indirect.c 42.7 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
/*
 *  linux/fs/ext4/indirect.c
 *
 *  from
 *
 *  linux/fs/ext4/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Goal-directed block allocation by Stephen Tweedie
 *	(sct@redhat.com), 1993, 1998
 */

#include "ext4_jbd2.h"
#include "truncate.h"
#include <linux/dax.h>
#include <linux/uio.h>

#include <trace/events/ext4.h>

typedef struct {
	__le32	*p;
	__le32	key;
	struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

/**
 *	ext4_block_to_path - parse the block number into array of offsets
 *	@inode: inode in question (we are only interested in its superblock)
 *	@i_block: block number to be parsed
 *	@offsets: array to store the offsets in
 *	@boundary: set this non-zero if the referred-to block is likely to be
 *	       followed (on disk) by an indirect block.
 *
 *	To store the locations of file's data ext4 uses a data structure common
 *	for UNIX filesystems - tree of pointers anchored in the inode, with
 *	data blocks at leaves and indirect blocks in intermediate nodes.
 *	This function translates the block number into path in that tree -
 *	return value is the path length and @offsets[n] is the offset of
 *	pointer to (n+1)th node in the nth one. If @block is out of range
 *	(negative or too large) warning is printed and zero returned.
 *
 *	Note: function doesn't find node addresses, so no IO is needed. All
 *	we need to know is the capacity of indirect blocks (taken from the
 *	inode->i_sb).
 */

/*
 * Portability note: the last comparison (check that we fit into triple
 * indirect block) is spelled differently, because otherwise on an
 * architecture with 32-bit longs and 8Kb pages we might get into trouble
 * if our filesystem had 8Kb blocks. We might use long long, but that would
 * kill us on x86. Oh, well, at least the sign propagation does not matter -
 * i_block would have to be negative in the very beginning, so we would not
 * get there at all.
 */

static int ext4_block_to_path(struct inode *inode,
			      ext4_lblk_t i_block,
			      ext4_lblk_t offsets[4], int *boundary)
{
	int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT4_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < direct_blocks) {
		offsets[n++] = i_block;
		final = direct_blocks;
	} else if ((i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT4_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT4_DIND_BLOCK;
		offsets[n++] = i_block >> ptrs_bits;
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
		offsets[n++] = EXT4_TIND_BLOCK;
		offsets[n++] = i_block >> (ptrs_bits * 2);
		offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else {
		ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
			     i_block + direct_blocks +
			     indirect_blocks + double_blocks, inode->i_ino);
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));
	return n;
}

/**
 *	ext4_get_branch - read the chain of indirect blocks leading to data
 *	@inode: inode in question
 *	@depth: depth of the chain (1 - direct pointer, etc.)
 *	@offsets: offsets of pointers in inode/indirect blocks
 *	@chain: place to store the result
 *	@err: here we store the error value
 *
 *	Function fills the array of triples <key, p, bh> and returns %NULL
 *	if everything went OK or the pointer to the last filled triple
 *	(incomplete one) otherwise. Upon the return chain[i].key contains
 *	the number of (i+1)-th block in the chain (as it is stored in memory,
 *	i.e. little-endian 32-bit), chain[i].p contains the address of that
 *	number (it points into struct inode for i==0 and into the bh->b_data
 *	for i>0) and chain[i].bh points to the buffer_head of i-th indirect
 *	block for i>0 and NULL for i==0. In other words, it holds the block
 *	numbers of the chain, addresses they were taken from (and where we can
 *	verify that chain did not change) and buffer_heads hosting these
 *	numbers.
 *
 *	Function stops when it stumbles upon zero pointer (absent block)
 *		(pointer to last triple returned, *@err == 0)
 *	or when it gets an IO error reading an indirect block
 *		(ditto, *@err == -EIO)
 *	or when it reads all @depth-1 indirect blocks successfully and finds
 *	the whole chain, all way to the data (returns %NULL, *err == 0).
 *
 *      Need to be called with
 *      down_read(&EXT4_I(inode)->i_data_sem)
 */
static Indirect *ext4_get_branch(struct inode *inode, int depth,
				 ext4_lblk_t  *offsets,
				 Indirect chain[4], int *err)
{
	struct super_block *sb = inode->i_sb;
	Indirect *p = chain;
	struct buffer_head *bh;
	int ret = -EIO;

	*err = 0;
	/* i_data is not going away, no lock needed */
	add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		bh = sb_getblk(sb, le32_to_cpu(p->key));
		if (unlikely(!bh)) {
			ret = -ENOMEM;
			goto failure;
		}

		if (!bh_uptodate_or_lock(bh)) {
			if (bh_submit_read(bh) < 0) {
				put_bh(bh);
				goto failure;
			}
			/* validate block references */
			if (ext4_check_indirect_blockref(inode, bh)) {
				put_bh(bh);
				goto failure;
			}
		}

		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

failure:
	*err = ret;
no_block:
	return p;
}

/**
 *	ext4_find_near - find a place for allocation with sufficient locality
 *	@inode: owner
 *	@ind: descriptor of indirect block.
 *
 *	This function returns the preferred place for block allocation.
 *	It is used when heuristic for sequential allocation fails.
 *	Rules are:
 *	  + if there is a block to the left of our position - allocate near it.
 *	  + if pointer will live in indirect block - allocate near that block.
 *	  + if pointer will live in inode - allocate in the same
 *	    cylinder group.
 *
 * In the latter case we colour the starting block by the callers PID to
 * prevent it from clashing with concurrent allocations for a different inode
 * in the same block group.   The PID is used here so that functionally related
 * files will be close-by on-disk.
 *
 *	Caller must make sure that @ind is valid and will stay that way.
 */
static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
	__le32 *p;

