size));
if (le32_to_cpu(packet->max_fragmented_size) <
SMBD_MIN_FRAGMENTED_SIZE) {
log_rdma_event(ERR, "error: max_fragmented_size=%d\n",
le32_to_cpu(packet->max_fragmented_size));
return false;
}
info->max_fragmented_send_size =
le32_to_cpu(packet->max_fragmented_size);
info->rdma_readwrite_threshold =
rdma_readwrite_threshold > info->max_fragmented_send_size ?
info->max_fragmented_send_size :
rdma_readwrite_threshold;
info->max_readwrite_size = min_t(u32,
le32_to_cpu(packet->max_readwrite_size),
info->max_frmr_depth * PAGE_SIZE);
info->max_frmr_depth = info->max_readwrite_size / PAGE_SIZE;
return true;
}
/*
* Check and schedule to send an immediate packet
* This is used to extend credtis to remote peer to keep the transport busy
*/
static void check_and_send_immediate(struct smbd_connection *info)
{
if (info->transport_status != SMBD_CONNECTED)
return;
info->send_immediate = true;
/*
* Promptly send a packet if our peer is running low on receive
* credits
*/
if (atomic_read(&info->receive_credits) <
info->receive_credit_target - 1)
queue_delayed_work(
info->workqueue, &info->send_immediate_work, 0);
}
static void smbd_post_send_credits(struct work_struct *work)
{
int ret = 0;
int use_receive_queue = 1;
int rc;
struct smbd_response *response;
struct smbd_connection *info =
container_of(work, struct smbd_connection,
post_send_credits_work);
if (info->transport_status != SMBD_CONNECTED) {
wake_up(&info->wait_receive_queues);
return;
}
if (info->receive_credit_target >
atomic_read(&info->receive_credits)) {
while (true) {
if (use_receive_queue)
response = get_receive_buffer(info);
else
response = get_empty_queue_buffer(info);
if (!response) {
/* now switch to emtpy packet queue */
if (use_receive_queue) {
use_receive_queue = 0;
continue;
} else
break;
}
response->type = SMBD_TRANSFER_DATA;
response->first_segment = false;
rc = smbd_post_recv(info, response);
if (rc) {
log_rdma_recv(ERR,
"post_recv failed rc=%d\n", rc);
put_receive_buffer(info, response);
break;
}
ret++;
}
}
spin_lock(&info->lock_new_credits_offered);
info->new_credits_offered += ret;
spin_unlock(&info->lock_new_credits_offered);
atomic_add(ret, &info->receive_credits);
/* Check if we can post new receive and grant credits to peer */
check_and_send_immediate(info);
}
static void smbd_recv_done_work(struct work_struct *work)
{
struct smbd_connection *info =
container_of(work, struct smbd_connection, recv_done_work);
/*
* We may have new send credits granted from remote peer
* If any sender is blcoked on lack of credets, unblock it
*/
if (atomic_read(&info->send_credits))
wake_up_interruptible(&info->wait_send_queue);
/*
* Check if we need to send something to remote peer to
* grant more credits or respond to KEEP_ALIVE packet
*/
check_and_send_immediate(info);
}
/* Called from softirq, when recv is done */
static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
{
struct smbd_data_transfer *data_transfer;
struct smbd_response *response =
container_of(wc->wr_cqe, struct smbd_response, cqe);
struct smbd_connection *info = response->info;
int data_length = 0;
log_rdma_recv(INFO, "response=%p type=%d wc status=%d wc opcode %d "
"byte_len=%d pkey_index=%x\n",
response, response->type, wc->status, wc->opcode,
wc->byte_len, wc->pkey_index);
if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) {
log_rdma_recv(INFO, "wc->status=%d opcode=%d\n",
wc->status, wc->opcode);
smbd_disconnect_rdma_connection(info);
goto error;
}
ib_dma_sync_single_for_cpu(
wc->qp->device,
response->sge.addr,
response->sge.length,
DMA_FROM_DEVICE);
switch (response->type) {
