linux_dsm_epyc7002/fs/ext4/super.c
Lukas Czerner bfff68738f ext4: add support for lazy inode table initialization
When the lazy_itable_init extended option is passed to mke2fs, it
considerably speeds up filesystem creation because inode tables are
not zeroed out.  The fact that parts of the inode table are
uninitialized is not a problem so long as the block group descriptors,
which contain information regarding how much of the inode table has
been initialized, has not been corrupted However, if the block group
checksums are not valid, e2fsck must scan the entire inode table, and
the the old, uninitialized data could potentially cause e2fsck to
report false problems.

Hence, it is important for the inode tables to be initialized as soon
as possble.  This commit adds this feature so that mke2fs can safely
use the lazy inode table initialization feature to speed up formatting
file systems.

This is done via a new new kernel thread called ext4lazyinit, which is
created on demand and destroyed, when it is no longer needed.  There
is only one thread for all ext4 filesystems in the system. When the
first filesystem with inititable mount option is mounted, ext4lazyinit
thread is created, then the filesystem can register its request in the
request list.

This thread then walks through the list of requests picking up
scheduled requests and invoking ext4_init_inode_table(). Next schedule
time for the request is computed by multiplying the time it took to
zero out last inode table with wait multiplier, which can be set with
the (init_itable=n) mount option (default is 10).  We are doing
this so we do not take the whole I/O bandwidth. When the thread is no
longer necessary (request list is empty) it frees the appropriate
structures and exits (and can be created later later by another
filesystem).

We do not disturb regular inode allocations in any way, it just do not
care whether the inode table is, or is not zeroed. But when zeroing, we
have to skip used inodes, obviously. Also we should prevent new inode
allocations from the group, while zeroing is on the way. For that we
take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem
in the ext4_claim_inode, so when we are unlucky and allocator hits the
group which is currently being zeroed, it just has to wait.

This can be suppresed using the mount option no_init_itable.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-27 21:30:05 -04:00

4789 lines
132 KiB
C

/*
* linux/fs/ext4/super.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
#include <linux/jbd2.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#include <asm/uaccess.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
struct ext4_lazy_init *ext4_li_info;
struct mutex ext4_li_mtx;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_commit_super(struct super_block *sb, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
static const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
static int ext4_remount(struct super_block *sb, int *flags, char *data);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static int ext4_get_sb(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data, struct vfsmount *mnt);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
.owner = THIS_MODULE,
.name = "ext3",
.get_sb = ext4_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
#else
#define IS_EXT3_SB(sb) (0)
#endif
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_block_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_table_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
__u32 ext4_free_blks_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
}
__u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_inodes_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_used_dirs_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
}
__u32 ext4_itable_unused_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_itable_unused_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
}
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
void ext4_free_blks_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
}
void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
}
void ext4_used_dirs_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
}
void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
/* Just increment the non-pointer handle value */
static handle_t *ext4_get_nojournal(void)
{
handle_t *handle = current->journal_info;
unsigned long ref_cnt = (unsigned long)handle;
BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
ref_cnt++;
handle = (handle_t *)ref_cnt;
current->journal_info = handle;
return handle;
}
/* Decrement the non-pointer handle value */
static void ext4_put_nojournal(handle_t *handle)
{
unsigned long ref_cnt = (unsigned long)handle;
BUG_ON(ref_cnt == 0);
ref_cnt--;
handle = (handle_t *)ref_cnt;
current->journal_info = handle;
}
/*
* Wrappers for jbd2_journal_start/end.
*
* The only special thing we need to do here is to make sure that all
* journal_end calls result in the superblock being marked dirty, so
* that sync() will call the filesystem's write_super callback if
* appropriate.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
vfs_check_frozen(sb, SB_FREEZE_TRANS);
/* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
if (journal) {
if (is_journal_aborted(journal)) {
ext4_abort(sb, "Detected aborted journal");
return ERR_PTR(-EROFS);
}
return jbd2_journal_start(journal, nblocks);
}
return ext4_get_nojournal();
}
/*
* The only special thing we need to do here is to make sure that all
* jbd2_journal_stop calls result in the superblock being marked dirty, so
* that sync() will call the filesystem's write_super callback if
* appropriate.
*/
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
int err;
int rc;
if (!ext4_handle_valid(handle)) {
ext4_put_nojournal(handle);
return 0;
}
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
if (!err)
err = rc;
if (err)
__ext4_std_error(sb, where, line, err);
return err;
}
void ext4_journal_abort_handle(const char *caller, unsigned int line,
const char *err_fn, struct buffer_head *bh,
handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
BUG_ON(!ext4_handle_valid(handle));
if (bh)
BUFFER_TRACE(bh, "abort");
if (!handle->h_err)
handle->h_err = err;
if (is_handle_aborted(handle))
return;
printk(KERN_ERR "%s:%d: aborting transaction: %s in %s\n",
caller, line, errstr, err_fn);
jbd2_journal_abort_handle(handle);
}
static void __save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
es->s_last_error_time = cpu_to_le32(get_seconds());
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
es->s_last_error_line = cpu_to_le32(line);
if (!es->s_first_error_time) {
es->s_first_error_time = es->s_last_error_time;
strncpy(es->s_first_error_func, func,
sizeof(es->s_first_error_func));
es->s_first_error_line = cpu_to_le32(line);
es->s_first_error_ino = es->s_last_error_ino;
es->s_first_error_block = es->s_last_error_block;
}
/*
* Start the daily error reporting function if it hasn't been
* started already
*/
if (!es->s_error_count)
mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
}
static void save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
__save_error_info(sb, func, line);
ext4_commit_super(sb, 1);
}
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
* On ext2, we can store the error state of the filesystem in the
* superblock. That is not possible on ext4, because we may have other
* write ordering constraints on the superblock which prevent us from
* writing it out straight away; and given that the journal is about to
* be aborted, we can't rely on the current, or future, transactions to
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
* the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
static void ext4_handle_error(struct super_block *sb)
{
if (sb->s_flags & MS_RDONLY)
return;
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (journal)
jbd2_journal_abort(journal, -EIO);
}
if (test_opt(sb, ERRORS_RO)) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
sb->s_flags |= MS_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: ",
sb->s_id, function, line, current->comm);
vprintk(fmt, args);
printk("\n");
va_end(args);
ext4_handle_error(sb);
}
void ext4_error_inode(struct inode *inode, const char *function,
unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
inode->i_sb->s_id, function, line, inode->i_ino);
if (block)
printk("block %llu: ", block);
printk("comm %s: ", current->comm);
vprintk(fmt, args);
printk("\n");
va_end(args);
ext4_handle_error(inode->i_sb);
}
void ext4_error_file(struct file *file, const char *function,
unsigned int line, const char *fmt, ...)
{
va_list args;
struct ext4_super_block *es;
struct inode *inode = file->f_dentry->d_inode;
char pathname[80], *path;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
path = d_path(&(file->f_path), pathname, sizeof(pathname));
if (!path)
path = "(unknown)";
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: inode #%lu "
"(comm %s path %s): ",
inode->i_sb->s_id, function, line, inode->i_ino,
current->comm, path);
vprintk(fmt, args);
printk("\n");
va_end(args);
ext4_handle_error(inode->i_sb);
}
static const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
char *errstr = NULL;
switch (errno) {
case -EIO:
errstr = "IO failure";
break;
case -ENOMEM:
errstr = "Out of memory";
break;
case -EROFS:
if (!sb || (EXT4_SB(sb)->s_journal &&
EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
errstr = "Journal has aborted";
else
errstr = "Readonly filesystem";
break;
default:
/* If the caller passed in an extra buffer for unknown
* errors, textualise them now. Else we just return
* NULL. */
if (nbuf) {
/* Check for truncated error codes... */
if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
errstr = nbuf;
}
break;
}
return errstr;
}
/* __ext4_std_error decodes expected errors from journaling functions
* automatically and invokes the appropriate error response. */
void __ext4_std_error(struct super_block *sb, const char *function,
unsigned int line, int errno)
{
char nbuf[16];
const char *errstr;
/* Special case: if the error is EROFS, and we're not already
* inside a transaction, then there's really no point in logging
* an error. */
if (errno == -EROFS && journal_current_handle() == NULL &&
(sb->s_flags & MS_RDONLY))
return;
errstr = ext4_decode_error(sb, errno, nbuf);
printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
sb->s_id, function, line, errstr);
save_error_info(sb, function, line);
ext4_handle_error(sb);
}
/*
* ext4_abort is a much stronger failure handler than ext4_error. The
* abort function may be used to deal with unrecoverable failures such
* as journal IO errors or ENOMEM at a critical moment in log management.
*
* We unconditionally force the filesystem into an ABORT|READONLY state,
* unless the error response on the fs has been set to panic in which
* case we take the easy way out and panic immediately.
