-
Notifications
You must be signed in to change notification settings - Fork 62
/
ucma.c
1858 lines (1556 loc) · 45 KB
/
ucma.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) 2005-2006 Intel Corporation. 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/completion.h>
#include <linux/file.h>
#include <linux/mutex.h>
#include <linux/poll.h>
#include <linux/sched.h>
#include <linux/idr.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/miscdevice.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
#include <linux/nospec.h>
#include <rdma/rdma_user_cm.h>
#include <rdma/ib_marshall.h>
#include <rdma/rdma_cm.h>
#include <rdma/rdma_cm_ib.h>
#include <rdma/ib_addr.h>
#include <rdma/ib.h>
#include <rdma/rdma_netlink.h>
#include "core_priv.h"
MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access");
MODULE_LICENSE("Dual BSD/GPL");
static unsigned int max_backlog = 1024;
static struct ctl_table_header *ucma_ctl_table_hdr;
static struct ctl_table ucma_ctl_table[] = {
{
.procname = "max_backlog",
.data = &max_backlog,
.maxlen = sizeof max_backlog,
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
struct ucma_file {
struct mutex mut;
struct file *filp;
struct list_head ctx_list;
struct list_head event_list;
wait_queue_head_t poll_wait;
struct workqueue_struct *close_wq;
};
struct ucma_context {
u32 id;
struct completion comp;
atomic_t ref;
int events_reported;
int backlog;
struct ucma_file *file;
struct rdma_cm_id *cm_id;
u64 uid;
struct list_head list;
struct list_head mc_list;
/* mark that device is in process of destroying the internal HW
* resources, protected by the ctx_table lock
*/
int closing;
/* sync between removal event and id destroy, protected by file mut */
int destroying;
struct work_struct close_work;
};
struct ucma_multicast {
struct ucma_context *ctx;
u32 id;
int events_reported;
u64 uid;
u8 join_state;
struct list_head list;
struct sockaddr_storage addr;
};
struct ucma_event {
struct ucma_context *ctx;
struct ucma_multicast *mc;
struct list_head list;
struct rdma_cm_id *cm_id;
struct rdma_ucm_event_resp resp;
struct work_struct close_work;
};
static DEFINE_XARRAY_ALLOC(ctx_table);
static DEFINE_XARRAY_ALLOC(multicast_table);
static const struct file_operations ucma_fops;
static inline struct ucma_context *_ucma_find_context(int id,
struct ucma_file *file)
{
struct ucma_context *ctx;
ctx = xa_load(&ctx_table, id);
if (!ctx)
ctx = ERR_PTR(-ENOENT);
else if (ctx->file != file || !ctx->cm_id)
ctx = ERR_PTR(-EINVAL);
return ctx;
}
static struct ucma_context *ucma_get_ctx(struct ucma_file *file, int id)
{
struct ucma_context *ctx;
xa_lock(&ctx_table);
ctx = _ucma_find_context(id, file);
if (!IS_ERR(ctx)) {
if (ctx->closing)
ctx = ERR_PTR(-EIO);
else
atomic_inc(&ctx->ref);
}
xa_unlock(&ctx_table);
return ctx;
}
static void ucma_put_ctx(struct ucma_context *ctx)
{
if (atomic_dec_and_test(&ctx->ref))
complete(&ctx->comp);
}
/*
* Same as ucm_get_ctx but requires that ->cm_id->device is valid, eg that the
* CM_ID is bound.
*/
static struct ucma_context *ucma_get_ctx_dev(struct ucma_file *file, int id)
{
struct ucma_context *ctx = ucma_get_ctx(file, id);
if (IS_ERR(ctx))
return ctx;
if (!ctx->cm_id->device) {
ucma_put_ctx(ctx);
return ERR_PTR(-EINVAL);
}
return ctx;
}
static void ucma_close_event_id(struct work_struct *work)
{
struct ucma_event *uevent_close = container_of(work, struct ucma_event, close_work);
rdma_destroy_id(uevent_close->cm_id);
kfree(uevent_close);
}
static void ucma_close_id(struct work_struct *work)
{
struct ucma_context *ctx = container_of(work, struct ucma_context, close_work);
/* once all inflight tasks are finished, we close all underlying
* resources. The context is still alive till its explicit destryoing
* by its creator.