	/* Try to find previous block */
	for (p = ind->p - 1; p >= start; p--) {
		if (*p)
			return le32_to_cpu(*p);
	}

	/* No such thing, so let's try location of indirect block */
	if (ind->bh)
		return ind->bh->b_blocknr;

	/*
	 * It is going to be referred to from the inode itself? OK, just put it
	 * into the same cylinder group then.
	 */
	return ext4_inode_to_goal_block(inode);
}

/**
 *	ext4_find_goal - find a preferred place for allocation.
 *	@inode: owner
 *	@block:  block we want
 *	@partial: pointer to the last triple within a chain
 *
 *	Normally this function find the preferred place for block allocation,
 *	returns it.
 *	Because this is only used for non-extent files, we limit the block nr
 *	to 32 bits.
 */
static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
				   Indirect *partial)
{
	ext4_fsblk_t goal;

	/*
	 * XXX need to get goal block from mballoc's data structures
	 */

	goal = ext4_find_near(inode, partial);
	goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
	return goal;
}

/**
 *	ext4_blks_to_allocate - Look up the block map and count the number
 *	of direct blocks need to be allocated for the given branch.
 *
 *	@branch: chain of indirect blocks
 *	@k: number of blocks need for indirect blocks
 *	@blks: number of data blocks to be mapped.
 *	@blocks_to_boundary:  the offset in the indirect block
 *
 *	return the total number of blocks to be allocate, including the
 *	direct and indirect blocks.
 */
static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
				 int blocks_to_boundary)
{
	unsigned int count = 0;

	/*
	 * Simple case, [t,d]Indirect block(s) has not allocated yet
	 * then it's clear blocks on that path have not allocated
	 */
	if (k > 0) {
		/* right now we don't handle cross boundary allocation */
		if (blks < blocks_to_boundary + 1)
			count += blks;
		else
			count += blocks_to_boundary + 1;
		return count;
	}

	count++;
	while (count < blks && count <= blocks_to_boundary &&
		le32_to_cpu(*(branch[0].p + count)) == 0) {
		count++;
	}
	return count;
}

/**
 *	ext4_alloc_branch - allocate and set up a chain of blocks.
 *	@handle: handle for this transaction
 *	@inode: owner
 *	@indirect_blks: number of allocated indirect blocks
 *	@blks: number of allocated direct blocks
 *	@goal: preferred place for allocation
 *	@offsets: offsets (in the blocks) to store the pointers to next.
 *	@branch: place to store the chain in.
 *
 *	This function allocates blocks, zeroes out all but the last one,
 *	links them into chain and (if we are synchronous) writes them to disk.
 *	In other words, it prepares a branch that can be spliced onto the
 *	inode. It stores the information about that chain in the branch[], in
 *	the same format as ext4_get_branch() would do. We are calling it after
 *	we had read the existing part of chain and partial points to the last
 *	triple of that (one with zero ->key). Upon the exit we have the same
 *	picture as after the successful ext4_get_block(), except that in one
 *	place chain is disconnected - *branch->p is still zero (we did not
 *	set the last link), but branch->key contains the number that should
 *	be placed into *branch->p to fill that gap.
 *
 *	If allocation fails we free all blocks we've allocated (and forget
 *	their buffer_heads) and return the error value the from failed
 *	ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */
static int ext4_alloc_branch(handle_t *handle,
			     struct ext4_allocation_request *ar,
			     int indirect_blks, ext4_lblk_t *offsets,
			     Indirect *branch)
{
	struct buffer_head *		bh;
	ext4_fsblk_t			b, new_blocks[4];
	__le32				*p;
	int				i, j, err, len = 1;

	for (i = 0; i <= indirect_blks; i++) {
		if (i == indirect_blks) {
			new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err);
		} else
			ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle,
					ar->inode, ar->goal,
					ar->flags & EXT4_MB_DELALLOC_RESERVED,
					NULL, &err);
		if (err) {
			i--;
			goto failed;
		}
		branch[i].key = cpu_to_le32(new_blocks[i]);
		if (i == 0)
			continue;

		bh = branch[i].bh = sb_getblk(ar->inode->i_sb, new_blocks[i-1]);
		if (unlikely(!bh)) {
			err = -ENOMEM;
			goto failed;
		}
		lock_buffer(bh);
		BUFFER_TRACE(bh, "call get_create_access");
		err = ext4_journal_get_create_access(handle, bh);
		if (err) {
			unlock_buffer(bh);
			goto failed;
		}

		memset(bh->b_data, 0, bh->b_size);
		p = branch[i].p = (__le32 *) bh->b_data + offsets[i];
		b = new_blocks[i];

		if (i == indirect_blks)
			len = ar->len;
		for (j = 0; j < len; j++)
			*p++ = cpu_to_le32(b++);

		BUFFER_TRACE(bh, "marking uptodate");
		set_buffer_uptodate(bh);
		unlock_buffer(bh);

		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
		err = ext4_handle_dirty_metadata(handle, ar->inode, bh);
		if (err)
			goto failed;
	}
	return 0;
failed:
	for (; i >= 0; i--) {
		/*
		 * We want to ext4_forget() only freshly allocated indirect
		 * blocks.  Buffer for new_blocks[i-1] is at branch[i].bh and
		 * buffer at branch[0].bh is indirect block / inode already
		 * existing before ext4_alloc_branch() was called.
		 */
		if (i > 0 && i != indirect_blks && branch[i].bh)
			ext4_forget(handle, 1, ar->inode, branch[i].bh,
				    branch[i].bh->b_blocknr);
		ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i],
				 (i == indirect_blks) ? ar->len : 1, 0);
	}
	return err;
}

/**
 * ext4_splice_branch - splice the allocated branch onto inode.
 * @handle: handle for this transaction
 * @inode: owner
 * @block: (logical) number of block we are adding
 * @chain: chain of indirect blocks (with a missing link - see
 *	ext4_alloc_branch)
 * @where: location of missing link
 * @num:   number of indirect blocks we are adding
 * @blks:  number of direct blocks we are adding
 *
 * This function fills the missing link and does all housekeeping needed in
 * inode (->i_blocks, etc.). In case of success we end up with the full
 * chain to new block and return 0.
 */
static int ext4_splice_branch(handle_t *handle,
			      struct ext4_allocation_request *ar,
			      Indirect *where, int num)
{
	int i;
	int err = 0;
	ext4_fsblk_t current_block;

	/*
	 * If we're splicing into a [td]indirect block (as opposed to the
	 * inode) then we need to get write access to the [td]indirect block
	 * before the splice.
	 */
	if (where->bh) {
		BUFFER_TRACE(where->bh, "get_write_access");
		err = ext4_journal_get_write_access(handle, where->bh);
		if (err)
			goto err_out;
	}
	/* That's it */

	*where->p = where->key;

	/*
	 * Update the host buffer_head or inode to point to more just allocated
	 * direct blocks blocks
	 */
	if (num == 0 && ar->len > 1) {
		current_block = le32_to_cpu(where->key) + 1;
		for (i = 1; i < ar->len; i++)
			*(where->p + i) = cpu_to_le32(current_block++);
	}

	/* We are done with atomic stuff, now do the rest of housekeeping */
	/* had we spliced it onto indirect block? */
	if (where->bh) {
		/*
		 * If we spliced it onto an indirect block, we haven't
		 * altered the inode.  Note however that if it is being spliced
		 * onto an indirect block at the very end of the file (the
		 * file is growing) then we *will* alter the inode to reflect
		 * the new i_size.  But that is not done here - it is done in
		 * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
		 */
		jbd_debug(5, "splicing indirect only\n");
		BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
		err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh);
		if (err)
			goto err_out;
	} else {
		/*
		 * OK, we spliced it into the inode itself on a direct block.
		 */
		ext4_mark_inode_dirty(handle, ar->inode);
		jbd_debug(5, "splicing direct\n");
	}
	return err;

err_out:
	for (i = 1; i <= num; i++) {
		/*
		 * branch[i].bh is newly allocated, so there is no
		 * need to revoke the block, which is why we don't
		 * need to set EXT4_FREE_BLOCKS_METADATA.
		 */
		ext4_free_blocks(handle, ar->inode, where[i].bh, 0, 1,
				 EXT4_FREE_BLOCKS_FORGET);
	}
	ext4_free_blocks(handle, ar->inode, NULL, le32_to_cpu(where[num].key),
			 ar->len, 0);

	return err;
}

/*
 * The ext4_ind_map_blocks() function handles non-extents inodes
 * (i.e., using the traditional indirect/double-indirect i_blocks
 * scheme) for ext4_map_blocks().
 *
 * Allocation strategy is simple: if we have to allocate something, we will
 * have to go the whole way to leaf. So let's do it before attaching anything
 * to tree, set linkage between the newborn blocks, write them if sync is
 * required, recheck the path, free and repeat if check fails, otherwise
 * set the last missing link (that will protect us from any truncate-generated
 * removals - all blocks on the path are immune now) and possibly force the
 * write on the parent block.
 * That has a nice additional property: no special recovery from the failed
 * allocations is needed - we simply release blocks and do not touch anything
 * reachable from inode.
 *
 * `handle' can be NULL if create == 0.
 *
 * return > 0, # of blocks mapped or allocated.
 * return = 0, if plain lookup failed.
 * return < 0, error case.
 *
 * The ext4_ind_get_blocks() function should be called with
 * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
 * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
 * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
 * blocks.
 */
int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
			struct ext4_map_blocks *map,
			int flags)
{
	struct ext4_allocation_request ar;
	int err = -EIO;
	ext4_lblk_t offsets[4];
	Indirect chain[4];
	Indirect *partial;
	int indirect_blks;
	int blocks_to_boundary = 0;
	int depth;
	int count = 0;
	ext4_fsblk_t first_block = 0;

	trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
	J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
	depth = ext4_block_to_path(inode, map->m_lblk, offsets,
				   &blocks_to_boundary);

	if (depth == 0)
		goto out;

	partial = ext4_get_branch(inode, depth, offsets, chain, &err);

	/* Simplest case - block found, no allocation needed */
	if (!partial) {
		first_block = le32_to_cpu(chain[depth - 1].key);
		count++;
		/*map more blocks*/
		while (count < map->m_len && count <= blocks_to_boundary) {
			ext4_fsblk_t blk;

			blk = le32_to_cpu(*(chain[depth-1].p + count));

			if (blk == first_block + count)
				count++;
			else
				break;
		}
		goto got_it;
	}

	/* Next simple case - plain lookup failed */
	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
		unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
		int i;

		/* Count number blocks in a subtree under 'partial' */
		count = 1;
		for (i = 0; partial + i != chain + depth - 1; i++)
			count *= epb;
		/* Fill in size of a hole we found */
		map->m_pblk = 0;
		map->m_len = min_t(unsigned int, map->m_len, count);
		goto cleanup;
	}

	/* Failed read of indirect block */
	if (err == -EIO)
		goto cleanup;

	/*
	 * Okay, we need to do block allocation.
	*/
	if (ext4_has_feature_bigalloc(inode->i_sb)) {
		EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
				 "non-extent mapped inodes with bigalloc");
		return -EFSCORRUPTED;
	}

	/* Set up for the direct block allocation */
	memset(&ar, 0, sizeof(ar));
	ar.inode = inode;
	ar.logical = map->m_lblk;
	if (S_ISREG(inode->i_mode))
		ar.flags = EXT4_MB_HINT_DATA;
	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
		ar.flags |= EXT4_MB_DELALLOC_RESERVED;
	if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
		ar.flags |= EXT4_MB_USE_RESERVED;

	ar.goal = ext4_find_goal(inode, map->m_lblk, partial);

	/* the number of blocks need to allocate for [d,t]indirect blocks */
	indirect_blks = (chain + depth) - partial - 1;

	/*
	 * Next look up the indirect map to count the totoal number of
	 * direct blocks to allocate for this branch.
	 */
	ar.len = ext4_blks_to_allocate(partial, indirect_blks,
				       map->m_len, blocks_to_boundary);

	/*
	 * Block out ext4_truncate while we alter the tree
	 */
	err = ext4_alloc_branch(handle, &ar, indirect_blks,
				offsets + (partial - chain), partial);

	/*
	 * The ext4_splice_branch call will free and forget any buffers
	 * on the new chain if there is a failure, but that risks using
	 * up transaction credits, especially for bitmaps where the
	 * credits cannot be returned.  Can we handle this somehow?  We
	 * may need to return -EAGAIN upwards in the worst case.  --sct
	 */
	if (!err)
		err = ext4_splice_branch(handle, &ar, partial, indirect_blks);
	if (err)
		goto cleanup;

	map->m_flags |= EXT4_MAP_NEW;

	ext4_update_inode_fsync_trans(handle, inode, 1);
	count = ar.len;
got_it:
	map->m_flags |= EXT4_MAP_MAPPED;
	map->m_pblk = le32_to_cpu(chain[depth-1].key);
	map->m_len = count;
	if (count > blocks_to_boundary)
		map->m_flags |= EXT4_MAP_BOUNDARY;
	err = count;
	/* Clean up and exit */
	partial = chain + depth - 1;	/* the whole chain */
cleanup:
	while (partial > chain) {
		BUFFER_TRACE(partial->bh, "call brelse");
		brelse(partial->bh);
		partial--;
	}
out:
	trace_ext4_ind_map_blocks_exit(inode, flags, map, err);
	return err;
}

/*
 * Calculate the number of metadata blocks need to reserve
 * to allocate a new block at @lblocks for non extent file based file
 */
int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
	int blk_bits;

	if (lblock < EXT4_NDIR_BLOCKS)
		return 0;

	lblock -= EXT4_NDIR_BLOCKS;

	if (ei->i_da_metadata_calc_len &&
	    (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
		ei->i_da_metadata_calc_len++;
		return 0;
	}
	ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
	ei->i_da_metadata_calc_len = 1;
	blk_bits = order_base_2(lblock);
	return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}

/*
 * Calculate number of indirect blocks touched by mapping @nrblocks logically
 * contiguous blocks
 */
int ext4_ind_trans_blocks(struct inode *inode, int nrblocks)
{
	/*
	 * With N contiguous data blocks, we need at most
	 * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
	 * 2 dindirect blocks, and 1 tindirect block
	 */
	return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
}

/*
 * Truncate transactions can be complex and absolutely huge.  So we need to
 * be able to restart the transaction at a conventient checkpoint to make
 * sure we don't overflow the journal.
 *
 * Try to extend this transaction for the purposes of truncation.  If
 * extend fails, we need to propagate the failure up and restart the
 * transaction in the top-level truncate loop. --sct
 *
 * Returns 0 if we managed to create more room.  If we can't create more
 * room, and the transaction must be restarted we return 1.
 */
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
	if (!ext4_handle_valid(handle))
		return 0;
	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
		return 0;
	if (!ext4_journal_extend(handle, ext4_blocks_for_truncate(inode)))
		return 0;
	return 1;
}

/*
 * Probably it should be a library function... search for first non-zero word
 * or memcmp with zero_page, whatever is better for particular architecture.
 * Linus?
 */
static inline int all_zeroes(__le32 *p, __le32 *q)
{
	while (p < q)
		if (*p++)
			return 0;
	return 1;
}

/**
 *	ext4_find_shared - find the indirect blocks for partial truncation.
 *	@inode:	  inode in question
 *	@depth:	  depth of the affected branch
 *	@offsets: offsets of pointers in that branch (see ext4_block_to_path)
 *	@chain:	  place to store the pointers to partial indirect blocks
 *	@top:	  place to the (detached) top of branch
 *
 *	This is a helper function used by ext4_truncate().
 *
 *	When we do truncate() we may have to clean the ends of several
 *	indirect blocks but leave the blocks themselves alive. Block is
 *	partially truncated if some data below the new i_size is referred
 *	from it (and it is on the path to the first completely truncated
 *	data block, indeed).  We have to free the top of that path along
 *	with everything to the right of the path. Since no allocation
 *	past the truncation point is possible until ext4_truncate()
 *	finishes, we may safely do the latter, but top of branch may
 *	require special attention - pageout below the truncation point
 *	might try to populate it.
 *
 *	We atomically detach the top of branch from the tree, store the
 *	block number of its root in *@top, pointers to buffer_heads of
 *	partially truncated blocks - in @chain[].bh and pointers to
 *	their last elements that should not be removed - in
 *	@chain[].p. Return value is the pointer to last filled element
 *	of @chain.
 *
 *	The work left to caller to do the actual freeing of subtrees:
 *		a) free the subtree starting from *@top
 *		b) free the subtrees whose roots are stored in
 *			(@chain[i].p+1 .. end of @chain[i].bh->b_data)
 *		c) free the subtrees growing from the inode past the @chain[0].
 *			(no partially truncated stuff there).  */

static Indirect *ext4_find_shared(struct inode *inode, int depth,
				  ext4_lblk_t offsets[4], Indirect chain[4],
				  __le32 *top)
{
	Indirect *partial, *p;
	int k, err;

	*top = 0;
	/* Make k index the deepest non-null offset + 1 */
	for (k = depth; k > 1 && !offsets[k-1]; k--)
		;
	partial = ext4_get_branch(inode, k, offsets, chain, &err);
	/* Writer: pointers */
	if (!partial)
		partial = chain + k-1;
	/*
	 * If the branch acquired continuation since we've looked at it -
	 * fine, it should all survive and (new) top doesn't belong to us.
	 */
	if (!partial->key && *partial->p)
		/* Writer: end */
		goto no_top;
	for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
		;
	/*
	 * OK, we've found the last block that must survive. The rest of our
	 * branch should be detached before unlocking. However, if that rest
	 * of branch is all ours and does not grow immediately from the inode
	 * it's easier to cheat and just decrement partial->p.
	 */
	if (p == chain + k - 1 && p > chain) {
		p->p--;
	} else {
		*top = *p->p;
		/* Nope, don't do this in ext4.  Must leave the tree intact */
#if 0
		*p->p = 0;
#endif
	}
	/* Writer: end */

	while (partial > p) {
		brelse(partial->bh);
		partial--;
	}
no_top:
	return partial;
}

/*
 * Zero a number of block pointers in either an inode or an indirect block.
 * If we restart the transaction we must again get write access to the
 * indirect block for further modification.
 *
 * We release `count' blocks on disk, but (last - first) may be greater
 * than `count' because there can be holes in there.
 *
 * Return 0 on success, 1 on invalid block range
 * and < 0 on fatal error.
 */
static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
			     struct buffer_head *bh,
			     ext4_fsblk_t block_to_free,
			     unsigned long count, __le32 *first,
			     __le32 *last)
{
	__le32 *p;
	int	flags = EXT4_FREE_BLOCKS_VALIDATED;
	int	err;

	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
		flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA;
	else if (ext4_should_journal_data(inode))
		flags |= EXT4_FREE_BLOCKS_FORGET;

	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
				   count)) {
		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
				 "blocks %llu len %lu",
				 (unsigned long long) block_to_free, count);
		return 1;
	}

	if (try_to_extend_transaction(handle, inode)) {
		if (bh) {
			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
			err = ext4_handle_dirty_metadata(handle, inode, bh);
			if (unlikely(err))
				goto out_err;
		}
		err = ext4_mark_inode_dirty(handle, inode);
		if (unlikely(err))
			goto out_err;
		err = ext4_truncate_restart_trans(handle, inode,
					ext4_blocks_for_truncate(inode));
		if (unlikely(err))
			goto out_err;
		if (bh) {
			BUFFER_TRACE(bh, "retaking write access");
			err = ext4_journal_get_write_access(handle, bh);
			if (unlikely(err))
				goto out_err;
		}
	}

	for (p = first; p < last; p++)
		*p = 0;

	ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
	return 0;
out_err:
	ext4_std_error(inode->i_sb, err);
	return err;
}

/**
 * ext4_free_data - free a list of data blocks
 * @handle:	handle for this transaction
 * @inode:	inode we are dealing with
 * @this_bh:	indirect buffer_head which contains *@first and *@last
 * @first:	array of block numbers
 * @last:	points immediately past the end of array
 *
 * We are freeing all blocks referred from that array (numbers are stored as
 * little-endian 32-bit) and updating @inode->i_blocks appropriately.
 *
 * We accumulate contiguous runs of blocks to free.  Conveniently, if these
 * blocks are contiguous then releasing them at one time will only affect one
 * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
 * actually use a lot of journal space.
 *
 * @this_bh will be %NULL if @first and @last point into the inode's direct
 * block pointers.
 */
static void ext4_free_data(handle_t *handle, struct inode *inode,
			   struct buffer_head *this_bh,
			   __le32 *first, __le32 *last)
{
	ext4_fsblk_t block_to_free = 0;    /* Starting block # of a run */
	unsigned long count = 0;	    /* Number of blocks in the run */
	__le32 *block_to_free_p = NULL;	    /* Pointer into inode/ind
					       corresponding to
					       block_to_free */
	ext4_fsblk_t nr;		    /* Current block # */
	__le32 *p;			    /* Pointer into inode/ind
					       for current block */
	int err = 0;

	if (this_bh) {				/* For indirect block */
		BUFFER_TRACE(this_bh, "get_write_access");
		err = ext4_journal_get_write_access(handle, this_bh);
		/* Important: if we can't update the indirect pointers
		 * to the blocks, we can't free them. */
		if (err)
			return;
	}

	for (p = first; p < last; p++) {
		nr = le32_to_cpu(*p);
		if (nr) {
			/* accumulate blocks to free if they're contiguous */
			if (count == 0) {
				block_to_free = nr;
				block_to_free_p = p;
				count = 1;
			} else if (nr == block_to_free + count) {
				count++;
			} else {
				err = ext4_clear_blocks(handle, inode, this_bh,
						        block_to_free, count,
						        block_to_free_p, p);
				if (err)
					break;
				block_to_free = nr;
				block_to_free_p = p;
				count = 1;
			}
		}
	}

	if (!err && count > 0)
		err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
					count, block_to_free_p, p);
	if (err < 0)
		/* fatal error */
		return;

	if (this_bh) {
		BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");

		/*
		 * The buffer head should have an attached journal head at this
		 * point. However, if the data is corrupted and an indirect
		 * block pointed to itself, it would have been detached when
		 * the block was cleared. Check for this instead of OOPSing.
		 */
		if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
			ext4_handle_dirty_metadata(handle, inode, this_bh);
		else
			EXT4_ERROR_INODE(inode,
					 "circular indirect block detected at "
					 "block %llu",
				(unsigned long long) this_bh->b_blocknr);
	}
}

/**
 *	ext4_free_branches - free an array of branches
 *	@handle: JBD handle for this transaction
 *	@inode:	inode we are dealing with
 *	@parent_bh: the buffer_head which contains *@first and *@last
 *	@first:	array of block numbers
 *	@last:	pointer immediately past the end of array
 *	@depth:	depth of the branches to free
 *
 *	We are freeing all blocks referred from these branches (numbers are
 *	stored as little-endian 32-bit) and updating @inode->i_blocks
 *	appropriately.
 */
static void ext4_free_branches(handle_t *handle, struct inode *inode,
			       struct buffer_head *parent_bh,
			       __le32 *first, __le32 *last, int depth)
{
	ext4_fsblk_t nr;
	__le32 *p;

	if (ext4_handle_is_aborted(handle))
		return;

	if (depth--) {
		struct buffer_head *bh;
		int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
		p = last;
		while (--p >= first) {
			nr = le32_to_cpu(*p);
			if (!nr)
				continue;		/* A hole */

			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
						   nr, 1)) {
				EXT4_ERROR_INODE(inode,
						 "invalid indirect mapped "
						 "block %lu (level %d)",
						 (unsigned long) nr, depth);
				break;
			}

			/* Go read the buffer for the next level down */
			bh = sb_bread(inode->i_sb, nr);

			/*
			 * A read failure? Report error and clear slot
			 * (should be rare).
			 */
			if (!bh) {
				EXT4_ERROR_INODE_BLOCK(inode, nr,
						       "Read failure");
				continue;
			}

			/* This zaps the entire block.  Bottom up. */
			BUFFER_TRACE(bh, "free child branches");
			ext4_free_branches(handle, inode, bh,
					(__le32 *) bh->b_data,
					(__le32 *) bh->b_data + addr_per_block,
					depth);
			brelse(bh);

			/*
			 * Everything below this this pointer has been
			 * released.  Now let this top-of-subtree go.
			 *
			 * We want the freeing of this indirect block to be
			 * atomic in the journal with the updating of the
			 * bitmap block which owns it.  So make some room in
			 * the journal.
			 *
			 * We zero the parent pointer *after* freeing its
			 * pointee in the bitmaps, so if extend_transaction()
			 * for some reason fails to put the bitmap changes and
			 * the release into the same transaction, recovery
			 * will merely complain about releasing a free block,
			 * rather than leaking blocks.
			 */
			if (ext4_handle_is_aborted(handle))
				return;
			if (try_to_extend_transaction(handle, inode)) {
				ext4_mark_inode_dirty(handle, inode);
				ext4_truncate_restart_trans(handle, inode,
					    ext4_blocks_for_truncate(inode));
			}

			/*
			 * The forget flag here is critical because if
			 * we are journaling (and not doing data
			 * journaling), we have to make sure a revoke
			 * record is written to prevent the journal
			 * replay from overwriting the (former)
			 * indirect block if it gets reallocated as a
			 * data block.  This must happen in the same
			 * transaction where the data blocks are
			 * actually freed.
			 */
			ext4_free_blocks(handle, inode, NULL, nr, 1,
					 EXT4_FREE_BLOCKS_METADATA|
					 EXT4_FREE_BLOCKS_FORGET);

			if (parent_bh) {
				/*
				 * The block which we have just freed is
				 * pointed to by an indirect block: journal it
				 */
				BUFFER_TRACE(parent_bh, "get_write_access");
				if (!ext4_journal_get_write_access(handle,
								   parent_bh)){
					*p = 0;
					BUFFER_TRACE(parent_bh,
					"call ext4_handle_dirty_metadata");
					ext4_handle_dirty_metadata(handle,
								   inode,
								   parent_bh);
				}
			}
		}
	} else {
		/* We have reached the bottom of the tree. */
		BUFFER_TRACE(parent_bh, "free data blocks");
		ext4_free_data(handle, inode, parent_bh, first, last);
	}
}

void ext4_ind_truncate(handle_t *handle, struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	__le32 *i_data = ei->i_data;
	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
	ext4_lblk_t offsets[4];
	Indirect chain[4];
	Indirect *partial;
	__le32 nr = 0;
	int n = 0;
	ext4_lblk_t last_block, max_block;
	unsigned blocksize = inode->i_sb->s_blocksize;

	last_block = (inode->i_size + blocksize-1)
					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);

	if (last_block != max_block) {
		n = ext4_block_to_path(inode, last_block, offsets, NULL);
		if (n == 0)
			return;
	}

	ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);

	/*
	 * The orphan list entry will now protect us from any crash which
	 * occurs before the truncate completes, so it is now safe to propagate
	 * the new, shorter inode size (held for now in i_size) into the
	 * on-disk inode. We do this via i_disksize, which is the value which
	 * ext4 *really* writes onto the disk inode.
	 */
	ei->i_disksize = inode->i_size;

	if (last_block == max_block) {
		/*
		 * It is unnecessary to free any data blocks if last_block is
		 * equal to the indirect block limit.
		 */
		return;
	} else if (n == 1) {		/* direct blocks */
		ext4_free_data(handle, inode, NULL, i_data+offsets[0],
			       i_data + EXT4_NDIR_BLOCKS);
		goto do_indirects;
	}

	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
	/* Kill the top of shared branch (not detached) */
	if (nr) {
		if (partial == chain) {
			/* Shared branch grows from the inode */
			ext4_free_branches(handle, inode, NULL,
					   &nr, &nr+1, (chain+n-1) - partial);
			*partial->p = 0;
			/*
			 * We mark the inode dirty prior to restart,
			 * and prior to stop.  No need for it here.
			 */
		} else {
			/* Shared branch grows from an indirect block */
			BUFFER_TRACE(partial->bh, "get_write_access");
			ext4_free_branches(handle, inode, partial->bh,
					partial->p,
					partial->p+1, (chain+n-1) - partial);
		}
	}
	/* Clear the ends of indirect blocks on the shared branch */
	while (partial > chain) {
		ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
				   (__le32*)partial->bh->b_data+addr_per_block,
				   (chain+n-1) - partial);
		BUFFER_TRACE(partial->bh, "call brelse");
		brelse(partial->bh);
		partial--;
	}
do_indirects:
	/* Kill the remaining (whole) subtrees */
	switch (offsets[0]) {
	default:
		nr = i_data[EXT4_IND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
			i_data[EXT4_IND_BLOCK] = 0;
		}
	case EXT4_IND_BLOCK:
		nr = i_data[EXT4_DIND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
			i_data[EXT4_DIND_BLOCK] = 0;
		}
	case EXT4_DIND_BLOCK:
		nr = i_data[EXT4_TIND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
			i_data[EXT4_TIND_BLOCK] = 0;
		}
	case EXT4_TIND_BLOCK:
		;
	}
}

/**
 *	ext4_ind_remove_space - remove space from the range
 *	@handle: JBD handle for this transaction
 *	@inode:	inode we are dealing with
 *	@start:	First block to remove
 *	@end:	One block after the last block to remove (exclusive)
 *
 *	Free the blocks in the defined range (end is exclusive endpoint of
 *	range). This is used by ext4_punch_hole().
 */
int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
			  ext4_lblk_t start, ext4_lblk_t end)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	__le32 *i_data = ei->i_data;
	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
	ext4_lblk_t offsets[4], offsets2[4];
	Indirect chain[4], chain2[4];
	Indirect *partial, *partial2;
	ext4_lblk_t max_block;
	__le32 nr = 0, nr2 = 0;
	int n = 0, n2 = 0;
	unsigned blocksize = inode->i_sb->s_blocksize;

	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
	if (end >= max_block)
		end = max_block;
	if ((start >= end) || (start > max_block))
		return 0;

	n = ext4_block_to_path(inode, start, offsets, NULL);
	n2 = ext4_block_to_path(inode, end, offsets2, NULL);

	BUG_ON(n > n2);

	if ((n == 1) && (n == n2)) {
		/* We're punching only within direct block range */
		ext4_free_data(handle, inode, NULL, i_data + offsets[0],
			       i_data + offsets2[0]);
		return 0;
	} else if (n2 > n) {
		/*
		 * Start and end are on a different levels so we're going to
		 * free partial block at start, and partial block at end of
		 * the range. If there are some levels in between then
		 * do_indirects label will take care of that.
		 */

		if (n == 1) {
			/*
			 * Start is at the direct block level, free
			 * everything to the end of the level.
			 */
			ext4_free_data(handle, inode, NULL, i_data + offsets[0],
				       i_data + EXT4_NDIR_BLOCKS);
			goto end_range;
		}


		partial = ext4_find_shared(inode, n, offsets, chain, &nr);
		if (nr) {
			if (partial == chain) {
				/* Shared branch grows from the inode */
				ext4_free_branches(handle, inode, NULL,
					   &nr, &nr+1, (chain+n-1) - partial);
				*partial->p = 0;
			} else {
				/* Shared branch grows from an indirect block */
				BUFFER_TRACE(partial->bh, "get_write_access");
				ext4_free_branches(handle, inode, partial->bh,
					partial->p,
					partial->p+1, (chain+n-1) - partial);
			}
		}

		/*
		 * Clear the ends of indirect blocks on the shared branch
		 * at the start of the range
		 */
		while (partial > chain) {
			ext4_free_branches(handle, inode, partial->bh,
				partial->p + 1,
				(__le32 *)partial->bh->b_data+addr_per_block,
				(chain+n-1) - partial);
			BUFFER_TRACE(partial->bh, "call brelse");
			brelse(partial->bh);
			partial--;
		}

end_range:
		partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
		if (nr2) {
			if (partial2 == chain2) {
				/*
				 * Remember, end is exclusive so here we're at
				 * the start of the next level we're not going
				 * to free. Everything was covered by the start
				 * of the range.
				 */
				goto do_indirects;
			}
		} else {
			/*
			 * ext4_find_shared returns Indirect structure which
			 * points to the last element which should not be
			 * removed by truncate. But this is end of the range
			 * in punch_hole so we need to point to the next element
			 */
			partial2->p++;
		}

		/*
		 * Clear the ends of indirect blocks on the shared branch
		 * at the end of the range
		 */
		while (partial2 > chain2) {
			ext4_free_branches(handle, inode, partial2->bh,
					   (__le32 *)partial2->bh->b_data,
					   partial2->p,
					   (chain2+n2-1) - partial2);
			BUFFER_TRACE(partial2->bh, "call brelse");
			brelse(partial2->bh);
			partial2--;
		}
		goto do_indirects;
	}

	/* Punch happened within the same level (n == n2) */
	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
	partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);

	/* Free top, but only if partial2 isn't its subtree. */
	if (nr) {
		int level = min(partial - chain, partial2 - chain2);
		int i;
		int subtree = 1;

		for (i = 0; i <= level; i++) {
			if (offsets[i] != offsets2[i]) {
				subtree = 0;
				break;
			}
		}

		if (!subtree) {
			if (partial == chain) {
				/* Shared branch grows from the inode */
				ext4_free_branches(handle, inode, NULL,
						   &nr, &nr+1,
						   (chain+n-1) - partial);
				*partial->p = 0;
			} else {
				/* Shared branch grows from an indirect block */
				BUFFER_TRACE(partial->bh, "get_write_access");
				ext4_free_branches(handle, inode, partial->bh,
						   partial->p,
						   partial->p+1,
						   (chain+n-1) - partial);
			}
		}
	}

	if (!nr2) {
		/*
		 * ext4_find_shared returns Indirect structure which
		 * points to the last element which should not be
		 * removed by truncate. But this is end of the range
		 * in punch_hole so we need to point to the next element
		 */
		partial2->p++;
	}

	while (partial > chain || partial2 > chain2) {
		int depth = (chain+n-1) - partial;
		int depth2 = (chain2+n2-1) - partial2;

		if (partial > chain && partial2 > chain2 &&
		    partial->bh->b_blocknr == partial2->bh->b_blocknr) {
			/*
			 * We've converged on the same block. Clear the range,
			 * then we're done.
			 */
			ext4_free_branches(handle, inode, partial->bh,
					   partial->p + 1,
					   partial2->p,
					   (chain+n-1) - partial);
			BUFFER_TRACE(partial->bh, "call brelse");
			brelse(partial->bh);
			BUFFER_TRACE(partial2->bh, "call brelse");
			brelse(partial2->bh);
			return 0;
		}

		/*
		 * The start and end partial branches may not be at the same
		 * level even though the punch happened within one level. So, we
		 * give them a chance to arrive at the same level, then walk
		 * them in step with each other until we converge on the same
		 * block.
		 */
		if (partial > chain && depth <= depth2) {
			ext4_free_branches(handle, inode, partial->bh,
					   partial->p + 1,
					   (__le32 *)partial->bh->b_data+addr_per_block,
					   (chain+n-1) - partial);
			BUFFER_TRACE(partial->bh, "call brelse");
			brelse(partial->bh);
			partial--;
		}
		if (partial2 > chain2 && depth2 <= depth) {
			ext4_free_branches(handle, inode, partial2->bh,
					   (__le32 *)partial2->bh->b_data,
					   partial2->p,
					   (chain2+n2-1) - partial2);
			BUFFER_TRACE(partial2->bh, "call brelse");
			brelse(partial2->bh);
			partial2--;
		}
	}
	return 0;

do_indirects:
	/* Kill the remaining (whole) subtrees */
	switch (offsets[0]) {
	default:
		if (++n >= n2)
			return 0;
		nr = i_data[EXT4_IND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
			i_data[EXT4_IND_BLOCK] = 0;
		}
	case EXT4_IND_BLOCK:
		if (++n >= n2)
			return 0;
		nr = i_data[EXT4_DIND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
			i_data[EXT4_DIND_BLOCK] = 0;
		}
	case EXT4_DIND_BLOCK:
		if (++n >= n2)
			return 0;
		nr = i_data[EXT4_TIND_BLOCK];
		if (nr) {
			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
			i_data[EXT4_TIND_BLOCK] = 0;
		}
	case EXT4_TIND_BLOCK:
		;
	}
	return 0;
}