#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/seq_file.h>
#include <linux/log2.h>
#include <linux/crc16.h>
-
#include <asm/uaccess.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "namei.h"
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
if (is_journal_aborted(journal)) {
- ext4_abort(sb, __FUNCTION__,
+ ext4_abort(sb, __func__,
"Detected aborted journal");
return ERR_PTR(-EROFS);
}
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
- ext4_warning(sb, __FUNCTION__,
+ ext4_warning(sb, __func__,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
+ 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);
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
+ jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
+ ei->i_reserved_data_blocks = 0;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_allocated_meta_blocks = 0;
+ ei->i_delalloc_reserved_flag = 0;
+ spin_lock_init(&(ei->i_block_reservation_lock));
return &ei->vfs_inode;
}
EXT4_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
+ jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+ &EXT4_I(inode)->jinode);
}
static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb)
seq_printf(seq, ",commit=%u",
(unsigned) (sbi->s_commit_interval / HZ));
}
- if (test_opt(sb, BARRIER))
- seq_puts(seq, ",barrier=1");
+ /*
+ * We're changing the default of barrier mount option, so
+ * let's always display its mount state so it's clear what its
+ * status is.
+ */
+ seq_puts(seq, ",barrier=");
+ seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
+ if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
+ seq_puts(seq, ",journal_async_commit");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
if (!test_opt(sb, EXTENTS))
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
- Opt_mballoc, Opt_nomballoc, Opt_stripe,
+ Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc,
};
static match_table_t tokens = {
{Opt_mballoc, "mballoc"},
{Opt_nomballoc, "nomballoc"},
{Opt_stripe, "stripe=%u"},
- {Opt_err, NULL},
{Opt_resize, "resize"},
+ {Opt_delalloc, "delalloc"},
+ {Opt_err, NULL},
};
static ext4_fsblk_t get_sb_block(void **data)
int data_opt = 0;
int option;
#ifdef CONFIG_QUOTA
- int qtype;
+ int qtype, qfmt;
char *qname;
#endif
case Opt_grpjquota:
qtype = GRPQUOTA;
set_qf_name:
- if (sb_any_quota_enabled(sb)) {
+ if ((sb_any_quota_enabled(sb) ||
+ sb_any_quota_suspended(sb)) &&
+ !sbi->s_qf_names[qtype]) {
printk(KERN_ERR
- "EXT4-fs: Cannot change journalled "
+ "EXT4-fs: Cannot change journaled "
"quota options when quota turned on.\n");
return 0;
}
case Opt_offgrpjquota:
qtype = GRPQUOTA;
clear_qf_name:
- if (sb_any_quota_enabled(sb)) {
+ if ((sb_any_quota_enabled(sb) ||
+ sb_any_quota_suspended(sb)) &&
+ sbi->s_qf_names[qtype]) {
printk(KERN_ERR "EXT4-fs: Cannot change "
- "journalled quota options when "
+ "journaled quota options when "
"quota turned on.\n");
return 0;
}
sbi->s_qf_names[qtype] = NULL;
break;
case Opt_jqfmt_vfsold:
- sbi->s_jquota_fmt = QFMT_VFS_OLD;
- break;
+ qfmt = QFMT_VFS_OLD;
+ goto set_qf_format;
case Opt_jqfmt_vfsv0:
- sbi->s_jquota_fmt = QFMT_VFS_V0;
+ qfmt = QFMT_VFS_V0;
+set_qf_format:
+ if ((sb_any_quota_enabled(sb) ||
+ sb_any_quota_suspended(sb)) &&
+ sbi->s_jquota_fmt != qfmt) {
+ printk(KERN_ERR "EXT4-fs: Cannot change "
+ "journaled quota options when "
+ "quota turned on.\n");
+ return 0;
+ }
+ sbi->s_jquota_fmt = qfmt;
break;
case Opt_quota:
case Opt_usrquota:
case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
+ printk(KERN_ERR
+ "EXT4-fs: quota options not supported.\n");
+ break;
case Opt_usrjquota:
case Opt_grpjquota:
case Opt_offusrjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
printk(KERN_ERR
- "EXT4-fs: journalled quota options not "
+ "EXT4-fs: journaled quota options not "
"supported.\n");
break;
case Opt_noquota:
return 0;
sbi->s_stripe = option;
break;
+ case Opt_delalloc:
+ set_opt(sbi->s_mount_opt, DELALLOC);
+ break;
default:
printk (KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
}
if (!sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT4-fs: journalled quota format "
+ printk(KERN_ERR "EXT4-fs: journaled quota format "
"not specified.\n");
return 0;
}
} else {
if (sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT4-fs: journalled quota format "
- "specified with no journalling "
+ printk(KERN_ERR "EXT4-fs: journaled quota format "
+ "specified with no journaling "
"enabled.\n");
return 0;
}
* a plain journaled filesystem we can keep it set as
