| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* | 
 | 2 |  *  linux/fs/ext2/ialloc.c | 
 | 3 |  * | 
 | 4 |  * Copyright (C) 1992, 1993, 1994, 1995 | 
 | 5 |  * Remy Card (card@masi.ibp.fr) | 
 | 6 |  * Laboratoire MASI - Institut Blaise Pascal | 
 | 7 |  * Universite Pierre et Marie Curie (Paris VI) | 
 | 8 |  * | 
 | 9 |  *  BSD ufs-inspired inode and directory allocation by  | 
 | 10 |  *  Stephen Tweedie (sct@dcs.ed.ac.uk), 1993 | 
 | 11 |  *  Big-endian to little-endian byte-swapping/bitmaps by | 
 | 12 |  *        David S. Miller (davem@caip.rutgers.edu), 1995 | 
 | 13 |  */ | 
 | 14 |  | 
 | 15 | #include <linux/config.h> | 
 | 16 | #include <linux/quotaops.h> | 
 | 17 | #include <linux/sched.h> | 
 | 18 | #include <linux/backing-dev.h> | 
 | 19 | #include <linux/buffer_head.h> | 
 | 20 | #include <linux/random.h> | 
 | 21 | #include "ext2.h" | 
 | 22 | #include "xattr.h" | 
 | 23 | #include "acl.h" | 
 | 24 |  | 
 | 25 | /* | 
 | 26 |  * ialloc.c contains the inodes allocation and deallocation routines | 
 | 27 |  */ | 
 | 28 |  | 
 | 29 | /* | 
 | 30 |  * The free inodes are managed by bitmaps.  A file system contains several | 
 | 31 |  * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap | 
 | 32 |  * block for inodes, N blocks for the inode table and data blocks. | 
 | 33 |  * | 
 | 34 |  * The file system contains group descriptors which are located after the | 
 | 35 |  * super block.  Each descriptor contains the number of the bitmap block and | 
 | 36 |  * the free blocks count in the block. | 
 | 37 |  */ | 
 | 38 |  | 
 | 39 |  | 
 | 40 | /* | 
 | 41 |  * Read the inode allocation bitmap for a given block_group, reading | 
 | 42 |  * into the specified slot in the superblock's bitmap cache. | 
 | 43 |  * | 
 | 44 |  * Return buffer_head of bitmap on success or NULL. | 
 | 45 |  */ | 
 | 46 | static struct buffer_head * | 
 | 47 | read_inode_bitmap(struct super_block * sb, unsigned long block_group) | 
 | 48 | { | 
 | 49 | 	struct ext2_group_desc *desc; | 
 | 50 | 	struct buffer_head *bh = NULL; | 
 | 51 |  | 
 | 52 | 	desc = ext2_get_group_desc(sb, block_group, NULL); | 
 | 53 | 	if (!desc) | 
 | 54 | 		goto error_out; | 
 | 55 |  | 
 | 56 | 	bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap)); | 
 | 57 | 	if (!bh) | 
 | 58 | 		ext2_error(sb, "read_inode_bitmap", | 
 | 59 | 			    "Cannot read inode bitmap - " | 
 | 60 | 			    "block_group = %lu, inode_bitmap = %u", | 
 | 61 | 			    block_group, le32_to_cpu(desc->bg_inode_bitmap)); | 
 | 62 | error_out: | 
 | 63 | 	return bh; | 
 | 64 | } | 
 | 65 |  | 
 | 66 | static void ext2_release_inode(struct super_block *sb, int group, int dir) | 
 | 67 | { | 
 | 68 | 	struct ext2_group_desc * desc; | 
 | 69 | 	struct buffer_head *bh; | 
 | 70 |  | 
 | 71 | 	desc = ext2_get_group_desc(sb, group, &bh); | 
 | 72 | 	if (!desc) { | 
 | 73 | 		ext2_error(sb, "ext2_release_inode", | 
 | 74 | 			"can't get descriptor for group %d", group); | 
 | 75 | 		return; | 
 | 76 | 	} | 
 | 77 |  | 
 | 78 | 	spin_lock(sb_bgl_lock(EXT2_SB(sb), group)); | 
 | 79 | 	desc->bg_free_inodes_count = | 
 | 80 | 		cpu_to_le16(le16_to_cpu(desc->bg_free_inodes_count) + 1); | 
 | 81 | 	if (dir) | 
 | 82 | 		desc->bg_used_dirs_count = | 
 | 83 | 			cpu_to_le16(le16_to_cpu(desc->bg_used_dirs_count) - 1); | 
 | 84 | 	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); | 
 | 85 | 	if (dir) | 
 | 86 | 		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); | 
 | 87 | 	sb->s_dirt = 1; | 
 | 88 | 	mark_buffer_dirty(bh); | 
 | 89 | } | 
 | 90 |  | 
 | 91 | /* | 
 | 92 |  * NOTE! When we get the inode, we're the only people | 
 | 93 |  * that have access to it, and as such there are no | 