*/
void __ext4_abort(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
va_list args;
save_error_info(sb, function, line);
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
function, line);
vprintk(fmt, args);
printk("\n");
va_end(args);
if ((sb->s_flags & MS_RDONLY) == 0) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
sb->s_flags |= MS_RDONLY;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
}
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs panic from previous error\n");
}
void ext4_msg (struct super_block * sb, const char *prefix,
const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
printk("%sEXT4-fs (%s): ", prefix, sb->s_id);
vprintk(fmt, args);
printk("\n");
va_end(args);
}
void __ext4_warning(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: ",
sb->s_id, function, line);
vprintk(fmt, args);
printk("\n");
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)
{
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
sb->s_id, function, line, grp);
if (ino)
printk("inode %lu: ", ino);
if (block)
printk("block %llu:", (unsigned long long) block);
vprintk(fmt, args);
printk("\n");
va_end(args);
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
return;
}
ext4_unlock_group(sb, grp);
ext4_handle_error(sb);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
* filesystem will have already been marked read/only and the
* journal has been aborted. We return 1 as a hint to callers
* who might what to use the return value from
* ext4_grp_locked_error() to distinguish beween the
* ERRORS_CONT and ERRORS_RO case, and perhaps return more
* aggressively from the ext4 function in question, with a
* more appropriate error code.
*/
ext4_lock_group(sb, grp);
return;
}
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
ext4_warning(sb,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV);
/* leave es->s_feature_*compat flags alone */
/* es->s_uuid will be set by e2fsck if empty */
/*
* The rest of the superblock fields should be zero, and if not it
* means they are likely already in use, so leave them alone. We
* can leave it up to e2fsck to clean up any inconsistencies there.
*/
}
/*
* Open the external journal device
*/
static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
char b[BDEVNAME_SIZE];
bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
if (IS_ERR(bdev))
goto fail;
return bdev;
fail:
ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
/*
* Release the journal device
*/
static int ext4_blkdev_put(struct block_device *bdev)
{
bd_release(bdev);
return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
}
static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
int ret = -ENODEV;
bdev = sbi->journal_bdev;
if (bdev) {
ret = ext4_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
return ret;
}
static inline struct inode *orphan_list_entry(struct list_head *l)
{
return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
}
static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
{
struct list_head *l;
ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
le32_to_cpu(sbi->s_es->s_last_orphan));
printk(KERN_ERR "sb_info orphan list:\n");
list_for_each(l, &sbi->s_orphan) {
struct inode *inode = orphan_list_entry(l);
printk(KERN_ERR " "
"inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
inode->i_sb->s_id, inode->i_ino, inode,
inode->i_mode, inode->i_nlink,
NEXT_ORPHAN(inode));
}
}
static void ext4_put_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int i, err;
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
flush_workqueue(sbi->dio_unwritten_wq);
destroy_workqueue(sbi->dio_unwritten_wq);
lock_super(sb);
lock_kernel();
if (sb->s_dirt)
ext4_commit_super(sb, 1);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
if (err < 0)
ext4_abort(sb, "Couldn't clean up the journal");
}
del_timer(&sbi->s_err_report);
ext4_unregister_li_request(sb);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
ext4_commit_super(sb, 1);
}
if (sbi->s_proc) {
remove_proc_entry(sb->s_id, ext4_proc_root);
}
kobject_del(&sbi->s_kobj);
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
if (is_vmalloc_addr(sbi->s_flex_groups))
vfree(sbi->s_flex_groups);
else
kfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
/* Debugging code just in case the in-memory inode orphan list
* isn't empty. The on-disk one can be non-empty if we've
* detected an error and taken the fs readonly, but the
* in-memory list had better be clean by this point. */
if (!list_empty(&sbi->s_orphan))
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
* Invalidate the journal device's buffers. We don't want them
* floating about in memory - the physical journal device may
* hotswapped, and it breaks the `ro-after' testing code.
*/
sync_blockdev(sbi->journal_bdev);
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
sb->s_fs_info = NULL;
/*
* Now that we are completely done shutting down the
* superblock, we need to actually destroy the kobject.
*/
unlock_kernel();
unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
}
static struct kmem_cache *ext4_inode_cachep;
/*
* Called inside transaction, so use GFP_NOFS
*/
static struct inode *ext4_alloc_inode(struct super_block *sb)
{
struct ext4_inode_info *ei;
ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
ei->vfs_inode.i_version = 1;
ei->vfs_inode.i_data.writeback_index = 0;
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
/*
* Note: We can be called before EXT4_SB(sb)->s_journal is set,
* therefore it can be null here. Don't check it, just initialize
* jinode.
*/
jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
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_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
#endif
INIT_LIST_HEAD(&ei->i_completed_io_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->cur_aio_dio = NULL;
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
return &ei->vfs_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();
}
kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
}
static void init_once(void *foo)
{
struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT4_FS_XATTR
init_rwsem(&ei->xattr_sem);
#endif
init_rwsem(&ei->i_data_sem);
inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
{
ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
sizeof(struct ext4_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD),
init_once);
if (ext4_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
kmem_cache_destroy(ext4_inode_cachep);
}
void ext4_clear_inode(struct inode *inode)
{
invalidate_inode_buffers(inode);
end_writeback(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_JOURNAL(inode))
jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
&EXT4_I(inode)->jinode);
}
static inline void ext4_show_quota_options(struct seq_file *seq,
struct super_block *sb)
{
#if defined(CONFIG_QUOTA)
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sbi->s_jquota_fmt) {
char *fmtname = "";
switch (sbi->s_jquota_fmt) {
case QFMT_VFS_OLD:
fmtname = "vfsold";
break;
case QFMT_VFS_V0:
fmtname = "vfsv0";
break;
case QFMT_VFS_V1:
fmtname = "vfsv1";
break;
}
seq_printf(seq, ",jqfmt=%s", fmtname);
}
if (sbi->s_qf_names[USRQUOTA])
seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
if (test_opt(sb, USRQUOTA))
seq_puts(seq, ",usrquota");
if (test_opt(sb, GRPQUOTA))
seq_puts(seq, ",grpquota");
#endif
}
/*
* Show an option if
* - it's set to a non-default value OR
* - if the per-sb default is different from the global default
*/
static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
int def_errors;
unsigned long def_mount_opts;
struct super_block *sb = vfs->mnt_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
def_errors = le16_to_cpu(es->s_errors);
if (sbi->s_sb_block != 1)
seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
if (test_opt(sb, MINIX_DF))
seq_puts(seq, ",minixdf");
if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
seq_puts(seq, ",grpid");
if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
seq_puts(seq, ",nogrpid");
if (sbi->s_resuid != EXT4_DEF_RESUID ||
le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) {
seq_printf(seq, ",resuid=%u", sbi->s_resuid);
}
if (sbi->s_resgid != EXT4_DEF_RESGID ||
le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
seq_printf(seq, ",resgid=%u", sbi->s_resgid);
}
if (test_opt(sb, ERRORS_RO)) {
if (def_errors == EXT4_ERRORS_PANIC ||
def_errors == EXT4_ERRORS_CONTINUE) {
seq_puts(seq, ",errors=remount-ro");
}
}
if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
seq_puts(seq, ",errors=continue");
if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
seq_puts(seq, ",errors=panic");
if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
seq_puts(seq, ",debug");
if (test_opt(sb, OLDALLOC))
seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
if (test_opt(sb, XATTR_USER) &&
!(def_mount_opts & EXT4_DEFM_XATTR_USER))
seq_puts(seq, ",user_xattr");
if (!test_opt(sb, XATTR_USER) &&
(def_mount_opts & EXT4_DEFM_XATTR_USER)) {
seq_puts(seq, ",nouser_xattr");
}
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
seq_puts(seq, ",acl");
if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
seq_puts(seq, ",noacl");
#endif
if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
seq_printf(seq, ",commit=%u",
(unsigned) (sbi->s_commit_interval / HZ));
}
if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
seq_printf(seq, ",min_batch_time=%u",
(unsigned) sbi->s_min_batch_time);
}
if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
seq_printf(seq, ",max_batch_time=%u",
(unsigned) sbi->s_min_batch_time);
}
/*
* We're changing the default of barrier mount option, so
* let's always display its mount state so it's clear what its
* status is.
