forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsch_taprio.c
2288 lines (1842 loc) · 58.1 KB
/
sch_taprio.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
/* net/sched/sch_taprio.c Time Aware Priority Scheduler
*
* Authors: Vinicius Costa Gomes <[email protected]>
*
*/
#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/math64.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/time.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/sch_generic.h>
#include <net/sock.h>
#include <net/tcp.h>
#include "sch_mqprio_lib.h"
static LIST_HEAD(taprio_list);
static struct static_key_false taprio_have_broken_mqprio;
static struct static_key_false taprio_have_working_mqprio;
#define TAPRIO_ALL_GATES_OPEN -1
#define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)
#define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)
#define TAPRIO_FLAGS_INVALID U32_MAX
struct sched_entry {
/* Durations between this GCL entry and the GCL entry where the
* respective traffic class gate closes
*/
u64 gate_duration[TC_MAX_QUEUE];
atomic_t budget[TC_MAX_QUEUE];
struct list_head list;
/* The instant that this entry ends and the next one
* should open, the qdisc will make some effort so that no
* packet leaves after this time.
*/
ktime_t end_time;
ktime_t next_txtime;
int index;
u32 gate_mask;
u32 interval;
u8 command;
};
struct sched_gate_list {
/* Longest non-zero contiguous gate durations per traffic class,
* or 0 if a traffic class gate never opens during the schedule.
*/
u64 max_open_gate_duration[TC_MAX_QUEUE];
struct rcu_head rcu;
struct list_head entries;
size_t num_entries;
ktime_t cycle_end_time;
s64 cycle_time;
s64 cycle_time_extension;
s64 base_time;
};
struct taprio_sched {
struct Qdisc **qdiscs;
struct Qdisc *root;
u32 flags;
enum tk_offsets tk_offset;
int clockid;
bool offloaded;
bool detected_mqprio;
bool broken_mqprio;
atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+
* speeds it's sub-nanoseconds per byte
*/
/* Protects the update side of the RCU protected current_entry */
spinlock_t current_entry_lock;
struct sched_entry __rcu *current_entry;
struct sched_gate_list __rcu *oper_sched;
struct sched_gate_list __rcu *admin_sched;
struct hrtimer advance_timer;
struct list_head taprio_list;
int cur_txq[TC_MAX_QUEUE];
u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */
u32 max_sdu[TC_MAX_QUEUE]; /* for dump and offloading */
u32 txtime_delay;
};
struct __tc_taprio_qopt_offload {
refcount_t users;
struct tc_taprio_qopt_offload offload;
};
static void taprio_calculate_gate_durations(struct taprio_sched *q,
struct sched_gate_list *sched)
{
struct net_device *dev = qdisc_dev(q->root);
int num_tc = netdev_get_num_tc(dev);
struct sched_entry *entry, *cur;
int tc;
list_for_each_entry(entry, &sched->entries, list) {
u32 gates_still_open = entry->gate_mask;
/* For each traffic class, calculate each open gate duration,
* starting at this schedule entry and ending at the schedule
* entry containing a gate close event for that TC.
*/
cur = entry;
do {
if (!gates_still_open)
break;
for (tc = 0; tc < num_tc; tc++) {
if (!(gates_still_open & BIT(tc)))
continue;
if (cur->gate_mask & BIT(tc))
entry->gate_duration[tc] += cur->interval;
else
gates_still_open &= ~BIT(tc);
}
cur = list_next_entry_circular(cur, &sched->entries, list);
} while (cur != entry);
/* Keep track of the maximum gate duration for each traffic
* class, taking care to not confuse a traffic class which is
* temporarily closed with one that is always closed.
