super.c

/*
 *  linux/fs/ext4/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/vmalloc.h>
#include <linux/jbd2.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#include <asm/uaccess.h>

#include <linux/kthread.h>
#include <linux/freezer.h>

#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"

#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>

static struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
struct ext4_lazy_init *ext4_li_info;
struct mutex ext4_li_mtx;
struct ext4_features *ext4_feat;

static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
			     unsigned long journal_devnum);
static int ext4_commit_super(struct super_block *sb, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
					struct ext4_super_block *es);
static void ext4_clear_journal_err(struct super_block *sb,
				   struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
static const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
static int ext4_remount(struct super_block *sb, int *flags, char *data);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
		       const char *dev_name, void *data);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);

#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext3",
	.mount		= ext4_mount,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
#else
#define IS_EXT3_SB(sb) (0)
#endif

ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
			       struct ext4_group_desc *bg)
{
	return le32_to_cpu(bg->bg_block_bitmap_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
}

ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
			       struct ext4_group_desc *bg)
{
	return le32_to_cpu(bg->bg_inode_bitmap_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
}

ext4_fsblk_t ext4_inode_table(struct super_block *sb,
			      struct ext4_group_desc *bg)
{
	return le32_to_cpu(bg->bg_inode_table_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}

__u32 ext4_free_blks_count(struct super_block *sb,
			      struct ext4_group_desc *bg)
{
	return le16_to_cpu(bg->bg_free_blocks_count_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
}

__u32 ext4_free_inodes_count(struct super_block *sb,
			      struct ext4_group_desc *bg)
{
	return le16_to_cpu(bg->bg_free_inodes_count_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
}

__u32 ext4_used_dirs_count(struct super_block *sb,
			      struct ext4_group_desc *bg)
{
	return le16_to_cpu(bg->bg_used_dirs_count_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
}

__u32 ext4_itable_unused_count(struct super_block *sb,
			      struct ext4_group_desc *bg)
{
	return le16_to_cpu(bg->bg_itable_unused_lo) |
		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
		 (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
}

void ext4_block_bitmap_set(struct super_block *sb,
			   struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
	bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
}

void ext4_inode_bitmap_set(struct super_block *sb,
			   struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
	bg->bg_inode_bitmap_lo  = cpu_to_le32((u32)blk);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
}

void ext4_inode_table_set(struct super_block *sb,
			  struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
	bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}

void ext4_free_blks_set(struct super_block *sb,
			  struct ext4_group_desc *bg, __u32 count)
{
	bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
}

void ext4_free_inodes_set(struct super_block *sb,
			  struct ext4_group_desc *bg, __u32 count)
{
	bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
}

void ext4_used_dirs_set(struct super_block *sb,
			  struct ext4_group_desc *bg, __u32 count)
{
	bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
}

void ext4_itable_unused_set(struct super_block *sb,
			  struct ext4_group_desc *bg, __u32 count)
{
	bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}


/* Just increment the non-pointer handle value */
static handle_t *ext4_get_nojournal(void)
{
	handle_t *handle = current->journal_info;
	unsigned long ref_cnt = (unsigned long)handle;

	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);

	ref_cnt++;
	handle = (handle_t *)ref_cnt;

	current->journal_info = handle;
	return handle;
}


/* Decrement the non-pointer handle value */
static void ext4_put_nojournal(handle_t *handle)
{
	unsigned long ref_cnt = (unsigned long)handle;

	BUG_ON(ref_cnt == 0);

	ref_cnt--;
	handle = (handle_t *)ref_cnt;

	current->journal_info = handle;
}

/*
 * Wrappers for jbd2_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
 * appropriate.
 */
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
	journal_t *journal;

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

	vfs_check_frozen(sb, SB_FREEZE_TRANS);
	/* 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 = EXT4_SB(sb)->s_journal;
	if (journal) {
		if (is_journal_aborted(journal)) {
			ext4_abort(sb, "Detected aborted journal");
			return ERR_PTR(-EROFS);
		}
		return jbd2_journal_start(journal, nblocks);
	}
	return ext4_get_nojournal();
}

