sch_qfq.c 42.6 KB
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
/*
 * net/sched/sch_qfq.c         Quick Fair Queueing Plus Scheduler.
 *
 * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente.
 * Copyright (c) 2012 Paolo Valente.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * version 2 as published by the Free Software Foundation.
 */

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


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

    Sources:

    [1] Paolo Valente,
    "Reducing the Execution Time of Fair-Queueing Schedulers."
    http://algo.ing.unimo.it/people/paolo/agg-sched/agg-sched.pdf

    Sources for QFQ:

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

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

/*

  QFQ+ divides classes into aggregates of at most MAX_AGG_CLASSES
  classes. Each aggregate is timestamped with a virtual start time S
  and a virtual finish time F, and scheduled according to its
  timestamps. S and F are computed as a function of a system virtual
  time function V. The classes within each aggregate are instead
  scheduled with DRR.

  To speed up operations, QFQ+ divides also aggregates into a limited
  number of groups. Which group a class belongs to depends on the
  ratio between the maximum packet length for the class and the weight
  of the class. Groups have their own S and F. In the end, QFQ+
  schedules groups, then aggregates within groups, then classes within
  aggregates. See [1] and [2] for a full description.

  Virtual time computations.

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

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

  The layout of the bits is as below:

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

  where MIN_SLOT_SHIFT is derived by difference from the others.

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

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

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

 */

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

/*
 * Shifts used for aggregate<->group mapping.  We allow class weights that are
 * in the range [1, 2^MAX_WSHIFT], and we try to map each aggregate i to the
 * group with the smallest index that can support the L_i / r_i configured
 * for the classes in the aggregate.
 *
 * grp->index is the index of the group; and grp->slot_shift
 * is the shift for the corresponding (scaled) sigma_i.
 */
#define QFQ_MAX_INDEX		24
#define QFQ_MAX_WSHIFT		10

#define	QFQ_MAX_WEIGHT		(1<<QFQ_MAX_WSHIFT) /* see qfq_slot_insert */
#define QFQ_MAX_WSUM		(64*QFQ_MAX_WEIGHT)

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

#define QFQ_MTU_SHIFT		16	/* to support TSO/GSO */
#define QFQ_MIN_LMAX		512	/* see qfq_slot_insert */

#define QFQ_MAX_AGG_CLASSES	8 /* max num classes per aggregate allowed */

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

struct qfq_group;

struct qfq_aggregate;

struct qfq_class {
	struct Qdisc_class_common common;

	unsigned int refcnt;
	unsigned int filter_cnt;

	struct gnet_stats_basic_packed bstats;
	struct gnet_stats_queue qstats;
	struct gnet_stats_rate_est64 rate_est;
	struct Qdisc *qdisc;
	struct list_head alist;		/* Link for active-classes list. */
	struct qfq_aggregate *agg;	/* Parent aggregate. */
	int deficit;			/* DRR deficit counter. */
};

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

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

	/* these are copied from the flowset. */
	u32	class_weight; /* Weight of each class in this aggregate. */
	/* Max pkt size for the classes in this aggregate, DRR quantum. */
	int	lmax;

	u32	inv_w;	    /* ONE_FP/(sum of weights of classes in aggr.). */
	u32	budgetmax;  /* Max budget for this aggregate. */
	u32	initial_budget, budget;     /* Initial and current budget. */

	int		  num_classes;	/* Number of classes in this aggr. */
	struct list_head  active;	/* DRR queue of active classes. */

	struct hlist_node nonfull_next;	/* See nonfull_aggs in qfq_sched. */
};

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

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

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

	u64			oldV, V;	/* Precise virtual times. */
	struct qfq_aggregate	*in_serv_agg;   /* Aggregate being served. */
	u32			num_active_agg; /* Num. of active aggregates */
	u32			wsum;		/* weight sum */
	u32			iwsum;		/* inverse weight sum */

	unsigned long bitmaps[QFQ_MAX_STATE];	    /* Group bitmaps. */
	struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
	u32 min_slot_shift;	/* Index of the group-0 bit in the bitmaps. */

	u32 max_agg_classes;		/* Max number of classes per aggr. */
	struct hlist_head nonfull_aggs; /* Aggs with room for more classes. */
};

/*
 * Possible reasons why the timestamps of an aggregate are updated
 * enqueue: the aggregate switches from idle to active and must scheduled
 *	    for service
 * requeue: the aggregate finishes its budget, so it stops being served and
 *	    must be rescheduled for service
 */
enum update_reason {enqueue, requeue};

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

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

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

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

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

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

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

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

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

	return index;
}

static void qfq_deactivate_agg(struct qfq_sched *, struct qfq_aggregate *);
static void qfq_activate_agg(struct qfq_sched *, struct qfq_aggregate *,
			     enum update_reason);

static void qfq_init_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
			 u32 lmax, u32 weight)
{
	INIT_LIST_HEAD(&agg->active);
	hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs);

	agg->lmax = lmax;
	agg->class_weight = weight;
}

static struct qfq_aggregate *qfq_find_agg(struct qfq_sched *q,
					  u32 lmax, u32 weight)
{
	struct qfq_aggregate *agg;

	hlist_for_each_entry(agg, &q->nonfull_aggs, nonfull_next)
		if (agg->lmax == lmax && agg->class_weight == weight)
			return agg;

	return NULL;
}


/* Update aggregate as a function of the new number of classes. */
static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
			   int new_num_classes)
{
	u32 new_agg_weight;

	if (new_num_classes == q->max_agg_classes)
		hlist_del_init(&agg->nonfull_next);

	if (agg->num_classes > new_num_classes &&
	    new_num_classes == q->max_agg_classes - 1) /* agg no more full */
		hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs);

	/* The next assignment may let
	 * agg->initial_budget > agg->budgetmax
	 * hold, we will take it into account in charge_actual_service().
	 */
	agg->budgetmax = new_num_classes * agg->lmax;
	new_agg_weight = agg->class_weight * new_num_classes;
	agg->inv_w = ONE_FP/new_agg_weight;

	if (agg->grp == NULL) {
		int i = qfq_calc_index(agg->inv_w, agg->budgetmax,
				       q->min_slot_shift);
		agg->grp = &q->groups[i];
	}

	q->wsum +=
		(int) agg->class_weight * (new_num_classes - agg->num_classes);
	q->iwsum = ONE_FP / q->wsum;

	agg->num_classes = new_num_classes;
}

/* Add class to aggregate. */
static void qfq_add_to_agg(struct qfq_sched *q,
			   struct qfq_aggregate *agg,
			   struct qfq_class *cl)
{
	cl->agg = agg;

	qfq_update_agg(q, agg, agg->num_classes+1);
	if (cl->qdisc->q.qlen > 0) { /* adding an active class */
		list_add_tail(&cl->alist, &agg->active);
		if (list_first_entry(&agg->active, struct qfq_class, alist) ==
		    cl && q->in_serv_agg != agg) /* agg was inactive */
			qfq_activate_agg(q, agg, enqueue); /* schedule agg */
	}
}

static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *);

static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
{
	if (!hlist_unhashed(&agg->nonfull_next))
		hlist_del_init(&agg->nonfull_next);
	q->wsum -= agg->class_weight;
	if (q->wsum != 0)
		q->iwsum = ONE_FP / q->wsum;

	if (q->in_serv_agg == agg)
		q->in_serv_agg = qfq_choose_next_agg(q);
	kfree(agg);
}

/* Deschedule class from within its parent aggregate. */
static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
{
	struct qfq_aggregate *agg = cl->agg;


	list_del(&cl->alist); /* remove from RR queue of the aggregate */
	if (list_empty(&agg->active)) /* agg is now inactive */
		qfq_deactivate_agg(q, agg);
}

/* Remove class from its parent aggregate. */
static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl)
{
	struct qfq_aggregate *agg = cl->agg;

	cl->agg = NULL;
	if (agg->num_classes == 1) { /* agg being emptied, destroy it */
		qfq_destroy_agg(q, agg);
		return;
	}
	qfq_update_agg(q, agg, agg->num_classes-1);
}

/* Deschedule class and remove it from its parent aggregate. */
static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl)
{
	if (cl->qdisc->q.qlen > 0) /* class is active */
		qfq_deactivate_class(q, cl);

	qfq_rm_from_agg(q, cl);
}

/* Move class to a new aggregate, matching the new class weight and/or lmax */
static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
			   u32 lmax)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight);

	if (new_agg == NULL) { /* create new aggregate */
		new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC);
		if (new_agg == NULL)
			return -ENOBUFS;
		qfq_init_agg(q, new_agg, lmax, weight);
	}
	qfq_deact_rm_from_agg(q, cl);
	qfq_add_to_agg(q, new_agg, cl);

	return 0;
}

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

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

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

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

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

	inv_w = ONE_FP / weight;
	weight = ONE_FP / inv_w;

	if (cl != NULL &&
	    lmax == cl->agg->lmax &&
	    weight == cl->agg->class_weight)
		return 0; /* nothing to change */

	delta_w = weight - (cl ? cl->agg->class_weight : 0);

	if (q->wsum + delta_w > QFQ_MAX_WSUM) {
		pr_notice("qfq: total weight out of range (%d + %u)\n",
			  delta_w, q->wsum);
		return -EINVAL;
	}

	if (cl != NULL) { /* modify existing class */
		if (tca[TCA_RATE]) {
			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
						    qdisc_root_sleeping_lock(sch),
						    tca[TCA_RATE]);
			if (err)
				return err;
		}
		existing = true;
		goto set_change_agg;
	}

	/* create and init new class */
	cl = kzalloc(sizeof(struct qfq_class), GFP_KERNEL);
	if (cl == NULL)
		return -ENOBUFS;

	cl->refcnt = 1;
	cl->common.classid = classid;
	cl->deficit = lmax;

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

	if (tca[TCA_RATE]) {
		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
					qdisc_root_sleeping_lock(sch),
					tca[TCA_RATE]);
		if (err)
			goto destroy_class;
	}

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

	qdisc_class_hash_grow(sch, &q->clhash);

set_change_agg:
	sch_tree_lock(sch);
	new_agg = qfq_find_agg(q, lmax, weight);
	if (new_agg == NULL) { /* create new aggregate */
		sch_tree_unlock(sch);
		new_agg = kzalloc(sizeof(*new_agg), GFP_KERNEL);
		if (new_agg == NULL) {
			err = -ENOBUFS;
			gen_kill_estimator(&cl->bstats, &cl->rate_est);
			goto destroy_class;
		}
		sch_tree_lock(sch);
		qfq_init_agg(q, new_agg, lmax, weight);
	}
	if (existing)
		qfq_deact_rm_from_agg(q, cl);
	qfq_add_to_agg(q, new_agg, cl);
	sch_tree_unlock(sch);

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

destroy_class:
	qdisc_destroy(cl->qdisc);
	kfree(cl);
	return err;
}

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

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

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

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

	sch_tree_lock(sch);

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

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

	sch_tree_unlock(sch);
	return 0;
}

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

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

	return (unsigned long)cl;
}

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

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

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

	if (cl)
		return NULL;

	return &q->filter_list;
}

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

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

	return (unsigned long)cl;
}

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

	cl->filter_cnt--;
}

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

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

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

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

	return cl->qdisc;
}

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

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

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;
	if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) ||
	    nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax))
		goto nla_put_failure;
	return nla_nest_end(skb, nest);

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

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

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

	xstats.weight = cl->agg->class_weight;
	xstats.lmax = cl->agg->lmax;

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

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

static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl;
	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 (arg->count < arg->skip) {
				arg->count++;
				continue;
			}
			if (arg->fn(sch, (unsigned long)cl, arg) < 0) {
				arg->stop = 1;
				return;
			}
			arg->count++;
		}
	}
}

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

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

	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
	result = tc_classify(skb, q->filter_list, &res);
	if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
		switch (result) {
		case TC_ACT_QUEUED:
		case TC_ACT_STOLEN:
			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
		case TC_ACT_SHOT:
			return NULL;
		}
#endif
		cl = (struct qfq_class *)res.class;
		if (cl == NULL)
			cl = qfq_find_class(sch, res.classid);
		return cl;
	}

	return NULL;
}

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

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

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

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

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

	return state;
}


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

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

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

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

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

	if (vslot != old_vslot) {
		unsigned long mask;
		int last_flip_pos = fls(vslot ^ old_vslot);

		if (last_flip_pos > 31) /* higher than the number of groups */
			mask = ~0UL;    /* make all groups eligible */
		else
			mask = (1UL << last_flip_pos) - 1;

		qfq_move_groups(q, mask, IR, ER);
		qfq_move_groups(q, mask, IB, EB);
	}
}

/*
 * The index of the slot in which the input aggregate agg is to be
 * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2'
 * and not a '-1' because the start time of the group may be moved
 * backward by one slot after the aggregate has been inserted, and
 * this would cause non-empty slots to be right-shifted by one
 * position.
 *
 * QFQ+ fully satisfies this bound to the slot index if the parameters
 * of the classes are not changed dynamically, and if QFQ+ never
 * happens to postpone the service of agg unjustly, i.e., it never
 * happens that the aggregate becomes backlogged and eligible, or just
 * eligible, while an aggregate with a higher approximated finish time
 * is being served. In particular, in this case QFQ+ guarantees that
 * the timestamps of agg are low enough that the slot index is never
 * higher than 2. Unfortunately, QFQ+ cannot provide the same
 * guarantee if it happens to unjustly postpone the service of agg, or
 * if the parameters of some class are changed.
 *
 * As for the first event, i.e., an out-of-order service, the
 * upper bound to the slot index guaranteed by QFQ+ grows to
 * 2 +
 * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
 * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1.
 *
 * The following function deals with this problem by backward-shifting
 * the timestamps of agg, if needed, so as to guarantee that the slot
 * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may
 * cause the service of other aggregates to be postponed, yet the
 * worst-case guarantees of these aggregates are not violated.  In
 * fact, in case of no out-of-order service, the timestamps of agg
 * would have been even lower than they are after the backward shift,
 * because QFQ+ would have guaranteed a maximum value equal to 2 for
 * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose
 * service is postponed because of the backward-shift would have
 * however waited for the service of agg before being served.
 *
 * The other event that may cause the slot index to be higher than 2
 * for agg is a recent change of the parameters of some class. If the
 * weight of a class is increased or the lmax (max_pkt_size) of the
 * class is decreased, then a new aggregate with smaller slot size
 * than the original parent aggregate of the class may happen to be
 * activated. The activation of this aggregate should be properly
 * delayed to when the service of the class has finished in the ideal
 * system tracked by QFQ+. If the activation of the aggregate is not
 * delayed to this reference time instant, then this aggregate may be
 * unjustly served before other aggregates waiting for service. This
 * may cause the above bound to the slot index to be violated for some
 * of these unlucky aggregates.
 *
 * Instead of delaying the activation of the new aggregate, which is
 * quite complex, the above-discussed capping of the slot index is
 * used to handle also the consequences of a change of the parameters
 * of a class.
 */
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg,
			    u64 roundedS)
{
	u64 slot = (roundedS - grp->S) >> grp->slot_shift;
	unsigned int i; /* slot index in the bucket list */

	if (unlikely(slot > QFQ_MAX_SLOTS - 2)) {
		u64 deltaS = roundedS - grp->S -
			((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift);
		agg->S -= deltaS;
		agg->F -= deltaS;
		slot = QFQ_MAX_SLOTS - 2;
	}

	i = (grp->front + slot) % QFQ_MAX_SLOTS;

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

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

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

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

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

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

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

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

	return qfq_slot_head(grp);
}

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

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

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

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

/* Dequeue head packet of the head class in the DRR queue of the aggregate. */
static void agg_dequeue(struct qfq_aggregate *agg,
			struct qfq_class *cl, unsigned int len)
{
	qdisc_dequeue_peeked(cl->qdisc);

	cl->deficit -= (int) len;

	if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
		list_del(&cl->alist);
	else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
		cl->deficit += agg->lmax;
		list_move_tail(&cl->alist, &agg->active);
	}
}

static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
					   struct qfq_class **cl,
					   unsigned int *len)
{
	struct sk_buff *skb;

	*cl = list_first_entry(&agg->active, struct qfq_class, alist);
	skb = (*cl)->qdisc->ops->peek((*cl)->qdisc);
	if (skb == NULL)
		WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n");
	else
		*len = qdisc_pkt_len(skb);

	return skb;
}

/* Update F according to the actual service received by the aggregate. */
static inline void charge_actual_service(struct qfq_aggregate *agg)
{
	/* Compute the service received by the aggregate, taking into
	 * account that, after decreasing the number of classes in
	 * agg, it may happen that
	 * agg->initial_budget - agg->budget > agg->bugdetmax
	 */
	u32 service_received = min(agg->budgetmax,
				   agg->initial_budget - agg->budget);

	agg->F = agg->S + (u64)service_received * agg->inv_w;
}

/* Assign a reasonable start time for a new aggregate in group i.
 * Admissible values for \hat(F) are multiples of \sigma_i
 * no greater than V+\sigma_i . Larger values mean that
 * we had a wraparound so we consider the timestamp to be stale.
 *
 * If F is not stale and F >= V then we set S = F.
 * Otherwise we should assign S = V, but this may violate
 * the ordering in EB (see [2]). So, if we have groups in ER,
 * set S to the F_j of the first group j which would be blocking us.
 * We are guaranteed not to move S backward because
 * otherwise our group i would still be blocked.
 */
static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg)
{
	unsigned long mask;
	u64 limit, roundedF;
	int slot_shift = agg->grp->slot_shift;

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

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

/* Update the timestamps of agg before scheduling/rescheduling it for
 * service.  In particular, assign to agg->F its maximum possible
 * value, i.e., the virtual finish time with which the aggregate
 * should be labeled if it used all its budget once in service.
 */
static inline void
qfq_update_agg_ts(struct qfq_sched *q,
		    struct qfq_aggregate *agg, enum update_reason reason)
{
	if (reason != requeue)
		qfq_update_start(q, agg);
	else /* just charge agg for the service received */
		agg->S = agg->F;

	agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w;
}

static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg);

static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_aggregate *in_serv_agg = q->in_serv_agg;
	struct qfq_class *cl;
	struct sk_buff *skb = NULL;
	/* next-packet len, 0 means no more active classes in in-service agg */
	unsigned int len = 0;

	if (in_serv_agg == NULL)
		return NULL;

	if (!list_empty(&in_serv_agg->active))
		skb = qfq_peek_skb(in_serv_agg, &cl, &len);

	/*
	 * If there are no active classes in the in-service aggregate,
	 * or if the aggregate has not enough budget to serve its next
	 * class, then choose the next aggregate to serve.
	 */
	if (len == 0 || in_serv_agg->budget < len) {
		charge_actual_service(in_serv_agg);

		/* recharge the budget of the aggregate */
		in_serv_agg->initial_budget = in_serv_agg->budget =
			in_serv_agg->budgetmax;

		if (!list_empty(&in_serv_agg->active)) {
			/*
			 * Still active: reschedule for
			 * service. Possible optimization: if no other
			 * aggregate is active, then there is no point
			 * in rescheduling this aggregate, and we can
			 * just keep it as the in-service one. This
			 * should be however a corner case, and to
			 * handle it, we would need to maintain an
			 * extra num_active_aggs field.
			*/
			qfq_update_agg_ts(q, in_serv_agg, requeue);
			qfq_schedule_agg(q, in_serv_agg);
		} else if (sch->q.qlen == 0) { /* no aggregate to serve */
			q->in_serv_agg = NULL;
			return NULL;
		}

		/*
		 * If we get here, there are other aggregates queued:
		 * choose the new aggregate to serve.
		 */
		in_serv_agg = q->in_serv_agg = qfq_choose_next_agg(q);
		skb = qfq_peek_skb(in_serv_agg, &cl, &len);
	}
	if (!skb)
		return NULL;

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

	agg_dequeue(in_serv_agg, cl, len);
	/* If lmax is lowered, through qfq_change_class, for a class
	 * owning pending packets with larger size than the new value
	 * of lmax, then the following condition may hold.
	 */
	if (unlikely(in_serv_agg->budget < len))
		in_serv_agg->budget = 0;
	else
		in_serv_agg->budget -= len;

	q->V += (u64)len * q->iwsum;
	pr_debug("qfq dequeue: len %u F %lld now %lld\n",
		 len, (unsigned long long) in_serv_agg->F,
		 (unsigned long long) q->V);

	return skb;
}

static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q)
{
	struct qfq_group *grp;
	struct qfq_aggregate *agg, *new_front_agg;
	u64 old_F;

	qfq_update_eligible(q);
	q->oldV = q->V;

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

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

	agg = qfq_slot_head(grp);

	/* agg starts to be served, remove it from schedule */
	qfq_front_slot_remove(grp);

	new_front_agg = qfq_slot_scan(grp);

	if (new_front_agg == NULL) /* group is now inactive, remove from ER */
		__clear_bit(grp->index, &q->bitmaps[ER]);
	else {
		u64 roundedS = qfq_round_down(new_front_agg->S,
					      grp->slot_shift);
		unsigned int s;

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

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

	return agg;
}

static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_class *cl;
	struct qfq_aggregate *agg;
	int err = 0;

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

	if (unlikely(cl->agg->lmax < qdisc_pkt_len(skb))) {
		pr_debug("qfq: increasing maxpkt from %u to %u for class %u",
			 cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
		err = qfq_change_agg(sch, cl, cl->agg->class_weight,
				     qdisc_pkt_len(skb));
		if (err)
			return err;
	}

