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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
|
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies. All rights reserved.
* Copyright (c) 2005 Voltaire, Inc. All rights reserved.
* Copyright (c) 2005 PathScale, Inc. 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/init.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/sched.h>
#include <linux/file.h>
#include <linux/cdev.h>
#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <rdma/ib.h>
#include <rdma/uverbs_std_types.h>
#include "uverbs.h"
#include "core_priv.h"
#include "rdma_core.h"
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("InfiniBand userspace verbs access");
MODULE_LICENSE("Dual BSD/GPL");
enum {
IB_UVERBS_MAJOR = 231,
IB_UVERBS_BASE_MINOR = 192,
IB_UVERBS_MAX_DEVICES = RDMA_MAX_PORTS,
IB_UVERBS_NUM_FIXED_MINOR = 32,
IB_UVERBS_NUM_DYNAMIC_MINOR = IB_UVERBS_MAX_DEVICES - IB_UVERBS_NUM_FIXED_MINOR,
};
#define IB_UVERBS_BASE_DEV MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR)
static dev_t dynamic_uverbs_dev;
static struct class *uverbs_class;
static DECLARE_BITMAP(dev_map, IB_UVERBS_MAX_DEVICES);
static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len) = {
[IB_USER_VERBS_CMD_GET_CONTEXT] = ib_uverbs_get_context,
[IB_USER_VERBS_CMD_QUERY_DEVICE] = ib_uverbs_query_device,
[IB_USER_VERBS_CMD_QUERY_PORT] = ib_uverbs_query_port,
[IB_USER_VERBS_CMD_ALLOC_PD] = ib_uverbs_alloc_pd,
[IB_USER_VERBS_CMD_DEALLOC_PD] = ib_uverbs_dealloc_pd,
[IB_USER_VERBS_CMD_REG_MR] = ib_uverbs_reg_mr,
[IB_USER_VERBS_CMD_REREG_MR] = ib_uverbs_rereg_mr,
[IB_USER_VERBS_CMD_DEREG_MR] = ib_uverbs_dereg_mr,
[IB_USER_VERBS_CMD_ALLOC_MW] = ib_uverbs_alloc_mw,
[IB_USER_VERBS_CMD_DEALLOC_MW] = ib_uverbs_dealloc_mw,
[IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL] = ib_uverbs_create_comp_channel,
[IB_USER_VERBS_CMD_CREATE_CQ] = ib_uverbs_create_cq,
[IB_USER_VERBS_CMD_RESIZE_CQ] = ib_uverbs_resize_cq,
[IB_USER_VERBS_CMD_POLL_CQ] = ib_uverbs_poll_cq,
[IB_USER_VERBS_CMD_REQ_NOTIFY_CQ] = ib_uverbs_req_notify_cq,
[IB_USER_VERBS_CMD_DESTROY_CQ] = ib_uverbs_destroy_cq,
[IB_USER_VERBS_CMD_CREATE_QP] = ib_uverbs_create_qp,
[IB_USER_VERBS_CMD_QUERY_QP] = ib_uverbs_query_qp,
[IB_USER_VERBS_CMD_MODIFY_QP] = ib_uverbs_modify_qp,
[IB_USER_VERBS_CMD_DESTROY_QP] = ib_uverbs_destroy_qp,
[IB_USER_VERBS_CMD_POST_SEND] = ib_uverbs_post_send,
[IB_USER_VERBS_CMD_POST_RECV] = ib_uverbs_post_recv,
[IB_USER_VERBS_CMD_POST_SRQ_RECV] = ib_uverbs_post_srq_recv,
[IB_USER_VERBS_CMD_CREATE_AH] = ib_uverbs_create_ah,
[IB_USER_VERBS_CMD_DESTROY_AH] = ib_uverbs_destroy_ah,
[IB_USER_VERBS_CMD_ATTACH_MCAST] = ib_uverbs_attach_mcast,
[IB_USER_VERBS_CMD_DETACH_MCAST] = ib_uverbs_detach_mcast,
[IB_USER_VERBS_CMD_CREATE_SRQ] = ib_uverbs_create_srq,
[IB_USER_VERBS_CMD_MODIFY_SRQ] = ib_uverbs_modify_srq,
[IB_USER_VERBS_CMD_QUERY_SRQ] = ib_uverbs_query_srq,
[IB_USER_VERBS_CMD_DESTROY_SRQ] = ib_uverbs_destroy_srq,
[IB_USER_VERBS_CMD_OPEN_XRCD] = ib_uverbs_open_xrcd,
[IB_USER_VERBS_CMD_CLOSE_XRCD] = ib_uverbs_close_xrcd,
[IB_USER_VERBS_CMD_CREATE_XSRQ] = ib_uverbs_create_xsrq,
[IB_USER_VERBS_CMD_OPEN_QP] = ib_uverbs_open_qp,
};
static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
struct ib_udata *ucore,
struct ib_udata *uhw) = {
[IB_USER_VERBS_EX_CMD_CREATE_FLOW] = ib_uverbs_ex_create_flow,
[IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow,
[IB_USER_VERBS_EX_CMD_QUERY_DEVICE] = ib_uverbs_ex_query_device,
[IB_USER_VERBS_EX_CMD_CREATE_CQ] = ib_uverbs_ex_create_cq,
[IB_USER_VERBS_EX_CMD_CREATE_QP] = ib_uverbs_ex_create_qp,
[IB_USER_VERBS_EX_CMD_CREATE_WQ] = ib_uverbs_ex_create_wq,
[IB_USER_VERBS_EX_CMD_MODIFY_WQ] = ib_uverbs_ex_modify_wq,
[IB_USER_VERBS_EX_CMD_DESTROY_WQ] = ib_uverbs_ex_destroy_wq,
[IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL] = ib_uverbs_ex_create_rwq_ind_table,
[IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL] = ib_uverbs_ex_destroy_rwq_ind_table,
[IB_USER_VERBS_EX_CMD_MODIFY_QP] = ib_uverbs_ex_modify_qp,
[IB_USER_VERBS_EX_CMD_MODIFY_CQ] = ib_uverbs_ex_modify_cq,
};
static void ib_uverbs_add_one(struct ib_device *device);
static void ib_uverbs_remove_one(struct ib_device *device, void *client_data);
/*
* Must be called with the ufile->device->disassociate_srcu held, and the lock
* must be held until use of the ucontext is finished.