*/
for (tc = 0; tc < num_tc; tc++)
if (entry->gate_duration[tc] &&
sched->max_open_gate_duration[tc] < entry->gate_duration[tc])
sched->max_open_gate_duration[tc] = entry->gate_duration[tc];
}
}
static ktime_t sched_base_time(const struct sched_gate_list *sched)
{
if (!sched)
return KTIME_MAX;
return ns_to_ktime(sched->base_time);
}
static ktime_t taprio_mono_to_any(const struct taprio_sched *q, ktime_t mono)
{
/* This pairs with WRITE_ONCE() in taprio_parse_clockid() */
enum tk_offsets tk_offset = READ_ONCE(q->tk_offset);
switch (tk_offset) {
case TK_OFFS_MAX:
return mono;
default:
return ktime_mono_to_any(mono, tk_offset);
}
}
static ktime_t taprio_get_time(const struct taprio_sched *q)
{
return taprio_mono_to_any(q, ktime_get());
}
static void taprio_free_sched_cb(struct rcu_head *head)
{
struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu);
struct sched_entry *entry, *n;
list_for_each_entry_safe(entry, n, &sched->entries, list) {
list_del(&entry->list);
kfree(entry);
}
kfree(sched);
}
static void switch_schedules(struct taprio_sched *q,
struct sched_gate_list **admin,
struct sched_gate_list **oper)
{
rcu_assign_pointer(q->oper_sched, *admin);
rcu_assign_pointer(q->admin_sched, NULL);
if (*oper)
call_rcu(&(*oper)->rcu, taprio_free_sched_cb);
*oper = *admin;
*admin = NULL;
}
/* Get how much time has been already elapsed in the current cycle. */
static s32 get_cycle_time_elapsed(struct sched_gate_list *sched, ktime_t time)
{
ktime_t time_since_sched_start;
s32 time_elapsed;
time_since_sched_start = ktime_sub(time, sched->base_time);
div_s64_rem(time_since_sched_start, sched->cycle_time, &time_elapsed);
return time_elapsed;
}
static ktime_t get_interval_end_time(struct sched_gate_list *sched,
struct sched_gate_list *admin,
struct sched_entry *entry,
ktime_t intv_start)
{
s32 cycle_elapsed = get_cycle_time_elapsed(sched, intv_start);
ktime_t intv_end, cycle_ext_end, cycle_end;
cycle_end = ktime_add_ns(intv_start, sched->cycle_time - cycle_elapsed);
intv_end = ktime_add_ns(intv_start, entry->interval);
cycle_ext_end = ktime_add(cycle_end, sched->cycle_time_extension);
if (ktime_before(intv_end, cycle_end))
return intv_end;
else if (admin && admin != sched &&
ktime_after(admin->base_time, cycle_end) &&
ktime_before(admin->base_time, cycle_ext_end))
return admin->base_time;
else
return cycle_end;
}
static int length_to_duration(struct taprio_sched *q, int len)
{
return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC);
}
/* Returns the entry corresponding to next available interval. If
* validate_interval is set, it only validates whether the timestamp occurs
* when the gate corresponding to the skb's traffic class is open.
*/
static struct sched_entry *find_entry_to_transmit(struct sk_buff *skb,
struct Qdisc *sch,
struct sched_gate_list *sched,
struct sched_gate_list *admin,
ktime_t time,
ktime_t *interval_start,
ktime_t *interval_end,
bool validate_interval)
{
ktime_t curr_intv_start, curr_intv_end, cycle_end, packet_transmit_time;
ktime_t earliest_txtime = KTIME_MAX, txtime, cycle, transmit_end_time;
struct sched_entry *entry = NULL, *entry_found = NULL;
struct taprio_sched *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
bool entry_available = false;
s32 cycle_elapsed;
int tc, n;
tc = netdev_get_prio_tc_map(dev, skb->priority);
packet_transmit_time = length_to_duration(q, qdisc_pkt_len(skb));
*interval_start = 0;
*interval_end = 0;
if (!sched)
return NULL;
cycle = sched->cycle_time;
cycle_elapsed = get_cycle_time_elapsed(sched, time);
curr_intv_end = ktime_sub_ns(time, cycle_elapsed);
cycle_end = ktime_add_ns(curr_intv_end, cycle);
list_for_each_entry(entry, &sched->entries, list) {
curr_intv_start = curr_intv_end;
curr_intv_end = get_interval_end_time(sched, admin, entry,
curr_intv_start);
if (ktime_after(curr_intv_start, cycle_end))
break;
if (!(entry->gate_mask & BIT(tc)) ||
packet_transmit_time > entry->interval)
continue;
txtime = entry->next_txtime;
if (ktime_before(txtime, time) || validate_interval) {
transmit_end_time = ktime_add_ns(time, packet_transmit_time);
if ((ktime_before(curr_intv_start, time) &&
ktime_before(transmit_end_time, curr_intv_end)) ||
(ktime_after(curr_intv_start, time) && !validate_interval)) {
entry_found = entry;
*interval_start = curr_intv_start;
*interval_end = curr_intv_end;
break;
} else if (!entry_available && !validate_interval) {
/* Here, we are just trying to find out the
* first available interval in the next cycle.
