2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* linux/fs/ext3/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/jbd.h>
|
|
|
|
#include <linux/ext3_fs.h>
|
|
|
|
#include <linux/ext3_jbd.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/vfs.h>
|
|
|
|
#include <linux/random.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/quotaops.h>
|
2005-09-07 00:16:54 +02:00
|
|
|
#include <linux/seq_file.h>
|
2005-10-31 00:02:56 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <asm/uaccess.h>
|
2005-10-31 00:02:56 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#include "xattr.h"
|
|
|
|
#include "acl.h"
|
2005-10-31 00:02:56 +01:00
|
|
|
#include "namei.h"
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2006-01-08 10:03:20 +01:00
|
|
|
static int ext3_load_journal(struct super_block *, struct ext3_super_block *,
|
|
|
|
unsigned long journal_devnum);
|
2005-04-17 00:20:36 +02:00
|
|
|
static int ext3_create_journal(struct super_block *, struct ext3_super_block *,
|
2006-09-27 10:49:30 +02:00
|
|
|
unsigned int);
|
2005-04-17 00:20:36 +02:00
|
|
|
static void ext3_commit_super (struct super_block * sb,
|
|
|
|
struct ext3_super_block * es,
|
|
|
|
int sync);
|
|
|
|
static void ext3_mark_recovery_complete(struct super_block * sb,
|
|
|
|
struct ext3_super_block * es);
|
|
|
|
static void ext3_clear_journal_err(struct super_block * sb,
|
|
|
|
struct ext3_super_block * es);
|
|
|
|
static int ext3_sync_fs(struct super_block *sb, int wait);
|
|
|
|
static const char *ext3_decode_error(struct super_block * sb, int errno,
|
|
|
|
char nbuf[16]);
|
|
|
|
static int ext3_remount (struct super_block * sb, int * flags, char * data);
|
2006-06-23 11:02:58 +02:00
|
|
|
static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
|
2005-04-17 00:20:36 +02:00
|
|
|
static void ext3_unlockfs(struct super_block *sb);
|
|
|
|
static void ext3_write_super (struct super_block * sb);
|
|
|
|
static void ext3_write_super_lockfs(struct super_block *sb);
|
|
|
|
|
2006-09-27 10:49:27 +02:00
|
|
|
/*
|
2005-04-17 00:20:36 +02:00
|
|
|
* Wrappers for 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
|
2006-09-27 10:49:27 +02:00
|
|
|
* appropriate.
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
|
|
|
handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
|
|
|
|
{
|
|
|
|
journal_t *journal;
|
|
|
|
|
|
|
|
if (sb->s_flags & MS_RDONLY)
|
|
|
|
return ERR_PTR(-EROFS);
|
|
|
|
|
|
|
|
/* 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 = EXT3_SB(sb)->s_journal;
|
|
|
|
if (is_journal_aborted(journal)) {
|
|
|
|
ext3_abort(sb, __FUNCTION__,
|
|
|
|
"Detected aborted journal");
|
|
|
|
return ERR_PTR(-EROFS);
|
|
|
|
}
|
|
|
|
|
|
|
|
return journal_start(journal, nblocks);
|
|
|
|
}
|
|
|
|
|
2006-09-27 10:49:27 +02:00
|
|
|
/*
|
2005-04-17 00:20:36 +02:00
|
|
|
* The only special thing we need to do here is to make sure that all
|
|
|
|
* journal_stop calls result in the superblock being marked dirty, so
|
|
|
|
* that sync() will call the filesystem's write_super callback if
|
2006-09-27 10:49:27 +02:00
|
|
|
* appropriate.
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
|
|
|
int __ext3_journal_stop(const char *where, handle_t *handle)
|
|
|
|
{
|
|
|
|
struct super_block *sb;
|
|
|
|
int err;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
sb = handle->h_transaction->t_journal->j_private;
|
|
|
|
err = handle->h_err;
|
|
|
|
rc = journal_stop(handle);
|
|
|
|
|
|
|
|
if (!err)
|
|
|
|
err = rc;
|
|
|
|
if (err)
|
|
|
|
__ext3_std_error(sb, where, err);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
void ext3_journal_abort_handle(const char *caller, const char *err_fn,
|
|
|
|
struct buffer_head *bh, handle_t *handle, int err)
|
|
|
|
{
|
|
|
|
char nbuf[16];
|
|
|
|
const char *errstr = ext3_decode_error(NULL, err, nbuf);
|
|
|
|
|
|
|
|
if (bh)
|
|
|
|
BUFFER_TRACE(bh, "abort");
|
|
|
|
|
|
|
|
if (!handle->h_err)
|
|
|
|
handle->h_err = err;
|
|
|
|
|
|
|
|
if (is_handle_aborted(handle))
|
|
|
|
return;
|
|
|
|
|
|
|
|
printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
|
|
|
|
caller, errstr, err_fn);
|
|
|
|
|
|
|
|
journal_abort_handle(handle);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* 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 ext3, 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 journal_abort() error code to record an error in
|
|
|
|
* the journal instead. On recovery, the journal will compain about
|
|
|
|
* that error until we've noted it down and cleared it.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void ext3_handle_error(struct super_block *sb)
|
|
|
|
{
|
|
|
|
struct ext3_super_block *es = EXT3_SB(sb)->s_es;
|
|
|
|
|
|
|
|
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
|
|
|
|
es->s_state |= cpu_to_le16(EXT3_ERROR_FS);
|
|
|
|
|
|
|
|
if (sb->s_flags & MS_RDONLY)
|
|
|
|
return;
|
|
|
|
|
2006-09-27 10:49:33 +02:00
|
|
|
if (!test_opt (sb, ERRORS_CONT)) {
|
2005-04-17 00:20:36 +02:00
|
|
|
journal_t *journal = EXT3_SB(sb)->s_journal;
|
|
|
|
|
|
|
|
EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
|
|
|
|
if (journal)
|
|
|
|
journal_abort(journal, -EIO);
|
|
|
|
}
|
2006-09-27 10:49:33 +02:00
|
|
|
if (test_opt (sb, ERRORS_RO)) {
|
|
|
|
printk (KERN_CRIT "Remounting filesystem read-only\n");
|
|
|
|
sb->s_flags |= MS_RDONLY;
|
|
|
|
}
|
|
|
|
ext3_commit_super(sb, es, 1);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (test_opt(sb, ERRORS_PANIC))
|
|
|
|
panic("EXT3-fs (device %s): panic forced after error\n",
|
|
|
|
sb->s_id);
|
|
|
|
}
|
|
|
|
|
|
|
|
void ext3_error (struct super_block * sb, const char * function,
|
|
|
|
const char * fmt, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
|
|
|
|
vprintk(fmt, args);
|
|
|
|
printk("\n");
|
|
|
|
va_end(args);
|
|
|
|
|
|
|
|
ext3_handle_error(sb);
|
|
|
|
}
|
|
|
|
|
|
|
|
static const char *ext3_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 || EXT3_SB(sb)->s_journal->j_flags & JFS_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;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* __ext3_std_error decodes expected errors from journaling functions
|
|
|
|
* automatically and invokes the appropriate error response. */
|
|
|
|
|
|
|
|
void __ext3_std_error (struct super_block * sb, const char * function,
|
|
|
|
int errno)
|
|
|
|
{
|
|
|
|
char nbuf[16];
|
2005-05-18 17:47:17 +02:00
|
|
|
const char *errstr;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2005-05-18 17:47:17 +02:00
|
|
|
/* 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 = ext3_decode_error(sb, errno, nbuf);
|
2005-04-17 00:20:36 +02:00
|
|
|
printk (KERN_CRIT "EXT3-fs error (device %s) in %s: %s\n",
|
|
|
|
sb->s_id, function, errstr);
|
|
|
|
|
|
|
|
ext3_handle_error(sb);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ext3_abort is a much stronger failure handler than ext3_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 ext3_abort (struct super_block * sb, const char * function,
|
|
|
|
const char * fmt, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
|
|
|
|
printk (KERN_CRIT "ext3_abort called.\n");
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
|
|
|
|
vprintk(fmt, args);
|
|
|
|
printk("\n");
|
|
|
|
va_end(args);
|
|
|
|
|
|
|
|
if (test_opt(sb, ERRORS_PANIC))
|
|
|
|
panic("EXT3-fs panic from previous error\n");
|
|
|
|
|
|
|
|
if (sb->s_flags & MS_RDONLY)
|
|
|
|
return;
|
|
|
|
|
|
|
|
printk(KERN_CRIT "Remounting filesystem read-only\n");
|
|
|
|
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
|
|
|
|
sb->s_flags |= MS_RDONLY;
|
|
|
|
EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
|
|
|
|
journal_abort(EXT3_SB(sb)->s_journal, -EIO);
|
|
|
|
}
|
|
|
|
|
|
|
|
void ext3_warning (struct super_block * sb, const char * function,
|
|
|
|
const char * fmt, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
printk(KERN_WARNING "EXT3-fs warning (device %s): %s: ",
|
|
|
|
sb->s_id, function);
|
|
|
|
vprintk(fmt, args);
|
|
|
|
printk("\n");
|
|
|
|
va_end(args);
|
|
|
|
}
|
|
|
|
|
|
|
|
void ext3_update_dynamic_rev(struct super_block *sb)
|
|
|
|
{
|
|
|
|
struct ext3_super_block *es = EXT3_SB(sb)->s_es;
|
|
|
|
|
|
|
|
if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV)
|
|
|
|
return;
|
|
|
|
|
|
|
|
ext3_warning(sb, __FUNCTION__,
|
|
|
|
"updating to rev %d because of new feature flag, "
|
|
|
|
"running e2fsck is recommended",
|
|
|
|
EXT3_DYNAMIC_REV);
|
|
|
|
|
|
|
|
es->s_first_ino = cpu_to_le32(EXT3_GOOD_OLD_FIRST_INO);
|
|
|
|
es->s_inode_size = cpu_to_le16(EXT3_GOOD_OLD_INODE_SIZE);
|
|
|
|
es->s_rev_level = cpu_to_le32(EXT3_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 *ext3_blkdev_get(dev_t dev)
|
|
|
|
{
|
|
|
|
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:
|
|
|
|
printk(KERN_ERR "EXT3: failed to open journal device %s: %ld\n",
|
|
|
|
__bdevname(dev, b), PTR_ERR(bdev));
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Release the journal device
|
|
|
|
*/
|
|
|
|
static int ext3_blkdev_put(struct block_device *bdev)
|
|
|
|
{
|
|
|
|
bd_release(bdev);
|
|
|
|
return blkdev_put(bdev);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
|
|
|
|
{
|
|
|
|
struct block_device *bdev;
|
|
|
|
int ret = -ENODEV;
|
|
|
|
|
|
|
|
bdev = sbi->journal_bdev;
|
|
|
|
if (bdev) {
|
|
|
|
ret = ext3_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 ext3_inode_info, i_orphan)->vfs_inode;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi)
|
|
|
|
{
|
|
|
|
struct list_head *l;
|
|
|
|
|
2006-09-27 10:49:27 +02:00
|
|
|
printk(KERN_ERR "sb orphan head is %d\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
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 " "
|
2006-09-27 10:49:30 +02:00
|
|
|
"inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
inode->i_sb->s_id, inode->i_ino, inode,
|
2006-09-27 10:49:27 +02:00
|
|
|
inode->i_mode, inode->i_nlink,
|
2005-04-17 00:20:36 +02:00
|
|
|
NEXT_ORPHAN(inode));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void ext3_put_super (struct super_block * sb)
|
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
|
|
|
struct ext3_super_block *es = sbi->s_es;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
ext3_xattr_put_super(sb);
|
|
|
|
journal_destroy(sbi->s_journal);
|
|
|
|
if (!(sb->s_flags & MS_RDONLY)) {
|
|
|
|
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
es->s_state = cpu_to_le16(sbi->s_mount_state);
|
|
|
|
BUFFER_TRACE(sbi->s_sbh, "marking dirty");
|
|
|
|
mark_buffer_dirty(sbi->s_sbh);
|
|
|
|
ext3_commit_super(sb, es, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < sbi->s_gdb_count; i++)
|
|
|
|
brelse(sbi->s_group_desc[i]);
|
|
|
|
kfree(sbi->s_group_desc);