*/
seq_puts(seq, ",barrier=");
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
seq_puts(seq, ",journal_async_commit");
else if (test_opt(sb, JOURNAL_CHECKSUM))
seq_puts(seq, ",journal_checksum");
if (test_opt(sb, I_VERSION))
seq_puts(seq, ",i_version");
if (!test_opt(sb, DELALLOC) &&
!(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
* journal mode get enabled in different ways
* So just print the value even if we didn't specify it
*/
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
seq_puts(seq, ",data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
seq_puts(seq, ",data=ordered");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
seq_puts(seq, ",data=writeback");
if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
seq_printf(seq, ",inode_readahead_blks=%u",
sbi->s_inode_readahead_blks);
if (test_opt(sb, DATA_ERR_ABORT))
seq_puts(seq, ",data_err=abort");
if (test_opt(sb, NO_AUTO_DA_ALLOC))
seq_puts(seq, ",noauto_da_alloc");
if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
seq_puts(seq, ",discard");
if (test_opt(sb, NOLOAD))
seq_puts(seq, ",norecovery");
if (test_opt(sb, DIOREAD_NOLOCK))
seq_puts(seq, ",dioread_nolock");
if (test_opt(sb, BLOCK_VALIDITY) &&
!(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
seq_puts(seq, ",block_validity");
if (!test_opt(sb, INIT_INODE_TABLE))
seq_puts(seq, ",noinit_inode_table");
else if (sbi->s_li_wait_mult)
seq_printf(seq, ",init_inode_table=%u",
(unsigned) sbi->s_li_wait_mult);
ext4_show_quota_options(seq, sb);
return 0;
}
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(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_WAIT);
return try_to_free_buffers(page);
}
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
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,
char *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 const struct dquot_operations ext4_quota_operations = {
#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
#endif
.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,
};
static const struct quotactl_ops ext4_qctl_operations = {
.quota_on = ext4_quota_on,
.quota_off = ext4_quota_off,
.quota_sync = dquot_quota_sync,
.get_info = dquot_get_dqinfo,
.set_info = dquot_set_dqinfo,
.get_dqblk = dquot_get_dqblk,
.set_dqblk = dquot_set_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,
.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,
#endif
.bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct super_operations ext4_nojournal_sops = {
.alloc_inode = ext4_alloc_inode,
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
.evict_inode = ext4_evict_inode,
.write_super = ext4_write_super,
.put_super = ext4_put_super,
.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,
#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_oldalloc, Opt_orlov,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
Opt_journal_update, Opt_journal_dev,
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_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
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_inode_table, Opt_noinit_inode_table,
};
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_oldalloc, "oldalloc"},
{Opt_orlov, "orlov"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_noload, "noload"},
{Opt_noload, "norecovery"},
{Opt_nobh, "nobh"},
{Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_update, "journal=update"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_checksum, "journal_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_stripe, "stripe=%u"},
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{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_inode_table, "init_itable=%u"},
{Opt_init_inode_table, "init_itable"},
{Opt_noinit_inode_table, "noinit_itable"},
{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;
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 0;
}
qname = match_strdup(args);
if (!qname) {
ext4_msg(sb, KERN_ERR,
"Not enough memory for storing quotafile name");
return 0;
}
if (sbi->s_qf_names[qtype] &&
strcmp(sbi->s_qf_names[qtype], qname)) {
ext4_msg(sb, KERN_ERR,
"%s quota file already specified", QTYPE2NAME(qtype));
kfree(qname);
return 0;
}
sbi->s_qf_names[qtype] = qname;
if (strchr(sbi->s_qf_names[qtype], '/')) {
ext4_msg(sb, KERN_ERR,
"quotafile must be on filesystem root");
kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
return 0;
}
set_opt(sbi->s_mount_opt, QUOTA);
return 1;
}
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 0;
}
/*
* The space will be released later when all options are confirmed
* to be correct
*/
sbi->s_qf_names[qtype] = NULL;
return 1;
}
#endif
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
unsigned int *journal_ioprio,
ext4_fsblk_t *n_blocks_count, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *p;
substring_t args[MAX_OPT_ARGS];
int data_opt = 0;
int option;
#ifdef CONFIG_QUOTA
int qfmt;
#endif
if (!options)
return 1;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
/*
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
args[0].to = args[0].from = 0;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, MINIX_DF);
break;
case Opt_minix_df:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, MINIX_DF);
break;
case Opt_grpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
break;
case Opt_nogrpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, GRPID);
break;
case Opt_resuid:
if (match_int(&args[0], &option))
return 0;
sbi->s_resuid = option;
break;
case Opt_resgid:
if (match_int(&args[0], &option))
return 0;
sbi->s_resgid = option;
break;
case Opt_sb:
/* handled by get_sb_block() instead of here */
/* *sb_block = match_int(&args[0]); */
break;
case Opt_err_panic:
clear_opt(sbi->s_mount_opt, ERRORS_CONT);
clear_opt(sbi->s_mount_opt, ERRORS_RO);
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
break;
case Opt_err_ro:
clear_opt(sbi->s_mount_opt, ERRORS_CONT);
clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
set_opt(sbi->s_mount_opt, ERRORS_RO);
break;
case Opt_err_cont:
clear_opt(sbi->s_mount_opt, ERRORS_RO);
clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
set_opt(sbi->s_mount_opt, ERRORS_CONT);
break;
case Opt_nouid32:
set_opt(sbi->s_mount_opt, NO_UID32);
break;
case Opt_debug:
set_opt(sbi->s_mount_opt, DEBUG);
break;
case Opt_oldalloc:
set_opt(sbi->s_mount_opt, OLDALLOC);
break;
case Opt_orlov:
clear_opt(sbi->s_mount_opt, OLDALLOC);
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
set_opt(sbi->s_mount_opt, XATTR_USER);
break;
case Opt_nouser_xattr:
clear_opt(sbi->s_mount_opt, XATTR_USER);
break;
#else
case Opt_user_xattr:
case Opt_nouser_xattr:
ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
break;
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
case Opt_acl:
set_opt(sbi->s_mount_opt, POSIX_ACL);
break;
case Opt_noacl:
clear_opt(sbi->s_mount_opt, POSIX_ACL);
break;
#else
case Opt_acl:
case Opt_noacl:
ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
break;
#endif
case Opt_journal_update:
/* @@@ FIXME */
/* Eventually we will want to be able to create
a journal file here. For now, only allow the
user to specify an existing inode to be the
journal file. */
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return 0;
}
set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
break;
case Opt_journal_dev:
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return 0;
}
if (match_int(&args[0], &option))
return 0;
*journal_devnum = option;
break;
case Opt_journal_checksum:
set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
break;
case Opt_journal_async_commit:
set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
break;
case Opt_noload:
set_opt(sbi->s_mount_opt, NOLOAD);
break;
case Opt_commit:
if (match_int(&args[0], &option))
return 0;
if (option < 0)
return 0;
if (option == 0)
option = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * option;
break;
case Opt_max_batch_time:
if (match_int(&args[0], &option))
return 0;
if (option < 0)
return 0;
if (option == 0)
option = EXT4_DEF_MAX_BATCH_TIME;
sbi->s_max_batch_time = option;
break;
case Opt_min_batch_time:
if (match_int(&args[0], &option))
return 0;
if (option < 0)
return 0;
sbi->s_min_batch_time = option;
break;
case Opt_data_journal:
data_opt = EXT4_MOUNT_JOURNAL_DATA;
goto datacheck;
case Opt_data_ordered:
data_opt = EXT4_MOUNT_ORDERED_DATA;
goto datacheck;
case Opt_data_writeback:
data_opt = EXT4_MOUNT_WRITEBACK_DATA;
datacheck:
if (is_remount) {
if (test_opt(sb, DATA_FLAGS) != data_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return 0;
}
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
sbi->s_mount_opt |= data_opt;
}
break;
case Opt_data_err_abort:
set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
break;
case Opt_data_err_ignore:
clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
if (!set_qf_name(sb, USRQUOTA, &args[0]))
return 0;
break;
case Opt_grpjquota:
if (!set_qf_name(sb, GRPQUOTA, &args[0]))
return 0;
break;
case Opt_offusrjquota:
if (!clear_qf_name(sb, USRQUOTA))
return 0;
break;
case Opt_offgrpjquota:
if (!clear_qf_name(sb, GRPQUOTA))
return 0;
break;
case Opt_jqfmt_vfsold:
qfmt = QFMT_VFS_OLD;
goto set_qf_format;
case Opt_jqfmt_vfsv0:
qfmt = QFMT_VFS_V0;
goto set_qf_format;
case Opt_jqfmt_vfsv1:
qfmt = QFMT_VFS_V1;
set_qf_format:
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
ext4_msg(sb, KERN_ERR, "Cannot change "
"journaled quota options when "
"quota turned on");
return 0;
}
sbi->s_jquota_fmt = qfmt;
break;
case Opt_quota:
case Opt_usrquota:
set_opt(sbi->s_mount_opt, QUOTA);
set_opt(sbi->s_mount_opt, USRQUOTA);
break;
case Opt_grpquota:
set_opt(sbi->s_mount_opt, QUOTA);
set_opt(sbi->s_mount_opt, GRPQUOTA);
break;
case Opt_noquota:
if (sb_any_quota_loaded(sb)) {
ext4_msg(sb, KERN_ERR, "Cannot change quota "
"options when quota turned on");
return 0;
}
clear_opt(sbi->s_mount_opt, QUOTA);
clear_opt(sbi->s_mount_opt, USRQUOTA);
clear_opt(sbi->s_mount_opt, GRPQUOTA);
break;
#else
case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
ext4_msg(sb, KERN_ERR,
"quota options not supported");
break;
case Opt_usrjquota:
case Opt_grpjquota:
case Opt_offusrjquota:
case Opt_offgrpjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
case Opt_jqfmt_vfsv1:
ext4_msg(sb, KERN_ERR,
"journaled quota options not supported");
break;
case Opt_noquota:
break;
#endif
case Opt_abort:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
break;
case Opt_nobarrier:
clear_opt(sbi->s_mount_opt, BARRIER);
break;
case Opt_barrier:
if (args[0].from) {
if (match_int(&args[0], &option))
return 0;
} else
option = 1; /* No argument, default to 1 */
if (option)
set_opt(sbi->s_mount_opt, BARRIER);
else
clear_opt(sbi->s_mount_opt, BARRIER);
break;
case Opt_ignore:
break;
case Opt_resize:
if (!is_remount) {
ext4_msg(sb, KERN_ERR,
"resize option only available "
"for remount");
return 0;
}
if (match_int(&args[0], &option) != 0)
return 0;
*n_blocks_count = option;
break;
case Opt_nobh:
ext4_msg(sb, KERN_WARNING,
"Ignoring deprecated nobh option");
break;
case Opt_bh:
ext4_msg(sb, KERN_WARNING,
"Ignoring deprecated bh option");
break;
case Opt_i_version:
set_opt(sbi->s_mount_opt, I_VERSION);
sb->s_flags |= MS_I_VERSION;
break;
case Opt_nodelalloc:
clear_opt(sbi->s_mount_opt, DELALLOC);
break;
case Opt_stripe:
if (match_int(&args[0], &option))
return 0;
if (option < 0)
return 0;
sbi->s_stripe = option;
break;
case Opt_delalloc:
set_opt(sbi->s_mount_opt, DELALLOC);
break;
case Opt_block_validity:
set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
break;
case Opt_noblock_validity:
clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
break;
