blob: 3822a5aedc61b241d937c474192bfa57e5b3b2c5 [file] [log] [blame]
/*
* 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/cleancache.h>
#include <asm/uaccess.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"
#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 void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
static 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);
/*
* 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_sem -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
* page lock -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_mutex -> mmap_sem
* sb_start_write -> i_mutex -> transaction start -> page lock ->
* i_data_sem (rw)
*
* truncate:
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
* i_mmap_rwsem (w) -> page lock
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
* transaction start -> i_data_sem (rw)
*
* direct IO:
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) -> mmap_sem
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) ->
* 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 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);
}
void *ext4_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kmalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags, PAGE_KERNEL);
return ret;
}
void *ext4_kvzalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kzalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
return ret;
}
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 __save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (bdev_read_only(sb->s_bdev))
return;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
es->s_last_error_time = cpu_to_le32(get_seconds());
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
es->s_last_error_line = cpu_to_le32(line);
if (!es->s_first_error_time) {
es->s_first_error_time = es->s_last_error_time;
strncpy(es->s_first_error_func, func,
sizeof(es->s_first_error_func));
es->s_first_error_line = cpu_to_le32(line);
es->s_first_error_ino = es->s_last_error_ino;
es->s_first_error_block = es->s_last_error_block;
}
/*
* Start the daily error reporting function if it hasn't been
* started already
*/
if (!es->s_error_count)
mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
le32_add_cpu(&es->s_error_count, 1);
}
static void save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
__save_error_info(sb, func, line);
ext4_commit_super(sb, 1);
}
/*
* 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);
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);
}
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
* On ext2, we can store the error state of the filesystem in the
* superblock. That is not possible on ext4, because we may have other
* write ordering constraints on the superblock which prevent us from
* writing it out straight away; and given that the journal is about to
* be aborted, we can't rely on the current, or future, transactions to
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
* the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
static void ext4_handle_error(struct super_block *sb)
{
if (sb->s_flags & MS_RDONLY)
return;
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (journal)
jbd2_journal_abort(journal, -EIO);
}
if (test_opt(sb, ERRORS_RO)) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= MS_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
!(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
return;
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, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
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, function, line);
ext4_handle_error(sb);
}
void __ext4_error_inode(struct inode *inode, const char *function,
unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
struct va_format vaf;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
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, 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 ext4_super_block *es;
struct inode *inode = file_inode(file);
char pathname[80], *path;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
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, 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;
/* Special case: if the error is EROFS, and we're not already
* inside a transaction, then there's really no point in logging
* an error. */
if (errno == -EROFS && journal_current_handle() == NULL &&
(sb->s_flags & MS_RDONLY))
return;
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, function, line);
ext4_handle_error(sb);
}
/*
* ext4_abort is a much stronger failure handler than ext4_error. The
* abort function may be used to deal with unrecoverable failures such
* as journal IO errors or ENOMEM at a critical moment in log management.
*
* We unconditionally force the filesystem into an ABORT|READONLY state,
* unless the error response on the fs has been set to panic in which
* case we take the easy way out and panic immediately.
*/
void __ext4_abort(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
va_list args;
save_error_info(sb, function, line);
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
function, line);
vprintk(fmt, args);
printk("\n");
va_end(args);
if ((sb->s_flags & MS_RDONLY) == 0) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= MS_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
!(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
return;
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;
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);
}
#define ext4_warning_ratelimit(sb) \
___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;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
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)) {
ext4_commit_super(sb, 0);
return;
}
ext4_unlock_group(sb, grp);
ext4_handle_error(sb);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
* filesystem will have already been marked read/only and the
* journal has been aborted. We return 1 as a hint to callers
* who might what to use the return value from
* ext4_grp_locked_error() to distinguish 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_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
ext4_warning(sb,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV);
/* leave es->s_feature_*compat flags alone */
/* es->s_uuid will be set by e2fsck if empty */
/*
* The rest of the superblock fields should be zero, and if not it
* means they are likely already in use, so leave them alone. We
* can leave it up to e2fsck to clean up any inconsistencies there.
*/
}
/*
* Open the external journal device
*/
static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
char b[BDEVNAME_SIZE];
bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
if (IS_ERR(bdev))
goto fail;
return bdev;
fail:
ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
/*
* Release the journal device
*/
static 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->journal_bdev;
if (bdev) {
ext4_blkdev_put(bdev);
sbi->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));
}
}
static void ext4_put_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int i, err;
ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
flush_workqueue(sbi->rsv_conversion_wq);
destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
if (err < 0)
ext4_abort(sb, "Couldn't clean up the journal");
}
ext4_unregister_sysfs(sb);
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->s_flags & MS_RDONLY)) {
ext4_clear_feature_journal_needs_recovery(sb);
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!(sb->s_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kvfree(sbi->s_group_desc);
kvfree(sbi->s_flex_groups);
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_free_rwsem(&sbi->s_journal_flag_rwsem);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
/* Debugging code just in case the in-memory inode orphan list
* isn't empty. The on-disk one can be non-empty if we've
* detected an error and taken the fs readonly, but the
* in-memory list had better be clean by this point. */
if (!list_empty(&sbi->s_orphan))
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
* Invalidate the journal device's buffers. We don't want them
* floating about in memory - the physical journal device may
* hotswapped, and it breaks the `ro-after' testing code.