*/
entry_available = true;
entry_found = entry;
*interval_start = ktime_add_ns(curr_intv_start, cycle);
*interval_end = ktime_add_ns(curr_intv_end, cycle);
}
} else if (ktime_before(txtime, earliest_txtime) &&
!entry_available) {
earliest_txtime = txtime;
entry_found = entry;
n = div_s64(ktime_sub(txtime, curr_intv_start), cycle);
*interval_start = ktime_add(curr_intv_start, n * cycle);
*interval_end = ktime_add(curr_intv_end, n * cycle);
}
}
return entry_found;
}
static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch)
{
struct taprio_sched *q = qdisc_priv(sch);
struct sched_gate_list *sched, *admin;
ktime_t interval_start, interval_end;
struct sched_entry *entry;
rcu_read_lock();
sched = rcu_dereference(q->oper_sched);
admin = rcu_dereference(q->admin_sched);
entry = find_entry_to_transmit(skb, sch, sched, admin, skb->tstamp,
&interval_start, &interval_end, true);
rcu_read_unlock();
return entry;
}
static bool taprio_flags_valid(u32 flags)
{
/* Make sure no other flag bits are set. */
if (flags & ~(TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST |
TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD))
return false;
/* txtime-assist and full offload are mutually exclusive */
if ((flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) &&
(flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD))
return false;
return true;
}
/* This returns the tstamp value set by TCP in terms of the set clock. */
static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb)
{
unsigned int offset = skb_network_offset(skb);
const struct ipv6hdr *ipv6h;
const struct iphdr *iph;
struct ipv6hdr _ipv6h;
ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
if (!ipv6h)
return 0;
if (ipv6h->version == 4) {
iph = (struct iphdr *)ipv6h;
offset += iph->ihl * 4;
/* special-case 6in4 tunnelling, as that is a common way to get
* v6 connectivity in the home
*/
if (iph->protocol == IPPROTO_IPV6) {
ipv6h = skb_header_pointer(skb, offset,
sizeof(_ipv6h), &_ipv6h);
if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP)
return 0;
} else if (iph->protocol != IPPROTO_TCP) {
return 0;
}
} else if (ipv6h->version == 6 && ipv6h->nexthdr != IPPROTO_TCP) {
return 0;
}
return taprio_mono_to_any(q, skb->skb_mstamp_ns);
}
/* There are a few scenarios where we will have to modify the txtime from
* what is read from next_txtime in sched_entry. They are:
* 1. If txtime is in the past,
* a. The gate for the traffic class is currently open and packet can be
* transmitted before it closes, schedule the packet right away.
* b. If the gate corresponding to the traffic class is going to open later
* in the cycle, set the txtime of packet to the interval start.
* 2. If txtime is in the future, there are packets corresponding to the
* current traffic class waiting to be transmitted. So, the following
* possibilities exist:
* a. We can transmit the packet before the window containing the txtime
* closes.
* b. The window might close before the transmission can be completed
* successfully. So, schedule the packet in the next open window.
*/
static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch)
{
ktime_t transmit_end_time, interval_end, interval_start, tcp_tstamp;
struct taprio_sched *q = qdisc_priv(sch);
struct sched_gate_list *sched, *admin;
ktime_t minimum_time, now, txtime;
int len, packet_transmit_time;
struct sched_entry *entry;
bool sched_changed;
now = taprio_get_time(q);
minimum_time = ktime_add_ns(now, q->txtime_delay);
tcp_tstamp = get_tcp_tstamp(q, skb);
minimum_time = max_t(ktime_t, minimum_time, tcp_tstamp);
rcu_read_lock();
admin = rcu_dereference(q->admin_sched);
sched = rcu_dereference(q->oper_sched);
if (admin && ktime_after(minimum_time, admin->base_time))
switch_schedules(q, &admin, &sched);
/* Until the schedule starts, all the queues are open */
if (!sched || ktime_before(minimum_time, sched->base_time)) {
txtime = minimum_time;
goto done;
}
len = qdisc_pkt_len(skb);
packet_transmit_time = length_to_duration(q, len);
do {
sched_changed = false;
entry = find_entry_to_transmit(skb, sch, sched, admin,
minimum_time,
&interval_start, &interval_end,
false);
if (!entry) {
txtime = 0;
goto done;
}
txtime = entry->next_txtime;
txtime = max_t(ktime_t, txtime, minimum_time);
txtime = max_t(ktime_t, txtime, interval_start);
if (admin && admin != sched &&
ktime_after(txtime, admin->base_time)) {
sched = admin;
sched_changed = true;
continue;
}
transmit_end_time = ktime_add(txtime, packet_transmit_time);
minimum_time = transmit_end_time;
/* Update the txtime of current entry to the next time it's
* interval starts.