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

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

	agg = cl->agg;
	/* if the queue was not empty, then done here */
	if (cl->qdisc->q.qlen != 1) {
		if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
		    list_first_entry(&agg->active, struct qfq_class, alist)
		    == cl && cl->deficit < qdisc_pkt_len(skb))
			list_move_tail(&cl->alist, &agg->active);

		return err;
	}

	/* schedule class for service within the aggregate */
	cl->deficit = agg->lmax;
	list_add_tail(&cl->alist, &agg->active);

	if (list_first_entry(&agg->active, struct qfq_class, alist) != cl ||
	    q->in_serv_agg == agg)
		return err; /* non-empty or in service, nothing else to do */

	qfq_activate_agg(q, agg, enqueue);

	return err;
}

/*
 * Schedule aggregate according to its timestamps.
 */
static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
{
	struct qfq_group *grp = agg->grp;
	u64 roundedS;
	int s;

	roundedS = qfq_round_down(agg->S, grp->slot_shift);

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

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

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

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

skip_update:
	qfq_slot_insert(grp, agg, roundedS);
}


/* Update agg ts and schedule agg for service */
static void qfq_activate_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
			     enum update_reason reason)
{
	agg->initial_budget = agg->budget = agg->budgetmax; /* recharge budg. */

	qfq_update_agg_ts(q, agg, reason);
	if (q->in_serv_agg == NULL) { /* no aggr. in service or scheduled */
		q->in_serv_agg = agg; /* start serving this aggregate */
		 /* update V: to be in service, agg must be eligible */
		q->oldV = q->V = agg->S;
	} else if (agg != q->in_serv_agg)
		qfq_schedule_agg(q, agg);
}

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

	roundedS = qfq_round_down(agg->S, grp->slot_shift);
	offset = (roundedS - grp->S) >> grp->slot_shift;

	i = (grp->front + offset) % QFQ_MAX_SLOTS;

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

/*
 * Called to forcibly deschedule an aggregate.  If the aggregate is
 * not in the front bucket, or if the latter has other aggregates in
 * the front bucket, we can simply remove the aggregate with no other
 * side effects.
 * Otherwise we must propagate the event up.
 */
static void qfq_deactivate_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
{
	struct qfq_group *grp = agg->grp;
	unsigned long mask;
	u64 roundedS;
	int s;

	if (agg == q->in_serv_agg) {
		charge_actual_service(agg);
		q->in_serv_agg = qfq_choose_next_agg(q);
		return;
	}

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

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

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

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

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

static unsigned int qfq_drop_from_slot(struct qfq_sched *q,
				       struct hlist_head *slot)
{
	struct qfq_aggregate *agg;
	struct qfq_class *cl;
	unsigned int len;

	hlist_for_each_entry(agg, slot, next) {
		list_for_each_entry(cl, &agg->active, alist) {

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

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

				return len;
			}
		}
	}
	return 0;
}

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

	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
		grp = &q->groups[i];
		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
			len = qfq_drop_from_slot(q, &grp->slots[j]);
			if (len > 0) {
				sch->q.qlen--;
				return len;
			}
		}

	}

	return 0;
}

static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_group *grp;
	int i, j, err;
	u32 max_cl_shift, maxbudg_shift, max_classes;

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

	if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES)
		max_classes = QFQ_MAX_AGG_CLASSES;
	else
		max_classes = qdisc_dev(sch)->tx_queue_len + 1;
	/* max_cl_shift = floor(log_2(max_classes)) */
	max_cl_shift = __fls(max_classes);
	q->max_agg_classes = 1<<max_cl_shift;

	/* maxbudg_shift = log2(max_len * max_classes_per_agg) */
	maxbudg_shift = QFQ_MTU_SHIFT + max_cl_shift;
	q->min_slot_shift = FRAC_BITS + maxbudg_shift - QFQ_MAX_INDEX;

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

	INIT_HLIST_HEAD(&q->nonfull_aggs);

	return 0;
}

static void qfq_reset_qdisc(struct Qdisc *sch)
{
	struct qfq_sched *q = qdisc_priv(sch);
	struct qfq_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->qdisc->q.qlen > 0)
				qfq_deactivate_class(q, cl);

			qdisc_reset(cl->qdisc);
		}
	}
	sch->q.qlen = 0;
}

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

	tcf_destroy_chain(&q->filter_list);

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

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

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

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

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

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