aboutsummaryrefslogtreecommitdiffstats
path: root/net/sched/sch_htb.c
blob: 3fda8199713de5e48f068a4585ab0916a8ee9790 (plain) (blame)
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
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
/*
 * net/sched/sch_htb.c	Hierarchical token bucket, feed tree version
 *
 *		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:	Martin Devera, <devik@cdi.cz>
 *
 * Credits (in time order) for older HTB versions:
 *              Stef Coene <stef.coene@docum.org>
 *			HTB support at LARTC mailing list
 *		Ondrej Kraus, <krauso@barr.cz>
 *			found missing INIT_QDISC(htb)
 *		Vladimir Smelhaus, Aamer Akhter, Bert Hubert
 *			helped a lot to locate nasty class stall bug
 *		Andi Kleen, Jamal Hadi, Bert Hubert
 *			code review and helpful comments on shaping
 *		Tomasz Wrona, <tw@eter.tym.pl>
 *			created test case so that I was able to fix nasty bug
 *		Wilfried Weissmann
 *			spotted bug in dequeue code and helped with fix
 *		Jiri Fojtasek
 *			fixed requeue routine
 *		and many others. thanks.
 */
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/compiler.h>
#include <linux/rbtree.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>

/* HTB algorithm.
    Author: devik@cdi.cz
    ========================================================================
    HTB is like TBF with multiple classes. It is also similar to CBQ because
    it allows to assign priority to each class in hierarchy.
    In fact it is another implementation of Floyd's formal sharing.

    Levels:
    Each class is assigned level. Leaf has ALWAYS level 0 and root
    classes have level TC_HTB_MAXDEPTH-1. Interior nodes has level
    one less than their parent.
*/

static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */
#define HTB_VER 0x30011		/* major must be matched with number suplied by TC as version */

#if HTB_VER >> 16 != TC_HTB_PROTOVER
#error "Mismatched sch_htb.c and pkt_sch.h"
#endif

/* Module parameter and sysfs export */
module_param    (htb_hysteresis, int, 0640);
MODULE_PARM_DESC(htb_hysteresis, "Hysteresis mode, less CPU load, less accurate");

/* used internaly to keep status of single class */
enum htb_cmode {
	HTB_CANT_SEND,		/* class can't send and can't borrow */
	HTB_MAY_BORROW,		/* class can't send but may borrow */
	HTB_CAN_SEND		/* class can send */
};

/* interior & leaf nodes; props specific to leaves are marked L: */
struct htb_class {
	struct Qdisc_class_common common;
	/* general class parameters */
	struct gnet_stats_basic bstats;
	struct gnet_stats_queue qstats;
	struct gnet_stats_rate_est rate_est;
	struct tc_htb_xstats xstats;	/* our special stats */
	int refcnt;		/* usage count of this class */

	/* topology */
	int level;		/* our level (see above) */
	unsigned int children;
	struct htb_class *parent;	/* parent class */

	union {
		struct htb_class_leaf {
			struct Qdisc *q;
			int prio;
			int aprio;
			int quantum;
			int deficit[TC_HTB_MAXDEPTH];
			struct list_head drop_list;
		} leaf;
		struct htb_class_inner {
			struct rb_root feed[TC_HTB_NUMPRIO];	/* feed trees */
			struct rb_node *ptr[TC_HTB_NUMPRIO];	/* current class ptr */
			/* When class changes from state 1->2 and disconnects from
			   parent's feed then we lost ptr value and start from the
			   first child again. Here we store classid of the
			   last valid ptr (used when ptr is NULL). */
			u32 last_ptr_id[TC_HTB_NUMPRIO];
		} inner;
	} un;
	struct rb_node node[TC_HTB_NUMPRIO];	/* node for self or feed tree */
	struct rb_node pq_node;	/* node for event queue */
	psched_time_t pq_key;

	int prio_activity;	/* for which prios are we active */
	enum htb_cmode cmode;	/* current mode of the class */

	/* class attached filters */
	struct tcf_proto *filter_list;
	int filter_cnt;

	int warned;		/* only one warning about non work conserving .. */

	/* token bucket parameters */
	struct qdisc_rate_table *rate;	/* rate table of the class itself */
	struct qdisc_rate_table *ceil;	/* ceiling rate (limits borrows too) */
	long buffer, cbuffer;	/* token bucket depth/rate */
	psched_tdiff_t mbuffer;	/* max wait time */
	long tokens, ctokens;	/* current number of tokens */
	psched_time_t t_c;	/* checkpoint time */

	int prio;		/* For parent to leaf return possible here */
	int quantum;		/* we do backup. Finally full replacement  */
				/* of un.leaf originals should be done. */
};

static inline long L2T(struct htb_class *cl, struct qdisc_rate_table *rate,
			   int size)
{
	long result = qdisc_l2t(rate, size);
	return result;
}

struct htb_sched {
	struct Qdisc_class_hash clhash;
	struct list_head drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */

	/* self list - roots of self generating tree */
	struct rb_root row[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO];
	int row_mask[TC_HTB_MAXDEPTH];
	struct rb_node *ptr[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO];
	u32 last_ptr_id[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO];

	/* self wait list - roots of wait PQs per row */
	struct rb_root wait_pq[TC_HTB_MAXDEPTH];

	/* time of nearest event per level (row) */
	psched_time_t near_ev_cache[TC_HTB_MAXDEPTH];

	/* whether we hit non-work conserving class during this dequeue; we use */
	int nwc_hit;		/* this to disable mindelay complaint in dequeue */

	int defcls;		/* class where unclassified flows go to */

	/* filters for qdisc itself */
	struct tcf_proto *filter_list;

	int rate2quantum;	/* quant = rate / rate2quantum */
	psched_time_t now;	/* cached dequeue time */
	struct qdisc_watchdog watchdog;

	/* non shaped skbs; let them go directly thru */
	struct sk_buff_head direct_queue;
	int direct_qlen;	/* max qlen of above */

	long direct_pkts;
};