*/
if (ktime_after(transmit_end_time, interval_end))
entry->next_txtime = ktime_add(interval_start, sched->cycle_time);
} while (sched_changed || ktime_after(transmit_end_time, interval_end));
entry->next_txtime = transmit_end_time;
done:
rcu_read_unlock();
return txtime;
}
static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch,
struct Qdisc *child, struct sk_buff **to_free)
{
struct taprio_sched *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
int prio = skb->priority;
u8 tc;
/* sk_flags are only safe to use on full sockets. */
if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) {
if (!is_valid_interval(skb, sch))
return qdisc_drop(skb, sch, to_free);
} else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
skb->tstamp = get_packet_txtime(skb, sch);
if (!skb->tstamp)
return qdisc_drop(skb, sch, to_free);
}
/* Devices with full offload are expected to honor this in hardware */
tc = netdev_get_prio_tc_map(dev, prio);
if (skb->len > q->max_frm_len[tc])
return qdisc_drop(skb, sch, to_free);
qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
return qdisc_enqueue(skb, child, to_free);
}
/* Will not be called in the full offload case, since the TX queues are
* attached to the Qdisc created using qdisc_create_dflt()
*/
static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct taprio_sched *q = qdisc_priv(sch);
struct Qdisc *child;
int queue;
queue = skb_get_queue_mapping(skb);
child = q->qdiscs[queue];
if (unlikely(!child))
return qdisc_drop(skb, sch, to_free);
/* Large packets might not be transmitted when the transmission duration
* exceeds any configured interval. Therefore, segment the skb into
* smaller chunks. Drivers with full offload are expected to handle
* this in hardware.
*/
if (skb_is_gso(skb)) {
unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb);
netdev_features_t features = netif_skb_features(skb);
struct sk_buff *segs, *nskb;
int ret;
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs))
return qdisc_drop(skb, sch, to_free);
skb_list_walk_safe(segs, segs, nskb) {
skb_mark_not_on_list(segs);
qdisc_skb_cb(segs)->pkt_len = segs->len;
slen += segs->len;
ret = taprio_enqueue_one(segs, sch, child, to_free);
if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))
qdisc_qstats_drop(sch);
} else {
numsegs++;
}
}
if (numsegs > 1)
qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen);
consume_skb(skb);
return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}
return taprio_enqueue_one(skb, sch, child, to_free);
}
static struct sk_buff *taprio_peek(struct Qdisc *sch)
{
WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented");
return NULL;
}
static void taprio_set_budgets(struct taprio_sched *q,
struct sched_gate_list *sched,
struct sched_entry *entry)
{
struct net_device *dev = qdisc_dev(q->root);
int num_tc = netdev_get_num_tc(dev);
int tc, budget;
for (tc = 0; tc < num_tc; tc++) {
/* Traffic classes which never close have infinite budget */
if (entry->gate_duration[tc] == sched->cycle_time)
budget = INT_MAX;
else
budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC,
atomic64_read(&q->picos_per_byte));
atomic_set(&entry->budget[tc], budget);
}
}
/* When an skb is sent, it consumes from the budget of all traffic classes */
static int taprio_update_budgets(struct sched_entry *entry, size_t len,
int tc_consumed, int num_tc)
{
int tc, budget, new_budget = 0;
for (tc = 0; tc < num_tc; tc++) {
budget = atomic_read(&entry->budget[tc]);
/* Don't consume from infinite budget */
if (budget == INT_MAX) {
if (tc == tc_consumed)
new_budget = budget;
continue;
}
if (tc == tc_consumed)
new_budget = atomic_sub_return(len, &entry->budget[tc]);
else
atomic_sub(len, &entry->budget[tc]);
}
return new_budget;
}
static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq,
struct sched_entry *entry,
u32 gate_mask)
{
struct taprio_sched *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
struct Qdisc *child = q->qdiscs[txq];
int num_tc = netdev_get_num_tc(dev);
struct sk_buff *skb;
ktime_t guard;
int prio;
int len;
u8 tc;
if (unlikely(!child))
return NULL;
if (TXTIME_ASSIST_IS_ENABLED(q->flags))
goto skip_peek_checks;
skb = child->ops->peek(child);
if (!skb)
return NULL;
prio = skb->priority;
tc = netdev_get_prio_tc_map(dev, prio);
if (!(gate_mask & BIT(tc)))
return NULL;
len = qdisc_pkt_len(skb);
guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len));
/* In the case that there's no gate entry, there's no
* guard band ...
