-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathnet-sysfs.c
1366 lines (1133 loc) · 32.3 KB
/
net-sysfs.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
/*
* net-sysfs.c - network device class and attributes
*
* Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
#include <net/sock.h>
#include <net/net_namespace.h>
#include <linux/rtnetlink.h>
#include <linux/wireless.h>
#include <linux/vmalloc.h>
#include <net/wext.h>
#include "net-sysfs.h"
#ifdef CONFIG_SYSFS
static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
static const char fmt_udec[] = "%u\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
static inline int dev_isalive(const struct net_device *dev)
{
return dev->reg_state <= NETREG_REGISTERED;
}
/* use same locking rules as GIF* ioctl's */
static ssize_t netdev_show(const struct device *dev,
struct device_attribute *attr, char *buf,
ssize_t (*format)(const struct net_device *, char *))
{
struct net_device *net = to_net_dev(dev);
ssize_t ret = -EINVAL;
read_lock(&dev_base_lock);
if (dev_isalive(net))
ret = (*format)(net, buf);
read_unlock(&dev_base_lock);
return ret;
}
/* generate a show function for simple field */
#define NETDEVICE_SHOW(field, format_string) \
static ssize_t format_##field(const struct net_device *net, char *buf) \
{ \
return sprintf(buf, format_string, net->field); \
} \
static ssize_t show_##field(struct device *dev, \
struct device_attribute *attr, char *buf) \
{ \
return netdev_show(dev, attr, buf, format_##field); \
}
/* use same locking and permission rules as SIF* ioctl's */
static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len,
int (*set)(struct net_device *, unsigned long))
{
struct net_device *net = to_net_dev(dev);
char *endp;
unsigned long new;
int ret = -EINVAL;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
new = simple_strtoul(buf, &endp, 0);
if (endp == buf)
goto err;
if (!rtnl_trylock())
return restart_syscall();
if (dev_isalive(net)) {
if ((ret = (*set)(net, new)) == 0)
ret = len;
}
rtnl_unlock();
err:
return ret;
}
NETDEVICE_SHOW(dev_id, fmt_hex);
NETDEVICE_SHOW(addr_assign_type, fmt_dec);
NETDEVICE_SHOW(addr_len, fmt_dec);
NETDEVICE_SHOW(iflink, fmt_dec);
NETDEVICE_SHOW(ifindex, fmt_dec);
NETDEVICE_SHOW(features, fmt_hex);
NETDEVICE_SHOW(type, fmt_dec);
NETDEVICE_SHOW(link_mode, fmt_dec);
/* use same locking rules as GIFHWADDR ioctl's */
static ssize_t show_address(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct net_device *net = to_net_dev(dev);
ssize_t ret = -EINVAL;
read_lock(&dev_base_lock);
if (dev_isalive(net))
ret = sysfs_format_mac(buf, net->dev_addr, net->addr_len);
read_unlock(&dev_base_lock);
return ret;
}
static ssize_t show_broadcast(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *net = to_net_dev(dev);
if (dev_isalive(net))
return sysfs_format_mac(buf, net->broadcast, net->addr_len);
return -EINVAL;
}
static ssize_t show_carrier(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
if (netif_running(netdev)) {
return sprintf(buf, fmt_dec, !!netif_carrier_ok(netdev));
}
return -EINVAL;
}
static ssize_t show_speed(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
int ret = -EINVAL;
if (!rtnl_trylock())
return restart_syscall();
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!dev_ethtool_get_settings(netdev, &cmd))
ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
return ret;
}
static ssize_t show_duplex(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
int ret = -EINVAL;
if (!rtnl_trylock())
return restart_syscall();
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!dev_ethtool_get_settings(netdev, &cmd))