/* find class in global hash table using given handle */
static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct Qdisc_class_common *clc;

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

/**
 * htb_classify - classify a packet into class
 *
 * It returns NULL if the packet should be dropped or -1 if the packet
 * should be passed directly thru. In all other cases leaf class is returned.
 * We allow direct class selection by classid in priority. The we examine
 * filters in qdisc and in inner nodes (if higher filter points to the inner
 * node). If we end up with classid MAJOR:0 we enqueue the skb into special
 * internal fifo (direct). These packets then go directly thru. If we still
 * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull
 * then finish and return direct queue.
 */
#define HTB_DIRECT (struct htb_class*)-1

static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
				      int *qerr)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl;
	struct tcf_result res;
	struct tcf_proto *tcf;
	int result;

	/* allow to select class by setting skb->priority to valid classid;
	   note that nfmark can be used too by attaching filter fw with no
	   rules in it */
	if (skb->priority == sch->handle)
		return HTB_DIRECT;	/* X:0 (direct flow) selected */
	if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0)
		return cl;

	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
	tcf = q->filter_list;
	while (tcf && (result = tc_classify(skb, tcf, &res)) >= 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
		if ((cl = (void *)res.class) == NULL) {
			if (res.classid == sch->handle)
				return HTB_DIRECT;	/* X:0 (direct flow) */
			if ((cl = htb_find(res.classid, sch)) == NULL)
				break;	/* filter selected invalid classid */
		}
		if (!cl->level)
			return cl;	/* we hit leaf; return it */

		/* we have got inner class; apply inner filter chain */
		tcf = cl->filter_list;
	}
	/* classification failed; try to use default class */
	cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch);
	if (!cl || cl->level)
		return HTB_DIRECT;	/* bad default .. this is safe bet */
	return cl;
}

/**
 * htb_add_to_id_tree - adds class to the round robin list
 *
 * Routine adds class to the list (actually tree) sorted by classid.
 * Make sure that class is not already on such list for given prio.
 */
static void htb_add_to_id_tree(struct rb_root *root,
			       struct htb_class *cl, int prio)
{
	struct rb_node **p = &root->rb_node, *parent = NULL;

	while (*p) {
		struct htb_class *c;
		parent = *p;
		c = rb_entry(parent, struct htb_class, node[prio]);

		if (cl->common.classid > c->common.classid)
			p = &parent->rb_right;
		else
			p = &parent->rb_left;
	}
	rb_link_node(&cl->node[prio], parent, p);
	rb_insert_color(&cl->node[prio], root);
}

/**
 * htb_add_to_wait_tree - adds class to the event queue with delay
 *
 * The class is added to priority event queue to indicate that class will
 * change its mode in cl->pq_key microseconds. Make sure that class is not
 * already in the queue.
 */
static void htb_add_to_wait_tree(struct htb_sched *q,
				 struct htb_class *cl, long delay)
{
	struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL;

	cl->pq_key = q->now + delay;
	if (cl->pq_key == q->now)
		cl->pq_key++;

	/* update the nearest event cache */
	if (q->near_ev_cache[cl->level] > cl->pq_key)
		q->near_ev_cache[cl->level] = cl->pq_key;

	while (*p) {
		struct htb_class *c;
		parent = *p;
		c = rb_entry(parent, struct htb_class, pq_node);
		if (cl->pq_key >= c->pq_key)
			p = &parent->rb_right;
		else
			p = &parent->rb_left;
	}
	rb_link_node(&cl->pq_node, parent, p);
	rb_insert_color(&cl->pq_node, &q->wait_pq[cl->level]);
}

/**
 * htb_next_rb_node - finds next node in binary tree
 *
 * When we are past last key we return NULL.
 * Average complexity is 2 steps per call.
 */
static inline void htb_next_rb_node(struct rb_node **n)
{
	*n = rb_next(*n);
}

/**
 * htb_add_class_to_row - add class to its row
 *
 * The class is added to row at priorities marked in mask.
 * It does nothing if mask == 0.
 */
static inline void htb_add_class_to_row(struct htb_sched *q,
					struct htb_class *cl, int mask)
{
	q->row_mask[cl->level] |= mask;
	while (mask) {
		int prio = ffz(~mask);
		mask &= ~(1 << prio);
		htb_add_to_id_tree(q->row[cl->level] + prio, cl, prio);
	}
}

/* If this triggers, it is a bug in this code, but it need not be fatal */
static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root)
{
	if (RB_EMPTY_NODE(rb)) {
		WARN_ON(1);
	} else {
		rb_erase(rb, root);
		RB_CLEAR_NODE(rb);
	}
}


/**
 * htb_remove_class_from_row - removes class from its row
 *
 * The class is removed from row at priorities marked in mask.
 * It does nothing if mask == 0.
 */
static inline void htb_remove_class_from_row(struct htb_sched *q,
						 struct htb_class *cl, int mask)
{
	int m = 0;

	while (mask) {
		int prio = ffz(~mask);

		mask &= ~(1 << prio);
		if (q->ptr[cl->level][prio] == cl->node + prio)
			htb_next_rb_node(q->ptr[cl->level] + prio);

		htb_safe_rb_erase(cl->node + prio, q->row[cl->level] + prio);
		if (!q->row[cl->level][prio].rb_node)
			m |= 1 << prio;
	}
	q->row_mask[cl->level] &= ~m;
}

/**
 * htb_activate_prios - creates active classe's feed chain
 *
 * The class is connected to ancestors and/or appropriate rows
 * for priorities it is participating on. cl->cmode must be new
 * (activated) mode. It does nothing if cl->prio_activity == 0.
 */
static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl)
{
	struct htb_class *p = cl->parent;
	long m, mask = cl->prio_activity;

	while (cl->cmode == HTB_MAY_BORROW && p && mask) {
		m = mask;
		while (m) {
			int prio = ffz(~m);
			m &= ~(1 << prio);

			if (p->un.inner.feed[prio].rb_node)
				/* parent already has its feed in use so that
				   reset bit in mask as parent is already ok */
				mask &= ~(1 << prio);

			htb_add_to_id_tree(p->un.inner.feed + prio, cl, prio);
		}
		p->prio_activity |= mask;
		cl = p;
		p = cl->parent;

