bitmap.c 39.3 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
/*
 * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
 */
/* Reiserfs block (de)allocator, bitmap-based. */

#include <linux/time.h>
#include "reiserfs.h"
#include <linux/errno.h>
#include <linux/buffer_head.h>
#include <linux/kernel.h>
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>

#define PREALLOCATION_SIZE 9

/* different reiserfs block allocator options */

#define SB_ALLOC_OPTS(s) (REISERFS_SB(s)->s_alloc_options.bits)

#define  _ALLOC_concentrating_formatted_nodes 0
#define  _ALLOC_displacing_large_files 1
#define  _ALLOC_displacing_new_packing_localities 2
#define  _ALLOC_old_hashed_relocation 3
#define  _ALLOC_new_hashed_relocation 4
#define  _ALLOC_skip_busy 5
#define  _ALLOC_displace_based_on_dirid 6
#define  _ALLOC_hashed_formatted_nodes 7
#define  _ALLOC_old_way 8
#define  _ALLOC_hundredth_slices 9
#define  _ALLOC_dirid_groups 10
#define  _ALLOC_oid_groups 11
#define  _ALLOC_packing_groups 12

#define  concentrating_formatted_nodes(s)	test_bit(_ALLOC_concentrating_formatted_nodes, &SB_ALLOC_OPTS(s))
#define  displacing_large_files(s)		test_bit(_ALLOC_displacing_large_files, &SB_ALLOC_OPTS(s))
#define  displacing_new_packing_localities(s)	test_bit(_ALLOC_displacing_new_packing_localities, &SB_ALLOC_OPTS(s))

#define SET_OPTION(optname) \
   do { \
	reiserfs_info(s, "block allocator option \"%s\" is set", #optname); \
	set_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)); \
    } while(0)
#define TEST_OPTION(optname, s) \
    test_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s))

static inline void get_bit_address(struct super_block *s,
				   b_blocknr_t block,
				   unsigned int *bmap_nr,
				   unsigned int *offset)
{
	/*
	 * It is in the bitmap block number equal to the block
	 * number divided by the number of bits in a block.
	 */
	*bmap_nr = block >> (s->s_blocksize_bits + 3);
	/* Within that bitmap block it is located at bit offset *offset. */
	*offset = block & ((s->s_blocksize << 3) - 1);
}

int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value)
{
	unsigned int bmap, offset;
	unsigned int bmap_count = reiserfs_bmap_count(s);

	if (block == 0 || block >= SB_BLOCK_COUNT(s)) {
		reiserfs_error(s, "vs-4010",
			       "block number is out of range %lu (%u)",
			       block, SB_BLOCK_COUNT(s));
		return 0;
	}

	get_bit_address(s, block, &bmap, &offset);

	/*
	 * Old format filesystem? Unlikely, but the bitmaps are all
	 * up front so we need to account for it.
	 */
	if (unlikely(test_bit(REISERFS_OLD_FORMAT,
			      &REISERFS_SB(s)->s_properties))) {
		b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1;
		if (block >= bmap1 &&
		    block <= bmap1 + bmap_count) {
			reiserfs_error(s, "vs-4019", "bitmap block %lu(%u) "
				       "can't be freed or reused",
				       block, bmap_count);
			return 0;
		}
	} else {
		if (offset == 0) {
			reiserfs_error(s, "vs-4020", "bitmap block %lu(%u) "
				       "can't be freed or reused",
				       block, bmap_count);
			return 0;
		}
	}

	if (bmap >= bmap_count) {
		reiserfs_error(s, "vs-4030", "bitmap for requested block "
			       "is out of range: block=%lu, bitmap_nr=%u",
			       block, bmap);
		return 0;
	}

	if (bit_value == 0 && block == SB_ROOT_BLOCK(s)) {
		reiserfs_error(s, "vs-4050", "this is root block (%u), "
			       "it must be busy", SB_ROOT_BLOCK(s));
		return 0;
	}

	return 1;
}

/*
 * Searches in journal structures for a given block number (bmap, off).
 * If block is found in reiserfs journal it suggests next free block
 * candidate to test.
 */
static inline int is_block_in_journal(struct super_block *s, unsigned int bmap,
				      int off, int *next)
{
	b_blocknr_t tmp;

	if (reiserfs_in_journal(s, bmap, off, 1, &tmp)) {
		if (tmp) {	/* hint supplied */
			*next = tmp;
			PROC_INFO_INC(s, scan_bitmap.in_journal_hint);
		} else {
			(*next) = off + 1;  /* inc offset to avoid looping. */
			PROC_INFO_INC(s, scan_bitmap.in_journal_nohint);
		}
		PROC_INFO_INC(s, scan_bitmap.retry);
		return 1;
	}
	return 0;
}

/*
 * Searches for a window of zero bits with given minimum and maximum
 * lengths in one bitmap block
 */
static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
			     unsigned int bmap_n, int *beg, int boundary,
			     int min, int max, int unfm)
{
	struct super_block *s = th->t_super;
	struct reiserfs_bitmap_info *bi = &SB_AP_BITMAP(s)[bmap_n];
	struct buffer_head *bh;
	int end, next;
	int org = *beg;

	BUG_ON(!th->t_trans_id);
	RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of "
	       "range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1);
	PROC_INFO_INC(s, scan_bitmap.bmap);

	if (!bi) {
		reiserfs_error(s, "jdm-4055", "NULL bitmap info pointer "
			       "for bitmap %d", bmap_n);
		return 0;
	}

	bh = reiserfs_read_bitmap_block(s, bmap_n);
	if (bh == NULL)
		return 0;

	while (1) {
cont:
		if (bi->free_count < min) {
			brelse(bh);
			return 0;	/* No free blocks in this bitmap */
		}

		/* search for a first zero bit -- beginning of a window */
		*beg = reiserfs_find_next_zero_le_bit
		    ((unsigned long *)(bh->b_data), boundary, *beg);

		/*
		 * search for a zero bit fails or the rest of bitmap block
		 * cannot contain a zero window of minimum size
		 */
		if (*beg + min > boundary) {
			brelse(bh);
			return 0;
		}

		if (unfm && is_block_in_journal(s, bmap_n, *beg, beg))
			continue;
		/* first zero bit found; we check next bits */
		for (end = *beg + 1;; end++) {
			if (end >= *beg + max || end >= boundary
			    || reiserfs_test_le_bit(end, bh->b_data)) {
				next = end;
				break;
			}

			/*
			 * finding the other end of zero bit window requires
			 * looking into journal structures (in case of
			 * searching for free blocks for unformatted nodes)
			 */
			if (unfm && is_block_in_journal(s, bmap_n, end, &next))
				break;
		}

		/*
		 * now (*beg) points to beginning of zero bits window,
		 * (end) points to one bit after the window end
		 */

		/* found window of proper size */
		if (end - *beg >= min) {
			int i;
			reiserfs_prepare_for_journal(s, bh, 1);
			/*
			 * try to set all blocks used checking are
			 * they still free
			 */
			for (i = *beg; i < end; i++) {
				/* Don't check in journal again. */
				if (reiserfs_test_and_set_le_bit
				    (i, bh->b_data)) {
					/*
					 * bit was set by another process while
					 * we slept in prepare_for_journal()
					 */
					PROC_INFO_INC(s, scan_bitmap.stolen);

					/*
					 * we can continue with smaller set
					 * of allocated blocks, if length of
					 * this set is more or equal to `min'
					 */
					if (i >= *beg + min) {
						end = i;
						break;
					}

					/*
					 * otherwise we clear all bit
					 * were set ...
					 */
					while (--i >= *beg)
						reiserfs_clear_le_bit
						    (i, bh->b_data);
					reiserfs_restore_prepared_buffer(s, bh);
					*beg = org;

					/*
					 * Search again in current block
					 * from beginning
					 */
					goto cont;
				}
			}
			bi->free_count -= (end - *beg);
			journal_mark_dirty(th, bh);
			brelse(bh);

			/* free block count calculation */
			reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s),
						     1);
			PUT_SB_FREE_BLOCKS(s, SB_FREE_BLOCKS(s) - (end - *beg));
			journal_mark_dirty(th, SB_BUFFER_WITH_SB(s));

			return end - (*beg);
		} else {
			*beg = next;
		}
	}
}

static int bmap_hash_id(struct super_block *s, u32 id)
{
	char *hash_in = NULL;
	unsigned long hash;
	unsigned bm;

	if (id <= 2) {
		bm = 1;
	} else {
		hash_in = (char *)(&id);
		hash = keyed_hash(hash_in, 4);
		bm = hash % reiserfs_bmap_count(s);
		if (!bm)
			bm = 1;
	}
	/* this can only be true when SB_BMAP_NR = 1 */
	if (bm >= reiserfs_bmap_count(s))
		bm = 0;
	return bm;
}

/*
 * hashes the id and then returns > 0 if the block group for the
 * corresponding hash is full
 */
static inline int block_group_used(struct super_block *s, u32 id)
{
	int bm = bmap_hash_id(s, id);
	struct reiserfs_bitmap_info *info = &SB_AP_BITMAP(s)[bm];

	/*
	 * If we don't have cached information on this bitmap block, we're
	 * going to have to load it later anyway. Loading it here allows us
	 * to make a better decision. This favors long-term performance gain
	 * with a better on-disk layout vs. a short term gain of skipping the
	 * read and potentially having a bad placement.
	 */
	if (info->free_count == UINT_MAX) {
		struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm);
		brelse(bh);
	}

	if (info->free_count > ((s->s_blocksize << 3) * 60 / 100)) {
		return 0;
	}
	return 1;
}

/*
 * the packing is returned in disk byte order
 */
__le32 reiserfs_choose_packing(struct inode * dir)
{
	__le32 packing;
	if (TEST_OPTION(packing_groups, dir->i_sb)) {
		u32 parent_dir = le32_to_cpu(INODE_PKEY(dir)->k_dir_id);
		/*
		 * some versions of reiserfsck expect packing locality 1 to be
		 * special
		 */
		if (parent_dir == 1 || block_group_used(dir->i_sb, parent_dir))
			packing = INODE_PKEY(dir)->k_objectid;
		else
			packing = INODE_PKEY(dir)->k_dir_id;
	} else
		packing = INODE_PKEY(dir)->k_objectid;
	return packing;
}

/*
 * Tries to find contiguous zero bit window (given size) in given region of
 * bitmap and place new blocks there. Returns number of allocated blocks.
 */
static int scan_bitmap(struct reiserfs_transaction_handle *th,
		       b_blocknr_t * start, b_blocknr_t finish,
		       int min, int max, int unfm, sector_t file_block)
{
	int nr_allocated = 0;
	struct super_block *s = th->t_super;
	unsigned int bm, off;
	unsigned int end_bm, end_off;
	unsigned int off_max = s->s_blocksize << 3;

	BUG_ON(!th->t_trans_id);
	PROC_INFO_INC(s, scan_bitmap.call);

	/* No point in looking for more free blocks */
	if (SB_FREE_BLOCKS(s) <= 0)
		return 0;

	get_bit_address(s, *start, &bm, &off);
	get_bit_address(s, finish, &end_bm, &end_off);
	if (bm > reiserfs_bmap_count(s))
		return 0;
	if (end_bm > reiserfs_bmap_count(s))
		end_bm = reiserfs_bmap_count(s);

	/*
	 * When the bitmap is more than 10% free, anyone can allocate.
	 * When it's less than 10% free, only files that already use the
	 * bitmap are allowed. Once we pass 80% full, this restriction
	 * is lifted.
	 *
	 * We do this so that files that grow later still have space close to
	 * their original allocation. This improves locality, and presumably
	 * performance as a result.
	 *
	 * This is only an allocation policy and does not make up for getting a
	 * bad hint. Decent hinting must be implemented for this to work well.
	 */
	if (TEST_OPTION(skip_busy, s)
	    && SB_FREE_BLOCKS(s) > SB_BLOCK_COUNT(s) / 20) {
		for (; bm < end_bm; bm++, off = 0) {
			if ((off && (!unfm || (file_block != 0)))
			    || SB_AP_BITMAP(s)[bm].free_count >
			    (s->s_blocksize << 3) / 10)
				nr_allocated =
				    scan_bitmap_block(th, bm, &off, off_max,
						      min, max, unfm);
			if (nr_allocated)
				goto ret;
		}
		/* we know from above that start is a reasonable number */
		get_bit_address(s, *start, &bm, &off);
	}

	for (; bm < end_bm; bm++, off = 0) {
		nr_allocated =
		    scan_bitmap_block(th, bm, &off, off_max, min, max, unfm);
		if (nr_allocated)
			goto ret;
	}

	nr_allocated =
	    scan_bitmap_block(th, bm, &off, end_off + 1, min, max, unfm);

ret:
	*start = bm * off_max + off;
	return nr_allocated;

}

static void _reiserfs_free_block(struct reiserfs_transaction_handle *th,
				 struct inode *inode, b_blocknr_t block,
				 int for_unformatted)
{
	struct super_block *s = th->t_super;
	struct reiserfs_super_block *rs;
	struct buffer_head *sbh, *bmbh;
	struct reiserfs_bitmap_info *apbi;
	unsigned int nr, offset;

	BUG_ON(!th->t_trans_id);
	PROC_INFO_INC(s, free_block);
	rs = SB_DISK_SUPER_BLOCK(s);
	sbh = SB_BUFFER_WITH_SB(s);
	apbi = SB_AP_BITMAP(s);

	get_bit_address(s, block, &nr, &offset);

	if (nr >= reiserfs_bmap_count(s)) {
		reiserfs_error(s, "vs-4075", "block %lu is out of range",
			       block);
		return;
	}

	bmbh = reiserfs_read_bitmap_block(s, nr);
	if (!bmbh)
		return;

	reiserfs_prepare_for_journal(s, bmbh, 1);

	/* clear bit for the given block in bit map */
	if (!reiserfs_test_and_clear_le_bit(offset, bmbh->b_data)) {
		reiserfs_error(s, "vs-4080",
			       "block %lu: bit already cleared", block);
	}
	apbi[nr].free_count++;
	journal_mark_dirty(th, bmbh);
	brelse(bmbh);

	reiserfs_prepare_for_journal(s, sbh, 1);
	/* update super block */
	set_sb_free_blocks(rs, sb_free_blocks(rs) + 1);

	journal_mark_dirty(th, sbh);
	if (for_unformatted) {
		int depth = reiserfs_write_unlock_nested(s);
		dquot_free_block_nodirty(inode, 1);
		reiserfs_write_lock_nested(s, depth);
	}
}

void reiserfs_free_block(struct reiserfs_transaction_handle *th,
			 struct inode *inode, b_blocknr_t block,
			 int for_unformatted)
{
	struct super_block *s = th->t_super;

	BUG_ON(!th->t_trans_id);
	RFALSE(!s, "vs-4061: trying to free block on nonexistent device");
	if (!is_reusable(s, block, 1))
		return;

	if (block > sb_block_count(REISERFS_SB(s)->s_rs)) {
		reiserfs_error(th->t_super, "bitmap-4072",
			       "Trying to free block outside file system "
			       "boundaries (%lu > %lu)",
			       block, sb_block_count(REISERFS_SB(s)->s_rs));
		return;
	}
	/* mark it before we clear it, just in case */
	journal_mark_freed(th, s, block);
	_reiserfs_free_block(th, inode, block, for_unformatted);
}

/* preallocated blocks don't need to be run through journal_mark_freed */
static void reiserfs_free_prealloc_block(struct reiserfs_transaction_handle *th,
					 struct inode *inode, b_blocknr_t block)
{
	BUG_ON(!th->t_trans_id);
	RFALSE(!th->t_super,
	       "vs-4060: trying to free block on nonexistent device");
	if (!is_reusable(th->t_super, block, 1))
		return;
	_reiserfs_free_block(th, inode, block, 1);
}

static void __discard_prealloc(struct reiserfs_transaction_handle *th,
			       struct reiserfs_inode_info *ei)
{
	unsigned long save = ei->i_prealloc_block;
	int dirty = 0;
	struct inode *inode = &ei->vfs_inode;

	BUG_ON(!th->t_trans_id);
#ifdef CONFIG_REISERFS_CHECK
	if (ei->i_prealloc_count < 0)
		reiserfs_error(th->t_super, "zam-4001",
			       "inode has negative prealloc blocks count.");
#endif
	while (ei->i_prealloc_count > 0) {
		reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block);
		ei->i_prealloc_block++;
		ei->i_prealloc_count--;
		dirty = 1;
	}
	if (dirty)
		reiserfs_update_sd(th, inode);
	ei->i_prealloc_block = save;
	list_del_init(&ei->i_prealloc_list);
}

/* FIXME: It should be inline function */
void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th,
			       struct inode *inode)
{
	struct reiserfs_inode_info *ei = REISERFS_I(inode);

	BUG_ON(!th->t_trans_id);
	if (ei->i_prealloc_count)
		__discard_prealloc(th, ei);
}

void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th)
{
	struct list_head *plist = &SB_JOURNAL(th->t_super)->j_prealloc_list;

	BUG_ON(!th->t_trans_id);
	while (!list_empty(plist)) {
		struct reiserfs_inode_info *ei;
		ei = list_entry(plist->next, struct reiserfs_inode_info,
				i_prealloc_list);
#ifdef CONFIG_REISERFS_CHECK
		if (!ei->i_prealloc_count) {
			reiserfs_error(th->t_super, "zam-4001",
				       "inode is in prealloc list but has "
				       "no preallocated blocks.");
		}
#endif
		__discard_prealloc(th, ei);
	}
}

void reiserfs_init_alloc_options(struct super_block *s)
{
	set_bit(_ALLOC_skip_busy, &SB_ALLOC_OPTS(s));
	set_bit(_ALLOC_dirid_groups, &SB_ALLOC_OPTS(s));
	set_bit(_ALLOC_packing_groups, &SB_ALLOC_OPTS(s));
}

/* block allocator related options are parsed here */
int reiserfs_parse_alloc_options(struct super_block *s, char *options)
{
	char *this_char, *value;

	/* clear default settings */
	REISERFS_SB(s)->s_alloc_options.bits = 0;

	while ((this_char = strsep(&options, ":")) != NULL) {
		if ((value = strchr(this_char, '=')) != NULL)
			*value++ = 0;

		if (!strcmp(this_char, "concentrating_formatted_nodes")) {
			int temp;
			SET_OPTION(concentrating_formatted_nodes);
			temp = (value
				&& *value) ? simple_strtoul(value, &value,
							    0) : 10;
			if (temp <= 0 || temp > 100) {
				REISERFS_SB(s)->s_alloc_options.border = 10;
			} else {
				REISERFS_SB(s)->s_alloc_options.border =
				    100 / temp;
			}
			continue;
		}
		if (!strcmp(this_char, "displacing_large_files")) {
			SET_OPTION(displacing_large_files);
			REISERFS_SB(s)->s_alloc_options.large_file_size =
			    (value
			     && *value) ? simple_strtoul(value, &value, 0) : 16;
			continue;
		}
		if (!strcmp(this_char, "displacing_new_packing_localities")) {
			SET_OPTION(displacing_new_packing_localities);
			continue;
		}

		if (!strcmp(this_char, "old_hashed_relocation")) {
			SET_OPTION(old_hashed_relocation);
			continue;
		}

		if (!strcmp(this_char, "new_hashed_relocation")) {
			SET_OPTION(new_hashed_relocation);
			continue;
		}

		if (!strcmp(this_char, "dirid_groups")) {
			SET_OPTION(dirid_groups);
			continue;
		}
		if (!strcmp(this_char, "oid_groups")) {
			SET_OPTION(oid_groups);
			continue;
		}
		if (!strcmp(this_char, "packing_groups")) {
			SET_OPTION(packing_groups);
			continue;
		}
		if (!strcmp(this_char, "hashed_formatted_nodes")) {
			SET_OPTION(hashed_formatted_nodes);
			continue;
		}

		if (!strcmp(this_char, "skip_busy")) {
			SET_OPTION(skip_busy);
			continue;
		}

		if (!strcmp(this_char, "hundredth_slices")) {
			SET_OPTION(hundredth_slices);
			continue;
		}

		if (!strcmp(this_char, "old_way")) {
			SET_OPTION(old_way);
			continue;
		}

		if (!strcmp(this_char, "displace_based_on_dirid")) {
			SET_OPTION(displace_based_on_dirid);
			continue;
		}

		if (!strcmp(this_char, "preallocmin")) {
			REISERFS_SB(s)->s_alloc_options.preallocmin =
			    (value
			     && *value) ? simple_strtoul(value, &value, 0) : 4;
			continue;
		}

		if (!strcmp(this_char, "preallocsize")) {
			REISERFS_SB(s)->s_alloc_options.preallocsize =
			    (value
			     && *value) ? simple_strtoul(value, &value,
							 0) :
			    PREALLOCATION_SIZE;
			continue;
		}

		reiserfs_warning(s, "zam-4001", "unknown option - %s",
				 this_char);
		return 1;
	}

	reiserfs_info(s, "allocator options = [%08x]\n", SB_ALLOC_OPTS(s));
	return 0;
}

static void print_sep(struct seq_file *seq, int *first)
{
	if (!*first)
		seq_puts(seq, ":");
	else
		*first = 0;
}

void show_alloc_options(struct seq_file *seq, struct super_block *s)
{
	int first = 1;

	if (SB_ALLOC_OPTS(s) == ((1 << _ALLOC_skip_busy) |
		(1 << _ALLOC_dirid_groups) | (1 << _ALLOC_packing_groups)))
		return;

	seq_puts(seq, ",alloc=");

	if (TEST_OPTION(concentrating_formatted_nodes, s)) {
		print_sep(seq, &first);
		if (REISERFS_SB(s)->s_alloc_options.border != 10) {
			seq_printf(seq, "concentrating_formatted_nodes=%d",
				100 / REISERFS_SB(s)->s_alloc_options.border);
		} else
			seq_puts(seq, "concentrating_formatted_nodes");
	}
	if (TEST_OPTION(displacing_large_files, s)) {
		print_sep(seq, &first);
		if (REISERFS_SB(s)->s_alloc_options.large_file_size != 16) {
			seq_printf(seq, "displacing_large_files=%lu",
			    REISERFS_SB(s)->s_alloc_options.large_file_size);
		} else
			seq_puts(seq, "displacing_large_files");
	}
	if (TEST_OPTION(displacing_new_packing_localities, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "displacing_new_packing_localities");
	}
	if (TEST_OPTION(old_hashed_relocation, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "old_hashed_relocation");
	}
	if (TEST_OPTION(new_hashed_relocation, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "new_hashed_relocation");
	}
	if (TEST_OPTION(dirid_groups, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "dirid_groups");
	}
	if (TEST_OPTION(oid_groups, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "oid_groups");
	}
	if (TEST_OPTION(packing_groups, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "packing_groups");
	}
	if (TEST_OPTION(hashed_formatted_nodes, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "hashed_formatted_nodes");
	}
	if (TEST_OPTION(skip_busy, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "skip_busy");
	}
	if (TEST_OPTION(hundredth_slices, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "hundredth_slices");
	}
	if (TEST_OPTION(old_way, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "old_way");
	}
	if (TEST_OPTION(displace_based_on_dirid, s)) {
		print_sep(seq, &first);
		seq_puts(seq, "displace_based_on_dirid");
	}
	if (REISERFS_SB(s)->s_alloc_options.preallocmin != 0) {
		print_sep(seq, &first);
		seq_printf(seq, "preallocmin=%d",
				REISERFS_SB(s)->s_alloc_options.preallocmin);
	}
	if (REISERFS_SB(s)->s_alloc_options.preallocsize != 17) {
		print_sep(seq, &first);
		seq_printf(seq, "preallocsize=%d",
				REISERFS_SB(s)->s_alloc_options.preallocsize);
	}
}

static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint)
{
	char *hash_in;

	if (hint->formatted_node) {
		hash_in = (char *)&hint->key.k_dir_id;
	} else {
		if (!hint->inode) {
			/*hint->search_start = hint->beg;*/
			hash_in = (char *)&hint->key.k_dir_id;
		} else
		    if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super))
			hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id);
		else
			hash_in =
			    (char *)(&INODE_PKEY(hint->inode)->k_objectid);
	}

	hint->search_start =
	    hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg);
}

/*
 * Relocation based on dirid, hashing them into a given bitmap block
 * files. Formatted nodes are unaffected, a separate policy covers them
 */
static void dirid_groups(reiserfs_blocknr_hint_t * hint)
{
	unsigned long hash;
	__u32 dirid = 0;
	int bm = 0;
	struct super_block *sb = hint->th->t_super;

	if (hint->inode)
		dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id);
	else if (hint->formatted_node)
		dirid = hint->key.k_dir_id;

	if (dirid) {
		bm = bmap_hash_id(sb, dirid);
		hash = bm * (sb->s_blocksize << 3);
		/* give a portion of the block group to metadata */
		if (hint->inode)
			hash += sb->s_blocksize / 2;
		hint->search_start = hash;
	}
}

/*
 * Relocation based on oid, hashing them into a given bitmap block
 * files. Formatted nodes are unaffected, a separate policy covers them
 */
static void oid_groups(reiserfs_blocknr_hint_t * hint)
{
	if (hint->inode) {
		unsigned long hash;
		__u32 oid;
		__u32 dirid;
		int bm;

		dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id);

		/*
		 * keep the root dir and it's first set of subdirs close to
		 * the start of the disk
		 */
		if (dirid <= 2)
			hash = (hint->inode->i_sb->s_blocksize << 3);
		else {
			oid = le32_to_cpu(INODE_PKEY(hint->inode)->k_objectid);
			bm = bmap_hash_id(hint->inode->i_sb, oid);
			hash = bm * (hint->inode->i_sb->s_blocksize << 3);
		}
		hint->search_start = hash;
	}
}

/*
 * returns 1 if it finds an indirect item and gets valid hint info
 * from it, otherwise 0
 */
static int get_left_neighbor(reiserfs_blocknr_hint_t * hint)
{
	struct treepath *path;
	struct buffer_head *bh;
	struct item_head *ih;
	int pos_in_item;
	__le32 *item;
	int ret = 0;

	/*
	 * reiserfs code can call this function w/o pointer to path
	 * structure supplied; then we rely on supplied search_start
	 */
	if (!hint->path)
		return 0;

	path = hint->path;
	bh = get_last_bh(path);
	RFALSE(!bh, "green-4002: Illegal path specified to get_left_neighbor");
	ih = tp_item_head(path);
	pos_in_item = path->pos_in_item;
	item = tp_item_body(path);

	hint->search_start = bh->b_blocknr;

	/*
	 * for indirect item: go to left and look for the first non-hole entry
	 * in the indirect item
	 */
	if (!hint->formatted_node && is_indirect_le_ih(ih)) {
		if (pos_in_item == I_UNFM_NUM(ih))
			pos_in_item--;
		while (pos_in_item >= 0) {
			int t = get_block_num(item, pos_in_item);
			if (t) {
				hint->search_start = t;
				ret = 1;
				break;
			}
			pos_in_item--;
		}
	}

	/* does result value fit into specified region? */
	return ret;
}

/*
 * should be, if formatted node, then try to put on first part of the device
 * specified as number of percent with mount option device, else try to put
 * on last of device.  This is not to say it is good code to do so,
 * but the effect should be measured.
 */
static inline void set_border_in_hint(struct super_block *s,
				      reiserfs_blocknr_hint_t * hint)
{
	b_blocknr_t border =
	    SB_BLOCK_COUNT(s) / REISERFS_SB(s)->s_alloc_options.border;

	if (hint->formatted_node)
		hint->end = border - 1;
	else
		hint->beg = border;
}

static inline void displace_large_file(reiserfs_blocknr_hint_t * hint)
{
	if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super))
		hint->search_start =
		    hint->beg +
		    keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_dir_id),
			       4) % (hint->end - hint->beg);
	else
		hint->search_start =
		    hint->beg +
		    keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_objectid),
			       4) % (hint->end - hint->beg);
}

static inline void hash_formatted_node(reiserfs_blocknr_hint_t * hint)
{
	char *hash_in;

	if (!hint->inode)
		hash_in = (char *)&hint->key.k_dir_id;
	else if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super))
		hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id);
	else
		hash_in = (char *)(&INODE_PKEY(hint->inode)->k_objectid);

	hint->search_start =
	    hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg);
}

static inline int
this_blocknr_allocation_would_make_it_a_large_file(reiserfs_blocknr_hint_t *
						   hint)
{
	return hint->block ==
	    REISERFS_SB(hint->th->t_super)->s_alloc_options.large_file_size;
}

#ifdef DISPLACE_NEW_PACKING_LOCALITIES
static inline void displace_new_packing_locality(reiserfs_blocknr_hint_t * hint)
{
	struct in_core_key *key = &hint->key;

	hint->th->displace_new_blocks = 0;
	hint->search_start =
	    hint->beg + keyed_hash((char *)(&key->k_objectid),
				   4) % (hint->end - hint->beg);
}
#endif

static inline int old_hashed_relocation(reiserfs_blocknr_hint_t * hint)
{
	b_blocknr_t border;
	u32 hash_in;

	if (hint->formatted_node || hint->inode == NULL) {
		return 0;
	}

	hash_in = le32_to_cpu((INODE_PKEY(hint->inode))->k_dir_id);
	border =
	    hint->beg + (u32) keyed_hash(((char *)(&hash_in)),
					 4) % (hint->end - hint->beg - 1);
	if (border > hint->search_start)
		hint->search_start = border;

	return 1;
}

static inline int old_way(reiserfs_blocknr_hint_t * hint)
{
	b_blocknr_t border;

	if (hint->formatted_node || hint->inode == NULL) {
		return 0;
	}

	border =
	    hint->beg +
	    le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id) % (hint->end -
							      hint->beg);
	if (border > hint->search_start)
		hint->search_start = border;

	return 1;
}

static inline void hundredth_slices(reiserfs_blocknr_hint_t * hint)
{
	struct in_core_key *key = &hint->key;
	b_blocknr_t slice_start;

	slice_start =
	    (keyed_hash((char *)(&key->k_dir_id), 4) % 100) * (hint->end / 100);
	if (slice_start > hint->search_start
	    || slice_start + (hint->end / 100) <= hint->search_start) {
		hint->search_start = slice_start;
	}
}

static void determine_search_start(reiserfs_blocknr_hint_t * hint,
				   int amount_needed)
{
	struct super_block *s = hint->th->t_super;
	int unfm_hint;

	hint->beg = 0;
	hint->end = SB_BLOCK_COUNT(s) - 1;

	/* This is former border algorithm. Now with tunable border offset */
	if (concentrating_formatted_nodes(s))
		set_border_in_hint(s, hint);

#ifdef DISPLACE_NEW_PACKING_LOCALITIES
	/*
	 * whenever we create a new directory, we displace it.  At first
	 * we will hash for location, later we might look for a moderately
	 * empty place for it
	 */
	if (displacing_new_packing_localities(s)
	    && hint->th->displace_new_blocks) {
		displace_new_packing_locality(hint);

		/*
		 * we do not continue determine_search_start,
		 * if new packing locality is being displaced
		 */
		return;
	}
#endif

	/*
	 * all persons should feel encouraged to add more special cases
	 * here and test them
	 */

	if (displacing_large_files(s) && !hint->formatted_node
	    && this_blocknr_allocation_would_make_it_a_large_file(hint)) {
		displace_large_file(hint);
		return;
	}

	/*
	 * if none of our special cases is relevant, use the left
	 * neighbor in the tree order of the new node we are allocating for
	 */
	if (hint->formatted_node && TEST_OPTION(hashed_formatted_nodes, s)) {
		hash_formatted_node(hint);
		return;
	}

	unfm_hint = get_left_neighbor(hint);

	/*
	 * Mimic old block allocator behaviour, that is if VFS allowed for
	 * preallocation, new blocks are displaced based on directory ID.
	 * Also, if suggested search_start is less than last preallocated
	 * block, we start searching from it, assuming that HDD dataflow
	 * is faster in forward direction
	 */
	if (TEST_OPTION(old_way, s)) {
		if (!hint->formatted_node) {
			if (!reiserfs_hashed_relocation(s))
				old_way(hint);
			else if (!reiserfs_no_unhashed_relocation(s))
				old_hashed_relocation(hint);

			if (hint->inode
			    && hint->search_start <
			    REISERFS_I(hint->inode)->i_prealloc_block)
				hint->search_start =
				    REISERFS_I(hint->inode)->i_prealloc_block;
		}
		return;
	}

	/* This is an approach proposed by Hans */
	if (TEST_OPTION(hundredth_slices, s)
	    && !(displacing_large_files(s) && !hint->formatted_node)) {
		hundredth_slices(hint);
		return;
	}

	/* old_hashed_relocation only works on unformatted */
	if (!unfm_hint && !hint->formatted_node &&
	    TEST_OPTION(old_hashed_relocation, s)) {
		old_hashed_relocation(hint);
	}

	/* new_hashed_relocation works with both formatted/unformatted nodes */
	if ((!unfm_hint || hint->formatted_node) &&
	    TEST_OPTION(new_hashed_relocation, s)) {
		new_hashed_relocation(hint);
	}

	/* dirid grouping works only on unformatted nodes */
	if (!unfm_hint && !hint->formatted_node && TEST_OPTION(dirid_groups, s)) {
		dirid_groups(hint);
	}
#ifdef DISPLACE_NEW_PACKING_LOCALITIES
	if (hint->formatted_node && TEST_OPTION(dirid_groups, s)) {
		dirid_groups(hint);
	}
#endif

	/* oid grouping works only on unformatted nodes */
	if (!unfm_hint && !hint->formatted_node && TEST_OPTION(oid_groups, s)) {
		oid_groups(hint);
	}
	return;
}

static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint)
{
	/* make minimum size a mount option and benchmark both ways */
	/* we preallocate blocks only for regular files, specific size */
	/* benchmark preallocating always and see what happens */

	hint->prealloc_size = 0;

	if (!hint->formatted_node && hint->preallocate) {
		if (S_ISREG(hint->inode->i_mode)
		    && hint->inode->i_size >=
		    REISERFS_SB(hint->th->t_super)->s_alloc_options.
		    preallocmin * hint->inode->i_sb->s_blocksize)
			hint->prealloc_size =
			    REISERFS_SB(hint->th->t_super)->s_alloc_options.
			    preallocsize - 1;
	}
	return CARRY_ON;
}

static inline int allocate_without_wrapping_disk(reiserfs_blocknr_hint_t * hint,
						 b_blocknr_t * new_blocknrs,
						 b_blocknr_t start,
						 b_blocknr_t finish, int min,
						 int amount_needed,
						 int prealloc_size)
{
	int rest = amount_needed;
	int nr_allocated;

	while (rest > 0 && start <= finish) {
		nr_allocated = scan_bitmap(hint->th, &start, finish, min,
					   rest + prealloc_size,
					   !hint->formatted_node, hint->block);

		if (nr_allocated == 0)	/* no new blocks allocated, return */
			break;

		/* fill free_blocknrs array first */
		while (rest > 0 && nr_allocated > 0) {
			*new_blocknrs++ = start++;
			rest--;
			nr_allocated--;
		}

		/* do we have something to fill prealloc. array also ? */
		if (nr_allocated > 0) {
			/*
			 * it means prealloc_size was greater that 0 and
			 * we do preallocation
			 */
			list_add(&REISERFS_I(hint->inode)->i_prealloc_list,
				 &SB_JOURNAL(hint->th->t_super)->
				 j_prealloc_list);
			REISERFS_I(hint->inode)->i_prealloc_block = start;
			REISERFS_I(hint->inode)->i_prealloc_count =
			    nr_allocated;
			break;
		}
	}

	return (amount_needed - rest);
}

static inline int blocknrs_and_prealloc_arrays_from_search_start
    (reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs,
     int amount_needed) {
	struct super_block *s = hint->th->t_super;
	b_blocknr_t start = hint->search_start;
	b_blocknr_t finish = SB_BLOCK_COUNT(s) - 1;
	int passno = 0;
	int nr_allocated = 0;
	int depth;

	determine_prealloc_size(hint);
	if (!hint->formatted_node) {
		int quota_ret;
#ifdef REISERQUOTA_DEBUG
		reiserfs_debug(s, REISERFS_DEBUG_CODE,
			       "reiserquota: allocating %d blocks id=%u",
			       amount_needed, hint->inode->i_uid);
#endif
		depth = reiserfs_write_unlock_nested(s);
		quota_ret =
		    dquot_alloc_block_nodirty(hint->inode, amount_needed);
		if (quota_ret) {	/* Quota exceeded? */
			reiserfs_write_lock_nested(s, depth);
			return QUOTA_EXCEEDED;
		}
		if (hint->preallocate && hint->prealloc_size) {
#ifdef REISERQUOTA_DEBUG
			reiserfs_debug(s, REISERFS_DEBUG_CODE,
				       "reiserquota: allocating (prealloc) %d blocks id=%u",
				       hint->prealloc_size, hint->inode->i_uid);
#endif
			quota_ret = dquot_prealloc_block_nodirty(hint->inode,
							 hint->prealloc_size);
			if (quota_ret)
				hint->preallocate = hint->prealloc_size = 0;
		}
		/* for unformatted nodes, force large allocations */
		reiserfs_write_lock_nested(s, depth);
	}

	do {
		switch (passno++) {
		case 0:	/* Search from hint->search_start to end of disk */
			start = hint->search_start;
			finish = SB_BLOCK_COUNT(s) - 1;
			break;
		case 1:	/* Search from hint->beg to hint->search_start */
			start = hint->beg;
			finish = hint->search_start;
			break;
		case 2:	/* Last chance: Search from 0 to hint->beg */
			start = 0;
			finish = hint->beg;
			break;
		default:
			/* We've tried searching everywhere, not enough space */
			/* Free the blocks */
			if (!hint->formatted_node) {
#ifdef REISERQUOTA_DEBUG
				reiserfs_debug(s, REISERFS_DEBUG_CODE,
					       "reiserquota: freeing (nospace) %d blocks id=%u",
					       amount_needed +
					       hint->prealloc_size -
					       nr_allocated,
					       hint->inode->i_uid);
#endif
				/* Free not allocated blocks */
				depth = reiserfs_write_unlock_nested(s);
				dquot_free_block_nodirty(hint->inode,
					amount_needed + hint->prealloc_size -
					nr_allocated);
				reiserfs_write_lock_nested(s, depth);
			}
			while (nr_allocated--)
				reiserfs_free_block(hint->th, hint->inode,
						    new_blocknrs[nr_allocated],
						    !hint->formatted_node);

			return NO_DISK_SPACE;
		}
	} while ((nr_allocated += allocate_without_wrapping_disk(hint,
								 new_blocknrs +
								 nr_allocated,
								 start, finish,
								 1,
								 amount_needed -
								 nr_allocated,
								 hint->
								 prealloc_size))
		 < amount_needed);
	if (!hint->formatted_node &&
	    amount_needed + hint->prealloc_size >
	    nr_allocated + REISERFS_I(hint->inode)->i_prealloc_count) {
		/* Some of preallocation blocks were not allocated */
#ifdef REISERQUOTA_DEBUG
		reiserfs_debug(s, REISERFS_DEBUG_CODE,
			       "reiserquota: freeing (failed prealloc) %d blocks id=%u",
			       amount_needed + hint->prealloc_size -
			       nr_allocated -
			       REISERFS_I(hint->inode)->i_prealloc_count,
			       hint->inode->i_uid);
#endif

		depth = reiserfs_write_unlock_nested(s);
		dquot_free_block_nodirty(hint->inode, amount_needed +
					 hint->prealloc_size - nr_allocated -
					 REISERFS_I(hint->inode)->
					 i_prealloc_count);
		reiserfs_write_lock_nested(s, depth);
	}

	return CARRY_ON;
}

/* grab new blocknrs from preallocated list */
/* return amount still needed after using them */
static int use_preallocated_list_if_available(reiserfs_blocknr_hint_t * hint,
					      b_blocknr_t * new_blocknrs,
					      int amount_needed)
{
	struct inode *inode = hint->inode;

	if (REISERFS_I(inode)->i_prealloc_count > 0) {
		while (amount_needed) {

			*new_blocknrs++ = REISERFS_I(inode)->i_prealloc_block++;
			REISERFS_I(inode)->i_prealloc_count--;

			amount_needed--;

			if (REISERFS_I(inode)->i_prealloc_count <= 0) {
				list_del(&REISERFS_I(inode)->i_prealloc_list);
				break;
			}
		}
	}
	/* return amount still needed after using preallocated blocks */
	return amount_needed;
}

int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *hint,
			       b_blocknr_t *new_blocknrs,
			       int amount_needed,
			       /* Amount of blocks we have already reserved */
			       int reserved_by_us)
{
	int initial_amount_needed = amount_needed;
	int ret;
	struct super_block *s = hint->th->t_super;

	/* Check if there is enough space, taking into account reserved space */
	if (SB_FREE_BLOCKS(s) - REISERFS_SB(s)->reserved_blocks <
	    amount_needed - reserved_by_us)
		return NO_DISK_SPACE;
	/* should this be if !hint->inode &&  hint->preallocate? */
	/* do you mean hint->formatted_node can be removed ? - Zam */
	/*
	 * hint->formatted_node cannot be removed because we try to access
	 * inode information here, and there is often no inode associated with
	 * metadata allocations - green
	 */

	if (!hint->formatted_node && hint->preallocate) {
		amount_needed = use_preallocated_list_if_available
		    (hint, new_blocknrs, amount_needed);

		/*
		 * We have all the block numbers we need from the
		 * prealloc list
		 */
		if (amount_needed == 0)
			return CARRY_ON;
		new_blocknrs += (initial_amount_needed - amount_needed);
	}

	/* find search start and save it in hint structure */
	determine_search_start(hint, amount_needed);
	if (hint->search_start >= SB_BLOCK_COUNT(s))
		hint->search_start = SB_BLOCK_COUNT(s) - 1;

	/* allocation itself; fill new_blocknrs and preallocation arrays */
	ret = blocknrs_and_prealloc_arrays_from_search_start
	    (hint, new_blocknrs, amount_needed);

	/*
	 * We used prealloc. list to fill (partially) new_blocknrs array.
	 * If final allocation fails we need to return blocks back to
	 * prealloc. list or just free them. -- Zam (I chose second
	 * variant)
	 */
	if (ret != CARRY_ON) {
		while (amount_needed++ < initial_amount_needed) {
			reiserfs_free_block(hint->th, hint->inode,
					    *(--new_blocknrs), 1);
		}
	}
	return ret;
}

void reiserfs_cache_bitmap_metadata(struct super_block *sb,
                                    struct buffer_head *bh,
                                    struct reiserfs_bitmap_info *info)
{
	unsigned long *cur = (unsigned long *)(bh->b_data + bh->b_size);

	/* The first bit must ALWAYS be 1 */
	if (!reiserfs_test_le_bit(0, (unsigned long *)bh->b_data))
		reiserfs_error(sb, "reiserfs-2025", "bitmap block %lu is "
			       "corrupted: first bit must be 1", bh->b_blocknr);

	info->free_count = 0;

	while (--cur >= (unsigned long *)bh->b_data) {
		/* 0 and ~0 are special, we can optimize for them */
		if (*cur == 0)
			info->free_count += BITS_PER_LONG;
		else if (*cur != ~0L)	/* A mix, investigate */
			info->free_count += BITS_PER_LONG - hweight_long(*cur);
	}
}

struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb,
                                               unsigned int bitmap)
{
	b_blocknr_t block = (sb->s_blocksize << 3) * bitmap;
	struct reiserfs_bitmap_info *info = SB_AP_BITMAP(sb) + bitmap;
	struct buffer_head *bh;

	/*
	 * Way old format filesystems had the bitmaps packed up front.
	 * I doubt there are any of these left, but just in case...
	 */
	if (unlikely(test_bit(REISERFS_OLD_FORMAT,
			      &REISERFS_SB(sb)->s_properties)))
		block = REISERFS_SB(sb)->s_sbh->b_blocknr + 1 + bitmap;
	else if (bitmap == 0)
		block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1;

	bh = sb_bread(sb, block);
	if (bh == NULL)
		reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) "
		                 "reading failed", __func__, block);
	else {
		if (buffer_locked(bh)) {
			int depth;
			PROC_INFO_INC(sb, scan_bitmap.wait);
			depth = reiserfs_write_unlock_nested(sb);
			__wait_on_buffer(bh);
			reiserfs_write_lock_nested(sb, depth);
		}
		BUG_ON(!buffer_uptodate(bh));
		BUG_ON(atomic_read(&bh->b_count) == 0);

		if (info->free_count == UINT_MAX)
			reiserfs_cache_bitmap_metadata(sb, bh, info);
	}

	return bh;
}

int reiserfs_init_bitmap_cache(struct super_block *sb)
{
	struct reiserfs_bitmap_info *bitmap;
	unsigned int bmap_nr = reiserfs_bmap_count(sb);

	bitmap = vmalloc(sizeof(*bitmap) * bmap_nr);
	if (bitmap == NULL)
		return -ENOMEM;

	memset(bitmap, 0xff, sizeof(*bitmap) * bmap_nr);

	SB_AP_BITMAP(sb) = bitmap;

	return 0;
}

void reiserfs_free_bitmap_cache(struct super_block *sb)
{
	if (SB_AP_BITMAP(sb)) {
		vfree(SB_AP_BITMAP(sb));
		SB_AP_BITMAP(sb) = NULL;
	}
}