 | 94 |  * race conditions we have to worry about. The inode | 
 | 95 |  * is not on the hash-lists, and it cannot be reached | 
 | 96 |  * through the filesystem because the directory entry | 
 | 97 |  * has been deleted earlier. | 
 | 98 |  * | 
 | 99 |  * HOWEVER: we must make sure that we get no aliases, | 
 | 100 |  * which means that we have to call "clear_inode()" | 
 | 101 |  * _before_ we mark the inode not in use in the inode | 
 | 102 |  * bitmaps. Otherwise a newly created file might use | 
 | 103 |  * the same inode number (not actually the same pointer | 
 | 104 |  * though), and then we'd have two inodes sharing the | 
 | 105 |  * same inode number and space on the harddisk. | 
 | 106 |  */ | 
 | 107 | void ext2_free_inode (struct inode * inode) | 
 | 108 | { | 
 | 109 | 	struct super_block * sb = inode->i_sb; | 
 | 110 | 	int is_directory; | 
 | 111 | 	unsigned long ino; | 
 | 112 | 	struct buffer_head *bitmap_bh = NULL; | 
 | 113 | 	unsigned long block_group; | 
 | 114 | 	unsigned long bit; | 
 | 115 | 	struct ext2_super_block * es; | 
 | 116 |  | 
 | 117 | 	ino = inode->i_ino; | 
 | 118 | 	ext2_debug ("freeing inode %lu\n", ino); | 
 | 119 |  | 
 | 120 | 	/* | 
 | 121 | 	 * Note: we must free any quota before locking the superblock, | 
 | 122 | 	 * as writing the quota to disk may need the lock as well. | 
 | 123 | 	 */ | 
 | 124 | 	if (!is_bad_inode(inode)) { | 
 | 125 | 		/* Quota is already initialized in iput() */ | 
 | 126 | 		ext2_xattr_delete_inode(inode); | 
 | 127 | 	    	DQUOT_FREE_INODE(inode); | 
 | 128 | 		DQUOT_DROP(inode); | 
 | 129 | 	} | 
 | 130 |  | 
 | 131 | 	es = EXT2_SB(sb)->s_es; | 
 | 132 | 	is_directory = S_ISDIR(inode->i_mode); | 
 | 133 |  | 
 | 134 | 	/* Do this BEFORE marking the inode not in use or returning an error */ | 
 | 135 | 	clear_inode (inode); | 
 | 136 |  | 
 | 137 | 	if (ino < EXT2_FIRST_INO(sb) || | 
 | 138 | 	    ino > le32_to_cpu(es->s_inodes_count)) { | 
 | 139 | 		ext2_error (sb, "ext2_free_inode", | 
 | 140 | 			    "reserved or nonexistent inode %lu", ino); | 
 | 141 | 		goto error_return; | 
 | 142 | 	} | 
 | 143 | 	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb); | 
 | 144 | 	bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb); | 
 | 145 | 	brelse(bitmap_bh); | 
 | 146 | 	bitmap_bh = read_inode_bitmap(sb, block_group); | 
 | 147 | 	if (!bitmap_bh) | 
 | 148 | 		goto error_return; | 
 | 149 |  | 
 | 150 | 	/* Ok, now we can actually update the inode bitmaps.. */ | 
 | 151 | 	if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group), | 
 | 152 | 				bit, (void *) bitmap_bh->b_data)) | 
 | 153 | 		ext2_error (sb, "ext2_free_inode", | 
 | 154 | 			      "bit already cleared for inode %lu", ino); | 
 | 155 | 	else | 
 | 156 | 		ext2_release_inode(sb, block_group, is_directory); | 
 | 157 | 	mark_buffer_dirty(bitmap_bh); | 
 | 158 | 	if (sb->s_flags & MS_SYNCHRONOUS) | 
 | 159 | 		sync_dirty_buffer(bitmap_bh); | 
 | 160 | error_return: | 
 | 161 | 	brelse(bitmap_bh); | 
 | 162 | } | 
 | 163 |  | 
 | 164 | /* | 
 | 165 |  * We perform asynchronous prereading of the new inode's inode block when | 
 | 166 |  * we create the inode, in the expectation that the inode will be written | 
 | 167 |  * back soon.  There are two reasons: | 
 | 168 |  * | 
 | 169 |  * - When creating a large number of files, the async prereads will be | 
 | 170 |  *   nicely merged into large reads | 
 | 171 |  * - When writing out a large number of inodes, we don't need to keep on | 
 | 172 |  *   stalling the writes while we read the inode block. | 
 | 173 |  * | 
 | 174 |  * FIXME: ext2_get_group_desc() needs to be simplified. | 
 | 175 |  */ | 