case Opt_inode_readahead_blks:
if (match_int(&args[0], &option))
return 0;
if (option < 0 || option > (1 << 30))
return 0;
if (!is_power_of_2(option)) {
ext4_msg(sb, KERN_ERR,
"EXT4-fs: inode_readahead_blks"
" must be a power of 2");
return 0;
}
sbi->s_inode_readahead_blks = option;
break;
case Opt_journal_ioprio:
if (match_int(&args[0], &option))
return 0;
if (option < 0 || option > 7)
break;
*journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
option);
break;
case Opt_noauto_da_alloc:
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
case Opt_auto_da_alloc:
if (args[0].from) {
if (match_int(&args[0], &option))
return 0;
} else
option = 1; /* No argument, default to 1 */
if (option)
clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
else
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
case Opt_discard:
set_opt(sbi->s_mount_opt, DISCARD);
break;
case Opt_nodiscard:
clear_opt(sbi->s_mount_opt, DISCARD);
break;
case Opt_dioread_nolock:
set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
break;
case Opt_dioread_lock:
clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
break;
case Opt_init_inode_table:
set_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
if (args[0].from) {
if (match_int(&args[0], &option))
return 0;
} else
option = EXT4_DEF_LI_WAIT_MULT;
if (option < 0)
return 0;
sbi->s_li_wait_mult = option;
break;
case Opt_noinit_inode_table:
clear_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
"or missing value", p);
return 0;
}
}
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sbi->s_mount_opt, USRQUOTA);
if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
clear_opt(sbi->s_mount_opt, 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;
}
} else {
if (sbi->s_jquota_fmt) {
ext4_msg(sb, KERN_ERR, "journaled quota format "
"specified with no journaling "
"enabled");
return 0;
}
}
#endif
return 1;
}
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)
return res;
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_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
return res;
}
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_count;
ext4_group_t flex_group;
int groups_per_flex = 0;
size_t size;
int i;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
groups_per_flex = 1 << sbi->s_log_groups_per_flex;
if (groups_per_flex < 2) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
/* We allocate both existing and potentially added groups */
flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
size = flex_group_count * sizeof(struct flex_groups);
sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
sbi->s_flex_groups = vmalloc(size);
if (sbi->s_flex_groups)
memset(sbi->s_flex_groups, 0, size);
}
if (sbi->s_flex_groups == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory for "
"%u flex groups", flex_group_count);
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);
atomic_add(ext4_free_blks_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_blocks);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
return 1;
failed:
return 0;
}
__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
struct ext4_group_desc *gdp)
{
__u16 crc = 0;
if (sbi->s_es->s_feature_ro_compat &
cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
int offset = offsetof(struct ext4_group_desc, bg_checksum);
__le32 le_group = cpu_to_le32(block_group);
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 ((sbi->s_es->s_feature_incompat &
cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
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);
}
return cpu_to_le16(crc);
}
int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
struct ext4_group_desc *gdp)
{
if ((sbi->s_es->s_feature_ro_compat &
cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) &&
(gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp)))
return 0;
return 1;
}
/* 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_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
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(sbi, 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(sbi, 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;
ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
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;
}
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
if (es->s_last_orphan)
jbd_debug(1, "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 < 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) {
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);
ext4_truncate(inode);
nr_truncates++;
} else {
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 < 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.
*
* 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 */
res = 1LL << 32;
res <<= blkbits;
res -= 1;
/* 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_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
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;
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);
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
return sbi->s_stripe;
if (stripe_width <= sbi->s_blocks_per_group)
return stripe_width;
if (stride <= sbi->s_blocks_per_group)
return stride;
return 0;
}
/* sysfs supprt */
struct ext4_attr {
struct attribute attr;
ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
const char *, size_t);
int offset;
};
static int parse_strtoul(const char *buf,
unsigned long max, unsigned long *value)
{
char *endp;
*value = simple_strtoul(skip_spaces(buf), &endp, 0);
endp = skip_spaces(endp);
if (*endp || *value > max)
return -EINVAL;
return 0;
}
static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
struct ext4_sb_info *sbi,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%llu\n",
(s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
}
static ssize_t session_write_kbytes_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
if (!sb->s_bdev->bd_part)
return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%lu\n",
(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
sbi->s_sectors_written_start) >> 1);
}
static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
if (!sb->s_bdev->bd_part)
return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
unsigned long t;
if (parse_strtoul(buf, 0x40000000, &t))
return -EINVAL;
if (!is_power_of_2(t))
return -EINVAL;
sbi->s_inode_readahead_blks = t;
return count;
}
static ssize_t sbi_ui_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}
static ssize_t sbi_ui_store(struct ext4_attr *a,
struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
unsigned long t;
if (parse_strtoul(buf, 0xffffffff, &t))
return -EINVAL;
*ui = t;
return count;
}
#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.show = _show, \
.store = _store, \
.offset = offsetof(struct ext4_sb_info, _elname), \
}
#define EXT4_ATTR(name, mode, show, store) \
static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
#define EXT4_RW_ATTR_SBI_UI(name, elname) \
EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
#define ATTR_LIST(name) &ext4_attr_##name.attr
EXT4_RO_ATTR(delayed_allocation_blocks);
EXT4_RO_ATTR(session_write_kbytes);
EXT4_RO_ATTR(lifetime_write_kbytes);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
inode_readahead_blks_store, s_inode_readahead_blks);
EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
ATTR_LIST(mb_max_to_scan),
ATTR_LIST(mb_min_to_scan),
ATTR_LIST(mb_order2_req),
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(max_writeback_mb_bump),
NULL,
};
static ssize_t ext4_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
return a->show ? a->show(a, sbi, buf) : 0;
}
static ssize_t ext4_attr_store(struct kobject *kobj,
struct attribute *attr,
const char *buf, size_t len)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
return a->store ? a->store(a, sbi, buf, len) : 0;
}
static void ext4_sb_release(struct kobject *kobj)
{
struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
s_kobj);
complete(&sbi->s_kobj_unregister);
}
static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
};
static struct kobj_type ext4_ktype = {
.default_attrs = ext4_attrs,
.sysfs_ops = &ext4_attr_ops,
.release = ext4_sb_release,
};
/*
* 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_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) {
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;
/* Check that feature set is OK for a read-write mount */
if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
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_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
if (sizeof(blkcnt_t) < sizeof(u64)) {
ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
"cannot be mounted RDWR without "
"CONFIG_LBDAF");
return 0;
}
}
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)
ext4_msg(sb, KERN_NOTICE, "error count: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): initial error at %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 %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 */
}
static void ext4_lazyinode_timeout(unsigned long data)
{
struct task_struct *p = (struct task_struct *)data;
wake_up_process(p);
}
/* 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;
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;
if (elr->lr_sbi->s_li_wait_mult)
timeout *= elr->lr_sbi->s_li_wait_mult;
else
timeout *= 20;
elr->lr_timeout = timeout;
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
return ret;
}
/*
* Remove lr_request from the list_request and free the
* request tructure. 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)
{
struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
if (!ext4_li_info)
return;
mutex_lock(&ext4_li_info->li_list_mtx);
ext4_remove_li_request(elr);
mutex_unlock(&ext4_li_info->li_list_mtx);
}
/*
* 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;
DEFINE_WAIT(wait);
int ret;
BUG_ON(NULL == eli);
eli->li_timer.data = (unsigned long)current;
eli->li_timer.function = ext4_lazyinode_timeout;
eli->li_task = current;
wake_up(&eli->li_wait_task);
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))
ret = ext4_run_li_request(elr);
if (ret) {
ret = 0;
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);
if (freezing(current))
refrigerator();
if (time_after_eq(jiffies, next_wakeup)) {
cond_resched();
continue;
}
eli->li_timer.expires = next_wakeup;
add_timer(&eli->li_timer);
prepare_to_wait(&eli->li_wait_daemon, &wait,
TASK_INTERRUPTIBLE);
if (time_before(jiffies, next_wakeup))
schedule();
finish_wait(&eli->li_wait_daemon, &wait);
}
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);
del_timer_sync(&ext4_li_info->li_timer);
eli->li_task = NULL;
wake_up(&eli->li_wait_task);
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);
if (list_empty(&ext4_li_info->li_request_list))
return;
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)
{
struct task_struct *t;
t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
if (IS_ERR(t)) {
int err = PTR_ERR(t);
ext4_clear_request_list();
del_timer_sync(&ext4_li_info->li_timer);
kfree(ext4_li_info);
ext4_li_info = NULL;
printk(KERN_CRIT "EXT4: error %d creating inode table "
"initialization thread\n",
err);
return err;
}
ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
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;
eli->li_task = NULL;
INIT_LIST_HEAD(&eli->li_request_list);
mutex_init(&eli->li_list_mtx);
init_waitqueue_head(&eli->li_wait_daemon);
init_waitqueue_head(&eli->li_wait_task);
init_timer(&eli->li_timer);
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;
unsigned long rnd;
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.