/*
 * The only special thing we need to do here is to make sure that all
 * jbd2_journal_stop calls result in the superblock being marked dirty, so
 * that sync() will call the filesystem's write_super callback if
 * appropriate.
 */
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
	struct super_block *sb;
	int err;
	int rc;

	if (!ext4_handle_valid(handle)) {
		ext4_put_nojournal(handle);
		return 0;
	}
	sb = handle->h_transaction->t_journal->j_private;
	err = handle->h_err;
	rc = jbd2_journal_stop(handle);

	if (!err)
		err = rc;
	if (err)
		__ext4_std_error(sb, where, line, err);
	return err;
}

void ext4_journal_abort_handle(const char *caller, unsigned int line,
			       const char *err_fn, struct buffer_head *bh,
			       handle_t *handle, int err)
{
	char nbuf[16];
	const char *errstr = ext4_decode_error(NULL, err, nbuf);

	BUG_ON(!ext4_handle_valid(handle));

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

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

	if (is_handle_aborted(handle))
		return;

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

	jbd2_journal_abort_handle(handle);
}

static void __save_error_info(struct super_block *sb, const char *func,
			    unsigned int line)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
	es->s_last_error_time = cpu_to_le32(get_seconds());
	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
	es->s_last_error_line = cpu_to_le32(line);
	if (!es->s_first_error_time) {
		es->s_first_error_time = es->s_last_error_time;
		strncpy(es->s_first_error_func, func,
			sizeof(es->s_first_error_func));
		es->s_first_error_line = cpu_to_le32(line);
		es->s_first_error_ino = es->s_last_error_ino;
		es->s_first_error_block = es->s_last_error_block;
	}
	/*
	 * Start the daily error reporting function if it hasn't been
	 * started already
	 */
	if (!es->s_error_count)
		mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
	es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
}

static void save_error_info(struct super_block *sb, const char *func,
			    unsigned int line)
{
	__save_error_info(sb, func, line);
	ext4_commit_super(sb, 1);
}


/* 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 ext4, 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 jbd2_journal_abort() error code to record an error in
 * the journal instead.  On recovery, the journal will complain about
 * that error until we've noted it down and cleared it.
 */

static void ext4_handle_error(struct super_block *sb)
{
	if (sb->s_flags & MS_RDONLY)
		return;

	if (!test_opt(sb, ERRORS_CONT)) {
		journal_t *journal = EXT4_SB(sb)->s_journal;

		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
		if (journal)
			jbd2_journal_abort(journal, -EIO);
	}
	if (test_opt(sb, ERRORS_RO)) {
		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
		sb->s_flags |= MS_RDONLY;
	}
	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT4-fs (device %s): panic forced after error\n",
			sb->s_id);
}

void __ext4_error(struct super_block *sb, const char *function,
		  unsigned int line, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
	       sb->s_id, function, line, current->comm, &vaf);
	va_end(args);

	ext4_handle_error(sb);
}

void ext4_error_inode(struct inode *inode, const char *function,
		      unsigned int line, ext4_fsblk_t block,
		      const char *fmt, ...)
{
	va_list args;
	struct va_format vaf;
	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;

	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
	es->s_last_error_block = cpu_to_le64(block);
	save_error_info(inode->i_sb, function, line);
	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
	       inode->i_sb->s_id, function, line, inode->i_ino);
	if (block)
		printk(KERN_CONT "block %llu: ", block);
	printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
	va_end(args);

	ext4_handle_error(inode->i_sb);
}

void ext4_error_file(struct file *file, const char *function,
		     unsigned int line, ext4_fsblk_t block,
		     const char *fmt, ...)
{
	va_list args;
	struct va_format vaf;
	struct ext4_super_block *es;
	struct inode *inode = file->f_dentry->d_inode;
	char pathname[80], *path;

	es = EXT4_SB(inode->i_sb)->s_es;
	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
	save_error_info(inode->i_sb, function, line);
	path = d_path(&(file->f_path), pathname, sizeof(pathname));
	if (IS_ERR(path))
		path = "(unknown)";
	printk(KERN_CRIT
	       "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
	       inode->i_sb->s_id, function, line, inode->i_ino);
	if (block)
		printk(KERN_CONT "block %llu: ", block);
	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
	va_end(args);

	ext4_handle_error(inode->i_sb);
}

static const char *ext4_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 || (EXT4_SB(sb)->s_journal &&
			    EXT4_SB(sb)->s_journal->j_flags & JBD2_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;
}

