-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsch_api.c
executable file
·1805 lines (1512 loc) · 47 KB
/
sch_api.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/sched/sch_api.c Packet scheduler API.
*
* 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.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Fixes:
*
* Rani Assaf <rani@magic.metawire.com> :980802: JIFFIES and CPU clock sources are repaired.
* Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support
* Jamal Hadi Salim <hadi@nortelnetworks.com>: 990601: ingress support
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/hrtimer.h>
#include <linux/lockdep.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
static int qdisc_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, u32 clid,
struct Qdisc *old, struct Qdisc *new);
static int tclass_notify(struct net *net, struct sk_buff *oskb,
struct nlmsghdr *n, struct Qdisc *q,
unsigned long cl, int event);
/*
Short review.
-------------
This file consists of two interrelated parts:
1. queueing disciplines manager frontend.
2. traffic classes manager frontend.
Generally, queueing discipline ("qdisc") is a black box,
which is able to enqueue packets and to dequeue them (when
device is ready to send something) in order and at times
determined by algorithm hidden in it.
qdisc's are divided to two categories:
- "queues", which have no internal structure visible from outside.
- "schedulers", which split all the packets to "traffic classes",
using "packet classifiers" (look at cls_api.c)
In turn, classes may have child qdiscs (as rule, queues)
attached to them etc. etc. etc.
The goal of the routines in this file is to translate
information supplied by user in the form of handles
to more intelligible for kernel form, to make some sanity
checks and part of work, which is common to all qdiscs
and to provide rtnetlink notifications.
All real intelligent work is done inside qdisc modules.
Every discipline has two major routines: enqueue and dequeue.
---dequeue
dequeue usually returns a skb to send. It is allowed to return NULL,
but it does not mean that queue is empty, it just means that
discipline does not want to send anything this time.
Queue is really empty if q->q.qlen == 0.
For complicated disciplines with multiple queues q->q is not
real packet queue, but however q->q.qlen must be valid.
---enqueue
enqueue returns 0, if packet was enqueued successfully.
If packet (this one or another one) was dropped, it returns
not zero error code.
NET_XMIT_DROP - this packet dropped
Expected action: do not backoff, but wait until queue will clear.
NET_XMIT_CN - probably this packet enqueued, but another one dropped.
Expected action: backoff or ignore
NET_XMIT_POLICED - dropped by police.
Expected action: backoff or error to real-time apps.
Auxiliary routines:
---peek
like dequeue but without removing a packet from the queue
---reset
returns qdisc to initial state: purge all buffers, clear all
timers, counters (except for statistics) etc.
---init
initializes newly created qdisc.
---destroy
destroys resources allocated by init and during lifetime of qdisc.
---change
changes qdisc parameters.
*/
/* Protects list of registered TC modules. It is pure SMP lock. */
static DEFINE_RWLOCK(qdisc_mod_lock);
/************************************************
* Queueing disciplines manipulation. *
************************************************/
/* The list of all installed queueing disciplines. */
static struct Qdisc_ops *qdisc_base;
/* Register/uregister queueing discipline */
// 使用int register_qdisc(struct Qdisc_ops *qops)注册对象类型。
// 使用int register_tcf_proto_ops(struct tcf_proto_ops *ops)注册过滤器类型。
//所有的Qdisc_ops结构通过register_qdisc添加到qdisc_base链表中
int register_qdisc(struct Qdisc_ops *qops)
{
struct Qdisc_ops *q, **qp;
int rc = -EEXIST;
write_lock(&qdisc_mod_lock);
for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next)
if (!strcmp(qops->id, q->id))
goto out;
if (qops->enqueue == NULL)
qops->enqueue = noop_qdisc_ops.enqueue;
if (qops->peek == NULL) {
if (qops->dequeue == NULL) {
qops->peek = noop_qdisc_ops.peek;
} else {
rc = -EINVAL;
goto out;
}
}
if (qops->dequeue == NULL)
qops->dequeue = noop_qdisc_ops.dequeue;
qops->next = NULL;
*qp = qops;
rc = 0;
out:
write_unlock(&qdisc_mod_lock);
return rc;
}
EXPORT_SYMBOL(register_qdisc);
int unregister_qdisc(struct Qdisc_ops *qops)
{
struct Qdisc_ops *q, **qp;
int err = -ENOENT;
write_lock(&qdisc_mod_lock);
for (qp = &qdisc_base; (q=*qp)!=NULL; qp = &q->next)
if (q == qops)
break;
if (q) {
*qp = q->next;
q->next = NULL;
err = 0;
}
write_unlock(&qdisc_mod_lock);
return err;
}
EXPORT_SYMBOL(unregister_qdisc);
/* We know handle. Find qdisc among all qdisc's attached to device
(root qdisc, all its children, children of children etc.)
