forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
sch_generic.c
1607 lines (1349 loc) · 38.3 KB
/
sch_generic.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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/sch_generic.c Generic packet scheduler routines.
*
* Authors: Alexey Kuznetsov, <[email protected]>
* Jamal Hadi Salim, <[email protected]> 990601
* - Ingress support
*/
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/if_vlan.h>
#include <linux/skb_array.h>
#include <linux/if_macvlan.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
#include <trace/events/qdisc.h>
#include <trace/events/net.h>
#include <net/xfrm.h>
/* Qdisc to use by default */
const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
EXPORT_SYMBOL(default_qdisc_ops);
static void qdisc_maybe_clear_missed(struct Qdisc *q,
const struct netdev_queue *txq)
{
clear_bit(__QDISC_STATE_MISSED, &q->state);
/* Make sure the below netif_xmit_frozen_or_stopped()
* checking happens after clearing STATE_MISSED.
*/
smp_mb__after_atomic();
/* Checking netif_xmit_frozen_or_stopped() again to
* make sure STATE_MISSED is set if the STATE_MISSED
* set by netif_tx_wake_queue()'s rescheduling of
* net_tx_action() is cleared by the above clear_bit().
*/
if (!netif_xmit_frozen_or_stopped(txq))
set_bit(__QDISC_STATE_MISSED, &q->state);
else
set_bit(__QDISC_STATE_DRAINING, &q->state);
}
/* Main transmission queue. */
/* Modifications to data participating in scheduling must be protected with
* qdisc_lock(qdisc) spinlock.
*
* The idea is the following:
* - enqueue, dequeue are serialized via qdisc root lock
* - ingress filtering is also serialized via qdisc root lock
* - updates to tree and tree walking are only done under the rtnl mutex.
*/
#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL)
static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
{
const struct netdev_queue *txq = q->dev_queue;
spinlock_t *lock = NULL;
struct sk_buff *skb;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
skb = skb_peek(&q->skb_bad_txq);
if (skb) {
/* check the reason of requeuing without tx lock first */
txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
skb = __skb_dequeue(&q->skb_bad_txq);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
skb = SKB_XOFF_MAGIC;
qdisc_maybe_clear_missed(q, txq);
}
}
if (lock)
spin_unlock(lock);
return skb;
}
static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q)
{
struct sk_buff *skb = skb_peek(&q->skb_bad_txq);
if (unlikely(skb))
skb = __skb_dequeue_bad_txq(q);
return skb;
}
static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
struct sk_buff *skb)
{
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
__skb_queue_tail(&q->skb_bad_txq, skb);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_inc(q, skb);
qdisc_qstats_cpu_qlen_inc(q);
} else {
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
if (lock)
spin_unlock(lock);
}
static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
while (skb) {
struct sk_buff *next = skb->next;
__skb_queue_tail(&q->gso_skb, skb);
/* it's still part of the queue */
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_requeues_inc(q);
qdisc_qstats_cpu_backlog_inc(q, skb);
qdisc_qstats_cpu_qlen_inc(q);
} else {
q->qstats.requeues++;
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
skb = next;
}
if (lock) {
spin_unlock(lock);
set_bit(__QDISC_STATE_MISSED, &q->state);
} else {
__netif_schedule(q);
}
}
static void try_bulk_dequeue_skb(struct Qdisc *q,
struct sk_buff *skb,
const struct netdev_queue *txq,
int *packets)
{
int bytelimit = qdisc_avail_bulklimit(txq) - skb->len;
while (bytelimit > 0) {
struct sk_buff *nskb = q->dequeue(q);
if (!nskb)
break;
bytelimit -= nskb->len; /* covers GSO len */
skb->next = nskb;
skb = nskb;
(*packets)++; /* GSO counts as one pkt */
}
skb_mark_not_on_list(skb);
}
/* This variant of try_bulk_dequeue_skb() makes sure
* all skbs in the chain are for the same txq
*/
static void try_bulk_dequeue_skb_slow(struct Qdisc *q,
struct sk_buff *skb,
int *packets)
{
int mapping = skb_get_queue_mapping(skb);
struct sk_buff *nskb;
int cnt = 0;
do {
nskb = q->dequeue(q);
if (!nskb)
break;
if (unlikely(skb_get_queue_mapping(nskb) != mapping)) {
qdisc_enqueue_skb_bad_txq(q, nskb);
break;
}
skb->next = nskb;
skb = nskb;
} while (++cnt < 8);
(*packets) += cnt;
skb_mark_not_on_list(skb);
}
/* Note that dequeue_skb can possibly return a SKB list (via skb->next).
