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
|
/*
* net/sched/sch_sfq.c Stochastic Fairness Queueing discipline.
*
* 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>
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/ipv6.h>
#include <linux/skbuff.h>
#include <linux/jhash.h>
#include <linux/slab.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
/* Stochastic Fairness Queuing algorithm.
=======================================
Source:
Paul E. McKenney "Stochastic Fairness Queuing",
IEEE INFOCOMM'90 Proceedings, San Francisco, 1990.
Paul E. McKenney "Stochastic Fairness Queuing",
"Interworking: Research and Experience", v.2, 1991, p.113-131.
See also:
M. Shreedhar and George Varghese "Efficient Fair
Queuing using Deficit Round Robin", Proc. SIGCOMM 95.
This is not the thing that is usually called (W)FQ nowadays.
It does not use any timestamp mechanism, but instead
processes queues in round-robin order.
ADVANTAGE:
- It is very cheap. Both CPU and memory requirements are minimal.
DRAWBACKS:
- "Stochastic" -> It is not 100% fair.
When hash collisions occur, several flows are considered as one.
- "Round-robin" -> It introduces larger delays than virtual clock
based schemes, and should not be used for isolating interactive
traffic from non-interactive. It means, that this scheduler
should be used as leaf of CBQ or P3, which put interactive traffic
to higher priority band.
We still need true WFQ for top level CSZ, but using WFQ
for the best effort traffic is absolutely pointless:
SFQ is superior for this purpose.
IMPLEMENTATION:
This implementation limits maximal queue length to 128;
max mtu to 2^18-1; max 128 flows, number of hash buckets to 1024.
The only goal of this restrictions was that all data
fit into one 4K page on 32bit arches.
It is easy to increase these values, but not in flight. */
#define SFQ_DEPTH 128 /* max number of packets per flow */
#define SFQ_SLOTS 128 /* max number of flows */
#define SFQ_EMPTY_SLOT 255
#define SFQ_HASH_DIVISOR 1024
/* We use 16 bits to store allot, and want to handle packets up to 64K
* Scale allot by 8 (1<<3) so that no overflow occurs.
*/
#define SFQ_ALLOT_SHIFT 3
#define SFQ_ALLOT_SIZE(X) DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT)
/* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
typedef unsigned char sfq_index;
/*
* We dont use pointers to save space.
* Small indexes [0 ... SFQ_SLOTS - 1] are 'pointers' to slots[] array
* while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1]
* are 'pointers' to dep[] array
*/
struct sfq_head
{
sfq_index next;
sfq_index prev;
};
struct sfq_slot {
struct sk_buff *skblist_next;
struct sk_buff *skblist_prev;
sfq_index qlen; /* number of skbs in skblist */
sfq_index next; /* next slot in sfq chain */
struct sfq_head dep; /* anchor in dep[] chains */
unsigned short hash; /* hash value (index in ht[]) */
short allot; /* credit for this slot */
};
struct sfq_sched_data
{
/* Parameters */
int perturb_period;
unsigned quantum; /* Allotment per round: MUST BE >= MTU */
int limit;
/* Variables */
struct tcf_proto *filter_list;
struct timer_list perturb_timer;
u32 perturbation;
sfq_index cur_depth; /* depth of longest slot */
unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
struct sfq_slot *tail; /* current slot in round */
sfq_index ht[SFQ_HASH_DIVISOR]; /* Hash table */
struct sfq_slot slots[SFQ_SLOTS];
struct sfq_head dep[SFQ_DEPTH]; /* Linked list of slots, indexed by depth */
};
/*
* sfq_head are either in a sfq_slot or in dep[] array
*/
static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index val)
{
if (val < SFQ_SLOTS)
return &q->slots[val].dep;
return &q->dep[val - SFQ_SLOTS];
}
static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
{
return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1);
}
static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
{
u32 h, h2;
switch (skb->protocol) {
case htons(ETH_P_IP):
{
const struct iphdr *iph;
int poff;
if (!pskb_network_may_pull(skb, sizeof(*iph)))
goto err;
iph = ip_hdr(skb);
h = (__force u32)iph->daddr;
h2 = (__force u32)iph->saddr ^ iph->protocol;
if (iph->frag_off & htons(IP_MF|IP_OFFSET))
break;
poff = proto_ports_offset(iph->protocol);
if (poff >= 0 &&
pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) {
iph = ip_hdr(skb);
h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff);
}
break;
}
case htons(ETH_P_IPV6):
{
struct ipv6hdr *iph;
int poff;
if (!pskb_network_may_pull(skb, sizeof(*iph)))
goto err;
iph = ipv6_hdr(skb);
h = (__force u32)iph->daddr.s6_addr32[3];
h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr;
poff = proto_ports_offset(iph->nexthdr);
if (poff >= 0 &&
pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) {
iph = ipv6_hdr(skb);
h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff);
}
break;
}
default:
err:
h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol;
h2 = (unsigned long)skb->sk;
}
return sfq_fold_hash(q, h, h2);
}
static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct tcf_result res;
int result;
if (TC_H_MAJ(skb->priority) == sch->handle &&
TC_H_MIN(skb->priority) > 0 &&
TC_H_MIN(skb->priority) <= SFQ_HASH_DIVISOR)
return TC_H_MIN(skb->priority);
if (!q->filter_list)
return sfq_hash(q, skb) + 1;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
result = tc_classify(skb, q->filter_list, &res);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
case TC_ACT_SHOT:
return 0;
}
#endif
if (TC_H_MIN(res.classid) <= SFQ_HASH_DIVISOR)
return TC_H_MIN(res.classid);
}
return 0;
}
/*
* x : slot number [0 .. SFQ_SLOTS - 1]
*/
static inline
|