*/
ucma_put_ctx(ctx);
wait_for_completion(&ctx->comp);
/* No new events will be generated after destroying the id. */
rdma_destroy_id(ctx->cm_id);
}
static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
{
struct ucma_context *ctx;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return NULL;
INIT_WORK(&ctx->close_work, ucma_close_id);
atomic_set(&ctx->ref, 1);
init_completion(&ctx->comp);
INIT_LIST_HEAD(&ctx->mc_list);
ctx->file = file;
if (xa_alloc(&ctx_table, &ctx->id, ctx, xa_limit_32b, GFP_KERNEL))
goto error;
list_add_tail(&ctx->list, &file->ctx_list);
return ctx;
error:
kfree(ctx);
return NULL;
}
static struct ucma_multicast* ucma_alloc_multicast(struct ucma_context *ctx)
{
struct ucma_multicast *mc;
mc = kzalloc(sizeof(*mc), GFP_KERNEL);
if (!mc)
return NULL;
mc->ctx = ctx;
if (xa_alloc(&multicast_table, &mc->id, NULL, xa_limit_32b, GFP_KERNEL))
goto error;
list_add_tail(&mc->list, &ctx->mc_list);
return mc;
error:
kfree(mc);
return NULL;
}
static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst,
struct rdma_conn_param *src)
{
if (src->private_data_len)
memcpy(dst->private_data, src->private_data,
src->private_data_len);
dst->private_data_len = src->private_data_len;
dst->responder_resources =src->responder_resources;
dst->initiator_depth = src->initiator_depth;
dst->flow_control = src->flow_control;
dst->retry_count = src->retry_count;
dst->rnr_retry_count = src->rnr_retry_count;
dst->srq = src->srq;
dst->qp_num = src->qp_num;
}
static void ucma_copy_ud_event(struct ib_device *device,
struct rdma_ucm_ud_param *dst,
struct rdma_ud_param *src)
{
if (src->private_data_len)
memcpy(dst->private_data, src->private_data,
src->private_data_len);
dst->private_data_len = src->private_data_len;
ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
dst->qp_num = src->qp_num;
dst->qkey = src->qkey;
}
static void ucma_set_event_context(struct ucma_context *ctx,
struct rdma_cm_event *event,
struct ucma_event *uevent)
{
uevent->ctx = ctx;
switch (event->event) {
case RDMA_CM_EVENT_MULTICAST_JOIN:
case RDMA_CM_EVENT_MULTICAST_ERROR:
uevent->mc = (struct ucma_multicast *)
event->param.ud.private_data;
uevent->resp.uid = uevent->mc->uid;
uevent->resp.id = uevent->mc->id;
break;
default:
uevent->resp.uid = ctx->uid;
uevent->resp.id = ctx->id;
break;
}
}
/* Called with file->mut locked for the relevant context. */
static void ucma_removal_event_handler(struct rdma_cm_id *cm_id)
{
struct ucma_context *ctx = cm_id->context;
struct ucma_event *con_req_eve;
int event_found = 0;
if (ctx->destroying)
return;
/* only if context is pointing to cm_id that it owns it and can be
* queued to be closed, otherwise that cm_id is an inflight one that
* is part of that context event list pending to be detached and
* reattached to its new context as part of ucma_get_event,
* handled separately below.
