super.c 39.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
/*
 *  linux/fs/ext2/super.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
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/module.h>
#include <linux/string.h>
21
#include <linux/fs.h>
L
Linus Torvalds 已提交
22 23 24 25 26 27
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/random.h>
#include <linux/buffer_head.h>
28
#include <linux/exportfs.h>
L
Linus Torvalds 已提交
29 30
#include <linux/smp_lock.h>
#include <linux/vfs.h>
31 32
#include <linux/seq_file.h>
#include <linux/mount.h>
V
vignesh babu 已提交
33
#include <linux/log2.h>
34
#include <linux/quotaops.h>
L
Linus Torvalds 已提交
35 36 37 38
#include <asm/uaccess.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
39
#include "xip.h"
L
Linus Torvalds 已提交
40 41 42 43

static void ext2_sync_super(struct super_block *sb,
			    struct ext2_super_block *es);
static int ext2_remount (struct super_block * sb, int * flags, char * data);
44
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
C
Christoph Hellwig 已提交
45
static int ext2_sync_fs(struct super_block *sb, int wait);
L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54 55

void ext2_error (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;

	if (!(sb->s_flags & MS_RDONLY)) {
		sbi->s_mount_state |= EXT2_ERROR_FS;
56
		es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
L
Linus Torvalds 已提交
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
		ext2_sync_super(sb, es);
	}

	va_start(args, fmt);
	printk(KERN_CRIT "EXT2-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT2-fs panic from previous error\n");
	if (test_opt(sb, ERRORS_RO)) {
		printk("Remounting filesystem read-only\n");
		sb->s_flags |= MS_RDONLY;
	}
}

void ext2_warning (struct super_block * sb, const char * function,
		   const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_WARNING "EXT2-fs warning (device %s): %s: ",
	       sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);
}

void ext2_update_dynamic_rev(struct super_block *sb)
{
	struct ext2_super_block *es = EXT2_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
		return;

94
	ext2_warning(sb, __func__,
L
Linus Torvalds 已提交
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
		     "updating to rev %d because of new feature flag, "
		     "running e2fsck is recommended",
		     EXT2_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV);
	/* leave es->s_feature_*compat flags alone */
	/* es->s_uuid will be set by e2fsck if empty */

	/*
	 * The rest of the superblock fields should be zero, and if not it
	 * means they are likely already in use, so leave them alone.  We
	 * can leave it up to e2fsck to clean up any inconsistencies there.
	 */
}

static void ext2_put_super (struct super_block * sb)
{
	int db_count;
	int i;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

118 119
	lock_kernel();

120 121 122
	if (sb->s_dirt)
		ext2_write_super(sb);

L
Linus Torvalds 已提交
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
	ext2_xattr_put_super(sb);
	if (!(sb->s_flags & MS_RDONLY)) {
		struct ext2_super_block *es = sbi->s_es;

		es->s_state = cpu_to_le16(sbi->s_mount_state);
		ext2_sync_super(sb, es);
	}
	db_count = sbi->s_gdb_count;
	for (i = 0; i < db_count; i++)
		if (sbi->s_group_desc[i])
			brelse (sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	brelse (sbi->s_sbh);
	sb->s_fs_info = NULL;
141
	kfree(sbi->s_blockgroup_lock);
L
Linus Torvalds 已提交
142 143
	kfree(sbi);

144
	unlock_kernel();
L
Linus Torvalds 已提交
145 146
}

147
static struct kmem_cache * ext2_inode_cachep;
L
Linus Torvalds 已提交
148 149 150 151

static struct inode *ext2_alloc_inode(struct super_block *sb)
{
	struct ext2_inode_info *ei;
152
	ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
153 154
	if (!ei)
		return NULL;
M
Martin J. Bligh 已提交
155
	ei->i_block_alloc_info = NULL;
L
Linus Torvalds 已提交
156 157 158 159 160 161 162 163 164
	ei->vfs_inode.i_version = 1;
	return &ei->vfs_inode;
}

static void ext2_destroy_inode(struct inode *inode)
{
	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
}

165
static void init_once(void *foo)
L
Linus Torvalds 已提交
166 167 168
{
	struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;

C
Christoph Lameter 已提交
169
	rwlock_init(&ei->i_meta_lock);
L
Linus Torvalds 已提交
170
#ifdef CONFIG_EXT2_FS_XATTR
C
Christoph Lameter 已提交
171
	init_rwsem(&ei->xattr_sem);
L
Linus Torvalds 已提交
172
#endif
M
Martin J. Bligh 已提交
173
	mutex_init(&ei->truncate_mutex);
C
Christoph Lameter 已提交
174
	inode_init_once(&ei->vfs_inode);
L
Linus Torvalds 已提交
175
}
176

L
Linus Torvalds 已提交
177 178 179 180
static int init_inodecache(void)
{
	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
					     sizeof(struct ext2_inode_info),
181 182
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
183
					     init_once);
L
Linus Torvalds 已提交
184 185 186 187 188 189 190
	if (ext2_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
191
	kmem_cache_destroy(ext2_inode_cachep);
L
Linus Torvalds 已提交
192 193 194 195
}

static void ext2_clear_inode(struct inode *inode)
{
M
Martin J. Bligh 已提交
196 197 198 199 200
	struct ext2_block_alloc_info *rsv = EXT2_I(inode)->i_block_alloc_info;
	ext2_discard_reservation(inode);
	EXT2_I(inode)->i_block_alloc_info = NULL;
	if (unlikely(rsv))
		kfree(rsv);
L
Linus Torvalds 已提交
201 202
}

203 204
static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
M
Miklos Szeredi 已提交
205 206 207 208
	struct super_block *sb = vfs->mnt_sb;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;
	unsigned long def_mount_opts;
209

M
Miklos Szeredi 已提交
210 211 212 213 214 215 216
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);

	if (sbi->s_sb_block != 1)
		seq_printf(seq, ",sb=%lu", sbi->s_sb_block);
	if (test_opt(sb, MINIX_DF))
		seq_puts(seq, ",minixdf");
	if (test_opt(sb, GRPID))
217
		seq_puts(seq, ",grpid");
M
Miklos Szeredi 已提交
218 219 220 221 222 223 224 225 226 227
	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
		seq_puts(seq, ",nogrpid");
	if (sbi->s_resuid != EXT2_DEF_RESUID ||
	    le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
	}
	if (sbi->s_resgid != EXT2_DEF_RESGID ||
	    le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
	}
228
	if (test_opt(sb, ERRORS_RO)) {
M
Miklos Szeredi 已提交
229 230 231
		int def_errors = le16_to_cpu(es->s_errors);

		if (def_errors == EXT2_ERRORS_PANIC ||
232 233
		    def_errors == EXT2_ERRORS_CONTINUE) {
			seq_puts(seq, ",errors=remount-ro");
M
Miklos Szeredi 已提交
234 235
		}
	}
236 237
	if (test_opt(sb, ERRORS_CONT))
		seq_puts(seq, ",errors=continue");
M
Miklos Szeredi 已提交
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
	if (test_opt(sb, ERRORS_PANIC))
		seq_puts(seq, ",errors=panic");
	if (test_opt(sb, NO_UID32))
		seq_puts(seq, ",nouid32");
	if (test_opt(sb, DEBUG))
		seq_puts(seq, ",debug");
	if (test_opt(sb, OLDALLOC))
		seq_puts(seq, ",oldalloc");

#ifdef CONFIG_EXT2_FS_XATTR
	if (test_opt(sb, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	if (!test_opt(sb, XATTR_USER) &&
	    (def_mount_opts & EXT2_DEFM_XATTR_USER)) {
		seq_puts(seq, ",nouser_xattr");
	}
#endif

#ifdef CONFIG_EXT2_FS_POSIX_ACL
	if (test_opt(sb, POSIX_ACL))
		seq_puts(seq, ",acl");
	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL))
		seq_puts(seq, ",noacl");
#endif

	if (test_opt(sb, NOBH))
		seq_puts(seq, ",nobh");
265 266 267 268 269 270 271 272 273

#if defined(CONFIG_QUOTA)
	if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
		seq_puts(seq, ",usrquota");

	if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA)
		seq_puts(seq, ",grpquota");
#endif

274 275 276 277 278
#if defined(CONFIG_EXT2_FS_XIP)
	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
		seq_puts(seq, ",xip");
#endif

M
Miklos Szeredi 已提交
279 280 281
	if (!test_opt(sb, RESERVATION))
		seq_puts(seq, ",noreservation");

282 283 284
	return 0;
}

L
Linus Torvalds 已提交
285 286 287 288 289
#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
#endif

290
static const struct super_operations ext2_sops = {
L
Linus Torvalds 已提交
291 292 293 294 295 296
	.alloc_inode	= ext2_alloc_inode,
	.destroy_inode	= ext2_destroy_inode,
	.write_inode	= ext2_write_inode,
	.delete_inode	= ext2_delete_inode,
	.put_super	= ext2_put_super,
	.write_super	= ext2_write_super,
C
Christoph Hellwig 已提交
297
	.sync_fs	= ext2_sync_fs,
L
Linus Torvalds 已提交
298 299 300
	.statfs		= ext2_statfs,
	.remount_fs	= ext2_remount,
	.clear_inode	= ext2_clear_inode,
301
	.show_options	= ext2_show_options,
L
Linus Torvalds 已提交
302 303 304 305 306 307
#ifdef CONFIG_QUOTA
	.quota_read	= ext2_quota_read,
	.quota_write	= ext2_quota_write,
#endif
};

C
Christoph Hellwig 已提交
308 309
static struct inode *ext2_nfs_get_inode(struct super_block *sb,
		u64 ino, u32 generation)
310 311 312 313 314 315 316 317 318 319 320 321 322
{
	struct inode *inode;

	if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO)
		return ERR_PTR(-ESTALE);
	if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
		return ERR_PTR(-ESTALE);

	/* iget isn't really right if the inode is currently unallocated!!
	 * ext2_read_inode currently does appropriate checks, but
	 * it might be "neater" to call ext2_get_inode first and check
	 * if the inode is valid.....
	 */
323 324 325 326
	inode = ext2_iget(sb, ino);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	if (generation && inode->i_generation != generation) {
327 328 329 330
		/* we didn't find the right inode.. */
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
C
Christoph Hellwig 已提交
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
	return inode;
}

static struct dentry *ext2_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    ext2_nfs_get_inode);
}

static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    ext2_nfs_get_inode);
346 347
}

L
Linus Torvalds 已提交
348 349 350 351 352
/* Yes, most of these are left as NULL!!
 * A NULL value implies the default, which works with ext2-like file
 * systems, but can be improved upon.
 * Currently only get_parent is required.
 */
353
static const struct export_operations ext2_export_ops = {
C
Christoph Hellwig 已提交
354 355
	.fh_to_dentry = ext2_fh_to_dentry,
	.fh_to_parent = ext2_fh_to_parent,
L
Linus Torvalds 已提交
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
	.get_parent = ext2_get_parent,
};

static unsigned long get_sb_block(void **data)
{
	unsigned long 	sb_block;
	char 		*options = (char *) *data;

	if (!options || strncmp(options, "sb=", 3) != 0)
		return 1;	/* Default location */
	options += 3;
	sb_block = simple_strtoul(options, &options, 0);
	if (*options && *options != ',') {
		printk("EXT2-fs: Invalid sb specification: %s\n",
		       (char *) *data);
		return 1;
	}
	if (*options == ',')
		options++;
	*data = (void *) options;
	return sb_block;
}

enum {
	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
381
	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
A
Adrian Bunk 已提交
382
	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
383 384
	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
M
Martin J. Bligh 已提交
385
	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
L
Linus Torvalds 已提交
386 387
};

388
static const match_table_t tokens = {
L
Linus Torvalds 已提交
389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411
	{Opt_bsd_df, "bsddf"},
	{Opt_minix_df, "minixdf"},
	{Opt_grpid, "grpid"},
	{Opt_grpid, "bsdgroups"},
	{Opt_nogrpid, "nogrpid"},
	{Opt_nogrpid, "sysvgroups"},
	{Opt_resgid, "resgid=%u"},
	{Opt_resuid, "resuid=%u"},
	{Opt_sb, "sb=%u"},
	{Opt_err_cont, "errors=continue"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_nouid32, "nouid32"},
	{Opt_nocheck, "check=none"},
	{Opt_nocheck, "nocheck"},
	{Opt_debug, "debug"},
	{Opt_oldalloc, "oldalloc"},
	{Opt_orlov, "orlov"},
	{Opt_nobh, "nobh"},
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
412
	{Opt_xip, "xip"},
413
	{Opt_grpquota, "grpquota"},
L
Linus Torvalds 已提交
414
	{Opt_ignore, "noquota"},
415 416
	{Opt_quota, "quota"},
	{Opt_usrquota, "usrquota"},
M
Martin J. Bligh 已提交
417 418
	{Opt_reservation, "reservation"},
	{Opt_noreservation, "noreservation"},
L
Linus Torvalds 已提交
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
	{Opt_err, NULL}
};

static int parse_options (char * options,
			  struct ext2_sb_info *sbi)
{
	char * p;
	substring_t args[MAX_OPT_ARGS];
	int option;

	if (!options)
		return 1;

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

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_bsd_df:
			clear_opt (sbi->s_mount_opt, MINIX_DF);
			break;
		case Opt_minix_df:
			set_opt (sbi->s_mount_opt, MINIX_DF);
			break;
		case Opt_grpid:
			set_opt (sbi->s_mount_opt, GRPID);
			break;
		case Opt_nogrpid:
			clear_opt (sbi->s_mount_opt, GRPID);
			break;
		case Opt_resuid:
			if (match_int(&args[0], &option))
				return 0;
			sbi->s_resuid = option;
			break;
		case Opt_resgid:
			if (match_int(&args[0], &option))
				return 0;
			sbi->s_resgid = option;
			break;
		case Opt_sb:
			/* handled by get_sb_block() instead of here */
			/* *sb_block = match_int(&args[0]); */
			break;
		case Opt_err_panic:
V
Vasily Averin 已提交
466 467 468
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			set_opt (sbi->s_mount_opt, ERRORS_PANIC);
L
Linus Torvalds 已提交
469 470
			break;
		case Opt_err_ro:
V
Vasily Averin 已提交
471 472 473
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_RO);
L
Linus Torvalds 已提交
474 475
			break;
		case Opt_err_cont:
V
Vasily Averin 已提交
476 477 478
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_CONT);
L
Linus Torvalds 已提交
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
			break;
		case Opt_nouid32:
			set_opt (sbi->s_mount_opt, NO_UID32);
			break;
		case Opt_nocheck:
			clear_opt (sbi->s_mount_opt, CHECK);
			break;
		case Opt_debug:
			set_opt (sbi->s_mount_opt, DEBUG);
			break;
		case Opt_oldalloc:
			set_opt (sbi->s_mount_opt, OLDALLOC);
			break;
		case Opt_orlov:
			clear_opt (sbi->s_mount_opt, OLDALLOC);
			break;
		case Opt_nobh:
			set_opt (sbi->s_mount_opt, NOBH);
			break;
#ifdef CONFIG_EXT2_FS_XATTR
		case Opt_user_xattr:
			set_opt (sbi->s_mount_opt, XATTR_USER);
			break;
		case Opt_nouser_xattr:
			clear_opt (sbi->s_mount_opt, XATTR_USER);
			break;
#else
		case Opt_user_xattr:
		case Opt_nouser_xattr:
			printk("EXT2 (no)user_xattr options not supported\n");
			break;
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
		case Opt_acl:
			set_opt(sbi->s_mount_opt, POSIX_ACL);
			break;
		case Opt_noacl:
			clear_opt(sbi->s_mount_opt, POSIX_ACL);
			break;
#else
		case Opt_acl:
		case Opt_noacl:
			printk("EXT2 (no)acl options not supported\n");
			break;
#endif
524 525 526 527 528 529 530
		case Opt_xip:
#ifdef CONFIG_EXT2_FS_XIP
			set_opt (sbi->s_mount_opt, XIP);
#else
			printk("EXT2 xip option not supported\n");
#endif
			break;
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550

#if defined(CONFIG_QUOTA)
		case Opt_quota:
		case Opt_usrquota:
			set_opt(sbi->s_mount_opt, USRQUOTA);
			break;

		case Opt_grpquota:
			set_opt(sbi->s_mount_opt, GRPQUOTA);
			break;
#else
		case Opt_quota:
		case Opt_usrquota:
		case Opt_grpquota:
			printk(KERN_ERR
				"EXT2-fs: quota operations not supported.\n");

			break;
#endif

M
Martin J. Bligh 已提交
551 552 553 554 555 556 557 558
		case Opt_reservation:
			set_opt(sbi->s_mount_opt, RESERVATION);
			printk("reservations ON\n");
			break;
		case Opt_noreservation:
			clear_opt(sbi->s_mount_opt, RESERVATION);
			printk("reservations OFF\n");
			break;
L
Linus Torvalds 已提交
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
		case Opt_ignore:
			break;
		default:
			return 0;
		}
	}
	return 1;
}

static int ext2_setup_super (struct super_block * sb,
			      struct ext2_super_block * es,
			      int read_only)
{
	int res = 0;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) {
		printk ("EXT2-fs warning: revision level too high, "
			"forcing read-only mode\n");
		res = MS_RDONLY;
	}
	if (read_only)
		return res;
	if (!(sbi->s_mount_state & EXT2_VALID_FS))
		printk ("EXT2-fs warning: mounting unchecked fs, "
			"running e2fsck is recommended\n");
	else if ((sbi->s_mount_state & EXT2_ERROR_FS))
		printk ("EXT2-fs warning: mounting fs with errors, "
			"running e2fsck is recommended\n");
	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
		 le16_to_cpu(es->s_mnt_count) >=
		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
		printk ("EXT2-fs warning: maximal mount count reached, "
			"running e2fsck is recommended\n");
	else if (le32_to_cpu(es->s_checkinterval) &&
		(le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds()))
		printk ("EXT2-fs warning: checktime reached, "
			"running e2fsck is recommended\n");
	if (!le16_to_cpu(es->s_max_mnt_count))
		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
M
Marcin Slusarz 已提交
599
	le16_add_cpu(&es->s_mnt_count, 1);
L
Linus Torvalds 已提交
600 601 602 603 604 605 606 607 608 609 610 611 612
	ext2_write_super(sb);
	if (test_opt (sb, DEBUG))
		printk ("[EXT II FS %s, %s, bs=%lu, fs=%lu, gc=%lu, "
			"bpg=%lu, ipg=%lu, mo=%04lx]\n",
			EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
			sbi->s_frag_size,
			sbi->s_groups_count,
			EXT2_BLOCKS_PER_GROUP(sb),
			EXT2_INODES_PER_GROUP(sb),
			sbi->s_mount_opt);
	return res;
}

613
static int ext2_check_descriptors(struct super_block *sb)
L
Linus Torvalds 已提交
614 615 616 617 618 619
{
	int i;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	ext2_debug ("Checking group descriptors");

620 621
	for (i = 0; i < sbi->s_groups_count; i++) {
		struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
622 623
		ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
		ext2_fsblk_t last_block;
624

E
Eric Sandeen 已提交
625 626 627 628 629 630 631 632
		if (i == sbi->s_groups_count - 1)
			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
		else
			last_block = first_block +
				(EXT2_BLOCKS_PER_GROUP(sb) - 1);

		if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_block_bitmap) > last_block)
L
Linus Torvalds 已提交
633 634 635 636 637 638 639
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Block bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap));
			return 0;
		}
E
Eric Sandeen 已提交
640 641
		if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
L
Linus Torvalds 已提交
642 643 644 645 646 647 648
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap));
			return 0;
		}
E
Eric Sandeen 已提交
649
		if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
650
		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
E
Eric Sandeen 已提交
651
		    last_block)
L
Linus Torvalds 已提交
652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode table for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
			return 0;
		}
	}
	return 1;
}

/*
 * Maximal file size.  There is a direct, and {,double-,triple-}indirect
 * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
 * We need to be 1 filesystem block less than the 2^32 sector limit.
 */
static loff_t ext2_max_size(int bits)
{
	loff_t res = EXT2_NDIR_BLOCKS;
671 672 673 674 675
	int meta_blocks;
	loff_t upper_limit;

	/* This is calculated to be the largest file size for a
	 * dense, file such that the total number of
L
Linus Torvalds 已提交
676
	 * sectors in the file, including data and all indirect blocks,
677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695
	 * does not exceed 2^32 -1
	 * __u32 i_blocks representing the total number of
	 * 512 bytes blocks of the file
	 */
	upper_limit = (1LL << 32) - 1;

	/* total blocks in file system block size */
	upper_limit >>= (bits - 9);


	/* indirect blocks */
	meta_blocks = 1;
	/* double indirect blocks */
	meta_blocks += 1 + (1LL << (bits-2));
	/* tripple indirect blocks */
	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));

	upper_limit -= meta_blocks;
	upper_limit <<= bits;
L
Linus Torvalds 已提交
696 697 698 699 700 701 702

	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > upper_limit)
		res = upper_limit;
703 704 705 706

	if (res > MAX_LFS_FILESIZE)
		res = MAX_LFS_FILESIZE;

L
Linus Torvalds 已提交
707 708 709 710 711 712 713 714
	return res;
}

static unsigned long descriptor_loc(struct super_block *sb,
				    unsigned long logic_sb_block,
				    int nr)
{
	struct ext2_sb_info *sbi = EXT2_SB(sb);
715
	unsigned long bg, first_meta_bg;
L
Linus Torvalds 已提交
716 717 718 719 720 721 722 723 724 725
	int has_super = 0;
	
	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

	if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return (logic_sb_block + nr + 1);
	bg = sbi->s_desc_per_block * nr;
	if (ext2_bg_has_super(sb, bg))
		has_super = 1;
726 727

	return ext2_group_first_block_no(sb, bg) + has_super;
L
Linus Torvalds 已提交
728 729 730 731 732 733 734 735 736 737 738 739 740
}

static int ext2_fill_super(struct super_block *sb, void *data, int silent)
{
	struct buffer_head * bh;
	struct ext2_sb_info * sbi;
	struct ext2_super_block * es;
	struct inode *root;
	unsigned long block;
	unsigned long sb_block = get_sb_block(&data);
	unsigned long logic_sb_block;
	unsigned long offset = 0;
	unsigned long def_mount_opts;
741
	long ret = -EINVAL;
L
Linus Torvalds 已提交
742 743 744 745
	int blocksize = BLOCK_SIZE;
	int db_count;
	int i, j;
	__le32 features;
746
	int err;
L
Linus Torvalds 已提交
747

748
	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
L
Linus Torvalds 已提交
749 750
	if (!sbi)
		return -ENOMEM;
751 752 753 754 755 756 757

	sbi->s_blockgroup_lock =
		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
	if (!sbi->s_blockgroup_lock) {
		kfree(sbi);
		return -ENOMEM;
	}
L
Linus Torvalds 已提交
758
	sb->s_fs_info = sbi;
M
Miklos Szeredi 已提交
759
	sbi->s_sb_block = sb_block;
L
Linus Torvalds 已提交
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

	/*
	 * See what the current blocksize for the device is, and
	 * use that as the blocksize.  Otherwise (or if the blocksize
	 * is smaller than the default) use the default.
	 * This is important for devices that have a hardware
	 * sectorsize that is larger than the default.
	 */
	blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
	if (!blocksize) {
		printk ("EXT2-fs: unable to set blocksize\n");
		goto failed_sbi;
	}

	/*
	 * If the superblock doesn't start on a hardware sector boundary,
	 * calculate the offset.  
	 */
	if (blocksize != BLOCK_SIZE) {
		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
	} else {
		logic_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logic_sb_block))) {
		printk ("EXT2-fs: unable to read superblock\n");
		goto failed_sbi;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext2 macro-instructions depend on its value
	 */
	es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT2_DEFM_DEBUG)
		set_opt(sbi->s_mount_opt, DEBUG);
	if (def_mount_opts & EXT2_DEFM_BSDGROUPS)
		set_opt(sbi->s_mount_opt, GRPID);
	if (def_mount_opts & EXT2_DEFM_UID16)
		set_opt(sbi->s_mount_opt, NO_UID32);
808
#ifdef CONFIG_EXT2_FS_XATTR
L
Linus Torvalds 已提交
809 810
	if (def_mount_opts & EXT2_DEFM_XATTR_USER)
		set_opt(sbi->s_mount_opt, XATTR_USER);
811 812
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
L
Linus Torvalds 已提交
813 814
	if (def_mount_opts & EXT2_DEFM_ACL)
		set_opt(sbi->s_mount_opt, POSIX_ACL);
815
#endif
L
Linus Torvalds 已提交
816 817 818
	
	if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
819
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
V
Vasily Averin 已提交
820
		set_opt(sbi->s_mount_opt, ERRORS_CONT);
821 822
	else
		set_opt(sbi->s_mount_opt, ERRORS_RO);
L
Linus Torvalds 已提交
823 824 825 826

	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
	
M
Martin J. Bligh 已提交
827 828
	set_opt(sbi->s_mount_opt, RESERVATION);

L
Linus Torvalds 已提交
829 830 831 832 833 834 835
	if (!parse_options ((char *) data, sbi))
		goto failed_mount;

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
		 MS_POSIXACL : 0);

836 837 838
	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
				    EXT2_MOUNT_XIP if not */

L
Linus Torvalds 已提交
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
	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U)))
		printk("EXT2-fs warning: feature flags set on rev 0 fs, "
		       "running e2fsck is recommended\n");
	/*
	 * Check feature flags regardless of the revision level, since we
	 * previously didn't change the revision level when setting the flags,
	 * so there is a chance incompat flags are set on a rev 0 filesystem.
	 */
	features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP);
	if (features) {
		printk("EXT2-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	if (!(sb->s_flags & MS_RDONLY) &&
	    (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
		printk("EXT2-fs: %s: couldn't mount RDWR because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}

	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);

N
Nick Piggin 已提交
867
	if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
868 869 870 871 872
		if (!silent)
			printk("XIP: Unsupported blocksize\n");
		goto failed_mount;
	}

L
Linus Torvalds 已提交
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
	/* If the blocksize doesn't match, re-read the thing.. */
	if (sb->s_blocksize != blocksize) {
		brelse(bh);

		if (!sb_set_blocksize(sb, blocksize)) {
			printk(KERN_ERR "EXT2-fs: blocksize too small for device.\n");
			goto failed_sbi;
		}

		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
		bh = sb_bread(sb, logic_sb_block);
		if(!bh) {
			printk("EXT2-fs: Couldn't read superblock on "
			       "2nd try.\n");
			goto failed_sbi;
		}
		es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) {
			printk ("EXT2-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);

	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO;
	} else {
		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
		if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) ||
V
vignesh babu 已提交
907
		    !is_power_of_2(sbi->s_inode_size) ||
L
Linus Torvalds 已提交
908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927
		    (sbi->s_inode_size > blocksize)) {
			printk ("EXT2-fs: unsupported inode size: %d\n",
				sbi->s_inode_size);
			goto failed_mount;
		}
	}

	sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
				   le32_to_cpu(es->s_log_frag_size);
	if (sbi->s_frag_size == 0)
		goto cantfind_ext2;
	sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;

	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);

	if (EXT2_INODE_SIZE(sb) == 0)
		goto cantfind_ext2;
	sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
928
	if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
L
Linus Torvalds 已提交
929 930 931 932 933 934 935 936
		goto cantfind_ext2;
	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = sb->s_blocksize /
					sizeof (struct ext2_group_desc);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits =
937
		ilog2 (EXT2_ADDR_PER_BLOCK(sb));
L
Linus Torvalds 已提交
938
	sbi->s_desc_per_block_bits =
939
		ilog2 (EXT2_DESC_PER_BLOCK(sb));
L
Linus Torvalds 已提交
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

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	if (sb->s_blocksize != bh->b_size) {
		if (!silent)
			printk ("VFS: Unsupported blocksize on dev "
				"%s.\n", sb->s_id);
		goto failed_mount;
	}

	if (sb->s_blocksize != sbi->s_frag_size) {
		printk ("EXT2-fs: fragsize %lu != blocksize %lu (not supported yet)\n",
			sbi->s_frag_size, sb->s_blocksize);
		goto failed_mount;
	}

	if (sbi->s_blocks_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #blocks per group too big: %lu\n",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #fragments per group too big: %lu\n",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext2;
E
Eric Sandeen 已提交
975 976 977
 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
 				le32_to_cpu(es->s_first_data_block) - 1)
 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
L
Linus Torvalds 已提交
978 979 980 981 982 983 984
	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
		   EXT2_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount;
	}
985
	bgl_lock_init(sbi->s_blockgroup_lock);
986
	sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
L
Linus Torvalds 已提交
987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007
	if (!sbi->s_debts) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount_group_desc;
	}
	for (i = 0; i < db_count; i++) {
		block = descriptor_loc(sb, logic_sb_block, i);
		sbi->s_group_desc[i] = sb_bread(sb, block);
		if (!sbi->s_group_desc[i]) {
			for (j = 0; j < i; j++)
				brelse (sbi->s_group_desc[j]);
			printk ("EXT2-fs: unable to read group descriptors\n");
			goto failed_mount_group_desc;
		}
	}
	if (!ext2_check_descriptors (sb)) {
		printk ("EXT2-fs: group descriptors corrupted!\n");
		goto failed_mount2;
	}
	sbi->s_gdb_count = db_count;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	spin_lock_init(&sbi->s_next_gen_lock);
1008

M
Martin J. Bligh 已提交
1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
	/* per fileystem reservation list head & lock */
	spin_lock_init(&sbi->s_rsv_window_lock);
	sbi->s_rsv_window_root = RB_ROOT;
	/*
	 * Add a single, static dummy reservation to the start of the
	 * reservation window list --- it gives us a placeholder for
	 * append-at-start-of-list which makes the allocation logic
	 * _much_ simpler.
	 */
	sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);

1024
	err = percpu_counter_init(&sbi->s_freeblocks_counter,
1025
				ext2_count_free_blocks(sb));
1026 1027
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
1028
				ext2_count_free_inodes(sb));
1029 1030 1031
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
1032
				ext2_count_dirs(sb));
1033 1034 1035 1036 1037
	}
	if (err) {
		printk(KERN_ERR "EXT2-fs: insufficient memory\n");
		goto failed_mount3;
	}
L
Linus Torvalds 已提交
1038 1039 1040 1041 1042 1043
	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext2_sops;
	sb->s_export_op = &ext2_export_ops;
	sb->s_xattr = ext2_xattr_handlers;
1044 1045 1046
	root = ext2_iget(sb, EXT2_ROOT_INO);
	if (IS_ERR(root)) {
		ret = PTR_ERR(root);
1047
		goto failed_mount3;
L
Linus Torvalds 已提交
1048 1049
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
1050
		iput(root);
L
Linus Torvalds 已提交
1051
		printk(KERN_ERR "EXT2-fs: corrupt root inode, run e2fsck\n");
1052
		goto failed_mount3;
L
Linus Torvalds 已提交
1053
	}
1054 1055 1056 1057 1058 1059 1060 1061

	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		iput(root);
		printk(KERN_ERR "EXT2-fs: get root inode failed\n");
		ret = -ENOMEM;
		goto failed_mount3;
	}
L
Linus Torvalds 已提交
1062
	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
1063
		ext2_warning(sb, __func__,
1064
			"mounting ext3 filesystem as ext2");
L
Linus Torvalds 已提交
1065 1066 1067 1068 1069 1070 1071 1072
	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
	return 0;

cantfind_ext2:
	if (!silent)
		printk("VFS: Can't find an ext2 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;
1073 1074 1075 1076
failed_mount3:
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
L
Linus Torvalds 已提交
1077 1078 1079 1080 1081 1082 1083 1084 1085 1086
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
failed_mount:
	brelse(bh);
failed_sbi:
	sb->s_fs_info = NULL;
1087
	kfree(sbi->s_blockgroup_lock);
L
Linus Torvalds 已提交
1088
	kfree(sbi);
1089
	return ret;
L
Linus Torvalds 已提交
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
}

static void ext2_commit_super (struct super_block * sb,
			       struct ext2_super_block * es)
{
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
{
	es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

/*
 * In the second extended file system, it is not necessary to
 * write the super block since we use a mapping of the
 * disk super block in a buffer.
 *
 * However, this function is still used to set the fs valid
 * flags to 0.  We need to set this flag to 0 since the fs
 * may have been checked while mounted and e2fsck may have
 * set s_state to EXT2_VALID_FS after some corrections.
 */

C
Christoph Hellwig 已提交
1121
static int ext2_sync_fs(struct super_block *sb, int wait)
L
Linus Torvalds 已提交
1122
{
C
Christoph Hellwig 已提交
1123 1124
	struct ext2_super_block *es = EXT2_SB(sb)->s_es;

L
Linus Torvalds 已提交
1125
	lock_kernel();
C
Christoph Hellwig 已提交
1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136
	if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
		ext2_debug("setting valid to 0\n");
		es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
		es->s_free_blocks_count =
			cpu_to_le32(ext2_count_free_blocks(sb));
		es->s_free_inodes_count =
			cpu_to_le32(ext2_count_free_inodes(sb));
		es->s_mtime = cpu_to_le32(get_seconds());
		ext2_sync_super(sb, es);
	} else {
		ext2_commit_super(sb, es);
L
Linus Torvalds 已提交
1137 1138 1139
	}
	sb->s_dirt = 0;
	unlock_kernel();
C
Christoph Hellwig 已提交
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150

	return 0;
}


void ext2_write_super(struct super_block *sb)
{
	if (!(sb->s_flags & MS_RDONLY))
		ext2_sync_fs(sb, 1);
	else
		sb->s_dirt = 0;
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156
}

static int ext2_remount (struct super_block * sb, int * flags, char * data)
{
	struct ext2_sb_info * sbi = EXT2_SB(sb);
	struct ext2_super_block * es;
1157
	unsigned long old_mount_opt = sbi->s_mount_opt;
1158 1159 1160 1161
	struct ext2_mount_options old_opts;
	unsigned long old_sb_flags;
	int err;

1162 1163
	lock_kernel();

1164 1165 1166 1167 1168
	/* Store the old options */
	old_sb_flags = sb->s_flags;
	old_opts.s_mount_opt = sbi->s_mount_opt;
	old_opts.s_resuid = sbi->s_resuid;
	old_opts.s_resgid = sbi->s_resgid;
L
Linus Torvalds 已提交
1169 1170 1171 1172

	/*
	 * Allow the "check" option to be passed as a remount option.
	 */
1173 1174 1175 1176
	if (!parse_options (data, sbi)) {
		err = -EINVAL;
		goto restore_opts;
	}
L
Linus Torvalds 已提交
1177 1178 1179 1180

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

1181 1182 1183 1184 1185
	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
				    EXT2_MOUNT_XIP if not */

	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
		printk("XIP: Unsupported blocksize\n");
1186
		err = -EINVAL;
1187 1188 1189
		goto restore_opts;
	}

L
Linus Torvalds 已提交
1190
	es = sbi->s_es;
1191 1192
	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
1193 1194 1195 1196 1197 1198
	    invalidate_inodes(sb)) {
		ext2_warning(sb, __func__, "refusing change of xip flag "
			     "with busy inodes while remounting");
		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
	}
1199 1200
	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
		unlock_kernel();
L
Linus Torvalds 已提交
1201
		return 0;
1202
	}
L
Linus Torvalds 已提交
1203 1204
	if (*flags & MS_RDONLY) {
		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
1205 1206
		    !(sbi->s_mount_state & EXT2_VALID_FS)) {
			unlock_kernel();
L
Linus Torvalds 已提交
1207
			return 0;
1208
		}
L
Linus Torvalds 已提交
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
		/*
		 * OK, we are remounting a valid rw partition rdonly, so set
		 * the rdonly flag and then mark the partition as valid again.
		 */
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		es->s_mtime = cpu_to_le32(get_seconds());
	} else {
		__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
					       ~EXT2_FEATURE_RO_COMPAT_SUPP);
		if (ret) {
			printk("EXT2-fs: %s: couldn't remount RDWR because of "
			       "unsupported optional features (%x).\n",
			       sb->s_id, le32_to_cpu(ret));
1222 1223
			err = -EROFS;
			goto restore_opts;
L
Linus Torvalds 已提交
1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
		}
		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by e2fsck since we originally mounted the partition.)
		 */
		sbi->s_mount_state = le16_to_cpu(es->s_state);
		if (!ext2_setup_super (sb, es, 0))
			sb->s_flags &= ~MS_RDONLY;
	}
	ext2_sync_super(sb, es);
1235
	unlock_kernel();
L
Linus Torvalds 已提交
1236
	return 0;
1237 1238 1239 1240 1241
restore_opts:
	sbi->s_mount_opt = old_opts.s_mount_opt;
	sbi->s_resuid = old_opts.s_resuid;
	sbi->s_resgid = old_opts.s_resgid;
	sb->s_flags = old_sb_flags;
1242
	unlock_kernel();
1243
	return err;
L
Linus Torvalds 已提交
1244 1245
}

1246
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
L
Linus Torvalds 已提交
1247
{
1248
	struct super_block *sb = dentry->d_sb;
L
Linus Torvalds 已提交
1249
	struct ext2_sb_info *sbi = EXT2_SB(sb);
P
Pekka Enberg 已提交
1250 1251
	struct ext2_super_block *es = sbi->s_es;
	u64 fsid;
L
Linus Torvalds 已提交
1252 1253

	if (test_opt (sb, MINIX_DF))
B
Badari Pulavarty 已提交
1254 1255 1256 1257 1258
		sbi->s_overhead_last = 0;
	else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
		unsigned long i, overhead = 0;
		smp_rmb();

L
Linus Torvalds 已提交
1259
		/*
B
Badari Pulavarty 已提交
1260 1261 1262
		 * Compute the overhead (FS structures). This is constant
		 * for a given filesystem unless the number of block groups
		 * changes so we cache the previous value until it does.
L
Linus Torvalds 已提交
1263 1264 1265 1266 1267 1268
		 */

		/*
		 * All of the blocks before first_data_block are
		 * overhead
		 */
P
Pekka Enberg 已提交
1269
		overhead = le32_to_cpu(es->s_first_data_block);
L
Linus Torvalds 已提交
1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285

		/*
		 * Add the overhead attributed to the superblock and
		 * block group descriptors.  If the sparse superblocks
		 * feature is turned on, then not all groups have this.
		 */
		for (i = 0; i < sbi->s_groups_count; i++)
			overhead += ext2_bg_has_super(sb, i) +
				ext2_bg_num_gdb(sb, i);

		/*
		 * Every block group has an inode bitmap, a block
		 * bitmap, and an inode table.
		 */
		overhead += (sbi->s_groups_count *
			     (2 + sbi->s_itb_per_group));
B
Badari Pulavarty 已提交
1286 1287 1288
		sbi->s_overhead_last = overhead;
		smp_wmb();
		sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
L
Linus Torvalds 已提交
1289 1290 1291 1292
	}

	buf->f_type = EXT2_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
B
Badari Pulavarty 已提交
1293
	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
L
Linus Torvalds 已提交
1294
	buf->f_bfree = ext2_count_free_blocks(sb);
B
Badari Pulavarty 已提交
1295
	es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
P
Pekka Enberg 已提交
1296 1297
	buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
	if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
L
Linus Torvalds 已提交
1298
		buf->f_bavail = 0;
P
Pekka Enberg 已提交
1299 1300
	buf->f_files = le32_to_cpu(es->s_inodes_count);
	buf->f_ffree = ext2_count_free_inodes(sb);
B
Badari Pulavarty 已提交
1301
	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
L
Linus Torvalds 已提交
1302
	buf->f_namelen = EXT2_NAME_LEN;
P
Pekka Enberg 已提交
1303 1304 1305 1306
	fsid = le64_to_cpup((void *)es->s_uuid) ^
	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
L
Linus Torvalds 已提交
1307 1308 1309
	return 0;
}

1310 1311
static int ext2_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
1312
{
1313
	return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt);
L
Linus Torvalds 已提交
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
}

#ifdef CONFIG_QUOTA

/* Read data from quotafile - avoid pagecache and such because we cannot afford
 * acquiring the locks... As quota files are never truncated and quota code
 * itself serializes the operations (and noone else should touch the files)
 * we don't have to be afraid of races */
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t toread;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;
	loff_t i_size = i_size_read(inode);

	if (off > i_size)
		return 0;
	if (off+len > i_size)
		len = i_size-off;
	toread = len;
	while (toread > 0) {
		tocopy = sb->s_blocksize - offset < toread ?
				sb->s_blocksize - offset : toread;

		tmp_bh.b_state = 0;
1345
		tmp_bh.b_size = sb->s_blocksize;
L
Linus Torvalds 已提交
1346
		err = ext2_get_block(inode, blk, &tmp_bh, 0);
M
Martin J. Bligh 已提交
1347
		if (err < 0)
L
Linus Torvalds 已提交
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
			return err;
		if (!buffer_mapped(&tmp_bh))	/* A hole? */
			memset(data, 0, tocopy);
		else {
			bh = sb_bread(sb, tmp_bh.b_blocknr);
			if (!bh)
				return -EIO;
			memcpy(data, bh->b_data+offset, tocopy);
			brelse(bh);
		}
		offset = 0;
		toread -= tocopy;
		data += tocopy;
		blk++;
	}
	return len;
}

/* Write to quotafile */
static ssize_t ext2_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t towrite = len;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;

1379
	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
L
Linus Torvalds 已提交
1380 1381 1382 1383 1384 1385
	while (towrite > 0) {
		tocopy = sb->s_blocksize - offset < towrite ?
				sb->s_blocksize - offset : towrite;

		tmp_bh.b_state = 0;
		err = ext2_get_block(inode, blk, &tmp_bh, 1);
M
Martin J. Bligh 已提交
1386
		if (err < 0)
L
Linus Torvalds 已提交
1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408
			goto out;
		if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
			bh = sb_bread(sb, tmp_bh.b_blocknr);
		else
			bh = sb_getblk(sb, tmp_bh.b_blocknr);
		if (!bh) {
			err = -EIO;
			goto out;
		}
		lock_buffer(bh);
		memcpy(bh->b_data+offset, data, tocopy);
		flush_dcache_page(bh->b_page);
		set_buffer_uptodate(bh);
		mark_buffer_dirty(bh);
		unlock_buffer(bh);
		brelse(bh);
		offset = 0;
		towrite -= tocopy;
		data += tocopy;
		blk++;
	}
out:
1409 1410
	if (len == towrite) {
		mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
1411
		return err;
1412
	}
L
Linus Torvalds 已提交
1413 1414 1415 1416 1417
	if (inode->i_size < off+len-towrite)
		i_size_write(inode, off+len-towrite);
	inode->i_version++;
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	mark_inode_dirty(inode);
1418
	mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459
	return len - towrite;
}

#endif

static struct file_system_type ext2_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext2",
	.get_sb		= ext2_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init init_ext2_fs(void)
{
	int err = init_ext2_xattr();
	if (err)
		return err;
	err = init_inodecache();
	if (err)
		goto out1;
        err = register_filesystem(&ext2_fs_type);
	if (err)
		goto out;
	return 0;
out:
	destroy_inodecache();
out1:
	exit_ext2_xattr();
	return err;
}

static void __exit exit_ext2_fs(void)
{
	unregister_filesystem(&ext2_fs_type);
	destroy_inodecache();
	exit_ext2_xattr();
}

module_init(init_ext2_fs)
module_exit(exit_ext2_fs)