*/
if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
ktime_after(guard, entry->end_time))
return NULL;
/* ... and no budget. */
if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
taprio_update_budgets(entry, len, tc, num_tc) < 0)
return NULL;
skip_peek_checks:
skb = child->ops->dequeue(child);
if (unlikely(!skb))
return NULL;
qdisc_bstats_update(sch, skb);
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
}
static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq)
{
int offset = dev->tc_to_txq[tc].offset;
int count = dev->tc_to_txq[tc].count;
(*txq)++;
if (*txq == offset + count)
*txq = offset;
}
/* Prioritize higher traffic classes, and select among TXQs belonging to the
* same TC using round robin
*/
static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch,
struct sched_entry *entry,
u32 gate_mask)
{
struct taprio_sched *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
int num_tc = netdev_get_num_tc(dev);
struct sk_buff *skb;
int tc;
for (tc = num_tc - 1; tc >= 0; tc--) {
int first_txq = q->cur_txq[tc];
if (!(gate_mask & BIT(tc)))
continue;
do {
skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc],
entry, gate_mask);
taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]);
if (skb)
return skb;
} while (q->cur_txq[tc] != first_txq);
}
return NULL;
}
/* Broken way of prioritizing smaller TXQ indices and ignoring the traffic
* class other than to determine whether the gate is open or not
*/
static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch,
struct sched_entry *entry,
u32 gate_mask)
{
struct net_device *dev = qdisc_dev(sch);
struct sk_buff *skb;
int i;
for (i = 0; i < dev->num_tx_queues; i++) {
skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask);
if (skb)
return skb;
}
return NULL;
}
/* Will not be called in the full offload case, since the TX queues are
* attached to the Qdisc created using qdisc_create_dflt()
*/
static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
{
struct taprio_sched *q = qdisc_priv(sch);
struct sk_buff *skb = NULL;
struct sched_entry *entry;
u32 gate_mask;
rcu_read_lock();
entry = rcu_dereference(q->current_entry);
/* if there's no entry, it means that the schedule didn't
* start yet, so force all gates to be open, this is in
* accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5
* "AdminGateStates"
*/
gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN;
if (!gate_mask)
goto done;
if (static_branch_unlikely(&taprio_have_broken_mqprio) &&
!static_branch_likely(&taprio_have_working_mqprio)) {
/* Single NIC kind which is broken */
skb = taprio_dequeue_txq_priority(sch, entry, gate_mask);
} else if (static_branch_likely(&taprio_have_working_mqprio) &&
!static_branch_unlikely(&taprio_have_broken_mqprio)) {
/* Single NIC kind which prioritizes properly */
skb = taprio_dequeue_tc_priority(sch, entry, gate_mask);
} else {
/* Mixed NIC kinds present in system, need dynamic testing */
if (q->broken_mqprio)
skb = taprio_dequeue_txq_priority(sch, entry, gate_mask);
else
skb = taprio_dequeue_tc_priority(sch, entry, gate_mask);
}
done:
rcu_read_unlock();
return skb;
}
static bool should_restart_cycle(const struct sched_gate_list *oper,
const struct sched_entry *entry)
{
if (list_is_last(&entry->list, &oper->entries))
return true;
if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0)
return true;
return false;
}
static bool should_change_schedules(const struct sched_gate_list *admin,
const struct sched_gate_list *oper,
ktime_t end_time)
{
ktime_t next_base_time, extension_time;
if (!admin)
return false;
next_base_time = sched_base_time(admin);
/* This is the simple case, the end_time would fall after
* the next schedule base_time.
*/
if (ktime_compare(next_base_time, end_time) <= 0)
return true;
/* This is the cycle_time_extension case, if the end_time
* plus the amount that can be extended would fall after the
* next schedule base_time, we can extend the current schedule
* for that amount.