/* __ext4_std_error decodes expected errors from journaling functions
 * automatically and invokes the appropriate error response.  */

void __ext4_std_error(struct super_block *sb, const char *function,
		      unsigned int line, int errno)
{
	char nbuf[16];
	const char *errstr;

	/* 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 = ext4_decode_error(sb, errno, nbuf);
	printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
	       sb->s_id, function, line, errstr);
	save_error_info(sb, function, line);

	ext4_handle_error(sb);
}

/*
 * ext4_abort is a much stronger failure handler than ext4_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 __ext4_abort(struct super_block *sb, const char *function,
		unsigned int line, const char *fmt, ...)
{
	va_list args;

	save_error_info(sb, function, line);
	va_start(args, fmt);
	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
	       function, line);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if ((sb->s_flags & MS_RDONLY) == 0) {
		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
		sb->s_flags |= MS_RDONLY;
		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
		if (EXT4_SB(sb)->s_journal)
			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
		save_error_info(sb, function, line);
	}
	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT4-fs panic from previous error\n");
}

void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
	va_end(args);
}

void __ext4_warning(struct super_block *sb, const char *function,
		    unsigned int line, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n",
	       sb->s_id, function, line, &vaf);
	va_end(args);
}

void __ext4_grp_locked_error(const char *function, unsigned int line,
			     struct super_block *sb, ext4_group_t grp,
			     unsigned long ino, ext4_fsblk_t block,
			     const char *fmt, ...)
__releases(bitlock)
__acquires(bitlock)
{
	struct va_format vaf;
	va_list args;
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

	es->s_last_error_ino = cpu_to_le32(ino);
	es->s_last_error_block = cpu_to_le64(block);
	__save_error_info(sb, function, line);

	va_start(args, fmt);

	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
	       sb->s_id, function, line, grp);
	if (ino)
		printk(KERN_CONT "inode %lu: ", ino);
	if (block)
		printk(KERN_CONT "block %llu:", (unsigned long long) block);
	printk(KERN_CONT "%pV\n", &vaf);
	va_end(args);

	if (test_opt(sb, ERRORS_CONT)) {
		ext4_commit_super(sb, 0);
		return;
	}

	ext4_unlock_group(sb, grp);
	ext4_handle_error(sb);
	/*
	 * We only get here in the ERRORS_RO case; relocking the group
	 * may be dangerous, but nothing bad will happen since the
	 * filesystem will have already been marked read/only and the
	 * journal has been aborted.  We return 1 as a hint to callers
	 * who might what to use the return value from
	 * ext4_grp_locked_error() to distinguish beween the
	 * ERRORS_CONT and ERRORS_RO case, and perhaps return more
	 * aggressively from the ext4 function in question, with a
	 * more appropriate error code.
	 */
	ext4_lock_group(sb, grp);
	return;
}

void ext4_update_dynamic_rev(struct super_block *sb)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
		return;

	ext4_warning(sb,
		     "updating to rev %d because of new feature flag, "
		     "running e2fsck is recommended",
		     EXT4_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT4_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 *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
	if (IS_ERR(bdev))
		goto fail;
	return bdev;

fail:
	ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
			__bdevname(dev, b), PTR_ERR(bdev));
	return NULL;
}

/*
 * Release the journal device
 */
static int ext4_blkdev_put(struct block_device *bdev)
{
	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}

static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
	struct block_device *bdev;
	int ret = -ENODEV;

	bdev = sbi->journal_bdev;
	if (bdev) {
		ret = ext4_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 ext4_inode_info, i_orphan)->vfs_inode;
}

static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
{
	struct list_head *l;

	ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
		 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 "  "
		       "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
		       inode->i_sb->s_id, inode->i_ino, inode,
		       inode->i_mode, inode->i_nlink,
		       NEXT_ORPHAN(inode));
	}
}

static void ext4_put_super(struct super_block *sb)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	int i, err;

	ext4_unregister_li_request(sb);
	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);

	flush_workqueue(sbi->dio_unwritten_wq);
	destroy_workqueue(sbi->dio_unwritten_wq);

	lock_super(sb);
	if (sb->s_dirt)
		ext4_commit_super(sb, 1);

	if (sbi->s_journal) {
		err = jbd2_journal_destroy(sbi->s_journal);
		sbi->s_journal = NULL;
		if (err < 0)
			ext4_abort(sb, "Couldn't clean up the journal");
	}