*/
sync_blockdev(sbi->journal_bdev);
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
if (sbi->s_mb_cache) {
ext4_xattr_destroy_cache(sbi->s_mb_cache);
sbi->s_mb_cache = NULL;
}
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
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);
kfree(sbi);
}
static struct kmem_cache *ext4_inode_cachep;
/*
* Called inside transaction, so use GFP_NOFS
*/
static struct inode *ext4_alloc_inode(struct super_block *sb)
{
struct ext4_inode_info *ei;
ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
ei->vfs_inode.i_version = 1;
spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
rwlock_init(&ei->i_es_lock);
INIT_LIST_HEAD(&ei->i_es_list);
ei->i_es_all_nr = 0;
ei->i_es_shk_nr = 0;
ei->i_es_shrink_lblk = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#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);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
ei->i_crypt_info = NULL;
#endif
return &ei->vfs_inode;
}
static int ext4_drop_inode(struct inode *inode)
{
int drop = generic_drop_inode(inode);
trace_ext4_drop_inode(inode, drop);
return drop;
}
static void ext4_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
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();
}
call_rcu(&inode->i_rcu, ext4_i_callback);
}
static void init_once(void *foo)
{
struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
}
static int __init init_inodecache(void)
{
ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
sizeof(struct ext4_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
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)
{
invalidate_inode_buffers(inode);
clear_inode(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
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;
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
if (EXT4_I(inode)->i_crypt_info)
ext4_free_encryption_info(inode, EXT4_I(inode)->i_crypt_info);
#endif
}
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
struct inode *inode;
if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
return ERR_PTR(-ESTALE);
if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return ERR_PTR(-ESTALE);
/* iget isn't really right if the inode is currently unallocated!!
*
* ext4_read_inode will return a bad_inode if the inode had been
* deleted, so we should be safe.
*
* Currently we don't know the generation for parent directory, so
* a generation of 0 means "accept any"
*/
inode = ext4_iget_normal(sb, ino);
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);
}
/*
* Try to release metadata pages (indirect blocks, directories) which are
* mapped via the block device. Since these pages could have journal heads
* which would prevent try_to_free_buffers() from freeing them, we must use
* jbd2 layer's try_to_free_buffers() function to release them.
*/
static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
gfp_t wait)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, page,
wait & ~__GFP_DIRECT_RECLAIM);
return try_to_free_buffers(page);
}
#ifdef CONFIG_QUOTA
static char *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,
struct path *path);
static int ext4_quota_off(struct super_block *sb, int type);
static int ext4_quota_on_mount(struct super_block *sb, int type);
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 int ext4_enable_quotas(struct super_block *sb);
static int ext4_get_next_id(struct super_block *sb, struct kqid *qid);
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_next_id = ext4_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,
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
.drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.put_super = ext4_put_super,
.sync_fs = ext4_sync_fs,
.freeze_fs = ext4_freeze,
.unfreeze_fs = ext4_unfreeze,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
.show_options = ext4_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
.get_dquots = ext4_get_dquots,
#endif
.bdev_try_to_free_page = bdev_try_to_free_page,
};
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,
};
enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime,
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,
};
static const match_table_t tokens = {
{Opt_bsd_df, "bsddf"},
{Opt_minix_df, "minixdf"},
{Opt_grpid, "grpid"},
{Opt_grpid, "bsdgroups"},
{Opt_nogrpid, "nogrpid"},
{Opt_nogrpid, "sysvgroups"},
{Opt_resgid, "resgid=%u"},
{Opt_resuid, "resuid=%u"},
{Opt_sb, "sb=%u"},
{Opt_err_cont, "errors=continue"},
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
{Opt_nouid32, "nouid32"},
{Opt_debug, "debug"},
{Opt_removed, "oldalloc"},
{Opt_removed, "orlov"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_noload, "norecovery"},
{Opt_noload, "noload"},
{Opt_removed, "nobh"},
{Opt_removed, "bh"},
{Opt_commit, "commit=%u"},
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_path, "journal_path=%s"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_nojournal_checksum, "nojournal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
{Opt_data_writeback, "data=writeback"},
{Opt_data_err_abort, "data_err=abort"},
{Opt_data_err_ignore, "data_err=ignore"},
{Opt_offusrjquota, "usrjquota="},
{Opt_usrjquota, "usrjquota=%s"},
{Opt_offgrpjquota, "grpjquota="},
{Opt_grpjquota, "grpjquota=%s"},
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_grpquota, "grpquota"},
{Opt_noquota, "noquota"},
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
{Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
{Opt_dax, "dax"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_removed, "mblk_io_submit"},
{Opt_removed, "nomblk_io_submit"},
{Opt_block_validity, "block_validity"},
{Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
{Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
{Opt_dioread_nolock, "dioread_nolock"},
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
{Opt_removed, "noreservation"}, /* mount option from ext2/3 */
{Opt_removed, "journal=%u"}, /* mount option from ext2/3 */
{Opt_err, NULL},
};
static ext4_fsblk_t get_sb_block(void **data)
{
ext4_fsblk_t sb_block;
char *options = (char *) *data;
if (!options || strncmp(options, "sb=", 3) != 0)
return 1; /* Default location */
options += 3;
/* TODO: use simple_strtoll with >32bit ext4 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
(char *) *data);
return 1;
}
if (*options == ',')
options++;
*data = (void *) options;
return sb_block;
}
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
#ifdef CONFIG_QUOTA
static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *qname;
int ret = -1;