*/
struct ib_ucontext *ib_uverbs_get_ucontext(struct ib_uverbs_file *ufile)
{
/*
* We do not hold the hw_destroy_rwsem lock for this flow, instead
* srcu is used. It does not matter if someone races this with
* get_context, we get NULL or valid ucontext.
*/
struct ib_ucontext *ucontext = smp_load_acquire(&ufile->ucontext);
if (!srcu_dereference(ufile->device->ib_dev,
&ufile->device->disassociate_srcu))
return ERR_PTR(-EIO);
if (!ucontext)
return ERR_PTR(-EINVAL);
return ucontext;
}
EXPORT_SYMBOL(ib_uverbs_get_ucontext);
int uverbs_dealloc_mw(struct ib_mw *mw)
{
struct ib_pd *pd = mw->pd;
int ret;
ret = mw->device->dealloc_mw(mw);
if (!ret)
atomic_dec(&pd->usecnt);
return ret;
}
static void ib_uverbs_release_dev(struct device *device)
{
struct ib_uverbs_device *dev =
container_of(device, struct ib_uverbs_device, dev);
uverbs_destroy_api(dev->uapi);
cleanup_srcu_struct(&dev->disassociate_srcu);
kfree(dev);
}
static void ib_uverbs_release_async_event_file(struct kref *ref)
{
struct ib_uverbs_async_event_file *file =
container_of(ref, struct ib_uverbs_async_event_file, ref);
kfree(file);
}
void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
struct ib_uverbs_completion_event_file *ev_file,
struct ib_ucq_object *uobj)
{
struct ib_uverbs_event *evt, *tmp;
if (ev_file) {
spin_lock_irq(&ev_file->ev_queue.lock);
list_for_each_entry_safe(evt, tmp, &uobj->comp_list, obj_list) {
list_del(&evt->list);
kfree(evt);
}
spin_unlock_irq(&ev_file->ev_queue.lock);
uverbs_uobject_put(&ev_file->uobj);
}
spin_lock_irq(&file->async_file->ev_queue.lock);
list_for_each_entry_safe(evt, tmp, &uobj->async_list, obj_list) {
list_del(&evt->list);
kfree(evt);
}
spin_unlock_irq(&file->async_file->ev_queue.lock);
}
void ib_uverbs_release_uevent(struct ib_uverbs_file *file,
struct ib_uevent_object *uobj)
{
struct ib_uverbs_event *evt, *tmp;
spin_lock_irq(&file->async_file->ev_queue.lock);
list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) {
list_del(&evt->list);
kfree(evt);
}
spin_unlock_irq(&file->async_file->ev_queue.lock);
}
void ib_uverbs_detach_umcast(struct ib_qp *qp,
struct ib_uqp_object *uobj)
{
struct ib_uverbs_mcast_entry *mcast, *tmp;
list_for_each_entry_safe(mcast, tmp, &uobj->mcast_list, list) {
ib_detach_mcast(qp, &mcast->gid, mcast->lid);
list_del(&mcast->list);
kfree(mcast);
}
}
static void ib_uverbs_comp_dev(struct ib_uverbs_device *dev)
{
complete(&dev->comp);
}
void ib_uverbs_release_file(struct kref *ref)
{
struct ib_uverbs_file *file =
container_of(ref, struct ib_uverbs_file, ref);
struct ib_device *ib_dev;
int srcu_key;
release_ufile_idr_uobject(file);
srcu_key = srcu_read_lock(&file->device->disassociate_srcu);
ib_dev = srcu_dereference(file->device->ib_dev,
&file->device->disassociate_srcu);
if (ib_dev && !ib_dev->disassociate_ucontext)
module_put(ib_dev->owner);
srcu_read_unlock(&file->device->disassociate_srcu, srcu_key);
if (atomic_dec_and_test(&file->device->refcount))
ib_uverbs_comp_dev(file->device);
put_device(&file->device->dev);
kfree(file);
}
static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue,
struct ib_uverbs_file *uverbs_file,
struct file *filp, char __user *buf,
size_t count, loff_t *pos,
size_t eventsz)
{
struct ib_uverbs_event *event;
int ret = 0;
spin_lock_irq(&ev_queue->lock);
while (list_empty(&ev_queue->event_list)) {
spin_unlock_irq(&ev_queue->lock);
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
if (wait_event_interruptible(ev_queue->poll_wait,
(!list_empty(&ev_queue->event_list) ||
/* The barriers built into wait_event_interruptible()
* and wake_up() guarentee this will see the null set
* without using RCU
*/
!uverbs_file->device->ib_dev)))
return -ERESTARTSYS;
/* If device was disassociated and no event exists set an error */
if (list_empty(&ev_queue->event_list) &&
!uverbs_file->device->ib_dev)
return -EIO;
spin_lock_irq(&ev_queue->lock);
}
event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list);
if (eventsz > count) {
ret = -EINVAL;
event = NULL;
} else {
list_del(ev_queue->event_list.next);
if (event->counter) {
++(*event->counter);
list_del(&event->obj_list);
}
}
spin_unlock_irq(&ev_queue->lock);
if (event) {
if (copy_to_user(buf, event, eventsz))
ret = -EFAULT;
else
ret = eventsz;
}
kfree(event);
return ret;
}
static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf,
size_t count, loff_t *pos)
{
struct ib_uverbs_async_event_file *file = filp->private_data;
return ib_uverbs_event_read(&file->ev_queue, file->uverbs_file, filp,
buf, count, pos,
sizeof(struct ib_uverbs_async_event_desc));
}
static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf,
size_t count, loff_t *pos)
{
struct ib_uverbs_completion_event_file *comp_ev_file =
filp->private_data;
return ib_uverbs_event_read(&comp_ev_file->ev_queue,
comp_ev_file->uobj.ufile, filp,
buf, count, pos,
sizeof(struct ib_uverbs_comp_event_desc));
}
static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue,
struct file *filp,
