fs/ext4/super.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  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/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.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/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#include <linux/dax.h>
#include <linux/cleancache.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
#include <linux/part_stat.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/fsnotify.h>

#include "ext4.h"
#include "ext4_extents.h"	/* Needed for trace points definition */
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"
#include "fsmap.h"

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

static struct ext4_lazy_init *ext4_li_info;
static DEFINE_MUTEX(ext4_li_mtx);
static struct ratelimit_state ext4_mount_msg_ratelimit;

static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
			     unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
static void ext4_update_super(struct super_block *sb);
static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
					struct ext4_super_block *es);
static int 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 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 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 inline int ext2_feature_set_ok(struct super_block *sb);
static inline int ext3_feature_set_ok(struct super_block *sb);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
static struct inode *ext4_get_journal_inode(struct super_block *sb,
					    unsigned int journal_inum);

/*
 * Lock ordering
 *
 * page fault path:
 * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
 *   -> page lock -> i_data_sem (rw)
 *
 * buffered write path:
 * sb_start_write -> i_mutex -> mmap_lock
 * sb_start_write -> i_mutex -> transaction start -> page lock ->
 *   i_data_sem (rw)
 *
 * truncate:
 * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
 *   page lock
 * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
 *   i_data_sem (rw)
 *
 * direct IO:
 * sb_start_write -> i_mutex -> mmap_lock
 * sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw)
 *
 * writepages:
 * transaction start -> page lock(s) -> i_data_sem (rw)
 */

#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
static struct file_system_type ext2_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext2",
	.mount		= ext4_mount,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext2");
MODULE_ALIAS("ext2");
#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
#else
#define IS_EXT2_SB(sb) (0)
#endif


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,
};
MODULE_ALIAS_FS("ext3");
MODULE_ALIAS("ext3");
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)


static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
				  bh_end_io_t *end_io)
{
	/*
	 * buffer's verified bit is no longer valid after reading from
	 * disk again due to write out error, clear it to make sure we
	 * recheck the buffer contents.
	 */
	clear_buffer_verified(bh);

	bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
	get_bh(bh);
	submit_bh(REQ_OP_READ, op_flags, bh);
}

void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
			 bh_end_io_t *end_io)
{
	BUG_ON(!buffer_locked(bh));

	if (ext4_buffer_uptodate(bh)) {
		unlock_buffer(bh);
		return;
	}
	__ext4_read_bh(bh, op_flags, end_io);
}

int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io)
{
	BUG_ON(!buffer_locked(bh));

	if (ext4_buffer_uptodate(bh)) {
		unlock_buffer(bh);
		return 0;
	}

	__ext4_read_bh(bh, op_flags, end_io);

	wait_on_buffer(bh);
	if (buffer_uptodate(bh))
		return 0;
	return -EIO;
}

int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
{
	if (trylock_buffer(bh)) {
		if (wait)
			return ext4_read_bh(bh, op_flags, NULL);
		ext4_read_bh_nowait(bh, op_flags, NULL);
		return 0;
	}
	if (wait) {
		wait_on_buffer(bh);
		if (buffer_uptodate(bh))
			return 0;
		return -EIO;
	}
	return 0;
}

/*
 * This works like __bread_gfp() except it uses ERR_PTR for error
 * returns.  Currently with sb_bread it's impossible to distinguish
 * between ENOMEM and EIO situations (since both result in a NULL
 * return.
 */
static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
					       sector_t block, int op_flags,
					       gfp_t gfp)
{
	struct buffer_head *bh;
	int ret;

	bh = sb_getblk_gfp(sb, block, gfp);
	if (bh == NULL)
		return ERR_PTR(-ENOMEM);
	if (ext4_buffer_uptodate(bh))
		return bh;

	ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true);
	if (ret) {
		put_bh(bh);
		return ERR_PTR(ret);
	}
	return bh;
}

struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
				   int op_flags)
{
	return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE);
}

struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
					    sector_t block)
{
	return __ext4_sb_bread_gfp(sb, block, 0, 0);
}

void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
{
	struct buffer_head *bh = sb_getblk_gfp(sb, block, 0);

	if (likely(bh)) {
		ext4_read_bh_lock(bh, REQ_RAHEAD, false);
		brelse(bh);
	}
}

static int ext4_verify_csum_type(struct super_block *sb,
				 struct ext4_super_block *es)
{
	if (!ext4_has_feature_metadata_csum(sb))
		return 1;

	return es->s_checksum_type == EXT4_CRC32C_CHKSUM;
}

static __le32 ext4_superblock_csum(struct super_block *sb,
				   struct ext4_super_block *es)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	int offset = offsetof(struct ext4_super_block, s_checksum);
	__u32 csum;

	csum = ext4_chksum(sbi, ~0, (char *)es, offset);

	return cpu_to_le32(csum);
}

static int ext4_superblock_csum_verify(struct super_block *sb,
				       struct ext4_super_block *es)
{
	if (!ext4_has_metadata_csum(sb))
		return 1;

	return es->s_checksum == ext4_superblock_csum(sb, es);
}

void ext4_superblock_csum_set(struct super_block *sb)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

	if (!ext4_has_metadata_csum(sb))
		return;

	es->s_checksum = ext4_superblock_csum(sb, es);
}

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_group_clusters(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_group_clusters_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);
}

static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now)
{
	now = clamp_val(now, 0, (1ull << 40) - 1);

	*lo = cpu_to_le32(lower_32_bits(now));
	*hi = upper_32_bits(now);
}

static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
{
	return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
}
#define ext4_update_tstamp(es, tstamp) \
	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \
			     ktime_get_real_seconds())
#define ext4_get_tstamp(es, tstamp) \
	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)

/*
 * The del_gendisk() function uninitializes the disk-specific data
 * structures, including the bdi structure, without telling anyone
 * else.  Once this happens, any attempt to call mark_buffer_dirty()
 * (for example, by ext4_commit_super), will cause a kernel OOPS.
 * This is a kludge to prevent these oops until we can put in a proper
 * hook in del_gendisk() to inform the VFS and file system layers.
 */
static int block_device_ejected(struct super_block *sb)
{
	struct inode *bd_inode = sb->s_bdev->bd_inode;
	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);

	return bdi->dev == NULL;
}

static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
{
	struct super_block		*sb = journal->j_private;
	struct ext4_sb_info		*sbi = EXT4_SB(sb);
	int				error = is_journal_aborted(journal);
	struct ext4_journal_cb_entry	*jce;

	BUG_ON(txn->t_state == T_FINISHED);

	ext4_process_freed_data(sb, txn->t_tid);

	spin_lock(&sbi->s_md_lock);
	while (!list_empty(&txn->t_private_list)) {
		jce = list_entry(txn->t_private_list.next,
				 struct ext4_journal_cb_entry, jce_list);
		list_del_init(&jce->jce_list);
		spin_unlock(&sbi->s_md_lock);
		jce->jce_func(sb, jce, error);
		spin_lock(&sbi->s_md_lock);
	}
	spin_unlock(&sbi->s_md_lock);
}

/*
 * This writepage callback for write_cache_pages()
 * takes care of a few cases after page cleaning.
 *
 * write_cache_pages() already checks for dirty pages
 * and calls clear_page_dirty_for_io(), which we want,
 * to write protect the pages.
 *
 * However, we may have to redirty a page (see below.)
 */
static int ext4_journalled_writepage_callback(struct page *page,
					      struct writeback_control *wbc,
					      void *data)
{
	transaction_t *transaction = (transaction_t *) data;
	struct buffer_head *bh, *head;
	struct journal_head *jh;

	bh = head = page_buffers(page);
	do {
		/*
		 * We have to redirty a page in these cases:
		 * 1) If buffer is dirty, it means the page was dirty because it
		 * contains a buffer that needs checkpointing. So the dirty bit
		 * needs to be preserved so that checkpointing writes the buffer
		 * properly.
		 * 2) If buffer is not part of the committing transaction
		 * (we may have just accidentally come across this buffer because
		 * inode range tracking is not exact) or if the currently running
		 * transaction already contains this buffer as well, dirty bit
		 * needs to be preserved so that the buffer gets writeprotected
		 * properly on running transaction's commit.
		 */
		jh = bh2jh(bh);
		if (buffer_dirty(bh) ||
		    (jh && (jh->b_transaction != transaction ||
			    jh->b_next_transaction))) {
			redirty_page_for_writepage(wbc, page);
			goto out;
		}
	} while ((bh = bh->b_this_page) != head);

out:
	return AOP_WRITEPAGE_ACTIVATE;
}

static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
	struct writeback_control wbc = {
		.sync_mode =  WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.range_start = jinode->i_dirty_start,
		.range_end = jinode->i_dirty_end,
        };

	return write_cache_pages(mapping, &wbc,
				 ext4_journalled_writepage_callback,
				 jinode->i_transaction);
}

static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
	int ret;

	if (ext4_should_journal_data(jinode->i_vfs_inode))
		ret = ext4_journalled_submit_inode_data_buffers(jinode);
	else
		ret = jbd2_journal_submit_inode_data_buffers(jinode);

	return ret;
}

static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
{
	int ret = 0;

	if (!ext4_should_journal_data(jinode->i_vfs_inode))
		ret = jbd2_journal_finish_inode_data_buffers(jinode);

	return ret;
}

static bool system_going_down(void)
{
	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
		|| system_state == SYSTEM_RESTART;
}

struct ext4_err_translation {
	int code;
	int errno;
};

