summaryrefslogtreecommitdiff
path: root/net/sched/sch_qfq.c
blob: cdd474afbbd29df3630d5a1765dd9f9cb1ef8af0 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
/*
 * net/sched/sch_qfq.c         Quick Fair Queueing Scheduler.
 *
 * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * version 2 as published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/pkt_sched.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>


/*  Quick Fair Queueing
    ===================

    Sources:

    Fabio Checconi, Luigi Rizzo, and Paolo Valente: "QFQ: Efficient
    Packet Scheduling with Tight Bandwidth Distribution Guarantees."

    See also:
    http://retis.sssup.it/~fabio/linux/qfq/
 */

/*

  Virtual time computations.

  S, F and V are all computed in fixed point arithmetic with
  FRAC_BITS decimal bits.

  QFQ_MAX_INDEX is the maximum index allowed for a group. We need
	one bit per index.
  QFQ_MAX_WSHIFT is the maximum power of two supported as a weight.

  The layout of the bits is as below:

                   [ MTU_SHIFT ][      FRAC_BITS    ]
                   [ MAX_INDEX    ][ MIN_SLOT_SHIFT ]
				 ^.__grp->index = 0
				 *.__grp->slot_shift

  where MIN_SLOT_SHIFT is derived by difference from the others.

  The max group index corresponds to Lmax/w_min, where
  Lmax=1<<MTU_SHIFT, w_min = 1 .
  From this, and knowing how many groups (MAX_INDEX) we want,
  we can derive the shift corresponding to each group.

  Because we often need to compute
	F = S + len/w_i  and V = V + len/wsum
  instead of storing w_i store the value
	inv_w = (1<<FRAC_BITS)/w_i
  so we can do F = S + len * inv_w * wsum.
  We use W_TOT in the formulas so we can easily move between
  static and adaptive weight sum.

  The per-scheduler-instance data contain all the data structures
  for the scheduler: bitmaps and bucket lists.

 */

/*
 * Maximum number of consecutive slots occupied by backlogged classes
 * inside a group.
 */
#define QFQ_MAX_SLOTS	32

/*
 * Shifts used for class<->group mapping.  We allow class weights that are
 * in the range [1, 2^MAX_WSHIFT], and we try to map each class i to the
 * group with the smallest index that can support the L_i / r_i configured
 * for the class.
 *
 * grp->index is the index of the group; and grp->slot_shift
 * is the shift for the corresponding (scaled) sigma_i.
 */
#define QFQ_MAX_INDEX		19
#define QFQ_MAX_WSHIFT		16

#define	QFQ_MAX_WEIGHT		(1<<QFQ_MAX_WSHIFT)
#define QFQ_MAX_WSUM		(2*QFQ_MAX_WEIGHT)

#define FRAC_BITS		30	/* fixed point arithmetic */
#define ONE_FP			(1UL << FRAC_BITS)
#define IWSUM			(ONE_FP/QFQ_MAX_WSUM)

#define QFQ_MTU_SHIFT		11
#define QFQ_MIN_SLOT_SHIFT	(FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX)

/*
 * Possible group states.  These values are used as indexes for the bitmaps
 * array of struct qfq_queue.
 */
enum qfq_state { ER, IR, EB, IB, QFQ_MAX_STATE };

struct qfq_group;

struct qfq_class {
	struct Qdisc_class_common common;

	unsigned int refcnt;
	unsigned int filter_cnt;

	struct gnet_stats_basic_packed bstats;
	struct gnet_stats_queue qstats;
	struct gnet_stats_rate_est rate_est;
	struct Qdisc *qdisc;

	struct hlist_node next;	/* Link for the slot list. */
	u64 S, F;		/* flow timestamps (exact) */

	/* group we belong to. In principle we would need the index,
	 * which is log_2(lmax/weight), but we never reference it
	 * directly, only the group.
	 */
	struct qfq_group *grp;