if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
ext4_msg(sb, KERN_ERR,
"Cannot change journaled "
"quota options when quota turned on");
return -1;
}
if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_INFO, "Journaled quota options "
"ignored when QUOTA feature is enabled");
return 1;
}
qname = match_strdup(args);
if (!qname) {
ext4_msg(sb, KERN_ERR,
"Not enough memory for storing quotafile name");
return -1;
}
if (sbi->s_qf_names[qtype]) {
if (strcmp(sbi->s_qf_names[qtype], qname) == 0)
ret = 1;
else
ext4_msg(sb, KERN_ERR,
"%s quota file already specified",
QTYPE2NAME(qtype));
goto errout;
}
if (strchr(qname, '/')) {
ext4_msg(sb, KERN_ERR,
"quotafile must be on filesystem root");
goto errout;
}
sbi->s_qf_names[qtype] = qname;
set_opt(sb, QUOTA);
return 1;
errout:
kfree(qname);
return ret;
}
static int clear_qf_name(struct super_block *sb, int qtype)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sb_any_quota_loaded(sb) &&
sbi->s_qf_names[qtype]) {
ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
" when quota turned on");
return -1;
}
kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
return 1;
}
#endif
#define MOPT_SET 0x0001
#define MOPT_CLEAR 0x0002
#define MOPT_NOSUPPORT 0x0004
#define MOPT_EXPLICIT 0x0008
#define MOPT_CLEAR_ERR 0x0010
#define MOPT_GTE0 0x0020
#ifdef CONFIG_QUOTA
#define MOPT_Q 0
#define MOPT_QFMT 0x0040
#else
#define MOPT_Q MOPT_NOSUPPORT
#define MOPT_QFMT MOPT_NOSUPPORT
#endif
#define MOPT_DATAJ 0x0080
#define MOPT_NO_EXT2 0x0100
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
#define MOPT_STRING 0x0400
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_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
EXT4_MOUNT_JOURNAL_CHECKSUM),
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET},
{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
MOPT_NO_EXT2},
{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
MOPT_NO_EXT2},
{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
{Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR},
{Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR},
{Opt_commit, 0, MOPT_GTE0},
{Opt_max_batch_time, 0, MOPT_GTE0},
{Opt_min_batch_time, 0, MOPT_GTE0},
{Opt_inode_readahead_blks, 0, MOPT_GTE0},
{Opt_init_itable, 0, MOPT_GTE0},
{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
{Opt_stripe, 0, MOPT_GTE0},
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
{Opt_journal_dev, 0, MOPT_NO_EXT2 | MOPT_GTE0},
{Opt_journal_path, 0, MOPT_NO_EXT2 | MOPT_STRING},
{Opt_journal_ioprio, 0, MOPT_NO_EXT2 | MOPT_GTE0},
{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA,
MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
#ifdef CONFIG_EXT4_FS_POSIX_ACL
{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
{Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
#else
{Opt_acl, 0, MOPT_NOSUPPORT},
{Opt_noacl, 0, MOPT_NOSUPPORT},
#endif
{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
{Opt_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_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
{Opt_usrjquota, 0, MOPT_Q},
{Opt_grpjquota, 0, MOPT_Q},
{Opt_offusrjquota, 0, MOPT_Q},
{Opt_offgrpjquota, 0, MOPT_Q},
{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_test_dummy_encryption, 0, MOPT_GTE0},
{Opt_err, 0, 0}
};
static int handle_mount_opt(struct super_block *sb, char *opt, int token,
substring_t *args, unsigned long *journal_devnum,
unsigned int *journal_ioprio, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const struct mount_opts *m;
kuid_t uid;
kgid_t gid;
int arg = 0;
#ifdef CONFIG_QUOTA
if (token == Opt_usrjquota)
return set_qf_name(sb, USRQUOTA, &args[0]);
else if (token == Opt_grpjquota)
return set_qf_name(sb, GRPQUOTA, &args[0]);
else if (token == Opt_offusrjquota)
return clear_qf_name(sb, USRQUOTA);
else if (token == Opt_offgrpjquota)
return clear_qf_name(sb, GRPQUOTA);
#endif
switch (token) {
case Opt_noacl:
case Opt_nouser_xattr:
ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5");
break;
case Opt_sb:
return 1; /* handled by get_sb_block() */
case Opt_removed:
ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
return 1;
case Opt_abort:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
return 1;
case Opt_i_version:
sb->s_flags |= MS_I_VERSION;
return 1;
case Opt_lazytime:
sb->s_flags |= MS_LAZYTIME;
return 1;
case Opt_nolazytime:
sb->s_flags &= ~MS_LAZYTIME;
return 1;
}
for (m = ext4_mount_opts; m->token != Opt_err; m++)
if (token == m->token)
break;
if (m->token == Opt_err) {
ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
"or missing value", opt);
return -1;
}
if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) {
ext4_msg(sb, KERN_ERR,
"Mount option \"%s\" incompatible with ext2", opt);
return -1;
}
if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) {
ext4_msg(sb, KERN_ERR,
"Mount option \"%s\" incompatible with ext3", opt);
return -1;
}
if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
if (m->flags & MOPT_EXPLICIT) {
if (m->mount_opt & EXT4_MOUNT_DELALLOC) {
set_opt2(sb, EXPLICIT_DELALLOC);
} else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) {
set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM);
} else
return -1;
}
if (m->flags & MOPT_CLEAR_ERR)
clear_opt(sb, ERRORS_MASK);
if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
ext4_msg(sb, KERN_ERR, "Cannot change quota "
"options when quota turned on");
return -1;
}
if (m->flags & MOPT_NOSUPPORT) {
ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
} else if (token == Opt_commit) {
if (arg == 0)
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
} else if (token == Opt_max_batch_time) {
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
sbi->s_min_batch_time = arg;
} else if (token == Opt_inode_readahead_blks) {
if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) {
ext4_msg(sb, KERN_ERR,
"EXT4-fs: inode_readahead_blks must be "
"0 or a power of 2 smaller than 2^31");
return -1;
}
sbi->s_inode_readahead_blks = arg;
} else if (token == Opt_init_itable) {
set_opt(sb, INIT_INODE_TABLE);
if (!args->from)
arg = EXT4_DEF_LI_WAIT_MULT;
sbi->s_li_wait_mult = arg;
} else if (token == Opt_max_dir_size_kb) {
sbi->s_max_dir_size_kb = arg;
} else if (token == Opt_stripe) {
sbi->s_stripe = arg;
} else if (token == Opt_resuid) {
uid = make_kuid(current_user_ns(), arg);
if (!uid_valid(uid)) {
ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
return -1;
}
sbi->s_resuid = uid;
} else if (token == Opt_resgid) {
gid = make_kgid(current_user_ns(), arg);
if (!gid_valid(gid)) {
ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