#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err }

static struct ext4_err_translation err_translation[] = {
	EXT4_ERR_TRANSLATE(EIO),
	EXT4_ERR_TRANSLATE(ENOMEM),
	EXT4_ERR_TRANSLATE(EFSBADCRC),
	EXT4_ERR_TRANSLATE(EFSCORRUPTED),
	EXT4_ERR_TRANSLATE(ENOSPC),
	EXT4_ERR_TRANSLATE(ENOKEY),
	EXT4_ERR_TRANSLATE(EROFS),
	EXT4_ERR_TRANSLATE(EFBIG),
	EXT4_ERR_TRANSLATE(EEXIST),
	EXT4_ERR_TRANSLATE(ERANGE),
	EXT4_ERR_TRANSLATE(EOVERFLOW),
	EXT4_ERR_TRANSLATE(EBUSY),
	EXT4_ERR_TRANSLATE(ENOTDIR),
	EXT4_ERR_TRANSLATE(ENOTEMPTY),
	EXT4_ERR_TRANSLATE(ESHUTDOWN),
	EXT4_ERR_TRANSLATE(EFAULT),
};

static int ext4_errno_to_code(int errno)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(err_translation); i++)
		if (err_translation[i].errno == errno)
			return err_translation[i].code;
	return EXT4_ERR_UNKNOWN;
}

static void save_error_info(struct super_block *sb, int error,
			    __u32 ino, __u64 block,
			    const char *func, unsigned int line)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	/* We default to EFSCORRUPTED error... */
	if (error == 0)
		error = EFSCORRUPTED;

	spin_lock(&sbi->s_error_lock);
	sbi->s_add_error_count++;
	sbi->s_last_error_code = error;
	sbi->s_last_error_line = line;
	sbi->s_last_error_ino = ino;
	sbi->s_last_error_block = block;
	sbi->s_last_error_func = func;
	sbi->s_last_error_time = ktime_get_real_seconds();
	if (!sbi->s_first_error_time) {
		sbi->s_first_error_code = error;
		sbi->s_first_error_line = line;
		sbi->s_first_error_ino = ino;
		sbi->s_first_error_block = block;
		sbi->s_first_error_func = func;
		sbi->s_first_error_time = sbi->s_last_error_time;
	}
	spin_unlock(&sbi->s_error_lock);
}

/* 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.
 *
 * If force_ro is set, 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. This is
 * used to deal with unrecoverable failures such as journal IO errors or ENOMEM
 * at a critical moment in log management.
 */
static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
			      __u32 ino, __u64 block,
			      const char *func, unsigned int line)
{
	journal_t *journal = EXT4_SB(sb)->s_journal;
	bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);

	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
	if (test_opt(sb, WARN_ON_ERROR))
		WARN_ON_ONCE(1);

	if (!continue_fs && !sb_rdonly(sb)) {
		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
		if (journal)
			jbd2_journal_abort(journal, -EIO);
	}

	if (!bdev_read_only(sb->s_bdev)) {
		save_error_info(sb, error, ino, block, func, line);
		/*
		 * In case the fs should keep running, we need to writeout
		 * superblock through the journal. Due to lock ordering
		 * constraints, it may not be safe to do it right here so we
		 * defer superblock flushing to a workqueue.
		 */
		if (continue_fs && journal)
			schedule_work(&EXT4_SB(sb)->s_error_work);
		else
			ext4_commit_super(sb);
	}

	/*
	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
	 * could panic during 'reboot -f' as the underlying device got already
	 * disabled.
	 */
	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
		panic("EXT4-fs (device %s): panic forced after error\n",
			sb->s_id);
	}

	if (sb_rdonly(sb) || continue_fs)
		return;

	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
	/*
	 * Make sure updated value of ->s_mount_flags will be visible before
	 * ->s_flags update
	 */
	smp_wmb();
	sb->s_flags |= SB_RDONLY;
}

static void flush_stashed_error_work(struct work_struct *work)
{
	struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
						s_error_work);
	journal_t *journal = sbi->s_journal;
	handle_t *handle;

	/*
	 * If the journal is still running, we have to write out superblock
	 * through the journal to avoid collisions of other journalled sb
	 * updates.
	 *
	 * We use directly jbd2 functions here to avoid recursing back into
	 * ext4 error handling code during handling of previous errors.
	 */
	if (!sb_rdonly(sbi->s_sb) && journal) {
		struct buffer_head *sbh = sbi->s_sbh;
		handle = jbd2_journal_start(journal, 1);
		if (IS_ERR(handle))
			goto write_directly;
		if (jbd2_journal_get_write_access(handle, sbh)) {
			jbd2_journal_stop(handle);
			goto write_directly;
		}
		ext4_update_super(sbi->s_sb);
		if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
			ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to "
				 "superblock detected");
			clear_buffer_write_io_error(sbh);
			set_buffer_uptodate(sbh);
		}

		if (jbd2_journal_dirty_metadata(handle, sbh)) {
			jbd2_journal_stop(handle);
			goto write_directly;
		}
		jbd2_journal_stop(handle);
		ext4_notify_error_sysfs(sbi);
		return;
	}
write_directly:
	/*
	 * Write through journal failed. Write sb directly to get error info
	 * out and hope for the best.
	 */
	ext4_commit_super(sbi->s_sb);
	ext4_notify_error_sysfs(sbi);
}

#define ext4_error_ratelimit(sb)					\
		___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state),	\
			     "EXT4-fs error")

void __ext4_error(struct super_block *sb, const char *function,
		  unsigned int line, bool force_ro, int error, __u64 block,
		  const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
		return;

	trace_ext4_error(sb, function, line);
	if (ext4_error_ratelimit(sb)) {
		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);
	}
	fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED);

	ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}

void __ext4_error_inode(struct inode *inode, const char *function,
			unsigned int line, ext4_fsblk_t block, int error,
			const char *fmt, ...)
{
	va_list args;
	struct va_format vaf;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return;

	trace_ext4_error(inode->i_sb, function, line);
	if (ext4_error_ratelimit(inode->i_sb)) {
		va_start(args, fmt);
		vaf.fmt = fmt;
		vaf.va = &args;
		if (block)
			printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
			       "inode #%lu: block %llu: comm %s: %pV\n",
			       inode->i_sb->s_id, function, line, inode->i_ino,
			       block, current->comm, &vaf);
		else
			printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
			       "inode #%lu: comm %s: %pV\n",
			       inode->i_sb->s_id, function, line, inode->i_ino,
			       current->comm, &vaf);
		va_end(args);
	}
	fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED);

	ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
			  function, line);
}

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 inode *inode = file_inode(file);
	char pathname[80], *path;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return;

	trace_ext4_error(inode->i_sb, function, line);
	if (ext4_error_ratelimit(inode->i_sb)) {
		path = file_path(file, pathname, sizeof(pathname));
		if (IS_ERR(path))
			path = "(unknown)";
		va_start(args, fmt);
		vaf.fmt = fmt;
		vaf.va = &args;
		if (block)
			printk(KERN_CRIT
			       "EXT4-fs error (device %s): %s:%d: inode #%lu: "
			       "block %llu: comm %s: path %s: %pV\n",
			       inode->i_sb->s_id, function, line, inode->i_ino,
			       block, current->comm, path, &vaf);
		else
			printk(KERN_CRIT
			       "EXT4-fs error (device %s): %s:%d: inode #%lu: "
			       "comm %s: path %s: %pV\n",
			       inode->i_sb->s_id, function, line, inode->i_ino,
			       current->comm, path, &vaf);
		va_end(args);
	}
	fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED);

	ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
			  function, line);
}

const char *ext4_decode_error(struct super_block *sb, int errno,
			      char nbuf[16])
{
	char *errstr = NULL;

	switch (errno) {
	case -EFSCORRUPTED:
		errstr = "Corrupt filesystem";
		break;
	case -EFSBADCRC:
		errstr = "Filesystem failed CRC";
		break;
	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;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
		return;