ret = sprintf(buf, "%s\n",
cmd.duplex ? "full" : "half");
}
rtnl_unlock();
return ret;
}
static ssize_t show_dormant(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
if (netif_running(netdev))
return sprintf(buf, fmt_dec, !!netif_dormant(netdev));
return -EINVAL;
}
static const char *const operstates[] = {
"unknown",
"notpresent", /* currently unused */
"down",
"lowerlayerdown",
"testing", /* currently unused */
"dormant",
"up"
};
static ssize_t show_operstate(struct device *dev,
struct device_attribute *attr, char *buf)
{
const struct net_device *netdev = to_net_dev(dev);
unsigned char operstate;
read_lock(&dev_base_lock);
operstate = netdev->operstate;
if (!netif_running(netdev))
operstate = IF_OPER_DOWN;
read_unlock(&dev_base_lock);
if (operstate >= ARRAY_SIZE(operstates))
return -EINVAL; /* should not happen */
return sprintf(buf, "%s\n", operstates[operstate]);
}
/* read-write attributes */
NETDEVICE_SHOW(mtu, fmt_dec);
static int change_mtu(struct net_device *net, unsigned long new_mtu)
{
return dev_set_mtu(net, (int) new_mtu);
}
static ssize_t store_mtu(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
return netdev_store(dev, attr, buf, len, change_mtu);
}
NETDEVICE_SHOW(flags, fmt_hex);
static int change_flags(struct net_device *net, unsigned long new_flags)
{
return dev_change_flags(net, (unsigned) new_flags);
}
static ssize_t store_flags(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
return netdev_store(dev, attr, buf, len, change_flags);
}
NETDEVICE_SHOW(tx_queue_len, fmt_ulong);
static int change_tx_queue_len(struct net_device *net, unsigned long new_len)
{
net->tx_queue_len = new_len;
return 0;
}
static ssize_t store_tx_queue_len(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t len)
{
return netdev_store(dev, attr, buf, len, change_tx_queue_len);
}
static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_device *netdev = to_net_dev(dev);
size_t count = len;
ssize_t ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
/* ignore trailing newline */
if (len > 0 && buf[len - 1] == '\n')
--count;
if (!rtnl_trylock())
return restart_syscall();
ret = dev_set_alias(netdev, buf, count);
rtnl_unlock();
return ret < 0 ? ret : len;
}
static ssize_t show_ifalias(struct device *dev,
struct device_attribute *attr, char *buf)
{
const struct net_device *netdev = to_net_dev(dev);
ssize_t ret = 0;
if (!rtnl_trylock())
return restart_syscall();
if (netdev->ifalias)
ret = sprintf(buf, "%s\n", netdev->ifalias);
rtnl_unlock();
return ret;
}
NETDEVICE_SHOW(group, fmt_dec);
static int change_group(struct net_device *net, unsigned long new_group)
{
dev_set_group(net, (int) new_group);
return 0;
}
static ssize_t store_group(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
return netdev_store(dev, attr, buf, len, change_group);
}
static struct device_attribute net_class_attributes[] = {
__ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL),
__ATTR(addr_len, S_IRUGO, show_addr_len, NULL),
__ATTR(dev_id, S_IRUGO, show_dev_id, NULL),
__ATTR(ifalias, S_IRUGO | S_IWUSR, show_ifalias, store_ifalias),
__ATTR(iflink, S_IRUGO, show_iflink, NULL),
__ATTR(ifindex, S_IRUGO, show_ifindex, NULL),
__ATTR(features, S_IRUGO, show_features, NULL),
__ATTR(type, S_IRUGO, show_type, NULL),
__ATTR(link_mode, S_IRUGO, show_link_mode, NULL),
__ATTR(address, S_IRUGO, show_address, NULL),
__ATTR(broadcast, S_IRUGO, show_broadcast, NULL),
__ATTR(carrier, S_IRUGO, show_carrier, NULL),
__ATTR(speed, S_IRUGO, show_speed, NULL),
__ATTR(duplex, S_IRUGO, show_duplex, NULL),
__ATTR(dormant, S_IRUGO, show_dormant, NULL),
__ATTR(operstate, S_IRUGO, show_operstate, NULL),
__ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu),
__ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags),
__ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len,
store_tx_queue_len),
__ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group),
{}
};
/* Show a given an attribute in the statistics group */
static ssize_t netstat_show(const struct device *d,
struct device_attribute *attr, char *buf,
unsigned long offset)
{
struct net_device *dev = to_net_dev(d);
ssize_t ret = -EINVAL;
WARN_ON(offset > sizeof(struct rtnl_link_stats64) ||
offset % sizeof(u64) != 0);
read_lock(&dev_base_lock);
if (dev_isalive(dev)) {
struct rtnl_link_stats64 temp;
const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset));
}
read_unlock(&dev_base_lock);
return ret;
}
/* generate a read-only statistics attribute */
#define NETSTAT_ENTRY(name) \
static ssize_t show_##name(struct device *d, \
struct device_attribute *attr, char *buf) \
{ \
return netstat_show(d, attr, buf, \
offsetof(struct rtnl_link_stats64, name)); \
} \
static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
NETSTAT_ENTRY(rx_packets);
NETSTAT_ENTRY(tx_packets);
NETSTAT_ENTRY(rx_bytes);
NETSTAT_ENTRY(tx_bytes);
NETSTAT_ENTRY(rx_errors);
NETSTAT_ENTRY(tx_errors);
NETSTAT_ENTRY(rx_dropped);
NETSTAT_ENTRY(tx_dropped);
NETSTAT_ENTRY(multicast);
NETSTAT_ENTRY(collisions);
NETSTAT_ENTRY(rx_length_errors);
NETSTAT_ENTRY(rx_over_errors);
NETSTAT_ENTRY(rx_crc_errors);
NETSTAT_ENTRY(rx_frame_errors);
NETSTAT_ENTRY(rx_fifo_errors);
NETSTAT_ENTRY(rx_missed_errors);
NETSTAT_ENTRY(tx_aborted_errors);
NETSTAT_ENTRY(tx_carrier_errors);
NETSTAT_ENTRY(tx_fifo_errors);
NETSTAT_ENTRY(tx_heartbeat_errors);
NETSTAT_ENTRY(tx_window_errors);
NETSTAT_ENTRY(rx_compressed);
NETSTAT_ENTRY(tx_compressed);
static struct attribute *netstat_attrs[] = {
&dev_attr_rx_packets.attr,
&dev_attr_tx_packets.attr,
&dev_attr_rx_bytes.attr,
&dev_attr_tx_bytes.attr,
&dev_attr_rx_errors.attr,
&dev_attr_tx_errors.attr,
&dev_attr_rx_dropped.attr,
&dev_attr_tx_dropped.attr,
&dev_attr_multicast.attr,
&dev_attr_collisions.attr,
&dev_attr_rx_length_errors.attr,
&dev_attr_rx_over_errors.attr,
&dev_attr_rx_crc_errors.attr,
&dev_attr_rx_frame_errors.attr,
&dev_attr_rx_fifo_errors.attr,
&dev_attr_rx_missed_errors.attr,
&dev_attr_tx_aborted_errors.attr,
&dev_attr_tx_carrier_errors.attr,
&dev_attr_tx_fifo_errors.attr,
&dev_attr_tx_heartbeat_errors.attr,
&dev_attr_tx_window_errors.attr,
&dev_attr_rx_compressed.attr,
&dev_attr_tx_compressed.attr,
NULL
};
static struct attribute_group netstat_group = {
.name = "statistics",
.attrs = netstat_attrs,
};
#ifdef CONFIG_WIRELESS_EXT_SYSFS
/* helper function that does all the locking etc for wireless stats */
static ssize_t wireless_show(struct device *d, char *buf,
ssize_t (*format)(const struct iw_statistics *,
char *))
{
struct net_device *dev = to_net_dev(d);
const struct iw_statistics *iw;
ssize_t ret = -EINVAL;
if (!rtnl_trylock())
return restart_syscall();
if (dev_isalive(dev)) {
iw = get_wireless_stats(dev);
if (iw)
ret = (*format)(iw, buf);
}
rtnl_unlock();
return ret;
}
/* show function template for wireless fields */
#define WIRELESS_SHOW(name, field, format_string) \
static ssize_t format_iw_##name(const struct iw_statistics *iw, char *buf) \
{ \
return sprintf(buf, format_string, iw->field); \
} \
static ssize_t show_iw_##name(struct device *d, \
struct device_attribute *attr, char *buf) \
{ \
return wireless_show(d, buf, format_iw_##name); \