* A requeued skb (via q->gso_skb) can also be a SKB list.
*/
static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
int *packets)
{
const struct netdev_queue *txq = q->dev_queue;
struct sk_buff *skb = NULL;
*packets = 1;
if (unlikely(!skb_queue_empty(&q->gso_skb))) {
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
skb = skb_peek(&q->gso_skb);
/* skb may be null if another cpu pulls gso_skb off in between
* empty check and lock.
*/
if (!skb) {
if (lock)
spin_unlock(lock);
goto validate;
}
/* skb in gso_skb were already validated */
*validate = false;
if (xfrm_offload(skb))
*validate = true;
/* check the reason of requeuing without tx lock first */
txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
skb = __skb_dequeue(&q->gso_skb);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
skb = NULL;
qdisc_maybe_clear_missed(q, txq);
}
if (lock)
spin_unlock(lock);
goto trace;
}
validate:
*validate = true;
if ((q->flags & TCQ_F_ONETXQUEUE) &&
netif_xmit_frozen_or_stopped(txq)) {
qdisc_maybe_clear_missed(q, txq);
return skb;
}
skb = qdisc_dequeue_skb_bad_txq(q);
if (unlikely(skb)) {
if (skb == SKB_XOFF_MAGIC)
return NULL;
goto bulk;
}
skb = q->dequeue(q);
if (skb) {
bulk:
if (qdisc_may_bulk(q))
try_bulk_dequeue_skb(q, skb, txq, packets);
else
try_bulk_dequeue_skb_slow(q, skb, packets);
}
trace:
trace_qdisc_dequeue(q, txq, *packets, skb);
return skb;
}
/*
* Transmit possibly several skbs, and handle the return status as
* required. Owning qdisc running bit guarantees that only one CPU
* can execute this function.
*
* Returns to the caller:
* false - hardware queue frozen backoff
* true - feel free to send more pkts
*/
bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev, struct netdev_queue *txq,
spinlock_t *root_lock, bool validate)
{
int ret = NETDEV_TX_BUSY;
bool again = false;
/* And release qdisc */
if (root_lock)
spin_unlock(root_lock);
/* Note that we validate skb (GSO, checksum, ...) outside of locks */
if (validate)
skb = validate_xmit_skb_list(skb, dev, &again);
#ifdef CONFIG_XFRM_OFFLOAD
if (unlikely(again)) {
if (root_lock)
spin_lock(root_lock);
dev_requeue_skb(skb, q);
return false;
}
#endif
if (likely(skb)) {
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
skb = dev_hard_start_xmit(skb, dev, txq, &ret);
else
qdisc_maybe_clear_missed(q, txq);
HARD_TX_UNLOCK(dev, txq);
} else {
if (root_lock)
spin_lock(root_lock);
return true;
}
if (root_lock)
spin_lock(root_lock);
if (!dev_xmit_complete(ret)) {
/* Driver returned NETDEV_TX_BUSY - requeue skb */
if (unlikely(ret != NETDEV_TX_BUSY))
net_warn_ratelimited("BUG %s code %d qlen %d\n",
dev->name, ret, q->q.qlen);
dev_requeue_skb(skb, q);
return false;
}
return true;
}
/*
* NOTE: Called under qdisc_lock(q) with locally disabled BH.
*
* running seqcount guarantees only one CPU can process
* this qdisc at a time. qdisc_lock(q) serializes queue accesses for
* this queue.
*
* netif_tx_lock serializes accesses to device driver.
*
* qdisc_lock(q) and netif_tx_lock are mutually exclusive,
* if one is grabbed, another must be free.
*
* Note, that this procedure can be called by a watchdog timer
*
* Returns to the caller:
* 0 - queue is empty or throttled.
* >0 - queue is not empty.
