super.c 75.8 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 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
/*
 *  linux/fs/ext3/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>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd.h>
#include <linux/ext3_fs.h>
#include <linux/ext3_jbd.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
37
#include <linux/seq_file.h>
B
Ben Dooks 已提交
38

L
Linus Torvalds 已提交
39
#include <asm/uaccess.h>
B
Ben Dooks 已提交
40

L
Linus Torvalds 已提交
41 42
#include "xattr.h"
#include "acl.h"
B
Ben Dooks 已提交
43
#include "namei.h"
L
Linus Torvalds 已提交
44

45 46
static int ext3_load_journal(struct super_block *, struct ext3_super_block *,
			     unsigned long journal_devnum);
L
Linus Torvalds 已提交
47
static int ext3_create_journal(struct super_block *, struct ext3_super_block *,
48
			       unsigned int);
L
Linus Torvalds 已提交
49 50 51 52 53 54 55 56 57 58 59
static void ext3_commit_super (struct super_block * sb,
			       struct ext3_super_block * es,
			       int sync);
static void ext3_mark_recovery_complete(struct super_block * sb,
					struct ext3_super_block * es);
static void ext3_clear_journal_err(struct super_block * sb,
				   struct ext3_super_block * es);
static int ext3_sync_fs(struct super_block *sb, int wait);
static const char *ext3_decode_error(struct super_block * sb, int errno,
				     char nbuf[16]);
static int ext3_remount (struct super_block * sb, int * flags, char * data);
60
static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
L
Linus Torvalds 已提交
61 62 63 64
static void ext3_unlockfs(struct super_block *sb);
static void ext3_write_super (struct super_block * sb);
static void ext3_write_super_lockfs(struct super_block *sb);

65
/*
L
Linus Torvalds 已提交
66 67 68 69 70
 * Wrappers for journal_start/end.
 *
 * The only special thing we need to do here is to make sure that all
 * journal_end calls result in the superblock being marked dirty, so
 * that sync() will call the filesystem's write_super callback if
71
 * appropriate.
L
Linus Torvalds 已提交
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
 */
handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
{
	journal_t *journal;

	if (sb->s_flags & MS_RDONLY)
		return ERR_PTR(-EROFS);

	/* Special case here: if the journal has aborted behind our
	 * backs (eg. EIO in the commit thread), then we still need to
	 * take the FS itself readonly cleanly. */
	journal = EXT3_SB(sb)->s_journal;
	if (is_journal_aborted(journal)) {
		ext3_abort(sb, __FUNCTION__,
			   "Detected aborted journal");
		return ERR_PTR(-EROFS);
	}

	return journal_start(journal, nblocks);
}

93
/*
L
Linus Torvalds 已提交
94 95 96
 * The only special thing we need to do here is to make sure that all
 * journal_stop calls result in the superblock being marked dirty, so
 * that sync() will call the filesystem's write_super callback if
97
 * appropriate.
L
Linus Torvalds 已提交
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
 */
int __ext3_journal_stop(const char *where, handle_t *handle)
{
	struct super_block *sb;
	int err;
	int rc;

	sb = handle->h_transaction->t_journal->j_private;
	err = handle->h_err;
	rc = journal_stop(handle);

	if (!err)
		err = rc;
	if (err)
		__ext3_std_error(sb, where, err);
	return err;
}

void ext3_journal_abort_handle(const char *caller, const char *err_fn,
		struct buffer_head *bh, handle_t *handle, int err)
{
	char nbuf[16];
	const char *errstr = ext3_decode_error(NULL, err, nbuf);

	if (bh)
		BUFFER_TRACE(bh, "abort");

	if (!handle->h_err)
		handle->h_err = err;

	if (is_handle_aborted(handle))
		return;

	printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
	       caller, errstr, err_fn);

	journal_abort_handle(handle);
}

/* Deal with the reporting of failure conditions on a filesystem such as
 * inconsistencies detected or read IO failures.
 *
 * On ext2, we can store the error state of the filesystem in the
 * superblock.  That is not possible on ext3, because we may have other
 * write ordering constraints on the superblock which prevent us from
 * writing it out straight away; and given that the journal is about to
 * be aborted, we can't rely on the current, or future, transactions to
 * write out the superblock safely.
 *
 * We'll just use the journal_abort() error code to record an error in
 * the journal instead.  On recovery, the journal will compain about
 * that error until we've noted it down and cleared it.
 */

static void ext3_handle_error(struct super_block *sb)
{
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;

	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
	es->s_state |= cpu_to_le16(EXT3_ERROR_FS);

	if (sb->s_flags & MS_RDONLY)
		return;

	if (test_opt (sb, ERRORS_RO)) {
		printk (KERN_CRIT "Remounting filesystem read-only\n");
		sb->s_flags |= MS_RDONLY;
	} else {
		journal_t *journal = EXT3_SB(sb)->s_journal;

		EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
		if (journal)
			journal_abort(journal, -EIO);
	}
	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT3-fs (device %s): panic forced after error\n",
			sb->s_id);
	ext3_commit_super(sb, es, 1);
}

void ext3_error (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	ext3_handle_error(sb);
}

static const char *ext3_decode_error(struct super_block * sb, int errno,
				     char nbuf[16])
{
	char *errstr = NULL;

	switch (errno) {
	case -EIO:
		errstr = "IO failure";
		break;
	case -ENOMEM:
		errstr = "Out of memory";
		break;
	case -EROFS:
		if (!sb || EXT3_SB(sb)->s_journal->j_flags & JFS_ABORT)
			errstr = "Journal has aborted";
		else
			errstr = "Readonly filesystem";
		break;
	default:
		/* If the caller passed in an extra buffer for unknown
		 * errors, textualise them now.  Else we just return
		 * NULL. */
		if (nbuf) {
			/* Check for truncated error codes... */
			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
				errstr = nbuf;
		}
		break;
	}

	return errstr;
}

/* __ext3_std_error decodes expected errors from journaling functions
 * automatically and invokes the appropriate error response.  */

void __ext3_std_error (struct super_block * sb, const char * function,
		       int errno)
{
	char nbuf[16];
232
	const char *errstr;
L
Linus Torvalds 已提交
233

234 235 236 237 238 239 240 241
	/* Special case: if the error is EROFS, and we're not already
	 * inside a transaction, then there's really no point in logging
	 * an error. */
	if (errno == -EROFS && journal_current_handle() == NULL &&
	    (sb->s_flags & MS_RDONLY))
		return;

	errstr = ext3_decode_error(sb, errno, nbuf);
L
Linus Torvalds 已提交
242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
	printk (KERN_CRIT "EXT3-fs error (device %s) in %s: %s\n",
		sb->s_id, function, errstr);

	ext3_handle_error(sb);
}

/*
 * ext3_abort is a much stronger failure handler than ext3_error.  The
 * abort function may be used to deal with unrecoverable failures such
 * as journal IO errors or ENOMEM at a critical moment in log management.
 *
 * We unconditionally force the filesystem into an ABORT|READONLY state,
 * unless the error response on the fs has been set to panic in which
 * case we take the easy way out and panic immediately.
 */

void ext3_abort (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;

	printk (KERN_CRIT "ext3_abort called.\n");

	va_start(args, fmt);
	printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT3-fs panic from previous error\n");

	if (sb->s_flags & MS_RDONLY)
		return;

	printk(KERN_CRIT "Remounting filesystem read-only\n");
	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
	sb->s_flags |= MS_RDONLY;
	EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
	journal_abort(EXT3_SB(sb)->s_journal, -EIO);
}

void ext3_warning (struct super_block * sb, const char * function,
		   const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_WARNING "EXT3-fs warning (device %s): %s: ",
	       sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);
}

void ext3_update_dynamic_rev(struct super_block *sb)
{
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV)
		return;

	ext3_warning(sb, __FUNCTION__,
		     "updating to rev %d because of new feature flag, "
		     "running e2fsck is recommended",
		     EXT3_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT3_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT3_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT3_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.
	 */
}

/*
 * Open the external journal device
 */
static struct block_device *ext3_blkdev_get(dev_t dev)
{
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
	if (IS_ERR(bdev))
		goto fail;
	return bdev;

fail:
	printk(KERN_ERR "EXT3: failed to open journal device %s: %ld\n",
			__bdevname(dev, b), PTR_ERR(bdev));
	return NULL;
}

/*
 * Release the journal device
 */
static int ext3_blkdev_put(struct block_device *bdev)
{
	bd_release(bdev);
	return blkdev_put(bdev);
}

static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
{
	struct block_device *bdev;
	int ret = -ENODEV;

	bdev = sbi->journal_bdev;
	if (bdev) {
		ret = ext3_blkdev_put(bdev);
		sbi->journal_bdev = NULL;
	}
	return ret;
}

static inline struct inode *orphan_list_entry(struct list_head *l)
{
	return &list_entry(l, struct ext3_inode_info, i_orphan)->vfs_inode;
}

static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi)
{
	struct list_head *l;

372
	printk(KERN_ERR "sb orphan head is %d\n",
L
Linus Torvalds 已提交
373 374 375 376 377 378
	       le32_to_cpu(sbi->s_es->s_last_orphan));

	printk(KERN_ERR "sb_info orphan list:\n");
	list_for_each(l, &sbi->s_orphan) {
		struct inode *inode = orphan_list_entry(l);
		printk(KERN_ERR "  "
379
		       "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
L
Linus Torvalds 已提交
380
		       inode->i_sb->s_id, inode->i_ino, inode,
381
		       inode->i_mode, inode->i_nlink,
L
Linus Torvalds 已提交
382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
		       NEXT_ORPHAN(inode));
	}
}

static void ext3_put_super (struct super_block * sb)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
	int i;

	ext3_xattr_put_super(sb);
	journal_destroy(sbi->s_journal);
	if (!(sb->s_flags & MS_RDONLY)) {
		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		BUFFER_TRACE(sbi->s_sbh, "marking dirty");
		mark_buffer_dirty(sbi->s_sbh);
		ext3_commit_super(sb, es, 1);
	}

	for (i = 0; i < sbi->s_gdb_count; i++)
		brelse(sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	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);
#ifdef CONFIG_QUOTA
	for (i = 0; i < MAXQUOTAS; i++)
		kfree(sbi->s_qf_names[i]);
#endif

	/* Debugging code just in case the in-memory inode orphan list
	 * isn't empty.  The on-disk one can be non-empty if we've
	 * detected an error and taken the fs readonly, but the
	 * in-memory list had better be clean by this point. */
	if (!list_empty(&sbi->s_orphan))
		dump_orphan_list(sb, sbi);
	J_ASSERT(list_empty(&sbi->s_orphan));

	invalidate_bdev(sb->s_bdev, 0);
	if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
		/*
		 * Invalidate the journal device's buffers.  We don't want them
		 * floating about in memory - the physical journal device may
		 * hotswapped, and it breaks the `ro-after' testing code.
		 */
		sync_blockdev(sbi->journal_bdev);
		invalidate_bdev(sbi->journal_bdev, 0);
		ext3_blkdev_remove(sbi);
	}
	sb->s_fs_info = NULL;
	kfree(sbi);
	return;
}

static kmem_cache_t *ext3_inode_cachep;

/*
 * Called inside transaction, so use GFP_NOFS
 */
static struct inode *ext3_alloc_inode(struct super_block *sb)
{
	struct ext3_inode_info *ei;

	ei = kmem_cache_alloc(ext3_inode_cachep, SLAB_NOFS);
	if (!ei)
		return NULL;
#ifdef CONFIG_EXT3_FS_POSIX_ACL
	ei->i_acl = EXT3_ACL_NOT_CACHED;
	ei->i_default_acl = EXT3_ACL_NOT_CACHED;
#endif
	ei->i_block_alloc_info = NULL;
	ei->vfs_inode.i_version = 1;
	return &ei->vfs_inode;
}

static void ext3_destroy_inode(struct inode *inode)
{
	kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
}

static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
{
	struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;

	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
	    SLAB_CTOR_CONSTRUCTOR) {
		INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT3_FS_XATTR
		init_rwsem(&ei->xattr_sem);
#endif
474
		mutex_init(&ei->truncate_mutex);
L
Linus Torvalds 已提交
475 476 477
		inode_init_once(&ei->vfs_inode);
	}
}
478

L
Linus Torvalds 已提交
479 480 481 482
static int init_inodecache(void)
{
	ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",
					     sizeof(struct ext3_inode_info),
483 484
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
L
Linus Torvalds 已提交
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500
					     init_once, NULL);
	if (ext3_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	if (kmem_cache_destroy(ext3_inode_cachep))
		printk(KERN_INFO "ext3_inode_cache: not all structures were freed\n");
}

static void ext3_clear_inode(struct inode *inode)
{
	struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info;
#ifdef CONFIG_EXT3_FS_POSIX_ACL
501 502 503 504 505 506 507 508 509 510
	if (EXT3_I(inode)->i_acl &&
			EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) {
		posix_acl_release(EXT3_I(inode)->i_acl);
		EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED;
	}
	if (EXT3_I(inode)->i_default_acl &&
			EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) {
		posix_acl_release(EXT3_I(inode)->i_default_acl);
		EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED;
	}
L
Linus Torvalds 已提交
511 512 513
#endif
	ext3_discard_reservation(inode);
	EXT3_I(inode)->i_block_alloc_info = NULL;
514 515
	if (unlikely(rsv))
		kfree(rsv);
L
Linus Torvalds 已提交
516 517
}

518
static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
519
{
520
#if defined(CONFIG_QUOTA)
521
	struct ext3_sb_info *sbi = EXT3_SB(sb);
522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538

	if (sbi->s_jquota_fmt)
		seq_printf(seq, ",jqfmt=%s",
		(sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");

	if (sbi->s_qf_names[USRQUOTA])
		seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);

	if (sbi->s_qf_names[GRPQUOTA])
		seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);

	if (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA)
		seq_puts(seq, ",usrquota");

	if (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)
		seq_puts(seq, ",grpquota");
#endif
539 540 541 542 543 544 545 546 547 548 549 550 551 552
}

static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct super_block *sb = vfs->mnt_sb;

	if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
		seq_puts(seq, ",data=journal");
	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
		seq_puts(seq, ",data=ordered");
	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
		seq_puts(seq, ",data=writeback");

	ext3_show_quota_options(seq, sb);
553 554 555

	return 0;
}
L
Linus Torvalds 已提交
556

557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597

static struct dentry *ext3_get_dentry(struct super_block *sb, void *vobjp)
{
	__u32 *objp = vobjp;
	unsigned long ino = objp[0];
	__u32 generation = objp[1];
	struct inode *inode;
	struct dentry *result;

	if (ino < EXT3_FIRST_INO(sb) && ino != EXT3_ROOT_INO)
		return ERR_PTR(-ESTALE);
	if (ino > le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count))
		return ERR_PTR(-ESTALE);

	/* iget isn't really right if the inode is currently unallocated!!
	 *
	 * ext3_read_inode will return a bad_inode if the inode had been
	 * deleted, so we should be safe.
	 *
	 * Currently we don't know the generation for parent directory, so
	 * a generation of 0 means "accept any"
	 */
	inode = iget(sb, ino);
	if (inode == NULL)
		return ERR_PTR(-ENOMEM);
	if (is_bad_inode(inode) ||
	    (generation && inode->i_generation != generation)) {
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
	/* now to find a dentry.
	 * If possible, get a well-connected one
	 */
	result = d_alloc_anon(inode);
	if (!result) {
		iput(inode);
		return ERR_PTR(-ENOMEM);
	}
	return result;
}

598
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))

static int ext3_dquot_initialize(struct inode *inode, int type);
static int ext3_dquot_drop(struct inode *inode);
static int ext3_write_dquot(struct dquot *dquot);
static int ext3_acquire_dquot(struct dquot *dquot);
static int ext3_release_dquot(struct dquot *dquot);
static int ext3_mark_dquot_dirty(struct dquot *dquot);
static int ext3_write_info(struct super_block *sb, int type);
static int ext3_quota_on(struct super_block *sb, int type, int format_id, char *path);
static int ext3_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off);
static ssize_t ext3_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off);

static struct dquot_operations ext3_quota_operations = {
	.initialize	= ext3_dquot_initialize,
	.drop		= ext3_dquot_drop,
	.alloc_space	= dquot_alloc_space,
	.alloc_inode	= dquot_alloc_inode,
	.free_space	= dquot_free_space,
	.free_inode	= dquot_free_inode,
	.transfer	= dquot_transfer,
	.write_dquot	= ext3_write_dquot,
	.acquire_dquot	= ext3_acquire_dquot,
	.release_dquot	= ext3_release_dquot,
	.mark_dirty	= ext3_mark_dquot_dirty,
	.write_info	= ext3_write_info
};

static struct quotactl_ops ext3_qctl_operations = {
	.quota_on	= ext3_quota_on,
	.quota_off	= vfs_quota_off,
	.quota_sync	= vfs_quota_sync,
	.get_info	= vfs_get_dqinfo,
	.set_info	= vfs_set_dqinfo,
	.get_dqblk	= vfs_get_dqblk,
	.set_dqblk	= vfs_set_dqblk
};
#endif

static struct super_operations ext3_sops = {
	.alloc_inode	= ext3_alloc_inode,
	.destroy_inode	= ext3_destroy_inode,
	.read_inode	= ext3_read_inode,
	.write_inode	= ext3_write_inode,
	.dirty_inode	= ext3_dirty_inode,
	.delete_inode	= ext3_delete_inode,
	.put_super	= ext3_put_super,
	.write_super	= ext3_write_super,
	.sync_fs	= ext3_sync_fs,
	.write_super_lockfs = ext3_write_super_lockfs,
	.unlockfs	= ext3_unlockfs,
	.statfs		= ext3_statfs,
	.remount_fs	= ext3_remount,
	.clear_inode	= ext3_clear_inode,
657
	.show_options	= ext3_show_options,
L
Linus Torvalds 已提交
658 659 660 661 662 663 664 665
#ifdef CONFIG_QUOTA
	.quota_read	= ext3_quota_read,
	.quota_write	= ext3_quota_write,
#endif
};

static struct export_operations ext3_export_ops = {
	.get_parent = ext3_get_parent,
666
	.get_dentry = ext3_get_dentry,
L
Linus Torvalds 已提交
667 668 669 670 671
};

enum {
	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
A
Adrian Bunk 已提交
672
	Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
L
Linus Torvalds 已提交
673
	Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
674
	Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
675
	Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
L
Linus Torvalds 已提交
676 677
	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
678
	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
679 680
	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
	Opt_grpquota
L
Linus Torvalds 已提交
681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
};

static match_table_t tokens = {
	{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, "nocheck"},
	{Opt_nocheck, "check=none"},
	{Opt_debug, "debug"},
	{Opt_oldalloc, "oldalloc"},
	{Opt_orlov, "orlov"},
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
	{Opt_reservation, "reservation"},
	{Opt_noreservation, "noreservation"},
	{Opt_noload, "noload"},
	{Opt_nobh, "nobh"},
710
	{Opt_bh, "bh"},
L
Linus Torvalds 已提交
711 712 713
	{Opt_commit, "commit=%u"},
	{Opt_journal_update, "journal=update"},
	{Opt_journal_inum, "journal=%u"},
714
	{Opt_journal_dev, "journal_dev=%u"},
L
Linus Torvalds 已提交
715 716 717 718 719 720 721 722 723 724
	{Opt_abort, "abort"},
	{Opt_data_journal, "data=journal"},
	{Opt_data_ordered, "data=ordered"},
	{Opt_data_writeback, "data=writeback"},
	{Opt_offusrjquota, "usrjquota="},
	{Opt_usrjquota, "usrjquota=%s"},
	{Opt_offgrpjquota, "grpjquota="},
	{Opt_grpjquota, "grpjquota=%s"},
	{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
	{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
725
	{Opt_grpquota, "grpquota"},
726 727
	{Opt_noquota, "noquota"},
	{Opt_quota, "quota"},
728
	{Opt_usrquota, "usrquota"},
L
Linus Torvalds 已提交
729 730 731 732 733
	{Opt_barrier, "barrier=%u"},
	{Opt_err, NULL},
	{Opt_resize, "resize"},
};

734
static ext3_fsblk_t get_sb_block(void **data)
L
Linus Torvalds 已提交
735
{
736
	ext3_fsblk_t 	sb_block;
L
Linus Torvalds 已提交
737 738 739 740 741
	char 		*options = (char *) *data;

	if (!options || strncmp(options, "sb=", 3) != 0)
		return 1;	/* Default location */
	options += 3;
742
	/*todo: use simple_strtoll with >32bit ext3 */
L
Linus Torvalds 已提交
743 744 745 746 747 748 749 750 751 752 753 754
	sb_block = simple_strtoul(options, &options, 0);
	if (*options && *options != ',') {
		printk("EXT3-fs: Invalid sb specification: %s\n",
		       (char *) *data);
		return 1;
	}
	if (*options == ',')
		options++;
	*data = (void *) options;
	return sb_block;
}

755
static int parse_options (char *options, struct super_block *sb,
756
			  unsigned int *inum, unsigned long *journal_devnum,
757
			  ext3_fsblk_t *n_blocks_count, int is_remount)
L
Linus Torvalds 已提交
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	char * p;
	substring_t args[MAX_OPT_ARGS];
	int data_opt = 0;
	int option;
#ifdef CONFIG_QUOTA
	int qtype;
	char *qname;
#endif

	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:
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			set_opt (sbi->s_mount_opt, ERRORS_PANIC);
			break;
		case Opt_err_ro:
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_RO);
			break;
		case Opt_err_cont:
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_CONT);
			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;
#ifdef CONFIG_EXT3_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("EXT3 (no)user_xattr options not supported\n");
			break;
#endif
#ifdef CONFIG_EXT3_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("EXT3 (no)acl options not supported\n");
			break;
#endif
		case Opt_reservation:
			set_opt(sbi->s_mount_opt, RESERVATION);
			break;
		case Opt_noreservation:
			clear_opt(sbi->s_mount_opt, RESERVATION);
			break;
		case Opt_journal_update:
			/* @@@ FIXME */
			/* Eventually we will want to be able to create
			   a journal file here.  For now, only allow the
			   user to specify an existing inode to be the
			   journal file. */
			if (is_remount) {
				printk(KERN_ERR "EXT3-fs: cannot specify "
				       "journal on remount\n");
				return 0;
			}
			set_opt (sbi->s_mount_opt, UPDATE_JOURNAL);
			break;
		case Opt_journal_inum:
			if (is_remount) {
				printk(KERN_ERR "EXT3-fs: cannot specify "
				       "journal on remount\n");
				return 0;
			}
			if (match_int(&args[0], &option))
				return 0;
			*inum = option;
			break;
890 891 892 893 894 895 896 897 898 899
		case Opt_journal_dev:
			if (is_remount) {
				printk(KERN_ERR "EXT3-fs: cannot specify "
				       "journal on remount\n");
				return 0;
			}
			if (match_int(&args[0], &option))
				return 0;
			*journal_devnum = option;
			break;
L
Linus Torvalds 已提交
900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
		case Opt_noload:
			set_opt (sbi->s_mount_opt, NOLOAD);
			break;
		case Opt_commit:
			if (match_int(&args[0], &option))
				return 0;
			if (option < 0)
				return 0;
			if (option == 0)
				option = JBD_DEFAULT_MAX_COMMIT_AGE;
			sbi->s_commit_interval = HZ * option;
			break;
		case Opt_data_journal:
			data_opt = EXT3_MOUNT_JOURNAL_DATA;
			goto datacheck;
		case Opt_data_ordered:
			data_opt = EXT3_MOUNT_ORDERED_DATA;
			goto datacheck;
		case Opt_data_writeback:
			data_opt = EXT3_MOUNT_WRITEBACK_DATA;
		datacheck:
			if (is_remount) {
				if ((sbi->s_mount_opt & EXT3_MOUNT_DATA_FLAGS)
						!= data_opt) {
					printk(KERN_ERR
						"EXT3-fs: cannot change data "
						"mode on remount\n");
					return 0;
				}
			} else {
				sbi->s_mount_opt &= ~EXT3_MOUNT_DATA_FLAGS;
				sbi->s_mount_opt |= data_opt;
			}
			break;
#ifdef CONFIG_QUOTA
		case Opt_usrjquota:
			qtype = USRQUOTA;
			goto set_qf_name;
		case Opt_grpjquota:
			qtype = GRPQUOTA;
set_qf_name:
			if (sb_any_quota_enabled(sb)) {
				printk(KERN_ERR
					"EXT3-fs: Cannot change journalled "
					"quota options when quota turned on.\n");
				return 0;
			}
			qname = match_strdup(&args[0]);
			if (!qname) {
				printk(KERN_ERR
					"EXT3-fs: not enough memory for "
					"storing quotafile name.\n");
				return 0;
			}
			if (sbi->s_qf_names[qtype] &&
			    strcmp(sbi->s_qf_names[qtype], qname)) {
				printk(KERN_ERR
					"EXT3-fs: %s quota file already "
					"specified.\n", QTYPE2NAME(qtype));
				kfree(qname);
				return 0;
			}
			sbi->s_qf_names[qtype] = qname;
			if (strchr(sbi->s_qf_names[qtype], '/')) {
				printk(KERN_ERR
					"EXT3-fs: quotafile must be on "
					"filesystem root.\n");
				kfree(sbi->s_qf_names[qtype]);
				sbi->s_qf_names[qtype] = NULL;
				return 0;
			}
971
			set_opt(sbi->s_mount_opt, QUOTA);
L
Linus Torvalds 已提交
972 973 974 975 976 977 978 979 980 981 982 983 984
			break;
		case Opt_offusrjquota:
			qtype = USRQUOTA;
			goto clear_qf_name;
		case Opt_offgrpjquota:
			qtype = GRPQUOTA;
clear_qf_name:
			if (sb_any_quota_enabled(sb)) {
				printk(KERN_ERR "EXT3-fs: Cannot change "
					"journalled quota options when "
					"quota turned on.\n");
				return 0;
			}
J
Jan Kara 已提交
985 986 987 988
			/*
			 * The space will be released later when all options
			 * are confirmed to be correct
			 */
L
Linus Torvalds 已提交
989 990 991 992 993 994 995 996
			sbi->s_qf_names[qtype] = NULL;
			break;
		case Opt_jqfmt_vfsold:
			sbi->s_jquota_fmt = QFMT_VFS_OLD;
			break;
		case Opt_jqfmt_vfsv0:
			sbi->s_jquota_fmt = QFMT_VFS_V0;
			break;
997
		case Opt_quota:
998 999 1000 1001 1002
		case Opt_usrquota:
			set_opt(sbi->s_mount_opt, QUOTA);
			set_opt(sbi->s_mount_opt, USRQUOTA);
			break;
		case Opt_grpquota:
1003
			set_opt(sbi->s_mount_opt, QUOTA);
1004
			set_opt(sbi->s_mount_opt, GRPQUOTA);
1005 1006 1007 1008 1009 1010 1011 1012
			break;
		case Opt_noquota:
			if (sb_any_quota_enabled(sb)) {
				printk(KERN_ERR "EXT3-fs: Cannot change quota "
					"options when quota turned on.\n");
				return 0;
			}
			clear_opt(sbi->s_mount_opt, QUOTA);
1013 1014
			clear_opt(sbi->s_mount_opt, USRQUOTA);
			clear_opt(sbi->s_mount_opt, GRPQUOTA);
1015
			break;
L
Linus Torvalds 已提交
1016
#else
1017 1018 1019
		case Opt_quota:
		case Opt_usrquota:
		case Opt_grpquota:
L
Linus Torvalds 已提交
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
		case Opt_usrjquota:
		case Opt_grpjquota:
		case Opt_offusrjquota:
		case Opt_offgrpjquota:
		case Opt_jqfmt_vfsold:
		case Opt_jqfmt_vfsv0:
			printk(KERN_ERR
				"EXT3-fs: journalled quota options not "
				"supported.\n");
			break;
1030 1031
		case Opt_noquota:
			break;
L
Linus Torvalds 已提交
1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046
#endif
		case Opt_abort:
			set_opt(sbi->s_mount_opt, ABORT);
			break;
		case Opt_barrier:
			if (match_int(&args[0], &option))
				return 0;
			if (option)
				set_opt(sbi->s_mount_opt, BARRIER);
			else
				clear_opt(sbi->s_mount_opt, BARRIER);
			break;
		case Opt_ignore:
			break;
		case Opt_resize:
J
Jan Kara 已提交
1047
			if (!is_remount) {
L
Linus Torvalds 已提交
1048 1049 1050 1051
				printk("EXT3-fs: resize option only available "
					"for remount\n");
				return 0;
			}
1052 1053
			if (match_int(&args[0], &option) != 0)
				return 0;
L
Linus Torvalds 已提交
1054 1055 1056 1057 1058
			*n_blocks_count = option;
			break;
		case Opt_nobh:
			set_opt(sbi->s_mount_opt, NOBH);
			break;
1059 1060 1061
		case Opt_bh:
			clear_opt(sbi->s_mount_opt, NOBH);
			break;
L
Linus Torvalds 已提交
1062 1063 1064 1065 1066 1067 1068 1069
		default:
			printk (KERN_ERR
				"EXT3-fs: Unrecognized mount option \"%s\" "
				"or missing value\n", p);
			return 0;
		}
	}
#ifdef CONFIG_QUOTA
1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
		if ((sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA) &&
		     sbi->s_qf_names[USRQUOTA])
			clear_opt(sbi->s_mount_opt, USRQUOTA);

		if ((sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA) &&
		     sbi->s_qf_names[GRPQUOTA])
			clear_opt(sbi->s_mount_opt, GRPQUOTA);

		if ((sbi->s_qf_names[USRQUOTA] &&
				(sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)) ||
		    (sbi->s_qf_names[GRPQUOTA] &&
				(sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA))) {
			printk(KERN_ERR "EXT3-fs: old and new quota "
					"format mixing.\n");
			return 0;
		}

		if (!sbi->s_jquota_fmt) {
			printk(KERN_ERR "EXT3-fs: journalled quota format "
					"not specified.\n");
			return 0;
		}
	} else {
		if (sbi->s_jquota_fmt) {
			printk(KERN_ERR "EXT3-fs: journalled quota format "
					"specified with no journalling "
					"enabled.\n");
			return 0;
		}
L
Linus Torvalds 已提交
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
	}
#endif
	return 1;
}

static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es,
			    int read_only)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	int res = 0;

	if (le32_to_cpu(es->s_rev_level) > EXT3_MAX_SUPP_REV) {
		printk (KERN_ERR "EXT3-fs warning: revision level too high, "
			"forcing read-only mode\n");
		res = MS_RDONLY;
	}
	if (read_only)
		return res;
	if (!(sbi->s_mount_state & EXT3_VALID_FS))
		printk (KERN_WARNING "EXT3-fs warning: mounting unchecked fs, "
			"running e2fsck is recommended\n");
	else if ((sbi->s_mount_state & EXT3_ERROR_FS))
		printk (KERN_WARNING
			"EXT3-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 (KERN_WARNING
			"EXT3-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 (KERN_WARNING
			"EXT3-fs warning: checktime reached, "
			"running e2fsck is recommended\n");
#if 0
		/* @@@ We _will_ want to clear the valid bit if we find
                   inconsistencies, to force a fsck at reboot.  But for
                   a plain journaled filesystem we can keep it set as
                   valid forever! :) */
	es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT3_VALID_FS);
#endif
	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
		es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT);
	es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
	es->s_mtime = cpu_to_le32(get_seconds());
	ext3_update_dynamic_rev(sb);
	EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);

	ext3_commit_super(sb, es, 1);
	if (test_opt(sb, DEBUG))
		printk(KERN_INFO "[EXT3 FS bs=%lu, gc=%lu, "
				"bpg=%lu, ipg=%lu, mo=%04lx]\n",
			sb->s_blocksize,
			sbi->s_groups_count,
			EXT3_BLOCKS_PER_GROUP(sb),
			EXT3_INODES_PER_GROUP(sb),
			sbi->s_mount_opt);

	printk(KERN_INFO "EXT3 FS on %s, ", sb->s_id);
	if (EXT3_SB(sb)->s_journal->j_inode == NULL) {
		char b[BDEVNAME_SIZE];

		printk("external journal on %s\n",
			bdevname(EXT3_SB(sb)->s_journal->j_dev, b));
	} else {
		printk("internal journal\n");
	}
	return res;
}

/* Called at mount-time, super-block is locked */
static int ext3_check_descriptors (struct super_block * sb)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
E
Eric Sandeen 已提交
1177 1178
	ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
	ext3_fsblk_t last_block;
L
Linus Torvalds 已提交
1179 1180 1181 1182 1183 1184 1185 1186
	struct ext3_group_desc * gdp = NULL;
	int desc_block = 0;
	int i;

	ext3_debug ("Checking group descriptors");

	for (i = 0; i < sbi->s_groups_count; i++)
	{
E
Eric Sandeen 已提交
1187 1188 1189 1190 1191 1192
		if (i == sbi->s_groups_count - 1)
			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
		else
			last_block = first_block +
				(EXT3_BLOCKS_PER_GROUP(sb) - 1);

L
Linus Torvalds 已提交
1193 1194 1195
		if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0)
			gdp = (struct ext3_group_desc *)
					sbi->s_group_desc[desc_block++]->b_data;
E
Eric Sandeen 已提交
1196 1197
		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
1198 1199 1200 1201 1202 1203 1204 1205
		{
			ext3_error (sb, "ext3_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
1206 1207
		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
1208 1209 1210 1211 1212 1213 1214 1215
		{
			ext3_error (sb, "ext3_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
1216 1217 1218
		if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >
		    last_block)
L
Linus Torvalds 已提交
1219 1220 1221 1222 1223 1224 1225 1226
		{
			ext3_error (sb, "ext3_check_descriptors",
				    "Inode table for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long)
					le32_to_cpu(gdp->bg_inode_table));
			return 0;
		}
E
Eric Sandeen 已提交
1227
		first_block += EXT3_BLOCKS_PER_GROUP(sb);
L
Linus Torvalds 已提交
1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308
		gdp++;
	}

	sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb));
	sbi->s_es->s_free_inodes_count=cpu_to_le32(ext3_count_free_inodes(sb));
	return 1;
}


/* ext3_orphan_cleanup() walks a singly-linked list of inodes (starting at
 * the superblock) which were deleted from all directories, but held open by
 * a process at the time of a crash.  We walk the list and try to delete these
 * inodes at recovery time (only with a read-write filesystem).
 *
 * In order to keep the orphan inode chain consistent during traversal (in
 * case of crash during recovery), we link each inode into the superblock
 * orphan list_head and handle it the same way as an inode deletion during
 * normal operation (which journals the operations for us).
 *
 * We only do an iget() and an iput() on each inode, which is very safe if we
 * accidentally point at an in-use or already deleted inode.  The worst that
 * can happen in this case is that we get a "bit already cleared" message from
 * ext3_free_inode().  The only reason we would point at a wrong inode is if
 * e2fsck was run on this filesystem, and it must have already done the orphan
 * inode cleanup for us, so we can safely abort without any further action.
 */
static void ext3_orphan_cleanup (struct super_block * sb,
				 struct ext3_super_block * es)
{
	unsigned int s_flags = sb->s_flags;
	int nr_orphans = 0, nr_truncates = 0;
#ifdef CONFIG_QUOTA
	int i;
#endif
	if (!es->s_last_orphan) {
		jbd_debug(4, "no orphan inodes to clean up\n");
		return;
	}

	if (EXT3_SB(sb)->s_mount_state & EXT3_ERROR_FS) {
		if (es->s_last_orphan)
			jbd_debug(1, "Errors on filesystem, "
				  "clearing orphan list.\n");
		es->s_last_orphan = 0;
		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
		return;
	}

	if (s_flags & MS_RDONLY) {
		printk(KERN_INFO "EXT3-fs: %s: orphan cleanup on readonly fs\n",
		       sb->s_id);
		sb->s_flags &= ~MS_RDONLY;
	}
#ifdef CONFIG_QUOTA
	/* Needed for iput() to work correctly and not trash data */
	sb->s_flags |= MS_ACTIVE;
	/* Turn on quotas so that they are updated correctly */
	for (i = 0; i < MAXQUOTAS; i++) {
		if (EXT3_SB(sb)->s_qf_names[i]) {
			int ret = ext3_quota_on_mount(sb, i);
			if (ret < 0)
				printk(KERN_ERR
					"EXT3-fs: Cannot turn on journalled "
					"quota: error %d\n", ret);
		}
	}
#endif

	while (es->s_last_orphan) {
		struct inode *inode;

		if (!(inode =
		      ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
			es->s_last_orphan = 0;
			break;
		}

		list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan);
		DQUOT_INIT(inode);
		if (inode->i_nlink) {
			printk(KERN_DEBUG
1309
				"%s: truncating inode %lu to %Ld bytes\n",
L
Linus Torvalds 已提交
1310
				__FUNCTION__, inode->i_ino, inode->i_size);
1311
			jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
L
Linus Torvalds 已提交
1312 1313 1314 1315 1316
				  inode->i_ino, inode->i_size);
			ext3_truncate(inode);
			nr_truncates++;
		} else {
			printk(KERN_DEBUG
1317
				"%s: deleting unreferenced inode %lu\n",
L
Linus Torvalds 已提交
1318
				__FUNCTION__, inode->i_ino);
1319
			jbd_debug(2, "deleting unreferenced inode %lu\n",
L
Linus Torvalds 已提交
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
				  inode->i_ino);
			nr_orphans++;
		}
		iput(inode);  /* The delete magic happens here! */
	}

#define PLURAL(x) (x), ((x)==1) ? "" : "s"

	if (nr_orphans)
		printk(KERN_INFO "EXT3-fs: %s: %d orphan inode%s deleted\n",
		       sb->s_id, PLURAL(nr_orphans));
	if (nr_truncates)
		printk(KERN_INFO "EXT3-fs: %s: %d truncate%s cleaned up\n",
		       sb->s_id, PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
	/* Turn quotas off */
	for (i = 0; i < MAXQUOTAS; i++) {
		if (sb_dqopt(sb)->files[i])
			vfs_quota_off(sb, i);
	}
#endif
	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}

#define log2(n) ffz(~(n))

/*
 * 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 ext3_max_size(int bits)
{
	loff_t res = EXT3_NDIR_BLOCKS;
	/* This constant is calculated to be the largest file size for a
	 * dense, 4k-blocksize file such that the total number of
	 * sectors in the file, including data and all indirect blocks,
	 * does not exceed 2^32. */
	const loff_t upper_limit = 0x1ff7fffd000LL;

	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > upper_limit)
		res = upper_limit;
	return res;
}

1369 1370
static ext3_fsblk_t descriptor_loc(struct super_block *sb,
				    ext3_fsblk_t logic_sb_block,
L
Linus Torvalds 已提交
1371 1372 1373
				    int nr)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
1374
	unsigned long bg, first_meta_bg;
L
Linus Torvalds 已提交
1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
	int has_super = 0;

	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

	if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return (logic_sb_block + nr + 1);
	bg = sbi->s_desc_per_block * nr;
	if (ext3_bg_has_super(sb, bg))
		has_super = 1;
1385
	return (has_super + ext3_group_first_block_no(sb, bg));
L
Linus Torvalds 已提交
1386 1387 1388 1389 1390 1391 1392 1393
}


static int ext3_fill_super (struct super_block *sb, void *data, int silent)
{
	struct buffer_head * bh;
	struct ext3_super_block *es = NULL;
	struct ext3_sb_info *sbi;
1394 1395 1396
	ext3_fsblk_t block;
	ext3_fsblk_t sb_block = get_sb_block(&data);
	ext3_fsblk_t logic_sb_block;
L
Linus Torvalds 已提交
1397
	unsigned long offset = 0;
1398
	unsigned int journal_inum = 0;
1399
	unsigned long journal_devnum = 0;
L
Linus Torvalds 已提交
1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
	unsigned long def_mount_opts;
	struct inode *root;
	int blocksize;
	int hblock;
	int db_count;
	int i;
	int needs_recovery;
	__le32 features;

	sbi = kmalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;
	memset(sbi, 0, sizeof(*sbi));
	sbi->s_mount_opt = 0;
	sbi->s_resuid = EXT3_DEF_RESUID;
	sbi->s_resgid = EXT3_DEF_RESGID;

	unlock_kernel();

	blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
	if (!blocksize) {
		printk(KERN_ERR "EXT3-fs: unable to set blocksize\n");
		goto out_fail;
	}

	/*
	 * The ext3 superblock will not be buffer aligned for other than 1kB
	 * block sizes.  We need to calculate the offset from buffer start.
	 */
	if (blocksize != EXT3_MIN_BLOCK_SIZE) {
		logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
		offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
	} else {
		logic_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logic_sb_block))) {
		printk (KERN_ERR "EXT3-fs: unable to read superblock\n");
		goto out_fail;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext3 macro-instructions depend on its value
	 */
	es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);
	if (sb->s_magic != EXT3_SUPER_MAGIC)
		goto cantfind_ext3;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT3_DEFM_DEBUG)
		set_opt(sbi->s_mount_opt, DEBUG);
	if (def_mount_opts & EXT3_DEFM_BSDGROUPS)
		set_opt(sbi->s_mount_opt, GRPID);
	if (def_mount_opts & EXT3_DEFM_UID16)
		set_opt(sbi->s_mount_opt, NO_UID32);
	if (def_mount_opts & EXT3_DEFM_XATTR_USER)
		set_opt(sbi->s_mount_opt, XATTR_USER);
	if (def_mount_opts & EXT3_DEFM_ACL)
		set_opt(sbi->s_mount_opt, POSIX_ACL);
	if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_DATA)
		sbi->s_mount_opt |= EXT3_MOUNT_JOURNAL_DATA;
	else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_ORDERED)
		sbi->s_mount_opt |= EXT3_MOUNT_ORDERED_DATA;
	else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_WBACK)
		sbi->s_mount_opt |= EXT3_MOUNT_WRITEBACK_DATA;

	if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC)
		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
		set_opt(sbi->s_mount_opt, ERRORS_RO);

	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);

	set_opt(sbi->s_mount_opt, RESERVATION);

1480 1481
	if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
			    NULL, 0))
L
Linus Torvalds 已提交
1482 1483 1484 1485 1486 1487 1488 1489 1490
		goto failed_mount;

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

	if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV &&
	    (EXT3_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U)))
1491
		printk(KERN_WARNING
L
Linus Torvalds 已提交
1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
		       "EXT3-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 = EXT3_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP);
	if (features) {
		printk(KERN_ERR "EXT3-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	features = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP);
	if (!(sb->s_flags & MS_RDONLY) && features) {
		printk(KERN_ERR "EXT3-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(es->s_log_block_size);

	if (blocksize < EXT3_MIN_BLOCK_SIZE ||
	    blocksize > EXT3_MAX_BLOCK_SIZE) {
1517
		printk(KERN_ERR
L
Linus Torvalds 已提交
1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540
		       "EXT3-fs: Unsupported filesystem blocksize %d on %s.\n",
		       blocksize, sb->s_id);
		goto failed_mount;
	}

	hblock = bdev_hardsect_size(sb->s_bdev);
	if (sb->s_blocksize != blocksize) {
		/*
		 * Make sure the blocksize for the filesystem is larger
		 * than the hardware sectorsize for the machine.
		 */
		if (blocksize < hblock) {
			printk(KERN_ERR "EXT3-fs: blocksize %d too small for "
			       "device blocksize %d.\n", blocksize, hblock);
			goto failed_mount;
		}

		brelse (bh);
		sb_set_blocksize(sb, blocksize);
		logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
		offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
		bh = sb_bread(sb, logic_sb_block);
		if (!bh) {
1541
			printk(KERN_ERR
L
Linus Torvalds 已提交
1542 1543 1544 1545 1546 1547
			       "EXT3-fs: Can't read superblock on 2nd try.\n");
			goto failed_mount;
		}
		es = (struct ext3_super_block *)(((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) {
1548
			printk (KERN_ERR
L
Linus Torvalds 已提交
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617
				"EXT3-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext3_max_size(sb->s_blocksize_bits);

	if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT3_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT3_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 < EXT3_GOOD_OLD_INODE_SIZE) ||
		    (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
		    (sbi->s_inode_size > blocksize)) {
			printk (KERN_ERR
				"EXT3-fs: unsupported inode size: %d\n",
				sbi->s_inode_size);
			goto failed_mount;
		}
	}
	sbi->s_frag_size = EXT3_MIN_FRAG_SIZE <<
				   le32_to_cpu(es->s_log_frag_size);
	if (blocksize != sbi->s_frag_size) {
		printk(KERN_ERR
		       "EXT3-fs: fragsize %lu != blocksize %u (unsupported)\n",
		       sbi->s_frag_size, blocksize);
		goto failed_mount;
	}
	sbi->s_frags_per_block = 1;
	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 (EXT3_INODE_SIZE(sb) == 0)
		goto cantfind_ext3;
	sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
	if (sbi->s_inodes_per_block == 0)
		goto cantfind_ext3;
	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = blocksize / sizeof(struct ext3_group_desc);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits = log2(EXT3_ADDR_PER_BLOCK(sb));
	sbi->s_desc_per_block_bits = log2(EXT3_DESC_PER_BLOCK(sb));
	for (i=0; i < 4; i++)
		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
	sbi->s_def_hash_version = es->s_def_hash_version;

	if (sbi->s_blocks_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #blocks per group too big: %lu\n",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_frags_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #fragments per group too big: %lu\n",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

1618 1619 1620 1621 1622 1623 1624 1625 1626 1627
	if (le32_to_cpu(es->s_blocks_count) >
		    (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
		printk(KERN_ERR "EXT3-fs: filesystem on %s:"
			" too large to mount safely\n", sb->s_id);
		if (sizeof(sector_t) < 8)
			printk(KERN_WARNING "EXT3-fs: CONFIG_LBD not "
					"enabled\n");
		goto failed_mount;
	}

L
Linus Torvalds 已提交
1628 1629
	if (EXT3_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext3;
E
Eric Sandeen 已提交
1630 1631 1632
	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
			       le32_to_cpu(es->s_first_data_block) - 1)
				       / EXT3_BLOCKS_PER_GROUP(sb)) + 1;
L
Linus Torvalds 已提交
1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
	db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) /
		   EXT3_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
				    GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		printk (KERN_ERR "EXT3-fs: not enough memory\n");
		goto failed_mount;
	}

	bgl_lock_init(&sbi->s_blockgroup_lock);

	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]) {
			printk (KERN_ERR "EXT3-fs: "
				"can't read group descriptor %d\n", i);
			db_count = i;
			goto failed_mount2;
		}
	}
	if (!ext3_check_descriptors (sb)) {
1655
		printk(KERN_ERR "EXT3-fs: group descriptors corrupted!\n");
L
Linus Torvalds 已提交
1656 1657 1658 1659 1660
		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);
1661 1662 1663 1664 1665 1666 1667 1668

	percpu_counter_init(&sbi->s_freeblocks_counter,
		ext3_count_free_blocks(sb));
	percpu_counter_init(&sbi->s_freeinodes_counter,
		ext3_count_free_inodes(sb));
	percpu_counter_init(&sbi->s_dirs_counter,
		ext3_count_dirs(sb));

L
Linus Torvalds 已提交
1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
	/* 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 = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext3_rsv_window_add(sb, &sbi->s_rsv_window_head);

	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext3_sops;
	sb->s_export_op = &ext3_export_ops;
	sb->s_xattr = ext3_xattr_handlers;
#ifdef CONFIG_QUOTA
	sb->s_qcop = &ext3_qctl_operations;
	sb->dq_op = &ext3_quota_operations;
#endif
	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */

	sb->s_root = NULL;

	needs_recovery = (es->s_last_orphan != 0 ||
			  EXT3_HAS_INCOMPAT_FEATURE(sb,
				    EXT3_FEATURE_INCOMPAT_RECOVER));

	/*
	 * The first inode we look at is the journal inode.  Don't try
	 * root first: it may be modified in the journal!
	 */
	if (!test_opt(sb, NOLOAD) &&
	    EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) {
1706
		if (ext3_load_journal(sb, es, journal_devnum))
1707
			goto failed_mount3;
L
Linus Torvalds 已提交
1708 1709
	} else if (journal_inum) {
		if (ext3_create_journal(sb, es, journal_inum))
1710
			goto failed_mount3;
L
Linus Torvalds 已提交
1711 1712 1713 1714 1715
	} else {
		if (!silent)
			printk (KERN_ERR
				"ext3: No journal on filesystem on %s\n",
				sb->s_id);
1716
		goto failed_mount3;
L
Linus Torvalds 已提交
1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738
	}

	/* We have now updated the journal if required, so we can
	 * validate the data journaling mode. */
	switch (test_opt(sb, DATA_FLAGS)) {
	case 0:
		/* No mode set, assume a default based on the journal
                   capabilities: ORDERED_DATA if the journal can
                   cope, else JOURNAL_DATA */
		if (journal_check_available_features
		    (sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE))
			set_opt(sbi->s_mount_opt, ORDERED_DATA);
		else
			set_opt(sbi->s_mount_opt, JOURNAL_DATA);
		break;

	case EXT3_MOUNT_ORDERED_DATA:
	case EXT3_MOUNT_WRITEBACK_DATA:
		if (!journal_check_available_features
		    (sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) {
			printk(KERN_ERR "EXT3-fs: Journal does not support "
			       "requested data journaling mode\n");
1739
			goto failed_mount4;
L
Linus Torvalds 已提交
1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761
		}
	default:
		break;
	}

	if (test_opt(sb, NOBH)) {
		if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) {
			printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - "
				"its supported only with writeback mode\n");
			clear_opt(sbi->s_mount_opt, NOBH);
		}
	}
	/*
	 * The journal_load will have done any necessary log recovery,
	 * so we can safely mount the rest of the filesystem now.
	 */

	root = iget(sb, EXT3_ROOT_INO);
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		printk(KERN_ERR "EXT3-fs: get root inode failed\n");
		iput(root);
1762
		goto failed_mount4;
L
Linus Torvalds 已提交
1763 1764 1765 1766 1767
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		dput(sb->s_root);
		sb->s_root = NULL;
		printk(KERN_ERR "EXT3-fs: corrupt root inode, run e2fsck\n");
1768
		goto failed_mount4;
L
Linus Torvalds 已提交
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799
	}

	ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
	/*
	 * akpm: core read_super() calls in here with the superblock locked.
	 * That deadlocks, because orphan cleanup needs to lock the superblock
	 * in numerous places.  Here we just pop the lock - it's relatively
	 * harmless, because we are now ready to accept write_super() requests,
	 * and aviro says that's the only reason for hanging onto the
	 * superblock lock.
	 */
	EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
	ext3_orphan_cleanup(sb, es);
	EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS;
	if (needs_recovery)
		printk (KERN_INFO "EXT3-fs: recovery complete.\n");
	ext3_mark_recovery_complete(sb, es);
	printk (KERN_INFO "EXT3-fs: mounted filesystem with %s data mode.\n",
		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
		"writeback");

	lock_kernel();
	return 0;

cantfind_ext3:
	if (!silent)
		printk(KERN_ERR "VFS: Can't find ext3 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;

1800
failed_mount4:
L
Linus Torvalds 已提交
1801
	journal_destroy(sbi->s_journal);
1802 1803 1804 1805
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
1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
failed_mount:
#ifdef CONFIG_QUOTA
	for (i = 0; i < MAXQUOTAS; i++)
		kfree(sbi->s_qf_names[i]);
#endif
	ext3_blkdev_remove(sbi);
	brelse(bh);
out_fail:
	sb->s_fs_info = NULL;
	kfree(sbi);
	lock_kernel();
	return -EINVAL;
}

/*
 * Setup any per-fs journal parameters now.  We'll do this both on
 * initial mount, once the journal has been initialised but before we've
1827
 * done any recovery; and again on any subsequent remount.
L
Linus Torvalds 已提交
1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846
 */
static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);

	if (sbi->s_commit_interval)
		journal->j_commit_interval = sbi->s_commit_interval;
	/* We could also set up an ext3-specific default for the commit
	 * interval here, but for now we'll just fall back to the jbd
	 * default. */

	spin_lock(&journal->j_state_lock);
	if (test_opt(sb, BARRIER))
		journal->j_flags |= JFS_BARRIER;
	else
		journal->j_flags &= ~JFS_BARRIER;
	spin_unlock(&journal->j_state_lock);
}

1847 1848
static journal_t *ext3_get_journal(struct super_block *sb,
				   unsigned int journal_inum)
L
Linus Torvalds 已提交
1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892
{
	struct inode *journal_inode;
	journal_t *journal;

	/* First, test for the existence of a valid inode on disk.  Bad
	 * things happen if we iget() an unused inode, as the subsequent
	 * iput() will try to delete it. */

	journal_inode = iget(sb, journal_inum);
	if (!journal_inode) {
		printk(KERN_ERR "EXT3-fs: no journal found.\n");
		return NULL;
	}
	if (!journal_inode->i_nlink) {
		make_bad_inode(journal_inode);
		iput(journal_inode);
		printk(KERN_ERR "EXT3-fs: journal inode is deleted.\n");
		return NULL;
	}

	jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
		  journal_inode, journal_inode->i_size);
	if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) {
		printk(KERN_ERR "EXT3-fs: invalid journal inode.\n");
		iput(journal_inode);
		return NULL;
	}

	journal = journal_init_inode(journal_inode);
	if (!journal) {
		printk(KERN_ERR "EXT3-fs: Could not load journal inode\n");
		iput(journal_inode);
		return NULL;
	}
	journal->j_private = sb;
	ext3_init_journal_params(sb, journal);
	return journal;
}

static journal_t *ext3_get_dev_journal(struct super_block *sb,
				       dev_t j_dev)
{
	struct buffer_head * bh;
	journal_t *journal;
1893
	ext3_fsblk_t start;
1894
	ext3_fsblk_t len;
L
Linus Torvalds 已提交
1895
	int hblock, blocksize;
1896
	ext3_fsblk_t sb_block;
L
Linus Torvalds 已提交
1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977
	unsigned long offset;
	struct ext3_super_block * es;
	struct block_device *bdev;

	bdev = ext3_blkdev_get(j_dev);
	if (bdev == NULL)
		return NULL;

	if (bd_claim(bdev, sb)) {
		printk(KERN_ERR
		        "EXT3: failed to claim external journal device.\n");
		blkdev_put(bdev);
		return NULL;
	}

	blocksize = sb->s_blocksize;
	hblock = bdev_hardsect_size(bdev);
	if (blocksize < hblock) {
		printk(KERN_ERR
			"EXT3-fs: blocksize too small for journal device.\n");
		goto out_bdev;
	}

	sb_block = EXT3_MIN_BLOCK_SIZE / blocksize;
	offset = EXT3_MIN_BLOCK_SIZE % blocksize;
	set_blocksize(bdev, blocksize);
	if (!(bh = __bread(bdev, sb_block, blocksize))) {
		printk(KERN_ERR "EXT3-fs: couldn't read superblock of "
		       "external journal\n");
		goto out_bdev;
	}

	es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
	if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) ||
	    !(le32_to_cpu(es->s_feature_incompat) &
	      EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) {
		printk(KERN_ERR "EXT3-fs: external journal has "
					"bad superblock\n");
		brelse(bh);
		goto out_bdev;
	}

	if (memcmp(EXT3_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
		printk(KERN_ERR "EXT3-fs: journal UUID does not match\n");
		brelse(bh);
		goto out_bdev;
	}

	len = le32_to_cpu(es->s_blocks_count);
	start = sb_block + 1;
	brelse(bh);	/* we're done with the superblock */

	journal = journal_init_dev(bdev, sb->s_bdev,
					start, len, blocksize);
	if (!journal) {
		printk(KERN_ERR "EXT3-fs: failed to create device journal\n");
		goto out_bdev;
	}
	journal->j_private = sb;
	ll_rw_block(READ, 1, &journal->j_sb_buffer);
	wait_on_buffer(journal->j_sb_buffer);
	if (!buffer_uptodate(journal->j_sb_buffer)) {
		printk(KERN_ERR "EXT3-fs: I/O error on journal device\n");
		goto out_journal;
	}
	if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
		printk(KERN_ERR "EXT3-fs: External journal has more than one "
					"user (unsupported) - %d\n",
			be32_to_cpu(journal->j_superblock->s_nr_users));
		goto out_journal;
	}
	EXT3_SB(sb)->journal_bdev = bdev;
	ext3_init_journal_params(sb, journal);
	return journal;
out_journal:
	journal_destroy(journal);
out_bdev:
	ext3_blkdev_put(bdev);
	return NULL;
}

1978 1979 1980
static int ext3_load_journal(struct super_block *sb,
			     struct ext3_super_block *es,
			     unsigned long journal_devnum)
L
Linus Torvalds 已提交
1981 1982
{
	journal_t *journal;
1983
	unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
1984
	dev_t journal_dev;
L
Linus Torvalds 已提交
1985 1986 1987
	int err = 0;
	int really_read_only;

1988 1989 1990 1991 1992 1993 1994 1995
	if (journal_devnum &&
	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
		printk(KERN_INFO "EXT3-fs: external journal device major/minor "
			"numbers have changed\n");
		journal_dev = new_decode_dev(journal_devnum);
	} else
		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));

L
Linus Torvalds 已提交
1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
	really_read_only = bdev_read_only(sb->s_bdev);

	/*
	 * Are we loading a blank journal or performing recovery after a
	 * crash?  For recovery, we need to check in advance whether we
	 * can get read-write access to the device.
	 */

	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER)) {
		if (sb->s_flags & MS_RDONLY) {
			printk(KERN_INFO "EXT3-fs: INFO: recovery "
					"required on readonly filesystem.\n");
			if (really_read_only) {
				printk(KERN_ERR "EXT3-fs: write access "
					"unavailable, cannot proceed.\n");
				return -EROFS;
			}
			printk (KERN_INFO "EXT3-fs: write access will "
					"be enabled during recovery.\n");
		}
	}

	if (journal_inum && journal_dev) {
		printk(KERN_ERR "EXT3-fs: filesystem has both journal "
		       "and inode journals!\n");
		return -EINVAL;
	}

	if (journal_inum) {
		if (!(journal = ext3_get_journal(sb, journal_inum)))
			return -EINVAL;
	} else {
		if (!(journal = ext3_get_dev_journal(sb, journal_dev)))
			return -EINVAL;
	}

	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
		err = journal_update_format(journal);
		if (err)  {
			printk(KERN_ERR "EXT3-fs: error updating journal.\n");
			journal_destroy(journal);
			return err;
		}
	}

	if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER))
		err = journal_wipe(journal, !really_read_only);
	if (!err)
		err = journal_load(journal);

	if (err) {
		printk(KERN_ERR "EXT3-fs: error loading journal.\n");
		journal_destroy(journal);
		return err;
	}

	EXT3_SB(sb)->s_journal = journal;
	ext3_clear_journal_err(sb, es);
2054 2055 2056 2057 2058 2059 2060 2061 2062 2063

	if (journal_devnum &&
	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
		es->s_journal_dev = cpu_to_le32(journal_devnum);
		sb->s_dirt = 1;

		/* Make sure we flush the recovery flag to disk. */
		ext3_commit_super(sb, es, 1);
	}

L
Linus Torvalds 已提交
2064 2065 2066 2067 2068
	return 0;
}

static int ext3_create_journal(struct super_block * sb,
			       struct ext3_super_block * es,
2069
			       unsigned int journal_inum)
L
Linus Torvalds 已提交
2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081
{
	journal_t *journal;

	if (sb->s_flags & MS_RDONLY) {
		printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to "
				"create journal.\n");
		return -EROFS;
	}

	if (!(journal = ext3_get_journal(sb, journal_inum)))
		return -EINVAL;

2082
	printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n",
L
Linus Torvalds 已提交
2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210
	       journal_inum);

	if (journal_create(journal)) {
		printk(KERN_ERR "EXT3-fs: error creating journal.\n");
		journal_destroy(journal);
		return -EIO;
	}

	EXT3_SB(sb)->s_journal = journal;

	ext3_update_dynamic_rev(sb);
	EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
	EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL);

	es->s_journal_inum = cpu_to_le32(journal_inum);
	sb->s_dirt = 1;

	/* Make sure we flush the recovery flag to disk. */
	ext3_commit_super(sb, es, 1);

	return 0;
}

static void ext3_commit_super (struct super_block * sb,
			       struct ext3_super_block * es,
			       int sync)
{
	struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;

	if (!sbh)
		return;
	es->s_wtime = cpu_to_le32(get_seconds());
	es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));
	BUFFER_TRACE(sbh, "marking dirty");
	mark_buffer_dirty(sbh);
	if (sync)
		sync_dirty_buffer(sbh);
}


/*
 * Have we just finished recovery?  If so, and if we are mounting (or
 * remounting) the filesystem readonly, then we will end up with a
 * consistent fs on disk.  Record that fact.
 */
static void ext3_mark_recovery_complete(struct super_block * sb,
					struct ext3_super_block * es)
{
	journal_t *journal = EXT3_SB(sb)->s_journal;

	journal_lock_updates(journal);
	journal_flush(journal);
	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
	    sb->s_flags & MS_RDONLY) {
		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		sb->s_dirt = 0;
		ext3_commit_super(sb, es, 1);
	}
	journal_unlock_updates(journal);
}

/*
 * If we are mounting (or read-write remounting) a filesystem whose journal
 * has recorded an error from a previous lifetime, move that error to the
 * main filesystem now.
 */
static void ext3_clear_journal_err(struct super_block * sb,
				   struct ext3_super_block * es)
{
	journal_t *journal;
	int j_errno;
	const char *errstr;

	journal = EXT3_SB(sb)->s_journal;

	/*
	 * Now check for any error status which may have been recorded in the
	 * journal by a prior ext3_error() or ext3_abort()
	 */

	j_errno = journal_errno(journal);
	if (j_errno) {
		char nbuf[16];

		errstr = ext3_decode_error(sb, j_errno, nbuf);
		ext3_warning(sb, __FUNCTION__, "Filesystem error recorded "
			     "from previous mount: %s", errstr);
		ext3_warning(sb, __FUNCTION__, "Marking fs in need of "
			     "filesystem check.");

		EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
		es->s_state |= cpu_to_le16(EXT3_ERROR_FS);
		ext3_commit_super (sb, es, 1);

		journal_clear_err(journal);
	}
}

/*
 * Force the running and committing transactions to commit,
 * and wait on the commit.
 */
int ext3_force_commit(struct super_block *sb)
{
	journal_t *journal;
	int ret;

	if (sb->s_flags & MS_RDONLY)
		return 0;

	journal = EXT3_SB(sb)->s_journal;
	sb->s_dirt = 0;
	ret = ext3_journal_force_commit(journal);
	return ret;
}

/*
 * Ext3 always journals updates to the superblock itself, so we don't
 * have to propagate any other updates to the superblock on disk at this
 * point.  Just start an async writeback to get the buffers on their way
 * to the disk.
 *
 * This implicitly triggers the writebehind on sync().
 */

static void ext3_write_super (struct super_block * sb)
{
2211
	if (mutex_trylock(&sb->s_lock) != 0)
L
Linus Torvalds 已提交
2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268
		BUG();
	sb->s_dirt = 0;
}

static int ext3_sync_fs(struct super_block *sb, int wait)
{
	tid_t target;

	sb->s_dirt = 0;
	if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
		if (wait)
			log_wait_commit(EXT3_SB(sb)->s_journal, target);
	}
	return 0;
}

/*
 * LVM calls this function before a (read-only) snapshot is created.  This
 * gives us a chance to flush the journal completely and mark the fs clean.
 */
static void ext3_write_super_lockfs(struct super_block *sb)
{
	sb->s_dirt = 0;

	if (!(sb->s_flags & MS_RDONLY)) {
		journal_t *journal = EXT3_SB(sb)->s_journal;

		/* Now we set up the journal barrier. */
		journal_lock_updates(journal);
		journal_flush(journal);

		/* Journal blocked and flushed, clear needs_recovery flag. */
		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
	}
}

/*
 * Called by LVM after the snapshot is done.  We need to reset the RECOVER
 * flag here, even though the filesystem is not technically dirty yet.
 */
static void ext3_unlockfs(struct super_block *sb)
{
	if (!(sb->s_flags & MS_RDONLY)) {
		lock_super(sb);
		/* Reser the needs_recovery flag before the fs is unlocked. */
		EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
		unlock_super(sb);
		journal_unlock_updates(EXT3_SB(sb)->s_journal);
	}
}

static int ext3_remount (struct super_block * sb, int * flags, char * data)
{
	struct ext3_super_block * es;
	struct ext3_sb_info *sbi = EXT3_SB(sb);
2269
	ext3_fsblk_t n_blocks_count = 0;
J
Jan Kara 已提交
2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287
	unsigned long old_sb_flags;
	struct ext3_mount_options old_opts;
	int err;
#ifdef CONFIG_QUOTA
	int i;
#endif

	/* Store the original 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;
	old_opts.s_commit_interval = sbi->s_commit_interval;
#ifdef CONFIG_QUOTA
	old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
	for (i = 0; i < MAXQUOTAS; i++)
		old_opts.s_qf_names[i] = sbi->s_qf_names[i];
#endif
L
Linus Torvalds 已提交
2288 2289 2290 2291

	/*
	 * Allow the "check" option to be passed as a remount option.
	 */
2292
	if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
J
Jan Kara 已提交
2293 2294 2295
		err = -EINVAL;
		goto restore_opts;
	}
L
Linus Torvalds 已提交
2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308

	if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
		ext3_abort(sb, __FUNCTION__, "Abort forced by user");

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

	es = sbi->s_es;

	ext3_init_journal_params(sb, sbi->s_journal);

	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
		n_blocks_count > le32_to_cpu(es->s_blocks_count)) {
J
Jan Kara 已提交
2309 2310 2311 2312
		if (sbi->s_mount_opt & EXT3_MOUNT_ABORT) {
			err = -EROFS;
			goto restore_opts;
		}
L
Linus Torvalds 已提交
2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338

		if (*flags & MS_RDONLY) {
			/*
			 * First of all, the unconditional stuff we have to do
			 * to disable replay of the journal when we next remount
			 */
			sb->s_flags |= MS_RDONLY;

			/*
			 * OK, test if we are remounting a valid rw partition
			 * readonly, and if so set the rdonly flag and then
			 * mark the partition as valid again.
			 */
			if (!(es->s_state & cpu_to_le16(EXT3_VALID_FS)) &&
			    (sbi->s_mount_state & EXT3_VALID_FS))
				es->s_state = cpu_to_le16(sbi->s_mount_state);

			ext3_mark_recovery_complete(sb, es);
		} else {
			__le32 ret;
			if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb,
					~EXT3_FEATURE_RO_COMPAT_SUPP))) {
				printk(KERN_WARNING "EXT3-fs: %s: couldn't "
				       "remount RDWR because of unsupported "
				       "optional features (%x).\n",
				       sb->s_id, le32_to_cpu(ret));
J
Jan Kara 已提交
2339 2340
				err = -EROFS;
				goto restore_opts;
L
Linus Torvalds 已提交
2341 2342 2343 2344 2345 2346 2347 2348 2349
			}
			/*
			 * 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.)
			 */
			ext3_clear_journal_err(sb, es);
			sbi->s_mount_state = le16_to_cpu(es->s_state);
J
Jan Kara 已提交
2350 2351 2352 2353
			if ((ret = ext3_group_extend(sb, es, n_blocks_count))) {
				err = ret;
				goto restore_opts;
			}
L
Linus Torvalds 已提交
2354 2355 2356 2357
			if (!ext3_setup_super (sb, es, 0))
				sb->s_flags &= ~MS_RDONLY;
		}
	}
J
Jan Kara 已提交
2358 2359 2360 2361 2362 2363 2364
#ifdef CONFIG_QUOTA
	/* Release old quota file names */
	for (i = 0; i < MAXQUOTAS; i++)
		if (old_opts.s_qf_names[i] &&
		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
			kfree(old_opts.s_qf_names[i]);
#endif
L
Linus Torvalds 已提交
2365
	return 0;
J
Jan Kara 已提交
2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381
restore_opts:
	sb->s_flags = old_sb_flags;
	sbi->s_mount_opt = old_opts.s_mount_opt;
	sbi->s_resuid = old_opts.s_resuid;
	sbi->s_resgid = old_opts.s_resgid;
	sbi->s_commit_interval = old_opts.s_commit_interval;
#ifdef CONFIG_QUOTA
	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
	for (i = 0; i < MAXQUOTAS; i++) {
		if (sbi->s_qf_names[i] &&
		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
			kfree(sbi->s_qf_names[i]);
		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
	}
#endif
	return err;
L
Linus Torvalds 已提交
2382 2383
}

2384
static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
L
Linus Torvalds 已提交
2385
{
2386
	struct super_block *sb = dentry->d_sb;
A
Alex Tomas 已提交
2387 2388
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
2389
	ext3_fsblk_t overhead;
L
Linus Torvalds 已提交
2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429
	int i;

	if (test_opt (sb, MINIX_DF))
		overhead = 0;
	else {
		unsigned long ngroups;
		ngroups = EXT3_SB(sb)->s_groups_count;
		smp_rmb();

		/*
		 * Compute the overhead (FS structures)
		 */

		/*
		 * All of the blocks before first_data_block are
		 * overhead
		 */
		overhead = le32_to_cpu(es->s_first_data_block);

		/*
		 * 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 < ngroups; i++) {
			overhead += ext3_bg_has_super(sb, i) +
				ext3_bg_num_gdb(sb, i);
			cond_resched();
		}

		/*
		 * Every block group has an inode bitmap, a block
		 * bitmap, and an inode table.
		 */
		overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group));
	}

	buf->f_type = EXT3_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - overhead;
A
Alex Tomas 已提交
2430
	buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
L
Linus Torvalds 已提交
2431 2432 2433 2434
	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))
		buf->f_bavail = 0;
	buf->f_files = le32_to_cpu(es->s_inodes_count);
A
Alex Tomas 已提交
2435
	buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
L
Linus Torvalds 已提交
2436 2437 2438 2439 2440 2441 2442 2443 2444
	buf->f_namelen = EXT3_NAME_LEN;
	return 0;
}

/* Helper function for writing quotas on sync - we need to start transaction before quota file
 * is locked for write. Otherwise the are possible deadlocks:
 * Process 1                         Process 2
 * ext3_create()                     quota_sync()
 *   journal_start()                   write_dquot()
I
Ingo Molnar 已提交
2445 2446
 *   DQUOT_INIT()                        down(dqio_mutex)
 *     down(dqio_mutex)                    journal_start()
L
Linus Torvalds 已提交
2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462
 *
 */

#ifdef CONFIG_QUOTA

static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
	return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
}

static int ext3_dquot_initialize(struct inode *inode, int type)
{
	handle_t *handle;
	int ret, err;

	/* We may create quota structure so we need to reserve enough blocks */
2463
	handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS(inode->i_sb));
L
Linus Torvalds 已提交
2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_initialize(inode, type);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

static int ext3_dquot_drop(struct inode *inode)
{
	handle_t *handle;
	int ret, err;

	/* We may delete quota structure so we need to reserve enough blocks */
2479
	handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
L
Linus Torvalds 已提交
2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_drop(inode);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

static int ext3_write_dquot(struct dquot *dquot)
{
	int ret, err;
	handle_t *handle;
	struct inode *inode;

	inode = dquot_to_inode(dquot);
	handle = ext3_journal_start(inode,
2497
					EXT3_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
L
Linus Torvalds 已提交
2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_commit(dquot);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

static int ext3_acquire_dquot(struct dquot *dquot)
{
	int ret, err;
	handle_t *handle;

	handle = ext3_journal_start(dquot_to_inode(dquot),
2513
					EXT3_QUOTA_INIT_BLOCKS(dquot->dq_sb));
L
Linus Torvalds 已提交
2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_acquire(dquot);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

static int ext3_release_dquot(struct dquot *dquot)
{
	int ret, err;
	handle_t *handle;

	handle = ext3_journal_start(dquot_to_inode(dquot),
2529
					EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb));
L
Linus Torvalds 已提交
2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_release(dquot);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

static int ext3_mark_dquot_dirty(struct dquot *dquot)
{
	/* Are we journalling quotas? */
	if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
	    EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
		dquot_mark_dquot_dirty(dquot);
		return ext3_write_dquot(dquot);
	} else {
		return dquot_mark_dquot_dirty(dquot);
	}
}

static int ext3_write_info(struct super_block *sb, int type)
{
	int ret, err;
	handle_t *handle;

	/* Data block + inode block */
	handle = ext3_journal_start(sb->s_root->d_inode, 2);
	if (IS_ERR(handle))
		return PTR_ERR(handle);
	ret = dquot_commit_info(sb, type);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;
}

/*
 * Turn on quotas during mount time - we need to find
 * the quota file and such...
 */
static int ext3_quota_on_mount(struct super_block *sb, int type)
{
2573 2574
	return vfs_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type],
			EXT3_SB(sb)->s_jquota_fmt, type);
L
Linus Torvalds 已提交
2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585
}

/*
 * Standard function to be called on quota_on
 */
static int ext3_quota_on(struct super_block *sb, int type, int format_id,
			 char *path)
{
	int err;
	struct nameidata nd;

2586 2587
	if (!test_opt(sb, QUOTA))
		return -EINVAL;
L
Linus Torvalds 已提交
2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663
	/* Not journalling quota? */
	if (!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
	    !EXT3_SB(sb)->s_qf_names[GRPQUOTA])
		return vfs_quota_on(sb, type, format_id, path);
	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
	if (err)
		return err;
	/* Quotafile not on the same filesystem? */
	if (nd.mnt->mnt_sb != sb) {
		path_release(&nd);
		return -EXDEV;
	}
	/* Quotafile not of fs root? */
	if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode)
		printk(KERN_WARNING
			"EXT3-fs: Quota file not on filesystem root. "
			"Journalled quota will not work.\n");
	path_release(&nd);
	return vfs_quota_on(sb, type, format_id, path);
}

/* 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 ext3_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 >> EXT3_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t toread;
	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;
		bh = ext3_bread(NULL, inode, blk, 0, &err);
		if (err)
			return err;
		if (!bh)	/* A hole? */
			memset(data, 0, tocopy);
		else
			memcpy(data, bh->b_data+offset, tocopy);
		brelse(bh);
		offset = 0;
		toread -= tocopy;
		data += tocopy;
		blk++;
	}
	return len;
}

/* Write to quotafile (we know the transaction is already started and has
 * enough credits) */
static ssize_t ext3_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 >> EXT3_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	int journal_quota = EXT3_SB(sb)->s_qf_names[type] != NULL;
	size_t towrite = len;
	struct buffer_head *bh;
	handle_t *handle = journal_current_handle();

2664
	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
L
Linus Torvalds 已提交
2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706
	while (towrite > 0) {
		tocopy = sb->s_blocksize - offset < towrite ?
				sb->s_blocksize - offset : towrite;
		bh = ext3_bread(handle, inode, blk, 1, &err);
		if (!bh)
			goto out;
		if (journal_quota) {
			err = ext3_journal_get_write_access(handle, bh);
			if (err) {
				brelse(bh);
				goto out;
			}
		}
		lock_buffer(bh);
		memcpy(bh->b_data+offset, data, tocopy);
		flush_dcache_page(bh->b_page);
		unlock_buffer(bh);
		if (journal_quota)
			err = ext3_journal_dirty_metadata(handle, bh);
		else {
			/* Always do at least ordered writes for quotas */
			err = ext3_journal_dirty_data(handle, bh);
			mark_buffer_dirty(bh);
		}
		brelse(bh);
		if (err)
			goto out;
		offset = 0;
		towrite -= tocopy;
		data += tocopy;
		blk++;
	}
out:
	if (len == towrite)
		return err;
	if (inode->i_size < off+len-towrite) {
		i_size_write(inode, off+len-towrite);
		EXT3_I(inode)->i_disksize = inode->i_size;
	}
	inode->i_version++;
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	ext3_mark_inode_dirty(handle, inode);
2707
	mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
2708 2709 2710 2711 2712
	return len - towrite;
}

#endif

2713 2714
static int ext3_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
2715
{
2716
	return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super, mnt);
L
Linus Torvalds 已提交
2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757
}

static struct file_system_type ext3_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext3",
	.get_sb		= ext3_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init init_ext3_fs(void)
{
	int err = init_ext3_xattr();
	if (err)
		return err;
	err = init_inodecache();
	if (err)
		goto out1;
        err = register_filesystem(&ext3_fs_type);
	if (err)
		goto out;
	return 0;
out:
	destroy_inodecache();
out1:
 	exit_ext3_xattr();
	return err;
}

static void __exit exit_ext3_fs(void)
{
	unregister_filesystem(&ext3_fs_type);
	destroy_inodecache();
	exit_ext3_xattr();
}

MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Second Extended Filesystem with journaling extensions");
MODULE_LICENSE("GPL");
module_init(init_ext3_fs)
module_exit(exit_ext3_fs)