*/
static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
{
struct Qdisc *q;
if (!(root->flags & TCQ_F_BUILTIN) &&
root->handle == handle)
return root;
list_for_each_entry(q, &root->list, list) {
if (q->handle == handle)
return q;
}
return NULL;
}
static void qdisc_list_add(struct Qdisc *q)
{
if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
}
void qdisc_list_del(struct Qdisc *q)
{
if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
list_del(&q->list);
}
EXPORT_SYMBOL(qdisc_list_del);
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
{
struct Qdisc *q;
q = qdisc_match_from_root(dev->qdisc, handle);
if (q)
goto out;
q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle);
out:
return q;
}
static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
{
unsigned long cl;
struct Qdisc *leaf;
const struct Qdisc_class_ops *cops = p->ops->cl_ops;
if (cops == NULL)
return NULL;
//例如tc qdisc add dev eth0 parent 22:4 handle 33
cl = cops->get(p, classid); //prio_class_ops对应的是 如果是prio队列规则，则这个是获取父Qdisc中的22:4中的4
if (cl == 0)
return NULL;
leaf = cops->leaf(p, cl);//如果父为prio类型队列规程，获取父QDISC p中的第classid(低16位)的qdisc，prio_sched_data->queues[cl]
cops->put(p, cl);
return leaf;
}
/* Find queueing discipline by name */
//更加排队规则名得到系统已注册的排队规则
static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
{
struct Qdisc_ops *q = NULL;
if (kind) {
read_lock(&qdisc_mod_lock);
for (q = qdisc_base; q; q = q->next) {
if (nla_strcmp(kind, q->id) == 0) {
if (!try_module_get(q->owner))
q = NULL;
break;
}
}
read_unlock(&qdisc_mod_lock);
}
return q;
}
static struct qdisc_rate_table *qdisc_rtab_list;
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
{
struct qdisc_rate_table *rtab;
for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) {
if (memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) == 0) {
rtab->refcnt++;
return rtab;
}
}
if (tab == NULL || r->rate == 0 || r->cell_log == 0 ||
nla_len(tab) != TC_RTAB_SIZE)
return NULL;
rtab = kmalloc(sizeof(*rtab), GFP_KERNEL);
if (rtab) {
rtab->rate = *r;
rtab->refcnt = 1;
memcpy(rtab->data, nla_data(tab), 1024);
rtab->next = qdisc_rtab_list;
qdisc_rtab_list = rtab;
}
return rtab;
}
EXPORT_SYMBOL(qdisc_get_rtab);
void qdisc_put_rtab(struct qdisc_rate_table *tab)
{
struct qdisc_rate_table *rtab, **rtabp;
if (!tab || --tab->refcnt)
return;
for (rtabp = &qdisc_rtab_list; (rtab=*rtabp) != NULL; rtabp = &rtab->next) {
if (rtab == tab) {
*rtabp = rtab->next;
kfree(rtab);
return;
}
}
}
EXPORT_SYMBOL(qdisc_put_rtab);
static LIST_HEAD(qdisc_stab_list);
static DEFINE_SPINLOCK(qdisc_stab_lock);
static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = {
[TCA_STAB_BASE] = { .len = sizeof(struct tc_sizespec) },
[TCA_STAB_DATA] = { .type = NLA_BINARY },
};
static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt)
{
struct nlattr *tb[TCA_STAB_MAX + 1];
struct qdisc_size_table *stab;
struct tc_sizespec *s;
unsigned int tsize = 0;
u16 *tab = NULL;
int err;
err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy);
if (err < 0)
return ERR_PTR(err);
if (!tb[TCA_STAB_BASE])
return ERR_PTR(-EINVAL);
s = nla_data(tb[TCA_STAB_BASE]);
if (s->tsize > 0) {
if (!tb[TCA_STAB_DATA])
return ERR_PTR(-EINVAL);
tab = nla_data(tb[TCA_STAB_DATA]);
tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16);
}
if (!s || tsize != s->tsize || (!tab && tsize > 0))
return ERR_PTR(-EINVAL);
spin_lock(&qdisc_stab_lock);
list_for_each_entry(stab, &qdisc_stab_list, list) {
if (memcmp(&stab->szopts, s, sizeof(*s)))