	/* these are copied from the flowset. */
	u32	inv_w;		/* ONE_FP/weight */
	u32	lmax;		/* Max packet size for this flow. */
};

struct qfq_group {
	u64 S, F;			/* group timestamps (approx). */
	unsigned int slot_shift;	/* Slot shift. */
	unsigned int index;		/* Group index. */
	unsigned int front;		/* Index of the front slot. */
	unsigned long full_slots;	/* non-empty slots */

	/* Array of RR lists of active classes. */
	struct hlist_head slots[QFQ_MAX_SLOTS];
};

struct qfq_sched {
	struct tcf_proto *filter_list;
	struct Qdisc_class_hash clhash;

	u64		V;		/* Precise virtual time. */
	u32		wsum;		/* weight sum */

	unsigned long bitmaps[QFQ_MAX_STATE];	    /* Group bitmaps. */
	struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
};

static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct Qdisc_class_common *clc;

	clc = qdisc_class_find(&q->clhash, classid);
	if (clc == NULL)
		return NULL;
	return container_of(clc, struct qfq_class, common);
}

static void qfq_purge_queue(struct qfq_class *cl)
{
	unsigned int len = cl->qdisc->q.qlen;

	qdisc_reset(cl->qdisc);
	qdisc_tree_decrease_qlen(cl->qdisc, len);
}

static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
	[TCA_QFQ_WEIGHT] = { .type = NLA_U32 },
	[TCA_QFQ_LMAX] = { .type = NLA_U32 },
};

/*
 * Calculate a flow index, given its weight and maximum packet length.
 * index = log_2(maxlen/weight) but we need to apply the scaling.
 * This is used only once at flow creation.
 */
static int qfq_calc_index(u32 inv_w, unsigned int maxlen)
{
	u64 slot_size = (u64)maxlen * inv_w;
	unsigned long size_map;
	int index = 0;

	size_map = slot_size >> QFQ_MIN_SLOT_SHIFT;
	if (!size_map)
		goto out;

	index = __fls(size_map) + 1;	/* basically a log_2 */
	index -= !(slot_size - (1ULL << (index + QFQ_MIN_SLOT_SHIFT - 1)));

	if (index < 0)
		index = 0;
out:
	pr_debug("qfq calc_index: W = %lu, L = %u, I = %d\n",
		 (unsigned long) ONE_FP/inv_w, maxlen, index);

	return index;
}

static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
			    struct nlattr **tca, unsigned long *arg)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl = (struct qfq_class *)*arg;
	struct nlattr *tb[TCA_QFQ_MAX + 1];
	u32 weight, lmax, inv_w;
	int i, err;
	int delta_w;

	if (tca[TCA_OPTIONS] == NULL) {
		pr_notice("qfq: no options\n");
		return -EINVAL;
	}

	err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy);
	if (err < 0)
		return err;

	if (tb[TCA_QFQ_WEIGHT]) {
		weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]);
		if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) {
			pr_notice("qfq: invalid weight %u\n", weight);
			return -EINVAL;
		}
	} else
		weight = 1;

	inv_w = ONE_FP / weight;
	weight = ONE_FP / inv_w;
	delta_w = weight - (cl ? ONE_FP / cl->inv_w : 0);
	if (q->wsum + delta_w > QFQ_MAX_WSUM) {
		pr_notice("qfq: total weight out of range (%u + %u)\n",
			  delta_w, q->wsum);
		return -EINVAL;
	}

	if (tb[TCA_QFQ_LMAX]) {
		lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
		if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) {
			pr_notice("qfq: invalid max length %u\n", lmax);
			return -EINVAL;
		}
	} else
		lmax = 1UL << QFQ_MTU_SHIFT;

	if (cl != NULL) {
		if (tca[TCA_RATE]) {
			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
						    qdisc_root_sleeping_lock(sch),
						    tca[TCA_RATE]);
			if (err)
				return err;
		}

		if (inv_w != cl->inv_w) {
			sch_tree_lock(sch);
			q->wsum += delta_w;
			cl->inv_w = inv_w;
			sch_tree_unlock(sch);
		}
		return 0;
	}