* valid forever! :)
*/
- es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT4_VALID_FS);
+ es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
#endif
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
- es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
+ le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
return res;
}
+static int ext4_fill_flex_info(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp = NULL;
+ struct buffer_head *bh;
+ ext4_group_t flex_group_count;
+ ext4_group_t flex_group;
+ int groups_per_flex = 0;
+ __u64 block_bitmap = 0;
+ int i;
+
+ if (!sbi->s_es->s_log_groups_per_flex) {
+ sbi->s_log_groups_per_flex = 0;
+ return 1;
+ }
+
+ sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+ groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+ flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
+ groups_per_flex;
+ sbi->s_flex_groups = kmalloc(flex_group_count *
+ sizeof(struct flex_groups), GFP_KERNEL);
+ if (sbi->s_flex_groups == NULL) {
+ printk(KERN_ERR "EXT4-fs: not enough memory\n");
+ goto failed;
+ }
+ memset(sbi->s_flex_groups, 0, flex_group_count *
+ sizeof(struct flex_groups));
+
+ gdp = ext4_get_group_desc(sb, 1, &bh);
+ block_bitmap = ext4_block_bitmap(sb, gdp) - 1;
+
+ for (i = 0; i < sbi->s_groups_count; i++) {
+ gdp = ext4_get_group_desc(sb, i, &bh);
+
+ flex_group = ext4_flex_group(sbi, i);
+ sbi->s_flex_groups[flex_group].free_inodes +=
+ le16_to_cpu(gdp->bg_free_inodes_count);
+ sbi->s_flex_groups[flex_group].free_blocks +=
+ le16_to_cpu(gdp->bg_free_blocks_count);
+ }
+
+ return 1;
+failed:
+ return 0;
+}
+
__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
struct ext4_group_desc *gdp)
{
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block)
{
- ext4_error (sb, "ext4_check_descriptors",
- "Block bitmap for group %lu"
- " not in group (block %llu)!",
- i, block_bitmap);
+ printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ "Block bitmap for group %lu not in group "
+ "(block %llu)!", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap < first_block || inode_bitmap > last_block)
{
- ext4_error (sb, "ext4_check_descriptors",
- "Inode bitmap for group %lu"
- " not in group (block %llu)!",
- i, inode_bitmap);
+ printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ "Inode bitmap for group %lu not in group "
+ "(block %llu)!", i, inode_bitmap);
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block)
{
- ext4_error (sb, "ext4_check_descriptors",
- "Inode table for group %lu"
- " not in group (block %llu)!",
- i, inode_table);
+ printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ "Inode table for group %lu not in group "
+ "(block %llu)!", i, inode_table);
return 0;
}
if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
- ext4_error(sb, __FUNCTION__,
- "Checksum for group %lu failed (%u!=%u)\n",
- i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
- gdp)), le16_to_cpu(gdp->bg_checksum));
+ printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ "Checksum for group %lu failed (%u!=%u)\n",
+ i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
+ gdp)), le16_to_cpu(gdp->bg_checksum));
return 0;
}
if (!flexbg_flag)
int ret = ext4_quota_on_mount(sb, i);
if (ret < 0)
printk(KERN_ERR
- "EXT4-fs: Cannot turn on journalled "
+ "EXT4-fs: Cannot turn on journaled "
"quota: error %d\n", ret);
}
}
while (es->s_last_orphan) {
struct inode *inode;
- if (!(inode =
- ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
+ inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
+ if (IS_ERR(inode)) {
es->s_last_orphan = 0;
break;
}
if (inode->i_nlink) {
printk(KERN_DEBUG
"%s: truncating inode %lu to %Ld bytes\n",
- __FUNCTION__, inode->i_ino, inode->i_size);
+ __func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
inode->i_ino, inode->i_size);
ext4_truncate(inode);
} else {
printk(KERN_DEBUG
"%s: deleting unreferenced inode %lu\n",
- __FUNCTION__, inode->i_ino);
+ __func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
}
static int ext4_fill_super (struct super_block *sb, void *data, int silent)
- __releases(kernel_sem)
- __acquires(kernel_sem)
+ __releases(kernel_lock)
+ __acquires(kernel_lock)
{
struct buffer_head * bh;
goto out_fail;
}
- if (!sb_set_blocksize(sb, blocksize)) {
- printk(KERN_ERR "EXT4-fs: bad blocksize %d.\n", blocksize);
- goto out_fail;
- }
-
/*
* The ext4 superblock will not be buffer aligned for other than 1kB
* block sizes. We need to calculate the offset from buffer start.