continue;
if (tsize > 0 && memcmp(stab->data, tab, tsize * sizeof(u16)))
continue;
stab->refcnt++;
spin_unlock(&qdisc_stab_lock);
return stab;
}
spin_unlock(&qdisc_stab_lock);
stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL);
if (!stab)
return ERR_PTR(-ENOMEM);
stab->refcnt = 1;
stab->szopts = *s;
if (tsize > 0)
memcpy(stab->data, tab, tsize * sizeof(u16));
spin_lock(&qdisc_stab_lock);
list_add_tail(&stab->list, &qdisc_stab_list);
spin_unlock(&qdisc_stab_lock);
return stab;
}
void qdisc_put_stab(struct qdisc_size_table *tab)
{
if (!tab)
return;
spin_lock(&qdisc_stab_lock);
if (--tab->refcnt == 0) {
list_del(&tab->list);
kfree(tab);
}
spin_unlock(&qdisc_stab_lock);
}
EXPORT_SYMBOL(qdisc_put_stab);
static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab)
{
struct nlattr *nest;
nest = nla_nest_start(skb, TCA_STAB);
if (nest == NULL)
goto nla_put_failure;
NLA_PUT(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts);
nla_nest_end(skb, nest);
return skb->len;
nla_put_failure:
return -1;
}
void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab)
{
int pkt_len, slot;
pkt_len = skb->len + stab->szopts.overhead;
if (unlikely(!stab->szopts.tsize))
goto out;
slot = pkt_len + stab->szopts.cell_align;
if (unlikely(slot < 0))
slot = 0;
slot >>= stab->szopts.cell_log;
if (likely(slot < stab->szopts.tsize))
pkt_len = stab->data[slot];
else
pkt_len = stab->data[stab->szopts.tsize - 1] *
(slot / stab->szopts.tsize) +
stab->data[slot % stab->szopts.tsize];
pkt_len <<= stab->szopts.size_log;
out:
if (unlikely(pkt_len < 1))
pkt_len = 1;
qdisc_skb_cb(skb)->pkt_len = pkt_len;
}
EXPORT_SYMBOL(qdisc_calculate_pkt_len);
void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
{
if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
printk(KERN_WARNING
"%s: %s qdisc %X: is non-work-conserving?\n",
txt, qdisc->ops->id, qdisc->handle >> 16);
qdisc->flags |= TCQ_F_WARN_NONWC;// 作为已经打印了警告信息的标志
}
}
EXPORT_SYMBOL(qdisc_warn_nonwc);
static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
{
struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
timer);
wd->qdisc->flags &= ~TCQ_F_THROTTLED;
__netif_schedule(qdisc_root(wd->qdisc));
return HRTIMER_NORESTART;
}
void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
{
hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
wd->timer.function = qdisc_watchdog;
wd->qdisc = qdisc;
}
EXPORT_SYMBOL(qdisc_watchdog_init);
void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires)
{
ktime_t time;
if (test_bit(__QDISC_STATE_DEACTIVATED,
&qdisc_root_sleeping(wd->qdisc)->state))
return;
wd->qdisc->flags |= TCQ_F_THROTTLED;
time = ktime_set(0, 0);
time = ktime_add_ns(time, PSCHED_TICKS2NS(expires));
hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS);
}
EXPORT_SYMBOL(qdisc_watchdog_schedule);
void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
{
hrtimer_cancel(&wd->timer);
wd->qdisc->flags &= ~TCQ_F_THROTTLED;
}
EXPORT_SYMBOL(qdisc_watchdog_cancel);
static struct hlist_head *qdisc_class_hash_alloc(unsigned int n)
{
unsigned int size = n * sizeof(struct hlist_head), i;
struct hlist_head *h;
if (size <= PAGE_SIZE)
h = kmalloc(size, GFP_KERNEL);
else
h = (struct hlist_head *)
__get_free_pages(GFP_KERNEL, get_order(size));
if (h != NULL) {
for (i = 0; i < n; i++)
INIT_HLIST_HEAD(&h[i]);
}
return h;
}
static void qdisc_class_hash_free(struct hlist_head *h, unsigned int n)
{
unsigned int size = n * sizeof(struct hlist_head);
if (size <= PAGE_SIZE)
kfree(h);
else
free_pages((unsigned long)h, get_order(size));
}
void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash)
{
struct Qdisc_class_common *cl;
struct hlist_node *n, *next;
struct hlist_head *nhash, *ohash;
unsigned int nsize, nmask, osize;
unsigned int i, h;
/* Rehash when load factor exceeds 0.75 */
if (clhash->hashelems * 4 <= clhash->hashsize * 3)//如果hash节点数hashelems超过设置的hashsize的0.75，则从新hash，hashsize扩大到之前hashsize两倍，见qdisc_class_hash_grow
return;
//实际hash数超过hashsize的0.75后，就要重新hash，hashsize扩大到原来的2倍
nsize = clhash->hashsize * 2;//如果hash节点数hashelems超过设置的hashsize的0.75，则从新hash，hashsize扩大到之前hashsize两倍，见qdisc_class_hash_grow
nmask = nsize - 1;
nhash = qdisc_class_hash_alloc(nsize); //创建nhash[]数组
if (nhash == NULL)
return;
ohash = clhash->hash;
osize = clhash->hashsize;
sch_tree_lock(sch);
for (i = 0; i < osize; i++) {
hlist_for_each_entry_safe(cl, n, next, &ohash[i], hnode) { //从新hash一次
h = qdisc_class_hash(cl->classid, nmask);
hlist_add_head(&cl->hnode, &nhash[h]);
}
}
clhash->hash = nhash;
clhash->hashsize = nsize;
clhash->hashmask = nmask;
sch_tree_unlock(sch);
qdisc_class_hash_free(ohash, osize);
}
EXPORT_SYMBOL(qdisc_class_hash_grow);
int qdisc_class_hash_init(struct Qdisc_class_hash *clhash)
{
unsigned int size = 4;
clhash->hash = qdisc_class_hash_alloc(size);
if (clhash->hash == NULL)
return -ENOMEM;
clhash->hashsize = size;
clhash->hashmask = size - 1;
clhash->hashelems = 0;
return 0;
}
EXPORT_SYMBOL(qdisc_class_hash_init);
void qdisc_class_hash_destroy(struct Qdisc_class_hash *clhash)
{
qdisc_class_hash_free(clhash->hash, clhash->hashsize);
}
EXPORT_SYMBOL(qdisc_class_hash_destroy);
void qdisc_class_hash_insert(struct Qdisc_class_hash *clhash,
struct Qdisc_class_common *cl)
{
unsigned int h;
INIT_HLIST_NODE(&cl->hnode);
h = qdisc_class_hash(cl->classid, clhash->hashmask);
hlist_add_head(&cl->hnode, &clhash->hash[h]);
clhash->hashelems++;
}
EXPORT_SYMBOL(qdisc_class_hash_insert);
void qdisc_class_hash_remove(struct Qdisc_class_hash *clhash,
struct Qdisc_class_common *cl)
{
hlist_del(&cl->hnode);
clhash->hashelems--;
}
EXPORT_SYMBOL(qdisc_class_hash_remove);
/* Allocate an unique handle from space managed by kernel */
static u32 qdisc_alloc_handle(struct net_device *dev)
{
int i = 0x10000;
static u32 autohandle = TC_H_MAKE(0x80000000U, 0);
do {
autohandle += TC_H_MAKE(0x10000U, 0);
if (autohandle == TC_H_MAKE(TC_H_ROOT, 0))
autohandle = TC_H_MAKE(0x80000000U, 0);
} while (qdisc_lookup(dev, autohandle) && --i > 0);
return i>0 ? autohandle : 0;
}
void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
{
const struct Qdisc_class_ops *cops;
unsigned long cl;
u32 parentid;
if (n == 0)
return;
while ((parentid = sch->parent)) {
if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
return;
sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
if (sch == NULL) {
WARN_ON(parentid != TC_H_ROOT);
return;
}
cops = sch->ops->cl_ops;
if (cops->qlen_notify) {
cl = cops->get(sch, parentid);
cops->qlen_notify(sch, cl);
cops->put(sch, cl);
}
sch->q.qlen -= n;
}
}
EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
static void notify_and_destroy(struct net *net, struct sk_buff *skb,
struct nlmsghdr *n, u32 clid,
struct Qdisc *old, struct Qdisc *new)
{
if (new || old)
qdisc_notify(net, skb, n, clid, old, new);
if (old)
qdisc_destroy(old);
}
/* Graft qdisc "new" to class "classid" of qdisc "parent" or
* to device "dev".
*
* When appropriate send a netlink notification using 'skb'
* and "n".
*
* On success, destroy old qdisc.
