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
|
/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, 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 "core_priv.h"
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/netdevice.h>
#include <linux/ethtool.h>
#include <rdma/ib_mad.h>
#include <rdma/ib_pma.h>
struct ib_port;
struct gid_attr_group {
struct ib_port *port;
struct kobject kobj;
struct attribute_group ndev;
struct attribute_group type;
};
struct ib_port {
struct kobject kobj;
struct ib_device *ibdev;
struct gid_attr_group *gid_attr_group;
struct attribute_group gid_group;
struct attribute_group pkey_group;
struct attribute_group *pma_table;
struct attribute_group *hw_stats_ag;
struct rdma_hw_stats *hw_stats;
u8 port_num;
};
struct port_attribute {
struct attribute attr;
ssize_t (*show)(struct ib_port *, struct port_attribute *, char *buf);
ssize_t (*store)(struct ib_port *, struct port_attribute *,
const char *buf, size_t count);
};
#define PORT_ATTR(_name, _mode, _show, _store) \
struct port_attribute port_attr_##_name = __ATTR(_name, _mode, _show, _store)
#define PORT_ATTR_RO(_name) \
struct port_attribute port_attr_##_name = __ATTR_RO(_name)
struct port_table_attribute {
struct port_attribute attr;
char name[8];
int index;
__be16 attr_id;
};
struct hw_stats_attribute {
struct attribute attr;
ssize_t (*show)(struct kobject *kobj,
struct attribute *attr, char *buf);
ssize_t (*store)(struct kobject *kobj,
struct attribute *attr,
const char *buf,
size_t count);
int index;
u8 port_num;
};
static ssize_t port_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct port_attribute *port_attr =
container_of(attr, struct port_attribute, attr);
struct ib_port *p = container_of(kobj, struct ib_port, kobj);
if (!port_attr->show)
return -EIO;
return port_attr->show(p, port_attr, buf);
}
static const struct sysfs_ops port_sysfs_ops = {
.show = port_attr_show
};
static ssize_t gid_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct port_attribute *port_attr =
container_of(attr, struct port_attribute, attr);
struct ib_port *p = container_of(kobj, struct gid_attr_group,
kobj)->port;
if (!port_attr->show)
return -EIO;
return port_attr->show(p, port_attr, buf);
}
static const struct sysfs_ops gid_attr_sysfs_ops = {
.show = gid_attr_show
};
static ssize_t state_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
static const char *state_name[] = {
[IB_PORT_NOP] = "NOP",
[IB_PORT_DOWN] = "DOWN",
[IB_PORT_INIT] = "INIT",
[IB_PORT_ARMED] = "ARMED",
[IB_PORT_ACTIVE] = "ACTIVE",
[IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER"
};
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "%d: %s\n", attr.state,
attr.state >= 0 && attr.state < ARRAY_SIZE(state_name) ?
state_name[attr.state] : "UNKNOWN");
}
static ssize_t lid_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "0x%x\n", attr.lid);
}
static ssize_t lid_mask_count_show(struct ib_port *p,
struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "%d\n", attr.lmc);
}
static ssize_t sm_lid_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "0x%x\n", attr.sm_lid);
}
static ssize_t sm_sl_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "%d\n", attr.sm_sl);
}
static ssize_t cap_mask_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
return sprintf(buf, "0x%08x\n", attr.port_cap_flags);
}
static ssize_t rate_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
char *speed = "";
int rate; /* in deci-Gb/sec */
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
switch (attr.active_speed) {
case IB_SPEED_DDR:
speed = " DDR";
rate = 50;
break;
case IB_SPEED_QDR:
speed = " QDR";
rate = 100;
break;
case IB_SPEED_FDR10:
speed = " FDR10";
rate = 100;
break;
case IB_SPEED_FDR:
speed = " FDR";
rate = 140;
break;
case IB_SPEED_EDR:
speed = " EDR";
rate = 250;
break;
case IB_SPEED_SDR:
default: /* default to SDR for invalid rates */
rate = 25;
break;
}
rate *= ib_width_enum_to_int(attr.active_width);
if (rate < 0)
return -EINVAL;
return sprintf(buf, "%d%s Gb/sec (%dX%s)\n",