} \
static DEVICE_ATTR(name, S_IRUGO, show_iw_##name, NULL)
WIRELESS_SHOW(status, status, fmt_hex);
WIRELESS_SHOW(link, qual.qual, fmt_dec);
WIRELESS_SHOW(level, qual.level, fmt_dec);
WIRELESS_SHOW(noise, qual.noise, fmt_dec);
WIRELESS_SHOW(nwid, discard.nwid, fmt_dec);
WIRELESS_SHOW(crypt, discard.code, fmt_dec);
WIRELESS_SHOW(fragment, discard.fragment, fmt_dec);
WIRELESS_SHOW(misc, discard.misc, fmt_dec);
WIRELESS_SHOW(retries, discard.retries, fmt_dec);
WIRELESS_SHOW(beacon, miss.beacon, fmt_dec);
static struct attribute *wireless_attrs[] = {
&dev_attr_status.attr,
&dev_attr_link.attr,
&dev_attr_level.attr,
&dev_attr_noise.attr,
&dev_attr_nwid.attr,
&dev_attr_crypt.attr,
&dev_attr_fragment.attr,
&dev_attr_retries.attr,
&dev_attr_misc.attr,
&dev_attr_beacon.attr,
NULL
};
static struct attribute_group wireless_group = {
.name = "wireless",
.attrs = wireless_attrs,
};
#endif
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_RPS
/*
* RX queue sysfs structures and functions.
*/
struct rx_queue_attribute {
struct attribute attr;
ssize_t (*show)(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr, char *buf);
ssize_t (*store)(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr, const char *buf, size_t len);
};
#define to_rx_queue_attr(_attr) container_of(_attr, \
struct rx_queue_attribute, attr)
#define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj)
static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
struct netdev_rx_queue *queue = to_rx_queue(kobj);
if (!attribute->show)
return -EIO;
return attribute->show(queue, attribute, buf);
}
static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
struct netdev_rx_queue *queue = to_rx_queue(kobj);
if (!attribute->store)
return -EIO;
return attribute->store(queue, attribute, buf, count);
}
static const struct sysfs_ops rx_queue_sysfs_ops = {
.show = rx_queue_attr_show,
.store = rx_queue_attr_store,
};
static ssize_t show_rps_map(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attribute, char *buf)
{
struct rps_map *map;
cpumask_var_t mask;
size_t len = 0;
int i;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
rcu_read_lock();
map = rcu_dereference(queue->rps_map);
if (map)
for (i = 0; i < map->len; i++)
cpumask_set_cpu(map->cpus[i], mask);
len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
if (PAGE_SIZE - len < 3) {
rcu_read_unlock();
free_cpumask_var(mask);
return -EINVAL;
}
rcu_read_unlock();
free_cpumask_var(mask);
len += sprintf(buf + len, "\n");
return len;
}
static void rps_map_release(struct rcu_head *rcu)
{
struct rps_map *map = container_of(rcu, struct rps_map, rcu);
kfree(map);
}
static ssize_t store_rps_map(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attribute,
const char *buf, size_t len)
{
struct rps_map *old_map, *map;
cpumask_var_t mask;
int err, cpu, i;
static DEFINE_SPINLOCK(rps_map_lock);
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
if (err) {
free_cpumask_var(mask);
return err;
}
map = kzalloc(max_t(unsigned,
RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES),
GFP_KERNEL);
if (!map) {
free_cpumask_var(mask);
return -ENOMEM;
}
i = 0;
for_each_cpu_and(cpu, mask, cpu_online_mask)
map->cpus[i++] = cpu;
if (i)
map->len = i;
else {
kfree(map);
map = NULL;
}
spin_lock(&rps_map_lock);
old_map = rcu_dereference_protected(queue->rps_map,
lockdep_is_held(&rps_map_lock));
rcu_assign_pointer(queue->rps_map, map);
spin_unlock(&rps_map_lock);
if (old_map)
call_rcu(&old_map->rcu, rps_map_release);
free_cpumask_var(mask);
return len;
}
static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr,