*/
extension_time = ktime_add_ns(end_time, oper->cycle_time_extension);
/* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about
* how precisely the extension should be made. So after
* conformance testing, this logic may change.
*/
if (ktime_compare(next_base_time, extension_time) <= 0)
return true;
return false;
}
static enum hrtimer_restart advance_sched(struct hrtimer *timer)
{
struct taprio_sched *q = container_of(timer, struct taprio_sched,
advance_timer);
struct sched_gate_list *oper, *admin;
struct sched_entry *entry, *next;
struct Qdisc *sch = q->root;
ktime_t end_time;
spin_lock(&q->current_entry_lock);
entry = rcu_dereference_protected(q->current_entry,
lockdep_is_held(&q->current_entry_lock));
oper = rcu_dereference_protected(q->oper_sched,
lockdep_is_held(&q->current_entry_lock));
admin = rcu_dereference_protected(q->admin_sched,
lockdep_is_held(&q->current_entry_lock));
if (!oper)
switch_schedules(q, &admin, &oper);
/* This can happen in two cases: 1. this is the very first run
* of this function (i.e. we weren't running any schedule
* previously); 2. The previous schedule just ended. The first
* entry of all schedules are pre-calculated during the
* schedule initialization.
*/
if (unlikely(!entry || entry->end_time == oper->base_time)) {
next = list_first_entry(&oper->entries, struct sched_entry,
list);
end_time = next->end_time;
goto first_run;
}
if (should_restart_cycle(oper, entry)) {
next = list_first_entry(&oper->entries, struct sched_entry,
list);
oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time,
oper->cycle_time);
} else {
next = list_next_entry(entry, list);
}
end_time = ktime_add_ns(entry->end_time, next->interval);
end_time = min_t(ktime_t, end_time, oper->cycle_end_time);
if (should_change_schedules(admin, oper, end_time)) {
/* Set things so the next time this runs, the new
* schedule runs.
*/
end_time = sched_base_time(admin);
switch_schedules(q, &admin, &oper);
}
next->end_time = end_time;
taprio_set_budgets(q, oper, next);
first_run:
rcu_assign_pointer(q->current_entry, next);
spin_unlock(&q->current_entry_lock);
hrtimer_set_expires(&q->advance_timer, end_time);
rcu_read_lock();
__netif_schedule(sch);
rcu_read_unlock();
return HRTIMER_RESTART;
}
static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = {
[TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 },
[TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 },
[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 },
[TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 },
};
static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = {
[TCA_TAPRIO_TC_ENTRY_INDEX] = { .type = NLA_U32 },
[TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 },
};
static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
[TCA_TAPRIO_ATTR_PRIOMAP] = {
.len = sizeof(struct tc_mqprio_qopt)
},
[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED },
[TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED },
[TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 },
[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 },
[TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 },
[TCA_TAPRIO_ATTR_TC_ENTRY] = { .type = NLA_NESTED },
};
static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
struct sched_entry *entry,
struct netlink_ext_ack *extack)
{
int min_duration = length_to_duration(q, ETH_ZLEN);
u32 interval = 0;
if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
entry->command = nla_get_u8(
tb[TCA_TAPRIO_SCHED_ENTRY_CMD]);
if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK])
entry->gate_mask = nla_get_u32(
tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]);
if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL])
interval = nla_get_u32(
tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]);
/* The interval should allow at least the minimum ethernet
* frame to go out.
*/
if (interval < min_duration) {
NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
return -EINVAL;
}
entry->interval = interval;
return 0;
}
static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n,
struct sched_entry *entry, int index,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
int err;
err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n,
entry_policy, NULL);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Could not parse nested entry");
return -EINVAL;
}
entry->index = index;
return fill_sched_entry(q, tb, entry, extack);
}
static int parse_sched_list(struct taprio_sched *q, struct nlattr *list,
struct sched_gate_list *sched,
struct netlink_ext_ack *extack)
{
struct nlattr *n;
int err, rem;
int i = 0;
if (!list)
return -EINVAL;
nla_for_each_nested(n, list, rem) {
struct sched_entry *entry;
if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) {
NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'");
continue;
}
entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry) {
NL_SET_ERR_MSG(extack, "Not enough memory for entry");
return -ENOMEM;
}
err = parse_sched_entry(q, n, entry, i, extack);
if (err < 0) {
kfree(entry);
return err;
}
list_add_tail(&entry->list, &sched->entries);
i++;
}