/* SMBD negotiation response */
case SMBD_NEGOTIATE_RESP:
dump_smbd_negotiate_resp(smbd_response_payload(response));
info->full_packet_received = true;
info->negotiate_done =
process_negotiation_response(response, wc->byte_len);
complete(&info->negotiate_completion);
break;
/* SMBD data transfer packet */
case SMBD_TRANSFER_DATA:
data_transfer = smbd_response_payload(response);
data_length = le32_to_cpu(data_transfer->data_length);
/*
* If this is a packet with data playload place the data in
* reassembly queue and wake up the reading thread
*/
if (data_length) {
if (info->full_packet_received)
response->first_segment = true;
if (le32_to_cpu(data_transfer->remaining_data_length))
info->full_packet_received = false;
else
info->full_packet_received = true;
enqueue_reassembly(
info,
response,
data_length);
} else
put_empty_packet(info, response);
if (data_length)
wake_up_interruptible(&info->wait_reassembly_queue);
atomic_dec(&info->receive_credits);
info->receive_credit_target =
le16_to_cpu(data_transfer->credits_requested);
atomic_add(le16_to_cpu(data_transfer->credits_granted),
&info->send_credits);
log_incoming(INFO, "data flags %d data_offset %d "
"data_length %d remaining_data_length %d\n",
le16_to_cpu(data_transfer->flags),
le32_to_cpu(data_transfer->data_offset),
le32_to_cpu(data_transfer->data_length),
le32_to_cpu(data_transfer->remaining_data_length));
/* Send a KEEP_ALIVE response right away if requested */
info->keep_alive_requested = KEEP_ALIVE_NONE;
if (le16_to_cpu(data_transfer->flags) &
SMB_DIRECT_RESPONSE_REQUESTED) {
info->keep_alive_requested = KEEP_ALIVE_PENDING;
}
queue_work(info->workqueue, &info->recv_done_work);
return;
default:
log_rdma_recv(ERR,
"unexpected response type=%d\n", response->type);
}
error:
put_receive_buffer(info, response);
}
static struct rdma_cm_id *smbd_create_id(
struct smbd_connection *info,
struct sockaddr *dstaddr, int port)
{
struct rdma_cm_id *id;
int rc;
__be16 *sport;
id = rdma_create_id(&init_net, smbd_conn_upcall, info,
RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(id)) {
rc = PTR_ERR(id);
log_rdma_event(ERR, "rdma_create_id() failed %i\n", rc);
return id;
}
if (dstaddr->sa_family == AF_INET6)
sport = &((struct sockaddr_in6 *)dstaddr)->sin6_port;
else
sport = &((struct sockaddr_in *)dstaddr)->sin_port;
*sport = htons(port);
init_completion(&info->ri_done);
info->ri_rc = -ETIMEDOUT;
rc = rdma_resolve_addr(id, NULL, (struct sockaddr *)dstaddr,
RDMA_RESOLVE_TIMEOUT);
if (rc) {
log_rdma_event(ERR, "rdma_resolve_addr() failed %i\n", rc);
goto out;
}
wait_for_completion_interruptible_timeout(
&info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT));
rc = info->ri_rc;
if (rc) {
log_rdma_event(ERR, "rdma_resolve_addr() completed %i\n", rc);
goto out;
}
info->ri_rc = -ETIMEDOUT;
rc = rdma_resolve_route(id, RDMA_RESOLVE_TIMEOUT);
if (rc) {
log_rdma_event(ERR, "rdma_resolve_route() failed %i\n", rc);
goto out;
}
wait_for_completion_interruptible_timeout(
&info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT));
rc = info->ri_rc;
if (rc) {
log_rdma_event(ERR, "rdma_resolve_route() completed %i\n", rc);
goto out;
}
return id;
out:
rdma_destroy_id(id);
return ERR_PTR(rc);
}
/*
* Test if FRWR (Fast Registration Work Requests) is supported on the device
* This implementation requries FRWR on RDMA read/write
* return value: true if it is supported
*/
static bool frwr_is_supported(struct ib_device_attr *attrs)
{
if (!(attrs->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
return false;
if (attrs->max_fast_reg_page_list_len == 0)
return false;
