summaryrefslogtreecommitdiffstats
path: root/net/sched/sch_htb.c
blob: f46643850df84477dfb21708369cbc605916ae07 (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
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
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * net/sched/sch_htb.c	Hierarchical token bucket, feed tree 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 <linux/workqueue.h>
#include <linux/slab.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.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 supplied 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");

static int htb_rate_est = 0; /* htb classes have a default rate estimator */
module_param(htb_rate_est, int, 0640);
MODULE_PARM_DESC(htb_rate_est, "setup a default rate estimator (4sec 16sec) for htb classes");

/* 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 */
};

struct htb_prio {
	union {
		struct rb_root	row;
		struct rb_root	feed;
	};
	struct rb_node	*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;
};

/* interior & leaf nodes; props specific to leaves are marked L:
 * To reduce false sharing, place mostly read fields at beginning,
 * and mostly written ones at the end.
 */
struct htb_class {
	struct Qdisc_class_common common;
	struct psched_ratecfg	rate;
	struct psched_ratecfg	ceil;
	s64			buffer, cbuffer;/* token bucket depth/rate */
	s64			mbuffer;	/* max wait time */
	u32			prio;		/* these two are used only by leaves... */
	int			quantum;	/* but stored for parent-to-leaf return */

	struct tcf_proto __rcu	*filter_list;	/* class attached filters */
	struct tcf_block	*block;
	int			filter_cnt;

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

	struct net_rate_estimator __rcu *rate_est;

	/*
	 * Written often fields
	 */
	struct gnet_stats_basic_sync bstats;
	struct gnet_stats_basic_sync bstats_bias;
	struct tc_htb_xstats	xstats;	/* our special stats */

	/* token bucket parameters */
	s64			tokens, ctokens;/* current number of tokens */
	s64			t_c;		/* checkpoint time */

	union {
		struct htb_class_leaf {
			int		deficit[TC_HTB_MAXDEPTH];
			struct Qdisc	*q;
			struct netdev_queue *offload_queue;
		} leaf;
		struct htb_class_inner {
			struct htb_prio clprio[TC_HTB_NUMPRIO];
		} inner;
	};
	s64			pq_key;

	int			prio_activity;	/* for which prios are we active */
	enum htb_cmode		cmode;		/* current mode of the class */
	struct rb_node		pq_node;	/* node for event queue */
	struct rb_node		node[TC_HTB_NUMPRIO];	/* node for self or feed tree */

	unsigned int drops ____cacheline_aligned_in_smp;
	unsigned int		overlimits;
};

struct htb_level {
	struct rb_root	wait_pq;
	struct htb_prio hprio[TC_HTB_NUMPRIO];
};

struct htb_sched {
	struct Qdisc_class_hash clhash;
	int			defcls;		/* class where unclassified flows go to */
	int			rate2quantum;	/* quant = rate / rate2quantum */

	/* filters for qdisc itself */
	struct tcf_proto __rcu	*filter_list;
	struct tcf_block	*block;

#define HTB_WARN_TOOMANYEVENTS	0x1
	unsigned int		warned;	/* only one warning */
	int			direct_qlen;
	struct work_struct	work;

	/* non shaped skbs; let them go directly thru */
	struct qdisc_skb_head	direct_queue;
	u32			direct_pkts;
	u32			overlimits;

	struct qdisc_watchdog	watchdog;

	s64			now;	/* cached dequeue time */

	/* time of nearest event per level (row) */
	s64			near_ev_cache[TC_HTB_MAXDEPTH];

	int			row_mask[TC_HTB_MAXDEPTH];

	struct htb_level	hlevel[TC_HTB_MAXDEPTH];

	struct Qdisc		**direct_qdiscs;
	unsigned int            num_direct_qdiscs;

	bool			offload;
};

/* 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);
}

static unsigned long htb_search(struct Qdisc *sch, u32 handle)
{
	return (unsigned long)htb_find(handle, sch);
}

#define HTB_DIRECT ((struct htb_class *)-1L)

/**
 * htb_classify - classify a packet into class
 * @skb: the socket buffer
 * @sch: the active queue discipline
 * @qerr: pointer for returned status code
 *
 * 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 unsuccessful
 * then finish and return direct queue.
 */
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 */
	cl = htb_find(skb->priority, sch);
	if (cl) {
		if (cl->level == 0)
			return cl;
		/* Start with inner filter chain if a non-leaf class is selected */
		tcf = rcu_dereference_bh(cl->filter_list);
	} else {
		tcf = rcu_dereference_bh(q->filter_list);
	}

	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
	while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) {
#ifdef CONFIG_NET_CLS_ACT
		switch (result) {
		case TC_ACT_QUEUED:
		case TC_ACT_STOLEN:
		case TC_ACT_TRAP:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
			fallthrough;
		case TC_ACT_SHOT:
			return NULL;
		}
#endif
		cl = (void *)res.class;
		if (!cl) {
			if (res.classid == sch->handle)
				return HTB_DIRECT;	/* X:0 (direct flow) */
			cl = htb_find(res.classid, sch);
			if (!cl)
				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 = rcu_dereference_bh(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
 * @root: the root of the tree
 * @cl: the class to add
 * @prio: the give prio in class
 *
 * 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
 * @q: the priority event queue
 * @cl: the class to add
 * @delay: delay in microseconds
 *
 * 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, s64 delay)
{
	struct rb_node **p = &q->hlevel[cl->level].wait_pq.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->hlevel[cl->level].wait_pq);
}

/**
 * htb_next_rb_node - finds next node in binary tree
 * @n: the current 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
 * @q: the priority event queue
 * @cl: the class to add
 * @mask: the given priorities in class in bitmap
 *
 * 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->hlevel[cl->level].hprio[prio].row, 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
 * @q: the priority event queue
 * @cl: the class to add
 * @mask: the given priorities in class in bitmap
 *
 * 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;
	struct htb_level *hlevel = &q->hlevel[cl->level];

	while (mask) {
		int prio = ffz(~mask);
		struct htb_prio *hprio = &hlevel->hprio[prio];

		mask &= ~(1 << prio);
		if (hprio->ptr == cl->node + prio)
			htb_next_rb_node(&hprio->ptr);

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

/**
 * htb_activate_prios - creates active classe's feed chain
 * @q: the priority event queue
 * @cl: the class to activate
 *
 * 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->inner.clprio[prio].feed.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->inner.clprio[prio].feed, 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
 * @q: the priority event queue
 * @cl: the class to deactivate
 *
 * 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->inner.clprio[prio].ptr == cl->node + prio) {
				/* we are removing child which is pointed to from
				 * parent feed - forget the pointer but remember
				 * classid
				 */
				p->inner.clprio[prio].last_ptr_id = cl->common.classid;
				p->inner.clprio[prio].ptr = NULL;
			}

			htb_safe_rb_erase(cl->node + prio,
					  &p->inner.clprio[prio].feed);

			if (!p->inner.clprio[prio].feed.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 s64 htb_lowater(const struct htb_class *cl)
{
	if (htb_hysteresis)
		return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0;
	else
		return 0;
}
static inline s64 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
 * @cl: the target class
 * @diff: diff time in microseconds
 *
 * 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, s64 *diff)
{
	s64 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
 * @q: the priority event queue
 * @cl: the target class
 * @diff: diff time in microseconds
 *
 * This should be the only way how to change classe's mode under normal
 * circumstances. 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, s64 *diff)
{
	enum htb_cmode new_mode = htb_class_mode(cl, diff);

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

	if (new_mode == HTB_CANT_SEND) {
		cl->overlimits++;
		q->overlimits++;
	}

	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
 * @q: the priority event queue
 * @cl: the target class
 *
 * 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->leaf.q || !cl->leaf.q->q.qlen);

	if (!cl->prio_activity) {
		cl->prio_activity = 1 << cl->prio;
		htb_activate_prios(q, cl);
	}
}

/**
 * htb_deactivate - remove leaf cl from active feeds
 * @q: the priority event queue
 * @cl: the target class
 *
 * 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;
}

static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
		       struct sk_buff **to_free)
{
	int ret;
	unsigned int len = qdisc_pkt_len(skb);
	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) {
			__qdisc_enqueue_tail(skb, &q->direct_queue);
			q->direct_pkts++;
		} else {
			return qdisc_drop(skb, sch, to_free);
		}
#ifdef CONFIG_NET_CLS_ACT
	} else if (!cl) {
		if (ret & __NET_XMIT_BYPASS)
			qdisc_qstats_drop(sch);
		__qdisc_drop(skb, to_free);
		return ret;
#endif
	} else if ((ret = qdisc_enqueue(skb, cl->leaf.q,
					to_free)) != NET_XMIT_SUCCESS) {
		if (net_xmit_drop_count(ret)) {
			qdisc_qstats_drop(sch);
			cl->drops++;
		}
		return ret;
	} else {
		htb_activate(q, cl);
	}

	sch->qstats.backlog += len;
	sch->q.qlen++;
	return NET_XMIT_SUCCESS;
}

static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff)
{
	s64 toks = diff + cl->tokens;

	if (toks > cl->buffer)
		toks = cl->buffer;
	toks -= (s64) psched_l2t_ns(&cl->rate, bytes);
	if (toks <= -cl->mbuffer)
		toks = 1 - cl->mbuffer;

	cl->tokens = toks;
}

static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff)
{
	s64 toks = diff + cl->ctokens;

	if (toks > cl->cbuffer)
		toks = cl->cbuffer;
	toks -= (s64) psched_l2t_ns(&cl->ceil, bytes);
	if (toks <= -cl->mbuffer)
		toks = 1 - cl->mbuffer;

	cl->ctokens = toks;
}

/**
 * htb_charge_class - charges amount "bytes" to leaf and ancestors
 * @q: the priority event queue
 * @cl: the class to start iterate
 * @level: the minimum level to account
 * @skb: the socket buffer
 *
 * 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);
	enum htb_cmode old_mode;
	s64 diff;

	while (cl) {
		diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
		if (cl->level >= level) {
			if (cl->level == level)
				cl->xstats.lends++;
			htb_accnt_tokens(cl, bytes, diff);
		} else {
			cl->xstats.borrows++;
			cl->tokens += diff;	/* we moved t_c; update tokens */
		}
		htb_accnt_ctokens(cl, bytes, diff);
		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->hlevel[cl->level].wait_pq);
			if (cl->cmode != HTB_CAN_SEND)
				htb_add_to_wait_tree(q, cl, diff);
		}

		/* update basic stats except for leaves which are already updated */
		if (cl->level)
			bstats_update(&cl->bstats, skb);

		cl = cl->parent;
	}
}

/**
 * htb_do_events - make mode changes to classes at the level
 * @q: the priority event queue
 * @level: which wait_pq in 'q->hlevel'
 * @start: start jiffies
 *
 * Scans event queue for pending events and applies them. Returns time of
 * next pending event (0 for no event in pq, q->now for too many events).
 * Note: Applied are events whose have cl->pq_key <= q->now.
 */
static s64 htb_do_events(struct htb_sched *q, const int level,
			 unsigned long start)
{
	/* 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 = start + 2;
	struct rb_root *wait_pq = &q->hlevel[level].wait_pq;

	while (time_before(jiffies, stop_at)) {
		struct htb_class *cl;
		s64 diff;
		struct rb_node *p = rb_first(wait_pq);

		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, wait_pq);
		diff = min_t(s64, 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 after a break for scheduling */
	if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) {
		pr_warn("htb: too many events!\n");
		q->warned |= HTB_WARN_TOOMANYEVENTS;
	}

	return q->now;
}

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

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

	BUG_ON(!hprio->row.rb_node);
	sp->root = hprio->row.rb_node;
	sp->pptr = &hprio->ptr;
	sp->pid = &hprio->last_ptr_id;

	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--;
				if (!*sp->pptr) {
					WARN_ON(1);
					return NULL;
				}
				htb_next_rb_node(sp->pptr);
			}
		} else {
			struct htb_class *cl;
			struct htb_prio *clp;

			cl = rb_entry(*sp->pptr, struct htb_class, node[prio]);
			if (!cl->level)
				return cl;
			clp = &cl->inner.clprio[prio];
			(++sp)->root = clp->feed.rb_node;
			sp->pptr = &clp->ptr;
			sp->pid = &clp->last_ptr_id;
		}
	}
	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, const int prio,
					const int level)
{
	struct sk_buff *skb = NULL;
	struct htb_class *cl, *start;
	struct htb_level *hlevel = &q->hlevel[level];
	struct htb_prio *hprio = &hlevel->hprio[prio];

	/* look initial class up in the row */
	start = cl = htb_lookup_leaf(hprio, prio);

	do {
next:
		if (unlikely(!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->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(hprio, prio);

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

		skb = cl->leaf.q->dequeue(cl->leaf.q);
		if (likely(skb != NULL))
			break;

		qdisc_warn_nonwc("htb", cl->leaf.q);
		htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr:
					 &q->hlevel[0].hprio[prio].ptr);
		cl = htb_lookup_leaf(hprio, prio);

	} while (cl != start);

	if (likely(skb != NULL)) {
		bstats_update(&cl->bstats, skb);
		cl->leaf.deficit[level] -= qdisc_pkt_len(skb);
		if (cl->leaf.deficit[level] < 0) {
			cl->leaf.deficit[level] += cl->quantum;
			htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr :
						 &q->hlevel[0].hprio[prio].ptr);
		}
		/* this used to be after charge_class but this constelation
		 * gives us slightly better performance
		 */
		if (!cl->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;
	struct htb_sched *q = qdisc_priv(sch);
	int level;
	s64 next_event;
	unsigned long start_at;

	/* try to dequeue direct packets as high prio (!) to minimize cpu work */
	skb = __qdisc_dequeue_head(&q->direct_queue);
	if (skb != NULL) {
ok:
		qdisc_bstats_update(sch, skb);
		qdisc_qstats_backlog_dec(sch, skb);
		sch->q.qlen--;
		return skb;
	}

	if (!sch->q.qlen)
		goto fin;
	q->now = ktime_get_ns();
	start_at = jiffies;

	next_event = q->now + 5LLU * NSEC_PER_SEC;

	for (level = 0; level < TC_HTB_MAXDEPTH; level++) {
		/* common case optimization - skip event handler quickly */
		int m;
		s64 event = q->near_ev_cache[level];

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

		if (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))
				goto ok;
		}
	}
	if (likely(next_event > q->now))
		qdisc_watchdog_schedule_ns(&q->watchdog, next_event);
	else
		schedule_work(&q->work);
fin:
	return skb;
}

/* 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;
	unsigned int i;

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
			if (cl->level)
				memset(&cl->inner, 0, sizeof(cl->inner));
			else {
				if (cl->leaf.q && !q->offload)
					qdisc_reset(cl->leaf.q);
			}
			cl->prio_activity = 0;
			cl->cmode = HTB_CAN_SEND;
		}
	}
	qdisc_watchdog_cancel(&q->watchdog);
	__qdisc_reset_queue(&q->direct_queue);
	memset(q->hlevel, 0, sizeof(q->hlevel));
	memset(q->row_mask, 0, sizeof(q->row_mask));
}

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 },
	[TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 },
	[TCA_HTB_RATE64] = { .type = NLA_U64 },
	[TCA_HTB_CEIL64] = { .type = NLA_U64 },
	[TCA_HTB_OFFLOAD] = { .type = NLA_FLAG },
};

static void htb_work_func(struct work_struct *work)
{
	struct htb_sched *q = container_of(work, struct htb_sched, work);
	struct Qdisc *sch = q->watchdog.qdisc;

	rcu_read_lock();
	__netif_schedule(qdisc_root(sch));
	rcu_read_unlock();
}

static void htb_set_lockdep_class_child(struct Qdisc *q)
{
	static struct lock_class_key child_key;

	lockdep_set_class(qdisc_lock(q), &child_key);
}

static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt)
{
	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt);
}

static int htb_init(struct Qdisc *sch, struct nlattr *opt,
		    struct netlink_ext_ack *extack)
{
	struct net_device *dev = qdisc_dev(sch);
	struct tc_htb_qopt_offload offload_opt;
	struct htb_sched *q = qdisc_priv(sch);
	struct nlattr *tb[TCA_HTB_MAX + 1];
	struct tc_htb_glob *gopt;
	unsigned int ntx;
	bool offload;
	int err;

	qdisc_watchdog_init(&q->watchdog, sch);
	INIT_WORK(&q->work, htb_work_func);

	if (!opt)
		return -EINVAL;

	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
	if (err)
		return err;

	err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy,
					  NULL);
	if (err < 0)
		return err;

	if (!tb[TCA_HTB_INIT])
		return -EINVAL;

	gopt = nla_data(tb[TCA_HTB_INIT]);
	if (gopt->version != HTB_VER >> 16)
		return -EINVAL;

	offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]);

	if (offload) {
		if (sch->parent != TC_H_ROOT) {
			NL_SET_ERR_MSG(extack, "HTB must be the root qdisc to use offload");
			return -EOPNOTSUPP;
		}

		if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) {
			NL_SET_ERR_MSG(extack, "hw-tc-offload ethtool feature flag must be on");
			return -EOPNOTSUPP;
		}

		q->num_direct_qdiscs = dev->real_num_tx_queues;
		q->direct_qdiscs = kcalloc(q->num_direct_qdiscs,
					   sizeof(*q->direct_qdiscs),
					   GFP_KERNEL);
		if (!q->direct_qdiscs)
			return -ENOMEM;
	}

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

	if (tb[TCA_HTB_DIRECT_QLEN])
		q->direct_qlen = nla_get_u32(tb[TCA_HTB_DIRECT_QLEN]);
	else
		q->direct_qlen = qdisc_dev(sch)->tx_queue_len;

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

	if (!offload)
		return 0;

	for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) {
		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
		struct Qdisc *qdisc;

		qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
					  TC_H_MAKE(sch->handle, 0), extack);
		if (!qdisc) {
			return -ENOMEM;
		}

		htb_set_lockdep_class_child(qdisc);
		q->direct_qdiscs[ntx] = qdisc;
		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
	}

	sch->flags |= TCQ_F_MQROOT;

	offload_opt = (struct tc_htb_qopt_offload) {
		.command = TC_HTB_CREATE,
		.parent_classid = TC_H_MAJ(sch->handle) >> 16,
		.classid = TC_H_MIN(q->defcls),
		.extack = extack,
	};
	err = htb_offload(dev, &offload_opt);
	if (err)
		return err;

	/* Defer this assignment, so that htb_destroy skips offload-related
	 * parts (especially calling ndo_setup_tc) on errors.
	 */
	q->offload = true;

	return 0;
}

static void htb_attach_offload(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	struct htb_sched *q = qdisc_priv(sch);
	unsigned int ntx;

	for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) {
		struct Qdisc *old, *qdisc = q->direct_qdiscs[ntx];

		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
		qdisc_put(old);
		qdisc_hash_add(qdisc, false);
	}
	for (ntx = q->num_direct_qdiscs; ntx < dev->num_tx_queues; ntx++) {
		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
		struct Qdisc *old = dev_graft_qdisc(dev_queue, NULL);

		qdisc_put(old);
	}

	kfree(q->direct_qdiscs);
	q->direct_qdiscs = NULL;
}

static void htb_attach_software(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	unsigned int ntx;

	/* Resemble qdisc_graft behavior. */
	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
		struct Qdisc *old = dev_graft_qdisc(dev_queue, sch);

		qdisc_refcount_inc(sch);

		qdisc_put(old);
	}
}

static void htb_attach(struct Qdisc *sch)
{
	struct htb_sched *q = qdisc_priv(sch);

	if (q->offload)
		htb_attach_offload(sch);
	else
		htb_attach_software(sch);
}

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

	if (q->offload)
		sch->flags |= TCQ_F_OFFLOADED;
	else
		sch->flags &= ~TCQ_F_OFFLOADED;

	sch->qstats.overlimits = q->overlimits;
	/* Its safe to not acquire qdisc lock. As we hold RTNL,
	 * no change can happen on the qdisc parameters.
	 */

	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_noflag(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;
	if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) ||
	    nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen))
		goto nla_put_failure;
	if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD))
		goto nla_put_failure;

	return nla_nest_end(skb, nest);

nla_put_failure:
	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;
	struct htb_sched *q = qdisc_priv(sch);
	struct nlattr *nest;
	struct tc_htb_opt opt;

	/* Its safe to not acquire qdisc lock. As we hold RTNL,
	 * no change can happen on the class parameters.
	 */
	tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT;
	tcm->tcm_handle = cl->common.classid;
	if (!cl->level && cl->leaf.q)
		tcm->tcm_info = cl->leaf.q->handle;

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

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

	psched_ratecfg_getrate(&opt.rate, &cl->rate);
	opt.buffer = PSCHED_NS2TICKS(cl->buffer);
	psched_ratecfg_getrate(&opt.ceil, &cl->ceil);
	opt.cbuffer = PSCHED_NS2TICKS(cl->cbuffer);
	opt.quantum = cl->quantum;
	opt.prio = cl->prio;
	opt.level = cl->level;
	if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt))
		goto nla_put_failure;
	if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD))
		goto nla_put_failure;
	if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) &&
	    nla_put_u64_64bit(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps,
			      TCA_HTB_PAD))
		goto nla_put_failure;
	if ((cl->ceil.rate_bytes_ps >= (1ULL << 32)) &&
	    nla_put_u64_64bit(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps,
			      TCA_HTB_PAD))
		goto nla_put_failure;

	return nla_nest_end(skb, nest);

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

static void htb_offload_aggregate_stats(struct htb_sched *q,
					struct htb_class *cl)
{
	u64 bytes = 0, packets = 0;
	struct htb_class *c;
	unsigned int i;

	gnet_stats_basic_sync_init(&cl->bstats);

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(c, &q->clhash.hash[i], common.hnode) {
			struct htb_class *p = c;

			while (p && p->level < cl->level)
				p = p->parent;

			if (p != cl)
				continue;

			bytes += u64_stats_read(&c->bstats_bias.bytes);
			packets += u64_stats_read(&c->bstats_bias.packets);
			if (c->level == 0) {
				bytes += u64_stats_read(&c->leaf.q->bstats.bytes);
				packets += u64_stats_read(&c->leaf.q->bstats.packets);
			}
		}
	}
	_bstats_update(&cl->bstats, bytes, packets);
}

static int
htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
{
	struct htb_class *cl = (struct htb_class *)arg;
	struct htb_sched *q = qdisc_priv(sch);
	struct gnet_stats_queue qs = {
		.drops = cl->drops,
		.overlimits = cl->overlimits,
	};
	__u32 qlen = 0;

	if (!cl->level && cl->leaf.q)
		qdisc_qstats_qlen_backlog(cl->leaf.q, &qlen, &qs.backlog);

	cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens),
				    INT_MIN, INT_MAX);
	cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens),
				     INT_MIN, INT_MAX);

	if (q->offload) {
		if (!cl->level) {
			if (cl->leaf.q)
				cl->bstats = cl->leaf.q->bstats;
			else
				gnet_stats_basic_sync_init(&cl->bstats);
			_bstats_update(&cl->bstats,
				       u64_stats_read(&cl->bstats_bias.bytes),
				       u64_stats_read(&cl->bstats_bias.packets));
		} else {
			htb_offload_aggregate_stats(q, cl);
		}
	}

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

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

static struct netdev_queue *
htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm)
{
	struct net_device *dev = qdisc_dev(sch);
	struct tc_htb_qopt_offload offload_opt;
	struct htb_sched *q = qdisc_priv(sch);
	int err;

	if (!q->offload)
		return sch->dev_queue;

	offload_opt = (struct tc_htb_qopt_offload) {
		.command = TC_HTB_LEAF_QUERY_QUEUE,
		.classid = TC_H_MIN(tcm->tcm_parent),
	};
	err = htb_offload(dev, &offload_opt);
	if (err || offload_opt.qid >= dev->num_tx_queues)
		return NULL;
	return netdev_get_tx_queue(dev, offload_opt.qid);
}

static struct Qdisc *
htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q)
{
	struct net_device *dev = dev_queue->dev;
	struct Qdisc *old_q;

	if (dev->flags & IFF_UP)
		dev_deactivate(dev);
	old_q = dev_graft_qdisc(dev_queue, new_q);
	if (new_q)
		new_q->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
	if (dev->flags & IFF_UP)
		dev_activate(dev);

	return old_q;
}

static struct netdev_queue *htb_offload_get_queue(struct htb_class *cl)
{
	struct netdev_queue *queue;

	queue = cl->leaf.offload_queue;
	if (!(cl->leaf.q->flags & TCQ_F_BUILTIN))
		WARN_ON(cl->leaf.q->dev_queue != queue);

	return queue;
}

static void htb_offload_move_qdisc(struct Qdisc *sch, struct htb_class *cl_old,
				   struct htb_class *cl_new, bool destroying)
{
	struct netdev_queue *queue_old, *queue_new;
	struct net_device *dev = qdisc_dev(sch);

	queue_old = htb_offload_get_queue(cl_old);
	queue_new = htb_offload_get_queue(cl_new);

	if (!destroying) {
		struct Qdisc *qdisc;

		if (dev->flags & IFF_UP)
			dev_deactivate(dev);
		qdisc = dev_graft_qdisc(queue_old, NULL);
		WARN_ON(qdisc != cl_old->leaf.q);
	}

	if (!(cl_old->leaf.q->flags & TCQ_F_BUILTIN))
		cl_old->leaf.q->dev_queue = queue_new;
	cl_old->leaf.offload_queue = queue_new;

	if (!destroying) {
		struct Qdisc *qdisc;

		qdisc = dev_graft_qdisc(queue_new, cl_old->leaf.q);
		if (dev->flags & IFF_UP)
			dev_activate(dev);
		WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN));
	}
}

static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
		     struct Qdisc **old, struct netlink_ext_ack *extack)
{
	struct netdev_queue *dev_queue = sch->dev_queue;
	struct htb_class *cl = (struct htb_class *)arg;
	struct htb_sched *q = qdisc_priv(sch);
	struct Qdisc *old_q;

	if (cl->level)
		return -EINVAL;

	if (q->offload)
		dev_queue = htb_offload_get_queue(cl);

	if (!new) {
		new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
					cl->common.classid, extack);
		if (!new)
			return -ENOBUFS;
	}

	if (q->offload) {
		htb_set_lockdep_class_child(new);
		/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */
		qdisc_refcount_inc(new);
		old_q = htb_graft_helper(dev_queue, new);
	}

	*old = qdisc_replace(sch, new, &cl->leaf.q);

	if (q->offload) {
		WARN_ON(old_q != *old);
		qdisc_put(old_q);
	}

	return 0;
}

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

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

	htb_deactivate(qdisc_priv(sch), 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 Qdisc *sch, struct htb_class *cl,
			       struct Qdisc *new_q)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *parent = cl->parent;

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

	if (parent->cmode != HTB_CAN_SEND)
		htb_safe_rb_erase(&parent->pq_node,
				  &q->hlevel[parent->level].wait_pq);

	parent->level = 0;
	memset(&parent->inner, 0, sizeof(parent->inner));
	parent->leaf.q = new_q ? new_q : &noop_qdisc;
	parent->tokens = parent->buffer;
	parent->ctokens = parent->cbuffer;
	parent->t_c = ktime_get_ns();
	parent->cmode = HTB_CAN_SEND;
	if (q->offload)
		parent->leaf.offload_queue = cl->leaf.offload_queue;
}

static void htb_parent_to_leaf_offload(struct Qdisc *sch,
				       struct netdev_queue *dev_queue,
				       struct Qdisc *new_q)
{
	struct Qdisc *old_q;

	/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */
	if (new_q)
		qdisc_refcount_inc(new_q);
	old_q = htb_graft_helper(dev_queue, new_q);
	WARN_ON(!(old_q->flags & TCQ_F_BUILTIN));
}

static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl,
				     bool last_child, bool destroying,
				     struct netlink_ext_ack *extack)
{
	struct tc_htb_qopt_offload offload_opt;
	struct netdev_queue *dev_queue;
	struct Qdisc *q = cl->leaf.q;
	struct Qdisc *old;
	int err;

	if (cl->level)
		return -EINVAL;

	WARN_ON(!q);
	dev_queue = htb_offload_get_queue(cl);
	/* When destroying, caller qdisc_graft grafts the new qdisc and invokes
	 * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload
	 * does not need to graft or qdisc_put the qdisc being destroyed.
	 */
	if (!destroying) {
		old = htb_graft_helper(dev_queue, NULL);
		/* Last qdisc grafted should be the same as cl->leaf.q when
		 * calling htb_delete.
		 */
		WARN_ON(old != q);
	}

	if (cl->parent) {
		_bstats_update(&cl->parent->bstats_bias,
			       u64_stats_read(&q->bstats.bytes),
			       u64_stats_read(&q->bstats.packets));
	}

	offload_opt = (struct tc_htb_qopt_offload) {
		.command = !last_child ? TC_HTB_LEAF_DEL :
			   destroying ? TC_HTB_LEAF_DEL_LAST_FORCE :
			   TC_HTB_LEAF_DEL_LAST,
		.classid = cl->common.classid,
		.extack = extack,
	};
	err = htb_offload(qdisc_dev(sch), &offload_opt);

	if (!destroying) {
		if (!err)
			qdisc_put(old);
		else
			htb_graft_helper(dev_queue, old);
	}

	if (last_child)
		return err;

	if (!err && offload_opt.classid != TC_H_MIN(cl->common.classid)) {
		u32 classid = TC_H_MAJ(sch->handle) |
			      TC_H_MIN(offload_opt.classid);
		struct htb_class *moved_cl = htb_find(classid, sch);

		htb_offload_move_qdisc(sch, moved_cl, cl, destroying);
	}

	return err;
}

static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
{
	if (!cl->level) {
		WARN_ON(!cl->leaf.q);
		qdisc_put(cl->leaf.q);
	}
	gen_kill_estimator(&cl->rate_est);
	tcf_block_put(cl->block);
	kfree(cl);
}

static void htb_destroy(struct Qdisc *sch)
{
	struct net_device *dev = qdisc_dev(sch);
	struct tc_htb_qopt_offload offload_opt;
	struct htb_sched *q = qdisc_priv(sch);
	struct hlist_node *next;
	bool nonempty, changed;
	struct htb_class *cl;
	unsigned int i;

	cancel_work_sync(&q->work);
	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_block_put(q->block);

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
			tcf_block_put(cl->block);
			cl->block = NULL;
		}
	}

	do {
		nonempty = false;
		changed = false;
		for (i = 0; i < q->clhash.hashsize; i++) {
			hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
						  common.hnode) {
				bool last_child;

				if (!q->offload) {
					htb_destroy_class(sch, cl);
					continue;
				}

				nonempty = true;

				if (cl->level)
					continue;

				changed = true;

				last_child = htb_parent_last_child(cl);
				htb_destroy_class_offload(sch, cl, last_child,
							  true, NULL);
				qdisc_class_hash_remove(&q->clhash,
							&cl->common);
				if (cl->parent)
					cl->parent->children--;
				if (last_child)
					htb_parent_to_leaf(sch, cl, NULL);
				htb_destroy_class(sch, cl);
			}
		}
	} while (changed);
	WARN_ON(nonempty);

	qdisc_class_hash_destroy(&q->clhash);
	__qdisc_reset_queue(&q->direct_queue);

	if (q->offload) {
		offload_opt = (struct tc_htb_qopt_offload) {
			.command = TC_HTB_DESTROY,
		};
		htb_offload(dev, &offload_opt);
	}

	if (!q->direct_qdiscs)
		return;
	for (i = 0; i < q->num_direct_qdiscs && q->direct_qdiscs[i]; i++)
		qdisc_put(q->direct_qdiscs[i]);
	kfree(q->direct_qdiscs);
}

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

	/* TODO: why don't allow to delete subtree ? references ? does
	 * tc subsys guarantee 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))
		last_child = 1;

	if (q->offload) {
		err = htb_destroy_class_offload(sch, cl, last_child, false,
						extack);
		if (err)
			return err;
	}

	if (last_child) {
		struct netdev_queue *dev_queue = sch->dev_queue;

		if (q->offload)
			dev_queue = htb_offload_get_queue(cl);

		new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
					  cl->parent->common.classid,
					  NULL);
		if (q->offload) {
			if (new_q)
				htb_set_lockdep_class_child(new_q);
			htb_parent_to_leaf_offload(sch, dev_queue, new_q);
		}
	}

	sch_tree_lock(sch);

	if (!cl->level)
		qdisc_purge_queue(cl->leaf.q);

	/* 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->hlevel[cl->level].wait_pq);

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

	sch_tree_unlock(sch);

	htb_destroy_class(sch, cl);
	return 0;
}

static int htb_change_class(struct Qdisc *sch, u32 classid,
			    u32 parentid, struct nlattr **tca,
			    unsigned long *arg, struct netlink_ext_ack *extack)
{
	int err = -EINVAL;
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = (struct htb_class *)*arg, *parent;
	struct tc_htb_qopt_offload offload_opt;
	struct nlattr *opt = tca[TCA_OPTIONS];
	struct nlattr *tb[TCA_HTB_MAX + 1];
	struct Qdisc *parent_qdisc = NULL;
	struct netdev_queue *dev_queue;
	struct tc_htb_opt *hopt;
	u64 rate64, ceil64;
	int warn = 0;

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

	err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy,
					  NULL);
	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]);
	if (!hopt->rate.rate || !hopt->ceil.rate)
		goto failure;

	if (q->offload) {
		/* Options not supported by the offload. */
		if (hopt->rate.overhead || hopt->ceil.overhead) {
			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the overhead parameter");
			goto failure;
		}
		if (hopt->rate.mpu || hopt->ceil.mpu) {
			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter");
			goto failure;
		}
		if (hopt->quantum) {
			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter");
			goto failure;
		}
		if (hopt->prio) {
			NL_SET_ERR_MSG(extack, "HTB offload doesn't support the prio parameter");
			goto failure;
		}
	}

	/* Keeping backward compatible with rate_table based iproute2 tc */
	if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
		qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB],
					      NULL));

	if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE)
		qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB],
					      NULL));

	rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
	ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;

	if (!cl) {		/* new class */
		struct net_device *dev = qdisc_dev(sch);
		struct Qdisc *new_q, *old_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) {
			pr_err("htb: tree is too deep\n");
			goto failure;
		}
		err = -ENOBUFS;
		cl = kzalloc(sizeof(*cl), GFP_KERNEL);
		if (!cl)
			goto failure;

		gnet_stats_basic_sync_init(&cl->bstats);
		gnet_stats_basic_sync_init(&cl->bstats_bias);

		err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack);
		if (err) {
			kfree(cl);
			goto failure;
		}
		if (htb_rate_est || tca[TCA_RATE]) {
			err = gen_new_estimator(&cl->bstats, NULL,
						&cl->rate_est,
						NULL,
						true,
						tca[TCA_RATE] ? : &est.nla);
			if (err)
				goto err_block_put;
		}

		cl->children = 0;
		RB_CLEAR_NODE(&cl->pq_node);

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

		cl->common.classid = classid;

		/* Make sure nothing interrupts us in between of two
		 * ndo_setup_tc calls.
		 */
		ASSERT_RTNL();

		/* 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
		 */
		if (!q->offload) {
			dev_queue = sch->dev_queue;
		} else if (!(parent && !parent->level)) {
			/* Assign a dev_queue to this classid. */
			offload_opt = (struct tc_htb_qopt_offload) {
				.command = TC_HTB_LEAF_ALLOC_QUEUE,
				.classid = cl->common.classid,
				.parent_classid = parent ?
					TC_H_MIN(parent->common.classid) :
					TC_HTB_CLASSID_ROOT,
				.rate = max_t(u64, hopt->rate.rate, rate64),
				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
				.extack = extack,
			};
			err = htb_offload(dev, &offload_opt);
			if (err) {
				pr_err("htb: TC_HTB_LEAF_ALLOC_QUEUE failed with err = %d\n",
				       err);
				goto err_kill_estimator;
			}
			dev_queue = netdev_get_tx_queue(dev, offload_opt.qid);
		} else { /* First child. */
			dev_queue = htb_offload_get_queue(parent);
			old_q = htb_graft_helper(dev_queue, NULL);
			WARN_ON(old_q != parent->leaf.q);
			offload_opt = (struct tc_htb_qopt_offload) {
				.command = TC_HTB_LEAF_TO_INNER,
				.classid = cl->common.classid,
				.parent_classid =
					TC_H_MIN(parent->common.classid),
				.rate = max_t(u64, hopt->rate.rate, rate64),
				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
				.extack = extack,
			};
			err = htb_offload(dev, &offload_opt);
			if (err) {
				pr_err("htb: TC_HTB_LEAF_TO_INNER failed with err = %d\n",
				       err);
				htb_graft_helper(dev_queue, old_q);
				goto err_kill_estimator;
			}
			_bstats_update(&parent->bstats_bias,
				       u64_stats_read(&old_q->bstats.bytes),
				       u64_stats_read(&old_q->bstats.packets));
			qdisc_put(old_q);
		}
		new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops,
					  classid, NULL);
		if (q->offload) {
			if (new_q) {
				htb_set_lockdep_class_child(new_q);
				/* One ref for cl->leaf.q, the other for
				 * dev_queue->qdisc.
				 */
				qdisc_refcount_inc(new_q);
			}
			old_q = htb_graft_helper(dev_queue, new_q);
			/* No qdisc_put needed. */
			WARN_ON(!(old_q->flags & TCQ_F_BUILTIN));
		}
		sch_tree_lock(sch);
		if (parent && !parent->level) {
			/* turn parent into inner node */
			qdisc_purge_queue(parent->leaf.q);
			parent_qdisc = parent->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->hlevel[0].wait_pq);
				parent->cmode = HTB_CAN_SEND;
			}
			parent->level = (parent->parent ? parent->parent->level
					 : TC_HTB_MAXDEPTH) - 1;
			memset(&parent->inner, 0, sizeof(parent->inner));
		}

		/* leaf (we) needs elementary qdisc */
		cl->leaf.q = new_q ? new_q : &noop_qdisc;
		if (q->offload)
			cl->leaf.offload_queue = dev_queue;

		cl->parent = parent;

		/* set class to be in HTB_CAN_SEND state */
		cl->tokens = PSCHED_TICKS2NS(hopt->buffer);
		cl->ctokens = PSCHED_TICKS2NS(hopt->cbuffer);
		cl->mbuffer = 60ULL * NSEC_PER_SEC;	/* 1min */
		cl->t_c = ktime_get_ns();
		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++;
		if (cl->leaf.q != &noop_qdisc)
			qdisc_hash_add(cl->leaf.q, true);
	} else {
		if (tca[TCA_RATE]) {
			err = gen_replace_estimator(&cl->bstats, NULL,
						    &cl->rate_est,
						    NULL,
						    true,
						    tca[TCA_RATE]);
			if (err)
				return err;
		}

		if (q->offload) {
			struct net_device *dev = qdisc_dev(sch);

			offload_opt = (struct tc_htb_qopt_offload) {
				.command = TC_HTB_NODE_MODIFY,
				.classid = cl->common.classid,
				.rate = max_t(u64, hopt->rate.rate, rate64),
				.ceil = max_t(u64, hopt->ceil.rate, ceil64),
				.extack = extack,
			};
			err = htb_offload(dev, &offload_opt);
			if (err)
				/* Estimator was replaced, and rollback may fail
				 * as well, so we don't try to recover it, and
				 * the estimator won't work property with the
				 * offload anyway, because bstats are updated
				 * only when the stats are queried.
				 */
				return err;
		}

		sch_tree_lock(sch);
	}

	psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);

	/* it used to be a nasty bug here, we have to check that node
	 * is really leaf before changing cl->leaf !
	 */
	if (!cl->level) {
		u64 quantum = cl->rate.rate_bytes_ps;

		do_div(quantum, q->rate2quantum);
		cl->quantum = min_t(u64, quantum, INT_MAX);

		if (!hopt->quantum && cl->quantum < 1000) {
			warn = -1;
			cl->quantum = 1000;
		}
		if (!hopt->quantum && cl->quantum > 200000) {
			warn = 1;
			cl->quantum = 200000;
		}
		if (hopt->quantum)
			cl->quantum = hopt->quantum;
		if ((cl->prio = hopt->prio) >= TC_HTB_NUMPRIO)
			cl->prio = TC_HTB_NUMPRIO - 1;
	}

	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);

	sch_tree_unlock(sch);
	qdisc_put(parent_qdisc);

	if (warn)
		pr_warn("HTB: quantum of class %X is %s. Consider r2q change.\n",
			    cl->common.classid, (warn == -1 ? "small" : "big"));

	qdisc_class_hash_grow(sch, &q->clhash);

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

err_kill_estimator:
	gen_kill_estimator(&cl->rate_est);
err_block_put:
	tcf_block_put(cl->block);
	kfree(cl);
failure:
	return err;
}

static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg,
				       struct netlink_ext_ack *extack)
{
	struct htb_sched *q = qdisc_priv(sch);
	struct htb_class *cl = (struct htb_class *)arg;

	return cl ? cl->block : q->block;
}

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;
	unsigned int i;

	if (arg->stop)
		return;

	for (i = 0; i < q->clhash.hashsize; i++) {
		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
			if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg))
				return;
		}
	}
}

static const struct Qdisc_class_ops htb_class_ops = {
	.select_queue	=	htb_select_queue,
	.graft		=	htb_graft,
	.leaf		=	htb_leaf,
	.qlen_notify	=	htb_qlen_notify,
	.find		=	htb_search,
	.change		=	htb_change_class,
	.delete		=	htb_delete,
	.walk		=	htb_walk,
	.tcf_block	=	htb_tcf_block,
	.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 = {
	.cl_ops		=	&htb_class_ops,
	.id		=	"htb",
	.priv_size	=	sizeof(struct htb_sched),
	.enqueue	=	htb_enqueue,
	.dequeue	=	htb_dequeue,
	.peek		=	qdisc_peek_dequeued,
	.init		=	htb_init,
	.attach		=	htb_attach,
	.reset		=	htb_reset,
	.destroy	=	htb_destroy,
	.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");