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
set_opt(sbi->s_mount_opt, RESERVATION);
+ set_opt(sbi->s_mount_opt, BARRIER);
/*
* turn on extents feature by default in ext4 filesystem
printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
goto failed_mount2;
}
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ if (!ext4_fill_flex_info(sb)) {
+ printk(KERN_ERR
+ "EXT4-fs: unable to initialize "
+ "flex_bg meta info!\n");
+ 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);
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3;
+ if (!(sb->s_flags & MS_RDONLY) &&
+ EXT4_SB(sb)->s_journal->j_failed_commit) {
+ printk(KERN_CRIT "EXT4-fs error (device %s): "
+ "ext4_fill_super: Journal transaction "
+ "%u is corrupt\n", sb->s_id,
+ EXT4_SB(sb)->s_journal->j_failed_commit);
+ if (test_opt (sb, ERRORS_RO)) {
+ printk (KERN_CRIT
+ "Mounting filesystem read-only\n");
+ sb->s_flags |= MS_RDONLY;
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ }
+ if (test_opt(sb, ERRORS_PANIC)) {
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ ext4_commit_super(sb, es, 1);
+ printk(KERN_CRIT
+ "EXT4-fs (device %s): mount failed\n",
+ sb->s_id);
+ goto failed_mount4;
+ }
+ }
} else if (journal_inum) {
if (ext4_create_journal(sb, es, journal_inum))
goto failed_mount3;
failed_mount4:
jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
char nbuf[16];
errstr = ext4_decode_error(sb, j_errno, nbuf);
- ext4_warning(sb, __FUNCTION__, "Filesystem error recorded "
+ ext4_warning(sb, __func__, "Filesystem error recorded "
"from previous mount: %s", errstr);
- ext4_warning(sb, __FUNCTION__, "Marking fs in need of "
+ ext4_warning(sb, __func__, "Marking fs in need of "
"filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
}
if (sbi->s_mount_opt & EXT4_MOUNT_ABORT)
- ext4_abort(sb, __FUNCTION__, "Abort forced by user");
+ ext4_abort(sb, __func__, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
/* We may delete quota structure so we need to reserve enough blocks */
handle = ext4_journal_start(inode, 2*EXT4_QUOTA_DEL_BLOCKS(inode->i_sb));
- if (IS_ERR(handle))
+ if (IS_ERR(handle)) {
+ /*
+ * We call dquot_drop() anyway to at least release references
+ * to quota structures so that umount does not hang.
+ */
+ dquot_drop(inode);
return PTR_ERR(handle);
+ }
ret = dquot_drop(inode);
err = ext4_journal_stop(handle);
if (!ret)
static int ext4_mark_dquot_dirty(struct dquot *dquot)
{
- /* Are we journalling quotas? */
+ /* Are we journaling quotas? */
if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
if (!test_opt(sb, QUOTA))
return -EINVAL;
- /* Not journalling quota? */
- if ((!EXT4_SB(sb)->s_qf_names[USRQUOTA] &&
- !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+ /* When remounting, no checks are needed and in fact, path is NULL */
+ if (remount)
return vfs_quota_on(sb, type, format_id, path, remount);
+
err = path_lookup(path, LOOKUP_FOLLOW, &nd);
if (err)
return err;
+
/* Quotafile not on the same filesystem? */
if (nd.path.mnt->mnt_sb != sb) {
path_put(&nd.path);
return -EXDEV;
}
- /* Quotafile not of fs root? */
- if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
- printk(KERN_WARNING
- "EXT4-fs: Quota file not on filesystem root. "
- "Journalled quota will not work.\n");
+ /* Journaling quota? */
+ if (EXT4_SB(sb)->s_qf_names[type]) {
+ /* Quotafile not of fs root? */
+ if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+ printk(KERN_WARNING
+ "EXT4-fs: Quota file not on filesystem root. "
+ "Journaled quota will not work.\n");
+ }
+
+ /*
+ * When we journal data on quota file, we have to flush journal to see
+ * all updates to the file when we bypass pagecache...
+ */
+ if (ext4_should_journal_data(nd.path.dentry->d_inode)) {
+ /*
+ * We don't need to lock updates but journal_flush() could
+ * otherwise be livelocked...
+ */
+ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+ jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ }
+
path_put(&nd.path);
return vfs_quota_on(sb, type, format_id, path, remount);
}
err = ext4_journal_dirty_metadata(handle, bh);
else {
/* Always do at least ordered writes for quotas */
- err = ext4_journal_dirty_data(handle, bh);
+ err = ext4_jbd2_file_inode(handle, inode);
mark_buffer_dirty(bh);
}
brelse(bh);
blk++;
}
out:
- if (len == towrite)
+ if (len == towrite) {
+ mutex_unlock(&inode->i_mutex);
return err;
+ }
if (inode->i_size < off+len-towrite) {
i_size_write(inode, off+len-towrite);
EXT4_I(inode)->i_disksize = inode->i_size;