struct poll_table_struct *wait)
{
__poll_t pollflags = 0;
poll_wait(filp, &ev_queue->poll_wait, wait);
spin_lock_irq(&ev_queue->lock);
if (!list_empty(&ev_queue->event_list))
pollflags = EPOLLIN | EPOLLRDNORM;
spin_unlock_irq(&ev_queue->lock);
return pollflags;
}
static __poll_t ib_uverbs_async_event_poll(struct file *filp,
struct poll_table_struct *wait)
{
return ib_uverbs_event_poll(filp->private_data, filp, wait);
}
static __poll_t ib_uverbs_comp_event_poll(struct file *filp,
struct poll_table_struct *wait)
{
struct ib_uverbs_completion_event_file *comp_ev_file =
filp->private_data;
return ib_uverbs_event_poll(&comp_ev_file->ev_queue, filp, wait);
}
static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on)
{
struct ib_uverbs_event_queue *ev_queue = filp->private_data;
return fasync_helper(fd, filp, on, &ev_queue->async_queue);
}
static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on)
{
struct ib_uverbs_completion_event_file *comp_ev_file =
filp->private_data;
return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue);
}
static int ib_uverbs_async_event_close(struct inode *inode, struct file *filp)
{
struct ib_uverbs_async_event_file *file = filp->private_data;
struct ib_uverbs_file *uverbs_file = file->uverbs_file;
struct ib_uverbs_event *entry, *tmp;
int closed_already = 0;
mutex_lock(&uverbs_file->device->lists_mutex);
spin_lock_irq(&file->ev_queue.lock);
closed_already = file->ev_queue.is_closed;
file->ev_queue.is_closed = 1;
list_for_each_entry_safe(entry, tmp, &file->ev_queue.event_list, list) {
if (entry->counter)
list_del(&entry->obj_list);
kfree(entry);
}
spin_unlock_irq(&file->ev_queue.lock);
if (!closed_already) {
list_del(&file->list);
ib_unregister_event_handler(&uverbs_file->event_handler);
}
mutex_unlock(&uverbs_file->device->lists_mutex);
kref_put(&uverbs_file->ref, ib_uverbs_release_file);
kref_put(&file->ref, ib_uverbs_release_async_event_file);
return 0;
}
static int ib_uverbs_comp_event_close(struct inode *inode, struct file *filp)
{
struct ib_uobject *uobj = filp->private_data;
struct ib_uverbs_completion_event_file *file = container_of(
uobj, struct ib_uverbs_completion_event_file, uobj);
struct ib_uverbs_event *entry, *tmp;
spin_lock_irq(&file->ev_queue.lock);
list_for_each_entry_safe(entry, tmp, &file->ev_queue.event_list, list) {
if (entry->counter)
list_del(&entry->obj_list);
kfree(entry);
}
file->ev_queue.is_closed = 1;
spin_unlock_irq(&file->ev_queue.lock);
uverbs_close_fd(filp);
return 0;
}
const struct file_operations uverbs_event_fops = {
.owner = THIS_MODULE,
.read = ib_uverbs_comp_event_read,
.poll = ib_uverbs_comp_event_poll,
.release = ib_uverbs_comp_event_close,
.fasync = ib_uverbs_comp_event_fasync,
.llseek = no_llseek,
};
static const struct file_operations uverbs_async_event_fops = {
.owner = THIS_MODULE,
.read = ib_uverbs_async_event_read,
.poll = ib_uverbs_async_event_poll,
.release = ib_uverbs_async_event_close,
.fasync = ib_uverbs_async_event_fasync,
.llseek = no_llseek,
};
void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context)
{
struct ib_uverbs_event_queue *ev_queue = cq_context;
struct ib_ucq_object *uobj;
struct ib_uverbs_event *entry;
unsigned long flags;
if (!ev_queue)
return;
spin_lock_irqsave(&ev_queue->lock, flags);
if (ev_queue->is_closed) {
spin_unlock_irqrestore(&ev_queue->lock, flags);
return;
}
entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry) {
spin_unlock_irqrestore(&ev_queue->lock, flags);
return;
}
uobj = container_of(cq->uobject, struct ib_ucq_object, uobject);
entry->desc.comp.cq_handle = cq->uobject->user_handle;
entry->counter = &uobj->comp_events_reported;
list_add_tail(&entry->list, &ev_queue->event_list);
list_add_tail(&entry->obj_list, &uobj->comp_list);
spin_unlock_irqrestore(&ev_queue->lock, flags);
wake_up_interruptible(&ev_queue->poll_wait);
kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN);
}
static void ib_uverbs_async_handler(struct ib_uverbs_file *file,
__u64 element, __u64 event,
struct list_head *obj_list,
u32 *counter)
{
struct ib_uverbs_event *entry;
unsigned long flags;
spin_lock_irqsave(&file->async_file->ev_queue.lock, flags);
if (file->async_file->ev_queue.is_closed) {
spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
return;
}
entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry) {
spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
return;
}
entry->desc.async.element = element;
entry->desc.async.event_type = event;
entry->desc.async.reserved = 0;
entry->counter = counter;
list_add_tail(&entry->list, &file->async_file->ev_queue.event_list);
if (obj_list)
list_add_tail(&entry->obj_list, obj_list);
spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
wake_up_interruptible(&file->async_file->ev_queue.poll_wait);
kill_fasync(&file->async_file->ev_queue.async_queue, SIGIO, POLL_IN);
}
void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr)
{
struct ib_ucq_object *uobj = container_of(event->element.cq->uobject,
struct ib_ucq_object, uobject);
ib_uverbs_async_handler(uobj->uobject.ufile, uobj->uobject.user_handle,
event->event, &uobj->async_list,
&uobj->async_events_reported);
}
void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr)
{
struct ib_uevent_object *uobj;
/* for XRC target qp's, check that qp is live */
if (!event->element.qp->uobject)
return;
uobj = container_of(event->element.qp->uobject,
struct ib_uevent_object, uobject);
ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
event->event, &uobj->event_list,
&uobj->events_reported);
}
void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr)
{
struct ib_uevent_object *uobj = container_of(event->element.wq->uobject,
struct ib_uevent_object, uobject);
ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
event->event, &uobj->event_list,
&uobj->events_reported);
}
void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr)
{
struct ib_uevent_object *uobj;
uobj = container_of(event->element.srq->uobject,
struct ib_uevent_object, uobject);
ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
event->event, &uobj->event_list,
&uobj->events_reported);
}
void ib_uverbs_event_handler(struct ib_event_handler *handler,
struct ib_event *event)
{
struct ib_uverbs_file *file =
container_of(handler, struct ib_uverbs_file, event_handler);
ib_uverbs_async_handler(file, event->element.port_num, event->event,
NULL, NULL);
}
void ib_uverbs_free_async_event_file(struct ib_uverbs_file *file)
{
kref_put(&file->async_file->ref, ib_uverbs_release_async_event_file);
file->async_file = NULL;
}
void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue)
{
spin_lock_init(&ev_queue->lock);
INIT_LIST_HEAD(&ev_queue->event_list);
init_waitqueue_head(&ev_queue->poll_wait);
ev_queue->is_closed = 0;
ev_queue->async_queue = NULL;
}
struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file,
struct ib_device *ib_dev)
{
struct ib_uverbs_async_event_file *ev_file;
struct file *filp;
ev_file = kzalloc(sizeof(*ev_file), GFP_KERNEL);
if (!ev_file)
return ERR_PTR(-ENOMEM);
ib_uverbs_init_event_queue(&ev_file->ev_queue);
ev_file->uverbs_file = uverbs_file;
kref_get(&ev_file->uverbs_file->ref);
kref_init(&ev_file->ref);
filp = anon_inode_getfile("[infinibandevent]", &uverbs_async_event_fops,
ev_file, O_RDONLY);
if (IS_ERR(filp))
goto err_put_refs;
mutex_lock(&uverbs_file->device->lists_mutex);
list_add_tail(&ev_file->list,
&uverbs_file->device->uverbs_events_file_list);
mutex_unlock(&uverbs_file->device->lists_mutex);
WARN_ON(uverbs_file->async_file);
uverbs_file->async_file = ev_file;
kref_get(&uverbs_file->async_file->ref);
INIT_IB_EVENT_HANDLER(&uverbs_file->event_handler,
ib_dev,
ib_uverbs_event_handler);
ib_register_event_handler(&uverbs_file->event_handler);
/* At that point async file stuff was fully set */
return filp;
err_put_refs:
kref_put(&ev_file->uverbs_file->ref, ib_uverbs_release_file);
kref_put(&ev_file->ref, ib_uverbs_release_async_event_file);
return filp;
}
static bool verify_command_mask(struct ib_uverbs_file *ufile, u32 command,
bool extended)
{
if (!extended)
return ufile->uverbs_cmd_mask & BIT_ULL(command);
return ufile->uverbs_ex_cmd_mask & BIT_ULL(command);
}
static bool verify_command_idx(u32 command, bool extended)
{
if (extended)
return command < ARRAY_SIZE(uverbs_ex_cmd_table) &&
uverbs_ex_cmd_table[command];
return command < ARRAY_SIZE(uverbs_cmd_table) &&
uverbs_cmd_table[command];
}
static ssize_t process_hdr(struct ib_uverbs_cmd_hdr *hdr,
u32 *command, bool *extended)
{
if (hdr->command & ~(u32)(IB_USER_VERBS_CMD_FLAG_EXTENDED |
IB_USER_VERBS_CMD_COMMAND_MASK))
return -EINVAL;
*command = hdr->command & IB_USER_VERBS_CMD_COMMAND_MASK;
*extended = hdr->command & IB_USER_VERBS_CMD_FLAG_EXTENDED;
if (!verify_command_idx(*command, *extended))
return -EOPNOTSUPP;
return 0;
}
static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr,
struct ib_uverbs_ex_cmd_hdr *ex_hdr,
size_t count, bool extended)
{
if (extended) {
count -= sizeof(*hdr) + sizeof(*ex_hdr);
if ((hdr->in_words + ex_hdr->provider_in_words) * 8 != count)
return -EINVAL;
if (ex_hdr->cmd_hdr_reserved)
return -EINVAL;
if (ex_hdr->response) {
if (!hdr->out_words && !ex_hdr->provider_out_words)
return -EINVAL;
if (!access_ok(VERIFY_WRITE,
u64_to_user_ptr(ex_hdr->response),
(hdr->out_words + ex_hdr->provider_out_words) * 8))
return -EFAULT;
} else {
if (hdr->out_words || ex_hdr->provider_out_words)
return -EINVAL;
}
return 0;
}
/* not extended command */
if (hdr->in_words * 4 != count)
return -EINVAL;
return 0;
}
static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
size_t count, loff_t *pos)
{
struct ib_uverbs_file *file = filp->private_data;
struct ib_uverbs_ex_cmd_hdr ex_hdr;
struct ib_uverbs_cmd_hdr hdr;
bool extended;
int srcu_key;
u32 command;
ssize_t ret;
if (!ib_safe_file_access(filp)) {
pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
task_tgid_vnr(current), current->comm);
return -EACCES;
}
if (count < sizeof(hdr))
return -EINVAL;
if (copy_from_user(&hdr, buf, sizeof(hdr)))
return -EFAULT;
ret = process_hdr(&hdr, &command, &extended);
if (ret)
return ret;
if (extended) {
if (count < (sizeof(hdr) + sizeof(ex_hdr)))
return -EINVAL;
if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr)))
return -EFAULT;
}
ret = verify_hdr(&hdr, &ex_hdr, count, extended);
if (ret)
return ret;
srcu_key = srcu_read_lock(&file->device->disassociate_srcu);
if (!verify_command_mask(file, command, extended)) {
ret = -EOPNOTSUPP;
goto out;
}
buf += sizeof(hdr);
if (!extended) {
ret = uverbs_cmd_table[command](file, buf,
hdr.in_words * 4,
hdr.out_words * 4);
} else {
struct ib_udata ucore;
struct ib_udata uhw;
buf += sizeof(ex_hdr);
ib_uverbs_init_udata_buf_or_null(&ucore, buf,
u64_to_user_ptr(ex_hdr.response),
hdr.in_words * 8, hdr.out_words * 8);
ib_uverbs_init_udata_buf_or_null(&uhw,
buf + ucore.inlen,
u64_to_user_ptr(ex_hdr.response) + ucore.outlen,
ex_hdr.provider_in_words * 8,
ex_hdr.provider_out_words * 8);
ret = uverbs_ex_cmd_table[command](file, &ucore, &uhw);
ret = (ret) ? : count;
}
out:
srcu_read_unlock(&file->device->disassociate_srcu, srcu_key);
return ret;
}
static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct ib_uverbs_file *file = filp->private_data;
struct ib_ucontext *ucontext;
int ret = 0;
int srcu_key;
srcu_key = srcu_read_lock(&file->device->disassociate_srcu);
ucontext = ib_uverbs_get_ucontext(file);
if (IS_ERR(ucontext)) {
ret = PTR_ERR(ucontext);
goto out;
}
ret = ucontext->device->mmap(ucontext, vma);
out:
srcu_read_unlock(&file->device->disassociate_srcu, srcu_key);
return ret;
}
/*
* Each time we map IO memory into user space this keeps track of the mapping.
* When the device is hot-unplugged we 'zap' the mmaps in user space to point
* to the zero page and allow the hot unplug to proceed.
*
* This is necessary for cases like PCI physical hot unplug as the actual BAR
* memory may vanish after this and access to it from userspace could MCE.
*
* RDMA drivers supporting disassociation must have their user space designed
* to cope in some way with their IO pages going to the zero page.
*/
struct rdma_umap_priv {
struct vm_area_struct *vma;
struct list_head list;
};
static const struct vm_operations_struct rdma_umap_ops;
static void rdma_umap_priv_init(struct rdma_umap_priv *priv,
struct vm_area_struct *vma)
{
struct ib_uverbs_file *ufile = vma->vm_file->private_data;
priv->vma = vma;
vma->vm_private_data = priv;
vma->vm_ops = &rdma_umap_ops;
mutex_lock(&ufile->umap_lock);
list_add(&priv->list, &ufile->umaps);
mutex_unlock(&ufile->umap_lock);
}
/*
* The VMA has been dup'd, initialize the vm_private_data with a new tracking
* struct
*/
static void rdma_umap_open(struct vm_area_struct *vma)
{
struct ib_uverbs_file *ufile = vma->vm_file->private_data;
struct rdma_umap_priv *opriv = vma->vm_private_data;
struct rdma_umap_priv *priv;
if (!opriv)
return;
/* We are racing with disassociation */
if (!down_read_trylock(&ufile->hw_destroy_rwsem))
goto out_zap;
/*
* Disassociation already completed, the VMA should already be zapped.
*/
if (!ufile->ucontext)
goto out_unlock;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
goto out_unlock;
rdma_umap_priv_init(priv, vma);
up_read(&ufile->hw_destroy_rwsem);
return;
out_unlock:
up_read(&ufile->hw_destroy_rwsem);
out_zap:
/*
* We can't allow the VMA to be created with the actual IO pages, that
* would break our API contract, and it can't be stopped at this
* point, so zap it.
*/
vma->vm_private_data = NULL;
zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
}
static void rdma_umap_close(struct vm_area_struct *vma)
{
struct ib_uverbs_file *ufile = vma->vm_file->private_data;
struct rdma_umap_priv *priv = vma->vm_private_data;
if (!priv)
return;
/*
* The vma holds a reference on the struct file that created it, which
* in turn means that the ib_uverbs_file is guaranteed to exist at
* this point.
*/
mutex_lock(&ufile->umap_lock);
list_del(&priv->list);
mutex_unlock(&ufile->umap_lock);
kfree(priv);
}
static const struct vm_operations_struct rdma_umap_ops = {
.open = rdma_umap_open,
.close = rdma_umap_close,
};
static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
struct vm_area_struct *vma,
unsigned long size)
{
struct ib_uverbs_file *ufile = ucontext->ufile;
struct rdma_umap_priv *priv;
if (vma->vm_end - vma->vm_start != size)
return ERR_PTR(-EINVAL);
/* Driver is using this wrong, must be called by ib_uverbs_mmap */
if (WARN_ON(!vma->vm_file ||
vma->vm_file->private_data != ufile))
return ERR_PTR(-EINVAL);
lockdep_assert_held(&ufile->device->disassociate_srcu);
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return ERR_PTR(-ENOMEM);
return priv;
}
/*
* Map IO memory into a process. This is to be called by drivers as part of
* their mmap() functions if they wish to send something like PCI-E BAR memory
* to userspace.
*/
int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
struct rdma_umap_priv *priv = rdma_user_mmap_pre(ucontext, vma, size);
if (IS_ERR(priv))
return PTR_ERR(priv);
vma->vm_page_prot = prot;
if (io_remap_pfn_range(vma, vma->vm_start, pfn, size, prot)) {
kfree(priv);
return -EAGAIN;
}
rdma_umap_priv_init(priv, vma);
return 0;
}
EXPORT_SYMBOL(rdma_user_mmap_io);
/*
* The page case is here for a slightly different reason, the driver expects
* to be able to free the page it is sharing to user space when it destroys
* its ucontext, which means we need to zap the user space references.
*
* We could handle this differently by providing an API to allocate a shared
* page and then only freeing the shared page when the last ufile is
* destroyed.
*/
int rdma_user_mmap_page(struct ib_ucontext *ucontext,
struct vm_area_struct *vma, struct page *page,
unsigned long size)
{
struct rdma_umap_priv *priv = rdma_user_mmap_pre(ucontext, vma, size);
if (IS_ERR(priv))
return PTR_ERR(priv);
if (remap_pfn_range(vma, vma->vm_start, page_to_pfn(page), size,
vma->vm_page_prot)) {
kfree(priv);
return -EAGAIN;
}
rdma_umap_priv_init(priv, vma);
return 0;
}
EXPORT_SYMBOL(rdma_user_mmap_page);
void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
{
struct rdma_umap_priv *priv, *next_priv;
lockdep_assert_held(&ufile->hw_destroy_rwsem);
while (1) {
struct mm_struct *mm = NULL;
/* Get an arbitrary mm pointer that hasn't been cleaned yet */
mutex_lock(&ufile->umap_lock);
if (!list_empty(&ufile->umaps)) {
mm = list_first_entry(&ufile->umaps,
struct rdma_umap_priv, list)
->vma->vm_mm;
mmget(mm);
}
mutex_unlock(&ufile->umap_lock);
if (!mm)
return;
/*
* The umap_lock is nested under mmap_sem since it used within
* the vma_ops callbacks, so we have to clean the list one mm
* at a time to get the lock ordering right. Typically there
* will only be one mm, so no big deal.
*/
down_write(&mm->mmap_sem);
mutex_lock(&ufile->umap_lock);
list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
list) {
struct vm_area_struct *vma = priv->vma;
if (vma->vm_mm != mm)
continue;
list_del_init(&priv->list);
zap_vma_ptes(vma, vma->vm_start,
vma->vm_end - vma->vm_start);
vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
}
mutex_unlock(&ufile->umap_lock);
up_write(&mm->mmap_sem);
mmput(mm);
}
}
/*
* ib_uverbs_open() does not need the BKL:
*
* - the ib_uverbs_device structures are properly reference counted and
* everything else is purely local to the file being created, so
* races against other open calls are not a problem;
* - there is no ioctl method to race against;
* - the open method will either immediately run -ENXIO, or all
* required initialization will be done.
*/
static int ib_uverbs_open(struct inode *inode, struct file *filp)
{
struct ib_uverbs_device *dev;
struct ib_uverbs_file *file;
struct ib_device *ib_dev;
int ret;
int module_dependent;
int srcu_key;
dev = container_of(inode->i_cdev, struct ib_uverbs_device, cdev);
if (!atomic_inc_not_zero(&dev->refcount))
return -ENXIO;
get_device(&dev->dev);
srcu_key = srcu_read_lock(&dev->disassociate_srcu);
mutex_lock(&dev->lists_mutex);
ib_dev = srcu_dereference(dev->ib_dev,
&dev->disassociate_srcu);
if (!ib_dev) {
ret = -EIO;
goto err;
}
/* In case IB device supports disassociate ucontext, there is no hard
* dependency between uverbs device and its low level device.
*/
module_dependent = !(ib_dev->disassociate_ucontext);
if (module_dependent) {
if (!try_module_get(ib_dev->owner)) {
ret = -ENODEV;
goto err;
}
}
file = kzalloc(sizeof(*file), GFP_KERNEL);
if (!file) {
ret = -ENOMEM;
if (module_dependent)
goto err_module;
goto err;
}
file->device = dev;
kref_init(&file->ref);
mutex_init(&file->ucontext_lock);
spin_lock_init(&file->uobjects_lock);
INIT_LIST_HEAD(&file->uobjects);
init_rwsem(&file->hw_destroy_rwsem);
mutex_init(&file->umap_lock);
INIT_LIST_HEAD(&file->umaps);
filp->private_data = file;
list_add_tail(&file->list, &dev->uverbs_file_list);
mutex_unlock(&dev->lists_mutex);
srcu_read_unlock(&dev->disassociate_srcu, srcu_key);
file->uverbs_cmd_mask = ib_dev->uverbs_cmd_mask;
file->uverbs_ex_cmd_mask = ib_dev->uverbs_ex_cmd_mask;
setup_ufile_idr_uobject(file);
return nonseekable_open(inode, filp);
err_module:
module_put(ib_dev->owner);
err:
mutex_unlock(&dev->lists_mutex);
srcu_read_unlock(&dev->disassociate_srcu, srcu_key);
if (atomic_dec_and_test(&dev->refcount))
ib_uverbs_comp_dev(dev);
put_device(&dev->dev);
return ret;
}
static int ib_uverbs_close(struct inode *inode, struct file *filp)
{
struct ib_uverbs_file *file = filp->private_data;
uverbs_destroy_ufile_hw(file, RDMA_REMOVE_CLOSE);
mutex_lock(&file->device->lists_mutex);
list_del_init(&file->list);
mutex_unlock(&file->device->lists_mutex);
if (file->async_file)
kref_put(&file->async_file->ref,
ib_uverbs_release_async_event_file);
kref_put(&file->ref, ib_uverbs_release_file);
return 0;
}
static const struct file_operations uverbs_fops = {
.owner = THIS_MODULE,
.write = ib_uverbs_write,
.open = ib_uverbs_open,
.release = ib_uverbs_close,
.llseek = no_llseek,
.unlocked_ioctl = ib_uverbs_ioctl,
.compat_ioctl = ib_uverbs_ioctl,
};
static const struct file_operations uverbs_mmap_fops = {
.owner = THIS_MODULE,
.write = ib_uverbs_write,
.mmap = ib_uverbs_mmap,
.open = ib_uverbs_open,
.release = ib_uverbs_close,
.llseek = no_llseek,
.unlocked_ioctl = ib_uverbs_ioctl,
.compat_ioctl = ib_uverbs_ioctl,
};
static struct ib_client uverbs_client = {
.name = "uverbs",
.add = ib_uverbs_add_one,
.remove = ib_uverbs_remove_one
};
static ssize_t ibdev_show(struct device *device, struct device_attribute *attr,
char *buf)
{
struct ib_uverbs_device *dev =
container_of(device, struct ib_uverbs_device, dev);
int ret = -ENODEV;
int srcu_key;
struct ib_device *ib_dev;
srcu_key = srcu_read_lock(&dev->disassociate_srcu);
ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu);
if (ib_dev)
ret = sprintf(buf, "%s\n", dev_name(&ib_dev->dev));
srcu_read_unlock(&dev->disassociate_srcu, srcu_key);
return ret;
}
static DEVICE_ATTR_RO(ibdev);
static ssize_t abi_version_show(struct device *device,
struct device_attribute *attr, char *buf)
{
struct ib_uverbs_device *dev =
container_of(device, struct ib_uverbs_device, dev);
int ret = -ENODEV;
int srcu_key;
struct ib_device *ib_dev;
srcu_key = srcu_read_lock(&dev->disassociate_srcu);
ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu);
if (ib_dev)
ret = sprintf(buf, "%d\n", ib_dev->uverbs_abi_ver);
srcu_read_unlock(&dev->disassociate_srcu, srcu_key);
return ret;
}
static DEVICE_ATTR_RO(abi_version);
static struct attribute *ib_dev_attrs[] = {
&dev_attr_abi_version.attr,
&dev_attr_ibdev.attr,
NULL,
};
static const struct attribute_group dev_attr_group = {
.attrs = ib_dev_attrs,
};
static CLASS_ATTR_STRING(abi_version, S_IRUGO,
__stringify(IB_USER_VERBS_ABI_VERSION));
static int ib_uverbs_create_uapi(struct ib_device *device,
struct ib_uverbs_device *uverbs_dev)
{
struct uverbs_api *uapi;
uapi = uverbs_alloc_api(device->driver_specs, device->driver_id);
if (IS_ERR(uapi))
return PTR_ERR(uapi);
uverbs_dev->uapi = uapi;
return 0;
}
static void ib_uverbs_add_one(struct ib_device *device)
{
int devnum;
dev_t base;
struct ib_uverbs_device *uverbs_dev;
int ret;
if (!device->alloc_ucontext)
return;
uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL);
if (!uverbs_dev)
return;
ret = init_srcu_struct(&uverbs_dev->disassociate_srcu);
if (ret) {
kfree(uverbs_dev);
return;
}
device_initialize(&uverbs_dev->dev);
uverbs_dev->dev.class = uverbs_class;
uverbs_dev->dev.parent = device->dev.parent;
uverbs_dev->dev.release = ib_uverbs_release_dev;
uverbs_dev->groups[0] = &dev_attr_group;
uverbs_dev->dev.groups = uverbs_dev->groups;
atomic_set(&uverbs_dev->refcount, 1);
init_completion(&uverbs_dev->comp);
uverbs_dev->xrcd_tree = RB_ROOT;
mutex_init(&uverbs_dev->xrcd_tree_mutex);
mutex_init(&uverbs_dev->lists_mutex);
INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list);
INIT_LIST_HEAD(&uverbs_dev->uverbs_events_file_list);
rcu_assign_pointer(uverbs_dev->ib_dev, device);
uverbs_dev->num_comp_vectors = device->num_comp_vectors;
devnum = find_first_zero_bit(dev_map, IB_UVERBS_MAX_DEVICES);
if (devnum >= IB_UVERBS_MAX_DEVICES)
goto err;
uverbs_dev->devnum = devnum;
set_bit(devnum, dev_map);
if (devnum >= IB_UVERBS_NUM_FIXED_MINOR)
base = dynamic_uverbs_dev + devnum - IB_UVERBS_NUM_FIXED_MINOR;
else
base = IB_UVERBS_BASE_DEV + devnum;
if (ib_uverbs_create_uapi(device, uverbs_dev))
goto err_uapi;
uverbs_dev->dev.devt = base;
dev_set_name(&uverbs_dev->dev, "uverbs%d", uverbs_dev->devnum);
cdev_init(&uverbs_dev->cdev,
device->mmap ? &uverbs_mmap_fops : &uverbs_fops);
uverbs_dev->cdev.owner = THIS_MODULE;
ret = cdev_device_add(&uverbs_dev->cdev, &uverbs_dev->dev);
if (ret)
goto err_uapi;
ib_set_client_data(device, &uverbs_client, uverbs_dev);
return;
err_uapi:
clear_bit(devnum, dev_map);
err:
if (atomic_dec_and_test(&uverbs_dev->refcount))
ib_uverbs_comp_dev(uverbs_dev);
wait_for_completion(&uverbs_dev->comp);
put_device(&uverbs_dev->dev);
return;
}
static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
struct ib_device *ib_dev)
{
struct ib_uverbs_file *file;
struct ib_uverbs_async_event_file *event_file;
struct ib_event event;
/* Pending running commands to terminate */
uverbs_disassociate_api_pre(uverbs_dev);
event.event = IB_EVENT_DEVICE_FATAL;
event.element.port_num = 0;
event.device = ib_dev;
mutex_lock(&uverbs_dev->lists_mutex);
while (!list_empty(&uverbs_dev->uverbs_file_list)) {
file = list_first_entry(&uverbs_dev->uverbs_file_list,
struct ib_uverbs_file, list);
list_del_init(&file->list);
kref_get(&file->ref);
/* We must release the mutex before going ahead and calling
* uverbs_cleanup_ufile, as it might end up indirectly calling
* uverbs_close, for example due to freeing the resources (e.g
* mmput).
*/
mutex_unlock(&uverbs_dev->lists_mutex);
ib_uverbs_event_handler(&file->event_handler, &event);
uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE);
kref_put(&file->ref, ib_uverbs_release_file);
mutex_lock(&uverbs_dev->lists_mutex);
}
while (!list_empty(&uverbs_dev->uverbs_events_file_list)) {
event_file = list_first_entry(&uverbs_dev->
uverbs_events_file_list,
struct ib_uverbs_async_event_file,
list);
spin_lock_irq(&event_file->ev_queue.lock);
event_file->ev_queue.is_closed = 1;
spin_unlock_irq(&event_file->ev_queue.lock);
list_del(&event_file->list);
ib_unregister_event_handler(
&event_file->uverbs_file->event_handler);
event_file->uverbs_file->event_handler.device =
NULL;
wake_up_interruptible(&event_file->ev_queue.poll_wait);
kill_fasync(&event_file->ev_queue.async_queue, SIGIO, POLL_IN);
}
mutex_unlock(&uverbs_dev->lists_mutex);
uverbs_disassociate_api(uverbs_dev->uapi);
}
static void ib_uverbs_remove_one(struct ib_device *device, void *client_data)
{
struct ib_uverbs_device *uverbs_dev = client_data;
int wait_clients = 1;
if (!uverbs_dev)
return;
cdev_device_del(&uverbs_dev->cdev, &uverbs_dev->dev);
clear_bit(uverbs_dev->devnum, dev_map);
if (device->disassociate_ucontext) {
/* We disassociate HW resources and immediately return.
* Userspace will see a EIO errno for all future access.
* Upon returning, ib_device may be freed internally and is not
* valid any more.
* uverbs_device is still available until all clients close
* their files, then the uverbs device ref count will be zero
* and its resources will be freed.
* Note: At this point no more files can be opened since the
* cdev was deleted, however active clients can still issue
* commands and close their open files.
*/
ib_uverbs_free_hw_resources(uverbs_dev, device);
wait_clients = 0;
}
if (atomic_dec_and_test(&uverbs_dev->refcount))
ib_uverbs_comp_dev(uverbs_dev);
if (wait_clients)
wait_for_completion(&uverbs_dev->comp);
put_device(&uverbs_dev->dev);
}
static char *uverbs_devnode(struct device *dev, umode_t *mode)
{
if (mode)
*mode = 0666;
return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
}
static int __init ib_uverbs_init(void)
{
int ret;
ret = register_chrdev_region(IB_UVERBS_BASE_DEV,
IB_UVERBS_NUM_FIXED_MINOR,
"infiniband_verbs");
if (ret) {
pr_err("user_verbs: couldn't register device number\n");
goto out;
}
ret = alloc_chrdev_region(&dynamic_uverbs_dev, 0,
IB_UVERBS_NUM_DYNAMIC_MINOR,
"infiniband_verbs");
if (ret) {
pr_err("couldn't register dynamic device number\n");
goto out_alloc;
}
uverbs_class = class_create(THIS_MODULE, "infiniband_verbs");
if (IS_ERR(uverbs_class)) {
ret = PTR_ERR(uverbs_class);
pr_err("user_verbs: couldn't create class infiniband_verbs\n");
goto out_chrdev;
}
uverbs_class->devnode = uverbs_devnode;
ret = class_create_file(uverbs_class, &class_attr_abi_version.attr);
if (ret) {
pr_err("user_verbs: couldn't create abi_version attribute\n");
goto out_class;
}
ret = ib_register_client(&uverbs_client);
if (ret) {
pr_err("user_verbs: couldn't register client\n");
goto out_class;
}
return 0;
out_class:
class_destroy(uverbs_class);
out_chrdev:
unregister_chrdev_region(dynamic_uverbs_dev,
IB_UVERBS_NUM_DYNAMIC_MINOR);
out_alloc:
unregister_chrdev_region(IB_UVERBS_BASE_DEV,
IB_UVERBS_NUM_FIXED_MINOR);
out:
return ret;
}
static void __exit ib_uverbs_cleanup(void)
{
ib_unregister_client(&uverbs_client);
class_destroy(uverbs_class);
unregister_chrdev_region(IB_UVERBS_BASE_DEV,
IB_UVERBS_NUM_FIXED_MINOR);
unregister_chrdev_region(dynamic_uverbs_dev,
IB_UVERBS_NUM_DYNAMIC_MINOR);
}
module_init(ib_uverbs_init);
module_exit(ib_uverbs_cleanup);
|