	cl = kzalloc(sizeof(struct qfq_class), GFP_KERNEL);
	if (cl == NULL)
		return -ENOBUFS;

	cl->refcnt = 1;
	cl->common.classid = classid;
	cl->lmax = lmax;
	cl->inv_w = inv_w;
	i = qfq_calc_index(cl->inv_w, cl->lmax);

	cl->grp = &q->groups[i];

	cl->qdisc = qdisc_create_dflt(sch->dev_queue,
				      &pfifo_qdisc_ops, classid);
	if (cl->qdisc == NULL)
		cl->qdisc = &noop_qdisc;

	if (tca[TCA_RATE]) {
		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
					qdisc_root_sleeping_lock(sch),
					tca[TCA_RATE]);
		if (err) {
			qdisc_destroy(cl->qdisc);
			kfree(cl);
			return err;
		}
	}
	q->wsum += weight;

	sch_tree_lock(sch);
	qdisc_class_hash_insert(&q->clhash, &cl->common);
	sch_tree_unlock(sch);

	qdisc_class_hash_grow(sch, &q->clhash);

	*arg = (unsigned long)cl;
	return 0;
}

static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
{
	struct qfq_sched *q = qdisc_priv(sch);

	if (cl->inv_w) {
		q->wsum -= ONE_FP / cl->inv_w;
		cl->inv_w = 0;
	}

	gen_kill_estimator(&cl->bstats, &cl->rate_est);
	qdisc_destroy(cl->qdisc);
	kfree(cl);
}

static int qfq_delete_class(struct Qdisc *sch, unsigned long arg)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl = (struct qfq_class *)arg;

	if (cl->filter_cnt > 0)
		return -EBUSY;

	sch_tree_lock(sch);

	qfq_purge_queue(cl);
	qdisc_class_hash_remove(&q->clhash, &cl->common);

	BUG_ON(--cl->refcnt == 0);
	/*
	 * This shouldn't happen: we "hold" one cops->get() when called
	 * from tc_ctl_tclass; the destroy method is done from cops->put().
	 */

	sch_tree_unlock(sch);
	return 0;
}

static unsigned long qfq_get_class(struct Qdisc *sch, u32 classid)
{
	struct qfq_class *cl = qfq_find_class(sch, classid);

	if (cl != NULL)
		cl->refcnt++;

	return (unsigned long)cl;
}

static void qfq_put_class(struct Qdisc *sch, unsigned long arg)
{
	struct qfq_class *cl = (struct qfq_class *)arg;

	if (--cl->refcnt == 0)
		qfq_destroy_class(sch, cl);
}

static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl)
{
	struct qfq_sched *q = qdisc_priv(sch);

	if (cl)
		return NULL;

	return &q->filter_list;
}

static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
				  u32 classid)
{
	struct qfq_class *cl = qfq_find_class(sch, classid);

	if (cl != NULL)
		cl->filter_cnt++;

	return (unsigned long)cl;
}

static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
	struct qfq_class *cl = (struct qfq_class *)arg;

	cl->filter_cnt--;
}

static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
			   struct Qdisc *new, struct Qdisc **old)
{
	struct qfq_class *cl = (struct qfq_class *)arg;

	if (new == NULL) {
		new = qdisc_create_dflt(sch->dev_queue,
					&pfifo_qdisc_ops, cl->common.classid);
		if (new == NULL)
			new = &noop_qdisc;
	}

	sch_tree_lock(sch);
	qfq_purge_queue(cl);
	*old = cl->qdisc;
	cl->qdisc = new;
	sch_tree_unlock(sch);
	return 0;
}

static struct Qdisc *qfq_class_leaf(struct Qdisc *sch, unsigned long arg)
{
	struct qfq_class *cl = (struct qfq_class *)arg;

	return cl->qdisc;
}

static int qfq_dump_class(struct Qdisc *sch, unsigned long arg,
			  struct sk_buff *skb, struct tcmsg *tcm)
{
	struct qfq_class *cl = (struct qfq_class *)arg;
	struct nlattr *nest;

	tcm->tcm_parent	= TC_H_ROOT;
	tcm->tcm_handle	= cl->common.classid;
	tcm->tcm_info	= cl->qdisc->handle;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;
	NLA_PUT_U32(skb, TCA_QFQ_WEIGHT, ONE_FP/cl->inv_w);
	NLA_PUT_U32(skb, TCA_QFQ_LMAX, cl->lmax);
	return nla_nest_end(skb, nest);