*/
/*
tc qdisc add dev eth0 parent 22:4 handle 33 prio bands 5 p为22对应的队列规程 q为33对应的队列规程
dev 上面的dev后面的eth0
parent:父Qdisc
skb:入队的skb
n:netlink发送的nlmsghdr结构
classid:父handle，上面的33
new:字Qdisc
*/
//添加子队列规程的时候，通过classid来进行分类，从而决定把子Qdisc添加到父Qdisc的那个分类信息中，一般一个Qdisc带多个分类信息，可以参考prio_qdisc_ops中的get和graft接口，就好理解了
static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
struct sk_buff *skb, struct nlmsghdr *n, u32 classid,
struct Qdisc *new, struct Qdisc *old)
{
struct Qdisc *q = old;
struct net *net = dev_net(dev);
int err = 0;
if (parent == NULL) { //如果是跟队列规程，则把该新的队列规程和dev设备关联起来
unsigned int i, num_q, ingress;
ingress = 0;
num_q = dev->num_tx_queues;
if ((q && q->flags & TCQ_F_INGRESS) ||
(new && new->flags & TCQ_F_INGRESS)) {
num_q = 1;
ingress = 1; //入口队列规程
}
if (dev->flags & IFF_UP)
dev_deactivate(dev);
if (new && new->ops->attach) { //prio_qdisc_ops
new->ops->attach(new);
num_q = 0;
}
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = &dev->rx_queue;
//////入口方向:ingress对应的是net_device dev中的rx_queue，出口方向为:net_device dev中的_tx[i]
if (!ingress)
dev_queue = netdev_get_tx_queue(dev, i);
old = dev_graft_qdisc(dev_queue, new);
//将跟Qdisc new和dev设备关联起来 保证net_device -> struct netdev_queue(这里有区分是如方向的还是出方向的qdisc)与该new qdisc关联起来
if (new && i > 0)
atomic_inc(&new->refcnt);
if (!ingress)
qdisc_destroy(old);
}
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
dev->qdisc, new);
if (new && !new->ops->attach)
atomic_inc(&new->refcnt);
dev->qdisc = new ? : &noop_qdisc; //dev->qdisc指向新创建的qdisc
} else {
notify_and_destroy(net, skb, n, classid, old, new);
}
if (dev->flags & IFF_UP)
dev_activate(dev);
} else {
const struct Qdisc_class_ops *cops = parent->ops->cl_ops;
err = -EOPNOTSUPP;
if (cops && cops->graft) { //以prio有类队列规程为例，见prio_qdisc_ops
//如果返回0，则表示选择分类数组的时候，选择的结果越过了分类数组，直接返回错误，例如prio中父Qdisc中设置的band频道位5，而创建子Qdisc的时候使用父parent 22:8表示选择8频道，越界了
unsigned long cl = cops->get(parent, classid);
if (cl) {
err = cops->graft(parent, cl, new, &old);
cops->put(parent, cl);
} else
err = -ENOENT;
}
if (!err)
notify_and_destroy(net, skb, n, classid, old, new);
}
return err;
}
/* lockdep annotation is needed for ingress; egress gets it only for name */
static struct lock_class_key qdisc_tx_lock;
static struct lock_class_key qdisc_rx_lock;
/*
Allocate and initialize new qdisc.
Parameters are passed via opt.
*/
//主要是创建Qdisc队列规程和对应的Qdisc_ops初始化，如fifo_init prio_init
static struct Qdisc *
qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
struct Qdisc *p, u32 parent, u32 handle,
struct nlattr **tca, int *errp)
{
int err;
struct nlattr *kind = tca[TCA_KIND];
struct Qdisc *sch;
struct Qdisc_ops *ops;
struct qdisc_size_table *stab;
ops = qdisc_lookup_ops(kind);
#ifdef CONFIG_MODULES
if (ops == NULL && kind != NULL) {
char name[IFNAMSIZ];
if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
* tell the caller to replay the request. We
* indicate this using -EAGAIN.
* We replay the request because the device may
* go away in the mean time.
*/
rtnl_unlock();
request_module("sch_%s", name);
rtnl_lock();
ops = qdisc_lookup_ops(kind);
if (ops != NULL) {
/* We will try again qdisc_lookup_ops,
* so don't keep a reference.