char *buf)
{
struct rps_dev_flow_table *flow_table;
unsigned int val = 0;
rcu_read_lock();
flow_table = rcu_dereference(queue->rps_flow_table);
if (flow_table)
val = flow_table->mask + 1;
rcu_read_unlock();
return sprintf(buf, "%u\n", val);
}
static void rps_dev_flow_table_release_work(struct work_struct *work)
{
struct rps_dev_flow_table *table = container_of(work,
struct rps_dev_flow_table, free_work);
vfree(table);
}
static void rps_dev_flow_table_release(struct rcu_head *rcu)
{
struct rps_dev_flow_table *table = container_of(rcu,
struct rps_dev_flow_table, rcu);
INIT_WORK(&table->free_work, rps_dev_flow_table_release_work);
schedule_work(&table->free_work);
}
static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr,
const char *buf, size_t len)
{
unsigned int count;
char *endp;
struct rps_dev_flow_table *table, *old_table;
static DEFINE_SPINLOCK(rps_dev_flow_lock);
if (!capable(CAP_NET_ADMIN))
return -EPERM;
count = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EINVAL;
if (count) {
int i;
if (count > 1<<30) {
/* Enforce a limit to prevent overflow */
return -EINVAL;
}
count = roundup_pow_of_two(count);
table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
if (!table)
return -ENOMEM;
table->mask = count - 1;
for (i = 0; i < count; i++)
table->flows[i].cpu = RPS_NO_CPU;
} else
table = NULL;
spin_lock(&rps_dev_flow_lock);
old_table = rcu_dereference_protected(queue->rps_flow_table,
lockdep_is_held(&rps_dev_flow_lock));
rcu_assign_pointer(queue->rps_flow_table, table);
spin_unlock(&rps_dev_flow_lock);
if (old_table)
call_rcu(&old_table->rcu, rps_dev_flow_table_release);
return len;
}
static struct rx_queue_attribute rps_cpus_attribute =
__ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map);
static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute =
__ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR,
show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt);
static struct attribute *rx_queue_default_attrs[] = {
&rps_cpus_attribute.attr,
&rps_dev_flow_table_cnt_attribute.attr,
NULL
};
static void rx_queue_release(struct kobject *kobj)
{
struct netdev_rx_queue *queue = to_rx_queue(kobj);
struct rps_map *map;
struct rps_dev_flow_table *flow_table;
map = rcu_dereference_raw(queue->rps_map);
if (map) {
RCU_INIT_POINTER(queue->rps_map, NULL);
call_rcu(&map->rcu, rps_map_release);
}
flow_table = rcu_dereference_raw(queue->rps_flow_table);
if (flow_table) {
RCU_INIT_POINTER(queue->rps_flow_table, NULL);
call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
}
memset(kobj, 0, sizeof(*kobj));
dev_put(queue->dev);
}
static struct kobj_type rx_queue_ktype = {
.sysfs_ops = &rx_queue_sysfs_ops,
.release = rx_queue_release,
.default_attrs = rx_queue_default_attrs,
};
static int rx_queue_add_kobject(struct net_device *net, int index)
{
struct netdev_rx_queue *queue = net->_rx + index;
struct kobject *kobj = &queue->kobj;
int error = 0;
kobj->kset = net->queues_kset;
error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
"rx-%u", index);
if (error) {
kobject_put(kobj);
return error;
}
kobject_uevent(kobj, KOBJ_ADD);
dev_hold(queue->dev);
return error;
}
#endif /* CONFIG_RPS */
int
net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
{
#ifdef CONFIG_RPS
int i;
int error = 0;
for (i = old_num; i < new_num; i++) {
error = rx_queue_add_kobject(net, i);
if (error) {
new_num = old_num;
break;
}
}
while (--i >= new_num)
kobject_put(&net->_rx[i].kobj);
return error;
#else
return 0;
#endif
}
#ifdef CONFIG_XPS
/*
* netdev_queue sysfs structures and functions.