rate / 10, rate % 10 ? ".5" : "",
ib_width_enum_to_int(attr.active_width), speed);
}
static ssize_t phys_state_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
struct ib_port_attr attr;
ssize_t ret;
ret = ib_query_port(p->ibdev, p->port_num, &attr);
if (ret)
return ret;
switch (attr.phys_state) {
case 1: return sprintf(buf, "1: Sleep\n");
case 2: return sprintf(buf, "2: Polling\n");
case 3: return sprintf(buf, "3: Disabled\n");
case 4: return sprintf(buf, "4: PortConfigurationTraining\n");
case 5: return sprintf(buf, "5: LinkUp\n");
case 6: return sprintf(buf, "6: LinkErrorRecovery\n");
case 7: return sprintf(buf, "7: Phy Test\n");
default: return sprintf(buf, "%d: <unknown>\n", attr.phys_state);
}
}
static ssize_t link_layer_show(struct ib_port *p, struct port_attribute *unused,
char *buf)
{
switch (rdma_port_get_link_layer(p->ibdev, p->port_num)) {
case IB_LINK_LAYER_INFINIBAND:
return sprintf(buf, "%s\n", "InfiniBand");
case IB_LINK_LAYER_ETHERNET:
return sprintf(buf, "%s\n", "Ethernet");
default:
return sprintf(buf, "%s\n", "Unknown");
}
}
static PORT_ATTR_RO(state);
static PORT_ATTR_RO(lid);
static PORT_ATTR_RO(lid_mask_count);
static PORT_ATTR_RO(sm_lid);
static PORT_ATTR_RO(sm_sl);
static PORT_ATTR_RO(cap_mask);
static PORT_ATTR_RO(rate);
static PORT_ATTR_RO(phys_state);
static PORT_ATTR_RO(link_layer);
static struct attribute *port_default_attrs[] = {
&port_attr_state.attr,
&port_attr_lid.attr,
&port_attr_lid_mask_count.attr,
&port_attr_sm_lid.attr,
&port_attr_sm_sl.attr,
&port_attr_cap_mask.attr,
&port_attr_rate.attr,
&port_attr_phys_state.attr,
&port_attr_link_layer.attr,
NULL
};
static size_t print_ndev(struct ib_gid_attr *gid_attr, char *buf)
{
if (!gid_attr->ndev)
return -EINVAL;
return sprintf(buf, "%s\n", gid_attr->ndev->name);
}
static size_t print_gid_type(struct ib_gid_attr *gid_attr, char *buf)
{
return sprintf(buf, "%s\n", ib_cache_gid_type_str(gid_attr->gid_type));
}
static ssize_t _show_port_gid_attr(struct ib_port *p,
struct port_attribute *attr,
char *buf,
size_t (*print)(struct ib_gid_attr *gid_attr,
char *buf))
{
struct port_table_attribute *tab_attr =
container_of(attr, struct port_table_attribute, attr);
union ib_gid gid;
struct ib_gid_attr gid_attr = {};
ssize_t ret;
ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid,
&gid_attr);
if (ret)
goto err;
ret = print(&gid_attr, buf);
err:
if (gid_attr.ndev)
dev_put(gid_attr.ndev);
return ret;
}
static ssize_t show_port_gid(struct ib_port *p, struct port_attribute *attr,
char *buf)
{
struct port_table_attribute *tab_attr =
container_of(attr, struct port_table_attribute, attr);
union ib_gid gid;
ssize_t ret;
ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid, NULL);
if (ret)
return ret;
return sprintf(buf, "%pI6\n", gid.raw);
}
static ssize_t show_port_gid_attr_ndev(struct ib_port *p,
struct port_attribute *attr, char *buf)
{
return _show_port_gid_attr(p, attr, buf, print_ndev);
}
static ssize_t show_port_gid_attr_gid_type(struct ib_port *p,
struct port_attribute *attr,
char *buf)
{
return _show_port_gid_attr(p, attr, buf, print_gid_type);
}
static ssize_t show_port_pkey(struct ib_port *p, struct port_attribute *attr,
char *buf)
{
struct port_table_attribute *tab_attr =
container_of(attr, struct port_table_attribute, attr);
u16 pkey;
ssize_t ret;
ret = ib_query_pkey(p->ibdev, p->port_num, tab_attr->index, &pkey);
if (ret)
return ret;
return sprintf(buf, "0x%04x\n", pkey);
}
#define PORT_PMA_ATTR(_name, _counter, _width, _offset) \
struct port_table_attribute port_pma_attr_##_name = { \
.attr = __ATTR(_name, S_IRUGO, show_pma_counter, NULL), \
.index = (_offset) | ((_width) << 16) | ((_counter) << 24), \
.attr_id = IB_PMA_PORT_COUNTERS , \
}
#define PORT_PMA_ATTR_EXT(_name, _width, _offset) \
struct port_table_attribute port_pma_attr_ext_##_name = { \
.attr = __ATTR(_name, S_IRUGO, show_pma_counter, NULL), \
.index = (_offset) | ((_width) << 16), \
.attr_id = IB_PMA_PORT_COUNTERS_EXT , \
}
/*
* Get a Perfmgmt MAD block of data.
* Returns error code or the number of bytes retrieved.