	del_timer(&sbi->s_err_report);
	ext4_release_system_zone(sb);
	ext4_mb_release(sb);
	ext4_ext_release(sb);
	ext4_xattr_put_super(sb);

	if (!(sb->s_flags & MS_RDONLY)) {
		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		ext4_commit_super(sb, 1);
	}
	if (sbi->s_proc) {
		remove_proc_entry(sb->s_id, ext4_proc_root);
	}
	kobject_del(&sbi->s_kobj);

	for (i = 0; i < sbi->s_gdb_count; i++)
		brelse(sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	if (is_vmalloc_addr(sbi->s_flex_groups))
		vfree(sbi->s_flex_groups);
	else
		kfree(sbi->s_flex_groups);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	percpu_counter_destroy(&sbi->s_dirtyblocks_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);
	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);
		ext4_blkdev_remove(sbi);
	}
	sb->s_fs_info = NULL;
	/*
	 * Now that we are completely done shutting down the
	 * superblock, we need to actually destroy the kobject.
	 */
	unlock_super(sb);
	kobject_put(&sbi->s_kobj);
	wait_for_completion(&sbi->s_kobj_unregister);
	kfree(sbi->s_blockgroup_lock);
	kfree(sbi);
}

static struct kmem_cache *ext4_inode_cachep;

/*
 * Called inside transaction, so use GFP_NOFS
 */
static struct inode *ext4_alloc_inode(struct super_block *sb)
{
	struct ext4_inode_info *ei;

	ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
	if (!ei)
		return NULL;

	ei->vfs_inode.i_version = 1;
	ei->vfs_inode.i_data.writeback_index = 0;
	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
	INIT_LIST_HEAD(&ei->i_prealloc_list);
	spin_lock_init(&ei->i_prealloc_lock);
	ei->i_reserved_data_blocks = 0;
	ei->i_reserved_meta_blocks = 0;
	ei->i_allocated_meta_blocks = 0;
	ei->i_da_metadata_calc_len = 0;
	spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
	ei->i_reserved_quota = 0;
#endif
	ei->jinode = NULL;
	INIT_LIST_HEAD(&ei->i_completed_io_list);
	spin_lock_init(&ei->i_completed_io_lock);
	ei->cur_aio_dio = NULL;
	ei->i_sync_tid = 0;
	ei->i_datasync_tid = 0;
	atomic_set(&ei->i_ioend_count, 0);
	atomic_set(&ei->i_aiodio_unwritten, 0);

	return &ei->vfs_inode;
}

static int ext4_drop_inode(struct inode *inode)
{
	int drop = generic_drop_inode(inode);

	trace_ext4_drop_inode(inode, drop);
	return drop;
}

static void ext4_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	INIT_LIST_HEAD(&inode->i_dentry);
	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
}

static void ext4_destroy_inode(struct inode *inode)
{
	ext4_ioend_wait(inode);
	if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
		ext4_msg(inode->i_sb, KERN_ERR,
			 "Inode %lu (%p): orphan list check failed!",
			 inode->i_ino, EXT4_I(inode));
		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
				EXT4_I(inode), sizeof(struct ext4_inode_info),
				true);
		dump_stack();
	}
	call_rcu(&inode->i_rcu, ext4_i_callback);
}

static void init_once(void *foo)
{
	struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;

	INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT4_FS_XATTR
	init_rwsem(&ei->xattr_sem);
#endif
	init_rwsem(&ei->i_data_sem);
	inode_init_once(&ei->vfs_inode);
}

static int init_inodecache(void)
{
	ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
					     sizeof(struct ext4_inode_info),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
					     init_once);
	if (ext4_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	kmem_cache_destroy(ext4_inode_cachep);
}

void ext4_clear_inode(struct inode *inode)
{
	invalidate_inode_buffers(inode);
	end_writeback(inode);
	dquot_drop(inode);
	ext4_discard_preallocations(inode);
	if (EXT4_I(inode)->jinode) {
		jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
					       EXT4_I(inode)->jinode);
		jbd2_free_inode(EXT4_I(inode)->jinode);
		EXT4_I(inode)->jinode = NULL;
	}
}

static inline void ext4_show_quota_options(struct seq_file *seq,
					   struct super_block *sb)
{
#if defined(CONFIG_QUOTA)
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (sbi->s_jquota_fmt) {
		char *fmtname = "";

		switch (sbi->s_jquota_fmt) {
		case QFMT_VFS_OLD:
			fmtname = "vfsold";
			break;
		case QFMT_VFS_V0:
			fmtname = "vfsv0";
			break;
		case QFMT_VFS_V1:
			fmtname = "vfsv1";
			break;
		}
		seq_printf(seq, ",jqfmt=%s", fmtname);
	}