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -EMSGSIZE;
}

static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
				struct gnet_dump *d)
{
	struct qfq_class *cl = (struct qfq_class *)arg;
	struct tc_qfq_stats xstats;

	memset(&xstats, 0, sizeof(xstats));
	cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;

	xstats.weight = ONE_FP/cl->inv_w;
	xstats.lmax = cl->lmax;

	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
		return -1;

	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
}

static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl;
	struct hlist_node *n;
	unsigned int i;

	if (arg->stop)
		return;

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) {
			if (arg->count < arg->skip) {
				arg->count++;
				continue;
			}
			if (arg->fn(sch, (unsigned long)cl, arg) < 0) {
				arg->stop = 1;
				return;
			}
			arg->count++;
		}
	}
}

static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
				      int *qerr)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl;
	struct tcf_result res;
	int result;

	if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
		pr_debug("qfq_classify: found %d\n", skb->priority);
		cl = qfq_find_class(sch, skb->priority);
		if (cl != NULL)
			return cl;
	}

	*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_QUEUED:
		case TC_ACT_STOLEN:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
		case TC_ACT_SHOT:
			return NULL;
		}
#endif
		cl = (struct qfq_class *)res.class;
		if (cl == NULL)
			cl = qfq_find_class(sch, res.classid);
		return cl;
	}

	return NULL;
}

/* Generic comparison function, handling wraparound. */
static inline int qfq_gt(u64 a, u64 b)
{
	return (s64)(a - b) > 0;
}

/* Round a precise timestamp to its slotted value. */
static inline u64 qfq_round_down(u64 ts, unsigned int shift)
{
	return ts & ~((1ULL << shift) - 1);
}

/* return the pointer to the group with lowest index in the bitmap */
static inline struct qfq_group *qfq_ffs(struct qfq_sched *q,
					unsigned long bitmap)
{
	int index = __ffs(bitmap);
	return &q->groups[index];
}
/* Calculate a mask to mimic what would be ffs_from(). */
static inline unsigned long mask_from(unsigned long bitmap, int from)
{
	return bitmap & ~((1UL << from) - 1);
}

/*
 * The state computation relies on ER=0, IR=1, EB=2, IB=3
 * First compute eligibility comparing grp->S, q->V,
 * then check if someone is blocking us and possibly add EB
 */
static int qfq_calc_state(struct qfq_sched *q, const struct qfq_group *grp)
{
	/* if S > V we are not eligible */
	unsigned int state = qfq_gt(grp->S, q->V);
	unsigned long mask = mask_from(q->bitmaps[ER], grp->index);
	struct qfq_group *next;

	if (mask) {
		next = qfq_ffs(q, mask);
		if (qfq_gt(grp->F, next->F))
			state |= EB;
	}

	return state;
}


/*
 * In principle
 *	q->bitmaps[dst] |= q->bitmaps[src] & mask;
 *	q->bitmaps[src] &= ~mask;
 * but we should make sure that src != dst
 */
static inline void qfq_move_groups(struct qfq_sched *q, unsigned long mask,
				   int src, int dst)
{
	q->bitmaps[dst] |= q->bitmaps[src] & mask;
	q->bitmaps[src] &= ~mask;
}

static void qfq_unblock_groups(struct qfq_sched *q, int index, u64 old_F)
{
	unsigned long mask = mask_from(q->bitmaps[ER], index + 1);
	struct qfq_group *next;

	if (mask) {
		next = qfq_ffs(q, mask);
		if (!qfq_gt(next->F, old_F))
			return;
	}

	mask = (1UL << index) - 1;
	qfq_move_groups(q, mask, EB, ER);
	qfq_move_groups(q, mask, IB, IR);
}