return -1;
}
sbi->s_resgid = gid;
} else if (token == Opt_journal_dev) {
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return -1;
}
*journal_devnum = arg;
} else if (token == Opt_journal_path) {
char *journal_path;
struct inode *journal_inode;
struct path path;
int error;
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return -1;
}
journal_path = match_strdup(&args[0]);
if (!journal_path) {
ext4_msg(sb, KERN_ERR, "error: could not dup "
"journal device string");
return -1;
}
error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
if (error) {
ext4_msg(sb, KERN_ERR, "error: could not find "
"journal device path: error %d", error);
kfree(journal_path);
return -1;
}
journal_inode = d_inode(path.dentry);
if (!S_ISBLK(journal_inode->i_mode)) {
ext4_msg(sb, KERN_ERR, "error: journal path %s "
"is not a block device", journal_path);
path_put(&path);
kfree(journal_path);
return -1;
}
*journal_devnum = new_encode_dev(journal_inode->i_rdev);
path_put(&path);
kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
if (arg > 7) {
ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
" (must be 0-7)");
return -1;
}
*journal_ioprio =
IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
} else if (token == Opt_test_dummy_encryption) {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION;
ext4_msg(sb, KERN_WARNING,
"Test dummy encryption mode enabled");
#else
ext4_msg(sb, KERN_WARNING,
"Test dummy encryption mount option ignored");
#endif
} else if (m->flags & MOPT_DATAJ) {
if (is_remount) {
if (!sbi->s_journal)
ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return -1;
}
} else {
clear_opt(sb, DATA_FLAGS);
sbi->s_mount_opt |= m->mount_opt;
}
#ifdef CONFIG_QUOTA
} else if (m->flags & MOPT_QFMT) {
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != m->mount_opt) {
ext4_msg(sb, KERN_ERR, "Cannot change journaled "
"quota options when quota turned on");
return -1;
}
if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_INFO,
"Quota format mount options ignored "
"when QUOTA feature is enabled");
return 1;
}
sbi->s_jquota_fmt = m->mount_opt;
#endif
} else if (token == Opt_dax) {
#ifdef CONFIG_FS_DAX
ext4_msg(sb, KERN_WARNING,
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
sbi->s_mount_opt |= m->mount_opt;
#else
ext4_msg(sb, KERN_INFO, "dax option not supported");
return -1;
#endif
} else if (token == Opt_data_err_abort) {
sbi->s_mount_opt |= m->mount_opt;
} else if (token == Opt_data_err_ignore) {
sbi->s_mount_opt &= ~m->mount_opt;
} else {
if (!args->from)
arg = 1;
if (m->flags & MOPT_CLEAR)
arg = !arg;
else if (unlikely(!(m->flags & MOPT_SET))) {
ext4_msg(sb, KERN_WARNING,
"buggy handling of option %s", opt);
WARN_ON(1);
return -1;
}
if (arg != 0)
sbi->s_mount_opt |= m->mount_opt;
else
sbi->s_mount_opt &= ~m->mount_opt;
}
return 1;
}
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
unsigned int *journal_ioprio,
int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *p;
substring_t args[MAX_OPT_ARGS];
int token;
if (!options)
return 1;
while ((p = strsep(&options, ",")) != NULL) {
if (!*p)
continue;
/*
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
if (handle_mount_opt(sb, p, token, args, journal_devnum,
journal_ioprio, is_remount) < 0)
return 0;
}
#ifdef CONFIG_QUOTA
if (ext4_has_feature_quota(sb) &&
(test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota "
"mount options ignored.");
clear_opt(sb, USRQUOTA);
clear_opt(sb, GRPQUOTA);
} else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sb, USRQUOTA);
if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
clear_opt(sb, GRPQUOTA);
if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
"format mixing");
return 0;
}
if (!sbi->s_jquota_fmt) {
ext4_msg(sb, KERN_ERR, "journaled quota format "
"not specified");
return 0;
}
}
#endif
if (test_opt(sb, DIOREAD_NOLOCK)) {
int blocksize =
BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
if (blocksize < PAGE_SIZE) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"dioread_nolock if block size != PAGE_SIZE");
return 0;
}
}
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA &&
test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with journal_async_commit "
"in data=ordered mode");
return 0;
}
return 1;
}
static inline void ext4_show_quota_options(struct seq_file *seq,
struct super_block *sb)
{
#if defined(CONFIG_QUOTA)
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sbi->s_jquota_fmt) {
char *fmtname = "";
switch (sbi->s_jquota_fmt) {
case QFMT_VFS_OLD:
fmtname = "vfsold";
break;
case QFMT_VFS_V0:
fmtname = "vfsv0";
break;
case QFMT_VFS_V1:
fmtname = "vfsv1";
break;
}
seq_printf(seq, ",jqfmt=%s", fmtname);
}
if (sbi->s_qf_names[USRQUOTA])
seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]);
if (sbi->s_qf_names[GRPQUOTA])
seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]);
#endif
}
static const char *token2str(int token)
{
const struct match_token *t;
for (t = tokens; t->token != Opt_err; t++)
if (t->token == token && !strchr(t->pattern, '='))
break;
return t->pattern;
}
/*
* Show an option if
* - it's set to a non-default value OR
* - if the per-sb default is different from the global default
*/
static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
int nodefs)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int def_errors, def_mount_opt = nodefs ? 0 : sbi->s_def_mount_opt;
const struct mount_opts *m;
char sep = nodefs ? '\n' : ',';
#define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep)
#define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg)
if (sbi->s_sb_block != 1)
SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block);
for (m = ext4_mount_opts; m->token != Opt_err; m++) {
int want_set = m->flags & MOPT_SET;
if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
(m->flags & MOPT_CLEAR_ERR))
continue;
if (!(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
continue; /* skip if same as the default */
if ((want_set &&
(sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
(!want_set && (sbi->s_mount_opt & m->mount_opt)))
continue; /* select Opt_noFoo vs Opt_Foo */
SEQ_OPTS_PRINT("%s", token2str(m->token));
}
if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) ||
le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
SEQ_OPTS_PRINT("resuid=%u",
from_kuid_munged(&init_user_ns, sbi->s_resuid));
if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) ||
le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
SEQ_OPTS_PRINT("resgid=%u",
from_kgid_munged(&init_user_ns, sbi->s_resgid));
def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