	}
	if (cl->cmode == HTB_CAN_SEND && mask)
		htb_add_class_to_row(q, cl, mask);
}

/**
 * htb_deactivate_prios - remove class from feed chain
 *
 * cl->cmode must represent old mode (before deactivation). It does
 * nothing if cl->prio_activity == 0. Class is removed from all feed
 * chains and rows.
 */
static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl)
{
	struct htb_class *p = cl->parent;
	long m, mask = cl->prio_activity;

	while (cl->cmode == HTB_MAY_BORROW && p && mask) {
		m = mask;
		mask = 0;
		while (m) {
			int prio = ffz(~m);
			m &= ~(1 << prio);

			if (p->un.inner.ptr[prio] == cl->node + prio) {
				/* we are removing child which is pointed to from
				   parent feed - forget the pointer but remember
				   classid */
				p->un.inner.last_ptr_id[prio] = cl->common.classid;
				p->un.inner.ptr[prio] = NULL;
			}

			htb_safe_rb_erase(cl->node + prio, p->un.inner.feed + prio);

			if (!p->un.inner.feed[prio].rb_node)
				mask |= 1 << prio;
		}

		p->prio_activity &= ~mask;
		cl = p;
		p = cl->parent;

	}
	if (cl->cmode == HTB_CAN_SEND && mask)
		htb_remove_class_from_row(q, cl, mask);
}

static inline long htb_lowater(const struct htb_class *cl)
{
	if (htb_hysteresis)
		return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0;
	else
		return 0;
}
static inline long htb_hiwater(const struct htb_class *cl)
{
	if (htb_hysteresis)
		return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0;
	else
		return 0;
}


/**
 * htb_class_mode - computes and returns current class mode
 *
 * It computes cl's mode at time cl->t_c+diff and returns it. If mode
 * is not HTB_CAN_SEND then cl->pq_key is updated to time difference
 * from now to time when cl will change its state.
 * Also it is worth to note that class mode doesn't change simply
 * at cl->{c,}tokens == 0 but there can rather be hysteresis of
 * 0 .. -cl->{c,}buffer range. It is meant to limit number of
 * mode transitions per time unit. The speed gain is about 1/6.
 */
static inline enum htb_cmode
htb_class_mode(struct htb_class *cl, long *diff)
{
	long toks;

	if ((toks = (cl->ctokens + *diff)) < htb_lowater(cl)) {
		*diff = -toks;
		return HTB_CANT_SEND;
	}

	if ((toks = (cl->tokens + *diff)) >= htb_hiwater(cl))
		return HTB_CAN_SEND;

	*diff = -toks;
	return HTB_MAY_BORROW;
}

/**
 * htb_change_class_mode - changes classe's mode
 *
 * This should be the only way how to change classe's mode under normal
 * cirsumstances. Routine will update feed lists linkage, change mode
 * and add class to the wait event queue if appropriate. New mode should
 * be different from old one and cl->pq_key has to be valid if changing
 * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree).
 */
static void
htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff)
{
	enum htb_cmode new_mode = htb_class_mode(cl, diff);

	if (new_mode == cl->cmode)
		return;

	if (cl->prio_activity) {	/* not necessary: speed optimization */
		if (cl->cmode != HTB_CANT_SEND)
			htb_deactivate_prios(q, cl);
		cl->cmode = new_mode;
		if (new_mode != HTB_CANT_SEND)
			htb_activate_prios(q, cl);
	} else
		cl->cmode = new_mode;
}

/**
 * htb_activate - inserts leaf cl into appropriate active feeds
 *
 * Routine learns (new) priority of leaf and activates feed chain
 * for the prio. It can be called on already active leaf safely.
 * It also adds leaf into droplist.
 */
static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
{
	WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen);

	if (!cl->prio_activity) {
		cl->prio_activity = 1 << (cl->un.leaf.aprio = cl->un.leaf.prio);
		htb_activate_prios(q, cl);
		list_add_tail(&cl->un.leaf.drop_list,
			      q->drops + cl->un.leaf.aprio);
	}
}

/**
 * htb_deactivate - remove leaf cl from active feeds
 *
 * Make sure that leaf is active. In the other words it can't be called
 * with non-active leaf. It also removes class from the drop list.
 */
static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
{
	WARN_ON(!cl->prio_activity);

	htb_deactivate_prios(q, cl);
	cl->prio_activity = 0;
	list_del_init(&cl->un.leaf.drop_list);
}

static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
	int ret;
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = htb_classify(skb, sch, &ret);

	if (cl == HTB_DIRECT) {
		/* enqueue to helper queue */
		if (q->direct_queue.qlen < q->direct_qlen) {
			__skb_queue_tail(&q->direct_queue, skb);
			q->direct_pkts++;
		} else {
			kfree_skb(skb);
			sch->qstats.drops++;
			return NET_XMIT_DROP;
		}
#ifdef CONFIG_NET_CLS_ACT
	} else if (!cl) {
		if (ret & __NET_XMIT_BYPASS)
			sch->qstats.drops++;
		kfree_skb(skb);
		return ret;
#endif
	} else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q)) != NET_XMIT_SUCCESS) {
		if (net_xmit_drop_count(ret)) {
			sch->qstats.drops++;
			cl->qstats.drops++;
		}
		return ret;
	} else {
		cl->bstats.packets +=
			skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
		cl->bstats.bytes += qdisc_pkt_len(skb);
		htb_activate(q, cl);
	}

	sch->q.qlen++;
	sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
	sch->bstats.bytes += qdisc_pkt_len(skb);
	return NET_XMIT_SUCCESS;
}