return true;
}
static int smbd_ia_open(
struct smbd_connection *info,
struct sockaddr *dstaddr, int port)
{
int rc;
info->id = smbd_create_id(info, dstaddr, port);
if (IS_ERR(info->id)) {
rc = PTR_ERR(info->id);
goto out1;
}
if (!frwr_is_supported(&info->id->device->attrs)) {
log_rdma_event(ERR,
"Fast Registration Work Requests "
"(FRWR) is not supported\n");
log_rdma_event(ERR,
"Device capability flags = %llx "
"max_fast_reg_page_list_len = %u\n",
info->id->device->attrs.device_cap_flags,
info->id->device->attrs.max_fast_reg_page_list_len);
rc = -EPROTONOSUPPORT;
goto out2;
}
info->max_frmr_depth = min_t(int,
smbd_max_frmr_depth,
info->id->device->attrs.max_fast_reg_page_list_len);
info->mr_type = IB_MR_TYPE_MEM_REG;
if (info->id->device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
info->mr_type = IB_MR_TYPE_SG_GAPS;
info->pd = ib_alloc_pd(info->id->device, 0);
if (IS_ERR(info->pd)) {
rc = PTR_ERR(info->pd);
log_rdma_event(ERR, "ib_alloc_pd() returned %d\n", rc);
goto out2;
}
return 0;
out2:
rdma_destroy_id(info->id);
info->id = NULL;
out1:
return rc;
}
/*
* Send a negotiation request message to the peer
* The negotiation procedure is in [MS-SMBD] 3.1.5.2 and 3.1.5.3
* After negotiation, the transport is connected and ready for
* carrying upper layer SMB payload
*/
static int smbd_post_send_negotiate_req(struct smbd_connection *info)
{
struct ib_send_wr send_wr, *send_wr_fail;
int rc = -ENOMEM;
struct smbd_request *request;
struct smbd_negotiate_req *packet;
request = mempool_alloc(info->request_mempool, GFP_KERNEL);
if (!request)
return rc;
request->info = info;
packet = smbd_request_payload(request);
packet->min_version = cpu_to_le16(SMBD_V1);
packet->max_version = cpu_to_le16(SMBD_V1);
packet->reserved = 0;
packet->credits_requested = cpu_to_le16(info->send_credit_target);
packet->preferred_send_size = cpu_to_le32(info->max_send_size);
packet->max_receive_size = cpu_to_le32(info->max_receive_size);
packet->max_fragmented_size =
cpu_to_le32(info->max_fragmented_recv_size);
request->num_sge = 1;
request->sge[0].addr = ib_dma_map_single(
info->id->device, (void *)packet,
sizeof(*packet), DMA_TO_DEVICE);
if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) {
rc = -EIO;
goto dma_mapping_failed;
}
request->sge[0].length = sizeof(*packet);
request->sge[0].lkey = info->pd->local_dma_lkey;
ib_dma_sync_single_for_device(
info->id->device, request->sge[0].addr,
request->sge[0].length, DMA_TO_DEVICE);
request->cqe.done = send_done;
send_wr.next = NULL;
send_wr.wr_cqe = &request->cqe;
send_wr.sg_list = request->sge;
send_wr.num_sge = request->num_sge;
send_wr.opcode = IB_WR_SEND;
send_wr.send_flags = IB_SEND_SIGNALED;
log_rdma_send(INFO, "sge addr=%llx length=%x lkey=%x\n",
request->sge[0].addr,
request->sge[0].length, request->sge[0].lkey);
request->has_payload = false;
atomic_inc(&info->send_pending);
rc = ib_post_send(info->id->qp, &send_wr, &send_wr_fail);
if (!rc)
return 0;
/* if we reach here, post send failed */
log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
atomic_dec(&info->send_pending);
ib_dma_unmap_single(info->id->device, request->sge[0].addr,
request->sge[0].length, DMA_TO_DEVICE);
dma_mapping_failed:
mempool_free(request, info->request_mempool);
return rc;
}
/*
* Extend the credits to remote peer
* This implements [MS-SMBD] 3.1.5.9
* The idea is that we should extend credits to remote peer as quickly as
* it's allowed, to maintain data flow. We allocate as much receive
* buffer as possible, and extend the receive credits to remote peer
* return value: the new credtis being granted.