SEQ_OPTS_PUTS("errors=remount-ro");
if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
SEQ_OPTS_PUTS("errors=continue");
if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
SEQ_OPTS_PUTS("errors=panic");
if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ)
SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ);
if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME)
SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
if (sb->s_flags & MS_I_VERSION)
SEQ_OPTS_PUTS("i_version");
if (nodefs || sbi->s_stripe)
SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ def_mount_opt)) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
SEQ_OPTS_PUTS("data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
SEQ_OPTS_PUTS("data=ordered");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
SEQ_OPTS_PUTS("data=writeback");
}
if (nodefs ||
sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
SEQ_OPTS_PRINT("inode_readahead_blks=%u",
sbi->s_inode_readahead_blks);
if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
(sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
if (nodefs || sbi->s_max_dir_size_kb)
SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
if (test_opt(sb, DATA_ERR_ABORT))
SEQ_OPTS_PUTS("data_err=abort");
ext4_show_quota_options(seq, sb);
return 0;
}
static int ext4_show_options(struct seq_file *seq, struct dentry *root)
{
return _ext4_show_options(seq, root->d_sb, 0);
}
int ext4_seq_options_show(struct seq_file *seq, void *offset)
{
struct super_block *sb = seq->private;
int rc;
seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw");
rc = _ext4_show_options(seq, sb, 1);
seq_puts(seq, "\n");
return rc;
}
static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
int read_only)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int res = 0;
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
res = MS_RDONLY;
}
if (read_only)
goto done;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
ext4_msg(sb, KERN_WARNING,
"warning: maximal mount count reached, "
"running e2fsck is recommended");
else if (le32_to_cpu(es->s_checkinterval) &&
(le32_to_cpu(es->s_lastcheck) +
le32_to_cpu(es->s_checkinterval) <= get_seconds()))
ext4_msg(sb, KERN_WARNING,
"warning: checktime reached, "
"running e2fsck is recommended");
if (!sbi->s_journal)
es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
ext4_commit_super(sb, 1);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
cleancache_init_fs(sb);
return res;
}
int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct flex_groups *new_groups;
int size;
if (!sbi->s_log_groups_per_flex)
return 0;
size = ext4_flex_group(sbi, ngroup - 1) + 1;
if (size <= sbi->s_flex_groups_allocated)
return 0;
size = roundup_pow_of_two(size * sizeof(struct flex_groups));
new_groups = ext4_kvzalloc(size, GFP_KERNEL);
if (!new_groups) {
ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
size / (int) sizeof(struct flex_groups));
return -ENOMEM;
}
if (sbi->s_flex_groups) {
memcpy(new_groups, sbi->s_flex_groups,
(sbi->s_flex_groups_allocated *
sizeof(struct flex_groups)));
kvfree(sbi->s_flex_groups);
}
sbi->s_flex_groups = new_groups;
sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
return 0;
}
static int ext4_fill_flex_info(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
ext4_group_t flex_group;
int i, err;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
if (err)
goto failed;
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
atomic64_add(ext4_free_group_clusters(sb, gdp),
&sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
return 1;
failed:
return 0;
}
static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
int offset;
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
__le16 save_csum;
__u32 csum32;
save_csum = gdp->bg_checksum;
gdp->bg_checksum = 0;
csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
sizeof(le_group));
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
sbi->s_desc_size);
gdp->bg_checksum = save_csum;
crc = csum32 & 0xFFFF;
goto out;
}
/* old crc16 code */
if (!ext4_has_feature_gdt_csum(sb))
return 0;
offset = offsetof(struct ext4_group_desc, bg_checksum);
crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
crc = crc16(crc, (__u8 *)gdp, offset);
offset += sizeof(gdp->bg_checksum); /* skip checksum */
/* for checksum of struct ext4_group_desc do the rest...*/
if (ext4_has_feature_64bit(sb) &&
offset < le16_to_cpu(sbi->s_es->s_desc_size))
crc = crc16(crc, (__u8 *)gdp + offset,
le16_to_cpu(sbi->s_es->s_desc_size) -
offset);
out:
return cpu_to_le16(crc);
}
int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
if (ext4_has_group_desc_csum(sb) &&
(gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp)))
return 0;
return 1;
}
void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
if (!ext4_has_group_desc_csum(sb))
return;
gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp);
}
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
ext4_fsblk_t last_block;
ext4_fsblk_t block_bitmap;
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
int flexbg_flag = 0;
ext4_group_t i, grp = sbi->s_groups_count;
if (ext4_has_feature_flex_bg(sb))
flexbg_flag = 1;
ext4_debug("Checking group descriptors");
for (i = 0; i < sbi->s_groups_count; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
if (i == sbi->s_groups_count - 1 || flexbg_flag)
last_block = ext4_blocks_count(sbi->s_es) - 1;
else
last_block = first_block +
(EXT4_BLOCKS_PER_GROUP(sb) - 1);
if ((grp == sbi->s_groups_count) &&
!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
"(block %llu)!", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
"(block %llu)!", i, inode_bitmap);
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode table for group %u not in group "
"(block %llu)!", i, inode_table);
return 0;
}
ext4_lock_group(sb, i);
if (!ext4_group_desc_csum_verify(sb, i, gdp)) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Checksum for group %u failed (%u!=%u)",
i, le16_to_cpu(ext4_group_desc_csum(sb, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
if (!(sb->s_flags & MS_RDONLY)) {
ext4_unlock_group(sb, i);
return 0;
}
}
ext4_unlock_group(sb, i);
if (!flexbg_flag)
first_block += EXT4_BLOCKS_PER_GROUP(sb);
}
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
return 1;
}
/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
* the superblock) which were deleted from all directories, but held open by
* a process at the time of a crash. We walk the list and try to delete these
* inodes at recovery time (only with a read-write filesystem).