/* TODO: requeuing packet charges it to policers again !! */
static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
{
	int ret;
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = htb_classify(skb, sch, &ret);
	struct sk_buff *tskb;

	if (cl == HTB_DIRECT) {
		/* enqueue to helper queue */
		if (q->direct_queue.qlen < q->direct_qlen) {
			__skb_queue_head(&q->direct_queue, skb);
		} else {
			__skb_queue_head(&q->direct_queue, skb);
			tskb = __skb_dequeue_tail(&q->direct_queue);
			kfree_skb(tskb);
			sch->qstats.drops++;
			return NET_XMIT_CN;
		}
#ifdef CONFIG_NET_CLS_ACT
	} else if (!cl) {
		if (ret & __NET_XMIT_BYPASS)
			sch->qstats.drops++;
		kfree_skb(skb);
		return ret;
#endif
	} else if ((ret = cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q)) !=
		   NET_XMIT_SUCCESS) {
		if (net_xmit_drop_count(ret)) {
			sch->qstats.drops++;
			cl->qstats.drops++;
		}
		return ret;
	} else
		htb_activate(q, cl);

	sch->q.qlen++;
	sch->qstats.requeues++;
	return NET_XMIT_SUCCESS;
}

/**
 * htb_charge_class - charges amount "bytes" to leaf and ancestors
 *
 * Routine assumes that packet "bytes" long was dequeued from leaf cl
 * borrowing from "level". It accounts bytes to ceil leaky bucket for
 * leaf and all ancestors and to rate bucket for ancestors at levels
 * "level" and higher. It also handles possible change of mode resulting
 * from the update. Note that mode can also increase here (MAY_BORROW to
 * CAN_SEND) because we can use more precise clock that event queue here.
 * In such case we remove class from event queue first.
 */
static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
			     int level, struct sk_buff *skb)
{
	int bytes = qdisc_pkt_len(skb);
	long toks, diff;
	enum htb_cmode old_mode;

#define HTB_ACCNT(T,B,R) toks = diff + cl->T; \
	if (toks > cl->B) toks = cl->B; \
	toks -= L2T(cl, cl->R, bytes); \
	if (toks <= -cl->mbuffer) toks = 1-cl->mbuffer; \
	cl->T = toks

	while (cl) {
		diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
		if (cl->level >= level) {
			if (cl->level == level)
				cl->xstats.lends++;
			HTB_ACCNT(tokens, buffer, rate);
		} else {
			cl->xstats.borrows++;
			cl->tokens += diff;	/* we moved t_c; update tokens */
		}
		HTB_ACCNT(ctokens, cbuffer, ceil);
		cl->t_c = q->now;

		old_mode = cl->cmode;
		diff = 0;
		htb_change_class_mode(q, cl, &diff);
		if (old_mode != cl->cmode) {
			if (old_mode != HTB_CAN_SEND)
				htb_safe_rb_erase(&cl->pq_node, q->wait_pq + cl->level);
			if (cl->cmode != HTB_CAN_SEND)
				htb_add_to_wait_tree(q, cl, diff);
		}

		/* update byte stats except for leaves which are already updated */
		if (cl->level) {
			cl->bstats.bytes += bytes;
			cl->bstats.packets += skb_is_gso(skb)?
					skb_shinfo(skb)->gso_segs:1;
		}
		cl = cl->parent;
	}
}

/**
 * htb_do_events - make mode changes to classes at the level
 *
 * Scans event queue for pending events and applies them. Returns time of
 * next pending event (0 for no event in pq).
 * Note: Applied are events whose have cl->pq_key <= q->now.
 */
static psched_time_t htb_do_events(struct htb_sched *q, int level)
{
	/* don't run for longer than 2 jiffies; 2 is used instead of
	   1 to simplify things when jiffy is going to be incremented
	   too soon */
	unsigned long stop_at = jiffies + 2;
	while (time_before(jiffies, stop_at)) {
		struct htb_class *cl;
		long diff;
		struct rb_node *p = rb_first(&q->wait_pq[level]);

		if (!p)
			return 0;

		cl = rb_entry(p, struct htb_class, pq_node);
		if (cl->pq_key > q->now)
			return cl->pq_key;

		htb_safe_rb_erase(p, q->wait_pq + level);
		diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
		htb_change_class_mode(q, cl, &diff);
		if (cl->cmode != HTB_CAN_SEND)
			htb_add_to_wait_tree(q, cl, diff);
	}
	/* too much load - let's continue on next jiffie */
	return q->now + PSCHED_TICKS_PER_SEC / HZ;
}

/* Returns class->node+prio from id-tree where classe's id is >= id. NULL
   is no such one exists. */
static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n,
					      u32 id)
{
	struct rb_node *r = NULL;
	while (n) {
		struct htb_class *cl =
		    rb_entry(n, struct htb_class, node[prio]);
		if (id == cl->common.classid)
			return n;

		if (id > cl->common.classid) {
			n = n->rb_right;
		} else {
			r = n;
			n = n->rb_left;
		}
	}
	return r;
}

/**
 * htb_lookup_leaf - returns next leaf class in DRR order
 *
 * Find leaf where current feed pointers points to.
 */
static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio,
					 struct rb_node **pptr, u32 * pid)
{
	int i;
	struct {
		struct rb_node *root;
		struct rb_node **pptr;
		u32 *pid;
	} stk[TC_HTB_MAXDEPTH], *sp = stk;