*
*/
static inline bool qdisc_restart(struct Qdisc *q, int *packets)
{
spinlock_t *root_lock = NULL;
struct netdev_queue *txq;
struct net_device *dev;
struct sk_buff *skb;
bool validate;
/* Dequeue packet */
skb = dequeue_skb(q, &validate, packets);
if (unlikely(!skb))
return false;
if (!(q->flags & TCQ_F_NOLOCK))
root_lock = qdisc_lock(q);
dev = qdisc_dev(q);
txq = skb_get_tx_queue(dev, skb);
return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
}
void __qdisc_run(struct Qdisc *q)
{
int quota = dev_tx_weight;
int packets;
while (qdisc_restart(q, &packets)) {
quota -= packets;
if (quota <= 0) {
if (q->flags & TCQ_F_NOLOCK)
set_bit(__QDISC_STATE_MISSED, &q->state);
else
__netif_schedule(q);
break;
}
}
}
unsigned long dev_trans_start(struct net_device *dev)
{
unsigned long val, res;
unsigned int i;
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
else if (netif_is_macvlan(dev))
dev = macvlan_dev_real_dev(dev);
res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start);
for (i = 1; i < dev->num_tx_queues; i++) {
val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start);
if (val && time_after(val, res))
res = val;
}
return res;
}
EXPORT_SYMBOL(dev_trans_start);
static void netif_freeze_queues(struct net_device *dev)
{
unsigned int i;
int cpu;
cpu = smp_processor_id();
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* We are the only thread of execution doing a
* freeze, but we have to grab the _xmit_lock in
* order to synchronize with threads which are in
* the ->hard_start_xmit() handler and already
* checked the frozen bit.
*/
__netif_tx_lock(txq, cpu);
set_bit(__QUEUE_STATE_FROZEN, &txq->state);
__netif_tx_unlock(txq);
}
}
void netif_tx_lock(struct net_device *dev)
{
spin_lock(&dev->tx_global_lock);
netif_freeze_queues(dev);
}
EXPORT_SYMBOL(netif_tx_lock);
static void netif_unfreeze_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* No need to grab the _xmit_lock here. If the
* queue is not stopped for another reason, we
* force a schedule.
*/
clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
netif_schedule_queue(txq);
}
}
void netif_tx_unlock(struct net_device *dev)
{
netif_unfreeze_queues(dev);
spin_unlock(&dev->tx_global_lock);
}
EXPORT_SYMBOL(netif_tx_unlock);
static void dev_watchdog(struct timer_list *t)
{
struct net_device *dev = from_timer(dev, t, watchdog_timer);
bool release = true;
spin_lock(&dev->tx_global_lock);
if (!qdisc_tx_is_noop(dev)) {
if (netif_device_present(dev) &&
netif_running(dev) &&
netif_carrier_ok(dev)) {
int some_queue_timedout = 0;
unsigned int i;
unsigned long trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i);
trans_start = READ_ONCE(txq->trans_start);
if (netif_xmit_stopped(txq) &&
time_after(jiffies, (trans_start +
dev->watchdog_timeo))) {
some_queue_timedout = 1;
atomic_long_inc(&txq->trans_timeout);
break;
}
}
if (unlikely(some_queue_timedout)) {
trace_net_dev_xmit_timeout(dev, i);
WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
dev->name, netdev_drivername(dev), i);
netif_freeze_queues(dev);
dev->netdev_ops->ndo_tx_timeout(dev, i);
netif_unfreeze_queues(dev);
}
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies +
dev->watchdog_timeo)))
release = false;
}
}
spin_unlock(&dev->tx_global_lock);
if (release)
dev_put_track(dev, &dev->watchdog_dev_tracker);
}
void __netdev_watchdog_up(struct net_device *dev)
{
if (dev->netdev_ops->ndo_tx_timeout) {
if (dev->watchdog_timeo <= 0)
dev->watchdog_timeo = 5*HZ;
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies + dev->watchdog_timeo)))
dev_hold_track(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC);
}
}
EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
static void dev_watchdog_up(struct net_device *dev)
{
__netdev_watchdog_up(dev);
}
static void dev_watchdog_down(struct net_device *dev)
{
netif_tx_lock_bh(dev);
if (del_timer(&dev->watchdog_timer))
dev_put_track(dev, &dev->watchdog_dev_tracker);
netif_tx_unlock_bh(dev);
}
/**
* netif_carrier_on - set carrier
* @dev: network device
*
* Device has detected acquisition of carrier.
*/
void netif_carrier_on(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_up_count);
linkwatch_fire_event(dev);
if (netif_running(dev))
__netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_carrier_on);
/**
* netif_carrier_off - clear carrier
* @dev: network device
*
* Device has detected loss of carrier.
*/
void netif_carrier_off(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_down_count);
linkwatch_fire_event(dev);
}
}
EXPORT_SYMBOL(netif_carrier_off);
/**
* netif_carrier_event - report carrier state event
* @dev: network device
*
* Device has detected a carrier event but the carrier state wasn't changed.
* Use in drivers when querying carrier state asynchronously, to avoid missing
* events (link flaps) if link recovers before it's queried.
*/
void netif_carrier_event(struct net_device *dev)
{
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_up_count);
atomic_inc(&dev->carrier_down_count);
linkwatch_fire_event(dev);
}
EXPORT_SYMBOL_GPL(netif_carrier_event);
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
cheaper.
*/
static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
{
__qdisc_drop(skb, to_free);
return NET_XMIT_CN;
}
static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
{
return NULL;
}
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct netdev_queue noop_netdev_queue = {
RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc),
.qdisc_sleeping = &noop_qdisc,
};
struct Qdisc noop_qdisc = {
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.flags = TCQ_F_BUILTIN,
.ops = &noop_qdisc_ops,
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.dev_queue = &noop_netdev_queue,
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
.gso_skb = {
.next = (struct sk_buff *)&noop_qdisc.gso_skb,
.prev = (struct sk_buff *)&noop_qdisc.gso_skb,
.qlen = 0,
.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock),
},
.skb_bad_txq = {
.next = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
.prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
.qlen = 0,
.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock),
},
};
EXPORT_SYMBOL(noop_qdisc);
static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
/* register_qdisc() assigns a default of noop_enqueue if unset,
* but __dev_queue_xmit() treats noqueue only as such
* if this is NULL - so clear it here. */
qdisc->enqueue = NULL;
return 0;
}
struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
.id = "noqueue",
.priv_size = 0,
.init = noqueue_init,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static const u8 prio2band[TC_PRIO_MAX + 1] = {
1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
};
/* 3-band FIFO queue: old style, but should be a bit faster than
generic prio+fifo combination.
*/
#define PFIFO_FAST_BANDS 3
/*
* Private data for a pfifo_fast scheduler containing:
* - rings for priority bands
*/
struct pfifo_fast_priv {
struct skb_array q[PFIFO_FAST_BANDS];
};
static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
int band)
{
return &priv->q[band];
}
static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
{
int band = prio2band[skb->priority & TC_PRIO_MAX];
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct skb_array *q = band2list(priv, band);
unsigned int pkt_len = qdisc_pkt_len(skb);
int err;
err = skb_array_produce(q, skb);
if (unlikely(err)) {
if (qdisc_is_percpu_stats(qdisc))
return qdisc_drop_cpu(skb, qdisc, to_free);
else
return qdisc_drop(skb, qdisc, to_free);
}
qdisc_update_stats_at_enqueue(qdisc, pkt_len);
return NET_XMIT_SUCCESS;
}
static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff *skb = NULL;
bool need_retry = true;
int band;
retry:
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
if (__skb_array_empty(q))
continue;
skb = __skb_array_consume(q);
}
if (likely(skb)) {
qdisc_update_stats_at_dequeue(qdisc, skb);
} else if (need_retry &&
READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) {
/* Delay clearing the STATE_MISSED here to reduce
* the overhead of the second spin_trylock() in
* qdisc_run_begin() and __netif_schedule() calling
* in qdisc_run_end().
*/
clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
/* Make sure dequeuing happens after clearing
* STATE_MISSED.
*/
smp_mb__after_atomic();
need_retry = false;
goto retry;
}
return skb;
}
static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff *skb = NULL;
int band;
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
skb = __skb_array_peek(q);
}
return skb;
}
static void pfifo_fast_reset(struct Qdisc *qdisc)
{
int i, band;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (band = 0; band < PFIFO_FAST_BANDS; band++) {
struct skb_array *q = band2list(priv, band);
struct sk_buff *skb;
/* NULL ring is possible if destroy path is due to a failed
* skb_array_init() in pfifo_fast_init() case.
*/
if (!q->ring.queue)
continue;
while ((skb = __skb_array_consume(q)) != NULL)
kfree_skb(skb);
}
if (qdisc_is_percpu_stats(qdisc)) {
for_each_possible_cpu(i) {
struct gnet_stats_queue *q;
q = per_cpu_ptr(qdisc->cpu_qstats, i);
q->backlog = 0;
q->qlen = 0;
}
}
}
static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
{
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
return skb->len;
nla_put_failure:
return -1;
}
static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
int prio;
/* guard against zero length rings */
if (!qlen)
return -EINVAL;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
int err;
err = skb_array_init(q, qlen, GFP_KERNEL);
if (err)
return -ENOMEM;
}
/* Can by-pass the queue discipline */
qdisc->flags |= TCQ_F_CAN_BYPASS;
return 0;
}
static void pfifo_fast_destroy(struct Qdisc *sch)
{
struct pfifo_fast_priv *priv = qdisc_priv(sch);
int prio;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
/* NULL ring is possible if destroy path is due to a failed
* skb_array_init() in pfifo_fast_init() case.
*/
if (!q->ring.queue)
continue;
/* Destroy ring but no need to kfree_skb because a call to
* pfifo_fast_reset() has already done that work.
*/
ptr_ring_cleanup(&q->ring, NULL);
}
}
static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch,
unsigned int new_len)
{
struct pfifo_fast_priv *priv = qdisc_priv(sch);
struct skb_array *bands[PFIFO_FAST_BANDS];
int prio;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
bands[prio] = q;
}
return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len,
GFP_KERNEL);
}
struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.id = "pfifo_fast",
.priv_size = sizeof(struct pfifo_fast_priv),
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
.peek = pfifo_fast_peek,
.init = pfifo_fast_init,
.destroy = pfifo_fast_destroy,
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
.change_tx_queue_len = pfifo_fast_change_tx_queue_len,
.owner = THIS_MODULE,
.static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS,
};
EXPORT_SYMBOL(pfifo_fast_ops);
static struct lock_class_key qdisc_tx_busylock;
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops,
struct netlink_ext_ack *extack)
{
struct Qdisc *sch;
unsigned int size = sizeof(*sch) + ops->priv_size;
int err = -ENOBUFS;
struct net_device *dev;
if (!dev_queue) {
NL_SET_ERR_MSG(extack, "No device queue given");
err = -EINVAL;
goto errout;
}
dev = dev_queue->dev;
sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue));
if (!sch)
goto errout;
__skb_queue_head_init(&sch->gso_skb);
__skb_queue_head_init(&sch->skb_bad_txq);
qdisc_skb_head_init(&sch->q);
gnet_stats_basic_sync_init(&sch->bstats);
spin_lock_init(&sch->q.lock);
if (ops->static_flags & TCQ_F_CPUSTATS) {
sch->cpu_bstats =
netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync);
if (!sch->cpu_bstats)
goto errout1;
sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
if (!sch->cpu_qstats) {
free_percpu(sch->cpu_bstats);
goto errout1;
}
}
spin_lock_init(&sch->busylock);
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
/* seqlock has the same scope of busylock, for NOLOCK qdisc */
spin_lock_init(&sch->seqlock);
lockdep_set_class(&sch->seqlock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
sch->ops = ops;
sch->flags = ops->static_flags;
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
sch->dev_queue = dev_queue;
dev_hold_track(dev, &sch->dev_tracker, GFP_KERNEL);
refcount_set(&sch->refcnt, 1);
return sch;
errout1:
kfree(sch);
errout:
return ERR_PTR(err);
}
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops,
unsigned int parentid,
struct netlink_ext_ack *extack)
{
struct Qdisc *sch;
if (!try_module_get(ops->owner)) {
NL_SET_ERR_MSG(extack, "Failed to increase module reference counter");
return NULL;
}
sch = qdisc_alloc(dev_queue, ops, extack);