*
* In order to keep the orphan inode chain consistent during traversal (in
* case of crash during recovery), we link each inode into the superblock
* orphan list_head and handle it the same way as an inode deletion during
* normal operation (which journals the operations for us).
*
* We only do an iget() and an iput() on each inode, which is very safe if we
* accidentally point at an in-use or already deleted inode. The worst that
* can happen in this case is that we get a "bit already cleared" message from
* ext4_free_inode(). The only reason we would point at a wrong inode is if
* e2fsck was run on this filesystem, and it must have already done the orphan
* inode cleanup for us, so we can safely abort without any further action.
*/
static void ext4_orphan_cleanup(struct super_block *sb,
struct ext4_super_block *es)
{
unsigned int s_flags = sb->s_flags;
int nr_orphans = 0, nr_truncates = 0;
#ifdef CONFIG_QUOTA
int i;
#endif
if (!es->s_last_orphan) {
jbd_debug(4, "no orphan inodes to clean up\n");
return;
}
if (bdev_read_only(sb->s_bdev)) {
ext4_msg(sb, KERN_ERR, "write access "
"unavailable, skipping orphan cleanup");
return;
}
/* Check if feature set would not allow a r/w mount */
if (!ext4_feature_set_ok(sb, 0)) {
ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
"unknown ROCOMPAT features");
return;
}
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
/* don't clear list on RO mount w/ errors */
if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
"clearing orphan list.\n");
es->s_last_orphan = 0;
}
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
return;
}
if (s_flags & MS_RDONLY) {
ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
sb->s_flags &= ~MS_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
sb->s_flags |= MS_ACTIVE;
/* Turn on quotas so that they are updated correctly */
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (EXT4_SB(sb)->s_qf_names[i]) {
int ret = ext4_quota_on_mount(sb, i);
if (ret < 0)
ext4_msg(sb, KERN_ERR,
"Cannot turn on journaled "
"quota: error %d", ret);
}
}
#endif
while (es->s_last_orphan) {
struct inode *inode;
inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
if (IS_ERR(inode)) {
es->s_last_orphan = 0;
break;
}
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
dquot_initialize(inode);
if (inode->i_nlink) {
if (test_opt(sb, DEBUG))
ext4_msg(sb, KERN_DEBUG,
"%s: truncating inode %lu to %lld bytes",
__func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
inode_lock(inode);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
inode_unlock(inode);
nr_truncates++;
} else {
if (test_opt(sb, DEBUG))
ext4_msg(sb, KERN_DEBUG,
"%s: deleting unreferenced inode %lu",
__func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
}
iput(inode); /* The delete magic happens here! */
}
#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
if (nr_orphans)
ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
PLURAL(nr_orphans));
if (nr_truncates)
ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
/* Turn quotas off */
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
dquot_quota_off(sb, i);
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}
/*
* Maximal extent format file size.
* Resulting logical blkno at s_maxbytes must fit in our on-disk
* extent format containers, within a sector_t, and within i_blocks
* in the vfs. ext4 inode has 48 bits of i_block in fsblock units,
* so that won't be a limiting factor.
*
* However there is other limiting factor. We do store extents in the form
* of starting block and length, hence the resulting length of the extent
* covering maximum file size must fit into on-disk format containers as
* well. Given that length is always by 1 unit bigger than max unit (because
* we count 0 as well) we have to lower the s_maxbytes by one fs block.
*
* Note, this does *not* consider any metadata overhead for vfs i_blocks.
*/
static loff_t ext4_max_size(int blkbits, int has_huge_files)
{
loff_t res;
loff_t upper_limit = MAX_LFS_FILESIZE;
/* small i_blocks in vfs inode? */
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
* CONFIG_LBDAF is not enabled implies the inode
* i_block represent total blocks in 512 bytes
* 32 == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (blkbits - 9);
upper_limit <<= blkbits;
}
/*
* 32-bit extent-start container, ee_block. We lower the maxbytes
* by one fs block, so ee_len can cover the extent of maximum file
* size
*/
res = (1LL << 32) - 1;
res <<= blkbits;
/* Sanity check against vm- & vfs- imposed limits */
if (res > upper_limit)
res = upper_limit;
return res;
}
/*
* Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
* We need to be 1 filesystem block less than the 2^48 sector limit.
*/
static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
{
loff_t res = EXT4_NDIR_BLOCKS;
int meta_blocks;
loff_t upper_limit;
/* This is calculated to be the largest file size for a dense, block
* mapped file such that the file's total number of 512-byte sectors,
* including data and all indirect blocks, does not exceed (2^48 - 1).
*
* __u32 i_blocks_lo and _u16 i_blocks_high represent the total
* number of 512-byte sectors of the file.
*/
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
* !has_huge_files or CONFIG_LBDAF not enabled implies that
* the inode i_block field represents total file blocks in
* 2^32 512-byte sectors == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
} else {
/*
* We use 48 bit ext4_inode i_blocks
* With EXT4_HUGE_FILE_FL set the i_blocks
* represent total number of blocks in
* file system block size
*/
upper_limit = (1LL << 48) - 1;
}
/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
upper_limit -= meta_blocks;
upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res += 1LL << (3*(bits-2));
res <<= bits;
if (res > upper_limit)
res = upper_limit;
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
return res;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
ext4_fsblk_t logical_sb_block, int nr)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t bg, first_meta_bg;
int has_super = 0;
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg)
return logical_sb_block + nr + 1;
bg = sbi->s_desc_per_block * nr;
if (ext4_bg_has_super(sb, bg))
has_super = 1;
/*
* If we have a meta_bg fs with 1k blocks, group 0's GDT is at
* block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
* on modern mke2fs or blksize > 1k on older mke2fs) then we must
* compensate.