*/
static int get_perf_mad(struct ib_device *dev, int port_num, __be16 attr,
void *data, int offset, size_t size)
{
struct ib_mad *in_mad;
struct ib_mad *out_mad;
size_t mad_size = sizeof(*out_mad);
u16 out_mad_pkey_index = 0;
ssize_t ret;
if (!dev->process_mad)
return -ENOSYS;
in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL);
out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
if (!in_mad || !out_mad) {
ret = -ENOMEM;
goto out;
}
in_mad->mad_hdr.base_version = 1;
in_mad->mad_hdr.mgmt_class = IB_MGMT_CLASS_PERF_MGMT;
in_mad->mad_hdr.class_version = 1;
in_mad->mad_hdr.method = IB_MGMT_METHOD_GET;
in_mad->mad_hdr.attr_id = attr;
if (attr != IB_PMA_CLASS_PORT_INFO)
in_mad->data[41] = port_num; /* PortSelect field */
if ((dev->process_mad(dev, IB_MAD_IGNORE_MKEY,
port_num, NULL, NULL,
(const struct ib_mad_hdr *)in_mad, mad_size,
(struct ib_mad_hdr *)out_mad, &mad_size,
&out_mad_pkey_index) &
(IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
(IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
ret = -EINVAL;
goto out;
}
memcpy(data, out_mad->data + offset, size);
ret = size;
out:
kfree(in_mad);
kfree(out_mad);
return ret;
}
static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
char *buf)
{
struct port_table_attribute *tab_attr =
container_of(attr, struct port_table_attribute, attr);
int offset = tab_attr->index & 0xffff;
int width = (tab_attr->index >> 16) & 0xff;
ssize_t ret;
u8 data[8];
ret = get_perf_mad(p->ibdev, p->port_num, tab_attr->attr_id, &data,
40 + offset / 8, sizeof(data));
if (ret < 0)
return sprintf(buf, "N/A (no PMA)\n");
switch (width) {
case 4:
ret = sprintf(buf, "%u\n", (*data >>
(4 - (offset % 8))) & 0xf);
break;
case 8:
ret = sprintf(buf, "%u\n", *data);
break;
case 16:
ret = sprintf(buf, "%u\n",
be16_to_cpup((__be16 *)data));
break;
case 32:
ret = sprintf(buf, "%u\n",
be32_to_cpup((__be32 *)data));
break;
case 64:
ret = sprintf(buf, "%llu\n",
be64_to_cpup((__be64 *)data));
break;
default:
ret = 0;
}
return ret;
}
static PORT_PMA_ATTR(symbol_error , 0, 16, 32);
static PORT_PMA_ATTR(link_error_recovery , 1, 8, 48);
static PORT_PMA_ATTR(link_downed , 2, 8, 56);
static PORT_PMA_ATTR(port_rcv_errors , 3, 16, 64);
static PORT_PMA_ATTR(port_rcv_remote_physical_errors, 4, 16, 80);
static PORT_PMA_ATTR(port_rcv_switch_relay_errors , 5, 16, 96);
static PORT_PMA_ATTR(port_xmit_discards , 6, 16, 112);
static PORT_PMA_ATTR(port_xmit_constraint_errors , 7, 8, 128);
static PORT_PMA_ATTR(port_rcv_constraint_errors , 8, 8, 136);
static PORT_PMA_ATTR(local_link_integrity_errors , 9, 4, 152);
static PORT_PMA_ATTR(excessive_buffer_overrun_errors, 10, 4, 156);
static PORT_PMA_ATTR(VL15_dropped , 11, 16, 176);
static PORT_PMA_ATTR(port_xmit_data , 12, 32, 192);
static PORT_PMA_ATTR(port_rcv_data , 13, 32, 224);
static PORT_PMA_ATTR(port_xmit_packets , 14, 32, 256);
static PORT_PMA_ATTR(port_rcv_packets , 15, 32, 288);
static PORT_PMA_ATTR(port_xmit_wait , 0, 32, 320);
/*
* Counters added by extended set
*/
static PORT_PMA_ATTR_EXT(port_xmit_data , 64, 64);
static PORT_PMA_ATTR_EXT(port_rcv_data , 64, 128);
static PORT_PMA_ATTR_EXT(port_xmit_packets , 64, 192);
static PORT_PMA_ATTR_EXT(port_rcv_packets , 64, 256);
static PORT_PMA_ATTR_EXT(unicast_xmit_packets , 64, 320);
static PORT_PMA_ATTR_EXT(unicast_rcv_packets , 64, 384);
static PORT_PMA_ATTR_EXT(multicast_xmit_packets , 64, 448);
static PORT_PMA_ATTR_EXT(multicast_rcv_packets , 64, 512);
static struct attribute *pma_attrs[] = {
&port_pma_attr_symbol_error.attr.attr,
&port_pma_attr_link_error_recovery.attr.attr,
&port_pma_attr_link_downed.attr.attr,
&port_pma_attr_port_rcv_errors.attr.attr,
&port_pma_attr_port_rcv_remote_physical_errors.attr.attr,
&port_pma_attr_port_rcv_switch_relay_errors.attr.attr,
&port_pma_attr_port_xmit_discards.attr.attr,
&port_pma_attr_port_xmit_constraint_errors.attr.attr,
&port_pma_attr_port_rcv_constraint_errors.attr.attr,
&port_pma_attr_local_link_integrity_errors.attr.attr,
&port_pma_attr_excessive_buffer_overrun_errors.attr.attr,
&port_pma_attr_VL15_dropped.attr.attr,
&port_pma_attr_port_xmit_data.attr.attr,
&port_pma_attr_port_rcv_data.attr.attr,
&port_pma_attr_port_xmit_packets.attr.attr,
&port_pma_attr_port_rcv_packets.attr.attr,
&port_pma_attr_port_xmit_wait.attr.attr,
NULL
};
static struct attribute *pma_attrs_ext[] = {
&port_pma_attr_symbol_error.attr.attr,
&port_pma_attr_link_error_recovery.attr.attr,
&port_pma_attr_link_downed.attr.attr,
&port_pma_attr_port_rcv_errors.attr.attr,
&port_pma_attr_port_rcv_remote_physical_errors.attr.attr,
&port_pma_attr_port_rcv_switch_relay_errors.attr.attr,
&port_pma_attr_port_xmit_discards.attr.attr,
&port_pma_attr_port_xmit_constraint_errors.attr.attr,
&port_pma_attr_port_rcv_constraint_errors.attr.attr,
&port_pma_attr_local_link_integrity_errors.attr.attr,
&port_pma_attr_excessive_buffer_overrun_errors.attr.attr,
&port_pma_attr_VL15_dropped.attr.attr,
&port_pma_attr_ext_port_xmit_data.attr.attr,
&port_pma_attr_ext_port_rcv_data.attr.attr,
&port_pma_attr_ext_port_xmit_packets.attr.attr,
&port_pma_attr_port_xmit_wait.attr.attr,
&port_pma_attr_ext_port_rcv_packets.attr.attr,
&port_pma_attr_ext_unicast_rcv_packets.attr.attr,
&port_pma_attr_ext_unicast_xmit_packets.attr.attr,
&port_pma_attr_ext_multicast_rcv_packets.attr.attr,
&port_pma_attr_ext_multicast_xmit_packets.attr.attr,
NULL
};
static struct attribute *pma_attrs_noietf[] = {
&port_pma_attr_symbol_error.attr.attr,
&port_pma_attr_link_error_recovery.attr.attr,
&port_pma_attr_link_downed.attr.attr,
&port_pma_attr_port_rcv_errors.attr.attr,
&port_pma_attr_port_rcv_remote_physical_errors.attr.attr,
&port_pma_attr_port_rcv_switch_relay_errors.attr.attr,
&port_pma_attr_port_xmit_discards.attr.attr,
&port_pma_attr_port_xmit_constraint_errors.attr.attr,
&port_pma_attr_port_rcv_constraint_errors.attr.attr,
&port_pma_attr_local_link_integrity_errors.attr.attr,
&port_pma_attr_excessive_buffer_overrun_errors.attr.attr,
&port_pma_attr_VL15_dropped.attr.attr,
&port_pma_attr_ext_port_xmit_data.attr.attr,
&port_pma_attr_ext_port_rcv_data.attr.attr,
&port_pma_attr_ext_port_xmit_packets.attr.attr,
&port_pma_attr_ext_port_rcv_packets.attr.attr,
&port_pma_attr_port_xmit_wait.attr.attr,
NULL
};
static struct attribute_group pma_group = {
.name = "counters",
.attrs = pma_attrs
};
static struct attribute_group pma_group_ext = {
.name = "counters",
.attrs = pma_attrs_ext
};
static struct attribute_group pma_group_noietf = {
.name = "counters",
.attrs = pma_attrs_noietf
};
static void ib_port_release(struct kobject *kobj)
{
struct ib_port *p = container_of(kobj, struct ib_port, kobj);
struct attribute *a;
int i;
if (p->gid_group.attrs) {
for (i = 0; (a = p->gid_group.attrs[i]); ++i)
kfree(a);
kfree(p->gid_group.attrs);
}
if (p->pkey_group.attrs) {
for (i = 0; (a = p->pkey_group.attrs[i]); ++i)
kfree(a);
kfree(p->pkey_group.attrs);
}
kfree(p);
}
static void ib_port_gid_attr_release(struct kobject *kobj)
{
struct gid_attr_group *g = container_of(kobj, struct gid_attr_group,
kobj);
struct attribute *a;
int i;
if (g->ndev.attrs) {
for (i = 0; (a = g->ndev.attrs[i]); ++i)
kfree(a);
kfree(g->ndev.attrs);
}
if (g->type.attrs) {
for (i = 0; (a = g->type.attrs[i]); ++i)
kfree(a);
kfree(g->type.attrs);
}
kfree(g);
}
static struct kobj_type port_type = {
.release = ib_port_release,
.sysfs_ops = &port_sysfs_ops,
.default_attrs = port_default_attrs
};
static struct kobj_type gid_attr_type = {
.sysfs_ops = &gid_attr_sysfs_ops,
.release = ib_port_gid_attr_release
};
static struct attribute **
alloc_group_attrs(ssize_t (*show)(struct ib_port *,
struct port_attribute *, char *buf),
int len)
{
struct attribute **tab_attr;
struct port_table_attribute *element;
int i;
tab_attr = kcalloc(1 + len, sizeof(struct attribute *), GFP_KERNEL);
if (!tab_attr)
return NULL;
for (i = 0; i < len; i++) {
element = kzalloc(sizeof(struct port_table_attribute),
GFP_KERNEL);
if (!element)
goto err;
if (snprintf(element->name, sizeof(element->name),
"%d", i) >= sizeof(element->name)) {
kfree(element);
goto err;
}
element->attr.attr.name = element->name;
element->attr.attr.mode = S_IRUGO;
element->attr.show = show;
element->index = i;
sysfs_attr_init(&element->attr.attr);
tab_attr[i] = &element->attr.attr;
}
return tab_attr;
err:
while (--i >= 0)
kfree(tab_attr[i]);
kfree(tab_attr);
return NULL;
}
/*
* Figure out which counter table to use depending on
* the device capabilities.
*/
static struct attribute_group *get_counter_table(struct ib_device *dev,
int port_num)
{
struct ib_class_port_info cpi;
if (get_perf_mad(dev, port_num, IB_PMA_CLASS_PORT_INFO,
&cpi, 40, sizeof(cpi)) >= 0) {
if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH)
/* We have extended counters */
return &pma_group_ext;
if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
/* But not the IETF ones */
return &pma_group_noietf;
}
/* Fall back to normal counters */
return &pma_group;
}
static int update_hw_stats(struct ib_device *dev, struct rdma_hw_stats *stats,
u8 port_num, int index)
{
int ret;
if (time_is_after_eq_jiffies(stats->timestamp + stats->lifespan))
return 0;
ret = dev->get_hw_stats(dev, stats, port_num, index);
if (ret < 0)
return ret;
if (ret == stats->num_counters)
stats->timestamp = jiffies;
return 0;
}
static ssize_t print_hw_stat(struct rdma_hw_stats *stats, int index, char *buf)
{
return sprintf(buf, "%llu\n", stats->value[index]);
}
static ssize_t show_hw_stats(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct ib_device *dev;
struct ib_port *port;
struct hw_stats_attribute *hsa;
struct rdma_hw_stats *stats;
int ret;
hsa = container_of(attr, struct hw_stats_attribute, attr);
if (!hsa->port_num) {
dev = container_of((struct device *)kobj,
struct ib_device, dev);
stats = dev->hw_stats;
} else {
port = container_of(kobj, struct ib_port, kobj);
dev = port->ibdev;
stats = port->hw_stats;
}
ret = update_hw_stats(dev, stats, hsa->port_num, hsa->index);
if (ret)
return ret;
return print_hw_stat(stats, hsa->index, buf);
}
static ssize_t show_stats_lifespan(struct kobject *kobj,
struct attribute *attr,
char *buf)
{
struct hw_stats_attribute *hsa;
int msecs;
hsa = container_of(attr, struct hw_stats_attribute, attr);
if (!hsa->port_num) {
struct ib_device *dev = container_of((struct device *)kobj,
struct ib_device, dev);
msecs = jiffies_to_msecs(dev->hw_stats->lifespan);
} else {
struct ib_port *p = container_of(kobj, struct ib_port, kobj);
msecs = jiffies_to_msecs(p->hw_stats->lifespan);
}
return sprintf(buf, "%d\n", msecs);
}
static ssize_t set_stats_lifespan(struct kobject *kobj,
struct attribute *attr,
const char *buf, size_t count)
{
struct hw_stats_attribute *hsa;
int msecs;
int jiffies;
int ret;
ret = kstrtoint(buf, 10, &msecs);
if (ret)
return ret;
if (msecs < 0 || msecs > 10000)
return -EINVAL;
jiffies = msecs_to_jiffies(msecs);
hsa = container_of(attr, struct hw_stats_attribute, attr);
if (!hsa->port_num) {
struct ib_device *dev = container_of((struct device *)kobj,
struct ib_device, dev);
dev->hw_stats->lifespan = jiffies;
} else {
struct ib_port *p = container_of(kobj, struct ib_port, kobj);
p->hw_stats->lifespan = jiffies;
}
return count;
}
static void free_hsag(struct kobject *kobj, struct attribute_group *attr_group)
{
struct attribute **attr;
sysfs_remove_group(kobj, attr_group);
for (attr = attr_group->attrs; *attr; attr++)
kfree(*attr);
kfree(attr_group);
}
static struct attribute *alloc_hsa(int index, u8 port_num, const char *name)
{
struct hw_stats_attribute *hsa;
hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
if (!hsa)
return NULL;
hsa->attr.name = (char *)name;
hsa->attr.mode = S_IRUGO;
hsa->show = show_hw_stats;
hsa->store = NULL;
hsa->index = index;
hsa->port_num = port_num;
return &hsa->attr;
}
static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num)
{
struct hw_stats_attribute *hsa;
hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
if (!hsa)
return NULL;
hsa->attr.name = name;
hsa->attr.mode = S_IWUSR | S_IRUGO;
hsa->show = show_stats_lifespan;
hsa->store = set_stats_lifespan;
hsa->index = 0;
hsa->port_num = port_num;
return &hsa->attr;
}
static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
u8 port_num)
{
struct attribute_group *hsag;
struct rdma_hw_stats *stats;
int i, ret;
stats = device->alloc_hw_stats(device, port_num);
if (!stats)
return;
if (!stats->names || stats->num_counters <= 0)
goto err_free_stats;
/*
* Two extra attribue elements here, one for the lifespan entry and
* one to NULL terminate the list for the sysfs core code
*/
hsag = kzalloc(sizeof(*hsag) +
sizeof(void *) * (stats->num_counters + 2),
GFP_KERNEL);
if (!hsag)
goto err_free_stats;
ret = device->get_hw_stats(device, stats, port_num,
stats->num_counters);
if (ret != stats->num_counters)
goto err_free_hsag;
stats->timestamp = jiffies;
hsag->name = "hw_counters";
hsag->attrs = (void *)hsag + sizeof(*hsag);
for (i = 0; i < stats->num_counters; i++) {
hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
if (!hsag->attrs[i])
goto err;
sysfs_attr_init(hsag->attrs[i]);
}
/* treat an error here as non-fatal */
hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
if (hsag->attrs[i])
sysfs_attr_init(hsag->attrs[i]);
if (port) {
struct kobject *kobj = &port->kobj;
ret = sysfs_create_group(kobj, hsag);
if (ret)
goto err;
port->hw_stats_ag = hsag;
port->hw_stats = stats;
} else {
struct kobject *kobj = &device->dev.kobj;
ret = sysfs_create_group(kobj, hsag);
if (ret)
goto err;
device->hw_stats_ag = hsag;
device->hw_stats = stats;
}
return;
err:
for (; i >= 0; i--)
kfree(hsag->attrs[i]);
err_free_hsag:
kfree(hsag);
err_free_stats:
kfree(stats);
return;
}
static int add_port(struct ib_device *device, int port_num,
int (*port_callback)(struct ib_device *,
u8, struct kobject *))
{
struct ib_port *p;
struct ib_port_attr attr;
int i;
int ret;
ret = ib_query_port(device, port_num, &attr);
if (ret)
return ret;
p = kzalloc(sizeof *p, GFP_KERNEL);
if (!p)
return -ENOMEM;
p->ibdev = device;
p->port_num = port_num;
ret = kobject_init_and_add(&p->kobj, &port_type,
device->ports_parent,
"%d", port_num);
if (ret) {
kfree(p);
return ret;
}
p->gid_attr_group = kzalloc(sizeof(*p->gid_attr_group), GFP_KERNEL);
if (!p->gid_attr_group) {
ret = -ENOMEM;
goto err_put;
}
p->gid_attr_group->port = p;
ret = kobject_init_and_add(&p->gid_attr_group->kobj, &gid_attr_type,
&p->kobj, "gid_attrs");
if (ret) {
kfree(p->gid_attr_group);
goto err_put;
}
p->pma_table = get_counter_table(device, port_num);
ret = sysfs_create_group(&p->kobj, p->pma_table);
if (ret)
goto err_put_gid_attrs;
p->gid_group.name = "gids";
p->gid_group.attrs = alloc_group_attrs(show_port_gid, attr.gid_tbl_len);
if (!p->gid_group.attrs) {
ret = -ENOMEM;
goto err_remove_pma;
}
ret = sysfs_create_group(&p->kobj, &p->gid_group);
if (ret)
goto err_free_gid;
