ialloc.c 21.6 KB
Newer Older
1
/*
2
 *  linux/fs/ext4/ialloc.c
3 4 5 6 7 8 9 10 11 12 13 14 15 16
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  BSD ufs-inspired inode and directory allocation by
 *  Stephen Tweedie (sct@redhat.com), 1993
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/time.h>
#include <linux/fs.h>
17
#include <linux/jbd2.h>
18
#include <linux/ext4_fs.h>
19
#include <linux/ext4_jbd2.h>
20 21 22 23 24 25
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include <linux/bitops.h>
26
#include <linux/blkdev.h>
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
#include <asm/byteorder.h>

#include "xattr.h"
#include "acl.h"

/*
 * ialloc.c contains the inodes allocation and deallocation routines
 */

/*
 * The free inodes are managed by bitmaps.  A file system contains several
 * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
 * block for inodes, N blocks for the inode table and data blocks.
 *
 * The file system contains group descriptors which are located after the
 * super block.  Each descriptor contains the number of the bitmap block and
 * the free blocks count in the block.
 */


/*
 * Read the inode allocation bitmap for a given block_group, reading
 * into the specified slot in the superblock's bitmap cache.
 *
 * Return buffer_head of bitmap on success or NULL.
 */
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
56
	struct ext4_group_desc *desc;
57 58
	struct buffer_head *bh = NULL;

59
	desc = ext4_get_group_desc(sb, block_group, NULL);
60 61 62 63 64
	if (!desc)
		goto error_out;

	bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap));
	if (!bh)
65
		ext4_error(sb, "read_inode_bitmap",
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
			    "Cannot read inode bitmap - "
			    "block_group = %lu, inode_bitmap = %u",
			    block_group, le32_to_cpu(desc->bg_inode_bitmap));
error_out:
	return bh;
}

/*
 * NOTE! When we get the inode, we're the only people
 * that have access to it, and as such there are no
 * race conditions we have to worry about. The inode
 * is not on the hash-lists, and it cannot be reached
 * through the filesystem because the directory entry
 * has been deleted earlier.
 *
 * HOWEVER: we must make sure that we get no aliases,
 * which means that we have to call "clear_inode()"
 * _before_ we mark the inode not in use in the inode
 * bitmaps. Otherwise a newly created file might use
 * the same inode number (not actually the same pointer
 * though), and then we'd have two inodes sharing the
 * same inode number and space on the harddisk.
 */
89
void ext4_free_inode (handle_t *handle, struct inode * inode)
90 91 92 93 94 95 96 97
{
	struct super_block * sb = inode->i_sb;
	int is_directory;
	unsigned long ino;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	unsigned long block_group;
	unsigned long bit;
98 99 100
	struct ext4_group_desc * gdp;
	struct ext4_super_block * es;
	struct ext4_sb_info *sbi;
101 102 103
	int fatal = 0, err;

	if (atomic_read(&inode->i_count) > 1) {
104
		printk ("ext4_free_inode: inode has count=%d\n",
105 106 107 108
					atomic_read(&inode->i_count));
		return;
	}
	if (inode->i_nlink) {
109
		printk ("ext4_free_inode: inode has nlink=%d\n",
110 111 112 113
			inode->i_nlink);
		return;
	}
	if (!sb) {
114
		printk("ext4_free_inode: inode on nonexistent device\n");
115 116
		return;
	}
117
	sbi = EXT4_SB(sb);
118 119

	ino = inode->i_ino;
120
	ext4_debug ("freeing inode %lu\n", ino);
121 122 123 124 125 126

	/*
	 * Note: we must free any quota before locking the superblock,
	 * as writing the quota to disk may need the lock as well.
	 */
	DQUOT_INIT(inode);
127
	ext4_xattr_delete_inode(handle, inode);
128 129 130 131 132 133 134 135
	DQUOT_FREE_INODE(inode);
	DQUOT_DROP(inode);

	is_directory = S_ISDIR(inode->i_mode);

	/* Do this BEFORE marking the inode not in use or returning an error */
	clear_inode (inode);

136 137 138
	es = EXT4_SB(sb)->s_es;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error (sb, "ext4_free_inode",
139 140 141
			    "reserved or nonexistent inode %lu", ino);
		goto error_return;
	}
142 143
	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
144 145 146 147 148
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;

	BUFFER_TRACE(bitmap_bh, "get_write_access");
149
	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
150 151 152 153
	if (fatal)
		goto error_return;