*/
if (sb->s_blocksize == 1024 && nr == 0 &&
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
has_super++;
return (has_super + ext4_group_first_block_no(sb, bg));
}
/**
* ext4_get_stripe_size: Get the stripe size.
* @sbi: In memory super block info
*
* If we have specified it via mount option, then
* use the mount option value. If the value specified at mount time is
* greater than the blocks per group use the super block value.
* If the super block value is greater than blocks per group return 0.
* Allocator needs it be less than blocks per group.
*
*/
static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
{
unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
unsigned long stripe_width =
le32_to_cpu(sbi->s_es->s_raid_stripe_width);
int ret;
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
ret = sbi->s_stripe;
else if (stripe_width <= sbi->s_blocks_per_group)
ret = stripe_width;
else if (stride <= sbi->s_blocks_per_group)
ret = stride;
else
ret = 0;
/*
* If the stripe width is 1, this makes no sense and
* we set it to 0 to turn off stripe handling code.
*/
if (ret <= 1)
ret = 0;
return ret;
}
/*
* Check whether this filesystem can be mounted based on
* the features present and the RDONLY/RDWR mount requested.
* Returns 1 if this filesystem can be mounted as requested,
* 0 if it cannot be.
*/
static int ext4_feature_set_ok(struct super_block *sb, int readonly)
{
if (ext4_has_unknown_ext4_incompat_features(sb)) {
ext4_msg(sb, KERN_ERR,
"Couldn't mount because of "
"unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
~EXT4_FEATURE_INCOMPAT_SUPP));
return 0;
}
if (readonly)
return 1;
if (ext4_has_feature_readonly(sb)) {
ext4_msg(sb, KERN_INFO, "filesystem is read-only");
sb->s_flags |= MS_RDONLY;
return 1;
}
/* Check that feature set is OK for a read-write mount */
if (ext4_has_unknown_ext4_ro_compat_features(sb)) {
ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
"unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
~EXT4_FEATURE_RO_COMPAT_SUPP));
return 0;
}
/*
* Large file size enabled file system can only be mounted
* read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
*/
if (ext4_has_feature_huge_file(sb)) {
if (sizeof(blkcnt_t) < sizeof(u64)) {
ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
"cannot be mounted RDWR without "
"CONFIG_LBDAF");
return 0;
}
}
if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) {
ext4_msg(sb, KERN_ERR,
"Can't support bigalloc feature without "
"extents feature\n");
return 0;
}
#ifndef CONFIG_QUOTA
if (ext4_has_feature_quota(sb) && !readonly) {
ext4_msg(sb, KERN_ERR,
"Filesystem with quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return 0;
}
if (ext4_has_feature_project(sb) && !readonly) {
ext4_msg(sb, KERN_ERR,
"Filesystem with project quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return 0;
}
#endif /* CONFIG_QUOTA */
return 1;
}
/*
* This function is called once a day if we have errors logged
* on the file system
*/
static void print_daily_error_info(unsigned long arg)
{
struct super_block *sb = (struct super_block *) arg;
struct ext4_sb_info *sbi;
struct ext4_super_block *es;
sbi = EXT4_SB(sb);
es = sbi->s_es;
if (es->s_error_count)
/* fsck newer than v1.41.13 is needed to clean this condition. */
ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
le32_to_cpu(es->s_first_error_line));
if (es->s_first_error_ino)
printk(": inode %u",
le32_to_cpu(es->s_first_error_ino));
if (es->s_first_error_block)
printk(": block %llu", (unsigned long long)
le64_to_cpu(es->s_first_error_block));
printk("\n");
}
if (es->s_last_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
le32_to_cpu(es->s_last_error_line));
if (es->s_last_error_ino)
printk(": inode %u",
le32_to_cpu(es->s_last_error_ino));
if (es->s_last_error_block)
printk(": block %llu", (unsigned long long)
le64_to_cpu(es->s_last_error_block));
printk("\n");
}
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
/* Find next suitable group and run ext4_init_inode_table */
static int ext4_run_li_request(struct ext4_li_request *elr)
{
struct ext4_group_desc *gdp = NULL;
ext4_group_t group, ngroups;
struct super_block *sb;
unsigned long timeout = 0;
int ret = 0;
sb = elr->lr_super;
ngroups = EXT4_SB(sb)->s_groups_count;
sb_start_write(sb);
for (group = elr->lr_next_group; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp) {
ret = 1;
break;
}
if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
break;
}
if (group >= ngroups)
ret = 1;
if (!ret) {
timeout = jiffies;
ret = ext4_init_inode_table(sb, group,
elr->lr_timeout ? 0 : 1);
if (elr->lr_timeout == 0) {
timeout = (jiffies - timeout) *
elr->lr_sbi->s_li_wait_mult;
elr->lr_timeout = timeout;
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
sb_end_write(sb);
return ret;
}
/*
* Remove lr_request from the list_request and free the
* request structure. Should be called with li_list_mtx held
*/
static void ext4_remove_li_request(struct ext4_li_request *elr)
{
struct ext4_sb_info *sbi;
if (!elr)
return;
sbi = elr->lr_sbi;
list_del(&elr->lr_request);
sbi->s_li_request = NULL;
kfree(elr);
}
static void ext4_unregister_li_request(struct super_block *sb)
{
mutex_lock(&ext4_li_mtx);
if (!ext4_li_info) {
mutex_unlock(&ext4_li_mtx);
return;
}
mutex_lock(&ext4_li_info->li_list_mtx);
ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
mutex_unlock(&ext4_li_info->li_list_mtx);
mutex_unlock(&ext4_li_mtx);
}
static struct task_struct *ext4_lazyinit_task;
/*
* This is the function where ext4lazyinit thread lives. It walks
* through the request list searching for next scheduled filesystem.