*/
if (ctx->cm_id == cm_id) {
xa_lock(&ctx_table);
ctx->closing = 1;
xa_unlock(&ctx_table);
queue_work(ctx->file->close_wq, &ctx->close_work);
return;
}
list_for_each_entry(con_req_eve, &ctx->file->event_list, list) {
if (con_req_eve->cm_id == cm_id &&
con_req_eve->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST) {
list_del(&con_req_eve->list);
INIT_WORK(&con_req_eve->close_work, ucma_close_event_id);
queue_work(ctx->file->close_wq, &con_req_eve->close_work);
event_found = 1;
break;
}
}
if (!event_found)
pr_err("ucma_removal_event_handler: warning: connect request event wasn't found\n");
}
static int ucma_event_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
struct ucma_event *uevent;
struct ucma_context *ctx = cm_id->context;
int ret = 0;
uevent = kzalloc(sizeof(*uevent), GFP_KERNEL);
if (!uevent)
return event->event == RDMA_CM_EVENT_CONNECT_REQUEST;
mutex_lock(&ctx->file->mut);
uevent->cm_id = cm_id;
ucma_set_event_context(ctx, event, uevent);
uevent->resp.event = event->event;
uevent->resp.status = event->status;
if (cm_id->qp_type == IB_QPT_UD)
ucma_copy_ud_event(cm_id->device, &uevent->resp.param.ud,
&event->param.ud);
else
ucma_copy_conn_event(&uevent->resp.param.conn,
&event->param.conn);
if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST) {
if (!ctx->backlog) {
ret = -ENOMEM;
kfree(uevent);
goto out;
}
ctx->backlog--;
} else if (!ctx->uid || ctx->cm_id != cm_id) {
/*
* We ignore events for new connections until userspace has set
* their context. This can only happen if an error occurs on a
* new connection before the user accepts it. This is okay,
* since the accept will just fail later. However, we do need
* to release the underlying HW resources in case of a device
* removal event.
*/
if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL)
ucma_removal_event_handler(cm_id);
kfree(uevent);
goto out;
}
list_add_tail(&uevent->list, &ctx->file->event_list);
wake_up_interruptible(&ctx->file->poll_wait);
if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL)
ucma_removal_event_handler(cm_id);
out:
mutex_unlock(&ctx->file->mut);
return ret;
}
static ssize_t ucma_get_event(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
struct ucma_context *ctx;
struct rdma_ucm_get_event cmd;
struct ucma_event *uevent;
int ret = 0;
/*
* Old 32 bit user space does not send the 4 byte padding in the
* reserved field. We don't care, allow it to keep working.
*/
if (out_len < sizeof(uevent->resp) - sizeof(uevent->resp.reserved))
return -ENOSPC;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
mutex_lock(&file->mut);
while (list_empty(&file->event_list)) {
mutex_unlock(&file->mut);
if (file->filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible(file->poll_wait,
!list_empty(&file->event_list)))
return -ERESTARTSYS;
mutex_lock(&file->mut);
}
uevent = list_entry(file->event_list.next, struct ucma_event, list);
if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST) {
ctx = ucma_alloc_ctx(file);
if (!ctx) {
ret = -ENOMEM;
goto done;
}
uevent->ctx->backlog++;
ctx->cm_id = uevent->cm_id;
ctx->cm_id->context = ctx;
uevent->resp.id = ctx->id;
}
if (copy_to_user(u64_to_user_ptr(cmd.response),
&uevent->resp,
min_t(size_t, out_len, sizeof(uevent->resp)))) {
ret = -EFAULT;
goto done;
}
list_del(&uevent->list);
uevent->ctx->events_reported++;
if (uevent->mc)
uevent->mc->events_reported++;
kfree(uevent);
done:
mutex_unlock(&file->mut);
return ret;
}
static int ucma_get_qp_type(struct rdma_ucm_create_id *cmd, enum ib_qp_type *qp_type)
{
switch (cmd->ps) {
case RDMA_PS_TCP:
*qp_type = IB_QPT_RC;
return 0;
case RDMA_PS_UDP:
case RDMA_PS_IPOIB:
*qp_type = IB_QPT_UD;
return 0;
case RDMA_PS_IB:
*qp_type = cmd->qp_type;
return 0;
default:
return -EINVAL;
}
}
static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_create_id cmd;
struct rdma_ucm_create_id_resp resp;
struct ucma_context *ctx;
struct rdma_cm_id *cm_id;
enum ib_qp_type qp_type;
int ret;
if (out_len < sizeof(resp))
return -ENOSPC;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
ret = ucma_get_qp_type(&cmd, &qp_type);
if (ret)
return ret;
mutex_lock(&file->mut);
ctx = ucma_alloc_ctx(file);
mutex_unlock(&file->mut);
if (!ctx)
return -ENOMEM;
ctx->uid = cmd.uid;
cm_id = __rdma_create_id(current->nsproxy->net_ns,
ucma_event_handler, ctx, cmd.ps, qp_type, NULL);
if (IS_ERR(cm_id)) {
ret = PTR_ERR(cm_id);
goto err1;
}
resp.id = ctx->id;
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp))) {
ret = -EFAULT;
goto err2;
}
ctx->cm_id = cm_id;
return 0;
err2:
rdma_destroy_id(cm_id);
err1:
xa_erase(&ctx_table, ctx->id);
mutex_lock(&file->mut);
list_del(&ctx->list);
mutex_unlock(&file->mut);
kfree(ctx);
return ret;
}
static void ucma_cleanup_multicast(struct ucma_context *ctx)
{
struct ucma_multicast *mc, *tmp;
mutex_lock(&ctx->file->mut);
list_for_each_entry_safe(mc, tmp, &ctx->mc_list, list) {
list_del(&mc->list);
xa_erase(&multicast_table, mc->id);
kfree(mc);
}
mutex_unlock(&ctx->file->mut);
}
static void ucma_cleanup_mc_events(struct ucma_multicast *mc)
{
struct ucma_event *uevent, *tmp;
list_for_each_entry_safe(uevent, tmp, &mc->ctx->file->event_list, list) {
if (uevent->mc != mc)
continue;
list_del(&uevent->list);
kfree(uevent);
}
}
/*
* ucma_free_ctx is called after the underlying rdma CM-ID is destroyed. At
* this point, no new events will be reported from the hardware. However, we
* still need to cleanup the UCMA context for this ID. Specifically, there
* might be events that have not yet been consumed by the user space software.
* These might include pending connect requests which we have not completed
* processing. We cannot call rdma_destroy_id while holding the lock of the
* context (file->mut), as it might cause a deadlock. We therefore extract all
* relevant events from the context pending events list while holding the
* mutex. After that we release them as needed.
*/
static int ucma_free_ctx(struct ucma_context *ctx)
{
int events_reported;
struct ucma_event *uevent, *tmp;
LIST_HEAD(list);
ucma_cleanup_multicast(ctx);
/* Cleanup events not yet reported to the user. */
mutex_lock(&ctx->file->mut);
list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) {
if (uevent->ctx == ctx)
list_move_tail(&uevent->list, &list);
}
list_del(&ctx->list);
mutex_unlock(&ctx->file->mut);
list_for_each_entry_safe(uevent, tmp, &list, list) {
list_del(&uevent->list);
if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST)
rdma_destroy_id(uevent->cm_id);
kfree(uevent);
}
events_reported = ctx->events_reported;
kfree(ctx);
return events_reported;
}
static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_destroy_id cmd;
struct rdma_ucm_destroy_id_resp resp;
struct ucma_context *ctx;
int ret = 0;
if (out_len < sizeof(resp))
return -ENOSPC;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
xa_lock(&ctx_table);
ctx = _ucma_find_context(cmd.id, file);
if (!IS_ERR(ctx))
__xa_erase(&ctx_table, ctx->id);
xa_unlock(&ctx_table);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
mutex_lock(&ctx->file->mut);
ctx->destroying = 1;
mutex_unlock(&ctx->file->mut);
flush_workqueue(ctx->file->close_wq);
/* At this point it's guaranteed that there is no inflight
* closing task */
xa_lock(&ctx_table);
if (!ctx->closing) {
xa_unlock(&ctx_table);
ucma_put_ctx(ctx);
wait_for_completion(&ctx->comp);
rdma_destroy_id(ctx->cm_id);
} else {
xa_unlock(&ctx_table);
}
resp.events_reported = ucma_free_ctx(ctx);
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp)))
ret = -EFAULT;
return ret;
}
static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_bind_ip cmd;
struct ucma_context *ctx;
int ret;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
if (!rdma_addr_size_in6(&cmd.addr))
return -EINVAL;
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr);
ucma_put_ctx(ctx);
return ret;
}
static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_bind cmd;
struct ucma_context *ctx;
int ret;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
if (cmd.reserved || !cmd.addr_size ||
cmd.addr_size != rdma_addr_size_kss(&cmd.addr))
return -EINVAL;
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr);
ucma_put_ctx(ctx);
return ret;
}
static ssize_t ucma_resolve_ip(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_resolve_ip cmd;
struct ucma_context *ctx;
int ret;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
if ((cmd.src_addr.sin6_family && !rdma_addr_size_in6(&cmd.src_addr)) ||
!rdma_addr_size_in6(&cmd.dst_addr))
return -EINVAL;
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr,
(struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms);
ucma_put_ctx(ctx);
return ret;
}
static ssize_t ucma_resolve_addr(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_resolve_addr cmd;
struct ucma_context *ctx;
int ret;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
if (cmd.reserved ||
(cmd.src_size && (cmd.src_size != rdma_addr_size_kss(&cmd.src_addr))) ||
!cmd.dst_size || (cmd.dst_size != rdma_addr_size_kss(&cmd.dst_addr)))
return -EINVAL;
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr,
(struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms);
ucma_put_ctx(ctx);
return ret;
}
static ssize_t ucma_resolve_route(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_resolve_route cmd;
struct ucma_context *ctx;
int ret;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms);
ucma_put_ctx(ctx);
return ret;
}
static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
struct rdma_route *route)
{
struct rdma_dev_addr *dev_addr;
resp->num_paths = route->num_paths;
switch (route->num_paths) {
case 0:
dev_addr = &route->addr.dev_addr;
rdma_addr_get_dgid(dev_addr,
(union ib_gid *) &resp->ib_route[0].dgid);
rdma_addr_get_sgid(dev_addr,
(union ib_gid *) &resp->ib_route[0].sgid);
resp->ib_route[0].pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr));
break;
case 2:
ib_copy_path_rec_to_user(&resp->ib_route[1],
&route->path_rec[1]);
/* fall through */
case 1:
ib_copy_path_rec_to_user(&resp->ib_route[0],
&route->path_rec[0]);
break;
default:
break;
}
}
static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
struct rdma_route *route)
{
resp->num_paths = route->num_paths;
switch (route->num_paths) {
case 0:
rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
(union ib_gid *)&resp->ib_route[0].dgid);
rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
(union ib_gid *)&resp->ib_route[0].sgid);
resp->ib_route[0].pkey = cpu_to_be16(0xffff);
break;
case 2:
ib_copy_path_rec_to_user(&resp->ib_route[1],
&route->path_rec[1]);
/* fall through */
case 1:
ib_copy_path_rec_to_user(&resp->ib_route[0],
&route->path_rec[0]);
break;
default:
break;
}
}
static void ucma_copy_iw_route(struct rdma_ucm_query_route_resp *resp,
struct rdma_route *route)
{
struct rdma_dev_addr *dev_addr;
dev_addr = &route->addr.dev_addr;
rdma_addr_get_dgid(dev_addr, (union ib_gid *) &resp->ib_route[0].dgid);
rdma_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid);
}
static ssize_t ucma_query_route(struct ucma_file *file,
const char __user *inbuf,
int in_len, int out_len)
{
struct rdma_ucm_query cmd;
struct rdma_ucm_query_route_resp resp;
struct ucma_context *ctx;
struct sockaddr *addr;
int ret = 0;
if (out_len < sizeof(resp))
return -ENOSPC;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
memset(&resp, 0, sizeof resp);
addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr;
memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ?
sizeof(struct sockaddr_in) :
sizeof(struct sockaddr_in6));
addr = (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr;
memcpy(&resp.dst_addr, addr, addr->sa_family == AF_INET ?
sizeof(struct sockaddr_in) :
sizeof(struct sockaddr_in6));
if (!ctx->cm_id->device)
goto out;
resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid;
resp.port_num = ctx->cm_id->port_num;
if (rdma_cap_ib_sa(ctx->cm_id->device, ctx->cm_id->port_num))
ucma_copy_ib_route(&resp, &ctx->cm_id->route);
else if (rdma_protocol_roce(ctx->cm_id->device, ctx->cm_id->port_num))
ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
else if (rdma_protocol_iwarp(ctx->cm_id->device, ctx->cm_id->port_num))
ucma_copy_iw_route(&resp, &ctx->cm_id->route);
out:
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp)))
ret = -EFAULT;
ucma_put_ctx(ctx);
return ret;
}
static void ucma_query_device_addr(struct rdma_cm_id *cm_id,
struct rdma_ucm_query_addr_resp *resp)
{
if (!cm_id->device)
return;
resp->node_guid = (__force __u64) cm_id->device->node_guid;
resp->port_num = cm_id->port_num;
resp->pkey = (__force __u16) cpu_to_be16(
ib_addr_get_pkey(&cm_id->route.addr.dev_addr));
}
static ssize_t ucma_query_addr(struct ucma_context *ctx,
void __user *response, int out_len)
{
struct rdma_ucm_query_addr_resp resp;
struct sockaddr *addr;
int ret = 0;
if (out_len < sizeof(resp))
return -ENOSPC;
memset(&resp, 0, sizeof resp);
addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr;
resp.src_size = rdma_addr_size(addr);
memcpy(&resp.src_addr, addr, resp.src_size);
addr = (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr;
resp.dst_size = rdma_addr_size(addr);
memcpy(&resp.dst_addr, addr, resp.dst_size);
ucma_query_device_addr(ctx->cm_id, &resp);
if (copy_to_user(response, &resp, sizeof(resp)))
ret = -EFAULT;
return ret;
}
static ssize_t ucma_query_path(struct ucma_context *ctx,
void __user *response, int out_len)
{
struct rdma_ucm_query_path_resp *resp;
int i, ret = 0;
if (out_len < sizeof(*resp))
return -ENOSPC;
resp = kzalloc(out_len, GFP_KERNEL);
if (!resp)
return -ENOMEM;
resp->num_paths = ctx->cm_id->route.num_paths;
for (i = 0, out_len -= sizeof(*resp);
i < resp->num_paths && out_len > sizeof(struct ib_path_rec_data);
i++, out_len -= sizeof(struct ib_path_rec_data)) {
struct sa_path_rec *rec = &ctx->cm_id->route.path_rec[i];
resp->path_data[i].flags = IB_PATH_GMP | IB_PATH_PRIMARY |
IB_PATH_BIDIRECTIONAL;
if (rec->rec_type == SA_PATH_REC_TYPE_OPA) {
struct sa_path_rec ib;
sa_convert_path_opa_to_ib(&ib, rec);
ib_sa_pack_path(&ib, &resp->path_data[i].path_rec);
} else {
ib_sa_pack_path(rec, &resp->path_data[i].path_rec);
}
}
if (copy_to_user(response, resp, struct_size(resp, path_data, i)))
ret = -EFAULT;
kfree(resp);
return ret;
}
static ssize_t ucma_query_gid(struct ucma_context *ctx,
void __user *response, int out_len)
{
struct rdma_ucm_query_addr_resp resp;
struct sockaddr_ib *addr;
int ret = 0;
if (out_len < sizeof(resp))
return -ENOSPC;
memset(&resp, 0, sizeof resp);
ucma_query_device_addr(ctx->cm_id, &resp);
addr = (struct sockaddr_ib *) &resp.src_addr;
resp.src_size = sizeof(*addr);
if (ctx->cm_id->route.addr.src_addr.ss_family == AF_IB) {
memcpy(addr, &ctx->cm_id->route.addr.src_addr, resp.src_size);
} else {
addr->sib_family = AF_IB;
addr->sib_pkey = (__force __be16) resp.pkey;
rdma_read_gids(ctx->cm_id, (union ib_gid *)&addr->sib_addr,
NULL);
addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *)
&ctx->cm_id->route.addr.src_addr);
}
addr = (struct sockaddr_ib *) &resp.dst_addr;
resp.dst_size = sizeof(*addr);
if (ctx->cm_id->route.addr.dst_addr.ss_family == AF_IB) {
memcpy(addr, &ctx->cm_id->route.addr.dst_addr, resp.dst_size);
} else {
addr->sib_family = AF_IB;
addr->sib_pkey = (__force __be16) resp.pkey;
rdma_read_gids(ctx->cm_id, NULL,
(union ib_gid *)&addr->sib_addr);
addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *)
&ctx->cm_id->route.addr.dst_addr);
}
if (copy_to_user(response, &resp, sizeof(resp)))
ret = -EFAULT;
return ret;
}
static ssize_t ucma_query(struct ucma_file *file,