/*
 * perhaps
 *
	old_V ^= q->V;
	old_V >>= QFQ_MIN_SLOT_SHIFT;
	if (old_V) {
		...
	}
 *
 */
static void qfq_make_eligible(struct qfq_sched *q, u64 old_V)
{
	unsigned long vslot = q->V >> QFQ_MIN_SLOT_SHIFT;
	unsigned long old_vslot = old_V >> QFQ_MIN_SLOT_SHIFT;

	if (vslot != old_vslot) {
		unsigned long mask = (1UL << fls(vslot ^ old_vslot)) - 1;
		qfq_move_groups(q, mask, IR, ER);
		qfq_move_groups(q, mask, IB, EB);
	}
}


/*
 * XXX we should make sure that slot becomes less than 32.
 * This is guaranteed by the input values.
 * roundedS is always cl->S rounded on grp->slot_shift bits.
 */
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl,
			    u64 roundedS)
{
	u64 slot = (roundedS - grp->S) >> grp->slot_shift;
	unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS;

	hlist_add_head(&cl->next, &grp->slots[i]);
	__set_bit(slot, &grp->full_slots);
}

/* Maybe introduce hlist_first_entry?? */
static struct qfq_class *qfq_slot_head(struct qfq_group *grp)
{
	return hlist_entry(grp->slots[grp->front].first,
			   struct qfq_class, next);
}

/*
 * remove the entry from the slot
 */
static void qfq_front_slot_remove(struct qfq_group *grp)
{
	struct qfq_class *cl = qfq_slot_head(grp);

	BUG_ON(!cl);
	hlist_del(&cl->next);
	if (hlist_empty(&grp->slots[grp->front]))
		__clear_bit(0, &grp->full_slots);
}

/*
 * Returns the first full queue in a group. As a side effect,
 * adjust the bucket list so the first non-empty bucket is at
 * position 0 in full_slots.
 */
static struct qfq_class *qfq_slot_scan(struct qfq_group *grp)
{
	unsigned int i;

	pr_debug("qfq slot_scan: grp %u full %#lx\n",
		 grp->index, grp->full_slots);

	if (grp->full_slots == 0)
		return NULL;

	i = __ffs(grp->full_slots);  /* zero based */
	if (i > 0) {
		grp->front = (grp->front + i) % QFQ_MAX_SLOTS;
		grp->full_slots >>= i;
	}

	return qfq_slot_head(grp);
}

/*
 * adjust the bucket list. When the start time of a group decreases,
 * we move the index down (modulo QFQ_MAX_SLOTS) so we don't need to
 * move the objects. The mask of occupied slots must be shifted
 * because we use ffs() to find the first non-empty slot.
 * This covers decreases in the group's start time, but what about
 * increases of the start time ?
 * Here too we should make sure that i is less than 32
 */
static void qfq_slot_rotate(struct qfq_group *grp, u64 roundedS)
{
	unsigned int i = (grp->S - roundedS) >> grp->slot_shift;

	grp->full_slots <<= i;
	grp->front = (grp->front - i) % QFQ_MAX_SLOTS;
}

static void qfq_update_eligible(struct qfq_sched *q, u64 old_V)
{
	struct qfq_group *grp;
	unsigned long ineligible;

	ineligible = q->bitmaps[IR] | q->bitmaps[IB];
	if (ineligible) {
		if (!q->bitmaps[ER]) {
			grp = qfq_ffs(q, ineligible);
			if (qfq_gt(grp->S, q->V))
				q->V = grp->S;
		}
		qfq_make_eligible(q, old_V);
	}
}