	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 (test_opt(sb, USRQUOTA))
		seq_puts(seq, ",usrquota");

	if (test_opt(sb, GRPQUOTA))
		seq_puts(seq, ",grpquota");
#endif
}

/*
 * Show an option if
 *  - it's set to a non-default value OR
 *  - if the per-sb default is different from the global default
 */
static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	int def_errors;
	unsigned long def_mount_opts;
	struct super_block *sb = vfs->mnt_sb;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;

	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	def_errors     = le16_to_cpu(es->s_errors);

	if (sbi->s_sb_block != 1)
		seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
	if (test_opt(sb, MINIX_DF))
		seq_puts(seq, ",minixdf");
	if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
		seq_puts(seq, ",grpid");
	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
		seq_puts(seq, ",nogrpid");
	if (sbi->s_resuid != EXT4_DEF_RESUID ||
	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) {
		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
	}
	if (sbi->s_resgid != EXT4_DEF_RESGID ||
	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
	}
	if (test_opt(sb, ERRORS_RO)) {
		if (def_errors == EXT4_ERRORS_PANIC ||
		    def_errors == EXT4_ERRORS_CONTINUE) {
			seq_puts(seq, ",errors=remount-ro");
		}
	}
	if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
		seq_puts(seq, ",errors=continue");
	if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
		seq_puts(seq, ",errors=panic");
	if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
		seq_puts(seq, ",nouid32");
	if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
		seq_puts(seq, ",debug");
	if (test_opt(sb, OLDALLOC))
		seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
	if (test_opt(sb, XATTR_USER) &&
		!(def_mount_opts & EXT4_DEFM_XATTR_USER))
		seq_puts(seq, ",user_xattr");
	if (!test_opt(sb, XATTR_USER) &&
	    (def_mount_opts & EXT4_DEFM_XATTR_USER)) {
		seq_puts(seq, ",nouser_xattr");
	}
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
	if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
		seq_puts(seq, ",acl");
	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
		seq_puts(seq, ",noacl");
#endif
	if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
		seq_printf(seq, ",commit=%u",
			   (unsigned) (sbi->s_commit_interval / HZ));
	}
	if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
		seq_printf(seq, ",min_batch_time=%u",
			   (unsigned) sbi->s_min_batch_time);
	}
	if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
		seq_printf(seq, ",max_batch_time=%u",
			   (unsigned) sbi->s_min_batch_time);
	}

	/*
	 * We're changing the default of barrier mount option, so
	 * let's always display its mount state so it's clear what its
	 * status is.
	 */
	seq_puts(seq, ",barrier=");
	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
		seq_puts(seq, ",journal_async_commit");
	else if (test_opt(sb, JOURNAL_CHECKSUM))
		seq_puts(seq, ",journal_checksum");
	if (test_opt(sb, I_VERSION))
		seq_puts(seq, ",i_version");
	if (!test_opt(sb, DELALLOC) &&
	    !(def_mount_opts & EXT4_DEFM_NODELALLOC))
		seq_puts(seq, ",nodelalloc");

	if (test_opt(sb, MBLK_IO_SUBMIT))
		seq_puts(seq, ",mblk_io_submit");
	if (sbi->s_stripe)
		seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
	/*
	 * journal mode get enabled in different ways
	 * So just print the value even if we didn't specify it
	 */
	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
		seq_puts(seq, ",data=journal");
	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
		seq_puts(seq, ",data=ordered");
	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
		seq_puts(seq, ",data=writeback");

	if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
		seq_printf(seq, ",inode_readahead_blks=%u",
			   sbi->s_inode_readahead_blks);

	if (test_opt(sb, DATA_ERR_ABORT))
		seq_puts(seq, ",data_err=abort");

	if (test_opt(sb, NO_AUTO_DA_ALLOC))
		seq_puts(seq, ",noauto_da_alloc");

	if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
		seq_puts(seq, ",discard");

	if (test_opt(sb, NOLOAD))