	WARN_ON(!tree->rb_node);
	sp->root = tree->rb_node;
	sp->pptr = pptr;
	sp->pid = pid;

	for (i = 0; i < 65535; i++) {
		if (!*sp->pptr && *sp->pid) {
			/* ptr was invalidated but id is valid - try to recover
			   the original or next ptr */
			*sp->pptr =
			    htb_id_find_next_upper(prio, sp->root, *sp->pid);
		}
		*sp->pid = 0;	/* ptr is valid now so that remove this hint as it
				   can become out of date quickly */
		if (!*sp->pptr) {	/* we are at right end; rewind & go up */
			*sp->pptr = sp->root;
			while ((*sp->pptr)->rb_left)
				*sp->pptr = (*sp->pptr)->rb_left;
			if (sp > stk) {
				sp--;
				WARN_ON(!*sp->pptr);
				if (!*sp->pptr)
					return NULL;
				htb_next_rb_node(sp->pptr);
			}
		} else {
			struct htb_class *cl;
			cl = rb_entry(*sp->pptr, struct htb_class, node[prio]);
			if (!cl->level)
				return cl;
			(++sp)->root = cl->un.inner.feed[prio].rb_node;
			sp->pptr = cl->un.inner.ptr + prio;
			sp->pid = cl->un.inner.last_ptr_id + prio;
		}
	}
	WARN_ON(1);
	return NULL;
}

/* dequeues packet at given priority and level; call only if
   you are sure that there is active class at prio/level */
static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio,
					int level)
{
	struct sk_buff *skb = NULL;
	struct htb_class *cl, *start;
	/* look initial class up in the row */
	start = cl = htb_lookup_leaf(q->row[level] + prio, prio,
				     q->ptr[level] + prio,
				     q->last_ptr_id[level] + prio);

	do {
next:
		WARN_ON(!cl);
		if (!cl)
			return NULL;

		/* class can be empty - it is unlikely but can be true if leaf
		   qdisc drops packets in enqueue routine or if someone used
		   graft operation on the leaf since last dequeue;
		   simply deactivate and skip such class */
		if (unlikely(cl->un.leaf.q->q.qlen == 0)) {
			struct htb_class *next;
			htb_deactivate(q, cl);

			/* row/level might become empty */
			if ((q->row_mask[level] & (1 << prio)) == 0)
				return NULL;

			next = htb_lookup_leaf(q->row[level] + prio,
					       prio, q->ptr[level] + prio,
					       q->last_ptr_id[level] + prio);

			if (cl == start)	/* fix start if we just deleted it */
				start = next;
			cl = next;
			goto next;
		}

		skb = cl->un.leaf.q->dequeue(cl->un.leaf.q);
		if (likely(skb != NULL))
			break;
		if (!cl->warned) {
			printk(KERN_WARNING
			       "htb: class %X isn't work conserving ?!\n",
			       cl->common.classid);
			cl->warned = 1;
		}
		q->nwc_hit++;
		htb_next_rb_node((level ? cl->parent->un.inner.ptr : q->
				  ptr[0]) + prio);
		cl = htb_lookup_leaf(q->row[level] + prio, prio,
				     q->ptr[level] + prio,
				     q->last_ptr_id[level] + prio);

	} while (cl != start);

	if (likely(skb != NULL)) {
		cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb);
		if (cl->un.leaf.deficit[level] < 0) {
			cl->un.leaf.deficit[level] += cl->un.leaf.quantum;
			htb_next_rb_node((level ? cl->parent->un.inner.ptr : q->
					  ptr[0]) + prio);
		}
		/* this used to be after charge_class but this constelation
		   gives us slightly better performance */
		if (!cl->un.leaf.q->q.qlen)
			htb_deactivate(q, cl);
		htb_charge_class(q, cl, level, skb);
	}
	return skb;
}

static struct sk_buff *htb_dequeue(struct Qdisc *sch)
{
	struct sk_buff *skb = NULL;
	struct htb_sched *q = qdisc_priv(sch);
	int level;
	psched_time_t next_event;

	/* try to dequeue direct packets as high prio (!) to minimize cpu work */
	skb = __skb_dequeue(&q->direct_queue);
	if (skb != NULL) {
		sch->flags &= ~TCQ_F_THROTTLED;
		sch->q.qlen--;
		return skb;
	}

	if (!sch->q.qlen)
		goto fin;
	q->now = psched_get_time();

	next_event = q->now + 5 * PSCHED_TICKS_PER_SEC;
	q->nwc_hit = 0;
	for (level = 0; level < TC_HTB_MAXDEPTH; level++) {
		/* common case optimization - skip event handler quickly */
		int m;
		psched_time_t event;

		if (q->now >= q->near_ev_cache[level]) {
			event = htb_do_events(q, level);
			if (!event)
				event = q->now + PSCHED_TICKS_PER_SEC;
			q->near_ev_cache[level] = event;
		} else
			event = q->near_ev_cache[level];

		if (event && next_event > event)
			next_event = event;

		m = ~q->row_mask[level];
		while (m != (int)(-1)) {
			int prio = ffz(m);
			m |= 1 << prio;
			skb = htb_dequeue_tree(q, prio, level);
			if (likely(skb != NULL)) {
				sch->q.qlen--;
				sch->flags &= ~TCQ_F_THROTTLED;
				goto fin;
			}
		}
	}
	sch->qstats.overlimits++;
	qdisc_watchdog_schedule(&q->watchdog, next_event);
fin:
	return skb;
}

/* try to drop from each class (by prio) until one succeed */
static unsigned int htb_drop(struct Qdisc *sch)
{
	struct htb_sched *q = qdisc_priv(sch);
	int prio;

	for (prio = TC_HTB_NUMPRIO - 1; prio >= 0; prio--) {
		struct list_head *p;
		list_for_each(p, q->drops + prio) {
			struct htb_class *cl = list_entry(p, struct htb_class,
							  un.leaf.drop_list);
			unsigned int len;
			if (cl->un.leaf.q->ops->drop &&
			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
				sch->q.qlen--;
				if (!cl->un.leaf.q->q.qlen)
					htb_deactivate(q, cl);
				return len;
			}
		}
	}
	return 0;
}

/* reset all classes */
/* always caled under BH & queue lock */
static void htb_reset(struct Qdisc *sch)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl;
	struct hlist_node *n;
	unsigned int i;