 | 176 | static void ext2_preread_inode(struct inode *inode) | 
 | 177 | { | 
 | 178 | 	unsigned long block_group; | 
 | 179 | 	unsigned long offset; | 
 | 180 | 	unsigned long block; | 
 | 181 | 	struct buffer_head *bh; | 
 | 182 | 	struct ext2_group_desc * gdp; | 
 | 183 | 	struct backing_dev_info *bdi; | 
 | 184 |  | 
 | 185 | 	bdi = inode->i_mapping->backing_dev_info; | 
 | 186 | 	if (bdi_read_congested(bdi)) | 
 | 187 | 		return; | 
 | 188 | 	if (bdi_write_congested(bdi)) | 
 | 189 | 		return; | 
 | 190 |  | 
 | 191 | 	block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); | 
 | 192 | 	gdp = ext2_get_group_desc(inode->i_sb, block_group, &bh); | 
 | 193 | 	if (gdp == NULL) | 
 | 194 | 		return; | 
 | 195 |  | 
 | 196 | 	/* | 
 | 197 | 	 * Figure out the offset within the block group inode table | 
 | 198 | 	 */ | 
 | 199 | 	offset = ((inode->i_ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) * | 
 | 200 | 				EXT2_INODE_SIZE(inode->i_sb); | 
 | 201 | 	block = le32_to_cpu(gdp->bg_inode_table) + | 
 | 202 | 				(offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb)); | 
 | 203 | 	sb_breadahead(inode->i_sb, block); | 
 | 204 | } | 
 | 205 |  | 
 | 206 | /* | 
 | 207 |  * There are two policies for allocating an inode.  If the new inode is | 
 | 208 |  * a directory, then a forward search is made for a block group with both | 
 | 209 |  * free space and a low directory-to-inode ratio; if that fails, then of | 
 | 210 |  * the groups with above-average free space, that group with the fewest | 
 | 211 |  * directories already is chosen. | 
 | 212 |  * | 
 | 213 |  * For other inodes, search forward from the parent directory\'s block | 
 | 214 |  * group to find a free inode. | 
 | 215 |  */ | 
 | 216 | static int find_group_dir(struct super_block *sb, struct inode *parent) | 
 | 217 | { | 
 | 218 | 	int ngroups = EXT2_SB(sb)->s_groups_count; | 
 | 219 | 	int avefreei = ext2_count_free_inodes(sb) / ngroups; | 
 | 220 | 	struct ext2_group_desc *desc, *best_desc = NULL; | 
 | 221 | 	struct buffer_head *bh, *best_bh = NULL; | 
 | 222 | 	int group, best_group = -1; | 
 | 223 |  | 
 | 224 | 	for (group = 0; group < ngroups; group++) { | 
 | 225 | 		desc = ext2_get_group_desc (sb, group, &bh); | 
 | 226 | 		if (!desc || !desc->bg_free_inodes_count) | 
 | 227 | 			continue; | 
 | 228 | 		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) | 
 | 229 | 			continue; | 
 | 230 | 		if (!best_desc ||  | 
 | 231 | 		    (le16_to_cpu(desc->bg_free_blocks_count) > | 
 | 232 | 		     le16_to_cpu(best_desc->bg_free_blocks_count))) { | 
 | 233 | 			best_group = group; | 
 | 234 | 			best_desc = desc; | 
 | 235 | 			best_bh = bh; | 
 | 236 | 		} | 
 | 237 | 	} | 
 | 238 | 	if (!best_desc) | 
 | 239 | 		return -1; | 
 | 240 |  | 
 | 241 | 	return best_group; | 
 | 242 | } | 
 | 243 |  | 
 | 244 | /*  | 
 | 245 |  * Orlov's allocator for directories.  | 
 | 246 |  *  | 
 | 247 |  * We always try to spread first-level directories. | 
 | 248 |  * | 
 | 249 |  * If there are blockgroups with both free inodes and free blocks counts  | 
 | 250 |  * not worse than average we return one with smallest directory count.  | 
 | 251 |  * Otherwise we simply return a random group.  | 
 | 252 |  *  | 
 | 253 |  * For the rest rules look so:  | 
 | 254 |  *  | 
 | 255 |  * It's OK to put directory into a group unless  | 
 | 256 |  * it has too many directories already (max_dirs) or  | 
 | 257 |  * it has too few free inodes left (min_inodes) or  | 
 | 258 |  * it has too few free blocks left (min_blocks) or  | 
 | 259 |  * it's already running too large debt (max_debt).  | 
 | 260 |  * Parent's group is prefered, if it doesn't satisfy these  | 