	/* 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_rdonly(sb))
		return;

	if (ext4_error_ratelimit(sb)) {
		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);
	}
	fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED);

	ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}

void __ext4_msg(struct super_block *sb,
		const char *prefix, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	atomic_inc(&EXT4_SB(sb)->s_msg_count);
	if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
		return;

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

static int ext4_warning_ratelimit(struct super_block *sb)
{
	atomic_inc(&EXT4_SB(sb)->s_warning_count);
	return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
			    "EXT4-fs warning");
}

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

	if (!ext4_warning_ratelimit(sb))
		return;

	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_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	if (!ext4_warning_ratelimit(inode->i_sb))
		return;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: "
	       "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id,
	       function, line, inode->i_ino, current->comm, &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;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
		return;

	trace_ext4_error(sb, function, line);
	if (ext4_error_ratelimit(sb)) {
		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)) {
		if (test_opt(sb, WARN_ON_ERROR))
			WARN_ON_ONCE(1);
		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
		if (!bdev_read_only(sb->s_bdev)) {
			save_error_info(sb, EFSCORRUPTED, ino, block, function,
					line);
			schedule_work(&EXT4_SB(sb)->s_error_work);
		}
		return;
	}
	ext4_unlock_group(sb, grp);
	ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
	/*
	 * 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 between 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_mark_group_bitmap_corrupted(struct super_block *sb,
				     ext4_group_t group,
				     unsigned int flags)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
	int ret;

	if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
					    &grp->bb_state);
		if (!ret)
			percpu_counter_sub(&sbi->s_freeclusters_counter,
					   grp->bb_free);
	}

	if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) {
		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
					    &grp->bb_state);
		if (!ret && gdp) {
			int count;

			count = ext4_free_inodes_count(sb, gdp);
			percpu_counter_sub(&sbi->s_freeinodes_counter,
					   count);
		}
	}
}

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;

	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 unknown-block(%u,%u) %ld",
		 MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
	return NULL;
}

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

static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
	struct block_device *bdev;
	bdev = sbi->s_journal_bdev;
	if (bdev) {
		ext4_blkdev_put(bdev);
		sbi->s_journal_bdev = NULL;
	}
}

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));
	}
}

#ifdef CONFIG_QUOTA
static int ext4_quota_off(struct super_block *sb, int type);

static inline void ext4_quota_off_umount(struct super_block *sb)
{
	int type;

	/* Use our quota_off function to clear inode flags etc. */
	for (type = 0; type < EXT4_MAXQUOTAS; type++)
		ext4_quota_off(sb, type);
}

/*
 * This is a helper function which is used in the mount/remount
 * codepaths (which holds s_umount) to fetch the quota file name.
 */
static inline char *get_qf_name(struct super_block *sb,
				struct ext4_sb_info *sbi,
				int type)
{
	return rcu_dereference_protected(sbi->s_qf_names[type],
					 lockdep_is_held(&sb->s_umount));
}
#else
static inline void ext4_quota_off_umount(struct super_block *sb)
{
}
#endif

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;
	struct buffer_head **group_desc;
	struct flex_groups **flex_groups;
	int aborted = 0;
	int i, err;

	ext4_unregister_li_request(sb);
	ext4_quota_off_umount(sb);

	flush_work(&sbi->s_error_work);
	destroy_workqueue(sbi->rsv_conversion_wq);
	ext4_release_orphan_info(sb);

	/*
	 * Unregister sysfs before destroying jbd2 journal.
	 * Since we could still access attr_journal_task attribute via sysfs
	 * path which could have sbi->s_journal->j_task as NULL
	 */
	ext4_unregister_sysfs(sb);

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

	ext4_es_unregister_shrinker(sbi);
	del_timer_sync(&sbi->s_err_report);
	ext4_release_system_zone(sb);
	ext4_mb_release(sb);
	ext4_ext_release(sb);

	if (!sb_rdonly(sb) && !aborted) {
		ext4_clear_feature_journal_needs_recovery(sb);
		ext4_clear_feature_orphan_present(sb);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
	}
	if (!sb_rdonly(sb))
		ext4_commit_super(sb);

	rcu_read_lock();
	group_desc = rcu_dereference(sbi->s_group_desc);
	for (i = 0; i < sbi->s_gdb_count; i++)
		brelse(group_desc[i]);
	kvfree(group_desc);
	flex_groups = rcu_dereference(sbi->s_flex_groups);
	if (flex_groups) {
		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
			kvfree(flex_groups[i]);
		kvfree(flex_groups);
	}
	rcu_read_unlock();
	percpu_counter_destroy(&sbi->s_freeclusters_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
	percpu_free_rwsem(&sbi->s_writepages_rwsem);
#ifdef CONFIG_QUOTA
	for (i = 0; i < EXT4_MAXQUOTAS; i++)
		kfree(get_qf_name(sb, sbi, 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);
	ASSERT(list_empty(&sbi->s_orphan));

	sync_blockdev(sb->s_bdev);
	invalidate_bdev(sb->s_bdev);
	if (sbi->s_journal_bdev && sbi->s_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->s_journal_bdev);
		invalidate_bdev(sbi->s_journal_bdev);
		ext4_blkdev_remove(sbi);
	}

	ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
	sbi->s_ea_inode_cache = NULL;

	ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
	sbi->s_ea_block_cache = NULL;

	ext4_stop_mmpd(sbi);

	brelse(sbi->s_sbh);
	sb->s_fs_info = NULL;
	/*
	 * Now that we are completely done shutting down the
	 * superblock, we need to actually destroy the kobject.
	 */
	kobject_put(&sbi->s_kobj);
	wait_for_completion(&sbi->s_kobj_unregister);
	if (sbi->s_chksum_driver)
		crypto_free_shash(sbi->s_chksum_driver);
	kfree(sbi->s_blockgroup_lock);
	fs_put_dax(sbi->s_daxdev);
	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
#ifdef CONFIG_UNICODE
	utf8_unload(sb->s_encoding);
#endif
	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;

	inode_set_iversion(&ei->vfs_inode, 1);
	spin_lock_init(&ei->i_raw_lock);
	INIT_LIST_HEAD(&ei->i_prealloc_list);
	atomic_set(&ei->i_prealloc_active, 0);
	spin_lock_init(&ei->i_prealloc_lock);
	ext4_es_init_tree(&ei->i_es_tree);
	rwlock_init(&ei->i_es_lock);
	INIT_LIST_HEAD(&ei->i_es_list);
	ei->i_es_all_nr = 0;
	ei->i_es_shk_nr = 0;
	ei->i_es_shrink_lblk = 0;
	ei->i_reserved_data_blocks = 0;
	spin_lock_init(&(ei->i_block_reservation_lock));
	ext4_init_pending_tree(&ei->i_pending_tree);
#ifdef CONFIG_QUOTA
	ei->i_reserved_quota = 0;
	memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
#endif
	ei->jinode = NULL;
	INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
	spin_lock_init(&ei->i_completed_io_lock);
	ei->i_sync_tid = 0;
	ei->i_datasync_tid = 0;
	atomic_set(&ei->i_unwritten, 0);
	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
	ext4_fc_init_inode(&ei->vfs_inode);
	mutex_init(&ei->i_fc_lock);
	return &ei->vfs_inode;
}

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

	if (!drop)
		drop = fscrypt_drop_inode(inode);

	trace_ext4_drop_inode(inode, drop);
	return drop;
}

static void ext4_free_in_core_inode(struct inode *inode)
{
	fscrypt_free_inode(inode);
	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
		pr_warn("%s: inode %ld still in fc list",
			__func__, inode->i_ino);
	}
	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
}

static void ext4_destroy_inode(struct inode *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();
	}

	if (EXT4_I(inode)->i_reserved_data_blocks)
		ext4_msg(inode->i_sb, KERN_ERR,
			 "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
			 inode->i_ino, EXT4_I(inode),
			 EXT4_I(inode)->i_reserved_data_blocks);
}

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

	INIT_LIST_HEAD(&ei->i_orphan);
	init_rwsem(&ei->xattr_sem);
	init_rwsem(&ei->i_data_sem);
	inode_init_once(&ei->vfs_inode);
	ext4_fc_init_inode(&ei->vfs_inode);
}

static int __init init_inodecache(void)
{
	ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache",
				sizeof(struct ext4_inode_info), 0,
				(SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
					SLAB_ACCOUNT),
				offsetof(struct ext4_inode_info, i_data),
				sizeof_field(struct ext4_inode_info, i_data),
				init_once);
	if (ext4_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(ext4_inode_cachep);
}

void ext4_clear_inode(struct inode *inode)
{
	ext4_fc_del(inode);
	invalidate_inode_buffers(inode);
	clear_inode(inode);
	ext4_discard_preallocations(inode, 0);
	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
	dquot_drop(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;
	}
	fscrypt_put_encryption_info(inode);
	fsverity_cleanup_inode(inode);
}

static struct inode *ext4_nfs_get_inode(struct super_block *sb,
					u64 ino, u32 generation)
{
	struct inode *inode;