/* What is length of next packet in queue (0 if queue is empty) */
static unsigned int qdisc_peek_len(struct Qdisc *sch)
{
	struct sk_buff *skb;

	skb = sch->ops->peek(sch);
	return skb ? qdisc_pkt_len(skb) : 0;
}

/*
 * Updates the class, returns true if also the group needs to be updated.
 */
static bool qfq_update_class(struct qfq_group *grp, struct qfq_class *cl)
{
	unsigned int len = qdisc_peek_len(cl->qdisc);

	cl->S = cl->F;
	if (!len)
		qfq_front_slot_remove(grp);	/* queue is empty */
	else {
		u64 roundedS;

		cl->F = cl->S + (u64)len * cl->inv_w;
		roundedS = qfq_round_down(cl->S, grp->slot_shift);
		if (roundedS == grp->S)
			return false;

		qfq_front_slot_remove(grp);
		qfq_slot_insert(grp, cl, roundedS);
	}

	return true;
}

static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	struct qfq_class *cl;
	struct sk_buff *skb;
	unsigned int len;
	u64 old_V;

	if (!q->bitmaps[ER])
		return NULL;

	grp = qfq_ffs(q, q->bitmaps[ER]);

	cl = qfq_slot_head(grp);
	skb = qdisc_dequeue_peeked(cl->qdisc);
	if (!skb) {
		WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n");
		return NULL;
	}

	sch->q.qlen--;
	qdisc_bstats_update(sch, skb);

	old_V = q->V;
	len = qdisc_pkt_len(skb);
	q->V += (u64)len * IWSUM;
	pr_debug("qfq dequeue: len %u F %lld now %lld\n",
		 len, (unsigned long long) cl->F, (unsigned long long) q->V);

	if (qfq_update_class(grp, cl)) {
		u64 old_F = grp->F;

		cl = qfq_slot_scan(grp);
		if (!cl)
			__clear_bit(grp->index, &q->bitmaps[ER]);
		else {
			u64 roundedS = qfq_round_down(cl->S, grp->slot_shift);
			unsigned int s;

			if (grp->S == roundedS)
				goto skip_unblock;
			grp->S = roundedS;
			grp->F = roundedS + (2ULL << grp->slot_shift);
			__clear_bit(grp->index, &q->bitmaps[ER]);
			s = qfq_calc_state(q, grp);
			__set_bit(grp->index, &q->bitmaps[s]);
		}

		qfq_unblock_groups(q, grp->index, old_F);
	}

skip_unblock:
	qfq_update_eligible(q, old_V);

	return skb;
}

/*
 * Assign a reasonable start time for a new flow k in group i.
 * Admissible values for \hat(F) are multiples of \sigma_i
 * no greater than V+\sigma_i . Larger values mean that
 * we had a wraparound so we consider the timestamp to be stale.
 *
 * If F is not stale and F >= V then we set S = F.
 * Otherwise we should assign S = V, but this may violate
 * the ordering in ER. So, if we have groups in ER, set S to
 * the F_j of the first group j which would be blocking us.
 * We are guaranteed not to move S backward because
 * otherwise our group i would still be blocked.
 */
static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl)
{
	unsigned long mask;
	u64 limit, roundedF;
	int slot_shift = cl->grp->slot_shift;

	roundedF = qfq_round_down(cl->F, slot_shift);
	limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift);

	if (!qfq_gt(cl->F, q->V) || qfq_gt(roundedF, limit)) {
		/* timestamp was stale */
		mask = mask_from(q->bitmaps[ER], cl->grp->index);
		if (mask) {
			struct qfq_group *next = qfq_ffs(q, mask);
			if (qfq_gt(roundedF, next->F)) {
				if (qfq_gt(limit, next->F))
					cl->S = next->F;
				else /* preserve timestamp correctness */
					cl->S = limit;
				return;
			}
		}
		cl->S = q->V;
	} else  /* timestamp is not stale */
		cl->S = cl->F;
}

static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	struct qfq_class *cl;
	int err;
	u64 roundedS;
	int s;

	cl = qfq_classify(skb, sch, &err);
	if (cl == NULL) {
		if (err & __NET_XMIT_BYPASS)
			sch->qstats.drops++;
		kfree_skb(skb);
		return err;
	}
	pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid);

	err = qdisc_enqueue(skb, cl->qdisc);
	if (unlikely(err != NET_XMIT_SUCCESS)) {
		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
		if (net_xmit_drop_count(err)) {
			cl->qstats.drops++;
			sch->qstats.drops++;
		}
		return err;
	}

	bstats_update(&cl->bstats, skb);
	++sch->q.qlen;