*/
get_random_bytes(&rnd, sizeof(rnd));
elr->lr_next_sched = jiffies + (unsigned long)rnd %
(EXT4_DEF_LI_MAX_START_DELAY * HZ);
return elr;
}
static 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;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
int ret = 0;
if (sbi->s_li_request != NULL)
goto out;
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
!test_opt(sb, INIT_INODE_TABLE)) {
sbi->s_li_request = NULL;
goto out;
}
if (first_not_zeroed == ngroups) {
sbi->s_li_request = NULL;
goto out;
}
elr = ext4_li_request_new(sb, first_not_zeroed);
if (!elr) {
ret = -ENOMEM;
goto out;
}
mutex_lock(&ext4_li_mtx);
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;
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
ret = ext4_run_lazyinit_thread();
if (ret)
goto out;
}
mutex_unlock(&ext4_li_mtx);
out:
if (ret) {
mutex_unlock(&ext4_li_mtx);
kfree(elr);
}
return ret;
}
/*
* We do not need to lock anything since this is called on
* module unload.
*/
static void ext4_destroy_lazyinit_thread(void)
{
/*
* If thread exited earlier
* there's nothing to be done.
*/
if (!ext4_li_info)
return;
ext4_clear_request_list();
while (ext4_li_info->li_task) {
wake_up(&ext4_li_info->li_wait_daemon);
wait_event(ext4_li_info->li_wait_task,
ext4_li_info->li_task == NULL);
}
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
{
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
struct ext4_sb_info *sbi;
ext4_fsblk_t block;
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
unsigned long offset = 0;
unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
char *cp;
const char *descr;
int ret = -ENOMEM;
int blocksize;
unsigned int db_count;
unsigned int i;
int needs_recovery, has_huge_files;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
ext4_group_t first_not_zeroed;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
goto out_free_orig;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock) {
kfree(sbi);
goto out_free_orig;
}
sb->s_fs_info = sbi;
sbi->s_mount_opt = 0;
sbi->s_resuid = EXT4_DEF_RESUID;
sbi->s_resgid = EXT4_DEF_RESGID;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sb_block = sb_block;
if (sb->s_bdev->bd_part)
sbi->s_sectors_written_start =
part_stat_read(sb->s_bdev->bd_part, sectors[1]);
unlock_kernel();
/* Cleanup superblock name */
for (cp = sb->s_id; (cp = strchr(cp, '/'));)
*cp = '!';
ret = -EINVAL;
blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
if (!blocksize) {
ext4_msg(sb, KERN_ERR, "unable to set blocksize");
goto out_fail;
}
/*
* The ext4 superblock will not be buffer aligned for other than 1kB
* block sizes. We need to calculate the offset from buffer start.
*/
if (blocksize != EXT4_MIN_BLOCK_SIZE) {
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
} else {
logical_sb_block = sb_block;
}
if (!(bh = sb_bread(sb, logical_sb_block))) {
ext4_msg(sb, KERN_ERR, "unable to read superblock");
goto out_fail;
}
/*
* Note: s_es must be initialized as soon as possible because
* some ext4 macro-instructions depend on its value
*/
es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
sbi->s_es = es;
sb->s_magic = le16_to_cpu(es->s_magic);
if (sb->s_magic != EXT4_SUPER_MAGIC)
goto cantfind_ext4;
sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written);
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
set_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
if (def_mount_opts & EXT4_DEFM_DEBUG)
set_opt(sbi->s_mount_opt, DEBUG);
if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
"2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
}
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT4_FS_XATTR
if (def_mount_opts & EXT4_DEFM_XATTR_USER)
set_opt(sbi->s_mount_opt, XATTR_USER);
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (def_mount_opts & EXT4_DEFM_ACL)
set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sbi->s_mount_opt, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
set_opt(sbi->s_mount_opt, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
set_opt(sbi->s_mount_opt, ERRORS_CONT);
else
set_opt(sbi->s_mount_opt, ERRORS_RO);
if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
if (def_mount_opts & EXT4_DEFM_DISCARD)
set_opt(sbi->s_mount_opt, DISCARD);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
set_opt(sbi->s_mount_opt, BARRIER);
/*
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
if (!IS_EXT3_SB(sb) &&
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sbi->s_mount_opt, DELALLOC);
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
&journal_devnum, &journal_ioprio, NULL, 0)) {
ext4_msg(sb, KERN_WARNING,
"failed to parse options in superblock: %s",
sbi->s_es->s_mount_opts);
}
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, NULL, 0))
goto failed_mount;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
ext4_msg(sb, KERN_WARNING,
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
/*
* Check feature flags regardless of the revision level, since we
* previously didn't change the revision level when setting the flags,
* so there is a chance incompat flags are set on a rev 0 filesystem.
*/
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
"Unsupported filesystem blocksize %d", blocksize);
goto failed_mount;
}
if (sb->s_blocksize != blocksize) {
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
goto failed_mount;
}
brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = sb_bread(sb, logical_sb_block);
if (!bh) {
ext4_msg(sb, KERN_ERR,
"Can't read superblock on 2nd try");
goto failed_mount;
}
es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
ext4_msg(sb, KERN_ERR,
"Magic mismatch, very weird!");
goto failed_mount;
}
}
has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
has_huge_files);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
} else {
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
(!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
ext4_msg(sb, KERN_ERR,
"unsupported inode size: %d",
sbi->s_inode_size);
goto failed_mount;
}
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
}
sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
!is_power_of_2(sbi->s_desc_size)) {
ext4_msg(sb, KERN_ERR,
"unsupported descriptor size %lu",
sbi->s_desc_size);
goto failed_mount;
}
} else
sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
goto cantfind_ext4;
sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0)
goto cantfind_ext4;
sbi->s_itb_per_group = sbi->s_inodes_per_group /
sbi->s_inodes_per_block;
sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
sbi->s_sbh = bh;
sbi->s_mount_state = le16_to_cpu(es->s_state);
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
i = le32_to_cpu(es->s_flags);
if (i & EXT2_FLAGS_UNSIGNED_HASH)
sbi->s_hash_unsigned = 3;
else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
sbi->s_hash_unsigned = 3;
#else
es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
sb->s_dirt = 1;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#blocks per group too big: %lu",
sbi->s_blocks_per_group);
goto failed_mount;
}
if (sbi->s_inodes_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#inodes per group too big: %lu",
sbi->s_inodes_per_group);
goto failed_mount;
}
/*
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
*/
if ((ext4_blocks_count(es) >
(sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) ||
(ext4_blocks_count(es) >
(pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) {
ext4_msg(sb, KERN_ERR, "filesystem"
" too large to mount safely on this system");
if (sizeof(sector_t) < 8)
ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
ret = -EFBIG;
goto failed_mount;
}
if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext4;
/* check blocks count against device size */
blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
if (blocks_count && ext4_blocks_count(es) > blocks_count) {
ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
"exceeds size of device (%llu blocks)",
ext4_blocks_count(es), blocks_count);
goto failed_mount;
}
/*
* It makes no sense for the first data block to be beyond the end
* of the filesystem.