* When such a fs is found, run the lazy initialization request
* (ext4_rn_li_request) and keep track of the time spend in this
* function. Based on that time we compute next schedule time of
* the request. When walking through the list is complete, compute
* next waking time and put itself into sleep.
*/
static int ext4_lazyinit_thread(void *arg)
{
struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
struct list_head *pos, *n;
struct ext4_li_request *elr;
unsigned long next_wakeup, cur;
BUG_ON(NULL == eli);
cont_thread:
while (true) {
next_wakeup = MAX_JIFFY_OFFSET;
mutex_lock(&eli->li_list_mtx);
if (list_empty(&eli->li_request_list)) {
mutex_unlock(&eli->li_list_mtx);
goto exit_thread;
}
list_for_each_safe(pos, n, &eli->li_request_list) {
elr = list_entry(pos, struct ext4_li_request,
lr_request);
if (time_after_eq(jiffies, elr->lr_next_sched)) {
if (ext4_run_li_request(elr) != 0) {
/* error, remove the lazy_init job */
ext4_remove_li_request(elr);
continue;
}
}
if (time_before(elr->lr_next_sched, next_wakeup))
next_wakeup = elr->lr_next_sched;
}
mutex_unlock(&eli->li_list_mtx);
try_to_freeze();
cur = jiffies;
if ((time_after_eq(cur, next_wakeup)) ||
(MAX_JIFFY_OFFSET == next_wakeup)) {
cond_resched();
continue;
}
schedule_timeout_interruptible(next_wakeup - cur);
if (kthread_should_stop()) {
ext4_clear_request_list();
goto exit_thread;
}
}
exit_thread:
/*
* It looks like the request list is empty, but we need
* to check it under the li_list_mtx lock, to prevent any
* additions into it, and of course we should lock ext4_li_mtx
* to atomically free the list and ext4_li_info, because at
* this point another ext4 filesystem could be registering
* new one.
*/
mutex_lock(&ext4_li_mtx);
mutex_lock(&eli->li_list_mtx);
if (!list_empty(&eli->li_request_list)) {
mutex_unlock(&eli->li_list_mtx);
mutex_unlock(&ext4_li_mtx);
goto cont_thread;
}
mutex_unlock(&eli->li_list_mtx);
kfree(ext4_li_info);
ext4_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
return 0;
}
static void ext4_clear_request_list(void)
{
struct list_head *pos, *n;
struct ext4_li_request *elr;
mutex_lock(&ext4_li_info->li_list_mtx);
list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
elr = list_entry(pos, struct ext4_li_request,
lr_request);
ext4_remove_li_request(elr);
}
mutex_unlock(&ext4_li_info->li_list_mtx);
}
static int ext4_run_lazyinit_thread(void)
{
ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
ext4_li_info, "ext4lazyinit");
if (IS_ERR(ext4_lazyinit_task)) {
int err = PTR_ERR(ext4_lazyinit_task);
ext4_clear_request_list();
kfree(ext4_li_info);
ext4_li_info = NULL;
printk(KERN_CRIT "EXT4-fs: error %d creating inode table "
"initialization thread\n",
err);
return err;
}
ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
return 0;
}
/*
* Check whether it make sense to run itable init. thread or not.
* If there is at least one uninitialized inode table, return
* corresponding group number, else the loop goes through all
* groups and return total number of groups.
*/
static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
{
ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *gdp = NULL;
for (group = 0; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp)
continue;
if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
break;
}
return group;
}
static int ext4_li_info_new(void)
{
struct ext4_lazy_init *eli = NULL;
eli = kzalloc(sizeof(*eli), GFP_KERNEL);
if (!eli)
return -ENOMEM;
INIT_LIST_HEAD(&eli->li_request_list);
mutex_init(&eli->li_list_mtx);
eli->li_state |= EXT4_LAZYINIT_QUIT;
ext4_li_info = eli;
return 0;
}
static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
ext4_group_t start)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr;
elr = kzalloc(sizeof(*elr), GFP_KERNEL);
if (!elr)
return NULL;
elr->lr_super = sb;
elr->lr_sbi = sbi;
elr->lr_next_group = start;
/*
* Randomize first schedule time of the request to
* spread the inode table initialization requests
* better.
*/
elr->lr_next_sched = jiffies + (prandom_u32() %
(EXT4_DEF_LI_MAX_START_DELAY * HZ));
return elr;
}
int ext4_register_li_request(struct super_block *sb,
ext4_group_t first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr = NULL;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
int ret = 0;
mutex_lock(&ext4_li_mtx);
if (sbi->s_li_request != NULL) {
/*
* Reset timeout so it can be computed again, because
* s_li_wait_mult might have changed.
*/
sbi->s_li_request->lr_timeout = 0;
goto out;
}
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
!test_opt(sb, INIT_INODE_TABLE))
goto out;
elr = ext4_li_request_new(sb, first_not_zeroed);
if (!elr) {
ret = -ENOMEM;
goto out;
}
if (NULL == ext4_li_info) {
ret = ext4_li_info_new();
if (ret)
goto out;
}
mutex_lock(&ext4_li_info->li_list_mtx);
list_add(&elr->lr_request, &ext4_li_info->li_request_list);
mutex_unlock(&ext4_li_info->li_list_mtx);
sbi->s_li_request = elr;
/*
* set elr to NULL here since it has been inserted to
* the request_list and the removal and free of it is
* handled by ext4_clear_request_list from now on.
*/
elr = NULL;
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {