static int ext4_unfreeze(struct super_block *sb);
static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
+static int ext4_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data, struct vfsmount *mnt);
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext3_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext3",
+ .get_sb = ext4_get_sb,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
+#else
+#define IS_EXT3_SB(sb) (0)
+#endif
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
/* 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. */
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
- * the journal instead. On recovery, the journal will compain about
+ * the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
ext4_handle_error(sb);
}
+void ext4_error_inode(const char *function, struct inode *inode,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: inode #%lu: (comm %s) ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
+void ext4_error_file(const char *function, struct file *file,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct inode *inode = file->f_dentry->d_inode;
+ char pathname[80], *path;
+
+ va_start(args, fmt);
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (!path)
+ path = "(unknown)";
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s: inode #%lu (comm %s path %s): ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm, path);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
static const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
struct ext4_super_block *es = sbi->s_es;
int i, err;
+ dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+
flush_workqueue(sbi->dio_unwritten_wq);
destroy_workqueue(sbi->dio_unwritten_wq);
ei->i_reserved_quota = 0;
#endif
INIT_LIST_HEAD(&ei->i_completed_io_list);
+ spin_lock_init(&ei->i_completed_io_lock);
ei->cur_aio_dio = NULL;
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
static void ext4_clear_inode(struct inode *inode)
{
+ dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_JOURNAL(inode))
jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
seq_puts(seq, ",journal_async_commit");
+ else if (test_opt(sb, JOURNAL_CHECKSUM))
+ seq_puts(seq, ",journal_checksum");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
if (test_opt(sb, I_VERSION))
if (test_opt(sb, NOLOAD))
seq_puts(seq, ",norecovery");
+ if (test_opt(sb, DIOREAD_NOLOCK))
+ seq_puts(seq, ",dioread_nolock");
+
ext4_show_quota_options(seq, sb);
return 0;
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *path, int remount);
+ char *path);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
const char *data, size_t len, loff_t off);
static const struct dquot_operations ext4_quota_operations = {
- .initialize = dquot_initialize,
- .drop = dquot_drop,
- .alloc_space = dquot_alloc_space,
- .reserve_space = dquot_reserve_space,
- .claim_space = dquot_claim_space,
- .release_rsv = dquot_release_reserved_space,
#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
#endif
- .alloc_inode = dquot_alloc_inode,
- .free_space = dquot_free_space,
- .free_inode = dquot_free_inode,
- .transfer = dquot_transfer,
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
static const struct quotactl_ops ext4_qctl_operations = {
.quota_on = ext4_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
+ .quota_off = dquot_quota_off,
+ .quota_sync = dquot_quota_sync,
+ .get_info = dquot_get_dqinfo,
+ .set_info = dquot_set_dqinfo,
+ .get_dqblk = dquot_get_dqblk,
+ .set_dqblk = dquot_set_dqblk
};
#endif
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
+ Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard,
};
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
+ {Opt_dioread_nolock, "dioread_nolock"},
+ {Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_err, NULL},
case Opt_nodiscard:
clear_opt(sbi->s_mount_opt, DISCARD);
break;
+ case Opt_dioread_nolock:
+ set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
+ case Opt_dioread_lock:
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
}
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
- vfs_dq_init(inode);
+ dquot_initialize(inode);
if (inode->i_nlink) {
ext4_msg(sb, KERN_DEBUG,
"%s: truncating inode %lu to %lld bytes",
/* Turn quotas off */
for (i = 0; i < MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
- vfs_quota_off(sb, i, 0);
+ dquot_quota_off(sb, i);
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
struct ext4_attr {
struct attribute attr;
ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
- ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
+ ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
const char *, size_t);
int offset;
};
}
-static struct sysfs_ops ext4_attr_ops = {
+static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
};
__releases(kernel_lock)
__acquires(kernel_lock)
{
+ char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
struct ext4_sb_info *sbi;
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
- set_opt(sbi->s_mount_opt, DELALLOC);
+ if (!IS_EXT3_SB(sb))
+ set_opt(sbi->s_mount_opt, DELALLOC);
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, NULL, 0))
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
- if (!err) {
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
- }
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
- goto failed_mount3;
- }
-
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
- goto failed_mount4;
+ goto failed_mount_wq;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
- goto failed_mount4;
+ goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
- goto failed_mount4;
+ goto failed_mount_wq;
}
default:
break;
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
no_journal:
-
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount_wq;
+ }
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
"its supported only with writeback mode");
clear_opt(sbi->s_mount_opt, NOBH);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
+ "not supported with nobh mode");
+ goto failed_mount_wq;
+ }
}
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
"requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - requested data journaling mode");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ if (sb->s_blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - block size is too small");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ }
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
- "zone (%d)\n", err);
+ "zone (%d)", err);
goto failed_mount4;
}
} else
descr = "out journal";
- ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr);
+ ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
+ "Opts: %s", descr, orig_data);
lock_kernel();
+ kfree(orig_data);
return 0;
cantfind_ext4:
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
else
kfree(sbi->s_flex_groups);
}
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
+ kfree(orig_data);
return ret;
}
if (!(sb->s_flags & MS_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal)
+ if (journal) {
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
ret = ext4_journal_force_commit(journal);
+ }
return ret;
}
* the journal.