	/*
	 * Currently we don't know the generation for parent directory, so
	 * a generation of 0 means "accept any"
	 */
	inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	if (generation && inode->i_generation != generation) {
		iput(inode);
		return ERR_PTR(-ESTALE);
	}

	return inode;
}

static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid,
					int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    ext4_nfs_get_inode);
}

static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
					int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    ext4_nfs_get_inode);
}

static int ext4_nfs_commit_metadata(struct inode *inode)
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL
	};

	trace_ext4_nfs_commit_metadata(inode);
	return ext4_write_inode(inode, &wbc);
}

#ifdef CONFIG_FS_ENCRYPTION
static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
{
	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
}

static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
							void *fs_data)
{
	handle_t *handle = fs_data;
	int res, res2, credits, retries = 0;

	/*
	 * Encrypting the root directory is not allowed because e2fsck expects
	 * lost+found to exist and be unencrypted, and encrypting the root
	 * directory would imply encrypting the lost+found directory as well as
	 * the filename "lost+found" itself.
	 */
	if (inode->i_ino == EXT4_ROOT_INO)
		return -EPERM;

	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
		return -EINVAL;

	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
		return -EOPNOTSUPP;

	res = ext4_convert_inline_data(inode);
	if (res)
		return res;

	/*
	 * If a journal handle was specified, then the encryption context is
	 * being set on a new inode via inheritance and is part of a larger
	 * transaction to create the inode.  Otherwise the encryption context is
	 * being set on an existing inode in its own transaction.  Only in the
	 * latter case should the "retry on ENOSPC" logic be used.
	 */

	if (handle) {
		res = ext4_xattr_set_handle(handle, inode,
					    EXT4_XATTR_INDEX_ENCRYPTION,
					    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
					    ctx, len, 0);
		if (!res) {
			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
			ext4_clear_inode_state(inode,
					EXT4_STATE_MAY_INLINE_DATA);
			/*
			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
			 * S_DAX may be disabled
			 */
			ext4_set_inode_flags(inode, false);
		}
		return res;
	}

	res = dquot_initialize(inode);
	if (res)
		return res;
retry:
	res = ext4_xattr_set_credits(inode, len, false /* is_create */,
				     &credits);
	if (res)
		return res;

	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
				    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
				    ctx, len, 0);
	if (!res) {
		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
		/*
		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
		 * S_DAX may be disabled
		 */
		ext4_set_inode_flags(inode, false);
		res = ext4_mark_inode_dirty(handle, inode);
		if (res)
			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
	}
	res2 = ext4_journal_stop(handle);

	if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
		goto retry;
	if (!res)
		res = res2;
	return res;
}

static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
{
	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
}

static bool ext4_has_stable_inodes(struct super_block *sb)
{
	return ext4_has_feature_stable_inodes(sb);
}

static void ext4_get_ino_and_lblk_bits(struct super_block *sb,
				       int *ino_bits_ret, int *lblk_bits_ret)
{
	*ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count);
	*lblk_bits_ret = 8 * sizeof(ext4_lblk_t);
}

static const struct fscrypt_operations ext4_cryptops = {
	.key_prefix		= "ext4:",
	.get_context		= ext4_get_context,
	.set_context		= ext4_set_context,
	.get_dummy_policy	= ext4_get_dummy_policy,
	.empty_dir		= ext4_empty_dir,
	.has_stable_inodes	= ext4_has_stable_inodes,
	.get_ino_and_lblk_bits	= ext4_get_ino_and_lblk_bits,
};
#endif

#ifdef CONFIG_QUOTA
static const char * const quotatypes[] = INITQFNAMES;
#define QTYPE2NAME(t) (quotatypes[t])

static int ext4_write_dquot(struct dquot *dquot);
static int ext4_acquire_dquot(struct dquot *dquot);
static int ext4_release_dquot(struct dquot *dquot);
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
			 const struct path *path);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off);
static ssize_t ext4_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off);
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
			     unsigned int flags);

static struct dquot **ext4_get_dquots(struct inode *inode)
{
	return EXT4_I(inode)->i_dquot;
}

static const struct dquot_operations ext4_quota_operations = {
	.get_reserved_space	= ext4_get_reserved_space,
	.write_dquot		= ext4_write_dquot,
	.acquire_dquot		= ext4_acquire_dquot,
	.release_dquot		= ext4_release_dquot,
	.mark_dirty		= ext4_mark_dquot_dirty,
	.write_info		= ext4_write_info,
	.alloc_dquot		= dquot_alloc,
	.destroy_dquot		= dquot_destroy,
	.get_projid		= ext4_get_projid,
	.get_inode_usage	= ext4_get_inode_usage,
	.get_next_id		= dquot_get_next_id,
};

static const struct quotactl_ops ext4_qctl_operations = {
	.quota_on	= ext4_quota_on,
	.quota_off	= ext4_quota_off,
	.quota_sync	= dquot_quota_sync,
	.get_state	= dquot_get_state,
	.set_info	= dquot_set_dqinfo,
	.get_dqblk	= dquot_get_dqblk,
	.set_dqblk	= dquot_set_dqblk,
	.get_nextdqblk	= dquot_get_next_dqblk,
};
#endif

static const struct super_operations ext4_sops = {
	.alloc_inode	= ext4_alloc_inode,
	.free_inode	= ext4_free_in_core_inode,
	.destroy_inode	= ext4_destroy_inode,
	.write_inode	= ext4_write_inode,
	.dirty_inode	= ext4_dirty_inode,
	.drop_inode	= ext4_drop_inode,
	.evict_inode	= ext4_evict_inode,
	.put_super	= ext4_put_super,
	.sync_fs	= ext4_sync_fs,
	.freeze_fs	= ext4_freeze,
	.unfreeze_fs	= ext4_unfreeze,
	.statfs		= ext4_statfs,
	.remount_fs	= ext4_remount,
	.show_options	= ext4_show_options,
#ifdef CONFIG_QUOTA
	.quota_read	= ext4_quota_read,
	.quota_write	= ext4_quota_write,
	.get_dquots	= ext4_get_dquots,
#endif
};

static const struct export_operations ext4_export_ops = {
	.fh_to_dentry = ext4_fh_to_dentry,
	.fh_to_parent = ext4_fh_to_parent,
	.get_parent = ext4_get_parent,
	.commit_metadata = ext4_nfs_commit_metadata,
};

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,
	Opt_nouid32, Opt_debug, Opt_removed,
	Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
	Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
	Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
	Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
	Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
	Opt_inlinecrypt,
	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
	Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
	Opt_nowarn_on_error, Opt_mblk_io_submit,
	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
	Opt_inode_readahead_blks, Opt_journal_ioprio,
	Opt_dioread_nolock, Opt_dioread_lock,
	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
	Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan,
#ifdef CONFIG_EXT4_DEBUG
	Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
};

static const 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_debug, "debug"},
	{Opt_removed, "oldalloc"},
	{Opt_removed, "orlov"},
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
	{Opt_noload, "norecovery"},
	{Opt_noload, "noload"},
	{Opt_removed, "nobh"},
	{Opt_removed, "bh"},
	{Opt_commit, "commit=%u"},
	{Opt_min_batch_time, "min_batch_time=%u"},
	{Opt_max_batch_time, "max_batch_time=%u"},
	{Opt_journal_dev, "journal_dev=%u"},
	{Opt_journal_path, "journal_path=%s"},
	{Opt_journal_checksum, "journal_checksum"},
	{Opt_nojournal_checksum, "nojournal_checksum"},
	{Opt_journal_async_commit, "journal_async_commit"},
	{Opt_abort, "abort"},
	{Opt_data_journal, "data=journal"},
	{Opt_data_ordered, "data=ordered"},
	{Opt_data_writeback, "data=writeback"},
	{Opt_data_err_abort, "data_err=abort"},
	{Opt_data_err_ignore, "data_err=ignore"},
	{Opt_offusrjquota, "usrjquota="},
	{Opt_usrjquota, "usrjquota=%s"},
	{Opt_offgrpjquota, "grpjquota="},
	{Opt_grpjquota, "grpjquota=%s"},
	{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
	{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
	{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
	{Opt_grpquota, "grpquota"},
	{Opt_noquota, "noquota"},
	{Opt_quota, "quota"},
	{Opt_usrquota, "usrquota"},
	{Opt_prjquota, "prjquota"},
	{Opt_barrier, "barrier=%u"},
	{Opt_barrier, "barrier"},
	{Opt_nobarrier, "nobarrier"},
	{Opt_i_version, "i_version"},
	{Opt_dax, "dax"},
	{Opt_dax_always, "dax=always"},
	{Opt_dax_inode, "dax=inode"},
	{Opt_dax_never, "dax=never"},
	{Opt_stripe, "stripe=%u"},
	{Opt_delalloc, "delalloc"},
	{Opt_warn_on_error, "warn_on_error"},
	{Opt_nowarn_on_error, "nowarn_on_error"},
	{Opt_lazytime, "lazytime"},
	{Opt_nolazytime, "nolazytime"},
	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
	{Opt_nodelalloc, "nodelalloc"},
	{Opt_removed, "mblk_io_submit"},
	{Opt_removed, "nomblk_io_submit"},
	{Opt_block_validity, "block_validity"},
	{Opt_noblock_validity, "noblock_validity"},
	{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
	{Opt_journal_ioprio, "journal_ioprio=%u"},
	{Opt_auto_da_alloc, "auto_da_alloc=%u"},
	{Opt_auto_da_alloc, "auto_da_alloc"},
	{Opt_noauto_da_alloc, "noauto_da_alloc"},
	{Opt_dioread_nolock, "dioread_nolock"},
	{Opt_dioread_lock, "nodioread_nolock"},
	{Opt_dioread_lock, "dioread_lock"},
	{Opt_discard, "discard"},
	{Opt_nodiscard, "nodiscard"},
	{Opt_init_itable, "init_itable=%u"},
	{Opt_init_itable, "init_itable"},
	{Opt_noinit_itable, "noinit_itable"},
#ifdef CONFIG_EXT4_DEBUG
	{Opt_fc_debug_force, "fc_debug_force"},
	{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
#endif
	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
	{Opt_test_dummy_encryption, "test_dummy_encryption"},
	{Opt_inlinecrypt, "inlinecrypt"},
	{Opt_nombcache, "nombcache"},
	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
	{Opt_removed, "prefetch_block_bitmaps"},
	{Opt_no_prefetch_block_bitmaps, "no_prefetch_block_bitmaps"},
	{Opt_mb_optimize_scan, "mb_optimize_scan=%d"},
	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
	{Opt_removed, "noreservation"}, /* mount option from ext2/3 */
	{Opt_removed, "journal=%u"},	/* mount option from ext2/3 */
	{Opt_err, NULL},
};

static ext4_fsblk_t get_sb_block(void **data)
{
	ext4_fsblk_t	sb_block;
	char		*options = (char *) *data;

	if (!options || strncmp(options, "sb=", 3) != 0)
		return 1;	/* Default location */

	options += 3;
	/* TODO: use simple_strtoll with >32bit ext4 */
	sb_block = simple_strtoul(options, &options, 0);
	if (*options && *options != ',') {
		printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
		       (char *) *data);
		return 1;
	}
	if (*options == ',')
		options++;
	*data = (void *) options;

	return sb_block;
}

#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
#define DEFAULT_MB_OPTIMIZE_SCAN	(-1)

static const char deprecated_msg[] =
	"Mount option \"%s\" will be removed by %s\n"
	"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";

#ifdef CONFIG_QUOTA
static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	char *qname, *old_qname = get_qf_name(sb, sbi, qtype);
	int ret = -1;

	if (sb_any_quota_loaded(sb) && !old_qname) {
		ext4_msg(sb, KERN_ERR,
			"Cannot change journaled "
			"quota options when quota turned on");
		return -1;
	}
	if (ext4_has_feature_quota(sb)) {
		ext4_msg(sb, KERN_INFO, "Journaled quota options "
			 "ignored when QUOTA feature is enabled");
		return 1;
	}
	qname = match_strdup(args);
	if (!qname) {
		ext4_msg(sb, KERN_ERR,
			"Not enough memory for storing quotafile name");
		return -1;
	}
	if (old_qname) {
		if (strcmp(old_qname, qname) == 0)
			ret = 1;
		else
			ext4_msg(sb, KERN_ERR,
				 "%s quota file already specified",
				 QTYPE2NAME(qtype));
		goto errout;
	}
	if (strchr(qname, '/')) {
		ext4_msg(sb, KERN_ERR,
			"quotafile must be on filesystem root");
		goto errout;
	}
	rcu_assign_pointer(sbi->s_qf_names[qtype], qname);
	set_opt(sb, QUOTA);
	return 1;
errout:
	kfree(qname);
	return ret;
}

static int clear_qf_name(struct super_block *sb, int qtype)
{

	struct ext4_sb_info *sbi = EXT4_SB(sb);
	char *old_qname = get_qf_name(sb, sbi, qtype);

	if (sb_any_quota_loaded(sb) && old_qname) {
		ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
			" when quota turned on");
		return -1;
	}
	rcu_assign_pointer(sbi->s_qf_names[qtype], NULL);
	synchronize_rcu();
	kfree(old_qname);
	return 1;
}
#endif

#define MOPT_SET	0x0001
#define MOPT_CLEAR	0x0002
#define MOPT_NOSUPPORT	0x0004
#define MOPT_EXPLICIT	0x0008
#define MOPT_CLEAR_ERR	0x0010
#define MOPT_GTE0	0x0020
#ifdef CONFIG_QUOTA
#define MOPT_Q		0
#define MOPT_QFMT	0x0040
#else
#define MOPT_Q		MOPT_NOSUPPORT
#define MOPT_QFMT	MOPT_NOSUPPORT
#endif
#define MOPT_DATAJ	0x0080
#define MOPT_NO_EXT2	0x0100
#define MOPT_NO_EXT3	0x0200
#define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
#define MOPT_STRING	0x0400
#define MOPT_SKIP	0x0800
#define	MOPT_2		0x1000

static const struct mount_opts {
	int	token;
	int	mount_opt;
	int	flags;
} ext4_mount_opts[] = {
	{Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET},
	{Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
	{Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
	{Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
	{Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
	{Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
	{Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK,
	 MOPT_EXT4_ONLY | MOPT_SET},
	{Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK,
	 MOPT_EXT4_ONLY | MOPT_CLEAR},
	{Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET},
	{Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR},
	{Opt_delalloc, EXT4_MOUNT_DELALLOC,
	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
	 MOPT_EXT4_ONLY | MOPT_CLEAR},
	{Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
	{Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
	{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
	 MOPT_EXT4_ONLY | MOPT_CLEAR},
	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
	{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
				    EXT4_MOUNT_JOURNAL_CHECKSUM),
	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
	{Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET},
	{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
	{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
	{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
	{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
	 MOPT_NO_EXT2},
	{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
	 MOPT_NO_EXT2},
	{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
	{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
	{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
	{Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR},
	{Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR},
	{Opt_commit, 0, MOPT_GTE0},
	{Opt_max_batch_time, 0, MOPT_GTE0},
	{Opt_min_batch_time, 0, MOPT_GTE0},
	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
	{Opt_init_itable, 0, MOPT_GTE0},
	{Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP},
	{Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS,
		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
	{Opt_dax_inode, EXT4_MOUNT2_DAX_INODE,
		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
	{Opt_dax_never, EXT4_MOUNT2_DAX_NEVER,
		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
	{Opt_stripe, 0, MOPT_GTE0},
	{Opt_resuid, 0, MOPT_GTE0},
	{Opt_resgid, 0, MOPT_GTE0},
	{Opt_journal_dev, 0, MOPT_NO_EXT2 | MOPT_GTE0},
	{Opt_journal_path, 0, MOPT_NO_EXT2 | MOPT_STRING},
	{Opt_journal_ioprio, 0, MOPT_NO_EXT2 | MOPT_GTE0},
	{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
	{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
	{Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA,
	 MOPT_NO_EXT2 | MOPT_DATAJ},
	{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
	{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
#ifdef CONFIG_EXT4_FS_POSIX_ACL
	{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
	{Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
#else
	{Opt_acl, 0, MOPT_NOSUPPORT},
	{Opt_noacl, 0, MOPT_NOSUPPORT},
#endif
	{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
	{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
	{Opt_debug_want_extra_isize, 0, MOPT_GTE0},
	{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
	{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
							MOPT_SET | MOPT_Q},
	{Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
							MOPT_SET | MOPT_Q},
	{Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA,
							MOPT_SET | MOPT_Q},
	{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
		       EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
							MOPT_CLEAR | MOPT_Q},
	{Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
	{Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
	{Opt_offusrjquota, 0, MOPT_Q},
	{Opt_offgrpjquota, 0, MOPT_Q},
	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
	{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
	{Opt_test_dummy_encryption, 0, MOPT_STRING},
	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
	{Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
	 MOPT_SET},
	{Opt_mb_optimize_scan, EXT4_MOUNT2_MB_OPTIMIZE_SCAN, MOPT_GTE0},
#ifdef CONFIG_EXT4_DEBUG
	{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
	 MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
	{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
#endif
	{Opt_err, 0, 0}
};

#ifdef CONFIG_UNICODE
static const struct ext4_sb_encodings {
	__u16 magic;
	char *name;
	char *version;
} ext4_sb_encoding_map[] = {
	{EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"},
};

static int ext4_sb_read_encoding(const struct ext4_super_block *es,
				 const struct ext4_sb_encodings **encoding,
				 __u16 *flags)
{
	__u16 magic = le16_to_cpu(es->s_encoding);
	int i;

	for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++)
		if (magic == ext4_sb_encoding_map[i].magic)
			break;

	if (i >= ARRAY_SIZE(ext4_sb_encoding_map))
		return -EINVAL;

	*encoding = &ext4_sb_encoding_map[i];
	*flags = le16_to_cpu(es->s_encoding_flags);

	return 0;
}
#endif

static int ext4_set_test_dummy_encryption(struct super_block *sb,
					  const char *opt,
					  const substring_t *arg,
					  bool is_remount)
{
#ifdef CONFIG_FS_ENCRYPTION
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	int err;

	/*
	 * This mount option is just for testing, and it's not worthwhile to
	 * implement the extra complexity (e.g. RCU protection) that would be
	 * needed to allow it to be set or changed during remount.  We do allow
	 * it to be specified during remount, but only if there is no change.
	 */
	if (is_remount && !sbi->s_dummy_enc_policy.policy) {
		ext4_msg(sb, KERN_WARNING,
			 "Can't set test_dummy_encryption on remount");
		return -1;
	}
	err = fscrypt_set_test_dummy_encryption(sb, arg->from,
						&sbi->s_dummy_enc_policy);
	if (err) {
		if (err == -EEXIST)
			ext4_msg(sb, KERN_WARNING,
				 "Can't change test_dummy_encryption on remount");
		else if (err == -EINVAL)
			ext4_msg(sb, KERN_WARNING,
				 "Value of option \"%s\" is unrecognized", opt);
		else
			ext4_msg(sb, KERN_WARNING,
				 "Error processing option \"%s\" [%d]",
				 opt, err);
		return -1;
	}
	ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled");
#else
	ext4_msg(sb, KERN_WARNING,
		 "Test dummy encryption mount option ignored");
#endif
	return 1;
}

struct ext4_parsed_options {
	unsigned long journal_devnum;
	unsigned int journal_ioprio;
	int mb_optimize_scan;
};

static int handle_mount_opt(struct super_block *sb, char *opt, int token,
			    substring_t *args, struct ext4_parsed_options *parsed_opts,
			    int is_remount)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	const struct mount_opts *m;
	kuid_t uid;
	kgid_t gid;
	int arg = 0;

#ifdef CONFIG_QUOTA
	if (token == Opt_usrjquota)
		return set_qf_name(sb, USRQUOTA, &args[0]);
	else if (token == Opt_grpjquota)
		return set_qf_name(sb, GRPQUOTA, &args[0]);
	else if (token == Opt_offusrjquota)
		return clear_qf_name(sb, USRQUOTA);
	else if (token == Opt_offgrpjquota)
		return clear_qf_name(sb, GRPQUOTA);
#endif
	switch (token) {
	case Opt_noacl:
	case Opt_nouser_xattr:
		ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5");
		break;
	case Opt_sb:
		return 1;	/* handled by get_sb_block() */
	case Opt_removed:
		ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
		return 1;
	case Opt_abort:
		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
		return 1;
	case Opt_i_version:
		sb->s_flags |= SB_I_VERSION;
		return 1;
	case Opt_lazytime:
		sb->s_flags |= SB_LAZYTIME;
		return 1;
	case Opt_nolazytime:
		sb->s_flags &= ~SB_LAZYTIME;
		return 1;
	case Opt_inlinecrypt:
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
		sb->s_flags |= SB_INLINECRYPT;
#else
		ext4_msg(sb, KERN_ERR, "inline encryption not supported");
#endif
		return 1;
	}

	for (m = ext4_mount_opts; m->token != Opt_err; m++)
		if (token == m->token)
			break;

	if (m->token == Opt_err) {
		ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
			 "or missing value", opt);
		return -1;
	}

	if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) {
		ext4_msg(sb, KERN_ERR,
			 "Mount option \"%s\" incompatible with ext2", opt);
		return -1;
	}
	if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) {
		ext4_msg(sb, KERN_ERR,
			 "Mount option \"%s\" incompatible with ext3", opt);
		return -1;
	}

	if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
		return -1;
	if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
		return -1;
	if (m->flags & MOPT_EXPLICIT) {
		if (m->mount_opt & EXT4_MOUNT_DELALLOC) {
			set_opt2(sb, EXPLICIT_DELALLOC);
		} else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) {
			set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM);
		} else
			return -1;
	}
	if (m->flags & MOPT_CLEAR_ERR)
		clear_opt(sb, ERRORS_MASK);
	if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
		ext4_msg(sb, KERN_ERR, "Cannot change quota "
			 "options when quota turned on");
		return -1;
	}

	if (m->flags & MOPT_NOSUPPORT) {
		ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
	} else if (token == Opt_commit) {
		if (arg == 0)
			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
		else if (arg > INT_MAX / HZ) {
			ext4_msg(sb, KERN_ERR,
				 "Invalid commit interval %d, "
				 "must be smaller than %d",
				 arg, INT_MAX / HZ);
			return -1;
		}
		sbi->s_commit_interval = HZ * arg;
	} else if (token == Opt_debug_want_extra_isize) {
		if ((arg & 1) ||
		    (arg < 4) ||
		    (arg > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE))) {
			ext4_msg(sb, KERN_ERR,
				 "Invalid want_extra_isize %d", arg);
			return -1;
		}
		sbi->s_want_extra_isize = arg;
	} else if (token == Opt_max_batch_time) {
		sbi->s_max_batch_time = arg;
	} else if (token == Opt_min_batch_time) {
		sbi->s_min_batch_time = arg;
	} else if (token == Opt_inode_readahead_blks) {
		if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) {
			ext4_msg(sb, KERN_ERR,
				 "EXT4-fs: inode_readahead_blks must be "
				 "0 or a power of 2 smaller than 2^31");
			return -1;
		}
		sbi->s_inode_readahead_blks = arg;
	} else if (token == Opt_init_itable) {
		set_opt(sb, INIT_INODE_TABLE);
		if (!args->from)
			arg = EXT4_DEF_LI_WAIT_MULT;
		sbi->s_li_wait_mult = arg;
	} else if (token == Opt_max_dir_size_kb) {
		sbi->s_max_dir_size_kb = arg;
#ifdef CONFIG_EXT4_DEBUG
	} else if (token == Opt_fc_debug_max_replay) {
		sbi->s_fc_debug_max_replay = arg;
#endif
	} else if (token == Opt_stripe) {
		sbi->s_stripe = arg;
	} else if (token == Opt_resuid) {
		uid = make_kuid(current_user_ns(), arg);
		if (!uid_valid(uid)) {
			ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
			return -1;
		}
		sbi->s_resuid = uid;
	} else if (token == Opt_resgid) {
		gid = make_kgid(current_user_ns(), arg);
		if (!gid_valid(gid)) {
			ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
			return -1;
		}
		sbi->s_resgid = gid;
	} else if (token == Opt_journal_dev) {
		if (is_remount) {
			ext4_msg(sb, KERN_ERR,
				 "Cannot specify journal on remount");
			return -1;
		}
		parsed_opts->journal_devnum = arg;
	} else if (token == Opt_journal_path) {
		char *journal_path;
		struct inode *journal_inode;
		struct path path;
		int error;

		if (is_remount) {
			ext4_msg(sb, KERN_ERR,
				 "Cannot specify journal on remount");
			return -1;
		}
		journal_path = match_strdup(&args[0]);
		if (!journal_path) {
			ext4_msg(sb, KERN_ERR, "error: could not dup "
				"journal device string");
			return -1;
		}

		error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
		if (error) {
			ext4_msg(sb, KERN_ERR, "error: could not find "
				"journal device path: error %d", error);
			kfree(journal_path);
			return -1;
		}

		journal_inode = d_inode(path.dentry);
		if (!S_ISBLK(journal_inode->i_mode)) {
			ext4_msg(sb, KERN_ERR, "error: journal path %s "
				"is not a block device", journal_path);
			path_put(&path);
			kfree(journal_path);
			return -1;
		}