	/* Ok, now we can actually update the inode bitmaps.. */
154
	if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
155
					bit, bitmap_bh->b_data))
156
		ext4_error (sb, "ext4_free_inode",
157 158
			      "bit already cleared for inode %lu", ino);
	else {
159
		gdp = ext4_get_group_desc (sb, block_group, &bh2);
160 161

		BUFFER_TRACE(bh2, "get_write_access");
162
		fatal = ext4_journal_get_write_access(handle, bh2);
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177
		if (fatal) goto error_return;

		if (gdp) {
			spin_lock(sb_bgl_lock(sbi, block_group));
			gdp->bg_free_inodes_count = cpu_to_le16(
				le16_to_cpu(gdp->bg_free_inodes_count) + 1);
			if (is_directory)
				gdp->bg_used_dirs_count = cpu_to_le16(
				  le16_to_cpu(gdp->bg_used_dirs_count) - 1);
			spin_unlock(sb_bgl_lock(sbi, block_group));
			percpu_counter_inc(&sbi->s_freeinodes_counter);
			if (is_directory)
				percpu_counter_dec(&sbi->s_dirs_counter);

		}
178 179
		BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
		err = ext4_journal_dirty_metadata(handle, bh2);
180 181
		if (!fatal) fatal = err;
	}
182 183
	BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
184 185 186 187 188
	if (!fatal)
		fatal = err;
	sb->s_dirt = 1;
error_return:
	brelse(bitmap_bh);
189
	ext4_std_error(sb, fatal);
190 191 192 193 194 195 196 197 198 199 200 201 202 203
}

/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory\'s block
 * group to find a free inode.
 */
static int find_group_dir(struct super_block *sb, struct inode *parent)
{
204
	int ngroups = EXT4_SB(sb)->s_groups_count;
205
	unsigned int freei, avefreei;
206
	struct ext4_group_desc *desc, *best_desc = NULL;
207 208 209
	struct buffer_head *bh;
	int group, best_group = -1;

210
	freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
211 212 213
	avefreei = freei / ngroups;

	for (group = 0; group < ngroups; group++) {
214
		desc = ext4_get_group_desc (sb, group, &bh);
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
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
			continue;
		if (!best_desc ||
		    (le16_to_cpu(desc->bg_free_blocks_count) >
		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
			best_group = group;
			best_desc = desc;
		}
	}
	return best_group;
}

/*
 * Orlov's allocator for directories.
 *
 * We always try to spread first-level directories.
 *
 * If there are blockgroups with both free inodes and free blocks counts
 * not worse than average we return one with smallest directory count.
 * Otherwise we simply return a random group.
 *
 * For the rest rules look so:
 *
 * It's OK to put directory into a group unless
 * it has too many directories already (max_dirs) or
 * it has too few free inodes left (min_inodes) or
 * it has too few free blocks left (min_blocks) or
 * it's already running too large debt (max_debt).
 * Parent's group is prefered, if it doesn't satisfy these
 * conditions we search cyclically through the rest. If none
 * of the groups look good we just look for a group with more
 * free inodes than average (starting at parent's group).
 *
 * Debt is incremented each time we allocate a directory and decremented
 * when we allocate an inode, within 0--255.
 */

#define INODE_COST 64
#define BLOCK_COST 256

static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
259 260 261
	int parent_group = EXT4_I(parent)->i_block_group;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
262
	int ngroups = sbi->s_groups_count;
263
	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
264
	unsigned int freei, avefreei;
265 266
	ext4_fsblk_t freeb, avefreeb;
	ext4_fsblk_t blocks_per_dir;
267 268
	unsigned int ndirs;
	int max_debt, max_dirs, min_inodes;
269
	ext4_grpblk_t min_blocks;
270
	int group = -1, i;
271
	struct ext4_group_desc *desc;
272 273 274 275 276
	struct buffer_head *bh;

	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
	avefreei = freei / ngroups;
	freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
277 278
	avefreeb = freeb;
	sector_div(avefreeb, ngroups);
279 280 281
	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);

	if ((parent == sb->s_root->d_inode) ||
282
	    (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
283 284 285 286 287 288 289
		int best_ndir = inodes_per_group;
		int best_group = -1;

		get_random_bytes(&group, sizeof(group));
		parent_group = (unsigned)group % ngroups;
		for (i = 0; i < ngroups; i++) {
			group = (parent_group + i) % ngroups;
290
			desc = ext4_get_group_desc (sb, group, &bh);
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306
			if (!desc || !desc->bg_free_inodes_count)
				continue;
			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
				continue;
			if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
				continue;
			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
				continue;
			best_group = group;
			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
		}
		if (best_group >= 0)
			return best_group;
		goto fallback;
	}