p->gid_attr_group->ndev.name = "ndevs";
p->gid_attr_group->ndev.attrs = alloc_group_attrs(show_port_gid_attr_ndev,
attr.gid_tbl_len);
if (!p->gid_attr_group->ndev.attrs) {
ret = -ENOMEM;
goto err_remove_gid;
}
ret = sysfs_create_group(&p->gid_attr_group->kobj,
&p->gid_attr_group->ndev);
if (ret)
goto err_free_gid_ndev;
p->gid_attr_group->type.name = "types";
p->gid_attr_group->type.attrs = alloc_group_attrs(show_port_gid_attr_gid_type,
attr.gid_tbl_len);
if (!p->gid_attr_group->type.attrs) {
ret = -ENOMEM;
goto err_remove_gid_ndev;
}
ret = sysfs_create_group(&p->gid_attr_group->kobj,
&p->gid_attr_group->type);
if (ret)
goto err_free_gid_type;
p->pkey_group.name = "pkeys";
p->pkey_group.attrs = alloc_group_attrs(show_port_pkey,
attr.pkey_tbl_len);
if (!p->pkey_group.attrs) {
ret = -ENOMEM;
goto err_remove_gid_type;
}
ret = sysfs_create_group(&p->kobj, &p->pkey_group);
if (ret)
goto err_free_pkey;
if (port_callback) {
ret = port_callback(device, port_num, &p->kobj);
if (ret)
goto err_remove_pkey;
}
/*
* If port == 0, it means we have only one port and the parent
* device, not this port device, should be the holder of the
* hw_counters
*/
if (device->alloc_hw_stats && port_num)
setup_hw_stats(device, p, port_num);
list_add_tail(&p->kobj.entry, &device->port_list);
kobject_uevent(&p->kobj, KOBJ_ADD);
return 0;
err_remove_pkey:
sysfs_remove_group(&p->kobj, &p->pkey_group);
err_free_pkey:
for (i = 0; i < attr.pkey_tbl_len; ++i)
kfree(p->pkey_group.attrs[i]);
kfree(p->pkey_group.attrs);
p->pkey_group.attrs = NULL;
err_remove_gid_type:
sysfs_remove_group(&p->gid_attr_group->kobj,
&p->gid_attr_group->type);
err_free_gid_type:
for (i = 0; i < attr.gid_tbl_len; ++i)
kfree(p->gid_attr_group->type.attrs[i]);
kfree(p->gid_attr_group->type.attrs);
p->gid_attr_group->type.attrs = NULL;
err_remove_gid_ndev:
sysfs_remove_group(&p->gid_attr_group->kobj,
&p->gid_attr_group->ndev);
err_free_gid_ndev:
for (i = 0; i < attr.gid_tbl_len; ++i)
kfree(p->gid_attr_group->ndev.attrs[i]);
kfree(p->gid_attr_group->ndev.attrs);
p->gid_attr_group->ndev.attrs = NULL;
err_remove_gid:
sysfs_remove_group(&p->kobj, &p->gid_group);
err_free_gid:
for (i = 0; i < attr.gid_tbl_len; ++i)
kfree(p->gid_group.attrs[i]);
kfree(p->gid_group.attrs);
p->gid_group.attrs = NULL;
err_remove_pma:
sysfs_remove_group(&p->kobj, p->pma_table);
err_put_gid_attrs:
kobject_put(&p->gid_attr_group->kobj);
err_put:
kobject_put(&p->kobj);
return ret;
}
static ssize_t show_node_type(struct device *device,
struct device_attribute *attr, char *buf)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
switch (dev->node_type) {
case RDMA_NODE_IB_CA: return sprintf(buf, "%d: CA\n", dev->node_type);
case RDMA_NODE_RNIC: return sprintf(buf, "%d: RNIC\n", dev->node_type);
case RDMA_NODE_USNIC: return sprintf(buf, "%d: usNIC\n", dev->node_type);
case RDMA_NODE_USNIC_UDP: return sprintf(buf, "%d: usNIC UDP\n", dev->node_type);
case RDMA_NODE_IB_SWITCH: return sprintf(buf, "%d: switch\n", dev->node_type);
case RDMA_NODE_IB_ROUTER: return sprintf(buf, "%d: router\n", dev->node_type);
default: return sprintf(buf, "%d: <unknown>\n", dev->node_type);
}
}
static ssize_t show_sys_image_guid(struct device *device,
struct device_attribute *dev_attr, char *buf)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
return sprintf(buf, "%04x:%04x:%04x:%04x\n",
be16_to_cpu(((__be16 *) &dev->attrs.sys_image_guid)[0]),
be16_to_cpu(((__be16 *) &dev->attrs.sys_image_guid)[1]),
be16_to_cpu(((__be16 *) &dev->attrs.sys_image_guid)[2]),
be16_to_cpu(((__be16 *) &dev->attrs.sys_image_guid)[3]));
}
static ssize_t show_node_guid(struct device *device,
struct device_attribute *attr, char *buf)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
return sprintf(buf, "%04x:%04x:%04x:%04x\n",
be16_to_cpu(((__be16 *) &dev->node_guid)[0]),
be16_to_cpu(((__be16 *) &dev->node_guid)[1]),
be16_to_cpu(((__be16 *) &dev->node_guid)[2]),
be16_to_cpu(((__be16 *) &dev->node_guid)[3]));
}
static ssize_t show_node_desc(struct device *device,
struct device_attribute *attr, char *buf)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
return sprintf(buf, "%.64s\n", dev->node_desc);
}
static ssize_t set_node_desc(struct device *device,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
struct ib_device_modify desc = {};
int ret;
if (!dev->modify_device)
return -EIO;
memcpy(desc.node_desc, buf, min_t(int, count, IB_DEVICE_NODE_DESC_MAX));
ret = ib_modify_device(dev, IB_DEVICE_MODIFY_NODE_DESC, &desc);
if (ret)
return ret;
return count;
}
static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
char *buf)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
ib_get_device_fw_str(dev, buf, PAGE_SIZE);
strlcat(buf, "\n", PAGE_SIZE);
return strlen(buf);
}
static DEVICE_ATTR(node_type, S_IRUGO, show_node_type, NULL);
static DEVICE_ATTR(sys_image_guid, S_IRUGO, show_sys_image_guid, NULL);
static DEVICE_ATTR(node_guid, S_IRUGO, show_node_guid, NULL);
static DEVICE_ATTR(node_desc, S_IRUGO | S_IWUSR, show_node_desc, set_node_desc);
static DEVICE_ATTR(fw_ver, S_IRUGO, show_fw_ver, NULL);
static struct device_attribute *ib_class_attributes[] = {
&dev_attr_node_type,
&dev_attr_sys_image_guid,
&dev_attr_node_guid,
&dev_attr_node_desc,
&dev_attr_fw_ver,
};
static void free_port_list_attributes(struct ib_device *device)
{
struct kobject *p, *t;
list_for_each_entry_safe(p, t, &device->port_list, entry) {
struct ib_port *port = container_of(p, struct ib_port, kobj);
list_del(&p->entry);
if (port->hw_stats) {
kfree(port->hw_stats);
free_hsag(&port->kobj, port->hw_stats_ag);
}
sysfs_remove_group(p, port->pma_table);
sysfs_remove_group(p, &port->pkey_group);
sysfs_remove_group(p, &port->gid_group);
sysfs_remove_group(&port->gid_attr_group->kobj,
&port->gid_attr_group->ndev);
sysfs_remove_group(&port->gid_attr_group->kobj,
&port->gid_attr_group->type);
kobject_put(&port->gid_attr_group->kobj);
kobject_put(p);
}
kobject_put(device->ports_parent);
}
int ib_device_register_sysfs(struct ib_device *device,
int (*port_callback)(struct ib_device *,
u8, struct kobject *))
{
struct device *class_dev = &device->dev;
int ret;
int i;
device->dev.parent = device->dma_device;
ret = dev_set_name(class_dev, "%s", device->name);
if (ret)
return ret;
ret = device_add(class_dev);
if (ret)
goto err;
for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i) {
ret = device_create_file(class_dev, ib_class_attributes[i]);
if (ret)
goto err_unregister;
}
device->ports_parent = kobject_create_and_add("ports",
&class_dev->kobj);
if (!device->ports_parent) {
ret = -ENOMEM;
goto err_put;
}
if (rdma_cap_ib_switch(device)) {
ret = add_port(device, 0, port_callback);
if (ret)
goto err_put;
} else {
for (i = 1; i <= device->phys_port_cnt; ++i) {
ret = add_port(device, i, port_callback);
if (ret)
goto err_put;
}
}
if (device->alloc_hw_stats)
setup_hw_stats(device, NULL, 0);
return 0;
err_put:
free_port_list_attributes(device);
err_unregister:
device_unregister(class_dev);
err:
return ret;
}
void ib_device_unregister_sysfs(struct ib_device *device)
{
int i;
/* Hold kobject until ib_dealloc_device() */
kobject_get(&device->dev.kobj);
free_port_list_attributes(device);
if (device->hw_stats) {
kfree(device->hw_stats);
free_hsag(&device->dev.kobj, device->hw_stats_ag);
}
for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i)
device_remove_file(&device->dev, ib_class_attributes[i]);
device_unregister(&device->dev);
}
|