 | 261 |  * conditions we search cyclically through the rest. If none  | 
 | 262 |  * of the groups look good we just look for a group with more  | 
 | 263 |  * free inodes than average (starting at parent's group).  | 
 | 264 |  *  | 
 | 265 |  * Debt is incremented each time we allocate a directory and decremented  | 
 | 266 |  * when we allocate an inode, within 0--255.  | 
 | 267 |  */  | 
 | 268 |  | 
 | 269 | #define INODE_COST 64 | 
 | 270 | #define BLOCK_COST 256 | 
 | 271 |  | 
 | 272 | static int find_group_orlov(struct super_block *sb, struct inode *parent) | 
 | 273 | { | 
 | 274 | 	int parent_group = EXT2_I(parent)->i_block_group; | 
 | 275 | 	struct ext2_sb_info *sbi = EXT2_SB(sb); | 
 | 276 | 	struct ext2_super_block *es = sbi->s_es; | 
 | 277 | 	int ngroups = sbi->s_groups_count; | 
 | 278 | 	int inodes_per_group = EXT2_INODES_PER_GROUP(sb); | 
 | 279 | 	int freei; | 
 | 280 | 	int avefreei; | 
 | 281 | 	int free_blocks; | 
 | 282 | 	int avefreeb; | 
 | 283 | 	int blocks_per_dir; | 
 | 284 | 	int ndirs; | 
 | 285 | 	int max_debt, max_dirs, min_blocks, min_inodes; | 
 | 286 | 	int group = -1, i; | 
 | 287 | 	struct ext2_group_desc *desc; | 
 | 288 | 	struct buffer_head *bh; | 
 | 289 |  | 
 | 290 | 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); | 
 | 291 | 	avefreei = freei / ngroups; | 
 | 292 | 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); | 
 | 293 | 	avefreeb = free_blocks / ngroups; | 
 | 294 | 	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); | 
 | 295 |  | 
 | 296 | 	if ((parent == sb->s_root->d_inode) || | 
 | 297 | 	    (EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) { | 
 | 298 | 		struct ext2_group_desc *best_desc = NULL; | 
 | 299 | 		struct buffer_head *best_bh = NULL; | 
 | 300 | 		int best_ndir = inodes_per_group; | 
 | 301 | 		int best_group = -1; | 
 | 302 |  | 
 | 303 | 		get_random_bytes(&group, sizeof(group)); | 
 | 304 | 		parent_group = (unsigned)group % ngroups; | 
 | 305 | 		for (i = 0; i < ngroups; i++) { | 
 | 306 | 			group = (parent_group + i) % ngroups; | 
 | 307 | 			desc = ext2_get_group_desc (sb, group, &bh); | 
 | 308 | 			if (!desc || !desc->bg_free_inodes_count) | 
 | 309 | 				continue; | 
 | 310 | 			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir) | 
 | 311 | 				continue; | 
 | 312 | 			if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) | 
 | 313 | 				continue; | 
 | 314 | 			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb) | 
 | 315 | 				continue; | 
 | 316 | 			best_group = group; | 
 | 317 | 			best_ndir = le16_to_cpu(desc->bg_used_dirs_count); | 
 | 318 | 			best_desc = desc; | 
 | 319 | 			best_bh = bh; | 
 | 320 | 		} | 
 | 321 | 		if (best_group >= 0) { | 
 | 322 | 			desc = best_desc; | 
 | 323 | 			bh = best_bh; | 
 | 324 | 			group = best_group; | 
 | 325 | 			goto found; | 
 | 326 | 		} | 
 | 327 | 		goto fallback; | 
 | 328 | 	} | 
 | 329 |  | 
 | 330 | 	if (ndirs == 0) | 
 | 331 | 		ndirs = 1;	/* percpu_counters are approximate... */ | 
 | 332 |  | 
 | 333 | 	blocks_per_dir = (le32_to_cpu(es->s_blocks_count)-free_blocks) / ndirs; | 
 | 334 |  | 
 | 335 | 	max_dirs = ndirs / ngroups + inodes_per_group / 16; | 
 | 336 | 	min_inodes = avefreei - inodes_per_group / 4; | 
 | 337 | 	min_blocks = avefreeb - EXT2_BLOCKS_PER_GROUP(sb) / 4; | 
 | 338 |  | 
 | 339 | 	max_debt = EXT2_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, BLOCK_COST); | 
 | 340 | 	if (max_debt * INODE_COST > inodes_per_group) | 
 | 341 | 		max_debt = inodes_per_group / INODE_COST; | 
 | 342 | 	if (max_debt > 255) | 
 | 343 | 		max_debt = 255; | 
 | 344 | 	if (max_debt == 0) | 
 | 345 | 		max_debt = 1; | 
 | 346 |  | 
 | 347 | 	for (i = 0; i < ngroups; i++) { | 
 | 348 | 		group = (parent_group + i) % ngroups; | 
 | 349 | 		desc = ext2_get_group_desc (sb, group, &bh); | 
 | 350 | 		if (!desc || !desc->bg_free_inodes_count) | 
 | 351 | 			continue; | 
 | 352 | 		if (sbi->s_debts[group] >= max_debt) | 
 | 353 | 			continue; | 
 | 354 | 		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs) | 
 | 355 | 			continue; | 
 | 356 | 		if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes) | 
 | 357 | 			continue; | 
 | 358 | 		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks) | 
 | 359 | 			continue; | 
 | 360 | 		goto found; | 
 | 361 | 	} | 
 | 362 |  | 
 | 363 | fallback: | 
 | 364 | 	for (i = 0; i < ngroups; i++) { | 
 | 365 | 		group = (parent_group + i) % ngroups; | 
 | 366 | 		desc = ext2_get_group_desc (sb, group, &bh); | 
 | 367 | 		if (!desc || !desc->bg_free_inodes_count) | 
 | 368 | 			continue; | 
 | 369 | 		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) | 
 | 370 | 			goto found; | 
 | 371 | 	} | 
 | 372 |  | 
 | 373 | 	if (avefreei) { | 
 | 374 | 		/* | 
 | 375 | 		 * The free-inodes counter is approximate, and for really small | 
 | 376 | 		 * filesystems the above test can fail to find any blockgroups | 
 | 377 | 		 */ | 
 | 378 | 		avefreei = 0; | 
 | 379 | 		goto fallback; | 
 | 380 | 	} | 
 | 381 |  | 
 | 382 | 	return -1; | 
 | 383 |  | 
 | 384 | found: | 
 | 385 | 	return group; | 
 | 386 | } | 
 | 387 |  | 
 | 388 | static int find_group_other(struct super_block *sb, struct inode *parent) | 
 | 389 | { | 
 | 390 | 	int parent_group = EXT2_I(parent)->i_block_group; | 
 | 391 | 	int ngroups = EXT2_SB(sb)->s_groups_count; | 
 | 392 | 	struct ext2_group_desc *desc; | 
 | 393 | 	struct buffer_head *bh; | 
 | 394 | 	int group, i; | 
 | 395 |  | 
 | 396 | 	/* | 
 | 397 | 	 * Try to place the inode in its parent directory | 
 | 398 | 	 */ | 
 | 399 | 	group = parent_group; | 
 | 400 | 	desc = ext2_get_group_desc (sb, group, &bh); | 
 | 401 | 	if (desc && le16_to_cpu(desc->bg_free_inodes_count) && | 
 | 402 | 			le16_to_cpu(desc->bg_free_blocks_count)) | 
 | 403 | 		goto found; | 
 | 404 |  | 
 | 405 | 	/* | 
 | 406 | 	 * We're going to place this inode in a different blockgroup from its | 
 | 407 | 	 * parent.  We want to cause files in a common directory to all land in | 
 | 408 | 	 * the same blockgroup.  But we want files which are in a different | 
 | 409 | 	 * directory which shares a blockgroup with our parent to land in a | 
 | 410 | 	 * different blockgroup. | 
 | 411 | 	 * | 
 | 412 | 	 * So add our directory's i_ino into the starting point for the hash. | 
 | 413 | 	 */ | 
 | 414 | 	group = (group + parent->i_ino) % ngroups; | 
 | 415 |  | 
 | 416 | 	/* | 
 | 417 | 	 * Use a quadratic hash to find a group with a free inode and some | 
 | 418 | 	 * free blocks. | 
 | 419 | 	 */ | 
 | 420 | 	for (i = 1; i < ngroups; i <<= 1) { | 
 | 421 | 		group += i; | 
 | 422 | 		if (group >= ngroups) | 
 | 423 | 			group -= ngroups; | 
 | 424 | 		desc = ext2_get_group_desc (sb, group, &bh); | 
 | 425 | 		if (desc && le16_to_cpu(desc->bg_free_inodes_count) && | 
 | 426 | 				le16_to_cpu(desc->bg_free_blocks_count)) | 
 | 427 | 			goto found; | 
 | 428 | 	} | 
 | 429 |  | 
 | 430 | 	/* | 
 | 431 | 	 * That failed: try linear search for a free inode, even if that group | 
 | 432 | 	 * has no free blocks. | 
 | 433 | 	 */ | 
 | 434 | 	group = parent_group; | 
 | 435 | 	for (i = 0; i < ngroups; i++) { | 
 | 436 | 		if (++group >= ngroups) | 
 | 437 | 			group = 0; | 
 | 438 | 		desc = ext2_get_group_desc (sb, group, &bh); | 
 | 439 | 		if (desc && le16_to_cpu(desc->bg_free_inodes_count)) | 
 | 440 | 			goto found; | 
 | 441 | 	} | 
 | 442 |  | 
 | 443 | 	return -1; | 
 | 444 |  | 
 | 445 | found: | 
 | 446 | 	return group; | 
 | 447 | } | 
 | 448 |  | 
 | 449 | struct inode *ext2_new_inode(struct inode *dir, int mode) | 
 | 450 | { | 
 | 451 | 	struct super_block *sb; | 
 | 452 | 	struct buffer_head *bitmap_bh = NULL; | 
 | 453 | 	struct buffer_head *bh2; | 
 | 454 | 	int group, i; | 
 | 455 | 	ino_t ino = 0; | 
 | 456 | 	struct inode * inode; | 
 | 457 | 	struct ext2_group_desc *gdp; | 
 | 458 | 	struct ext2_super_block *es; | 
 | 459 | 	struct ext2_inode_info *ei; | 
 | 460 | 	struct ext2_sb_info *sbi; | 
 | 461 | 	int err; | 
 | 462 |  | 
 | 463 | 	sb = dir->i_sb; | 
 | 464 | 	inode = new_inode(sb); | 
 | 465 | 	if (!inode) | 
 | 466 | 		return ERR_PTR(-ENOMEM); | 
 | 467 |  | 
 | 468 | 	ei = EXT2_I(inode); | 
 | 469 | 	sbi = EXT2_SB(sb); | 
 | 470 | 	es = sbi->s_es; | 
 | 471 | 	if (S_ISDIR(mode)) { | 
 | 472 | 		if (test_opt(sb, OLDALLOC)) | 
 | 473 | 			group = find_group_dir(sb, dir); | 
 | 474 | 		else | 
 | 475 | 			group = find_group_orlov(sb, dir); | 
 | 476 | 	} else  | 
 | 477 | 		group = find_group_other(sb, dir); | 
 | 478 |  | 
 | 479 | 	if (group == -1) { | 
 | 480 | 		err = -ENOSPC; | 
 | 481 | 		goto fail; | 
 | 482 | 	} | 
 | 483 |  | 
 | 484 | 	for (i = 0; i < sbi->s_groups_count; i++) { | 
 | 485 | 		gdp = ext2_get_group_desc(sb, group, &bh2); | 
 | 486 | 		brelse(bitmap_bh); | 
 | 487 | 		bitmap_bh = read_inode_bitmap(sb, group); | 
 | 488 | 		if (!bitmap_bh) { | 
 | 489 | 			err = -EIO; | 
 | 490 | 			goto fail; | 
 | 491 | 		} | 
 | 492 | 		ino = 0; | 
 | 493 |  | 
 | 494 | repeat_in_this_group: | 
 | 495 | 		ino = ext2_find_next_zero_bit((unsigned long *)bitmap_bh->b_data, | 
 | 496 | 					      EXT2_INODES_PER_GROUP(sb), ino); | 
 | 497 | 		if (ino >= EXT2_INODES_PER_GROUP(sb)) { | 
 | 498 | 			/* | 
 | 499 | 			 * Rare race: find_group_xx() decided that there were | 
 | 500 | 			 * free inodes in this group, but by the time we tried | 
 | 501 | 			 * to allocate one, they're all gone.  This can also | 
 | 502 | 			 * occur because the counters which find_group_orlov() | 
 | 503 | 			 * uses are approximate.  So just go and search the | 
 | 504 | 			 * next block group. | 
 | 505 | 			 */ | 
 | 506 | 			if (++group == sbi->s_groups_count) | 
 | 507 | 				group = 0; | 
 | 508 | 			continue; | 
 | 509 | 		} | 
 | 510 | 		if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group), | 
 | 511 | 						ino, bitmap_bh->b_data)) { | 
 | 512 | 			/* we lost this inode */ | 
 | 513 | 			if (++ino >= EXT2_INODES_PER_GROUP(sb)) { | 
 | 514 | 				/* this group is exhausted, try next group */ | 
 | 515 | 				if (++group == sbi->s_groups_count) | 
 | 516 | 					group = 0; | 
 | 517 | 				continue; | 
 | 518 | 			} | 
 | 519 | 			/* try to find free inode in the same group */ | 
 | 520 | 			goto repeat_in_this_group; | 
 | 521 | 		} | 
 | 522 | 		goto got; | 
 | 523 | 	} | 
 | 524 |  | 
 | 525 | 	/* | 
 | 526 | 	 * Scanned all blockgroups. | 
 | 527 | 	 */ | 
 | 528 | 	err = -ENOSPC; | 
 | 529 | 	goto fail; | 
 | 530 | got: | 
 | 531 | 	mark_buffer_dirty(bitmap_bh); | 
 | 532 | 	if (sb->s_flags & MS_SYNCHRONOUS) | 
 | 533 | 		sync_dirty_buffer(bitmap_bh); | 
 | 534 | 	brelse(bitmap_bh); | 
 | 535 |  | 
 | 536 | 	ino += group * EXT2_INODES_PER_GROUP(sb) + 1; | 
 | 537 | 	if (ino < EXT2_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { | 
 | 538 | 		ext2_error (sb, "ext2_new_inode", | 
 | 539 | 			    "reserved inode or inode > inodes count - " | 
 | 540 | 			    "block_group = %d,inode=%lu", group, | 
 | 541 | 			    (unsigned long) ino); | 
 | 542 | 		err = -EIO; | 
 | 543 | 		goto fail; | 
 | 544 | 	} | 
 | 545 |  | 
 | 546 | 	percpu_counter_mod(&sbi->s_freeinodes_counter, -1); | 
 | 547 | 	if (S_ISDIR(mode)) | 
 | 548 | 		percpu_counter_inc(&sbi->s_dirs_counter); | 
 | 549 |  | 
 | 550 | 	spin_lock(sb_bgl_lock(sbi, group)); | 
 | 551 | 	gdp->bg_free_inodes_count = | 
 | 552 |                 cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1); | 
 | 553 | 	if (S_ISDIR(mode)) { | 
 | 554 | 		if (sbi->s_debts[group] < 255) | 
 | 555 | 			sbi->s_debts[group]++; | 
 | 556 | 		gdp->bg_used_dirs_count = | 
 | 557 | 			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1); | 
 | 558 | 	} else { | 
 | 559 | 		if (sbi->s_debts[group]) | 
 | 560 | 			sbi->s_debts[group]--; | 
 | 561 | 	} | 
 | 562 | 	spin_unlock(sb_bgl_lock(sbi, group)); | 
 | 563 |  | 
 | 564 | 	sb->s_dirt = 1; | 
 | 565 | 	mark_buffer_dirty(bh2); | 
 | 566 | 	inode->i_uid = current->fsuid; | 
 | 567 | 	if (test_opt (sb, GRPID)) | 
 | 568 | 		inode->i_gid = dir->i_gid; | 
 | 569 | 	else if (dir->i_mode & S_ISGID) { | 
 | 570 | 		inode->i_gid = dir->i_gid; | 
 | 571 | 		if (S_ISDIR(mode)) | 
 | 572 | 			mode |= S_ISGID; | 
 | 573 | 	} else | 
 | 574 | 		inode->i_gid = current->fsgid; | 
 | 575 | 	inode->i_mode = mode; | 
 | 576 |  | 
 | 577 | 	inode->i_ino = ino; | 
 | 578 | 	inode->i_blksize = PAGE_SIZE;	/* This is the optimal IO size (for stat), not the fs block size */ | 
 | 579 | 	inode->i_blocks = 0; | 
 | 580 | 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; | 
 | 581 | 	memset(ei->i_data, 0, sizeof(ei->i_data)); | 
 | 582 | 	ei->i_flags = EXT2_I(dir)->i_flags & ~EXT2_BTREE_FL; | 
 | 583 | 	if (S_ISLNK(mode)) | 
 | 584 | 		ei->i_flags &= ~(EXT2_IMMUTABLE_FL|EXT2_APPEND_FL); | 
 | 585 | 	/* dirsync is only applied to directories */ | 
 | 586 | 	if (!S_ISDIR(mode)) | 
 | 587 | 		ei->i_flags &= ~EXT2_DIRSYNC_FL; | 
 | 588 | 	ei->i_faddr = 0; | 
 | 589 | 	ei->i_frag_no = 0; | 
 | 590 | 	ei->i_frag_size = 0; | 
 | 591 | 	ei->i_file_acl = 0; | 
 | 592 | 	ei->i_dir_acl = 0; | 
 | 593 | 	ei->i_dtime = 0; | 
 | 594 | 	ei->i_block_group = group; | 
 | 595 | 	ei->i_next_alloc_block = 0; | 
 | 596 | 	ei->i_next_alloc_goal = 0; | 
 | 597 | 	ei->i_prealloc_block = 0; | 
 | 598 | 	ei->i_prealloc_count = 0; | 
 | 599 | 	ei->i_dir_start_lookup = 0; | 
 | 600 | 	ei->i_state = EXT2_STATE_NEW; | 
 | 601 | 	ext2_set_inode_flags(inode); | 
 | 602 | 	spin_lock(&sbi->s_next_gen_lock); | 
 | 603 | 	inode->i_generation = sbi->s_next_generation++; | 
 | 604 | 	spin_unlock(&sbi->s_next_gen_lock); | 
 | 605 | 	insert_inode_hash(inode); | 
 | 606 |  | 
 | 607 | 	if (DQUOT_ALLOC_INODE(inode)) { | 
 | 608 | 		DQUOT_DROP(inode); | 
 | 609 | 		err = -ENOSPC; | 
 | 610 | 		goto fail2; | 
 | 611 | 	} | 
 | 612 | 	err = ext2_init_acl(inode, dir); | 
 | 613 | 	if (err) { | 
 | 614 | 		DQUOT_FREE_INODE(inode); | 
 | 615 | 		goto fail2; | 
 | 616 | 	} | 
 | 617 | 	mark_inode_dirty(inode); | 
 | 618 | 	ext2_debug("allocating inode %lu\n", inode->i_ino); | 
 | 619 | 	ext2_preread_inode(inode); | 
 | 620 | 	return inode; | 
 | 621 |  | 
 | 622 | fail2: | 
 | 623 | 	inode->i_flags |= S_NOQUOTA; | 
 | 624 | 	inode->i_nlink = 0; | 
 | 625 | 	iput(inode); | 
 | 626 | 	return ERR_PTR(err); | 
 | 627 |  | 
 | 628 | fail: | 
 | 629 | 	make_bad_inode(inode); | 
 | 630 | 	iput(inode); | 
 | 631 | 	return ERR_PTR(err); | 
 | 632 | } | 
 | 633 |  | 
 | 634 | unsigned long ext2_count_free_inodes (struct super_block * sb) | 
 | 635 | { | 
 | 636 | 	struct ext2_group_desc *desc; | 
 | 637 | 	unsigned long desc_count = 0; | 
 | 638 | 	int i;	 | 
 | 639 |  | 
 | 640 | #ifdef EXT2FS_DEBUG | 
 | 641 | 	struct ext2_super_block *es; | 
 | 642 | 	unsigned long bitmap_count = 0; | 
 | 643 | 	struct buffer_head *bitmap_bh = NULL; | 
 | 644 |  | 
 | 645 | 	lock_super (sb); | 
 | 646 | 	es = EXT2_SB(sb)->s_es; | 
 | 647 | 	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { | 
 | 648 | 		unsigned x; | 
 | 649 |  | 
 | 650 | 		desc = ext2_get_group_desc (sb, i, NULL); | 
 | 651 | 		if (!desc) | 
 | 652 | 			continue; | 
 | 653 | 		desc_count += le16_to_cpu(desc->bg_free_inodes_count); | 
 | 654 | 		brelse(bitmap_bh); | 
 | 655 | 		bitmap_bh = read_inode_bitmap(sb, i); | 
 | 656 | 		if (!bitmap_bh) | 
 | 657 | 			continue; | 
 | 658 |  | 
 | 659 | 		x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8); | 
 | 660 | 		printk("group %d: stored = %d, counted = %u\n", | 
 | 661 | 			i, le16_to_cpu(desc->bg_free_inodes_count), x); | 
 | 662 | 		bitmap_count += x; | 
 | 663 | 	} | 
 | 664 | 	brelse(bitmap_bh); | 
 | 665 | 	printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n", | 
 | 666 | 		percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter), | 
 | 667 | 		desc_count, bitmap_count); | 
 | 668 | 	unlock_super(sb); | 
 | 669 | 	return desc_count; | 
 | 670 | #else | 
 | 671 | 	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { | 
 | 672 | 		desc = ext2_get_group_desc (sb, i, NULL); | 
 | 673 | 		if (!desc) | 
 | 674 | 			continue; | 
 | 675 | 		desc_count += le16_to_cpu(desc->bg_free_inodes_count); | 
 | 676 | 	} | 
 | 677 | 	return desc_count; | 
 | 678 | #endif | 
 | 679 | } | 
 | 680 |  | 
 | 681 | /* Called at mount-time, super-block is locked */ | 
 | 682 | unsigned long ext2_count_dirs (struct super_block * sb) | 
 | 683 | { | 
 | 684 | 	unsigned long count = 0; | 
 | 685 | 	int i; | 
 | 686 |  | 
 | 687 | 	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { | 
 | 688 | 		struct ext2_group_desc *gdp = ext2_get_group_desc (sb, i, NULL); | 
 | 689 | 		if (!gdp) | 
 | 690 | 			continue; | 
 | 691 | 		count += le16_to_cpu(gdp->bg_used_dirs_count); | 
 | 692 | 	} | 
 | 693 | 	return count; | 
 | 694 | } | 
 | 695 |  | 
 | 696 | #ifdef CONFIG_EXT2_CHECK | 
 | 697 | /* Called at mount-time, super-block is locked */ | 
 | 698 | void ext2_check_inodes_bitmap (struct super_block * sb) | 
 | 699 | { | 
 | 700 | 	struct ext2_super_block * es = EXT2_SB(sb)->s_es; | 
 | 701 | 	unsigned long desc_count = 0, bitmap_count = 0; | 
 | 702 | 	struct buffer_head *bitmap_bh = NULL; | 
 | 703 | 	int i; | 
 | 704 |  | 
 | 705 | 	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { | 
 | 706 | 		struct ext2_group_desc *desc; | 
 | 707 | 		unsigned x; | 
 | 708 |  | 
 | 709 | 		desc = ext2_get_group_desc(sb, i, NULL); | 
 | 710 | 		if (!desc) | 
 | 711 | 			continue; | 
 | 712 | 		desc_count += le16_to_cpu(desc->bg_free_inodes_count); | 
 | 713 | 		brelse(bitmap_bh); | 
 | 714 | 		bitmap_bh = read_inode_bitmap(sb, i); | 
 | 715 | 		if (!bitmap_bh) | 
 | 716 | 			continue; | 
 | 717 | 		 | 
 | 718 | 		x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8); | 
 | 719 | 		if (le16_to_cpu(desc->bg_free_inodes_count) != x) | 
 | 720 | 			ext2_error (sb, "ext2_check_inodes_bitmap", | 
 | 721 | 				    "Wrong free inodes count in group %d, " | 
 | 722 | 				    "stored = %d, counted = %lu", i, | 
 | 723 | 				    le16_to_cpu(desc->bg_free_inodes_count), x); | 
 | 724 | 		bitmap_count += x; | 
 | 725 | 	} | 
 | 726 | 	brelse(bitmap_bh); | 
 | 727 | 	if (percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter) != | 
 | 728 | 				bitmap_count) | 
 | 729 | 		ext2_error(sb, "ext2_check_inodes_bitmap", | 
 | 730 | 			    "Wrong free inodes count in super block, " | 
 | 731 | 			    "stored = %lu, counted = %lu", | 
 | 732 | 			    (unsigned long)le32_to_cpu(es->s_free_inodes_count), | 
 | 733 | 			    bitmap_count); | 
 | 734 | } | 
 | 735 | #endif |