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 "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 struct 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 int ext4_commit_super(struct super_block *sb, int sync);
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 int ext4_feature_set_ok(struct super_block *sb, int readonly);
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
 *
 * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
 * i_mmap_rwsem (inode->i_mmap_rwsem)!
 *
 * page fault path:
 * mmap_lock -> sb_start_pagefault -> i_mmap_sem (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 -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
 * sb_start_write -> i_mutex -> i_mmap_sem (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 = ktime_get_real_seconds();

	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)
#define ext4_get_tstamp(es, tstamp) \
	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)

static void __save_error_info(struct super_block *sb, int error,
			      __u32 ino, __u64 block,
			      const char *func, unsigned int line)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	int err;

	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
	if (bdev_read_only(sb->s_bdev))
		return;
	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
	ext4_update_tstamp(es, s_last_error_time);
	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
	es->s_last_error_line = cpu_to_le32(line);
	es->s_last_error_ino = cpu_to_le32(ino);
	es->s_last_error_block = cpu_to_le64(block);
	switch (error) {
	case EIO:
		err = EXT4_ERR_EIO;
		break;
	case ENOMEM:
		err = EXT4_ERR_ENOMEM;
		break;
	case EFSBADCRC:
		err = EXT4_ERR_EFSBADCRC;
		break;
	case 0:
	case EFSCORRUPTED:
		err = EXT4_ERR_EFSCORRUPTED;
		break;
	case ENOSPC:
		err = EXT4_ERR_ENOSPC;
		break;
	case ENOKEY:
		err = EXT4_ERR_ENOKEY;
		break;
	case EROFS:
		err = EXT4_ERR_EROFS;
		break;
	case EFBIG:
		err = EXT4_ERR_EFBIG;
		break;
	case EEXIST:
		err = EXT4_ERR_EEXIST;
		break;
	case ERANGE:
		err = EXT4_ERR_ERANGE;
		break;
	case EOVERFLOW:
		err = EXT4_ERR_EOVERFLOW;
		break;
	case EBUSY:
		err = EXT4_ERR_EBUSY;
		break;
	case ENOTDIR:
		err = EXT4_ERR_ENOTDIR;
		break;
	case ENOTEMPTY:
		err = EXT4_ERR_ENOTEMPTY;
		break;
	case ESHUTDOWN:
		err = EXT4_ERR_ESHUTDOWN;
		break;
	case EFAULT:
		err = EXT4_ERR_EFAULT;
		break;
	default:
		err = EXT4_ERR_UNKNOWN;
	}
	es->s_last_error_errcode = err;
	if (!es->s_first_error_time) {
		es->s_first_error_time = es->s_last_error_time;
		es->s_first_error_time_hi = es->s_last_error_time_hi;
		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;
		es->s_first_error_errcode = es->s_last_error_errcode;
	}
	/*
	 * 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);
	le32_add_cpu(&es->s_error_count, 1);
}

static void save_error_info(struct super_block *sb, int error,
			    __u32 ino, __u64 block,
			    const char *func, unsigned int line)
{
	__save_error_info(sb, error, ino, block, func, line);
	if (!bdev_read_only(sb->s_bdev))
		ext4_commit_super(sb, 1);
}

/*
 * 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;
}

/* 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)
{
	journal_t *journal = EXT4_SB(sb)->s_journal;

	if (test_opt(sb, WARN_ON_ERROR))
		WARN_ON_ONCE(1);

	if (sb_rdonly(sb) || test_opt(sb, ERRORS_CONT))
		return;

	ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
	if (journal)
		jbd2_journal_abort(journal, -EIO);
	/*
	 * 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_RO) || system_going_down()) {
		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;
	} else if (test_opt(sb, ERRORS_PANIC)) {
		panic("EXT4-fs (device %s): panic forced after error\n",
			sb->s_id);
	}
}

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

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

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);
	}

	save_error_info(sb, -errno, 0, 0, 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, int error, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

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

	save_error_info(sb, error, 0, 0, function, line);
	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
	       sb->s_id, function, line, &vaf);
	va_end(args);

	if (sb_rdonly(sb) == 0) {
		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
		if (EXT4_SB(sb)->s_journal)
			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);

		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;
	}
	if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
		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;

	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);
	__save_error_info(sb, EFSCORRUPTED, ino, block, 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, WARN_ON_ERROR))
		WARN_ON_ONCE(1);

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

	ext4_unlock_group(sb, grp);
	ext4_commit_super(sb, 1);
	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 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);

	destroy_workqueue(sbi->rsv_conversion_wq);

	/*
	 * 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);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
	}
	if (!sb_rdonly(sb))