*/
if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
ext4_msg(sb, KERN_WARNING, "bad geometry: first data"
"block %u is beyond end of filesystem (%llu)",
le32_to_cpu(es->s_first_data_block),
ext4_blocks_count(es));
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
"(block count %llu, first data block %u, "
"blocks per group %lu)", sbi->s_groups_count,
ext4_blocks_count(es),
le32_to_cpu(es->s_first_data_block),
EXT4_BLOCKS_PER_GROUP(sb));
goto failed_mount;
}
sbi->s_groups_count = blocks_count;
sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
goto failed_mount;
}
#ifdef CONFIG_PROC_FS
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
#endif
bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logical_sb_block, i);
sbi->s_group_desc[i] = sb_bread(sb, block);
if (!sbi->s_group_desc[i]) {
ext4_msg(sb, KERN_ERR,
"can't read group descriptor %d", i);
db_count = i;
goto failed_mount2;
}
}
if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
goto failed_mount2;
}
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
if (!ext4_fill_flex_info(sb)) {
ext4_msg(sb, KERN_ERR,
"unable to initialize "
"flex_bg meta info!");
goto failed_mount2;
}
sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
/*
* set up enough so that it can read an inode
*/
if (!test_opt(sb, NOLOAD) &&
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
sb->s_op = &ext4_sops;
else
sb->s_op = &ext4_nojournal_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
sb->s_qcop = &ext4_qctl_operations;
sb->dq_op = &ext4_quota_operations;
#endif
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
mutex_init(&sbi->s_resize_lock);
sb->s_root = NULL;
needs_recovery = (es->s_last_orphan != 0 ||
EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_RECOVER));
/*
* The first inode we look at is the journal inode. Don't try
* root first: it may be modified in the journal!
*/
if (!test_opt(sb, NOLOAD) &&
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3;
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
goto failed_mount_wq;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
}
if (ext4_blocks_count(es) > 0xffffffffULL &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
jbd2_journal_set_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else if (test_opt(sb, JOURNAL_CHECKSUM)) {
jbd2_journal_set_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else {
jbd2_journal_clear_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
}
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
case 0:
/* No mode set, assume a default based on the journal
* capabilities: ORDERED_DATA if the journal can
* cope, else JOURNAL_DATA
*/
if (jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
set_opt(sbi->s_mount_opt, ORDERED_DATA);
else
set_opt(sbi->s_mount_opt, JOURNAL_DATA);
break;
case EXT4_MOUNT_ORDERED_DATA:
case EXT4_MOUNT_WRITEBACK_DATA:
if (!jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
goto failed_mount_wq;
}
default:
break;
}
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
no_journal:
err = percpu_counter_init(&sbi->s_freeblocks_counter,
ext4_count_free_blocks(sb));
if (!err)
err = percpu_counter_init(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
if (!err)
err = percpu_counter_init(&sbi->s_dirs_counter,
ext4_count_dirs(sb));
if (!err)
err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount_wq;
}
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
goto failed_mount_wq;
}
/*
* The jbd2_journal_load will have done any necessary log recovery,
* so we can safely mount the rest of the filesystem now.
*/
root = ext4_iget(sb, EXT4_ROOT_INO);
if (IS_ERR(root)) {
ext4_msg(sb, KERN_ERR, "get root inode failed");
ret = PTR_ERR(root);
goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
goto failed_mount4;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
ext4_msg(sb, KERN_ERR, "get root dentry failed");
iput(root);
ret = -ENOMEM;
goto failed_mount4;
}
ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY);
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) {
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_want_extra_isize))
sbi->s_want_extra_isize =
le16_to_cpu(es->s_want_extra_isize);
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_min_extra_isize))
sbi->s_want_extra_isize =
le16_to_cpu(es->s_min_extra_isize);
}
}
/* Check if enough inode space is available */
if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
sbi->s_inode_size) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
ext4_msg(sb, KERN_INFO, "required extra inode space not"
"available");
}
if (test_opt(sb, DELALLOC) &&
(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
"requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
"option - requested data journaling mode");
clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
}
if (sb->s_blocksize < PAGE_SIZE) {
ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
"option - block size is too small");
clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
}
}
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
"zone (%d)", err);
goto failed_mount4;
}
ext4_ext_init(sb);
err = ext4_mb_init(sb, needs_recovery);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
goto failed_mount4;
}
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
goto failed_mount4;
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
"%s", sb->s_id);
if (err) {
ext4_mb_release(sb);
ext4_ext_release(sb);
goto failed_mount4;
};
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
if (needs_recovery) {
ext4_msg(sb, KERN_INFO, "recovery complete");
ext4_mark_recovery_complete(sb, es);
}
if (EXT4_SB(sb)->s_journal) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
descr = " journalled data mode";
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
descr = " ordered data mode";
else
descr = " writeback data mode";
} else
descr = "out journal";
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
"Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
init_timer(&sbi->s_err_report);
sbi->s_err_report.function = print_daily_error_info;
sbi->s_err_report.data = (unsigned long) sb;
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
lock_kernel();
kfree(orig_data);
return 0;
cantfind_ext4:
if (!silent)
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
failed_mount_wq:
ext4_release_system_zone(sb);
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
vfree(sbi->s_flex_groups);
else
kfree(sbi->s_flex_groups);
}
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
failed_mount:
if (sbi->s_proc) {
remove_proc_entry(sb->s_id, ext4_proc_root);
}
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
ext4_blkdev_remove(sbi);
brelse(bh);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
out_free_orig:
kfree(orig_data);
return ret;
}
/*
* Setup any per-fs journal parameters now. We'll do this both on
* initial mount, once the journal has been initialised but before we've
* done any recovery; and again on any subsequent remount.
*/
static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
journal->j_commit_interval = sbi->s_commit_interval;
journal->j_min_batch_time = sbi->s_min_batch_time;
journal->j_max_batch_time = sbi->s_max_batch_time;
write_lock(&journal->j_state_lock);
if (test_opt(sb, BARRIER))
journal->j_flags |= JBD2_BARRIER;
else
journal->j_flags &= ~JBD2_BARRIER;
if (test_opt(sb, DATA_ERR_ABORT))
journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
else
journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
write_unlock(&journal->j_state_lock);
}
static journal_t *ext4_get_journal(struct super_block *sb,
unsigned int journal_inum)
{
struct inode *journal_inode;
journal_t *journal;
BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
/* First, test for the existence of a valid inode on disk. Bad
* things happen if we iget() an unused inode, as the subsequent
* iput() will try to delete it. */
journal_inode = ext4_iget(sb, journal_inum);
if (IS_ERR(journal_inode)) {
ext4_msg(sb, KERN_ERR, "no journal found");
return NULL;
}
if (!journal_inode->i_nlink) {
make_bad_inode(journal_inode);
iput(journal_inode);
ext4_msg(sb, KERN_ERR, "journal inode is deleted");
return NULL;
}
jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
journal_inode, journal_inode->i_size);
if (!S_ISREG(journal_inode->i_mode)) {
ext4_msg(sb, KERN_ERR, "invalid journal inode");
iput(journal_inode);
return NULL;
}
journal = jbd2_journal_init_inode(journal_inode);
if (!journal) {
ext4_msg(sb, KERN_ERR, "Could not load journal inode");
iput(journal_inode);
return NULL;
}
journal->j_private = sb;
ext4_init_journal_params(sb, journal);
return journal;
}
static journal_t *ext4_get_dev_journal(struct super_block *sb,
dev_t j_dev)
{
struct buffer_head *bh;
journal_t *journal;
ext4_fsblk_t start;
ext4_fsblk_t len;
int hblock, blocksize;
ext4_fsblk_t sb_block;
unsigned long offset;
struct ext4_super_block *es;
struct block_device *bdev;
BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
bdev = ext4_blkdev_get(j_dev, sb);
if (bdev == NULL)
return NULL;
if (bd_claim(bdev, sb)) {
ext4_msg(sb, KERN_ERR,
"failed to claim external journal device");
blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
return NULL;
}
blocksize = sb->s_blocksize;
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
ext4_msg(sb, KERN_ERR,
"blocksize too small for journal device");
goto out_bdev;
}
sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
offset = EXT4_MIN_BLOCK_SIZE % blocksize;
set_blocksize(bdev, blocksize);
if (!(bh = __bread(bdev, sb_block, blocksize))) {
ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
"external journal");
goto out_bdev;
}
es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
ext4_msg(sb, KERN_ERR, "external journal has "
"bad superblock");
brelse(bh);
goto out_bdev;
}
if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
ext4_msg(sb, KERN_ERR, "journal UUID does not match");
brelse(bh);
goto out_bdev;
}
len = ext4_blocks_count(es);
start = sb_block + 1;
brelse(bh); /* we're done with the superblock */
journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
start, len, blocksize);
if (!journal) {
ext4_msg(sb, KERN_ERR, "failed to create device journal");
goto out_bdev;
}
journal->j_private = sb;
ll_rw_block(READ, 1, &journal->j_sb_buffer);
wait_on_buffer(journal->j_sb_buffer);
if (!buffer_uptodate(journal->j_sb_buffer)) {
ext4_msg(sb, KERN_ERR, "I/O error on journal device");
goto out_journal;
}
if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
ext4_msg(sb, KERN_ERR, "External journal has more than one "
"user (unsupported) - %d",
be32_to_cpu(journal->j_superblock->s_nr_users));
goto out_journal;
}
EXT4_SB(sb)->journal_bdev = bdev;
ext4_init_journal_params(sb, journal);
return journal;
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
ext4_blkdev_put(bdev);
return NULL;
}
static int ext4_load_journal(struct super_block *sb,
struct ext4_super_block *es,
unsigned long journal_devnum)
{
journal_t *journal;
unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
dev_t journal_dev;
int err = 0;
int really_read_only;
BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
ext4_msg(sb, KERN_INFO, "external journal device major/minor "
"numbers have changed");
journal_dev = new_decode_dev(journal_devnum);
} else
journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
really_read_only = bdev_read_only(sb->s_bdev);
/*
* Are we loading a blank journal or performing recovery after a
* crash? For recovery, we need to check in advance whether we
* can get read-write access to the device.
*/
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
if (sb->s_flags & MS_RDONLY) {
ext4_msg(sb, KERN_INFO, "INFO: recovery "
"required on readonly filesystem");
if (really_read_only) {
ext4_msg(sb, KERN_ERR, "write access "
"unavailable, cannot proceed");
return -EROFS;
}
ext4_msg(sb, KERN_INFO, "write access will "
"be enabled during recovery");
}
}
if (journal_inum && journal_dev) {
ext4_msg(sb, KERN_ERR, "filesystem has both journal "
"and inode journals!");
return -EINVAL;
}
if (journal_inum) {
if (!(journal = ext4_get_journal(sb, journal_inum)))
return -EINVAL;
} else {
if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
return -EINVAL;
}
if (!(journal->j_flags & JBD2_BARRIER))
ext4_msg(sb, KERN_INFO, "barriers disabled");
if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
err = jbd2_journal_update_format(journal);
if (err) {
ext4_msg(sb, KERN_ERR, "error updating journal");
jbd2_journal_destroy(journal);
return err;
}
}
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
err = jbd2_journal_wipe(journal, !really_read_only);
if (!err) {
char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
if (save)
memcpy(save, ((char *) es) +
EXT4_S_ERR_START, EXT4_S_ERR_LEN);
err = jbd2_journal_load(journal);
if (save)
memcpy(((char *) es) + EXT4_S_ERR_START,
save, EXT4_S_ERR_LEN);
kfree(save);
}
if (err) {
ext4_msg(sb, KERN_ERR, "error loading journal");
jbd2_journal_destroy(journal);
return err;
}
EXT4_SB(sb)->s_journal = journal;
ext4_clear_journal_err(sb, es);
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
ext4_commit_super(sb, 1);
}
return 0;
}
static int ext4_commit_super(struct super_block *sb, int sync)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
if (!sbh)
return error;
if (buffer_write_io_error(sbh)) {
/*
* Oh, dear. A previous attempt to write the
* superblock failed. This could happen because the
* USB device was yanked out. Or it could happen to
* be a transient write error and maybe the block will
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
ext4_msg(sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
* write time when we are mounting the root file system
* read/only but we need to replay the journal; at that point,
* for people who are east of GMT and who make their clock
* tick in localtime for Windows bug-for-bug compatibility,
* the clock is set in the future, and this will cause e2fsck
* to complain and force a full file system check.
*/
if (!(sb->s_flags & MS_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
if (sb->s_bdev->bd_part)
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
else
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeblocks_counter));
es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
sb->s_dirt = 0;
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
if (sync) {
error = sync_dirty_buffer(sbh);
if (error)
return error;
error = buffer_write_io_error(sbh);
if (error) {
ext4_msg(sb, KERN_ERR, "I/O error while writing "
"superblock");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
}
return error;
}
/*
* Have we just finished recovery? If so, and if we are mounting (or
* remounting) the filesystem readonly, then we will end up with a
* consistent fs on disk. Record that fact.
*/
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
BUG_ON(journal != NULL);
return;
}
jbd2_journal_lock_updates(journal);
if (jbd2_journal_flush(journal) < 0)
goto out;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
sb->s_flags & MS_RDONLY) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
}
out:
jbd2_journal_unlock_updates(journal);
}
/*
* If we are mounting (or read-write remounting) a filesystem whose journal
* has recorded an error from a previous lifetime, move that error to the
* main filesystem now.
*/
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es)
{
journal_t *journal;
int j_errno;
const char *errstr;
BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
journal = EXT4_SB(sb)->s_journal;
/*
* Now check for any error status which may have been recorded in the
* journal by a prior ext4_error() or ext4_abort()
*/
j_errno = jbd2_journal_errno(journal);
if (j_errno) {
char nbuf[16];
errstr = ext4_decode_error(sb, j_errno, nbuf);
ext4_warning(sb, "Filesystem error recorded "
"from previous mount: %s", errstr);
ext4_warning(sb, "Marking fs in need of filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, 1);
jbd2_journal_clear_err(journal);
}
}
/*
* Force the running and committing transactions to commit,
* and wait on the commit.
*/
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
int ret = 0;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
if (journal) {
vfs_check_frozen(sb, SB_FREEZE_TRANS);
ret = ext4_journal_force_commit(journal);
}
return ret;
}
static void ext4_write_super(struct super_block *sb)
{
lock_super(sb);
ext4_commit_super(sb, 1);
unlock_super(sb);
}
static int ext4_sync_fs(struct super_block *sb, int wait)
{
int ret = 0;
tid_t target;
struct ext4_sb_info *sbi = EXT4_SB(sb);
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->dio_unwritten_wq);
if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
jbd2_log_wait_commit(sbi->s_journal, target);
}
return ret;
}
/*
* LVM calls this function before a (read-only) snapshot is created. This
* gives us a chance to flush the journal completely and mark the fs clean.
*/
static int ext4_freeze(struct super_block *sb)
{
int error = 0;
journal_t *journal;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
/* Now we set up the journal barrier. */
jbd2_journal_lock_updates(journal);
/*
* Don't clear the needs_recovery flag if we failed to flush
* the journal.
*/
error = jbd2_journal_flush(journal);
if (error < 0)
goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
out:
/* we rely on s_frozen to stop further updates */
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return error;
}
/*
* Called by LVM after the snapshot is done. We need to reset the RECOVER
* flag here, even though the filesystem is not technically dirty yet.
*/
static int ext4_unfreeze(struct super_block *sb)
{
if (sb->s_flags & MS_RDONLY)
return 0;
lock_super(sb);
/* Reset the needs_recovery flag before the fs is unlocked. */
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
unlock_super(sb);
return 0;
}
static int ext4_remount(struct super_block *sb, int *flags, char *data)
{
struct ext4_super_block *es;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t n_blocks_count = 0;
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
lock_kernel();
/* Store the original options */
lock_super(sb);
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
old_opts.s_min_batch_time = sbi->s_min_batch_time;
old_opts.s_max_batch_time = sbi->s_max_batch_time;
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
old_opts.s_qf_names[i] = sbi->s_qf_names[i];
#endif
if (sbi->s_journal && sbi->s_journal->j_task->io_context)
journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
/*
* Allow the "check" option to be passed as a remount option.
*/
if (!parse_options(data, sb, NULL, &journal_ioprio,
&n_blocks_count, 1)) {
err = -EINVAL;
goto restore_opts;
}
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
es = sbi->s_es;
if (sbi->s_journal) {
ext4_init_journal_params(sb, sbi->s_journal);
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
}
if (*flags & MS_RDONLY) {
err = dquot_suspend(sb, -1);
if (err < 0)
goto restore_opts;
/*
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
*/
sb->s_flags |= MS_RDONLY;
/*
* OK, test if we are remounting a valid rw partition
* readonly, and if so set the rdonly flag and then
* mark the partition as valid again.