|
|
|
|
percpu_counter_destroy(&sbi->s_freeblocks_counter);
|
|
|
|
percpu_counter_destroy(&sbi->s_freeinodes_counter);
|
|
|
|
percpu_counter_destroy(&sbi->s_dirs_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, 0);
|
|
|
|
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, 0);
|
|
|
|
ext3_blkdev_remove(sbi);
|
|
|
|
}
|
|
|
|
sb->s_fs_info = NULL;
|
|
|
|
kfree(sbi);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2006-12-07 05:33:20 +01:00
|
|
|
static struct kmem_cache *ext3_inode_cachep;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Called inside transaction, so use GFP_NOFS
|
|
|
|
*/
|
|
|
|
static struct inode *ext3_alloc_inode(struct super_block *sb)
|
|
|
|
{
|
|
|
|
struct ext3_inode_info *ei;
|
|
|
|
|
2006-12-07 05:33:14 +01:00
|
|
|
ei = kmem_cache_alloc(ext3_inode_cachep, GFP_NOFS);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (!ei)
|
|
|
|
return NULL;
|
|
|
|
#ifdef CONFIG_EXT3_FS_POSIX_ACL
|
|
|
|
ei->i_acl = EXT3_ACL_NOT_CACHED;
|
|
|
|
ei->i_default_acl = EXT3_ACL_NOT_CACHED;
|
|
|
|
#endif
|
|
|
|
ei->i_block_alloc_info = NULL;
|
|
|
|
ei->vfs_inode.i_version = 1;
|
|
|
|
return &ei->vfs_inode;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void ext3_destroy_inode(struct inode *inode)
|
|
|
|
{
|
|
|
|
kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
|
|
|
|
}
|
|
|
|
|
2006-12-07 05:33:20 +01:00
|
|
|
static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;
|
|
|
|
|
|
|
|
if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
|
|
|
|
SLAB_CTOR_CONSTRUCTOR) {
|
|
|
|
INIT_LIST_HEAD(&ei->i_orphan);
|
|
|
|
#ifdef CONFIG_EXT3_FS_XATTR
|
|
|
|
init_rwsem(&ei->xattr_sem);
|
|
|
|
#endif
|
2006-03-23 12:00:42 +01:00
|
|
|
mutex_init(&ei->truncate_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
inode_init_once(&ei->vfs_inode);
|
|
|
|
}
|
|
|
|
}
|
2006-09-27 10:49:27 +02:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
static int init_inodecache(void)
|
|
|
|
{
|
|
|
|
ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",
|
|
|
|
sizeof(struct ext3_inode_info),
|
2006-03-24 12:16:06 +01:00
|
|
|
0, (SLAB_RECLAIM_ACCOUNT|
|
|
|
|
SLAB_MEM_SPREAD),
|
2005-04-17 00:20:36 +02:00
|
|
|
init_once, NULL);
|
|
|
|
if (ext3_inode_cachep == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void destroy_inodecache(void)
|
|
|
|
{
|
2006-09-27 10:49:40 +02:00
|
|
|
kmem_cache_destroy(ext3_inode_cachep);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static void ext3_clear_inode(struct inode *inode)
|
|
|
|
{
|
|
|
|
struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info;
|
|
|
|
#ifdef CONFIG_EXT3_FS_POSIX_ACL
|
2006-06-23 11:05:32 +02:00
|
|
|
if (EXT3_I(inode)->i_acl &&
|
|
|
|
EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) {
|
|
|
|
posix_acl_release(EXT3_I(inode)->i_acl);
|
|
|
|
EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED;
|
|
|
|
}
|
|
|
|
if (EXT3_I(inode)->i_default_acl &&
|
|
|
|
EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) {
|
|
|
|
posix_acl_release(EXT3_I(inode)->i_default_acl);
|
|
|
|
EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
#endif
|
|
|
|
ext3_discard_reservation(inode);
|
|
|
|
EXT3_I(inode)->i_block_alloc_info = NULL;
|
2006-06-23 11:05:32 +02:00
|
|
|
if (unlikely(rsv))
|
|
|
|
kfree(rsv);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
2005-10-28 20:23:39 +02:00
|
|
|
static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
|
2005-09-07 00:16:54 +02:00
|
|
|
{
|
2005-10-28 20:23:39 +02:00
|
|
|
#if defined(CONFIG_QUOTA)
|
2005-09-23 06:44:03 +02:00
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
2005-09-07 00:16:54 +02:00
|
|
|
|
|
|
|
if (sbi->s_jquota_fmt)
|
|
|
|
seq_printf(seq, ",jqfmt=%s",
|
|
|
|
(sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
|
|
|
|
|
|
|
|
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 (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA)
|
|
|
|
seq_puts(seq, ",usrquota");
|
|
|
|
|
|
|
|
if (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)
|
|
|
|
seq_puts(seq, ",grpquota");
|
|
|
|
#endif
|
2005-10-28 20:23:39 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
|
|
|
|
{
|
|
|
|
struct super_block *sb = vfs->mnt_sb;
|
|
|
|
|
|
|
|
if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
|
|
|
|
seq_puts(seq, ",data=journal");
|
|
|
|
else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
|
|
|
|
seq_puts(seq, ",data=ordered");
|
|
|
|
else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
|
|
|
|
seq_puts(seq, ",data=writeback");
|
|
|
|
|
|
|
|
ext3_show_quota_options(seq, sb);
|
2005-09-07 00:16:54 +02:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2006-09-16 21:15:38 +02:00
|
|
|
|
|
|
|
static struct dentry *ext3_get_dentry(struct super_block *sb, void *vobjp)
|
|
|
|
{
|
|
|
|
__u32 *objp = vobjp;
|
|
|
|
unsigned long ino = objp[0];
|
|
|
|
__u32 generation = objp[1];
|
|
|
|
struct inode *inode;
|
|
|
|
struct dentry *result;
|
|
|
|
|
|
|
|
if (ino < EXT3_FIRST_INO(sb) && ino != EXT3_ROOT_INO)
|
|
|
|
return ERR_PTR(-ESTALE);
|
|
|
|
if (ino > le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count))
|
|
|
|
return ERR_PTR(-ESTALE);
|
|
|
|
|
|
|
|
/* iget isn't really right if the inode is currently unallocated!!
|
|
|
|
*
|
|
|
|
* ext3_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 = iget(sb, ino);
|
|
|
|
if (inode == NULL)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (is_bad_inode(inode) ||
|
|
|
|
(generation && inode->i_generation != generation)) {
|
|
|
|
iput(inode);
|
|
|
|
return ERR_PTR(-ESTALE);
|
|
|
|
}
|
|
|
|
/* now to find a dentry.
|
|
|
|
* If possible, get a well-connected one
|
|
|
|
*/
|
|
|
|
result = d_alloc_anon(inode);
|
|
|
|
if (!result) {
|
|
|
|
iput(inode);
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2005-09-07 00:16:54 +02:00
|
|
|
#ifdef CONFIG_QUOTA
|
2005-04-17 00:20:36 +02:00
|
|
|
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
|
|
|
|
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
|
|
|
|
|
|
|
|
static int ext3_dquot_initialize(struct inode *inode, int type);
|
|
|
|
static int ext3_dquot_drop(struct inode *inode);
|
|
|
|
static int ext3_write_dquot(struct dquot *dquot);
|
|
|
|
static int ext3_acquire_dquot(struct dquot *dquot);
|
|
|
|
static int ext3_release_dquot(struct dquot *dquot);
|
|
|
|
static int ext3_mark_dquot_dirty(struct dquot *dquot);
|
|
|
|
static int ext3_write_info(struct super_block *sb, int type);
|
|
|
|
static int ext3_quota_on(struct super_block *sb, int type, int format_id, char *path);
|
|
|
|
static int ext3_quota_on_mount(struct super_block *sb, int type);
|
|
|
|
static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
|
|
|
|
size_t len, loff_t off);
|
|
|
|
static ssize_t ext3_quota_write(struct super_block *sb, int type,
|
|
|
|
const char *data, size_t len, loff_t off);
|
|
|
|
|
|
|
|
static struct dquot_operations ext3_quota_operations = {
|
|
|
|
.initialize = ext3_dquot_initialize,
|
|
|
|
.drop = ext3_dquot_drop,
|
|
|
|
.alloc_space = dquot_alloc_space,
|
|
|
|
.alloc_inode = dquot_alloc_inode,
|
|
|
|
.free_space = dquot_free_space,
|
|
|
|
.free_inode = dquot_free_inode,
|
|
|
|
.transfer = dquot_transfer,
|
|
|
|
.write_dquot = ext3_write_dquot,
|
|
|
|
.acquire_dquot = ext3_acquire_dquot,
|
|
|
|
.release_dquot = ext3_release_dquot,
|
|
|
|
.mark_dirty = ext3_mark_dquot_dirty,
|
|
|
|
.write_info = ext3_write_info
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct quotactl_ops ext3_qctl_operations = {
|
|
|
|
.quota_on = ext3_quota_on,
|
|
|
|
.quota_off = vfs_quota_off,
|
|
|
|
.quota_sync = vfs_quota_sync,
|
|
|
|
.get_info = vfs_get_dqinfo,
|
|
|
|
.set_info = vfs_set_dqinfo,
|
|
|
|
.get_dqblk = vfs_get_dqblk,
|
|
|
|
.set_dqblk = vfs_set_dqblk
|
|
|
|
};
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static struct super_operations ext3_sops = {
|
|
|
|
.alloc_inode = ext3_alloc_inode,
|
|
|
|
.destroy_inode = ext3_destroy_inode,
|
|
|
|
.read_inode = ext3_read_inode,
|
|
|
|
.write_inode = ext3_write_inode,
|
|
|
|
.dirty_inode = ext3_dirty_inode,
|
|
|
|
.delete_inode = ext3_delete_inode,
|
|
|
|
.put_super = ext3_put_super,
|
|
|
|
.write_super = ext3_write_super,
|
|
|
|
.sync_fs = ext3_sync_fs,
|
|
|
|
.write_super_lockfs = ext3_write_super_lockfs,
|
|
|
|
.unlockfs = ext3_unlockfs,
|
|
|
|
.statfs = ext3_statfs,
|
|
|
|
.remount_fs = ext3_remount,
|
|
|
|
.clear_inode = ext3_clear_inode,
|
2005-09-07 00:16:54 +02:00
|
|
|
.show_options = ext3_show_options,
|
2005-04-17 00:20:36 +02:00
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
.quota_read = ext3_quota_read,
|
|
|
|
.quota_write = ext3_quota_write,
|
|
|
|
#endif
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct export_operations ext3_export_ops = {
|
|
|
|
.get_parent = ext3_get_parent,
|
2006-09-16 21:15:38 +02:00
|
|
|
.get_dentry = ext3_get_dentry,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
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,
|
2005-11-09 06:34:59 +01:00
|
|
|
Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
|
2005-04-17 00:20:36 +02:00
|
|
|
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
|
2006-06-26 09:25:04 +02:00
|
|
|
Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
|
2006-01-08 10:03:20 +01:00
|
|
|
Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
|
2005-04-17 00:20:36 +02:00
|
|
|
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
|
|
|
|
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
|
2005-06-24 07:01:04 +02:00
|
|
|
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
|
2005-09-07 00:16:54 +02:00
|
|
|
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
|
|
|
|
Opt_grpquota
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
static 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_nocheck, "nocheck"},
|
|
|
|
{Opt_nocheck, "check=none"},
|
|
|
|
{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_reservation, "reservation"},
|
|
|
|
{Opt_noreservation, "noreservation"},
|
|
|
|
{Opt_noload, "noload"},
|
|
|
|
{Opt_nobh, "nobh"},
|
2006-06-26 09:25:04 +02:00
|
|
|
{Opt_bh, "bh"},
|
2005-04-17 00:20:36 +02:00
|
|
|
{Opt_commit, "commit=%u"},
|
|
|
|
{Opt_journal_update, "journal=update"},
|
|
|
|
{Opt_journal_inum, "journal=%u"},
|
2006-01-08 10:03:20 +01:00
|
|
|
{Opt_journal_dev, "journal_dev=%u"},
|
2005-04-17 00:20:36 +02:00
|
|
|
{Opt_abort, "abort"},
|
|
|
|
{Opt_data_journal, "data=journal"},
|
|
|
|
{Opt_data_ordered, "data=ordered"},
|
|
|
|
{Opt_data_writeback, "data=writeback"},
|
|
|
|
{Opt_offusrjquota, "usrjquota="},
|
|
|
|
{Opt_usrjquota, "usrjquota=%s"},
|
|
|
|
{Opt_offgrpjquota, "grpjquota="},
|
|
|
|
{Opt_grpjquota, "grpjquota=%s"},
|
|
|
|
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
|
|
|
|
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
|
2005-09-07 00:16:54 +02:00
|
|
|
{Opt_grpquota, "grpquota"},
|
2005-06-24 07:01:04 +02:00
|
|
|
{Opt_noquota, "noquota"},
|
|
|
|
{Opt_quota, "quota"},
|
2005-09-07 00:16:54 +02:00
|
|
|
{Opt_usrquota, "usrquota"},
|
2005-04-17 00:20:36 +02:00
|
|
|
{Opt_barrier, "barrier=%u"},
|
|
|
|
{Opt_err, NULL},
|
|
|
|
{Opt_resize, "resize"},
|
|
|
|
};
|
|
|
|
|
2006-06-25 14:48:07 +02:00
|
|
|
static ext3_fsblk_t get_sb_block(void **data)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2006-09-27 10:49:35 +02:00
|
|
|
ext3_fsblk_t sb_block;
|
|
|
|
char *options = (char *) *data;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (!options || strncmp(options, "sb=", 3) != 0)
|
|
|
|
return 1; /* Default location */
|
|
|
|
options += 3;
|
2006-06-25 14:48:07 +02:00
|
|
|
/*todo: use simple_strtoll with >32bit ext3 */
|
2005-04-17 00:20:36 +02:00
|
|
|
sb_block = simple_strtoul(options, &options, 0);
|
|
|
|
if (*options && *options != ',') {
|
|
|
|
printk("EXT3-fs: Invalid sb specification: %s\n",
|
|
|
|
(char *) *data);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
if (*options == ',')
|
|
|
|
options++;
|
|
|
|
*data = (void *) options;
|
|
|
|
return sb_block;
|
|
|
|
}
|
|
|
|
|
2006-01-08 10:03:20 +01:00
|
|
|
static int parse_options (char *options, struct super_block *sb,
|
2006-09-27 10:49:30 +02:00
|
|
|
unsigned int *inum, unsigned long *journal_devnum,
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t *n_blocks_count, int is_remount)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
|
|
|
char * p;
|
|
|
|
substring_t args[MAX_OPT_ARGS];
|
|
|
|
int data_opt = 0;
|
|
|
|
int option;
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
int qtype;
|
|
|
|
char *qname;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
if (!options)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
while ((p = strsep (&options, ",")) != NULL) {
|
|
|
|
int token;
|
|
|
|
if (!*p)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
token = match_token(p, tokens, args);
|
|
|
|
switch (token) {
|
|
|
|
case Opt_bsd_df:
|
|
|
|
clear_opt (sbi->s_mount_opt, MINIX_DF);
|
|
|
|
break;
|
|
|
|
case Opt_minix_df:
|
|
|
|
set_opt (sbi->s_mount_opt, MINIX_DF);
|
|
|
|
break;
|
|
|
|
case Opt_grpid:
|
|
|
|
set_opt (sbi->s_mount_opt, GRPID);
|
|
|
|
break;
|
|
|
|
case Opt_nogrpid:
|
|
|
|
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_nocheck:
|
|
|
|
clear_opt (sbi->s_mount_opt, CHECK);
|
|
|
|
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_EXT3_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:
|
|
|
|
printk("EXT3 (no)user_xattr options not supported\n");
|
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_EXT3_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:
|
|
|
|
printk("EXT3 (no)acl options not supported\n");
|
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
case Opt_reservation:
|
|
|
|
set_opt(sbi->s_mount_opt, RESERVATION);
|
|
|
|
break;
|
|
|
|
case Opt_noreservation:
|
|
|
|
clear_opt(sbi->s_mount_opt, RESERVATION);
|
|
|
|
break;
|
|
|
|
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) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: cannot specify "
|
|
|
|
"journal on remount\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
set_opt (sbi->s_mount_opt, UPDATE_JOURNAL);
|
|
|
|
break;
|
|
|
|
case Opt_journal_inum:
|
|
|
|
if (is_remount) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: cannot specify "
|
|
|
|
"journal on remount\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
if (match_int(&args[0], &option))
|
|
|
|
return 0;
|
|
|
|
*inum = option;
|
|
|
|
break;
|
2006-01-08 10:03:20 +01:00
|
|
|
case Opt_journal_dev:
|
|
|
|
if (is_remount) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: cannot specify "
|
|
|
|
"journal on remount\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
if (match_int(&args[0], &option))
|
|
|
|
return 0;
|
|
|
|
*journal_devnum = option;
|
|
|
|
break;
|
2005-04-17 00:20:36 +02:00
|
|
|
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 = JBD_DEFAULT_MAX_COMMIT_AGE;
|
|
|
|
sbi->s_commit_interval = HZ * option;
|
|
|
|
break;
|
|
|
|
case Opt_data_journal:
|
|
|
|
data_opt = EXT3_MOUNT_JOURNAL_DATA;
|
|
|
|
goto datacheck;
|
|
|
|
case Opt_data_ordered:
|
|
|
|
data_opt = EXT3_MOUNT_ORDERED_DATA;
|
|
|
|
goto datacheck;
|
|
|
|
case Opt_data_writeback:
|
|
|
|
data_opt = EXT3_MOUNT_WRITEBACK_DATA;
|
|
|
|
datacheck:
|
|
|
|
if (is_remount) {
|
|
|
|
if ((sbi->s_mount_opt & EXT3_MOUNT_DATA_FLAGS)
|
|
|
|
!= data_opt) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: cannot change data "
|
|
|
|
"mode on remount\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
sbi->s_mount_opt &= ~EXT3_MOUNT_DATA_FLAGS;
|
|
|
|
sbi->s_mount_opt |= data_opt;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
case Opt_usrjquota:
|
|
|
|
qtype = USRQUOTA;
|
|
|
|
goto set_qf_name;
|
|
|
|
case Opt_grpjquota:
|
|
|
|
qtype = GRPQUOTA;
|
|
|
|
set_qf_name:
|
|
|
|
if (sb_any_quota_enabled(sb)) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: Cannot change journalled "
|
|
|
|
"quota options when quota turned on.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
qname = match_strdup(&args[0]);
|
|
|
|
if (!qname) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: not enough memory for "
|
|
|
|
"storing quotafile name.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
if (sbi->s_qf_names[qtype] &&
|
|
|
|
strcmp(sbi->s_qf_names[qtype], qname)) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: %s quota file already "
|
|
|
|
"specified.\n", QTYPE2NAME(qtype));
|
|
|
|
kfree(qname);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
sbi->s_qf_names[qtype] = qname;
|
|
|
|
if (strchr(sbi->s_qf_names[qtype], '/')) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: quotafile must be on "
|
|
|
|
"filesystem root.\n");
|
|
|
|
kfree(sbi->s_qf_names[qtype]);
|
|
|
|
sbi->s_qf_names[qtype] = NULL;
|
|
|
|
return 0;
|
|
|
|
}
|
2005-06-24 07:01:04 +02:00
|
|
|
set_opt(sbi->s_mount_opt, QUOTA);
|
2005-04-17 00:20:36 +02:00
|
|
|
break;
|
|
|
|
case Opt_offusrjquota:
|
|
|
|
qtype = USRQUOTA;
|
|
|
|
goto clear_qf_name;
|
|
|
|
case Opt_offgrpjquota:
|
|
|
|
qtype = GRPQUOTA;
|
|
|
|
clear_qf_name:
|
|
|
|
if (sb_any_quota_enabled(sb)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: Cannot change "
|
|
|
|
"journalled quota options when "
|
|
|
|
"quota turned on.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
2005-07-12 22:58:28 +02:00
|
|
|
/*
|
|
|
|
* The space will be released later when all options
|
|
|
|
* are confirmed to be correct
|
|
|
|
*/
|
2005-04-17 00:20:36 +02:00
|
|
|
sbi->s_qf_names[qtype] = NULL;
|
|
|
|
break;
|
|
|
|
case Opt_jqfmt_vfsold:
|
|
|
|
sbi->s_jquota_fmt = QFMT_VFS_OLD;
|
|
|
|
break;
|
|
|
|
case Opt_jqfmt_vfsv0:
|
|
|
|
sbi->s_jquota_fmt = QFMT_VFS_V0;
|
|
|
|
break;
|
2005-06-24 07:01:04 +02:00
|
|
|
case Opt_quota:
|
2005-09-07 00:16:54 +02:00
|
|
|
case Opt_usrquota:
|
|
|
|
set_opt(sbi->s_mount_opt, QUOTA);
|
|
|
|
set_opt(sbi->s_mount_opt, USRQUOTA);
|
|
|
|
break;
|
|
|
|
case Opt_grpquota:
|
2005-06-24 07:01:04 +02:00
|
|
|
set_opt(sbi->s_mount_opt, QUOTA);
|
2005-09-07 00:16:54 +02:00
|
|
|
set_opt(sbi->s_mount_opt, GRPQUOTA);
|
2005-06-24 07:01:04 +02:00
|
|
|
break;
|
|
|
|
case Opt_noquota:
|
|
|
|
if (sb_any_quota_enabled(sb)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: Cannot change quota "
|
|
|
|
"options when quota turned on.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
clear_opt(sbi->s_mount_opt, QUOTA);
|
2005-09-07 00:16:54 +02:00
|
|
|
clear_opt(sbi->s_mount_opt, USRQUOTA);
|
|
|
|
clear_opt(sbi->s_mount_opt, GRPQUOTA);
|
2005-06-24 07:01:04 +02:00
|
|
|
break;
|
2005-04-17 00:20:36 +02:00
|
|
|
#else
|
2005-09-07 00:16:54 +02:00
|
|
|
case Opt_quota:
|
|
|
|
case Opt_usrquota:
|
|
|
|
case Opt_grpquota:
|
2005-04-17 00:20:36 +02:00
|
|
|
case Opt_usrjquota:
|
|
|
|
case Opt_grpjquota:
|
|
|
|
case Opt_offusrjquota:
|
|
|
|
case Opt_offgrpjquota:
|
|
|
|
case Opt_jqfmt_vfsold:
|
|
|
|
case Opt_jqfmt_vfsv0:
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: journalled quota options not "
|
|
|
|
"supported.\n");
|
|
|
|
break;
|
2005-06-24 07:01:04 +02:00
|
|
|
case Opt_noquota:
|
|
|
|
break;
|
2005-04-17 00:20:36 +02:00
|
|
|
#endif
|
|
|
|
case Opt_abort:
|
|
|
|
set_opt(sbi->s_mount_opt, ABORT);
|
|
|
|
break;
|
|
|
|
case Opt_barrier:
|
|
|
|
if (match_int(&args[0], &option))
|
|
|
|
return 0;
|
|
|
|
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:
|
2005-07-12 22:58:28 +02:00
|
|
|
if (!is_remount) {
|
2005-04-17 00:20:36 +02:00
|
|
|
printk("EXT3-fs: resize option only available "
|
|
|
|
"for remount\n");
|
|
|
|
return 0;
|
|
|
|
}
|
2005-06-29 05:45:11 +02:00
|
|
|
if (match_int(&args[0], &option) != 0)
|
|
|
|
return 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
*n_blocks_count = option;
|
|
|
|
break;
|
|
|
|
case Opt_nobh:
|
|
|
|
set_opt(sbi->s_mount_opt, NOBH);
|
|
|
|
break;
|
2006-06-26 09:25:04 +02:00
|
|
|
case Opt_bh:
|
|
|
|
clear_opt(sbi->s_mount_opt, NOBH);
|
|
|
|
break;
|
2005-04-17 00:20:36 +02:00
|
|
|
default:
|
|
|
|
printk (KERN_ERR
|
|
|
|
"EXT3-fs: Unrecognized mount option \"%s\" "
|
|
|
|
"or missing value\n", p);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#ifdef CONFIG_QUOTA
|
2005-09-07 00:16:54 +02:00
|
|
|
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
|
|
|
|
if ((sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA) &&
|
|
|
|
sbi->s_qf_names[USRQUOTA])
|
|
|
|
clear_opt(sbi->s_mount_opt, USRQUOTA);
|
|
|
|
|
|
|
|
if ((sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA) &&
|
|
|
|
sbi->s_qf_names[GRPQUOTA])
|
|
|
|
clear_opt(sbi->s_mount_opt, GRPQUOTA);
|
|
|
|
|
|
|
|
if ((sbi->s_qf_names[USRQUOTA] &&
|
|
|
|
(sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)) ||
|
|
|
|
(sbi->s_qf_names[GRPQUOTA] &&
|
|
|
|
(sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA))) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: old and new quota "
|
|
|
|
"format mixing.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!sbi->s_jquota_fmt) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: journalled quota format "
|
|
|
|
"not specified.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (sbi->s_jquota_fmt) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: journalled quota format "
|
|
|
|
"specified with no journalling "
|
|
|
|
"enabled.\n");
|
|
|
|
return 0;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es,
|
|
|
|
int read_only)
|
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
|
|
|
int res = 0;
|
|
|
|
|
|
|
|
if (le32_to_cpu(es->s_rev_level) > EXT3_MAX_SUPP_REV) {
|
|
|
|
printk (KERN_ERR "EXT3-fs warning: revision level too high, "
|
|
|
|
"forcing read-only mode\n");
|
|
|
|
res = MS_RDONLY;
|
|
|
|
}
|
|
|
|
if (read_only)
|
|
|
|
return res;
|
|
|
|
if (!(sbi->s_mount_state & EXT3_VALID_FS))
|
|
|
|
printk (KERN_WARNING "EXT3-fs warning: mounting unchecked fs, "
|
|
|
|
"running e2fsck is recommended\n");
|
|
|
|
else if ((sbi->s_mount_state & EXT3_ERROR_FS))
|
|
|
|
printk (KERN_WARNING
|
|
|
|
"EXT3-fs warning: mounting fs with errors, "
|
|
|
|
"running e2fsck is recommended\n");
|
|
|
|
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))
|
|
|
|
printk (KERN_WARNING
|
|
|
|
"EXT3-fs warning: maximal mount count reached, "
|
|
|
|
"running e2fsck is recommended\n");
|
|
|
|
else if (le32_to_cpu(es->s_checkinterval) &&
|
|
|
|
(le32_to_cpu(es->s_lastcheck) +
|
|
|
|
le32_to_cpu(es->s_checkinterval) <= get_seconds()))
|
|
|
|
printk (KERN_WARNING
|
|
|
|
"EXT3-fs warning: checktime reached, "
|
|
|
|
"running e2fsck is recommended\n");
|
|
|
|
#if 0
|
|
|
|
/* @@@ We _will_ want to clear the valid bit if we find
|
|
|
|
inconsistencies, to force a fsck at reboot. But for
|
|
|
|
a plain journaled filesystem we can keep it set as
|
|
|
|
valid forever! :) */
|
|
|
|
es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT3_VALID_FS);
|
|
|
|
#endif
|
|
|
|
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
|
|
|
|
es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT);
|
|
|
|
es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
|
|
|
|
es->s_mtime = cpu_to_le32(get_seconds());
|
|
|
|
ext3_update_dynamic_rev(sb);
|
|
|
|
EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
|
|
|
|
ext3_commit_super(sb, es, 1);
|
|
|
|
if (test_opt(sb, DEBUG))
|
|
|
|
printk(KERN_INFO "[EXT3 FS bs=%lu, gc=%lu, "
|
|
|
|
"bpg=%lu, ipg=%lu, mo=%04lx]\n",
|
|
|
|
sb->s_blocksize,
|
|
|
|
sbi->s_groups_count,
|
|
|
|
EXT3_BLOCKS_PER_GROUP(sb),
|
|
|
|
EXT3_INODES_PER_GROUP(sb),
|
|
|
|
sbi->s_mount_opt);
|
|
|
|
|
|
|
|
printk(KERN_INFO "EXT3 FS on %s, ", sb->s_id);
|
|
|
|
if (EXT3_SB(sb)->s_journal->j_inode == NULL) {
|
|
|
|
char b[BDEVNAME_SIZE];
|
|
|
|
|
|
|
|
printk("external journal on %s\n",
|
|
|
|
bdevname(EXT3_SB(sb)->s_journal->j_dev, b));
|
|
|
|
} else {
|
|
|
|
printk("internal journal\n");
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Called at mount-time, super-block is locked */
|
|
|
|
static int ext3_check_descriptors (struct super_block * sb)
|
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
|
|
|
|
ext3_fsblk_t last_block;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct ext3_group_desc * gdp = NULL;
|
|
|
|
int desc_block = 0;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
ext3_debug ("Checking group descriptors");
|
|
|
|
|
|
|
|
for (i = 0; i < sbi->s_groups_count; i++)
|
|
|
|
{
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
if (i == sbi->s_groups_count - 1)
|
|
|
|
last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
|
|
|
|
else
|
|
|
|
last_block = first_block +
|
|
|
|
(EXT3_BLOCKS_PER_GROUP(sb) - 1);
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0)
|
|
|
|
gdp = (struct ext3_group_desc *)
|
|
|
|
sbi->s_group_desc[desc_block++]->b_data;
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
|
|
|
|
le32_to_cpu(gdp->bg_block_bitmap) > last_block)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
ext3_error (sb, "ext3_check_descriptors",
|
|
|
|
"Block bitmap for group %d"
|
|
|
|
" not in group (block %lu)!",
|
|
|
|
i, (unsigned long)
|
|
|
|
le32_to_cpu(gdp->bg_block_bitmap));
|
|
|
|
return 0;
|
|
|
|
}
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
|
|
|
|
le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
ext3_error (sb, "ext3_check_descriptors",
|
|
|
|
"Inode bitmap for group %d"
|
|
|
|
" not in group (block %lu)!",
|
|
|
|
i, (unsigned long)
|
|
|
|
le32_to_cpu(gdp->bg_inode_bitmap));
|
|
|
|
return 0;
|
|
|
|
}
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
|
|
|
|
le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >
|
|
|
|
last_block)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
ext3_error (sb, "ext3_check_descriptors",
|
|
|
|
"Inode table for group %d"
|
|
|
|
" not in group (block %lu)!",
|
|
|
|
i, (unsigned long)
|
|
|
|
le32_to_cpu(gdp->bg_inode_table));
|
|
|
|
return 0;
|
|
|
|
}
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
first_block += EXT3_BLOCKS_PER_GROUP(sb);
|
2005-04-17 00:20:36 +02:00
|
|
|
gdp++;
|
|
|
|
}
|
|
|
|
|
|
|
|
sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb));
|
|
|
|
sbi->s_es->s_free_inodes_count=cpu_to_le32(ext3_count_free_inodes(sb));
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* ext3_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
|
|
|
|
* ext3_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 ext3_orphan_cleanup (struct super_block * sb,
|
|
|
|
struct ext3_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;
|
|
|
|
}
|
|
|
|
|
2006-12-07 05:40:13 +01:00
|
|
|
if (bdev_read_only(sb->s_bdev)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: write access "
|
|
|
|
"unavailable, skipping orphan cleanup.\n");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
if (EXT3_SB(sb)->s_mount_state & EXT3_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) {
|
|
|
|
printk(KERN_INFO "EXT3-fs: %s: orphan cleanup on readonly fs\n",
|
|
|
|
sb->s_id);
|
|
|
|
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 (EXT3_SB(sb)->s_qf_names[i]) {
|
|
|
|
int ret = ext3_quota_on_mount(sb, i);
|
|
|
|
if (ret < 0)
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: Cannot turn on journalled "
|
|
|
|
"quota: error %d\n", ret);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
while (es->s_last_orphan) {
|
|
|
|
struct inode *inode;
|
|
|
|
|
|
|
|
if (!(inode =
|
|
|
|
ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
|
|
|
|
es->s_last_orphan = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan);
|
|
|
|
DQUOT_INIT(inode);
|
|
|
|
if (inode->i_nlink) {
|
|
|
|
printk(KERN_DEBUG
|
2006-09-27 10:49:30 +02:00
|
|
|
"%s: truncating inode %lu to %Ld bytes\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
__FUNCTION__, inode->i_ino, inode->i_size);
|
2006-09-27 10:49:30 +02:00
|
|
|
jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
inode->i_ino, inode->i_size);
|
|
|
|
ext3_truncate(inode);
|
|
|
|
nr_truncates++;
|
|
|
|
} else {
|
|
|
|
printk(KERN_DEBUG
|
2006-09-27 10:49:30 +02:00
|
|
|
"%s: deleting unreferenced inode %lu\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
__FUNCTION__, inode->i_ino);
|
2006-09-27 10:49:30 +02:00
|
|
|
jbd_debug(2, "deleting unreferenced inode %lu\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
inode->i_ino);
|
|
|
|
nr_orphans++;
|
|
|
|
}
|
|
|
|
iput(inode); /* The delete magic happens here! */
|
|
|
|
}
|
|
|
|
|
|
|
|
#define PLURAL(x) (x), ((x)==1) ? "" : "s"
|
|
|
|
|
|
|
|
if (nr_orphans)
|
|
|
|
printk(KERN_INFO "EXT3-fs: %s: %d orphan inode%s deleted\n",
|
|
|
|
sb->s_id, PLURAL(nr_orphans));
|
|
|
|
if (nr_truncates)
|
|
|
|
printk(KERN_INFO "EXT3-fs: %s: %d truncate%s cleaned up\n",
|
|
|
|
sb->s_id, PLURAL(nr_truncates));
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
/* Turn quotas off */
|
|
|
|
for (i = 0; i < MAXQUOTAS; i++) {
|
|
|
|
if (sb_dqopt(sb)->files[i])
|
|
|
|
vfs_quota_off(sb, i);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Maximal file size. There is a direct, and {,double-,triple-}indirect
|
|
|
|
* block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
|
|
|
|
* We need to be 1 filesystem block less than the 2^32 sector limit.
|
|
|
|
*/
|
|
|
|
static loff_t ext3_max_size(int bits)
|
|
|
|
{
|
|
|
|
loff_t res = EXT3_NDIR_BLOCKS;
|
|
|
|
/* This constant is calculated to be the largest file size for a
|
|
|
|
* dense, 4k-blocksize file such that the total number of
|
|
|
|
* sectors in the file, including data and all indirect blocks,
|
|
|
|
* does not exceed 2^32. */
|
|
|
|
const loff_t upper_limit = 0x1ff7fffd000LL;
|
|
|
|
|
|
|
|
res += 1LL << (bits-2);
|
|
|
|
res += 1LL << (2*(bits-2));
|
|
|
|
res += 1LL << (3*(bits-2));
|
|
|
|
res <<= bits;
|
|
|
|
if (res > upper_limit)
|
|
|
|
res = upper_limit;
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
2006-06-25 14:48:07 +02:00
|
|
|
static ext3_fsblk_t descriptor_loc(struct super_block *sb,
|
|
|
|
ext3_fsblk_t logic_sb_block,
|
2005-04-17 00:20:36 +02:00
|
|
|
int nr)
|
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
2006-06-25 14:48:07 +02:00
|
|
|
unsigned long bg, first_meta_bg;
|
2005-04-17 00:20:36 +02:00
|
|
|
int has_super = 0;
|
|
|
|
|
|
|
|
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
|
|
|
|
|
|
|
|
if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_META_BG) ||
|
|
|
|
nr < first_meta_bg)
|
|
|
|
return (logic_sb_block + nr + 1);
|
|
|
|
bg = sbi->s_desc_per_block * nr;
|
|
|
|
if (ext3_bg_has_super(sb, bg))
|
|
|
|
has_super = 1;
|
2006-06-25 14:48:07 +02:00
|
|
|
return (has_super + ext3_group_first_block_no(sb, bg));
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int ext3_fill_super (struct super_block *sb, void *data, int silent)
|
|
|
|
{
|
|
|
|
struct buffer_head * bh;
|
|
|
|
struct ext3_super_block *es = NULL;
|
|
|
|
struct ext3_sb_info *sbi;
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t block;
|
|
|
|
ext3_fsblk_t sb_block = get_sb_block(&data);
|
|
|
|
ext3_fsblk_t logic_sb_block;
|
2005-04-17 00:20:36 +02:00
|
|
|
unsigned long offset = 0;
|
2006-09-27 10:49:30 +02:00
|
|
|
unsigned int journal_inum = 0;
|
2006-01-08 10:03:20 +01:00
|
|
|
unsigned long journal_devnum = 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
unsigned long def_mount_opts;
|
|
|
|
struct inode *root;
|
|
|
|
int blocksize;
|
|
|
|
int hblock;
|
|
|
|
int db_count;
|
|
|
|
int i;
|
|
|
|
int needs_recovery;
|
|
|
|
__le32 features;
|
|
|
|
|
2006-09-27 10:49:37 +02:00
|
|
|
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (!sbi)
|
|
|
|
return -ENOMEM;
|
|
|
|
sb->s_fs_info = sbi;
|
|
|
|
sbi->s_mount_opt = 0;
|
|
|
|
sbi->s_resuid = EXT3_DEF_RESUID;
|
|
|
|
sbi->s_resgid = EXT3_DEF_RESGID;
|
|
|
|
|
|
|
|
unlock_kernel();
|
|
|
|
|
|
|
|
blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
|
|
|
|
if (!blocksize) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: unable to set blocksize\n");
|
|
|
|
goto out_fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The ext3 superblock will not be buffer aligned for other than 1kB
|
|
|
|
* block sizes. We need to calculate the offset from buffer start.
|
|
|
|
*/
|
|
|
|
if (blocksize != EXT3_MIN_BLOCK_SIZE) {
|
|
|
|
logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
|
|
|
|
offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
|
|
|
|
} else {
|
|
|
|
logic_sb_block = sb_block;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(bh = sb_bread(sb, logic_sb_block))) {
|
|
|
|
printk (KERN_ERR "EXT3-fs: unable to read superblock\n");
|
|
|
|
goto out_fail;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Note: s_es must be initialized as soon as possible because
|
|
|
|
* some ext3 macro-instructions depend on its value
|
|
|
|
*/
|
|
|
|
es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
|
|
|
|
sbi->s_es = es;
|
|
|
|
sb->s_magic = le16_to_cpu(es->s_magic);
|
|
|
|
if (sb->s_magic != EXT3_SUPER_MAGIC)
|
|
|
|
goto cantfind_ext3;
|
|
|
|
|
|
|
|
/* Set defaults before we parse the mount options */
|
|
|
|
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
|
|
|
|
if (def_mount_opts & EXT3_DEFM_DEBUG)
|
|
|
|
set_opt(sbi->s_mount_opt, DEBUG);
|
|
|
|
if (def_mount_opts & EXT3_DEFM_BSDGROUPS)
|
|
|
|
set_opt(sbi->s_mount_opt, GRPID);
|
|
|
|
if (def_mount_opts & EXT3_DEFM_UID16)
|
|
|
|
set_opt(sbi->s_mount_opt, NO_UID32);
|
|
|
|
if (def_mount_opts & EXT3_DEFM_XATTR_USER)
|
|
|
|
set_opt(sbi->s_mount_opt, XATTR_USER);
|
|
|
|
if (def_mount_opts & EXT3_DEFM_ACL)
|
|
|
|
set_opt(sbi->s_mount_opt, POSIX_ACL);
|
|
|
|
if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_DATA)
|
|
|
|
sbi->s_mount_opt |= EXT3_MOUNT_JOURNAL_DATA;
|
|
|
|
else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_ORDERED)
|
|
|
|
sbi->s_mount_opt |= EXT3_MOUNT_ORDERED_DATA;
|
|
|
|
else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_WBACK)
|
|
|
|
sbi->s_mount_opt |= EXT3_MOUNT_WRITEBACK_DATA;
|
|
|
|
|
|
|
|
if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC)
|
|
|
|
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
|
|
|
|
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
|
|
|
|
set_opt(sbi->s_mount_opt, ERRORS_RO);
|
2006-10-11 10:21:49 +02:00
|
|
|
else
|
|
|
|
set_opt(sbi->s_mount_opt, ERRORS_CONT);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
|
|
|
|
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
|
|
|
|
|
|
|
|
set_opt(sbi->s_mount_opt, RESERVATION);
|
|
|
|
|
2006-01-08 10:03:20 +01:00
|
|
|
if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
|
|
|
|
NULL, 0))
|
2005-04-17 00:20:36 +02:00
|
|
|
goto failed_mount;
|
|
|
|
|
|
|
|
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
|
|
|
|
((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
|
|
|
|
|
|
|
|
if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV &&
|
|
|
|
(EXT3_HAS_COMPAT_FEATURE(sb, ~0U) ||
|
|
|
|
EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
|
|
|
|
EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U)))
|
2006-09-27 10:49:27 +02:00
|
|
|
printk(KERN_WARNING
|
2005-04-17 00:20:36 +02:00
|
|
|
"EXT3-fs warning: feature flags set on rev 0 fs, "
|
|
|
|
"running e2fsck is recommended\n");
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
features = EXT3_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP);
|
|
|
|
if (features) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: %s: couldn't mount because of "
|
|
|
|
"unsupported optional features (%x).\n",
|
|
|
|
sb->s_id, le32_to_cpu(features));
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
features = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP);
|
|
|
|
if (!(sb->s_flags & MS_RDONLY) && features) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: %s: couldn't mount RDWR because of "
|
|
|
|
"unsupported optional features (%x).\n",
|
|
|
|
sb->s_id, le32_to_cpu(features));
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
|
|
|
|
|
|
|
|
if (blocksize < EXT3_MIN_BLOCK_SIZE ||
|
|
|
|
blocksize > EXT3_MAX_BLOCK_SIZE) {
|
2006-09-27 10:49:27 +02:00
|
|
|
printk(KERN_ERR
|
2005-04-17 00:20:36 +02:00
|
|
|
"EXT3-fs: Unsupported filesystem blocksize %d on %s.\n",
|
|
|
|
blocksize, sb->s_id);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
|
|
|
|
hblock = bdev_hardsect_size(sb->s_bdev);
|
|
|
|
if (sb->s_blocksize != blocksize) {
|
|
|
|
/*
|
|
|
|
* Make sure the blocksize for the filesystem is larger
|
|
|
|
* than the hardware sectorsize for the machine.
|
|
|
|
*/
|
|
|
|
if (blocksize < hblock) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: blocksize %d too small for "
|
|
|
|
"device blocksize %d.\n", blocksize, hblock);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
|
|
|
|
brelse (bh);
|
|
|
|
sb_set_blocksize(sb, blocksize);
|
|
|
|
logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
|
|
|
|
offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
|
|
|
|
bh = sb_bread(sb, logic_sb_block);
|
|
|
|
if (!bh) {
|
2006-09-27 10:49:27 +02:00
|
|
|
printk(KERN_ERR
|
2005-04-17 00:20:36 +02:00
|
|
|
"EXT3-fs: Can't read superblock on 2nd try.\n");
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
es = (struct ext3_super_block *)(((char *)bh->b_data) + offset);
|
|
|
|
sbi->s_es = es;
|
|
|
|
if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) {
|
2006-09-27 10:49:27 +02:00
|
|
|
printk (KERN_ERR
|
2005-04-17 00:20:36 +02:00
|
|
|
"EXT3-fs: Magic mismatch, very weird !\n");
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
sb->s_maxbytes = ext3_max_size(sb->s_blocksize_bits);
|
|
|
|
|
|
|
|
if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV) {
|
|
|
|
sbi->s_inode_size = EXT3_GOOD_OLD_INODE_SIZE;
|
|
|
|
sbi->s_first_ino = EXT3_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 < EXT3_GOOD_OLD_INODE_SIZE) ||
|
|
|
|
(sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
|
|
|
|
(sbi->s_inode_size > blocksize)) {
|
|
|
|
printk (KERN_ERR
|
|
|
|
"EXT3-fs: unsupported inode size: %d\n",
|
|
|
|
sbi->s_inode_size);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
sbi->s_frag_size = EXT3_MIN_FRAG_SIZE <<
|
|
|
|
le32_to_cpu(es->s_log_frag_size);
|
|
|
|
if (blocksize != sbi->s_frag_size) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: fragsize %lu != blocksize %u (unsupported)\n",
|
|
|
|
sbi->s_frag_size, blocksize);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
sbi->s_frags_per_block = 1;
|
|
|
|
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
|
|
|
|
sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
|
|
|
|
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
|
|
|
|
if (EXT3_INODE_SIZE(sb) == 0)
|
|
|
|
goto cantfind_ext3;
|
|
|
|
sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
|
|
|
|
if (sbi->s_inodes_per_block == 0)
|
|
|
|
goto cantfind_ext3;
|
|
|
|
sbi->s_itb_per_group = sbi->s_inodes_per_group /
|
|
|
|
sbi->s_inodes_per_block;
|
|
|
|
sbi->s_desc_per_block = blocksize / sizeof(struct ext3_group_desc);
|
|
|
|
sbi->s_sbh = bh;
|
|
|
|
sbi->s_mount_state = le16_to_cpu(es->s_state);
|
2006-12-08 11:37:49 +01:00
|
|
|
sbi->s_addr_per_block_bits = ilog2(EXT3_ADDR_PER_BLOCK(sb));
|
|
|
|
sbi->s_desc_per_block_bits = ilog2(EXT3_DESC_PER_BLOCK(sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
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;
|
|
|
|
|
|
|
|
if (sbi->s_blocks_per_group > blocksize * 8) {
|
|
|
|
printk (KERN_ERR
|
|
|
|
"EXT3-fs: #blocks per group too big: %lu\n",
|
|
|
|
sbi->s_blocks_per_group);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
if (sbi->s_frags_per_group > blocksize * 8) {
|
|
|
|
printk (KERN_ERR
|
|
|
|
"EXT3-fs: #fragments per group too big: %lu\n",
|
|
|
|
sbi->s_frags_per_group);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
if (sbi->s_inodes_per_group > blocksize * 8) {
|
|
|
|
printk (KERN_ERR
|
|
|
|
"EXT3-fs: #inodes per group too big: %lu\n",
|
|
|
|
sbi->s_inodes_per_group);
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
|
2006-06-25 14:47:50 +02:00
|
|
|
if (le32_to_cpu(es->s_blocks_count) >
|
|
|
|
(sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: filesystem on %s:"
|
|
|
|
" too large to mount safely\n", sb->s_id);
|
|
|
|
if (sizeof(sector_t) < 8)
|
|
|
|
printk(KERN_WARNING "EXT3-fs: CONFIG_LBD not "
|
|
|
|
"enabled\n");
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
if (EXT3_BLOCKS_PER_GROUP(sb) == 0)
|
|
|
|
goto cantfind_ext3;
|
[PATCH] fix ext3 mounts at 16T
I need to do some actual IO testing now, but this gets things mounting for
a 16T ext3 filesystem. (patched up e2fsprogs is needed too, I'll send that
off the kernel list)
This patch fixes these issues in the kernel:
o sbi->s_groups_count overflows in ext3_fill_super()
sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) +
EXT3_BLOCKS_PER_GROUP(sb) - 1) /
EXT3_BLOCKS_PER_GROUP(sb);
at 16T, s_blocks_count is already maxed out; adding
EXT3_BLOCKS_PER_GROUP(sb) overflows it and groups_count comes out to 0.
Not really what we want, and causes a failed mount.
Feel free to check my math (actually, please do!), but changing it this
way should work & avoid the overflow:
(A + B - 1)/B changed to: ((A - 1)/B) + 1
o ext3_check_descriptors() overflows range checks
ext3_check_descriptors() iterates over all block groups making sure
that various bits are within the right block ranges... on the last pass
through, it is checking the error case
[item] >= block + EXT3_BLOCKS_PER_GROUP(sb)
where "block" is the first block in the last block group. The last
block in this group (and the last one that will fit in 32 bits) is block
+ EXT3_BLOCKS_PER_GROUP(sb)- 1. block + EXT3_BLOCKS_PER_GROUP(sb) wraps
back around to 0.
so, make things clearer with "first_block" and "last_block" where those
are first and last, inclusive, and use <, > rather than <, >=.
Finally, the last block group may be smaller than the rest, so account
for this on the last pass through: last_block = sb->s_blocks_count - 1;
(a similar patch could be done for ext2; does anyone in their right mind
use ext2 at 16T? I'll send an ext2 patch doing the same thing if that's
warranted)
Signed-off-by: Eric Sandeen <esandeen@redhat.com>
Cc: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 10:49:29 +02:00
|
|
|
sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
|
|
|
|
le32_to_cpu(es->s_first_data_block) - 1)
|
|
|
|
/ EXT3_BLOCKS_PER_GROUP(sb)) + 1;
|
2005-04-17 00:20:36 +02:00
|
|
|
db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) /
|
|
|
|
EXT3_DESC_PER_BLOCK(sb);
|
|
|
|
sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
|
|
|
|
GFP_KERNEL);
|
|
|
|
if (sbi->s_group_desc == NULL) {
|
|
|
|
printk (KERN_ERR "EXT3-fs: not enough memory\n");
|
|
|
|
goto failed_mount;
|
|
|
|
}
|
|
|
|
|
|
|
|
bgl_lock_init(&sbi->s_blockgroup_lock);
|
|
|
|
|
|
|
|
for (i = 0; i < db_count; i++) {
|
|
|
|
block = descriptor_loc(sb, logic_sb_block, i);
|
|
|
|
sbi->s_group_desc[i] = sb_bread(sb, block);
|
|
|
|
if (!sbi->s_group_desc[i]) {
|
|
|
|
printk (KERN_ERR "EXT3-fs: "
|
|
|
|
"can't read group descriptor %d\n", i);
|
|
|
|
db_count = i;
|
|
|
|
goto failed_mount2;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!ext3_check_descriptors (sb)) {
|
2006-06-25 14:47:52 +02:00
|
|
|
printk(KERN_ERR "EXT3-fs: group descriptors corrupted!\n");
|
2005-04-17 00:20:36 +02:00
|
|
|
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);
|
2006-06-23 11:05:41 +02:00
|
|
|
|
|
|
|
percpu_counter_init(&sbi->s_freeblocks_counter,
|
|
|
|
ext3_count_free_blocks(sb));
|
|
|
|
percpu_counter_init(&sbi->s_freeinodes_counter,
|
|
|
|
ext3_count_free_inodes(sb));
|
|
|
|
percpu_counter_init(&sbi->s_dirs_counter,
|
|
|
|
ext3_count_dirs(sb));
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* per fileystem reservation list head & lock */
|
|
|
|
spin_lock_init(&sbi->s_rsv_window_lock);
|
|
|
|
sbi->s_rsv_window_root = RB_ROOT;
|
|
|
|
/* Add a single, static dummy reservation to the start of the
|
|
|
|
* reservation window list --- it gives us a placeholder for
|
|
|
|
* append-at-start-of-list which makes the allocation logic
|
|
|
|
* _much_ simpler. */
|
|
|
|
sbi->s_rsv_window_head.rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
|
|
|
|
sbi->s_rsv_window_head.rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
|
|
|
|
sbi->s_rsv_window_head.rsv_alloc_hit = 0;
|
|
|
|
sbi->s_rsv_window_head.rsv_goal_size = 0;
|
|
|
|
ext3_rsv_window_add(sb, &sbi->s_rsv_window_head);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* set up enough so that it can read an inode
|
|
|
|
*/
|
|
|
|
sb->s_op = &ext3_sops;
|
|
|
|
sb->s_export_op = &ext3_export_ops;
|
|
|
|
sb->s_xattr = ext3_xattr_handlers;
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
sb->s_qcop = &ext3_qctl_operations;
|
|
|
|
sb->dq_op = &ext3_quota_operations;
|
|
|
|
#endif
|
|
|
|
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
|
|
|
|
|
|
|
|
sb->s_root = NULL;
|
|
|
|
|
|
|
|
needs_recovery = (es->s_last_orphan != 0 ||
|
|
|
|
EXT3_HAS_INCOMPAT_FEATURE(sb,
|
|
|
|
EXT3_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) &&
|
|
|
|
EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) {
|
2006-01-08 10:03:20 +01:00
|
|
|
if (ext3_load_journal(sb, es, journal_devnum))
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount3;
|
2005-04-17 00:20:36 +02:00
|
|
|
} else if (journal_inum) {
|
|
|
|
if (ext3_create_journal(sb, es, journal_inum))
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount3;
|
2005-04-17 00:20:36 +02:00
|
|
|
} else {
|
|
|
|
if (!silent)
|
|
|
|
printk (KERN_ERR
|
|
|
|
"ext3: No journal on filesystem on %s\n",
|
|
|
|
sb->s_id);
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount3;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* 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 (journal_check_available_features
|
|
|
|
(sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE))
|
|
|
|
set_opt(sbi->s_mount_opt, ORDERED_DATA);
|
|
|
|
else
|
|
|
|
set_opt(sbi->s_mount_opt, JOURNAL_DATA);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case EXT3_MOUNT_ORDERED_DATA:
|
|
|
|
case EXT3_MOUNT_WRITEBACK_DATA:
|
|
|
|
if (!journal_check_available_features
|
|
|
|
(sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: Journal does not support "
|
|
|
|
"requested data journaling mode\n");
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount4;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (test_opt(sb, NOBH)) {
|
|
|
|
if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) {
|
|
|
|
printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - "
|
|
|
|
"its supported only with writeback mode\n");
|
|
|
|
clear_opt(sbi->s_mount_opt, NOBH);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* The journal_load will have done any necessary log recovery,
|
|
|
|
* so we can safely mount the rest of the filesystem now.
|
|
|
|
*/
|
|
|
|
|
|
|
|
root = iget(sb, EXT3_ROOT_INO);
|
|
|
|
sb->s_root = d_alloc_root(root);
|
|
|
|
if (!sb->s_root) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: get root inode failed\n");
|
|
|
|
iput(root);
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount4;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
|
|
|
|
dput(sb->s_root);
|
|
|
|
sb->s_root = NULL;
|
|
|
|
printk(KERN_ERR "EXT3-fs: corrupt root inode, run e2fsck\n");
|
2006-06-23 11:05:41 +02:00
|
|
|
goto failed_mount4;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
|
|
|
|
/*
|
|
|
|
* akpm: core read_super() calls in here with the superblock locked.
|
|
|
|
* That deadlocks, because orphan cleanup needs to lock the superblock
|
|
|
|
* in numerous places. Here we just pop the lock - it's relatively
|
|
|
|
* harmless, because we are now ready to accept write_super() requests,
|
|
|
|
* and aviro says that's the only reason for hanging onto the
|
|
|
|
* superblock lock.
|
|
|
|
*/
|
|
|
|
EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
|
|
|
|
ext3_orphan_cleanup(sb, es);
|
|
|
|
EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS;
|
|
|
|
if (needs_recovery)
|
|
|
|
printk (KERN_INFO "EXT3-fs: recovery complete.\n");
|
|
|
|
ext3_mark_recovery_complete(sb, es);
|
|
|
|
printk (KERN_INFO "EXT3-fs: mounted filesystem with %s data mode.\n",
|
|
|
|
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
|
|
|
|
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
|
|
|
|
"writeback");
|
|
|
|
|
|
|
|
lock_kernel();
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
cantfind_ext3:
|
|
|
|
if (!silent)
|
|
|
|
printk(KERN_ERR "VFS: Can't find ext3 filesystem on dev %s.\n",
|
|
|
|
sb->s_id);
|
|
|
|
goto failed_mount;
|
|
|
|
|
2006-06-23 11:05:41 +02:00
|
|
|
failed_mount4:
|
2005-04-17 00:20:36 +02:00
|
|
|
journal_destroy(sbi->s_journal);
|
2006-06-23 11:05:41 +02:00
|
|
|
failed_mount3:
|
|
|
|
percpu_counter_destroy(&sbi->s_freeblocks_counter);
|
|
|
|
percpu_counter_destroy(&sbi->s_freeinodes_counter);
|
|
|
|
percpu_counter_destroy(&sbi->s_dirs_counter);
|
2005-04-17 00:20:36 +02:00
|
|
|
failed_mount2:
|
|
|
|
for (i = 0; i < db_count; i++)
|
|
|
|
brelse(sbi->s_group_desc[i]);
|
|
|
|
kfree(sbi->s_group_desc);
|
|
|
|
failed_mount:
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
for (i = 0; i < MAXQUOTAS; i++)
|
|
|
|
kfree(sbi->s_qf_names[i]);
|
|
|
|
#endif
|
|
|
|
ext3_blkdev_remove(sbi);
|
|
|
|
brelse(bh);
|
|
|
|
out_fail:
|
|
|
|
sb->s_fs_info = NULL;
|
|
|
|
kfree(sbi);
|
|
|
|
lock_kernel();
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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
|
2006-09-27 10:49:27 +02:00
|
|
|
* done any recovery; and again on any subsequent remount.
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
|
|
|
static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
|
|
|
|
{
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
|
|
|
|
|
|
|
if (sbi->s_commit_interval)
|
|
|
|
journal->j_commit_interval = sbi->s_commit_interval;
|
|
|
|
/* We could also set up an ext3-specific default for the commit
|
|
|
|
* interval here, but for now we'll just fall back to the jbd
|
|
|
|
* default. */
|
|
|
|
|
|
|
|
spin_lock(&journal->j_state_lock);
|
|
|
|
if (test_opt(sb, BARRIER))
|
|
|
|
journal->j_flags |= JFS_BARRIER;
|
|
|
|
else
|
|
|
|
journal->j_flags &= ~JFS_BARRIER;
|
|
|
|
spin_unlock(&journal->j_state_lock);
|
|
|
|
}
|
|
|
|
|
2006-09-27 10:49:30 +02:00
|
|
|
static journal_t *ext3_get_journal(struct super_block *sb,
|
|
|
|
unsigned int journal_inum)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
struct inode *journal_inode;
|
|
|
|
journal_t *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 = iget(sb, journal_inum);
|
|
|
|
if (!journal_inode) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: no journal found.\n");
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
if (!journal_inode->i_nlink) {
|
|
|
|
make_bad_inode(journal_inode);
|
|
|
|
iput(journal_inode);
|
|
|
|
printk(KERN_ERR "EXT3-fs: journal inode is deleted.\n");
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
|
|
|
|
journal_inode, journal_inode->i_size);
|
|
|
|
if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: invalid journal inode.\n");
|
|
|
|
iput(journal_inode);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
journal = journal_init_inode(journal_inode);
|
|
|
|
if (!journal) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: Could not load journal inode\n");
|
|
|
|
iput(journal_inode);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
journal->j_private = sb;
|
|
|
|
ext3_init_journal_params(sb, journal);
|
|
|
|
return journal;
|
|
|
|
}
|
|
|
|
|
|
|
|
static journal_t *ext3_get_dev_journal(struct super_block *sb,
|
|
|
|
dev_t j_dev)
|
|
|
|
{
|
|
|
|
struct buffer_head * bh;
|
|
|
|
journal_t *journal;
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t start;
|
[PATCH] ext3_fsblk_t: filesystem, group blocks and bug fixes
Some of the in-kernel ext3 block variable type are treated as signed 4 bytes
int type, thus limited ext3 filesystem to 8TB (4kblock size based). While
trying to fix them, it seems quite confusing in the ext3 code where some
blocks are filesystem-wide blocks, some are group relative offsets that need
to be signed value (as -1 has special meaning). So it seem saner to define
two types of physical blocks: one is filesystem wide blocks, another is
group-relative blocks. The following patches clarify these two types of
blocks in the ext3 code, and fix the type bugs which limit current 32 bit ext3
filesystem limit to 8TB.
With this series of patches and the percpu counter data type changes in the mm
tree, we are able to extend exts filesystem limit to 16TB.
This work is also a pre-request for the recent >32 bit ext3 work, and makes
the kernel to able to address 48 bit ext3 block a lot easier: Simply redefine
ext3_fsblk_t from unsigned long to sector_t and redefine the format string for
ext3 filesystem block corresponding.
Two RFC with a series patches have been posted to ext2-devel list and have
been reviewed and discussed:
http://marc.theaimsgroup.com/?l=ext2-devel&m=114722190816690&w=2
http://marc.theaimsgroup.com/?l=ext2-devel&m=114784919525942&w=2
Patches are tested on both 32 bit machine and 64 bit machine, <8TB ext3 and
>8TB ext3 filesystem(with the latest to be released e2fsprogs-1.39). Tests
includes overnight fsx, tiobench, dbench and fsstress.
This patch:
Defines ext3_fsblk_t and ext3_grpblk_t, and the printk format string for
filesystem wide blocks.
This patch classifies all block group relative blocks, and ext3_fsblk_t blocks
occurs in the same function where used to be confusing before. Also include
kernel bug fixes for filesystem wide in-kernel block variables. There are
some fileystem wide blocks are treated as int/unsigned int type in the kernel
currently, especially in ext3 block allocation and reservation code. This
patch fixed those bugs by converting those variables to ext3_fsblk_t(unsigned
long) type.
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 14:48:06 +02:00
|
|
|
ext3_fsblk_t len;
|
2005-04-17 00:20:36 +02:00
|
|
|
int hblock, blocksize;
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t sb_block;
|
2005-04-17 00:20:36 +02:00
|
|
|
unsigned long offset;
|
|
|
|
struct ext3_super_block * es;
|
|
|
|
struct block_device *bdev;
|
|
|
|
|
|
|
|
bdev = ext3_blkdev_get(j_dev);
|
|
|
|
if (bdev == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (bd_claim(bdev, sb)) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3: failed to claim external journal device.\n");
|
|
|
|
blkdev_put(bdev);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
blocksize = sb->s_blocksize;
|
|
|
|
hblock = bdev_hardsect_size(bdev);
|
|
|
|
if (blocksize < hblock) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"EXT3-fs: blocksize too small for journal device.\n");
|
|
|
|
goto out_bdev;
|
|
|
|
}
|
|
|
|
|
|
|
|
sb_block = EXT3_MIN_BLOCK_SIZE / blocksize;
|
|
|
|
offset = EXT3_MIN_BLOCK_SIZE % blocksize;
|
|
|
|
set_blocksize(bdev, blocksize);
|
|
|
|
if (!(bh = __bread(bdev, sb_block, blocksize))) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: couldn't read superblock of "
|
|
|
|
"external journal\n");
|
|
|
|
goto out_bdev;
|
|
|
|
}
|
|
|
|
|
|
|
|
es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
|
|
|
|
if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) ||
|
|
|
|
!(le32_to_cpu(es->s_feature_incompat) &
|
|
|
|
EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: external journal has "
|
|
|
|
"bad superblock\n");
|
|
|
|
brelse(bh);
|
|
|
|
goto out_bdev;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (memcmp(EXT3_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: journal UUID does not match\n");
|
|
|
|
brelse(bh);
|
|
|
|
goto out_bdev;
|
|
|
|
}
|
|
|
|
|
|
|
|
len = le32_to_cpu(es->s_blocks_count);
|
|
|
|
start = sb_block + 1;
|
|
|
|
brelse(bh); /* we're done with the superblock */
|
|
|
|
|
|
|
|
journal = journal_init_dev(bdev, sb->s_bdev,
|
|
|
|
start, len, blocksize);
|
|
|
|
if (!journal) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: failed to create device journal\n");
|
|
|
|
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)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: I/O error on journal device\n");
|
|
|
|
goto out_journal;
|
|
|
|
}
|
|
|
|
if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: External journal has more than one "
|
|
|
|
"user (unsupported) - %d\n",
|
|
|
|
be32_to_cpu(journal->j_superblock->s_nr_users));
|
|
|
|
goto out_journal;
|
|
|
|
}
|
|
|
|
EXT3_SB(sb)->journal_bdev = bdev;
|
|
|
|
ext3_init_journal_params(sb, journal);
|
|
|
|
return journal;
|
|
|
|
out_journal:
|
|
|
|
journal_destroy(journal);
|
|
|
|
out_bdev:
|
|
|
|
ext3_blkdev_put(bdev);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2006-01-08 10:03:20 +01:00
|
|
|
static int ext3_load_journal(struct super_block *sb,
|
|
|
|
struct ext3_super_block *es,
|
|
|
|
unsigned long journal_devnum)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
journal_t *journal;
|
2006-09-27 10:49:30 +02:00
|
|
|
unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
|
2006-01-08 10:03:20 +01:00
|
|
|
dev_t journal_dev;
|
2005-04-17 00:20:36 +02:00
|
|
|
int err = 0;
|
|
|
|
int really_read_only;
|
|
|
|
|
2006-01-08 10:03:20 +01:00
|
|
|
if (journal_devnum &&
|
|
|
|
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
|
|
|
|
printk(KERN_INFO "EXT3-fs: external journal device major/minor "
|
|
|
|
"numbers have changed\n");
|
|
|
|
journal_dev = new_decode_dev(journal_devnum);
|
|
|
|
} else
|
|
|
|
journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
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 (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER)) {
|
|
|
|
if (sb->s_flags & MS_RDONLY) {
|
|
|
|
printk(KERN_INFO "EXT3-fs: INFO: recovery "
|
|
|
|
"required on readonly filesystem.\n");
|
|
|
|
if (really_read_only) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: write access "
|
|
|
|
"unavailable, cannot proceed.\n");
|
|
|
|
return -EROFS;
|
|
|
|
}
|
|
|
|
printk (KERN_INFO "EXT3-fs: write access will "
|
|
|
|
"be enabled during recovery.\n");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (journal_inum && journal_dev) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: filesystem has both journal "
|
|
|
|
"and inode journals!\n");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (journal_inum) {
|
|
|
|
if (!(journal = ext3_get_journal(sb, journal_inum)))
|
|
|
|
return -EINVAL;
|
|
|
|
} else {
|
|
|
|
if (!(journal = ext3_get_dev_journal(sb, journal_dev)))
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
|
|
|
|
err = journal_update_format(journal);
|
|
|
|
if (err) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: error updating journal.\n");
|
|
|
|
journal_destroy(journal);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER))
|
|
|
|
err = journal_wipe(journal, !really_read_only);
|
|
|
|
if (!err)
|
|
|
|
err = journal_load(journal);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: error loading journal.\n");
|
|
|
|
journal_destroy(journal);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXT3_SB(sb)->s_journal = journal;
|
|
|
|
ext3_clear_journal_err(sb, es);
|
2006-01-08 10:03:20 +01:00
|
|
|
|
|
|
|
if (journal_devnum &&
|
|
|
|
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
|
|
|
|
es->s_journal_dev = cpu_to_le32(journal_devnum);
|
|
|
|
sb->s_dirt = 1;
|
|
|
|
|
|
|
|
/* Make sure we flush the recovery flag to disk. */
|
|
|
|
ext3_commit_super(sb, es, 1);
|
|
|
|
}
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_create_journal(struct super_block * sb,
|
|
|
|
struct ext3_super_block * es,
|
2006-09-27 10:49:30 +02:00
|
|
|
unsigned int journal_inum)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
journal_t *journal;
|
|
|
|
|
|
|
|
if (sb->s_flags & MS_RDONLY) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to "
|
|
|
|
"create journal.\n");
|
|
|
|
return -EROFS;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(journal = ext3_get_journal(sb, journal_inum)))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2006-09-27 10:49:30 +02:00
|
|
|
printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n",
|
2005-04-17 00:20:36 +02:00
|
|
|
journal_inum);
|
|
|
|
|
|
|
|
if (journal_create(journal)) {
|
|
|
|
printk(KERN_ERR "EXT3-fs: error creating journal.\n");
|
|
|
|
journal_destroy(journal);
|
|
|
|
return -EIO;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXT3_SB(sb)->s_journal = journal;
|
|
|
|
|
|
|
|
ext3_update_dynamic_rev(sb);
|
|
|
|
EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL);
|
|
|
|
|
|
|
|
es->s_journal_inum = cpu_to_le32(journal_inum);
|
|
|
|
sb->s_dirt = 1;
|
|
|
|
|
|
|
|
/* Make sure we flush the recovery flag to disk. */
|
|
|
|
ext3_commit_super(sb, es, 1);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void ext3_commit_super (struct super_block * sb,
|
|
|
|
struct ext3_super_block * es,
|
|
|
|
int sync)
|
|
|
|
{
|
|
|
|
struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;
|
|
|
|
|
|
|
|
if (!sbh)
|
|
|
|
return;
|
|
|
|
es->s_wtime = cpu_to_le32(get_seconds());
|
|
|
|
es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));
|
|
|
|
es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));
|
|
|
|
BUFFER_TRACE(sbh, "marking dirty");
|
|
|
|
mark_buffer_dirty(sbh);
|
|
|
|
if (sync)
|
|
|
|
sync_dirty_buffer(sbh);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 ext3_mark_recovery_complete(struct super_block * sb,
|
|
|
|
struct ext3_super_block * es)
|
|
|
|
{
|
|
|
|
journal_t *journal = EXT3_SB(sb)->s_journal;
|
|
|
|
|
|
|
|
journal_lock_updates(journal);
|
|
|
|
journal_flush(journal);
|
|
|
|
if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
|
|
|
|
sb->s_flags & MS_RDONLY) {
|
|
|
|
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
sb->s_dirt = 0;
|
|
|
|
ext3_commit_super(sb, es, 1);
|
|
|
|
}
|
|
|
|
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 ext3_clear_journal_err(struct super_block * sb,
|
|
|
|
struct ext3_super_block * es)
|
|
|
|
{
|
|
|
|
journal_t *journal;
|
|
|
|
int j_errno;
|
|
|
|
const char *errstr;
|
|
|
|
|
|
|
|
journal = EXT3_SB(sb)->s_journal;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now check for any error status which may have been recorded in the
|
|
|
|
* journal by a prior ext3_error() or ext3_abort()
|
|
|
|
*/
|
|
|
|
|
|
|
|
j_errno = journal_errno(journal);
|
|
|
|
if (j_errno) {
|
|
|
|
char nbuf[16];
|
|
|
|
|
|
|
|
errstr = ext3_decode_error(sb, j_errno, nbuf);
|
|
|
|
ext3_warning(sb, __FUNCTION__, "Filesystem error recorded "
|
|
|
|
"from previous mount: %s", errstr);
|
|
|
|
ext3_warning(sb, __FUNCTION__, "Marking fs in need of "
|
|
|
|
"filesystem check.");
|
|
|
|
|
|
|
|
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
|
|
|
|
es->s_state |= cpu_to_le16(EXT3_ERROR_FS);
|
|
|
|
ext3_commit_super (sb, es, 1);
|
|
|
|
|
|
|
|
journal_clear_err(journal);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Force the running and committing transactions to commit,
|
|
|
|
* and wait on the commit.
|
|
|
|
*/
|
|
|
|
int ext3_force_commit(struct super_block *sb)
|
|
|
|
{
|
|
|
|
journal_t *journal;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (sb->s_flags & MS_RDONLY)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
journal = EXT3_SB(sb)->s_journal;
|
|
|
|
sb->s_dirt = 0;
|
|
|
|
ret = ext3_journal_force_commit(journal);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ext3 always journals updates to the superblock itself, so we don't
|
|
|
|
* have to propagate any other updates to the superblock on disk at this
|
|
|
|
* point. Just start an async writeback to get the buffers on their way
|
|
|
|
* to the disk.
|
|
|
|
*
|
|
|
|
* This implicitly triggers the writebehind on sync().
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void ext3_write_super (struct super_block * sb)
|
|
|
|
{
|
2006-01-10 00:59:25 +01:00
|
|
|
if (mutex_trylock(&sb->s_lock) != 0)
|
2005-04-17 00:20:36 +02:00
|
|
|
BUG();
|
|
|
|
sb->s_dirt = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_sync_fs(struct super_block *sb, int wait)
|
|
|
|
{
|
|
|
|
tid_t target;
|
|
|
|
|
|
|
|
sb->s_dirt = 0;
|
|
|
|
if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
|
|
|
|
if (wait)
|
|
|
|
log_wait_commit(EXT3_SB(sb)->s_journal, target);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 void ext3_write_super_lockfs(struct super_block *sb)
|
|
|
|
{
|
|
|
|
sb->s_dirt = 0;
|
|
|
|
|
|
|
|
if (!(sb->s_flags & MS_RDONLY)) {
|
|
|
|
journal_t *journal = EXT3_SB(sb)->s_journal;
|
|
|
|
|
|
|
|
/* Now we set up the journal barrier. */
|
|
|
|
journal_lock_updates(journal);
|
|
|
|
journal_flush(journal);
|
|
|
|
|
|
|
|
/* Journal blocked and flushed, clear needs_recovery flag. */
|
|
|
|
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 void ext3_unlockfs(struct super_block *sb)
|
|
|
|
{
|
|
|
|
if (!(sb->s_flags & MS_RDONLY)) {
|
|
|
|
lock_super(sb);
|
|
|
|
/* Reser the needs_recovery flag before the fs is unlocked. */
|
|
|
|
EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
|
|
|
|
ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
|
|
|
|
unlock_super(sb);
|
|
|
|
journal_unlock_updates(EXT3_SB(sb)->s_journal);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_remount (struct super_block * sb, int * flags, char * data)
|
|
|
|
{
|
|
|
|
struct ext3_super_block * es;
|
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t n_blocks_count = 0;
|
2005-07-12 22:58:28 +02:00
|
|
|
unsigned long old_sb_flags;
|
|
|
|
struct ext3_mount_options old_opts;
|
|
|
|
int err;
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
int i;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Store the original options */
|
|
|
|
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;
|
|
|
|
#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
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Allow the "check" option to be passed as a remount option.
|
|
|
|
*/
|
2006-01-08 10:03:20 +01:00
|
|
|
if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
|
2005-07-12 22:58:28 +02:00
|
|
|
err = -EINVAL;
|
|
|
|
goto restore_opts;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
|
|
|
|
ext3_abort(sb, __FUNCTION__, "Abort forced by user");
|
|
|
|
|
|
|
|
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
|
|
|
|
((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
|
|
|
|
|
|
|
|
es = sbi->s_es;
|
|
|
|
|
|
|
|
ext3_init_journal_params(sb, sbi->s_journal);
|
|
|
|
|
|
|
|
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
|
|
|
|
n_blocks_count > le32_to_cpu(es->s_blocks_count)) {
|
2005-07-12 22:58:28 +02:00
|
|
|
if (sbi->s_mount_opt & EXT3_MOUNT_ABORT) {
|
|
|
|
err = -EROFS;
|
|
|
|
goto restore_opts;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (*flags & MS_RDONLY) {
|
|
|
|
/*
|
|
|
|
* 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(EXT3_VALID_FS)) &&
|
|
|
|
(sbi->s_mount_state & EXT3_VALID_FS))
|
|
|
|
es->s_state = cpu_to_le16(sbi->s_mount_state);
|
|
|
|
|
|
|
|
ext3_mark_recovery_complete(sb, es);
|
|
|
|
} else {
|
|
|
|
__le32 ret;
|
|
|
|
if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb,
|
|
|
|
~EXT3_FEATURE_RO_COMPAT_SUPP))) {
|
|
|
|
printk(KERN_WARNING "EXT3-fs: %s: couldn't "
|
|
|
|
"remount RDWR because of unsupported "
|
|
|
|
"optional features (%x).\n",
|
|
|
|
sb->s_id, le32_to_cpu(ret));
|
2005-07-12 22:58:28 +02:00
|
|
|
err = -EROFS;
|
|
|
|
goto restore_opts;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
/*
|
|
|
|
* 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.)
|
|
|
|
*/
|
|
|
|
ext3_clear_journal_err(sb, es);
|
|
|
|
sbi->s_mount_state = le16_to_cpu(es->s_state);
|
2006-09-27 10:49:36 +02:00
|
|
|
if ((err = ext3_group_extend(sb, es, n_blocks_count)))
|
2005-07-12 22:58:28 +02:00
|
|
|
goto restore_opts;
|
2005-04-17 00:20:36 +02:00
|
|
|
if (!ext3_setup_super (sb, es, 0))
|
|
|
|
sb->s_flags &= ~MS_RDONLY;
|
|
|
|
}
|
|
|
|
}
|
2005-07-12 22:58:28 +02:00
|
|
|
#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
|
2005-04-17 00:20:36 +02:00
|
|
|
return 0;
|
2005-07-12 22:58:28 +02:00
|
|
|
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;
|
|
|
|
#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
|
|
|
|
return err;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
2006-06-23 11:02:58 +02:00
|
|
|
static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2006-06-23 11:02:58 +02:00
|
|
|
struct super_block *sb = dentry->d_sb;
|
2006-03-24 12:16:16 +01:00
|
|
|
struct ext3_sb_info *sbi = EXT3_SB(sb);
|
|
|
|
struct ext3_super_block *es = sbi->s_es;
|
2006-06-25 14:48:07 +02:00
|
|
|
ext3_fsblk_t overhead;
|
2005-04-17 00:20:36 +02:00
|
|
|
int i;
|
2006-12-07 05:35:28 +01:00
|
|
|
u64 fsid;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
if (test_opt (sb, MINIX_DF))
|
|
|
|
overhead = 0;
|
|
|
|
else {
|
|
|
|
unsigned long ngroups;
|
|
|
|
ngroups = EXT3_SB(sb)->s_groups_count;
|
|
|
|
smp_rmb();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Compute the overhead (FS structures)
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 += ext3_bg_has_super(sb, i) +
|
|
|
|
ext3_bg_num_gdb(sb, i);
|
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Every block group has an inode bitmap, a block
|
|
|
|
* bitmap, and an inode table.
|
|
|
|
*/
|
|
|
|
overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group));
|
|
|
|
}
|
|
|
|
|
|
|
|
buf->f_type = EXT3_SUPER_MAGIC;
|
|
|
|
buf->f_bsize = sb->s_blocksize;
|
|
|
|
buf->f_blocks = le32_to_cpu(es->s_blocks_count) - overhead;
|
2006-03-24 12:16:16 +01:00
|
|
|
buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
|
2005-04-17 00:20:36 +02:00
|
|
|
buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
|
|
|
|
if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
|
|
|
|
buf->f_bavail = 0;
|
|
|
|
buf->f_files = le32_to_cpu(es->s_inodes_count);
|
2006-03-24 12:16:16 +01:00
|
|
|
buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
|
2005-04-17 00:20:36 +02:00
|
|
|
buf->f_namelen = EXT3_NAME_LEN;
|
2006-12-07 05:35:28 +01:00
|
|
|
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;
|
2005-04-17 00:20:36 +02:00
|
|
|
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
|
|
|
|
* ext3_create() quota_sync()
|
|
|
|
* journal_start() write_dquot()
|
2006-03-23 12:00:29 +01:00
|
|
|
* DQUOT_INIT() down(dqio_mutex)
|
|
|
|
* down(dqio_mutex) journal_start()
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#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 ext3_dquot_initialize(struct inode *inode, int type)
|
|
|
|
{
|
|
|
|
handle_t *handle;
|
|
|
|
int ret, err;
|
|
|
|
|
|
|
|
/* We may create quota structure so we need to reserve enough blocks */
|
2005-06-24 07:01:04 +02:00
|
|
|
handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS(inode->i_sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_initialize(inode, type);
|
|
|
|
err = ext3_journal_stop(handle);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_dquot_drop(struct inode *inode)
|
|
|
|
{
|
|
|
|
handle_t *handle;
|
|
|
|
int ret, err;
|
|
|
|
|
|
|
|
/* We may delete quota structure so we need to reserve enough blocks */
|
2005-06-24 07:01:04 +02:00
|
|
|
handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_drop(inode);
|
|
|
|
err = ext3_journal_stop(handle);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_write_dquot(struct dquot *dquot)
|
|
|
|
{
|
|
|
|
int ret, err;
|
|
|
|
handle_t *handle;
|
|
|
|
struct inode *inode;
|
|
|
|
|
|
|
|
inode = dquot_to_inode(dquot);
|
|
|
|
handle = ext3_journal_start(inode,
|
2005-06-24 07:01:04 +02:00
|
|
|
EXT3_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_commit(dquot);
|
|
|
|
err = ext3_journal_stop(handle);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_acquire_dquot(struct dquot *dquot)
|
|
|
|
{
|
|
|
|
int ret, err;
|
|
|
|
handle_t *handle;
|
|
|
|
|
|
|
|
handle = ext3_journal_start(dquot_to_inode(dquot),
|
2005-06-24 07:01:04 +02:00
|
|
|
EXT3_QUOTA_INIT_BLOCKS(dquot->dq_sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_acquire(dquot);
|
|
|
|
err = ext3_journal_stop(handle);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_release_dquot(struct dquot *dquot)
|
|
|
|
{
|
|
|
|
int ret, err;
|
|
|
|
handle_t *handle;
|
|
|
|
|
|
|
|
handle = ext3_journal_start(dquot_to_inode(dquot),
|
2005-06-24 07:01:04 +02:00
|
|
|
EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb));
|
2005-04-17 00:20:36 +02:00
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_release(dquot);
|
|
|
|
err = ext3_journal_stop(handle);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_mark_dquot_dirty(struct dquot *dquot)
|
|
|
|
{
|
|
|
|
/* Are we journalling quotas? */
|
|
|
|
if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
|
|
|
|
EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
|
|
|
|
dquot_mark_dquot_dirty(dquot);
|
|
|
|
return ext3_write_dquot(dquot);
|
|
|
|
} else {
|
|
|
|
return dquot_mark_dquot_dirty(dquot);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ext3_write_info(struct super_block *sb, int type)
|
|
|
|
{
|
|
|
|
int ret, err;
|
|
|
|
handle_t *handle;
|
|
|
|
|
|
|
|
/* Data block + inode block */
|
|
|
|
handle = ext3_journal_start(sb->s_root->d_inode, 2);
|
|
|
|
if (IS_ERR(handle))
|
|
|
|
return PTR_ERR(handle);
|
|
|
|
ret = dquot_commit_info(sb, type);
|
|
|
|
err = ext3_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 ext3_quota_on_mount(struct super_block *sb, int type)
|
|
|
|
{
|
2005-06-23 09:09:16 +02:00
|
|
|
return vfs_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type],
|
|
|
|
EXT3_SB(sb)->s_jquota_fmt, type);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Standard function to be called on quota_on
|
|
|
|
*/
|
|
|
|
static int ext3_quota_on(struct super_block *sb, int type, int format_id,
|
|
|
|
char *path)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct nameidata nd;
|
|
|
|
|
2005-06-24 07:01:04 +02:00
|
|
|
if (!test_opt(sb, QUOTA))
|
|
|
|
return -EINVAL;
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Not journalling quota? */
|
|
|
|
if (!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
|
|
|
|
!EXT3_SB(sb)->s_qf_names[GRPQUOTA])
|
|
|
|
return vfs_quota_on(sb, type, format_id, path);
|
|
|
|
err = path_lookup(path, LOOKUP_FOLLOW, &nd);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
/* Quotafile not on the same filesystem? */
|
|
|
|
if (nd.mnt->mnt_sb != sb) {
|
|
|
|
path_release(&nd);
|
|
|
|
return -EXDEV;
|
|
|
|
}
|
|
|
|
/* Quotafile not of fs root? */
|
|
|
|
if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode)
|
|
|
|
printk(KERN_WARNING
|
|
|
|
"EXT3-fs: Quota file not on filesystem root. "
|
|
|
|
"Journalled quota will not work.\n");
|
|
|
|
path_release(&nd);
|
|
|
|
return vfs_quota_on(sb, type, format_id, path);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* 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 ext3_quota_read(struct super_block *sb, int type, char *data,
|
|
|
|
size_t len, loff_t off)
|
|
|
|
{
|
|
|
|
struct inode *inode = sb_dqopt(sb)->files[type];
|
|
|
|
sector_t blk = off >> EXT3_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 = ext3_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 ext3_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];
|
|
|
|
sector_t blk = off >> EXT3_BLOCK_SIZE_BITS(sb);
|
|
|
|
int err = 0;
|
|
|
|
int offset = off & (sb->s_blocksize - 1);
|
|
|
|
int tocopy;
|
|
|
|
int journal_quota = EXT3_SB(sb)->s_qf_names[type] != NULL;
|
|
|
|
size_t towrite = len;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
handle_t *handle = journal_current_handle();
|
|
|
|
|
2006-07-03 09:25:20 +02:00
|
|
|
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
|
2005-04-17 00:20:36 +02:00
|
|
|
while (towrite > 0) {
|
|
|
|
tocopy = sb->s_blocksize - offset < towrite ?
|
|
|
|
sb->s_blocksize - offset : towrite;
|
|
|
|
bh = ext3_bread(handle, inode, blk, 1, &err);
|
|
|
|
if (!bh)
|
|
|
|
goto out;
|
|
|
|
if (journal_quota) {
|
|
|
|
err = ext3_journal_get_write_access(handle, bh);
|
|
|
|
if (err) {
|
|
|
|
brelse(bh);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
lock_buffer(bh);
|
|
|
|
memcpy(bh->b_data+offset, data, tocopy);
|
|
|
|
flush_dcache_page(bh->b_page);
|
|
|
|
unlock_buffer(bh);
|
|
|
|
if (journal_quota)
|
|
|
|
err = ext3_journal_dirty_metadata(handle, bh);
|
|
|
|
else {
|
|
|
|
/* Always do at least ordered writes for quotas */
|
|
|
|
err = ext3_journal_dirty_data(handle, bh);
|
|
|
|
mark_buffer_dirty(bh);
|
|
|
|
}
|
|
|
|
brelse(bh);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
offset = 0;
|
|
|
|
towrite -= tocopy;
|
|
|
|
data += tocopy;
|
|
|
|
blk++;
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
if (len == towrite)
|
|
|
|
return err;
|
|
|
|
if (inode->i_size < off+len-towrite) {
|
|
|
|
i_size_write(inode, off+len-towrite);
|
|
|
|
EXT3_I(inode)->i_disksize = inode->i_size;
|
|
|
|
}
|
|
|
|
inode->i_version++;
|
|
|
|
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
|
|
|
|
ext3_mark_inode_dirty(handle, inode);
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_unlock(&inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
return len - towrite;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:02:57 +02:00
|
|
|
static int ext3_get_sb(struct file_system_type *fs_type,
|
|
|
|
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:02:57 +02:00
|
|
|
return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super, mnt);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct file_system_type ext3_fs_type = {
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.name = "ext3",
|
|
|
|
.get_sb = ext3_get_sb,
|
|
|
|
.kill_sb = kill_block_super,
|
|
|
|
.fs_flags = FS_REQUIRES_DEV,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init init_ext3_fs(void)
|
|
|
|
{
|
|
|
|
int err = init_ext3_xattr();
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
err = init_inodecache();
|
|
|
|
if (err)
|
|
|
|
goto out1;
|
|
|
|
err = register_filesystem(&ext3_fs_type);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
return 0;
|
|
|
|
out:
|
|
|
|
destroy_inodecache();
|
|
|
|
out1:
|
2006-09-27 10:49:35 +02:00
|
|
|
exit_ext3_xattr();
|
2005-04-17 00:20:36 +02:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit exit_ext3_fs(void)
|
|
|
|
{
|
|
|
|
unregister_filesystem(&ext3_fs_type);
|
|
|
|
destroy_inodecache();
|
|
|
|
exit_ext3_xattr();
|
|
|
|
}
|
|
|
|
|
|
|
|
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
|
|
|
|
MODULE_DESCRIPTION("Second Extended Filesystem with journaling extensions");
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
module_init(init_ext3_fs)
|
|
|
|
module_exit(exit_ext3_fs)
|