*/
struct netdev_queue_attribute {
struct attribute attr;
ssize_t (*show)(struct netdev_queue *queue,
struct netdev_queue_attribute *attr, char *buf);
ssize_t (*store)(struct netdev_queue *queue,
struct netdev_queue_attribute *attr, const char *buf, size_t len);
};
#define to_netdev_queue_attr(_attr) container_of(_attr, \
struct netdev_queue_attribute, attr)
#define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj)
static ssize_t netdev_queue_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr);
struct netdev_queue *queue = to_netdev_queue(kobj);
if (!attribute->show)
return -EIO;
return attribute->show(queue, attribute, buf);
}
static ssize_t netdev_queue_attr_store(struct kobject *kobj,
struct attribute *attr,
const char *buf, size_t count)
{
struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr);
struct netdev_queue *queue = to_netdev_queue(kobj);
if (!attribute->store)
return -EIO;
return attribute->store(queue, attribute, buf, count);
}
static const struct sysfs_ops netdev_queue_sysfs_ops = {
.show = netdev_queue_attr_show,
.store = netdev_queue_attr_store,
};
static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
int i;
for (i = 0; i < dev->num_tx_queues; i++)
if (queue == &dev->_tx[i])
break;
BUG_ON(i >= dev->num_tx_queues);
return i;
}
static ssize_t show_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute, char *buf)
{
struct net_device *dev = queue->dev;
struct xps_dev_maps *dev_maps;
cpumask_var_t mask;
unsigned long index;
size_t len = 0;
int i;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
index = get_netdev_queue_index(queue);
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
for_each_possible_cpu(i) {
struct xps_map *map =
rcu_dereference(dev_maps->cpu_map[i]);
if (map) {
int j;
for (j = 0; j < map->len; j++) {
if (map->queues[j] == index) {
cpumask_set_cpu(i, mask);
break;
}
}
}
}
}
rcu_read_unlock();
len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
if (PAGE_SIZE - len < 3) {
free_cpumask_var(mask);
return -EINVAL;
}
free_cpumask_var(mask);
len += sprintf(buf + len, "\n");
return len;
}
static void xps_map_release(struct rcu_head *rcu)
{
struct xps_map *map = container_of(rcu, struct xps_map, rcu);
kfree(map);
}
static void xps_dev_maps_release(struct rcu_head *rcu)
{
struct xps_dev_maps *dev_maps =
container_of(rcu, struct xps_dev_maps, rcu);
kfree(dev_maps);
}
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
static ssize_t store_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute,
const char *buf, size_t len)
{
struct net_device *dev = queue->dev;
cpumask_var_t mask;
int err, i, cpu, pos, map_len, alloc_len, need_set;
unsigned long index;
struct xps_map *map, *new_map;
struct xps_dev_maps *dev_maps, *new_dev_maps;
int nonempty = 0;
int numa_node = -2;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
index = get_netdev_queue_index(queue);
err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
if (err) {
free_cpumask_var(mask);
return err;
}
new_dev_maps = kzalloc(max_t(unsigned,
XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL);
if (!new_dev_maps) {
free_cpumask_var(mask);
return -ENOMEM;
}
mutex_lock(&xps_map_mutex);
dev_maps = xmap_dereference(dev->xps_maps);
for_each_possible_cpu(cpu) {
map = dev_maps ?
xmap_dereference(dev_maps->cpu_map[cpu]) : NULL;
new_map = map;
if (map) {
for (pos = 0; pos < map->len; pos++)
if (map->queues[pos] == index)
break;
map_len = map->len;
alloc_len = map->alloc_len;
} else
pos = map_len = alloc_len = 0;
need_set = cpu_isset(cpu, *mask) && cpu_online(cpu);
#ifdef CONFIG_NUMA
if (need_set) {
if (numa_node == -2)
numa_node = cpu_to_node(cpu);
else if (numa_node != cpu_to_node(cpu))
numa_node = -1;
}
#endif
if (need_set && pos >= map_len) {
/* Need to add queue to this CPU's map */
if (map_len >= alloc_len) {
alloc_len = alloc_len ?
2 * alloc_len : XPS_MIN_MAP_ALLOC;
new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len),
GFP_KERNEL,
cpu_to_node(cpu));
if (!new_map)
goto error;
new_map->alloc_len = alloc_len;
for (i = 0; i < map_len; i++)
new_map->queues[i] = map->queues[i];
new_map->len = map_len;
}
new_map->queues[new_map->len++] = index;
} else if (!need_set && pos < map_len) {
/* Need to remove queue from this CPU's map */
if (map_len > 1)
new_map->queues[pos] =
new_map->queues[--new_map->len];
else
new_map = NULL;
}
RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map);