*/
if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) &&
(sbi->s_mount_state & EXT4_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
} else {
/* Make sure we can mount this feature set readwrite */
if (!ext4_feature_set_ok(sb, 0)) {
err = -EROFS;
goto restore_opts;
}
/*
* Make sure the group descriptor checksums
* are sane. If they aren't, refuse to remount r/w.
*/
for (g = 0; g < sbi->s_groups_count; g++) {
struct ext4_group_desc *gdp =
ext4_get_group_desc(sb, g, NULL);
if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
ext4_msg(sb, KERN_ERR,
"ext4_remount: Checksum for group %u failed (%u!=%u)",
g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
err = -EINVAL;
goto restore_opts;
}
}
/*
* If we have an unprocessed orphan list hanging
* around from a previously readonly bdev mount,
* require a full umount/remount for now.
*/
if (es->s_last_orphan) {
ext4_msg(sb, KERN_WARNING, "Couldn't "
"remount RDWR because of unprocessed "
"orphan inode list. Please "
"umount/remount instead");
err = -EINVAL;
goto restore_opts;
}
/*
* Mounting a RDONLY partition read-write, so reread
* and store the current valid flag. (It may have
* been changed by e2fsck since we originally mounted
* the partition.)
*/
if (sbi->s_journal)
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if ((err = ext4_group_extend(sb, es, n_blocks_count)))
goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
enable_quota = 1;
}
}
/*
* Reinitialize lazy itable initialization thread based on
* current settings
*/
if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
ext4_unregister_li_request(sb);
else {
ext4_group_t first_not_zeroed;
first_not_zeroed = ext4_has_uninit_itable(sb);
ext4_register_li_request(sb, first_not_zeroed);
}
ext4_setup_system_zone(sb);
if (sbi->s_journal == NULL)
ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
if (old_opts.s_qf_names[i] &&
old_opts.s_qf_names[i] != sbi->s_qf_names[i])
kfree(old_opts.s_qf_names[i]);
#endif
unlock_super(sb);
unlock_kernel();
if (enable_quota)
dquot_resume(sb, -1);
ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
kfree(orig_data);
return 0;
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
sbi->s_min_batch_time = old_opts.s_min_batch_time;
sbi->s_max_batch_time = old_opts.s_max_batch_time;
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
if (sbi->s_qf_names[i] &&
old_opts.s_qf_names[i] != sbi->s_qf_names[i])
kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
unlock_super(sb);
unlock_kernel();
kfree(orig_data);
return err;
}
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
u64 fsid;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
/*
* Compute the overhead (FS structures). This is constant
* for a given filesystem unless the number of block groups
* changes so we cache the previous value until it does.
*/
/*
* All of the blocks before first_data_block are
* overhead
*/
overhead = le32_to_cpu(es->s_first_data_block);
/*
* Add the overhead attributed to the superblock and
* block group descriptors. If the sparse superblocks
* feature is turned on, then not all groups have this.
*/
for (i = 0; i < ngroups; i++) {
overhead += ext4_bg_has_super(sb, i) +
ext4_bg_num_gdb(sb, i);
cond_resched();
}
/*
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
overhead += ngroups * (2 + sbi->s_itb_per_group);
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = ext4_blocks_count(es);
}
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
buf->f_namelen = EXT4_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
return 0;
}
/* Helper function for writing quotas on sync - we need to start transaction
* before quota file is locked for write. Otherwise the are possible deadlocks:
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
* dquot_initialize() down(dqio_mutex)
* down(dqio_mutex) jbd2_journal_start()
*
*/
#ifdef CONFIG_QUOTA
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
}
static int ext4_write_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
struct inode *inode;
inode = dquot_to_inode(dquot);
handle = ext4_journal_start(inode,
EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_acquire_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot),
EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_acquire(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_release_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot),
EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle)) {
/* Release dquot anyway to avoid endless cycle in dqput() */
dquot_release(dquot);
return PTR_ERR(handle);
}
ret = dquot_release(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_mark_dquot_dirty(struct dquot *dquot)
{
/* Are we journaling quotas? */
if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
return ext4_write_dquot(dquot);
} else {
return dquot_mark_dquot_dirty(dquot);
}
}
static int ext4_write_info(struct super_block *sb, int type)
{
int ret, err;
handle_t *handle;
/* Data block + inode block */
handle = ext4_journal_start(sb->s_root->d_inode, 2);
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit_info(sb, type);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
/*
* Turn on quotas during mount time - we need to find
* the quota file and such...
*/
static int ext4_quota_on_mount(struct super_block *sb, int type)
{
return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
EXT4_SB(sb)->s_jquota_fmt, type);
}
/*
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
char *name)
{
int err;
struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
err = kern_path(name, LOOKUP_FOLLOW, &path);
if (err)
return err;
/* Quotafile not on the same filesystem? */
if (path.mnt->mnt_sb != sb) {
path_put(&path);
return -EXDEV;
}
/* Journaling quota? */
if (EXT4_SB(sb)->s_qf_names[type]) {
/* Quotafile not in fs root? */
if (path.dentry->d_parent != sb->s_root)
ext4_msg(sb, KERN_WARNING,
"Quota file not on filesystem root. "
"Journaled quota will not work");
}
/*
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
if (EXT4_SB(sb)->s_journal &&
ext4_should_journal_data(path.dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
*/
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
if (err) {
path_put(&path);
return err;
}
}
err = dquot_quota_on_path(sb, type, format_id, &path);
path_put(&path);
return err;
}
static int ext4_quota_off(struct super_block *sb, int type)
{
/* Force all delayed allocation blocks to be allocated */
if (test_opt(sb, DELALLOC)) {
down_read(&sb->s_umount);
sync_filesystem(sb);
up_read(&sb->s_umount);
}
return dquot_quota_off(sb, type);
}
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
* itself serializes the operations (and noone else should touch the files)
* we don't have to be afraid of races */
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
int tocopy;
size_t toread;
struct buffer_head *bh;
loff_t i_size = i_size_read(inode);
if (off > i_size)
return 0;
if (off+len > i_size)
len = i_size-off;
toread = len;
while (toread > 0) {
tocopy = sb->s_blocksize - offset < toread ?
sb->s_blocksize - offset : toread;
bh = ext4_bread(NULL, inode, blk, 0, &err);
if (err)
return err;
if (!bh) /* A hole? */
memset(data, 0, tocopy);
else
memcpy(data, bh->b_data+offset, tocopy);
brelse(bh);
offset = 0;
toread -= tocopy;
data += tocopy;
blk++;
}
return len;
}
/* Write to quotafile (we know the transaction is already started and has
* enough credits) */
static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
if (EXT4_SB(sb)->s_journal && !handle) {
ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
" cancelled because transaction is not started",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
/*
* Since we account only one data block in transaction credits,
* then it is impossible to cross a block boundary.
*/
if (sb->s_blocksize - offset < len) {
ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
" cancelled because not block aligned",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
goto out;
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, len);
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
out:
if (err) {
mutex_unlock(&inode->i_mutex);
return err;
}
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
}
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
return len;
}
#endif
static int ext4_get_sb(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data, struct vfsmount *mnt)
{
return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = "ext2",
.get_sb = ext4_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
static inline void register_as_ext2(void)
{
int err = register_filesystem(&ext2_fs_type);
if (err)
printk(KERN_WARNING
"EXT4-fs: Unable to register as ext2 (%d)\n", err);
}
static inline void unregister_as_ext2(void)
{
unregister_filesystem(&ext2_fs_type);
}
MODULE_ALIAS("ext2");
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
#endif
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static inline void register_as_ext3(void)
{
int err = register_filesystem(&ext3_fs_type);
if (err)
printk(KERN_WARNING
"EXT4-fs: Unable to register as ext3 (%d)\n", err);
}
static inline void unregister_as_ext3(void)
{
unregister_filesystem(&ext3_fs_type);
}
MODULE_ALIAS("ext3");
#else
static inline void register_as_ext3(void) { }
static inline void unregister_as_ext3(void) { }
#endif
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
.get_sb = ext4_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
static int __init init_ext4_fs(void)
{
int err;
ext4_check_flag_values();
err = init_ext4_system_zone();
if (err)
return err;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
goto out4;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = init_ext4_mballoc();
if (err)
goto out3;
err = init_ext4_xattr();
if (err)
goto out2;
err = init_inodecache();
if (err)
goto out1;
register_as_ext2();
register_as_ext3();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
ext4_li_info = NULL;
mutex_init(&ext4_li_mtx);
return 0;
out:
unregister_as_ext2();
unregister_as_ext3();
destroy_inodecache();
out1:
exit_ext4_xattr();
out2:
exit_ext4_mballoc();
out3:
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
out4:
exit_ext4_system_zone();
return err;
}
static void __exit exit_ext4_fs(void)
{
ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
exit_ext4_xattr();
exit_ext4_mballoc();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
exit_ext4_system_zone();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
module_init(init_ext4_fs)
module_exit(exit_ext4_fs)