307 308
	blocks_per_dir = le32_to_cpu(es->s_blocks_count) - freeb;
	sector_div(blocks_per_dir, ndirs);
309 310 311

	max_dirs = ndirs / ngroups + inodes_per_group / 16;
	min_inodes = avefreei - inodes_per_group / 4;
312
	min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;
313

314 315
	max_debt = EXT4_BLOCKS_PER_GROUP(sb);
	sector_div(max_debt, max(blocks_per_dir, (ext4_fsblk_t)BLOCK_COST));
316 317 318 319 320 321 322 323 324
	if (max_debt * INODE_COST > inodes_per_group)
		max_debt = inodes_per_group / INODE_COST;
	if (max_debt > 255)
		max_debt = 255;
	if (max_debt == 0)
		max_debt = 1;

	for (i = 0; i < ngroups; i++) {
		group = (parent_group + i) % ngroups;
325
		desc = ext4_get_group_desc (sb, group, &bh);
326 327 328 329 330 331 332 333 334 335 336 337 338 339
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
			continue;
		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
			continue;
		return group;
	}

fallback:
	for (i = 0; i < ngroups; i++) {
		group = (parent_group + i) % ngroups;
340
		desc = ext4_get_group_desc (sb, group, &bh);
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
		if (!desc || !desc->bg_free_inodes_count)
			continue;
		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
			return group;
	}

	if (avefreei) {
		/*
		 * The free-inodes counter is approximate, and for really small
		 * filesystems the above test can fail to find any blockgroups
		 */
		avefreei = 0;
		goto fallback;
	}

	return -1;
}

static int find_group_other(struct super_block *sb, struct inode *parent)
{
361 362 363
	int parent_group = EXT4_I(parent)->i_block_group;
	int ngroups = EXT4_SB(sb)->s_groups_count;
	struct ext4_group_desc *desc;
364 365 366 367 368 369 370
	struct buffer_head *bh;
	int group, i;

	/*
	 * Try to place the inode in its parent directory
	 */
	group = parent_group;
371
	desc = ext4_get_group_desc (sb, group, &bh);
372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394
	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
			le16_to_cpu(desc->bg_free_blocks_count))
		return group;

	/*
	 * We're going to place this inode in a different blockgroup from its
	 * parent.  We want to cause files in a common directory to all land in
	 * the same blockgroup.  But we want files which are in a different
	 * directory which shares a blockgroup with our parent to land in a
	 * different blockgroup.
	 *
	 * So add our directory's i_ino into the starting point for the hash.
	 */
	group = (group + parent->i_ino) % ngroups;

	/*
	 * Use a quadratic hash to find a group with a free inode and some free
	 * blocks.
	 */
	for (i = 1; i < ngroups; i <<= 1) {
		group += i;
		if (group >= ngroups)
			group -= ngroups;
395
		desc = ext4_get_group_desc (sb, group, &bh);
396 397 398 399 400 401 402 403 404 405 406 407 408
		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
				le16_to_cpu(desc->bg_free_blocks_count))
			return group;
	}

	/*
	 * That failed: try linear search for a free inode, even if that group
	 * has no free blocks.
	 */
	group = parent_group;
	for (i = 0; i < ngroups; i++) {
		if (++group >= ngroups)
			group = 0;
409
		desc = ext4_get_group_desc (sb, group, &bh);
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
			return group;
	}

	return -1;
}

/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
427
struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
428 429 430 431 432 433 434
{
	struct super_block *sb;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	int group;
	unsigned long ino = 0;
	struct inode * inode;
435 436 437 438
	struct ext4_group_desc * gdp = NULL;
	struct ext4_super_block * es;
	struct ext4_inode_info *ei;
	struct ext4_sb_info *sbi;
439 440 441 442 443 444 445 446 447 448 449 450
	int err = 0;
	struct inode *ret;
	int i;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
451
	ei = EXT4_I(inode);
452

453
	sbi = EXT4_SB(sb);
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469
	es = sbi->s_es;
	if (S_ISDIR(mode)) {
		if (test_opt (sb, OLDALLOC))
			group = find_group_dir(sb, dir);
		else
			group = find_group_orlov(sb, dir);
	} else
		group = find_group_other(sb, dir);

	err = -ENOSPC;
	if (group == -1)
		goto out;

	for (i = 0; i < sbi->s_groups_count; i++) {
		err = -EIO;

470
		gdp = ext4_get_group_desc(sb, group, &bh2);
471 472 473 474 475 476 477 478 479 480 481
		if (!gdp)
			goto fail;

		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, group);
		if (!bitmap_bh)
			goto fail;

		ino = 0;

repeat_in_this_group:
482 483 484
		ino = ext4_find_next_zero_bit((unsigned long *)
				bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
		if (ino < EXT4_INODES_PER_GROUP(sb)) {
485 486

			BUFFER_TRACE(bitmap_bh, "get_write_access");
487
			err = ext4_journal_get_write_access(handle, bitmap_bh);
488 489 490
			if (err)
				goto fail;

491
			if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
492 493 494
						ino, bitmap_bh->b_data)) {
				/* we won it */
				BUFFER_TRACE(bitmap_bh,
495 496
					"call ext4_journal_dirty_metadata");
				err = ext4_journal_dirty_metadata(handle,
497 498 499 500 501 502
								bitmap_bh);
				if (err)
					goto fail;
				goto got;
			}
			/* we lost it */
503
			jbd2_journal_release_buffer(handle, bitmap_bh);
504

505
			if (++ino < EXT4_INODES_PER_GROUP(sb))
506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
				goto repeat_in_this_group;
		}

		/*
		 * This case is possible in concurrent environment.  It is very
		 * rare.  We cannot repeat the find_group_xxx() call because
		 * that will simply return the same blockgroup, because the
		 * group descriptor metadata has not yet been updated.
		 * So we just go onto the next blockgroup.
		 */
		if (++group == sbi->s_groups_count)
			group = 0;
	}
	err = -ENOSPC;
	goto out;

got:
523 524 525
	ino += group * EXT4_INODES_PER_GROUP(sb) + 1;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error (sb, "ext4_new_inode",
526 527 528 529 530 531 532
			    "reserved inode or inode > inodes count - "
			    "block_group = %d, inode=%lu", group, ino);
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
533
	err = ext4_journal_get_write_access(handle, bh2);
534 535 536 537 538 539 540 541 542
	if (err) goto fail;
	spin_lock(sb_bgl_lock(sbi, group));
	gdp->bg_free_inodes_count =
		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
	if (S_ISDIR(mode)) {
		gdp->bg_used_dirs_count =
			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
	}
	spin_unlock(sb_bgl_lock(sbi, group));
543 544
	BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bh2);
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
	if (err) goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);
	sb->s_dirt = 1;

	inode->i_uid = current->fsuid;
	if (test_opt (sb, GRPID))
		inode->i_gid = dir->i_gid;
	else if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current->fsgid;
	inode->i_mode = mode;

	inode->i_ino = ino;
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

572
	ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
573
	if (S_ISLNK(mode))
574
		ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
575 576
	/* dirsync only applies to directories */
	if (!S_ISDIR(mode))
577 578
		ei->i_flags &= ~EXT4_DIRSYNC_FL;
#ifdef EXT4_FRAGMENTS
579 580 581 582 583 584 585 586 587 588
	ei->i_faddr = 0;
	ei->i_frag_no = 0;
	ei->i_frag_size = 0;
#endif
	ei->i_file_acl = 0;
	ei->i_dir_acl = 0;
	ei->i_dtime = 0;
	ei->i_block_alloc_info = NULL;
	ei->i_block_group = group;

589
	ext4_set_inode_flags(inode);
590 591 592 593 594 595 596
	if (IS_DIRSYNC(inode))
		handle->h_sync = 1;
	insert_inode_hash(inode);
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

597
	ei->i_state = EXT4_STATE_NEW;
598
	ei->i_extra_isize =
599 600
		(EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) ?
		sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE : 0;
601 602 603 604 605 606 607

	ret = inode;
	if(DQUOT_ALLOC_INODE(inode)) {
		err = -EDQUOT;
		goto fail_drop;
	}

608
	err = ext4_init_acl(handle, inode, dir);
609 610 611
	if (err)
		goto fail_free_drop;

612
	err = ext4_init_security(handle,inode, dir);
613 614 615
	if (err)
		goto fail_free_drop;

616
	err = ext4_mark_inode_dirty(handle, inode);
617
	if (err) {
618
		ext4_std_error(sb, err);
619 620
		goto fail_free_drop;
	}
A
Alex Tomas 已提交
621 622 623 624 625 626 627 628 629 630 631
	if (test_opt(sb, EXTENTS)) {
		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
		ext4_ext_tree_init(handle, inode);
		if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
			err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
			if (err) goto fail;
			EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
			BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
			err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
		}
	}
632

633
	ext4_debug("allocating inode %lu\n", inode->i_ino);
634 635
	goto really_out;
fail:
636
	ext4_std_error(sb, err);
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(bitmap_bh);
	return ret;

fail_free_drop:
	DQUOT_FREE_INODE(inode);

fail_drop:
	DQUOT_DROP(inode);
	inode->i_flags |= S_NOQUOTA;
	inode->i_nlink = 0;
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}

/* Verify that we are loading a valid orphan from disk */
657
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
658
{
659
	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
660 661 662 663 664 665 666
	unsigned long block_group;
	int bit;
	struct buffer_head *bitmap_bh = NULL;
	struct inode *inode = NULL;

	/* Error cases - e2fsck has already cleaned up for us */
	if (ino > max_ino) {
667
		ext4_warning(sb, __FUNCTION__,
668 669 670 671
			     "bad orphan ino %lu!  e2fsck was run?", ino);
		goto out;
	}

672 673
	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
674 675
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh) {
676
		ext4_warning(sb, __FUNCTION__,
677 678 679 680 681 682 683 684
			     "inode bitmap error for orphan %lu", ino);
		goto out;
	}

	/* Having the inode bit set should be a 100% indicator that this
	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
	 * inodes that were being truncated, so we can't check i_nlink==0.
	 */
685
	if (!ext4_test_bit(bit, bitmap_bh->b_data) ||
686 687
			!(inode = iget(sb, ino)) || is_bad_inode(inode) ||
			NEXT_ORPHAN(inode) > max_ino) {
688
		ext4_warning(sb, __FUNCTION__,
689
			     "bad orphan inode %lu!  e2fsck was run?", ino);
690
		printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
691
		       bit, (unsigned long long)bitmap_bh->b_blocknr,
692
		       ext4_test_bit(bit, bitmap_bh->b_data));
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711
		printk(KERN_NOTICE "inode=%p\n", inode);
		if (inode) {
			printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
			       is_bad_inode(inode));
			printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
			       NEXT_ORPHAN(inode));
			printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
		}
		/* Avoid freeing blocks if we got a bad deleted inode */
		if (inode && inode->i_nlink == 0)
			inode->i_blocks = 0;
		iput(inode);
		inode = NULL;
	}
out:
	brelse(bitmap_bh);
	return inode;
}

712
unsigned long ext4_count_free_inodes (struct super_block * sb)
713 714
{
	unsigned long desc_count;
715
	struct ext4_group_desc *gdp;
716
	int i;
717 718
#ifdef EXT4FS_DEBUG
	struct ext4_super_block *es;
719 720 721
	unsigned long bitmap_count, x;
	struct buffer_head *bitmap_bh = NULL;

722
	es = EXT4_SB(sb)->s_es;
723 724 725
	desc_count = 0;
	bitmap_count = 0;
	gdp = NULL;
726 727
	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		gdp = ext4_get_group_desc (sb, i, NULL);
728 729 730 731 732 733 734 735
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, i);
		if (!bitmap_bh)
			continue;

736
		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
737 738 739 740 741
		printk("group %d: stored = %d, counted = %lu\n",
			i, le16_to_cpu(gdp->bg_free_inodes_count), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
742
	printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
743 744 745 746
		le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
	return desc_count;
#else
	desc_count = 0;
747 748
	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		gdp = ext4_get_group_desc (sb, i, NULL);
749 750 751 752 753 754 755 756 757 758
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
		cond_resched();
	}
	return desc_count;
#endif
}

/* Called at mount-time, super-block is locked */
759
unsigned long ext4_count_dirs (struct super_block * sb)
760 761 762 763
{
	unsigned long count = 0;
	int i;

764 765
	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
		struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
766 767 768 769 770 771 772
		if (!gdp)
			continue;
		count += le16_to_cpu(gdp->bg_used_dirs_count);
	}
	return count;
}