	/* If the new skb is not the head of queue, then done here. */
	if (cl->qdisc->q.qlen != 1)
		return err;

	/* If reach this point, queue q was idle */
	grp = cl->grp;
	qfq_update_start(q, cl);

	/* compute new finish time and rounded start. */
	cl->F = cl->S + (u64)qdisc_pkt_len(skb) * cl->inv_w;
	roundedS = qfq_round_down(cl->S, grp->slot_shift);

	/*
	 * insert cl in the correct bucket.
	 * If cl->S >= grp->S we don't need to adjust the
	 * bucket list and simply go to the insertion phase.
	 * Otherwise grp->S is decreasing, we must make room
	 * in the bucket list, and also recompute the group state.
	 * Finally, if there were no flows in this group and nobody
	 * was in ER make sure to adjust V.
	 */
	if (grp->full_slots) {
		if (!qfq_gt(grp->S, cl->S))
			goto skip_update;

		/* create a slot for this cl->S */
		qfq_slot_rotate(grp, roundedS);
		/* group was surely ineligible, remove */
		__clear_bit(grp->index, &q->bitmaps[IR]);
		__clear_bit(grp->index, &q->bitmaps[IB]);
	} else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V))
		q->V = roundedS;

	grp->S = roundedS;
	grp->F = roundedS + (2ULL << grp->slot_shift);
	s = qfq_calc_state(q, grp);
	__set_bit(grp->index, &q->bitmaps[s]);

	pr_debug("qfq enqueue: new state %d %#lx S %lld F %lld V %lld\n",
		 s, q->bitmaps[s],
		 (unsigned long long) cl->S,
		 (unsigned long long) cl->F,
		 (unsigned long long) q->V);

skip_update:
	qfq_slot_insert(grp, cl, roundedS);

	return err;
}


static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp,
			    struct qfq_class *cl)
{
	unsigned int i, offset;
	u64 roundedS;

	roundedS = qfq_round_down(cl->S, grp->slot_shift);
	offset = (roundedS - grp->S) >> grp->slot_shift;
	i = (grp->front + offset) % QFQ_MAX_SLOTS;

	hlist_del(&cl->next);
	if (hlist_empty(&grp->slots[i]))
		__clear_bit(offset, &grp->full_slots);
}

/*
 * called to forcibly destroy a queue.
 * If the queue is not in the front bucket, or if it has
 * other queues in the front bucket, we can simply remove
 * the queue with no other side effects.
 * Otherwise we must propagate the event up.
 */
static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
{
	struct qfq_group *grp = cl->grp;
	unsigned long mask;
	u64 roundedS;
	int s;

	cl->F = cl->S;
	qfq_slot_remove(q, grp, cl);

	if (!grp->full_slots) {
		__clear_bit(grp->index, &q->bitmaps[IR]);
		__clear_bit(grp->index, &q->bitmaps[EB]);
		__clear_bit(grp->index, &q->bitmaps[IB]);

		if (test_bit(grp->index, &q->bitmaps[ER]) &&
		    !(q->bitmaps[ER] & ~((1UL << grp->index) - 1))) {
			mask = q->bitmaps[ER] & ((1UL << grp->index) - 1);
			if (mask)
				mask = ~((1UL << __fls(mask)) - 1);
			else
				mask = ~0UL;
			qfq_move_groups(q, mask, EB, ER);
			qfq_move_groups(q, mask, IB, IR);
		}
		__clear_bit(grp->index, &q->bitmaps[ER]);
	} else if (hlist_empty(&grp->slots[grp->front])) {
		cl = qfq_slot_scan(grp);
		roundedS = qfq_round_down(cl->S, grp->slot_shift);
		if (grp->S != roundedS) {
			__clear_bit(grp->index, &q->bitmaps[ER]);
			__clear_bit(grp->index, &q->bitmaps[IR]);
			__clear_bit(grp->index, &q->bitmaps[EB]);
			__clear_bit(grp->index, &q->bitmaps[IB]);
			grp->S = roundedS;
			grp->F = roundedS + (2ULL << grp->slot_shift);
			s = qfq_calc_state(q, grp);
			__set_bit(grp->index, &q->bitmaps[s]);
		}
	}

	qfq_update_eligible(q, q->V);
}

static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl = (struct qfq_class *)arg;

	if (cl->qdisc->q.qlen == 0)
		qfq_deactivate_class(q, cl);
}

static unsigned int qfq_drop(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	unsigned int i, j, len;

	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
		grp = &q->groups[i];
		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
			struct qfq_class *cl;
			struct hlist_node *n;

			hlist_for_each_entry(cl, n, &grp->slots[j], next) {

				if (!cl->qdisc->ops->drop)
					continue;

				len = cl->qdisc->ops->drop(cl->qdisc);
				if (len > 0) {
					sch->q.qlen--;
					if (!cl->qdisc->q.qlen)
						qfq_deactivate_class(q, cl);

					return len;
				}
			}
		}
	}

	return 0;
}

static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	int i, j, err;

	err = qdisc_class_hash_init(&q->clhash);
	if (err < 0)
		return err;

	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
		grp = &q->groups[i];
		grp->index = i;
		grp->slot_shift = QFQ_MTU_SHIFT + FRAC_BITS
				   - (QFQ_MAX_INDEX - i);
		for (j = 0; j < QFQ_MAX_SLOTS; j++)
			INIT_HLIST_HEAD(&grp->slots[j]);
	}

	return 0;
}

static void qfq_reset_qdisc(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	struct qfq_class *cl;
	struct hlist_node *n, *tmp;
	unsigned int i, j;

	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
		grp = &q->groups[i];
		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
			hlist_for_each_entry_safe(cl, n, tmp,
						  &grp->slots[j], next) {
				qfq_deactivate_class(q, cl);
			}
		}
	}

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode)
			qdisc_reset(cl->qdisc);
	}
	sch->q.qlen = 0;
}

static void qfq_destroy_qdisc(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl;
	struct hlist_node *n, *next;
	unsigned int i;

	tcf_destroy_chain(&q->filter_list);

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i],
					  common.hnode) {
			qfq_destroy_class(sch, cl);
		}
	}
	qdisc_class_hash_destroy(&q->clhash);
}

static const struct Qdisc_class_ops qfq_class_ops = {
	.change		= qfq_change_class,
	.delete		= qfq_delete_class,
	.get		= qfq_get_class,
	.put		= qfq_put_class,
	.tcf_chain	= qfq_tcf_chain,
	.bind_tcf	= qfq_bind_tcf,
	.unbind_tcf	= qfq_unbind_tcf,
	.graft		= qfq_graft_class,
	.leaf		= qfq_class_leaf,
	.qlen_notify	= qfq_qlen_notify,
	.dump		= qfq_dump_class,
	.dump_stats	= qfq_dump_class_stats,
	.walk		= qfq_walk,
};

static struct Qdisc_ops qfq_qdisc_ops __read_mostly = {
	.cl_ops		= &qfq_class_ops,
	.id		= "qfq",
	.priv_size	= sizeof(struct qfq_sched),
	.enqueue	= qfq_enqueue,
	.dequeue	= qfq_dequeue,
	.peek		= qdisc_peek_dequeued,
	.drop		= qfq_drop,
	.init		= qfq_init_qdisc,
	.reset		= qfq_reset_qdisc,
	.destroy	= qfq_destroy_qdisc,
	.owner		= THIS_MODULE,
};

static int __init qfq_init(void)
{
	return register_qdisc(&qfq_qdisc_ops);
}

static void __exit qfq_exit(void)
{
	unregister_qdisc(&qfq_qdisc_ops);
}

module_init(qfq_init);
module_exit(qfq_exit);
MODULE_LICENSE("GPL");