kvj
/
linux-zen-desktop
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
linux-zen-desktop/fs/ext4/super.c

7391 lines
204 KiB
C
Raw Blame History

// 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/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 <linux/fs_context.h>
#include <linux/fs_parser.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_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
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);
static int ext4_validate_options(struct fs_context *fc);
static int ext4_check_opt_consistency(struct fs_context *fc,
struct super_block *sb);
static void ext4_apply_options(struct fs_context *fc, struct super_block *sb);
static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param);
static int ext4_get_tree(struct fs_context *fc);
static int ext4_reconfigure(struct fs_context *fc);
static void ext4_fc_free(struct fs_context *fc);
static int ext4_init_fs_context(struct fs_context *fc);
static const struct fs_parameter_spec ext4_param_specs[];
/*
* 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)
*/
static const struct fs_context_operations ext4_context_ops = {
.parse_param = ext4_parse_param,
.get_tree = ext4_get_tree,
.reconfigure = ext4_reconfigure,
.free = ext4_fc_free,
};
#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",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
.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",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
.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, blk_opf_t 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, blk_opf_t 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, blk_opf_t 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, blk_opf_t op_flags, bool wait)
{
lock_buffer(bh);
if (!wait) {
ext4_read_bh_nowait(bh, op_flags, NULL);
return 0;
}
return ext4_read_bh(bh, op_flags, NULL);
}
/*
* 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,
blk_opf_t 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,
blk_opf_t 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)) {
if (trylock_buffer(bh))
ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
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;
}
__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 folio *folio,
struct writeback_control *wbc,
void *data)
{
transaction_t *transaction = (transaction_t *) data;
struct buffer_head *bh, *head;
struct journal_head *jh;
bh = head = folio_buffers(folio);
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))) {
folio_redirty_for_writepage(wbc, folio);
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 = ext4_normal_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;
if (sb) {
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;
if (sb)
printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
else
printk("%sEXT4-fs: %pV\n", prefix, &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 (!grp || !gdp)
return;
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.
*/
}
static void ext4_bdev_mark_dead(struct block_device *bdev)
{
ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH);
}
static const struct blk_holder_ops ext4_holder_ops = {
.mark_dead = ext4_bdev_mark_dead,
};
/*
* 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, BLK_OPEN_READ | BLK_OPEN_WRITE, sb,
&ext4_holder_ops);
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_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
bdev = sbi->s_journal_bdev;
if (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.
*/
invalidate_bdev(bdev);
blkdev_put(bdev, sbi->s_sb);
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_quotas_off(struct super_block *sb, int type)
{
BUG_ON(type > EXT4_MAXQUOTAS);
/* Use our quota_off function to clear inode flags etc. */
for (type--; type >= 0; 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_quotas_off(struct super_block *sb, int type)
{
}
#endif
static int ext4_percpu_param_init(struct ext4_sb_info *sbi)
{
ext4_fsblk_t block;
int err;
block = ext4_count_free_clusters(sbi->s_sb);
ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block));
err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
GFP_KERNEL);
if (!err) {
unsigned long freei = ext4_count_free_inodes(sbi->s_sb);
sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
GFP_KERNEL);
}
if (!err)
err = percpu_counter_init(&sbi->s_dirs_counter,
ext4_count_dirs(sbi->s_sb), GFP_KERNEL);
if (!err)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
GFP_KERNEL);
if (!err)
err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
if (err)
ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory");
return err;
}
static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi)
{
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);
}
static void ext4_group_desc_free(struct ext4_sb_info *sbi)
{
struct buffer_head **group_desc;
int i;
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);
rcu_read_unlock();
}
static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
{
struct flex_groups **flex_groups;
int i;
rcu_read_lock();
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();
}
static void ext4_put_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int aborted = 0;
int err;
/*
* 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
* Unregister sysfs before flush sbi->s_error_work.
* Since user may read /proc/fs/ext4/xx/mb_groups during umount, If
* read metadata verify failed then will queue error work.
* flush_stashed_error_work will call start_this_handle may trigger
* BUG_ON.
*/
ext4_unregister_sysfs(sb);
if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount"))
ext4_msg(sb, KERN_INFO, "unmounting filesystem %pU.",
&sb->s_uuid);
ext4_unregister_li_request(sb);
ext4_quotas_off(sb, EXT4_MAXQUOTAS);
flush_work(&sbi->s_error_work);
destroy_workqueue(sbi->rsv_conversion_wq);
ext4_release_orphan_info(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);
timer_shutdown_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);
ext4_group_desc_free(sbi);
ext4_flex_groups_free(sbi);
ext4_percpu_param_destroy(sbi);
#ifdef CONFIG_QUOTA
for (int 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) {
sync_blockdev(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, NULL);
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
#if IS_ENABLED(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 = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
inode_set_iversion(&ei->vfs_inode, 1);
ei->i_flags = 0;
spin_lock_init(&ei->i_raw_lock);
ei->i_prealloc_node = RB_ROOT;
atomic_set(&ei->i_prealloc_active, 0);
rwlock_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 ext4_shutdown(struct super_block *sb)
{
ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH);
}
static void init_once(void *foo)
{
struct ext4_inode_info *ei = 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_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,
.show_options = ext4_show_options,
.shutdown = ext4_shutdown,
#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_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_acl,
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_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_prjquota,
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_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,
Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type,
#ifdef CONFIG_EXT4_DEBUG
Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
};
static const struct constant_table ext4_param_errors[] = {
{"continue", EXT4_MOUNT_ERRORS_CONT},
{"panic", EXT4_MOUNT_ERRORS_PANIC},
{"remount-ro", EXT4_MOUNT_ERRORS_RO},
{}
};
static const struct constant_table ext4_param_data[] = {
{"journal", EXT4_MOUNT_JOURNAL_DATA},
{"ordered", EXT4_MOUNT_ORDERED_DATA},
{"writeback", EXT4_MOUNT_WRITEBACK_DATA},
{}
};
static const struct constant_table ext4_param_data_err[] = {
{"abort", Opt_data_err_abort},
{"ignore", Opt_data_err_ignore},
{}
};
static const struct constant_table ext4_param_jqfmt[] = {
{"vfsold", QFMT_VFS_OLD},
{"vfsv0", QFMT_VFS_V0},
{"vfsv1", QFMT_VFS_V1},
{}
};
static const struct constant_table ext4_param_dax[] = {
{"always", Opt_dax_always},
{"inode", Opt_dax_inode},
{"never", Opt_dax_never},
{}
};
/* String parameter that allows empty argument */
#define fsparam_string_empty(NAME, OPT) \
__fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL)
/*
* Mount option specification
* We don't use fsparam_flag_no because of the way we set the
* options and the way we show them in _ext4_show_options(). To
* keep the changes to a minimum, let's keep the negative options
* separate for now.
*/
static const struct fs_parameter_spec ext4_param_specs[] = {
fsparam_flag ("bsddf", Opt_bsd_df),
fsparam_flag ("minixdf", Opt_minix_df),
fsparam_flag ("grpid", Opt_grpid),
fsparam_flag ("bsdgroups", Opt_grpid),
fsparam_flag ("nogrpid", Opt_nogrpid),
fsparam_flag ("sysvgroups", Opt_nogrpid),
fsparam_u32 ("resgid", Opt_resgid),
fsparam_u32 ("resuid", Opt_resuid),
fsparam_u32 ("sb", Opt_sb),
fsparam_enum ("errors", Opt_errors, ext4_param_errors),
fsparam_flag ("nouid32", Opt_nouid32),
fsparam_flag ("debug", Opt_debug),
fsparam_flag ("oldalloc", Opt_removed),
fsparam_flag ("orlov", Opt_removed),
fsparam_flag ("user_xattr", Opt_user_xattr),
fsparam_flag ("acl", Opt_acl),
fsparam_flag ("norecovery", Opt_noload),
fsparam_flag ("noload", Opt_noload),
fsparam_flag ("bh", Opt_removed),
fsparam_flag ("nobh", Opt_removed),
fsparam_u32 ("commit", Opt_commit),
fsparam_u32 ("min_batch_time", Opt_min_batch_time),
fsparam_u32 ("max_batch_time", Opt_max_batch_time),
fsparam_u32 ("journal_dev", Opt_journal_dev),
fsparam_bdev ("journal_path", Opt_journal_path),
fsparam_flag ("journal_checksum", Opt_journal_checksum),
fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum),
fsparam_flag ("journal_async_commit",Opt_journal_async_commit),
fsparam_flag ("abort", Opt_abort),
fsparam_enum ("data", Opt_data, ext4_param_data),
fsparam_enum ("data_err", Opt_data_err,
ext4_param_data_err),
fsparam_string_empty
("usrjquota", Opt_usrjquota),
fsparam_string_empty
("grpjquota", Opt_grpjquota),
fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt),
fsparam_flag ("grpquota", Opt_grpquota),
fsparam_flag ("quota", Opt_quota),
fsparam_flag ("noquota", Opt_noquota),
fsparam_flag ("usrquota", Opt_usrquota),
fsparam_flag ("prjquota", Opt_prjquota),
fsparam_flag ("barrier", Opt_barrier),
fsparam_u32 ("barrier", Opt_barrier),
fsparam_flag ("nobarrier", Opt_nobarrier),
fsparam_flag ("i_version", Opt_removed),
fsparam_flag ("dax", Opt_dax),
fsparam_enum ("dax", Opt_dax_type, ext4_param_dax),
fsparam_u32 ("stripe", Opt_stripe),
fsparam_flag ("delalloc", Opt_delalloc),
fsparam_flag ("nodelalloc", Opt_nodelalloc),
fsparam_flag ("warn_on_error", Opt_warn_on_error),
fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error),
fsparam_u32 ("debug_want_extra_isize",
Opt_debug_want_extra_isize),
fsparam_flag ("mblk_io_submit", Opt_removed),
fsparam_flag ("nomblk_io_submit", Opt_removed),
fsparam_flag ("block_validity", Opt_block_validity),
fsparam_flag ("noblock_validity", Opt_noblock_validity),
fsparam_u32 ("inode_readahead_blks",
Opt_inode_readahead_blks),
fsparam_u32 ("journal_ioprio", Opt_journal_ioprio),
fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc),
fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc),
fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc),
fsparam_flag ("dioread_nolock", Opt_dioread_nolock),
fsparam_flag ("nodioread_nolock", Opt_dioread_lock),
fsparam_flag ("dioread_lock", Opt_dioread_lock),
fsparam_flag ("discard", Opt_discard),
fsparam_flag ("nodiscard", Opt_nodiscard),
fsparam_u32 ("init_itable", Opt_init_itable),
fsparam_flag ("init_itable", Opt_init_itable),
fsparam_flag ("noinit_itable", Opt_noinit_itable),
#ifdef CONFIG_EXT4_DEBUG
fsparam_flag ("fc_debug_force", Opt_fc_debug_force),
fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay),
#endif
fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb),
fsparam_flag ("test_dummy_encryption",
Opt_test_dummy_encryption),
fsparam_string ("test_dummy_encryption",
Opt_test_dummy_encryption),
fsparam_flag ("inlinecrypt", Opt_inlinecrypt),
fsparam_flag ("nombcache", Opt_nombcache),
fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */
fsparam_flag ("prefetch_block_bitmaps",
Opt_removed),
fsparam_flag ("no_prefetch_block_bitmaps",
Opt_no_prefetch_block_bitmaps),
fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan),
fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */
fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */
fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */
fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */
fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */
{}
};
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
#define MOPT_SET 0x0001
#define MOPT_CLEAR 0x0002
#define MOPT_NOSUPPORT 0x0004
#define MOPT_EXPLICIT 0x0008
#ifdef CONFIG_QUOTA
#define MOPT_Q 0
#define MOPT_QFMT 0x0010
#else
#define MOPT_Q MOPT_NOSUPPORT
#define MOPT_QFMT MOPT_NOSUPPORT
#endif
#define MOPT_NO_EXT2 0x0020
#define MOPT_NO_EXT3 0x0040
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
#define MOPT_SKIP 0x0080
#define MOPT_2 0x0100
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_commit, 0, MOPT_NO_EXT2},
{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_data_err, 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_dax_type, 0, MOPT_EXT4_ONLY},
{Opt_journal_dev, 0, MOPT_NO_EXT2},
{Opt_journal_path, 0, MOPT_NO_EXT2},
{Opt_journal_ioprio, 0, MOPT_NO_EXT2},
{Opt_data, 0, MOPT_NO_EXT2},
{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
#ifdef CONFIG_EXT4_FS_POSIX_ACL
{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
#else
{Opt_acl, 0, MOPT_NOSUPPORT},
#endif
{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
{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},
{Opt_grpjquota, 0, MOPT_Q},
{Opt_jqfmt, 0, MOPT_QFMT},
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
#endif
{Opt_err, 0, 0}
};
#if IS_ENABLED(CONFIG_UNICODE)
static const struct ext4_sb_encodings {
__u16 magic;
char *name;
unsigned int version;
} ext4_sb_encoding_map[] = {
{EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
};
static const struct ext4_sb_encodings *
ext4_sb_read_encoding(const struct ext4_super_block *es)
{
__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)
return &ext4_sb_encoding_map[i];
return NULL;
}
#endif
#define EXT4_SPEC_JQUOTA (1 << 0)
#define EXT4_SPEC_JQFMT (1 << 1)
#define EXT4_SPEC_DATAJ (1 << 2)
#define EXT4_SPEC_SB_BLOCK (1 << 3)
#define EXT4_SPEC_JOURNAL_DEV (1 << 4)
#define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5)
#define EXT4_SPEC_s_want_extra_isize (1 << 7)
#define EXT4_SPEC_s_max_batch_time (1 << 8)
#define EXT4_SPEC_s_min_batch_time (1 << 9)
#define EXT4_SPEC_s_inode_readahead_blks (1 << 10)
#define EXT4_SPEC_s_li_wait_mult (1 << 11)
#define EXT4_SPEC_s_max_dir_size_kb (1 << 12)
#define EXT4_SPEC_s_stripe (1 << 13)
#define EXT4_SPEC_s_resuid (1 << 14)
#define EXT4_SPEC_s_resgid (1 << 15)
#define EXT4_SPEC_s_commit_interval (1 << 16)
#define EXT4_SPEC_s_fc_debug_max_replay (1 << 17)
#define EXT4_SPEC_s_sb_block (1 << 18)
#define EXT4_SPEC_mb_optimize_scan (1 << 19)
struct ext4_fs_context {
char *s_qf_names[EXT4_MAXQUOTAS];
struct fscrypt_dummy_policy dummy_enc_policy;
int s_jquota_fmt; /* Format of quota to use */
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
unsigned short qname_spec;
unsigned long vals_s_flags; /* Bits to set in s_flags */
unsigned long mask_s_flags; /* Bits changed in s_flags */
unsigned long journal_devnum;
unsigned long s_commit_interval;
unsigned long s_stripe;
unsigned int s_inode_readahead_blks;
unsigned int s_want_extra_isize;
unsigned int s_li_wait_mult;
unsigned int s_max_dir_size_kb;
unsigned int journal_ioprio;
unsigned int vals_s_mount_opt;
unsigned int mask_s_mount_opt;
unsigned int vals_s_mount_opt2;
unsigned int mask_s_mount_opt2;
unsigned long vals_s_mount_flags;
unsigned long mask_s_mount_flags;
unsigned int opt_flags; /* MOPT flags */
unsigned int spec;
u32 s_max_batch_time;
u32 s_min_batch_time;
kuid_t s_resuid;
kgid_t s_resgid;
ext4_fsblk_t s_sb_block;
};
static void ext4_fc_free(struct fs_context *fc)
{
struct ext4_fs_context *ctx = fc->fs_private;
int i;
if (!ctx)
return;
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(ctx->s_qf_names[i]);
fscrypt_free_dummy_policy(&ctx->dummy_enc_policy);
kfree(ctx);
}
int ext4_init_fs_context(struct fs_context *fc)
{
struct ext4_fs_context *ctx;
ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
fc->fs_private = ctx;
fc->ops = &ext4_context_ops;
return 0;
}
#ifdef CONFIG_QUOTA
/*
* Note the name of the specified quota file.
*/
static int note_qf_name(struct fs_context *fc, int qtype,
struct fs_parameter *param)
{
struct ext4_fs_context *ctx = fc->fs_private;
char *qname;
if (param->size < 1) {
ext4_msg(NULL, KERN_ERR, "Missing quota name");
return -EINVAL;
}
if (strchr(param->string, '/')) {
ext4_msg(NULL, KERN_ERR,
"quotafile must be on filesystem root");
return -EINVAL;
}
if (ctx->s_qf_names[qtype]) {
if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) {
ext4_msg(NULL, KERN_ERR,
"%s quota file already specified",
QTYPE2NAME(qtype));
return -EINVAL;
}
return 0;
}
qname = kmemdup_nul(param->string, param->size, GFP_KERNEL);
if (!qname) {
ext4_msg(NULL, KERN_ERR,
"Not enough memory for storing quotafile name");
return -ENOMEM;
}
ctx->s_qf_names[qtype] = qname;
ctx->qname_spec |= 1 << qtype;
ctx->spec |= EXT4_SPEC_JQUOTA;
return 0;
}
/*
* Clear the name of the specified quota file.
*/
static int unnote_qf_name(struct fs_context *fc, int qtype)
{
struct ext4_fs_context *ctx = fc->fs_private;
if (ctx->s_qf_names[qtype])
kfree(ctx->s_qf_names[qtype]);
ctx->s_qf_names[qtype] = NULL;
ctx->qname_spec |= 1 << qtype;
ctx->spec |= EXT4_SPEC_JQUOTA;
return 0;
}
#endif
static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param,
struct ext4_fs_context *ctx)
{
int err;
if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) {
ext4_msg(NULL, KERN_WARNING,
"test_dummy_encryption option not supported");
return -EINVAL;
}
err = fscrypt_parse_test_dummy_encryption(param,
&ctx->dummy_enc_policy);
if (err == -EINVAL) {
ext4_msg(NULL, KERN_WARNING,
"Value of option \"%s\" is unrecognized", param->key);
} else if (err == -EEXIST) {
ext4_msg(NULL, KERN_WARNING,
"Conflicting test_dummy_encryption options");
return -EINVAL;
}
return err;
}
#define EXT4_SET_CTX(name) \
static inline void ctx_set_##name(struct ext4_fs_context *ctx, \
unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name |= flag; \
}
#define EXT4_CLEAR_CTX(name) \
static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \
unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name &= ~flag; \
}
#define EXT4_TEST_CTX(name) \
static inline unsigned long \
ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \
{ \
return (ctx->vals_s_##name & flag); \
}
EXT4_SET_CTX(flags); /* set only */
EXT4_SET_CTX(mount_opt);
EXT4_CLEAR_CTX(mount_opt);
EXT4_TEST_CTX(mount_opt);
EXT4_SET_CTX(mount_opt2);
EXT4_CLEAR_CTX(mount_opt2);
EXT4_TEST_CTX(mount_opt2);
static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit)
{
set_bit(bit, &ctx->mask_s_mount_flags);
set_bit(bit, &ctx->vals_s_mount_flags);
}
static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct ext4_fs_context *ctx = fc->fs_private;
struct fs_parse_result result;
const struct mount_opts *m;
int is_remount;
kuid_t uid;
kgid_t gid;
int token;
token = fs_parse(fc, ext4_param_specs, param, &result);
if (token < 0)
return token;
is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE;
for (m = ext4_mount_opts; m->token != Opt_err; m++)
if (token == m->token)
break;
ctx->opt_flags |= m->flags;
if (m->flags & MOPT_EXPLICIT) {
if (m->mount_opt & EXT4_MOUNT_DELALLOC) {
ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC);
} else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) {
ctx_set_mount_opt2(ctx,
EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM);
} else
return -EINVAL;
}
if (m->flags & MOPT_NOSUPPORT) {
ext4_msg(NULL, KERN_ERR, "%s option not supported",
param->key);
return 0;
}
switch (token) {
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
if (!*param->string)
return unnote_qf_name(fc, USRQUOTA);
else
return note_qf_name(fc, USRQUOTA, param);
case Opt_grpjquota:
if (!*param->string)
return unnote_qf_name(fc, GRPQUOTA);
else
return note_qf_name(fc, GRPQUOTA, param);
#endif
case Opt_sb:
if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
ext4_msg(NULL, KERN_WARNING,
"Ignoring %s option on remount", param->key);
} else {
ctx->s_sb_block = result.uint_32;
ctx->spec |= EXT4_SPEC_s_sb_block;
}
return 0;
case Opt_removed:
ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option",
param->key);
return 0;
case Opt_abort:
ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
return 0;
case Opt_inlinecrypt:
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
ctx_set_flags(ctx, SB_INLINECRYPT);
#else
ext4_msg(NULL, KERN_ERR, "inline encryption not supported");
#endif
return 0;
case Opt_errors:
ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK);
ctx_set_mount_opt(ctx, result.uint_32);
return 0;
#ifdef CONFIG_QUOTA
case Opt_jqfmt:
ctx->s_jquota_fmt = result.uint_32;
ctx->spec |= EXT4_SPEC_JQFMT;
return 0;
#endif
case Opt_data:
ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS);
ctx_set_mount_opt(ctx, result.uint_32);
ctx->spec |= EXT4_SPEC_DATAJ;
return 0;
case Opt_commit:
if (result.uint_32 == 0)
result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE;
else if (result.uint_32 > INT_MAX / HZ) {
ext4_msg(NULL, KERN_ERR,
"Invalid commit interval %d, "
"must be smaller than %d",
result.uint_32, INT_MAX / HZ);
return -EINVAL;
}
ctx->s_commit_interval = HZ * result.uint_32;
ctx->spec |= EXT4_SPEC_s_commit_interval;
return 0;
case Opt_debug_want_extra_isize:
if ((result.uint_32 & 1) || (result.uint_32 < 4)) {
ext4_msg(NULL, KERN_ERR,
"Invalid want_extra_isize %d", result.uint_32);
return -EINVAL;
}
ctx->s_want_extra_isize = result.uint_32;
ctx->spec |= EXT4_SPEC_s_want_extra_isize;
return 0;
case Opt_max_batch_time:
ctx->s_max_batch_time = result.uint_32;
ctx->spec |= EXT4_SPEC_s_max_batch_time;
return 0;
case Opt_min_batch_time:
ctx->s_min_batch_time = result.uint_32;
ctx->spec |= EXT4_SPEC_s_min_batch_time;
return 0;
case Opt_inode_readahead_blks:
if (result.uint_32 &&
(result.uint_32 > (1 << 30) ||
!is_power_of_2(result.uint_32))) {
ext4_msg(NULL, KERN_ERR,
"EXT4-fs: inode_readahead_blks must be "
"0 or a power of 2 smaller than 2^31");
return -EINVAL;
}
ctx->s_inode_readahead_blks = result.uint_32;
ctx->spec |= EXT4_SPEC_s_inode_readahead_blks;
return 0;
case Opt_init_itable:
ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE);
ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
if (param->type == fs_value_is_string)
ctx->s_li_wait_mult = result.uint_32;
ctx->spec |= EXT4_SPEC_s_li_wait_mult;
return 0;
case Opt_max_dir_size_kb:
ctx->s_max_dir_size_kb = result.uint_32;
ctx->spec |= EXT4_SPEC_s_max_dir_size_kb;
return 0;
#ifdef CONFIG_EXT4_DEBUG
case Opt_fc_debug_max_replay:
ctx->s_fc_debug_max_replay = result.uint_32;
ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay;
return 0;
#endif
case Opt_stripe:
ctx->s_stripe = result.uint_32;
ctx->spec |= EXT4_SPEC_s_stripe;
return 0;
case Opt_resuid:
uid = make_kuid(current_user_ns(), result.uint_32);
if (!uid_valid(uid)) {
ext4_msg(NULL, KERN_ERR, "Invalid uid value %d",
result.uint_32);
return -EINVAL;
}
ctx->s_resuid = uid;
ctx->spec |= EXT4_SPEC_s_resuid;
return 0;
case Opt_resgid:
gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(gid)) {
ext4_msg(NULL, KERN_ERR, "Invalid gid value %d",
result.uint_32);
return -EINVAL;
}
ctx->s_resgid = gid;
ctx->spec |= EXT4_SPEC_s_resgid;
return 0;
case Opt_journal_dev:
if (is_remount) {
ext4_msg(NULL, KERN_ERR,
"Cannot specify journal on remount");
return -EINVAL;
}
ctx->journal_devnum = result.uint_32;
ctx->spec |= EXT4_SPEC_JOURNAL_DEV;
return 0;
case Opt_journal_path:
{
struct inode *journal_inode;
struct path path;
int error;
if (is_remount) {
ext4_msg(NULL, KERN_ERR,
"Cannot specify journal on remount");
return -EINVAL;
}
error = fs_lookup_param(fc, param, 1, LOOKUP_FOLLOW, &path);
if (error) {
ext4_msg(NULL, KERN_ERR, "error: could not find "
"journal device path");
return -EINVAL;
}
journal_inode = d_inode(path.dentry);
ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev);
ctx->spec |= EXT4_SPEC_JOURNAL_DEV;
path_put(&path);
return 0;
}
case Opt_journal_ioprio:
if (result.uint_32 > 7) {
ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority"
" (must be 0-7)");
return -EINVAL;
}
ctx->journal_ioprio =
IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32);
ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO;
return 0;
case Opt_test_dummy_encryption:
return ext4_parse_test_dummy_encryption(param, ctx);
case Opt_dax:
case Opt_dax_type:
#ifdef CONFIG_FS_DAX
{
int type = (token == Opt_dax) ?
Opt_dax : result.uint_32;
switch (type) {
case Opt_dax:
case Opt_dax_always:
ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS);
ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER);
break;
case Opt_dax_never:
ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER);
ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS);
break;
case Opt_dax_inode:
ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS);
ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER);
/* Strictly for printing options */
ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE);
break;
}
return 0;
}
#else
ext4_msg(NULL, KERN_INFO, "dax option not supported");
return -EINVAL;
#endif
case Opt_data_err:
if (result.uint_32 == Opt_data_err_abort)
ctx_set_mount_opt(ctx, m->mount_opt);
else if (result.uint_32 == Opt_data_err_ignore)
ctx_clear_mount_opt(ctx, m->mount_opt);
return 0;
case Opt_mb_optimize_scan:
if (result.int_32 == 1) {
ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
ctx->spec |= EXT4_SPEC_mb_optimize_scan;
} else if (result.int_32 == 0) {
ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
ctx->spec |= EXT4_SPEC_mb_optimize_scan;
} else {
ext4_msg(NULL, KERN_WARNING,
"mb_optimize_scan should be set to 0 or 1.");
return -EINVAL;
}
return 0;
}
/*
* At this point we should only be getting options requiring MOPT_SET,
* or MOPT_CLEAR. Anything else is a bug
*/
if (m->token == Opt_err) {
ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s",
param->key);
WARN_ON(1);
return -EINVAL;
}
else {
unsigned int set = 0;
if ((param->type == fs_value_is_flag) ||
result.uint_32 > 0)
set = 1;
if (m->flags & MOPT_CLEAR)
set = !set;
else if (unlikely(!(m->flags & MOPT_SET))) {
ext4_msg(NULL, KERN_WARNING,
"buggy handling of option %s",
param->key);
WARN_ON(1);
return -EINVAL;
}
if (m->flags & MOPT_2) {
if (set != 0)
ctx_set_mount_opt2(ctx, m->mount_opt);
else
ctx_clear_mount_opt2(ctx, m->mount_opt);
} else {
if (set != 0)
ctx_set_mount_opt(ctx, m->mount_opt);
else
ctx_clear_mount_opt(ctx, m->mount_opt);
}
}
return 0;
}
static int parse_options(struct fs_context *fc, char *options)
{
struct fs_parameter param;
int ret;
char *key;
if (!options)
return 0;
while ((key = strsep(&options, ",")) != NULL) {
if (*key) {
size_t v_len = 0;
char *value = strchr(key, '=');
param.type = fs_value_is_flag;
param.string = NULL;
if (value) {
if (value == key)
continue;
*value++ = 0;
v_len = strlen(value);
param.string = kmemdup_nul(value, v_len,
GFP_KERNEL);
if (!param.string)
return -ENOMEM;
param.type = fs_value_is_string;
}
param.key = key;
param.size = v_len;
ret = ext4_parse_param(fc, &param);
if (param.string)
kfree(param.string);
if (ret < 0)
return ret;
}
}
ret = ext4_validate_options(fc);
if (ret < 0)
return ret;
return 0;
}
static int parse_apply_sb_mount_options(struct super_block *sb,
struct ext4_fs_context *m_ctx)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *s_mount_opts = NULL;
struct ext4_fs_context *s_ctx = NULL;
struct fs_context *fc = NULL;
int ret = -ENOMEM;
if (!sbi->s_es->s_mount_opts[0])
return 0;
s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
sizeof(sbi->s_es->s_mount_opts),
GFP_KERNEL);
if (!s_mount_opts)
return ret;
fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL);
if (!fc)
goto out_free;
s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL);
if (!s_ctx)
goto out_free;
fc->fs_private = s_ctx;
fc->s_fs_info = sbi;
ret = parse_options(fc, s_mount_opts);
if (ret < 0)
goto parse_failed;
ret = ext4_check_opt_consistency(fc, sb);
if (ret < 0) {
parse_failed:
ext4_msg(sb, KERN_WARNING,
"failed to parse options in superblock: %s",
s_mount_opts);
ret = 0;
goto out_free;
}
if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV)
m_ctx->journal_devnum = s_ctx->journal_devnum;
if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)
m_ctx->journal_ioprio = s_ctx->journal_ioprio;
ext4_apply_options(fc, sb);
ret = 0;
out_free:
if (fc) {
ext4_fc_free(fc);
kfree(fc);