*/
static int manage_credits_prior_sending(struct smbd_connection *info)
{
int new_credits;
spin_lock(&info->lock_new_credits_offered);
new_credits = info->new_credits_offered;
info->new_credits_offered = 0;
spin_unlock(&info->lock_new_credits_offered);
return new_credits;
}
/*
* Check if we need to send a KEEP_ALIVE message
* The idle connection timer triggers a KEEP_ALIVE message when expires
* SMB_DIRECT_RESPONSE_REQUESTED is set in the message flag to have peer send
* back a response.
* return value:
* 1 if SMB_DIRECT_RESPONSE_REQUESTED needs to be set
* 0: otherwise
*/
static int manage_keep_alive_before_sending(struct smbd_connection *info)
{
if (info->keep_alive_requested == KEEP_ALIVE_PENDING) {
info->keep_alive_requested = KEEP_ALIVE_SENT;
return 1;
}
return 0;
}
/*
* Build and prepare the SMBD packet header
* This function waits for avaialbe send credits and build a SMBD packet
* header. The caller then optional append payload to the packet after
* the header
* intput values
* size: the size of the payload
* remaining_data_length: remaining data to send if this is part of a
* fragmented packet
* output values
* request_out: the request allocated from this function
* return values: 0 on success, otherwise actual error code returned
*/
static int smbd_create_header(struct smbd_connection *info,
int size, int remaining_data_length,
struct smbd_request **request_out)
{
struct smbd_request *request;
struct smbd_data_transfer *packet;
int header_length;
int rc;
/* Wait for send credits. A SMBD packet needs one credit */
rc = wait_event_interruptible(info->wait_send_queue,
atomic_read(&info->send_credits) > 0 ||
info->transport_status != SMBD_CONNECTED);
if (rc)
return rc;
if (info->transport_status != SMBD_CONNECTED) {
log_outgoing(ERR, "disconnected not sending\n");
return -ENOENT;
}
atomic_dec(&info->send_credits);
request = mempool_alloc(info->request_mempool, GFP_KERNEL);
if (!request) {
rc = -ENOMEM;
goto err;
}
request->info = info;
/* Fill in the packet header */
packet = smbd_request_payload(request);
packet->credits_requested = cpu_to_le16(info->send_credit_target);
packet->credits_granted =
cpu_to_le16(manage_credits_prior_sending(info));
info->send_immediate = false;
packet->flags = 0;
if (manage_keep_alive_before_sending(info))
packet->flags |= cpu_to_le16(SMB_DIRECT_RESPONSE_REQUESTED);
packet->reserved = 0;
if (!size)
packet->data_offset = 0;
else
packet->data_offset = cpu_to_le32(24);
packet->data_length = cpu_to_le32(size);
packet->remaining_data_length = cpu_to_le32(remaining_data_length);
packet->padding = 0;
log_outgoing(INFO, "credits_requested=%d credits_granted=%d "
"data_offset=%d data_length=%d remaining_data_length=%d\n",
le16_to_cpu(packet->credits_requested),
le16_to_cpu(packet->credits_granted),
le32_to_cpu(packet->data_offset),
le32_to_cpu(packet->data_length),
le32_to_cpu(packet->remaining_data_length));
/* Map the packet to DMA */
header_length = sizeof(struct smbd_data_transfer);
/* If this is a packet without payload, don't send padding */
if (!size)
header_length = offsetof(struct smbd_data_transfer, padding);
request->num_sge = 1;
request->sge[0].addr = ib_dma_map_single(info->id->device,
(void *)packet,
header_length,
DMA_BIDIRECTIONAL);
if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) {
mempool_free(request, info->request_mempool);
rc = -EIO;
goto err;
}
request->sge[0].length = header_length;
request->sge[0].lkey = info->pd->local_dma_lkey;
*request_out = request;
return 0;