*/
module_put(ops->owner);
err = -EAGAIN;
goto err_out;
}
}
}
#endif
err = -ENOENT;
if (ops == NULL)
goto err_out;
sch = qdisc_alloc(dev_queue, ops);
if (IS_ERR(sch)) {
err = PTR_ERR(sch);
goto err_out2;
}
sch->parent = parent;
if (handle == TC_H_INGRESS) {
sch->flags |= TCQ_F_INGRESS;
handle = TC_H_MAKE(TC_H_INGRESS, 0);
lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock);
} else {
if (handle == 0) {
handle = qdisc_alloc_handle(dev);//自动分配一个handle
err = -ENOMEM;
if (handle == 0)
goto err_out3;
}
lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
}
sch->handle = handle;
if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {//如果为prio队列规定，prio_init初始化prio参数
if (tca[TCA_STAB]) {
stab = qdisc_get_stab(tca[TCA_STAB]);
if (IS_ERR(stab)) {
err = PTR_ERR(stab);
goto err_out4;
}
sch->stab = stab;
}
if (tca[TCA_RATE]) {//cbq队列规则中的rate参数
spinlock_t *root_lock;
err = -EOPNOTSUPP;
if (sch->flags & TCQ_F_MQROOT)
goto err_out4;
if ((sch->parent != TC_H_ROOT) &&
!(sch->flags & TCQ_F_INGRESS) &&
(!p || !(p->flags & TCQ_F_MQROOT)))
root_lock = qdisc_root_sleeping_lock(sch);
else
root_lock = qdisc_lock(sch);
err = gen_new_estimator(&sch->bstats, &sch->rate_est,
root_lock, tca[TCA_RATE]);
if (err)
goto err_out4;
}
qdisc_list_add(sch);
return sch;
}
err_out3:
dev_put(dev);
kfree((char *) sch - sch->padded);
err_out2:
module_put(ops->owner);
err_out:
*errp = err;
return NULL;
err_out4:
/*
* Any broken qdiscs that would require a ops->reset() here?
* The qdisc was never in action so it shouldn't be necessary.
*/
qdisc_put_stab(sch->stab);
if (ops->destroy)
ops->destroy(sch);
goto err_out3;
}
static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
{
struct qdisc_size_table *stab = NULL;
int err = 0;
if (tca[TCA_OPTIONS]) {
if (sch->ops->change == NULL)
return -EINVAL;
err = sch->ops->change(sch, tca[TCA_OPTIONS]);
if (err)
return err;
}
if (tca[TCA_STAB]) {
stab = qdisc_get_stab(tca[TCA_STAB]);
if (IS_ERR(stab))
return PTR_ERR(stab);
}
qdisc_put_stab(sch->stab);
sch->stab = stab;
if (tca[TCA_RATE]) {
/* NB: ignores errors from replace_estimator
because change can't be undone. */
if (sch->flags & TCQ_F_MQROOT)
goto out;
gen_replace_estimator(&sch->bstats, &sch->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
}
out:
return 0;
}
struct check_loop_arg
{
struct qdisc_walker w;
struct Qdisc *p;
int depth;
};
static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w);
static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth)
{
struct check_loop_arg arg;
if (q->ops->cl_ops == NULL)
return 0;
arg.w.stop = arg.w.skip = arg.w.count = 0;
arg.w.fn = check_loop_fn;
arg.depth = depth;
arg.p = p;
q->ops->cl_ops->walk(q, &arg.w);
return arg.w.stop ? -ELOOP : 0;
}
static int
check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
{
struct Qdisc *leaf;
const struct Qdisc_class_ops *cops = q->ops->cl_ops;
struct check_loop_arg *arg = (struct check_loop_arg *)w;
leaf = cops->leaf(q, cl);
if (leaf) {
if (leaf == arg->p || arg->depth > 7)
return -ELOOP;
return check_loop(leaf, arg->p, arg->depth + 1);
}
return 0;
}
/*
* Delete/get qdisc.
*/
//理解参考pktsched_init
static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
struct tcmsg *tcm = NLMSG_DATA(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
u32 clid = tcm->tcm_parent;
struct Qdisc *q = NULL;
struct Qdisc *p = NULL;
int err;
if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
return -ENODEV;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
if (err < 0)
return err;
if (clid) {
if (clid != TC_H_ROOT) {
if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) {
if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL)
return -ENOENT;
q = qdisc_leaf(p, clid);
} else { /* ingress */
q = dev->rx_queue.qdisc_sleeping;
}
} else {
q = dev->qdisc;
}
if (!q)
return -ENOENT;
if (tcm->tcm_handle && q->handle != tcm->tcm_handle)
return -EINVAL;
} else {
if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL)