blk-cgroup.c 38.4 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
/*
 * Common Block IO controller cgroup interface
 *
 * Based on ideas and code from CFQ, CFS and BFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
 * 	              Nauman Rafique <nauman@google.com>
 */
#include <linux/ioprio.h>
#include <linux/seq_file.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include "blk-cgroup.h"
#include <linux/genhd.h>

#define MAX_KEY_LEN 100

static DEFINE_SPINLOCK(blkio_list_lock);
static LIST_HEAD(blkio_list);

struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkio_root_cgroup);

static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
						  struct cgroup *);
static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
			      struct task_struct *, bool);
static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
			   struct cgroup *, struct task_struct *, bool);
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);

/* for encoding cft->private value on file */
#define BLKIOFILE_PRIVATE(x, val)	(((x) << 16) | (val))
/* What policy owns the file, proportional or throttle */
#define BLKIOFILE_POLICY(val)		(((val) >> 16) & 0xffff)
#define BLKIOFILE_ATTR(val)		((val) & 0xffff)

struct cgroup_subsys blkio_subsys = {
	.name = "blkio",
	.create = blkiocg_create,
	.can_attach = blkiocg_can_attach,
	.attach = blkiocg_attach,
	.destroy = blkiocg_destroy,
	.populate = blkiocg_populate,
#ifdef CONFIG_BLK_CGROUP
	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
	.subsys_id = blkio_subsys_id,
#endif
	.use_id = 1,
	.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);

static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
					    struct blkio_policy_node *pn)
{
	list_add(&pn->node, &blkcg->policy_list);
}

static inline bool cftype_blkg_same_policy(struct cftype *cft,
			struct blkio_group *blkg)
{
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);

	if (blkg->plid == plid)
		return 1;

	return 0;
}

/* Determines if policy node matches cgroup file being accessed */
static inline bool pn_matches_cftype(struct cftype *cft,
			struct blkio_policy_node *pn)
{
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int fileid = BLKIOFILE_ATTR(cft->private);

	return (plid == pn->plid && fileid == pn->fileid);
}

/* Must be called with blkcg->lock held */
static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
{
	list_del(&pn->node);
}

/* Must be called with blkcg->lock held */
static struct blkio_policy_node *
blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
		enum blkio_policy_id plid, int fileid)
{
	struct blkio_policy_node *pn;

	list_for_each_entry(pn, &blkcg->policy_list, node) {
		if (pn->dev == dev && pn->plid == plid && pn->fileid == fileid)
			return pn;
	}

	return NULL;
}

struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
			    struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);

static inline void
blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
{
	struct blkio_policy_type *blkiop;

	list_for_each_entry(blkiop, &blkio_list, list) {
		/* If this policy does not own the blkg, do not send updates */
		if (blkiop->plid != blkg->plid)
			continue;
		if (blkiop->ops.blkio_update_group_weight_fn)
			blkiop->ops.blkio_update_group_weight_fn(blkg->key,
							blkg, weight);
	}
}

static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
				int fileid)
{
	struct blkio_policy_type *blkiop;

	list_for_each_entry(blkiop, &blkio_list, list) {

		/* If this policy does not own the blkg, do not send updates */
		if (blkiop->plid != blkg->plid)
			continue;

		if (fileid == BLKIO_THROTL_read_bps_device
		    && blkiop->ops.blkio_update_group_read_bps_fn)
			blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
								blkg, bps);

		if (fileid == BLKIO_THROTL_write_bps_device
		    && blkiop->ops.blkio_update_group_write_bps_fn)
			blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
								blkg, bps);
	}
}

static inline void blkio_update_group_iops(struct blkio_group *blkg,
			unsigned int iops, int fileid)
{
	struct blkio_policy_type *blkiop;

	list_for_each_entry(blkiop, &blkio_list, list) {

		/* If this policy does not own the blkg, do not send updates */
		if (blkiop->plid != blkg->plid)
			continue;

		if (fileid == BLKIO_THROTL_read_iops_device
		    && blkiop->ops.blkio_update_group_read_iops_fn)
			blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
								blkg, iops);

		if (fileid == BLKIO_THROTL_write_iops_device
		    && blkiop->ops.blkio_update_group_write_iops_fn)
			blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
								blkg,iops);
	}
}

/*
 * Add to the appropriate stat variable depending on the request type.
 * This should be called with the blkg->stats_lock held.
 */
static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
				bool sync)
{
	if (direction)
		stat[BLKIO_STAT_WRITE] += add;
	else
		stat[BLKIO_STAT_READ] += add;
	if (sync)
		stat[BLKIO_STAT_SYNC] += add;
	else
		stat[BLKIO_STAT_ASYNC] += add;
}

/*
 * Decrements the appropriate stat variable if non-zero depending on the
 * request type. Panics on value being zero.
 * This should be called with the blkg->stats_lock held.
 */
static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)
{
	if (direction) {
		BUG_ON(stat[BLKIO_STAT_WRITE] == 0);
		stat[BLKIO_STAT_WRITE]--;
	} else {
		BUG_ON(stat[BLKIO_STAT_READ] == 0);
		stat[BLKIO_STAT_READ]--;
	}
	if (sync) {
		BUG_ON(stat[BLKIO_STAT_SYNC] == 0);
		stat[BLKIO_STAT_SYNC]--;
	} else {
		BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);
		stat[BLKIO_STAT_ASYNC]--;
	}
}

#ifdef CONFIG_DEBUG_BLK_CGROUP
/* This should be called with the blkg->stats_lock held. */
static void blkio_set_start_group_wait_time(struct blkio_group *blkg,
						struct blkio_group *curr_blkg)
{
	if (blkio_blkg_waiting(&blkg->stats))
		return;
	if (blkg == curr_blkg)
		return;
	blkg->stats.start_group_wait_time = sched_clock();
	blkio_mark_blkg_waiting(&blkg->stats);
}

/* This should be called with the blkg->stats_lock held. */
static void blkio_update_group_wait_time(struct blkio_group_stats *stats)
{
	unsigned long long now;

	if (!blkio_blkg_waiting(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_group_wait_time))
		stats->group_wait_time += now - stats->start_group_wait_time;
	blkio_clear_blkg_waiting(stats);
}

/* This should be called with the blkg->stats_lock held. */
static void blkio_end_empty_time(struct blkio_group_stats *stats)
{
	unsigned long long now;

	if (!blkio_blkg_empty(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_empty_time))
		stats->empty_time += now - stats->start_empty_time;
	blkio_clear_blkg_empty(stats);
}

void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
{
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	BUG_ON(blkio_blkg_idling(&blkg->stats));
	blkg->stats.start_idle_time = sched_clock();
	blkio_mark_blkg_idling(&blkg->stats);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats);

void blkiocg_update_idle_time_stats(struct blkio_group *blkg)
{
	unsigned long flags;
	unsigned long long now;
	struct blkio_group_stats *stats;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	stats = &blkg->stats;
	if (blkio_blkg_idling(stats)) {
		now = sched_clock();
		if (time_after64(now, stats->start_idle_time))
			stats->idle_time += now - stats->start_idle_time;
		blkio_clear_blkg_idling(stats);
	}
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);

void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
{
	unsigned long flags;
	struct blkio_group_stats *stats;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	stats = &blkg->stats;
	stats->avg_queue_size_sum +=
			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +
			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];
	stats->avg_queue_size_samples++;
	blkio_update_group_wait_time(stats);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);

void blkiocg_set_start_empty_time(struct blkio_group *blkg)
{
	unsigned long flags;
	struct blkio_group_stats *stats;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	stats = &blkg->stats;

	if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
		spin_unlock_irqrestore(&blkg->stats_lock, flags);
		return;
	}

	/*
	 * group is already marked empty. This can happen if cfqq got new
	 * request in parent group and moved to this group while being added
	 * to service tree. Just ignore the event and move on.
	 */
	if(blkio_blkg_empty(stats)) {
		spin_unlock_irqrestore(&blkg->stats_lock, flags);
		return;
	}

	stats->start_empty_time = sched_clock();
	blkio_mark_blkg_empty(stats);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);

void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
			unsigned long dequeue)
{
	blkg->stats.dequeue += dequeue;
}
EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
#else
static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
					struct blkio_group *curr_blkg) {}
static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
#endif

void blkiocg_update_io_add_stats(struct blkio_group *blkg,
			struct blkio_group *curr_blkg, bool direction,
			bool sync)
{
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,
			sync);
	blkio_end_empty_time(&blkg->stats);
	blkio_set_start_group_wait_time(blkg, curr_blkg);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);

void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
						bool direction, bool sync)
{
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],
					direction, sync);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);

void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
{
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	blkg->stats.time += time;
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);

void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
				uint64_t bytes, bool direction, bool sync)
{
	struct blkio_group_stats *stats;
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	stats = &blkg->stats;
	stats->sectors += bytes >> 9;
	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
			sync);
	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
			direction, sync);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);

void blkiocg_update_completion_stats(struct blkio_group *blkg,
	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
{
	struct blkio_group_stats *stats;
	unsigned long flags;
	unsigned long long now = sched_clock();

	spin_lock_irqsave(&blkg->stats_lock, flags);
	stats = &blkg->stats;
	if (time_after64(now, io_start_time))
		blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME],
				now - io_start_time, direction, sync);
	if (time_after64(io_start_time, start_time))
		blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME],
				io_start_time - start_time, direction, sync);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);

void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
					bool sync)
{
	unsigned long flags;

	spin_lock_irqsave(&blkg->stats_lock, flags);
	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
			sync);
	spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);

void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
		struct blkio_group *blkg, void *key, dev_t dev,
		enum blkio_policy_id plid)
{
	unsigned long flags;

	spin_lock_irqsave(&blkcg->lock, flags);
	spin_lock_init(&blkg->stats_lock);
	rcu_assign_pointer(blkg->key, key);
	blkg->blkcg_id = css_id(&blkcg->css);
	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
	blkg->plid = plid;
	spin_unlock_irqrestore(&blkcg->lock, flags);
	/* Need to take css reference ? */
	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
	blkg->dev = dev;
}
EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);

static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
	hlist_del_init_rcu(&blkg->blkcg_node);
	blkg->blkcg_id = 0;
}

/*
 * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
 * indicating that blk_group was unhashed by the time we got to it.
 */
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
	struct blkio_cgroup *blkcg;
	unsigned long flags;
	struct cgroup_subsys_state *css;
	int ret = 1;

	rcu_read_lock();
	css = css_lookup(&blkio_subsys, blkg->blkcg_id);
	if (css) {
		blkcg = container_of(css, struct blkio_cgroup, css);
		spin_lock_irqsave(&blkcg->lock, flags);
		if (!hlist_unhashed(&blkg->blkcg_node)) {
			__blkiocg_del_blkio_group(blkg);
			ret = 0;
		}
		spin_unlock_irqrestore(&blkcg->lock, flags);
	}

	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);

/* called under rcu_read_lock(). */
struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
{
	struct blkio_group *blkg;
	struct hlist_node *n;
	void *__key;

	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
		__key = blkg->key;
		if (__key == key)
			return blkg;
	}

	return NULL;
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);

static int
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
	struct blkio_cgroup *blkcg;
	struct blkio_group *blkg;
	struct blkio_group_stats *stats;
	struct hlist_node *n;
	uint64_t queued[BLKIO_STAT_TOTAL];
	int i;
#ifdef CONFIG_DEBUG_BLK_CGROUP
	bool idling, waiting, empty;
	unsigned long long now = sched_clock();
#endif

	blkcg = cgroup_to_blkio_cgroup(cgroup);
	spin_lock_irq(&blkcg->lock);
	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
		spin_lock(&blkg->stats_lock);
		stats = &blkg->stats;
#ifdef CONFIG_DEBUG_BLK_CGROUP
		idling = blkio_blkg_idling(stats);
		waiting = blkio_blkg_waiting(stats);
		empty = blkio_blkg_empty(stats);
#endif
		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
			queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i];
		memset(stats, 0, sizeof(struct blkio_group_stats));
		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
			stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];
#ifdef CONFIG_DEBUG_BLK_CGROUP
		if (idling) {
			blkio_mark_blkg_idling(stats);
			stats->start_idle_time = now;
		}
		if (waiting) {
			blkio_mark_blkg_waiting(stats);
			stats->start_group_wait_time = now;
		}
		if (empty) {
			blkio_mark_blkg_empty(stats);
			stats->start_empty_time = now;
		}
#endif
		spin_unlock(&blkg->stats_lock);
	}
	spin_unlock_irq(&blkcg->lock);
	return 0;
}

static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str,
				int chars_left, bool diskname_only)
{
	snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev));
	chars_left -= strlen(str);
	if (chars_left <= 0) {
		printk(KERN_WARNING
			"Possibly incorrect cgroup stat display format");
		return;
	}
	if (diskname_only)
		return;
	switch (type) {
	case BLKIO_STAT_READ:
		strlcat(str, " Read", chars_left);
		break;
	case BLKIO_STAT_WRITE:
		strlcat(str, " Write", chars_left);
		break;
	case BLKIO_STAT_SYNC:
		strlcat(str, " Sync", chars_left);
		break;
	case BLKIO_STAT_ASYNC:
		strlcat(str, " Async", chars_left);
		break;
	case BLKIO_STAT_TOTAL:
		strlcat(str, " Total", chars_left);
		break;
	default:
		strlcat(str, " Invalid", chars_left);
	}
}

static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
				struct cgroup_map_cb *cb, dev_t dev)
{
	blkio_get_key_name(0, dev, str, chars_left, true);
	cb->fill(cb, str, val);
	return val;
}

/* This should be called with blkg->stats_lock held */
static uint64_t blkio_get_stat(struct blkio_group *blkg,
		struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
{
	uint64_t disk_total;
	char key_str[MAX_KEY_LEN];
	enum stat_sub_type sub_type;

	if (type == BLKIO_STAT_TIME)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.time, cb, dev);
	if (type == BLKIO_STAT_SECTORS)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.sectors, cb, dev);
#ifdef CONFIG_DEBUG_BLK_CGROUP
	if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
		uint64_t sum = blkg->stats.avg_queue_size_sum;
		uint64_t samples = blkg->stats.avg_queue_size_samples;
		if (samples)
			do_div(sum, samples);
		else
			sum = 0;
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);
	}
	if (type == BLKIO_STAT_GROUP_WAIT_TIME)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.group_wait_time, cb, dev);
	if (type == BLKIO_STAT_IDLE_TIME)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.idle_time, cb, dev);
	if (type == BLKIO_STAT_EMPTY_TIME)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.empty_time, cb, dev);
	if (type == BLKIO_STAT_DEQUEUE)
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
					blkg->stats.dequeue, cb, dev);
#endif

	for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
			sub_type++) {
		blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
		cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]);
	}
	disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] +
			blkg->stats.stat_arr[type][BLKIO_STAT_WRITE];
	blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
	cb->fill(cb, key_str, disk_total);
	return disk_total;
}

static int blkio_check_dev_num(dev_t dev)
{
	int part = 0;
	struct gendisk *disk;

	disk = get_gendisk(dev, &part);
	if (!disk || part)
		return -ENODEV;

	return 0;
}

static int blkio_policy_parse_and_set(char *buf,
	struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
{
	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
	int ret;
	unsigned long major, minor, temp;
	int i = 0;
	dev_t dev;
	u64 bps, iops;

	memset(s, 0, sizeof(s));

	while ((p = strsep(&buf, " ")) != NULL) {
		if (!*p)
			continue;

		s[i++] = p;

		/* Prevent from inputing too many things */
		if (i == 3)
			break;
	}

	if (i != 2)
		return -EINVAL;

	p = strsep(&s[0], ":");
	if (p != NULL)
		major_s = p;
	else
		return -EINVAL;

	minor_s = s[0];
	if (!minor_s)
		return -EINVAL;

	ret = strict_strtoul(major_s, 10, &major);
	if (ret)
		return -EINVAL;

	ret = strict_strtoul(minor_s, 10, &minor);
	if (ret)
		return -EINVAL;

	dev = MKDEV(major, minor);

	ret = blkio_check_dev_num(dev);
	if (ret)
		return ret;

	newpn->dev = dev;

	if (s[1] == NULL)
		return -EINVAL;

	switch (plid) {
	case BLKIO_POLICY_PROP:
		ret = strict_strtoul(s[1], 10, &temp);
		if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
			temp > BLKIO_WEIGHT_MAX)
			return -EINVAL;

		newpn->plid = plid;
		newpn->fileid = fileid;
		newpn->val.weight = temp;
		break;
	case BLKIO_POLICY_THROTL:
		switch(fileid) {
		case BLKIO_THROTL_read_bps_device:
		case BLKIO_THROTL_write_bps_device:
			ret = strict_strtoull(s[1], 10, &bps);
			if (ret)
				return -EINVAL;

			newpn->plid = plid;
			newpn->fileid = fileid;
			newpn->val.bps = bps;
			break;
		case BLKIO_THROTL_read_iops_device:
		case BLKIO_THROTL_write_iops_device:
			ret = strict_strtoull(s[1], 10, &iops);
			if (ret)
				return -EINVAL;

			if (iops > THROTL_IOPS_MAX)
				return -EINVAL;

			newpn->plid = plid;
			newpn->fileid = fileid;
			newpn->val.iops = (unsigned int)iops;
			break;
		}
		break;
	default:
		BUG();
	}

	return 0;
}

unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
			      dev_t dev)
{
	struct blkio_policy_node *pn;