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) {
			if (cl->level)
				memset(&cl->un.inner, 0, sizeof(cl->un.inner));
			else {
				if (cl->un.leaf.q)
					qdisc_reset(cl->un.leaf.q);
				INIT_LIST_HEAD(&cl->un.leaf.drop_list);
			}
			cl->prio_activity = 0;
			cl->cmode = HTB_CAN_SEND;

		}
	}
	qdisc_watchdog_cancel(&q->watchdog);
	__skb_queue_purge(&q->direct_queue);
	sch->q.qlen = 0;
	memset(q->row, 0, sizeof(q->row));
	memset(q->row_mask, 0, sizeof(q->row_mask));
	memset(q->wait_pq, 0, sizeof(q->wait_pq));
	memset(q->ptr, 0, sizeof(q->ptr));
	for (i = 0; i < TC_HTB_NUMPRIO; i++)
		INIT_LIST_HEAD(q->drops + i);
}

static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
	[TCA_HTB_PARMS]	= { .len = sizeof(struct tc_htb_opt) },
	[TCA_HTB_INIT]	= { .len = sizeof(struct tc_htb_glob) },
	[TCA_HTB_CTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
	[TCA_HTB_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
};

static int htb_init(struct Qdisc *sch, struct nlattr *opt)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct nlattr *tb[TCA_HTB_INIT + 1];
	struct tc_htb_glob *gopt;
	int err;
	int i;

	if (!opt)
		return -EINVAL;

	err = nla_parse_nested(tb, TCA_HTB_INIT, opt, htb_policy);
	if (err < 0)
		return err;

	if (tb[TCA_HTB_INIT] == NULL) {
		printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n");
		return -EINVAL;
	}
	gopt = nla_data(tb[TCA_HTB_INIT]);
	if (gopt->version != HTB_VER >> 16) {
		printk(KERN_ERR
		       "HTB: need tc/htb version %d (minor is %d), you have %d\n",
		       HTB_VER >> 16, HTB_VER & 0xffff, gopt->version);
		return -EINVAL;
	}

	err = qdisc_class_hash_init(&q->clhash);
	if (err < 0)
		return err;
	for (i = 0; i < TC_HTB_NUMPRIO; i++)
		INIT_LIST_HEAD(q->drops + i);

	qdisc_watchdog_init(&q->watchdog, sch);
	skb_queue_head_init(&q->direct_queue);

	q->direct_qlen = qdisc_dev(sch)->tx_queue_len;
	if (q->direct_qlen < 2)	/* some devices have zero tx_queue_len */
		q->direct_qlen = 2;

	if ((q->rate2quantum = gopt->rate2quantum) < 1)
		q->rate2quantum = 1;
	q->defcls = gopt->defcls;

	return 0;
}

static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
{
	spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
	struct htb_sched *q = qdisc_priv(sch);
	struct nlattr *nest;
	struct tc_htb_glob gopt;

	spin_lock_bh(root_lock);

	gopt.direct_pkts = q->direct_pkts;
	gopt.version = HTB_VER;
	gopt.rate2quantum = q->rate2quantum;
	gopt.defcls = q->defcls;
	gopt.debug = 0;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;
	NLA_PUT(skb, TCA_HTB_INIT, sizeof(gopt), &gopt);
	nla_nest_end(skb, nest);

	spin_unlock_bh(root_lock);
	return skb->len;

nla_put_failure:
	spin_unlock_bh(root_lock);
	nla_nest_cancel(skb, nest);
	return -1;
}

static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
			  struct sk_buff *skb, struct tcmsg *tcm)
{
	struct htb_class *cl = (struct htb_class *)arg;
	spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
	struct nlattr *nest;
	struct tc_htb_opt opt;

	spin_lock_bh(root_lock);
	tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT;
	tcm->tcm_handle = cl->common.classid;
	if (!cl->level && cl->un.leaf.q)
		tcm->tcm_info = cl->un.leaf.q->handle;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;

	memset(&opt, 0, sizeof(opt));

	opt.rate = cl->rate->rate;
	opt.buffer = cl->buffer;
	opt.ceil = cl->ceil->rate;
	opt.cbuffer = cl->cbuffer;
	opt.quantum = cl->un.leaf.quantum;
	opt.prio = cl->un.leaf.prio;
	opt.level = cl->level;
	NLA_PUT(skb, TCA_HTB_PARMS, sizeof(opt), &opt);

	nla_nest_end(skb, nest);
	spin_unlock_bh(root_lock);
	return skb->len;

nla_put_failure:
	spin_unlock_bh(root_lock);
	nla_nest_cancel(skb, nest);
	return -1;
}

static int
htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
{
	struct htb_class *cl = (struct htb_class *)arg;

	if (!cl->level && cl->un.leaf.q)
		cl->qstats.qlen = cl->un.leaf.q->q.qlen;
	cl->xstats.tokens = cl->tokens;
	cl->xstats.ctokens = cl->ctokens;

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

	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
}

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

	if (cl && !cl->level) {
		if (new == NULL &&
		    (new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue,
					     &pfifo_qdisc_ops,
					     cl->common.classid))
		    == NULL)
			return -ENOBUFS;
		sch_tree_lock(sch);
		if ((*old = xchg(&cl->un.leaf.q, new)) != NULL) {
			qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
			qdisc_reset(*old);
		}
		sch_tree_unlock(sch);
		return 0;
	}
	return -ENOENT;
}

static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg)
{
	struct htb_class *cl = (struct htb_class *)arg;
	return (cl && !cl->level) ? cl->un.leaf.q : NULL;
}

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

	if (cl->un.leaf.q->q.qlen == 0)
		htb_deactivate(qdisc_priv(sch), cl);
}

static unsigned long htb_get(struct Qdisc *sch, u32 classid)
{
	struct htb_class *cl = htb_find(classid, sch);
	if (cl)
		cl->refcnt++;
	return (unsigned long)cl;
}

static inline int htb_parent_last_child(struct htb_class *cl)
{
	if (!cl->parent)
		/* the root class */
		return 0;
	if (cl->parent->children > 1)
		/* not the last child */
		return 0;
	return 1;
}

static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl,
			       struct Qdisc *new_q)
{
	struct htb_class *parent = cl->parent;

	WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity);

	if (parent->cmode != HTB_CAN_SEND)
		htb_safe_rb_erase(&parent->pq_node, q->wait_pq + parent->level);

	parent->level = 0;
	memset(&parent->un.inner, 0, sizeof(parent->un.inner));
	INIT_LIST_HEAD(&parent->un.leaf.drop_list);
	parent->un.leaf.q = new_q ? new_q : &noop_qdisc;
	parent->un.leaf.quantum = parent->quantum;
	parent->un.leaf.prio = parent->prio;
	parent->tokens = parent->buffer;
	parent->ctokens = parent->cbuffer;
	parent->t_c = psched_get_time();
	parent->cmode = HTB_CAN_SEND;
}

static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
{
	if (!cl->level) {
		WARN_ON(!cl->un.leaf.q);
		qdisc_destroy(cl->un.leaf.q);
	}
	gen_kill_estimator(&cl->bstats, &cl->rate_est);
	qdisc_put_rtab(cl->rate);
	qdisc_put_rtab(cl->ceil);

	tcf_destroy_chain(&cl->filter_list);
	kfree(cl);
}

/* always caled under BH & queue lock */
static void htb_destroy(struct Qdisc *sch)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct hlist_node *n, *next;
	struct htb_class *cl;
	unsigned int i;

	qdisc_watchdog_cancel(&q->watchdog);
	/* This line used to be after htb_destroy_class call below
	   and surprisingly it worked in 2.4. But it must precede it
	   because filter need its target class alive to be able to call
	   unbind_filter on it (without Oops). */
	tcf_destroy_chain(&q->filter_list);

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

static int htb_delete(struct Qdisc *sch, unsigned long arg)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = (struct htb_class *)arg;
	unsigned int qlen;
	struct Qdisc *new_q = NULL;
	int last_child = 0;

	// TODO: why don't allow to delete subtree ? references ? does
	// tc subsys quarantee us that in htb_destroy it holds no class
	// refs so that we can remove children safely there ?
	if (cl->children || cl->filter_cnt)
		return -EBUSY;

	if (!cl->level && htb_parent_last_child(cl)) {
		new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue,
					  &pfifo_qdisc_ops,
					  cl->parent->common.classid);
		last_child = 1;
	}

	sch_tree_lock(sch);

	if (!cl->level) {
		qlen = cl->un.leaf.q->q.qlen;
		qdisc_reset(cl->un.leaf.q);
		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
	}

	/* delete from hash and active; remainder in destroy_class */
	qdisc_class_hash_remove(&q->clhash, &cl->common);
	if (cl->parent)
		cl->parent->children--;

	if (cl->prio_activity)
		htb_deactivate(q, cl);

	if (cl->cmode != HTB_CAN_SEND)
		htb_safe_rb_erase(&cl->pq_node, q->wait_pq + cl->level);

	if (last_child)
		htb_parent_to_leaf(q, cl, new_q);

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

	sch_tree_unlock(sch);
	return 0;
}

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

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

static int htb_change_class(struct Qdisc *sch, u32 classid,
			    u32 parentid, struct nlattr **tca,
			    unsigned long *arg)
{
	int err = -EINVAL;
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = (struct htb_class *)*arg, *parent;
	struct nlattr *opt = tca[TCA_OPTIONS];
	struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
	struct nlattr *tb[TCA_HTB_RTAB + 1];
	struct tc_htb_opt *hopt;

	/* extract all subattrs from opt attr */
	if (!opt)
		goto failure;

	err = nla_parse_nested(tb, TCA_HTB_RTAB, opt, htb_policy);
	if (err < 0)
		goto failure;

	err = -EINVAL;
	if (tb[TCA_HTB_PARMS] == NULL)
		goto failure;

	parent = parentid == TC_H_ROOT ? NULL : htb_find(parentid, sch);

	hopt = nla_data(tb[TCA_HTB_PARMS]);

	rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
	ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
	if (!rtab || !ctab)
		goto failure;

	if (!cl) {		/* new class */
		struct Qdisc *new_q;
		int prio;
		struct {
			struct nlattr		nla;
			struct gnet_estimator	opt;
		} est = {
			.nla = {
				.nla_len	= nla_attr_size(sizeof(est.opt)),
				.nla_type	= TCA_RATE,
			},
			.opt = {
				/* 4s interval, 16s averaging constant */
				.interval	= 2,
				.ewma_log	= 2,
			},
		};

		/* check for valid classid */
		if (!classid || TC_H_MAJ(classid ^ sch->handle)
		    || htb_find(classid, sch))
			goto failure;

		/* check maximal depth */
		if (parent && parent->parent && parent->parent->level < 2) {
			printk(KERN_ERR "htb: tree is too deep\n");
			goto failure;
		}
		err = -ENOBUFS;
		if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL)
			goto failure;

		gen_new_estimator(&cl->bstats, &cl->rate_est,
				  qdisc_root_sleeping_lock(sch),
				  tca[TCA_RATE] ? : &est.nla);
		cl->refcnt = 1;
		cl->children = 0;
		INIT_LIST_HEAD(&cl->un.leaf.drop_list);
		RB_CLEAR_NODE(&cl->pq_node);

		for (prio = 0; prio < TC_HTB_NUMPRIO; prio++)
			RB_CLEAR_NODE(&cl->node[prio]);

		/* create leaf qdisc early because it uses kmalloc(GFP_KERNEL)
		   so that can't be used inside of sch_tree_lock
		   -- thanks to Karlis Peisenieks */
		new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue,
					  &pfifo_qdisc_ops, classid);
		sch_tree_lock(sch);
		if (parent && !parent->level) {
			unsigned int qlen = parent->un.leaf.q->q.qlen;

			/* turn parent into inner node */
			qdisc_reset(parent->un.leaf.q);
			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
			qdisc_destroy(parent->un.leaf.q);
			if (parent->prio_activity)
				htb_deactivate(q, parent);

			/* remove from evt list because of level change */
			if (parent->cmode != HTB_CAN_SEND) {
				htb_safe_rb_erase(&parent->pq_node, q->wait_pq);
				parent->cmode = HTB_CAN_SEND;
			}
			parent->level = (parent->parent ? parent->parent->level
					 : TC_HTB_MAXDEPTH) - 1;
			memset(&parent->un.inner, 0, sizeof(parent->un.inner));
		}
		/* leaf (we) needs elementary qdisc */
		cl->un.leaf.q = new_q ? new_q : &noop_qdisc;

		cl->common.classid = classid;
		cl->parent = parent;

		/* set class to be in HTB_CAN_SEND state */
		cl->tokens = hopt->buffer;
		cl->ctokens = hopt->cbuffer;
		cl->mbuffer = 60 * PSCHED_TICKS_PER_SEC;	/* 1min */
		cl->t_c = psched_get_time();
		cl->cmode = HTB_CAN_SEND;

		/* attach to the hash list and parent's family */
		qdisc_class_hash_insert(&q->clhash, &cl->common);
		if (parent)
			parent->children++;
	} else {
		if (tca[TCA_RATE])
			gen_replace_estimator(&cl->bstats, &cl->rate_est,
					      qdisc_root_sleeping_lock(sch),
					      tca[TCA_RATE]);
		sch_tree_lock(sch);
	}

	/* it used to be a nasty bug here, we have to check that node
	   is really leaf before changing cl->un.leaf ! */
	if (!cl->level) {
		cl->un.leaf.quantum = rtab->rate.rate / q->rate2quantum;
		if (!hopt->quantum && cl->un.leaf.quantum < 1000) {
			printk(KERN_WARNING
			       "HTB: quantum of class %X is small. Consider r2q change.\n",
			       cl->common.classid);
			cl->un.leaf.quantum = 1000;
		}
		if (!hopt->quantum && cl->un.leaf.quantum > 200000) {
			printk(KERN_WARNING
			       "HTB: quantum of class %X is big. Consider r2q change.\n",
			       cl->common.classid);
			cl->un.leaf.quantum = 200000;
		}
		if (hopt->quantum)
			cl->un.leaf.quantum = hopt->quantum;
		if ((cl->un.leaf.prio = hopt->prio) >= TC_HTB_NUMPRIO)
			cl->un.leaf.prio = TC_HTB_NUMPRIO - 1;

		/* backup for htb_parent_to_leaf */
		cl->quantum = cl->un.leaf.quantum;
		cl->prio = cl->un.leaf.prio;
	}

	cl->buffer = hopt->buffer;
	cl->cbuffer = hopt->cbuffer;
	if (cl->rate)
		qdisc_put_rtab(cl->rate);
	cl->rate = rtab;
	if (cl->ceil)
		qdisc_put_rtab(cl->ceil);
	cl->ceil = ctab;
	sch_tree_unlock(sch);

	qdisc_class_hash_grow(sch, &q->clhash);

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

failure:
	if (rtab)
		qdisc_put_rtab(rtab);
	if (ctab)
		qdisc_put_rtab(ctab);
	return err;
}

static struct tcf_proto **htb_find_tcf(struct Qdisc *sch, unsigned long arg)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = (struct htb_class *)arg;
	struct tcf_proto **fl = cl ? &cl->filter_list : &q->filter_list;

	return fl;
}

static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent,
				     u32 classid)
{
	struct htb_class *cl = htb_find(classid, sch);

	/*if (cl && !cl->level) return 0;
	   The line above used to be there to prevent attaching filters to
	   leaves. But at least tc_index filter uses this just to get class
	   for other reasons so that we have to allow for it.
	   ----
	   19.6.2002 As Werner explained it is ok - bind filter is just
	   another way to "lock" the class - unlike "get" this lock can
	   be broken by class during destroy IIUC.
	 */
	if (cl)
		cl->filter_cnt++;
	return (unsigned long)cl;
}

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

	if (cl)
		cl->filter_cnt--;
}

static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_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 const struct Qdisc_class_ops htb_class_ops = {
	.graft		=	htb_graft,
	.leaf		=	htb_leaf,
	.qlen_notify	=	htb_qlen_notify,
	.get		=	htb_get,
	.put		=	htb_put,
	.change		=	htb_change_class,
	.delete		=	htb_delete,
	.walk		=	htb_walk,
	.tcf_chain	=	htb_find_tcf,
	.bind_tcf	=	htb_bind_filter,
	.unbind_tcf	=	htb_unbind_filter,
	.dump		=	htb_dump_class,
	.dump_stats	=	htb_dump_class_stats,
};

static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
	.next		=	NULL,
	.cl_ops		=	&htb_class_ops,
	.id		=	"htb",
	.priv_size	=	sizeof(struct htb_sched),
	.enqueue	=	htb_enqueue,
	.dequeue	=	htb_dequeue,
	.peek		=	qdisc_peek_dequeued,
	.requeue	=	htb_requeue,
	.drop		=	htb_drop,
	.init		=	htb_init,
	.reset		=	htb_reset,
	.destroy	=	htb_destroy,
	.change		=	NULL /* htb_change */,
	.dump		=	htb_dump,
	.owner		=	THIS_MODULE,
};

static int __init htb_module_init(void)
{
	return register_qdisc(&htb_qdisc_ops);
}
static void __exit htb_module_exit(void)
{
	unregister_qdisc(&htb_qdisc_ops);
}

module_init(htb_module_init)
module_exit(htb_module_exit)
MODULE_LICENSE("GPL");