*/
error = jbd2_journal_flush(journal);
- if (error < 0) {
- out:
- jbd2_journal_unlock_updates(journal);
- return error;
- }
+ if (error < 0)
+ goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
- if (error)
- goto out;
- return 0;
+out:
+ /* we rely on s_frozen to stop further updates */
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ return error;
}
/*
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
unlock_super(sb);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return 0;
}
ext4_fsblk_t n_blocks_count = 0;
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
+ int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
#endif
+ char *orig_data = kstrdup(data, GFP_KERNEL);
lock_kernel();
}
if (*flags & MS_RDONLY) {
+ err = dquot_suspend(sb, -1);
+ if (err < 0)
+ goto restore_opts;
+
/*
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
+ enable_quota = 1;
}
}
ext4_setup_system_zone(sb);
#endif
unlock_super(sb);
unlock_kernel();
+ if (enable_quota)
+ dquot_resume(sb, -1);
+
+ ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+ kfree(orig_data);
return 0;
restore_opts:
#endif
unlock_super(sb);
unlock_kernel();
+ kfree(orig_data);
return err;
}
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
- * vfs_dq_init() down(dqio_mutex)
+ * dquot_initialize() down(dqio_mutex)
* down(dqio_mutex) jbd2_journal_start()
*
*/
*/
static int ext4_quota_on_mount(struct super_block *sb, int type)
{
- return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
- EXT4_SB(sb)->s_jquota_fmt, type);
+ return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
+ EXT4_SB(sb)->s_jquota_fmt, type);
}
/*
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *name, int remount)
+ char *name)
{
int err;
struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
- /* When remounting, no checks are needed and in fact, name is NULL */
- if (remount)
- return vfs_quota_on(sb, type, format_id, name, remount);
err = kern_path(name, LOOKUP_FOLLOW, &path);
if (err)
}
}
- err = vfs_quota_on_path(sb, type, format_id, &path);
+ err = dquot_quota_on_path(sb, type, format_id, &path);
path_put(&path);
return err;
}
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
- int tocopy;
int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL;
- size_t towrite = len;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
+ /*
+ * Since we account only one data block in transaction credits,
+ * then it is impossible to cross a block boundary.
+ */
+ if (sb->s_blocksize - offset < len) {
+ ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+ " cancelled because not block aligned",
+ (unsigned long long)off, (unsigned long long)len);
+ return -EIO;
+ }
+
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
- while (towrite > 0) {
- tocopy = sb->s_blocksize - offset < towrite ?
- sb->s_blocksize - offset : towrite;
- bh = ext4_bread(handle, inode, blk, 1, &err);
- if (!bh)
+ bh = ext4_bread(handle, inode, blk, 1, &err);
+ if (!bh)
+ goto out;
+ if (journal_quota) {
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
goto out;
- if (journal_quota) {
- err = ext4_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 = ext4_handle_dirty_metadata(handle, NULL, bh);
- else {
- /* Always do at least ordered writes for quotas */
- err = ext4_jbd2_file_inode(handle, inode);
- mark_buffer_dirty(bh);
- }
- brelse(bh);
- if (err)
- goto out;
- offset = 0;
- towrite -= tocopy;
- data += tocopy;
- blk++;
}
+ lock_buffer(bh);
+ memcpy(bh->b_data+offset, data, len);
+ flush_dcache_page(bh->b_page);
+ unlock_buffer(bh);
+ if (journal_quota)
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ else {
+ /* Always do at least ordered writes for quotas */
+ err = ext4_jbd2_file_inode(handle, inode);
+ mark_buffer_dirty(bh);
+ }
+ brelse(bh);
out:
- if (len == towrite) {
+ if (err) {
mutex_unlock(&inode->i_mutex);
return err;
}
- if (inode->i_size < off+len-towrite) {
- i_size_write(inode, off+len-towrite);
+ if (inode->i_size < off + len) {
+ i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
}
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
- return len - towrite;
+ return len;
}
#endif
return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
-#if !defined(CONTIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = "ext2",
static inline void unregister_as_ext2(void) { }
#endif
-#if !defined(CONTIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
-static struct file_system_type ext3_fs_type = {
- .owner = THIS_MODULE,
- .name = "ext3",
- .get_sb = ext4_get_sb,
- .kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
-};
-
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static inline void register_as_ext3(void)
{
int err = register_filesystem(&ext3_fs_type);
{
int err;
+ ext4_check_flag_values();
err = init_ext4_system_zone();
if (err)
return err;