		parsed_opts->journal_devnum = new_encode_dev(journal_inode->i_rdev);
		path_put(&path);
		kfree(journal_path);
	} else if (token == Opt_journal_ioprio) {
		if (arg > 7) {
			ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
				 " (must be 0-7)");
			return -1;
		}
		parsed_opts->journal_ioprio =
			IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
	} else if (token == Opt_test_dummy_encryption) {
		return ext4_set_test_dummy_encryption(sb, opt, &args[0],
						      is_remount);
	} else if (m->flags & MOPT_DATAJ) {
		if (is_remount) {
			if (!sbi->s_journal)
				ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
			else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) {
				ext4_msg(sb, KERN_ERR,
					 "Cannot change data mode on remount");
				return -1;
			}
		} else {
			clear_opt(sb, DATA_FLAGS);
			sbi->s_mount_opt |= m->mount_opt;
		}
#ifdef CONFIG_QUOTA
	} else if (m->flags & MOPT_QFMT) {
		if (sb_any_quota_loaded(sb) &&
		    sbi->s_jquota_fmt != m->mount_opt) {
			ext4_msg(sb, KERN_ERR, "Cannot change journaled "
				 "quota options when quota turned on");
			return -1;
		}
		if (ext4_has_feature_quota(sb)) {
			ext4_msg(sb, KERN_INFO,
				 "Quota format mount options ignored "
				 "when QUOTA feature is enabled");
			return 1;
		}
		sbi->s_jquota_fmt = m->mount_opt;
#endif
	} else if (token == Opt_dax || token == Opt_dax_always ||
		   token == Opt_dax_inode || token == Opt_dax_never) {
#ifdef CONFIG_FS_DAX
		switch (token) {
		case Opt_dax:
		case Opt_dax_always:
			if (is_remount &&
			    (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) {
			fail_dax_change_remount:
				ext4_msg(sb, KERN_ERR, "can't change "
					 "dax mount option while remounting");
				return -1;
			}
			if (is_remount &&
			    (test_opt(sb, DATA_FLAGS) ==
			     EXT4_MOUNT_JOURNAL_DATA)) {
				    ext4_msg(sb, KERN_ERR, "can't mount with "
					     "both data=journal and dax");
				    return -1;
			}
			ext4_msg(sb, KERN_WARNING,
				"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
			sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS;
			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
			break;
		case Opt_dax_never:
			if (is_remount &&
			    (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
			     (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS)))
				goto fail_dax_change_remount;
			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
			break;
		case Opt_dax_inode:
			if (is_remount &&
			    ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
			     !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE)))
				goto fail_dax_change_remount;
			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
			/* Strictly for printing options */
			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE;
			break;
		}
#else
		ext4_msg(sb, KERN_INFO, "dax option not supported");
		sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
		sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
		return -1;
#endif
	} else if (token == Opt_data_err_abort) {
		sbi->s_mount_opt |= m->mount_opt;
	} else if (token == Opt_data_err_ignore) {
		sbi->s_mount_opt &= ~m->mount_opt;
	} else if (token == Opt_mb_optimize_scan) {
		if (arg != 0 && arg != 1) {
			ext4_msg(sb, KERN_WARNING,
				 "mb_optimize_scan should be set to 0 or 1.");
			return -1;
		}
		parsed_opts->mb_optimize_scan = arg;
	} else {
		if (!args->from)
			arg = 1;
		if (m->flags & MOPT_CLEAR)
			arg = !arg;
		else if (unlikely(!(m->flags & MOPT_SET))) {
			ext4_msg(sb, KERN_WARNING,
				 "buggy handling of option %s", opt);
			WARN_ON(1);
			return -1;
		}
		if (m->flags & MOPT_2) {
			if (arg != 0)
				sbi->s_mount_opt2 |= m->mount_opt;
			else
				sbi->s_mount_opt2 &= ~m->mount_opt;
		} else {
			if (arg != 0)
				sbi->s_mount_opt |= m->mount_opt;
			else
				sbi->s_mount_opt &= ~m->mount_opt;
		}
	}
	return 1;
}

static int parse_options(char *options, struct super_block *sb,
			 struct ext4_parsed_options *ret_opts,
			 int is_remount)
{
	struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb);
	char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name;
	substring_t args[MAX_OPT_ARGS];
	int token;

	if (!options)
		return 1;

	while ((p = strsep(&options, ",")) != NULL) {
		if (!*p)
			continue;
		/*
		 * Initialize args struct so we know whether arg was
		 * found; some options take optional arguments.
		 */
		args[0].to = args[0].from = NULL;
		token = match_token(p, tokens, args);
		if (handle_mount_opt(sb, p, token, args, ret_opts,
				     is_remount) < 0)
			return 0;
	}
#ifdef CONFIG_QUOTA
	/*
	 * We do the test below only for project quotas. 'usrquota' and
	 * 'grpquota' mount options are allowed even without quota feature
	 * to support legacy quotas in quota files.
	 */
	if (test_opt(sb, PRJQUOTA) && !ext4_has_feature_project(sb)) {
		ext4_msg(sb, KERN_ERR, "Project quota feature not enabled. "
			 "Cannot enable project quota enforcement.");
		return 0;
	}
	usr_qf_name = get_qf_name(sb, sbi, USRQUOTA);
	grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA);
	if (usr_qf_name || grp_qf_name) {
		if (test_opt(sb, USRQUOTA) && usr_qf_name)
			clear_opt(sb, USRQUOTA);

		if (test_opt(sb, GRPQUOTA) && grp_qf_name)
			clear_opt(sb, GRPQUOTA);

		if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
			ext4_msg(sb, KERN_ERR, "old and new quota "
					"format mixing");
			return 0;
		}

		if (!sbi->s_jquota_fmt) {
			ext4_msg(sb, KERN_ERR, "journaled quota format "
					"not specified");
			return 0;
		}
	}
#endif
	if (test_opt(sb, DIOREAD_NOLOCK)) {
		int blocksize =
			BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
		if (blocksize < PAGE_SIZE)
			ext4_msg(sb, KERN_WARNING, "Warning: mounting with an "
				 "experimental mount option 'dioread_nolock' "
				 "for blocksize < PAGE_SIZE");
	}
	return 1;
}

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);
	char *usr_qf_name, *grp_qf_name;

	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);
	}

	rcu_read_lock();
	usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]);
	grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]);
	if (usr_qf_name)
		seq_show_option(seq, "usrjquota", usr_qf_name);
	if (grp_qf_name)
		seq_show_option(seq, "grpjquota", grp_qf_name);
	rcu_read_unlock();
#endif
}

static const char *token2str(int token)
{
	const struct match_token *t;

	for (t = tokens; t->token != Opt_err; t++)
		if (t->token == token && !strchr(t->pattern, '='))
			break;
	return t->pattern;
}

/*
 * 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 super_block *sb,
			      int nodefs)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_super_block *es = sbi->s_es;
	int def_errors, def_mount_opt = sbi->s_def_mount_opt;
	const struct mount_opts *m;
	char sep = nodefs ? '\n' : ',';

#define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep)
#define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg)

	if (sbi->s_sb_block != 1)
		SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block);

	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
		int want_set = m->flags & MOPT_SET;
		if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
		    (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP)
			continue;
		if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
			continue; /* skip if same as the default */
		if ((want_set &&
		     (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
		    (!want_set && (sbi->s_mount_opt & m->mount_opt)))
			continue; /* select Opt_noFoo vs Opt_Foo */
		SEQ_OPTS_PRINT("%s", token2str(m->token));
	}

	if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) ||
	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
		SEQ_OPTS_PRINT("resuid=%u",
				from_kuid_munged(&init_user_ns, sbi->s_resuid));
	if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) ||
	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
		SEQ_OPTS_PRINT("resgid=%u",
				from_kgid_munged(&init_user_ns, sbi->s_resgid));
	def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
	if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
		SEQ_OPTS_PUTS("errors=remount-ro");
	if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
		SEQ_OPTS_PUTS("errors=continue");
	if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
		SEQ_OPTS_PUTS("errors=panic");
	if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ)
		SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ);
	if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME)
		SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
	if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
		SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
	if (sb->s_flags & SB_I_VERSION)
		SEQ_OPTS_PUTS("i_version");
	if (nodefs || sbi->s_stripe)
		SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
	if (nodefs || EXT4_MOUNT_DATA_FLAGS &
			(sbi->s_mount_opt ^ def_mount_opt)) {
		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
			SEQ_OPTS_PUTS("data=journal");
		else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
			SEQ_OPTS_PUTS("data=ordered");
		else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
			SEQ_OPTS_PUTS("data=writeback");
	}
	if (nodefs ||
	    sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
		SEQ_OPTS_PRINT("inode_readahead_blks=%u",
			       sbi->s_inode_readahead_blks);

	if (test_opt(sb, INIT_INODE_TABLE) && (nodefs ||
		       (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
		SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
	if (nodefs || sbi->s_max_dir_size_kb)
		SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
	if (test_opt(sb, DATA_ERR_ABORT))
		SEQ_OPTS_PUTS("data_err=abort");

	fscrypt_show_test_dummy_encryption(seq, sep, sb);

	if (sb->s_flags & SB_INLINECRYPT)
		SEQ_OPTS_PUTS("inlinecrypt");

	if (test_opt(sb, DAX_ALWAYS)) {
		if (IS_EXT2_SB(sb))
			SEQ_OPTS_PUTS("dax");
		else
			SEQ_OPTS_PUTS("dax=always");
	} else if (test_opt2(sb, DAX_NEVER)) {
		SEQ_OPTS_PUTS("dax=never");
	} else if (test_opt2(sb, DAX_INODE)) {
		SEQ_OPTS_PUTS("dax=inode");
	}
	ext4_show_quota_options(seq, sb);
	return 0;
}

static int ext4_show_options(struct seq_file *seq, struct dentry *root)
{
	return _ext4_show_options(seq, root->d_sb, 0);
}

int ext4_seq_options_show(struct seq_file *seq, void *offset)
{
	struct super_block *sb = seq->private;
	int rc;

	seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw");
	rc = _ext4_show_options(seq, sb, 1);
	seq_puts(seq, "\n");
	return rc;
}

static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
			    int read_only)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	int err = 0;

	if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
		ext4_msg(sb, KERN_ERR, "revision level too high, "
			 "forcing read-only mode");
		err = -EROFS;
		goto done;
	}
	if (read_only)
		goto done;
	if (!(sbi->s_mount_state & EXT4_VALID_FS))
		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
			 "running e2fsck is recommended");
	else if (sbi->s_mount_state & EXT4_ERROR_FS)
		ext4_msg(sb, KERN_WARNING,
			 "warning: mounting fs with errors, "
			 "running e2fsck is recommended");
	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))
		ext4_msg(sb, KERN_WARNING,
			 "warning: maximal mount count reached, "
			 "running e2fsck is recommended");
	else if (le32_to_cpu(es->s_checkinterval) &&
		 (ext4_get_tstamp(es, s_lastcheck) +
		  le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds()))
		ext4_msg(sb, KERN_WARNING,
			 "warning: checktime reached, "
			 "running e2fsck is recommended");
	if (!sbi->s_journal)
		es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
	le16_add_cpu(&es->s_mnt_count, 1);
	ext4_update_tstamp(es, s_mtime);
	if (sbi->s_journal) {
		ext4_set_feature_journal_needs_recovery(sb);
		if (ext4_has_feature_orphan_file(sb))
			ext4_set_feature_orphan_present(sb);
	}

	err = ext4_commit_super(sb);
done:
	if (test_opt(sb, DEBUG))
		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
				"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
			sb->s_blocksize,
			sbi->s_groups_count,
			EXT4_BLOCKS_PER_GROUP(sb),
			EXT4_INODES_PER_GROUP(sb),
			sbi->s_mount_opt, sbi->s_mount_opt2);

	cleancache_init_fs(sb);
	return err;
}

int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct flex_groups **old_groups, **new_groups;
	int size, i, j;

	if (!sbi->s_log_groups_per_flex)
		return 0;

	size = ext4_flex_group(sbi, ngroup - 1) + 1;
	if (size <= sbi->s_flex_groups_allocated)
		return 0;

	new_groups = kvzalloc(roundup_pow_of_two(size *
			      sizeof(*sbi->s_flex_groups)), GFP_KERNEL);
	if (!new_groups) {
		ext4_msg(sb, KERN_ERR,
			 "not enough memory for %d flex group pointers", size);
		return -ENOMEM;
	}
	for (i = sbi->s_flex_groups_allocated; i < size; i++) {
		new_groups[i] = kvzalloc(roundup_pow_of_two(
					 sizeof(struct flex_groups)),
					 GFP_KERNEL);
		if (!new_groups[i]) {
			for (j = sbi->s_flex_groups_allocated; j < i; j++)
				kvfree(new_groups[j]);
			kvfree(new_groups);
			ext4_msg(sb, KERN_ERR,
				 "not enough memory for %d flex groups", size);
			return -ENOMEM;
		}
	}
	rcu_read_lock();
	old_groups = rcu_dereference(sbi->s_flex_groups);
	if (old_groups)
		memcpy(new_groups, old_groups,
		       (sbi->s_flex_groups_allocated *
			sizeof(struct flex_groups *)));
	rcu_read_unlock();
	rcu_assign_pointer(sbi->s_flex_groups, new_groups);
	sbi->s_flex_groups_allocated = size;
	if (old_groups)
		ext4_kvfree_array_rcu(old_groups);
	return 0;
}

static int ext4_fill_flex_info(struct super_block *sb)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_group_desc *gdp = NULL;
	struct flex_groups *fg;
	ext4_group_t flex_group;
	int i, err;

	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
		sbi->s_log_groups_per_flex = 0;
		return 1;
	}

	err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
	if (err)
		goto failed;

	for (i = 0; i < sbi->s_groups_count; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);

		flex_group = ext4_flex_group(sbi, i);
		fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
		atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes);
		atomic64_add(ext4_free_group_clusters(sb, gdp),
			     &fg->free_clusters);
		atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs);
	}

	return 1;
failed:
	return 0;
}

static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
				   struct ext4_group_desc *gdp)
{
	int offset = offsetof(struct ext4_group_desc, bg_checksum);
	__u16 crc = 0;
	__le32 le_group = cpu_to_le32(block_group);
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (ext4_has_metadata_csum(sbi->s_sb)) {
		/* Use new metadata_csum algorithm */
		__u32 csum32;
		__u16 dummy_csum = 0;

		csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
				     sizeof(le_group));
		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
		csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
				     sizeof(dummy_csum));
		offset += sizeof(dummy_csum);
		if (offset < sbi->s_desc_size)
			csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
					     sbi->s_desc_size - offset);

		crc = csum32 & 0xFFFF;
		goto out;
	}

	/* old crc16 code */
	if (!ext4_has_feature_gdt_csum(sb))
		return 0;

	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
	crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
	crc = crc16(crc, (__u8 *)gdp, offset);
	offset += sizeof(gdp->bg_checksum); /* skip checksum */
	/* for checksum of struct ext4_group_desc do the rest...*/
	if (ext4_has_feature_64bit(sb) &&
	    offset < le16_to_cpu(sbi->s_es->s_desc_size))
		crc = crc16(crc, (__u8 *)gdp + offset,
			    le16_to_cpu(sbi->s_es->s_desc_size) -
				offset);

out:
	return cpu_to_le16(crc);
}

int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group,
				struct ext4_group_desc *gdp)
{
	if (ext4_has_group_desc_csum(sb) &&
	    (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp)))
		return 0;

	return 1;
}

void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
			      struct ext4_group_desc *gdp)
{
	if (!ext4_has_group_desc_csum(sb))
		return;
	gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp);
}

/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
				  ext4_fsblk_t sb_block,
				  ext4_group_t *first_not_zeroed)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
	ext4_fsblk_t last_block;
	ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0);
	ext4_fsblk_t block_bitmap;
	ext4_fsblk_t inode_bitmap;
	ext4_fsblk_t inode_table;
	int flexbg_flag = 0;
	ext4_group_t i, grp = sbi->s_groups_count;

	if (ext4_has_feature_flex_bg(sb))
		flexbg_flag = 1;

	ext4_debug("Checking group descriptors");

	for (i = 0; i < sbi->s_groups_count; i++) {
		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);

		if (i == sbi->s_groups_count - 1 || flexbg_flag)
			last_block = ext4_blocks_count(sbi->s_es) - 1;
		else
			last_block = first_block +
				(EXT4_BLOCKS_PER_GROUP(sb) - 1);

		if ((grp == sbi->s_groups_count) &&
		   !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
			grp = i;

		block_bitmap = ext4_block_bitmap(sb, gdp);
		if (block_bitmap == sb_block) {
			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
				 "Block bitmap for group %u overlaps "
				 "superblock", i);
			if (!sb_rdonly(sb))
				return 0;
		}
		if (block_bitmap >= sb_block + 1 &&
		    block_bitmap <= last_bg_block) {
			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
				 "Block bitmap for group %u overlaps "
				 "block group descriptors", i);
			if (!sb_rdonly(sb))
				return 0;
		}