	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
				BLKIO_PROP_weight_device);
	if (pn)
		return pn->val.weight;
	else
		return blkcg->weight;
}
EXPORT_SYMBOL_GPL(blkcg_get_weight);

uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
	struct blkio_policy_node *pn;

	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
				BLKIO_THROTL_read_bps_device);
	if (pn)
		return pn->val.bps;
	else
		return -1;
}

uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
	struct blkio_policy_node *pn;
	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
				BLKIO_THROTL_write_bps_device);
	if (pn)
		return pn->val.bps;
	else
		return -1;
}

unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
	struct blkio_policy_node *pn;

	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
				BLKIO_THROTL_read_iops_device);
	if (pn)
		return pn->val.iops;
	else
		return -1;
}

unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
	struct blkio_policy_node *pn;
	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
				BLKIO_THROTL_write_iops_device);
	if (pn)
		return pn->val.iops;
	else
		return -1;
}

/* Checks whether user asked for deleting a policy rule */
static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
{
	switch(pn->plid) {
	case BLKIO_POLICY_PROP:
		if (pn->val.weight == 0)
			return 1;
		break;
	case BLKIO_POLICY_THROTL:
		switch(pn->fileid) {
		case BLKIO_THROTL_read_bps_device:
		case BLKIO_THROTL_write_bps_device:
			if (pn->val.bps == 0)
				return 1;
			break;
		case BLKIO_THROTL_read_iops_device:
		case BLKIO_THROTL_write_iops_device:
			if (pn->val.iops == 0)
				return 1;
		}
		break;
	default:
		BUG();
	}

	return 0;
}

static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
					struct blkio_policy_node *newpn)
{
	switch(oldpn->plid) {
	case BLKIO_POLICY_PROP:
		oldpn->val.weight = newpn->val.weight;
		break;
	case BLKIO_POLICY_THROTL:
		switch(newpn->fileid) {
		case BLKIO_THROTL_read_bps_device:
		case BLKIO_THROTL_write_bps_device:
			oldpn->val.bps = newpn->val.bps;
			break;
		case BLKIO_THROTL_read_iops_device:
		case BLKIO_THROTL_write_iops_device:
			oldpn->val.iops = newpn->val.iops;
		}
		break;
	default:
		BUG();
	}
}

/*
 * Some rules/values in blkg have changed. Propogate those to respective
 * policies.
 */
static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
		struct blkio_group *blkg, struct blkio_policy_node *pn)
{
	unsigned int weight, iops;
	u64 bps;

	switch(pn->plid) {
	case BLKIO_POLICY_PROP:
		weight = pn->val.weight ? pn->val.weight :
				blkcg->weight;
		blkio_update_group_weight(blkg, weight);
		break;
	case BLKIO_POLICY_THROTL:
		switch(pn->fileid) {
		case BLKIO_THROTL_read_bps_device:
		case BLKIO_THROTL_write_bps_device:
			bps = pn->val.bps ? pn->val.bps : (-1);
			blkio_update_group_bps(blkg, bps, pn->fileid);
			break;
		case BLKIO_THROTL_read_iops_device:
		case BLKIO_THROTL_write_iops_device:
			iops = pn->val.iops ? pn->val.iops : (-1);
			blkio_update_group_iops(blkg, iops, pn->fileid);
			break;
		}
		break;
	default:
		BUG();
	}
}

/*
 * A policy node rule has been updated. Propogate this update to all the
 * block groups which might be affected by this update.
 */
static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
				struct blkio_policy_node *pn)
{
	struct blkio_group *blkg;
	struct hlist_node *n;

	spin_lock(&blkio_list_lock);
	spin_lock_irq(&blkcg->lock);

	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
		if (pn->dev != blkg->dev || pn->plid != blkg->plid)
			continue;
		blkio_update_blkg_policy(blkcg, blkg, pn);
	}

	spin_unlock_irq(&blkcg->lock);
	spin_unlock(&blkio_list_lock);
}

static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
 				       const char *buffer)
{
	int ret = 0;
	char *buf;
	struct blkio_policy_node *newpn, *pn;
	struct blkio_cgroup *blkcg;
	int keep_newpn = 0;
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int fileid = BLKIOFILE_ATTR(cft->private);

	buf = kstrdup(buffer, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
	if (!newpn) {
		ret = -ENOMEM;
		goto free_buf;
	}

	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid);
	if (ret)
		goto free_newpn;

	blkcg = cgroup_to_blkio_cgroup(cgrp);

	spin_lock_irq(&blkcg->lock);

	pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);
	if (!pn) {
		if (!blkio_delete_rule_command(newpn)) {
			blkio_policy_insert_node(blkcg, newpn);
			keep_newpn = 1;
		}
		spin_unlock_irq(&blkcg->lock);
		goto update_io_group;
	}

	if (blkio_delete_rule_command(newpn)) {
		blkio_policy_delete_node(pn);
		spin_unlock_irq(&blkcg->lock);
		goto update_io_group;
	}
	spin_unlock_irq(&blkcg->lock);

	blkio_update_policy_rule(pn, newpn);

update_io_group:
	blkio_update_policy_node_blkg(blkcg, newpn);

free_newpn:
	if (!keep_newpn)
		kfree(newpn);
free_buf:
	kfree(buf);
	return ret;
}

static void
blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
{
	switch(pn->plid) {
		case BLKIO_POLICY_PROP:
			if (pn->fileid == BLKIO_PROP_weight_device)
				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
					MINOR(pn->dev), pn->val.weight);
			break;
		case BLKIO_POLICY_THROTL:
			switch(pn->fileid) {
			case BLKIO_THROTL_read_bps_device:
			case BLKIO_THROTL_write_bps_device:
				seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
					MINOR(pn->dev), pn->val.bps);
				break;
			case BLKIO_THROTL_read_iops_device:
			case BLKIO_THROTL_write_iops_device:
				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
					MINOR(pn->dev), pn->val.iops);
				break;
			}
			break;
		default:
			BUG();
	}
}

/* cgroup files which read their data from policy nodes end up here */
static void blkio_read_policy_node_files(struct cftype *cft,
			struct blkio_cgroup *blkcg, struct seq_file *m)
{
	struct blkio_policy_node *pn;

	if (!list_empty(&blkcg->policy_list)) {
		spin_lock_irq(&blkcg->lock);
		list_for_each_entry(pn, &blkcg->policy_list, node) {
			if (!pn_matches_cftype(cft, pn))
				continue;
			blkio_print_policy_node(m, pn);
		}
		spin_unlock_irq(&blkcg->lock);
	}
}

static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
				struct seq_file *m)
{
	struct blkio_cgroup *blkcg;
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int name = BLKIOFILE_ATTR(cft->private);

	blkcg = cgroup_to_blkio_cgroup(cgrp);

	switch(plid) {
	case BLKIO_POLICY_PROP:
		switch(name) {
		case BLKIO_PROP_weight_device:
			blkio_read_policy_node_files(cft, blkcg, m);
			return 0;
		default:
			BUG();
		}
		break;
	case BLKIO_POLICY_THROTL:
		switch(name){
		case BLKIO_THROTL_read_bps_device:
		case BLKIO_THROTL_write_bps_device:
		case BLKIO_THROTL_read_iops_device:
		case BLKIO_THROTL_write_iops_device:
			blkio_read_policy_node_files(cft, blkcg, m);
			return 0;
		default:
			BUG();
		}
		break;
	default:
		BUG();
	}

	return 0;
}

static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
		struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
		bool show_total)
{
	struct blkio_group *blkg;
	struct hlist_node *n;
	uint64_t cgroup_total = 0;

	rcu_read_lock();
	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
		if (blkg->dev) {
			if (!cftype_blkg_same_policy(cft, blkg))
				continue;
			spin_lock_irq(&blkg->stats_lock);
			cgroup_total += blkio_get_stat(blkg, cb, blkg->dev,
						type);
			spin_unlock_irq(&blkg->stats_lock);
		}
	}
	if (show_total)
		cb->fill(cb, "Total", cgroup_total);
	rcu_read_unlock();
	return 0;
}

/* All map kind of cgroup file get serviced by this function */
static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
				struct cgroup_map_cb *cb)
{
	struct blkio_cgroup *blkcg;
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int name = BLKIOFILE_ATTR(cft->private);

	blkcg = cgroup_to_blkio_cgroup(cgrp);

	switch(plid) {
	case BLKIO_POLICY_PROP:
		switch(name) {
		case BLKIO_PROP_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_TIME, 0);
		case BLKIO_PROP_sectors:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SECTORS, 0);
		case BLKIO_PROP_io_service_bytes:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SERVICE_BYTES, 1);
		case BLKIO_PROP_io_serviced:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SERVICED, 1);
		case BLKIO_PROP_io_service_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SERVICE_TIME, 1);
		case BLKIO_PROP_io_wait_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_WAIT_TIME, 1);
		case BLKIO_PROP_io_merged:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_MERGED, 1);
		case BLKIO_PROP_io_queued:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_QUEUED, 1);
#ifdef CONFIG_DEBUG_BLK_CGROUP
		case BLKIO_PROP_dequeue:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_DEQUEUE, 0);
		case BLKIO_PROP_avg_queue_size:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_AVG_QUEUE_SIZE, 0);
		case BLKIO_PROP_group_wait_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_GROUP_WAIT_TIME, 0);
		case BLKIO_PROP_idle_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_IDLE_TIME, 0);
		case BLKIO_PROP_empty_time:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_EMPTY_TIME, 0);
#endif
		default:
			BUG();
		}
		break;
	case BLKIO_POLICY_THROTL:
		switch(name){
		case BLKIO_THROTL_io_service_bytes:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SERVICE_BYTES, 1);
		case BLKIO_THROTL_io_serviced:
			return blkio_read_blkg_stats(blkcg, cft, cb,
						BLKIO_STAT_SERVICED, 1);
		default:
			BUG();
		}
		break;
	default:
		BUG();
	}

	return 0;
}

static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
{
	struct blkio_group *blkg;
	struct hlist_node *n;
	struct blkio_policy_node *pn;

	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
		return -EINVAL;

	spin_lock(&blkio_list_lock);
	spin_lock_irq(&blkcg->lock);
	blkcg->weight = (unsigned int)val;

	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
		pn = blkio_policy_search_node(blkcg, blkg->dev,
				BLKIO_POLICY_PROP, BLKIO_PROP_weight_device);
		if (pn)
			continue;

		blkio_update_group_weight(blkg, blkcg->weight);
	}
	spin_unlock_irq(&blkcg->lock);
	spin_unlock(&blkio_list_lock);
	return 0;
}

static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
	struct blkio_cgroup *blkcg;
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int name = BLKIOFILE_ATTR(cft->private);

	blkcg = cgroup_to_blkio_cgroup(cgrp);

	switch(plid) {
	case BLKIO_POLICY_PROP:
		switch(name) {
		case BLKIO_PROP_weight:
			return (u64)blkcg->weight;
		}
		break;
	default:
		BUG();
	}
	return 0;
}

static int
blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
{
	struct blkio_cgroup *blkcg;
	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
	int name = BLKIOFILE_ATTR(cft->private);

	blkcg = cgroup_to_blkio_cgroup(cgrp);

	switch(plid) {
	case BLKIO_POLICY_PROP:
		switch(name) {
		case BLKIO_PROP_weight:
			return blkio_weight_write(blkcg, val);
		}
		break;
	default:
		BUG();
	}

	return 0;
}

struct cftype blkio_files[] = {
	{
		.name = "weight_device",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_weight_device),
		.read_seq_string = blkiocg_file_read,
		.write_string = blkiocg_file_write,
		.max_write_len = 256,
	},
	{
		.name = "weight",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_weight),
		.read_u64 = blkiocg_file_read_u64,
		.write_u64 = blkiocg_file_write_u64,
	},
	{
		.name = "time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "sectors",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_sectors),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_service_bytes",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_service_bytes),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_serviced",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_serviced),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_service_time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_service_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_wait_time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_wait_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_merged",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_merged),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "io_queued",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_io_queued),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "reset_stats",
		.write_u64 = blkiocg_reset_stats,
	},
#ifdef CONFIG_BLK_DEV_THROTTLING
	{
		.name = "throttle.read_bps_device",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_read_bps_device),
		.read_seq_string = blkiocg_file_read,
		.write_string = blkiocg_file_write,
		.max_write_len = 256,
	},

	{
		.name = "throttle.write_bps_device",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_write_bps_device),
		.read_seq_string = blkiocg_file_read,
		.write_string = blkiocg_file_write,
		.max_write_len = 256,
	},

	{
		.name = "throttle.read_iops_device",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_read_iops_device),
		.read_seq_string = blkiocg_file_read,
		.write_string = blkiocg_file_write,
		.max_write_len = 256,
	},

	{
		.name = "throttle.write_iops_device",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_write_iops_device),
		.read_seq_string = blkiocg_file_read,
		.write_string = blkiocg_file_write,
		.max_write_len = 256,
	},
	{
		.name = "throttle.io_service_bytes",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_io_service_bytes),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "throttle.io_serviced",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
				BLKIO_THROTL_io_serviced),
		.read_map = blkiocg_file_read_map,
	},
#endif /* CONFIG_BLK_DEV_THROTTLING */

#ifdef CONFIG_DEBUG_BLK_CGROUP
	{
		.name = "avg_queue_size",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_avg_queue_size),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "group_wait_time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_group_wait_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "idle_time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_idle_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "empty_time",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_empty_time),
		.read_map = blkiocg_file_read_map,
	},
	{
		.name = "dequeue",
		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
				BLKIO_PROP_dequeue),
		.read_map = blkiocg_file_read_map,
	},
#endif
};

static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	return cgroup_add_files(cgroup, subsys, blkio_files,
				ARRAY_SIZE(blkio_files));
}

static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
	unsigned long flags;
	struct blkio_group *blkg;
	void *key;
	struct blkio_policy_type *blkiop;
	struct blkio_policy_node *pn, *pntmp;

	rcu_read_lock();
	do {
		spin_lock_irqsave(&blkcg->lock, flags);

		if (hlist_empty(&blkcg->blkg_list)) {
			spin_unlock_irqrestore(&blkcg->lock, flags);
			break;
		}

		blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
					blkcg_node);
		key = rcu_dereference(blkg->key);
		__blkiocg_del_blkio_group(blkg);

		spin_unlock_irqrestore(&blkcg->lock, flags);

		/*
		 * This blkio_group is being unlinked as associated cgroup is
		 * going away. Let all the IO controlling policies know about
		 * this event.
		 */
		spin_lock(&blkio_list_lock);
		list_for_each_entry(blkiop, &blkio_list, list) {
			if (blkiop->plid != blkg->plid)
				continue;
			blkiop->ops.blkio_unlink_group_fn(key, blkg);
		}
		spin_unlock(&blkio_list_lock);
	} while (1);

	list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) {
		blkio_policy_delete_node(pn);
		kfree(pn);
	}

	free_css_id(&blkio_subsys, &blkcg->css);
	rcu_read_unlock();
	if (blkcg != &blkio_root_cgroup)
		kfree(blkcg);
}

static struct cgroup_subsys_state *
blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg;
	struct cgroup *parent = cgroup->parent;

	if (!parent) {
		blkcg = &blkio_root_cgroup;
		goto done;
	}

	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
	if (!blkcg)
		return ERR_PTR(-ENOMEM);

	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
done:
	spin_lock_init(&blkcg->lock);
	INIT_HLIST_HEAD(&blkcg->blkg_list);

	INIT_LIST_HEAD(&blkcg->policy_list);
	return &blkcg->css;
}

/*
 * We cannot support shared io contexts, as we have no mean to support
 * two tasks with the same ioc in two different groups without major rework
 * of the main cic data structures.  For now we allow a task to change
 * its cgroup only if it's the only owner of its ioc.
 */
static int blkiocg_can_attach(struct cgroup_subsys *subsys,
				struct cgroup *cgroup, struct task_struct *tsk,
				bool threadgroup)
{
	struct io_context *ioc;
	int ret = 0;

	/* task_lock() is needed to avoid races with exit_io_context() */
	task_lock(tsk);
	ioc = tsk->io_context;
	if (ioc && atomic_read(&ioc->nr_tasks) > 1)
		ret = -EINVAL;
	task_unlock(tsk);

	return ret;
}

static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
				struct cgroup *prev, struct task_struct *tsk,
				bool threadgroup)
{
	struct io_context *ioc;

	task_lock(tsk);
	ioc = tsk->io_context;
	if (ioc)
		ioc->cgroup_changed = 1;
	task_unlock(tsk);
}

void blkio_policy_register(struct blkio_policy_type *blkiop)
{
	spin_lock(&blkio_list_lock);
	list_add_tail(&blkiop->list, &blkio_list);
	spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_register);

void blkio_policy_unregister(struct blkio_policy_type *blkiop)
{
	spin_lock(&blkio_list_lock);
	list_del_init(&blkiop->list);
	spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_unregister);

static int __init init_cgroup_blkio(void)
{
	return cgroup_load_subsys(&blkio_subsys);
}

static void __exit exit_cgroup_blkio(void)
{
	cgroup_unload_subsys(&blkio_subsys);
}

module_init(init_cgroup_blkio);
module_exit(exit_cgroup_blkio);
MODULE_LICENSE("GPL");